diff options
1292 files changed, 20470 insertions, 7400 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb index 3a4abfc44f5e..136ba17d2da0 100644 --- a/Documentation/ABI/testing/sysfs-bus-usb +++ b/Documentation/ABI/testing/sysfs-bus-usb @@ -134,19 +134,21 @@ Description: enabled for the device. Developer can write y/Y/1 or n/N/0 to the file to enable/disable the feature. -What: /sys/bus/usb/devices/.../power/usb3_hardware_lpm -Date: June 2015 +What: /sys/bus/usb/devices/.../power/usb3_hardware_lpm_u1 + /sys/bus/usb/devices/.../power/usb3_hardware_lpm_u2 +Date: November 2015 Contact: Kevin Strasser <kevin.strasser@linux.intel.com> + Lu Baolu <baolu.lu@linux.intel.com> Description: If CONFIG_PM is set and a USB 3.0 lpm-capable device is plugged in to a xHCI host which supports link PM, it will check if U1 and U2 exit latencies have been set in the BOS descriptor; if - the check is is passed and the host supports USB3 hardware LPM, + the check is passed and the host supports USB3 hardware LPM, USB3 hardware LPM will be enabled for the device and the USB - device directory will contain a file named - power/usb3_hardware_lpm. The file holds a string value (enable - or disable) indicating whether or not USB3 hardware LPM is - enabled for the device. + device directory will contain two files named + power/usb3_hardware_lpm_u1 and power/usb3_hardware_lpm_u2. These + files hold a string value (enable or disable) indicating whether + or not USB3 hardware LPM U1 or U2 is enabled for the device. What: /sys/bus/usb/devices/.../removable Date: February 2012 diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX index e840b47613f7..bc5148757edb 100644 --- a/Documentation/block/00-INDEX +++ b/Documentation/block/00-INDEX @@ -26,3 +26,9 @@ switching-sched.txt - Switching I/O schedulers at runtime writeback_cache_control.txt - Control of volatile write back caches +mmc-max-speed.txt + - eMMC layer speed simulation, related to /sys/block/mmcblk*/ + attributes: + max_read_speed + max_write_speed + cache_size diff --git a/Documentation/block/mmc-max-speed.txt b/Documentation/block/mmc-max-speed.txt new file mode 100644 index 000000000000..3f052b9fb999 --- /dev/null +++ b/Documentation/block/mmc-max-speed.txt @@ -0,0 +1,38 @@ +eMMC Block layer simulation speed controls in /sys/block/mmcblk*/ +=============================================== + +Turned on with CONFIG_MMC_SIMULATE_MAX_SPEED which enables MMC device speed +limiting. Used to test and simulate the behavior of the system when +confronted with a slow MMC. + +Enables max_read_speed, max_write_speed and cache_size attributes and module +default parameters to control the write or read maximum KB/second speed +behaviors. + +NB: There is room for improving the algorithm for aspects tied directly to +eMMC specific behavior. For instance, wear leveling and stalls from an +exhausted erase pool. We would expect that if there was a need to provide +similar speed simulation controls to other types of block devices, aspects of +their behavior are modelled separately (e.g. head seek times, heat assist, +shingling and rotational latency). + +/sys/block/mmcblk0/max_read_speed: + +Number of KB/second reads allowed to the block device. Used to test and +simulate the behavior of the system when confronted with a slow reading MMC. +Set to 0 or "off" to place no speed limit. + +/sys/block/mmcblk0/max_write_speed: + +Number of KB/second writes allowed to the block device. Used to test and +simulate the behavior of the system when confronted with a slow writing MMC. +Set to 0 or "off" to place no speed limit. + +/sys/block/mmcblk0/cache_size: + +Number of MB of high speed memory or high speed SLC cache expected on the +eMMC device being simulated. Used to help simulate the write-back behavior +more accurately. The assumption is the cache has no delay, but draws down +in the background to the MLC/TLC primary store at the max_write_speed rate. +Any write speed delays will show up when the cache is full, or when an I/O +request to flush is issued. diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt index e15bc1a0fb98..89fd8f9a259f 100644 --- a/Documentation/device-mapper/verity.txt +++ b/Documentation/device-mapper/verity.txt @@ -18,11 +18,11 @@ Construction Parameters 0 is the original format used in the Chromium OS. The salt is appended when hashing, digests are stored continuously and - the rest of the block is padded with zeros. + the rest of the block is padded with zeroes. 1 is the current format that should be used for new devices. The salt is prepended when hashing and each digest is - padded with zeros to the power of two. + padded with zeroes to the power of two. <dev> This is the device containing data, the integrity of which needs to be @@ -79,6 +79,37 @@ restart_on_corruption not compatible with ignore_corruption and requires user space support to avoid restart loops. +ignore_zero_blocks + Do not verify blocks that are expected to contain zeroes and always return + zeroes instead. This may be useful if the partition contains unused blocks + that are not guaranteed to contain zeroes. + +use_fec_from_device <fec_dev> + Use forward error correction (FEC) to recover from corruption if hash + verification fails. Use encoding data from the specified device. This + may be the same device where data and hash blocks reside, in which case + fec_start must be outside data and hash areas. + + If the encoding data covers additional metadata, it must be accessible + on the hash device after the hash blocks. + + Note: block sizes for data and hash devices must match. Also, if the + verity <dev> is encrypted the <fec_dev> should be too. + +fec_roots <num> + Number of generator roots. This equals to the number of parity bytes in + the encoding data. For example, in RS(M, N) encoding, the number of roots + is M-N. + +fec_blocks <num> + The number of encoding data blocks on the FEC device. The block size for + the FEC device is <data_block_size>. + +fec_start <offset> + This is the offset, in <data_block_size> blocks, from the start of the + FEC device to the beginning of the encoding data. + + Theory of operation =================== @@ -98,6 +129,11 @@ per-block basis. This allows for a lightweight hash computation on first read into the page cache. Block hashes are stored linearly, aligned to the nearest block size. +If forward error correction (FEC) support is enabled any recovery of +corrupted data will be verified using the cryptographic hash of the +corresponding data. This is why combining error correction with +integrity checking is essential. + Hash Tree --------- diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt index 9f4e5136e568..12af302bca6a 100644 --- a/Documentation/devicetree/bindings/arm/omap/omap.txt +++ b/Documentation/devicetree/bindings/arm/omap/omap.txt @@ -23,6 +23,7 @@ Optional properties: during suspend. - ti,no-reset-on-init: When present, the module should not be reset at init - ti,no-idle-on-init: When present, the module should not be idled at init +- ti,no-idle: When present, the module is never allowed to idle. Example: diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt index c2340eeeb97f..c000832a7fb9 100644 --- a/Documentation/devicetree/bindings/ata/ahci-platform.txt +++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt @@ -30,6 +30,10 @@ Optional properties: - target-supply : regulator for SATA target power - phys : reference to the SATA PHY node - phy-names : must be "sata-phy" +- ports-implemented : Mask that indicates which ports that the HBA supports + are available for software to use. Useful if PORTS_IMPL + is not programmed by the BIOS, which is true with + some embedded SOC's. Required properties when using sub-nodes: - #address-cells : number of cells to encode an address diff --git a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt index 08a4a32c8eb0..0326154c7925 100644 --- a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt @@ -134,12 +134,12 @@ mfio80 ddr_debug, mips_trace_data, mips_debug mfio81 dreq0, mips_trace_data, eth_debug mfio82 dreq1, mips_trace_data, eth_debug mfio83 mips_pll_lock, mips_trace_data, usb_debug -mfio84 sys_pll_lock, mips_trace_data, usb_debug -mfio85 wifi_pll_lock, mips_trace_data, sdhost_debug -mfio86 bt_pll_lock, mips_trace_data, sdhost_debug -mfio87 rpu_v_pll_lock, dreq2, socif_debug -mfio88 rpu_l_pll_lock, dreq3, socif_debug -mfio89 audio_pll_lock, dreq4, dreq5 +mfio84 audio_pll_lock, mips_trace_data, usb_debug +mfio85 rpu_v_pll_lock, mips_trace_data, sdhost_debug +mfio86 rpu_l_pll_lock, mips_trace_data, sdhost_debug +mfio87 sys_pll_lock, dreq2, socif_debug +mfio88 wifi_pll_lock, dreq3, socif_debug +mfio89 bt_pll_lock, dreq4, dreq5 tck trstn tdi diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt index c477af086e65..686a64bba775 100644 --- a/Documentation/filesystems/efivarfs.txt +++ b/Documentation/filesystems/efivarfs.txt @@ -14,3 +14,10 @@ filesystem. efivarfs is typically mounted like this, mount -t efivarfs none /sys/firmware/efi/efivars + +Due to the presence of numerous firmware bugs where removing non-standard +UEFI variables causes the system firmware to fail to POST, efivarfs +files that are not well-known standardized variables are created +as immutable files. This doesn't prevent removal - "chattr -i" will work - +but it does prevent this kind of failure from being accomplished +accidentally. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 742f69d18fc8..0e4102ae1a61 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3928,6 +3928,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. sector if the number is odd); i = IGNORE_DEVICE (don't bind to this device); + j = NO_REPORT_LUNS (don't use report luns + command, uas only); l = NOT_LOCKABLE (don't try to lock and unlock ejectable media); m = MAX_SECTORS_64 (don't transfer more diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt index 4a15c90bc11d..0a94ffe17ab6 100644 --- a/Documentation/usb/power-management.txt +++ b/Documentation/usb/power-management.txt @@ -537,17 +537,18 @@ relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm. can write y/Y/1 or n/N/0 to the file to enable/disable USB2 hardware LPM manually. This is for test purpose mainly. - power/usb3_hardware_lpm + power/usb3_hardware_lpm_u1 + power/usb3_hardware_lpm_u2 When a USB 3.0 lpm-capable device is plugged in to a xHCI host which supports link PM, it will check if U1 and U2 exit latencies have been set in the BOS descriptor; if the check is is passed and the host supports USB3 hardware LPM, USB3 hardware LPM will be - enabled for the device and this file will be created. - The file holds a string value (enable or disable) - indicating whether or not USB3 hardware LPM is - enabled for the device. + enabled for the device and these files will be created. + The files hold a string value (enable or disable) + indicating whether or not USB3 hardware LPM U1 or U2 + is enabled for the device. USB Port Power Control ---------------------- diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index 3a4d681c3e98..b653641d4261 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -358,7 +358,8 @@ In the first case there are two additional complications: - if CR4.SMEP is enabled: since we've turned the page into a kernel page, the kernel may now execute it. We handle this by also setting spte.nx. If we get a user fetch or read fault, we'll change spte.u=1 and - spte.nx=gpte.nx back. + spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when + shadow paging is in use. - if CR4.SMAP is disabled: since the page has been changed to a kernel page, it can not be reused when CR4.SMAP is enabled. We set CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note, diff --git a/MAINTAINERS b/MAINTAINERS index 233f83464814..ab65bbecb159 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -230,13 +230,13 @@ F: kernel/sys_ni.c ABIT UGURU 1,2 HARDWARE MONITOR DRIVER M: Hans de Goede <hdegoede@redhat.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/abituguru.c ABIT UGURU 3 HARDWARE MONITOR DRIVER M: Alistair John Strachan <alistair@devzero.co.uk> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/abituguru3.c @@ -373,14 +373,14 @@ S: Maintained ADM1025 HARDWARE MONITOR DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/adm1025 F: drivers/hwmon/adm1025.c ADM1029 HARDWARE MONITOR DRIVER M: Corentin Labbe <clabbe.montjoie@gmail.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/adm1029.c @@ -425,7 +425,7 @@ F: drivers/video/backlight/adp8860_bl.c ADS1015 HARDWARE MONITOR DRIVER M: Dirk Eibach <eibach@gdsys.de> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ads1015 F: drivers/hwmon/ads1015.c @@ -438,7 +438,7 @@ F: drivers/macintosh/therm_adt746x.c ADT7475 HARDWARE MONITOR DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/adt7475 F: drivers/hwmon/adt7475.c @@ -615,7 +615,7 @@ F: include/linux/ccp.h AMD FAM15H PROCESSOR POWER MONITORING DRIVER M: Andreas Herrmann <herrmann.der.user@googlemail.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/fam15h_power F: drivers/hwmon/fam15h_power.c @@ -779,7 +779,7 @@ F: drivers/input/mouse/bcm5974.c APPLE SMC DRIVER M: Henrik Rydberg <rydberg@bitmath.org> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Odd fixes F: drivers/hwmon/applesmc.c @@ -1777,7 +1777,7 @@ F: include/media/as3645a.h ASC7621 HARDWARE MONITOR DRIVER M: George Joseph <george.joseph@fairview5.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/asc7621 F: drivers/hwmon/asc7621.c @@ -1864,7 +1864,7 @@ F: drivers/net/wireless/ath/carl9170/ ATK0110 HWMON DRIVER M: Luca Tettamanti <kronos.it@gmail.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/asus_atk0110.c @@ -2984,7 +2984,7 @@ F: mm/swap_cgroup.c CORETEMP HARDWARE MONITORING DRIVER M: Fenghua Yu <fenghua.yu@intel.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/coretemp F: drivers/hwmon/coretemp.c @@ -3549,7 +3549,7 @@ T: git git://git.infradead.org/users/vkoul/slave-dma.git DME1737 HARDWARE MONITOR DRIVER M: Juerg Haefliger <juergh@gmail.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/dme1737 F: drivers/hwmon/dme1737.c @@ -4097,8 +4097,8 @@ F: Documentation/efi-stub.txt F: arch/ia64/kernel/efi.c F: arch/x86/boot/compressed/eboot.[ch] F: arch/x86/include/asm/efi.h -F: arch/x86/platform/efi/* -F: drivers/firmware/efi/* +F: arch/x86/platform/efi/ +F: drivers/firmware/efi/ F: include/linux/efi*.h EFI VARIABLE FILESYSTEM @@ -4262,7 +4262,7 @@ F: include/video/exynos_mipi* F71805F HARDWARE MONITORING DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/f71805f F: drivers/hwmon/f71805f.c @@ -4341,7 +4341,7 @@ F: fs/* FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER M: Riku Voipio <riku.voipio@iki.fi> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/f75375s.c F: include/linux/f75375s.h @@ -4883,8 +4883,8 @@ F: drivers/media/usb/hackrf/ HARDWARE MONITORING M: Jean Delvare <jdelvare@suse.com> M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org -W: http://www.lm-sensors.org/ +L: linux-hwmon@vger.kernel.org +W: http://hwmon.wiki.kernel.org/ T: quilt http://jdelvare.nerim.net/devel/linux/jdelvare-hwmon/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git S: Maintained @@ -5393,7 +5393,7 @@ F: drivers/usb/atm/ueagle-atm.c INA209 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ina209 F: Documentation/devicetree/bindings/i2c/ina209.txt @@ -5401,7 +5401,7 @@ F: drivers/hwmon/ina209.c INA2XX HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ina2xx F: drivers/hwmon/ina2xx.c @@ -5884,7 +5884,7 @@ F: drivers/isdn/hardware/eicon/ IT87 HARDWARE MONITORING DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/it87 F: drivers/hwmon/it87.c @@ -5920,7 +5920,7 @@ F: drivers/media/dvb-frontends/ix2505v* JC42.4 TEMPERATURE SENSOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/jc42.c F: Documentation/hwmon/jc42 @@ -5970,14 +5970,14 @@ F: drivers/tty/serial/jsm/ K10TEMP HARDWARE MONITORING DRIVER M: Clemens Ladisch <clemens@ladisch.de> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/k10temp F: drivers/hwmon/k10temp.c K8TEMP HARDWARE MONITORING DRIVER M: Rudolf Marek <r.marek@assembler.cz> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/k8temp F: drivers/hwmon/k8temp.c @@ -6485,27 +6485,27 @@ F: net/llc/ LM73 HARDWARE MONITOR DRIVER M: Guillaume Ligneul <guillaume.ligneul@gmail.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/lm73.c LM78 HARDWARE MONITOR DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/lm78 F: drivers/hwmon/lm78.c LM83 HARDWARE MONITOR DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/lm83 F: drivers/hwmon/lm83.c LM90 HARDWARE MONITOR DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/lm90 F: Documentation/devicetree/bindings/hwmon/lm90.txt @@ -6513,7 +6513,7 @@ F: drivers/hwmon/lm90.c LM95234 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/lm95234 F: drivers/hwmon/lm95234.c @@ -6580,7 +6580,7 @@ F: drivers/scsi/sym53c8xx_2/ LTC4261 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ltc4261 F: drivers/hwmon/ltc4261.c @@ -6749,28 +6749,28 @@ F: include/uapi/linux/matroxfb.h MAX16065 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/max16065 F: drivers/hwmon/max16065.c MAX20751 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/max20751 F: drivers/hwmon/max20751.c MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER M: "Hans J. Koch" <hjk@hansjkoch.de> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/max6650 F: drivers/hwmon/max6650.c MAX6697 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/max6697 F: Documentation/devicetree/bindings/i2c/max6697.txt @@ -7303,7 +7303,7 @@ F: drivers/scsi/NCR_D700.* NCT6775 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/nct6775 F: drivers/hwmon/nct6775.c @@ -8064,7 +8064,7 @@ F: drivers/video/logo/logo_parisc* PC87360 HARDWARE MONITORING DRIVER M: Jim Cromie <jim.cromie@gmail.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/pc87360 F: drivers/hwmon/pc87360.c @@ -8076,7 +8076,7 @@ F: drivers/char/pc8736x_gpio.c PC87427 HARDWARE MONITORING DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/pc87427 F: drivers/hwmon/pc87427.c @@ -8415,8 +8415,8 @@ F: drivers/rtc/rtc-puv3.c PMBUS HARDWARE MONITORING DRIVERS M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org -W: http://www.lm-sensors.org/ +L: linux-hwmon@vger.kernel.org +W: http://hwmon.wiki.kernel.org/ W: http://www.roeck-us.net/linux/drivers/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git S: Maintained @@ -8610,7 +8610,7 @@ F: drivers/media/usb/pwc/* PWM FAN DRIVER M: Kamil Debski <k.debski@samsung.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/hwmon/pwm-fan.txt F: Documentation/hwmon/pwm-fan @@ -9882,28 +9882,28 @@ F: Documentation/devicetree/bindings/media/i2c/nokia,smia.txt SMM665 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/smm665 F: drivers/hwmon/smm665.c SMSC EMC2103 HARDWARE MONITOR DRIVER M: Steve Glendinning <steve.glendinning@shawell.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/emc2103 F: drivers/hwmon/emc2103.c SMSC SCH5627 HARDWARE MONITOR DRIVER M: Hans de Goede <hdegoede@redhat.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Supported F: Documentation/hwmon/sch5627 F: drivers/hwmon/sch5627.c SMSC47B397 HARDWARE MONITOR DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/smsc47b397 F: drivers/hwmon/smsc47b397.c @@ -10289,9 +10289,11 @@ S: Maintained F: drivers/net/ethernet/dlink/sundance.c SUPERH +M: Yoshinori Sato <ysato@users.sourceforge.jp> +M: Rich Felker <dalias@libc.org> L: linux-sh@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-sh/list/ -S: Orphan +S: Maintained F: Documentation/sh/ F: arch/sh/ F: drivers/sh/ @@ -10828,7 +10830,7 @@ F: include/linux/mmc/sh_mobile_sdhi.h TMP401 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/tmp401 F: drivers/hwmon/tmp401.c @@ -11562,14 +11564,14 @@ F: Documentation/networking/vrf.txt VT1211 HARDWARE MONITOR DRIVER M: Juerg Haefliger <juergh@gmail.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/vt1211 F: drivers/hwmon/vt1211.c VT8231 HARDWARE MONITOR DRIVER M: Roger Lucas <vt8231@hiddenengine.co.uk> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/vt8231.c @@ -11588,21 +11590,21 @@ F: drivers/w1/ W83791D HARDWARE MONITORING DRIVER M: Marc Hulsman <m.hulsman@tudelft.nl> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/w83791d F: drivers/hwmon/w83791d.c W83793 HARDWARE MONITORING DRIVER M: Rudolf Marek <r.marek@assembler.cz> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/w83793 F: drivers/hwmon/w83793.c W83795 HARDWARE MONITORING DRIVER M: Jean Delvare <jdelvare@suse.com> -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/w83795.c @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 0 +SUBLEVEL = 10 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg index a4cffb1840d7..304f1d4fd7c4 100644 --- a/android/configs/android-base.cfg +++ b/android/configs/android-base.cfg @@ -21,6 +21,7 @@ CONFIG_CGROUP_SCHED=y CONFIG_CP15_BARRIER_EMULATION=y CONFIG_DM_CRYPT=y CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y CONFIG_EMBEDDED=y CONFIG_FB=y CONFIG_HIGH_RES_TIMERS=y @@ -28,6 +29,7 @@ CONFIG_INET6_AH=y CONFIG_INET6_ESP=y CONFIG_INET6_IPCOMP=y CONFIG_INET=y +CONFIG_INET_DIAG_DESTROY=y CONFIG_INET_ESP=y CONFIG_INET_XFRM_MODE_TUNNEL=y CONFIG_IP6_NF_FILTER=y @@ -55,6 +57,7 @@ CONFIG_IP_NF_MANGLE=y CONFIG_IP_NF_MATCH_AH=y CONFIG_IP_NF_MATCH_ECN=y CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_NAT=y CONFIG_IP_NF_RAW=y CONFIG_IP_NF_SECURITY=y CONFIG_IP_NF_TARGET_MASQUERADE=y @@ -136,6 +139,7 @@ CONFIG_PPP_BSDCOMP=y CONFIG_PPP_DEFLATE=y CONFIG_PPP_MPPE=y CONFIG_PREEMPT=y +CONFIG_QUOTA=y CONFIG_RESOURCE_COUNTERS=y CONFIG_RTC_CLASS=y CONFIG_RT_GROUP_SCHED=y @@ -144,7 +148,6 @@ CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SETEND_EMULATION=y CONFIG_STAGING=y -CONFIG_SWITCH=y CONFIG_SWP_EMULATION=y CONFIG_SYNC=y CONFIG_TUN=y diff --git a/android/configs/android-recommended.cfg b/android/configs/android-recommended.cfg index e4c8aaade197..35936afdcae4 100644 --- a/android/configs/android-recommended.cfg +++ b/android/configs/android-recommended.cfg @@ -119,7 +119,6 @@ CONFIG_TIMER_STATS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_UHID=y -CONFIG_UID_STAT=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_HIDDEV=y diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index 57c1f33844d4..0352fb8d21b9 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -35,21 +35,6 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\ \ m += nr >> 5; \ \ - /* \ - * ARC ISA micro-optimization: \ - * \ - * Instructions dealing with bitpos only consider lower 5 bits \ - * e.g (x << 33) is handled like (x << 1) by ASL instruction \ - * (mem pointer still needs adjustment to point to next word) \ - * \ - * Hence the masking to clamp @nr arg can be elided in general. \ - * \ - * However if @nr is a constant (above assumed in a register), \ - * and greater than 31, gcc can optimize away (x << 33) to 0, \ - * as overflow, given the 32-bit ISA. Thus masking needs to be \ - * done for const @nr, but no code is generated due to gcc \ - * const prop. \ - */ \ nr &= 0x1f; \ \ __asm__ __volatile__( \ diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 694ece8a0243..cb69299a492e 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -13,6 +13,15 @@ #include <asm/byteorder.h> #include <asm/page.h> +#ifdef CONFIG_ISA_ARCV2 +#include <asm/barrier.h> +#define __iormb() rmb() +#define __iowmb() wmb() +#else +#define __iormb() do { } while (0) +#define __iowmb() do { } while (0) +#endif + extern void __iomem *ioremap(unsigned long physaddr, unsigned long size); extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, unsigned long flags); @@ -22,6 +31,15 @@ extern void iounmap(const void __iomem *addr); #define ioremap_wc(phy, sz) ioremap(phy, sz) #define ioremap_wt(phy, sz) ioremap(phy, sz) +/* + * io{read,write}{16,32}be() macros + */ +#define ioread16be(p) ({ u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) + +#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force u32)cpu_to_be32(v), p); }) + /* Change struct page to physical address */ #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) @@ -99,15 +117,6 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) } -#ifdef CONFIG_ISA_ARCV2 -#include <asm/barrier.h> -#define __iormb() rmb() -#define __iowmb() wmb() -#else -#define __iormb() do { } while (0) -#define __iowmb() do { } while (0) -#endif - /* * MMIO can also get buffered/optimized in micro-arch, so barriers needed * Based on ARM model for the typical use case @@ -129,15 +138,23 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) #define writel(v,c) ({ __iowmb(); writel_relaxed(v,c); }) /* - * Relaxed API for drivers which can handle any ordering themselves + * Relaxed API for drivers which can handle barrier ordering themselves + * + * Also these are defined to perform little endian accesses. + * To provide the typical device register semantics of fixed endian, + * swap the byte order for Big Endian + * + * http://lkml.kernel.org/r/201603100845.30602.arnd@arndb.de */ #define readb_relaxed(c) __raw_readb(c) -#define readw_relaxed(c) __raw_readw(c) -#define readl_relaxed(c) __raw_readl(c) +#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \ + __raw_readw(c)); __r; }) +#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \ + __raw_readl(c)); __r; }) #define writeb_relaxed(v,c) __raw_writeb(v,c) -#define writew_relaxed(v,c) __raw_writew(v,c) -#define writel_relaxed(v,c) __raw_writel(v,c) +#define writew_relaxed(v,c) __raw_writew((__force u16) cpu_to_le16(v),c) +#define writel_relaxed(v,c) __raw_writel((__force u32) cpu_to_le32(v),c) #include <asm-generic/io.h> diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index 258b0e5ad332..68b6092349d7 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -22,6 +22,7 @@ #define AUX_IRQ_CTRL 0x00E #define AUX_IRQ_ACT 0x043 /* Active Intr across all levels */ #define AUX_IRQ_LVL_PEND 0x200 /* Pending Intr across all levels */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ #define AUX_IRQ_PRIORITY 0x206 #define ICAUSE 0x40a #define AUX_IRQ_SELECT 0x40b @@ -112,6 +113,16 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } +static inline void arc_softirq_trigger(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, irq); +} + +static inline void arc_softirq_clear(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, 0); +} + #else .macro IRQ_DISABLE scratch diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index cbfec79137bf..c1264607bbff 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -45,11 +45,12 @@ VECTOR reserved ; Reserved slots VECTOR handle_interrupt ; (16) Timer0 VECTOR handle_interrupt ; unused (Timer1) VECTOR handle_interrupt ; unused (WDT) -VECTOR handle_interrupt ; (19) ICI (inter core interrupt) -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt ; (23) End of fixed IRQs +VECTOR handle_interrupt ; (19) Inter core Interrupt (IPI) +VECTOR handle_interrupt ; (20) perf Interrupt +VECTOR handle_interrupt ; (21) Software Triggered Intr (Self IPI) +VECTOR handle_interrupt ; unused +VECTOR handle_interrupt ; (23) unused +# End of fixed IRQs .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8 VECTOR handle_interrupt @@ -211,7 +212,11 @@ debug_marker_syscall: ; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig ; entry was via Exception in DS which got preempted in kernel). ; -; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling +; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround +; +; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline +; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly + .Lintr_ret_to_delay_slot: debug_marker_ds: @@ -222,18 +227,23 @@ debug_marker_ds: ld r2, [sp, PT_ret] ld r3, [sp, PT_status32] + ; STAT32 for Int return created from scratch + ; (No delay dlot, disable Further intr in trampoline) + bic r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK st r0, [sp, PT_status32] mov r1, .Lintr_ret_to_delay_slot_2 st r1, [sp, PT_ret] + ; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots st r2, [sp, 0] st r3, [sp, 4] b .Lisr_ret_fast_path .Lintr_ret_to_delay_slot_2: + ; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP sub sp, sp, SZ_PT_REGS st r9, [sp, -4] @@ -243,11 +253,19 @@ debug_marker_ds: ld r9, [sp, 4] sr r9, [erstatus] + ; restore AUX_USER_SP if returning to U mode + bbit0 r9, STATUS_U_BIT, 1f + ld r9, [sp, PT_sp] + sr r9, [AUX_USER_SP] + +1: ld r9, [sp, 8] sr r9, [erbta] ld r9, [sp, -4] add sp, sp, SZ_PT_REGS + + ; return from pure kernel mode to delay slot rtie END(ret_from_exception) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index bd237acdf4f2..30d806ce0c78 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -11,9 +11,12 @@ #include <linux/smp.h> #include <linux/irq.h> #include <linux/spinlock.h> +#include <asm/irqflags-arcv2.h> #include <asm/mcip.h> #include <asm/setup.h> +#define SOFTIRQ_IRQ 21 + static char smp_cpuinfo_buf[128]; static int idu_detected; @@ -22,6 +25,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static void mcip_setup_per_cpu(int cpu) { smp_ipi_irq_setup(cpu, IPI_IRQ); + smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); } static void mcip_ipi_send(int cpu) @@ -29,6 +33,12 @@ static void mcip_ipi_send(int cpu) unsigned long flags; int ipi_was_pending; + /* ARConnect can only send IPI to others */ + if (unlikely(cpu == raw_smp_processor_id())) { + arc_softirq_trigger(SOFTIRQ_IRQ); + return; + } + /* * NOTE: We must spin here if the other cpu hasn't yet * serviced a previous message. This can burn lots @@ -63,6 +73,11 @@ static void mcip_ipi_clear(int irq) unsigned long flags; unsigned int __maybe_unused copy; + if (unlikely(irq == SOFTIRQ_IRQ)) { + arc_softirq_clear(irq); + return; + } + raw_spin_lock_irqsave(&mcip_lock, flags); /* Who sent the IPI */ diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 0901c6bd458f..f08e4fd600a3 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -162,10 +162,9 @@ choice mobile SoCs in the Kona family of chips (e.g. bcm28155, bcm11351, etc...) - config DEBUG_BCM63XX + config DEBUG_BCM63XX_UART bool "Kernel low-level debugging on BCM63XX UART" depends on ARCH_BCM_63XX - select DEBUG_UART_BCM63XX config DEBUG_BERLIN_UART bool "Marvell Berlin SoC Debug UART" @@ -1348,7 +1347,7 @@ config DEBUG_LL_INCLUDE default "debug/vf.S" if DEBUG_VF_UART default "debug/vt8500.S" if DEBUG_VT8500_UART0 default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1 - default "debug/bcm63xx.S" if DEBUG_UART_BCM63XX + default "debug/bcm63xx.S" if DEBUG_BCM63XX_UART default "debug/digicolor.S" if DEBUG_DIGICOLOR_UA0 default "mach/debug-macro.S" @@ -1364,10 +1363,6 @@ config DEBUG_UART_8250 ARCH_IOP33X || ARCH_IXP4XX || \ ARCH_LPC32XX || ARCH_MV78XX0 || ARCH_ORION5X || ARCH_RPC -# Compatibility options for BCM63xx -config DEBUG_UART_BCM63XX - def_bool ARCH_BCM_63XX - config DEBUG_UART_PHYS hex "Physical base address of debug UART" default 0x00100a00 if DEBUG_NETX_UART @@ -1462,7 +1457,7 @@ config DEBUG_UART_PHYS default 0xfffb0000 if DEBUG_OMAP1UART1 || DEBUG_OMAP7XXUART1 default 0xfffb0800 if DEBUG_OMAP1UART2 || DEBUG_OMAP7XXUART2 default 0xfffb9800 if DEBUG_OMAP1UART3 || DEBUG_OMAP7XXUART3 - default 0xfffe8600 if DEBUG_UART_BCM63XX + default 0xfffe8600 if DEBUG_BCM63XX_UART default 0xfffff700 if ARCH_IOP33X depends on ARCH_EP93XX || \ DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \ @@ -1474,7 +1469,7 @@ config DEBUG_UART_PHYS DEBUG_RCAR_GEN2_SCIF0 || DEBUG_RCAR_GEN2_SCIF2 || \ DEBUG_RMOBILE_SCIFA0 || DEBUG_RMOBILE_SCIFA1 || \ DEBUG_RMOBILE_SCIFA4 || DEBUG_S3C24XX_UART || \ - DEBUG_UART_BCM63XX || DEBUG_ASM9260_UART || \ + DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \ DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0 || \ DEBUG_AT91_UART @@ -1515,7 +1510,7 @@ config DEBUG_UART_VIRT default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT default 0xfc40ab00 if DEBUG_BRCMSTB_UART default 0xfc705000 if DEBUG_ZTE_ZX - default 0xfcfe8600 if DEBUG_UART_BCM63XX + default 0xfcfe8600 if DEBUG_BCM63XX_UART default 0xfd000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX default 0xfd000000 if ARCH_SPEAR13XX default 0xfd012000 if ARCH_MV78XX0 @@ -1566,7 +1561,7 @@ config DEBUG_UART_VIRT DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \ DEBUG_NETX_UART || \ DEBUG_QCOM_UARTDM || DEBUG_S3C24XX_UART || \ - DEBUG_UART_BCM63XX || DEBUG_ASM9260_UART || \ + DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \ DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0 config DEBUG_UART_8250_SHIFT diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 47954ed990f8..00707aac72fc 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -792,3 +792,8 @@ tx-num-evt = <32>; rx-num-evt = <32>; }; + +&synctimer_32kclk { + assigned-clocks = <&mux_synctimer32k_ck>; + assigned-clock-parents = <&clkdiv32k_ick>; +}; diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi index 7ccce7529b0c..cc952cf8ec30 100644 --- a/arch/arm/boot/dts/armada-375.dtsi +++ b/arch/arm/boot/dts/armada-375.dtsi @@ -529,7 +529,7 @@ }; sata@a0000 { - compatible = "marvell,orion-sata"; + compatible = "marvell,armada-370-sata"; reg = <0xa0000 0x5000>; interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gateclk 14>, <&gateclk 20>; diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index 3710755c6d76..85d2c377c332 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -117,7 +117,7 @@ }; /* USB part of the eSATA/USB 2.0 port */ - usb@50000 { + usb@58000 { status = "okay"; }; diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts index a633be3defda..cd316021d6ce 100644 --- a/arch/arm/boot/dts/armada-388-gp.dts +++ b/arch/arm/boot/dts/armada-388-gp.dts @@ -303,16 +303,6 @@ gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; }; - reg_usb2_1_vbus: v5-vbus1 { - compatible = "regulator-fixed"; - regulator-name = "v5.0-vbus1"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - enable-active-high; - regulator-always-on; - gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; - }; - reg_sata0: pwr-sata0 { compatible = "regulator-fixed"; regulator-name = "pwr_en_sata0"; diff --git a/arch/arm/boot/dts/armada-xp-axpwifiap.dts b/arch/arm/boot/dts/armada-xp-axpwifiap.dts index 23fc670c0427..5c21b236721f 100644 --- a/arch/arm/boot/dts/armada-xp-axpwifiap.dts +++ b/arch/arm/boot/dts/armada-xp-axpwifiap.dts @@ -70,8 +70,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts index f774101416a5..ebe1d267406d 100644 --- a/arch/arm/boot/dts/armada-xp-db.dts +++ b/arch/arm/boot/dts/armada-xp-db.dts @@ -76,8 +76,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts index 4878d7353069..5730b875c4f5 100644 --- a/arch/arm/boot/dts/armada-xp-gp.dts +++ b/arch/arm/boot/dts/armada-xp-gp.dts @@ -95,8 +95,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts index 58b500873bfd..d960fef77ca1 100644 --- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts +++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts @@ -65,8 +65,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index 6e9820e141f8..b89e6cf1271a 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -70,8 +70,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts index 6ab33837a2b6..6522b04f4a8e 100644 --- a/arch/arm/boot/dts/armada-xp-matrix.dts +++ b/arch/arm/boot/dts/armada-xp-matrix.dts @@ -68,8 +68,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; internal-regs { serial@12000 { diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index 6fe8972de0a2..db54c7158a36 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -64,8 +64,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index a5db17782e08..853bd392a4fe 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -65,9 +65,9 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x8000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x01, 0x2f) 0 0 0xe8000000 0x8000000 + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-synology-ds414.dts b/arch/arm/boot/dts/armada-xp-synology-ds414.dts index 2391b11dc546..d17dab0a6f51 100644 --- a/arch/arm/boot/dts/armada-xp-synology-ds414.dts +++ b/arch/arm/boot/dts/armada-xp-synology-ds414.dts @@ -78,8 +78,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index ff888d21c786..f3e2b96c06a3 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -303,6 +303,7 @@ regulator-name = "mmc0-card-supply"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + regulator-always-on; }; gpio_keys { diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 131614f28e75..da84e65b56ef 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -86,10 +86,12 @@ macb0: ethernet@f8020000 { phy-mode = "rmii"; status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy0: ethernet-phy@1 { interrupt-parent = <&pioE>; - interrupts = <1 IRQ_TYPE_EDGE_FALLING>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; reg = <1>; }; }; @@ -152,6 +154,10 @@ atmel,pins = <AT91_PIOE 8 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; }; + pinctrl_macb0_phy_irq: macb0_phy_irq_0 { + atmel,pins = + <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; + }; }; }; }; @@ -262,5 +268,6 @@ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; vin-supply = <&vcc_3v3_reg>; + regulator-always-on; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index 2d4a33100af6..4e98cda97403 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -160,8 +160,15 @@ }; macb0: ethernet@f8020000 { + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy-mode = "rmii"; status = "okay"; + + ethernet-phy@1 { + reg = <0x1>; + interrupt-parent = <&pioE>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + }; }; mmc1: mmc@fc000000 { @@ -193,6 +200,10 @@ pinctrl@fc06a000 { board { + pinctrl_macb0_phy_irq: macb0_phy_irq { + atmel,pins = + <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; + }; pinctrl_mmc0_cd: mmc0_cd { atmel,pins = <AT91_PIOE 5 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index fe99231cbde5..c2a03c740e79 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1497,6 +1497,16 @@ 0x48485200 0x2E00>; #address-cells = <1>; #size-cells = <1>; + + /* + * Do not allow gating of cpsw clock as workaround + * for errata i877. Keeping internal clock disabled + * causes the device switching characteristics + * to degrade over time and eventually fail to meet + * the data manual delay time/skew specs. + */ + ti,no-idle; + /* * rx_thresh_pend * rx_pend diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 36387b11451d..80f6c786a37e 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -122,6 +122,7 @@ interrupt-parent = <&gpio5>; interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */ ref-clock-frequency = <26000000>; + tcxo-clock-frequency = <26000000>; }; }; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 5cf76a1c5c75..41e80e7f20be 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -130,6 +130,16 @@ }; }; +&gpio8 { + /* TI trees use GPIO instead of msecure, see also muxing */ + p234 { + gpio-hog; + gpios = <10 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "gpio8_234/msecure"; + }; +}; + &omap5_pmx_core { pinctrl-names = "default"; pinctrl-0 = < @@ -213,6 +223,13 @@ >; }; + /* TI trees use GPIO mode; msecure mode does not work reliably? */ + palmas_msecure_pins: palmas_msecure_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x180, PIN_OUTPUT | MUX_MODE6) /* gpio8_234 */ + >; + }; + usbhost_pins: pinmux_usbhost_pins { pinctrl-single,pins = < 0x84 (PIN_INPUT | MUX_MODE0) /* usbb2_hsic_strobe */ @@ -278,6 +295,12 @@ &usbhost_wkup_pins >; + palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */ + >; + }; + usbhost_wkup_pins: pinmux_usbhost_wkup_pins { pinctrl-single,pins = < 0x1A (PIN_OUTPUT | MUX_MODE0) /* fref_clk1_out, USB hub clk */ @@ -345,6 +368,8 @@ interrupt-controller; #interrupt-cells = <2>; ti,system-power-controller; + pinctrl-names = "default"; + pinctrl-0 = <&palmas_sys_nirq_pins &palmas_msecure_pins>; extcon_usb3: palmas_usb { compatible = "ti,palmas-usb-vid"; @@ -358,6 +383,14 @@ #clock-cells = <0>; }; + rtc { + compatible = "ti,palmas-rtc"; + interrupt-parent = <&palmas>; + interrupts = <8 IRQ_TYPE_NONE>; + ti,backup-battery-chargeable; + ti,backup-battery-charge-high-current; + }; + palmas_pmic { compatible = "ti,palmas-pmic"; interrupt-parent = <&palmas>; diff --git a/arch/arm/boot/dts/pxa3xx.dtsi b/arch/arm/boot/dts/pxa3xx.dtsi index cf6998a0804d..564341af7e97 100644 --- a/arch/arm/boot/dts/pxa3xx.dtsi +++ b/arch/arm/boot/dts/pxa3xx.dtsi @@ -30,7 +30,7 @@ reg = <0x43100000 90>; interrupts = <45>; clocks = <&clks CLK_NAND>; - dmas = <&pdma 97>; + dmas = <&pdma 97 3>; dma-names = "data"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h index 1afe24629d1f..b0c912feaa2f 100644 --- a/arch/arm/boot/dts/sama5d2-pinfunc.h +++ b/arch/arm/boot/dts/sama5d2-pinfunc.h @@ -90,7 +90,7 @@ #define PIN_PA14__I2SC1_MCK PINMUX_PIN(PIN_PA14, 4, 2) #define PIN_PA14__FLEXCOM3_IO2 PINMUX_PIN(PIN_PA14, 5, 1) #define PIN_PA14__D9 PINMUX_PIN(PIN_PA14, 6, 2) -#define PIN_PA15 14 +#define PIN_PA15 15 #define PIN_PA15__GPIO PINMUX_PIN(PIN_PA15, 0, 0) #define PIN_PA15__SPI0_MOSI PINMUX_PIN(PIN_PA15, 1, 1) #define PIN_PA15__TF1 PINMUX_PIN(PIN_PA15, 2, 1) diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi index 2193637b9cd2..3daf8d5d7878 100644 --- a/arch/arm/boot/dts/sama5d4.dtsi +++ b/arch/arm/boot/dts/sama5d4.dtsi @@ -1342,7 +1342,7 @@ dbgu: serial@fc069000 { compatible = "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; reg = <0xfc069000 0x200>; - interrupts = <2 IRQ_TYPE_LEVEL_HIGH 7>; + interrupts = <45 IRQ_TYPE_LEVEL_HIGH 7>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_dbgu>; clocks = <&dbgu_clk>; diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index d0c743853318..27a333eb8987 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -127,22 +127,14 @@ }; mmcsd_default_mode: mmcsd_default { mmcsd_default_cfg1 { - /* MCCLK */ - pins = "GPIO8_B10"; - ste,output = <0>; - }; - mmcsd_default_cfg2 { - /* MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 */ - pins = "GPIO10_C11", "GPIO15_A12", - "GPIO16_C13", "GPIO23_D15"; - ste,output = <1>; - }; - mmcsd_default_cfg3 { - /* MCCMD, MCDAT3-0, MCMSFBCLK */ - pins = "GPIO9_A10", "GPIO11_B11", - "GPIO12_A11", "GPIO13_C12", - "GPIO14_B12", "GPIO24_C15"; - ste,input = <1>; + /* + * MCCLK, MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 + * MCCMD, MCDAT3-0, MCMSFBCLK + */ + pins = "GPIO8_B10", "GPIO9_A10", "GPIO10_C11", "GPIO11_B11", + "GPIO12_A11", "GPIO13_C12", "GPIO14_B12", "GPIO15_A12", + "GPIO16_C13", "GPIO23_D15", "GPIO24_C15"; + ste,output = <2>; }; }; }; @@ -802,10 +794,21 @@ clock-names = "mclk", "apb_pclk"; interrupt-parent = <&vica>; interrupts = <22>; - max-frequency = <48000000>; + max-frequency = <400000>; bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + full-pwr-cycle; + /* + * The STw4811 circuit used with the Nomadik strictly + * requires that all of these signal direction pins be + * routed and used for its 4-bit levelshifter. + */ + st,sig-dir-dat0; + st,sig-dir-dat2; + st,sig-dir-dat31; + st,sig-dir-cmd; + st,sig-pin-fbclk; pinctrl-names = "default"; pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>; vmmc-supply = <&vmmc_regulator>; diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c index 2dc6da70ae59..d7ed252708c5 100644 --- a/arch/arm/common/icst.c +++ b/arch/arm/common/icst.c @@ -16,7 +16,7 @@ */ #include <linux/module.h> #include <linux/kernel.h> - +#include <asm/div64.h> #include <asm/hardware/icst.h> /* @@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div); unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco) { - return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]); + u64 dividend = p->ref * 2 * (u64)(vco.v + 8); + u32 divisor = (vco.r + 2) * p->s2div[vco.s]; + + do_div(dividend, divisor); + return (unsigned long)dividend; } EXPORT_SYMBOL(icst_hz); @@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq) if (f > p->vco_min && f <= p->vco_max) break; + i++; } while (i < 8); if (i >= 8) diff --git a/arch/arm/include/asm/mach/mmc.h b/arch/arm/include/asm/mach/mmc.h deleted file mode 100644 index bca864ac945f..000000000000 --- a/arch/arm/include/asm/mach/mmc.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * arch/arm/include/asm/mach/mmc.h - */ -#ifndef ASMARM_MACH_MMC_H -#define ASMARM_MACH_MMC_H - -#include <linux/mmc/host.h> -#include <linux/mmc/card.h> -#include <linux/mmc/sdio_func.h> - -struct embedded_sdio_data { - struct sdio_cis cis; - struct sdio_cccr cccr; - struct sdio_embedded_func *funcs; - int num_funcs; -}; - -struct mmc_platform_data { - unsigned int ocr_mask; /* available voltages */ - int built_in; /* built-in device flag */ - int card_present; /* card detect state */ - u32 (*translate_vdd)(struct device *, unsigned int); - unsigned int (*status)(struct device *); - struct embedded_sdio_data *embedded_sdio; - int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id); -}; - -#endif diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 0375c8caa061..9408a994cc91 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page); + unsigned long page_pfn = page_to_xen_pfn(page); + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); + unsigned long compound_pages = + (1<<compound_order(page)) * XEN_PFN_PER_PAGE; + bool local = (page_pfn <= dev_pfn) && + (dev_pfn - page_pfn < compound_pages); + /* - * Dom0 is mapped 1:1, while the Linux page can be spanned accross - * multiple Xen page, it's not possible to have a mix of local and - * foreign Xen page. So if the first xen_pfn == mfn the page is local - * otherwise it's a foreign page grant-mapped in dom0. If the page is - * local we can safely call the native dma_ops function, otherwise we - * call the xen specific function. + * Dom0 is mapped 1:1, while the Linux page can span across + * multiple Xen pages, it's not possible for it to contain a + * mix of local and foreign Xen pages. So if the first xen_pfn + * == mfn the page is local otherwise it's a foreign page + * grant-mapped in dom0. If the page is local we can safely + * call the native dma_ops function, otherwise we call the xen + * specific function. */ if (local) __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 96e935bbc38c..3705fc2921c2 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -155,7 +155,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } static unsigned long num_core_regs(void) diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 47905a50e075..318394ed5c7a 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -220,13 +220,13 @@ static void cns3xxx_write_config(struct cns3xxx_pcie *cnspci, u32 mask = (0x1ull << (size * 8)) - 1; int shift = (where % 4) * 8; - v = readl_relaxed(base + (where & 0xffc)); + v = readl_relaxed(base); v &= ~(mask << shift); v |= (val & mask) << shift; - writel_relaxed(v, base + (where & 0xffc)); - readl_relaxed(base + (where & 0xffc)); + writel_relaxed(v, base); + readl_relaxed(base); } static void __init cns3xxx_pcie_hw_init(struct cns3xxx_pcie *cnspci) diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index 3a10f1a8317a..bfd8bb371477 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -26,6 +26,7 @@ menuconfig ARCH_EXYNOS select S5P_DEV_MFC select SRAM select THERMAL + select THERMAL_OF select MFD_SYSCON help Support for SAMSUNG EXYNOS SoCs (EXYNOS4/5) diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index 7c21760f590f..875a2bab64f6 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -92,7 +92,7 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on) if (IS_ERR(pd->clk[i])) break; - if (IS_ERR(pd->clk[i])) + if (IS_ERR(pd->pclk[i])) continue; /* Skip on first power up */ if (clk_set_parent(pd->clk[i], pd->pclk[i])) pr_err("%s: error setting parent to clock%d\n", diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c index aa7b379e2661..2a3db0bd9e15 100644 --- a/arch/arm/mach-omap2/cpuidle34xx.c +++ b/arch/arm/mach-omap2/cpuidle34xx.c @@ -34,6 +34,7 @@ #include "pm.h" #include "control.h" #include "common.h" +#include "soc.h" /* Mach specific information to be recorded in the C-state driver_data */ struct omap3_idle_statedata { @@ -315,6 +316,69 @@ static struct cpuidle_driver omap3_idle_driver = { .safe_state_index = 0, }; +/* + * Numbers based on measurements made in October 2009 for PM optimized kernel + * with CPU freq enabled on device Nokia N900. Assumes OPP2 (main idle OPP, + * and worst case latencies). + */ +static struct cpuidle_driver omap3430_idle_driver = { + .name = "omap3430_idle", + .owner = THIS_MODULE, + .states = { + { + .enter = omap3_enter_idle_bm, + .exit_latency = 110 + 162, + .target_residency = 5, + .name = "C1", + .desc = "MPU ON + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 106 + 180, + .target_residency = 309, + .name = "C2", + .desc = "MPU ON + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 107 + 410, + .target_residency = 46057, + .name = "C3", + .desc = "MPU RET + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 121 + 3374, + .target_residency = 46057, + .name = "C4", + .desc = "MPU OFF + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 855 + 1146, + .target_residency = 46057, + .name = "C5", + .desc = "MPU RET + CORE RET", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 7580 + 4134, + .target_residency = 484329, + .name = "C6", + .desc = "MPU OFF + CORE RET", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 7505 + 15274, + .target_residency = 484329, + .name = "C7", + .desc = "MPU OFF + CORE OFF", + }, + }, + .state_count = ARRAY_SIZE(omap3_idle_data), + .safe_state_index = 0, +}; + /* Public functions */ /** @@ -333,5 +397,8 @@ int __init omap3_idle_init(void) if (!mpu_pd || !core_pd || !per_pd || !cam_pd) return -ENODEV; - return cpuidle_register(&omap3_idle_driver, NULL); + if (cpu_is_omap3430()) + return cpuidle_register(&omap3430_idle_driver, NULL); + else + return cpuidle_register(&omap3_idle_driver, NULL); } diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 7b76ce01c21d..8633c703546a 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base) static void set_onenand_cfg(void __iomem *onenand_base) { - u32 reg; + u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT; - reg = readw(onenand_base + ONENAND_REG_SYS_CFG1); - reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9)); reg |= (latency << ONENAND_SYS_CFG1_BRL_SHIFT) | ONENAND_SYS_CFG1_BL_16; if (onenand_flags & ONENAND_FLAG_SYNCREAD) @@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base) reg |= ONENAND_SYS_CFG1_VHF; else reg &= ~ONENAND_SYS_CFG1_VHF; + writew(reg, onenand_base + ONENAND_REG_SYS_CFG1); } @@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) } } + onenand_async.sync_write = true; omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 3eaeaca5da05..3a911d8dea8b 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -368,6 +368,7 @@ void __init omap5_map_io(void) void __init dra7xx_map_io(void) { iotable_init(dra7xx_io_desc, ARRAY_SIZE(dra7xx_io_desc)); + omap_barriers_init(); } #endif /* diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 48495ad82aba..147c90e70b2e 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1416,9 +1416,7 @@ static void _enable_sysc(struct omap_hwmod *oh) (sf & SYSC_HAS_CLOCKACTIVITY)) _set_clockactivity(oh, oh->class->sysc->clockact, &v); - /* If the cached value is the same as the new value, skip the write */ - if (oh->_sysc_cache != v) - _write_sysconfig(v, oh); + _write_sysconfig(v, oh); /* * Set the autoidle bit only after setting the smartidle bit @@ -1481,7 +1479,9 @@ static void _idle_sysc(struct omap_hwmod *oh) _set_master_standbymode(oh, idlemode, &v); } - _write_sysconfig(v, oh); + /* If the cached value is the same as the new value, skip the write */ + if (oh->_sysc_cache != v) + _write_sysconfig(v, oh); } /** @@ -2200,6 +2200,11 @@ static int _enable(struct omap_hwmod *oh) */ static int _idle(struct omap_hwmod *oh) { + if (oh->flags & HWMOD_NO_IDLE) { + oh->_int_flags |= _HWMOD_SKIP_ENABLE; + return 0; + } + pr_debug("omap_hwmod: %s: idling\n", oh->name); if (oh->_state != _HWMOD_STATE_ENABLED) { @@ -2504,6 +2509,8 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->flags |= HWMOD_INIT_NO_RESET; if (of_find_property(np, "ti,no-idle-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_IDLE; + if (of_find_property(np, "ti,no-idle", NULL)) + oh->flags |= HWMOD_NO_IDLE; } oh->_state = _HWMOD_STATE_INITIALIZED; @@ -2630,7 +2637,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh) * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data - * it should be set by the core code as a runtime flag during startup */ - if ((oh->flags & HWMOD_INIT_NO_IDLE) && + if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) && (postsetup_state == _HWMOD_STATE_IDLE)) { oh->_int_flags |= _HWMOD_SKIP_ENABLE; postsetup_state = _HWMOD_STATE_ENABLED; diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 76bce11c85a4..7c7a31169475 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -525,6 +525,8 @@ struct omap_hwmod_omap4_prcm { * or idled. * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to * operate and they need to be handled at the same time as the main_clk. + * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain + * IPs like CPSW on DRA7, where clocks to this module cannot be disabled. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -541,6 +543,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_SWSUP_SIDLE_ACT (1 << 12) #define HWMOD_RECONFIG_IO_CHAIN (1 << 13) #define HWMOD_OPT_CLKS_NEEDED (1 << 14) +#define HWMOD_NO_IDLE (1 << 15) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index eafd120b53f1..1b9f0520dea9 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -86,13 +86,18 @@ ENTRY(enable_omap3630_toggle_l2_on_restore) stmfd sp!, {lr} @ save registers on stack /* Setup so that we will disable and enable l2 */ mov r1, #0x1 - adrl r2, l2dis_3630 @ may be too distant for plain adr - str r1, [r2] + adrl r3, l2dis_3630_offset @ may be too distant for plain adr + ldr r2, [r3] @ value for offset + str r1, [r2, r3] @ write to l2dis_3630 ldmfd sp!, {pc} @ restore regs and return ENDPROC(enable_omap3630_toggle_l2_on_restore) - .text -/* Function to call rom code to save secure ram context */ +/* + * Function to call rom code to save secure ram context. This gets + * relocated to SRAM, so it can be all in .data section. Otherwise + * we need to initialize api_params separately. + */ + .data .align 3 ENTRY(save_secure_ram_context) stmfd sp!, {r4 - r11, lr} @ save registers on stack @@ -126,6 +131,8 @@ ENDPROC(save_secure_ram_context) ENTRY(save_secure_ram_context_sz) .word . - save_secure_ram_context + .text + /* * ====================== * == Idle entry point == @@ -289,12 +296,6 @@ wait_sdrc_ready: bic r5, r5, #0x40 str r5, [r4] -/* - * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a - * base instead. - * Be careful not to clobber r7 when maintaing this code. - */ - is_dll_in_lock_mode: /* Is dll in lock mode? */ ldr r4, sdrc_dlla_ctrl @@ -302,11 +303,7 @@ is_dll_in_lock_mode: tst r5, #0x4 bne exit_nonoff_modes @ Return if locked /* wait till dll locks */ - adr r7, kick_counter wait_dll_lock_timed: - ldr r4, wait_dll_lock_counter - add r4, r4, #1 - str r4, [r7, #wait_dll_lock_counter - kick_counter] ldr r4, sdrc_dlla_status /* Wait 20uS for lock */ mov r6, #8 @@ -330,9 +327,6 @@ kick_dll: orr r6, r6, #(1<<3) @ enable dll str r6, [r4] dsb - ldr r4, kick_counter - add r4, r4, #1 - str r4, [r7] @ kick_counter b wait_dll_lock_timed exit_nonoff_modes: @@ -360,15 +354,6 @@ sdrc_dlla_status: .word SDRC_DLLA_STATUS_V sdrc_dlla_ctrl: .word SDRC_DLLA_CTRL_V - /* - * When exporting to userspace while the counters are in SRAM, - * these 2 words need to be at the end to facilitate retrival! - */ -kick_counter: - .word 0 -wait_dll_lock_counter: - .word 0 - ENTRY(omap3_do_wfi_sz) .word . - omap3_do_wfi @@ -437,7 +422,9 @@ ENTRY(omap3_restore) cmp r2, #0x0 @ Check if target power state was OFF or RET bne logic_l1_restore - ldr r0, l2dis_3630 + adr r1, l2dis_3630_offset @ address for offset + ldr r0, [r1] @ value for offset + ldr r0, [r1, r0] @ value at l2dis_3630 cmp r0, #0x1 @ should we disable L2 on 3630? bne skipl2dis mrc p15, 0, r0, c1, c0, 1 @@ -449,12 +436,14 @@ skipl2dis: and r1, #0x700 cmp r1, #0x300 beq l2_inv_gp + adr r0, l2_inv_api_params_offset + ldr r3, [r0] + add r3, r3, r0 @ r3 points to dummy parameters mov r0, #40 @ set service ID for PPA mov r12, r0 @ copy secure Service ID in r12 mov r1, #0 @ set task id for ROM code in r1 mov r2, #4 @ set some flags in r2, r6 mov r6, #0xff - adr r3, l2_inv_api_params @ r3 points to dummy parameters dsb @ data write barrier dmb @ data memory barrier smc #1 @ call SMI monitor (smi #1) @@ -488,8 +477,8 @@ skipl2dis: b logic_l1_restore .align -l2_inv_api_params: - .word 0x1, 0x00 +l2_inv_api_params_offset: + .long l2_inv_api_params - . l2_inv_gp: /* Execute smi to invalidate L2 cache */ mov r12, #0x1 @ set up to invalidate L2 @@ -506,7 +495,9 @@ l2_inv_gp: mov r12, #0x2 smc #0 @ Call SMI monitor (smieq) logic_l1_restore: - ldr r1, l2dis_3630 + adr r0, l2dis_3630_offset @ adress for offset + ldr r1, [r0] @ value for offset + ldr r1, [r0, r1] @ value at l2dis_3630 cmp r1, #0x1 @ Test if L2 re-enable needed on 3630 bne skipl2reen mrc p15, 0, r1, c1, c0, 1 @@ -535,9 +526,17 @@ control_stat: .word CONTROL_STAT control_mem_rta: .word CONTROL_MEM_RTA_CTRL +l2dis_3630_offset: + .long l2dis_3630 - . + + .data l2dis_3630: .word 0 + .data +l2_inv_api_params: + .word 0x1, 0x00 + /* * Internal functions */ diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S index 9b09d85d811a..c7a3b4aab4b5 100644 --- a/arch/arm/mach-omap2/sleep44xx.S +++ b/arch/arm/mach-omap2/sleep44xx.S @@ -29,12 +29,6 @@ dsb .endm -ppa_zero_params: - .word 0x0 - -ppa_por_params: - .word 1, 0 - #ifdef CONFIG_ARCH_OMAP4 /* @@ -266,7 +260,9 @@ ENTRY(omap4_cpu_resume) beq skip_ns_smp_enable ppa_actrl_retry: mov r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX - adr r3, ppa_zero_params @ Pointer to parameters + adr r1, ppa_zero_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_zero_params mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag mov r6, #0xff @@ -303,7 +299,9 @@ skip_ns_smp_enable: ldr r0, =OMAP4_PPA_L2_POR_INDEX ldr r1, =OMAP44XX_SAR_RAM_BASE ldr r4, [r1, #L2X0_PREFETCH_CTRL_OFFSET] - adr r3, ppa_por_params + adr r1, ppa_por_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_por_params str r4, [r3, #0x04] mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag @@ -328,6 +326,8 @@ skip_l2en: #endif b cpu_resume @ Jump to generic resume +ppa_por_params_offset: + .long ppa_por_params - . ENDPROC(omap4_cpu_resume) #endif /* CONFIG_ARCH_OMAP4 */ @@ -380,4 +380,13 @@ ENTRY(omap_do_wfi) nop ldmfd sp!, {pc} +ppa_zero_params_offset: + .long ppa_zero_params - . ENDPROC(omap_do_wfi) + + .data +ppa_zero_params: + .word 0 + +ppa_por_params: + .word 1, 0 diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig index 9ab8932403e5..56e55fd37d13 100644 --- a/arch/arm/mach-prima2/Kconfig +++ b/arch/arm/mach-prima2/Kconfig @@ -1,6 +1,7 @@ menuconfig ARCH_SIRF bool "CSR SiRF" if ARCH_MULTI_V7 select ARCH_HAS_RESET_CONTROLLER + select RESET_CONTROLLER select ARCH_REQUIRE_GPIOLIB select GENERIC_IRQ_CHIP select NO_IOPORT_MAP diff --git a/arch/arm/mach-s3c64xx/dev-audio.c b/arch/arm/mach-s3c64xx/dev-audio.c index ff780a8d8366..9a42736ef4ac 100644 --- a/arch/arm/mach-s3c64xx/dev-audio.c +++ b/arch/arm/mach-s3c64xx/dev-audio.c @@ -54,12 +54,12 @@ static int s3c64xx_i2s_cfg_gpio(struct platform_device *pdev) static struct resource s3c64xx_iis0_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IIS0, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_I2S0_OUT), - [2] = DEFINE_RES_DMA(DMACH_I2S0_IN), }; -static struct s3c_audio_pdata i2sv3_pdata = { +static struct s3c_audio_pdata i2s0_pdata = { .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_I2S0_OUT, + .dma_capture = DMACH_I2S0_IN, }; struct platform_device s3c64xx_device_iis0 = { @@ -68,15 +68,19 @@ struct platform_device s3c64xx_device_iis0 = { .num_resources = ARRAY_SIZE(s3c64xx_iis0_resource), .resource = s3c64xx_iis0_resource, .dev = { - .platform_data = &i2sv3_pdata, + .platform_data = &i2s0_pdata, }, }; EXPORT_SYMBOL(s3c64xx_device_iis0); static struct resource s3c64xx_iis1_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IIS1, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_I2S1_OUT), - [2] = DEFINE_RES_DMA(DMACH_I2S1_IN), +}; + +static struct s3c_audio_pdata i2s1_pdata = { + .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_I2S1_OUT, + .dma_capture = DMACH_I2S1_IN, }; struct platform_device s3c64xx_device_iis1 = { @@ -85,19 +89,19 @@ struct platform_device s3c64xx_device_iis1 = { .num_resources = ARRAY_SIZE(s3c64xx_iis1_resource), .resource = s3c64xx_iis1_resource, .dev = { - .platform_data = &i2sv3_pdata, + .platform_data = &i2s1_pdata, }, }; EXPORT_SYMBOL(s3c64xx_device_iis1); static struct resource s3c64xx_iisv4_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IISV4, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_TX), - [2] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_RX), }; static struct s3c_audio_pdata i2sv4_pdata = { .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_HSI_I2SV40_TX, + .dma_capture = DMACH_HSI_I2SV40_RX, .type = { .i2s = { .quirks = QUIRK_PRI_6CHAN, @@ -142,12 +146,12 @@ static int s3c64xx_pcm_cfg_gpio(struct platform_device *pdev) static struct resource s3c64xx_pcm0_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_PCM0, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_PCM0_TX), - [2] = DEFINE_RES_DMA(DMACH_PCM0_RX), }; static struct s3c_audio_pdata s3c_pcm0_pdata = { .cfg_gpio = s3c64xx_pcm_cfg_gpio, + .dma_capture = DMACH_PCM0_RX, + .dma_playback = DMACH_PCM0_TX, }; struct platform_device s3c64xx_device_pcm0 = { @@ -163,12 +167,12 @@ EXPORT_SYMBOL(s3c64xx_device_pcm0); static struct resource s3c64xx_pcm1_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_PCM1, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_PCM1_TX), - [2] = DEFINE_RES_DMA(DMACH_PCM1_RX), }; static struct s3c_audio_pdata s3c_pcm1_pdata = { .cfg_gpio = s3c64xx_pcm_cfg_gpio, + .dma_playback = DMACH_PCM1_TX, + .dma_capture = DMACH_PCM1_RX, }; struct platform_device s3c64xx_device_pcm1 = { @@ -196,13 +200,14 @@ static int s3c64xx_ac97_cfg_gpe(struct platform_device *pdev) static struct resource s3c64xx_ac97_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_AC97, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_AC97_PCMOUT), - [2] = DEFINE_RES_DMA(DMACH_AC97_PCMIN), - [3] = DEFINE_RES_DMA(DMACH_AC97_MICIN), - [4] = DEFINE_RES_IRQ(IRQ_AC97), + [1] = DEFINE_RES_IRQ(IRQ_AC97), }; -static struct s3c_audio_pdata s3c_ac97_pdata; +static struct s3c_audio_pdata s3c_ac97_pdata = { + .dma_playback = DMACH_AC97_PCMOUT, + .dma_capture = DMACH_AC97_PCMIN, + .dma_capture_mic = DMACH_AC97_MICIN, +}; static u64 s3c64xx_ac97_dmamask = DMA_BIT_MASK(32); diff --git a/arch/arm/mach-s3c64xx/include/mach/dma.h b/arch/arm/mach-s3c64xx/include/mach/dma.h index 096e14073bd9..9c739eafe95c 100644 --- a/arch/arm/mach-s3c64xx/include/mach/dma.h +++ b/arch/arm/mach-s3c64xx/include/mach/dma.h @@ -14,38 +14,38 @@ #define S3C64XX_DMA_CHAN(name) ((unsigned long)(name)) /* DMA0/SDMA0 */ -#define DMACH_UART0 S3C64XX_DMA_CHAN("uart0_tx") -#define DMACH_UART0_SRC2 S3C64XX_DMA_CHAN("uart0_rx") -#define DMACH_UART1 S3C64XX_DMA_CHAN("uart1_tx") -#define DMACH_UART1_SRC2 S3C64XX_DMA_CHAN("uart1_rx") -#define DMACH_UART2 S3C64XX_DMA_CHAN("uart2_tx") -#define DMACH_UART2_SRC2 S3C64XX_DMA_CHAN("uart2_rx") -#define DMACH_UART3 S3C64XX_DMA_CHAN("uart3_tx") -#define DMACH_UART3_SRC2 S3C64XX_DMA_CHAN("uart3_rx") -#define DMACH_PCM0_TX S3C64XX_DMA_CHAN("pcm0_tx") -#define DMACH_PCM0_RX S3C64XX_DMA_CHAN("pcm0_rx") -#define DMACH_I2S0_OUT S3C64XX_DMA_CHAN("i2s0_tx") -#define DMACH_I2S0_IN S3C64XX_DMA_CHAN("i2s0_rx") +#define DMACH_UART0 "uart0_tx" +#define DMACH_UART0_SRC2 "uart0_rx" +#define DMACH_UART1 "uart1_tx" +#define DMACH_UART1_SRC2 "uart1_rx" +#define DMACH_UART2 "uart2_tx" +#define DMACH_UART2_SRC2 "uart2_rx" +#define DMACH_UART3 "uart3_tx" +#define DMACH_UART3_SRC2 "uart3_rx" +#define DMACH_PCM0_TX "pcm0_tx" +#define DMACH_PCM0_RX "pcm0_rx" +#define DMACH_I2S0_OUT "i2s0_tx" +#define DMACH_I2S0_IN "i2s0_rx" #define DMACH_SPI0_TX S3C64XX_DMA_CHAN("spi0_tx") #define DMACH_SPI0_RX S3C64XX_DMA_CHAN("spi0_rx") -#define DMACH_HSI_I2SV40_TX S3C64XX_DMA_CHAN("i2s2_tx") -#define DMACH_HSI_I2SV40_RX S3C64XX_DMA_CHAN("i2s2_rx") +#define DMACH_HSI_I2SV40_TX "i2s2_tx" +#define DMACH_HSI_I2SV40_RX "i2s2_rx" /* DMA1/SDMA1 */ -#define DMACH_PCM1_TX S3C64XX_DMA_CHAN("pcm1_tx") -#define DMACH_PCM1_RX S3C64XX_DMA_CHAN("pcm1_rx") -#define DMACH_I2S1_OUT S3C64XX_DMA_CHAN("i2s1_tx") -#define DMACH_I2S1_IN S3C64XX_DMA_CHAN("i2s1_rx") +#define DMACH_PCM1_TX "pcm1_tx" +#define DMACH_PCM1_RX "pcm1_rx" +#define DMACH_I2S1_OUT "i2s1_tx" +#define DMACH_I2S1_IN "i2s1_rx" #define DMACH_SPI1_TX S3C64XX_DMA_CHAN("spi1_tx") #define DMACH_SPI1_RX S3C64XX_DMA_CHAN("spi1_rx") -#define DMACH_AC97_PCMOUT S3C64XX_DMA_CHAN("ac97_out") -#define DMACH_AC97_PCMIN S3C64XX_DMA_CHAN("ac97_in") -#define DMACH_AC97_MICIN S3C64XX_DMA_CHAN("ac97_mic") -#define DMACH_PWM S3C64XX_DMA_CHAN("pwm") -#define DMACH_IRDA S3C64XX_DMA_CHAN("irda") -#define DMACH_EXTERNAL S3C64XX_DMA_CHAN("external") -#define DMACH_SECURITY_RX S3C64XX_DMA_CHAN("sec_rx") -#define DMACH_SECURITY_TX S3C64XX_DMA_CHAN("sec_tx") +#define DMACH_AC97_PCMOUT "ac97_out" +#define DMACH_AC97_PCMIN "ac97_in" +#define DMACH_AC97_MICIN "ac97_mic" +#define DMACH_PWM "pwm" +#define DMACH_IRDA "irda" +#define DMACH_EXTERNAL "external" +#define DMACH_SECURITY_RX "sec_rx" +#define DMACH_SECURITY_TX "sec_tx" enum dma_ch { DMACH_MAX = 32 diff --git a/arch/arm/mach-socfpga/headsmp.S b/arch/arm/mach-socfpga/headsmp.S index 5d94b7a2fb10..c160fa3007e9 100644 --- a/arch/arm/mach-socfpga/headsmp.S +++ b/arch/arm/mach-socfpga/headsmp.S @@ -13,6 +13,7 @@ #include <asm/assembler.h> .arch armv7-a + .arm ENTRY(secondary_trampoline) /* CPU1 will always fetch from 0x0 when it is brought out of reset. diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 82074625de5c..e212f9d804bd 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -65,6 +65,7 @@ #include <linux/platform_data/usb-ohci-s3c2410.h> #include <plat/usb-phy.h> #include <plat/regs-spi.h> +#include <linux/platform_data/asoc-s3c.h> #include <linux/platform_data/spi-s3c64xx.h> static u64 samsung_device_dma_mask = DMA_BIT_MASK(32); @@ -74,9 +75,12 @@ static u64 samsung_device_dma_mask = DMA_BIT_MASK(32); static struct resource s3c_ac97_resource[] = { [0] = DEFINE_RES_MEM(S3C2440_PA_AC97, S3C2440_SZ_AC97), [1] = DEFINE_RES_IRQ(IRQ_S3C244X_AC97), - [2] = DEFINE_RES_DMA_NAMED(DMACH_PCM_OUT, "PCM out"), - [3] = DEFINE_RES_DMA_NAMED(DMACH_PCM_IN, "PCM in"), - [4] = DEFINE_RES_DMA_NAMED(DMACH_MIC_IN, "Mic in"), +}; + +static struct s3c_audio_pdata s3c_ac97_pdata = { + .dma_playback = (void *)DMACH_PCM_OUT, + .dma_capture = (void *)DMACH_PCM_IN, + .dma_capture_mic = (void *)DMACH_MIC_IN, }; struct platform_device s3c_device_ac97 = { @@ -87,6 +91,7 @@ struct platform_device s3c_device_ac97 = { .dev = { .dma_mask = &samsung_device_dma_mask, .coherent_dma_mask = DMA_BIT_MASK(32), + .platform_data = &s3c_ac97_pdata, } }; #endif /* CONFIG_CPU_S3C2440 */ diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index a5c84594f6ad..285b32fa41c1 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -28,6 +28,7 @@ endif KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) KBUILD_CFLAGS += -fno-pic +KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) KBUILD_AFLAGS += $(lseinstr) ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts index 691ddf0d79ce..5d5e240a2b00 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts +++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -28,6 +28,22 @@ stdout-path = "serial3:115200n8"; }; + fiq-debugger { + compatible = "android,irq-hi6220-uart"; + reg = <0x0 0xf7113000 0x0 0x1000>; + interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "fiq", "signal"; + }; + + uart_overlay@0 { + fragment@0 { + target-path="/soc/uart@f7113000"; + __overlay__ { + status = "disabled"; + }; + }; + }; + /* * Reserve below regions from memory node: * diff --git a/arch/arm64/configs/hikey_defconfig b/arch/arm64/configs/hikey_defconfig index d79975cc726b..c2f3f063fb69 100644 --- a/arch/arm64/configs/hikey_defconfig +++ b/arch/arm64/configs/hikey_defconfig @@ -44,7 +44,6 @@ CONFIG_PCI_MSI=y CONFIG_PCI_XGENE=y CONFIG_SCHED_MC=y CONFIG_SCHED_SMT=y -CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y @@ -58,12 +57,14 @@ CONFIG_CMDLINE="console=ttyAMA0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=y CONFIG_COMPAT=y -# CONFIG_SUSPEND is not set -CONFIG_PM=y +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y CONFIG_ARM_CPUIDLE=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE=y +CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPUFREQ_DT=y CONFIG_ARM_HISI_ACPU_CPUFREQ=y CONFIG_NET=y @@ -90,7 +91,6 @@ CONFIG_INET6_AH=y CONFIG_INET6_ESP=y CONFIG_INET6_IPCOMP=y CONFIG_IPV6_MIP6=y -# CONFIG_IPV6_SIT is not set CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NETLABEL=y CONFIG_NETFILTER=y @@ -133,7 +133,9 @@ CONFIG_NETFILTER_XT_MATCH_MAC=y CONFIG_NETFILTER_XT_MATCH_MARK=y CONFIG_NETFILTER_XT_MATCH_POLICY=y CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QTAGUID=y CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_QUOTA2=y CONFIG_NETFILTER_XT_MATCH_SOCKET=y CONFIG_NETFILTER_XT_MATCH_STATE=y CONFIG_NETFILTER_XT_MATCH_STATISTIC=y @@ -147,6 +149,8 @@ CONFIG_IP_NF_MATCH_ECN=y CONFIG_IP_NF_MATCH_TTL=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_TARGET_MASQUERADE=y CONFIG_IP_NF_MANGLE=y CONFIG_IP_NF_RAW=y CONFIG_IP_NF_SECURITY=y @@ -155,10 +159,19 @@ CONFIG_IP_NF_ARPFILTER=y CONFIG_IP_NF_ARP_MANGLE=y CONFIG_NF_CONNTRACK_IPV6=y CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_MATCH_AH=y +CONFIG_IP6_NF_MATCH_EUI64=y +CONFIG_IP6_NF_MATCH_FRAG=y +CONFIG_IP6_NF_MATCH_OPTS=y +CONFIG_IP6_NF_MATCH_HL=y +CONFIG_IP6_NF_MATCH_IPV6HEADER=y +CONFIG_IP6_NF_MATCH_MH=y CONFIG_IP6_NF_FILTER=y CONFIG_IP6_NF_TARGET_REJECT=y CONFIG_IP6_NF_MANGLE=y CONFIG_IP6_NF_RAW=y +CONFIG_IP6_NF_NAT=y +CONFIG_IP6_NF_TARGET_MASQUERADE=y CONFIG_BRIDGE=y CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_VLAN_8021Q=y @@ -394,7 +407,6 @@ CONFIG_LEDS_REGULATOR=y CONFIG_LEDS_SYSCON=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_LEDS_TRIGGER_CPU=y -CONFIG_SWITCH=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_EFI=y CONFIG_RTC_DRV_PL031=y @@ -409,6 +421,12 @@ CONFIG_ANDROID_LOW_MEMORY_KILLER=y CONFIG_SYNC=y CONFIG_ION=y CONFIG_ION_HISI=y +CONFIG_FIQ_DEBUGGER_NO_SLEEP=y +CONFIG_FIQ_DEBUGGER_CONSOLE=y +CONFIG_FIQ_DEBUGGER_CONSOLE_DEFAULT_ENABLE=y +CONFIG_FIQ_DEBUGGER_UART_OVERLAY=y +CONFIG_HISI_FIQ_DEBUGGER=y +CONFIG_STUB_CLK_HI6220=y CONFIG_MAILBOX=y CONFIG_HI6220_MBOX=y # CONFIG_IOMMU_SUPPORT is not set diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h index 4e603ea36ad3..123f45d92cd1 100644 --- a/arch/arm64/include/asm/opcodes.h +++ b/arch/arm64/include/asm/opcodes.h @@ -1 +1,5 @@ +#ifdef CONFIG_CPU_BIG_ENDIAN +#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN +#endif + #include <../../arm/include/asm/opcodes.h> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 63f52b55defe..c63868ae9a4a 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -34,7 +34,7 @@ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. * - * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array + * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array * (rounded up to PUD_SIZE). * VMALLOC_START: beginning of the kernel VA space * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, @@ -51,7 +51,9 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) -#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) +#define VMEMMAP_START (VMALLOC_END + SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL @@ -67,11 +69,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -81,7 +83,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) @@ -153,6 +155,7 @@ extern struct page *empty_zero_page; #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) +#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #ifdef CONFIG_ARM64_HW_AFDBM #define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) @@ -163,8 +166,6 @@ extern struct page *empty_zero_page; #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) -#define pte_valid_user(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) @@ -262,13 +263,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - if (pte_valid_user(pte)) { - if (!pte_special(pte) && pte_exec(pte)) - __sync_icache_dcache(pte, addr); + if (pte_present(pte)) { if (pte_sw_dirty(pte) && pte_write(pte)) pte_val(pte) &= ~PTE_RDONLY; else pte_val(pte) |= PTE_RDONLY; + if (pte_user(pte) && pte_exec(pte) && !pte_special(pte)) + __sync_icache_dcache(pte, addr); } /* @@ -639,6 +640,7 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; * bits 0-1: present (must be zero) * bits 2-7: swap type * bits 8-57: swap offset + * bit 58: PTE_PROT_NONE (must be zero) */ #define __SWP_TYPE_SHIFT 2 #define __SWP_TYPE_BITS 6 diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 8aee3aeec3e6..c1492ba1f6d1 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -186,20 +186,21 @@ static void clear_regs_spsr_ss(struct pt_regs *regs) /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); -static DEFINE_RWLOCK(step_hook_lock); +static DEFINE_SPINLOCK(step_hook_lock); void register_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_add(&hook->node, &step_hook); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_add_rcu(&hook->node, &step_hook); + spin_unlock(&step_hook_lock); } void unregister_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_del(&hook->node); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_del_rcu(&hook->node); + spin_unlock(&step_hook_lock); + synchronize_rcu(); } /* @@ -213,15 +214,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) struct step_hook *hook; int retval = DBG_HOOK_ERROR; - read_lock(&step_hook_lock); + rcu_read_lock(); - list_for_each_entry(hook, &step_hook, node) { + list_for_each_entry_rcu(hook, &step_hook, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - read_unlock(&step_hook_lock); + rcu_read_unlock(); return retval; } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 23cfc08fc8ba..b685257926f0 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -512,9 +512,14 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #endif /* EL2 debug */ + mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x0, #8, #4 + cmp x0, #1 + b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to msr mdcr_el2, x0 // all PMU counters from EL1 +4: /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 5b1897e8ca24..62d3dc60ca09 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -574,9 +574,6 @@ static void armv8pmu_reset(void *info) /* Initialize & Reset PMNC: C and P bits. */ armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C); - - /* Disable access from userspace. */ - asm volatile("msr pmuserenr_el0, %0" :: "r" (0)); } static int armv8_pmuv3_map_event(struct perf_event *event) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1971f491bb90..ff7f13239515 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -58,6 +58,12 @@ */ void ptrace_disable(struct task_struct *child) { + /* + * This would be better off in core code, but PTRACE_DETACH has + * grown its fair share of arch-specific worts and changing it + * is likely to cause regressions on obscure architectures. + */ + user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index d250160d32bc..3039f080e2d5 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -186,7 +186,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } /** diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 6ad554b01e95..ddfb97a299f2 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void) ret = register_iommu_dma_ops_notifier(&platform_bus_type); if (!ret) ret = register_iommu_dma_ops_notifier(&amba_bustype); + + /* handle devices queued before this arch_initcall */ + if (!ret) + __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); return ret; } arch_initcall(__iommu_dma_init); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 325f89ff897e..224238943aff 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -321,8 +321,8 @@ void __init mem_init(void) #endif MLG(VMALLOC_START, VMALLOC_END), #ifdef CONFIG_SPARSEMEM_VMEMMAP - MLG((unsigned long)vmemmap, - (unsigned long)vmemmap + VMEMMAP_SIZE), + MLG(VMEMMAP_START, + VMEMMAP_START + VMEMMAP_SIZE), MLM((unsigned long)virt_to_page(PAGE_OFFSET), (unsigned long)virt_to_page(high_memory)), #endif diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 873e363048c6..116ad654dd59 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -456,6 +456,9 @@ void __init paging_init(void) empty_zero_page = virt_to_page(zero_page); + /* Ensure the zero page is visible to the page table walker */ + dsb(ishst); + /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 3571c7309c5e..cf6240741134 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages, if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; + if (!numpages) + return 0; + data.set_mask = set_mask; data.clear_mask = clear_mask; diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index 4c4d93c4bf65..d69dffffaa89 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -62,3 +62,15 @@ bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH #endif .endm + +/* + * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present + */ + .macro reset_pmuserenr_el0, tmpreg + mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx \tmpreg, \tmpreg, #8, #4 + cmp \tmpreg, #1 // Skip if no PMU present + b.lt 9000f + msr pmuserenr_el0, xzr // Disable PMU access from EL0 +9000: + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index cacecc4ad3e5..b8f04b3f2786 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -117,6 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -155,6 +156,7 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h index 9041bbe2b7b4..8fdb9c7eeb66 100644 --- a/arch/ia64/include/asm/io.h +++ b/arch/ia64/include/asm/io.h @@ -436,6 +436,7 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo return ioremap(phys_addr, size); } #define ioremap_cache ioremap_cache +#define ioremap_uc ioremap_nocache /* diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index 0392112a5d70..a5ecef7188ba 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -81,7 +81,10 @@ static struct resource code_resource = { }; unsigned long memory_start; +EXPORT_SYMBOL(memory_start); + unsigned long memory_end; +EXPORT_SYMBOL(memory_end); void __init setup_arch(char **); int get_cpuinfo(char *); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 71683a853372..db459612de44 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2155,7 +2155,7 @@ config MIPS_MT_SMP select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI select SYNC_R4K - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select MIPS_MT select SMP select SMP_UP @@ -2253,7 +2253,7 @@ config MIPS_VPE_APSP_API_MT config MIPS_CMP bool "MIPS CMP framework support (DEPRECATED)" depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K select SYS_SUPPORTS_SMP @@ -2273,7 +2273,7 @@ config MIPS_CPS select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU @@ -2292,6 +2292,7 @@ config MIPS_CPS_PM bool config MIPS_GIC_IPI + depends on MIPS_GIC bool config MIPS_CM diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c index bdeed9d13c6f..433c4b9a9f0a 100644 --- a/arch/mips/alchemy/devboards/db1000.c +++ b/arch/mips/alchemy/devboards/db1000.c @@ -503,15 +503,15 @@ int __init db1000_dev_setup(void) if (board == BCSR_WHOAMI_DB1500) { c0 = AU1500_GPIO2_INT; c1 = AU1500_GPIO5_INT; - d0 = AU1500_GPIO0_INT; - d1 = AU1500_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1500_GPIO1_INT; s1 = AU1500_GPIO4_INT; } else if (board == BCSR_WHOAMI_DB1100) { c0 = AU1100_GPIO2_INT; c1 = AU1100_GPIO5_INT; - d0 = AU1100_GPIO0_INT; - d1 = AU1100_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1100_GPIO1_INT; s1 = AU1100_GPIO4_INT; @@ -545,15 +545,15 @@ int __init db1000_dev_setup(void) } else if (board == BCSR_WHOAMI_DB1000) { c0 = AU1000_GPIO2_INT; c1 = AU1000_GPIO5_INT; - d0 = AU1000_GPIO0_INT; - d1 = AU1000_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1000_GPIO1_INT; s1 = AU1000_GPIO4_INT; platform_add_devices(db1000_devs, ARRAY_SIZE(db1000_devs)); } else if ((board == BCSR_WHOAMI_PB1500) || (board == BCSR_WHOAMI_PB1500R2)) { c0 = AU1500_GPIO203_INT; - d0 = AU1500_GPIO201_INT; + d0 = 1; /* GPIO number, NOT irq! */ s0 = AU1500_GPIO202_INT; twosocks = 0; flashsize = 64; @@ -566,7 +566,7 @@ int __init db1000_dev_setup(void) */ } else if (board == BCSR_WHOAMI_PB1100) { c0 = AU1100_GPIO11_INT; - d0 = AU1100_GPIO9_INT; + d0 = 9; /* GPIO number, NOT irq! */ s0 = AU1100_GPIO10_INT; twosocks = 0; flashsize = 64; @@ -583,7 +583,6 @@ int __init db1000_dev_setup(void) } else return 0; /* unknown board, no further dev setup to do */ - irq_set_irq_type(d0, IRQ_TYPE_EDGE_BOTH); irq_set_irq_type(c0, IRQ_TYPE_LEVEL_LOW); irq_set_irq_type(s0, IRQ_TYPE_LEVEL_LOW); @@ -597,7 +596,6 @@ int __init db1000_dev_setup(void) c0, d0, /*s0*/0, 0, 0); if (twosocks) { - irq_set_irq_type(d1, IRQ_TYPE_EDGE_BOTH); irq_set_irq_type(c1, IRQ_TYPE_LEVEL_LOW); irq_set_irq_type(s1, IRQ_TYPE_LEVEL_LOW); diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c index 5740bcfdfc7f..6c37b9326f41 100644 --- a/arch/mips/alchemy/devboards/db1550.c +++ b/arch/mips/alchemy/devboards/db1550.c @@ -514,7 +514,7 @@ static void __init db1550_devices(void) AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1, AU1000_PCMCIA_IO_PHYS_ADDR, AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1, - AU1550_GPIO3_INT, AU1550_GPIO0_INT, + AU1550_GPIO3_INT, 0, /*AU1550_GPIO21_INT*/0, 0, 0); db1x_register_pcmcia_socket( @@ -524,7 +524,7 @@ static void __init db1550_devices(void) AU1000_PCMCIA_MEM_PHYS_ADDR + 0x004400000 - 1, AU1000_PCMCIA_IO_PHYS_ADDR + 0x004000000, AU1000_PCMCIA_IO_PHYS_ADDR + 0x004010000 - 1, - AU1550_GPIO5_INT, AU1550_GPIO1_INT, + AU1550_GPIO5_INT, 1, /*AU1550_GPIO22_INT*/0, 0, 1); platform_device_register(&db1550_nand_dev); diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 2046c0230224..21ed7150fec3 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -33,7 +33,7 @@ #define PAGE_SHIFT 16 #endif #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) +#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1)) /* * This is used for calculating the real page sizes diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 8957f15e21ec..18826aa15a7c 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -353,7 +353,7 @@ static inline pte_t pte_mkdirty(pte_t pte) static inline pte_t pte_mkyoung(pte_t pte) { pte_val(pte) |= _PAGE_ACCESSED; -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (!(pte_val(pte) & _PAGE_NO_READ)) pte_val(pte) |= _PAGE_SILENT_READ; else @@ -560,7 +560,7 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) { pmd_val(pmd) |= _PAGE_ACCESSED; -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (!(pmd_val(pmd) & _PAGE_NO_READ)) pmd_val(pmd) |= _PAGE_SILENT_READ; else diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 6499d93ae68d..47bc45a67e9b 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task, /* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */ if ((config_enabled(CONFIG_32BIT) || test_tsk_thread_flag(task, TIF_32BIT_REGS)) && - (regs->regs[2] == __NR_syscall)) { + (regs->regs[2] == __NR_syscall)) i++; - n++; - } while (n--) ret |= mips_get_syscall_arg(args++, task, regs, i++); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index bd4385a8e6e8..2b521e07b860 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -121,6 +121,7 @@ static inline void calculate_cpu_foreign_map(void) cpumask_t temp_foreign_map; /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); for_each_online_cpu(i) { core_present = 0; for_each_cpu(k, &temp_foreign_map) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 886cb1976e90..ca9a81007489 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -690,15 +690,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode) asmlinkage void do_ov(struct pt_regs *regs) { enum ctx_state prev_state; - siginfo_t info; + siginfo_t info = { + .si_signo = SIGFPE, + .si_code = FPE_INTOVF, + .si_addr = (void __user *)regs->cp0_epc, + }; prev_state = exception_enter(); die_if_kernel("Integer overflow", regs); - info.si_code = FPE_INTOVF; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); exception_exit(prev_state); } @@ -874,7 +874,7 @@ out: void do_trap_or_bp(struct pt_regs *regs, unsigned int code, const char *str) { - siginfo_t info; + siginfo_t info = { 0 }; char b[40]; #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP @@ -903,7 +903,6 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, else info.si_code = FPE_INTOVF; info.si_signo = SIGFPE; - info.si_errno = 0; info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); break; diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 490cea569d57..5c62065cbf22 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -885,7 +885,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, { union mips_instruction insn; unsigned long value; - unsigned int res; + unsigned int res, preempted; unsigned long origpc; unsigned long orig31; void __user *fault_addr = NULL; @@ -1226,27 +1226,36 @@ static void emulate_load_store_insn(struct pt_regs *regs, if (!access_ok(VERIFY_READ, addr, sizeof(*fpr))) goto sigbus; - /* - * Disable preemption to avoid a race between copying - * state from userland, migrating to another CPU and - * updating the hardware vector register below. - */ - preempt_disable(); - - res = __copy_from_user_inatomic(fpr, addr, - sizeof(*fpr)); - if (res) - goto fault; - - /* - * Update the hardware register if it is in use by the - * task in this quantum, in order to avoid having to - * save & restore the whole vector context. - */ - if (test_thread_flag(TIF_USEDMSA)) - write_msa_wr(wd, fpr, df); + do { + /* + * If we have live MSA context keep track of + * whether we get preempted in order to avoid + * the register context we load being clobbered + * by the live context as it's saved during + * preemption. If we don't have live context + * then it can't be saved to clobber the value + * we load. + */ + preempted = test_thread_flag(TIF_USEDMSA); + + res = __copy_from_user_inatomic(fpr, addr, + sizeof(*fpr)); + if (res) + goto fault; - preempt_enable(); + /* + * Update the hardware register if it is in use + * by the task in this quantum, in order to + * avoid having to save & restore the whole + * vector context. + */ + preempt_disable(); + if (test_thread_flag(TIF_USEDMSA)) { + write_msa_wr(wd, fpr, df); + preempted = 0; + } + preempt_enable(); + } while (preempted); break; case msa_st_op: diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b9b803facdbf..2683d04fdda5 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_to_user(uaddr, vs, 16); + return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0; } else { return -EINVAL; } @@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_from_user(vs, uaddr, 16); + return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0; } else { return -EINVAL; } diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c index bf9f1a77f0e5..a2631a52ca99 100644 --- a/arch/mips/loongson64/loongson-3/hpet.c +++ b/arch/mips/loongson64/loongson-3/hpet.c @@ -13,6 +13,9 @@ #define SMBUS_PCI_REG64 0x64 #define SMBUS_PCI_REGB4 0xb4 +#define HPET_MIN_CYCLES 64 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) + static DEFINE_SPINLOCK(hpet_lock); DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device); @@ -161,8 +164,9 @@ static int hpet_next_event(unsigned long delta, cnt += delta; hpet_write(HPET_T0_CMP, cnt); - res = ((int)(hpet_read(HPET_COUNTER) - cnt) > 0) ? -ETIME : 0; - return res; + res = (int)(cnt - hpet_read(HPET_COUNTER)); + + return res < HPET_MIN_CYCLES ? -ETIME : 0; } static irqreturn_t hpet_irq_handler(int irq, void *data) @@ -237,7 +241,7 @@ void __init setup_hpet_timer(void) cd->cpumask = cpumask_of(cpu); clockevent_set_clock(cd, HPET_FREQ); cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd); - cd->min_delta_ns = 5000; + cd->min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, cd); clockevents_register_device(cd); setup_irq(HPET_T0_IRQ, &hpet_irq); diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 1a4738a8f2d3..509832a9836c 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -30,13 +30,13 @@ #include "smp.h" DEFINE_PER_CPU(int, cpu_state); -DEFINE_PER_CPU(uint32_t, core0_c0count); static void *ipi_set0_regs[16]; static void *ipi_clear0_regs[16]; static void *ipi_status0_regs[16]; static void *ipi_en0_regs[16]; static void *ipi_mailbox_buf[16]; +static uint32_t core0_c0count[NR_CPUS]; /* read a 32bit value from ipi register */ #define loongson3_ipi_read32(addr) readl(addr) @@ -275,12 +275,14 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) if (action & SMP_ASK_C0COUNT) { BUG_ON(cpu != 0); c0count = read_c0_count(); - for (i = 1; i < num_possible_cpus(); i++) - per_cpu(core0_c0count, i) = c0count; + c0count = c0count ? c0count : 1; + for (i = 1; i < nr_cpu_ids; i++) + core0_c0count[i] = c0count; + __wbflush(); /* Let others see the result ASAP */ } } -#define MAX_LOOPS 1111 +#define MAX_LOOPS 800 /* * SMP init and finish on secondary CPUs */ @@ -305,16 +307,20 @@ static void loongson3_init_secondary(void) cpu_logical_map(cpu) / loongson_sysconf.cores_per_package; i = 0; - __this_cpu_write(core0_c0count, 0); + core0_c0count[cpu] = 0; loongson3_send_ipi_single(0, SMP_ASK_C0COUNT); - while (!__this_cpu_read(core0_c0count)) { + while (!core0_c0count[cpu]) { i++; cpu_relax(); } if (i > MAX_LOOPS) i = MAX_LOOPS; - initcount = __this_cpu_read(core0_c0count) + i; + if (cpu_data[cpu].package) + initcount = core0_c0count[cpu] + i; + else /* Local access is faster for loops */ + initcount = core0_c0count[cpu] + i/2; + write_c0_count(initcount); } diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 3bd0597d9c3d..ddb8154610cc 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -164,11 +164,13 @@ static int __init mips_sc_probe_cm3(void) sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK; sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF; - c->scache.sets = 64 << sets; + if (sets) + c->scache.sets = 64 << sets; line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK; line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF; - c->scache.linesz = 2 << line_sz; + if (line_sz) + c->scache.linesz = 2 << line_sz; assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK; assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF; @@ -176,9 +178,12 @@ static int __init mips_sc_probe_cm3(void) c->scache.waysize = c->scache.sets * c->scache.linesz; c->scache.waybit = __ffs(c->scache.waysize); - c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + if (c->scache.linesz) { + c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + return 1; + } - return 1; + return 0; } void __weak platform_early_l2_init(void) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 32e0be27673f..29f73e00253d 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -242,7 +242,7 @@ static void output_pgtable_bits_defines(void) pr_define("_PAGE_HUGE_SHIFT %d\n", _PAGE_HUGE_SHIFT); pr_define("_PAGE_SPLITTING_SHIFT %d\n", _PAGE_SPLITTING_SHIFT); #endif -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (cpu_has_rixi) { #ifdef _PAGE_NO_EXEC_SHIFT pr_define("_PAGE_NO_EXEC_SHIFT %d\n", _PAGE_NO_EXEC_SHIFT); diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index 7d56a9ccb752..a65d888716c4 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -54,24 +54,12 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) return pte_wrprotect(pte); } -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - pte_t old_pte = *ptep; - set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); -} +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, +int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) -{ - int changed = !pte_same(*ptep, pte); - if (changed) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); - flush_tlb_page(vma, addr); - } - return changed; -} + pte_t pte, int dirty); static inline pte_t huge_ptep_get(pte_t *ptep) { diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0abdd4c607ed..1960b87c1c8b 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -76,6 +76,7 @@ struct exception_table_entry { */ struct exception_data { unsigned long fault_ip; + unsigned long fault_gp; unsigned long fault_space; unsigned long fault_addr; }; diff --git a/arch/parisc/include/uapi/asm/siginfo.h b/arch/parisc/include/uapi/asm/siginfo.h index d7034728f377..1c75565d984b 100644 --- a/arch/parisc/include/uapi/asm/siginfo.h +++ b/arch/parisc/include/uapi/asm/siginfo.h @@ -1,6 +1,10 @@ #ifndef _PARISC_SIGINFO_H #define _PARISC_SIGINFO_H +#if defined(__LP64__) +#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) +#endif + #include <asm-generic/siginfo.h> #undef NSIGTRAP diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index d2f62570a7b1..78d30d2ea2d8 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -299,6 +299,7 @@ int main(void) #endif BLANK(); DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); + DEFINE(EXCDATA_GP, offsetof(struct exception_data, fault_gp)); DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); BLANK(); diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 568b2c61ea02..3cad8aadc69e 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -47,11 +47,11 @@ EXPORT_SYMBOL(__cmpxchg_u64); EXPORT_SYMBOL(lclear_user); EXPORT_SYMBOL(lstrnlen_user); -/* Global fixups */ -extern void fixup_get_user_skip_1(void); -extern void fixup_get_user_skip_2(void); -extern void fixup_put_user_skip_1(void); -extern void fixup_put_user_skip_2(void); +/* Global fixups - defined as int to avoid creation of function pointers */ +extern int fixup_get_user_skip_1; +extern int fixup_get_user_skip_2; +extern int fixup_put_user_skip_1; +extern int fixup_put_user_skip_2; EXPORT_SYMBOL(fixup_get_user_skip_1); EXPORT_SYMBOL(fixup_get_user_skip_2); EXPORT_SYMBOL(fixup_put_user_skip_1); diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9585c81f755f..ce0b2b4075c7 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - /* Do the secure computing check first. */ secure_computing_strict(regs->gr[20]); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - ret = -1L; + tracehook_report_syscall_entry(regs)) { + /* + * Tracing decided this syscall should not happen or the + * debugger stored an invalid system call number. Skip + * the system call and the system call restart handling. + */ + regs->gr[20] = -1UL; + goto out; + } #ifdef CONFIG_64BIT if (!is_compat_task()) @@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[24] & 0xffffffff, regs->gr[23] & 0xffffffff); - return ret ? : regs->gr[20]; +out: + return regs->gr[20]; } void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 3fbd7252a4b2..fbafa0d0e2bf 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -343,7 +343,7 @@ tracesys_next: #endif comiclr,>>= __NR_Linux_syscalls, %r20, %r0 - b,n .Lsyscall_nosys + b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 @@ -359,6 +359,9 @@ tracesys_next: be 0(%sr7,%r19) ldo R%tracesys_exit(%r2),%r2 +.Ltracesys_nosys: + ldo -ENOSYS(%r0),%r28 /* set errno */ + /* Do *not* call this function on the gateway page, because it makes a direct call to syscall_trace. */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 553b09855cfd..77e2262c97f6 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -798,6 +798,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs) if (fault_space == 0 && !faulthandler_disabled()) { + /* Clean up and return if in exception table. */ + if (fixup_exception(regs)) + return; pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC); parisc_terminate("Kernel Fault", regs, code, fault_address); } diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S index 536ef66bb94b..1052b747e011 100644 --- a/arch/parisc/lib/fixup.S +++ b/arch/parisc/lib/fixup.S @@ -26,6 +26,7 @@ #ifdef CONFIG_SMP .macro get_fault_ip t1 t2 + loadgp addil LT%__per_cpu_offset,%r27 LDREG RT%__per_cpu_offset(%r1),\t1 /* t2 = smp_processor_id() */ @@ -40,14 +41,19 @@ LDREG RT%exception_data(%r1),\t1 /* t1 = this_cpu_ptr(&exception_data) */ add,l \t1,\t2,\t1 + /* %r27 = t1->fault_gp - restore gp */ + LDREG EXCDATA_GP(\t1), %r27 /* t1 = t1->fault_ip */ LDREG EXCDATA_IP(\t1), \t1 .endm #else .macro get_fault_ip t1 t2 + loadgp /* t1 = this_cpu_ptr(&exception_data) */ addil LT%exception_data,%r27 LDREG RT%exception_data(%r1),\t2 + /* %r27 = t2->fault_gp - restore gp */ + LDREG EXCDATA_GP(\t2), %r27 /* t1 = t2->fault_ip */ LDREG EXCDATA_IP(\t2), \t1 .endm diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index a762864ec92e..f9064449908a 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -151,6 +151,7 @@ int fixup_exception(struct pt_regs *regs) struct exception_data *d; d = this_cpu_ptr(&exception_data); d->fault_ip = regs->iaoq[0]; + d->fault_gp = regs->gr[27]; d->fault_space = regs->isr; d->fault_addr = regs->ior; diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index f6fdc77a72bd..54ba39262b82 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -105,15 +105,13 @@ static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long ad addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT; for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) { - mtsp(mm->context, 1); - pdtlb(addr); - if (unlikely(split_tlb)) - pitlb(addr); + purge_tlb_entries(mm, addr); addr += (1UL << REAL_HPAGE_SHIFT); } } -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, +/* __set_huge_pte_at() must be called holding the pa_tlb_lock. */ +static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { unsigned long addr_start; @@ -123,14 +121,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, addr_start = addr; for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - /* Directly write pte entry. We could call set_pte_at(mm, addr, ptep, entry) - * instead, but then we get double locking on pa_tlb_lock. */ - *ptep = entry; + set_pte(ptep, entry); ptep++; - /* Drop the PAGE_SIZE/non-huge tlb entry */ - purge_tlb_entries(mm, addr); - addr += PAGE_SIZE; pte_val(entry) += PAGE_SIZE; } @@ -138,18 +131,61 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, purge_tlb_entries_huge(mm, addr_start); } +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) +{ + unsigned long flags; + + purge_tlb_start(flags); + __set_huge_pte_at(mm, addr, ptep, entry); + purge_tlb_end(flags); +} + pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { + unsigned long flags; pte_t entry; + purge_tlb_start(flags); entry = *ptep; - set_huge_pte_at(mm, addr, ptep, __pte(0)); + __set_huge_pte_at(mm, addr, ptep, __pte(0)); + purge_tlb_end(flags); return entry; } + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long flags; + pte_t old_pte; + + purge_tlb_start(flags); + old_pte = *ptep; + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); + purge_tlb_end(flags); +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + unsigned long flags; + int changed; + + purge_tlb_start(flags); + changed = !pte_same(*ptep, pte); + if (changed) { + __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + } + purge_tlb_end(flags); + return changed; +} + + int pmd_huge(pmd_t pmd) { return 0; diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index ad6263cffb0f..d1a8d93cccfd 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -18,12 +18,12 @@ __xchg_u32(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stwcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned int *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -61,12 +61,12 @@ __xchg_u64(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stdcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned long *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -151,14 +151,14 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) unsigned int prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" PPC405_ERR77(0,%2) " stwcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) @@ -197,13 +197,13 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new) unsigned long prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 # __cmpxchg_u64\n\ cmpd 0,%0,%3\n\ bne- 2f\n\ stdcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index c5eb86f3d452..867c39b45df6 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -81,6 +81,7 @@ struct pci_dn; #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ #define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */ #define EEH_PE_REMOVED (1 << 10) /* Removed permanently */ +#define EEH_PE_PRI_BUS (1 << 11) /* Cached primary bus */ struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 8374afed9d0a..f8faaaeeca1e 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -157,7 +157,8 @@ #define OPAL_LEDS_GET_INDICATOR 114 #define OPAL_LEDS_SET_INDICATOR 115 #define OPAL_CEC_REBOOT2 116 -#define OPAL_LAST 116 +#define OPAL_CONSOLE_FLUSH 117 +#define OPAL_LAST 117 /* Device tree flags */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 800115910e43..07a99e638449 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -35,6 +35,7 @@ int64_t opal_console_read(int64_t term_number, __be64 *length, uint8_t *buffer); int64_t opal_console_write_buffer_space(int64_t term_number, __be64 *length); +int64_t opal_console_flush(int64_t term_number); int64_t opal_rtc_read(__be32 *year_month_day, __be64 *hour_minute_second_millisecond); int64_t opal_rtc_write(uint32_t year_month_day, @@ -262,6 +263,8 @@ extern int opal_resync_timebase(void); extern void opal_lpc_init(void); +extern void opal_kmsg_init(void); + extern int opal_event_request(unsigned int opal_event_nr); struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index e682a7143edb..c50868681f9e 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -44,7 +44,7 @@ static inline void isync(void) MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup); #define PPC_ACQUIRE_BARRIER "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER) #define PPC_RELEASE_BARRIER stringify_in_c(LWSYNC) "\n" -#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n" +#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(sync) "\n" #define PPC_ATOMIC_EXIT_BARRIER "\n" stringify_in_c(sync) "\n" #else #define PPC_ACQUIRE_BARRIER diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index e4396a7d0f7c..4afe66aa1400 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -82,7 +82,7 @@ static inline unsigned long create_zero_mask(unsigned long bits) "andc %1,%1,%2\n\t" "popcntd %0,%1" : "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask) - : "r" (bits)); + : "b" (bits)); return leading_zero_bits; } diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 43686043e297..2734c005da21 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -31,6 +31,7 @@ #define PPC_FEATURE_PSERIES_PERFMON_COMPAT \ 0x00000040 +/* Reserved - do not use 0x00000004 */ #define PPC_FEATURE_TRUE_LE 0x00000002 #define PPC_FEATURE_PPC_LE 0x00000001 diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 59dad113897b..c2d21d11c2d2 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -295,6 +295,8 @@ do { \ #define R_PPC64_TLSLD 108 #define R_PPC64_TOCSAVE 109 +#define R_PPC64_ENTRY 118 + #define R_PPC64_REL16 249 #define R_PPC64_REL16_LO 250 #define R_PPC64_REL16_HI 251 diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 8d14feb40f12..52c1e273f8cd 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata) eeh_pcid_put(dev); if (driver->err_handler && driver->err_handler->error_detected && - driver->err_handler->slot_reset && - driver->err_handler->resume) + driver->err_handler->slot_reset) return NULL; } @@ -564,6 +563,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); pci_unlock_rescan_remove(); @@ -803,6 +803,7 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); @@ -886,6 +887,7 @@ static void eeh_handle_special_event(void) continue; /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 8654cb166c19..98f81800e00c 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); - struct device_node *dn = pci_bus_to_OF_node(bus); + struct device_node *dn; const char *loc = NULL; - if (!dn) - goto out; + while (bus) { + dn = pci_bus_to_OF_node(bus); + if (!dn) { + bus = bus->parent; + continue; + } - /* PHB PE or root PE ? */ - if (pci_is_root_bus(bus)) { - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) + if (pci_is_root_bus(bus)) loc = of_get_property(dn, "ibm,io-base-loc-code", NULL); + else + loc = of_get_property(dn, "ibm,slot-location-code", + NULL); + if (loc) - goto out; + return loc; - /* Check the root port */ - dn = dn->child; - if (!dn) - goto out; + bus = bus->parent; } - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) - loc = of_get_property(dn, "ibm,slot-location-code", NULL); - -out: - return loc ? loc : "N/A"; + return "N/A"; } /** @@ -931,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) bus = pe->phb->bus; } else if (pe->type & EEH_PE_BUS || pe->type & EEH_PE_DEVICE) { - if (pe->bus) { + if (pe->state & EEH_PE_PRI_BUS) { bus = pe->bus; goto out; } diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 68384514506b..e4f7d4eed20c 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -335,7 +335,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) if (syms[i].st_shndx == SHN_UNDEF) { char *name = strtab + syms[i].st_name; if (name[0] == '.') - memmove(name, name+1, strlen(name)); + syms[i].st_name++; } } } @@ -635,6 +635,33 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, */ break; + case R_PPC64_ENTRY: + /* + * Optimize ELFv2 large code model entry point if + * the TOC is within 2GB range of current location. + */ + value = my_r2(sechdrs, me) - (unsigned long)location; + if (value + 0x80008000 > 0xffffffff) + break; + /* + * Check for the large code model prolog sequence: + * ld r2, ...(r12) + * add r2, r2, r12 + */ + if ((((uint32_t *)location)[0] & ~0xfffc) + != 0xe84c0000) + break; + if (((uint32_t *)location)[1] != 0x7c426214) + break; + /* + * If found, replace it with: + * addis r2, r12, (.TOC.-func)@ha + * addi r2, r12, (.TOC.-func)@l + */ + ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); + ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); + break; + case R_PPC64_REL16_HA: /* Subtract location pointer */ value -= (unsigned long)location; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 7030b035905d..a15fe1d4e84a 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -148,23 +148,25 @@ static struct ibm_pa_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ + unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */ unsigned char pabyte; /* byte number in ibm,pa-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ } ibm_pa_features[] __initdata = { - {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, - {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, - {CPU_FTR_CTRL, 0, 0, 0, 3, 0}, - {CPU_FTR_NOEXECUTE, 0, 0, 0, 6, 0}, - {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, - {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, - {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, + {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0, 0}, + {0, 0, PPC_FEATURE_HAS_FPU, 0, 0, 1, 0}, + {CPU_FTR_CTRL, 0, 0, 0, 0, 3, 0}, + {CPU_FTR_NOEXECUTE, 0, 0, 0, 0, 6, 0}, + {CPU_FTR_NODSISRALIGN, 0, 0, 0, 1, 1, 1}, + {0, MMU_FTR_CI_LARGE_PAGE, 0, 0, 1, 2, 0}, + {CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0}, /* - * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n), - * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP - * which is 0 if the kernel doesn't support TM. + * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n), + * we don't want to turn on TM here, so we use the *_COMP versions + * which are 0 if the kernel doesn't support TM. */ - {CPU_FTR_TM_COMP, 0, 0, 22, 0, 0}, + {CPU_FTR_TM_COMP, 0, 0, + PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -195,10 +197,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs, if (bit ^ fp->invert) { cur_cpu_spec->cpu_features |= fp->cpu_features; cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features |= fp->mmu_features; } else { cur_cpu_spec->cpu_features &= ~fp->cpu_features; cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features &= ~fp->mmu_features; } } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 3c6badcd53ef..463af88c95a2 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1370,6 +1370,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6, VCPU_ACOP(r9) stw r7, VCPU_GUEST_PID(r9) std r8, VCPU_WORT(r9) + /* + * Restore various registers to 0, where non-zero values + * set by the guest could disrupt the host. + */ + li r0, 0 + mtspr SPRN_IAMR, r0 + mtspr SPRN_CIABR, r0 + mtspr SPRN_DAWRX, r0 + mtspr SPRN_TCSCR, r0 + mtspr SPRN_WORT, r0 + /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ + li r0, 1 + sldi r0, r0, 31 + mtspr SPRN_MMCRS, r0 8: /* Save and reset AMR and UAMOR before turning on the MMU */ @@ -2153,7 +2167,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */ 2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW - rlwimi r5, r4, 1, DAWRX_WT + rlwimi r5, r4, 2, DAWRX_WT clrrdi r4, r4, 3 std r4, VCPU_DAWR(r3) std r5, VCPU_DAWRX(r3) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6fd2405c7f4a..a3b182dcb823 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: - if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { - r = -ENXIO; - break; - } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ default: @@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ default: diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 9833fee493ec..807f1594701d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -486,13 +486,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = this_cpu_ptr(&hugepd_freelist_cur); + batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))) { kmem_cache_free(hugepte_cache, hugepte); - put_cpu_var(hugepd_freelist_cur); + put_cpu_var(hugepd_freelist_cur); return; } diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 1c8cdb6250e7..b9de7ef48849 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -2,6 +2,7 @@ obj-y += setup.o opal-wrappers.o opal.o opal-async.o idle.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o +obj-y += opal-kmsg.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e1c90725522a..2ba602591a20 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * PCI devices of the PE are expected to be removed prior * to PE reset. */ - if (!edev->pe->bus) + if (!(edev->pe->state & EEH_PE_PRI_BUS)) { edev->pe->bus = pci_find_bus(hose->global_number, pdn->busno); + if (edev->pe->bus) + edev->pe->state |= EEH_PE_PRI_BUS; + } /* * Enable EEH explicitly so that we will do EEH check diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c new file mode 100644 index 000000000000..6f1214d4de92 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-kmsg.c @@ -0,0 +1,75 @@ +/* + * kmsg dumper that ensures the OPAL console fully flushes panic messages + * + * Author: Russell Currey <ruscur@russell.cc> + * + * Copyright 2015 IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/kmsg_dump.h> + +#include <asm/opal.h> +#include <asm/opal-api.h> + +/* + * Console output is controlled by OPAL firmware. The kernel regularly calls + * OPAL_POLL_EVENTS, which flushes some console output. In a panic state, + * however, the kernel no longer calls OPAL_POLL_EVENTS and the panic message + * may not be completely printed. This function does not actually dump the + * message, it just ensures that OPAL completely flushes the console buffer. + */ +static void force_opal_console_flush(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + int i; + int64_t ret; + + /* + * Outside of a panic context the pollers will continue to run, + * so we don't need to do any special flushing. + */ + if (reason != KMSG_DUMP_PANIC) + return; + + if (opal_check_token(OPAL_CONSOLE_FLUSH)) { + ret = opal_console_flush(0); + + if (ret == OPAL_UNSUPPORTED || ret == OPAL_PARAMETER) + return; + + /* Incrementally flush until there's nothing left */ + while (opal_console_flush(0) != OPAL_SUCCESS); + } else { + /* + * If OPAL_CONSOLE_FLUSH is not implemented in the firmware, + * the console can still be flushed by calling the polling + * function enough times to flush the buffer. We don't know + * how much output still needs to be flushed, but we can be + * generous since the kernel is in panic and doesn't need + * to do much else. + */ + printk(KERN_NOTICE "opal: OPAL_CONSOLE_FLUSH missing.\n"); + for (i = 0; i < 1024; i++) { + opal_poll_events(NULL); + } + } +} + +static struct kmsg_dumper opal_kmsg_dumper = { + .dump = force_opal_console_flush +}; + +void __init opal_kmsg_init(void) +{ + int rc; + + /* Add our dumper to the list */ + rc = kmsg_dump_register(&opal_kmsg_dumper); + if (rc != 0) + pr_err("opal: kmsg_dump_register failed; returned %d\n", rc); +} diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index b7a464fef7a7..e45b88a5d7e0 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -301,3 +301,4 @@ OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); OPAL_CALL(opal_prd_msg, OPAL_PRD_MSG); OPAL_CALL(opal_leds_get_ind, OPAL_LEDS_GET_INDICATOR); OPAL_CALL(opal_leds_set_ind, OPAL_LEDS_SET_INDICATOR); +OPAL_CALL(opal_console_flush, OPAL_CONSOLE_FLUSH); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 57cffb80bc36..ae29eaf85e9e 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -758,6 +758,9 @@ static int __init opal_init(void) opal_pdev_init(opal_node, "ibm,opal-flash"); opal_pdev_init(opal_node, "ibm,opal-prd"); + /* Initialise OPAL kmsg dumper for flushing console on panic */ + opal_kmsg_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 414fd1a00fda..e40d0714679e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3034,6 +3034,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, + .dma_bus_setup = pnv_pci_dma_bus_setup, #ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index f2dd77234240..ad8c3f4a5e0b 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -601,6 +601,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages, u64 rpn = __pa(uaddr) >> tbl->it_page_shift; long i; + if (proto_tce & TCE_PCI_WRITE) + proto_tce |= TCE_PCI_READ; + for (i = 0; i < npages; i++) { unsigned long newtce = proto_tce | ((rpn + i) << tbl->it_page_shift); @@ -622,6 +625,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index, BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl)); + if (newtce & TCE_PCI_WRITE) + newtce |= TCE_PCI_READ; + oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce)); *hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE); *direction = iommu_tce_direction(oldtce); @@ -762,6 +768,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev) phb->dma_dev_setup(phb, pdev); } +void pnv_pci_dma_bus_setup(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pe; + + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))) + continue; + + if (!pe->pbus) + continue; + + if (bus->number == ((pe->rid >> 8) & 0xFF)) { + pe->pbus = bus; + break; + } + } +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index c8ff50e90766..36a99feab7d8 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -235,6 +235,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev); +extern void pnv_pci_dma_bus_setup(struct pci_bus *bus); extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h index 2559b16da525..17d9dcd29d45 100644 --- a/arch/s390/include/asm/fpu/internal.h +++ b/arch/s390/include/asm/fpu/internal.h @@ -48,6 +48,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) { fpregs->pad = 0; + fpregs->fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); else @@ -57,6 +58,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) { + fpu->fpc = fpregs->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); else diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index efaac2c3bb77..e9a983f40a24 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -506,7 +506,6 @@ struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; unsigned int host_acrs[NUM_ACRS]; struct fpu host_fpregs; - struct fpu guest_fpregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index fb1b93ea3e3f..e485817f7b1a 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -15,17 +15,25 @@ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + spin_lock_init(&mm->context.list_lock); + INIT_LIST_HEAD(&mm->context.pgtable_list); + INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.attach_count, 0); mm->context.flush_mm = 0; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; - mm->context.asce_bits |= _ASCE_TYPE_REGION3; #ifdef CONFIG_PGSTE mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - mm->context.asce_limit = STACK_TOP_MAX; + if (mm->context.asce_limit == 0) { + /* context created by exec, set asce limit to 4TB */ + mm->context.asce_bits = _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + mm->context.asce_limit = STACK_TOP_MAX; + } else if (mm->context.asce_limit == (1UL << 31)) { + mm_inc_nr_pmds(mm); + } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; } @@ -111,8 +119,6 @@ static inline void activate_mm(struct mm_struct *prev, static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { - if (oldmm->context.asce_limit < mm->context.asce_limit) - crst_table_downgrade(mm, oldmm->context.asce_limit); } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index c873e682b67f..6dafabb6ae1a 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -45,7 +45,8 @@ struct zpci_fmb { u64 rpcit_ops; u64 dma_rbytes; u64 dma_wbytes; -} __packed __aligned(16); + u64 pad[2]; +} __packed __aligned(128); enum zpci_state { ZPCI_FN_STATE_RESERVED, diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 7b7858f158b4..d7cc79fb6191 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - spin_lock_init(&mm->context.list_lock); - INIT_LIST_HEAD(&mm->context.pgtable_list); - INIT_LIST_HEAD(&mm->context.gmap_list); - return (pgd_t *) crst_table_alloc(mm); + unsigned long *table = crst_table_alloc(mm); + + if (!table) + return NULL; + if (mm->context.asce_limit == (1UL << 31)) { + /* Forking a compat process with 2 page table levels */ + if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + crst_table_free(mm, table); + return NULL; + } + } + return (pgd_t *) table; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + if (mm->context.asce_limit == (1UL << 31)) + pgtable_pmd_page_dtor(virt_to_page(pgd)); + crst_table_free(mm, (unsigned long *) pgd); } -#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 9cd248f637c7..dc6c9c604543 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -181,6 +181,7 @@ int main(void) OFFSET(__LC_PSW_SAVE_AREA, _lowcore, psw_save_area); OFFSET(__LC_PREFIX_SAVE_AREA, _lowcore, prefixreg_save_area); OFFSET(__LC_FP_CREG_SAVE_AREA, _lowcore, fpt_creg_save_area); + OFFSET(__LC_TOD_PROGREG_SAVE_AREA, _lowcore, tod_progreg_save_area); OFFSET(__LC_CPU_TIMER_SAVE_AREA, _lowcore, cpu_timer_save_area); OFFSET(__LC_CLOCK_COMP_SAVE_AREA, _lowcore, clock_comp_save_area); OFFSET(__LC_AREGS_SAVE_AREA, _lowcore, access_regs_save_area); diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 66c94417c0ba..4af60374eba0 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs, /* Restore high gprs from signal stack */ if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high, - sizeof(&sregs_ext->gprs_high))) + sizeof(sregs_ext->gprs_high))) return -EFAULT; for (i = 0; i < NUM_GPRS; i++) *(__u32 *)®s->gprs[i] = gprs_high[i]; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 857b6526d298..424e6809ad07 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1197,114 +1197,12 @@ cleanup_critical: .quad .Lpsw_idle_lpsw .Lcleanup_save_fpu_regs: - TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bor %r14 - clg %r9,BASED(.Lcleanup_save_fpu_regs_done) - jhe 5f - clg %r9,BASED(.Lcleanup_save_fpu_regs_fp) - jhe 4f - clg %r9,BASED(.Lcleanup_save_fpu_regs_vx_high) - jhe 3f - clg %r9,BASED(.Lcleanup_save_fpu_regs_vx_low) - jhe 2f - clg %r9,BASED(.Lcleanup_save_fpu_fpc_end) - jhe 1f - lg %r2,__LC_CURRENT - aghi %r2,__TASK_thread -0: # Store floating-point controls - stfpc __THREAD_FPU_fpc(%r2) -1: # Load register save area and check if VX is active - lg %r3,__THREAD_FPU_regs(%r2) - TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX - jz 4f # no VX -> store FP regs -2: # Store vector registers (V0-V15) - VSTM %v0,%v15,0,%r3 # vstm 0,15,0(3) -3: # Store vector registers (V16-V31) - VSTM %v16,%v31,256,%r3 # vstm 16,31,256(3) - j 5f # -> done, set CIF_FPU flag -4: # Store floating-point registers - std 0,0(%r3) - std 1,8(%r3) - std 2,16(%r3) - std 3,24(%r3) - std 4,32(%r3) - std 5,40(%r3) - std 6,48(%r3) - std 7,56(%r3) - std 8,64(%r3) - std 9,72(%r3) - std 10,80(%r3) - std 11,88(%r3) - std 12,96(%r3) - std 13,104(%r3) - std 14,112(%r3) - std 15,120(%r3) -5: # Set CIF_FPU flag - oi __LC_CPU_FLAGS+7,_CIF_FPU - lg %r9,48(%r11) # return from save_fpu_regs + larl %r9,save_fpu_regs br %r14 -.Lcleanup_save_fpu_fpc_end: - .quad .Lsave_fpu_regs_fpc_end -.Lcleanup_save_fpu_regs_vx_low: - .quad .Lsave_fpu_regs_vx_low -.Lcleanup_save_fpu_regs_vx_high: - .quad .Lsave_fpu_regs_vx_high -.Lcleanup_save_fpu_regs_fp: - .quad .Lsave_fpu_regs_fp -.Lcleanup_save_fpu_regs_done: - .quad .Lsave_fpu_regs_done .Lcleanup_load_fpu_regs: - TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bnor %r14 - clg %r9,BASED(.Lcleanup_load_fpu_regs_done) - jhe 1f - clg %r9,BASED(.Lcleanup_load_fpu_regs_fp) - jhe 2f - clg %r9,BASED(.Lcleanup_load_fpu_regs_vx_high) - jhe 3f - clg %r9,BASED(.Lcleanup_load_fpu_regs_vx) - jhe 4f - lg %r4,__LC_CURRENT - aghi %r4,__TASK_thread - lfpc __THREAD_FPU_fpc(%r4) - TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX - lg %r4,__THREAD_FPU_regs(%r4) # %r4 <- reg save area - jz 2f # -> no VX, load FP regs -4: # Load V0 ..V15 registers - VLM %v0,%v15,0,%r4 -3: # Load V16..V31 registers - VLM %v16,%v31,256,%r4 - j 1f -2: # Load floating-point registers - ld 0,0(%r4) - ld 1,8(%r4) - ld 2,16(%r4) - ld 3,24(%r4) - ld 4,32(%r4) - ld 5,40(%r4) - ld 6,48(%r4) - ld 7,56(%r4) - ld 8,64(%r4) - ld 9,72(%r4) - ld 10,80(%r4) - ld 11,88(%r4) - ld 12,96(%r4) - ld 13,104(%r4) - ld 14,112(%r4) - ld 15,120(%r4) -1: # Clear CIF_FPU bit - ni __LC_CPU_FLAGS+7,255-_CIF_FPU - lg %r9,48(%r11) # return from load_fpu_regs + larl %r9,load_fpu_regs br %r14 -.Lcleanup_load_fpu_regs_vx: - .quad .Lload_fpu_regs_vx -.Lcleanup_load_fpu_regs_vx_high: - .quad .Lload_fpu_regs_vx_high -.Lcleanup_load_fpu_regs_fp: - .quad .Lload_fpu_regs_fp -.Lcleanup_load_fpu_regs_done: - .quad .Lload_fpu_regs_done /* * Integer constants diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 58b719fa8067..1ad2407c7f75 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -16,7 +16,7 @@ __HEAD ENTRY(startup_continue) - tm __LC_STFL_FAC_LIST+6,0x80 # LPP available ? + tm __LC_STFL_FAC_LIST+5,0x80 # LPP available ? jz 0f xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid mvi __LC_LPP,0x80 # and set LPP_MAGIC diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index c837bcacf218..1f581eb61bc2 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -329,6 +329,7 @@ static void __init setup_lowcore(void) + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->current_task = (unsigned long) init_thread_union.thread_info.task; lc->thread_info = (unsigned long) &init_thread_union; + lc->lpp = LPP_MAGIC; lc->machine_flags = S390_lowcore.machine_flags; lc->stfl_fac_list = S390_lowcore.stfl_fac_list; memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 846589281b04..575dc123bda2 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1268,44 +1268,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) return 0; } -/* - * Backs up the current FP/VX register save area on a particular - * destination. Used to switch between different register save - * areas. - */ -static inline void save_fpu_to(struct fpu *dst) -{ - dst->fpc = current->thread.fpu.fpc; - dst->regs = current->thread.fpu.regs; -} - -/* - * Switches the FP/VX register save area from which to lazy - * restore register contents. - */ -static inline void load_fpu_from(struct fpu *from) -{ - current->thread.fpu.fpc = from->fpc; - current->thread.fpu.regs = from->regs; -} - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Save host register state */ save_fpu_regs(); - save_fpu_to(&vcpu->arch.host_fpregs); - - if (test_kvm_facility(vcpu->kvm, 129)) { - current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - /* - * Use the register save area in the SIE-control block - * for register restore and save in kvm_arch_vcpu_put() - */ - current->thread.fpu.vxrs = - (__vector128 *)&vcpu->run->s.regs.vrs; - } else - load_fpu_from(&vcpu->arch.guest_fpregs); + vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; + vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; + /* Depending on MACHINE_HAS_VX, data stored to vrs either + * has vector register or floating point register format. + */ + current->thread.fpu.regs = vcpu->run->s.regs.vrs; + current->thread.fpu.fpc = vcpu->run->s.regs.fpc; if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ current->thread.fpu.fpc = 0; @@ -1321,19 +1295,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); gmap_disable(vcpu->arch.gmap); + /* Save guest register state */ save_fpu_regs(); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - if (test_kvm_facility(vcpu->kvm, 129)) - /* - * kvm_arch_vcpu_load() set up the register save area to - * the &vcpu->run->s.regs.vrs and, thus, the vector registers - * are already saved. Only the floating-point control must be - * copied. - */ - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - else - save_fpu_to(&vcpu->arch.guest_fpregs); - load_fpu_from(&vcpu->arch.host_fpregs); + /* Restore host register state */ + current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; + current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); @@ -1351,8 +1319,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64)); vcpu->arch.sie_block->gcr[0] = 0xE0UL; vcpu->arch.sie_block->gcr[14] = 0xC2000000UL; - vcpu->arch.guest_fpregs.fpc = 0; - asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); + /* make sure the new fpc will be lazily loaded */ + save_fpu_regs(); + current->thread.fpu.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; @@ -1501,19 +1470,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.local_int.wq = &vcpu->wq; vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; - /* - * Allocate a save area for floating-point registers. If the vector - * extension is available, register contents are saved in the SIE - * control block. The allocated save area is still required in - * particular places, for example, in kvm_s390_vcpu_store_status(). - */ - vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS, - GFP_KERNEL); - if (!vcpu->arch.guest_fpregs.fprs) { - rc = -ENOMEM; - goto out_free_sie_block; - } - rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) goto out_free_sie_block; @@ -1734,19 +1690,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { + /* make sure the new values will be lazily loaded */ + save_fpu_regs(); if (test_fp_ctl(fpu->fpc)) return -EINVAL; - memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); - vcpu->arch.guest_fpregs.fpc = fpu->fpc; - save_fpu_regs(); - load_fpu_from(&vcpu->arch.guest_fpregs); + current->thread.fpu.fpc = fpu->fpc; + if (MACHINE_HAS_VX) + convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs); + else + memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs)); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs)); - fpu->fpc = vcpu->arch.guest_fpregs.fpc; + /* make sure we have the latest values */ + save_fpu_regs(); + if (MACHINE_HAS_VX) + convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs); + else + memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs)); + fpu->fpc = current->thread.fpu.fpc; return 0; } @@ -2266,41 +2230,50 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) { unsigned char archmode = 1; + freg_t fprs[NUM_FPRS]; unsigned int px; u64 clkcomp; int rc; + px = kvm_s390_get_prefix(vcpu); if (gpa == KVM_S390_STORE_STATUS_NOADDR) { if (write_guest_abs(vcpu, 163, &archmode, 1)) return -EFAULT; - gpa = SAVE_AREA_BASE; + gpa = 0; } else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) { if (write_guest_real(vcpu, 163, &archmode, 1)) return -EFAULT; - gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE); + gpa = px; + } else + gpa -= __LC_FPREGS_SAVE_AREA; + + /* manually convert vector registers if necessary */ + if (MACHINE_HAS_VX) { + convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + fprs, 128); + } else { + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + vcpu->run->s.regs.vrs, 128); } - rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs), - vcpu->arch.guest_fpregs.fprs, 128); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA, vcpu->run->s.regs.gprs, 128); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw), + rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA, &vcpu->arch.sie_block->gpsw, 16); - px = kvm_s390_get_prefix(vcpu); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg), + rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA, &px, 4); - rc |= write_guest_abs(vcpu, - gpa + offsetof(struct save_area, fp_ctrl_reg), - &vcpu->arch.guest_fpregs.fpc, 4); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg), + rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA, + &vcpu->run->s.regs.fpc, 4); + rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA, &vcpu->arch.sie_block->todpr, 4); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer), + rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA, &vcpu->arch.sie_block->cputm, 8); clkcomp = vcpu->arch.sie_block->ckc >> 8; - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp), + rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA, &clkcomp, 8); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_AREGS_SAVE_AREA, &vcpu->run->s.regs.acrs, 64); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_CREGS_SAVE_AREA, &vcpu->arch.sie_block->gcr, 128); return rc ? -EFAULT : 0; } @@ -2313,19 +2286,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) * it into the save area */ save_fpu_regs(); - if (test_kvm_facility(vcpu->kvm, 129)) { - /* - * If the vector extension is available, the vector registers - * which overlaps with floating-point registers are saved in - * the SIE-control block. Hence, extract the floating-point - * registers and the FPC value and store them in the - * guest_fpregs structure. - */ - vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc; - convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs, - current->thread.fpu.vxrs); - } else - save_fpu_to(&vcpu->arch.guest_fpregs); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; save_access_regs(vcpu->run->s.regs.acrs); return kvm_s390_store_status_unloaded(vcpu, addr); diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c index 4d1ee88864e8..18c8b819b0aa 100644 --- a/arch/s390/mm/extable.c +++ b/arch/s390/mm/extable.c @@ -52,12 +52,16 @@ void sort_extable(struct exception_table_entry *start, int i; /* Normalize entries to being relative to the start of the section */ - for (p = start, i = 0; p < finish; p++, i += 8) + for (p = start, i = 0; p < finish; p++, i += 8) { p->insn += i; + p->fixup += i + 4; + } sort(start, finish - start, sizeof(*start), cmp_ex, NULL); /* Denormalize all entries */ - for (p = start, i = 0; p < finish; p++, i += 8) + for (p = start, i = 0; p < finish; p++, i += 8) { p->insn -= i; + p->fixup -= i + 4; + } } #ifdef CONFIG_MODULES diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 7ef12a3ace3a..19442395f413 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -871,8 +871,11 @@ static inline int barsize(u8 size) static int zpci_mem_init(void) { + BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) || + __alignof__(struct zpci_fmb) < sizeof(struct zpci_fmb)); + zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb), - 16, 0, NULL); + __alignof__(struct zpci_fmb), 0, NULL); if (!zdev_fmb_cache) goto error_zdev; diff --git a/arch/sh/mm/kmap.c b/arch/sh/mm/kmap.c index ec29e14ec5a8..bf25d7c79a2d 100644 --- a/arch/sh/mm/kmap.c +++ b/arch/sh/mm/kmap.c @@ -36,6 +36,7 @@ void *kmap_coherent(struct page *page, unsigned long addr) BUG_ON(!test_bit(PG_dcache_clean, &page->flags)); + preempt_disable(); pagefault_disable(); idx = FIX_CMAP_END - @@ -64,4 +65,5 @@ void kunmap_coherent(void *kvaddr) } pagefault_enable(); + preempt_enable(); } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index c48d93b60afe..b489e9759518 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -413,7 +413,7 @@ out: SYSCALL_DEFINE1(sparc64_personality, unsigned long, personality) { - int ret; + long ret; if (personality(current->personality) == PER_LINUX32 && personality(personality) == PER_LINUX) diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 29880c9b324e..e22e57298522 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -133,7 +133,7 @@ void mconsole_proc(struct mc_request *req) ptr += strlen("proc"); ptr = skip_spaces(ptr); - file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY); + file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0); if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file)); diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 47f1ff056a54..22a358ef1b0c 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -94,6 +94,8 @@ static int start_ptraced_child(void) { int pid, n, status; + fflush(stdout); + pid = fork(); if (pid == 0) ptrace_child(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ae3c83e8bde8..be2395bc2172 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1142,22 +1142,23 @@ config MICROCODE bool "CPU microcode loading support" default y depends on CPU_SUP_AMD || CPU_SUP_INTEL - depends on BLK_DEV_INITRD select FW_LOADER ---help--- - If you say Y here, you will be able to update the microcode on - certain Intel and AMD processors. The Intel support is for the - IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, - Xeon etc. The AMD support is for families 0x10 and later. You will - obviously need the actual microcode binary data itself which is not - shipped with the Linux kernel. - - This option selects the general module only, you need to select - at least one vendor specific module as well. - - To compile this driver as a module, choose M here: the module - will be called microcode. + Intel and AMD processors. The Intel support is for the IA32 family, + e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. The + AMD support is for families 0x10 and later. You will obviously need + the actual microcode binary data itself which is not shipped with + the Linux kernel. + + The preferred method to load microcode from a detached initrd is described + in Documentation/x86/early-microcode.txt. For that you need to enable + CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the + initrd for microcode blobs. + + In addition, you can build-in the microcode into the kernel. For that you + need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode + to the CONFIG_EXTRA_FIRMWARE config option. config MICROCODE_INTEL bool "Intel microcode loading support" diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 712b13047b41..3a33124e9112 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -157,7 +157,9 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - sub $0x40,%rsp + mov %rsp,%r11 + sub $0x80,%rsp + and $~63,%rsp # x0..15[0-3] = s0..3[0..3] movq 0x00(%rdi),%xmm1 @@ -620,6 +622,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - add $0x40,%rsp + mov %r11,%rsp ret ENDPROC(chacha20_4block_xor_ssse3) diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index a841e9765bd6..8381c09d2870 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -453,10 +453,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03663740c866..1a4477cedc49 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -268,6 +268,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* Called with IRQs disabled. */ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) { + struct thread_info *ti = pt_regs_to_thread_info(regs); u32 cached_flags; if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) @@ -275,12 +276,22 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) lockdep_sys_exit(); - cached_flags = - READ_ONCE(pt_regs_to_thread_info(regs)->flags); + cached_flags = READ_ONCE(ti->flags); if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) exit_to_usermode_loop(regs, cached_flags); +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. We need to clear it *after* signal + * handling, because syscall restart has a fixup for compat + * syscalls. The fixup is exercised by the ptrace_syscall_32 + * selftest. + */ + ti->status &= ~TS_COMPAT; +#endif + user_enter(); } @@ -332,14 +343,6 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs) if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS)) syscall_slow_exit_work(regs, cached_flags); -#ifdef CONFIG_COMPAT - /* - * Compat syscalls set TS_COMPAT. Make sure we clear it before - * returning to user mode. - */ - ti->status &= ~TS_COMPAT; -#endif - local_irq_disable(); prepare_exit_to_usermode(regs); } diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 6a1ae3751e82..15cfebaa7688 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -267,6 +267,7 @@ ENTRY(entry_INT80_compat) * Interrupts are off on entry. */ PARAVIRT_ADJUST_EXCEPTION_FRAME + ASM_CLAC /* Do this early to minimize exposure */ SWAPGS /* diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a30316bf801a..163769d82475 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -638,8 +638,8 @@ static inline void entering_irq(void) static inline void entering_ack_irq(void) { - ack_APIC_irq(); entering_irq(); + ack_APIC_irq(); } static inline void ipi_entering_ack_irq(void) diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 4fa687a47a62..6b8d6e8cd449 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -27,7 +27,7 @@ #define BOOT_HEAP_SIZE 0x400000 #else /* !CONFIG_KERNEL_BZIP2 */ -#define BOOT_HEAP_SIZE 0x8000 +#define BOOT_HEAP_SIZE 0x10000 #endif /* !CONFIG_KERNEL_BZIP2 */ diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index f8a29d2c97b0..e6a8613fbfb0 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -4,6 +4,7 @@ #include <asm/page.h> #include <asm-generic/hugetlb.h> +#define hugepages_supported() cpu_has_pse static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 1e3408e88604..59caa55fb9b5 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -136,6 +136,7 @@ struct irq_alloc_info { struct irq_cfg { unsigned int dest_apicid; u8 vector; + u8 old_vector; }; extern struct irq_cfg *irq_cfg(unsigned int irq); diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 881b4768644a..e7de5c9a4fbd 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu); #define __ARCH_HAS_DO_SOFTIRQ +struct irq_desc; + #ifdef CONFIG_HOTPLUG_CPU #include <linux/cpumask.h> extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); -extern void irq_force_complete_move(int); +extern void irq_force_complete_move(struct irq_desc *desc); #endif #ifdef CONFIG_HAVE_KVM @@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); -struct irq_desc; extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 30cfd64295a0..9d2abb2a41d2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -41,7 +41,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 -#define KVM_HALT_POLL_NS_DEFAULT 500000 +#define KVM_HALT_POLL_NS_DEFAULT 400000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 34e62b1dcfce..712b24ed3a64 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -2,6 +2,7 @@ #define _ASM_X86_MICROCODE_H #include <linux/earlycpio.h> +#include <linux/initrd.h> #define native_rdmsr(msr, val1, val2) \ do { \ @@ -168,4 +169,29 @@ static inline void reload_early_microcode(void) { } static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } #endif + +static inline unsigned long get_initrd_start(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD + return initrd_start; +#else + return 0; +#endif +} + +static inline unsigned long get_initrd_start_addr(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD +#ifdef CONFIG_X86_32 + unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); + + return (unsigned long)__pa_nodebug(*initrd_start_p); +#else + return get_initrd_start(); +#endif +#else /* CONFIG_BLK_DEV_INITRD */ + return 0; +#endif +} + #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 379cd3658799..bfd9b2a35a0b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -116,8 +116,36 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, #endif cpumask_set_cpu(cpu, mm_cpumask(next)); - /* Re-load page tables */ + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + * + */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ @@ -156,10 +184,14 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * schedule, protecting us from simultaneous changes. */ cpumask_set_cpu(cpu, mm_cpumask(next)); + /* * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. + * + * As above, load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask write. */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index fa1195dae425..164e3f8d3c3d 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); +extern bool mp_should_keep_irq(struct device *dev); + struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 7bcb861a04e5..5a2ed3ed2f26 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -165,6 +165,7 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_ASIF BIT_ULL(60) #define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) #define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) +#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) /* * IBS cpuid feature detection diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a471cadb9630..79c91853e50e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -363,20 +363,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); return new; } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 8b2d4bea9962..39171b3646bb 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,4 +62,6 @@ void xen_arch_register_cpu(int num); void xen_arch_unregister_cpu(int num); #endif +extern void xen_set_iopl_mask(unsigned mask); + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index d1daead5fcdd..adb3eaf8fe2a 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -16,6 +16,7 @@ #include <asm/cacheflush.h> #include <asm/realmode.h> +#include <linux/ftrace.h> #include "../../realmode/rm/wakeup.h" #include "sleep.h" @@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x123456789abcdef0L; #endif /* CONFIG_64BIT */ + /* + * Pause/unpause graph tracing around do_suspend_lowlevel as it has + * inconsistent call/return info after it jumps to the wakeup vector. + */ + pause_graph_tracing(); do_suspend_lowlevel(); + unpause_graph_tracing(); return 0; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index f25321894ad2..fdb0fbfb1197 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; const struct cpumask *mask; + struct irq_desc *desc; struct irq_data *idata; struct irq_chip *chip; @@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void) if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) continue; - idata = irq_get_irq_data(irq); + desc = irq_to_desc(irq); + raw_spin_lock_irq(&desc->lock); + idata = irq_desc_get_irq_data(desc); /* * Honour affinities which have been set in early boot @@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void) /* Might be lapic_chip for irq 0 */ if (chip->irq_set_affinity) chip->irq_set_affinity(idata, mask, false); + raw_spin_unlock_irq(&desc->lock); } } #endif diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 861bc59c8f25..df6b4eeac0bd 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -30,7 +30,7 @@ struct apic_chip_data { struct irq_domain *x86_vector_domain; static DEFINE_RAW_SPINLOCK(vector_lock); -static cpumask_var_t vector_cpumask; +static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask; static struct irq_chip lapic_controller; #ifdef CONFIG_X86_IO_APIC static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; @@ -116,35 +116,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, err; + int cpu, vector; - if (d->move_in_progress) + /* + * If there is still a move in progress or the previous move has not + * been cleaned up completely, tell the caller to come back later. + */ + if (d->move_in_progress || + cpumask_intersects(d->old_domain, cpu_online_mask)) return -EBUSY; /* Only try and allocate irqs on cpus that are present */ - err = -ENOSPC; cpumask_clear(d->old_domain); + cpumask_clear(searched_cpumask); cpu = cpumask_first_and(mask, cpu_online_mask); while (cpu < nr_cpu_ids) { - int new_cpu, vector, offset; + int new_cpu, offset; + /* Get the possible target cpus for @mask/@cpu from the apic */ apic->vector_allocation_domain(cpu, vector_cpumask, mask); + /* + * Clear the offline cpus from @vector_cpumask for searching + * and verify whether the result overlaps with @mask. If true, + * then the call to apic->cpu_mask_to_apicid_and() will + * succeed as well. If not, no point in trying to find a + * vector in this mask. + */ + cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask); + if (!cpumask_intersects(vector_searchmask, mask)) + goto next_cpu; + if (cpumask_subset(vector_cpumask, d->domain)) { - err = 0; if (cpumask_equal(vector_cpumask, d->domain)) - break; + goto success; /* - * New cpumask using the vector is a proper subset of - * the current in use mask. So cleanup the vector - * allocation for the members that are not used anymore. + * Mark the cpus which are not longer in the mask for + * cleanup. */ - cpumask_andnot(d->old_domain, d->domain, - vector_cpumask); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - cpumask_and(d->domain, d->domain, vector_cpumask); - break; + cpumask_andnot(d->old_domain, d->domain, vector_cpumask); + vector = d->cfg.vector; + goto update; } vector = current_vector; @@ -156,45 +168,61 @@ next: vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) { - cpumask_or(d->old_domain, d->old_domain, - vector_cpumask); - cpumask_andnot(vector_cpumask, mask, d->old_domain); - cpu = cpumask_first_and(vector_cpumask, - cpu_online_mask); - continue; - } + /* If the search wrapped around, try the next cpu */ + if (unlikely(current_vector == vector)) + goto next_cpu; if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) { + for_each_cpu(new_cpu, vector_searchmask) { if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) goto next; } /* Found one! */ current_vector = vector; current_offset = offset; - if (d->cfg.vector) { + /* Schedule the old vector for cleanup on all cpus */ + if (d->cfg.vector) cpumask_copy(d->old_domain, d->domain); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - } - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) + for_each_cpu(new_cpu, vector_searchmask) per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); - d->cfg.vector = vector; - cpumask_copy(d->domain, vector_cpumask); - err = 0; - break; - } + goto update; - if (!err) { - /* cache destination APIC IDs into cfg->dest_apicid */ - err = apic->cpu_mask_to_apicid_and(mask, d->domain, - &d->cfg.dest_apicid); +next_cpu: + /* + * We exclude the current @vector_cpumask from the requested + * @mask and try again with the next online cpu in the + * result. We cannot modify @mask, so we use @vector_cpumask + * as a temporary buffer here as it will be reassigned when + * calling apic->vector_allocation_domain() above. + */ + cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask); + cpumask_andnot(vector_cpumask, mask, searched_cpumask); + cpu = cpumask_first_and(vector_cpumask, cpu_online_mask); + continue; } + return -ENOSPC; - return err; +update: + /* + * Exclude offline cpus from the cleanup mask and set the + * move_in_progress flag when the result is not empty. + */ + cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); + d->move_in_progress = !cpumask_empty(d->old_domain); + d->cfg.old_vector = d->move_in_progress ? d->cfg.vector : 0; + d->cfg.vector = vector; + cpumask_copy(d->domain, vector_cpumask); +success: + /* + * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail + * as we already established, that mask & d->domain & cpu_online_mask + * is not empty. + */ + BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain, + &d->cfg.dest_apicid)); + return 0; } static int assign_irq_vector(int irq, struct apic_chip_data *data, @@ -224,11 +252,10 @@ static int assign_irq_vector_policy(int irq, int node, static void clear_irq_vector(int irq, struct apic_chip_data *data) { struct irq_desc *desc; - unsigned long flags; int cpu, vector; - raw_spin_lock_irqsave(&vector_lock, flags); - BUG_ON(!data->cfg.vector); + if (!data->cfg.vector) + return; vector = data->cfg.vector; for_each_cpu_and(cpu, data->domain, cpu_online_mask) @@ -237,10 +264,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) data->cfg.vector = 0; cpumask_clear(data->domain); - if (likely(!data->move_in_progress)) { - raw_spin_unlock_irqrestore(&vector_lock, flags); + /* + * If move is in progress or the old_domain mask is not empty, + * i.e. the cleanup IPI has not been processed yet, we need to remove + * the old references to desc from all cpus vector tables. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) return; - } desc = irq_to_desc(irq); for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { @@ -253,7 +283,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) } } data->move_in_progress = 0; - raw_spin_unlock_irqrestore(&vector_lock, flags); } void init_irq_alloc_info(struct irq_alloc_info *info, @@ -274,19 +303,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) static void x86_vector_free_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { + struct apic_chip_data *apic_data; struct irq_data *irq_data; + unsigned long flags; int i; for (i = 0; i < nr_irqs; i++) { irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); if (irq_data && irq_data->chip_data) { + raw_spin_lock_irqsave(&vector_lock, flags); clear_irq_vector(virq + i, irq_data->chip_data); - free_apic_chip_data(irq_data->chip_data); + apic_data = irq_data->chip_data; + irq_domain_reset_irq_data(irq_data); + raw_spin_unlock_irqrestore(&vector_lock, flags); + free_apic_chip_data(apic_data); #ifdef CONFIG_X86_IO_APIC if (virq + i < nr_legacy_irqs()) legacy_irq_data[virq + i] = NULL; #endif - irq_domain_reset_irq_data(irq_data); } } } @@ -404,6 +438,8 @@ int __init arch_early_irq_init(void) arch_init_htirq_domain(x86_vector_domain); BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL)); return arch_early_ioapic_init(); } @@ -492,14 +528,7 @@ static int apic_set_affinity(struct irq_data *irq_data, return -EINVAL; err = assign_irq_vector(irq, data, dest); - if (err) { - if (assign_irq_vector(irq, data, - irq_data_get_affinity_mask(irq_data))) - pr_err("Failed to recover vector for irq %d\n", irq); - return err; - } - - return IRQ_SET_MASK_OK; + return err ? err : IRQ_SET_MASK_OK; } static struct irq_chip lapic_controller = { @@ -511,20 +540,12 @@ static struct irq_chip lapic_controller = { #ifdef CONFIG_SMP static void __send_cleanup_vector(struct apic_chip_data *data) { - cpumask_var_t cleanup_mask; - - if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { - unsigned int i; - - for_each_cpu_and(i, data->old_domain, cpu_online_mask) - apic->send_IPI_mask(cpumask_of(i), - IRQ_MOVE_CLEANUP_VECTOR); - } else { - cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask); - apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); - free_cpumask_var(cleanup_mask); - } + raw_spin_lock(&vector_lock); + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); data->move_in_progress = 0; + if (!cpumask_empty(data->old_domain)) + apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR); + raw_spin_unlock(&vector_lock); } void send_cleanup_vector(struct irq_cfg *cfg) @@ -568,12 +589,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; /* - * Check if the irq migration is in progress. If so, we - * haven't received the cleanup request yet for this irq. + * Nothing to cleanup if irq migration is in progress + * or this cpu is not set in the cleanup mask. */ - if (data->move_in_progress) + if (data->move_in_progress || + !cpumask_test_cpu(me, data->old_domain)) goto unlock; + /* + * We have two cases to handle here: + * 1) vector is unchanged but the target mask got reduced + * 2) vector and the target mask has changed + * + * #1 is obvious, but in #2 we have two vectors with the same + * irq descriptor: the old and the new vector. So we need to + * make sure that we only cleanup the old vector. The new + * vector has the current @vector number in the config and + * this cpu is part of the target mask. We better leave that + * one alone. + */ if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) goto unlock; @@ -591,6 +625,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; } __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + cpumask_clear_cpu(me, data->old_domain); unlock: raw_spin_unlock(&desc->lock); } @@ -619,12 +654,99 @@ void irq_complete_move(struct irq_cfg *cfg) __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); } -void irq_force_complete_move(int irq) +/* + * Called from fixup_irqs() with @desc->lock held and interrupts disabled. + */ +void irq_force_complete_move(struct irq_desc *desc) { - struct irq_cfg *cfg = irq_cfg(irq); + struct irq_data *irqdata = irq_desc_get_irq_data(desc); + struct apic_chip_data *data = apic_chip_data(irqdata); + struct irq_cfg *cfg = data ? &data->cfg : NULL; + unsigned int cpu; + + if (!cfg) + return; + + /* + * This is tricky. If the cleanup of @data->old_domain has not been + * done yet, then the following setaffinity call will fail with + * -EBUSY. This can leave the interrupt in a stale state. + * + * All CPUs are stuck in stop machine with interrupts disabled so + * calling __irq_complete_move() would be completely pointless. + */ + raw_spin_lock(&vector_lock); + /* + * Clean out all offline cpus (including the outgoing one) from the + * old_domain mask. + */ + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); - if (cfg) - __irq_complete_move(cfg, cfg->vector); + /* + * If move_in_progress is cleared and the old_domain mask is empty, + * then there is nothing to cleanup. fixup_irqs() will take care of + * the stale vectors on the outgoing cpu. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) { + raw_spin_unlock(&vector_lock); + return; + } + + /* + * 1) The interrupt is in move_in_progress state. That means that we + * have not seen an interrupt since the io_apic was reprogrammed to + * the new vector. + * + * 2) The interrupt has fired on the new vector, but the cleanup IPIs + * have not been processed yet. + */ + if (data->move_in_progress) { + /* + * In theory there is a race: + * + * set_ioapic(new_vector) <-- Interrupt is raised before update + * is effective, i.e. it's raised on + * the old vector. + * + * So if the target cpu cannot handle that interrupt before + * the old vector is cleaned up, we get a spurious interrupt + * and in the worst case the ioapic irq line becomes stale. + * + * But in case of cpu hotplug this should be a non issue + * because if the affinity update happens right before all + * cpus rendevouz in stop machine, there is no way that the + * interrupt can be blocked on the target cpu because all cpus + * loops first with interrupts enabled in stop machine, so the + * old vector is not yet cleaned up when the interrupt fires. + * + * So the only way to run into this issue is if the delivery + * of the interrupt on the apic/system bus would be delayed + * beyond the point where the target cpu disables interrupts + * in stop machine. I doubt that it can happen, but at least + * there is a theroretical chance. Virtualization might be + * able to expose this, but AFAICT the IOAPIC emulation is not + * as stupid as the real hardware. + * + * Anyway, there is nothing we can do about that at this point + * w/o refactoring the whole fixup_irq() business completely. + * We print at least the irq number and the old vector number, + * so we have the necessary information when a problem in that + * area arises. + */ + pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n", + irqdata->irq, cfg->old_vector); + } + /* + * If old_domain is not empty, then other cpus still have the irq + * descriptor set in their vector array. Clean it up. + */ + for_each_cpu(cpu, data->old_domain) + per_cpu(vector_irq, cpu)[cfg->old_vector] = VECTOR_UNUSED; + + /* Cleanup the left overs of the (half finished) move */ + cpumask_clear(data->old_domain); + data->move_in_progress = 0; + raw_spin_unlock(&vector_lock); } #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 0a850100c594..2658e2af74ec 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -29,7 +29,7 @@ static char gen_pool_buf[MCE_POOLSZ]; void mce_gen_pool_process(void) { struct llist_node *head; - struct mce_evt_llist *node; + struct mce_evt_llist *node, *tmp; struct mce *mce; head = llist_del_all(&mce_event_llist); @@ -37,7 +37,7 @@ void mce_gen_pool_process(void) return; head = llist_reverse_order(head); - llist_for_each_entry(node, head, llnode) { + llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->mce; atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 2c5aaf8c2e2f..05538582a809 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -385,6 +385,9 @@ static void intel_thermal_interrupt(void) { __u64 msr_val; + if (static_cpu_has(X86_FEATURE_HWP)) + wrmsrl_safe(MSR_HWP_STATUS, 0); + rdmsrl(MSR_IA32_THERM_STATUS, msr_val); /* Check for violation of core thermal thresholds*/ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ce47402eb2f9..ac8975a65280 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -555,10 +555,14 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, cd.data = NULL; cd.size = 0; - cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) { + /* try built-in microcode if no initrd */ + if (!size) { if (!load_builtin_intel_microcode(&cd)) return UCODE_ERROR; + } else { + cd = find_cpio_data(p, (void *)start, size, &offset); + if (!cd.data) + return UCODE_ERROR; } return get_matching_model_microcode(0, start, cd.data, cd.size, @@ -694,7 +698,7 @@ int __init save_microcode_in_initrd_intel(void) if (count == 0) return ret; - copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); + copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, get_initrd_start(), count); ret = save_microcode(&mc_saved_data, mc_saved, count); if (ret) pr_err("Cannot save microcode patches from initrd.\n"); @@ -732,16 +736,20 @@ void __init load_ucode_intel_bsp(void) struct boot_params *p; p = (struct boot_params *)__pa_nodebug(&boot_params); - start = p->hdr.ramdisk_image; size = p->hdr.ramdisk_size; - _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), - (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), - start, size); + /* + * Set start only if we have an initrd image. We cannot use initrd_start + * because it is not set that early yet. + */ + start = (size ? p->hdr.ramdisk_image : 0); + + _load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), + start, size); #else - start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; size = boot_params.hdr.ramdisk_size; + start = (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0); _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); #endif @@ -752,20 +760,14 @@ void load_ucode_intel_ap(void) struct mc_saved_data *mc_saved_data_p; struct ucode_cpu_info uci; unsigned long *mc_saved_in_initrd_p; - unsigned long initrd_start_addr; enum ucode_state ret; #ifdef CONFIG_X86_32 - unsigned long *initrd_start_p; - mc_saved_in_initrd_p = - (unsigned long *)__pa_nodebug(mc_saved_in_initrd); + mc_saved_in_initrd_p = (unsigned long *)__pa_nodebug(mc_saved_in_initrd); mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); - initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); - initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); #else - mc_saved_data_p = &mc_saved_data; mc_saved_in_initrd_p = mc_saved_in_initrd; - initrd_start_addr = initrd_start; + mc_saved_data_p = &mc_saved_data; #endif /* @@ -777,7 +779,7 @@ void load_ucode_intel_ap(void) collect_cpu_info_early(&uci); ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, - initrd_start_addr, &uci); + get_initrd_start_addr(), &uci); if (ret != UCODE_OK) return; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2bf79d7c97df..a3aeb2cc361e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -593,6 +593,19 @@ void x86_pmu_disable_all(void) } } +/* + * There may be PMI landing after enabled=0. The PMI hitting could be before or + * after disable_all. + * + * If PMI hits before disable_all, the PMU will be disabled in the NMI handler. + * It will not be re-enabled in the NMI handler again, because enabled=0. After + * handling the NMI, disable_all will be called, which will not change the + * state either. If PMI hits after disable_all, the PMU is already disabled + * before entering NMI handler. The NMI handler will not change the state + * either. + * + * So either situation is harmless. + */ static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index d0e35ebb2adb..ee70445fbb1f 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -591,6 +591,7 @@ struct x86_pmu { pebs_active :1, pebs_broken :1; int pebs_record_size; + int pebs_buffer_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); @@ -907,6 +908,8 @@ void intel_pmu_lbr_init_hsw(void); void intel_pmu_lbr_init_skl(void); +void intel_pmu_pebs_data_source_nhm(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index e2a430021e46..078de2e86b7a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1458,7 +1458,15 @@ static __initconst const u64 slm_hw_cache_event_ids }; /* - * Use from PMIs where the LBRs are already disabled. + * Used from PMIs where the LBRs are already disabled. + * + * This function could be called consecutively. It is required to remain in + * disabled state if called consecutively. + * + * During consecutive calls, the same disable value will be written to related + * registers, so the PMU state remains unchanged. hw.state in + * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive + * calls. */ static void __intel_pmu_disable_all(void) { @@ -1840,6 +1848,16 @@ again: if (__test_and_clear_bit(62, (unsigned long *)&status)) { handled++; x86_pmu.drain_pebs(regs); + /* + * There are cases where, even though, the PEBS ovfl bit is set + * in GLOBAL_OVF_STATUS, the PEBS events may also have their + * overflow bits set for their counters. We must clear them + * here because they have been processed as exact samples in + * the drain_pebs() routine. They must not be processed again + * in the for_each_bit_set() loop for regular samples below. + */ + status &= ~cpuc->pebs_enabled; + status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; } /* @@ -1885,7 +1903,10 @@ again: goto again; done: - __intel_pmu_enable_all(0, true); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + __intel_pmu_enable_all(0, true); + /* * Only unmask the NMI after the overflow counters * have been reset. This avoids spurious NMIs on @@ -3315,6 +3336,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); x86_add_quirk(intel_nehalem_quirk); pr_cont("Nehalem events, "); @@ -3377,6 +3399,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); pr_cont("Westmere events, "); break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 5db1c7755548..7abb2b88572e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -51,7 +51,8 @@ union intel_x86_pebs_dse { #define OP_LH (P(OP, LOAD) | P(LVL, HIT)) #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) -static const u64 pebs_data_source[] = { +/* Version for Sandy Bridge and later */ +static u64 pebs_data_source[] = { P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ @@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = { OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ }; +/* Patch up minor differences in the bits */ +void __init intel_pmu_pebs_data_source_nhm(void) +{ + pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT); + pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); + pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); +} + static u64 precise_store_data(u64 status) { union intel_x86_pebs_dse dse; @@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node); + buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu) per_cpu(insn_buffer, cpu) = ibuffer; } - max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; + max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size; ds->pebs_buffer_base = (u64)(unsigned long)buffer; ds->pebs_index = ds->pebs_buffer_base; @@ -1296,6 +1305,7 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); + x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; int format = x86_pmu.intel_cap.pebs_format; @@ -1304,6 +1314,14 @@ void __init intel_ds_init(void) case 0: printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); + /* + * Using >PAGE_SIZE buffers makes the WRMSR to + * PERF_GLOBAL_CTRL in intel_pmu_enable_all() + * mysteriously hang on Core2. + * + * As a workaround, we don't do this. + */ + x86_pmu.pebs_buffer_size = PAGE_SIZE; x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; break; diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c index 5b0c232d1ee6..b931095e86d4 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -263,7 +263,9 @@ again: goto again; done: - knc_pmu_enable_all(0); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + knc_pmu_enable_all(0); return handled; } diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 37dae792dbbe..589b3193f102 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -96,9 +96,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) SYSCALL_DEFINE1(iopl, unsigned int, level) { struct pt_regs *regs = current_pt_regs(); - unsigned int old = (regs->flags >> 12) & 3; struct thread_struct *t = ¤t->thread; + /* + * Careful: the IOPL bits in regs->flags are undefined under Xen PV + * and changing them has no effect. + */ + unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT; + if (level > 3) return -EINVAL; /* Trying to gain more privileges? */ @@ -106,8 +111,9 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) if (!capable(CAP_SYS_RAWIO)) return -EPERM; } - regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); - t->iopl = level << 12; + regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | + (level << X86_EFLAGS_IOPL_BIT); + t->iopl = level << X86_EFLAGS_IOPL_BIT; set_iopl_mask(t->iopl); return 0; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index f8062aaf5df9..61521dc19c10 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -462,7 +462,7 @@ void fixup_irqs(void) * non intr-remapping case, we can't wait till this interrupt * arrives at this cpu before completing the irq move. */ - irq_force_complete_move(irq); + irq_force_complete_move(desc); if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; @@ -470,6 +470,15 @@ void fixup_irqs(void) } chip = irq_data_get_irq_chip(data); + /* + * The interrupt descriptor might have been cleaned up + * already, but it is not yet removed from the radix tree + */ + if (!chip) { + raw_spin_unlock(&desc->lock); + continue; + } + if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e835d263a33b..4cbb60fbff3e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -48,6 +48,7 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> +#include <asm/xen/hypervisor.h> asmlinkage extern void ret_from_fork(void); @@ -411,6 +412,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); +#ifdef CONFIG_XEN + /* + * On Xen PV, IOPL bits in pt_regs->flags have no effect, and + * current_pt_regs()->flags may not match the current task's + * intended IOPL. We need to switch it manually. + */ + if (unlikely(static_cpu_has(X86_FEATURE_XENPV) && + prev->iopl != next->iopl)) + xen_set_iopl_mask(next->iopl); +#endif + if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { /* * AMD CPUs have a misfeature: SYSRET sets the SS selector but diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 02693dd9a079..f660d63f40fe 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the iMac10,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"), + }, + }, /* ASRock */ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index b285d4e8c68e..5da924bbf0a0 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -106,14 +106,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id) continue; for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { resource_size_t start, end; + unsigned long flags; + + flags = pci_resource_flags(dev, i); + if (!(flags & IORESOURCE_MEM)) + continue; + + if (flags & IORESOURCE_UNSET) + continue; + + if (pci_resource_len(dev, i) == 0) + continue; start = pci_resource_start(dev, i); - if (start == 0) - break; end = pci_resource_end(dev, i); if (screen_info.lfb_base >= start && screen_info.lfb_base < end) { found_bar = 1; + break; } } } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 92ae6acac8a7..6aa0f4d9eea6 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void) if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); - ratio = (lo >> 8) & 0x1f; + ratio = (lo >> 8) & 0xff; } else { rdmsr(MSR_IA32_PERF_STATUS, lo, hi); ratio = (hi >> 8) & 0x1f; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1505587d06e9..b9b09fec173b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, u16 sel; la = seg_base(ctxt, addr.seg) + addr.ea; - *linear = la; *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: + *linear = la; if (is_noncanonical_address(la)) goto bad; @@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, goto bad; break; default: + *linear = la = (u32)la; usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, addr.seg); if (!usable) @@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (size > *max_size) goto bad; } - la &= (u32)-1; break; } if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index b0ea42b78ccd..ab5318727579 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -245,7 +245,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) * PIC is being reset. Handle it gracefully here */ atomic_inc(&ps->pending); - else if (value > 0) + else if (value > 0 && ps->reinject) /* in this case, we had multiple outstanding pit interrupts * that we needed to inject. Reinject */ @@ -288,7 +288,9 @@ static void pit_do_work(struct kthread_work *work) * last one has been acked. */ spin_lock(&ps->inject_lock); - if (ps->irq_ack) { + if (!ps->reinject) + inject = 1; + else if (ps->irq_ack) { ps->irq_ack = 0; inject = 1; } @@ -317,10 +319,10 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer); struct kvm_pit *pt = ps->kvm->arch.vpit; - if (ps->reinject || !atomic_read(&ps->pending)) { + if (ps->reinject) atomic_inc(&ps->pending); - queue_kthread_work(&pt->worker, &pt->expired); - } + + queue_kthread_work(&pt->worker, &pt->expired); if (ps->is_periodic) { hrtimer_add_expires_ns(&ps->timer, ps->period); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e7c2c1428a69..8eb8a934b531 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3754,13 +3754,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, - context->shadow_root_level, context->nx, + context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 3058a22a658d..7be8a251363e 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -249,7 +249,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, return ret; kvm_vcpu_mark_page_dirty(vcpu, table_gfn); - walker->ptes[level] = pte; + walker->ptes[level - 1] = pte; } return 0; } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 120302511802..ab9ae67a80e4 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -268,7 +268,7 @@ TRACE_EVENT(kvm_inj_virq, #define kvm_trace_sym_exc \ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ - EXS(MF), EXS(MC) + EXS(MF), EXS(AC), EXS(MC) /* * Tracepoint for kvm interrupt injection: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 44976a596fa6..f34ab71dfd57 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -595,6 +595,8 @@ struct vcpu_vmx { /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; + + u64 current_tsc_ratio; }; enum segment_cache_field { @@ -1746,6 +1748,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1783,26 +1792,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1813,16 +1827,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) @@ -2062,14 +2081,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - /* Setup TSC multiplier */ - if (cpu_has_vmx_tsc_scaling()) - vmcs_write64(TSC_MULTIPLIER, - vcpu->arch.tsc_scaling_ratio); - vmx->loaded_vmcs->cpu = cpu; } + /* Setup TSC multiplier */ + if (kvm_has_tsc_control && + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { + vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); + } + vmx_vcpu_pi_load(vcpu, cpu); } @@ -2616,8 +2637,15 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + /* + * Old versions of KVM use the single-context version without + * checking for support, so declare that it is supported even + * though it is treated as global context. The alternative is + * not failing the single-context invvpid, and it is worse. + */ if (enable_vpid) vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | + VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; else vmx->nested.nested_vmx_vpid_caps = 0; @@ -7319,6 +7347,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } @@ -7377,6 +7406,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } @@ -7393,12 +7423,17 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) } switch (type) { + case VMX_VPID_EXTENT_SINGLE_CONTEXT: + /* + * Old versions of KVM use the single-context version so we + * have to support it; just treat it the same as all-context. + */ case VMX_VPID_EXTENT_ALL_CONTEXT: __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); nested_vmx_succeed(vcpu); break; default: - /* Trap single context invalidation invvpid calls */ + /* Trap individual address invalidation invvpid calls */ BUG_ON(1); break; } @@ -8932,7 +8967,8 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) best->ebx &= ~bit(X86_FEATURE_INVPCID); } - vmcs_set_secondary_exec_control(secondary_exec_ctl); + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(secondary_exec_ctl); if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) { if (guest_cpuid_has_pcommit(vcpu)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 97592e190413..605cea75eb0d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -697,7 +697,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } - kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) @@ -951,7 +950,7 @@ static u32 msrs_to_save[] = { MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, }; static unsigned num_msrs_to_save; @@ -2736,6 +2735,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -4006,16 +4006,17 @@ static void kvm_init_msr_list(void) /* * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. We could work around this - * in VMX with the generic MSR save/load machinery, but it - * is not really worthwhile since it will really only - * happen with nested virtualization. + * to the guests in some cases. */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: if (!kvm_x86_ops->mpx_supported()) continue; break; + case MSR_TSC_AUX: + if (!kvm_x86_ops->rdtscp_supported()) + continue; + break; default: break; } @@ -6022,12 +6023,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } /* try to inject new event if pending */ - if (vcpu->arch.nmi_pending) { - if (kvm_x86_ops->nmi_allowed(vcpu)) { - --vcpu->arch.nmi_pending; - vcpu->arch.nmi_injected = true; - kvm_x86_ops->set_nmi(vcpu); - } + if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { + --vcpu->arch.nmi_pending; + vcpu->arch.nmi_injected = true; + kvm_x86_ops->set_nmi(vcpu); } else if (kvm_cpu_has_injectable_intr(vcpu)) { /* * Because interrupts can be injected asynchronously, we are @@ -6472,10 +6471,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (inject_pending_event(vcpu, req_int_win) != 0) req_immediate_exit = true; /* enable NMI/IRQ window open exits if needed */ - else if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); - else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); + else { + if (vcpu->arch.nmi_pending) + kvm_x86_ops->enable_nmi_window(vcpu); + if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) + kvm_x86_ops->enable_irq_window(vcpu); + } if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -6493,8 +6494,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->prepare_guest_switch(vcpu); if (vcpu->fpu_active) kvm_load_guest_fpu(vcpu); - kvm_load_guest_xcr0(vcpu); - vcpu->mode = IN_GUEST_MODE; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -6517,6 +6516,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } + kvm_load_guest_xcr0(vcpu); + if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); @@ -6543,12 +6544,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { - int i; - WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops->sync_dirty_debug_regs(vcpu); - for (i = 0; i < KVM_NR_DB_REGS; i++) - vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + kvm_update_dr0123(vcpu); + kvm_update_dr6(vcpu); + kvm_update_dr7(vcpu); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } /* @@ -6566,6 +6567,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + kvm_put_guest_xcr0(vcpu); + /* Interrupt is enabled by handle_external_intr() */ kvm_x86_ops->handle_external_intr(vcpu); @@ -7213,7 +7216,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) * and assume host would use all available bits. * Guest xcr0 would be loaded later. */ - kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); @@ -7222,8 +7224,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - kvm_put_guest_xcr0(vcpu); - if (!vcpu->guest_fpu_loaded) { vcpu->fpu_counter = 0; return; diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 982ce34f4a9b..27f89c79a44b 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string) /* * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. + * This will force destination out of cache for more performance. + * + * Note: Cached memory copy is used when destination or size is not + * naturally aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. */ ENTRY(__copy_user_nocache) ASM_STAC + + /* If size is less than 8 bytes, go to 4-byte copy */ cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .L_4b_nocache_copy_entry + + /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION + + /* Set 4x8-byte copy count and remainder */ movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_8b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 4x8-byte nocache loop-copy */ +.L_4x8b_nocache_copy_loop: 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi decl %ecx - jnz 1b -17: movl %edx,%ecx + jnz .L_4x8b_nocache_copy_loop + + /* Set 8-byte copy count and remainder */ +.L_8b_nocache_copy_entry: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) + jz .L_4b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 8-byte nocache loop-copy */ +.L_8b_nocache_copy_loop: +20: movq (%rsi),%r8 +21: movnti %r8,(%rdi) leaq 8(%rsi),%rsi leaq 8(%rdi),%rdi decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f + jnz .L_8b_nocache_copy_loop + + /* If no byte left, we're done */ +.L_4b_nocache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* If destination is not 4-byte aligned, go to byte copy: */ + movl %edi,%ecx + andl $3,%ecx + jnz .L_1b_cache_copy_entry + + /* Set 4-byte copy count (1 or 0) and remainder */ movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) + andl $3,%edx + shrl $2,%ecx + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 4-byte nocache copy: */ +30: movl (%rsi),%r8d +31: movnti %r8d,(%rdi) + leaq 4(%rsi),%rsi + leaq 4(%rdi),%rdi + + /* If no bytes left, we're done: */ + andl %edx,%edx + jz .L_finish_copy + + /* Perform byte "cache" loop-copy for the remainder */ +.L_1b_cache_copy_entry: + movl %edx,%ecx +.L_1b_cache_copy_loop: +40: movb (%rsi),%al +41: movb %al,(%rdi) incq %rsi incq %rdi decl %ecx - jnz 21b -23: xorl %eax,%eax + jnz .L_1b_cache_copy_loop + + /* Finished copying; fence the prior stores */ +.L_finish_copy: + xorl %eax,%eax ASM_CLAC sfence ret .section .fixup,"ax" -30: shll $6,%ecx +.L_fixup_4x8b_copy: + shll $6,%ecx addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence + jmp .L_fixup_handle_tail +.L_fixup_8b_copy: + lea (%rdx,%rcx,8),%rdx + jmp .L_fixup_handle_tail +.L_fixup_4b_copy: + lea (%rdx,%rcx,4),%rdx + jmp .L_fixup_handle_tail +.L_fixup_1b_copy: + movl %ecx,%edx +.L_fixup_handle_tail: + sfence jmp copy_user_handle_tail .previous - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) + _ASM_EXTABLE(1b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(2b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(3b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(4b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(5b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(6b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(7b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(8b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(9b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(10b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(11b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(12b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(13b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(14b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(15b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(20b,.L_fixup_8b_copy) + _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(30b,.L_fixup_4b_copy) + _ASM_EXTABLE(31b,.L_fixup_4b_copy) + _ASM_EXTABLE(40b,.L_fixup_1b_copy) + _ASM_EXTABLE(41b,.L_fixup_1b_copy) ENDPROC(__copy_user_nocache) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index eef44d9a3f77..e830c71a1323 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -360,8 +363,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 637ab34ed632..ddb2244b06a1 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -33,7 +33,7 @@ struct kmmio_fault_page { struct list_head list; struct kmmio_fault_page *release_next; - unsigned long page; /* location of the fault page */ + unsigned long addr; /* the requested address */ pteval_t old_presence; /* page presence prior to arming */ bool armed; @@ -70,9 +70,16 @@ unsigned int kmmio_count; static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE]; static LIST_HEAD(kmmio_probes); -static struct list_head *kmmio_page_list(unsigned long page) +static struct list_head *kmmio_page_list(unsigned long addr) { - return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)]; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); + + if (!pte) + return NULL; + addr &= page_level_mask(l); + + return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)]; } /* Accessed per-cpu */ @@ -98,15 +105,19 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr) } /* You must be holding RCU read lock. */ -static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page) +static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr) { struct list_head *head; struct kmmio_fault_page *f; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); - page &= PAGE_MASK; - head = kmmio_page_list(page); + if (!pte) + return NULL; + addr &= page_level_mask(l); + head = kmmio_page_list(addr); list_for_each_entry_rcu(f, head, list) { - if (f->page == page) + if (f->addr == addr) return f; } return NULL; @@ -137,10 +148,10 @@ static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old) static int clear_page_presence(struct kmmio_fault_page *f, bool clear) { unsigned int level; - pte_t *pte = lookup_address(f->page, &level); + pte_t *pte = lookup_address(f->addr, &level); if (!pte) { - pr_err("no pte for page 0x%08lx\n", f->page); + pr_err("no pte for addr 0x%08lx\n", f->addr); return -1; } @@ -156,7 +167,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->page); + __flush_tlb_one(f->addr); return 0; } @@ -176,12 +187,12 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f) int ret; WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n")); if (f->armed) { - pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n", - f->page, f->count, !!f->old_presence); + pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n", + f->addr, f->count, !!f->old_presence); } ret = clear_page_presence(f, true); - WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"), - f->page); + WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"), + f->addr); f->armed = true; return ret; } @@ -191,7 +202,7 @@ static void disarm_kmmio_fault_page(struct kmmio_fault_page *f) { int ret = clear_page_presence(f, false); WARN_ONCE(ret < 0, - KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page); + KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr); f->armed = false; } @@ -215,6 +226,12 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) struct kmmio_context *ctx; struct kmmio_fault_page *faultpage; int ret = 0; /* default to fault not handled */ + unsigned long page_base = addr; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); + if (!pte) + return -EINVAL; + page_base &= page_level_mask(l); /* * Preemption is now disabled to prevent process switch during @@ -227,7 +244,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) preempt_disable(); rcu_read_lock(); - faultpage = get_kmmio_fault_page(addr); + faultpage = get_kmmio_fault_page(page_base); if (!faultpage) { /* * Either this page fault is not caused by kmmio, or @@ -239,7 +256,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx = &get_cpu_var(kmmio_ctx); if (ctx->active) { - if (addr == ctx->addr) { + if (page_base == ctx->addr) { /* * A second fault on the same page means some other * condition needs handling by do_page_fault(), the @@ -267,9 +284,9 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx->active++; ctx->fpage = faultpage; - ctx->probe = get_kmmio_probe(addr); + ctx->probe = get_kmmio_probe(page_base); ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); - ctx->addr = addr; + ctx->addr = page_base; if (ctx->probe && ctx->probe->pre_handler) ctx->probe->pre_handler(ctx->probe, regs, addr); @@ -354,12 +371,11 @@ out: } /* You must be holding kmmio_lock. */ -static int add_kmmio_fault_page(unsigned long page) +static int add_kmmio_fault_page(unsigned long addr) { struct kmmio_fault_page *f; - page &= PAGE_MASK; - f = get_kmmio_fault_page(page); + f = get_kmmio_fault_page(addr); if (f) { if (!f->count) arm_kmmio_fault_page(f); @@ -372,26 +388,25 @@ static int add_kmmio_fault_page(unsigned long page) return -1; f->count = 1; - f->page = page; + f->addr = addr; if (arm_kmmio_fault_page(f)) { kfree(f); return -1; } - list_add_rcu(&f->list, kmmio_page_list(f->page)); + list_add_rcu(&f->list, kmmio_page_list(f->addr)); return 0; } /* You must be holding kmmio_lock. */ -static void release_kmmio_fault_page(unsigned long page, +static void release_kmmio_fault_page(unsigned long addr, struct kmmio_fault_page **release_list) { struct kmmio_fault_page *f; - page &= PAGE_MASK; - f = get_kmmio_fault_page(page); + f = get_kmmio_fault_page(addr); if (!f) return; @@ -420,18 +435,27 @@ int register_kmmio_probe(struct kmmio_probe *p) int ret = 0; unsigned long size = 0; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); + unsigned int l; + pte_t *pte; spin_lock_irqsave(&kmmio_lock, flags); if (get_kmmio_probe(p->addr)) { ret = -EEXIST; goto out; } + + pte = lookup_address(p->addr, &l); + if (!pte) { + ret = -EINVAL; + goto out; + } + kmmio_count++; list_add_rcu(&p->list, &kmmio_probes); while (size < size_lim) { if (add_kmmio_fault_page(p->addr + size)) pr_err("Unable to set page fault.\n"); - size += PAGE_SIZE; + size += page_level_size(l); } out: spin_unlock_irqrestore(&kmmio_lock, flags); @@ -506,11 +530,17 @@ void unregister_kmmio_probe(struct kmmio_probe *p) const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); struct kmmio_fault_page *release_list = NULL; struct kmmio_delayed_release *drelease; + unsigned int l; + pte_t *pte; + + pte = lookup_address(p->addr, &l); + if (!pte) + return; spin_lock_irqsave(&kmmio_lock, flags); while (size < size_lim) { release_kmmio_fault_page(p->addr + size, &release_list); - size += PAGE_SIZE; + size += page_level_size(l); } list_del_rcu(&p->list); kmmio_count--; diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b2fd67da1701..ef05755a1900 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, break; } - if (regno > nr_registers) { + if (regno >= nr_registers) { WARN_ONCE(1, "decoded an instruction with an invalid register"); return -EINVAL; } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3137a4feed1..b599a780a5a9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -414,24 +414,30 @@ pmd_t *lookup_pmd_address(unsigned long address) phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; - unsigned long phys_addr, offset; + phys_addr_t phys_addr; + unsigned long offset; enum pg_level level; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ switch (level) { case PG_LEVEL_1G: - phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PUD_PAGE_MASK; break; case PG_LEVEL_2M: - phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PMD_PAGE_MASK; break; default: - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; offset = virt_addr & ~PAGE_MASK; } @@ -1345,7 +1351,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8ddb5d0d66fb..5fb6adaaa796 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -106,8 +106,6 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; - if (!f->flush_end) - f->flush_end = f->flush_start + PAGE_SIZE; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { @@ -135,12 +133,20 @@ void native_flush_tlb_others(const struct cpumask *cpumask, unsigned long end) { struct flush_tlb_info info; + + if (end == 0) + end = start + PAGE_SIZE; info.flush_mm = mm; info.flush_start = start; info.flush_end = end; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); - trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start); + if (end == TLB_FLUSH_ALL) + trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); + else + trace_tlb_flush(TLB_REMOTE_SEND_IPI, + (end - start) >> PAGE_SHIFT); + if (is_uv_system()) { unsigned int cpu; @@ -161,7 +167,10 @@ void flush_tlb_current_task(void) preempt_disable(); count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + + /* This is an implicit full barrier that synchronizes with switch_mm. */ local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -188,17 +197,29 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); - if (current->active_mm != mm) + if (current->active_mm != mm) { + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; + } if (!current->mm) { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; } if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* + * Both branches below are implicit full barriers (MOV to CR or + * INVLPG) that synchronize with switch_mm. + */ if (base_pages_to_flush > tlb_single_page_flush_ceiling) { base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); @@ -228,10 +249,18 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) preempt_disable(); if (current->active_mm == mm) { - if (current->mm) + if (current->mm) { + /* + * Implicit full barrier (INVLPG) that synchronizes + * with switch_mm. + */ __flush_tlb_one(start); - else + } else { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + } } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index eccd4d99e6a4..8fd6f44aee83 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -673,28 +673,22 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } -int pcibios_alloc_irq(struct pci_dev *dev) +int pcibios_enable_device(struct pci_dev *dev, int mask) { - /* - * If the PCI device was already claimed by core code and has - * MSI enabled, probing of the pcibios IRQ will overwrite - * dev->irq. So bail out if MSI is already enabled. - */ - if (pci_dev_msi_enabled(dev)) - return -EBUSY; + int err; - return pcibios_enable_irq(dev); -} + if ((err = pci_enable_resources(dev, mask)) < 0) + return err; -void pcibios_free_irq(struct pci_dev *dev) -{ - if (pcibios_disable_irq) - pcibios_disable_irq(dev); + if (!pci_dev_msi_enabled(dev)) + return pcibios_enable_irq(dev); + return 0; } -int pcibios_enable_device(struct pci_dev *dev, int mask) +void pcibios_disable_device (struct pci_dev *dev) { - return pci_enable_resources(dev, mask); + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); } int pci_ext_cfg_avail(void) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e58565556703..0ae7e9fa348d 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -540,3 +540,10 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev) } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone); + +static void pci_bdwep_bar(struct pci_dev *dev) +{ + dev->non_compliant_bars = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar); diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 0d24e7c10145..8b93e634af84 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) int polarity; int ret; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; switch (intel_mid_identify_cpu()) { @@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (pci_has_managed_irq(dev)) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - /* - * Don't reset dev->irq here, otherwise - * intel_mid_pci_irq_enable() will fail on next call. - */ } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 32e70343e6fd..9bd115484745 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - pci_set_managed_irq(dev, irq); + dev->irq_managed = 1; + dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } +bool mp_should_keep_irq(struct device *dev) +{ + if (dev->power.is_prepared) + return true; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return true; +#endif + + return false; +} + static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); - pci_reset_managed_irq(dev); + dev->irq = 0; + dev->irq_managed = 0; } } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index b7de78bdc09c..beab8c706ac9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -961,7 +961,7 @@ static void xen_load_sp0(struct tss_struct *tss, tss->x86_tss.sp0 = thread->sp0; } -static void xen_set_iopl_mask(unsigned mask) +void xen_set_iopl_mask(unsigned mask) { struct physdev_set_iopl set_iopl; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index df0c40559583..7f664c416faf 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -34,7 +34,8 @@ static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_init_shared_info(); + if (!suspend_cancelled) + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 9ed55649ac8e..05e1df943856 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -128,7 +128,7 @@ ENTRY(_startup) wsr a0, icountlevel .set _index, 0 - .rept XCHAL_NUM_DBREAK - 1 + .rept XCHAL_NUM_DBREAK wsr a0, SREG_DBREAKC + _index .set _index, _index + 1 .endr diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index d75aa1476da7..1a804a2f9a5b 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -97,11 +97,11 @@ void clear_user_highpage(struct page *page, unsigned long vaddr) unsigned long paddr; void *kvaddr = coherent_kvaddr(page, TLBTEMP_BASE_1, vaddr, &paddr); - pagefault_disable(); + preempt_disable(); kmap_invalidate_coherent(page, vaddr); set_bit(PG_arch_1, &page->flags); clear_page_alias(kvaddr, paddr); - pagefault_enable(); + preempt_enable(); } void copy_user_highpage(struct page *dst, struct page *src, @@ -113,11 +113,11 @@ void copy_user_highpage(struct page *dst, struct page *src, void *src_vaddr = coherent_kvaddr(src, TLBTEMP_BASE_2, vaddr, &src_paddr); - pagefault_disable(); + preempt_disable(); kmap_invalidate_coherent(dst, vaddr); set_bit(PG_arch_1, &dst->flags); copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr); - pagefault_enable(); + preempt_enable(); } #endif /* DCACHE_WAY_SIZE > PAGE_SIZE */ diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 70cb408bc20d..92d785fefb6d 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -100,21 +100,23 @@ static void rs_poll(unsigned long priv) { struct tty_port *port = (struct tty_port *)priv; int i = 0; + int rd = 1; unsigned char c; spin_lock(&timer_lock); while (simc_poll(0)) { - simc_read(0, &c, 1); + rd = simc_read(0, &c, 1); + if (rd <= 0) + break; tty_insert_flip_char(port, c, TTY_NORMAL); i++; } if (i) tty_flip_buffer_push(port); - - - mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); + if (rd) + mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); spin_unlock(&timer_lock); } diff --git a/block/bio.c b/block/bio.c index 4f184d938942..d4d144363250 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1090,9 +1090,12 @@ int bio_uncopy_user(struct bio *bio) if (!bio_flagged(bio, BIO_NULL_MAPPED)) { /* * if we're in a workqueue, the request is orphaned, so - * don't copy into a random user address space, just free. + * don't copy into a random user address space, just free + * and return -EINTR so user space doesn't expect any data. */ - if (current->mm && bio_data_dir(bio) == READ) + if (!current->mm) + ret = -EINTR; + else if (bio_data_dir(bio) == READ) ret = bio_copy_to_iter(bio, bmd->iter); if (bmd->is_our_pages) bio_free_pages(bio); diff --git a/block/blk-core.c b/block/blk-core.c index 33e2f62d5062..f8e64cac981a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2189,7 +2189,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) if (q->mq_ops) { if (blk_queue_io_stat(q)) blk_account_io_start(rq, true); - blk_mq_insert_request(rq, false, true, true); + blk_mq_insert_request(rq, false, true, false); return 0; } diff --git a/block/blk-merge.c b/block/blk-merge.c index e01405a3e8b3..b966db8f3556 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -68,6 +68,18 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q, return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); } +static inline unsigned get_max_io_size(struct request_queue *q, + struct bio *bio) +{ + unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); + unsigned mask = queue_logical_block_size(q) - 1; + + /* aligned to logical block size */ + sectors &= ~(mask >> 9); + + return sectors; +} + static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, @@ -79,11 +91,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, unsigned front_seg_size = bio->bi_seg_front_size; bool do_split = true; struct bio *new = NULL; + const unsigned max_sectors = get_max_io_size(q, bio); bio_for_each_segment(bv, bio, iter) { - if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q)) - goto split; - /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. @@ -91,6 +101,21 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; + if (sectors + (bv.bv_len >> 9) > max_sectors) { + /* + * Consider this a new segment if we're splitting in + * the middle of this vector. + */ + if (nsegs < queue_max_segments(q) && + sectors < max_sectors) { + nsegs++; + sectors = max_sectors; + } + if (sectors) + goto split; + /* Make this single bvec as the 1st segment */ + } + if (bvprvp && blk_queue_cluster(q)) { if (seg_size + bv.bv_len > queue_max_segment_size(q)) goto new_segment; diff --git a/block/blk-settings.c b/block/blk-settings.c index dd4973583978..c7bb666aafd1 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -91,8 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim) lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->virt_boundary_mask = 0; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; - lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors = - BLK_SAFE_MAX_SECTORS; + lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; + lim->max_dev_sectors = 0; lim->chunk_sectors = 0; lim->max_write_same_sectors = 0; lim->max_discard_sectors = 0; diff --git a/block/partition-generic.c b/block/partition-generic.c index ae95e963c5bb..91327dbfbb1d 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -360,15 +360,20 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, goto out_del; } + err = hd_ref_init(p); + if (err) { + if (flags & ADDPART_FLAG_WHOLEDISK) + goto out_remove_file; + goto out_del; + } + /* everything is up and running, commence */ rcu_assign_pointer(ptbl->part[partno], p); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) kobject_uevent(&pdev->kobj, KOBJ_ADD); - - if (!hd_ref_init(p)) - return p; + return p; out_free_info: free_part_info(p); @@ -377,6 +382,8 @@ out_free_stats: out_free: kfree(p); return ERR_PTR(err); +out_remove_file: + device_remove_file(pdev, &dev_attr_whole_disk); out_del: kobject_put(p->holder_dir); device_del(pdev); diff --git a/build.config.net_test b/build.config.net_test new file mode 100644 index 000000000000..e1808d938ee5 --- /dev/null +++ b/build.config.net_test @@ -0,0 +1,9 @@ +ARCH=um +SUBARCH=x86_64 +CROSS_COMPILE= +EXTRA_CMDS='' +KERNEL_DIR=hikey-linaro +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN= +FILES=" +linux +" diff --git a/build_test.sh b/build_test.sh new file mode 100755 index 000000000000..654e65c39e18 --- /dev/null +++ b/build_test.sh @@ -0,0 +1,21 @@ +#!/bin/bash + +# Usage: +# build/build_test.sh + +export MAKE_ARGS=$@ +export ROOT_DIR=$(dirname $(readlink -f $0)) +export NET_TEST=${ROOT_DIR}/../kernel/tests/net/test +export BUILD_CONFIG=build/build.config.net_test + +test=all_tests.sh +set -e +source ${ROOT_DIR}/envsetup.sh + +echo "========================================================" +echo " Building kernel and running tests " + +cd ${KERNEL_DIR} +$NET_TEST/run_net_test.sh --builder $test +echo $? +echo "======Finished running tests======" diff --git a/crypto/af_alg.c b/crypto/af_alg.c index a8e7aa3e257b..f5e18c2a4852 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -76,6 +76,8 @@ int af_alg_register_type(const struct af_alg_type *type) goto unlock; type->ops->owner = THIS_MODULE; + if (type->ops_nokey) + type->ops_nokey->owner = THIS_MODULE; node->type = type; list_add(&node->list, &alg_types); err = 0; @@ -125,6 +127,26 @@ int af_alg_release(struct socket *sock) } EXPORT_SYMBOL_GPL(af_alg_release); +void af_alg_release_parent(struct sock *sk) +{ + struct alg_sock *ask = alg_sk(sk); + unsigned int nokey = ask->nokey_refcnt; + bool last = nokey && !ask->refcnt; + + sk = ask->parent; + ask = alg_sk(sk); + + lock_sock(sk); + ask->nokey_refcnt -= nokey; + if (!last) + last = !--ask->refcnt; + release_sock(sk); + + if (last) + sock_put(sk); +} +EXPORT_SYMBOL_GPL(af_alg_release_parent); + static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { const u32 forbidden = CRYPTO_ALG_INTERNAL; @@ -133,6 +155,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_alg *sa = (void *)uaddr; const struct af_alg_type *type; void *private; + int err; if (sock->state == SS_CONNECTED) return -EINVAL; @@ -160,16 +183,22 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return PTR_ERR(private); } + err = -EBUSY; lock_sock(sk); + if (ask->refcnt | ask->nokey_refcnt) + goto unlock; swap(ask->type, type); swap(ask->private, private); + err = 0; + +unlock: release_sock(sk); alg_do_release(type, private); - return 0; + return err; } static int alg_setkey(struct sock *sk, char __user *ukey, @@ -202,11 +231,15 @@ static int alg_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; - int err = -ENOPROTOOPT; + int err = -EBUSY; lock_sock(sk); + if (ask->refcnt) + goto unlock; + type = ask->type; + err = -ENOPROTOOPT; if (level != SOL_ALG || !type) goto unlock; @@ -238,6 +271,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; struct sock *sk2; + unsigned int nokey; int err; lock_sock(sk); @@ -257,20 +291,29 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); - if (err) { - sk_free(sk2); + + nokey = err == -ENOKEY; + if (nokey && type->accept_nokey) + err = type->accept_nokey(ask->private, sk2); + + if (err) goto unlock; - } sk2->sk_family = PF_ALG; - sock_hold(sk); + if (nokey || !ask->refcnt++) + sock_hold(sk); + ask->nokey_refcnt += nokey; alg_sk(sk2)->parent = sk; alg_sk(sk2)->type = type; + alg_sk(sk2)->nokey_refcnt = nokey; newsock->ops = type->ops; newsock->state = SS_CONNECTED; + if (nokey) + newsock->ops = type->ops_nokey; + err = 0; unlock: diff --git a/crypto/ahash.c b/crypto/ahash.c index 9c1dc8d6106a..d19b52324cf5 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -451,6 +451,7 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm) struct ahash_alg *alg = crypto_ahash_alg(hash); hash->setkey = ahash_nosetkey; + hash->has_setkey = false; hash->export = ahash_no_export; hash->import = ahash_no_import; @@ -463,8 +464,10 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm) hash->finup = alg->finup ?: ahash_def_finup; hash->digest = alg->digest; - if (alg->setkey) + if (alg->setkey) { hash->setkey = alg->setkey; + hash->has_setkey = true; + } if (alg->export) hash->export = alg->export; if (alg->import) diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index b4c24fe3dcfb..68a5ceaa04c8 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -34,6 +34,11 @@ struct hash_ctx { struct ahash_request req; }; +struct algif_hash_tfm { + struct crypto_ahash *hash; + bool has_key; +}; + static int hash_sendmsg(struct socket *sock, struct msghdr *msg, size_t ignored) { @@ -49,7 +54,8 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); if (!ctx->more) { - err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(crypto_ahash_init(&ctx->req), + &ctx->completion); if (err) goto unlock; } @@ -120,6 +126,7 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, } else { if (!ctx->more) { err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(err, &ctx->completion); if (err) goto unlock; } @@ -235,19 +242,151 @@ static struct proto_ops algif_hash_ops = { .accept = hash_accept, }; +static int hash_check_key(struct socket *sock) +{ + int err = 0; + struct sock *psk; + struct alg_sock *pask; + struct algif_hash_tfm *tfm; + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + + lock_sock(sk); + if (ask->refcnt) + goto unlock_child; + + psk = ask->parent; + pask = alg_sk(ask->parent); + tfm = pask->private; + + err = -ENOKEY; + lock_sock_nested(psk, SINGLE_DEPTH_NESTING); + if (!tfm->has_key) + goto unlock; + + if (!pask->refcnt++) + sock_hold(psk); + + ask->refcnt = 1; + sock_put(psk); + + err = 0; + +unlock: + release_sock(psk); +unlock_child: + release_sock(sk); + + return err; +} + +static int hash_sendmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t size) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_sendmsg(sock, msg, size); +} + +static ssize_t hash_sendpage_nokey(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_sendpage(sock, page, offset, size, flags); +} + +static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_recvmsg(sock, msg, ignored, flags); +} + +static int hash_accept_nokey(struct socket *sock, struct socket *newsock, + int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_accept(sock, newsock, flags); +} + +static struct proto_ops algif_hash_ops_nokey = { + .family = PF_ALG, + + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .getname = sock_no_getname, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .getsockopt = sock_no_getsockopt, + .mmap = sock_no_mmap, + .bind = sock_no_bind, + .setsockopt = sock_no_setsockopt, + .poll = sock_no_poll, + + .release = af_alg_release, + .sendmsg = hash_sendmsg_nokey, + .sendpage = hash_sendpage_nokey, + .recvmsg = hash_recvmsg_nokey, + .accept = hash_accept_nokey, +}; + static void *hash_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_ahash(name, type, mask); + struct algif_hash_tfm *tfm; + struct crypto_ahash *hash; + + tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); + if (!tfm) + return ERR_PTR(-ENOMEM); + + hash = crypto_alloc_ahash(name, type, mask); + if (IS_ERR(hash)) { + kfree(tfm); + return ERR_CAST(hash); + } + + tfm->hash = hash; + + return tfm; } static void hash_release(void *private) { - crypto_free_ahash(private); + struct algif_hash_tfm *tfm = private; + + crypto_free_ahash(tfm->hash); + kfree(tfm); } static int hash_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_ahash_setkey(private, key, keylen); + struct algif_hash_tfm *tfm = private; + int err; + + err = crypto_ahash_setkey(tfm->hash, key, keylen); + tfm->has_key = !err; + + return err; } static void hash_sock_destruct(struct sock *sk) @@ -261,12 +400,14 @@ static void hash_sock_destruct(struct sock *sk) af_alg_release_parent(sk); } -static int hash_accept_parent(void *private, struct sock *sk) +static int hash_accept_parent_nokey(void *private, struct sock *sk) { struct hash_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(private); - unsigned ds = crypto_ahash_digestsize(private); + struct algif_hash_tfm *tfm = private; + struct crypto_ahash *hash = tfm->hash; + unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(hash); + unsigned ds = crypto_ahash_digestsize(hash); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) @@ -286,7 +427,7 @@ static int hash_accept_parent(void *private, struct sock *sk) ask->private = ctx; - ahash_request_set_tfm(&ctx->req, private); + ahash_request_set_tfm(&ctx->req, hash); ahash_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); @@ -295,12 +436,24 @@ static int hash_accept_parent(void *private, struct sock *sk) return 0; } +static int hash_accept_parent(void *private, struct sock *sk) +{ + struct algif_hash_tfm *tfm = private; + + if (!tfm->has_key && crypto_ahash_has_setkey(tfm->hash)) + return -ENOKEY; + + return hash_accept_parent_nokey(private, sk); +} + static const struct af_alg_type algif_type_hash = { .bind = hash_bind, .release = hash_release, .setkey = hash_setkey, .accept = hash_accept_parent, + .accept_nokey = hash_accept_parent_nokey, .ops = &algif_hash_ops, + .ops_nokey = &algif_hash_ops_nokey, .name = "hash", .owner = THIS_MODULE }; diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 634b4d1ab681..f5e9f9310b48 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -31,6 +31,11 @@ struct skcipher_sg_list { struct scatterlist sg[0]; }; +struct skcipher_tfm { + struct crypto_skcipher *skcipher; + bool has_key; +}; + struct skcipher_ctx { struct list_head tsgl; struct af_alg_sgl rsgl; @@ -60,18 +65,10 @@ struct skcipher_async_req { struct skcipher_async_rsgl first_sgl; struct list_head list; struct scatterlist *tsg; - char iv[]; + atomic_t *inflight; + struct skcipher_request req; }; -#define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \ - crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))) - -#define GET_REQ_SIZE(ctx) \ - crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)) - -#define GET_IV_SIZE(ctx) \ - crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req)) - #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) @@ -97,15 +94,12 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq) static void skcipher_async_cb(struct crypto_async_request *req, int err) { - struct sock *sk = req->data; - struct alg_sock *ask = alg_sk(sk); - struct skcipher_ctx *ctx = ask->private; - struct skcipher_async_req *sreq = GET_SREQ(req, ctx); + struct skcipher_async_req *sreq = req->data; struct kiocb *iocb = sreq->iocb; - atomic_dec(&ctx->inflight); + atomic_dec(sreq->inflight); skcipher_free_async_sgls(sreq); - kfree(req); + kzfree(sreq); iocb->ki_complete(iocb, err, err); } @@ -301,8 +295,11 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req); + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; unsigned ivsize = crypto_skcipher_ivsize(tfm); struct skcipher_sg_list *sgl; struct af_alg_control con = {}; @@ -387,7 +384,8 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, sgl = list_entry(ctx->tsgl.prev, struct skcipher_sg_list, list); sg = sgl->sg; - sg_unmark_end(sg + sgl->cur); + if (sgl->cur) + sg_unmark_end(sg + sgl->cur - 1); do { i = sgl->cur; plen = min_t(int, len, PAGE_SIZE); @@ -503,37 +501,43 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; struct skcipher_sg_list *sgl; struct scatterlist *sg; struct skcipher_async_req *sreq; struct skcipher_request *req; struct skcipher_async_rsgl *last_rsgl = NULL; - unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx); - unsigned int reqlen = sizeof(struct skcipher_async_req) + - GET_REQ_SIZE(ctx) + GET_IV_SIZE(ctx); + unsigned int txbufs = 0, len = 0, tx_nents; + unsigned int reqsize = crypto_skcipher_reqsize(tfm); + unsigned int ivsize = crypto_skcipher_ivsize(tfm); int err = -ENOMEM; bool mark = false; + char *iv; - lock_sock(sk); - req = kmalloc(reqlen, GFP_KERNEL); - if (unlikely(!req)) - goto unlock; + sreq = kzalloc(sizeof(*sreq) + reqsize + ivsize, GFP_KERNEL); + if (unlikely(!sreq)) + goto out; - sreq = GET_SREQ(req, ctx); + req = &sreq->req; + iv = (char *)(req + 1) + reqsize; sreq->iocb = msg->msg_iocb; - memset(&sreq->first_sgl, '\0', sizeof(struct skcipher_async_rsgl)); INIT_LIST_HEAD(&sreq->list); + sreq->inflight = &ctx->inflight; + + lock_sock(sk); + tx_nents = skcipher_all_sg_nents(ctx); sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL); - if (unlikely(!sreq->tsg)) { - kfree(req); + if (unlikely(!sreq->tsg)) goto unlock; - } sg_init_table(sreq->tsg, tx_nents); - memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx)); - skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req)); - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - skcipher_async_cb, sk); + memcpy(iv, ctx->iv, ivsize); + skcipher_request_set_tfm(req, tfm); + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, + skcipher_async_cb, sreq); while (iov_iter_count(&msg->msg_iter)) { struct skcipher_async_rsgl *rsgl; @@ -609,20 +613,22 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, sg_mark_end(sreq->tsg + txbufs - 1); skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg, - len, sreq->iv); + len, iv); err = ctx->enc ? crypto_skcipher_encrypt(req) : crypto_skcipher_decrypt(req); if (err == -EINPROGRESS) { atomic_inc(&ctx->inflight); err = -EIOCBQUEUED; + sreq = NULL; goto unlock; } free: skcipher_free_async_sgls(sreq); - kfree(req); unlock: skcipher_wmem_wakeup(sk); release_sock(sk); + kzfree(sreq); +out: return err; } @@ -631,9 +637,12 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; - unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm( - &ctx->req)); + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; + unsigned bs = crypto_skcipher_blocksize(tfm); struct skcipher_sg_list *sgl; struct scatterlist *sg; int err = -EAGAIN; @@ -642,13 +651,6 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, lock_sock(sk); while (msg_data_left(msg)) { - sgl = list_first_entry(&ctx->tsgl, - struct skcipher_sg_list, list); - sg = sgl->sg; - - while (!sg->length) - sg++; - if (!ctx->used) { err = skcipher_wait_for_data(sk, flags); if (err) @@ -669,6 +671,13 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, if (!used) goto free; + sgl = list_first_entry(&ctx->tsgl, + struct skcipher_sg_list, list); + sg = sgl->sg; + + while (!sg->length) + sg++; + skcipher_request_set_crypt(&ctx->req, sg, ctx->rsgl.sg, used, ctx->iv); @@ -748,19 +757,139 @@ static struct proto_ops algif_skcipher_ops = { .poll = skcipher_poll, }; +static int skcipher_check_key(struct socket *sock) +{ + int err = 0; + struct sock *psk; + struct alg_sock *pask; + struct skcipher_tfm *tfm; + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + + lock_sock(sk); + if (ask->refcnt) + goto unlock_child; + + psk = ask->parent; + pask = alg_sk(ask->parent); + tfm = pask->private; + + err = -ENOKEY; + lock_sock_nested(psk, SINGLE_DEPTH_NESTING); + if (!tfm->has_key) + goto unlock; + + if (!pask->refcnt++) + sock_hold(psk); + + ask->refcnt = 1; + sock_put(psk); + + err = 0; + +unlock: + release_sock(psk); +unlock_child: + release_sock(sk); + + return err; +} + +static int skcipher_sendmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t size) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_sendmsg(sock, msg, size); +} + +static ssize_t skcipher_sendpage_nokey(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_sendpage(sock, page, offset, size, flags); +} + +static int skcipher_recvmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_recvmsg(sock, msg, ignored, flags); +} + +static struct proto_ops algif_skcipher_ops_nokey = { + .family = PF_ALG, + + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .getname = sock_no_getname, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .getsockopt = sock_no_getsockopt, + .mmap = sock_no_mmap, + .bind = sock_no_bind, + .accept = sock_no_accept, + .setsockopt = sock_no_setsockopt, + + .release = af_alg_release, + .sendmsg = skcipher_sendmsg_nokey, + .sendpage = skcipher_sendpage_nokey, + .recvmsg = skcipher_recvmsg_nokey, + .poll = skcipher_poll, +}; + static void *skcipher_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_skcipher(name, type, mask); + struct skcipher_tfm *tfm; + struct crypto_skcipher *skcipher; + + tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); + if (!tfm) + return ERR_PTR(-ENOMEM); + + skcipher = crypto_alloc_skcipher(name, type, mask); + if (IS_ERR(skcipher)) { + kfree(tfm); + return ERR_CAST(skcipher); + } + + tfm->skcipher = skcipher; + + return tfm; } static void skcipher_release(void *private) { - crypto_free_skcipher(private); + struct skcipher_tfm *tfm = private; + + crypto_free_skcipher(tfm->skcipher); + kfree(tfm); } static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_skcipher_setkey(private, key, keylen); + struct skcipher_tfm *tfm = private; + int err; + + err = crypto_skcipher_setkey(tfm->skcipher, key, keylen); + tfm->has_key = !err; + + return err; } static void skcipher_wait(struct sock *sk) @@ -788,24 +917,26 @@ static void skcipher_sock_destruct(struct sock *sk) af_alg_release_parent(sk); } -static int skcipher_accept_parent(void *private, struct sock *sk) +static int skcipher_accept_parent_nokey(void *private, struct sock *sk) { struct skcipher_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(private); + struct skcipher_tfm *tfm = private; + struct crypto_skcipher *skcipher = tfm->skcipher; + unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(skcipher); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; - ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(private), + ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(skcipher), GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } - memset(ctx->iv, 0, crypto_skcipher_ivsize(private)); + memset(ctx->iv, 0, crypto_skcipher_ivsize(skcipher)); INIT_LIST_HEAD(&ctx->tsgl); ctx->len = len; @@ -818,8 +949,9 @@ static int skcipher_accept_parent(void *private, struct sock *sk) ask->private = ctx; - skcipher_request_set_tfm(&ctx->req, private); - skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, + skcipher_request_set_tfm(&ctx->req, skcipher); + skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_SLEEP | + CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); sk->sk_destruct = skcipher_sock_destruct; @@ -827,12 +959,24 @@ static int skcipher_accept_parent(void *private, struct sock *sk) return 0; } +static int skcipher_accept_parent(void *private, struct sock *sk) +{ + struct skcipher_tfm *tfm = private; + + if (!tfm->has_key && crypto_skcipher_has_setkey(tfm->skcipher)) + return -ENOKEY; + + return skcipher_accept_parent_nokey(private, sk); +} + static const struct af_alg_type algif_type_skcipher = { .bind = skcipher_bind, .release = skcipher_release, .setkey = skcipher_setkey, .accept = skcipher_accept_parent, + .accept_nokey = skcipher_accept_parent_nokey, .ops = &algif_skcipher_ops, + .ops_nokey = &algif_skcipher_ops_nokey, .name = "skcipher", .owner = THIS_MODULE }; diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c index 90d6d47965b0..ecdb5a2ce085 100644 --- a/crypto/asymmetric_keys/pkcs7_trust.c +++ b/crypto/asymmetric_keys/pkcs7_trust.c @@ -178,6 +178,8 @@ int pkcs7_validate_trust(struct pkcs7_message *pkcs7, int cached_ret = -ENOKEY; int ret; + *_trusted = false; + for (p = pkcs7->certs; p; p = p->next) p->seen = false; diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 021d39c0ba75..13c4e5a5fe8c 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -494,7 +494,7 @@ int x509_decode_time(time64_t *_t, size_t hdrlen, unsigned char tag, const unsigned char *value, size_t vlen) { - static const unsigned char month_lengths[] = { 31, 29, 31, 30, 31, 30, + static const unsigned char month_lengths[] = { 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 }; const unsigned char *p = value; unsigned year, mon, day, hour, min, sec, mon_len; @@ -540,9 +540,9 @@ int x509_decode_time(time64_t *_t, size_t hdrlen, if (year % 4 == 0) { mon_len = 29; if (year % 100 == 0) { - year /= 100; - if (year % 4 != 0) - mon_len = 28; + mon_len = 28; + if (year % 400 == 0) + mon_len = 29; } } } diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c index 06f1b60f02b2..4c0a0e271876 100644 --- a/crypto/crc32c_generic.c +++ b/crypto/crc32c_generic.c @@ -172,4 +172,3 @@ MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CRYPTO("crc32c"); MODULE_ALIAS_CRYPTO("crc32c-generic"); -MODULE_SOFTDEP("pre: crc32c"); diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 237f3795cfaa..43fe85f20d57 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -499,6 +499,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (link->dump == NULL) return -EINVAL; + down_read(&crypto_alg_sem); list_for_each_entry(alg, &crypto_alg_list, cra_list) dump_alloc += CRYPTO_REPORT_MAXSIZE; @@ -508,8 +509,11 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) .done = link->done, .min_dump_alloc = dump_alloc, }; - return netlink_dump_start(crypto_nlsk, skb, nlh, &c); + err = netlink_dump_start(crypto_nlsk, skb, nlh, &c); } + up_read(&crypto_alg_sem); + + return err; } err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX, diff --git a/crypto/keywrap.c b/crypto/keywrap.c index b1d106ce55f3..72014f963ba7 100644 --- a/crypto/keywrap.c +++ b/crypto/keywrap.c @@ -212,7 +212,7 @@ static int crypto_kw_decrypt(struct blkcipher_desc *desc, SEMIBSIZE)) ret = -EBADMSG; - memzero_explicit(&block, sizeof(struct crypto_kw_block)); + memzero_explicit(block, sizeof(struct crypto_kw_block)); return ret; } @@ -297,7 +297,7 @@ static int crypto_kw_encrypt(struct blkcipher_desc *desc, /* establish the IV for the caller to pick up */ memcpy(desc->info, block->A, SEMIBSIZE); - memzero_explicit(&block, sizeof(struct crypto_kw_block)); + memzero_explicit(block, sizeof(struct crypto_kw_block)); return 0; } diff --git a/crypto/shash.c b/crypto/shash.c index ecb1e3d39bf0..359754591653 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -354,9 +354,10 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm) crt->final = shash_async_final; crt->finup = shash_async_finup; crt->digest = shash_async_digest; + crt->setkey = shash_async_setkey; + + crt->has_setkey = alg->setkey != shash_no_setkey; - if (alg->setkey) - crt->setkey = shash_async_setkey; if (alg->export) crt->export = shash_async_export; if (alg->import) diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 7591928be7ca..d199c0b1751c 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -118,6 +118,7 @@ static int crypto_init_skcipher_ops_blkcipher(struct crypto_tfm *tfm) skcipher->decrypt = skcipher_decrypt_blkcipher; skcipher->ivsize = crypto_blkcipher_ivsize(blkcipher); + skcipher->has_setkey = calg->cra_blkcipher.max_keysize; return 0; } @@ -210,6 +211,7 @@ static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm) skcipher->ivsize = crypto_ablkcipher_ivsize(ablkcipher); skcipher->reqsize = crypto_ablkcipher_reqsize(ablkcipher) + sizeof(struct ablkcipher_request); + skcipher->has_setkey = calg->cra_ablkcipher.max_keysize; return 0; } diff --git a/drivers/Kconfig b/drivers/Kconfig index 3c363e559864..d2ac339de85f 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -104,8 +104,6 @@ source "drivers/memstick/Kconfig" source "drivers/leds/Kconfig" -source "drivers/switch/Kconfig" - source "drivers/accessibility/Kconfig" source "drivers/infiniband/Kconfig" diff --git a/drivers/Makefile b/drivers/Makefile index 8acfb530993d..795d0ca714bf 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -122,7 +122,6 @@ obj-$(CONFIG_CPU_IDLE) += cpuidle/ obj-y += mmc/ obj-$(CONFIG_MEMSTICK) += memstick/ obj-y += leds/ -obj-$(CONFIG_SWITCH) += switch/ obj-$(CONFIG_INFINIBAND) += infiniband/ obj-$(CONFIG_SGI_SN) += sn/ obj-y += firmware/ diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 6979186dbd4b..9f77943653fb 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -491,6 +491,58 @@ static void acpi_processor_remove(struct acpi_device *device) } #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#ifdef CONFIG_X86 +static bool acpi_hwp_native_thermal_lvt_set; +static acpi_status __init acpi_hwp_native_thermal_lvt_osc(acpi_handle handle, + u32 lvl, + void *context, + void **rv) +{ + u8 sb_uuid_str[] = "4077A616-290C-47BE-9EBD-D87058713953"; + u32 capbuf[2]; + struct acpi_osc_context osc_context = { + .uuid_str = sb_uuid_str, + .rev = 1, + .cap.length = 8, + .cap.pointer = capbuf, + }; + + if (acpi_hwp_native_thermal_lvt_set) + return AE_CTRL_TERMINATE; + + capbuf[0] = 0x0000; + capbuf[1] = 0x1000; /* set bit 12 */ + + if (ACPI_SUCCESS(acpi_run_osc(handle, &osc_context))) { + if (osc_context.ret.pointer && osc_context.ret.length > 1) { + u32 *capbuf_ret = osc_context.ret.pointer; + + if (capbuf_ret[1] & 0x1000) { + acpi_handle_info(handle, + "_OSC native thermal LVT Acked\n"); + acpi_hwp_native_thermal_lvt_set = true; + } + } + kfree(osc_context.ret.pointer); + } + + return AE_OK; +} + +void __init acpi_early_processor_osc(void) +{ + if (boot_cpu_has(X86_FEATURE_HWP)) { + acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, + acpi_hwp_native_thermal_lvt_osc, + NULL, NULL, NULL); + acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID, + acpi_hwp_native_thermal_lvt_osc, + NULL, NULL); + } +} +#endif + /* * The following ACPI IDs are known to be suitable for representing as * processor devices. diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 3405f7a41e25..5fdac394207a 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -465,6 +465,15 @@ static struct dmi_system_id video_dmi_table[] = { * as brightness control does not work. */ { + /* https://bugzilla.kernel.org/show_bug.cgi?id=21012 */ + .callback = video_disable_backlight_sysfs_if, + .ident = "Toshiba Portege R700", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE R700"), + }, + }, + { /* https://bugs.freedesktop.org/show_bug.cgi?id=82634 */ .callback = video_disable_backlight_sysfs_if, .ident = "Toshiba Portege R830", @@ -473,6 +482,15 @@ static struct dmi_system_id video_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE R830"), }, }, + { + /* https://bugzilla.kernel.org/show_bug.cgi?id=21012 */ + .callback = video_disable_backlight_sysfs_if, + .ident = "Toshiba Satellite R830", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE R830"), + }, + }, /* * Some machine's _DOD IDs don't have bit 31(Device ID Scheme) set * but the IDs actually follow the Device ID Scheme. diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index bc32f3194afe..28c50c6b5f45 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -417,6 +417,9 @@ acpi_ds_begin_method_execution(struct acpi_namespace_node *method_node, obj_desc->method.mutex->mutex. original_sync_level = obj_desc->method.mutex->mutex.sync_level; + + obj_desc->method.mutex->mutex.thread_id = + acpi_os_get_thread_id(); } } diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index a212cefae524..ca4f28432d87 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1004,6 +1004,9 @@ static int __init acpi_bus_init(void) goto error1; } + /* Set capability bits for _OSC under processor scope */ + acpi_early_processor_osc(); + /* * _OSC method may exist in module level code, * so it must be run after ACPI_FULL_INITIALIZATION diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 11d87bf67e73..0f3f41c13b38 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -130,6 +130,12 @@ void acpi_early_processor_set_pdc(void); static inline void acpi_early_processor_set_pdc(void) {} #endif +#ifdef CONFIG_X86 +void acpi_early_processor_osc(void); +#else +static inline void acpi_early_processor_osc(void) {} +#endif + /* -------------------------------------------------------------------------- Embedded Controller -------------------------------------------------------------------------- */ diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index aa45d4802707..11d8209e6e5d 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -468,37 +468,16 @@ static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc, nfit_mem->bdw = NULL; } -static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, +static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa) { u16 dcr = __to_nfit_memdev(nfit_mem)->region_index; struct nfit_memdev *nfit_memdev; struct nfit_flush *nfit_flush; - struct nfit_dcr *nfit_dcr; struct nfit_bdw *nfit_bdw; struct nfit_idt *nfit_idt; u16 idt_idx, range_index; - list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { - if (nfit_dcr->dcr->region_index != dcr) - continue; - nfit_mem->dcr = nfit_dcr->dcr; - break; - } - - if (!nfit_mem->dcr) { - dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n", - spa->range_index, __to_nfit_memdev(nfit_mem) - ? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR"); - return -ENODEV; - } - - /* - * We've found enough to create an nvdimm, optionally - * find an associated BDW - */ - list_add(&nfit_mem->list, &acpi_desc->dimms); - list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) { if (nfit_bdw->bdw->region_index != dcr) continue; @@ -507,12 +486,12 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } if (!nfit_mem->bdw) - return 0; + return; nfit_mem_find_spa_bdw(acpi_desc, nfit_mem); if (!nfit_mem->spa_bdw) - return 0; + return; range_index = nfit_mem->spa_bdw->range_index; list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { @@ -537,8 +516,6 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } break; } - - return 0; } static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, @@ -547,7 +524,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, *found; struct nfit_memdev *nfit_memdev; int type = nfit_spa_type(spa); - u16 dcr; switch (type) { case NFIT_SPA_DCR: @@ -558,14 +534,18 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, } list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { - int rc; + struct nfit_dcr *nfit_dcr; + u32 device_handle; + u16 dcr; if (nfit_memdev->memdev->range_index != spa->range_index) continue; found = NULL; dcr = nfit_memdev->memdev->region_index; + device_handle = nfit_memdev->memdev->device_handle; list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) - if (__to_nfit_memdev(nfit_mem)->region_index == dcr) { + if (__to_nfit_memdev(nfit_mem)->device_handle + == device_handle) { found = nfit_mem; break; } @@ -578,6 +558,31 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, if (!nfit_mem) return -ENOMEM; INIT_LIST_HEAD(&nfit_mem->list); + list_add(&nfit_mem->list, &acpi_desc->dimms); + } + + list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { + if (nfit_dcr->dcr->region_index != dcr) + continue; + /* + * Record the control region for the dimm. For + * the ACPI 6.1 case, where there are separate + * control regions for the pmem vs blk + * interfaces, be sure to record the extended + * blk details. + */ + if (!nfit_mem->dcr) + nfit_mem->dcr = nfit_dcr->dcr; + else if (nfit_mem->dcr->windows == 0 + && nfit_dcr->dcr->windows) + nfit_mem->dcr = nfit_dcr->dcr; + break; + } + + if (dcr && !nfit_mem->dcr) { + dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n", + spa->range_index, dcr); + return -ENODEV; } if (type == NFIT_SPA_DCR) { @@ -594,6 +599,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, nfit_mem->idt_dcr = nfit_idt->idt; break; } + nfit_mem_init_bdw(acpi_desc, nfit_mem, spa); } else { /* * A single dimm may belong to multiple SPA-PM @@ -602,13 +608,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, */ nfit_mem->memdev_pmem = nfit_memdev->memdev; } - - if (found) - continue; - - rc = nfit_mem_add(acpi_desc, nfit_mem, spa); - if (rc) - return rc; } return 0; diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index c9336751e5e3..8a10a7ae6a8a 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -409,7 +409,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev) return 0; } - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; entry = acpi_pci_irq_lookup(dev, pin); @@ -454,7 +454,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev) kfree(entry); return rc; } - pci_set_managed_irq(dev, rc); + dev->irq = rc; + dev->irq_managed = 1; if (link) snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link); @@ -477,9 +478,17 @@ void acpi_pci_irq_disable(struct pci_dev *dev) u8 pin; pin = dev->pin; - if (!pin || !pci_has_managed_irq(dev)) + if (!pin || !dev->irq_managed || dev->irq <= 0) return; + /* Keep IOAPIC pin configuration when suspending */ + if (dev->dev.power.is_prepared) + return; +#ifdef CONFIG_PM + if (dev->dev.power.runtime_status == RPM_SUSPENDING) + return; +#endif + entry = acpi_pci_irq_lookup(dev, pin); if (!entry) return; @@ -499,6 +508,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev) dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin)); if (gsi >= 0) { acpi_unregister_gsi(gsi); - pci_reset_managed_irq(dev); + dev->irq_managed = 0; } } diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index cdc5c2599beb..627f8fbb5e9a 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -26,8 +26,20 @@ #ifdef CONFIG_X86 #define valid_IRQ(i) (((i) != 0) && ((i) != 2)) +static inline bool acpi_iospace_resource_valid(struct resource *res) +{ + /* On X86 IO space is limited to the [0 - 64K] IO port range */ + return res->end < 0x10003; +} #else #define valid_IRQ(i) (true) +/* + * ACPI IO descriptors on arches other than X86 contain MMIO CPU physical + * addresses mapping IO space in CPU physical address space, IO space + * resources can be placed anywhere in the 64-bit physical address space. + */ +static inline bool +acpi_iospace_resource_valid(struct resource *res) { return true; } #endif static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io) @@ -126,7 +138,7 @@ static void acpi_dev_ioresource_flags(struct resource *res, u64 len, if (!acpi_dev_resource_len_valid(res->start, res->end, len, true)) res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; - if (res->end >= 0x10003) + if (!acpi_iospace_resource_valid(res)) res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; if (io_decode == ACPI_DECODE_16) diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 0d94621dc856..e3322adaaae0 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -714,6 +714,7 @@ static int acpi_hibernation_enter(void) static void acpi_hibernation_leave(void) { + pm_set_resume_via_firmware(); /* * If ACPI is not enabled by the BIOS and the boot kernel, we need to * enable it here. diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index daaf1c4e1e0f..80e55cb0827b 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -135,14 +135,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"), }, }, - { - .callback = video_detect_force_vendor, - .ident = "Dell Inspiron 5737", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"), - }, - }, /* * These models have a working acpi_video backlight control, and using diff --git a/drivers/android/binder.c b/drivers/android/binder.c index f0ce9959d14d..57f52a2afa35 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2081,7 +2081,7 @@ static int binder_thread_write(struct binder_proc *proc, if (get_user(cookie, (binder_uintptr_t __user *)ptr)) return -EFAULT; - ptr += sizeof(void *); + ptr += sizeof(cookie); list_for_each_entry(w, &proc->delivered_death, entry) { struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work); diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index cdfbcc54821f..60a15831c009 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -264,6 +264,26 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */ + { PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */ { PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */ @@ -347,15 +367,21 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d2), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d6), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 04975b851c23..639adb1f8abd 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -51,6 +51,9 @@ static int ahci_probe(struct platform_device *pdev) if (rc) return rc; + of_property_read_u32(dev->of_node, + "ports-implemented", &hpriv->force_port_map); + if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci")) hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ; diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index e2c6d9e0c5ac..e916bff6cee8 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -739,9 +739,9 @@ static int xgene_ahci_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "%s: Error reading device info. Assume version1\n", __func__); version = XGENE_AHCI_V1; - } - if (info->valid & ACPI_VALID_CID) + } else if (info->valid & ACPI_VALID_CID) { version = XGENE_AHCI_V2; + } } } #endif diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 4665512dae44..9628fa131757 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -467,6 +467,7 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) dev_info(dev, "forcing port_map 0x%x -> 0x%x\n", port_map, hpriv->force_port_map); port_map = hpriv->force_port_map; + hpriv->saved_port_map = port_map; } if (hpriv->mask_port_map) { @@ -495,8 +496,8 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) } } - /* fabricate port_map from cap.nr_ports */ - if (!port_map) { + /* fabricate port_map from cap.nr_ports for < AHCI 1.3 */ + if (!port_map && vers < 0x10300) { port_map = (1 << ahci_nr_ports(cap)) - 1; dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map); @@ -1142,8 +1143,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, /* mark esata ports */ tmp = readl(port_mmio + PORT_CMD); - if ((tmp & PORT_CMD_HPCP) || - ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS))) + if ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS)) ap->pflags |= ATA_PFLAG_EXTERNAL; } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7e959f90c020..e417e1a1d02c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -675,19 +675,18 @@ static int ata_ioc32(struct ata_port *ap) int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev, int cmd, void __user *arg) { - int val = -EINVAL, rc = -EINVAL; + unsigned long val; + int rc = -EINVAL; unsigned long flags; switch (cmd) { - case ATA_IOC_GET_IO32: + case HDIO_GET_32BIT: spin_lock_irqsave(ap->lock, flags); val = ata_ioc32(ap); spin_unlock_irqrestore(ap->lock, flags); - if (copy_to_user(arg, &val, 1)) - return -EFAULT; - return 0; + return put_user(val, (unsigned long __user *)arg); - case ATA_IOC_SET_IO32: + case HDIO_SET_32BIT: val = (unsigned long) arg; rc = 0; spin_lock_irqsave(ap->lock, flags); diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index cdf6215a9a22..7dbba387d12a 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -997,12 +997,9 @@ static inline int ata_hsm_ok_in_wq(struct ata_port *ap, static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) { struct ata_port *ap = qc->ap; - unsigned long flags; if (ap->ops->error_handler) { if (in_wq) { - spin_lock_irqsave(ap->lock, flags); - /* EH might have kicked in while host lock is * released. */ @@ -1014,8 +1011,6 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) } else ata_port_freeze(ap); } - - spin_unlock_irqrestore(ap->lock, flags); } else { if (likely(!(qc->err_mask & AC_ERR_HSM))) ata_qc_complete(qc); @@ -1024,10 +1019,8 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) } } else { if (in_wq) { - spin_lock_irqsave(ap->lock, flags); ata_sff_irq_on(ap); ata_qc_complete(qc); - spin_unlock_irqrestore(ap->lock, flags); } else ata_qc_complete(qc); } @@ -1048,9 +1041,10 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, { struct ata_link *link = qc->dev->link; struct ata_eh_info *ehi = &link->eh_info; - unsigned long flags = 0; int poll_next; + lockdep_assert_held(ap->lock); + WARN_ON_ONCE((qc->flags & ATA_QCFLAG_ACTIVE) == 0); /* Make sure ata_sff_qc_issue() does not throw things @@ -1112,14 +1106,6 @@ fsm_start: } } - /* Send the CDB (atapi) or the first data block (ata pio out). - * During the state transition, interrupt handler shouldn't - * be invoked before the data transfer is complete and - * hsm_task_state is changed. Hence, the following locking. - */ - if (in_wq) - spin_lock_irqsave(ap->lock, flags); - if (qc->tf.protocol == ATA_PROT_PIO) { /* PIO data out protocol. * send first data block. @@ -1135,9 +1121,6 @@ fsm_start: /* send CDB */ atapi_send_cdb(ap, qc); - if (in_wq) - spin_unlock_irqrestore(ap->lock, flags); - /* if polling, ata_sff_pio_task() handles the rest. * otherwise, interrupt handler takes over from here. */ @@ -1361,12 +1344,14 @@ static void ata_sff_pio_task(struct work_struct *work) u8 status; int poll_next; + spin_lock_irq(ap->lock); + BUG_ON(ap->sff_pio_task_link == NULL); /* qc can be NULL if timeout occurred */ qc = ata_qc_from_tag(ap, link->active_tag); if (!qc) { ap->sff_pio_task_link = NULL; - return; + goto out_unlock; } fsm_start: @@ -1381,11 +1366,14 @@ fsm_start: */ status = ata_sff_busy_wait(ap, ATA_BUSY, 5); if (status & ATA_BUSY) { + spin_unlock_irq(ap->lock); ata_msleep(ap, 2); + spin_lock_irq(ap->lock); + status = ata_sff_busy_wait(ap, ATA_BUSY, 10); if (status & ATA_BUSY) { ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE); - return; + goto out_unlock; } } @@ -1402,6 +1390,8 @@ fsm_start: */ if (poll_next) goto fsm_start; +out_unlock: + spin_unlock_irq(ap->lock); } /** diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c index 12fe0f3bb7e9..c8b6a780a290 100644 --- a/drivers/ata/pata_rb532_cf.c +++ b/drivers/ata/pata_rb532_cf.c @@ -32,6 +32,8 @@ #include <linux/libata.h> #include <scsi/scsi_host.h> +#include <asm/mach-rc32434/rb.h> + #define DRV_NAME "pata-rb532-cf" #define DRV_VERSION "0.1.0" #define DRV_DESC "PATA driver for RouterBOARD 532 Compact Flash" @@ -107,6 +109,7 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) int gpio; struct resource *res; struct ata_host *ah; + struct cf_device *pdata; struct rb532_cf_info *info; int ret; @@ -122,7 +125,13 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) return -ENOENT; } - gpio = irq_to_gpio(irq); + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + dev_err(&pdev->dev, "no platform data specified\n"); + return -EINVAL; + } + + gpio = pdata->gpio_pin; if (gpio < 0) { dev_err(&pdev->dev, "no GPIO found for irq%d\n", irq); return -ENOENT; diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 1dd6d3bf1098..176b59f5bc47 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -513,10 +513,15 @@ static int platform_drv_probe(struct device *_dev) return ret; ret = dev_pm_domain_attach(_dev, true); - if (ret != -EPROBE_DEFER && drv->probe) { - ret = drv->probe(dev); - if (ret) - dev_pm_domain_detach(_dev, true); + if (ret != -EPROBE_DEFER) { + if (drv->probe) { + ret = drv->probe(dev); + if (ret) + dev_pm_domain_detach(_dev, true); + } else { + /* don't fail if just dev_pm_domain_attach failed */ + ret = 0; + } } if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) { diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 65f50eccd49b..a48824deabc5 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1381,7 +1381,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, mutex_lock(&genpd->lock); - if (!list_empty(&subdomain->slave_links) || subdomain->device_count) { + if (!list_empty(&subdomain->master_links) || subdomain->device_count) { pr_warn("%s: unable to remove subdomain %s\n", genpd->name, subdomain->name); ret = -EBUSY; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 6ed8b9326629..2f7a6e1b568c 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -62,12 +62,6 @@ struct suspend_stats suspend_stats; static DEFINE_MUTEX(dpm_list_mtx); static pm_message_t pm_transition; -static void dpm_drv_timeout(unsigned long data); -struct dpm_drv_wd_data { - struct device *dev; - struct task_struct *tsk; -}; - static int async_error; static char *pm_verb(int event) @@ -839,30 +833,6 @@ static void async_resume(void *data, async_cookie_t cookie) } /** - * dpm_drv_timeout - Driver suspend / resume watchdog handler - * @data: struct device which timed out - * - * Called when a driver has timed out suspending or resuming. - * There's not much we can do here to recover so - * BUG() out for a crash-dump - * - */ -static void dpm_drv_timeout(unsigned long data) -{ - struct dpm_drv_wd_data *wd_data = (void *)data; - struct device *dev = wd_data->dev; - struct task_struct *tsk = wd_data->tsk; - - printk(KERN_EMERG "**** DPM device timeout: %s (%s)\n", dev_name(dev), - (dev->driver ? dev->driver->name : "no driver")); - - printk(KERN_EMERG "dpm suspend stack:\n"); - show_stack(tsk, NULL); - - BUG(); -} - -/** * dpm_resume - Execute "resume" callbacks for non-sysdev devices. * @state: PM transition of the system being carried out. * @@ -1380,8 +1350,6 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) pm_callback_t callback = NULL; char *info = NULL; int error = 0; - struct timer_list timer; - struct dpm_drv_wd_data data; char suspend_abort[MAX_SUSPEND_ABORT_LEN]; DECLARE_DPM_WATCHDOG_ON_STACK(wd); @@ -1412,14 +1380,6 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) if (dev->power.syscore) goto Complete; - - data.dev = dev; - data.tsk = current; - init_timer_on_stack(&timer); - timer.expires = jiffies + HZ * 12; - timer.function = dpm_drv_timeout; - timer.data = (unsigned long)&data; - add_timer(&timer); if (dev->power.direct_complete) { if (pm_runtime_status_suspended(dev)) { @@ -1500,9 +1460,6 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) device_unlock(dev); dpm_watchdog_clear(&wd); - del_timer_sync(&timer); - destroy_timer_on_stack(&timer); - Complete: complete_all(&dev->power.completion); if (error) diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index b8e76f75073b..f8580900c273 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -809,8 +809,14 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev) } opp->u_volt = microvolt[0]; - opp->u_volt_min = microvolt[1]; - opp->u_volt_max = microvolt[2]; + + if (count == 1) { + opp->u_volt_min = opp->u_volt; + opp->u_volt_max = opp->u_volt; + } else { + opp->u_volt_min = microvolt[1]; + opp->u_volt_max = microvolt[2]; + } if (!of_property_read_u32(opp->np, "opp-microamp", &val)) opp->u_amp = val; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index a5880f4ab40e..1914c63ca8b1 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -338,7 +338,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) if (unlikely(bio->bi_rw & REQ_DISCARD)) { if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) || - bio->bi_iter.bi_size & PAGE_MASK) + bio->bi_iter.bi_size & ~PAGE_MASK) goto io_error; discard_from_brd(brd, sector, bio->bi_iter.bi_size); goto out; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 423f4ca7d712..80cf8add46ff 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -488,6 +488,12 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); iov_iter_bvec(&iter, ITER_BVEC | rw, bvec, bio_segments(bio), blk_rq_bytes(cmd->rq)); + /* + * This bio may be started from the middle of the 'bvec' + * because of bio splitting, so offset from the bvec must + * be passed to iov iterator + */ + iter.iov_offset = bio->bi_iter.bi_bvec_done; cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 3457ac8c03e2..55d3d1da72de 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -173,7 +173,13 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd) { struct request *rq; + if (mtip_check_surprise_removal(dd->pdev)) + return NULL; + rq = blk_mq_alloc_request(dd->queue, 0, __GFP_RECLAIM, true); + if (IS_ERR(rq)) + return NULL; + return blk_mq_rq_to_pdu(rq); } @@ -233,15 +239,9 @@ static void mtip_async_complete(struct mtip_port *port, "Command tag %d failed due to TFE\n", tag); } - /* Unmap the DMA scatter list entries */ - dma_unmap_sg(&dd->pdev->dev, cmd->sg, cmd->scatter_ents, cmd->direction); - rq = mtip_rq_from_tag(dd, tag); - if (unlikely(cmd->unaligned)) - up(&port->cmd_slot_unal); - - blk_mq_end_request(rq, status ? -EIO : 0); + blk_mq_complete_request(rq, status); } /* @@ -581,6 +581,8 @@ static void mtip_completion(struct mtip_port *port, dev_warn(&port->dd->pdev->dev, "Internal command %d completed with TFE\n", tag); + command->comp_func = NULL; + command->comp_data = NULL; complete(waiting); } @@ -618,8 +620,6 @@ static void mtip_handle_tfe(struct driver_data *dd) port = dd->port; - set_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags); - if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) { cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL); dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n"); @@ -628,7 +628,7 @@ static void mtip_handle_tfe(struct driver_data *dd) cmd->comp_func(port, MTIP_TAG_INTERNAL, cmd, PORT_IRQ_TF_ERR); } - goto handle_tfe_exit; + return; } /* clear the tag accumulator */ @@ -701,7 +701,7 @@ static void mtip_handle_tfe(struct driver_data *dd) fail_reason = "thermal shutdown"; } if (buf[288] == 0xBF) { - set_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag); + set_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag); dev_info(&dd->pdev->dev, "Drive indicates rebuild has failed. Secure erase required.\n"); fail_all_ncq_cmds = 1; @@ -771,11 +771,6 @@ static void mtip_handle_tfe(struct driver_data *dd) } } print_tags(dd, "reissued (TFE)", tagaccum, cmd_cnt); - -handle_tfe_exit: - /* clear eh_active */ - clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags); - wake_up_interruptible(&port->svc_wait); } /* @@ -1007,6 +1002,7 @@ static bool mtip_pause_ncq(struct mtip_port *port, (fis->features == 0x27 || fis->features == 0x72 || fis->features == 0x62 || fis->features == 0x26))) { clear_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag); + clear_bit(MTIP_DDF_REBUILD_FAILED_BIT, &port->dd->dd_flag); /* Com reset after secure erase or lowlevel format */ mtip_restart_port(port); clear_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags); @@ -1021,12 +1017,14 @@ static bool mtip_pause_ncq(struct mtip_port *port, * * @port Pointer to port data structure * @timeout Max duration to wait (ms) + * @atomic gfp_t flag to indicate blockable context or not * * return value * 0 Success * -EBUSY Commands still active */ -static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout) +static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout, + gfp_t atomic) { unsigned long to; unsigned int n; @@ -1037,16 +1035,21 @@ static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout) to = jiffies + msecs_to_jiffies(timeout); do { if (test_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags) && - test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) { + test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags) && + atomic == GFP_KERNEL) { msleep(20); continue; /* svc thd is actively issuing commands */ } - msleep(100); + if (atomic == GFP_KERNEL) + msleep(100); + else { + cpu_relax(); + udelay(100); + } + if (mtip_check_surprise_removal(port->dd->pdev)) goto err_fault; - if (test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &port->dd->dd_flag)) - goto err_fault; /* * Ignore s_active bit 0 of array element 0. @@ -1099,6 +1102,7 @@ static int mtip_exec_internal_command(struct mtip_port *port, struct mtip_cmd *int_cmd; struct driver_data *dd = port->dd; int rv = 0; + unsigned long start; /* Make sure the buffer is 8 byte aligned. This is asic specific. */ if (buffer & 0x00000007) { @@ -1107,6 +1111,10 @@ static int mtip_exec_internal_command(struct mtip_port *port, } int_cmd = mtip_get_int_command(dd); + if (!int_cmd) { + dbg_printk(MTIP_DRV_NAME "Unable to allocate tag for PIO cmd\n"); + return -EFAULT; + } set_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags); @@ -1119,7 +1127,7 @@ static int mtip_exec_internal_command(struct mtip_port *port, if (fis->command != ATA_CMD_STANDBYNOW1) { /* wait for io to complete if non atomic */ if (mtip_quiesce_io(port, - MTIP_QUIESCE_IO_TIMEOUT_MS) < 0) { + MTIP_QUIESCE_IO_TIMEOUT_MS, atomic) < 0) { dev_warn(&dd->pdev->dev, "Failed to quiesce IO\n"); mtip_put_int_command(dd, int_cmd); @@ -1162,6 +1170,8 @@ static int mtip_exec_internal_command(struct mtip_port *port, /* Populate the command header */ int_cmd->command_header->byte_count = 0; + start = jiffies; + /* Issue the command to the hardware */ mtip_issue_non_ncq_command(port, MTIP_TAG_INTERNAL); @@ -1170,10 +1180,12 @@ static int mtip_exec_internal_command(struct mtip_port *port, if ((rv = wait_for_completion_interruptible_timeout( &wait, msecs_to_jiffies(timeout))) <= 0) { + if (rv == -ERESTARTSYS) { /* interrupted */ dev_err(&dd->pdev->dev, - "Internal command [%02X] was interrupted after %lu ms\n", - fis->command, timeout); + "Internal command [%02X] was interrupted after %u ms\n", + fis->command, + jiffies_to_msecs(jiffies - start)); rv = -EINTR; goto exec_ic_exit; } else if (rv == 0) /* timeout */ @@ -2897,6 +2909,42 @@ static int mtip_ftl_rebuild_poll(struct driver_data *dd) return -EFAULT; } +static void mtip_softirq_done_fn(struct request *rq) +{ + struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq); + struct driver_data *dd = rq->q->queuedata; + + /* Unmap the DMA scatter list entries */ + dma_unmap_sg(&dd->pdev->dev, cmd->sg, cmd->scatter_ents, + cmd->direction); + + if (unlikely(cmd->unaligned)) + up(&dd->port->cmd_slot_unal); + + blk_mq_end_request(rq, rq->errors); +} + +static void mtip_abort_cmd(struct request *req, void *data, + bool reserved) +{ + struct driver_data *dd = data; + + dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag); + + clear_bit(req->tag, dd->port->cmds_to_issue); + req->errors = -EIO; + mtip_softirq_done_fn(req); +} + +static void mtip_queue_cmd(struct request *req, void *data, + bool reserved) +{ + struct driver_data *dd = data; + + set_bit(req->tag, dd->port->cmds_to_issue); + blk_abort_request(req); +} + /* * service thread to issue queued commands * @@ -2909,7 +2957,7 @@ static int mtip_ftl_rebuild_poll(struct driver_data *dd) static int mtip_service_thread(void *data) { struct driver_data *dd = (struct driver_data *)data; - unsigned long slot, slot_start, slot_wrap; + unsigned long slot, slot_start, slot_wrap, to; unsigned int num_cmd_slots = dd->slot_groups * 32; struct mtip_port *port = dd->port; @@ -2924,9 +2972,7 @@ static int mtip_service_thread(void *data) * is in progress nor error handling is active */ wait_event_interruptible(port->svc_wait, (port->flags) && - !(port->flags & MTIP_PF_PAUSE_IO)); - - set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags); + (port->flags & MTIP_PF_SVC_THD_WORK)); if (kthread_should_stop() || test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags)) @@ -2936,6 +2982,8 @@ static int mtip_service_thread(void *data) &dd->dd_flag))) goto st_out; + set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags); + restart_eh: /* Demux bits: start with error handling */ if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags)) { @@ -2946,6 +2994,32 @@ restart_eh: if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags)) goto restart_eh; + if (test_bit(MTIP_PF_TO_ACTIVE_BIT, &port->flags)) { + to = jiffies + msecs_to_jiffies(5000); + + do { + mdelay(100); + } while (atomic_read(&dd->irq_workers_active) != 0 && + time_before(jiffies, to)); + + if (atomic_read(&dd->irq_workers_active) != 0) + dev_warn(&dd->pdev->dev, + "Completion workers still active!"); + + spin_lock(dd->queue->queue_lock); + blk_mq_all_tag_busy_iter(*dd->tags.tags, + mtip_queue_cmd, dd); + spin_unlock(dd->queue->queue_lock); + + set_bit(MTIP_PF_ISSUE_CMDS_BIT, &dd->port->flags); + + if (mtip_device_reset(dd)) + blk_mq_all_tag_busy_iter(*dd->tags.tags, + mtip_abort_cmd, dd); + + clear_bit(MTIP_PF_TO_ACTIVE_BIT, &dd->port->flags); + } + if (test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) { slot = 1; /* used to restrict the loop to one iteration */ @@ -2978,10 +3052,8 @@ restart_eh: } if (test_bit(MTIP_PF_REBUILD_BIT, &port->flags)) { - if (mtip_ftl_rebuild_poll(dd) < 0) - set_bit(MTIP_DDF_REBUILD_FAILED_BIT, - &dd->dd_flag); - clear_bit(MTIP_PF_REBUILD_BIT, &port->flags); + if (mtip_ftl_rebuild_poll(dd) == 0) + clear_bit(MTIP_PF_REBUILD_BIT, &port->flags); } } @@ -3096,7 +3168,7 @@ static int mtip_hw_get_identify(struct driver_data *dd) if (buf[288] == 0xBF) { dev_info(&dd->pdev->dev, "Drive indicates rebuild has failed.\n"); - /* TODO */ + set_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag); } } @@ -3270,20 +3342,25 @@ out1: return rv; } -static void mtip_standby_drive(struct driver_data *dd) +static int mtip_standby_drive(struct driver_data *dd) { - if (dd->sr) - return; + int rv = 0; + if (dd->sr || !dd->port) + return -ENODEV; /* * Send standby immediate (E0h) to the drive so that it * saves its state. */ if (!test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags) && - !test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag)) - if (mtip_standby_immediate(dd->port)) + !test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag) && + !test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag)) { + rv = mtip_standby_immediate(dd->port); + if (rv) dev_warn(&dd->pdev->dev, "STANDBY IMMEDIATE failed\n"); + } + return rv; } /* @@ -3296,10 +3373,6 @@ static void mtip_standby_drive(struct driver_data *dd) */ static int mtip_hw_exit(struct driver_data *dd) { - /* - * Send standby immediate (E0h) to the drive so that it - * saves its state. - */ if (!dd->sr) { /* de-initialize the port. */ mtip_deinit_port(dd->port); @@ -3341,8 +3414,7 @@ static int mtip_hw_shutdown(struct driver_data *dd) * Send standby immediate (E0h) to the drive so that it * saves its state. */ - if (!dd->sr && dd->port) - mtip_standby_immediate(dd->port); + mtip_standby_drive(dd); return 0; } @@ -3365,7 +3437,7 @@ static int mtip_hw_suspend(struct driver_data *dd) * Send standby immediate (E0h) to the drive * so that it saves its state. */ - if (mtip_standby_immediate(dd->port) != 0) { + if (mtip_standby_drive(dd) != 0) { dev_err(&dd->pdev->dev, "Failed standby-immediate command\n"); return -EFAULT; @@ -3603,6 +3675,28 @@ static int mtip_block_getgeo(struct block_device *dev, return 0; } +static int mtip_block_open(struct block_device *dev, fmode_t mode) +{ + struct driver_data *dd; + + if (dev && dev->bd_disk) { + dd = (struct driver_data *) dev->bd_disk->private_data; + + if (dd) { + if (test_bit(MTIP_DDF_REMOVAL_BIT, + &dd->dd_flag)) { + return -ENODEV; + } + return 0; + } + } + return -ENODEV; +} + +void mtip_block_release(struct gendisk *disk, fmode_t mode) +{ +} + /* * Block device operation function. * @@ -3610,6 +3704,8 @@ static int mtip_block_getgeo(struct block_device *dev, * layer. */ static const struct block_device_operations mtip_block_ops = { + .open = mtip_block_open, + .release = mtip_block_release, .ioctl = mtip_block_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = mtip_block_compat_ioctl, @@ -3671,10 +3767,9 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq) rq_data_dir(rq))) { return -ENODATA; } - if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag))) + if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag) || + test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag))) return -ENODATA; - if (test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag)) - return -ENXIO; } if (rq->cmd_flags & REQ_DISCARD) { @@ -3786,11 +3881,33 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx, return 0; } +static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req, + bool reserved) +{ + struct driver_data *dd = req->q->queuedata; + int ret = BLK_EH_RESET_TIMER; + + if (reserved) + goto exit_handler; + + if (test_bit(req->tag, dd->port->cmds_to_issue)) + goto exit_handler; + + if (test_and_set_bit(MTIP_PF_TO_ACTIVE_BIT, &dd->port->flags)) + goto exit_handler; + + wake_up_interruptible(&dd->port->svc_wait); +exit_handler: + return ret; +} + static struct blk_mq_ops mtip_mq_ops = { .queue_rq = mtip_queue_rq, .map_queue = blk_mq_map_queue, .init_request = mtip_init_cmd, .exit_request = mtip_free_cmd, + .complete = mtip_softirq_done_fn, + .timeout = mtip_cmd_timeout, }; /* @@ -3857,7 +3974,6 @@ static int mtip_block_initialize(struct driver_data *dd) mtip_hw_debugfs_init(dd); -skip_create_disk: memset(&dd->tags, 0, sizeof(dd->tags)); dd->tags.ops = &mtip_mq_ops; dd->tags.nr_hw_queues = 1; @@ -3867,12 +3983,13 @@ skip_create_disk: dd->tags.numa_node = dd->numa_node; dd->tags.flags = BLK_MQ_F_SHOULD_MERGE; dd->tags.driver_data = dd; + dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS; rv = blk_mq_alloc_tag_set(&dd->tags); if (rv) { dev_err(&dd->pdev->dev, "Unable to allocate request queue\n"); - goto block_queue_alloc_init_error; + goto block_queue_alloc_tag_error; } /* Allocate the request queue. */ @@ -3887,6 +4004,7 @@ skip_create_disk: dd->disk->queue = dd->queue; dd->queue->queuedata = dd; +skip_create_disk: /* Initialize the protocol layer. */ wait_for_rebuild = mtip_hw_get_identify(dd); if (wait_for_rebuild < 0) { @@ -3983,8 +4101,9 @@ kthread_run_error: read_capacity_error: init_hw_cmds_error: blk_cleanup_queue(dd->queue); - blk_mq_free_tag_set(&dd->tags); block_queue_alloc_init_error: + blk_mq_free_tag_set(&dd->tags); +block_queue_alloc_tag_error: mtip_hw_debugfs_exit(dd); disk_index_error: spin_lock(&rssd_index_lock); @@ -4001,6 +4120,22 @@ protocol_init_error: return rv; } +static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv) +{ + struct driver_data *dd = (struct driver_data *)data; + struct mtip_cmd *cmd; + + if (likely(!reserv)) + blk_mq_complete_request(rq, -ENODEV); + else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) { + + cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL); + if (cmd->comp_func) + cmd->comp_func(dd->port, MTIP_TAG_INTERNAL, + cmd, -ENODEV); + } +} + /* * Block layer deinitialization function. * @@ -4032,12 +4167,23 @@ static int mtip_block_remove(struct driver_data *dd) } } - if (!dd->sr) - mtip_standby_drive(dd); + if (!dd->sr) { + /* + * Explicitly wait here for IOs to quiesce, + * as mtip_standby_drive usually won't wait for IOs. + */ + if (!mtip_quiesce_io(dd->port, MTIP_QUIESCE_IO_TIMEOUT_MS, + GFP_KERNEL)) + mtip_standby_drive(dd); + } else dev_info(&dd->pdev->dev, "device %s surprise removal\n", dd->disk->disk_name); + blk_mq_freeze_queue_start(dd->queue); + blk_mq_stop_hw_queues(dd->queue); + blk_mq_all_tag_busy_iter(dd->tags.tags[0], mtip_no_dev_cleanup, dd); + /* * Delete our gendisk structure. This also removes the device * from /dev @@ -4047,7 +4193,8 @@ static int mtip_block_remove(struct driver_data *dd) dd->bdev = NULL; } if (dd->disk) { - del_gendisk(dd->disk); + if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag)) + del_gendisk(dd->disk); if (dd->disk->queue) { blk_cleanup_queue(dd->queue); blk_mq_free_tag_set(&dd->tags); @@ -4088,7 +4235,8 @@ static int mtip_block_shutdown(struct driver_data *dd) dev_info(&dd->pdev->dev, "Shutting down %s ...\n", dd->disk->disk_name); - del_gendisk(dd->disk); + if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag)) + del_gendisk(dd->disk); if (dd->disk->queue) { blk_cleanup_queue(dd->queue); blk_mq_free_tag_set(&dd->tags); @@ -4433,7 +4581,7 @@ static void mtip_pci_remove(struct pci_dev *pdev) struct driver_data *dd = pci_get_drvdata(pdev); unsigned long flags, to; - set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag); + set_bit(MTIP_DDF_REMOVAL_BIT, &dd->dd_flag); spin_lock_irqsave(&dev_lock, flags); list_del_init(&dd->online_list); @@ -4450,12 +4598,17 @@ static void mtip_pci_remove(struct pci_dev *pdev) } while (atomic_read(&dd->irq_workers_active) != 0 && time_before(jiffies, to)); + if (!dd->sr) + fsync_bdev(dd->bdev); + if (atomic_read(&dd->irq_workers_active) != 0) { dev_warn(&dd->pdev->dev, "Completion workers still active!\n"); } - blk_mq_stop_hw_queues(dd->queue); + blk_set_queue_dying(dd->queue); + set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag); + /* Clean up the block layer. */ mtip_block_remove(dd); diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index 3274784008eb..7617888f7944 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -134,16 +134,24 @@ enum { MTIP_PF_EH_ACTIVE_BIT = 1, /* error handling */ MTIP_PF_SE_ACTIVE_BIT = 2, /* secure erase */ MTIP_PF_DM_ACTIVE_BIT = 3, /* download microcde */ + MTIP_PF_TO_ACTIVE_BIT = 9, /* timeout handling */ MTIP_PF_PAUSE_IO = ((1 << MTIP_PF_IC_ACTIVE_BIT) | (1 << MTIP_PF_EH_ACTIVE_BIT) | (1 << MTIP_PF_SE_ACTIVE_BIT) | - (1 << MTIP_PF_DM_ACTIVE_BIT)), + (1 << MTIP_PF_DM_ACTIVE_BIT) | + (1 << MTIP_PF_TO_ACTIVE_BIT)), MTIP_PF_SVC_THD_ACTIVE_BIT = 4, MTIP_PF_ISSUE_CMDS_BIT = 5, MTIP_PF_REBUILD_BIT = 6, MTIP_PF_SVC_THD_STOP_BIT = 8, + MTIP_PF_SVC_THD_WORK = ((1 << MTIP_PF_EH_ACTIVE_BIT) | + (1 << MTIP_PF_ISSUE_CMDS_BIT) | + (1 << MTIP_PF_REBUILD_BIT) | + (1 << MTIP_PF_SVC_THD_STOP_BIT) | + (1 << MTIP_PF_TO_ACTIVE_BIT)), + /* below are bit numbers in 'dd_flag' defined in driver_data */ MTIP_DDF_SEC_LOCK_BIT = 0, MTIP_DDF_REMOVE_PENDING_BIT = 1, @@ -153,6 +161,7 @@ enum { MTIP_DDF_RESUME_BIT = 6, MTIP_DDF_INIT_DONE_BIT = 7, MTIP_DDF_REBUILD_FAILED_BIT = 8, + MTIP_DDF_REMOVAL_BIT = 9, MTIP_DDF_STOP_IO = ((1 << MTIP_DDF_REMOVE_PENDING_BIT) | (1 << MTIP_DDF_SEC_LOCK_BIT) | diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 93b3f99b6865..8f1ce6d57a08 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -618,8 +618,8 @@ static void nbd_request_handler(struct request_queue *q) req, req->cmd_type); if (unlikely(!nbd->sock)) { - dev_err(disk_to_dev(nbd->disk), - "Attempted send on closed socket\n"); + dev_err_ratelimited(disk_to_dev(nbd->disk), + "Attempted send on closed socket\n"); req->errors++; nbd_end_request(nbd, req); spin_lock_irq(q->queue_lock); diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 562b5a4ca7b7..78a39f736c64 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -126,7 +126,7 @@ */ #include <linux/types.h> -static bool verbose = 0; +static int verbose = 0; static int major = PD_MAJOR; static char *name = PD_NAME; static int cluster = 64; @@ -161,7 +161,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_GEO, D_SBY, D_DLY, D_SLV}; static DEFINE_MUTEX(pd_mutex); static DEFINE_SPINLOCK(pd_lock); -module_param(verbose, bool, 0); +module_param(verbose, int, 0); module_param(major, int, 0); module_param(name, charp, 0); module_param(cluster, int, 0); diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c index 1740d75e8a32..216a94fed5b4 100644 --- a/drivers/block/paride/pt.c +++ b/drivers/block/paride/pt.c @@ -117,7 +117,7 @@ */ -static bool verbose = 0; +static int verbose = 0; static int major = PT_MAJOR; static char *name = PT_NAME; static int disable = 0; @@ -152,7 +152,7 @@ static int (*drives[4])[6] = {&drive0, &drive1, &drive2, &drive3}; #include <asm/uaccess.h> -module_param(verbose, bool, 0); +module_param(verbose, int, 0); module_param(major, int, 0); module_param(name, charp, 0); module_param_array(drive0, int, NULL, 0); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 81ea69fee7ca..fbdddd6f94b8 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1955,7 +1955,7 @@ static struct ceph_osd_request *rbd_osd_req_create( osdc = &rbd_dev->rbd_client->client->osdc; osd_req = ceph_osdc_alloc_request(osdc, snapc, num_ops, false, - GFP_ATOMIC); + GFP_NOIO); if (!osd_req) return NULL; /* ENOMEM */ @@ -2004,7 +2004,7 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request) rbd_dev = img_request->rbd_dev; osdc = &rbd_dev->rbd_client->client->osdc; osd_req = ceph_osdc_alloc_request(osdc, snapc, num_osd_ops, - false, GFP_ATOMIC); + false, GFP_NOIO); if (!osd_req) return NULL; /* ENOMEM */ @@ -2506,7 +2506,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request, bio_chain_clone_range(&bio_list, &bio_offset, clone_size, - GFP_ATOMIC); + GFP_NOIO); if (!obj_request->bio_list) goto out_unwind; } else if (type == OBJ_REQUEST_PAGES) { diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 5cb13ca3a3ac..c53617752b93 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -76,7 +76,7 @@ static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm) */ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp) { - struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL); + struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_NOIO); if (!zstrm) return NULL; @@ -85,7 +85,7 @@ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp) * allocate 2 pages. 1 for compressed data, plus 1 extra for the * case when compressed size is larger than the original one */ - zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); + zstrm->buffer = (void *)__get_free_pages(GFP_NOIO | __GFP_ZERO, 1); if (!zstrm->private || !zstrm->buffer) { zcomp_strm_free(comp, zstrm); zstrm = NULL; diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c index f2afb7e988c3..dd6083124276 100644 --- a/drivers/block/zram/zcomp_lz4.c +++ b/drivers/block/zram/zcomp_lz4.c @@ -10,17 +10,36 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/lz4.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> #include "zcomp_lz4.h" static void *zcomp_lz4_create(void) { - return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL); + void *ret; + + /* + * This function can be called in swapout/fs write path + * so we can't use GFP_FS|IO. And it assumes we already + * have at least one stream in zram initialization so we + * don't do best effort to allocate more stream in here. + * A default stream will work well without further multiple + * streams. That's why we use NORETRY | NOWARN. + */ + ret = kzalloc(LZ4_MEM_COMPRESS, GFP_NOIO | __GFP_NORETRY | + __GFP_NOWARN); + if (!ret) + ret = __vmalloc(LZ4_MEM_COMPRESS, + GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN | + __GFP_ZERO | __GFP_HIGHMEM, + PAGE_KERNEL); + return ret; } static void zcomp_lz4_destroy(void *private) { - kfree(private); + kvfree(private); } static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst, diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c index da1bc47d588e..edc549920fa0 100644 --- a/drivers/block/zram/zcomp_lzo.c +++ b/drivers/block/zram/zcomp_lzo.c @@ -10,17 +10,36 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/lzo.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> #include "zcomp_lzo.h" static void *lzo_create(void) { - return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); + void *ret; + + /* + * This function can be called in swapout/fs write path + * so we can't use GFP_FS|IO. And it assumes we already + * have at least one stream in zram initialization so we + * don't do best effort to allocate more stream in here. + * A default stream will work well without further multiple + * streams. That's why we use NORETRY | NOWARN. + */ + ret = kzalloc(LZO1X_MEM_COMPRESS, GFP_NOIO | __GFP_NORETRY | + __GFP_NOWARN); + if (!ret) + ret = __vmalloc(LZO1X_MEM_COMPRESS, + GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN | + __GFP_ZERO | __GFP_HIGHMEM, + PAGE_KERNEL); + return ret; } static void lzo_destroy(void *private) { - kfree(private); + kvfree(private); } static int lzo_compress(const unsigned char *src, unsigned char *dst, diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 47915d736f8d..370c2f76016d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1325,7 +1325,6 @@ static int zram_remove(struct zram *zram) pr_info("Removed device: %s\n", zram->disk->disk_name); - idr_remove(&zram_index_idr, zram->disk->first_minor); blk_cleanup_queue(zram->disk->queue); del_gendisk(zram->disk); put_disk(zram->disk); @@ -1367,10 +1366,12 @@ static ssize_t hot_remove_store(struct class *class, mutex_lock(&zram_index_mutex); zram = idr_find(&zram_index_idr, dev_id); - if (zram) + if (zram) { ret = zram_remove(zram); - else + idr_remove(&zram_index_idr, dev_id); + } else { ret = -ENODEV; + } mutex_unlock(&zram_index_mutex); return ret ? ret : count; diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index fa893c3ec408..0beaa52df66b 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -82,6 +82,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x0489, 0xe05f) }, { USB_DEVICE(0x0489, 0xe076) }, { USB_DEVICE(0x0489, 0xe078) }, + { USB_DEVICE(0x0489, 0xe095) }, { USB_DEVICE(0x04c5, 0x1330) }, { USB_DEVICE(0x04CA, 0x3004) }, { USB_DEVICE(0x04CA, 0x3005) }, @@ -92,6 +93,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x04CA, 0x300d) }, { USB_DEVICE(0x04CA, 0x300f) }, { USB_DEVICE(0x04CA, 0x3010) }, + { USB_DEVICE(0x04CA, 0x3014) }, { USB_DEVICE(0x0930, 0x0219) }, { USB_DEVICE(0x0930, 0x021c) }, { USB_DEVICE(0x0930, 0x0220) }, @@ -113,10 +115,12 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x13d3, 0x3362) }, { USB_DEVICE(0x13d3, 0x3375) }, { USB_DEVICE(0x13d3, 0x3393) }, + { USB_DEVICE(0x13d3, 0x3395) }, { USB_DEVICE(0x13d3, 0x3402) }, { USB_DEVICE(0x13d3, 0x3408) }, { USB_DEVICE(0x13d3, 0x3423) }, { USB_DEVICE(0x13d3, 0x3432) }, + { USB_DEVICE(0x13d3, 0x3472) }, { USB_DEVICE(0x13d3, 0x3474) }, /* Atheros AR5BBU12 with sflash firmware */ @@ -144,6 +148,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe095), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, @@ -154,6 +159,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, @@ -175,10 +181,12 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3395), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3472), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU22 with sflash firmware */ diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 92f0ee388f9e..79107597a594 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -153,6 +153,10 @@ static const struct usb_device_id btusb_table[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x13d3, 0xff, 0x01, 0x01), .driver_info = BTUSB_BCM_PATCHRAM }, + /* Toshiba Corp - Broadcom based */ + { USB_VENDOR_AND_INTERFACE_INFO(0x0930, 0xff, 0x01, 0x01), + .driver_info = BTUSB_BCM_PATCHRAM }, + /* Intel Bluetooth USB Bootloader (RAM module) */ { USB_DEVICE(0x8087, 0x0a5a), .driver_info = BTUSB_INTEL_BOOT | BTUSB_BROKEN_ISOC }, @@ -192,6 +196,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe095), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, @@ -202,6 +207,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, @@ -223,10 +229,12 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3395), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3472), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU12 with sflash firmware */ diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index e98d15eaa799..1827fc4d15c1 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -150,7 +150,7 @@ static int __init weim_parse_dt(struct platform_device *pdev, return ret; } - for_each_child_of_node(pdev->dev.of_node, child) { + for_each_available_child_of_node(pdev->dev.of_node, child) { if (!child->name) continue; diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 45cc39aabeee..252142524ff2 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -136,11 +136,13 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev, chip->cdev.owner = chip->pdev->driver->owner; chip->cdev.kobj.parent = &chip->dev.kobj; + devm_add_action(dev, (void (*)(void *)) put_device, &chip->dev); + return chip; } EXPORT_SYMBOL_GPL(tpmm_chip_alloc); -static int tpm_dev_add_device(struct tpm_chip *chip) +static int tpm_add_char_device(struct tpm_chip *chip) { int rc; @@ -151,7 +153,6 @@ static int tpm_dev_add_device(struct tpm_chip *chip) chip->devname, MAJOR(chip->dev.devt), MINOR(chip->dev.devt), rc); - device_unregister(&chip->dev); return rc; } @@ -162,16 +163,17 @@ static int tpm_dev_add_device(struct tpm_chip *chip) chip->devname, MAJOR(chip->dev.devt), MINOR(chip->dev.devt), rc); + cdev_del(&chip->cdev); return rc; } return rc; } -static void tpm_dev_del_device(struct tpm_chip *chip) +static void tpm_del_char_device(struct tpm_chip *chip) { cdev_del(&chip->cdev); - device_unregister(&chip->dev); + device_del(&chip->dev); } static int tpm1_chip_register(struct tpm_chip *chip) @@ -222,7 +224,7 @@ int tpm_chip_register(struct tpm_chip *chip) tpm_add_ppi(chip); - rc = tpm_dev_add_device(chip); + rc = tpm_add_char_device(chip); if (rc) goto out_err; @@ -274,6 +276,6 @@ void tpm_chip_unregister(struct tpm_chip *chip) sysfs_remove_link(&chip->pdev->kobj, "ppi"); tpm1_chip_unregister(chip); - tpm_dev_del_device(chip); + tpm_del_char_device(chip); } EXPORT_SYMBOL_GPL(tpm_chip_unregister); diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 4bb9727c1047..61e64293b765 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -310,11 +310,11 @@ static int crb_acpi_remove(struct acpi_device *device) struct device *dev = &device->dev; struct tpm_chip *chip = dev_get_drvdata(dev); - tpm_chip_unregister(chip); - if (chip->flags & TPM_CHIP_FLAG_TPM2) tpm2_shutdown(chip, TPM2_SU_CLEAR); + tpm_chip_unregister(chip); + return 0; } diff --git a/drivers/char/tpm/tpm_eventlog.c b/drivers/char/tpm/tpm_eventlog.c index bd72fb04225e..4e6940acf639 100644 --- a/drivers/char/tpm/tpm_eventlog.c +++ b/drivers/char/tpm/tpm_eventlog.c @@ -232,7 +232,7 @@ static int tpm_binary_bios_measurements_show(struct seq_file *m, void *v) { struct tcpa_event *event = v; struct tcpa_event temp_event; - char *tempPtr; + char *temp_ptr; int i; memcpy(&temp_event, event, sizeof(struct tcpa_event)); @@ -242,10 +242,16 @@ static int tpm_binary_bios_measurements_show(struct seq_file *m, void *v) temp_event.event_type = do_endian_conversion(event->event_type); temp_event.event_size = do_endian_conversion(event->event_size); - tempPtr = (char *)&temp_event; + temp_ptr = (char *) &temp_event; - for (i = 0; i < sizeof(struct tcpa_event) + temp_event.event_size; i++) - seq_putc(m, tempPtr[i]); + for (i = 0; i < (sizeof(struct tcpa_event) - 1) ; i++) + seq_putc(m, temp_ptr[i]); + + temp_ptr = (char *) v; + + for (i = (sizeof(struct tcpa_event) - 1); + i < (sizeof(struct tcpa_event) + temp_event.event_size); i++) + seq_putc(m, temp_ptr[i]); return 0; diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index 39bf5820297e..4f9830c1b121 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -1097,13 +1097,15 @@ static int bcm2835_pll_divider_set_rate(struct clk_hw *hw, struct bcm2835_pll_divider *divider = bcm2835_pll_divider_from_hw(hw); struct bcm2835_cprman *cprman = divider->cprman; const struct bcm2835_pll_divider_data *data = divider->data; - u32 cm; - int ret; + u32 cm, div, max_div = 1 << A2W_PLL_DIV_BITS; - ret = clk_divider_ops.set_rate(hw, rate, parent_rate); - if (ret) - return ret; + div = DIV_ROUND_UP_ULL(parent_rate, rate); + + div = min(div, max_div); + if (div == max_div) + div = 0; + cprman_write(cprman, data->a2w_reg, div); cm = cprman_read(cprman, data->cm_reg); cprman_write(cprman, data->cm_reg, cm | data->load_mask); cprman_write(cprman, data->cm_reg, cm & ~data->load_mask); diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index 3ace102a2a0a..bbf206e3da0d 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -422,6 +422,12 @@ const struct clk_ops clk_divider_ops = { }; EXPORT_SYMBOL_GPL(clk_divider_ops); +const struct clk_ops clk_divider_ro_ops = { + .recalc_rate = clk_divider_recalc_rate, + .round_rate = clk_divider_round_rate, +}; +EXPORT_SYMBOL_GPL(clk_divider_ro_ops); + static struct clk *_register_divider(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 shift, u8 width, @@ -445,7 +451,10 @@ static struct clk *_register_divider(struct device *dev, const char *name, return ERR_PTR(-ENOMEM); init.name = name; - init.ops = &clk_divider_ops; + if (clk_divider_flags & CLK_DIVIDER_READ_ONLY) + init.ops = &clk_divider_ro_ops; + else + init.ops = &clk_divider_ops; init.flags = flags | CLK_IS_BASIC; init.parent_names = (parent_name ? &parent_name: NULL); init.num_parents = (parent_name ? 1 : 0); diff --git a/drivers/clk/meson/clkc.c b/drivers/clk/meson/clkc.c index c83ae1367abc..d920d410b51d 100644 --- a/drivers/clk/meson/clkc.c +++ b/drivers/clk/meson/clkc.c @@ -198,7 +198,7 @@ meson_clk_register_fixed_rate(const struct clk_conf *clk_conf, } void __init meson_clk_register_clks(const struct clk_conf *clk_confs, - size_t nr_confs, + unsigned int nr_confs, void __iomem *clk_base) { unsigned int i; diff --git a/drivers/clk/nxp/clk-lpc18xx-ccu.c b/drivers/clk/nxp/clk-lpc18xx-ccu.c index 13aabbb3acbe..558da89555af 100644 --- a/drivers/clk/nxp/clk-lpc18xx-ccu.c +++ b/drivers/clk/nxp/clk-lpc18xx-ccu.c @@ -222,7 +222,7 @@ static void lpc18xx_ccu_register_branch_gate_div(struct lpc18xx_clk_branch *bran div->width = 1; div_hw = &div->hw; - div_ops = &clk_divider_ops; + div_ops = &clk_divider_ro_ops; } branch->gate.reg = branch->offset + reg_base; diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c index 66c18bc97857..bdc4b2d07a23 100644 --- a/drivers/clk/qcom/gcc-msm8960.c +++ b/drivers/clk/qcom/gcc-msm8960.c @@ -2753,7 +2753,7 @@ static struct clk_rcg ce3_src = { }, .freq_tbl = clk_tbl_ce3, .clkr = { - .enable_reg = 0x2c08, + .enable_reg = 0x36c0, .enable_mask = BIT(7), .hw.init = &(struct clk_init_data){ .name = "ce3_src", @@ -2769,7 +2769,7 @@ static struct clk_branch ce3_core_clk = { .halt_reg = 0x2fdc, .halt_bit = 5, .clkr = { - .enable_reg = 0x36c4, + .enable_reg = 0x36cc, .enable_mask = BIT(4), .hw.init = &(struct clk_init_data){ .name = "ce3_core_clk", diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c index abb47608713b..fe728f8dcbe4 100644 --- a/drivers/clk/rockchip/clk-rk3188.c +++ b/drivers/clk/rockchip/clk-rk3188.c @@ -718,6 +718,7 @@ static const char *const rk3188_critical_clocks[] __initconst = { "hclk_peri", "pclk_cpu", "pclk_peri", + "hclk_cpubus" }; static void __init rk3188_common_clk_init(struct device_node *np) diff --git a/drivers/clk/rockchip/clk-rk3368.c b/drivers/clk/rockchip/clk-rk3368.c index 7e6b783e6eee..1b148694b633 100644 --- a/drivers/clk/rockchip/clk-rk3368.c +++ b/drivers/clk/rockchip/clk-rk3368.c @@ -165,7 +165,7 @@ static const struct rockchip_cpuclk_reg_data rk3368_cpuclkb_data = { .core_reg = RK3368_CLKSEL_CON(0), .div_core_shift = 0, .div_core_mask = 0x1f, - .mux_core_shift = 15, + .mux_core_shift = 7, }; static const struct rockchip_cpuclk_reg_data rk3368_cpuclkl_data = { @@ -218,29 +218,29 @@ static const struct rockchip_cpuclk_reg_data rk3368_cpuclkl_data = { } static struct rockchip_cpuclk_rate_table rk3368_cpuclkb_rates[] __initdata = { - RK3368_CPUCLKB_RATE(1512000000, 2, 6, 6), - RK3368_CPUCLKB_RATE(1488000000, 2, 5, 5), - RK3368_CPUCLKB_RATE(1416000000, 2, 5, 5), - RK3368_CPUCLKB_RATE(1200000000, 2, 4, 4), - RK3368_CPUCLKB_RATE(1008000000, 2, 4, 4), - RK3368_CPUCLKB_RATE( 816000000, 2, 3, 3), - RK3368_CPUCLKB_RATE( 696000000, 2, 3, 3), - RK3368_CPUCLKB_RATE( 600000000, 2, 2, 2), - RK3368_CPUCLKB_RATE( 408000000, 2, 2, 2), - RK3368_CPUCLKB_RATE( 312000000, 2, 2, 2), + RK3368_CPUCLKB_RATE(1512000000, 1, 5, 5), + RK3368_CPUCLKB_RATE(1488000000, 1, 4, 4), + RK3368_CPUCLKB_RATE(1416000000, 1, 4, 4), + RK3368_CPUCLKB_RATE(1200000000, 1, 3, 3), + RK3368_CPUCLKB_RATE(1008000000, 1, 3, 3), + RK3368_CPUCLKB_RATE( 816000000, 1, 2, 2), + RK3368_CPUCLKB_RATE( 696000000, 1, 2, 2), + RK3368_CPUCLKB_RATE( 600000000, 1, 1, 1), + RK3368_CPUCLKB_RATE( 408000000, 1, 1, 1), + RK3368_CPUCLKB_RATE( 312000000, 1, 1, 1), }; static struct rockchip_cpuclk_rate_table rk3368_cpuclkl_rates[] __initdata = { - RK3368_CPUCLKL_RATE(1512000000, 2, 7, 7), - RK3368_CPUCLKL_RATE(1488000000, 2, 6, 6), - RK3368_CPUCLKL_RATE(1416000000, 2, 6, 6), - RK3368_CPUCLKL_RATE(1200000000, 2, 5, 5), - RK3368_CPUCLKL_RATE(1008000000, 2, 5, 5), - RK3368_CPUCLKL_RATE( 816000000, 2, 4, 4), - RK3368_CPUCLKL_RATE( 696000000, 2, 3, 3), - RK3368_CPUCLKL_RATE( 600000000, 2, 3, 3), - RK3368_CPUCLKL_RATE( 408000000, 2, 2, 2), - RK3368_CPUCLKL_RATE( 312000000, 2, 2, 2), + RK3368_CPUCLKL_RATE(1512000000, 1, 6, 6), + RK3368_CPUCLKL_RATE(1488000000, 1, 5, 5), + RK3368_CPUCLKL_RATE(1416000000, 1, 5, 5), + RK3368_CPUCLKL_RATE(1200000000, 1, 4, 4), + RK3368_CPUCLKL_RATE(1008000000, 1, 4, 4), + RK3368_CPUCLKL_RATE( 816000000, 1, 3, 3), + RK3368_CPUCLKL_RATE( 696000000, 1, 2, 2), + RK3368_CPUCLKL_RATE( 600000000, 1, 2, 2), + RK3368_CPUCLKL_RATE( 408000000, 1, 1, 1), + RK3368_CPUCLKL_RATE( 312000000, 1, 1, 1), }; static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = { @@ -384,10 +384,10 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = { * Clock-Architecture Diagram 3 */ - COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_usb_p, 0, + COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_npll_usb_p, 0, RK3368_CLKSEL_CON(15), 6, 2, MFLAGS, 0, 5, DFLAGS, RK3368_CLKGATE_CON(4), 6, GFLAGS), - COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_usb_p, 0, + COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_npll_usb_p, 0, RK3368_CLKSEL_CON(15), 14, 2, MFLAGS, 8, 5, DFLAGS, RK3368_CLKGATE_CON(4), 7, GFLAGS), @@ -442,7 +442,7 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = { GATE(SCLK_HDMI_HDCP, "sclk_hdmi_hdcp", "xin24m", 0, RK3368_CLKGATE_CON(4), 13, GFLAGS), GATE(SCLK_HDMI_CEC, "sclk_hdmi_cec", "xin32k", 0, - RK3368_CLKGATE_CON(5), 12, GFLAGS), + RK3368_CLKGATE_CON(4), 12, GFLAGS), COMPOSITE_NODIV(0, "vip_src", mux_pll_src_cpll_gpll_p, 0, RK3368_CLKSEL_CON(21), 15, 1, MFLAGS, diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c index be6c7fd8315d..9b6c8188efac 100644 --- a/drivers/clk/rockchip/clk.c +++ b/drivers/clk/rockchip/clk.c @@ -70,7 +70,7 @@ static struct clk *rockchip_clk_register_branch(const char *name, if (gate_offset >= 0) { gate = kzalloc(sizeof(*gate), GFP_KERNEL); if (!gate) - return ERR_PTR(-ENOMEM); + goto err_gate; gate->flags = gate_flags; gate->reg = base + gate_offset; @@ -82,7 +82,7 @@ static struct clk *rockchip_clk_register_branch(const char *name, if (div_width > 0) { div = kzalloc(sizeof(*div), GFP_KERNEL); if (!div) - return ERR_PTR(-ENOMEM); + goto err_div; div->flags = div_flags; div->reg = base + muxdiv_offset; @@ -90,7 +90,9 @@ static struct clk *rockchip_clk_register_branch(const char *name, div->width = div_width; div->lock = lock; div->table = div_table; - div_ops = &clk_divider_ops; + div_ops = (div_flags & CLK_DIVIDER_READ_ONLY) + ? &clk_divider_ro_ops + : &clk_divider_ops; } clk = clk_register_composite(NULL, name, parent_names, num_parents, @@ -100,6 +102,11 @@ static struct clk *rockchip_clk_register_branch(const char *name, flags); return clk; +err_div: + kfree(gate); +err_gate: + kfree(mux); + return ERR_PTR(-ENOMEM); } static struct clk *rockchip_clk_register_frac_branch(const char *name, diff --git a/drivers/clk/samsung/clk-cpu.c b/drivers/clk/samsung/clk-cpu.c index 2fe37f708dc7..813003d6ce09 100644 --- a/drivers/clk/samsung/clk-cpu.c +++ b/drivers/clk/samsung/clk-cpu.c @@ -148,6 +148,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, unsigned long alt_prate = clk_get_rate(cpuclk->alt_parent); unsigned long alt_div = 0, alt_div_mask = DIV_MASK; unsigned long div0, div1 = 0, mux_reg; + unsigned long flags; /* find out the divider values to use for clock data */ while ((cfg_data->prate * 1000) != ndata->new_rate) { @@ -156,7 +157,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, cfg_data++; } - spin_lock(cpuclk->lock); + spin_lock_irqsave(cpuclk->lock, flags); /* * For the selected PLL clock frequency, get the pre-defined divider @@ -212,7 +213,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, DIV_MASK_ALL); } - spin_unlock(cpuclk->lock); + spin_unlock_irqrestore(cpuclk->lock, flags); return 0; } @@ -223,6 +224,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata, const struct exynos_cpuclk_cfg_data *cfg_data = cpuclk->cfg; unsigned long div = 0, div_mask = DIV_MASK; unsigned long mux_reg; + unsigned long flags; /* find out the divider values to use for clock data */ if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) { @@ -233,7 +235,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata, } } - spin_lock(cpuclk->lock); + spin_lock_irqsave(cpuclk->lock, flags); /* select mout_apll as the alternate parent */ mux_reg = readl(base + E4210_SRC_CPU); @@ -246,7 +248,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata, } exynos_set_safe_div(base, div, div_mask); - spin_unlock(cpuclk->lock); + spin_unlock_irqrestore(cpuclk->lock, flags); return 0; } diff --git a/drivers/clk/versatile/clk-sp810.c b/drivers/clk/versatile/clk-sp810.c index a1cdef6b0f90..897c36c1754a 100644 --- a/drivers/clk/versatile/clk-sp810.c +++ b/drivers/clk/versatile/clk-sp810.c @@ -92,6 +92,7 @@ static void __init clk_sp810_of_setup(struct device_node *node) int num = ARRAY_SIZE(parent_names); char name[12]; struct clk_init_data init; + static int instance; int i; bool deprecated; @@ -118,7 +119,7 @@ static void __init clk_sp810_of_setup(struct device_node *node) deprecated = !of_find_property(node, "assigned-clock-parents", NULL); for (i = 0; i < ARRAY_SIZE(sp810->timerclken); i++) { - snprintf(name, ARRAY_SIZE(name), "timerclken%d", i); + snprintf(name, sizeof(name), "sp810_%d_%d", instance, i); sp810->timerclken[i].sp810 = sp810; sp810->timerclken[i].channel = i; @@ -139,5 +140,6 @@ static void __init clk_sp810_of_setup(struct device_node *node) } of_clk_add_provider(node, clk_sp810_timerclken_of_get, sp810); + instance++; } CLK_OF_DECLARE(sp810, "arm,sp810", clk_sp810_of_setup); diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index 6ee91401918e..4da2af9694a2 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -98,7 +98,8 @@ static int tc_shutdown(struct clock_event_device *d) __raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR)); __raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); - clk_disable(tcd->clk); + if (!clockevent_state_detached(d)) + clk_disable(tcd->clk); return 0; } diff --git a/drivers/clocksource/vt8500_timer.c b/drivers/clocksource/vt8500_timer.c index a92e94b40b5b..dfc3bb410b00 100644 --- a/drivers/clocksource/vt8500_timer.c +++ b/drivers/clocksource/vt8500_timer.c @@ -50,6 +50,8 @@ #define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t) +#define MIN_OSCR_DELTA 16 + static void __iomem *regbase; static cycle_t vt8500_timer_read(struct clocksource *cs) @@ -80,7 +82,7 @@ static int vt8500_timer_set_next_event(unsigned long cycles, cpu_relax(); writel((unsigned long)alarm, regbase + TIMER_MATCH_VAL); - if ((signed)(alarm - clocksource.read(&clocksource)) <= 16) + if ((signed)(alarm - clocksource.read(&clocksource)) <= MIN_OSCR_DELTA) return -ETIME; writel(1, regbase + TIMER_IER_VAL); @@ -151,7 +153,7 @@ static void __init vt8500_timer_init(struct device_node *np) pr_err("%s: setup_irq failed for %s\n", __func__, clockevent.name); clockevents_config_and_register(&clockevent, VT8500_TIMER_HZ, - 4, 0xf0000000); + MIN_OSCR_DELTA * 2, 0xf0000000); } CLOCKSOURCE_OF_DECLARE(vt8500, "via,vt8500-timer", vt8500_timer_init); diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index b260576ddb12..d994b0f652d3 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -356,16 +356,18 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy, if (!have_governor_per_policy()) cdata->gdbs_data = dbs_data; + policy->governor_data = dbs_data; + ret = sysfs_create_group(get_governor_parent_kobj(policy), get_sysfs_attr(dbs_data)); if (ret) goto reset_gdbs_data; - policy->governor_data = dbs_data; - return 0; reset_gdbs_data: + policy->governor_data = NULL; + if (!have_governor_per_policy()) cdata->gdbs_data = NULL; cdata->exit(dbs_data, !policy->governor->initialized); @@ -386,16 +388,19 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy, if (!cdbs->shared || cdbs->shared->policy) return -EBUSY; - policy->governor_data = NULL; if (!--dbs_data->usage_count) { sysfs_remove_group(get_governor_parent_kobj(policy), get_sysfs_attr(dbs_data)); + policy->governor_data = NULL; + if (!have_governor_per_policy()) cdata->gdbs_data = NULL; cdata->exit(dbs_data, policy->governor->initialized == 1); kfree(dbs_data); + } else { + policy->governor_data = NULL; } free_common_dbs_info(policy, cdata); diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c index 0be66df4a6e6..bd83be39f17b 100644 --- a/drivers/cpufreq/cpufreq_interactive.c +++ b/drivers/cpufreq/cpufreq_interactive.c @@ -511,6 +511,58 @@ static void cpufreq_interactive_idle_end(void) up_read(&pcpu->enable_sem); } +static void cpufreq_interactive_get_policy_info(struct cpufreq_policy *policy, + unsigned int *pmax_freq, + u64 *phvt, u64 *pfvt) +{ + struct cpufreq_interactive_cpuinfo *pcpu; + unsigned int max_freq = 0; + u64 hvt = ~0ULL, fvt = 0; + unsigned int i; + + for_each_cpu(i, policy->cpus) { + pcpu = &per_cpu(cpuinfo, i); + + fvt = max(fvt, pcpu->loc_floor_val_time); + if (pcpu->target_freq > max_freq) { + max_freq = pcpu->target_freq; + hvt = pcpu->loc_hispeed_val_time; + } else if (pcpu->target_freq == max_freq) { + hvt = min(hvt, pcpu->loc_hispeed_val_time); + } + } + + *pmax_freq = max_freq; + *phvt = hvt; + *pfvt = fvt; +} + +static void cpufreq_interactive_adjust_cpu(unsigned int cpu, + struct cpufreq_policy *policy) +{ + struct cpufreq_interactive_cpuinfo *pcpu; + u64 hvt, fvt; + unsigned int max_freq; + int i; + + cpufreq_interactive_get_policy_info(policy, &max_freq, &hvt, &fvt); + + for_each_cpu(i, policy->cpus) { + pcpu = &per_cpu(cpuinfo, i); + pcpu->pol_floor_val_time = fvt; + } + + if (max_freq != policy->cur) { + __cpufreq_driver_target(policy, max_freq, CPUFREQ_RELATION_H); + for_each_cpu(i, policy->cpus) { + pcpu = &per_cpu(cpuinfo, i); + pcpu->pol_hispeed_val_time = hvt; + } + } + + trace_cpufreq_interactive_setspeed(cpu, max_freq, policy->cur); +} + static int cpufreq_interactive_speedchange_task(void *data) { unsigned int cpu; @@ -539,49 +591,18 @@ static int cpufreq_interactive_speedchange_task(void *data) spin_unlock_irqrestore(&speedchange_cpumask_lock, flags); for_each_cpu(cpu, &tmp_mask) { - unsigned int j; - unsigned int max_freq = 0; - struct cpufreq_interactive_cpuinfo *pjcpu; - u64 hvt = ~0ULL, fvt = 0; - pcpu = &per_cpu(cpuinfo, cpu); - if (!down_read_trylock(&pcpu->enable_sem)) - continue; - if (!pcpu->governor_enabled) { - up_read(&pcpu->enable_sem); - continue; - } - - for_each_cpu(j, pcpu->policy->cpus) { - pjcpu = &per_cpu(cpuinfo, j); - fvt = max(fvt, pjcpu->loc_floor_val_time); - if (pjcpu->target_freq > max_freq) { - max_freq = pjcpu->target_freq; - hvt = pjcpu->loc_hispeed_val_time; - } else if (pjcpu->target_freq == max_freq) { - hvt = min(hvt, pjcpu->loc_hispeed_val_time); - } - } - for_each_cpu(j, pcpu->policy->cpus) { - pjcpu = &per_cpu(cpuinfo, j); - pjcpu->pol_floor_val_time = fvt; - } + down_write(&pcpu->policy->rwsem); - if (max_freq != pcpu->policy->cur) { - __cpufreq_driver_target(pcpu->policy, - max_freq, - CPUFREQ_RELATION_H); - for_each_cpu(j, pcpu->policy->cpus) { - pjcpu = &per_cpu(cpuinfo, j); - pjcpu->pol_hispeed_val_time = hvt; - } + if (likely(down_read_trylock(&pcpu->enable_sem))) { + if (likely(pcpu->governor_enabled)) + cpufreq_interactive_adjust_cpu(cpu, + pcpu->policy); + up_read(&pcpu->enable_sem); } - trace_cpufreq_interactive_setspeed(cpu, - pcpu->target_freq, - pcpu->policy->cur); - up_read(&pcpu->enable_sem); + up_write(&pcpu->policy->rwsem); } } @@ -601,8 +622,19 @@ static void cpufreq_interactive_boost(struct cpufreq_interactive_tunables *tunab for_each_online_cpu(i) { pcpu = &per_cpu(cpuinfo, i); - if (tunables != pcpu->policy->governor_data) + + if (!down_read_trylock(&pcpu->enable_sem)) + continue; + + if (!pcpu->governor_enabled) { + up_read(&pcpu->enable_sem); + continue; + } + + if (tunables != pcpu->policy->governor_data) { + up_read(&pcpu->enable_sem); continue; + } spin_lock_irqsave(&pcpu->target_freq_lock, flags[1]); if (pcpu->target_freq < tunables->hispeed_freq) { @@ -613,6 +645,8 @@ static void cpufreq_interactive_boost(struct cpufreq_interactive_tunables *tunab anyboost = 1; } spin_unlock_irqrestore(&pcpu->target_freq_lock, flags[1]); + + up_read(&pcpu->enable_sem); } spin_unlock_irqrestore(&speedchange_cpumask_lock, flags[0]); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 98fb8821382d..f53b02a6bc05 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -667,6 +667,11 @@ static int core_get_max_pstate(void) if (err) goto skip_tar; + /* For level 1 and 2, bits[23:16] contain the ratio */ + if (tdp_ctrl) + tdp_ratio >>= 16; + + tdp_ratio &= 0xff; /* ratios are only 8 bits long */ if (tdp_ratio - 1 == tar) { max_pstate = tar; pr_debug("max_pstate=TAC %x\n", max_pstate); diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c index 1d99c97defa9..096377232747 100644 --- a/drivers/cpufreq/pxa2xx-cpufreq.c +++ b/drivers/cpufreq/pxa2xx-cpufreq.c @@ -202,7 +202,7 @@ static void __init pxa_cpufreq_init_voltages(void) } } #else -static int pxa_cpufreq_change_voltage(struct pxa_freqs *pxa_freq) +static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq) { return 0; } diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c index 545069d5fdfb..e342565e8715 100644 --- a/drivers/cpuidle/cpuidle-arm.c +++ b/drivers/cpuidle/cpuidle-arm.c @@ -50,7 +50,7 @@ static int arm_enter_idle_state(struct cpuidle_device *dev, * call the CPU ops suspend protocol with idle index as a * parameter. */ - arm_cpuidle_suspend(idx); + ret = arm_cpuidle_suspend(idx); cpu_pm_exit(); } diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index fb16d812c8f5..1dffb13e5c2f 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -1396,9 +1396,9 @@ static int atmel_aes_probe(struct platform_device *pdev) } aes_dd->io_base = devm_ioremap_resource(&pdev->dev, aes_res); - if (!aes_dd->io_base) { + if (IS_ERR(aes_dd->io_base)) { dev_err(dev, "can't ioremap\n"); - err = -ENOMEM; + err = PTR_ERR(aes_dd->io_base); goto res_err; } diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 660d8c06540b..0dadb6332f0e 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -783,7 +783,7 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err) dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU | SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); if (req->base.complete) req->base.complete(&req->base, err); @@ -796,7 +796,7 @@ static int atmel_sha_hw_init(struct atmel_sha_dev *dd) { int err; - err = clk_prepare_enable(dd->iclk); + err = clk_enable(dd->iclk); if (err) return err; @@ -823,7 +823,7 @@ static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd) dev_info(dd->dev, "version: 0x%x\n", dd->hw_version); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); } static int atmel_sha_handle_queue(struct atmel_sha_dev *dd, @@ -1405,12 +1405,16 @@ static int atmel_sha_probe(struct platform_device *pdev) } sha_dd->io_base = devm_ioremap_resource(&pdev->dev, sha_res); - if (!sha_dd->io_base) { + if (IS_ERR(sha_dd->io_base)) { dev_err(dev, "can't ioremap\n"); - err = -ENOMEM; + err = PTR_ERR(sha_dd->io_base); goto res_err; } + err = clk_prepare(sha_dd->iclk); + if (err) + goto res_err; + atmel_sha_hw_version_init(sha_dd); atmel_sha_get_cap(sha_dd); @@ -1422,12 +1426,12 @@ static int atmel_sha_probe(struct platform_device *pdev) if (IS_ERR(pdata)) { dev_err(&pdev->dev, "platform data not available\n"); err = PTR_ERR(pdata); - goto res_err; + goto iclk_unprepare; } } if (!pdata->dma_slave) { err = -ENXIO; - goto res_err; + goto iclk_unprepare; } err = atmel_sha_dma_init(sha_dd, pdata); if (err) @@ -1458,6 +1462,8 @@ err_algs: if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); err_sha_dma: +iclk_unprepare: + clk_unprepare(sha_dd->iclk); res_err: tasklet_kill(&sha_dd->done_task); sha_dd_err: @@ -1484,12 +1490,7 @@ static int atmel_sha_remove(struct platform_device *pdev) if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); - iounmap(sha_dd->io_base); - - clk_put(sha_dd->iclk); - - if (sha_dd->irq >= 0) - free_irq(sha_dd->irq, sha_dd); + clk_unprepare(sha_dd->iclk); return 0; } diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index 2c7a628d0375..bf467d7be35c 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -1417,9 +1417,9 @@ static int atmel_tdes_probe(struct platform_device *pdev) } tdes_dd->io_base = devm_ioremap_resource(&pdev->dev, tdes_res); - if (!tdes_dd->io_base) { + if (IS_ERR(tdes_dd->io_base)) { dev_err(dev, "can't ioremap\n"); - err = -ENOMEM; + err = PTR_ERR(tdes_dd->io_base); goto res_err; } diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 8abb4bc548cc..69d4a1326fee 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -534,8 +534,8 @@ static int caam_probe(struct platform_device *pdev) * long pointers in master configuration register */ clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH | - MCFGR_WDENABLE | (sizeof(dma_addr_t) == sizeof(u64) ? - MCFGR_LONG_PTR : 0)); + MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | + (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0)); /* * Read the Compile Time paramters and SCFGR to determine diff --git a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c index d89f20c04266..60fc0fa26fd3 100644 --- a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c +++ b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c @@ -220,6 +220,42 @@ static int ccp_aes_cmac_digest(struct ahash_request *req) return ccp_aes_cmac_finup(req); } +static int ccp_aes_cmac_export(struct ahash_request *req, void *out) +{ + struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req); + struct ccp_aes_cmac_exp_ctx state; + + /* Don't let anything leak to 'out' */ + memset(&state, 0, sizeof(state)); + + state.null_msg = rctx->null_msg; + memcpy(state.iv, rctx->iv, sizeof(state.iv)); + state.buf_count = rctx->buf_count; + memcpy(state.buf, rctx->buf, sizeof(state.buf)); + + /* 'out' may not be aligned so memcpy from local variable */ + memcpy(out, &state, sizeof(state)); + + return 0; +} + +static int ccp_aes_cmac_import(struct ahash_request *req, const void *in) +{ + struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req); + struct ccp_aes_cmac_exp_ctx state; + + /* 'in' may not be aligned so memcpy to local variable */ + memcpy(&state, in, sizeof(state)); + + memset(rctx, 0, sizeof(*rctx)); + rctx->null_msg = state.null_msg; + memcpy(rctx->iv, state.iv, sizeof(rctx->iv)); + rctx->buf_count = state.buf_count; + memcpy(rctx->buf, state.buf, sizeof(rctx->buf)); + + return 0; +} + static int ccp_aes_cmac_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int key_len) { @@ -352,10 +388,13 @@ int ccp_register_aes_cmac_algs(struct list_head *head) alg->final = ccp_aes_cmac_final; alg->finup = ccp_aes_cmac_finup; alg->digest = ccp_aes_cmac_digest; + alg->export = ccp_aes_cmac_export; + alg->import = ccp_aes_cmac_import; alg->setkey = ccp_aes_cmac_setkey; halg = &alg->halg; halg->digestsize = AES_BLOCK_SIZE; + halg->statesize = sizeof(struct ccp_aes_cmac_exp_ctx); base = &halg->base; snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "cmac(aes)"); diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c index d14b3f28e010..ab9945f2cb7a 100644 --- a/drivers/crypto/ccp/ccp-crypto-sha.c +++ b/drivers/crypto/ccp/ccp-crypto-sha.c @@ -207,6 +207,46 @@ static int ccp_sha_digest(struct ahash_request *req) return ccp_sha_finup(req); } +static int ccp_sha_export(struct ahash_request *req, void *out) +{ + struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req); + struct ccp_sha_exp_ctx state; + + /* Don't let anything leak to 'out' */ + memset(&state, 0, sizeof(state)); + + state.type = rctx->type; + state.msg_bits = rctx->msg_bits; + state.first = rctx->first; + memcpy(state.ctx, rctx->ctx, sizeof(state.ctx)); + state.buf_count = rctx->buf_count; + memcpy(state.buf, rctx->buf, sizeof(state.buf)); + + /* 'out' may not be aligned so memcpy from local variable */ + memcpy(out, &state, sizeof(state)); + + return 0; +} + +static int ccp_sha_import(struct ahash_request *req, const void *in) +{ + struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req); + struct ccp_sha_exp_ctx state; + + /* 'in' may not be aligned so memcpy to local variable */ + memcpy(&state, in, sizeof(state)); + + memset(rctx, 0, sizeof(*rctx)); + rctx->type = state.type; + rctx->msg_bits = state.msg_bits; + rctx->first = state.first; + memcpy(rctx->ctx, state.ctx, sizeof(rctx->ctx)); + rctx->buf_count = state.buf_count; + memcpy(rctx->buf, state.buf, sizeof(rctx->buf)); + + return 0; +} + static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int key_len) { @@ -403,9 +443,12 @@ static int ccp_register_sha_alg(struct list_head *head, alg->final = ccp_sha_final; alg->finup = ccp_sha_finup; alg->digest = ccp_sha_digest; + alg->export = ccp_sha_export; + alg->import = ccp_sha_import; halg = &alg->halg; halg->digestsize = def->digest_size; + halg->statesize = sizeof(struct ccp_sha_exp_ctx); base = &halg->base; snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name); diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h index 76a96f0f44c6..a326ec20bfa8 100644 --- a/drivers/crypto/ccp/ccp-crypto.h +++ b/drivers/crypto/ccp/ccp-crypto.h @@ -129,6 +129,15 @@ struct ccp_aes_cmac_req_ctx { struct ccp_cmd cmd; }; +struct ccp_aes_cmac_exp_ctx { + unsigned int null_msg; + + u8 iv[AES_BLOCK_SIZE]; + + unsigned int buf_count; + u8 buf[AES_BLOCK_SIZE]; +}; + /***** SHA related defines *****/ #define MAX_SHA_CONTEXT_SIZE SHA256_DIGEST_SIZE #define MAX_SHA_BLOCK_SIZE SHA256_BLOCK_SIZE @@ -171,6 +180,19 @@ struct ccp_sha_req_ctx { struct ccp_cmd cmd; }; +struct ccp_sha_exp_ctx { + enum ccp_sha_type type; + + u64 msg_bits; + + unsigned int first; + + u8 ctx[MAX_SHA_CONTEXT_SIZE]; + + unsigned int buf_count; + u8 buf[MAX_SHA_BLOCK_SIZE]; +}; + /***** Common Context Structure *****/ struct ccp_ctx { int (*complete)(struct crypto_async_request *req, int ret); diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c index 0643e3366e33..80239ae69527 100644 --- a/drivers/crypto/marvell/cesa.c +++ b/drivers/crypto/marvell/cesa.c @@ -306,7 +306,7 @@ static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa) return -ENOMEM; dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0); - if (!dma->cache_pool) + if (!dma->padding_pool) return -ENOMEM; cesa->dma = dma; @@ -420,7 +420,7 @@ static int mv_cesa_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); cesa->regs = devm_ioremap_resource(dev, res); if (IS_ERR(cesa->regs)) - return -ENOMEM; + return PTR_ERR(cesa->regs); ret = mv_cesa_dev_dma_init(cesa); if (ret) diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c index eab6fe227fa0..107cd2a41cae 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c @@ -39,6 +39,7 @@ static struct sun4i_ss_alg_template ss_algs[] = { .import = sun4i_hash_import_md5, .halg = { .digestsize = MD5_DIGEST_SIZE, + .statesize = sizeof(struct md5_state), .base = { .cra_name = "md5", .cra_driver_name = "md5-sun4i-ss", @@ -66,6 +67,7 @@ static struct sun4i_ss_alg_template ss_algs[] = { .import = sun4i_hash_import_sha1, .halg = { .digestsize = SHA1_DIGEST_SIZE, + .statesize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", .cra_driver_name = "sha1-sun4i-ss", diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index b6f9f42e2985..a04fea4d0063 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -63,6 +63,14 @@ static void to_talitos_ptr(struct talitos_ptr *ptr, dma_addr_t dma_addr, ptr->eptr = upper_32_bits(dma_addr); } +static void copy_talitos_ptr(struct talitos_ptr *dst_ptr, + struct talitos_ptr *src_ptr, bool is_sec1) +{ + dst_ptr->ptr = src_ptr->ptr; + if (!is_sec1) + dst_ptr->eptr = src_ptr->eptr; +} + static void to_talitos_ptr_len(struct talitos_ptr *ptr, unsigned int len, bool is_sec1) { @@ -1083,21 +1091,20 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, sg_count = dma_map_sg(dev, areq->src, edesc->src_nents ?: 1, (areq->src == areq->dst) ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); - /* hmac data */ desc->ptr[1].len = cpu_to_be16(areq->assoclen); if (sg_count > 1 && (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0, areq->assoclen, &edesc->link_tbl[tbl_off])) > 1) { - tbl_off += ret; - to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off * sizeof(struct talitos_ptr), 0); desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP; dma_sync_single_for_device(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); + + tbl_off += ret; } else { to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0); desc->ptr[1].j_extent = 0; @@ -1126,11 +1133,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV) sg_link_tbl_len += authsize; - if (sg_count > 1 && - (ret = sg_to_link_tbl_offset(areq->src, sg_count, areq->assoclen, - sg_link_tbl_len, - &edesc->link_tbl[tbl_off])) > 1) { - tbl_off += ret; + if (sg_count == 1) { + to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src) + + areq->assoclen, 0); + } else if ((ret = sg_to_link_tbl_offset(areq->src, sg_count, + areq->assoclen, sg_link_tbl_len, + &edesc->link_tbl[tbl_off])) > + 1) { desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP; to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl + tbl_off * @@ -1138,8 +1147,10 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, dma_sync_single_for_device(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); - } else - to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0); + tbl_off += ret; + } else { + copy_talitos_ptr(&desc->ptr[4], &edesc->link_tbl[tbl_off], 0); + } /* cipher out */ desc->ptr[5].len = cpu_to_be16(cryptlen); @@ -1151,11 +1162,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, edesc->icv_ool = false; - if (sg_count > 1 && - (sg_count = sg_to_link_tbl_offset(areq->dst, sg_count, + if (sg_count == 1) { + to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst) + + areq->assoclen, 0); + } else if ((sg_count = + sg_to_link_tbl_offset(areq->dst, sg_count, areq->assoclen, cryptlen, - &edesc->link_tbl[tbl_off])) > - 1) { + &edesc->link_tbl[tbl_off])) > 1) { struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off]; to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl + @@ -1178,8 +1191,9 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, edesc->dma_len, DMA_BIDIRECTIONAL); edesc->icv_ool = true; - } else - to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0); + } else { + copy_talitos_ptr(&desc->ptr[5], &edesc->link_tbl[tbl_off], 0); + } /* iv out */ map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv, @@ -2519,21 +2533,11 @@ struct talitos_crypto_alg { struct talitos_alg_template algt; }; -static int talitos_cra_init(struct crypto_tfm *tfm) +static int talitos_init_common(struct talitos_ctx *ctx, + struct talitos_crypto_alg *talitos_alg) { - struct crypto_alg *alg = tfm->__crt_alg; - struct talitos_crypto_alg *talitos_alg; - struct talitos_ctx *ctx = crypto_tfm_ctx(tfm); struct talitos_private *priv; - if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH) - talitos_alg = container_of(__crypto_ahash_alg(alg), - struct talitos_crypto_alg, - algt.alg.hash); - else - talitos_alg = container_of(alg, struct talitos_crypto_alg, - algt.alg.crypto); - /* update context with ptr to dev */ ctx->dev = talitos_alg->dev; @@ -2551,10 +2555,33 @@ static int talitos_cra_init(struct crypto_tfm *tfm) return 0; } +static int talitos_cra_init(struct crypto_tfm *tfm) +{ + struct crypto_alg *alg = tfm->__crt_alg; + struct talitos_crypto_alg *talitos_alg; + struct talitos_ctx *ctx = crypto_tfm_ctx(tfm); + + if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH) + talitos_alg = container_of(__crypto_ahash_alg(alg), + struct talitos_crypto_alg, + algt.alg.hash); + else + talitos_alg = container_of(alg, struct talitos_crypto_alg, + algt.alg.crypto); + + return talitos_init_common(ctx, talitos_alg); +} + static int talitos_cra_init_aead(struct crypto_aead *tfm) { - talitos_cra_init(crypto_aead_tfm(tfm)); - return 0; + struct aead_alg *alg = crypto_aead_alg(tfm); + struct talitos_crypto_alg *talitos_alg; + struct talitos_ctx *ctx = crypto_aead_ctx(tfm); + + talitos_alg = container_of(alg, struct talitos_crypto_alg, + algt.alg.aead); + + return talitos_init_common(ctx, talitos_alg); } static int talitos_cra_init_ahash(struct crypto_tfm *tfm) diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index 4c243c1ffc7f..790f7cadc1ed 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -1440,9 +1440,9 @@ static int ux500_cryp_probe(struct platform_device *pdev) device_data->phybase = res->start; device_data->base = devm_ioremap_resource(dev, res); - if (!device_data->base) { + if (IS_ERR(device_data->base)) { dev_err(dev, "[%s]: ioremap failed!", __func__); - ret = -ENOMEM; + ret = PTR_ERR(device_data->base); goto out; } diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index f47d112041b2..66b1c3313e2e 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -1675,9 +1675,9 @@ static int ux500_hash_probe(struct platform_device *pdev) device_data->phybase = res->start; device_data->base = devm_ioremap_resource(dev, res); - if (!device_data->base) { + if (IS_ERR(device_data->base)) { dev_err(dev, "%s: ioremap() failed!\n", __func__); - ret = -ENOMEM; + ret = PTR_ERR(device_data->base); goto out; } spin_lock_init(&device_data->ctx_lock); diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 370c661c7d7b..02f9aa4ebe05 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -176,6 +176,7 @@ #define AT_XDMAC_MAX_CHAN 0x20 #define AT_XDMAC_MAX_CSIZE 16 /* 16 data */ #define AT_XDMAC_MAX_DWIDTH 8 /* 64 bits */ +#define AT_XDMAC_RESIDUE_MAX_RETRIES 5 #define AT_XDMAC_DMA_BUSWIDTHS\ (BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\ @@ -1383,8 +1384,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, struct at_xdmac_desc *desc, *_desc; struct list_head *descs_list; enum dma_status ret; - int residue; - u32 cur_nda, mask, value; + int residue, retry; + u32 cur_nda, check_nda, cur_ubc, mask, value; u8 dwidth = 0; unsigned long flags; @@ -1421,7 +1422,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, cpu_relax(); } + /* + * When processing the residue, we need to read two registers but we + * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where + * we stand in the descriptor list and AT_XDMAC_CUBC is used + * to know how many data are remaining for the current descriptor. + * Since the dma channel is not paused to not loose data, between the + * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of + * descriptor. + * For that reason, after reading AT_XDMAC_CUBC, we check if we are + * still using the same descriptor by reading a second time + * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to + * read again AT_XDMAC_CUBC. + * Memory barriers are used to ensure the read order of the registers. + * A max number of retries is set because unlikely it can never ends if + * we are transferring a lot of data with small buffers. + */ cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + rmb(); + cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) { + rmb(); + check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + + if (likely(cur_nda == check_nda)) + break; + + cur_nda = check_nda; + rmb(); + cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + } + + if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) { + ret = DMA_ERROR; + goto spin_unlock; + } + /* * Remove size of all microblocks already transferred and the current * one. Then add the remaining size to transfer of the current @@ -1434,7 +1470,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda) break; } - residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth; + residue += cur_ubc << dwidth; dma_set_residue(txstate, residue); @@ -1688,6 +1724,7 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan) list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node) at_xdmac_remove_xfer(atchan, desc); + clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status); clear_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status); spin_unlock_irqrestore(&atchan->lock, flags); @@ -1820,6 +1857,8 @@ static int atmel_xdmac_resume(struct device *dev) atchan = to_at_xdmac_chan(chan); at_xdmac_chan_write(atchan, AT_XDMAC_CC, atchan->save_cc); if (at_xdmac_chan_is_cyclic(atchan)) { + if (at_xdmac_chan_is_paused(atchan)) + at_xdmac_device_resume(chan); at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, atchan->save_cnda); at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, atchan->save_cndc); at_xdmac_chan_write(atchan, AT_XDMAC_CIE, atchan->save_cim); diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 7067b6ddc1db..c66133b5e852 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -130,26 +130,14 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc) static void dwc_initialize(struct dw_dma_chan *dwc) { struct dw_dma *dw = to_dw_dma(dwc->chan.device); - struct dw_dma_slave *dws = dwc->chan.private; u32 cfghi = DWC_CFGH_FIFO_MODE; u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority); if (dwc->initialized == true) return; - if (dws) { - /* - * We need controller-specific data to set up slave - * transfers. - */ - BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev); - - cfghi |= DWC_CFGH_DST_PER(dws->dst_id); - cfghi |= DWC_CFGH_SRC_PER(dws->src_id); - } else { - cfghi |= DWC_CFGH_DST_PER(dwc->dst_id); - cfghi |= DWC_CFGH_SRC_PER(dwc->src_id); - } + cfghi |= DWC_CFGH_DST_PER(dwc->dst_id); + cfghi |= DWC_CFGH_SRC_PER(dwc->src_id); channel_writel(dwc, CFG_LO, cfglo); channel_writel(dwc, CFG_HI, cfghi); @@ -536,16 +524,17 @@ EXPORT_SYMBOL(dw_dma_get_dst_addr); /* Called with dwc->lock held and all DMAC interrupts disabled */ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, - u32 status_err, u32 status_xfer) + u32 status_block, u32 status_err, u32 status_xfer) { unsigned long flags; - if (dwc->mask) { + if (status_block & dwc->mask) { void (*callback)(void *param); void *callback_param; dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n", channel_readl(dwc, LLP)); + dma_writel(dw, CLEAR.BLOCK, dwc->mask); callback = dwc->cdesc->period_callback; callback_param = dwc->cdesc->period_callback_param; @@ -577,6 +566,7 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, channel_writel(dwc, CTL_LO, 0); channel_writel(dwc, CTL_HI, 0); + dma_writel(dw, CLEAR.BLOCK, dwc->mask); dma_writel(dw, CLEAR.ERROR, dwc->mask); dma_writel(dw, CLEAR.XFER, dwc->mask); @@ -585,6 +575,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, spin_unlock_irqrestore(&dwc->lock, flags); } + + /* Re-enable interrupts */ + channel_set_bit(dw, MASK.BLOCK, dwc->mask); } /* ------------------------------------------------------------------------- */ @@ -593,10 +586,12 @@ static void dw_dma_tasklet(unsigned long data) { struct dw_dma *dw = (struct dw_dma *)data; struct dw_dma_chan *dwc; + u32 status_block; u32 status_xfer; u32 status_err; int i; + status_block = dma_readl(dw, RAW.BLOCK); status_xfer = dma_readl(dw, RAW.XFER); status_err = dma_readl(dw, RAW.ERROR); @@ -605,16 +600,15 @@ static void dw_dma_tasklet(unsigned long data) for (i = 0; i < dw->dma.chancnt; i++) { dwc = &dw->chan[i]; if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) - dwc_handle_cyclic(dw, dwc, status_err, status_xfer); + dwc_handle_cyclic(dw, dwc, status_block, status_err, + status_xfer); else if (status_err & (1 << i)) dwc_handle_error(dw, dwc); else if (status_xfer & (1 << i)) dwc_scan_descriptors(dw, dwc); } - /* - * Re-enable interrupts. - */ + /* Re-enable interrupts */ channel_set_bit(dw, MASK.XFER, dw->all_chan_mask); channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask); } @@ -635,6 +629,7 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id) * softirq handler. */ channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask); + channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask); channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask); status = dma_readl(dw, STATUS_INT); @@ -645,6 +640,7 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id) /* Try to recover */ channel_clear_bit(dw, MASK.XFER, (1 << 8) - 1); + channel_clear_bit(dw, MASK.BLOCK, (1 << 8) - 1); channel_clear_bit(dw, MASK.SRC_TRAN, (1 << 8) - 1); channel_clear_bit(dw, MASK.DST_TRAN, (1 << 8) - 1); channel_clear_bit(dw, MASK.ERROR, (1 << 8) - 1); @@ -928,7 +924,7 @@ bool dw_dma_filter(struct dma_chan *chan, void *param) struct dw_dma_chan *dwc = to_dw_dma_chan(chan); struct dw_dma_slave *dws = param; - if (!dws || dws->dma_dev != chan->device->dev) + if (dws->dma_dev != chan->device->dev) return false; /* We have to copy data since dws can be temporary storage */ @@ -1111,6 +1107,7 @@ static void dw_dma_off(struct dw_dma *dw) dma_writel(dw, CFG, 0); channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask); + channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask); channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask); channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask); channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask); @@ -1151,6 +1148,14 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan) * doesn't mean what you think it means), and status writeback. */ + /* + * We need controller-specific data to set up slave transfers. + */ + if (chan->private && !dw_dma_filter(chan, chan->private)) { + dev_warn(chan2dev(chan), "Wrong controller-specific data\n"); + return -EINVAL; + } + /* Enable controller here if needed */ if (!dw->in_use) dw_dma_on(dw); @@ -1212,10 +1217,19 @@ static void dwc_free_chan_resources(struct dma_chan *chan) spin_lock_irqsave(&dwc->lock, flags); list_splice_init(&dwc->free_list, &list); dwc->descs_allocated = 0; + + /* Clear custom channel configuration */ + dwc->src_id = 0; + dwc->dst_id = 0; + + dwc->src_master = 0; + dwc->dst_master = 0; + dwc->initialized = false; /* Disable interrupts */ channel_clear_bit(dw, MASK.XFER, dwc->mask); + channel_clear_bit(dw, MASK.BLOCK, dwc->mask); channel_clear_bit(dw, MASK.ERROR, dwc->mask); spin_unlock_irqrestore(&dwc->lock, flags); @@ -1245,7 +1259,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan) int dw_dma_cyclic_start(struct dma_chan *chan) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dw_dma *dw = to_dw_dma(dwc->chan.device); + struct dw_dma *dw = to_dw_dma(chan->device); unsigned long flags; if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) { @@ -1255,25 +1269,10 @@ int dw_dma_cyclic_start(struct dma_chan *chan) spin_lock_irqsave(&dwc->lock, flags); - /* Assert channel is idle */ - if (dma_readl(dw, CH_EN) & dwc->mask) { - dev_err(chan2dev(&dwc->chan), - "%s: BUG: Attempted to start non-idle channel\n", - __func__); - dwc_dump_chan_regs(dwc); - spin_unlock_irqrestore(&dwc->lock, flags); - return -EBUSY; - } + /* Enable interrupts to perform cyclic transfer */ + channel_set_bit(dw, MASK.BLOCK, dwc->mask); - dma_writel(dw, CLEAR.ERROR, dwc->mask); - dma_writel(dw, CLEAR.XFER, dwc->mask); - - /* Setup DMAC channel registers */ - channel_writel(dwc, LLP, dwc->cdesc->desc[0]->txd.phys); - channel_writel(dwc, CTL_LO, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN); - channel_writel(dwc, CTL_HI, 0); - - channel_set_bit(dw, CH_EN, dwc->mask); + dwc_dostart(dwc, dwc->cdesc->desc[0]); spin_unlock_irqrestore(&dwc->lock, flags); @@ -1479,6 +1478,7 @@ void dw_dma_cyclic_free(struct dma_chan *chan) dwc_chan_disable(dw, dwc); + dma_writel(dw, CLEAR.BLOCK, dwc->mask); dma_writel(dw, CLEAR.ERROR, dwc->mask); dma_writel(dw, CLEAR.XFER, dwc->mask); @@ -1567,9 +1567,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) /* Force dma off, just in case */ dw_dma_off(dw); - /* Disable BLOCK interrupts as well */ - channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask); - /* Create a pool of consistent memory blocks for hardware descriptors */ dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", chip->dev, sizeof(struct dw_desc), 4, 0); diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c index 823ad728aecf..efc02b98e6ba 100644 --- a/drivers/dma/hsu/hsu.c +++ b/drivers/dma/hsu/hsu.c @@ -135,7 +135,7 @@ static u32 hsu_dma_chan_get_sr(struct hsu_dma_chan *hsuc) sr = hsu_chan_readl(hsuc, HSU_CH_SR); spin_unlock_irqrestore(&hsuc->vchan.lock, flags); - return sr; + return sr & ~(HSU_CH_SR_DESCE_ANY | HSU_CH_SR_CDESC_ANY); } irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr) diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h index f06579c6d548..26da2865b025 100644 --- a/drivers/dma/hsu/hsu.h +++ b/drivers/dma/hsu/hsu.h @@ -41,6 +41,9 @@ #define HSU_CH_SR_DESCTO(x) BIT(8 + (x)) #define HSU_CH_SR_DESCTO_ANY (BIT(11) | BIT(10) | BIT(9) | BIT(8)) #define HSU_CH_SR_CHE BIT(15) +#define HSU_CH_SR_DESCE(x) BIT(16 + (x)) +#define HSU_CH_SR_DESCE_ANY (BIT(19) | BIT(18) | BIT(17) | BIT(16)) +#define HSU_CH_SR_CDESC_ANY (BIT(31) | BIT(30)) /* Bits in HSU_CH_CR */ #define HSU_CH_CR_CHA BIT(0) diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index fc4156afa070..55f5d33f6dc7 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -122,6 +122,7 @@ struct pxad_chan { struct pxad_device { struct dma_device slave; int nr_chans; + int nr_requestors; void __iomem *base; struct pxad_phy *phys; spinlock_t phy_lock; /* Phy association */ @@ -473,7 +474,7 @@ static void pxad_free_phy(struct pxad_chan *chan) return; /* clear the channel mapping in DRCMR */ - if (chan->drcmr <= DRCMR_CHLNUM) { + if (chan->drcmr <= pdev->nr_requestors) { reg = pxad_drcmr(chan->drcmr); writel_relaxed(0, chan->phy->base + reg); } @@ -509,6 +510,7 @@ static bool is_running_chan_misaligned(struct pxad_chan *chan) static void phy_enable(struct pxad_phy *phy, bool misaligned) { + struct pxad_device *pdev; u32 reg, dalgn; if (!phy->vchan) @@ -518,7 +520,8 @@ static void phy_enable(struct pxad_phy *phy, bool misaligned) "%s(); phy=%p(%d) misaligned=%d\n", __func__, phy, phy->idx, misaligned); - if (phy->vchan->drcmr <= DRCMR_CHLNUM) { + pdev = to_pxad_dev(phy->vchan->vc.chan.device); + if (phy->vchan->drcmr <= pdev->nr_requestors) { reg = pxad_drcmr(phy->vchan->drcmr); writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg); } @@ -583,6 +586,8 @@ static void set_updater_desc(struct pxad_desc_sw *sw_desc, (PXA_DCMD_LENGTH & sizeof(u32)); if (flags & DMA_PREP_INTERRUPT) updater->dcmd |= PXA_DCMD_ENDIRQEN; + if (sw_desc->cyclic) + sw_desc->hw_desc[sw_desc->nb_desc - 2]->ddadr = sw_desc->first; } static bool is_desc_completed(struct virt_dma_desc *vd) @@ -673,6 +678,10 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id) dev_dbg(&chan->vc.chan.dev->device, "%s(): checking txd %p[%x]: completed=%d\n", __func__, vd, vd->tx.cookie, is_desc_completed(vd)); + if (to_pxad_sw_desc(vd)->cyclic) { + vchan_cyclic_callback(vd); + break; + } if (is_desc_completed(vd)) { list_del(&vd->node); vchan_cookie_complete(vd); @@ -908,6 +917,7 @@ static void pxad_get_config(struct pxad_chan *chan, { u32 maxburst = 0, dev_addr = 0; enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED; + struct pxad_device *pdev = to_pxad_dev(chan->vc.chan.device); *dcmd = 0; if (dir == DMA_DEV_TO_MEM) { @@ -916,7 +926,7 @@ static void pxad_get_config(struct pxad_chan *chan, dev_addr = chan->cfg.src_addr; *dev_src = dev_addr; *dcmd |= PXA_DCMD_INCTRGADDR; - if (chan->drcmr <= DRCMR_CHLNUM) + if (chan->drcmr <= pdev->nr_requestors) *dcmd |= PXA_DCMD_FLOWSRC; } if (dir == DMA_MEM_TO_DEV) { @@ -925,7 +935,7 @@ static void pxad_get_config(struct pxad_chan *chan, dev_addr = chan->cfg.dst_addr; *dev_dst = dev_addr; *dcmd |= PXA_DCMD_INCSRCADDR; - if (chan->drcmr <= DRCMR_CHLNUM) + if (chan->drcmr <= pdev->nr_requestors) *dcmd |= PXA_DCMD_FLOWTRG; } if (dir == DMA_MEM_TO_MEM) @@ -1080,7 +1090,7 @@ pxad_prep_dma_cyclic(struct dma_chan *dchan, return NULL; pxad_get_config(chan, dir, &dcmd, &dsadr, &dtadr); - dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH | period_len); + dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH & period_len); dev_dbg(&chan->vc.chan.dev->device, "%s(): buf_addr=0x%lx len=%zu period=%zu dir=%d flags=%lx\n", __func__, (unsigned long)buf_addr, len, period_len, dir, flags); @@ -1335,13 +1345,15 @@ static struct dma_chan *pxad_dma_xlate(struct of_phandle_args *dma_spec, static int pxad_init_dmadev(struct platform_device *op, struct pxad_device *pdev, - unsigned int nr_phy_chans) + unsigned int nr_phy_chans, + unsigned int nr_requestors) { int ret; unsigned int i; struct pxad_chan *c; pdev->nr_chans = nr_phy_chans; + pdev->nr_requestors = nr_requestors; INIT_LIST_HEAD(&pdev->slave.channels); pdev->slave.device_alloc_chan_resources = pxad_alloc_chan_resources; pdev->slave.device_free_chan_resources = pxad_free_chan_resources; @@ -1376,7 +1388,7 @@ static int pxad_probe(struct platform_device *op) const struct of_device_id *of_id; struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev); struct resource *iores; - int ret, dma_channels = 0; + int ret, dma_channels = 0, nb_requestors = 0; const enum dma_slave_buswidth widths = DMA_SLAVE_BUSWIDTH_1_BYTE | DMA_SLAVE_BUSWIDTH_2_BYTES | DMA_SLAVE_BUSWIDTH_4_BYTES; @@ -1393,13 +1405,23 @@ static int pxad_probe(struct platform_device *op) return PTR_ERR(pdev->base); of_id = of_match_device(pxad_dt_ids, &op->dev); - if (of_id) + if (of_id) { of_property_read_u32(op->dev.of_node, "#dma-channels", &dma_channels); - else if (pdata && pdata->dma_channels) + ret = of_property_read_u32(op->dev.of_node, "#dma-requests", + &nb_requestors); + if (ret) { + dev_warn(pdev->slave.dev, + "#dma-requests set to default 32 as missing in OF: %d", + ret); + nb_requestors = 32; + }; + } else if (pdata && pdata->dma_channels) { dma_channels = pdata->dma_channels; - else + nb_requestors = pdata->nb_requestors; + } else { dma_channels = 32; /* default 32 channel */ + } dma_cap_set(DMA_SLAVE, pdev->slave.cap_mask); dma_cap_set(DMA_MEMCPY, pdev->slave.cap_mask); @@ -1416,7 +1438,7 @@ static int pxad_probe(struct platform_device *op) pdev->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR; pdev->slave.dev = &op->dev; - ret = pxad_init_dmadev(op, pdev, dma_channels); + ret = pxad_init_dmadev(op, pdev, dma_channels, nb_requestors); if (ret) { dev_err(pdev->slave.dev, "unable to register\n"); return ret; @@ -1435,7 +1457,8 @@ static int pxad_probe(struct platform_device *op) platform_set_drvdata(op, pdev); pxad_init_debugfs(pdev); - dev_info(pdev->slave.dev, "initialized %d channels\n", dma_channels); + dev_info(pdev->slave.dev, "initialized %d channels on %d requestors\n", + dma_channels, nb_requestors); return 0; } diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 9eee13ef83a5..d87a47547ba5 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -1452,7 +1452,7 @@ static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range, u64 chan_off; u64 dram_base = get_dram_base(pvt, range); u64 hole_off = f10_dhar_offset(pvt); - u64 dct_sel_base_off = (pvt->dct_sel_hi & 0xFFFFFC00) << 16; + u64 dct_sel_base_off = (u64)(pvt->dct_sel_hi & 0xFFFFFC00) << 16; if (hi_rng) { /* diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 592af5f0cf39..53587377e672 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -435,16 +435,13 @@ void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev, */ void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev) { - int status; - if (!edac_dev->edac_check) return; - status = cancel_delayed_work(&edac_dev->work); - if (status == 0) { - /* workq instance might be running, wait for it */ - flush_workqueue(edac_workqueue); - } + edac_dev->op_state = OP_OFFLINE; + + cancel_delayed_work_sync(&edac_dev->work); + flush_workqueue(edac_workqueue); } /* diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 77ecd6a4179a..1b2c2187b347 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -586,18 +586,10 @@ static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec, */ static void edac_mc_workq_teardown(struct mem_ctl_info *mci) { - int status; - - if (mci->op_state != OP_RUNNING_POLL) - return; - - status = cancel_delayed_work(&mci->work); - if (status == 0) { - edac_dbg(0, "not canceled, flush the queue\n"); + mci->op_state = OP_OFFLINE; - /* workq instance might be running, wait for it */ - flush_workqueue(edac_workqueue); - } + cancel_delayed_work_sync(&mci->work); + flush_workqueue(edac_workqueue); } /* diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index a75acea0f674..58aed67b7eba 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -880,21 +880,26 @@ static struct device_type mci_attr_type = { int edac_create_sysfs_mci_device(struct mem_ctl_info *mci, const struct attribute_group **groups) { + char *name; int i, err; /* * The memory controller needs its own bus, in order to avoid * namespace conflicts at /sys/bus/edac. */ - mci->bus->name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx); - if (!mci->bus->name) + name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx); + if (!name) return -ENOMEM; + mci->bus->name = name; + edac_dbg(0, "creating bus %s\n", mci->bus->name); err = bus_register(mci->bus); - if (err < 0) - goto fail_free_name; + if (err < 0) { + kfree(name); + return err; + } /* get the /sys/devices/system/edac subsys reference */ mci->dev.type = &mci_attr_type; @@ -961,8 +966,8 @@ fail_unregister_dimm: device_unregister(&mci->dev); fail_unregister_bus: bus_unregister(mci->bus); -fail_free_name: - kfree(mci->bus->name); + kfree(name); + return err; } @@ -993,10 +998,12 @@ void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci) void edac_unregister_sysfs(struct mem_ctl_info *mci) { + const char *name = mci->bus->name; + edac_dbg(1, "Unregistering device %s\n", dev_name(&mci->dev)); device_unregister(&mci->dev); bus_unregister(mci->bus); - kfree(mci->bus->name); + kfree(name); } static void mc_attr_release(struct device *dev) diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c index 2cf44b4db80c..b4b38603b804 100644 --- a/drivers/edac/edac_pci.c +++ b/drivers/edac/edac_pci.c @@ -274,13 +274,12 @@ static void edac_pci_workq_setup(struct edac_pci_ctl_info *pci, */ static void edac_pci_workq_teardown(struct edac_pci_ctl_info *pci) { - int status; - edac_dbg(0, "\n"); - status = cancel_delayed_work(&pci->work); - if (status == 0) - flush_workqueue(edac_workqueue); + pci->op_state = OP_OFFLINE; + + cancel_delayed_work_sync(&pci->work); + flush_workqueue(edac_workqueue); } /* diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 01087a38da22..792bdae2b91d 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1866,7 +1866,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val, i7_dev = get_i7core_dev(mce->socketid); if (!i7_dev) - return NOTIFY_BAD; + return NOTIFY_DONE; mci = i7_dev->mci; pvt = mci->pvt_info; diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 429309c62699..37649221f81c 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -1117,8 +1117,8 @@ static void get_memory_layout(const struct mem_ctl_info *mci) edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n", n_tads, gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, - (u32)TAD_SOCK(reg), - (u32)TAD_CH(reg), + (u32)(1 << TAD_SOCK(reg)), + (u32)TAD_CH(reg) + 1, (u32)TAD_TGT0(reg), (u32)TAD_TGT1(reg), (u32)TAD_TGT2(reg), @@ -1396,7 +1396,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, } ch_way = TAD_CH(reg) + 1; - sck_way = TAD_SOCK(reg) + 1; + sck_way = TAD_SOCK(reg); if (ch_way == 3) idx = addr >> 6; @@ -1435,7 +1435,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, switch(ch_way) { case 2: case 4: - sck_xch = 1 << sck_way * (ch_way >> 1); + sck_xch = (1 << sck_way) * (ch_way >> 1); break; default: sprintf(msg, "Invalid mirror set. Can't decode addr"); @@ -1453,7 +1453,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, n_tads, addr, limit, - (u32)TAD_SOCK(reg), + sck_way, ch_way, offset, idx, @@ -1468,18 +1468,12 @@ static int get_memory_error_data(struct mem_ctl_info *mci, offset, addr); return -EINVAL; } - addr -= offset; - /* Store the low bits [0:6] of the addr */ - ch_addr = addr & 0x7f; - /* Remove socket wayness and remove 6 bits */ - addr >>= 6; - addr = div_u64(addr, sck_xch); -#if 0 - /* Divide by channel way */ - addr = addr / ch_way; -#endif - /* Recover the last 6 bits */ - ch_addr |= addr << 6; + + ch_addr = addr - offset; + ch_addr >>= (6 + shiftup); + ch_addr /= sck_xch; + ch_addr <<= (6 + shiftup); + ch_addr |= addr & ((1 << (6 + shiftup)) - 1); /* * Step 3) Decode rank @@ -2260,7 +2254,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, mci = get_mci_for_node_id(mce->socketid); if (!mci) - return NOTIFY_BAD; + return NOTIFY_DONE; pvt = mci->pvt_info; /* diff --git a/drivers/extcon/extcon-max77843.c b/drivers/extcon/extcon-max77843.c index 9f9ea334399c..b6cb30d207be 100644 --- a/drivers/extcon/extcon-max77843.c +++ b/drivers/extcon/extcon-max77843.c @@ -803,7 +803,7 @@ static int max77843_muic_probe(struct platform_device *pdev) /* Clear IRQ bits before request IRQs */ ret = regmap_bulk_read(max77843->regmap_muic, MAX77843_MUIC_REG_INT1, info->status, - MAX77843_MUIC_IRQ_NUM); + MAX77843_MUIC_STATUS_NUM); if (ret) { dev_err(&pdev->dev, "Failed to Clear IRQ bits\n"); goto err_muic_irq; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 027ca212179f..3b52677f459a 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -180,6 +180,7 @@ static int generic_ops_register(void) { generic_ops.get_variable = efi.get_variable; generic_ops.set_variable = efi.set_variable; + generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking; generic_ops.get_next_variable = efi.get_next_variable; generic_ops.query_variable_store = efi_query_variable_store; diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 756eca8c4cf8..10e6774ab2a2 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -221,7 +221,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor, } if ((attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(name, data, size) == false) { + efivar_validate(vendor, name, data, size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } @@ -447,7 +447,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, } if ((attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(name, data, size) == false) { + efivar_validate(new_var->VendorGuid, name, data, + size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } @@ -540,38 +541,30 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, static int efivar_create_sysfs_entry(struct efivar_entry *new_var) { - int i, short_name_size; + int short_name_size; char *short_name; - unsigned long variable_name_size; - efi_char16_t *variable_name; + unsigned long utf8_name_size; + efi_char16_t *variable_name = new_var->var.VariableName; int ret; - variable_name = new_var->var.VariableName; - variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t); - /* - * Length of the variable bytes in ASCII, plus the '-' separator, + * Length of the variable bytes in UTF8, plus the '-' separator, * plus the GUID, plus trailing NUL */ - short_name_size = variable_name_size / sizeof(efi_char16_t) - + 1 + EFI_VARIABLE_GUID_LEN + 1; - - short_name = kzalloc(short_name_size, GFP_KERNEL); + utf8_name_size = ucs2_utf8size(variable_name); + short_name_size = utf8_name_size + 1 + EFI_VARIABLE_GUID_LEN + 1; + short_name = kmalloc(short_name_size, GFP_KERNEL); if (!short_name) return -ENOMEM; - /* Convert Unicode to normal chars (assume top bits are 0), - ala UTF-8 */ - for (i=0; i < (int)(variable_name_size / sizeof(efi_char16_t)); i++) { - short_name[i] = variable_name[i] & 0xFF; - } + ucs2_as_utf8(short_name, variable_name, short_name_size); + /* This is ugly, but necessary to separate one vendor's private variables from another's. */ - - *(short_name + strlen(short_name)) = '-'; + short_name[utf8_name_size] = '-'; efi_guid_to_str(&new_var->var.VendorGuid, - short_name + strlen(short_name)); + short_name + utf8_name_size + 1); new_var->kobj.kset = efivars_kset; diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 70a0fb10517f..6f182fd91a6d 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -165,67 +165,148 @@ validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer, } struct variable_validate { + efi_guid_t vendor; char *name; bool (*validate)(efi_char16_t *var_name, int match, u8 *data, unsigned long len); }; +/* + * This is the list of variables we need to validate, as well as the + * whitelist for what we think is safe not to default to immutable. + * + * If it has a validate() method that's not NULL, it'll go into the + * validation routine. If not, it is assumed valid, but still used for + * whitelisting. + * + * Note that it's sorted by {vendor,name}, but globbed names must come after + * any other name with the same prefix. + */ static const struct variable_validate variable_validate[] = { - { "BootNext", validate_uint16 }, - { "BootOrder", validate_boot_order }, - { "DriverOrder", validate_boot_order }, - { "Boot*", validate_load_option }, - { "Driver*", validate_load_option }, - { "ConIn", validate_device_path }, - { "ConInDev", validate_device_path }, - { "ConOut", validate_device_path }, - { "ConOutDev", validate_device_path }, - { "ErrOut", validate_device_path }, - { "ErrOutDev", validate_device_path }, - { "Timeout", validate_uint16 }, - { "Lang", validate_ascii_string }, - { "PlatformLang", validate_ascii_string }, - { "", NULL }, + { EFI_GLOBAL_VARIABLE_GUID, "BootNext", validate_uint16 }, + { EFI_GLOBAL_VARIABLE_GUID, "BootOrder", validate_boot_order }, + { EFI_GLOBAL_VARIABLE_GUID, "Boot*", validate_load_option }, + { EFI_GLOBAL_VARIABLE_GUID, "DriverOrder", validate_boot_order }, + { EFI_GLOBAL_VARIABLE_GUID, "Driver*", validate_load_option }, + { EFI_GLOBAL_VARIABLE_GUID, "ConIn", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConInDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConOut", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConOutDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL }, + { EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 }, + { LINUX_EFI_CRASH_GUID, "*", NULL }, + { NULL_GUID, "", NULL }, }; +/* + * Check if @var_name matches the pattern given in @match_name. + * + * @var_name: an array of @len non-NUL characters. + * @match_name: a NUL-terminated pattern string, optionally ending in "*". A + * final "*" character matches any trailing characters @var_name, + * including the case when there are none left in @var_name. + * @match: on output, the number of non-wildcard characters in @match_name + * that @var_name matches, regardless of the return value. + * @return: whether @var_name fully matches @match_name. + */ +static bool +variable_matches(const char *var_name, size_t len, const char *match_name, + int *match) +{ + for (*match = 0; ; (*match)++) { + char c = match_name[*match]; + + switch (c) { + case '*': + /* Wildcard in @match_name means we've matched. */ + return true; + + case '\0': + /* @match_name has ended. Has @var_name too? */ + return (*match == len); + + default: + /* + * We've reached a non-wildcard char in @match_name. + * Continue only if there's an identical character in + * @var_name. + */ + if (*match < len && c == var_name[*match]) + continue; + return false; + } + } +} + bool -efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len) +efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, + unsigned long data_size) { int i; - u16 *unicode_name = var_name; + unsigned long utf8_size; + u8 *utf8_name; - for (i = 0; variable_validate[i].validate != NULL; i++) { - const char *name = variable_validate[i].name; - int match; + utf8_size = ucs2_utf8size(var_name); + utf8_name = kmalloc(utf8_size + 1, GFP_KERNEL); + if (!utf8_name) + return false; - for (match = 0; ; match++) { - char c = name[match]; - u16 u = unicode_name[match]; + ucs2_as_utf8(utf8_name, var_name, utf8_size); + utf8_name[utf8_size] = '\0'; - /* All special variables are plain ascii */ - if (u > 127) - return true; + for (i = 0; variable_validate[i].name[0] != '\0'; i++) { + const char *name = variable_validate[i].name; + int match = 0; - /* Wildcard in the matching name means we've matched */ - if (c == '*') - return variable_validate[i].validate(var_name, - match, data, len); + if (efi_guidcmp(vendor, variable_validate[i].vendor)) + continue; - /* Case sensitive match */ - if (c != u) + if (variable_matches(utf8_name, utf8_size+1, name, &match)) { + if (variable_validate[i].validate == NULL) break; - - /* Reached the end of the string while matching */ - if (!c) - return variable_validate[i].validate(var_name, - match, data, len); + kfree(utf8_name); + return variable_validate[i].validate(var_name, match, + data, data_size); } } - + kfree(utf8_name); return true; } EXPORT_SYMBOL_GPL(efivar_validate); +bool +efivar_variable_is_removable(efi_guid_t vendor, const char *var_name, + size_t len) +{ + int i; + bool found = false; + int match = 0; + + /* + * Check if our variable is in the validated variables list + */ + for (i = 0; variable_validate[i].name[0] != '\0'; i++) { + if (efi_guidcmp(variable_validate[i].vendor, vendor)) + continue; + + if (variable_matches(var_name, len, + variable_validate[i].name, &match)) { + found = true; + break; + } + } + + /* + * If it's in our list, it is removable. + */ + return found; +} +EXPORT_SYMBOL_GPL(efivar_variable_is_removable); + static efi_status_t check_var_size(u32 attributes, unsigned long size) { @@ -852,7 +933,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, *set = false; - if (efivar_validate(name, data, *size) == false) + if (efivar_validate(*vendor, name, data, *size) == false) return -EINVAL; /* diff --git a/drivers/gpu/arm/utgard/common/mali_timeline.c b/drivers/gpu/arm/utgard/common/mali_timeline.c index 5a767b39d56e..3f86077cde71 100644 --- a/drivers/gpu/arm/utgard/common/mali_timeline.c +++ b/drivers/gpu/arm/utgard/common/mali_timeline.c @@ -237,18 +237,15 @@ static void mali_timeline_destroy(struct mali_timeline *timeline) MALI_DEBUG_ASSERT(NULL != timeline->system); MALI_DEBUG_ASSERT(MALI_TIMELINE_MAX > timeline->id); -#if defined(CONFIG_SYNC) - if (NULL != timeline->sync_tl) { - sync_timeline_destroy(timeline->sync_tl); - } -#endif /* defined(CONFIG_SYNC) */ - if (NULL != timeline->delayed_work) { _mali_osk_wq_delayed_cancel_work_sync(timeline->delayed_work); _mali_osk_wq_delayed_delete_work_nonflush(timeline->delayed_work); } - -#ifndef CONFIG_SYNC +#if defined(CONFIG_SYNC) + if (NULL != timeline->sync_tl) { + sync_timeline_destroy(timeline->sync_tl); + } +#else _mali_osk_free(timeline); #endif } @@ -947,16 +944,21 @@ void mali_timeline_system_destroy(struct mali_timeline_system *system) mali_spinlock_reentrant_wait(system->timelines[i]->spinlock, tid); system->timelines[i]->destroyed = MALI_TRUE; mali_spinlock_reentrant_signal(system->timelines[i]->spinlock, tid); + if (NULL != system->timelines[i]->sync_tl) { + sync_timeline_destroy(system->timelines[i]->sync_tl); + } } } -#endif /* defined(CONFIG_SYNC) */ - +#else for (i = 0; i < MALI_TIMELINE_MAX; ++i) { if (NULL != system->timelines[i]) { mali_timeline_destroy(system->timelines[i]); } } +#endif /* defined(CONFIG_SYNC) */ + + if (NULL != system->spinlock) { mali_spinlock_reentrant_term(system->spinlock); } diff --git a/drivers/gpu/arm/utgard/platform/hikey/mali_hikey.c b/drivers/gpu/arm/utgard/platform/hikey/mali_hikey.c index 78f220d5e466..cc556b2656fe 100644 --- a/drivers/gpu/arm/utgard/platform/hikey/mali_hikey.c +++ b/drivers/gpu/arm/utgard/platform/hikey/mali_hikey.c @@ -162,6 +162,7 @@ static int mali_clock_on(void) static void mali_clock_off(void) { clk_disable_unprepare(mali_clk_g3d); + clk_disable_unprepare(mali_pclk_g3d); } static int mali_domain_powerup_finish(void) @@ -216,10 +217,8 @@ static int mali_regulator_enable(void) return stat; for (i = 0; i < 50; i++) { - unsigned int res = mali_reg_readl( - mali_soc_addr_table->soc_ao_sctrl_base_addr, - SOC_AO_SCTRL_SC_PW_MTCMOS_STAT0_ADDR(0), 1, 1); - if (res) + stat = regulator_is_enabled(mali_regulator); + if (stat > 0) break; udelay(1); } @@ -260,8 +259,6 @@ static int mali_regulator_disable(void) { mali_reg_writel(mali_soc_addr_table->soc_media_sctrl_base_addr, SOC_MEDIA_SCTRL_SC_MEDIA_RSTEN_ADDR(0), 0, 0, 1); - mali_reg_writel(mali_soc_addr_table->soc_media_sctrl_base_addr, - SOC_MEDIA_SCTRL_SC_MEDIA_CLKDIS_ADDR(0), 1, 1, 1); mali_reg_writel(mali_soc_addr_table->soc_ao_sctrl_base_addr, SOC_AO_SCTRL_SC_PW_CLKDIS0_ADDR(0), 1, 1, 1); mali_reg_writel(mali_soc_addr_table->soc_ao_sctrl_base_addr, diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 04c270757030..ca066018ea34 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -22,7 +22,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \ amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o # add asic specific block -amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o gmc_v7_0.o cik_ih.o kv_smc.o kv_dpm.o \ +amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \ ci_smc.o ci_dpm.o dce_v8_0.o gfx_v7_0.o cik_sdma.o uvd_v4_2.o vce_v2_0.o \ amdgpu_amdkfd_gfx_v7.o @@ -31,6 +31,7 @@ amdgpu-y += \ # add GMC block amdgpu-y += \ + gmc_v7_0.o \ gmc_v8_0.o # add IH block diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 048cfe073dae..053fc2f465df 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -604,8 +604,6 @@ struct amdgpu_sa_manager { uint32_t align; }; -struct amdgpu_sa_bo; - /* sub-allocation buffer */ struct amdgpu_sa_bo { struct list_head olist; @@ -1675,6 +1673,7 @@ struct amdgpu_uvd { struct amdgpu_bo *vcpu_bo; void *cpu_addr; uint64_t gpu_addr; + unsigned fw_version; atomic_t handles[AMDGPU_MAX_UVD_HANDLES]; struct drm_file *filp[AMDGPU_MAX_UVD_HANDLES]; struct delayed_work idle_work; @@ -2314,6 +2313,8 @@ bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo); int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr, uint32_t flags); bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm); +bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, + unsigned long end); bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm); uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, struct ttm_mem_reg *mem); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 89c3dd62ba21..119cdc2c43e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -77,7 +77,7 @@ void amdgpu_connector_hotplug(struct drm_connector *connector) } else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) { /* Don't try to start link training before we * have the dpcd */ - if (!amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) + if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) return; /* set it to OFF so that drm_helper_connector_dpms() diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d5b421330145..c961fe093e12 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1744,15 +1744,20 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } /* post card */ - amdgpu_atom_asic_init(adev->mode_info.atom_context); + if (!amdgpu_card_posted(adev)) + amdgpu_atom_asic_init(adev->mode_info.atom_context); r = amdgpu_resume(adev); + if (r) + DRM_ERROR("amdgpu_resume failed (%d).\n", r); amdgpu_fence_driver_resume(adev); - r = amdgpu_ib_ring_tests(adev); - if (r) - DRM_ERROR("ib ring test failed (%d).\n", r); + if (resume) { + r = amdgpu_ib_ring_tests(adev); + if (r) + DRM_ERROR("ib ring test failed (%d).\n", r); + } r = amdgpu_late_init(adev); if (r) @@ -1788,6 +1793,7 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } drm_kms_helper_poll_enable(dev); + drm_helper_hpd_irq_event(dev); if (fbcon) { amdgpu_fbdev_set_suspend(adev, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 5580d3420c3a..82903ca78529 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -72,8 +72,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &amdgpuCrtc->base; unsigned long flags; - unsigned i; - int vpos, hpos, stat, min_udelay; + unsigned i, repcnt = 4; + int vpos, hpos, stat, min_udelay = 0; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; amdgpu_flip_wait_fence(adev, &work->excl); @@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (amdgpuCrtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -112,12 +112,24 @@ static void amdgpu_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base); /* set the flip status */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 0508c5cd103a..8d6668cedf6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -250,11 +250,11 @@ static struct pci_device_id pciidlist[] = { {0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU}, #endif /* topaz */ - {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, /* tonga */ {0x1002, 0x6920, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, {0x1002, 0x6921, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index e23843f4d877..4488e82f87b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -303,7 +303,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file fw_info.feature = adev->vce.fb_version; break; case AMDGPU_INFO_FW_UVD: - fw_info.ver = 0; + fw_info.ver = adev->uvd.fw_version; fw_info.feature = 0; break; case AMDGPU_INFO_FW_GMC: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index b1969f2b2038..d4e2780c0796 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -142,7 +142,8 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn, list_for_each_entry(bo, &node->bos, mn_list) { - if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound) + if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start, + end)) continue; r = amdgpu_bo_reserve(bo, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 064ebb347074..89df7871653d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -52,7 +52,7 @@ struct amdgpu_hpd; #define AMDGPU_MAX_HPD_PINS 6 #define AMDGPU_MAX_CRTCS 6 -#define AMDGPU_MAX_AFMT_BLOCKS 7 +#define AMDGPU_MAX_AFMT_BLOCKS 9 enum amdgpu_rmx_type { RMX_OFF, @@ -308,8 +308,8 @@ struct amdgpu_mode_info { struct atom_context *atom_context; struct card_info *atom_card_info; bool mode_config_initialized; - struct amdgpu_crtc *crtcs[6]; - struct amdgpu_afmt *afmt[7]; + struct amdgpu_crtc *crtcs[AMDGPU_MAX_CRTCS]; + struct amdgpu_afmt *afmt[AMDGPU_MAX_AFMT_BLOCKS]; /* DVI-I properties */ struct drm_property *coherent_mode_property; /* DAC enable load detect */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index c3ce103b6a33..73628c7599e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <drm/drmP.h> #include <drm/amdgpu_drm.h> +#include <drm/drm_cache.h> #include "amdgpu.h" #include "amdgpu_trace.h" @@ -261,6 +262,13 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev, AMDGPU_GEM_DOMAIN_OA); bo->flags = flags; + + /* For architectures that don't support WC memory, + * mask out the WC flag from the BO + */ + if (!drm_arch_can_wc_memory()) + bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC; + amdgpu_fill_placement_to_bo(bo, placement); /* Kernel allocation are uninterruptible */ r = ttm_bo_init(&adev->mman.bdev, &bo->tbo, size, type, @@ -399,7 +407,8 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, } if (fpfn > bo->placements[i].fpfn) bo->placements[i].fpfn = fpfn; - if (lpfn && lpfn < bo->placements[i].lpfn) + if (!bo->placements[i].lpfn || + (lpfn && lpfn < bo->placements[i].lpfn)) bo->placements[i].lpfn = lpfn; bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT; } @@ -531,6 +540,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, if (!metadata_size) { if (bo->metadata_size) { kfree(bo->metadata); + bo->metadata = NULL; bo->metadata_size = 0; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 22a8c7d3a3ab..7ae15fad16ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -595,11 +595,6 @@ force: /* update display watermarks based on new power state */ amdgpu_display_bandwidth_update(adev); - /* update displays */ - amdgpu_dpm_display_configuration_changed(adev); - - adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; - adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; /* wait for the rings to drain */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { @@ -616,6 +611,12 @@ force: amdgpu_dpm_post_set_power_state(adev); + /* update displays */ + amdgpu_dpm_display_configuration_changed(adev); + + adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; + adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; + if (adev->pm.funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c index 8b88edb0434b..ca72a2e487b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c @@ -354,12 +354,15 @@ int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager, for (i = 0, count = 0; i < AMDGPU_MAX_RINGS; ++i) if (fences[i]) - fences[count++] = fences[i]; + fences[count++] = fence_get(fences[i]); if (count) { spin_unlock(&sa_manager->wq.lock); t = fence_wait_any_timeout(fences, count, false, MAX_SCHEDULE_TIMEOUT); + for (i = 0; i < count; ++i) + fence_put(fences[i]); + r = (t > 0) ? 0 : t; spin_lock(&sa_manager->wq.lock); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index dd005c336c97..181ce39ef5e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -293,7 +293,8 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync, fence = to_amdgpu_fence(sync->sync_to[i]); /* check if we really need to sync */ - if (!amdgpu_fence_need_sync(fence, ring)) + if (!amdgpu_enable_scheduler && + !amdgpu_fence_need_sync(fence, ring)) continue; /* prevent GPU deadlocks */ @@ -303,7 +304,7 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync, } if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores) { - r = fence_wait(&fence->base, true); + r = fence_wait(sync->sync_to[i], true); if (r) return r; continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8a1752ff3d8e..1cbb16e15307 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -712,7 +712,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm) 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(adev->pdev, gtt->ttm.dma_address[i])) { - while (--i) { + while (i--) { pci_unmap_page(adev->pdev, gtt->ttm.dma_address[i], PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); gtt->ttm.dma_address[i] = 0; @@ -783,6 +783,25 @@ bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm) return !!gtt->userptr; } +bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, + unsigned long end) +{ + struct amdgpu_ttm_tt *gtt = (void *)ttm; + unsigned long size; + + if (gtt == NULL) + return false; + + if (gtt->ttm.ttm.state != tt_bound || !gtt->userptr) + return false; + + size = (unsigned long)gtt->ttm.ttm.num_pages * PAGE_SIZE; + if (gtt->userptr > end || gtt->userptr + size <= start) + return false; + + return true; +} + bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm) { struct amdgpu_ttm_tt *gtt = (void *)ttm; @@ -808,7 +827,7 @@ uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, flags |= AMDGPU_PTE_SNOOPED; } - if (adev->asic_type >= CHIP_TOPAZ) + if (adev->asic_type >= CHIP_TONGA) flags |= AMDGPU_PTE_EXECUTABLE; flags |= AMDGPU_PTE_READABLE; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 53f987aeeacf..3b35ad83867c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -156,6 +156,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n", version_major, version_minor, family_id); + adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) | + (family_id << 8)); + bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8) + AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE; r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true, @@ -273,6 +276,8 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev) memcpy(adev->uvd.cpu_addr, (adev->uvd.fw->data) + offset, (adev->uvd.fw->size) - offset); + cancel_delayed_work_sync(&adev->uvd.idle_work); + size = amdgpu_bo_size(adev->uvd.vcpu_bo); size -= le32_to_cpu(hdr->ucode_size_bytes); ptr = adev->uvd.cpu_addr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index a745eeeb5d82..bb0da76051a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -220,6 +220,7 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) if (i == AMDGPU_MAX_VCE_HANDLES) return 0; + cancel_delayed_work_sync(&adev->vce.idle_work); /* TODO: suspending running encoding sessions isn't supported */ return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index b53d273eb7a1..8c5ec151ddac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1010,13 +1010,13 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, return -EINVAL; /* make sure object fit at this offset */ - eaddr = saddr + size; + eaddr = saddr + size - 1; if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) return -EINVAL; last_pfn = eaddr / AMDGPU_GPU_PAGE_SIZE; - if (last_pfn > adev->vm_manager.max_pfn) { - dev_err(adev->dev, "va above limit (0x%08X > 0x%08X)\n", + if (last_pfn >= adev->vm_manager.max_pfn) { + dev_err(adev->dev, "va above limit (0x%08X >= 0x%08X)\n", last_pfn, adev->vm_manager.max_pfn); return -EINVAL; } @@ -1025,7 +1025,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, eaddr /= AMDGPU_GPU_PAGE_SIZE; spin_lock(&vm->it_lock); - it = interval_tree_iter_first(&vm->va, saddr, eaddr - 1); + it = interval_tree_iter_first(&vm->va, saddr, eaddr); spin_unlock(&vm->it_lock); if (it) { struct amdgpu_bo_va_mapping *tmp; @@ -1046,7 +1046,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, INIT_LIST_HEAD(&mapping->list); mapping->it.start = saddr; - mapping->it.last = eaddr - 1; + mapping->it.last = eaddr; mapping->offset = offset; mapping->flags = flags; @@ -1248,7 +1248,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) { const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE, AMDGPU_VM_PTE_COUNT * 8); - unsigned pd_size, pd_entries, pts_size; + unsigned pd_size, pd_entries; int i, r; for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { @@ -1266,8 +1266,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) pd_entries = amdgpu_vm_num_pdes(adev); /* allocate page table array */ - pts_size = pd_entries * sizeof(struct amdgpu_vm_pt); - vm->page_tables = kzalloc(pts_size, GFP_KERNEL); + vm->page_tables = drm_calloc_large(pd_entries, sizeof(struct amdgpu_vm_pt)); if (vm->page_tables == NULL) { DRM_ERROR("Cannot allocate memory for page table array\n"); return -ENOMEM; @@ -1327,7 +1326,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) for (i = 0; i < amdgpu_vm_num_pdes(adev); i++) amdgpu_bo_unref(&vm->page_tables[i].bo); - kfree(vm->page_tables); + drm_free_large(vm->page_tables); amdgpu_bo_unref(&vm->page_directory); fence_put(vm->page_directory_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 1e0bba29e167..1cd6de575305 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -298,6 +298,10 @@ bool amdgpu_atombios_encoder_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (amdgpu_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) amdgpu_panel_mode_fixup(encoder, adjusted_mode); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 72793f93e2fc..946300764609 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -3628,6 +3628,19 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned vm_id, uint64_t pd_addr) { int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX); + uint32_t seq = ring->fence_drv.sync_seq[ring->idx]; + uint64_t addr = ring->fence_drv.gpu_addr; + + amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); + amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); + amdgpu_ring_write(ring, seq); + amdgpu_ring_write(ring, 0xffffffff); + amdgpu_ring_write(ring, 4); /* poll interval */ + if (usepfp) { /* synce CE with ME to prevent CE fetch CEIB before context switch done */ amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index e1dcab98e249..d1054034d14b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -90,7 +90,6 @@ MODULE_FIRMWARE("amdgpu/topaz_ce.bin"); MODULE_FIRMWARE("amdgpu/topaz_pfp.bin"); MODULE_FIRMWARE("amdgpu/topaz_me.bin"); MODULE_FIRMWARE("amdgpu/topaz_mec.bin"); -MODULE_FIRMWARE("amdgpu/topaz_mec2.bin"); MODULE_FIRMWARE("amdgpu/topaz_rlc.bin"); MODULE_FIRMWARE("amdgpu/fiji_ce.bin"); @@ -807,7 +806,8 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); - if (adev->asic_type != CHIP_STONEY) { + if ((adev->asic_type != CHIP_STONEY) && + (adev->asic_type != CHIP_TOPAZ)) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); if (!err) { @@ -4681,7 +4681,8 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ - WAIT_REG_MEM_FUNCTION(3))); /* equal */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index ed8abb58a785..ea87033bfaf6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -42,9 +42,39 @@ static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev); MODULE_FIRMWARE("radeon/bonaire_mc.bin"); MODULE_FIRMWARE("radeon/hawaii_mc.bin"); +MODULE_FIRMWARE("amdgpu/topaz_mc.bin"); + +static const u32 golden_settings_iceland_a11[] = +{ + mmVM_PRT_APERTURE0_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE1_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE2_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE3_LOW_ADDR, 0x0fffffff, 0x0fffffff +}; + +static const u32 iceland_mgcg_cgcg_init[] = +{ + mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 +}; + +static void gmc_v7_0_init_golden_registers(struct amdgpu_device *adev) +{ + switch (adev->asic_type) { + case CHIP_TOPAZ: + amdgpu_program_register_sequence(adev, + iceland_mgcg_cgcg_init, + (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init)); + amdgpu_program_register_sequence(adev, + golden_settings_iceland_a11, + (const u32)ARRAY_SIZE(golden_settings_iceland_a11)); + break; + default: + break; + } +} /** - * gmc8_mc_wait_for_idle - wait for MC idle callback. + * gmc7_mc_wait_for_idle - wait for MC idle callback. * * @adev: amdgpu_device pointer * @@ -132,13 +162,20 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev) case CHIP_HAWAII: chip_name = "hawaii"; break; + case CHIP_TOPAZ: + chip_name = "topaz"; + break; case CHIP_KAVERI: case CHIP_KABINI: return 0; default: BUG(); } - snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + if (adev->asic_type == CHIP_TOPAZ) + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name); + else + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + err = request_firmware(&adev->mc.fw, fw_name, adev->dev); if (err) goto out; @@ -861,14 +898,6 @@ static int gmc_v7_0_early_init(void *handle) gmc_v7_0_set_gart_funcs(adev); gmc_v7_0_set_irq_funcs(adev); - if (adev->flags & AMD_IS_APU) { - adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; - } else { - u32 tmp = RREG32(mmMC_SEQ_MISC0); - tmp &= MC_SEQ_MISC0__MT__MASK; - adev->mc.vram_type = gmc_v7_0_convert_vram_type(tmp); - } - return 0; } @@ -889,6 +918,14 @@ static int gmc_v7_0_sw_init(void *handle) if (r) return r; + if (adev->flags & AMD_IS_APU) { + adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; + } else { + u32 tmp = RREG32(mmMC_SEQ_MISC0); + tmp &= MC_SEQ_MISC0__MT__MASK; + adev->mc.vram_type = gmc_v7_0_convert_vram_type(tmp); + } + r = amdgpu_irq_add_id(adev, 146, &adev->mc.vm_fault); if (r) return r; @@ -980,6 +1017,8 @@ static int gmc_v7_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v7_0_init_golden_registers(adev); + gmc_v7_0_mc_program(adev); if (!(adev->flags & AMD_IS_APU)) { diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index d39028440814..08423089fb84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -42,9 +42,7 @@ static void gmc_v8_0_set_gart_funcs(struct amdgpu_device *adev); static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev); -MODULE_FIRMWARE("amdgpu/topaz_mc.bin"); MODULE_FIRMWARE("amdgpu/tonga_mc.bin"); -MODULE_FIRMWARE("amdgpu/fiji_mc.bin"); static const u32 golden_settings_tonga_a11[] = { @@ -75,19 +73,6 @@ static const u32 fiji_mgcg_cgcg_init[] = mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 }; -static const u32 golden_settings_iceland_a11[] = -{ - mmVM_PRT_APERTURE0_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE1_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE2_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE3_LOW_ADDR, 0x0fffffff, 0x0fffffff -}; - -static const u32 iceland_mgcg_cgcg_init[] = -{ - mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 -}; - static const u32 cz_mgcg_cgcg_init[] = { mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 @@ -102,14 +87,6 @@ static const u32 stoney_mgcg_cgcg_init[] = static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev) { switch (adev->asic_type) { - case CHIP_TOPAZ: - amdgpu_program_register_sequence(adev, - iceland_mgcg_cgcg_init, - (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init)); - amdgpu_program_register_sequence(adev, - golden_settings_iceland_a11, - (const u32)ARRAY_SIZE(golden_settings_iceland_a11)); - break; case CHIP_FIJI: amdgpu_program_register_sequence(adev, fiji_mgcg_cgcg_init, @@ -229,15 +206,10 @@ static int gmc_v8_0_init_microcode(struct amdgpu_device *adev) DRM_DEBUG("\n"); switch (adev->asic_type) { - case CHIP_TOPAZ: - chip_name = "topaz"; - break; case CHIP_TONGA: chip_name = "tonga"; break; case CHIP_FIJI: - chip_name = "fiji"; - break; case CHIP_CARRIZO: case CHIP_STONEY: return 0; @@ -880,14 +852,6 @@ static int gmc_v8_0_early_init(void *handle) gmc_v8_0_set_gart_funcs(adev); gmc_v8_0_set_irq_funcs(adev); - if (adev->flags & AMD_IS_APU) { - adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; - } else { - u32 tmp = RREG32(mmMC_SEQ_MISC0); - tmp &= MC_SEQ_MISC0__MT__MASK; - adev->mc.vram_type = gmc_v8_0_convert_vram_type(tmp); - } - return 0; } @@ -898,6 +862,8 @@ static int gmc_v8_0_late_init(void *handle) return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); } +#define mmMC_SEQ_MISC0_FIJI 0xA71 + static int gmc_v8_0_sw_init(void *handle) { int r; @@ -908,6 +874,19 @@ static int gmc_v8_0_sw_init(void *handle) if (r) return r; + if (adev->flags & AMD_IS_APU) { + adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; + } else { + u32 tmp; + + if (adev->asic_type == CHIP_FIJI) + tmp = RREG32(mmMC_SEQ_MISC0_FIJI); + else + tmp = RREG32(mmMC_SEQ_MISC0); + tmp &= MC_SEQ_MISC0__MT__MASK; + adev->mc.vram_type = gmc_v8_0_convert_vram_type(tmp); + } + r = amdgpu_irq_add_id(adev, 146, &adev->mc.vm_fault); if (r) return r; @@ -1003,7 +982,7 @@ static int gmc_v8_0_hw_init(void *handle) gmc_v8_0_mc_program(adev); - if (!(adev->flags & AMD_IS_APU)) { + if (adev->asic_type == CHIP_TONGA) { r = gmc_v8_0_mc_load_microcode(adev); if (r) { DRM_ERROR("Failed to load MC firmware!\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c index 966d4b2ed9da..090486c18249 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c @@ -432,7 +432,7 @@ static uint32_t iceland_smu_get_mask_for_fw_type(uint32_t fw_type) case AMDGPU_UCODE_ID_CP_ME: return UCODE_ID_CP_ME_MASK; case AMDGPU_UCODE_ID_CP_MEC1: - return UCODE_ID_CP_MEC_MASK | UCODE_ID_CP_MEC_JT1_MASK | UCODE_ID_CP_MEC_JT2_MASK; + return UCODE_ID_CP_MEC_MASK | UCODE_ID_CP_MEC_JT1_MASK; case AMDGPU_UCODE_ID_CP_MEC2: return UCODE_ID_CP_MEC_MASK; case AMDGPU_UCODE_ID_RLC_G: @@ -522,12 +522,6 @@ static int iceland_smu_request_load_fw(struct amdgpu_device *adev) return -EINVAL; } - if (iceland_smu_populate_single_firmware_entry(adev, UCODE_ID_CP_MEC_JT2, - &toc->entry[toc->num_entries++])) { - DRM_ERROR("Failed to get firmware entry for MEC_JT2\n"); - return -EINVAL; - } - if (iceland_smu_populate_single_firmware_entry(adev, UCODE_ID_SDMA0, &toc->entry[toc->num_entries++])) { DRM_ERROR("Failed to get firmware entry for SDMA0\n"); @@ -550,8 +544,8 @@ static int iceland_smu_request_load_fw(struct amdgpu_device *adev) UCODE_ID_CP_ME_MASK | UCODE_ID_CP_PFP_MASK | UCODE_ID_CP_MEC_MASK | - UCODE_ID_CP_MEC_JT1_MASK | - UCODE_ID_CP_MEC_JT2_MASK; + UCODE_ID_CP_MEC_JT1_MASK; + if (iceland_send_msg_to_smc_with_parameter_without_waiting(adev, PPSMC_MSG_LoadUcodes, fw_to_load)) { DRM_ERROR("Fail to request SMU load ucode\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 2cf50180cc51..b1c7a9b3631b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -32,8 +32,8 @@ #include "oss/oss_2_4_d.h" #include "oss/oss_2_4_sh_mask.h" -#include "gmc/gmc_8_1_d.h" -#include "gmc/gmc_8_1_sh_mask.h" +#include "gmc/gmc_7_1_d.h" +#include "gmc/gmc_7_1_sh_mask.h" #include "gca/gfx_8_0_d.h" #include "gca/gfx_8_0_enum.h" diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c index 204903897b4f..63d6cb3c1110 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c @@ -122,25 +122,12 @@ static int tonga_dpm_hw_fini(void *handle) static int tonga_dpm_suspend(void *handle) { - return 0; + return tonga_dpm_hw_fini(handle); } static int tonga_dpm_resume(void *handle) { - int ret; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - mutex_lock(&adev->pm.mutex); - - ret = tonga_smu_start(adev); - if (ret) { - DRM_ERROR("SMU start failed\n"); - goto fail; - } - -fail: - mutex_unlock(&adev->pm.mutex); - return ret; + return tonga_dpm_hw_init(handle); } static int tonga_dpm_set_clockgating_state(void *handle, diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 2adc1c855e85..3e9cbe398151 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -60,6 +60,7 @@ #include "vi.h" #include "vi_dpm.h" #include "gmc_v8_0.h" +#include "gmc_v7_0.h" #include "gfx_v8_0.h" #include "sdma_v2_4.h" #include "sdma_v3_0.h" @@ -1081,10 +1082,10 @@ static const struct amdgpu_ip_block_version topaz_ip_blocks[] = }, { .type = AMD_IP_BLOCK_TYPE_GMC, - .major = 8, - .minor = 0, + .major = 7, + .minor = 4, .rev = 0, - .funcs = &gmc_v8_0_ip_funcs, + .funcs = &gmc_v7_0_ip_funcs, }, { .type = AMD_IP_BLOCK_TYPE_IH, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index c34c393e9aea..d5e19b5fbbfb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -513,7 +513,7 @@ static int dbgdev_wave_control_set_registers( union SQ_CMD_BITS *in_reg_sq_cmd, union GRBM_GFX_INDEX_BITS *in_reg_gfx_index) { - int status; + int status = 0; union SQ_CMD_BITS reg_sq_cmd; union GRBM_GFX_INDEX_BITS reg_gfx_index; struct HsaDbgWaveMsgAMDGen2 *pMsg; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 541a610667ad..e0b4586a26fd 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -227,7 +227,7 @@ static int ast_get_dram_info(struct drm_device *dev) } while (ast_read32(ast, 0x10000) != 0x01); data = ast_read32(ast, 0x10004); - if (data & 0x400) + if (data & 0x40) ast->dram_bus_width = 16; else ast->dram_bus_width = 32; diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 9535c5b60387..7e5a97204051 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -178,7 +178,7 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, { struct drm_dp_aux_msg msg; unsigned int retry; - int err; + int err = 0; memset(&msg, 0, sizeof(msg)); msg.address = offset; @@ -186,6 +186,8 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, msg.buffer = buffer; msg.size = size; + mutex_lock(&aux->hw_mutex); + /* * The specification doesn't give any recommendation on how often to * retry native transactions. We used to retry 7 times like for @@ -194,25 +196,24 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, */ for (retry = 0; retry < 32; retry++) { - mutex_lock(&aux->hw_mutex); err = aux->transfer(aux, &msg); - mutex_unlock(&aux->hw_mutex); if (err < 0) { if (err == -EBUSY) continue; - return err; + goto unlock; } switch (msg.reply & DP_AUX_NATIVE_REPLY_MASK) { case DP_AUX_NATIVE_REPLY_ACK: if (err < size) - return -EPROTO; - return err; + err = -EPROTO; + goto unlock; case DP_AUX_NATIVE_REPLY_NACK: - return -EIO; + err = -EIO; + goto unlock; case DP_AUX_NATIVE_REPLY_DEFER: usleep_range(AUX_RETRY_INTERVAL, AUX_RETRY_INTERVAL + 100); @@ -221,7 +222,11 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, } DRM_DEBUG_KMS("too many retries, giving up\n"); - return -EIO; + err = -EIO; + +unlock: + mutex_unlock(&aux->hw_mutex); + return err; } /** @@ -543,9 +548,7 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) int max_retries = max(7, drm_dp_i2c_retry_count(msg, dp_aux_i2c_speed_khz)); for (retry = 0, defer_i2c = 0; retry < (max_retries + defer_i2c); retry++) { - mutex_lock(&aux->hw_mutex); ret = aux->transfer(aux, msg); - mutex_unlock(&aux->hw_mutex); if (ret < 0) { if (ret == -EBUSY) continue; @@ -684,6 +687,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, memset(&msg, 0, sizeof(msg)); + mutex_lock(&aux->hw_mutex); + for (i = 0; i < num; i++) { msg.address = msgs[i].addr; drm_dp_i2c_msg_set_request(&msg, &msgs[i]); @@ -738,6 +743,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, msg.size = 0; (void)drm_dp_i2c_do_msg(aux, &msg); + mutex_unlock(&aux->hw_mutex); + return err; } diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 809959d56d78..d268bf18a662 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -798,6 +798,18 @@ static struct drm_dp_mst_branch *drm_dp_add_mst_branch_device(u8 lct, u8 *rad) return mstb; } +static void drm_dp_free_mst_port(struct kref *kref); + +static void drm_dp_free_mst_branch_device(struct kref *kref) +{ + struct drm_dp_mst_branch *mstb = container_of(kref, struct drm_dp_mst_branch, kref); + if (mstb->port_parent) { + if (list_empty(&mstb->port_parent->next)) + kref_put(&mstb->port_parent->kref, drm_dp_free_mst_port); + } + kfree(mstb); +} + static void drm_dp_destroy_mst_branch_device(struct kref *kref) { struct drm_dp_mst_branch *mstb = container_of(kref, struct drm_dp_mst_branch, kref); @@ -805,6 +817,15 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref) bool wake_tx = false; /* + * init kref again to be used by ports to remove mst branch when it is + * not needed anymore + */ + kref_init(kref); + + if (mstb->port_parent && list_empty(&mstb->port_parent->next)) + kref_get(&mstb->port_parent->kref); + + /* * destroy all ports - don't need lock * as there are no more references to the mst branch * device at this point. @@ -830,7 +851,8 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref) if (wake_tx) wake_up(&mstb->mgr->tx_waitq); - kfree(mstb); + + kref_put(kref, drm_dp_free_mst_branch_device); } static void drm_dp_put_mst_branch_device(struct drm_dp_mst_branch *mstb) @@ -878,6 +900,7 @@ static void drm_dp_destroy_port(struct kref *kref) * from an EDID retrieval */ mutex_lock(&mgr->destroy_connector_lock); + kref_get(&port->parent->kref); list_add(&port->next, &mgr->destroy_connector_list); mutex_unlock(&mgr->destroy_connector_lock); schedule_work(&mgr->destroy_connector_work); @@ -973,17 +996,17 @@ static struct drm_dp_mst_port *drm_dp_get_port(struct drm_dp_mst_branch *mstb, u static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port, u8 *rad) { - int lct = port->parent->lct; + int parent_lct = port->parent->lct; int shift = 4; - int idx = lct / 2; - if (lct > 1) { - memcpy(rad, port->parent->rad, idx); - shift = (lct % 2) ? 4 : 0; + int idx = (parent_lct - 1) / 2; + if (parent_lct > 1) { + memcpy(rad, port->parent->rad, idx + 1); + shift = (parent_lct % 2) ? 4 : 0; } else rad[0] = 0; rad[idx] |= port->port_num << shift; - return lct + 1; + return parent_lct + 1; } /* @@ -1013,18 +1036,27 @@ static bool drm_dp_port_setup_pdt(struct drm_dp_mst_port *port) return send_link; } -static void drm_dp_check_port_guid(struct drm_dp_mst_branch *mstb, - struct drm_dp_mst_port *port) +static void drm_dp_check_mstb_guid(struct drm_dp_mst_branch *mstb, u8 *guid) { int ret; - if (port->dpcd_rev >= 0x12) { - port->guid_valid = drm_dp_validate_guid(mstb->mgr, port->guid); - if (!port->guid_valid) { - ret = drm_dp_send_dpcd_write(mstb->mgr, - port, - DP_GUID, - 16, port->guid); - port->guid_valid = true; + + memcpy(mstb->guid, guid, 16); + + if (!drm_dp_validate_guid(mstb->mgr, mstb->guid)) { + if (mstb->port_parent) { + ret = drm_dp_send_dpcd_write( + mstb->mgr, + mstb->port_parent, + DP_GUID, + 16, + mstb->guid); + } else { + + ret = drm_dp_dpcd_write( + mstb->mgr->aux, + DP_GUID, + mstb->guid, + 16); } } } @@ -1039,7 +1071,7 @@ static void build_mst_prop_path(const struct drm_dp_mst_branch *mstb, snprintf(proppath, proppath_size, "mst:%d", mstb->mgr->conn_base_id); for (i = 0; i < (mstb->lct - 1); i++) { int shift = (i % 2) ? 0 : 4; - int port_num = mstb->rad[i / 2] >> shift; + int port_num = (mstb->rad[i / 2] >> shift) & 0xf; snprintf(temp, sizeof(temp), "-%d", port_num); strlcat(proppath, temp, proppath_size); } @@ -1081,7 +1113,6 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, port->dpcd_rev = port_msg->dpcd_revision; port->num_sdp_streams = port_msg->num_sdp_streams; port->num_sdp_stream_sinks = port_msg->num_sdp_stream_sinks; - memcpy(port->guid, port_msg->peer_guid, 16); /* manage mstb port lists with mgr lock - take a reference for this list */ @@ -1094,11 +1125,9 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, if (old_ddps != port->ddps) { if (port->ddps) { - drm_dp_check_port_guid(mstb, port); if (!port->input) drm_dp_send_enum_path_resources(mstb->mgr, mstb, port); } else { - port->guid_valid = false; port->available_pbn = 0; } } @@ -1157,10 +1186,8 @@ static void drm_dp_update_port(struct drm_dp_mst_branch *mstb, if (old_ddps != port->ddps) { if (port->ddps) { - drm_dp_check_port_guid(mstb, port); dowork = true; } else { - port->guid_valid = false; port->available_pbn = 0; } } @@ -1190,7 +1217,7 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_ for (i = 0; i < lct - 1; i++) { int shift = (i % 2) ? 0 : 4; - int port_num = rad[i / 2] >> shift; + int port_num = (rad[i / 2] >> shift) & 0xf; list_for_each_entry(port, &mstb->ports, next) { if (port->port_num == port_num) { @@ -1210,6 +1237,48 @@ out: return mstb; } +static struct drm_dp_mst_branch *get_mst_branch_device_by_guid_helper( + struct drm_dp_mst_branch *mstb, + uint8_t *guid) +{ + struct drm_dp_mst_branch *found_mstb; + struct drm_dp_mst_port *port; + + if (memcmp(mstb->guid, guid, 16) == 0) + return mstb; + + + list_for_each_entry(port, &mstb->ports, next) { + if (!port->mstb) + continue; + + found_mstb = get_mst_branch_device_by_guid_helper(port->mstb, guid); + + if (found_mstb) + return found_mstb; + } + + return NULL; +} + +static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device_by_guid( + struct drm_dp_mst_topology_mgr *mgr, + uint8_t *guid) +{ + struct drm_dp_mst_branch *mstb; + + /* find the port by iterating down */ + mutex_lock(&mgr->lock); + + mstb = get_mst_branch_device_by_guid_helper(mgr->mst_primary, guid); + + if (mstb) + kref_get(&mstb->kref); + + mutex_unlock(&mgr->lock); + return mstb; +} + static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_branch *mstb) { @@ -1320,6 +1389,7 @@ static int set_hdr_from_dst_qlock(struct drm_dp_sideband_msg_hdr *hdr, struct drm_dp_sideband_msg_tx *txmsg) { struct drm_dp_mst_branch *mstb = txmsg->dst; + u8 req_type; /* both msg slots are full */ if (txmsg->seqno == -1) { @@ -1336,7 +1406,13 @@ static int set_hdr_from_dst_qlock(struct drm_dp_sideband_msg_hdr *hdr, txmsg->seqno = 1; mstb->tx_slots[txmsg->seqno] = txmsg; } - hdr->broadcast = 0; + + req_type = txmsg->msg[0] & 0x7f; + if (req_type == DP_CONNECTION_STATUS_NOTIFY || + req_type == DP_RESOURCE_STATUS_NOTIFY) + hdr->broadcast = 1; + else + hdr->broadcast = 0; hdr->path_msg = txmsg->path_msg; hdr->lct = mstb->lct; hdr->lcr = mstb->lct - 1; @@ -1438,26 +1514,18 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) } /* called holding qlock */ -static void process_single_up_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) +static void process_single_up_tx_qlock(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_sideband_msg_tx *txmsg) { - struct drm_dp_sideband_msg_tx *txmsg; int ret; /* construct a chunk from the first msg in the tx_msg queue */ - if (list_empty(&mgr->tx_msg_upq)) { - mgr->tx_up_in_progress = false; - return; - } - - txmsg = list_first_entry(&mgr->tx_msg_upq, struct drm_dp_sideband_msg_tx, next); ret = process_single_tx_qlock(mgr, txmsg, true); - if (ret == 1) { - /* up txmsgs aren't put in slots - so free after we send it */ - list_del(&txmsg->next); - kfree(txmsg); - } else if (ret) + + if (ret != 1) DRM_DEBUG_KMS("failed to send msg in q %d\n", ret); - mgr->tx_up_in_progress = true; + + txmsg->dst->tx_slots[txmsg->seqno] = NULL; } static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr, @@ -1507,6 +1575,9 @@ static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, txmsg->reply.u.link_addr.ports[i].num_sdp_streams, txmsg->reply.u.link_addr.ports[i].num_sdp_stream_sinks); } + + drm_dp_check_mstb_guid(mstb, txmsg->reply.u.link_addr.guid); + for (i = 0; i < txmsg->reply.u.link_addr.nports; i++) { drm_dp_add_port(mstb, mgr->dev, &txmsg->reply.u.link_addr.ports[i]); } @@ -1554,6 +1625,37 @@ static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, return 0; } +static struct drm_dp_mst_port *drm_dp_get_last_connected_port_to_mstb(struct drm_dp_mst_branch *mstb) +{ + if (!mstb->port_parent) + return NULL; + + if (mstb->port_parent->mstb != mstb) + return mstb->port_parent; + + return drm_dp_get_last_connected_port_to_mstb(mstb->port_parent->parent); +} + +static struct drm_dp_mst_branch *drm_dp_get_last_connected_port_and_mstb(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_branch *mstb, + int *port_num) +{ + struct drm_dp_mst_branch *rmstb = NULL; + struct drm_dp_mst_port *found_port; + mutex_lock(&mgr->lock); + if (mgr->mst_primary) { + found_port = drm_dp_get_last_connected_port_to_mstb(mstb); + + if (found_port) { + rmstb = found_port->parent; + kref_get(&rmstb->kref); + *port_num = found_port->port_num; + } + } + mutex_unlock(&mgr->lock); + return rmstb; +} + static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, int id, @@ -1561,12 +1663,23 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, { struct drm_dp_sideband_msg_tx *txmsg; struct drm_dp_mst_branch *mstb; - int len, ret; + int len, ret, port_num; - mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent); - if (!mstb) + port = drm_dp_get_validated_port_ref(mgr, port); + if (!port) return -EINVAL; + port_num = port->port_num; + mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent); + if (!mstb) { + mstb = drm_dp_get_last_connected_port_and_mstb(mgr, port->parent, &port_num); + + if (!mstb) { + drm_dp_put_port(port); + return -EINVAL; + } + } + txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL); if (!txmsg) { ret = -ENOMEM; @@ -1574,7 +1687,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, } txmsg->dst = mstb; - len = build_allocate_payload(txmsg, port->port_num, + len = build_allocate_payload(txmsg, port_num, id, pbn); @@ -1590,6 +1703,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, kfree(txmsg); fail_put: drm_dp_put_mst_branch_device(mstb); + drm_dp_put_port(port); return ret; } @@ -1672,6 +1786,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) req_payload.start_slot = cur_slots; if (mgr->proposed_vcpis[i]) { port = container_of(mgr->proposed_vcpis[i], struct drm_dp_mst_port, vcpi); + port = drm_dp_get_validated_port_ref(mgr, port); + if (!port) { + mutex_unlock(&mgr->payload_lock); + return -EINVAL; + } req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots; } else { port = NULL; @@ -1697,6 +1816,9 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) mgr->payloads[i].payload_state = req_payload.payload_state; } cur_slots += req_payload.num_slots; + + if (port) + drm_dp_put_port(port); } for (i = 0; i < mgr->max_payloads; i++) { @@ -1844,11 +1966,12 @@ static int drm_dp_send_up_ack_reply(struct drm_dp_mst_topology_mgr *mgr, drm_dp_encode_up_ack_reply(txmsg, req_type); mutex_lock(&mgr->qlock); - list_add_tail(&txmsg->next, &mgr->tx_msg_upq); - if (!mgr->tx_up_in_progress) { - process_single_up_tx_qlock(mgr); - } + + process_single_up_tx_qlock(mgr, txmsg); + mutex_unlock(&mgr->qlock); + + kfree(txmsg); return 0; } @@ -1927,31 +2050,17 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms mgr->mst_primary = mstb; kref_get(&mgr->mst_primary->kref); - { - struct drm_dp_payload reset_pay; - reset_pay.start_slot = 0; - reset_pay.num_slots = 0x3f; - drm_dp_dpcd_write_payload(mgr, 0, &reset_pay); - } - ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, - DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC); + DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC); if (ret < 0) { goto out_unlock; } - - /* sort out guid */ - ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, mgr->guid, 16); - if (ret != 16) { - DRM_DEBUG_KMS("failed to read DP GUID %d\n", ret); - goto out_unlock; - } - - mgr->guid_valid = drm_dp_validate_guid(mgr, mgr->guid); - if (!mgr->guid_valid) { - ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, mgr->guid, 16); - mgr->guid_valid = true; + { + struct drm_dp_payload reset_pay; + reset_pay.start_slot = 0; + reset_pay.num_slots = 0x3f; + drm_dp_dpcd_write_payload(mgr, 0, &reset_pay); } queue_work(system_long_wq, &mgr->work); @@ -2015,6 +2124,8 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) if (mgr->mst_primary) { int sret; + u8 guid[16]; + sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE); if (sret != DP_RECEIVER_CAP_SIZE) { DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); @@ -2029,6 +2140,16 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) ret = -1; goto out_unlock; } + + /* Some hubs forget their guids after they resume */ + sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (sret != 16) { + DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); + ret = -1; + goto out_unlock; + } + drm_dp_check_mstb_guid(mgr->mst_primary, guid); + ret = 0; } else ret = -1; @@ -2145,28 +2266,51 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) if (mgr->up_req_recv.have_eomt) { struct drm_dp_sideband_msg_req_body msg; - struct drm_dp_mst_branch *mstb; + struct drm_dp_mst_branch *mstb = NULL; bool seqno; - mstb = drm_dp_get_mst_branch_device(mgr, - mgr->up_req_recv.initial_hdr.lct, - mgr->up_req_recv.initial_hdr.rad); - if (!mstb) { - DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); - memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); - return 0; + + if (!mgr->up_req_recv.initial_hdr.broadcast) { + mstb = drm_dp_get_mst_branch_device(mgr, + mgr->up_req_recv.initial_hdr.lct, + mgr->up_req_recv.initial_hdr.rad); + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } } seqno = mgr->up_req_recv.initial_hdr.seqno; drm_dp_sideband_parse_req(&mgr->up_req_recv, &msg); if (msg.req_type == DP_CONNECTION_STATUS_NOTIFY) { - drm_dp_send_up_ack_reply(mgr, mstb, msg.req_type, seqno, false); + drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false); + + if (!mstb) + mstb = drm_dp_get_mst_branch_device_by_guid(mgr, msg.u.conn_stat.guid); + + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } + drm_dp_update_port(mstb, &msg.u.conn_stat); + DRM_DEBUG_KMS("Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", msg.u.conn_stat.port_number, msg.u.conn_stat.legacy_device_plug_status, msg.u.conn_stat.displayport_device_plug_status, msg.u.conn_stat.message_capability_status, msg.u.conn_stat.input_port, msg.u.conn_stat.peer_device_type); (*mgr->cbs->hotplug)(mgr); } else if (msg.req_type == DP_RESOURCE_STATUS_NOTIFY) { - drm_dp_send_up_ack_reply(mgr, mstb, msg.req_type, seqno, false); + drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false); + if (!mstb) + mstb = drm_dp_get_mst_branch_device_by_guid(mgr, msg.u.resource_stat.guid); + + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } + DRM_DEBUG_KMS("Got RSN: pn: %d avail_pbn %d\n", msg.u.resource_stat.port_number, msg.u.resource_stat.available_pbn); } @@ -2346,6 +2490,7 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp DRM_DEBUG_KMS("payload: vcpi %d already allocated for pbn %d - requested pbn %d\n", port->vcpi.vcpi, port->vcpi.pbn, pbn); if (pbn == port->vcpi.pbn) { *slots = port->vcpi.num_slots; + drm_dp_put_port(port); return true; } } @@ -2505,32 +2650,31 @@ EXPORT_SYMBOL(drm_dp_check_act_status); */ int drm_dp_calc_pbn_mode(int clock, int bpp) { - fixed20_12 pix_bw; - fixed20_12 fbpp; - fixed20_12 result; - fixed20_12 margin, tmp; - u32 res; - - pix_bw.full = dfixed_const(clock); - fbpp.full = dfixed_const(bpp); - tmp.full = dfixed_const(8); - fbpp.full = dfixed_div(fbpp, tmp); - - result.full = dfixed_mul(pix_bw, fbpp); - margin.full = dfixed_const(54); - tmp.full = dfixed_const(64); - margin.full = dfixed_div(margin, tmp); - result.full = dfixed_div(result, margin); - - margin.full = dfixed_const(1006); - tmp.full = dfixed_const(1000); - margin.full = dfixed_div(margin, tmp); - result.full = dfixed_mul(result, margin); - - result.full = dfixed_div(result, tmp); - result.full = dfixed_ceil(result); - res = dfixed_trunc(result); - return res; + u64 kbps; + s64 peak_kbps; + u32 numerator; + u32 denominator; + + kbps = clock * bpp; + + /* + * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006 + * The unit of 54/64Mbytes/sec is an arbitrary unit chosen based on + * common multiplier to render an integer PBN for all link rate/lane + * counts combinations + * calculate + * peak_kbps *= (1006/1000) + * peak_kbps *= (64/54) + * peak_kbps *= 8 convert to bytes + */ + + numerator = 64 * 1006; + denominator = 54 * 8 * 1000 * 1000; + + kbps *= numerator; + peak_kbps = drm_fixp_from_fraction(kbps, denominator); + + return drm_fixp2int_ceil(peak_kbps); } EXPORT_SYMBOL(drm_dp_calc_pbn_mode); @@ -2538,11 +2682,23 @@ static int test_calc_pbn_mode(void) { int ret; ret = drm_dp_calc_pbn_mode(154000, 30); - if (ret != 689) + if (ret != 689) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 154000, 30, 689, ret); return -EINVAL; + } ret = drm_dp_calc_pbn_mode(234000, 30); - if (ret != 1047) + if (ret != 1047) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 234000, 30, 1047, ret); + return -EINVAL; + } + ret = drm_dp_calc_pbn_mode(297000, 24); + if (ret != 1063) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 297000, 24, 1063, ret); return -EINVAL; + } return 0; } @@ -2683,6 +2839,13 @@ static void drm_dp_tx_work(struct work_struct *work) mutex_unlock(&mgr->qlock); } +static void drm_dp_free_mst_port(struct kref *kref) +{ + struct drm_dp_mst_port *port = container_of(kref, struct drm_dp_mst_port, kref); + kref_put(&port->parent->kref, drm_dp_free_mst_branch_device); + kfree(port); +} + static void drm_dp_destroy_connector_work(struct work_struct *work) { struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work); @@ -2703,13 +2866,22 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) list_del(&port->next); mutex_unlock(&mgr->destroy_connector_lock); + kref_init(&port->kref); + INIT_LIST_HEAD(&port->next); + mgr->cbs->destroy_connector(mgr, port->connector); drm_dp_port_teardown_pdt(port, port->pdt); - if (!port->input && port->vcpi.vcpi > 0) - drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); - kfree(port); + if (!port->input && port->vcpi.vcpi > 0) { + if (mgr->mst_state) { + drm_dp_mst_reset_vcpi_slots(mgr, port); + drm_dp_update_payload_part1(mgr); + drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); + } + } + + kref_put(&port->kref, drm_dp_free_mst_port); send_hotplug = true; } if (send_hotplug) @@ -2736,7 +2908,6 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, mutex_init(&mgr->qlock); mutex_init(&mgr->payload_lock); mutex_init(&mgr->destroy_connector_lock); - INIT_LIST_HEAD(&mgr->tx_msg_upq); INIT_LIST_HEAD(&mgr->tx_msg_downq); INIT_LIST_HEAD(&mgr->destroy_connector_list); INIT_WORK(&mgr->work, drm_dp_mst_link_probe_work); diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 607f493ae801..8090989185b2 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -221,6 +221,64 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0; } + /* + * Within a drm_vblank_pre_modeset - drm_vblank_post_modeset + * interval? If so then vblank irqs keep running and it will likely + * happen that the hardware vblank counter is not trustworthy as it + * might reset at some point in that interval and vblank timestamps + * are not trustworthy either in that interval. Iow. this can result + * in a bogus diff >> 1 which must be avoided as it would cause + * random large forward jumps of the software vblank counter. + */ + if (diff > 1 && (vblank->inmodeset & 0x2)) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u" + " due to pre-modeset.\n", pipe, diff); + diff = 1; + } + + /* + * FIMXE: Need to replace this hack with proper seqlocks. + * + * Restrict the bump of the software vblank counter to a safe maximum + * value of +1 whenever there is the possibility that concurrent readers + * of vblank timestamps could be active at the moment, as the current + * implementation of the timestamp caching and updating is not safe + * against concurrent readers for calls to store_vblank() with a bump + * of anything but +1. A bump != 1 would very likely return corrupted + * timestamps to userspace, because the same slot in the cache could + * be concurrently written by store_vblank() and read by one of those + * readers without the read-retry logic detecting the collision. + * + * Concurrent readers can exist when we are called from the + * drm_vblank_off() or drm_vblank_on() functions and other non-vblank- + * irq callers. However, all those calls to us are happening with the + * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount + * can't increase while we are executing. Therefore a zero refcount at + * this point is safe for arbitrary counter bumps if we are called + * outside vblank irq, a non-zero count is not 100% safe. Unfortunately + * we must also accept a refcount of 1, as whenever we are called from + * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and + * we must let that one pass through in order to not lose vblank counts + * during vblank irq off - which would completely defeat the whole + * point of this routine. + * + * Whenever we are called from vblank irq, we have to assume concurrent + * readers exist or can show up any time during our execution, even if + * the refcount is currently zero, as vblank irqs are usually only + * enabled due to the presence of readers, and because when we are called + * from vblank irq we can't hold the vbl_lock to protect us from sudden + * bumps in vblank refcount. Therefore also restrict bumps to +1 when + * called from vblank irq. + */ + if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 || + (flags & DRM_CALLED_FROM_VBLIRQ))) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u " + "refcount %u, vblirq %u\n", pipe, diff, + atomic_read(&vblank->refcount), + (flags & DRM_CALLED_FROM_VBLIRQ) != 0); + diff = 1; + } + DRM_DEBUG_VBL("updating vblank count on crtc %u:" " current=%u, diff=%u, hw=%u hw_last=%u\n", pipe, vblank->count, diff, cur_vblank, vblank->last); @@ -1313,7 +1371,13 @@ void drm_vblank_off(struct drm_device *dev, unsigned int pipe) spin_lock_irqsave(&dev->event_lock, irqflags); spin_lock(&dev->vbl_lock); - vblank_disable_and_save(dev, pipe); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + + /* Avoid redundant vblank disables without previous drm_vblank_on(). */ + if (drm_core_check_feature(dev, DRIVER_ATOMIC) || !vblank->inmodeset) + vblank_disable_and_save(dev, pipe); + wake_up(&vblank->queue); /* @@ -1415,6 +1479,9 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) return; spin_lock_irqsave(&dev->vbl_lock, irqflags); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + /* Drop our private "prevent drm_vblank_get" refcount */ if (vblank->inmodeset) { atomic_dec(&vblank->refcount); @@ -1427,8 +1494,7 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) * re-enable interrupts if there are users left, or the * user wishes vblank interrupts to be enabled all the time. */ - if (atomic_read(&vblank->refcount) != 0 || - (!dev->vblank_disable_immediate && drm_vblank_offdelay == 0)) + if (atomic_read(&vblank->refcount) != 0 || drm_vblank_offdelay == 0) WARN_ON(drm_vblank_enable(dev, pipe)); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); } @@ -1523,6 +1589,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, unsigned int pipe) if (vblank->inmodeset) { spin_lock_irqsave(&dev->vbl_lock, irqflags); dev->vblank_disable_allowed = true; + drm_reset_vblank_timestamp(dev, pipe); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); if (vblank->inmodeset & 0x2) diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c index c707fa6fca85..e3bdc8b1c32c 100644 --- a/drivers/gpu/drm/gma500/gem.c +++ b/drivers/gpu/drm/gma500/gem.c @@ -130,7 +130,7 @@ int psb_gem_create(struct drm_file *file, struct drm_device *dev, u64 size, return ret; } /* We have the initial and handle reference but need only one now */ - drm_gem_object_unreference(&r->gem); + drm_gem_object_unreference_unlocked(&r->gem); *handlep = handle; return 0; } diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index b4741d121a74..61fcb3b22297 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -402,6 +402,8 @@ static int i915_load_modeset_init(struct drm_device *dev) if (ret) goto cleanup_gem_stolen; + intel_setup_gmbus(dev); + /* Important: The output setup functions called by modeset_init need * working irqs for e.g. gmbus and dp aux transfers. */ intel_modeset_init(dev); @@ -451,6 +453,7 @@ cleanup_gem: cleanup_irq: intel_guc_ucode_fini(dev); drm_irq_uninstall(dev); + intel_teardown_gmbus(dev); cleanup_gem_stolen: i915_gem_cleanup_stolen(dev); cleanup_vga_switcheroo: @@ -1028,7 +1031,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) /* Try to make sure MCHBAR is enabled before poking at it */ intel_setup_mchbar(dev); - intel_setup_gmbus(dev); intel_opregion_setup(dev); i915_gem_load(dev); @@ -1099,7 +1101,6 @@ out_gem_unload: if (dev->pdev->msi_enabled) pci_disable_msi(dev->pdev); - intel_teardown_gmbus(dev); intel_teardown_mchbar(dev); pm_qos_remove_request(&dev_priv->pm_qos); destroy_workqueue(dev_priv->gpu_error.hangcheck_wq); @@ -1198,7 +1199,6 @@ int i915_driver_unload(struct drm_device *dev) intel_csr_ucode_fini(dev); - intel_teardown_gmbus(dev); intel_teardown_mchbar(dev); destroy_workqueue(dev_priv->hotplug.dp_wq); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 760e0ce4aa26..a6ad938f44a6 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -531,7 +531,10 @@ void intel_detect_pch(struct drm_device *dev) dev_priv->pch_type = PCH_SPT; DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n"); WARN_ON(!IS_SKYLAKE(dev)); - } else if (id == INTEL_PCH_P2X_DEVICE_ID_TYPE) { + } else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) || + ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) && + pch->subsystem_vendor == 0x1af4 && + pch->subsystem_device == 0x1100)) { dev_priv->pch_type = intel_virt_detect_pch(dev); } else continue; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index f4af19a0d569..d3ce4da6a6ad 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2614,6 +2614,7 @@ struct drm_i915_cmd_table { #define INTEL_PCH_SPT_DEVICE_ID_TYPE 0xA100 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE 0x9D00 #define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 +#define INTEL_PCH_QEMU_DEVICE_ID_TYPE 0x2900 /* qemu q35 has 2918 */ #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type) #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT) diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 02ceb7a4b481..0433d25f9d23 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -340,6 +340,10 @@ void i915_gem_context_reset(struct drm_device *dev) i915_gem_context_unreference(lctx); ring->last_context = NULL; } + + /* Force the GPU state to be reinitialised on enabling */ + if (ring->default_context) + ring->default_context->legacy_hw_ctx.initialized = false; } } @@ -708,7 +712,7 @@ static int do_switch(struct drm_i915_gem_request *req) if (ret) goto unpin_out; - if (!to->legacy_hw_ctx.initialized) { + if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to)) { hw_flags |= MI_RESTORE_INHIBIT; /* NB: If we inhibit the restore, the context is not allowed to * die because future work may end up depending on valid address diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 0d228f909dcb..0f42a2782afc 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2354,9 +2354,13 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) spt_irq_handler(dev, pch_iir); else cpt_irq_handler(dev, pch_iir); - } else - DRM_ERROR("The master control interrupt lied (SDE)!\n"); - + } else { + /* + * Like on previous PCH there seems to be something + * fishy going on with forwarding PCH interrupts. + */ + DRM_DEBUG_DRIVER("The master control interrupt lied (SDE)!\n"); + } } I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index bc7b8faba84d..7e461dca564c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2838,7 +2838,14 @@ enum skl_disp_power_wells { #define GEN6_RP_STATE_CAP (MCHBAR_MIRROR_BASE_SNB + 0x5998) #define BXT_RP_STATE_CAP 0x138170 -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7) +/* + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS + * 8300) freezing up around GPU hangs. Looks as if even + * scheduling/timer interrupts start misbehaving if the RPS + * EI/thresholds are "bad", leading to a very sluggish or even + * frozen machine. + */ +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25) #define INTERVAL_1_33_US(us) (((us) * 3) >> 2) #define INTERVAL_0_833_US(us) (((us) * 6) / 5) #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \ diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 9e530a739354..fc28c512ece3 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -180,7 +180,8 @@ struct stepping_info { static const struct stepping_info skl_stepping_info[] = { {'A', '0'}, {'B', '0'}, {'C', '0'}, {'D', '0'}, {'E', '0'}, {'F', '0'}, - {'G', '0'}, {'H', '0'}, {'I', '0'} + {'G', '0'}, {'H', '0'}, {'I', '0'}, + {'J', '0'}, {'K', '0'} }; static struct stepping_info bxt_stepping_info[] = { diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index a6752a61d99f..3c6b07683bd9 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -464,9 +464,17 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, } else if (IS_BROADWELL(dev)) { ddi_translations_fdi = bdw_ddi_translations_fdi; ddi_translations_dp = bdw_ddi_translations_dp; - ddi_translations_edp = bdw_ddi_translations_edp; + + if (dev_priv->edp_low_vswing) { + ddi_translations_edp = bdw_ddi_translations_edp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + } else { + ddi_translations_edp = bdw_ddi_translations_dp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); + } + ddi_translations_hdmi = bdw_ddi_translations_hdmi; - n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); hdmi_default_entry = 7; @@ -1582,7 +1590,8 @@ skl_ddi_pll_select(struct intel_crtc *intel_crtc, DPLL_CFGCR2_KDIV(wrpll_params.kdiv) | DPLL_CFGCR2_PDIV(wrpll_params.pdiv) | wrpll_params.central_freq; - } else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) { + } else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT || + intel_encoder->type == INTEL_OUTPUT_DP_MST) { switch (crtc_state->port_clock / 2) { case 81000: ctrl1 |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_810, 0); @@ -3187,12 +3196,6 @@ void intel_ddi_get_config(struct intel_encoder *encoder, intel_ddi_clock_get(encoder, pipe_config); } -static void intel_ddi_destroy(struct drm_encoder *encoder) -{ - /* HDMI has nothing special to destroy, so we can go with this. */ - intel_dp_encoder_destroy(encoder); -} - static bool intel_ddi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -3211,7 +3214,8 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder, } static const struct drm_encoder_funcs intel_ddi_funcs = { - .destroy = intel_ddi_destroy, + .reset = intel_dp_encoder_reset, + .destroy = intel_dp_encoder_destroy, }; static struct intel_connector * @@ -3283,6 +3287,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->post_disable = intel_ddi_post_disable; intel_encoder->get_hw_state = intel_ddi_get_hw_state; intel_encoder->get_config = intel_ddi_get_config; + intel_encoder->suspend = intel_dp_encoder_suspend; intel_dig_port->port = port; intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 32cf97346978..afa81691163d 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4447,7 +4447,7 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state) intel_crtc->base.base.id, intel_crtc->pipe, SKL_CRTC_INDEX); return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX, - &state->scaler_state.scaler_id, DRM_ROTATE_0, + &state->scaler_state.scaler_id, BIT(DRM_ROTATE_0), state->pipe_src_w, state->pipe_src_h, adjusted_mode->crtc_hdisplay, adjusted_mode->crtc_vdisplay); } @@ -11930,11 +11930,21 @@ connected_sink_compute_bpp(struct intel_connector *connector, pipe_config->pipe_bpp = connector->base.display_info.bpc*3; } - /* Clamp bpp to 8 on screens without EDID 1.4 */ - if (connector->base.display_info.bpc == 0 && bpp > 24) { - DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of 24\n", - bpp); - pipe_config->pipe_bpp = 24; + /* Clamp bpp to default limit on screens without EDID 1.4 */ + if (connector->base.display_info.bpc == 0) { + int type = connector->base.connector_type; + int clamp_bpp = 24; + + /* Fall back to 18 bpp when DP sink capability is unknown. */ + if (type == DRM_MODE_CONNECTOR_DisplayPort || + type == DRM_MODE_CONNECTOR_eDP) + clamp_bpp = 18; + + if (bpp > clamp_bpp) { + DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of %d\n", + bpp, clamp_bpp); + pipe_config->pipe_bpp = clamp_bpp; + } } } @@ -13537,11 +13547,12 @@ intel_check_primary_plane(struct drm_plane *plane, int max_scale = DRM_PLANE_HELPER_NO_SCALING; bool can_position = false; - /* use scaler when colorkey is not required */ - if (INTEL_INFO(plane->dev)->gen >= 9 && - state->ckey.flags == I915_SET_COLORKEY_NONE) { - min_scale = 1; - max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state); + if (INTEL_INFO(plane->dev)->gen >= 9) { + /* use scaler when colorkey is not required */ + if (state->ckey.flags == I915_SET_COLORKEY_NONE) { + min_scale = 1; + max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state); + } can_position = true; } @@ -15565,6 +15576,8 @@ void intel_modeset_cleanup(struct drm_device *dev) mutex_lock(&dev->struct_mutex); intel_cleanup_gt_powersave(dev); mutex_unlock(&dev->struct_mutex); + + intel_teardown_gmbus(dev); } /* diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 78b8ec84d576..e55a82a99e7f 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -5035,7 +5035,7 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder) kfree(intel_dig_port); } -static void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base); @@ -5077,7 +5077,7 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) edp_panel_vdd_schedule_off(intel_dp); } -static void intel_dp_encoder_reset(struct drm_encoder *encoder) +void intel_dp_encoder_reset(struct drm_encoder *encoder) { struct intel_dp *intel_dp; diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 0639275fc471..06bd9257acdc 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -477,6 +477,8 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct intel_connector *intel_connector = to_intel_connector(connector); struct drm_device *dev = connector->dev; + intel_connector->unregister(intel_connector); + /* need to nuke the connector */ drm_modeset_lock_all(dev); if (connector->state->crtc) { @@ -490,11 +492,7 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, WARN(ret, "Disabling mst crtc failed with %i\n", ret); } - drm_modeset_unlock_all(dev); - intel_connector->unregister(intel_connector); - - drm_modeset_lock_all(dev); intel_connector_remove_from_fbdev(intel_connector); drm_connector_cleanup(connector); drm_modeset_unlock_all(dev); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0d00f07b7163..f34a219ec5c4 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1204,6 +1204,8 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp, void intel_dp_start_link_train(struct intel_dp *intel_dp); void intel_dp_stop_link_train(struct intel_dp *intel_dp); void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); +void intel_dp_encoder_reset(struct drm_encoder *encoder); +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder); void intel_dp_encoder_destroy(struct drm_encoder *encoder); int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc); bool intel_dp_compute_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c index a5e99ac305da..a8912aecc31f 100644 --- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c @@ -207,7 +207,12 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) gpio = *data++; /* pull up/down */ - action = *data++; + action = *data++ & 1; + + if (gpio >= ARRAY_SIZE(gtable)) { + DRM_DEBUG_KMS("unknown gpio %u\n", gpio); + goto out; + } function = gtable[gpio].function_reg; pad = gtable[gpio].pad_reg; @@ -226,6 +231,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) vlv_gpio_nc_write(dev_priv, pad, val); mutex_unlock(&dev_priv->sb_lock); +out: return data; } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index e6c035b0fc1c..4b8ed9f2dabc 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1388,8 +1388,16 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) hdmi_to_dig_port(intel_hdmi)); } - if (!live_status) - DRM_DEBUG_KMS("Live status not up!"); + if (!live_status) { + DRM_DEBUG_KMS("HDMI live status down\n"); + /* + * Live status register is not reliable on all intel platforms. + * So consider live_status only for certain platforms, for + * others, read EDID to determine presence of sink. + */ + if (INTEL_INFO(dev_priv)->gen < 7 || IS_IVYBRIDGE(dev_priv)) + live_status = true; + } intel_hdmi_unset_edid(connector); diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c index b17785719598..d7a6437d9da2 100644 --- a/drivers/gpu/drm/i915/intel_hotplug.c +++ b/drivers/gpu/drm/i915/intel_hotplug.c @@ -468,9 +468,14 @@ void intel_hpd_init(struct drm_i915_private *dev_priv) list_for_each_entry(connector, &mode_config->connector_list, head) { struct intel_connector *intel_connector = to_intel_connector(connector); connector->polled = intel_connector->polled; - if (connector->encoder && !connector->polled && I915_HAS_HOTPLUG(dev) && intel_connector->encoder->hpd_pin > HPD_NONE) - connector->polled = DRM_CONNECTOR_POLL_HPD; + + /* MST has a dynamic intel_connector->encoder and it's reprobing + * is all handled by the MST helpers. */ if (intel_connector->mst_port) + continue; + + if (!connector->polled && I915_HAS_HOTPLUG(dev) && + intel_connector->encoder->hpd_pin > HPD_NONE) connector->polled = DRM_CONNECTOR_POLL_HPD; } diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 8324654037b6..f3bee54c414f 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -675,7 +675,7 @@ int intel_setup_gmbus(struct drm_device *dev) return 0; err: - while (--pin) { + while (pin--) { if (!intel_gmbus_is_valid_pin(dev_priv, pin)) continue; diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 88e12bdf79e2..7058f75c7b42 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -776,11 +776,11 @@ static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes) if (unlikely(total_bytes > remain_usable)) { /* * The base request will fit but the reserved space - * falls off the end. So only need to to wait for the - * reserved size after flushing out the remainder. + * falls off the end. So don't need an immediate wrap + * and only need to effectively wait for the reserved + * size space from the start of ringbuffer. */ wait_bytes = remain_actual + ringbuf->reserved_size; - need_wrap = true; } else if (total_bytes > ringbuf->space) { /* No wrapping required, just waiting. */ wait_bytes = total_bytes; @@ -1706,6 +1706,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 9461a238f5d5..9d48443bca2e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -347,6 +347,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { @@ -419,6 +420,7 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { @@ -1920,6 +1922,17 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req, return 0; } +static void cleanup_phys_status_page(struct intel_engine_cs *ring) +{ + struct drm_i915_private *dev_priv = to_i915(ring->dev); + + if (!dev_priv->status_page_dmah) + return; + + drm_pci_free(ring->dev, dev_priv->status_page_dmah); + ring->status_page.page_addr = NULL; +} + static void cleanup_status_page(struct intel_engine_cs *ring) { struct drm_i915_gem_object *obj; @@ -1936,9 +1949,9 @@ static void cleanup_status_page(struct intel_engine_cs *ring) static int init_status_page(struct intel_engine_cs *ring) { - struct drm_i915_gem_object *obj; + struct drm_i915_gem_object *obj = ring->status_page.obj; - if ((obj = ring->status_page.obj) == NULL) { + if (obj == NULL) { unsigned flags; int ret; @@ -2132,7 +2145,7 @@ static int intel_init_ring_buffer(struct drm_device *dev, if (ret) goto error; } else { - BUG_ON(ring->id != RCS); + WARN_ON(ring->id != RCS); ret = init_phys_status_page(ring); if (ret) goto error; @@ -2177,7 +2190,12 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) if (ring->cleanup) ring->cleanup(ring); - cleanup_status_page(ring); + if (I915_NEED_GFX_HWS(ring->dev)) { + cleanup_status_page(ring); + } else { + WARN_ON(ring->id != RCS); + cleanup_phys_status_page(ring); + } i915_cmd_parser_fini_ring(ring); i915_gem_batch_pool_fini(&ring->batch_pool); @@ -2339,11 +2357,11 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes) if (unlikely(total_bytes > remain_usable)) { /* * The base request will fit but the reserved space - * falls off the end. So only need to to wait for the - * reserved size after flushing out the remainder. + * falls off the end. So don't need an immediate wrap + * and only need to effectively wait for the reserved + * size space from the start of ringbuffer. */ wait_bytes = remain_actual + ringbuf->reserved_size; - need_wrap = true; } else if (total_bytes > ringbuf->space) { /* No wrapping required, just waiting. */ wait_bytes = total_bytes; diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 43cba129a0c0..cc91ae832ffb 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1132,7 +1132,11 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev) } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { dev_priv->uncore.funcs.force_wake_get = fw_domains_get_with_thread_status; - dev_priv->uncore.funcs.force_wake_put = fw_domains_put; + if (IS_HASWELL(dev)) + dev_priv->uncore.funcs.force_wake_put = + fw_domains_put_with_fifo; + else + dev_priv->uncore.funcs.force_wake_put = fw_domains_put; fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE_MT, FORCEWAKE_ACK_HSW); } else if (IS_IVYBRIDGE(dev)) { diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 2e7cbe933533..2a5ed7460354 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -969,10 +969,13 @@ nouveau_connector_hotplug(struct nvif_notify *notify) NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name); + mutex_lock(&drm->dev->mode_config.mutex); if (plugged) drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); else drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); + mutex_unlock(&drm->dev->mode_config.mutex); + drm_helper_hpd_irq_event(connector->dev); } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 64c8d932d5f1..58a3f7cf2fb3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -634,10 +634,6 @@ nouveau_display_resume(struct drm_device *dev, bool runtime) nv_crtc->lut.depth = 0; } - /* Make sure that drm and hw vblank irqs get resumed if needed. */ - for (head = 0; head < dev->mode_config.num_crtc; head++) - drm_vblank_on(dev, head); - /* This should ensure we don't hit a locking problem when someone * wakes us up via a connector. We should never go into suspend * while the display is on anyways. @@ -647,6 +643,10 @@ nouveau_display_resume(struct drm_device *dev, bool runtime) drm_helper_resume_force_mode(dev); + /* Make sure that drm and hw vblank irqs get resumed if needed. */ + for (head = 0; head < dev->mode_config.num_crtc; head++) + drm_vblank_on(dev, head); + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c index 60e32c4e4e49..35ecc0d0458f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_platform.c +++ b/drivers/gpu/drm/nouveau/nouveau_platform.c @@ -24,7 +24,7 @@ static int nouveau_platform_probe(struct platform_device *pdev) { const struct nvkm_device_tegra_func *func; - struct nvkm_device *device; + struct nvkm_device *device = NULL; struct drm_device *drm; int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/core/ramht.c b/drivers/gpu/drm/nouveau/nvkm/core/ramht.c index 3216e157a8a0..89da47234016 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/ramht.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/ramht.c @@ -131,7 +131,7 @@ nvkm_ramht_del(struct nvkm_ramht **pramht) struct nvkm_ramht *ramht = *pramht; if (ramht) { nvkm_gpuobj_del(&ramht->gpuobj); - kfree(*pramht); + vfree(*pramht); *pramht = NULL; } } @@ -143,8 +143,8 @@ nvkm_ramht_new(struct nvkm_device *device, u32 size, u32 align, struct nvkm_ramht *ramht; int ret, i; - if (!(ramht = *pramht = kzalloc(sizeof(*ramht) + (size >> 3) * - sizeof(*ramht->data), GFP_KERNEL))) + if (!(ramht = *pramht = vzalloc(sizeof(*ramht) + + (size >> 3) * sizeof(*ramht->data)))) return -ENOMEM; ramht->device = device; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c index 7f8a42721eb2..e7e581d6a8ff 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c @@ -252,32 +252,40 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL))) return -ENOMEM; - *pdevice = &tdev->device; + tdev->func = func; tdev->pdev = pdev; tdev->irq = -1; tdev->vdd = devm_regulator_get(&pdev->dev, "vdd"); - if (IS_ERR(tdev->vdd)) - return PTR_ERR(tdev->vdd); + if (IS_ERR(tdev->vdd)) { + ret = PTR_ERR(tdev->vdd); + goto free; + } tdev->rst = devm_reset_control_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->rst)) - return PTR_ERR(tdev->rst); + if (IS_ERR(tdev->rst)) { + ret = PTR_ERR(tdev->rst); + goto free; + } tdev->clk = devm_clk_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->clk)) - return PTR_ERR(tdev->clk); + if (IS_ERR(tdev->clk)) { + ret = PTR_ERR(tdev->clk); + goto free; + } tdev->clk_pwr = devm_clk_get(&pdev->dev, "pwr"); - if (IS_ERR(tdev->clk_pwr)) - return PTR_ERR(tdev->clk_pwr); + if (IS_ERR(tdev->clk_pwr)) { + ret = PTR_ERR(tdev->clk_pwr); + goto free; + } nvkm_device_tegra_probe_iommu(tdev); ret = nvkm_device_tegra_power_up(tdev); if (ret) - return ret; + goto remove; tdev->gpu_speedo = tegra_sku_info.gpu_speedo_value; ret = nvkm_device_ctor(&nvkm_device_tegra_func, NULL, &pdev->dev, @@ -285,9 +293,19 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, cfg, dbg, detect, mmio, subdev_mask, &tdev->device); if (ret) - return ret; + goto powerdown; + + *pdevice = &tdev->device; return 0; + +powerdown: + nvkm_device_tegra_power_down(tdev); +remove: + nvkm_device_tegra_remove_iommu(tdev); +free: + kfree(tdev); + return ret; } #else int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c index 74e2f7c6c07e..9688970eca47 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c @@ -328,6 +328,7 @@ nvkm_dp_train(struct work_struct *w) .outp = outp, }, *dp = &_dp; u32 datarate = 0; + u8 pwr; int ret; if (!outp->base.info.location && disp->func->sor.magic) @@ -355,6 +356,15 @@ nvkm_dp_train(struct work_struct *w) /* disable link interrupt handling during link training */ nvkm_notify_put(&outp->irq); + /* ensure sink is not in a low-power state */ + if (!nvkm_rdaux(outp->aux, DPCD_SC00, &pwr, 1)) { + if ((pwr & DPCD_SC00_SET_POWER) != DPCD_SC00_SET_POWER_D0) { + pwr &= ~DPCD_SC00_SET_POWER; + pwr |= DPCD_SC00_SET_POWER_D0; + nvkm_wraux(outp->aux, DPCD_SC00, &pwr, 1); + } + } + /* enable down-spreading and execute pre-train script from vbios */ dp_link_train_init(dp, outp->dpcd[3] & 0x01); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h index 9596290329c7..6e10c5e0ef11 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h @@ -71,5 +71,11 @@ #define DPCD_LS0C_LANE1_POST_CURSOR2 0x0c #define DPCD_LS0C_LANE0_POST_CURSOR2 0x03 +/* DPCD Sink Control */ +#define DPCD_SC00 0x00600 +#define DPCD_SC00_SET_POWER 0x03 +#define DPCD_SC00_SET_POWER_D0 0x01 +#define DPCD_SC00_SET_POWER_D3 0x03 + void nvkm_dp_train(struct work_struct *); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c index 9f5dfc85147a..36655a74c538 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c @@ -1717,6 +1717,8 @@ gf100_gr_init(struct gf100_gr *gr) gf100_gr_mmio(gr, gr->func->mmio); + nvkm_mask(device, TPC_UNIT(0, 0, 0x05c), 0x00000001, 0x00000001); + memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr)); for (i = 0, gpc = -1; i < gr->tpc_total; i++) { do { diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 183aea1abebc..5edebf495c07 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -375,10 +375,15 @@ static int qxl_crtc_cursor_set2(struct drm_crtc *crtc, qxl_bo_kunmap(user_bo); + qcrtc->cur_x += qcrtc->hot_spot_x - hot_x; + qcrtc->cur_y += qcrtc->hot_spot_y - hot_y; + qcrtc->hot_spot_x = hot_x; + qcrtc->hot_spot_y = hot_y; + cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release); cmd->type = QXL_CURSOR_SET; - cmd->u.set.position.x = qcrtc->cur_x; - cmd->u.set.position.y = qcrtc->cur_y; + cmd->u.set.position.x = qcrtc->cur_x + qcrtc->hot_spot_x; + cmd->u.set.position.y = qcrtc->cur_y + qcrtc->hot_spot_y; cmd->u.set.shape = qxl_bo_physical_address(qdev, cursor_bo, 0); @@ -441,8 +446,8 @@ static int qxl_crtc_cursor_move(struct drm_crtc *crtc, cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release); cmd->type = QXL_CURSOR_MOVE; - cmd->u.position.x = qcrtc->cur_x; - cmd->u.position.y = qcrtc->cur_y; + cmd->u.position.x = qcrtc->cur_x + qcrtc->hot_spot_x; + cmd->u.position.y = qcrtc->cur_y + qcrtc->hot_spot_y; qxl_release_unmap(qdev, release, &cmd->release_info); qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 01a86948eb8c..3ab90179e9ab 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -135,6 +135,8 @@ struct qxl_crtc { int index; int cur_x; int cur_y; + int hot_spot_x; + int hot_spot_y; }; struct qxl_output { diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index 2ae8577497ca..7c2e78201ead 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -168,7 +168,8 @@ static int qxl_process_single_command(struct qxl_device *qdev, cmd->command_size)) return -EFAULT; - reloc_info = kmalloc(sizeof(struct qxl_reloc_info) * cmd->relocs_num, GFP_KERNEL); + reloc_info = kmalloc_array(cmd->relocs_num, + sizeof(struct qxl_reloc_info), GFP_KERNEL); if (!reloc_info) return -ENOMEM; diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index bb292143997e..0b04b9282f56 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -310,6 +310,10 @@ static bool radeon_atom_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) { radeon_panel_mode_fixup(encoder, adjusted_mode); @@ -892,8 +896,6 @@ atombios_dig_encoder_setup2(struct drm_encoder *encoder, int action, int panel_m else args.v1.ucLaneNum = 4; - if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode) && (dp_clock == 270000)) - args.v1.ucConfig |= ATOM_ENCODER_CONFIG_DPLINKRATE_2_70GHZ; switch (radeon_encoder->encoder_id) { case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: args.v1.ucConfig = ATOM_ENCODER_CONFIG_V2_TRANSMITTER1; @@ -910,6 +912,10 @@ atombios_dig_encoder_setup2(struct drm_encoder *encoder, int action, int panel_m args.v1.ucConfig |= ATOM_ENCODER_CONFIG_LINKB; else args.v1.ucConfig |= ATOM_ENCODER_CONFIG_LINKA; + + if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode) && (dp_clock == 270000)) + args.v1.ucConfig |= ATOM_ENCODER_CONFIG_DPLINKRATE_2_70GHZ; + break; case 2: case 3: diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 752072771388..367a916f364e 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -301,6 +301,14 @@ void dce6_dp_audio_set_dto(struct radeon_device *rdev, * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ if (ASIC_IS_DCE8(rdev)) { + unsigned int div = (RREG32(DENTIST_DISPCLK_CNTL) & + DENTIST_DPREFCLK_WDIVIDER_MASK) >> + DENTIST_DPREFCLK_WDIVIDER_SHIFT; + div = radeon_audio_decode_dfs_div(div); + + if (div) + clock = clock * 100 / div; + WREG32(DCE8_DCCG_AUDIO_DTO1_PHASE, 24000); WREG32(DCE8_DCCG_AUDIO_DTO1_MODULE, clock); } else { diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 2ad462896896..32491355a1d4 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2608,10 +2608,152 @@ static void evergreen_agp_enable(struct radeon_device *rdev) WREG32(VM_CONTEXT1_CNTL, 0); } +static const unsigned ni_dig_offsets[] = +{ + NI_DIG0_REGISTER_OFFSET, + NI_DIG1_REGISTER_OFFSET, + NI_DIG2_REGISTER_OFFSET, + NI_DIG3_REGISTER_OFFSET, + NI_DIG4_REGISTER_OFFSET, + NI_DIG5_REGISTER_OFFSET +}; + +static const unsigned ni_tx_offsets[] = +{ + NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1 +}; + +static const unsigned evergreen_dp_offsets[] = +{ + EVERGREEN_DP0_REGISTER_OFFSET, + EVERGREEN_DP1_REGISTER_OFFSET, + EVERGREEN_DP2_REGISTER_OFFSET, + EVERGREEN_DP3_REGISTER_OFFSET, + EVERGREEN_DP4_REGISTER_OFFSET, + EVERGREEN_DP5_REGISTER_OFFSET +}; + + +/* + * Assumption is that EVERGREEN_CRTC_MASTER_EN enable for requested crtc + * We go from crtc to connector and it is not relible since it + * should be an opposite direction .If crtc is enable then + * find the dig_fe which selects this crtc and insure that it enable. + * if such dig_fe is found then find dig_be which selects found dig_be and + * insure that it enable and in DP_SST mode. + * if UNIPHY_PLL_CONTROL1.enable then we should disconnect timing + * from dp symbols clocks . + */ +static bool evergreen_is_dp_sst_stream_enabled(struct radeon_device *rdev, + unsigned crtc_id, unsigned *ret_dig_fe) +{ + unsigned i; + unsigned dig_fe; + unsigned dig_be; + unsigned dig_en_be; + unsigned uniphy_pll; + unsigned digs_fe_selected; + unsigned dig_be_mode; + unsigned dig_fe_mask; + bool is_enabled = false; + bool found_crtc = false; + + /* loop through all running dig_fe to find selected crtc */ + for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) { + dig_fe = RREG32(NI_DIG_FE_CNTL + ni_dig_offsets[i]); + if (dig_fe & NI_DIG_FE_CNTL_SYMCLK_FE_ON && + crtc_id == NI_DIG_FE_CNTL_SOURCE_SELECT(dig_fe)) { + /* found running pipe */ + found_crtc = true; + dig_fe_mask = 1 << i; + dig_fe = i; + break; + } + } + + if (found_crtc) { + /* loop through all running dig_be to find selected dig_fe */ + for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) { + dig_be = RREG32(NI_DIG_BE_CNTL + ni_dig_offsets[i]); + /* if dig_fe_selected by dig_be? */ + digs_fe_selected = NI_DIG_BE_CNTL_FE_SOURCE_SELECT(dig_be); + dig_be_mode = NI_DIG_FE_CNTL_MODE(dig_be); + if (dig_fe_mask & digs_fe_selected && + /* if dig_be in sst mode? */ + dig_be_mode == NI_DIG_BE_DPSST) { + dig_en_be = RREG32(NI_DIG_BE_EN_CNTL + + ni_dig_offsets[i]); + uniphy_pll = RREG32(NI_DCIO_UNIPHY0_PLL_CONTROL1 + + ni_tx_offsets[i]); + /* dig_be enable and tx is running */ + if (dig_en_be & NI_DIG_BE_EN_CNTL_ENABLE && + dig_en_be & NI_DIG_BE_EN_CNTL_SYMBCLK_ON && + uniphy_pll & NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE) { + is_enabled = true; + *ret_dig_fe = dig_fe; + break; + } + } + } + } + + return is_enabled; +} + +/* + * Blank dig when in dp sst mode + * Dig ignores crtc timing + */ +static void evergreen_blank_dp_output(struct radeon_device *rdev, + unsigned dig_fe) +{ + unsigned stream_ctrl; + unsigned fifo_ctrl; + unsigned counter = 0; + + if (dig_fe >= ARRAY_SIZE(evergreen_dp_offsets)) { + DRM_ERROR("invalid dig_fe %d\n", dig_fe); + return; + } + + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + if (!(stream_ctrl & EVERGREEN_DP_VID_STREAM_CNTL_ENABLE)) { + DRM_ERROR("dig %d , should be enable\n", dig_fe); + return; + } + + stream_ctrl &=~EVERGREEN_DP_VID_STREAM_CNTL_ENABLE; + WREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe], stream_ctrl); + + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + while (counter < 32 && stream_ctrl & EVERGREEN_DP_VID_STREAM_STATUS) { + msleep(1); + counter++; + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + } + if (counter >= 32 ) + DRM_ERROR("counter exceeds %d\n", counter); + + fifo_ctrl = RREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe]); + fifo_ctrl |= EVERGREEN_DP_STEER_FIFO_RESET; + WREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe], fifo_ctrl); + +} + void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save) { u32 crtc_enabled, tmp, frame_count, blackout; int i, j; + unsigned dig_fe; if (!ASIC_IS_NODCE(rdev)) { save->vga_render_control = RREG32(VGA_RENDER_CONTROL); @@ -2651,7 +2793,17 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav break; udelay(1); } - + /*we should disable dig if it drives dp sst*/ + /*but we are in radeon_device_init and the topology is unknown*/ + /*and it is available after radeon_modeset_init*/ + /*the following method radeon_atom_encoder_dpms_dig*/ + /*does the job if we initialize it properly*/ + /*for now we do it this manually*/ + /**/ + if (ASIC_IS_DCE5(rdev) && + evergreen_is_dp_sst_stream_enabled(rdev, i ,&dig_fe)) + evergreen_blank_dp_output(rdev, dig_fe); + /*we could remove 6 lines below*/ /* XXX this is a hack to avoid strange behavior with EFI on certain systems */ WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index 9953356fe263..3cf04a2f44bb 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -289,6 +289,16 @@ void dce4_dp_audio_set_dto(struct radeon_device *rdev, * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ + if (ASIC_IS_DCE41(rdev)) { + unsigned int div = (RREG32(DCE41_DENTIST_DISPCLK_CNTL) & + DENTIST_DPREFCLK_WDIVIDER_MASK) >> + DENTIST_DPREFCLK_WDIVIDER_SHIFT; + div = radeon_audio_decode_dfs_div(div); + + if (div) + clock = 100 * clock / div; + } + WREG32(DCCG_AUDIO_DTO1_PHASE, 24000); WREG32(DCCG_AUDIO_DTO1_MODULE, clock); } diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h index aa939dfed3a3..b436badf9efa 100644 --- a/drivers/gpu/drm/radeon/evergreen_reg.h +++ b/drivers/gpu/drm/radeon/evergreen_reg.h @@ -250,8 +250,43 @@ /* HDMI blocks at 0x7030, 0x7c30, 0x10830, 0x11430, 0x12030, 0x12c30 */ #define EVERGREEN_HDMI_BASE 0x7030 +/*DIG block*/ +#define NI_DIG0_REGISTER_OFFSET (0x7000 - 0x7000) +#define NI_DIG1_REGISTER_OFFSET (0x7C00 - 0x7000) +#define NI_DIG2_REGISTER_OFFSET (0x10800 - 0x7000) +#define NI_DIG3_REGISTER_OFFSET (0x11400 - 0x7000) +#define NI_DIG4_REGISTER_OFFSET (0x12000 - 0x7000) +#define NI_DIG5_REGISTER_OFFSET (0x12C00 - 0x7000) + + +#define NI_DIG_FE_CNTL 0x7000 +# define NI_DIG_FE_CNTL_SOURCE_SELECT(x) ((x) & 0x3) +# define NI_DIG_FE_CNTL_SYMCLK_FE_ON (1<<24) + + +#define NI_DIG_BE_CNTL 0x7140 +# define NI_DIG_BE_CNTL_FE_SOURCE_SELECT(x) (((x) >> 8 ) & 0x3F) +# define NI_DIG_FE_CNTL_MODE(x) (((x) >> 16) & 0x7 ) + +#define NI_DIG_BE_EN_CNTL 0x7144 +# define NI_DIG_BE_EN_CNTL_ENABLE (1 << 0) +# define NI_DIG_BE_EN_CNTL_SYMBCLK_ON (1 << 8) +# define NI_DIG_BE_DPSST 0 /* Display Port block */ +#define EVERGREEN_DP0_REGISTER_OFFSET (0x730C - 0x730C) +#define EVERGREEN_DP1_REGISTER_OFFSET (0x7F0C - 0x730C) +#define EVERGREEN_DP2_REGISTER_OFFSET (0x10B0C - 0x730C) +#define EVERGREEN_DP3_REGISTER_OFFSET (0x1170C - 0x730C) +#define EVERGREEN_DP4_REGISTER_OFFSET (0x1230C - 0x730C) +#define EVERGREEN_DP5_REGISTER_OFFSET (0x12F0C - 0x730C) + + +#define EVERGREEN_DP_VID_STREAM_CNTL 0x730C +# define EVERGREEN_DP_VID_STREAM_CNTL_ENABLE (1 << 0) +# define EVERGREEN_DP_VID_STREAM_STATUS (1 <<16) +#define EVERGREEN_DP_STEER_FIFO 0x7310 +# define EVERGREEN_DP_STEER_FIFO_RESET (1 << 0) #define EVERGREEN_DP_SEC_CNTL 0x7280 # define EVERGREEN_DP_SEC_STREAM_ENABLE (1 << 0) # define EVERGREEN_DP_SEC_ASP_ENABLE (1 << 4) @@ -266,4 +301,15 @@ # define EVERGREEN_DP_SEC_N_BASE_MULTIPLE(x) (((x) & 0xf) << 24) # define EVERGREEN_DP_SEC_SS_EN (1 << 28) +/*DCIO_UNIPHY block*/ +#define NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1 (0x6600 -0x6600) +#define NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1 (0x6640 -0x6600) +#define NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1 (0x6680 - 0x6600) +#define NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1 (0x66C0 - 0x6600) +#define NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1 (0x6700 - 0x6600) +#define NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1 (0x6740 - 0x6600) + +#define NI_DCIO_UNIPHY0_PLL_CONTROL1 0x6618 +# define NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE (1 << 0) + #endif diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index 4aa5f755572b..13b6029d65cc 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -511,6 +511,11 @@ #define DCCG_AUDIO_DTO1_CNTL 0x05cc # define DCCG_AUDIO_DTO1_USE_512FBR_DTO (1 << 3) +#define DCE41_DENTIST_DISPCLK_CNTL 0x049c +# define DENTIST_DPREFCLK_WDIVIDER(x) (((x) & 0x7f) << 24) +# define DENTIST_DPREFCLK_WDIVIDER_MASK (0x7f << 24) +# define DENTIST_DPREFCLK_WDIVIDER_SHIFT 24 + /* DCE 4.0 AFMT */ #define HDMI_CONTROL 0x7030 # define HDMI_KEEPOUT_MODE (1 << 0) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 87db64983ea8..5580568088bb 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -268,6 +268,7 @@ struct radeon_clock { uint32_t current_dispclk; uint32_t dp_extclk; uint32_t max_pixel_clock; + uint32_t vco_freq; }; /* diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 8f285244c839..de9a2ffcf5f7 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -437,7 +437,9 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev, } /* Fujitsu D3003-S2 board lists DVI-I as DVI-D and VGA */ - if (((dev->pdev->device == 0x9802) || (dev->pdev->device == 0x9806)) && + if (((dev->pdev->device == 0x9802) || + (dev->pdev->device == 0x9805) || + (dev->pdev->device == 0x9806)) && (dev->pdev->subsystem_vendor == 0x1734) && (dev->pdev->subsystem_device == 0x11bd)) { if (*connector_type == DRM_MODE_CONNECTOR_VGA) { @@ -448,14 +450,6 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev, } } - /* Fujitsu D3003-S2 board lists DVI-I as DVI-I and VGA */ - if ((dev->pdev->device == 0x9805) && - (dev->pdev->subsystem_vendor == 0x1734) && - (dev->pdev->subsystem_device == 0x11bd)) { - if (*connector_type == DRM_MODE_CONNECTOR_VGA) - return false; - } - return true; } @@ -1112,6 +1106,31 @@ union firmware_info { ATOM_FIRMWARE_INFO_V2_2 info_22; }; +union igp_info { + struct _ATOM_INTEGRATED_SYSTEM_INFO info; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8; +}; + +static void radeon_atombios_get_dentist_vco_freq(struct radeon_device *rdev) +{ + struct radeon_mode_info *mode_info = &rdev->mode_info; + int index = GetIndexIntoMasterTable(DATA, IntegratedSystemInfo); + union igp_info *igp_info; + u8 frev, crev; + u16 data_offset; + + if (atom_parse_data_header(mode_info->atom_context, index, NULL, + &frev, &crev, &data_offset)) { + igp_info = (union igp_info *)(mode_info->atom_context->bios + + data_offset); + rdev->clock.vco_freq = + le32_to_cpu(igp_info->info_6.ulDentistVCOFreq); + } +} + bool radeon_atom_get_clock_info(struct drm_device *dev) { struct radeon_device *rdev = dev->dev_private; @@ -1263,20 +1282,25 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) rdev->mode_info.firmware_flags = le16_to_cpu(firmware_info->info.usFirmwareCapability.susAccess); + if (ASIC_IS_DCE8(rdev)) + rdev->clock.vco_freq = + le32_to_cpu(firmware_info->info_22.ulGPUPLL_OutputFreq); + else if (ASIC_IS_DCE5(rdev)) + rdev->clock.vco_freq = rdev->clock.current_dispclk; + else if (ASIC_IS_DCE41(rdev)) + radeon_atombios_get_dentist_vco_freq(rdev); + else + rdev->clock.vco_freq = rdev->clock.current_dispclk; + + if (rdev->clock.vco_freq == 0) + rdev->clock.vco_freq = 360000; /* 3.6 GHz */ + return true; } return false; } -union igp_info { - struct _ATOM_INTEGRATED_SYSTEM_INFO info; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8; -}; - bool radeon_atombios_sideport_present(struct radeon_device *rdev) { struct radeon_mode_info *mode_info = &rdev->mode_info; diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index 2c02e99b5f95..b214663b370d 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.c +++ b/drivers/gpu/drm/radeon/radeon_audio.c @@ -739,9 +739,6 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - struct radeon_connector *radeon_connector = to_radeon_connector(connector); - struct radeon_connector_atom_dig *dig_connector = - radeon_connector->con_priv; if (!dig || !dig->afmt) return; @@ -753,10 +750,7 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, radeon_audio_write_speaker_allocation(encoder); radeon_audio_write_sad_regs(encoder); radeon_audio_write_latency_fields(encoder, mode); - if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev)) - radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10); - else - radeon_audio_set_dto(encoder, dig_connector->dp_clock); + radeon_audio_set_dto(encoder, rdev->clock.vco_freq * 10); radeon_audio_set_audio_packet(encoder); radeon_audio_select_pin(encoder); @@ -781,3 +775,15 @@ void radeon_audio_dpms(struct drm_encoder *encoder, int mode) if (radeon_encoder->audio && radeon_encoder->audio->dpms) radeon_encoder->audio->dpms(encoder, mode == DRM_MODE_DPMS_ON); } + +unsigned int radeon_audio_decode_dfs_div(unsigned int div) +{ + if (div >= 8 && div < 64) + return (div - 8) * 25 + 200; + else if (div >= 64 && div < 96) + return (div - 64) * 50 + 1600; + else if (div >= 96 && div < 128) + return (div - 96) * 100 + 3200; + else + return 0; +} diff --git a/drivers/gpu/drm/radeon/radeon_audio.h b/drivers/gpu/drm/radeon/radeon_audio.h index 059cc3012062..5c70cceaa4a6 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.h +++ b/drivers/gpu/drm/radeon/radeon_audio.h @@ -79,5 +79,6 @@ void radeon_audio_fini(struct radeon_device *rdev); void radeon_audio_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode); void radeon_audio_dpms(struct drm_encoder *encoder, int mode); +unsigned int radeon_audio_decode_dfs_div(unsigned int div); #endif diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 340f3f549f29..9cfc1c3e1965 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1996,10 +1996,12 @@ radeon_add_atom_connector(struct drm_device *dev, rdev->mode_info.dither_property, RADEON_FMT_DITHER_DISABLE); - if (radeon_audio != 0) + if (radeon_audio != 0) { drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.audio_property, RADEON_AUDIO_AUTO); + radeon_connector->audio = RADEON_AUDIO_AUTO; + } if (ASIC_IS_DCE5(rdev)) drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.output_csc_property, @@ -2124,6 +2126,7 @@ radeon_add_atom_connector(struct drm_device *dev, drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.audio_property, RADEON_AUDIO_AUTO); + radeon_connector->audio = RADEON_AUDIO_AUTO; } if (connector_type == DRM_MODE_CONNECTOR_DVII) { radeon_connector->dac_load_detect = true; @@ -2179,6 +2182,7 @@ radeon_add_atom_connector(struct drm_device *dev, drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.audio_property, RADEON_AUDIO_AUTO); + radeon_connector->audio = RADEON_AUDIO_AUTO; } if (ASIC_IS_DCE5(rdev)) drm_object_attach_property(&radeon_connector->base.base, @@ -2231,6 +2235,7 @@ radeon_add_atom_connector(struct drm_device *dev, drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.audio_property, RADEON_AUDIO_AUTO); + radeon_connector->audio = RADEON_AUDIO_AUTO; } if (ASIC_IS_DCE5(rdev)) drm_object_attach_property(&radeon_connector->base.base, diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 1eca0acac016..3645b223aa37 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -403,7 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &radeon_crtc->base; unsigned long flags; int r; - int vpos, hpos, stat, min_udelay; + int vpos, hpos, stat, min_udelay = 0; + unsigned repcnt = 4; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; down_read(&rdev->exclusive_lock); @@ -454,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (radeon_crtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -470,12 +471,24 @@ static void radeon_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base); diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 84d45633d28c..fb6ad143873f 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <drm/drmP.h> #include <drm/radeon_drm.h> +#include <drm/drm_cache.h> #include "radeon.h" #include "radeon_trace.h" @@ -245,6 +246,12 @@ int radeon_bo_create(struct radeon_device *rdev, DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for " "better performance thanks to write-combining\n"); bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); +#else + /* For architectures that don't support WC memory, + * mask out the WC flag from the BO + */ + if (!drm_arch_can_wc_memory()) + bo->flags &= ~RADEON_GEM_GTT_WC; #endif radeon_ttm_placement_from_domain(bo, domain); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 59abebd6b5dc..60ab31517153 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1078,10 +1078,6 @@ force: /* update displays */ radeon_dpm_display_configuration_changed(rdev); - rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; - rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; - rdev->pm.dpm.single_display = single_display; - /* wait for the rings to drain */ for (i = 0; i < RADEON_NUM_RINGS; i++) { struct radeon_ring *ring = &rdev->ring[i]; @@ -1097,6 +1093,10 @@ force: radeon_dpm_post_set_power_state(rdev); + rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; + rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; + rdev->pm.dpm.single_display = single_display; + if (rdev->asic->dpm.force_performance_level) { if (rdev->pm.dpm.thermal_active) { enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level; diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c index c507896aca45..197b157b73d0 100644 --- a/drivers/gpu/drm/radeon/radeon_sa.c +++ b/drivers/gpu/drm/radeon/radeon_sa.c @@ -349,8 +349,13 @@ int radeon_sa_bo_new(struct radeon_device *rdev, /* see if we can skip over some allocations */ } while (radeon_sa_bo_next_hole(sa_manager, fences, tries)); + for (i = 0; i < RADEON_NUM_RINGS; ++i) + radeon_fence_ref(fences[i]); + spin_unlock(&sa_manager->wq.lock); r = radeon_fence_wait_any(rdev, fences, false); + for (i = 0; i < RADEON_NUM_RINGS; ++i) + radeon_fence_unref(&fences[i]); spin_lock(&sa_manager->wq.lock); /* if we have nothing to wait for block */ if (r == -ENOENT) { diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index e34307459e50..f342aad79cc6 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -235,6 +235,8 @@ static int radeon_verify_access(struct ttm_buffer_object *bo, struct file *filp) { struct radeon_bo *rbo = container_of(bo, struct radeon_bo, tbo); + if (radeon_ttm_tt_has_userptr(bo->ttm)) + return -EPERM; return drm_vma_node_verify_access(&rbo->gem_base.vma_node, filp); } @@ -758,7 +760,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm) 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(rdev->pdev, gtt->ttm.dma_address[i])) { - while (--i) { + while (i--) { pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i], PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); gtt->ttm.dma_address[i] = 0; diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index 48d97c040f49..3979632b9225 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -455,15 +455,15 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, if (soffset) { /* make sure object fit at this offset */ - eoffset = soffset + size; + eoffset = soffset + size - 1; if (soffset >= eoffset) { r = -EINVAL; goto error_unreserve; } last_pfn = eoffset / RADEON_GPU_PAGE_SIZE; - if (last_pfn > rdev->vm_manager.max_pfn) { - dev_err(rdev->dev, "va above limit (0x%08X > 0x%08X)\n", + if (last_pfn >= rdev->vm_manager.max_pfn) { + dev_err(rdev->dev, "va above limit (0x%08X >= 0x%08X)\n", last_pfn, rdev->vm_manager.max_pfn); r = -EINVAL; goto error_unreserve; @@ -478,7 +478,7 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, eoffset /= RADEON_GPU_PAGE_SIZE; if (soffset || eoffset) { struct interval_tree_node *it; - it = interval_tree_iter_first(&vm->va, soffset, eoffset - 1); + it = interval_tree_iter_first(&vm->va, soffset, eoffset); if (it && it != &bo_va->it) { struct radeon_bo_va *tmp; tmp = container_of(it, struct radeon_bo_va, it); @@ -518,7 +518,7 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, if (soffset || eoffset) { spin_lock(&vm->status_lock); bo_va->it.start = soffset; - bo_va->it.last = eoffset - 1; + bo_va->it.last = eoffset; list_add(&bo_va->vm_status, &vm->cleared); spin_unlock(&vm->status_lock); interval_tree_insert(&bo_va->it, &vm->va); @@ -888,7 +888,7 @@ static void radeon_vm_fence_pts(struct radeon_vm *vm, unsigned i; start >>= radeon_vm_block_size; - end >>= radeon_vm_block_size; + end = (end - 1) >> radeon_vm_block_size; for (i = start; i <= end; ++i) radeon_bo_fence(vm->page_tables[i].bo, fence, true); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index a82b891ae1fe..caa73de584a5 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2926,9 +2926,12 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = { /* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */ { PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x148c, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6810, 0x1682, 0x9275, 0, 120000 }, { 0, 0, 0, 0 }, }; @@ -3008,6 +3011,10 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, } ++p; } + /* limit mclk on all R7 370 parts for stability */ + if (rdev->pdev->device == 0x6811 && + rdev->pdev->revision == 0x81) + max_mclk = 120000; if (rps->vce_active) { rps->evclk = rdev->pm.dpm.vce_states[rdev->pm.dpm.vce_level].evclk; diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h index 4c4a7218a3bd..d1a7b58dd291 100644 --- a/drivers/gpu/drm/radeon/sid.h +++ b/drivers/gpu/drm/radeon/sid.h @@ -915,6 +915,11 @@ #define DCCG_AUDIO_DTO1_PHASE 0x05c0 #define DCCG_AUDIO_DTO1_MODULE 0x05c4 +#define DENTIST_DISPCLK_CNTL 0x0490 +# define DENTIST_DPREFCLK_WDIVIDER(x) (((x) & 0x7f) << 24) +# define DENTIST_DPREFCLK_WDIVIDER_MASK (0x7f << 24) +# define DENTIST_DPREFCLK_WDIVIDER_SHIFT 24 + #define AFMT_AUDIO_SRC_CONTROL 0x713c #define AFMT_AUDIO_SRC_SELECT(x) (((x) & 7) << 0) /* AFMT_AUDIO_SRC_SELECT diff --git a/drivers/gpu/drm/radeon/vce_v1_0.c b/drivers/gpu/drm/radeon/vce_v1_0.c index 07a0d378e122..a01efe39a820 100644 --- a/drivers/gpu/drm/radeon/vce_v1_0.c +++ b/drivers/gpu/drm/radeon/vce_v1_0.c @@ -178,12 +178,12 @@ int vce_v1_0_load_fw(struct radeon_device *rdev, uint32_t *data) return -EINVAL; } - for (i = 0; i < sign->num; ++i) { - if (sign->val[i].chip_id == chip_id) + for (i = 0; i < le32_to_cpu(sign->num); ++i) { + if (le32_to_cpu(sign->val[i].chip_id) == chip_id) break; } - if (i == sign->num) + if (i == le32_to_cpu(sign->num)) return -EINVAL; data += (256 - 64) / 4; @@ -191,18 +191,18 @@ int vce_v1_0_load_fw(struct radeon_device *rdev, uint32_t *data) data[1] = sign->val[i].nonce[1]; data[2] = sign->val[i].nonce[2]; data[3] = sign->val[i].nonce[3]; - data[4] = sign->len + 64; + data[4] = cpu_to_le32(le32_to_cpu(sign->len) + 64); memset(&data[5], 0, 44); memcpy(&data[16], &sign[1], rdev->vce_fw->size - sizeof(*sign)); - data += data[4] / 4; + data += le32_to_cpu(data[4]) / 4; data[0] = sign->val[i].sigval[0]; data[1] = sign->val[i].sigval[1]; data[2] = sign->val[i].sigval[2]; data[3] = sign->val[i].sigval[3]; - rdev->vce.keyselect = sign->val[i].keyselect; + rdev->vce.keyselect = le32_to_cpu(sign->val[i].keyselect); return 0; } diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index 62c7b1dafaa4..73e41a8613da 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -539,7 +539,7 @@ static int udlfb_create(struct drm_fb_helper *helper, out_destroy_fbi: drm_fb_helper_release_fbi(helper); out_gfree: - drm_gem_object_unreference(&ufbdev->ufb.obj->base); + drm_gem_object_unreference_unlocked(&ufbdev->ufb.obj->base); out: return ret; } diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c index 2a0a784ab6ee..d7528e0d8442 100644 --- a/drivers/gpu/drm/udl/udl_gem.c +++ b/drivers/gpu/drm/udl/udl_gem.c @@ -52,7 +52,7 @@ udl_gem_create(struct drm_file *file, return ret; } - drm_gem_object_unreference(&obj->base); + drm_gem_object_unreference_unlocked(&obj->base); *handle_p = handle; return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 6377e8151000..67cebb23c940 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -247,7 +247,7 @@ static void __vmw_cmdbuf_header_free(struct vmw_cmdbuf_header *header) { struct vmw_cmdbuf_man *man = header->man; - BUG_ON(!spin_is_locked(&man->lock)); + lockdep_assert_held_once(&man->lock); if (header->inline_space) { vmw_cmdbuf_header_inline_free(header); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index c49812b80dd0..24fb348a44e1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -25,6 +25,7 @@ * **************************************************************************/ #include <linux/module.h> +#include <linux/console.h> #include <drm/drmP.h> #include "vmwgfx_drv.h" @@ -1538,6 +1539,12 @@ static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent) static int __init vmwgfx_init(void) { int ret; + +#ifdef CONFIG_VGA_CONSOLE + if (vgacon_text_force()) + return -EINVAL; +#endif + ret = drm_pci_init(&driver, &vmw_pci_driver); if (ret) DRM_ERROR("Failed initializing DRM.\n"); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 9b4bb9e74d73..7c2e118a77b0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -763,21 +763,25 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev, uint32_t format; struct drm_vmw_size content_base_size; struct vmw_resource *res; + unsigned int bytes_pp; int ret; switch (mode_cmd->depth) { case 32: case 24: format = SVGA3D_X8R8G8B8; + bytes_pp = 4; break; case 16: case 15: format = SVGA3D_R5G6B5; + bytes_pp = 2; break; case 8: format = SVGA3D_P8; + bytes_pp = 1; break; default: @@ -785,7 +789,7 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev, return -EINVAL; } - content_base_size.width = mode_cmd->width; + content_base_size.width = mode_cmd->pitch / bytes_pp; content_base_size.height = mode_cmd->height; content_base_size.depth = 1; diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index f2e13eb8339f..0585fd2031dd 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -1050,6 +1050,17 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) for (i = 0; i < ARRAY_SIZE(client_reg); i++) { const struct ipu_platform_reg *reg = &client_reg[i]; struct platform_device *pdev; + struct device_node *of_node; + + /* Associate subdevice with the corresponding port node */ + of_node = of_graph_get_port_by_id(dev->of_node, i); + if (!of_node) { + dev_info(dev, + "no port@%d node in %s, not using %s%d\n", + i, dev->of_node->full_name, + (i / 2) ? "DI" : "CSI", i % 2); + continue; + } pdev = platform_device_alloc(reg->name, id++); if (!pdev) { @@ -1059,15 +1070,6 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) pdev->dev.parent = dev; - /* Associate subdevice with the corresponding port node */ - pdev->dev.of_node = of_graph_get_port_by_id(dev->of_node, i); - if (!pdev->dev.of_node) { - dev_err(dev, "missing port@%d node in %s\n", i, - dev->of_node->full_name); - ret = -ENODEV; - goto err_register; - } - ret = platform_device_add_data(pdev, ®->pdata, sizeof(reg->pdata)); if (!ret) @@ -1076,6 +1078,12 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) platform_device_put(pdev); goto err_register; } + + /* + * Set of_node only after calling platform_device_add. Otherwise + * the platform:imx-ipuv3-crtc modalias won't be used. + */ + pdev->dev.of_node = of_node; } return 0; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index c6f7a694f67a..ec791e169f8f 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1897,6 +1897,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_ELITE_KBD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_CORDLESS_DESKTOP_LX500) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_EXTREME_3D) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DUAL_ACTION) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_WHEEL) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD_CORD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD) }, @@ -2615,9 +2616,10 @@ int hid_add_device(struct hid_device *hdev) /* * Scan generic devices for group information */ - if (hid_ignore_special_drivers || - (!hdev->group && - !hid_match_id(hdev, hid_have_special_driver))) { + if (hid_ignore_special_drivers) { + hdev->group = HID_GROUP_GENERIC; + } else if (!hdev->group && + !hid_match_id(hdev, hid_have_special_driver)) { ret = hid_scan_report(hdev); if (ret) hid_warn(hdev, "bad device descriptor (%d)\n", ret); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 8b78a7f1f779..909ab0176ef2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -255,6 +255,7 @@ #define USB_DEVICE_ID_CORSAIR_K90 0x1b02 #define USB_VENDOR_ID_CREATIVELABS 0x041e +#define USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51 0x322c #define USB_DEVICE_ID_PRODIKEYS_PCMIDI 0x2801 #define USB_VENDOR_ID_CVTOUCH 0x1ff7 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 96759b270360..c5ec4f915594 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -357,8 +357,19 @@ static void mt_feature_mapping(struct hid_device *hdev, break; } - td->inputmode = field->report->id; - td->inputmode_index = usage->usage_index; + if (td->inputmode < 0) { + td->inputmode = field->report->id; + td->inputmode_index = usage->usage_index; + } else { + /* + * Some elan panels wrongly declare 2 input mode + * features, and silently ignore when we set the + * value in the second field. Skip the second feature + * and hope for the best. + */ + dev_info(&hdev->dev, + "Ignoring the extra HID_DG_INPUTMODE\n"); + } break; case HID_DG_CONTACTMAX: @@ -385,6 +396,11 @@ static void mt_feature_mapping(struct hid_device *hdev, td->is_buttonpad = true; break; + case 0xff0000c5: + /* Retrieve the Win8 blob once to enable some devices */ + if (usage->usage_index == 0) + mt_get_feature(hdev, field->report); + break; } } @@ -434,16 +450,6 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON) td->buttons_count++; - /* Only map fields from TouchScreen or TouchPad collections. - * We need to ignore fields that belong to other collections - * such as Mouse that might have the same GenericDesktop usages. */ - if (field->application == HID_DG_TOUCHSCREEN) - set_bit(INPUT_PROP_DIRECT, hi->input->propbit); - else if (field->application == HID_DG_TOUCHPAD) - set_bit(INPUT_PROP_POINTER, hi->input->propbit); - else - return 0; - if (usage->usage_index) prev_usage = &field->usage[usage->usage_index - 1]; diff --git a/drivers/hid/hid-steelseries.c b/drivers/hid/hid-steelseries.c index 93ddc1c65b4c..3edd4ac36494 100644 --- a/drivers/hid/hid-steelseries.c +++ b/drivers/hid/hid-steelseries.c @@ -253,11 +253,6 @@ static int steelseries_srws1_probe(struct hid_device *hdev, goto err_free; } - if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 0, 0, 16)) { - ret = -ENODEV; - goto err_free; - } - ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "hw start failed\n"); diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 10bd8e6e4c9c..0b80633bae91 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -282,17 +282,21 @@ static int i2c_hid_set_or_send_report(struct i2c_client *client, u8 reportType, u16 dataRegister = le16_to_cpu(ihid->hdesc.wDataRegister); u16 outputRegister = le16_to_cpu(ihid->hdesc.wOutputRegister); u16 maxOutputLength = le16_to_cpu(ihid->hdesc.wMaxOutputLength); + u16 size; + int args_len; + int index = 0; + + i2c_hid_dbg(ihid, "%s\n", __func__); + + if (data_len > ihid->bufsize) + return -EINVAL; - /* hid_hw_* already checked that data_len < HID_MAX_BUFFER_SIZE */ - u16 size = 2 /* size */ + + size = 2 /* size */ + (reportID ? 1 : 0) /* reportID */ + data_len /* buf */; - int args_len = (reportID >= 0x0F ? 1 : 0) /* optional third byte */ + + args_len = (reportID >= 0x0F ? 1 : 0) /* optional third byte */ + 2 /* dataRegister */ + size /* args */; - int index = 0; - - i2c_hid_dbg(ihid, "%s\n", __func__); if (!use_data && maxOutputLength == 0) return -ENOSYS; diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 36712e9f56c2..0df32fe0e345 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -477,8 +477,6 @@ static void hid_ctrl(struct urb *urb) struct usbhid_device *usbhid = hid->driver_data; int unplug = 0, status = urb->status; - spin_lock(&usbhid->lock); - switch (status) { case 0: /* success */ if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_IN) @@ -498,6 +496,8 @@ static void hid_ctrl(struct urb *urb) hid_warn(urb->dev, "ctrl urb status %d received\n", status); } + spin_lock(&usbhid->lock); + if (unplug) { usbhid->ctrltail = usbhid->ctrlhead; } else { @@ -951,14 +951,6 @@ static int usbhid_output_report(struct hid_device *hid, __u8 *buf, size_t count) return ret; } -static void usbhid_restart_queues(struct usbhid_device *usbhid) -{ - if (usbhid->urbout && !test_bit(HID_OUT_RUNNING, &usbhid->iofl)) - usbhid_restart_out_queue(usbhid); - if (!test_bit(HID_CTRL_RUNNING, &usbhid->iofl)) - usbhid_restart_ctrl_queue(usbhid); -} - static void hid_free_buffers(struct usb_device *dev, struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; @@ -1404,6 +1396,37 @@ static void hid_cease_io(struct usbhid_device *usbhid) usb_kill_urb(usbhid->urbout); } +static void hid_restart_io(struct hid_device *hid) +{ + struct usbhid_device *usbhid = hid->driver_data; + int clear_halt = test_bit(HID_CLEAR_HALT, &usbhid->iofl); + int reset_pending = test_bit(HID_RESET_PENDING, &usbhid->iofl); + + spin_lock_irq(&usbhid->lock); + clear_bit(HID_SUSPENDED, &usbhid->iofl); + usbhid_mark_busy(usbhid); + + if (clear_halt || reset_pending) + schedule_work(&usbhid->reset_work); + usbhid->retry_delay = 0; + spin_unlock_irq(&usbhid->lock); + + if (reset_pending || !test_bit(HID_STARTED, &usbhid->iofl)) + return; + + if (!clear_halt) { + if (hid_start_in(hid) < 0) + hid_io_error(hid); + } + + spin_lock_irq(&usbhid->lock); + if (usbhid->urbout && !test_bit(HID_OUT_RUNNING, &usbhid->iofl)) + usbhid_restart_out_queue(usbhid); + if (!test_bit(HID_CTRL_RUNNING, &usbhid->iofl)) + usbhid_restart_ctrl_queue(usbhid); + spin_unlock_irq(&usbhid->lock); +} + /* Treat USB reset pretty much the same as suspend/resume */ static int hid_pre_reset(struct usb_interface *intf) { @@ -1453,14 +1476,14 @@ static int hid_post_reset(struct usb_interface *intf) return 1; } + /* No need to do another reset or clear a halted endpoint */ spin_lock_irq(&usbhid->lock); clear_bit(HID_RESET_PENDING, &usbhid->iofl); + clear_bit(HID_CLEAR_HALT, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); hid_set_idle(dev, intf->cur_altsetting->desc.bInterfaceNumber, 0, 0); - status = hid_start_in(hid); - if (status < 0) - hid_io_error(hid); - usbhid_restart_queues(usbhid); + + hid_restart_io(hid); return 0; } @@ -1483,25 +1506,9 @@ void usbhid_put_power(struct hid_device *hid) #ifdef CONFIG_PM static int hid_resume_common(struct hid_device *hid, bool driver_suspended) { - struct usbhid_device *usbhid = hid->driver_data; - int status; - - spin_lock_irq(&usbhid->lock); - clear_bit(HID_SUSPENDED, &usbhid->iofl); - usbhid_mark_busy(usbhid); - - if (test_bit(HID_CLEAR_HALT, &usbhid->iofl) || - test_bit(HID_RESET_PENDING, &usbhid->iofl)) - schedule_work(&usbhid->reset_work); - usbhid->retry_delay = 0; - - usbhid_restart_queues(usbhid); - spin_unlock_irq(&usbhid->lock); - - status = hid_start_in(hid); - if (status < 0) - hid_io_error(hid); + int status = 0; + hid_restart_io(hid); if (driver_suspended && hid->driver && hid->driver->resume) status = hid->driver->resume(hid); return status; @@ -1570,12 +1577,8 @@ static int hid_suspend(struct usb_interface *intf, pm_message_t message) static int hid_resume(struct usb_interface *intf) { struct hid_device *hid = usb_get_intfdata (intf); - struct usbhid_device *usbhid = hid->driver_data; int status; - if (!test_bit(HID_STARTED, &usbhid->iofl)) - return 0; - status = hid_resume_common(hid, true); dev_dbg(&intf->dev, "resume status %d\n", status); return 0; @@ -1584,10 +1587,8 @@ static int hid_resume(struct usb_interface *intf) static int hid_reset_resume(struct usb_interface *intf) { struct hid_device *hid = usb_get_intfdata(intf); - struct usbhid_device *usbhid = hid->driver_data; int status; - clear_bit(HID_SUSPENDED, &usbhid->iofl); status = hid_post_reset(intf); if (status >= 0 && hid->driver && hid->driver->reset_resume) { int ret = hid->driver->reset_resume(hid); diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 7dd0953cd70f..dc8e6adf95a4 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -70,6 +70,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 01a4f05c1642..5c02d7bbc7f2 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2493,6 +2493,17 @@ void wacom_setup_device_quirks(struct wacom *wacom) } /* + * Hack for the Bamboo One: + * the device presents a PAD/Touch interface as most Bamboos and even + * sends ghosts PAD data on it. However, later, we must disable this + * ghost interface, and we can not detect it unless we set it here + * to WACOM_DEVICETYPE_PAD or WACOM_DEVICETYPE_TOUCH. + */ + if (features->type == BAMBOO_PEN && + features->pktlen == WACOM_PKGLEN_BBTOUCH3) + features->device_type |= WACOM_DEVICETYPE_PAD; + + /* * Raw Wacom-mode pen and touch events both come from interface * 0, whose HID descriptor has an application usage of 0xFF0D * (i.e., WACOM_VENDORDEFINED_PEN). We route pen packets back @@ -3438,6 +3449,10 @@ static const struct wacom_features wacom_features_0x33E = { "Wacom Intuos PT M 2", 21600, 13500, 2047, 63, INTUOSHT2, WACOM_INTUOS_RES, WACOM_INTUOS_RES, .touch_max = 16, .check_for_hid_type = true, .hid_type = HID_TYPE_USBNONE }; +static const struct wacom_features wacom_features_0x343 = + { "Wacom DTK1651", 34616, 19559, 1023, 0, + DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4, + WACOM_DTU_OFFSET, WACOM_DTU_OFFSET }; static const struct wacom_features wacom_features_HID_ANY_ID = { "Wacom HID", .type = HID_GENERIC }; @@ -3603,6 +3618,7 @@ const struct hid_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x33C) }, { USB_DEVICE_WACOM(0x33D) }, { USB_DEVICE_WACOM(0x33E) }, + { USB_DEVICE_WACOM(0x343) }, { USB_DEVICE_WACOM(0x4001) }, { USB_DEVICE_WACOM(0x4004) }, { USB_DEVICE_WACOM(0x5000) }, diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index c4dcab048cb8..9098f13f2f44 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -630,10 +630,19 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer, * on the ring. We will not signal if more data is * to be placed. * + * Based on the channel signal state, we will decide + * which signaling policy will be applied. + * * If we cannot write to the ring-buffer; signal the host * even if we may not have written anything. This is a rare * enough condition that it should not matter. */ + + if (channel->signal_policy) + signal = true; + else + kick_q = true; + if (((ret == 0) && kick_q && signal) || (ret)) vmbus_setevent(channel); @@ -733,10 +742,19 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, * on the ring. We will not signal if more data is * to be placed. * + * Based on the channel signal state, we will decide + * which signaling policy will be applied. + * * If we cannot write to the ring-buffer; signal the host * even if we may not have written anything. This is a rare * enough condition that it should not matter. */ + + if (channel->signal_policy) + signal = true; + else + kick_q = true; + if (((ret == 0) && kick_q && signal) || (ret)) vmbus_setevent(channel); diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c index f155b8380481..2b3105c8aed3 100644 --- a/drivers/hwmon/ads1015.c +++ b/drivers/hwmon/ads1015.c @@ -126,7 +126,7 @@ static int ads1015_reg_to_mv(struct i2c_client *client, unsigned int channel, struct ads1015_data *data = i2c_get_clientdata(client); unsigned int pga = data->channel_data[channel].pga; int fullscale = fullscale_table[pga]; - const unsigned mask = data->id == ads1115 ? 0x7fff : 0x7ff0; + const int mask = data->id == ads1115 ? 0x7fff : 0x7ff0; return DIV_ROUND_CLOSEST(reg * fullscale, mask); } diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index c8487894b312..c43318d3416e 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -932,6 +932,17 @@ MODULE_DEVICE_TABLE(dmi, i8k_dmi_table); static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = { { /* + * CPU fan speed going up and down on Dell Studio XPS 8000 + * for unknown reasons. + */ + .ident = "Dell Studio XPS 8000", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8000"), + }, + }, + { + /* * CPU fan speed going up and down on Dell Studio XPS 8100 * for unknown reasons. */ diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 82de3deeb18a..685568b1236d 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -406,16 +406,11 @@ static int gpio_fan_get_cur_state(struct thermal_cooling_device *cdev, unsigned long *state) { struct gpio_fan_data *fan_data = cdev->devdata; - int r; if (!fan_data) return -EINVAL; - r = get_fan_speed_index(fan_data); - if (r < 0) - return r; - - *state = r; + *state = fan_data->speed_index; return 0; } diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c index 36544c4f653c..303d0c9df907 100644 --- a/drivers/hwmon/max1111.c +++ b/drivers/hwmon/max1111.c @@ -85,6 +85,9 @@ static struct max1111_data *the_max1111; int max1111_read_channel(int channel) { + if (!the_max1111 || !the_max1111->spi) + return -ENODEV; + return max1111_read(&the_max1111->spi->dev, channel); } EXPORT_SYMBOL(max1111_read_channel); @@ -258,6 +261,9 @@ static int max1111_remove(struct spi_device *spi) { struct max1111_data *data = spi_get_drvdata(spi); +#ifdef CONFIG_SHARPSL_PM + the_max1111 = NULL; +#endif hwmon_device_unregister(data->hwmon_dev); sysfs_remove_group(&spi->dev.kobj, &max1110_attr_group); sysfs_remove_group(&spi->dev.kobj, &max1111_attr_group); diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 52f708bcf77f..d50c701b19d6 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -313,6 +313,10 @@ int of_hwspin_lock_get_id(struct device_node *np, int index) hwlock = radix_tree_deref_slot(slot); if (unlikely(!hwlock)) continue; + if (radix_tree_is_indirect_ptr(hwlock)) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (hwlock->bank->dev->of_node == args.np) { ret = 0; diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index e25492137d8b..93738dfbf631 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -548,7 +548,7 @@ static int coresight_name_match(struct device *dev, void *data) to_match = data; i_csdev = to_coresight_device(dev); - if (!strcmp(to_match, dev_name(&i_csdev->dev))) + if (to_match && !strcmp(to_match, dev_name(&i_csdev->dev))) return 1; return 0; diff --git a/drivers/hwtracing/stm/Kconfig b/drivers/hwtracing/stm/Kconfig index 83e9f591a54b..e7a348807f0c 100644 --- a/drivers/hwtracing/stm/Kconfig +++ b/drivers/hwtracing/stm/Kconfig @@ -1,6 +1,7 @@ config STM tristate "System Trace Module devices" select CONFIGFS_FS + select SRCU help A System Trace Module (STM) is a device exporting data in System Trace Protocol (STP) format as defined by MIPI STP standards. diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c index 8e9637eea512..81115abf3c1f 100644 --- a/drivers/i2c/busses/i2c-brcmstb.c +++ b/drivers/i2c/busses/i2c-brcmstb.c @@ -562,8 +562,7 @@ static int brcmstb_i2c_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; - dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(struct bsc_regs *), - GFP_KERNEL); + dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(*dev->bsc_regmap), GFP_KERNEL); if (!dev->bsc_regmap) return -ENOMEM; diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index 714bdc837769..b167ab25310a 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -116,8 +116,8 @@ struct cpm_i2c { cbd_t __iomem *rbase; u_char *txbuf[CPM_MAXBD]; u_char *rxbuf[CPM_MAXBD]; - u32 txdma[CPM_MAXBD]; - u32 rxdma[CPM_MAXBD]; + dma_addr_t txdma[CPM_MAXBD]; + dma_addr_t rxdma[CPM_MAXBD]; }; static irqreturn_t cpm_i2c_interrupt(int irq, void *dev_id) diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c index b29c7500461a..f54ece8fce78 100644 --- a/drivers/i2c/busses/i2c-exynos5.c +++ b/drivers/i2c/busses/i2c-exynos5.c @@ -671,7 +671,9 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap, return -EIO; } - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; for (i = 0; i < num; i++, msgs++) { stop = (i == num - 1); @@ -695,7 +697,7 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap, } out: - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); return ret; } @@ -747,7 +749,9 @@ static int exynos5_i2c_probe(struct platform_device *pdev) return -ENOENT; } - clk_prepare_enable(i2c->clk); + ret = clk_prepare_enable(i2c->clk); + if (ret) + return ret; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); i2c->regs = devm_ioremap_resource(&pdev->dev, mem); @@ -799,6 +803,10 @@ static int exynos5_i2c_probe(struct platform_device *pdev) platform_set_drvdata(pdev, i2c); + clk_disable(i2c->clk); + + return 0; + err_clk: clk_disable_unprepare(i2c->clk); return ret; @@ -810,6 +818,8 @@ static int exynos5_i2c_remove(struct platform_device *pdev) i2c_del_adapter(&i2c->adap); + clk_unprepare(i2c->clk); + return 0; } @@ -821,6 +831,8 @@ static int exynos5_i2c_suspend_noirq(struct device *dev) i2c->suspended = 1; + clk_unprepare(i2c->clk); + return 0; } @@ -830,7 +842,9 @@ static int exynos5_i2c_resume_noirq(struct device *dev) struct exynos5_i2c *i2c = platform_get_drvdata(pdev); int ret = 0; - clk_prepare_enable(i2c->clk); + ret = clk_prepare_enable(i2c->clk); + if (ret) + return ret; ret = exynos5_hsi2c_clock_setup(i2c); if (ret) { @@ -839,7 +853,7 @@ static int exynos5_i2c_resume_noirq(struct device *dev) } exynos5_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); i2c->suspended = 0; return 0; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index f62d69799a9c..27fa0cb09538 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1271,6 +1271,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) switch (dev->device) { case PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS: case PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS: + case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS: + case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS: case PCI_DEVICE_ID_INTEL_DNV_SMBUS: priv->features |= FEATURE_I2C_BLOCK_READ; priv->features |= FEATURE_IRQ; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index cd4510a63375..146eed70bdf4 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -65,7 +65,7 @@ #include <asm/mwait.h> #include <asm/msr.h> -#define INTEL_IDLE_VERSION "0.4" +#define INTEL_IDLE_VERSION "0.4.1" #define PREFIX "intel_idle: " static struct cpuidle_driver intel_idle_driver = { @@ -994,36 +994,92 @@ static void intel_idle_cpuidle_devices_uninit(void) } /* - * intel_idle_state_table_update() - * - * Update the default state_table for this CPU-id + * ivt_idle_state_table_update(void) * - * Currently used to access tuned IVT multi-socket targets + * Tune IVT multi-socket targets * Assumption: num_sockets == (max_package_num + 1) */ -void intel_idle_state_table_update(void) +static void ivt_idle_state_table_update(void) { /* IVT uses a different table for 1-2, 3-4, and > 4 sockets */ - if (boot_cpu_data.x86_model == 0x3e) { /* IVT */ - int cpu, package_num, num_sockets = 1; - - for_each_online_cpu(cpu) { - package_num = topology_physical_package_id(cpu); - if (package_num + 1 > num_sockets) { - num_sockets = package_num + 1; - - if (num_sockets > 4) { - cpuidle_state_table = ivt_cstates_8s; - return; - } + int cpu, package_num, num_sockets = 1; + + for_each_online_cpu(cpu) { + package_num = topology_physical_package_id(cpu); + if (package_num + 1 > num_sockets) { + num_sockets = package_num + 1; + + if (num_sockets > 4) { + cpuidle_state_table = ivt_cstates_8s; + return; } } + } + + if (num_sockets > 2) + cpuidle_state_table = ivt_cstates_4s; + + /* else, 1 and 2 socket systems use default ivt_cstates */ +} +/* + * sklh_idle_state_table_update(void) + * + * On SKL-H (model 0x5e) disable C8 and C9 if: + * C10 is enabled and SGX disabled + */ +static void sklh_idle_state_table_update(void) +{ + unsigned long long msr; + unsigned int eax, ebx, ecx, edx; + + + /* if PC10 disabled via cmdline intel_idle.max_cstate=7 or shallower */ + if (max_cstate <= 7) + return; + + /* if PC10 not present in CPUID.MWAIT.EDX */ + if ((mwait_substates & (0xF << 28)) == 0) + return; + + rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr); + + /* PC10 is not enabled in PKG C-state limit */ + if ((msr & 0xF) != 8) + return; + + ecx = 0; + cpuid(7, &eax, &ebx, &ecx, &edx); + + /* if SGX is present */ + if (ebx & (1 << 2)) { - if (num_sockets > 2) - cpuidle_state_table = ivt_cstates_4s; - /* else, 1 and 2 socket systems use default ivt_cstates */ + rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); + + /* if SGX is enabled */ + if (msr & (1 << 18)) + return; + } + + skl_cstates[5].disabled = 1; /* C8-SKL */ + skl_cstates[6].disabled = 1; /* C9-SKL */ +} +/* + * intel_idle_state_table_update() + * + * Update the default state_table for this CPU-id + */ + +static void intel_idle_state_table_update(void) +{ + switch (boot_cpu_data.x86_model) { + + case 0x3e: /* IVT */ + ivt_idle_state_table_update(); + break; + case 0x5e: /* SKL-H */ + sklh_idle_state_table_update(); + break; } - return; } /* @@ -1063,6 +1119,14 @@ static int __init intel_idle_cpuidle_driver_init(void) if (num_substates == 0) continue; + /* if state marked as disabled, skip it */ + if (cpuidle_state_table[cstate].disabled != 0) { + pr_debug(PREFIX "state %s is disabled", + cpuidle_state_table[cstate].name); + continue; + } + + if (((mwait_cstate + 1) > 2) && !boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halts in idle" diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index 969428dd6329..16cc5c691a55 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -173,6 +173,7 @@ config STK8312 config STK8BA50 tristate "Sensortek STK8BA50 3-Axis Accelerometer Driver" depends on I2C + depends on IIO_TRIGGER help Say yes here to get support for the Sensortek STK8BA50 3-axis accelerometer. diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c index 2d33f1e821db..291c61a41c9a 100644 --- a/drivers/iio/accel/bmc150-accel-core.c +++ b/drivers/iio/accel/bmc150-accel-core.c @@ -547,7 +547,7 @@ static int bmc150_accel_get_axis(struct bmc150_accel_data *data, { int ret; int axis = chan->scan_index; - unsigned int raw_val; + __le16 raw_val; mutex_lock(&data->mutex); ret = bmc150_accel_set_power_state(data, true); @@ -557,14 +557,14 @@ static int bmc150_accel_get_axis(struct bmc150_accel_data *data, } ret = regmap_bulk_read(data->regmap, BMC150_ACCEL_AXIS_TO_REG(axis), - &raw_val, 2); + &raw_val, sizeof(raw_val)); if (ret < 0) { dev_err(data->dev, "Error reading axis %d\n", axis); bmc150_accel_set_power_state(data, false); mutex_unlock(&data->mutex); return ret; } - *val = sign_extend32(raw_val >> chan->scan_type.shift, + *val = sign_extend32(le16_to_cpu(raw_val) >> chan->scan_type.shift, chan->scan_type.realbits - 1); ret = bmc150_accel_set_power_state(data, false); mutex_unlock(&data->mutex); @@ -988,6 +988,7 @@ static const struct iio_event_spec bmc150_accel_event = { .realbits = (bits), \ .storagebits = 16, \ .shift = 16 - (bits), \ + .endianness = IIO_LE, \ }, \ .event_spec = &bmc150_accel_event, \ .num_event_specs = 1 \ diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 7868c744fd4b..1e7aded53117 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -372,6 +372,7 @@ config TWL6030_GPADC config VF610_ADC tristate "Freescale vf610 ADC driver" depends on OF + depends on HAS_IOMEM select IIO_BUFFER select IIO_TRIGGERED_BUFFER help diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 942320e32753..c1e05532d437 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -289,7 +289,7 @@ static int tiadc_iio_buffered_hardware_setup(struct iio_dev *indio_dev, goto error_kfifo_free; indio_dev->setup_ops = setup_ops; - indio_dev->modes |= INDIO_BUFFER_HARDWARE; + indio_dev->modes |= INDIO_BUFFER_SOFTWARE; return 0; diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 43d14588448d..b4dde8315210 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -300,6 +300,7 @@ static int mcp4725_probe(struct i2c_client *client, data->client = client; indio_dev->dev.parent = &client->dev; + indio_dev->name = id->name; indio_dev->info = &mcp4725_info; indio_dev->channels = &mcp4725_channel; indio_dev->num_channels = 1; diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index 02ff789852a0..acb3b303d800 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -452,7 +452,7 @@ static int bmg160_get_temp(struct bmg160_data *data, int *val) static int bmg160_get_axis(struct bmg160_data *data, int axis, int *val) { int ret; - unsigned int raw_val; + __le16 raw_val; mutex_lock(&data->mutex); ret = bmg160_set_power_state(data, true); @@ -462,7 +462,7 @@ static int bmg160_get_axis(struct bmg160_data *data, int axis, int *val) } ret = regmap_bulk_read(data->regmap, BMG160_AXIS_TO_REG(axis), &raw_val, - 2); + sizeof(raw_val)); if (ret < 0) { dev_err(data->dev, "Error reading axis %d\n", axis); bmg160_set_power_state(data, false); @@ -470,7 +470,7 @@ static int bmg160_get_axis(struct bmg160_data *data, int axis, int *val) return ret; } - *val = sign_extend32(raw_val, 15); + *val = sign_extend32(le16_to_cpu(raw_val), 15); ret = bmg160_set_power_state(data, false); mutex_unlock(&data->mutex); if (ret < 0) @@ -733,6 +733,7 @@ static const struct iio_event_spec bmg160_event = { .sign = 's', \ .realbits = 16, \ .storagebits = 16, \ + .endianness = IIO_LE, \ }, \ .event_spec = &bmg160_event, \ .num_event_specs = 1 \ @@ -780,7 +781,7 @@ static irqreturn_t bmg160_trigger_handler(int irq, void *p) mutex_unlock(&data->mutex); goto err; } - data->buffer[i++] = ret; + data->buffer[i++] = val; } mutex_unlock(&data->mutex); diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c index cb32b593f1c5..36607d52fee0 100644 --- a/drivers/iio/imu/adis_buffer.c +++ b/drivers/iio/imu/adis_buffer.c @@ -43,7 +43,7 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, return -ENOMEM; rx = adis->buffer; - tx = rx + indio_dev->scan_bytes; + tx = rx + scan_count; spi_message_init(&adis->msg); diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index c8bad3cf891d..217e9306aa0f 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -351,6 +351,8 @@ EXPORT_SYMBOL_GPL(iio_channel_get); void iio_channel_release(struct iio_channel *channel) { + if (!channel) + return; iio_device_put(channel->indio_dev); kfree(channel); } diff --git a/drivers/iio/light/acpi-als.c b/drivers/iio/light/acpi-als.c index 60537ec0c923..53201d99a16c 100644 --- a/drivers/iio/light/acpi-als.c +++ b/drivers/iio/light/acpi-als.c @@ -54,7 +54,9 @@ static const struct iio_chan_spec acpi_als_channels[] = { .realbits = 32, .storagebits = 32, }, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), + /* _RAW is here for backward ABI compatibility */ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | + BIT(IIO_CHAN_INFO_PROCESSED), }, }; @@ -152,7 +154,7 @@ static int acpi_als_read_raw(struct iio_dev *indio_dev, s32 temp_val; int ret; - if (mask != IIO_CHAN_INFO_RAW) + if ((mask != IIO_CHAN_INFO_PROCESSED) && (mask != IIO_CHAN_INFO_RAW)) return -EINVAL; /* we support only illumination (_ALI) so far. */ diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c index 809a961b9a7f..6bf89d8f3741 100644 --- a/drivers/iio/light/ltr501.c +++ b/drivers/iio/light/ltr501.c @@ -180,7 +180,7 @@ static const struct ltr501_samp_table ltr501_ps_samp_table[] = { {500000, 2000000} }; -static unsigned int ltr501_match_samp_freq(const struct ltr501_samp_table *tab, +static int ltr501_match_samp_freq(const struct ltr501_samp_table *tab, int len, int val, int val2) { int i, freq; diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index b13936dacc78..f2a7f72f7aa6 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -462,6 +462,8 @@ static int ak8975_setup_irq(struct ak8975_data *data) int rc; int irq; + init_waitqueue_head(&data->data_ready_queue); + clear_bit(0, &data->flags); if (client->irq) irq = client->irq; else @@ -477,8 +479,6 @@ static int ak8975_setup_irq(struct ak8975_data *data) return rc; } - init_waitqueue_head(&data->data_ready_queue); - clear_bit(0, &data->flags); data->eoc_irq = irq; return rc; @@ -732,7 +732,7 @@ static int ak8975_probe(struct i2c_client *client, int eoc_gpio; int err; const char *name = NULL; - enum asahi_compass_chipset chipset; + enum asahi_compass_chipset chipset = AK_MAX_TYPE; /* Grab and set up the supplied GPIO. */ if (client->dev.platform_data) diff --git a/drivers/iio/magnetometer/st_magn.h b/drivers/iio/magnetometer/st_magn.h index 06a4d9c35581..9daca4681922 100644 --- a/drivers/iio/magnetometer/st_magn.h +++ b/drivers/iio/magnetometer/st_magn.h @@ -44,6 +44,7 @@ static inline int st_magn_allocate_ring(struct iio_dev *indio_dev) static inline void st_magn_deallocate_ring(struct iio_dev *indio_dev) { } +#define ST_MAGN_TRIGGER_SET_STATE NULL #endif /* CONFIG_IIO_BUFFER */ #endif /* ST_MAGN_H */ diff --git a/drivers/iio/pressure/mpl115.c b/drivers/iio/pressure/mpl115.c index f5ecd6e19f5d..a0d7deeac62f 100644 --- a/drivers/iio/pressure/mpl115.c +++ b/drivers/iio/pressure/mpl115.c @@ -117,7 +117,7 @@ static int mpl115_read_raw(struct iio_dev *indio_dev, *val = ret >> 6; return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: - *val = 605; + *val = -605; *val2 = 750000; return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_SCALE: diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 0a26dd6d9b19..d6d2b3582910 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -782,11 +782,11 @@ static void cm_enter_timewait(struct cm_id_private *cm_id_priv) wait_time = cm_convert_to_ms(cm_id_priv->av.timeout); /* Check if the device started its remove_one */ - spin_lock_irq(&cm.lock); + spin_lock_irqsave(&cm.lock, flags); if (!cm_dev->going_down) queue_delayed_work(cm.wq, &cm_id_priv->timewait_info->work.work, msecs_to_jiffies(wait_time)); - spin_unlock_irq(&cm.lock); + spin_unlock_irqrestore(&cm.lock, flags); cm_id_priv->timewait_info = NULL; } diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 2d762a2ecd81..17a15c56028c 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -453,7 +453,7 @@ static inline int cma_validate_port(struct ib_device *device, u8 port, if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port)) return ret; - if (dev_type == ARPHRD_ETHER) + if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) ndev = dev_get_by_index(&init_net, bound_if_index); ret = ib_find_cached_gid_by_port(device, gid, port, ndev, NULL); diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 6b4e8a008bc0..564adf3116e8 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -48,6 +48,7 @@ #include <asm/uaccess.h> +#include <rdma/ib.h> #include <rdma/ib_cm.h> #include <rdma/ib_user_cm.h> #include <rdma/ib_marshall.h> @@ -1103,6 +1104,9 @@ static ssize_t ib_ucm_write(struct file *filp, const char __user *buf, struct ib_ucm_cmd_hdr hdr; ssize_t result; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (len < sizeof(hdr)) return -EINVAL; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 8b5a934e1133..886f61ea6cc7 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1574,6 +1574,9 @@ static ssize_t ucma_write(struct file *filp, const char __user *buf, struct rdma_ucm_cmd_hdr hdr; ssize_t ret; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (len < sizeof(hdr)) return -EINVAL; diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index e3ef28861be6..24f3ca2c4ad7 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -48,6 +48,8 @@ #include <asm/uaccess.h> +#include <rdma/ib.h> + #include "uverbs.h" MODULE_AUTHOR("Roland Dreier"); @@ -682,6 +684,9 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, int srcu_key; ssize_t ret; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (count < sizeof hdr) return -EINVAL; diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index cb78b1e9bcd9..f504ba73e5dc 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -149,7 +149,7 @@ static int iwch_l2t_send(struct t3cdev *tdev, struct sk_buff *skb, struct l2t_en error = l2t_send(tdev, skb, l2e); if (error < 0) kfree_skb(skb); - return error; + return error < 0 ? error : 0; } int iwch_cxgb3_ofld_send(struct t3cdev *tdev, struct sk_buff *skb) @@ -165,7 +165,7 @@ int iwch_cxgb3_ofld_send(struct t3cdev *tdev, struct sk_buff *skb) error = cxgb3_ofld_send(tdev, skb); if (error < 0) kfree_skb(skb); - return error; + return error < 0 ? error : 0; } static void release_tid(struct t3cdev *tdev, u32 hwtid, struct sk_buff *skb) diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index de9cd6901752..bc147582bed9 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -162,7 +162,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, cq->bar2_va = c4iw_bar2_addrs(rdev, cq->cqid, T4_BAR2_QTYPE_INGRESS, &cq->bar2_qid, user ? &cq->bar2_pa : NULL); - if (user && !cq->bar2_va) { + if (user && !cq->bar2_pa) { pr_warn(MOD "%s: cqid %u not in BAR2 range.\n", pci_name(rdev->lldi.pdev), cq->cqid); ret = -EINVAL; diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index aa515afee724..53aa7515f542 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -185,6 +185,10 @@ void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid, if (pbar2_pa) *pbar2_pa = (rdev->bar2_pa + bar2_qoffset) & PAGE_MASK; + + if (is_t4(rdev->lldi.adapter_type)) + return NULL; + return rdev->bar2_kva + bar2_qoffset; } @@ -270,7 +274,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, /* * User mode must have bar2 access. */ - if (user && (!wq->sq.bar2_va || !wq->rq.bar2_va)) { + if (user && (!wq->sq.bar2_pa || !wq->rq.bar2_pa)) { pr_warn(MOD "%s: sqid %u or rqid %u not in BAR2 range.\n", pci_name(rdev->lldi.pdev), wq->sq.qid, wq->rq.qid); goto free_dma; diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 3dfd287256d6..92ddae101ecc 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -756,7 +756,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int uninitialized_var(index); int uninitialized_var(inlen); int cqe_size; - int irqn; + unsigned int irqn; int eqn; int err; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 7e97cb55a6bf..721d63f5b461 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -273,9 +273,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, sizeof(struct mlx5_wqe_ctrl_seg)) / sizeof(struct mlx5_wqe_data_seg); props->max_sge = min(max_rq_sg, max_sq_sg); - props->max_sge_rd = props->max_sge; + props->max_sge_rd = MLX5_MAX_SGE_RD; props->max_cq = 1 << MLX5_CAP_GEN(mdev, log_max_cq); - props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_eq_sz)) - 1; + props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_cq_sz)) - 1; props->max_mr = 1 << MLX5_CAP_GEN(mdev, log_max_mkey); props->max_pd = 1 << MLX5_CAP_GEN(mdev, log_max_pd); props->max_qp_rd_atom = 1 << MLX5_CAP_GEN(mdev, log_max_ra_req_qp); diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index e449e394963f..24f4a782e0f4 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -45,6 +45,8 @@ #include <linux/export.h> #include <linux/uio.h> +#include <rdma/ib.h> + #include "qib.h" #include "qib_common.h" #include "qib_user_sdma.h" @@ -2067,6 +2069,9 @@ static ssize_t qib_write(struct file *fp, const char __user *data, ssize_t ret = 0; void *dest; + if (WARN_ON_ONCE(!ib_safe_file_access(fp))) + return -EACCES; + if (count < sizeof(cmd.type)) { ret = -EINVAL; goto bail; diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 40f85bb3e0d3..3eff35c2d453 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -100,9 +100,10 @@ static u32 credit_table[31] = { 32768 /* 1E */ }; -static void get_map_page(struct qib_qpn_table *qpt, struct qpn_map *map) +static void get_map_page(struct qib_qpn_table *qpt, struct qpn_map *map, + gfp_t gfp) { - unsigned long page = get_zeroed_page(GFP_KERNEL); + unsigned long page = get_zeroed_page(gfp); /* * Free the page if someone raced with us installing it. @@ -121,7 +122,7 @@ static void get_map_page(struct qib_qpn_table *qpt, struct qpn_map *map) * zero/one for QP type IB_QPT_SMI/IB_QPT_GSI. */ static int alloc_qpn(struct qib_devdata *dd, struct qib_qpn_table *qpt, - enum ib_qp_type type, u8 port) + enum ib_qp_type type, u8 port, gfp_t gfp) { u32 i, offset, max_scan, qpn; struct qpn_map *map; @@ -151,7 +152,7 @@ static int alloc_qpn(struct qib_devdata *dd, struct qib_qpn_table *qpt, max_scan = qpt->nmaps - !offset; for (i = 0;;) { if (unlikely(!map->page)) { - get_map_page(qpt, map); + get_map_page(qpt, map, gfp); if (unlikely(!map->page)) break; } @@ -983,13 +984,21 @@ struct ib_qp *qib_create_qp(struct ib_pd *ibpd, size_t sz; size_t sg_list_sz; struct ib_qp *ret; + gfp_t gfp; + if (init_attr->cap.max_send_sge > ib_qib_max_sges || init_attr->cap.max_send_wr > ib_qib_max_qp_wrs || - init_attr->create_flags) { - ret = ERR_PTR(-EINVAL); - goto bail; - } + init_attr->create_flags & ~(IB_QP_CREATE_USE_GFP_NOIO)) + return ERR_PTR(-EINVAL); + + /* GFP_NOIO is applicable in RC QPs only */ + if (init_attr->create_flags & IB_QP_CREATE_USE_GFP_NOIO && + init_attr->qp_type != IB_QPT_RC) + return ERR_PTR(-EINVAL); + + gfp = init_attr->create_flags & IB_QP_CREATE_USE_GFP_NOIO ? + GFP_NOIO : GFP_KERNEL; /* Check receive queue parameters if no SRQ is specified. */ if (!init_attr->srq) { @@ -1021,7 +1030,8 @@ struct ib_qp *qib_create_qp(struct ib_pd *ibpd, sz = sizeof(struct qib_sge) * init_attr->cap.max_send_sge + sizeof(struct qib_swqe); - swq = vmalloc((init_attr->cap.max_send_wr + 1) * sz); + swq = __vmalloc((init_attr->cap.max_send_wr + 1) * sz, + gfp, PAGE_KERNEL); if (swq == NULL) { ret = ERR_PTR(-ENOMEM); goto bail; @@ -1037,13 +1047,13 @@ struct ib_qp *qib_create_qp(struct ib_pd *ibpd, } else if (init_attr->cap.max_recv_sge > 1) sg_list_sz = sizeof(*qp->r_sg_list) * (init_attr->cap.max_recv_sge - 1); - qp = kzalloc(sz + sg_list_sz, GFP_KERNEL); + qp = kzalloc(sz + sg_list_sz, gfp); if (!qp) { ret = ERR_PTR(-ENOMEM); goto bail_swq; } RCU_INIT_POINTER(qp->next, NULL); - qp->s_hdr = kzalloc(sizeof(*qp->s_hdr), GFP_KERNEL); + qp->s_hdr = kzalloc(sizeof(*qp->s_hdr), gfp); if (!qp->s_hdr) { ret = ERR_PTR(-ENOMEM); goto bail_qp; @@ -1058,8 +1068,16 @@ struct ib_qp *qib_create_qp(struct ib_pd *ibpd, qp->r_rq.max_sge = init_attr->cap.max_recv_sge; sz = (sizeof(struct ib_sge) * qp->r_rq.max_sge) + sizeof(struct qib_rwqe); - qp->r_rq.wq = vmalloc_user(sizeof(struct qib_rwq) + - qp->r_rq.size * sz); + if (gfp != GFP_NOIO) + qp->r_rq.wq = vmalloc_user( + sizeof(struct qib_rwq) + + qp->r_rq.size * sz); + else + qp->r_rq.wq = __vmalloc( + sizeof(struct qib_rwq) + + qp->r_rq.size * sz, + gfp, PAGE_KERNEL); + if (!qp->r_rq.wq) { ret = ERR_PTR(-ENOMEM); goto bail_qp; @@ -1090,7 +1108,7 @@ struct ib_qp *qib_create_qp(struct ib_pd *ibpd, dev = to_idev(ibpd->device); dd = dd_from_dev(dev); err = alloc_qpn(dd, &dev->qpn_table, init_attr->qp_type, - init_attr->port_num); + init_attr->port_num, gfp); if (err < 0) { ret = ERR_PTR(err); vfree(qp->r_rq.wq); diff --git a/drivers/infiniband/hw/qib/qib_verbs_mcast.c b/drivers/infiniband/hw/qib/qib_verbs_mcast.c index f8ea069a3eaf..b2fb5286dbd9 100644 --- a/drivers/infiniband/hw/qib/qib_verbs_mcast.c +++ b/drivers/infiniband/hw/qib/qib_verbs_mcast.c @@ -286,15 +286,13 @@ int qib_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) struct qib_ibdev *dev = to_idev(ibqp->device); struct qib_ibport *ibp = to_iport(ibqp->device, qp->port_num); struct qib_mcast *mcast = NULL; - struct qib_mcast_qp *p, *tmp; + struct qib_mcast_qp *p, *tmp, *delp = NULL; struct rb_node *n; int last = 0; int ret; - if (ibqp->qp_num <= 1 || qp->state == IB_QPS_RESET) { - ret = -EINVAL; - goto bail; - } + if (ibqp->qp_num <= 1 || qp->state == IB_QPS_RESET) + return -EINVAL; spin_lock_irq(&ibp->lock); @@ -303,8 +301,7 @@ int qib_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) while (1) { if (n == NULL) { spin_unlock_irq(&ibp->lock); - ret = -EINVAL; - goto bail; + return -EINVAL; } mcast = rb_entry(n, struct qib_mcast, rb_node); @@ -328,6 +325,7 @@ int qib_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) */ list_del_rcu(&p->list); mcast->n_attached--; + delp = p; /* If this was the last attached QP, remove the GID too. */ if (list_empty(&mcast->qp_list)) { @@ -338,15 +336,16 @@ int qib_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) } spin_unlock_irq(&ibp->lock); + /* QP not attached */ + if (!delp) + return -EINVAL; + /* + * Wait for any list walkers to finish before freeing the + * list element. + */ + wait_event(mcast->wait, atomic_read(&mcast->refcount) <= 1); + qib_mcast_qp_free(delp); - if (p) { - /* - * Wait for any list walkers to finish before freeing the - * list element. - */ - wait_event(mcast->wait, atomic_read(&mcast->refcount) <= 1); - qib_mcast_qp_free(p); - } if (last) { atomic_dec(&mcast->refcount); wait_event(mcast->wait, !atomic_read(&mcast->refcount)); @@ -355,11 +354,7 @@ int qib_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) dev->n_mcast_grps_allocated--; spin_unlock_irq(&dev->n_mcast_grps_lock); } - - ret = 0; - -bail: - return ret; + return 0; } int qib_mcast_tree_empty(struct qib_ibport *ibp) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index f357ca67a41c..87799de90a1d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -456,7 +456,10 @@ out_locked: return status; } -static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) +/* + * Caller must hold 'priv->lock' + */ +static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ib_sa_multicast *multicast; @@ -466,6 +469,10 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) ib_sa_comp_mask comp_mask; int ret = 0; + if (!priv->broadcast || + !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) + return -EINVAL; + ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw); rec.mgid = mcast->mcmember.mgid; @@ -525,20 +532,23 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) rec.join_state = 4; #endif } + spin_unlock_irq(&priv->lock); multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, &rec, comp_mask, GFP_KERNEL, ipoib_mcast_join_complete, mcast); + spin_lock_irq(&priv->lock); if (IS_ERR(multicast)) { ret = PTR_ERR(multicast); ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret); - spin_lock_irq(&priv->lock); /* Requeue this join task with a backoff delay */ __ipoib_mcast_schedule_join_thread(priv, mcast, 1); clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); spin_unlock_irq(&priv->lock); complete(&mcast->done); + spin_lock_irq(&priv->lock); } + return 0; } void ipoib_mcast_join_task(struct work_struct *work) @@ -620,9 +630,10 @@ void ipoib_mcast_join_task(struct work_struct *work) /* Found the next unjoined group */ init_completion(&mcast->done); set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - spin_unlock_irq(&priv->lock); - ipoib_mcast_join(dev, mcast); - spin_lock_irq(&priv->lock); + if (ipoib_mcast_join(dev, mcast)) { + spin_unlock_irq(&priv->lock); + return; + } } else if (!delay_until || time_before(mcast->delay_until, delay_until)) delay_until = mcast->delay_until; @@ -641,10 +652,9 @@ out: if (mcast) { init_completion(&mcast->done); set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + ipoib_mcast_join(dev, mcast); } spin_unlock_irq(&priv->lock); - if (mcast) - ipoib_mcast_join(dev, mcast); } int ipoib_mcast_start_thread(struct net_device *dev) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 8a51c3b5d657..b0edb66a291b 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -66,6 +66,7 @@ isert_rdma_accept(struct isert_conn *isert_conn); struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np); static void isert_release_work(struct work_struct *work); +static void isert_wait4flush(struct isert_conn *isert_conn); static inline bool isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd) @@ -815,12 +816,31 @@ isert_put_conn(struct isert_conn *isert_conn) kref_put(&isert_conn->kref, isert_release_kref); } +static void +isert_handle_unbound_conn(struct isert_conn *isert_conn) +{ + struct isert_np *isert_np = isert_conn->cm_id->context; + + mutex_lock(&isert_np->mutex); + if (!list_empty(&isert_conn->node)) { + /* + * This means iscsi doesn't know this connection + * so schedule a cleanup ourselves + */ + list_del_init(&isert_conn->node); + isert_put_conn(isert_conn); + complete(&isert_conn->wait); + queue_work(isert_release_wq, &isert_conn->release_work); + } + mutex_unlock(&isert_np->mutex); +} + /** * isert_conn_terminate() - Initiate connection termination * @isert_conn: isert connection struct * * Notes: - * In case the connection state is FULL_FEATURE, move state + * In case the connection state is BOUND, move state * to TEMINATING and start teardown sequence (rdma_disconnect). * In case the connection state is UP, complete flush as well. * @@ -832,23 +852,19 @@ isert_conn_terminate(struct isert_conn *isert_conn) { int err; - switch (isert_conn->state) { - case ISER_CONN_TERMINATING: - break; - case ISER_CONN_UP: - case ISER_CONN_FULL_FEATURE: /* FALLTHRU */ - isert_info("Terminating conn %p state %d\n", - isert_conn, isert_conn->state); - isert_conn->state = ISER_CONN_TERMINATING; - err = rdma_disconnect(isert_conn->cm_id); - if (err) - isert_warn("Failed rdma_disconnect isert_conn %p\n", - isert_conn); - break; - default: - isert_warn("conn %p teminating in state %d\n", - isert_conn, isert_conn->state); - } + if (isert_conn->state >= ISER_CONN_TERMINATING) + return; + + isert_info("Terminating conn %p state %d\n", + isert_conn, isert_conn->state); + isert_conn->state = ISER_CONN_TERMINATING; + err = rdma_disconnect(isert_conn->cm_id); + if (err) + isert_warn("Failed rdma_disconnect isert_conn %p\n", + isert_conn); + + isert_info("conn %p completing wait\n", isert_conn); + complete(&isert_conn->wait); } static int @@ -882,35 +898,27 @@ static int isert_disconnected_handler(struct rdma_cm_id *cma_id, enum rdma_cm_event_type event) { - struct isert_np *isert_np = cma_id->context; - struct isert_conn *isert_conn; - bool terminating = false; - - if (isert_np->cm_id == cma_id) - return isert_np_cma_handler(cma_id->context, event); - - isert_conn = cma_id->qp->qp_context; + struct isert_conn *isert_conn = cma_id->qp->qp_context; mutex_lock(&isert_conn->mutex); - terminating = (isert_conn->state == ISER_CONN_TERMINATING); - isert_conn_terminate(isert_conn); - mutex_unlock(&isert_conn->mutex); - - isert_info("conn %p completing wait\n", isert_conn); - complete(&isert_conn->wait); - - if (terminating) - goto out; - - mutex_lock(&isert_np->mutex); - if (!list_empty(&isert_conn->node)) { - list_del_init(&isert_conn->node); - isert_put_conn(isert_conn); - queue_work(isert_release_wq, &isert_conn->release_work); + switch (isert_conn->state) { + case ISER_CONN_TERMINATING: + break; + case ISER_CONN_UP: + isert_conn_terminate(isert_conn); + isert_wait4flush(isert_conn); + isert_handle_unbound_conn(isert_conn); + break; + case ISER_CONN_BOUND: + case ISER_CONN_FULL_FEATURE: /* FALLTHRU */ + iscsit_cause_connection_reinstatement(isert_conn->conn, 0); + break; + default: + isert_warn("conn %p teminating in state %d\n", + isert_conn, isert_conn->state); } - mutex_unlock(&isert_np->mutex); + mutex_unlock(&isert_conn->mutex); -out: return 0; } @@ -929,12 +937,16 @@ isert_connect_error(struct rdma_cm_id *cma_id) static int isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { + struct isert_np *isert_np = cma_id->context; int ret = 0; isert_info("%s (%d): status %d id %p np %p\n", rdma_event_msg(event->event), event->event, event->status, cma_id, cma_id->context); + if (isert_np->cm_id == cma_id) + return isert_np_cma_handler(cma_id->context, event->event); + switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: ret = isert_connect_request(cma_id, event); @@ -980,13 +992,10 @@ isert_post_recvm(struct isert_conn *isert_conn, u32 count) rx_wr--; rx_wr->next = NULL; /* mark end of work requests list */ - isert_conn->post_recv_buf_count += count; ret = ib_post_recv(isert_conn->qp, isert_conn->rx_wr, &rx_wr_failed); - if (ret) { + if (ret) isert_err("ib_post_recv() failed with ret: %d\n", ret); - isert_conn->post_recv_buf_count -= count; - } return ret; } @@ -1002,12 +1011,9 @@ isert_post_recv(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc) rx_wr.num_sge = 1; rx_wr.next = NULL; - isert_conn->post_recv_buf_count++; ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_failed); - if (ret) { + if (ret) isert_err("ib_post_recv() failed with ret: %d\n", ret); - isert_conn->post_recv_buf_count--; - } return ret; } @@ -1120,12 +1126,9 @@ isert_rdma_post_recvl(struct isert_conn *isert_conn) rx_wr.sg_list = &sge; rx_wr.num_sge = 1; - isert_conn->post_recv_buf_count++; ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_fail); - if (ret) { + if (ret) isert_err("ib_post_recv() failed: %d\n", ret); - isert_conn->post_recv_buf_count--; - } return ret; } @@ -1620,7 +1623,6 @@ isert_rcv_completion(struct iser_rx_desc *desc, ib_dma_sync_single_for_device(ib_dev, rx_dma, rx_buflen, DMA_FROM_DEVICE); - isert_conn->post_recv_buf_count--; } static int @@ -2035,7 +2037,8 @@ is_isert_tx_desc(struct isert_conn *isert_conn, void *wr_id) void *start = isert_conn->rx_descs; int len = ISERT_QP_MAX_RECV_DTOS * sizeof(*isert_conn->rx_descs); - if (wr_id >= start && wr_id < start + len) + if ((wr_id >= start && wr_id < start + len) || + (wr_id == isert_conn->login_req_buf)) return false; return true; @@ -2059,10 +2062,6 @@ isert_cq_comp_err(struct isert_conn *isert_conn, struct ib_wc *wc) isert_unmap_tx_desc(desc, ib_dev); else isert_completion_put(desc, isert_cmd, ib_dev, true); - } else { - isert_conn->post_recv_buf_count--; - if (!isert_conn->post_recv_buf_count) - iscsit_cause_connection_reinstatement(isert_conn->conn, 0); } } @@ -3193,6 +3192,7 @@ accept_wait: conn->context = isert_conn; isert_conn->conn = conn; + isert_conn->state = ISER_CONN_BOUND; isert_set_conn_info(np, conn, isert_conn); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index 3d7fbc47c343..1874d21daee0 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -50,6 +50,7 @@ enum iser_ib_op_code { enum iser_conn_state { ISER_CONN_INIT, ISER_CONN_UP, + ISER_CONN_BOUND, ISER_CONN_FULL_FEATURE, ISER_CONN_TERMINATING, ISER_CONN_DOWN, @@ -144,7 +145,6 @@ struct isert_device; struct isert_conn { enum iser_conn_state state; - int post_recv_buf_count; u32 responder_resources; u32 initiator_depth; bool pi_support; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 2e2fe818ca9f..eaabf3125846 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1737,47 +1737,6 @@ send_sense: return -1; } -/** - * srpt_rx_mgmt_fn_tag() - Process a task management function by tag. - * @ch: RDMA channel of the task management request. - * @fn: Task management function to perform. - * @req_tag: Tag of the SRP task management request. - * @mgmt_ioctx: I/O context of the task management request. - * - * Returns zero if the target core will process the task management - * request asynchronously. - * - * Note: It is assumed that the initiator serializes tag-based task management - * requests. - */ -static int srpt_rx_mgmt_fn_tag(struct srpt_send_ioctx *ioctx, u64 tag) -{ - struct srpt_device *sdev; - struct srpt_rdma_ch *ch; - struct srpt_send_ioctx *target; - int ret, i; - - ret = -EINVAL; - ch = ioctx->ch; - BUG_ON(!ch); - BUG_ON(!ch->sport); - sdev = ch->sport->sdev; - BUG_ON(!sdev); - spin_lock_irq(&sdev->spinlock); - for (i = 0; i < ch->rq_size; ++i) { - target = ch->ioctx_ring[i]; - if (target->cmd.se_lun == ioctx->cmd.se_lun && - target->cmd.tag == tag && - srpt_get_cmd_state(target) != SRPT_STATE_DONE) { - ret = 0; - /* now let the target core abort &target->cmd; */ - break; - } - } - spin_unlock_irq(&sdev->spinlock); - return ret; -} - static int srp_tmr_to_tcm(int fn) { switch (fn) { @@ -1812,7 +1771,6 @@ static void srpt_handle_tsk_mgmt(struct srpt_rdma_ch *ch, struct se_cmd *cmd; struct se_session *sess = ch->sess; uint64_t unpacked_lun; - uint32_t tag = 0; int tcm_tmr; int rc; @@ -1828,25 +1786,10 @@ static void srpt_handle_tsk_mgmt(struct srpt_rdma_ch *ch, srpt_set_cmd_state(send_ioctx, SRPT_STATE_MGMT); send_ioctx->cmd.tag = srp_tsk->tag; tcm_tmr = srp_tmr_to_tcm(srp_tsk->tsk_mgmt_func); - if (tcm_tmr < 0) { - send_ioctx->cmd.se_tmr_req->response = - TMR_TASK_MGMT_FUNCTION_NOT_SUPPORTED; - goto fail; - } unpacked_lun = srpt_unpack_lun((uint8_t *)&srp_tsk->lun, sizeof(srp_tsk->lun)); - - if (srp_tsk->tsk_mgmt_func == SRP_TSK_ABORT_TASK) { - rc = srpt_rx_mgmt_fn_tag(send_ioctx, srp_tsk->task_tag); - if (rc < 0) { - send_ioctx->cmd.se_tmr_req->response = - TMR_TASK_DOES_NOT_EXIST; - goto fail; - } - tag = srp_tsk->task_tag; - } rc = target_submit_tmr(&send_ioctx->cmd, sess, NULL, unpacked_lun, - srp_tsk, tcm_tmr, GFP_KERNEL, tag, + srp_tsk, tcm_tmr, GFP_KERNEL, srp_tsk->task_tag, TARGET_SCF_ACK_KREF); if (rc != 0) { send_ioctx->cmd.se_tmr_req->response = TMR_FUNCTION_REJECTED; diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c index cfd58e87da26..1c5914cae853 100644 --- a/drivers/input/misc/ati_remote2.c +++ b/drivers/input/misc/ati_remote2.c @@ -817,26 +817,49 @@ static int ati_remote2_probe(struct usb_interface *interface, const struct usb_d ar2->udev = udev; + /* Sanity check, first interface must have an endpoint */ + if (alt->desc.bNumEndpoints < 1 || !alt->endpoint) { + dev_err(&interface->dev, + "%s(): interface 0 must have an endpoint\n", __func__); + r = -ENODEV; + goto fail1; + } ar2->intf[0] = interface; ar2->ep[0] = &alt->endpoint[0].desc; + /* Sanity check, the device must have two interfaces */ ar2->intf[1] = usb_ifnum_to_if(udev, 1); + if ((udev->actconfig->desc.bNumInterfaces < 2) || !ar2->intf[1]) { + dev_err(&interface->dev, "%s(): need 2 interfaces, found %d\n", + __func__, udev->actconfig->desc.bNumInterfaces); + r = -ENODEV; + goto fail1; + } + r = usb_driver_claim_interface(&ati_remote2_driver, ar2->intf[1], ar2); if (r) goto fail1; + + /* Sanity check, second interface must have an endpoint */ alt = ar2->intf[1]->cur_altsetting; + if (alt->desc.bNumEndpoints < 1 || !alt->endpoint) { + dev_err(&interface->dev, + "%s(): interface 1 must have an endpoint\n", __func__); + r = -ENODEV; + goto fail2; + } ar2->ep[1] = &alt->endpoint[0].desc; r = ati_remote2_urb_init(ar2); if (r) - goto fail2; + goto fail3; ar2->channel_mask = channel_mask; ar2->mode_mask = mode_mask; r = ati_remote2_setup(ar2, ar2->channel_mask); if (r) - goto fail2; + goto fail3; usb_make_path(udev, ar2->phys, sizeof(ar2->phys)); strlcat(ar2->phys, "/input0", sizeof(ar2->phys)); @@ -845,11 +868,11 @@ static int ati_remote2_probe(struct usb_interface *interface, const struct usb_d r = sysfs_create_group(&udev->dev.kobj, &ati_remote2_attr_group); if (r) - goto fail2; + goto fail3; r = ati_remote2_input_init(ar2); if (r) - goto fail3; + goto fail4; usb_set_intfdata(interface, ar2); @@ -857,10 +880,11 @@ static int ati_remote2_probe(struct usb_interface *interface, const struct usb_d return 0; - fail3: + fail4: sysfs_remove_group(&udev->dev.kobj, &ati_remote2_attr_group); - fail2: + fail3: ati_remote2_urb_cleanup(ar2); + fail2: usb_driver_release_interface(&ati_remote2_driver, ar2->intf[1]); fail1: kfree(ar2); diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c index ac1fa5f44580..9c0ea36913b4 100644 --- a/drivers/input/misc/ims-pcu.c +++ b/drivers/input/misc/ims-pcu.c @@ -1663,6 +1663,8 @@ static int ims_pcu_parse_cdc_data(struct usb_interface *intf, struct ims_pcu *pc pcu->ctrl_intf = usb_ifnum_to_if(pcu->udev, union_desc->bMasterInterface0); + if (!pcu->ctrl_intf) + return -EINVAL; alt = pcu->ctrl_intf->cur_altsetting; pcu->ep_ctrl = &alt->endpoint[0].desc; @@ -1670,6 +1672,8 @@ static int ims_pcu_parse_cdc_data(struct usb_interface *intf, struct ims_pcu *pc pcu->data_intf = usb_ifnum_to_if(pcu->udev, union_desc->bSlaveInterface0); + if (!pcu->data_intf) + return -EINVAL; alt = pcu->data_intf->cur_altsetting; if (alt->desc.bNumEndpoints != 2) { diff --git a/drivers/input/misc/pmic8xxx-pwrkey.c b/drivers/input/misc/pmic8xxx-pwrkey.c index 3f02e0e03d12..67aab86048ad 100644 --- a/drivers/input/misc/pmic8xxx-pwrkey.c +++ b/drivers/input/misc/pmic8xxx-pwrkey.c @@ -353,7 +353,8 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev) if (of_property_read_u32(pdev->dev.of_node, "debounce", &kpd_delay)) kpd_delay = 15625; - if (kpd_delay > 62500 || kpd_delay == 0) { + /* Valid range of pwr key trigger delay is 1/64 sec to 2 seconds. */ + if (kpd_delay > USEC_PER_SEC * 2 || kpd_delay < USEC_PER_SEC / 64) { dev_err(&pdev->dev, "invalid power key trigger delay\n"); return -EINVAL; } @@ -385,8 +386,8 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev) pwr->name = "pmic8xxx_pwrkey"; pwr->phys = "pmic8xxx_pwrkey/input0"; - delay = (kpd_delay << 10) / USEC_PER_SEC; - delay = 1 + ilog2(delay); + delay = (kpd_delay << 6) / USEC_PER_SEC; + delay = ilog2(delay); err = regmap_read(regmap, PON_CNTL_1, &pon_cntl); if (err < 0) { diff --git a/drivers/input/misc/powermate.c b/drivers/input/misc/powermate.c index 63b539d3daba..84909a12ff36 100644 --- a/drivers/input/misc/powermate.c +++ b/drivers/input/misc/powermate.c @@ -307,6 +307,9 @@ static int powermate_probe(struct usb_interface *intf, const struct usb_device_i int error = -ENOMEM; interface = intf->cur_altsetting; + if (interface->desc.bNumEndpoints < 1) + return -EINVAL; + endpoint = &interface->endpoint[0].desc; if (!usb_endpoint_is_int_in(endpoint)) return -EIO; diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 537ebb0e193a..78f93cf68840 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1222,7 +1222,7 @@ static int elantech_set_input_params(struct psmouse *psmouse) input_set_abs_params(dev, ABS_TOOL_WIDTH, ETP_WMIN_V2, ETP_WMAX_V2, 0, 0); } - input_mt_init_slots(dev, 2, 0); + input_mt_init_slots(dev, 2, INPUT_MT_SEMI_MT); input_set_abs_params(dev, ABS_MT_POSITION_X, x_min, x_max, 0, 0); input_set_abs_params(dev, ABS_MT_POSITION_Y, y_min, y_max, 0, 0); break; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 6025eb430c0a..a41d8328c064 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -862,8 +862,9 @@ static void synaptics_report_ext_buttons(struct psmouse *psmouse, if (!SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap)) return; - /* Bug in FW 8.1, buttons are reported only when ExtBit is 1 */ - if (SYN_ID_FULL(priv->identity) == 0x801 && + /* Bug in FW 8.1 & 8.2, buttons are reported only when ExtBit is 1 */ + if ((SYN_ID_FULL(priv->identity) == 0x801 || + SYN_ID_FULL(priv->identity) == 0x802) && !((psmouse->packet[0] ^ psmouse->packet[3]) & 0x02)) return; diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c index e272f06258ce..a3f0f5a47490 100644 --- a/drivers/input/mouse/vmmouse.c +++ b/drivers/input/mouse/vmmouse.c @@ -458,8 +458,6 @@ int vmmouse_init(struct psmouse *psmouse) priv->abs_dev = abs_dev; psmouse->private = priv; - input_set_capability(rel_dev, EV_REL, REL_WHEEL); - /* Set up and register absolute device */ snprintf(priv->phys, sizeof(priv->phys), "%s/input1", psmouse->ps2dev.serio->phys); @@ -475,10 +473,6 @@ int vmmouse_init(struct psmouse *psmouse) abs_dev->id.version = psmouse->model; abs_dev->dev.parent = &psmouse->ps2dev.serio->dev; - error = input_register_device(priv->abs_dev); - if (error) - goto init_fail; - /* Set absolute device capabilities */ input_set_capability(abs_dev, EV_KEY, BTN_LEFT); input_set_capability(abs_dev, EV_KEY, BTN_RIGHT); @@ -488,6 +482,13 @@ int vmmouse_init(struct psmouse *psmouse) input_set_abs_params(abs_dev, ABS_X, 0, VMMOUSE_MAX_X, 0, 0); input_set_abs_params(abs_dev, ABS_Y, 0, VMMOUSE_MAX_Y, 0, 0); + error = input_register_device(priv->abs_dev); + if (error) + goto init_fail; + + /* Add wheel capability to the relative device */ + input_set_capability(rel_dev, EV_REL, REL_WHEEL); + psmouse->protocol_handler = vmmouse_process_byte; psmouse->disconnect = vmmouse_disconnect; psmouse->reconnect = vmmouse_reconnect; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index c11556563ef0..68f5f4a0f1e7 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -258,6 +258,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { }, }, { + /* Fujitsu Lifebook U745 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"), + }, + }, + { /* Fujitsu T70H */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c index 3a7f3a4a4396..7c18249d6c8e 100644 --- a/drivers/input/tablet/gtco.c +++ b/drivers/input/tablet/gtco.c @@ -858,6 +858,14 @@ static int gtco_probe(struct usb_interface *usbinterface, goto err_free_buf; } + /* Sanity check that a device has an endpoint */ + if (usbinterface->altsetting[0].desc.bNumEndpoints < 1) { + dev_err(&usbinterface->dev, + "Invalid number of endpoints\n"); + error = -EINVAL; + goto err_free_urb; + } + /* * The endpoint is always altsetting 0, we know this since we know * this device only has one interrupt endpoint @@ -879,7 +887,7 @@ static int gtco_probe(struct usb_interface *usbinterface, * HID report descriptor */ if (usb_get_extra_descriptor(usbinterface->cur_altsetting, - HID_DEVICE_TYPE, &hid_desc) != 0){ + HID_DEVICE_TYPE, &hid_desc) != 0) { dev_err(&usbinterface->dev, "Can't retrieve exta USB descriptor to get hid report descriptor length\n"); error = -EIO; diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 9bbadaaf6bc3..7b3845aa5983 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -370,8 +370,8 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload) point.coord_x = point.coord_y = 0; } - point.state = payload[9 * i + 5] & 0x03; - point.id = (payload[9 * i + 5] & 0xfc) >> 2; + point.state = payload[9 * i + 5] & 0x0f; + point.id = (payload[9 * i + 5] & 0xf0) >> 4; /* determine touch major, minor and orientation */ point.area_major = max(payload[9 * i + 6], diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 8b2be1e7714f..b9319b76a8a1 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -91,6 +91,7 @@ struct iommu_dev_data { struct list_head dev_data_list; /* For global dev_data_list */ struct protection_domain *domain; /* Domain the device is bound to */ u16 devid; /* PCI Device ID */ + u16 alias; /* Alias Device ID */ bool iommu_v2; /* Device can make use of IOMMUv2 */ bool passthrough; /* Device is identity mapped */ struct { @@ -125,6 +126,13 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom) return container_of(dom, struct protection_domain, domain); } +static inline u16 get_device_id(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + return PCI_DEVID(pdev->bus->number, pdev->devfn); +} + static struct iommu_dev_data *alloc_dev_data(u16 devid) { struct iommu_dev_data *dev_data; @@ -162,6 +170,68 @@ out_unlock: return dev_data; } +static int __last_alias(struct pci_dev *pdev, u16 alias, void *data) +{ + *(u16 *)data = alias; + return 0; +} + +static u16 get_alias(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + u16 devid, ivrs_alias, pci_alias; + + devid = get_device_id(dev); + ivrs_alias = amd_iommu_alias_table[devid]; + pci_for_each_dma_alias(pdev, __last_alias, &pci_alias); + + if (ivrs_alias == pci_alias) + return ivrs_alias; + + /* + * DMA alias showdown + * + * The IVRS is fairly reliable in telling us about aliases, but it + * can't know about every screwy device. If we don't have an IVRS + * reported alias, use the PCI reported alias. In that case we may + * still need to initialize the rlookup and dev_table entries if the + * alias is to a non-existent device. + */ + if (ivrs_alias == devid) { + if (!amd_iommu_rlookup_table[pci_alias]) { + amd_iommu_rlookup_table[pci_alias] = + amd_iommu_rlookup_table[devid]; + memcpy(amd_iommu_dev_table[pci_alias].data, + amd_iommu_dev_table[devid].data, + sizeof(amd_iommu_dev_table[pci_alias].data)); + } + + return pci_alias; + } + + pr_info("AMD-Vi: Using IVRS reported alias %02x:%02x.%d " + "for device %s[%04x:%04x], kernel reported alias " + "%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias), + PCI_FUNC(ivrs_alias), dev_name(dev), pdev->vendor, pdev->device, + PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias), + PCI_FUNC(pci_alias)); + + /* + * If we don't have a PCI DMA alias and the IVRS alias is on the same + * bus, then the IVRS table may know about a quirk that we don't. + */ + if (pci_alias == devid && + PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) { + pdev->dev_flags |= PCI_DEV_FLAGS_DMA_ALIAS_DEVFN; + pdev->dma_alias_devfn = ivrs_alias & 0xff; + pr_info("AMD-Vi: Added PCI DMA alias %02x.%d for %s\n", + PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias), + dev_name(dev)); + } + + return ivrs_alias; +} + static struct iommu_dev_data *find_dev_data(u16 devid) { struct iommu_dev_data *dev_data; @@ -174,13 +244,6 @@ static struct iommu_dev_data *find_dev_data(u16 devid) return dev_data; } -static inline u16 get_device_id(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - - return PCI_DEVID(pdev->bus->number, pdev->devfn); -} - static struct iommu_dev_data *get_dev_data(struct device *dev) { return dev->archdata.iommu; @@ -308,6 +371,8 @@ static int iommu_init_device(struct device *dev) if (!dev_data) return -ENOMEM; + dev_data->alias = get_alias(dev); + if (pci_iommuv2_capable(pdev)) { struct amd_iommu *iommu; @@ -328,7 +393,7 @@ static void iommu_ignore_device(struct device *dev) u16 devid, alias; devid = get_device_id(dev); - alias = amd_iommu_alias_table[devid]; + alias = get_alias(dev); memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry)); memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry)); @@ -1017,7 +1082,7 @@ static int device_flush_dte(struct iommu_dev_data *dev_data) int ret; iommu = amd_iommu_rlookup_table[dev_data->devid]; - alias = amd_iommu_alias_table[dev_data->devid]; + alias = dev_data->alias; ret = iommu_flush_dte(iommu, dev_data->devid); if (!ret && alias != dev_data->devid) @@ -1891,7 +1956,7 @@ static void do_attach(struct iommu_dev_data *dev_data, bool ats; iommu = amd_iommu_rlookup_table[dev_data->devid]; - alias = amd_iommu_alias_table[dev_data->devid]; + alias = dev_data->alias; ats = dev_data->ats.enabled; /* Update data structures */ @@ -1905,7 +1970,7 @@ static void do_attach(struct iommu_dev_data *dev_data, /* Update device table */ set_dte_entry(dev_data->devid, domain, ats); if (alias != dev_data->devid) - set_dte_entry(dev_data->devid, domain, ats); + set_dte_entry(alias, domain, ats); device_flush_dte(dev_data); } @@ -1925,7 +1990,7 @@ static void do_detach(struct iommu_dev_data *dev_data) return; iommu = amd_iommu_rlookup_table[dev_data->devid]; - alias = amd_iommu_alias_table[dev_data->devid]; + alias = dev_data->alias; /* decrease reference counters */ dev_data->domain->dev_iommu[iommu->index] -= 1; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 013bdfff2d4d..bf4959f4225b 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -228,6 +228,10 @@ static int amd_iommu_enable_interrupts(void); static int __init iommu_go_to_state(enum iommu_init_state state); static void init_device_table_dma(void); +static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu, + u8 bank, u8 cntr, u8 fxn, + u64 *value, bool is_write); + static inline void update_last_devid(u16 devid) { if (devid > amd_iommu_last_bdf) @@ -1016,6 +1020,34 @@ static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu) } /* + * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission) + * Workaround: + * BIOS should enable ATS write permission check by setting + * L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b + */ +static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu) +{ + u32 value; + + if ((boot_cpu_data.x86 != 0x15) || + (boot_cpu_data.x86_model < 0x30) || + (boot_cpu_data.x86_model > 0x3f)) + return; + + /* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */ + value = iommu_read_l2(iommu, 0x47); + + if (value & BIT(0)) + return; + + /* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */ + iommu_write_l2(iommu, 0x47, value | BIT(0)); + + pr_info("AMD-Vi: Applying ATS write check workaround for IOMMU at %s\n", + dev_name(&iommu->dev->dev)); +} + +/* * This function clues the initialization function for one IOMMU * together and also allocates the command buffer and programs the * hardware. It does NOT enable the IOMMU. This is done afterwards. @@ -1142,8 +1174,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu) amd_iommu_pc_present = true; /* Check if the performance counters can be written to */ - if ((0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val, true)) || - (0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val2, false)) || + if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) || + (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) || (val != val2)) { pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n"); amd_iommu_pc_present = false; @@ -1284,6 +1316,7 @@ static int iommu_init_pci(struct amd_iommu *iommu) } amd_iommu_erratum_746_workaround(iommu); + amd_iommu_ats_write_check_workaround(iommu); iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu, amd_iommu_groups, "ivhd%d", @@ -2283,22 +2316,15 @@ u8 amd_iommu_pc_get_max_counters(u16 devid) } EXPORT_SYMBOL(amd_iommu_pc_get_max_counters); -int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, +static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu, + u8 bank, u8 cntr, u8 fxn, u64 *value, bool is_write) { - struct amd_iommu *iommu; u32 offset; u32 max_offset_lim; - /* Make sure the IOMMU PC resource is available */ - if (!amd_iommu_pc_present) - return -ENODEV; - - /* Locate the iommu associated with the device ID */ - iommu = amd_iommu_rlookup_table[devid]; - /* Check for valid iommu and pc register indexing */ - if (WARN_ON((iommu == NULL) || (fxn > 0x28) || (fxn & 7))) + if (WARN_ON((fxn > 0x28) || (fxn & 7))) return -ENODEV; offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn); @@ -2322,3 +2348,16 @@ int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, return 0; } EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val); + +int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, + u64 *value, bool is_write) +{ + struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; + + /* Make sure the IOMMU PC resource is available */ + if (!amd_iommu_pc_present || iommu == NULL) + return -ENODEV; + + return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn, + value, is_write); +} diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 72d6182666cb..58f2fe687a24 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -403,7 +403,7 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents, unsigned int s_length = sg_dma_len(s); unsigned int s_dma_len = s->length; - s->offset = s_offset; + s->offset += s_offset; s->length = s_length; sg_dma_address(s) = dma_addr + s_offset; dma_addr += s_dma_len; @@ -422,7 +422,7 @@ static void __invalidate_sg(struct scatterlist *sg, int nents) for_each_sg(sg, s, nents, i) { if (sg_dma_address(s) != DMA_ERROR_CODE) - s->offset = sg_dma_address(s); + s->offset += sg_dma_address(s); if (sg_dma_len(s)) s->length = sg_dma_len(s); sg_dma_address(s) = DMA_ERROR_CODE; diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 80e3c176008e..3821c4786662 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -329,7 +329,8 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, /* Only care about add/remove events for physical functions */ if (pdev->is_virtfn) return NOTIFY_DONE; - if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE) + if (action != BUS_NOTIFY_ADD_DEVICE && + action != BUS_NOTIFY_REMOVED_DEVICE) return NOTIFY_DONE; info = dmar_alloc_pci_notify_info(pdev, action); @@ -339,7 +340,7 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, down_write(&dmar_global_lock); if (action == BUS_NOTIFY_ADD_DEVICE) dmar_pci_bus_add_dev(info); - else if (action == BUS_NOTIFY_DEL_DEVICE) + else if (action == BUS_NOTIFY_REMOVED_DEVICE) dmar_pci_bus_del_dev(info); up_write(&dmar_global_lock); @@ -1347,7 +1348,7 @@ void dmar_disable_qi(struct intel_iommu *iommu) raw_spin_lock_irqsave(&iommu->register_lock, flags); - sts = dmar_readq(iommu->reg + DMAR_GSTS_REG); + sts = readl(iommu->reg + DMAR_GSTS_REG); if (!(sts & DMA_GSTS_QIES)) goto end; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac7387686ddc..a2e1b7f14df2 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1489,7 +1489,7 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info) { struct pci_dev *pdev; - if (dev_is_pci(info->dev)) + if (!dev_is_pci(info->dev)) return; pdev = to_pci_dev(info->dev); @@ -4367,7 +4367,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) rmrru->devices_cnt); if(ret < 0) return ret; - } else if (info->event == BUS_NOTIFY_DEL_DEVICE) { + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { dmar_remove_dev_scope(info, rmrr->segment, rmrru->devices, rmrru->devices_cnt); } @@ -4387,7 +4387,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) break; else if(ret < 0) return ret; - } else if (info->event == BUS_NOTIFY_DEL_DEVICE) { + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { if (dmar_remove_dev_scope(info, atsr->segment, atsru->devices, atsru->devices_cnt)) break; diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 50464833d0b8..d9939fa9b588 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -249,12 +249,30 @@ static void intel_flush_pasid_dev(struct intel_svm *svm, struct intel_svm_dev *s static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct intel_svm *svm = container_of(mn, struct intel_svm, notifier); + struct intel_svm_dev *sdev; + /* This might end up being called from exit_mmap(), *before* the page + * tables are cleared. And __mmu_notifier_release() will delete us from + * the list of notifiers so that our invalidate_range() callback doesn't + * get called when the page tables are cleared. So we need to protect + * against hardware accessing those page tables. + * + * We do it by clearing the entry in the PASID table and then flushing + * the IOTLB and the PASID table caches. This might upset hardware; + * perhaps we'll want to point the PASID to a dummy PGD (like the zero + * page) so that we end up taking a fault that the hardware really + * *has* to handle gracefully without affecting other processes. + */ svm->iommu->pasid_table[svm->pasid].val = 0; + wmb(); + + rcu_read_lock(); + list_for_each_entry_rcu(sdev, &svm->devs, list) { + intel_flush_pasid_dev(svm, sdev, svm->pasid); + intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm); + } + rcu_read_unlock(); - /* There's no need to do any flush because we can't get here if there - * are any devices left anyway. */ - WARN_ON(!list_empty(&svm->devs)); } static const struct mmu_notifier_ops intel_mmuops = { @@ -379,7 +397,6 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ goto out; } iommu->pasid_table[svm->pasid].val = (u64)__pa(mm->pgd) | 1; - mm = NULL; } else iommu->pasid_table[svm->pasid].val = (u64)__pa(init_mm.pgd) | 1 | (1ULL << 11); wmb(); @@ -442,11 +459,11 @@ int intel_svm_unbind_mm(struct device *dev, int pasid) kfree_rcu(sdev, rcu); if (list_empty(&svm->devs)) { - mmu_notifier_unregister(&svm->notifier, svm->mm); idr_remove(&svm->iommu->pasid_idr, svm->pasid); if (svm->mm) - mmput(svm->mm); + mmu_notifier_unregister(&svm->notifier, svm->mm); + /* We mandate that no page faults may be outstanding * for the PASID when intel_svm_unbind_mm() is called. * If that is not obeyed, subtle errors will happen. @@ -507,6 +524,10 @@ static irqreturn_t prq_event_thread(int irq, void *d) struct intel_svm *svm = NULL; int head, tail, handled = 0; + /* Clear PPR bit before reading head/tail registers, to + * ensure that we get a new interrupt if needed. */ + writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG); + tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK; head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK; while (head != tail) { @@ -551,6 +572,9 @@ static irqreturn_t prq_event_thread(int irq, void *d) * any faults on kernel addresses. */ if (!svm->mm) goto bad_req; + /* If the mm is already defunct, don't handle faults. */ + if (!atomic_inc_not_zero(&svm->mm->mm_users)) + goto bad_req; down_read(&svm->mm->mmap_sem); vma = find_extend_vma(svm->mm, address); if (!vma || address < vma->vm_start) @@ -567,6 +591,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) result = QI_RESP_SUCCESS; invalid: up_read(&svm->mm->mmap_sem); + mmput(svm->mm); bad_req: /* Accounting for major/minor faults? */ rcu_read_lock(); diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 1fae1881648c..e9b241b1c9dd 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -629,7 +629,7 @@ static void iommu_disable_irq_remapping(struct intel_iommu *iommu) raw_spin_lock_irqsave(&iommu->register_lock, flags); - sts = dmar_readq(iommu->reg + DMAR_GSTS_REG); + sts = readl(iommu->reg + DMAR_GSTS_REG); if (!(sts & DMA_GSTS_IRES)) goto end; diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 7df97777662d..dad768caa9c5 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -405,17 +405,18 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl, arm_lpae_iopte *start, *end; unsigned long table_size; - /* Only leaf entries at the last level */ - if (lvl == ARM_LPAE_MAX_LEVELS - 1) - return; - if (lvl == ARM_LPAE_START_LVL(data)) table_size = data->pgd_size; else table_size = 1UL << data->pg_shift; start = ptep; - end = (void *)ptep + table_size; + + /* Only leaf entries at the last level */ + if (lvl == ARM_LPAE_MAX_LEVELS - 1) + end = ptep; + else + end = (void *)ptep + table_size; while (ptep != end) { arm_lpae_iopte pte = *ptep++; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 0e3b0092ec92..515bb8b80952 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -848,7 +848,8 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev) if (!group->default_domain) { group->default_domain = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA); - group->domain = group->default_domain; + if (!group->domain) + group->domain = group->default_domain; } ret = iommu_group_add_device(group, dev); diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c index b12a5d58546f..37199b9b2cfa 100644 --- a/drivers/irqchip/irq-atmel-aic-common.c +++ b/drivers/irqchip/irq-atmel-aic-common.c @@ -86,7 +86,7 @@ int aic_common_set_priority(int priority, unsigned *val) priority > AT91_AIC_IRQ_MAX_PRIORITY) return -EINVAL; - *val &= AT91_AIC_PRIOR; + *val &= ~AT91_AIC_PRIOR; *val |= priority; return 0; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index e23d1d18f9d6..a159529f9d53 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -597,11 +597,6 @@ static void its_unmask_irq(struct irq_data *d) lpi_set_config(d, true); } -static void its_eoi_irq(struct irq_data *d) -{ - gic_write_eoir(d->hwirq); -} - static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { @@ -638,7 +633,7 @@ static struct irq_chip its_irq_chip = { .name = "ITS", .irq_mask = its_mask_irq, .irq_unmask = its_unmask_irq, - .irq_eoi = its_eoi_irq, + .irq_eoi = irq_chip_eoi_parent, .irq_set_affinity = its_set_affinity, .irq_compose_msi_msg = its_irq_compose_msi_msg, }; diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index c22e2d40cb30..17304705f2cf 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -183,7 +183,7 @@ static void __iomem * __init icoll_init_iobase(struct device_node *np) void __iomem *icoll_base; icoll_base = of_io_request_and_map(np, 0, np->name); - if (!icoll_base) + if (IS_ERR(icoll_base)) panic("%s: unable to map resource", np->full_name); return icoll_base; } @@ -241,6 +241,7 @@ static int __init asm9260_of_init(struct device_node *np, writel(0, icoll_priv.intr + i); icoll_add_domain(np, ASM9260_NUM_IRQS); + set_handle_irq(icoll_handle_irq); return 0; } diff --git a/drivers/irqchip/irq-omap-intc.c b/drivers/irqchip/irq-omap-intc.c index 8587d0f8d8c0..f6cb1b8bb981 100644 --- a/drivers/irqchip/irq-omap-intc.c +++ b/drivers/irqchip/irq-omap-intc.c @@ -47,6 +47,7 @@ #define INTC_ILR0 0x0100 #define ACTIVEIRQ_MASK 0x7f /* omap2/3 active interrupt bits */ +#define SPURIOUSIRQ_MASK (0x1ffffff << 7) #define INTCPS_NR_ILR_REGS 128 #define INTCPS_NR_MIR_REGS 4 @@ -330,11 +331,35 @@ static int __init omap_init_irq(u32 base, struct device_node *node) static asmlinkage void __exception_irq_entry omap_intc_handle_irq(struct pt_regs *regs) { + extern unsigned long irq_err_count; u32 irqnr; irqnr = intc_readl(INTC_SIR); + + /* + * A spurious IRQ can result if interrupt that triggered the + * sorting is no longer active during the sorting (10 INTC + * functional clock cycles after interrupt assertion). Or a + * change in interrupt mask affected the result during sorting + * time. There is no special handling required except ignoring + * the SIR register value just read and retrying. + * See section 6.2.5 of AM335x TRM Literature Number: SPRUH73K + * + * Many a times, a spurious interrupt situation has been fixed + * by adding a flush for the posted write acking the IRQ in + * the device driver. Typically, this is going be the device + * driver whose interrupt was handled just before the spurious + * IRQ occurred. Pay attention to those device drivers if you + * run into hitting the spurious IRQ condition below. + */ + if (unlikely((irqnr & SPURIOUSIRQ_MASK) == SPURIOUSIRQ_MASK)) { + pr_err_once("%s: spurious irq!\n", __func__); + irq_err_count++; + omap_ack_irq(NULL); + return; + } + irqnr &= ACTIVEIRQ_MASK; - WARN_ONCE(!irqnr, "Spurious IRQ ?\n"); handle_domain_irq(domain, irqnr, regs); } diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c index 4ef178078e5b..1254e98f6b57 100644 --- a/drivers/irqchip/irq-sunxi-nmi.c +++ b/drivers/irqchip/irq-sunxi-nmi.c @@ -154,9 +154,9 @@ static int __init sunxi_sc_nmi_irq_init(struct device_node *node, gc = irq_get_domain_generic_chip(domain, 0); gc->reg_base = of_io_request_and_map(node, 0, of_node_full_name(node)); - if (!gc->reg_base) { + if (IS_ERR(gc->reg_base)) { pr_err("unable to map resource\n"); - ret = -ENOMEM; + ret = PTR_ERR(gc->reg_base); goto fail_irqd_remove; } diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 7913fdcfc849..d8b0ab6f3753 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -458,6 +458,18 @@ config DM_VERITY If unsure, say N. +config DM_VERITY_FEC + bool "Verity forward error correction support" + depends on DM_VERITY + select REED_SOLOMON + select REED_SOLOMON_DEC8 + ---help--- + Add forward error correction support to dm-verity. This option + makes it possible to use pre-generated error correction data to + recover from corrupted blocks. + + If unsure, say N. + config DM_SWITCH tristate "Switch target support (EXPERIMENTAL)" depends on BLK_DEV_DM diff --git a/drivers/md/Makefile b/drivers/md/Makefile index f34979cd141a..62a65764e8e0 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -16,6 +16,7 @@ dm-cache-mq-y += dm-cache-policy-mq.o dm-cache-smq-y += dm-cache-policy-smq.o dm-cache-cleaner-y += dm-cache-policy-cleaner.o dm-era-y += dm-era-target.o +dm-verity-y += dm-verity-target.o md-mod-y += md.o bitmap.o raid456-y += raid5.o raid5-cache.o @@ -63,3 +64,7 @@ obj-$(CONFIG_DM_LOG_WRITES) += dm-log-writes.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o endif + +ifeq ($(CONFIG_DM_VERITY_FEC),y) +dm-verity-objs += dm-verity-fec.o +endif diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 83392f856dfd..22b9e34ceb75 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1741,6 +1741,7 @@ static void bch_btree_gc(struct cache_set *c) do { ret = btree_root(gc_root, c, &op, &writes, &stats); closure_sync(&writes); + cond_resched(); if (ret && ret != -EAGAIN) pr_warn("gc failed!"); @@ -2162,8 +2163,10 @@ int bch_btree_insert_check_key(struct btree *b, struct btree_op *op, rw_lock(true, b, b->level); if (b->key.ptr[0] != btree_ptr || - b->seq != seq + 1) + b->seq != seq + 1) { + op->lock = b->level; goto out; + } } SET_KEY_PTRS(check_key, 1); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 679a093a3bf6..a296425a7270 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -685,6 +685,8 @@ static void bcache_device_link(struct bcache_device *d, struct cache_set *c, WARN(sysfs_create_link(&d->kobj, &c->kobj, "cache") || sysfs_create_link(&c->kobj, &d->kobj, d->name), "Couldn't create device <-> cache set symlinks"); + + clear_bit(BCACHE_DEV_UNLINK_DONE, &d->flags); } static void bcache_device_detach(struct bcache_device *d) @@ -847,8 +849,11 @@ void bch_cached_dev_run(struct cached_dev *dc) buf[SB_LABEL_SIZE] = '\0'; env[2] = kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf); - if (atomic_xchg(&dc->running, 1)) + if (atomic_xchg(&dc->running, 1)) { + kfree(env[1]); + kfree(env[2]); return; + } if (!d->c && BDEV_STATE(&dc->sb) != BDEV_STATE_NONE) { @@ -1010,8 +1015,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c) */ atomic_set(&dc->count, 1); - if (bch_cached_dev_writeback_start(dc)) + /* Block writeback thread, but spawn it */ + down_write(&dc->writeback_lock); + if (bch_cached_dev_writeback_start(dc)) { + up_write(&dc->writeback_lock); return -ENOMEM; + } if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) { bch_sectors_dirty_init(dc); @@ -1023,6 +1032,9 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c) bch_cached_dev_run(dc); bcache_device_link(&dc->disk, c, "bdev"); + /* Allow the writeback thread to proceed */ + up_write(&dc->writeback_lock); + pr_info("Caching %s as %s on set %pU", bdevname(dc->bdev, buf), dc->disk.disk->disk_name, dc->disk.c->sb.set_uuid); @@ -1361,6 +1373,9 @@ static void cache_set_flush(struct closure *cl) struct btree *b; unsigned i; + if (!c) + closure_return(cl); + bch_cache_accounting_destroy(&c->accounting); kobject_put(&c->internal); @@ -1823,11 +1838,12 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca) return 0; } -static void register_cache(struct cache_sb *sb, struct page *sb_page, +static int register_cache(struct cache_sb *sb, struct page *sb_page, struct block_device *bdev, struct cache *ca) { char name[BDEVNAME_SIZE]; - const char *err = "cannot allocate memory"; + const char *err = NULL; + int ret = 0; memcpy(&ca->sb, sb, sizeof(struct cache_sb)); ca->bdev = bdev; @@ -1842,27 +1858,35 @@ static void register_cache(struct cache_sb *sb, struct page *sb_page, if (blk_queue_discard(bdev_get_queue(ca->bdev))) ca->discard = CACHE_DISCARD(&ca->sb); - if (cache_alloc(sb, ca) != 0) + ret = cache_alloc(sb, ca); + if (ret != 0) goto err; - err = "error creating kobject"; - if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) - goto err; + if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) { + err = "error calling kobject_add"; + ret = -ENOMEM; + goto out; + } mutex_lock(&bch_register_lock); err = register_cache_set(ca); mutex_unlock(&bch_register_lock); - if (err) - goto err; + if (err) { + ret = -ENODEV; + goto out; + } pr_info("registered cache device %s", bdevname(bdev, name)); + out: kobject_put(&ca->kobj); - return; + err: - pr_notice("error opening %s: %s", bdevname(bdev, name), err); - goto out; + if (err) + pr_notice("error opening %s: %s", bdevname(bdev, name), err); + + return ret; } /* Global interfaces/init */ @@ -1933,6 +1957,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, else err = "device busy"; mutex_unlock(&bch_register_lock); + if (attr == &ksysfs_register_quiet) + goto out; } goto err; } @@ -1958,7 +1984,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (!ca) goto err_close; - register_cache(sb, sb_page, bdev, ca); + if (register_cache(sb, sb_page, bdev, ca) != 0) + goto err_close; } out: if (sb_page) @@ -1971,8 +1998,7 @@ out: err_close: blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); err: - if (attr != &ksysfs_register_quiet) - pr_info("error opening %s: %s", path, err); + pr_info("error opening %s: %s", path, err); ret = -EINVAL; goto out; } @@ -2066,8 +2092,10 @@ static int __init bcache_init(void) closure_debug_init(); bcache_major = register_blkdev(0, "bcache"); - if (bcache_major < 0) + if (bcache_major < 0) { + unregister_reboot_notifier(&reboot); return bcache_major; + } if (!(bcache_wq = create_workqueue("bcache")) || !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) || diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index b23f88d9f18c..b9346cd9cda1 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -323,6 +323,10 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode, static bool dirty_pred(struct keybuf *buf, struct bkey *k) { + struct cached_dev *dc = container_of(buf, struct cached_dev, writeback_keys); + + BUG_ON(KEY_INODE(k) != dc->disk.id); + return KEY_DIRTY(k); } @@ -372,11 +376,24 @@ next: } } +/* + * Returns true if we scanned the entire disk + */ static bool refill_dirty(struct cached_dev *dc) { struct keybuf *buf = &dc->writeback_keys; + struct bkey start = KEY(dc->disk.id, 0, 0); struct bkey end = KEY(dc->disk.id, MAX_KEY_OFFSET, 0); - bool searched_from_start = false; + struct bkey start_pos; + + /* + * make sure keybuf pos is inside the range for this disk - at bringup + * we might not be attached yet so this disk's inode nr isn't + * initialized then + */ + if (bkey_cmp(&buf->last_scanned, &start) < 0 || + bkey_cmp(&buf->last_scanned, &end) > 0) + buf->last_scanned = start; if (dc->partial_stripes_expensive) { refill_full_stripes(dc); @@ -384,14 +401,20 @@ static bool refill_dirty(struct cached_dev *dc) return false; } - if (bkey_cmp(&buf->last_scanned, &end) >= 0) { - buf->last_scanned = KEY(dc->disk.id, 0, 0); - searched_from_start = true; - } - + start_pos = buf->last_scanned; bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred); - return bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start; + if (bkey_cmp(&buf->last_scanned, &end) < 0) + return false; + + /* + * If we get to the end start scanning again from the beginning, and + * only scan up to where we initially started scanning from: + */ + buf->last_scanned = start; + bch_refill_keybuf(dc->disk.c, buf, &start_pos, dirty_pred); + + return bkey_cmp(&buf->last_scanned, &start_pos) >= 0; } static int bch_writeback_thread(void *arg) diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index 0a9dab187b79..073a042aed24 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -63,7 +63,8 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, static inline void bch_writeback_queue(struct cached_dev *dc) { - wake_up_process(dc->writeback_thread); + if (!IS_ERR_OR_NULL(dc->writeback_thread)) + wake_up_process(dc->writeback_thread); } static inline void bch_writeback_add(struct cached_dev *dc) diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index f6543f3a970f..3970cda10080 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -867,18 +867,55 @@ static int blocks_are_unmapped_or_clean(struct dm_cache_metadata *cmd, return 0; } -#define WRITE_LOCK(cmd) \ - if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) \ - return -EINVAL; \ - down_write(&cmd->root_lock) +static bool cmd_write_lock(struct dm_cache_metadata *cmd) +{ + down_write(&cmd->root_lock); + if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { + up_write(&cmd->root_lock); + return false; + } + return true; +} + +#define WRITE_LOCK(cmd) \ + do { \ + if (!cmd_write_lock((cmd))) \ + return -EINVAL; \ + } while(0) -#define WRITE_LOCK_VOID(cmd) \ - if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) \ - return; \ - down_write(&cmd->root_lock) +#define WRITE_LOCK_VOID(cmd) \ + do { \ + if (!cmd_write_lock((cmd))) \ + return; \ + } while(0) #define WRITE_UNLOCK(cmd) \ - up_write(&cmd->root_lock) + up_write(&(cmd)->root_lock) + +static bool cmd_read_lock(struct dm_cache_metadata *cmd) +{ + down_read(&cmd->root_lock); + if (cmd->fail_io) { + up_read(&cmd->root_lock); + return false; + } + return true; +} + +#define READ_LOCK(cmd) \ + do { \ + if (!cmd_read_lock((cmd))) \ + return -EINVAL; \ + } while(0) + +#define READ_LOCK_VOID(cmd) \ + do { \ + if (!cmd_read_lock((cmd))) \ + return; \ + } while(0) + +#define READ_UNLOCK(cmd) \ + up_read(&(cmd)->root_lock) int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size) { @@ -1015,22 +1052,20 @@ int dm_cache_load_discards(struct dm_cache_metadata *cmd, { int r; - down_read(&cmd->root_lock); + READ_LOCK(cmd); r = __load_discards(cmd, fn, context); - up_read(&cmd->root_lock); + READ_UNLOCK(cmd); return r; } -dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd) +int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result) { - dm_cblock_t r; - - down_read(&cmd->root_lock); - r = cmd->cache_blocks; - up_read(&cmd->root_lock); + READ_LOCK(cmd); + *result = cmd->cache_blocks; + READ_UNLOCK(cmd); - return r; + return 0; } static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock) @@ -1188,9 +1223,9 @@ int dm_cache_load_mappings(struct dm_cache_metadata *cmd, { int r; - down_read(&cmd->root_lock); + READ_LOCK(cmd); r = __load_mappings(cmd, policy, fn, context); - up_read(&cmd->root_lock); + READ_UNLOCK(cmd); return r; } @@ -1215,18 +1250,18 @@ static int __dump_mappings(struct dm_cache_metadata *cmd) void dm_cache_dump(struct dm_cache_metadata *cmd) { - down_read(&cmd->root_lock); + READ_LOCK_VOID(cmd); __dump_mappings(cmd); - up_read(&cmd->root_lock); + READ_UNLOCK(cmd); } int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd) { int r; - down_read(&cmd->root_lock); + READ_LOCK(cmd); r = cmd->changed; - up_read(&cmd->root_lock); + READ_UNLOCK(cmd); return r; } @@ -1276,9 +1311,9 @@ int dm_cache_set_dirty(struct dm_cache_metadata *cmd, void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd, struct dm_cache_statistics *stats) { - down_read(&cmd->root_lock); + READ_LOCK_VOID(cmd); *stats = cmd->stats; - up_read(&cmd->root_lock); + READ_UNLOCK(cmd); } void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd, @@ -1312,9 +1347,9 @@ int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd, { int r = -EINVAL; - down_read(&cmd->root_lock); + READ_LOCK(cmd); r = dm_sm_get_nr_free(cmd->metadata_sm, result); - up_read(&cmd->root_lock); + READ_UNLOCK(cmd); return r; } @@ -1324,9 +1359,9 @@ int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd, { int r = -EINVAL; - down_read(&cmd->root_lock); + READ_LOCK(cmd); r = dm_sm_get_nr_blocks(cmd->metadata_sm, result); - up_read(&cmd->root_lock); + READ_UNLOCK(cmd); return r; } @@ -1417,7 +1452,13 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy * int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result) { - return blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result); + int r; + + READ_LOCK(cmd); + r = blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result); + READ_UNLOCK(cmd); + + return r; } void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd) @@ -1440,10 +1481,7 @@ int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd) struct dm_block *sblock; struct cache_disk_superblock *disk_super; - /* - * We ignore fail_io for this function. - */ - down_write(&cmd->root_lock); + WRITE_LOCK(cmd); set_bit(NEEDS_CHECK, &cmd->flags); r = superblock_lock(cmd, &sblock); @@ -1458,19 +1496,17 @@ int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd) dm_bm_unlock(sblock); out: - up_write(&cmd->root_lock); + WRITE_UNLOCK(cmd); return r; } -bool dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd) +int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result) { - bool needs_check; + READ_LOCK(cmd); + *result = !!test_bit(NEEDS_CHECK, &cmd->flags); + READ_UNLOCK(cmd); - down_read(&cmd->root_lock); - needs_check = !!test_bit(NEEDS_CHECK, &cmd->flags); - up_read(&cmd->root_lock); - - return needs_check; + return 0; } int dm_cache_metadata_abort(struct dm_cache_metadata *cmd) diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h index 2ffee21f318d..8528744195e5 100644 --- a/drivers/md/dm-cache-metadata.h +++ b/drivers/md/dm-cache-metadata.h @@ -66,7 +66,7 @@ void dm_cache_metadata_close(struct dm_cache_metadata *cmd); * origin blocks to map to. */ int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size); -dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd); +int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result); int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd, sector_t discard_block_size, @@ -137,7 +137,7 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy * */ int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result); -bool dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd); +int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result); int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd); void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd); void dm_cache_metadata_set_read_write(struct dm_cache_metadata *cmd); diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 2fd4c8296144..bb9b92ebbf8e 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -118,14 +118,12 @@ static void iot_io_end(struct io_tracker *iot, sector_t len) */ struct dm_hook_info { bio_end_io_t *bi_end_io; - void *bi_private; }; static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio, bio_end_io_t *bi_end_io, void *bi_private) { h->bi_end_io = bio->bi_end_io; - h->bi_private = bio->bi_private; bio->bi_end_io = bi_end_io; bio->bi_private = bi_private; @@ -134,7 +132,6 @@ static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio, static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio) { bio->bi_end_io = h->bi_end_io; - bio->bi_private = h->bi_private; } /*----------------------------------------------------------------*/ @@ -987,9 +984,14 @@ static void notify_mode_switch(struct cache *cache, enum cache_metadata_mode mod static void set_cache_mode(struct cache *cache, enum cache_metadata_mode new_mode) { - bool needs_check = dm_cache_metadata_needs_check(cache->cmd); + bool needs_check; enum cache_metadata_mode old_mode = get_cache_mode(cache); + if (dm_cache_metadata_needs_check(cache->cmd, &needs_check)) { + DMERR("unable to read needs_check flag, setting failure mode"); + new_mode = CM_FAIL; + } + if (new_mode == CM_WRITE && needs_check) { DMERR("%s: unable to switch cache to write mode until repaired.", cache_device_name(cache)); @@ -3513,6 +3515,7 @@ static void cache_status(struct dm_target *ti, status_type_t type, char buf[BDEVNAME_SIZE]; struct cache *cache = ti->private; dm_cblock_t residency; + bool needs_check; switch (type) { case STATUSTYPE_INFO: @@ -3586,7 +3589,9 @@ static void cache_status(struct dm_target *ti, status_type_t type, else DMEMIT("rw "); - if (dm_cache_metadata_needs_check(cache->cmd)) + r = dm_cache_metadata_needs_check(cache->cmd, &needs_check); + + if (r || needs_check) DMEMIT("needs_check "); else DMEMIT("- "); diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index fae34e7a0b1e..12b5216c2cfe 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -69,7 +69,7 @@ struct dm_exception_store_type { * Update the metadata with this exception. */ void (*commit_exception) (struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context); diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 3164b8bce294..4d3909393f2c 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -695,7 +695,7 @@ static int persistent_prepare_exception(struct dm_exception_store *store, } static void persistent_commit_exception(struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context) { @@ -704,6 +704,9 @@ static void persistent_commit_exception(struct dm_exception_store *store, struct core_exception ce; struct commit_callback *cb; + if (!valid) + ps->valid = 0; + ce.old_chunk = e->old_chunk; ce.new_chunk = e->new_chunk; write_exception(ps, ps->current_committed++, &ce); diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c index 9b7c8c8049d6..4d50a12cf00c 100644 --- a/drivers/md/dm-snap-transient.c +++ b/drivers/md/dm-snap-transient.c @@ -52,12 +52,12 @@ static int transient_prepare_exception(struct dm_exception_store *store, } static void transient_commit_exception(struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context) { /* Just succeed */ - callback(callback_context, 1); + callback(callback_context, valid); } static void transient_usage(struct dm_exception_store *store, diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index c06b74e91cd6..e4d1bafe78c1 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -207,7 +207,6 @@ struct dm_snap_pending_exception { */ struct bio *full_bio; bio_end_io_t *full_bio_end_io; - void *full_bio_private; }; /* @@ -1106,6 +1105,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) int i; int r = -EINVAL; char *origin_path, *cow_path; + dev_t origin_dev, cow_dev; unsigned args_used, num_flush_bios = 1; fmode_t origin_mode = FMODE_READ; @@ -1136,11 +1136,19 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->error = "Cannot get origin device"; goto bad_origin; } + origin_dev = s->origin->bdev->bd_dev; cow_path = argv[0]; argv++; argc--; + cow_dev = dm_get_dev_t(cow_path); + if (cow_dev && cow_dev == origin_dev) { + ti->error = "COW device cannot be the same as origin device"; + r = -EINVAL; + goto bad_cow; + } + r = dm_get_device(ti, cow_path, dm_table_get_mode(ti->table), &s->cow); if (r) { ti->error = "Cannot get COW device"; @@ -1438,8 +1446,9 @@ static void __invalidate_snapshot(struct dm_snapshot *s, int err) dm_table_event(s->ti->table); } -static void pending_complete(struct dm_snap_pending_exception *pe, int success) +static void pending_complete(void *context, int success) { + struct dm_snap_pending_exception *pe = context; struct dm_exception *e; struct dm_snapshot *s = pe->snap; struct bio *origin_bios = NULL; @@ -1485,10 +1494,8 @@ out: snapshot_bios = bio_list_get(&pe->snapshot_bios); origin_bios = bio_list_get(&pe->origin_bios); full_bio = pe->full_bio; - if (full_bio) { + if (full_bio) full_bio->bi_end_io = pe->full_bio_end_io; - full_bio->bi_private = pe->full_bio_private; - } increment_pending_exceptions_done_count(); up_write(&s->lock); @@ -1509,24 +1516,13 @@ out: free_pending_exception(pe); } -static void commit_callback(void *context, int success) -{ - struct dm_snap_pending_exception *pe = context; - - pending_complete(pe, success); -} - static void complete_exception(struct dm_snap_pending_exception *pe) { struct dm_snapshot *s = pe->snap; - if (unlikely(pe->copy_error)) - pending_complete(pe, 0); - - else - /* Update the metadata if we are persistent */ - s->store->type->commit_exception(s->store, &pe->e, - commit_callback, pe); + /* Update the metadata if we are persistent */ + s->store->type->commit_exception(s->store, &pe->e, !pe->copy_error, + pending_complete, pe); } /* @@ -1605,7 +1601,6 @@ static void start_full_bio(struct dm_snap_pending_exception *pe, pe->full_bio = bio; pe->full_bio_end_io = bio->bi_end_io; - pe->full_bio_private = bio->bi_private; callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client, copy_callback, pe); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 061152a43730..cb5d0daf53bb 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -365,6 +365,26 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, } /* + * Convert the path to a device + */ +dev_t dm_get_dev_t(const char *path) +{ + dev_t uninitialized_var(dev); + struct block_device *bdev; + + bdev = lookup_bdev(path); + if (IS_ERR(bdev)) + dev = name_to_dev_t(path); + else { + dev = bdev->bd_dev; + bdput(bdev); + } + + return dev; +} +EXPORT_SYMBOL_GPL(dm_get_dev_t); + +/* * Add a device to the list, or just increment the usage count if * it's already present. */ @@ -372,23 +392,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, struct dm_dev **result) { int r; - dev_t uninitialized_var(dev); + dev_t dev; struct dm_dev_internal *dd; struct dm_table *t = ti->table; - struct block_device *bdev; BUG_ON(!t); - /* convert the path to a device */ - bdev = lookup_bdev(path); - if (IS_ERR(bdev)) { - dev = name_to_dev_t(path); - if (!dev) - return -ENODEV; - } else { - dev = bdev->bd_dev; - bdput(bdev); - } + dev = dm_get_dev_t(path); + if (!dev) + return -ENODEV; dd = find_device(&t->devices, dev); if (!dd) { diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index c219a053c7f6..911ada643364 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1943,5 +1943,8 @@ bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd) void dm_pool_issue_prefetches(struct dm_pool_metadata *pmd) { - dm_tm_issue_prefetches(pmd->tm); + down_read(&pmd->root_lock); + if (!pmd->fail_io) + dm_tm_issue_prefetches(pmd->tm); + up_read(&pmd->root_lock); } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 63903a5a5d9e..a1cc797fe88f 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3453,8 +3453,8 @@ static void pool_postsuspend(struct dm_target *ti) struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - cancel_delayed_work(&pool->waker); - cancel_delayed_work(&pool->no_space_timeout); + cancel_delayed_work_sync(&pool->waker); + cancel_delayed_work_sync(&pool->no_space_timeout); flush_workqueue(pool->wq); (void) commit(pool); } diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c new file mode 100644 index 000000000000..ad10d6d8ed28 --- /dev/null +++ b/drivers/md/dm-verity-fec.c @@ -0,0 +1,861 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * Author: Sami Tolvanen <samitolvanen@google.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +#include "dm-verity-fec.h" +#include <linux/math64.h> +#include <linux/sysfs.h> + +#define DM_MSG_PREFIX "verity-fec" + +/* + * If error correction has been configured, returns true. + */ +bool verity_fec_is_enabled(struct dm_verity *v) +{ + return v->fec && v->fec->dev; +} + +/* + * Return a pointer to dm_verity_fec_io after dm_verity_io and its variable + * length fields. + */ +static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io) +{ + return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io); +} + +/* + * Return an interleaved offset for a byte in RS block. + */ +static inline u64 fec_interleave(struct dm_verity *v, u64 offset) +{ + u32 mod; + + mod = do_div(offset, v->fec->rsn); + return offset + mod * (v->fec->rounds << v->data_dev_block_bits); +} + +/* + * Decode an RS block using Reed-Solomon. + */ +static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, + u8 *data, u8 *fec, int neras) +{ + int i; + uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; + + for (i = 0; i < v->fec->roots; i++) + par[i] = fec[i]; + + return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras, + fio->erasures, 0, NULL); +} + +/* + * Read error-correcting codes for the requested RS block. Returns a pointer + * to the data block. Caller is responsible for releasing buf. + */ +static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, + unsigned *offset, struct dm_buffer **buf) +{ + u64 position, block; + u8 *res; + + position = (index + rsb) * v->fec->roots; + block = position >> v->data_dev_block_bits; + *offset = (unsigned)(position - (block << v->data_dev_block_bits)); + + res = dm_bufio_read(v->fec->bufio, v->fec->start + block, buf); + if (unlikely(IS_ERR(res))) { + DMERR("%s: FEC %llu: parity read failed (block %llu): %ld", + v->data_dev->name, (unsigned long long)rsb, + (unsigned long long)(v->fec->start + block), + PTR_ERR(res)); + *buf = NULL; + } + + return res; +} + +/* Loop over each preallocated buffer slot. */ +#define fec_for_each_prealloc_buffer(__i) \ + for (__i = 0; __i < DM_VERITY_FEC_BUF_PREALLOC; __i++) + +/* Loop over each extra buffer slot. */ +#define fec_for_each_extra_buffer(io, __i) \ + for (__i = DM_VERITY_FEC_BUF_PREALLOC; __i < DM_VERITY_FEC_BUF_MAX; __i++) + +/* Loop over each allocated buffer. */ +#define fec_for_each_buffer(io, __i) \ + for (__i = 0; __i < (io)->nbufs; __i++) + +/* Loop over each RS block in each allocated buffer. */ +#define fec_for_each_buffer_rs_block(io, __i, __j) \ + fec_for_each_buffer(io, __i) \ + for (__j = 0; __j < 1 << DM_VERITY_FEC_BUF_RS_BITS; __j++) + +/* + * Return a pointer to the current RS block when called inside + * fec_for_each_buffer_rs_block. + */ +static inline u8 *fec_buffer_rs_block(struct dm_verity *v, + struct dm_verity_fec_io *fio, + unsigned i, unsigned j) +{ + return &fio->bufs[i][j * v->fec->rsn]; +} + +/* + * Return an index to the current RS block when called inside + * fec_for_each_buffer_rs_block. + */ +static inline unsigned fec_buffer_rs_index(unsigned i, unsigned j) +{ + return (i << DM_VERITY_FEC_BUF_RS_BITS) + j; +} + +/* + * Decode all RS blocks from buffers and copy corrected bytes into fio->output + * starting from block_offset. + */ +static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio, + u64 rsb, int byte_index, unsigned block_offset, + int neras) +{ + int r, corrected = 0, res; + struct dm_buffer *buf; + unsigned n, i, offset; + u8 *par, *block; + + par = fec_read_parity(v, rsb, block_offset, &offset, &buf); + if (IS_ERR(par)) + return PTR_ERR(par); + + /* + * Decode the RS blocks we have in bufs. Each RS block results in + * one corrected target byte and consumes fec->roots parity bytes. + */ + fec_for_each_buffer_rs_block(fio, n, i) { + block = fec_buffer_rs_block(v, fio, n, i); + res = fec_decode_rs8(v, fio, block, &par[offset], neras); + if (res < 0) { + dm_bufio_release(buf); + + r = res; + goto error; + } + + corrected += res; + fio->output[block_offset] = block[byte_index]; + + block_offset++; + if (block_offset >= 1 << v->data_dev_block_bits) + goto done; + + /* read the next block when we run out of parity bytes */ + offset += v->fec->roots; + if (offset >= 1 << v->data_dev_block_bits) { + dm_bufio_release(buf); + + par = fec_read_parity(v, rsb, block_offset, &offset, &buf); + if (unlikely(IS_ERR(par))) + return PTR_ERR(par); + } + } +done: + r = corrected; +error: + if (r < 0 && neras) + DMERR_LIMIT("%s: FEC %llu: failed to correct: %d", + v->data_dev->name, (unsigned long long)rsb, r); + else if (r > 0) { + DMWARN_LIMIT("%s: FEC %llu: corrected %d errors", + v->data_dev->name, (unsigned long long)rsb, r); + atomic_add_unless(&v->fec->corrected, 1, INT_MAX); + } + + return r; +} + +/* + * Locate data block erasures using verity hashes. + */ +static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io, + u8 *want_digest, u8 *data) +{ + if (unlikely(verity_hash(v, verity_io_hash_desc(v, io), + data, 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io)))) + return 0; + + return memcmp(verity_io_real_digest(v, io), want_digest, + v->digest_size) != 0; +} + +/* + * Read data blocks that are part of the RS block and deinterleave as much as + * fits into buffers. Check for erasure locations if @neras is non-NULL. + */ +static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, + u64 rsb, u64 target, unsigned block_offset, + int *neras) +{ + bool is_zero; + int i, j, target_index = -1; + struct dm_buffer *buf; + struct dm_bufio_client *bufio; + struct dm_verity_fec_io *fio = fec_io(io); + u64 block, ileaved; + u8 *bbuf, *rs_block; + u8 want_digest[v->digest_size]; + unsigned n, k; + + if (neras) + *neras = 0; + + /* + * read each of the rsn data blocks that are part of the RS block, and + * interleave contents to available bufs + */ + for (i = 0; i < v->fec->rsn; i++) { + ileaved = fec_interleave(v, rsb * v->fec->rsn + i); + + /* + * target is the data block we want to correct, target_index is + * the index of this block within the rsn RS blocks + */ + if (ileaved == target) + target_index = i; + + block = ileaved >> v->data_dev_block_bits; + bufio = v->fec->data_bufio; + + if (block >= v->data_blocks) { + block -= v->data_blocks; + + /* + * blocks outside the area were assumed to contain + * zeros when encoding data was generated + */ + if (unlikely(block >= v->fec->hash_blocks)) + continue; + + block += v->hash_start; + bufio = v->bufio; + } + + bbuf = dm_bufio_read(bufio, block, &buf); + if (unlikely(IS_ERR(bbuf))) { + DMWARN_LIMIT("%s: FEC %llu: read failed (%llu): %ld", + v->data_dev->name, + (unsigned long long)rsb, + (unsigned long long)block, PTR_ERR(bbuf)); + + /* assume the block is corrupted */ + if (neras && *neras <= v->fec->roots) + fio->erasures[(*neras)++] = i; + + continue; + } + + /* locate erasures if the block is on the data device */ + if (bufio == v->fec->data_bufio && + verity_hash_for_block(v, io, block, want_digest, + &is_zero) == 0) { + /* skip known zero blocks entirely */ + if (is_zero) + continue; + + /* + * skip if we have already found the theoretical + * maximum number (i.e. fec->roots) of erasures + */ + if (neras && *neras <= v->fec->roots && + fec_is_erasure(v, io, want_digest, bbuf)) + fio->erasures[(*neras)++] = i; + } + + /* + * deinterleave and copy the bytes that fit into bufs, + * starting from block_offset + */ + fec_for_each_buffer_rs_block(fio, n, j) { + k = fec_buffer_rs_index(n, j) + block_offset; + + if (k >= 1 << v->data_dev_block_bits) + goto done; + + rs_block = fec_buffer_rs_block(v, fio, n, j); + rs_block[i] = bbuf[k]; + } +done: + dm_bufio_release(buf); + } + + return target_index; +} + +/* + * Allocate RS control structure and FEC buffers from preallocated mempools, + * and attempt to allocate as many extra buffers as available. + */ +static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) +{ + unsigned n; + + if (!fio->rs) { + fio->rs = mempool_alloc(v->fec->rs_pool, 0); + if (unlikely(!fio->rs)) { + DMERR("failed to allocate RS"); + return -ENOMEM; + } + } + + fec_for_each_prealloc_buffer(n) { + if (fio->bufs[n]) + continue; + + fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOIO); + if (unlikely(!fio->bufs[n])) { + DMERR("failed to allocate FEC buffer"); + return -ENOMEM; + } + } + + /* try to allocate the maximum number of buffers */ + fec_for_each_extra_buffer(fio, n) { + if (fio->bufs[n]) + continue; + + fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOIO); + /* we can manage with even one buffer if necessary */ + if (unlikely(!fio->bufs[n])) + break; + } + fio->nbufs = n; + + if (!fio->output) { + fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO); + + if (!fio->output) { + DMERR("failed to allocate FEC page"); + return -ENOMEM; + } + } + + return 0; +} + +/* + * Initialize buffers and clear erasures. fec_read_bufs() assumes buffers are + * zeroed before deinterleaving. + */ +static void fec_init_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) +{ + unsigned n; + + fec_for_each_buffer(fio, n) + memset(fio->bufs[n], 0, v->fec->rsn << DM_VERITY_FEC_BUF_RS_BITS); + + memset(fio->erasures, 0, sizeof(fio->erasures)); +} + +/* + * Decode all RS blocks in a single data block and return the target block + * (indicated by @offset) in fio->output. If @use_erasures is non-zero, uses + * hashes to locate erasures. + */ +static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, + struct dm_verity_fec_io *fio, u64 rsb, u64 offset, + bool use_erasures) +{ + int r, neras = 0; + unsigned pos; + + r = fec_alloc_bufs(v, fio); + if (unlikely(r < 0)) + return r; + + for (pos = 0; pos < 1 << v->data_dev_block_bits; ) { + fec_init_bufs(v, fio); + + r = fec_read_bufs(v, io, rsb, offset, pos, + use_erasures ? &neras : NULL); + if (unlikely(r < 0)) + return r; + + r = fec_decode_bufs(v, fio, rsb, r, pos, neras); + if (r < 0) + return r; + + pos += fio->nbufs << DM_VERITY_FEC_BUF_RS_BITS; + } + + /* Always re-validate the corrected block against the expected hash */ + r = verity_hash(v, verity_io_hash_desc(v, io), fio->output, + 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io)); + if (unlikely(r < 0)) + return r; + + if (memcmp(verity_io_real_digest(v, io), verity_io_want_digest(v, io), + v->digest_size)) { + DMERR_LIMIT("%s: FEC %llu: failed to correct (%d erasures)", + v->data_dev->name, (unsigned long long)rsb, neras); + return -EILSEQ; + } + + return 0; +} + +static int fec_bv_copy(struct dm_verity *v, struct dm_verity_io *io, u8 *data, + size_t len) +{ + struct dm_verity_fec_io *fio = fec_io(io); + + memcpy(data, &fio->output[fio->output_pos], len); + fio->output_pos += len; + + return 0; +} + +/* + * Correct errors in a block. Copies corrected block to dest if non-NULL, + * otherwise to a bio_vec starting from iter. + */ +int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, + enum verity_block_type type, sector_t block, u8 *dest, + struct bvec_iter *iter) +{ + int r; + struct dm_verity_fec_io *fio = fec_io(io); + u64 offset, res, rsb; + + if (!verity_fec_is_enabled(v)) + return -EOPNOTSUPP; + + if (type == DM_VERITY_BLOCK_TYPE_METADATA) + block += v->data_blocks; + + /* + * For RS(M, N), the continuous FEC data is divided into blocks of N + * bytes. Since block size may not be divisible by N, the last block + * is zero padded when decoding. + * + * Each byte of the block is covered by a different RS(M, N) code, + * and each code is interleaved over N blocks to make it less likely + * that bursty corruption will leave us in unrecoverable state. + */ + + offset = block << v->data_dev_block_bits; + + res = offset; + div64_u64(res, v->fec->rounds << v->data_dev_block_bits); + + /* + * The base RS block we can feed to the interleaver to find out all + * blocks required for decoding. + */ + rsb = offset - res * (v->fec->rounds << v->data_dev_block_bits); + + /* + * Locating erasures is slow, so attempt to recover the block without + * them first. Do a second attempt with erasures if the corruption is + * bad enough. + */ + r = fec_decode_rsb(v, io, fio, rsb, offset, false); + if (r < 0) { + r = fec_decode_rsb(v, io, fio, rsb, offset, true); + if (r < 0) + return r; + } + + if (dest) + memcpy(dest, fio->output, 1 << v->data_dev_block_bits); + else if (iter) { + fio->output_pos = 0; + r = verity_for_bv_block(v, io, iter, fec_bv_copy); + } + + return r; +} + +/* + * Clean up per-bio data. + */ +void verity_fec_finish_io(struct dm_verity_io *io) +{ + unsigned n; + struct dm_verity_fec *f = io->v->fec; + struct dm_verity_fec_io *fio = fec_io(io); + + if (!verity_fec_is_enabled(io->v)) + return; + + mempool_free(fio->rs, f->rs_pool); + + fec_for_each_prealloc_buffer(n) + mempool_free(fio->bufs[n], f->prealloc_pool); + + fec_for_each_extra_buffer(fio, n) + mempool_free(fio->bufs[n], f->extra_pool); + + mempool_free(fio->output, f->output_pool); +} + +/* + * Initialize per-bio data. + */ +void verity_fec_init_io(struct dm_verity_io *io) +{ + struct dm_verity_fec_io *fio = fec_io(io); + + if (!verity_fec_is_enabled(io->v)) + return; + + fio->rs = NULL; + memset(fio->bufs, 0, sizeof(fio->bufs)); + fio->nbufs = 0; + fio->output = NULL; +} + +/* + * Append feature arguments and values to the status table. + */ +unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, + char *result, unsigned maxlen) +{ + if (!verity_fec_is_enabled(v)) + return sz; + + DMEMIT(" " DM_VERITY_OPT_FEC_DEV " %s " + DM_VERITY_OPT_FEC_BLOCKS " %llu " + DM_VERITY_OPT_FEC_START " %llu " + DM_VERITY_OPT_FEC_ROOTS " %d", + v->fec->dev->name, + (unsigned long long)v->fec->blocks, + (unsigned long long)v->fec->start, + v->fec->roots); + + return sz; +} + +void verity_fec_dtr(struct dm_verity *v) +{ + struct dm_verity_fec *f = v->fec; + struct kobject *kobj = &f->kobj_holder.kobj; + + if (!verity_fec_is_enabled(v)) + goto out; + + mempool_destroy(f->rs_pool); + mempool_destroy(f->prealloc_pool); + mempool_destroy(f->extra_pool); + kmem_cache_destroy(f->cache); + + if (f->data_bufio) + dm_bufio_client_destroy(f->data_bufio); + if (f->bufio) + dm_bufio_client_destroy(f->bufio); + + if (f->dev) + dm_put_device(v->ti, f->dev); + + if (kobj->state_initialized) { + kobject_put(kobj); + wait_for_completion(dm_get_completion_from_kobject(kobj)); + } + +out: + kfree(f); + v->fec = NULL; +} + +static void *fec_rs_alloc(gfp_t gfp_mask, void *pool_data) +{ + struct dm_verity *v = (struct dm_verity *)pool_data; + + return init_rs(8, 0x11d, 0, 1, v->fec->roots); +} + +static void fec_rs_free(void *element, void *pool_data) +{ + struct rs_control *rs = (struct rs_control *)element; + + if (rs) + free_rs(rs); +} + +bool verity_is_fec_opt_arg(const char *arg_name) +{ + return (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_START) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)); +} + +int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, + unsigned *argc, const char *arg_name) +{ + int r; + struct dm_target *ti = v->ti; + const char *arg_value; + unsigned long long num_ll; + unsigned char num_c; + char dummy; + + if (!*argc) { + ti->error = "FEC feature arguments require a value"; + return -EINVAL; + } + + arg_value = dm_shift_arg(as); + (*argc)--; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) { + r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev); + if (r) { + ti->error = "FEC device lookup failed"; + return r; + } + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS)) { + if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 || + ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) + >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + v->fec->blocks = num_ll; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_START)) { + if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 || + ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) >> + (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_START; + return -EINVAL; + } + v->fec->start = num_ll; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)) { + if (sscanf(arg_value, "%hhu%c", &num_c, &dummy) != 1 || !num_c || + num_c < (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MAX_RSN) || + num_c > (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_ROOTS; + return -EINVAL; + } + v->fec->roots = num_c; + + } else { + ti->error = "Unrecognized verity FEC feature request"; + return -EINVAL; + } + + return 0; +} + +static ssize_t corrected_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct dm_verity_fec *f = container_of(kobj, struct dm_verity_fec, + kobj_holder.kobj); + + return sprintf(buf, "%d\n", atomic_read(&f->corrected)); +} + +static struct kobj_attribute attr_corrected = __ATTR_RO(corrected); + +static struct attribute *fec_attrs[] = { + &attr_corrected.attr, + NULL +}; + +static struct kobj_type fec_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = fec_attrs +}; + +/* + * Allocate dm_verity_fec for v->fec. Must be called before verity_fec_ctr. + */ +int verity_fec_ctr_alloc(struct dm_verity *v) +{ + struct dm_verity_fec *f; + + f = kzalloc(sizeof(struct dm_verity_fec), GFP_KERNEL); + if (!f) { + v->ti->error = "Cannot allocate FEC structure"; + return -ENOMEM; + } + v->fec = f; + + return 0; +} + +/* + * Validate arguments and preallocate memory. Must be called after arguments + * have been parsed using verity_fec_parse_opt_args. + */ +int verity_fec_ctr(struct dm_verity *v) +{ + int r; + struct dm_verity_fec *f = v->fec; + struct dm_target *ti = v->ti; + struct mapped_device *md = dm_table_get_md(ti->table); + u64 hash_blocks; + + if (!verity_fec_is_enabled(v)) { + verity_fec_dtr(v); + return 0; + } + + /* Create a kobject and sysfs attributes */ + init_completion(&f->kobj_holder.completion); + + r = kobject_init_and_add(&f->kobj_holder.kobj, &fec_ktype, + &disk_to_dev(dm_disk(md))->kobj, "%s", "fec"); + if (r) { + ti->error = "Cannot create kobject"; + return r; + } + + /* + * FEC is computed over data blocks, possible metadata, and + * hash blocks. In other words, FEC covers total of fec_blocks + * blocks consisting of the following: + * + * data blocks | hash blocks | metadata (optional) + * + * We allow metadata after hash blocks to support a use case + * where all data is stored on the same device and FEC covers + * the entire area. + * + * If metadata is included, we require it to be available on the + * hash device after the hash blocks. + */ + + hash_blocks = v->hash_blocks - v->hash_start; + + /* + * Require matching block sizes for data and hash devices for + * simplicity. + */ + if (v->data_dev_block_bits != v->hash_dev_block_bits) { + ti->error = "Block sizes must match to use FEC"; + return -EINVAL; + } + + if (!f->roots) { + ti->error = "Missing " DM_VERITY_OPT_FEC_ROOTS; + return -EINVAL; + } + f->rsn = DM_VERITY_FEC_RSM - f->roots; + + if (!f->blocks) { + ti->error = "Missing " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + + f->rounds = f->blocks; + if (sector_div(f->rounds, f->rsn)) + f->rounds++; + + /* + * Due to optional metadata, f->blocks can be larger than + * data_blocks and hash_blocks combined. + */ + if (f->blocks < v->data_blocks + hash_blocks || !f->rounds) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + + /* + * Metadata is accessed through the hash device, so we require + * it to be large enough. + */ + f->hash_blocks = f->blocks - v->data_blocks; + if (dm_bufio_get_device_size(v->bufio) < f->hash_blocks) { + ti->error = "Hash device is too small for " + DM_VERITY_OPT_FEC_BLOCKS; + return -E2BIG; + } + + f->bufio = dm_bufio_client_create(f->dev->bdev, + 1 << v->data_dev_block_bits, + 1, 0, NULL, NULL); + if (IS_ERR(f->bufio)) { + ti->error = "Cannot initialize FEC bufio client"; + return PTR_ERR(f->bufio); + } + + if (dm_bufio_get_device_size(f->bufio) < + ((f->start + f->rounds * f->roots) >> v->data_dev_block_bits)) { + ti->error = "FEC device is too small"; + return -E2BIG; + } + + f->data_bufio = dm_bufio_client_create(v->data_dev->bdev, + 1 << v->data_dev_block_bits, + 1, 0, NULL, NULL); + if (IS_ERR(f->data_bufio)) { + ti->error = "Cannot initialize FEC data bufio client"; + return PTR_ERR(f->data_bufio); + } + + if (dm_bufio_get_device_size(f->data_bufio) < v->data_blocks) { + ti->error = "Data device is too small"; + return -E2BIG; + } + + /* Preallocate an rs_control structure for each worker thread */ + f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc, + fec_rs_free, (void *) v); + if (!f->rs_pool) { + ti->error = "Cannot allocate RS pool"; + return -ENOMEM; + } + + f->cache = kmem_cache_create("dm_verity_fec_buffers", + f->rsn << DM_VERITY_FEC_BUF_RS_BITS, + 0, 0, NULL); + if (!f->cache) { + ti->error = "Cannot create FEC buffer cache"; + return -ENOMEM; + } + + /* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */ + f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() * + DM_VERITY_FEC_BUF_PREALLOC, + f->cache); + if (!f->prealloc_pool) { + ti->error = "Cannot allocate FEC buffer prealloc pool"; + return -ENOMEM; + } + + f->extra_pool = mempool_create_slab_pool(0, f->cache); + if (!f->extra_pool) { + ti->error = "Cannot allocate FEC buffer extra pool"; + return -ENOMEM; + } + + /* Preallocate an output buffer for each thread */ + f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(), + 1 << v->data_dev_block_bits); + if (!f->output_pool) { + ti->error = "Cannot allocate FEC output pool"; + return -ENOMEM; + } + + /* Reserve space for our per-bio data */ + ti->per_bio_data_size += sizeof(struct dm_verity_fec_io); + + return 0; +} diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h new file mode 100644 index 000000000000..8c4bee052a73 --- /dev/null +++ b/drivers/md/dm-verity-fec.h @@ -0,0 +1,155 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * Author: Sami Tolvanen <samitolvanen@google.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +#ifndef DM_VERITY_FEC_H +#define DM_VERITY_FEC_H + +#include "dm.h" +#include "dm-verity.h" +#include <linux/rslib.h> + +/* Reed-Solomon(M, N) parameters */ +#define DM_VERITY_FEC_RSM 255 +#define DM_VERITY_FEC_MAX_RSN 253 +#define DM_VERITY_FEC_MIN_RSN 231 /* ~10% space overhead */ + +/* buffers for deinterleaving and decoding */ +#define DM_VERITY_FEC_BUF_PREALLOC 1 /* buffers to preallocate */ +#define DM_VERITY_FEC_BUF_RS_BITS 4 /* 1 << RS blocks per buffer */ +/* we need buffers for at most 1 << block size RS blocks */ +#define DM_VERITY_FEC_BUF_MAX \ + (1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS)) + +#define DM_VERITY_OPT_FEC_DEV "use_fec_from_device" +#define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks" +#define DM_VERITY_OPT_FEC_START "fec_start" +#define DM_VERITY_OPT_FEC_ROOTS "fec_roots" + +/* configuration */ +struct dm_verity_fec { + struct dm_dev *dev; /* parity data device */ + struct dm_bufio_client *data_bufio; /* for data dev access */ + struct dm_bufio_client *bufio; /* for parity data access */ + sector_t start; /* parity data start in blocks */ + sector_t blocks; /* number of blocks covered */ + sector_t rounds; /* number of interleaving rounds */ + sector_t hash_blocks; /* blocks covered after v->hash_start */ + unsigned char roots; /* number of parity bytes, M-N of RS(M, N) */ + unsigned char rsn; /* N of RS(M, N) */ + mempool_t *rs_pool; /* mempool for fio->rs */ + mempool_t *prealloc_pool; /* mempool for preallocated buffers */ + mempool_t *extra_pool; /* mempool for extra buffers */ + mempool_t *output_pool; /* mempool for output */ + struct kmem_cache *cache; /* cache for buffers */ + atomic_t corrected; /* corrected errors */ + struct dm_kobject_holder kobj_holder; /* for sysfs attributes */ +}; + +/* per-bio data */ +struct dm_verity_fec_io { + struct rs_control *rs; /* Reed-Solomon state */ + int erasures[DM_VERITY_FEC_MAX_RSN]; /* erasures for decode_rs8 */ + u8 *bufs[DM_VERITY_FEC_BUF_MAX]; /* bufs for deinterleaving */ + unsigned nbufs; /* number of buffers allocated */ + u8 *output; /* buffer for corrected output */ + size_t output_pos; +}; + +#ifdef CONFIG_DM_VERITY_FEC + +/* each feature parameter requires a value */ +#define DM_VERITY_OPTS_FEC 8 + +extern bool verity_fec_is_enabled(struct dm_verity *v); + +extern int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, + enum verity_block_type type, sector_t block, + u8 *dest, struct bvec_iter *iter); + +extern unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, + char *result, unsigned maxlen); + +extern void verity_fec_finish_io(struct dm_verity_io *io); +extern void verity_fec_init_io(struct dm_verity_io *io); + +extern bool verity_is_fec_opt_arg(const char *arg_name); +extern int verity_fec_parse_opt_args(struct dm_arg_set *as, + struct dm_verity *v, unsigned *argc, + const char *arg_name); + +extern void verity_fec_dtr(struct dm_verity *v); + +extern int verity_fec_ctr_alloc(struct dm_verity *v); +extern int verity_fec_ctr(struct dm_verity *v); + +#else /* !CONFIG_DM_VERITY_FEC */ + +#define DM_VERITY_OPTS_FEC 0 + +static inline bool verity_fec_is_enabled(struct dm_verity *v) +{ + return false; +} + +static inline int verity_fec_decode(struct dm_verity *v, + struct dm_verity_io *io, + enum verity_block_type type, + sector_t block, u8 *dest, + struct bvec_iter *iter) +{ + return -EOPNOTSUPP; +} + +static inline unsigned verity_fec_status_table(struct dm_verity *v, + unsigned sz, char *result, + unsigned maxlen) +{ + return sz; +} + +static inline void verity_fec_finish_io(struct dm_verity_io *io) +{ +} + +static inline void verity_fec_init_io(struct dm_verity_io *io) +{ +} + +static inline bool verity_is_fec_opt_arg(const char *arg_name) +{ + return false; +} + +static inline int verity_fec_parse_opt_args(struct dm_arg_set *as, + struct dm_verity *v, + unsigned *argc, + const char *arg_name) +{ + return -EINVAL; +} + +static inline void verity_fec_dtr(struct dm_verity *v) +{ +} + +static inline int verity_fec_ctr_alloc(struct dm_verity *v) +{ + return 0; +} + +static inline int verity_fec_ctr(struct dm_verity *v) +{ + return 0; +} + +#endif /* CONFIG_DM_VERITY_FEC */ + +#endif /* DM_VERITY_FEC_H */ diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity-target.c index ccf41886ebcf..5c5d30cb6ec5 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity-target.c @@ -14,12 +14,11 @@ * access behavior. */ -#include "dm-bufio.h" +#include "dm-verity.h" +#include "dm-verity-fec.h" #include <linux/module.h> -#include <linux/device-mapper.h> #include <linux/reboot.h> -#include <crypto/hash.h> #define DM_MSG_PREFIX "verity" @@ -28,83 +27,18 @@ #define DM_VERITY_DEFAULT_PREFETCH_SIZE 262144 -#define DM_VERITY_MAX_LEVELS 63 #define DM_VERITY_MAX_CORRUPTED_ERRS 100 #define DM_VERITY_OPT_LOGGING "ignore_corruption" #define DM_VERITY_OPT_RESTART "restart_on_corruption" +#define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks" + +#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC) static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR); -enum verity_mode { - DM_VERITY_MODE_EIO, - DM_VERITY_MODE_LOGGING, - DM_VERITY_MODE_RESTART -}; - -enum verity_block_type { - DM_VERITY_BLOCK_TYPE_DATA, - DM_VERITY_BLOCK_TYPE_METADATA -}; - -struct dm_verity { - struct dm_dev *data_dev; - struct dm_dev *hash_dev; - struct dm_target *ti; - struct dm_bufio_client *bufio; - char *alg_name; - struct crypto_shash *tfm; - u8 *root_digest; /* digest of the root block */ - u8 *salt; /* salt: its size is salt_size */ - unsigned salt_size; - sector_t data_start; /* data offset in 512-byte sectors */ - sector_t hash_start; /* hash start in blocks */ - sector_t data_blocks; /* the number of data blocks */ - sector_t hash_blocks; /* the number of hash blocks */ - unsigned char data_dev_block_bits; /* log2(data blocksize) */ - unsigned char hash_dev_block_bits; /* log2(hash blocksize) */ - unsigned char hash_per_block_bits; /* log2(hashes in hash block) */ - unsigned char levels; /* the number of tree levels */ - unsigned char version; - unsigned digest_size; /* digest size for the current hash algorithm */ - unsigned shash_descsize;/* the size of temporary space for crypto */ - int hash_failed; /* set to 1 if hash of any block failed */ - enum verity_mode mode; /* mode for handling verification errors */ - unsigned corrupted_errs;/* Number of errors for corrupted blocks */ - - struct workqueue_struct *verify_wq; - - /* starting blocks for each tree level. 0 is the lowest level. */ - sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; -}; - -struct dm_verity_io { - struct dm_verity *v; - - /* original values of bio->bi_end_io and bio->bi_private */ - bio_end_io_t *orig_bi_end_io; - void *orig_bi_private; - - sector_t block; - unsigned n_blocks; - - struct bvec_iter iter; - - struct work_struct work; - - /* - * Three variably-size fields follow this struct: - * - * u8 hash_desc[v->shash_descsize]; - * u8 real_digest[v->digest_size]; - * u8 want_digest[v->digest_size]; - * - * To access them use: io_hash_desc(), io_real_digest() and io_want_digest(). - */ -}; - struct dm_verity_prefetch_work { struct work_struct work; struct dm_verity *v; @@ -112,21 +46,6 @@ struct dm_verity_prefetch_work { unsigned n_blocks; }; -static struct shash_desc *io_hash_desc(struct dm_verity *v, struct dm_verity_io *io) -{ - return (struct shash_desc *)(io + 1); -} - -static u8 *io_real_digest(struct dm_verity *v, struct dm_verity_io *io) -{ - return (u8 *)(io + 1) + v->shash_descsize; -} - -static u8 *io_want_digest(struct dm_verity *v, struct dm_verity_io *io) -{ - return (u8 *)(io + 1) + v->shash_descsize + v->digest_size; -} - /* * Auxiliary structure appended to each dm-bufio buffer. If the value * hash_verified is nonzero, hash of the block has been verified. @@ -173,6 +92,84 @@ static sector_t verity_position_at_level(struct dm_verity *v, sector_t block, return block >> (level * v->hash_per_block_bits); } +/* + * Wrapper for crypto_shash_init, which handles verity salting. + */ +static int verity_hash_init(struct dm_verity *v, struct shash_desc *desc) +{ + int r; + + desc->tfm = v->tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + r = crypto_shash_init(desc); + + if (unlikely(r < 0)) { + DMERR("crypto_shash_init failed: %d", r); + return r; + } + + if (likely(v->version >= 1)) { + r = crypto_shash_update(desc, v->salt, v->salt_size); + + if (unlikely(r < 0)) { + DMERR("crypto_shash_update failed: %d", r); + return r; + } + } + + return 0; +} + +static int verity_hash_update(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len) +{ + int r = crypto_shash_update(desc, data, len); + + if (unlikely(r < 0)) + DMERR("crypto_shash_update failed: %d", r); + + return r; +} + +static int verity_hash_final(struct dm_verity *v, struct shash_desc *desc, + u8 *digest) +{ + int r; + + if (unlikely(!v->version)) { + r = crypto_shash_update(desc, v->salt, v->salt_size); + + if (r < 0) { + DMERR("crypto_shash_update failed: %d", r); + return r; + } + } + + r = crypto_shash_final(desc, digest); + + if (unlikely(r < 0)) + DMERR("crypto_shash_final failed: %d", r); + + return r; +} + +int verity_hash(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len, u8 *digest) +{ + int r; + + r = verity_hash_init(v, desc); + if (unlikely(r < 0)) + return r; + + r = verity_hash_update(v, desc, data, len); + if (unlikely(r < 0)) + return r; + + return verity_hash_final(v, desc, digest); +} + static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level, sector_t *hash_block, unsigned *offset) { @@ -246,17 +243,17 @@ out: * Verify hash of a metadata block pertaining to the specified data block * ("block" argument) at a specified level ("level" argument). * - * On successful return, io_want_digest(v, io) contains the hash value for - * a lower tree level or for the data block (if we're at the lowest leve). + * On successful return, verity_io_want_digest(v, io) contains the hash value + * for a lower tree level or for the data block (if we're at the lowest level). * * If "skip_unverified" is true, unverified buffer is skipped and 1 is returned. * If "skip_unverified" is false, unverified buffer is hashed and verified - * against current value of io_want_digest(v, io). + * against current value of verity_io_want_digest(v, io). */ -static int verity_verify_level(struct dm_verity_io *io, sector_t block, - int level, bool skip_unverified) +static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, int level, bool skip_unverified, + u8 *want_digest) { - struct dm_verity *v = io->v; struct dm_buffer *buf; struct buffer_aux *aux; u8 *data; @@ -273,72 +270,128 @@ static int verity_verify_level(struct dm_verity_io *io, sector_t block, aux = dm_bufio_get_aux_data(buf); if (!aux->hash_verified) { - struct shash_desc *desc; - u8 *result; - if (skip_unverified) { r = 1; goto release_ret_r; } - desc = io_hash_desc(v, io); - desc->tfm = v->tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - r = crypto_shash_init(desc); - if (r < 0) { - DMERR("crypto_shash_init failed: %d", r); + r = verity_hash(v, verity_io_hash_desc(v, io), + data, 1 << v->hash_dev_block_bits, + verity_io_real_digest(v, io)); + if (unlikely(r < 0)) goto release_ret_r; - } - - if (likely(v->version >= 1)) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - } - r = crypto_shash_update(desc, data, 1 << v->hash_dev_block_bits); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); + if (likely(memcmp(verity_io_real_digest(v, io), want_digest, + v->digest_size) == 0)) + aux->hash_verified = 1; + else if (verity_fec_decode(v, io, + DM_VERITY_BLOCK_TYPE_METADATA, + hash_block, data, NULL) == 0) + aux->hash_verified = 1; + else if (verity_handle_err(v, + DM_VERITY_BLOCK_TYPE_METADATA, + hash_block)) { + r = -EIO; goto release_ret_r; } + } - if (!v->version) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - } + data += offset; + memcpy(want_digest, data, v->digest_size); + r = 0; - result = io_real_digest(v, io); - r = crypto_shash_final(desc, result); - if (r < 0) { - DMERR("crypto_shash_final failed: %d", r); - goto release_ret_r; - } - if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA, - hash_block)) { - r = -EIO; - goto release_ret_r; - } - } else - aux->hash_verified = 1; +release_ret_r: + dm_bufio_release(buf); + return r; +} + +/* + * Find a hash for a given block, write it to digest and verify the integrity + * of the hash tree if necessary. + */ +int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, u8 *digest, bool *is_zero) +{ + int r = 0, i; + + if (likely(v->levels)) { + /* + * First, we try to get the requested hash for + * the current block. If the hash block itself is + * verified, zero is returned. If it isn't, this + * function returns 1 and we fall back to whole + * chain verification. + */ + r = verity_verify_level(v, io, block, 0, true, digest); + if (likely(r <= 0)) + goto out; } - data += offset; + memcpy(digest, v->root_digest, v->digest_size); - memcpy(io_want_digest(v, io), data, v->digest_size); + for (i = v->levels - 1; i >= 0; i--) { + r = verity_verify_level(v, io, block, i, false, digest); + if (unlikely(r)) + goto out; + } +out: + if (!r && v->zero_digest) + *is_zero = !memcmp(v->zero_digest, digest, v->digest_size); + else + *is_zero = false; + + return r; +} + +/* + * Calls function process for 1 << v->data_dev_block_bits bytes in the bio_vec + * starting from iter. + */ +int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter *iter, + int (*process)(struct dm_verity *v, + struct dm_verity_io *io, u8 *data, + size_t len)) +{ + unsigned todo = 1 << v->data_dev_block_bits; + struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size); + + do { + int r; + u8 *page; + unsigned len; + struct bio_vec bv = bio_iter_iovec(bio, *iter); + + page = kmap_atomic(bv.bv_page); + len = bv.bv_len; + + if (likely(len >= todo)) + len = todo; + + r = process(v, io, page + bv.bv_offset, len); + kunmap_atomic(page); + + if (r < 0) + return r; + + bio_advance_iter(bio, iter, len); + todo -= len; + } while (todo); - dm_bufio_release(buf); return 0; +} -release_ret_r: - dm_bufio_release(buf); +static int verity_bv_hash_update(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + return verity_hash_update(v, verity_io_hash_desc(v, io), data, len); +} - return r; +static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + memset(data, 0, len); + return 0; } /* @@ -346,99 +399,56 @@ release_ret_r: */ static int verity_verify_io(struct dm_verity_io *io) { + bool is_zero; struct dm_verity *v = io->v; - struct bio *bio = dm_bio_from_per_bio_data(io, - v->ti->per_bio_data_size); + struct bvec_iter start; unsigned b; - int i; for (b = 0; b < io->n_blocks; b++) { - struct shash_desc *desc; - u8 *result; int r; - unsigned todo; + struct shash_desc *desc = verity_io_hash_desc(v, io); + + r = verity_hash_for_block(v, io, io->block + b, + verity_io_want_digest(v, io), + &is_zero); + if (unlikely(r < 0)) + return r; - if (likely(v->levels)) { + if (is_zero) { /* - * First, we try to get the requested hash for - * the current block. If the hash block itself is - * verified, zero is returned. If it isn't, this - * function returns 0 and we fall back to whole - * chain verification. + * If we expect a zero block, don't validate, just + * return zeros. */ - int r = verity_verify_level(io, io->block + b, 0, true); - if (likely(!r)) - goto test_block_hash; - if (r < 0) + r = verity_for_bv_block(v, io, &io->iter, + verity_bv_zero); + if (unlikely(r < 0)) return r; - } - memcpy(io_want_digest(v, io), v->root_digest, v->digest_size); - - for (i = v->levels - 1; i >= 0; i--) { - int r = verity_verify_level(io, io->block + b, i, false); - if (unlikely(r)) - return r; + continue; } -test_block_hash: - desc = io_hash_desc(v, io); - desc->tfm = v->tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - r = crypto_shash_init(desc); - if (r < 0) { - DMERR("crypto_shash_init failed: %d", r); + r = verity_hash_init(v, desc); + if (unlikely(r < 0)) return r; - } - - if (likely(v->version >= 1)) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - } - todo = 1 << v->data_dev_block_bits; - do { - u8 *page; - unsigned len; - struct bio_vec bv = bio_iter_iovec(bio, io->iter); - - page = kmap_atomic(bv.bv_page); - len = bv.bv_len; - if (likely(len >= todo)) - len = todo; - r = crypto_shash_update(desc, page + bv.bv_offset, len); - kunmap_atomic(page); - - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - - bio_advance_iter(bio, &io->iter, len); - todo -= len; - } while (todo); - if (!v->version) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - } + start = io->iter; + r = verity_for_bv_block(v, io, &io->iter, verity_bv_hash_update); + if (unlikely(r < 0)) + return r; - result = io_real_digest(v, io); - r = crypto_shash_final(desc, result); - if (r < 0) { - DMERR("crypto_shash_final failed: %d", r); + r = verity_hash_final(v, desc, verity_io_real_digest(v, io)); + if (unlikely(r < 0)) return r; - } - if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, - io->block + b)) - return -EIO; - } + + if (likely(memcmp(verity_io_real_digest(v, io), + verity_io_want_digest(v, io), v->digest_size) == 0)) + continue; + else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b, NULL, &start) == 0) + continue; + else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b)) + return -EIO; } return 0; @@ -453,9 +463,10 @@ static void verity_finish_io(struct dm_verity_io *io, int error) struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size); bio->bi_end_io = io->orig_bi_end_io; - bio->bi_private = io->orig_bi_private; bio->bi_error = error; + verity_fec_finish_io(io); + bio_endio(bio); } @@ -470,7 +481,7 @@ static void verity_end_io(struct bio *bio) { struct dm_verity_io *io = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_error && !verity_fec_is_enabled(io->v)) { verity_finish_io(io, bio->bi_error); return; } @@ -566,7 +577,6 @@ static int verity_map(struct dm_target *ti, struct bio *bio) io = dm_per_bio_data(bio, ti->per_bio_data_size); io->v = v; io->orig_bi_end_io = bio->bi_end_io; - io->orig_bi_private = bio->bi_private; io->block = bio->bi_iter.bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT); io->n_blocks = bio->bi_iter.bi_size >> v->data_dev_block_bits; @@ -574,6 +584,8 @@ static int verity_map(struct dm_target *ti, struct bio *bio) bio->bi_private = io; io->iter = bio->bi_iter; + verity_fec_init_io(io); + verity_submit_prefetch(v, io); generic_make_request(bio); @@ -588,6 +600,7 @@ static void verity_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { struct dm_verity *v = ti->private; + unsigned args = 0; unsigned sz = 0; unsigned x; @@ -614,8 +627,17 @@ static void verity_status(struct dm_target *ti, status_type_t type, else for (x = 0; x < v->salt_size; x++) DMEMIT("%02x", v->salt[x]); + if (v->mode != DM_VERITY_MODE_EIO) + args++; + if (verity_fec_is_enabled(v)) + args += DM_VERITY_OPTS_FEC; + if (v->zero_digest) + args++; + if (!args) + return; + DMEMIT(" %u", args); if (v->mode != DM_VERITY_MODE_EIO) { - DMEMIT(" 1 "); + DMEMIT(" "); switch (v->mode) { case DM_VERITY_MODE_LOGGING: DMEMIT(DM_VERITY_OPT_LOGGING); @@ -627,6 +649,9 @@ static void verity_status(struct dm_target *ti, status_type_t type, BUG(); } } + if (v->zero_digest) + DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES); + sz = verity_fec_status_table(v, sz, result, maxlen); break; } } @@ -677,6 +702,7 @@ static void verity_dtr(struct dm_target *ti) kfree(v->salt); kfree(v->root_digest); + kfree(v->zero_digest); if (v->tfm) crypto_free_shash(v->tfm); @@ -689,9 +715,94 @@ static void verity_dtr(struct dm_target *ti) if (v->data_dev) dm_put_device(ti, v->data_dev); + verity_fec_dtr(v); + kfree(v); } +static int verity_alloc_zero_digest(struct dm_verity *v) +{ + int r = -ENOMEM; + struct shash_desc *desc; + u8 *zero_data; + + v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL); + + if (!v->zero_digest) + return r; + + desc = kmalloc(v->shash_descsize, GFP_KERNEL); + + if (!desc) + return r; /* verity_dtr will free zero_digest */ + + zero_data = kzalloc(1 << v->data_dev_block_bits, GFP_KERNEL); + + if (!zero_data) + goto out; + + r = verity_hash(v, desc, zero_data, 1 << v->data_dev_block_bits, + v->zero_digest); + +out: + kfree(desc); + kfree(zero_data); + + return r; +} + +static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v) +{ + int r; + unsigned argc; + struct dm_target *ti = v->ti; + const char *arg_name; + + static struct dm_arg _args[] = { + {0, DM_VERITY_OPTS_MAX, "Invalid number of feature args"}, + }; + + r = dm_read_arg_group(_args, as, &argc, &ti->error); + if (r) + return -EINVAL; + + if (!argc) + return 0; + + do { + arg_name = dm_shift_arg(as); + argc--; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_LOGGING)) { + v->mode = DM_VERITY_MODE_LOGGING; + continue; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_RESTART)) { + v->mode = DM_VERITY_MODE_RESTART; + continue; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_IGN_ZEROES)) { + r = verity_alloc_zero_digest(v); + if (r) { + ti->error = "Cannot allocate zero digest"; + return r; + } + continue; + + } else if (verity_is_fec_opt_arg(arg_name)) { + r = verity_fec_parse_opt_args(as, v, &argc, arg_name); + if (r) + return r; + continue; + } + + ti->error = "Unrecognized verity feature request"; + return -EINVAL; + } while (argc && !r); + + return r; +} + /* * Target parameters: * <version> The current format is version 1. @@ -710,18 +821,13 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) { struct dm_verity *v; struct dm_arg_set as; - const char *opt_string; - unsigned int num, opt_params; + unsigned int num; unsigned long long num_ll; int r; int i; sector_t hash_position; char dummy; - static struct dm_arg _args[] = { - {0, 1, "Invalid number of feature args"}, - }; - v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL); if (!v) { ti->error = "Cannot allocate verity structure"; @@ -730,6 +836,10 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->private = v; v->ti = ti; + r = verity_fec_ctr_alloc(v); + if (r) + goto bad; + if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) { ti->error = "Device must be readonly"; r = -EINVAL; @@ -866,29 +976,9 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) as.argc = argc; as.argv = argv; - r = dm_read_arg_group(_args, &as, &opt_params, &ti->error); - if (r) + r = verity_parse_opt_args(&as, v); + if (r < 0) goto bad; - - while (opt_params) { - opt_params--; - opt_string = dm_shift_arg(&as); - if (!opt_string) { - ti->error = "Not enough feature arguments"; - r = -EINVAL; - goto bad; - } - - if (!strcasecmp(opt_string, DM_VERITY_OPT_LOGGING)) - v->mode = DM_VERITY_MODE_LOGGING; - else if (!strcasecmp(opt_string, DM_VERITY_OPT_RESTART)) - v->mode = DM_VERITY_MODE_RESTART; - else { - ti->error = "Invalid feature arguments"; - r = -EINVAL; - goto bad; - } - } } v->hash_per_block_bits = @@ -938,8 +1028,6 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } - ti->per_bio_data_size = roundup(sizeof(struct dm_verity_io) + v->shash_descsize + v->digest_size * 2, __alignof__(struct dm_verity_io)); - /* WQ_UNBOUND greatly improves performance when running on ramdisk */ v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus()); if (!v->verify_wq) { @@ -948,6 +1036,16 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } + ti->per_bio_data_size = sizeof(struct dm_verity_io) + + v->shash_descsize + v->digest_size * 2; + + r = verity_fec_ctr(v); + if (r) + goto bad; + + ti->per_bio_data_size = roundup(ti->per_bio_data_size, + __alignof__(struct dm_verity_io)); + return 0; bad: @@ -958,7 +1056,7 @@ bad: static struct target_type verity_target = { .name = "verity", - .version = {1, 2, 0}, + .version = {1, 3, 0}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h new file mode 100644 index 000000000000..fb419f422d73 --- /dev/null +++ b/drivers/md/dm-verity.h @@ -0,0 +1,129 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * Copyright (C) 2015 Google, Inc. + * + * Author: Mikulas Patocka <mpatocka@redhat.com> + * + * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors + * + * This file is released under the GPLv2. + */ + +#ifndef DM_VERITY_H +#define DM_VERITY_H + +#include "dm-bufio.h" +#include <linux/device-mapper.h> +#include <crypto/hash.h> + +#define DM_VERITY_MAX_LEVELS 63 + +enum verity_mode { + DM_VERITY_MODE_EIO, + DM_VERITY_MODE_LOGGING, + DM_VERITY_MODE_RESTART +}; + +enum verity_block_type { + DM_VERITY_BLOCK_TYPE_DATA, + DM_VERITY_BLOCK_TYPE_METADATA +}; + +struct dm_verity_fec; + +struct dm_verity { + struct dm_dev *data_dev; + struct dm_dev *hash_dev; + struct dm_target *ti; + struct dm_bufio_client *bufio; + char *alg_name; + struct crypto_shash *tfm; + u8 *root_digest; /* digest of the root block */ + u8 *salt; /* salt: its size is salt_size */ + u8 *zero_digest; /* digest for a zero block */ + unsigned salt_size; + sector_t data_start; /* data offset in 512-byte sectors */ + sector_t hash_start; /* hash start in blocks */ + sector_t data_blocks; /* the number of data blocks */ + sector_t hash_blocks; /* the number of hash blocks */ + unsigned char data_dev_block_bits; /* log2(data blocksize) */ + unsigned char hash_dev_block_bits; /* log2(hash blocksize) */ + unsigned char hash_per_block_bits; /* log2(hashes in hash block) */ + unsigned char levels; /* the number of tree levels */ + unsigned char version; + unsigned digest_size; /* digest size for the current hash algorithm */ + unsigned shash_descsize;/* the size of temporary space for crypto */ + int hash_failed; /* set to 1 if hash of any block failed */ + enum verity_mode mode; /* mode for handling verification errors */ + unsigned corrupted_errs;/* Number of errors for corrupted blocks */ + + struct workqueue_struct *verify_wq; + + /* starting blocks for each tree level. 0 is the lowest level. */ + sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; + + struct dm_verity_fec *fec; /* forward error correction */ +}; + +struct dm_verity_io { + struct dm_verity *v; + + /* original value of bio->bi_end_io */ + bio_end_io_t *orig_bi_end_io; + + sector_t block; + unsigned n_blocks; + + struct bvec_iter iter; + + struct work_struct work; + + /* + * Three variably-size fields follow this struct: + * + * u8 hash_desc[v->shash_descsize]; + * u8 real_digest[v->digest_size]; + * u8 want_digest[v->digest_size]; + * + * To access them use: verity_io_hash_desc(), verity_io_real_digest() + * and verity_io_want_digest(). + */ +}; + +static inline struct shash_desc *verity_io_hash_desc(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (struct shash_desc *)(io + 1); +} + +static inline u8 *verity_io_real_digest(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (u8 *)(io + 1) + v->shash_descsize; +} + +static inline u8 *verity_io_want_digest(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (u8 *)(io + 1) + v->shash_descsize + v->digest_size; +} + +static inline u8 *verity_io_digest_end(struct dm_verity *v, + struct dm_verity_io *io) +{ + return verity_io_want_digest(v, io) + v->digest_size; +} + +extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter *iter, + int (*process)(struct dm_verity *v, + struct dm_verity_io *io, + u8 *data, size_t len)); + +extern int verity_hash(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len, u8 *digest); + +extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, u8 *digest, bool *is_zero); + +#endif /* DM_VERITY_H */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 5df40480228b..c338aebb4ccd 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1109,12 +1109,8 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) * back into ->request_fn() could deadlock attempting to grab the * queue lock again. */ - if (run_queue) { - if (md->queue->mq_ops) - blk_mq_run_hw_queues(md->queue, true); - else - blk_run_queue_async(md->queue); - } + if (!md->queue->mq_ops && run_queue) + blk_run_queue_async(md->queue); /* * dm_put() must be at the end of this function. See the comment above @@ -1191,6 +1187,8 @@ static void dm_unprep_request(struct request *rq) if (clone) free_rq_clone(clone); + else if (!tio->md->queue->mq_ops) + free_rq_tio(tio); } /* @@ -1212,9 +1210,9 @@ static void dm_requeue_original_request(struct mapped_device *md, { int rw = rq_data_dir(rq); + rq_end_stats(md, rq); dm_unprep_request(rq); - rq_end_stats(md, rq); if (!rq->q->mq_ops) old_requeue_request(rq); else { @@ -1334,7 +1332,10 @@ static void dm_complete_request(struct request *rq, int error) struct dm_rq_target_io *tio = tio_from_request(rq); tio->error = error; - blk_complete_request(rq); + if (!rq->q->mq_ops) + blk_complete_request(rq); + else + blk_mq_complete_request(rq, error); } /* diff --git a/drivers/md/md.c b/drivers/md/md.c index 61aacab424cf..c57fdf847b47 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -293,6 +293,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) * go away inside make_request */ sectors = bio_sectors(bio); + /* bio could be mergeable after passing to underlayer */ + bio->bi_rw &= ~REQ_NOMERGE; mddev->pers->make_request(mddev, bio); cpu = part_stat_lock(); @@ -2017,28 +2019,32 @@ int md_integrity_register(struct mddev *mddev) } EXPORT_SYMBOL(md_integrity_register); -/* Disable data integrity if non-capable/non-matching disk is being added */ -void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) +/* + * Attempt to add an rdev, but only if it is consistent with the current + * integrity profile + */ +int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) { struct blk_integrity *bi_rdev; struct blk_integrity *bi_mddev; + char name[BDEVNAME_SIZE]; if (!mddev->gendisk) - return; + return 0; bi_rdev = bdev_get_integrity(rdev->bdev); bi_mddev = blk_get_integrity(mddev->gendisk); if (!bi_mddev) /* nothing to do */ - return; - if (rdev->raid_disk < 0) /* skip spares */ - return; - if (bi_rdev && blk_integrity_compare(mddev->gendisk, - rdev->bdev->bd_disk) >= 0) - return; - WARN_ON_ONCE(!mddev->suspended); - printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev)); - blk_integrity_unregister(mddev->gendisk); + return 0; + + if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) { + printk(KERN_NOTICE "%s: incompatible integrity profile for %s\n", + mdname(mddev), bdevname(rdev->bdev, name)); + return -ENXIO; + } + + return 0; } EXPORT_SYMBOL(md_integrity_add_rdev); diff --git a/drivers/md/md.h b/drivers/md/md.h index ca0b643fe3c1..dfa57b41541b 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -657,7 +657,7 @@ extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); -extern void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); +extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern void mddev_init(struct mddev *mddev); diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 7331a80d89f1..dd483bb2e111 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -129,7 +129,9 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio) } multipath = conf->multipaths + mp_bh->path; - mp_bh->bio = *bio; + bio_init(&mp_bh->bio); + __bio_clone_fast(&mp_bh->bio, bio); + mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset; mp_bh->bio.bi_bdev = multipath->rdev->bdev; mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT; @@ -257,6 +259,9 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); + err = md_integrity_add_rdev(rdev, mddev); + if (err) + break; spin_lock_irq(&conf->device_lock); mddev->degraded--; rdev->raid_disk = path; @@ -264,9 +269,6 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) spin_unlock_irq(&conf->device_lock); rcu_assign_pointer(p->rdev, rdev); err = 0; - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); break; } diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index fca6dbcf9a47..7e44005595c1 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -152,12 +152,9 @@ static int brb_peek(struct bop_ring_buffer *brb, struct block_op *result) static int brb_pop(struct bop_ring_buffer *brb) { - struct block_op *bop; - if (brb_empty(brb)) return -ENODATA; - bop = brb->bops + brb->begin; brb->begin = brb_next(brb, brb->begin); return 0; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index e2169ff6e0f0..515554c7365b 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1589,6 +1589,9 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (mddev->recovery_disabled == conf->recovery_disabled) return -EBUSY; + if (md_integrity_add_rdev(rdev, mddev)) + return -ENXIO; + if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -1632,9 +1635,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); print_conf(conf); @@ -2274,6 +2274,7 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) if (fail) { spin_lock_irq(&conf->device_lock); list_add(&r1_bio->retry_list, &conf->bio_end_io_list); + conf->nr_queued++; spin_unlock_irq(&conf->device_lock); md_wakeup_thread(conf->mddev->thread); } else { @@ -2391,8 +2392,10 @@ static void raid1d(struct md_thread *thread) LIST_HEAD(tmp); spin_lock_irqsave(&conf->device_lock, flags); if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) { - list_add(&tmp, &conf->bio_end_io_list); - list_del_init(&conf->bio_end_io_list); + while (!list_empty(&conf->bio_end_io_list)) { + list_move(conf->bio_end_io_list.prev, &tmp); + conf->nr_queued--; + } } spin_unlock_irqrestore(&conf->device_lock, flags); while (!list_empty(&tmp)) { diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 96c1f6c3eac9..c67e11882278 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1787,6 +1787,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1)) return -EINVAL; + if (md_integrity_add_rdev(rdev, mddev)) + return -ENXIO; + if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -1828,9 +1831,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) rcu_assign_pointer(p->rdev, rdev); break; } - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); @@ -2753,6 +2753,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) if (fail) { spin_lock_irq(&conf->device_lock); list_add(&r10_bio->retry_list, &conf->bio_end_io_list); + conf->nr_queued++; spin_unlock_irq(&conf->device_lock); md_wakeup_thread(conf->mddev->thread); } else { @@ -2780,8 +2781,10 @@ static void raid10d(struct md_thread *thread) LIST_HEAD(tmp); spin_lock_irqsave(&conf->device_lock, flags); if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) { - list_add(&tmp, &conf->bio_end_io_list); - list_del_init(&conf->bio_end_io_list); + while (!list_empty(&conf->bio_end_io_list)) { + list_move(conf->bio_end_io_list.prev, &tmp); + conf->nr_queued--; + } } spin_unlock_irqrestore(&conf->device_lock, flags); while (!list_empty(&tmp)) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 704ef7fcfbf8..10ce885445f6 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -340,8 +340,7 @@ static void release_inactive_stripe_list(struct r5conf *conf, int hash) { int size; - unsigned long do_wakeup = 0; - int i = 0; + bool do_wakeup = false; unsigned long flags; if (hash == NR_STRIPE_HASH_LOCKS) { @@ -362,19 +361,15 @@ static void release_inactive_stripe_list(struct r5conf *conf, !list_empty(list)) atomic_dec(&conf->empty_inactive_list_nr); list_splice_tail_init(list, conf->inactive_list + hash); - do_wakeup |= 1 << hash; + do_wakeup = true; spin_unlock_irqrestore(conf->hash_locks + hash, flags); } size--; hash--; } - for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) { - if (do_wakeup & (1 << i)) - wake_up(&conf->wait_for_stripe[i]); - } - if (do_wakeup) { + wake_up(&conf->wait_for_stripe); if (atomic_read(&conf->active_stripes) == 0) wake_up(&conf->wait_for_quiescent); if (conf->retry_read_aligned) @@ -687,15 +682,14 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector, if (!sh) { set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); - wait_event_exclusive_cmd( - conf->wait_for_stripe[hash], + wait_event_lock_irq( + conf->wait_for_stripe, !list_empty(conf->inactive_list + hash) && (atomic_read(&conf->active_stripes) < (conf->max_nr_stripes * 3 / 4) || !test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)), - spin_unlock_irq(conf->hash_locks + hash), - spin_lock_irq(conf->hash_locks + hash)); + *(conf->hash_locks + hash)); clear_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); } else { @@ -720,9 +714,6 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector, } } while (sh == NULL); - if (!list_empty(conf->inactive_list + hash)) - wake_up(&conf->wait_for_stripe[hash]); - spin_unlock_irq(conf->hash_locks + hash); return sh; } @@ -2091,6 +2082,14 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors) unsigned long cpu; int err = 0; + /* + * Never shrink. And mddev_suspend() could deadlock if this is called + * from raid5d. In that case, scribble_disks and scribble_sectors + * should equal to new_disks and new_sectors + */ + if (conf->scribble_disks >= new_disks && + conf->scribble_sectors >= new_sectors) + return 0; mddev_suspend(conf->mddev); get_online_cpus(); for_each_present_cpu(cpu) { @@ -2112,6 +2111,10 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors) } put_online_cpus(); mddev_resume(conf->mddev); + if (!err) { + conf->scribble_disks = new_disks; + conf->scribble_sectors = new_sectors; + } return err; } @@ -2192,7 +2195,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) cnt = 0; list_for_each_entry(nsh, &newstripes, lru) { lock_device_hash_lock(conf, hash); - wait_event_exclusive_cmd(conf->wait_for_stripe[hash], + wait_event_cmd(conf->wait_for_stripe, !list_empty(conf->inactive_list + hash), unlock_device_hash_lock(conf, hash), lock_device_hash_lock(conf, hash)); @@ -4238,7 +4241,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) | (1 << STRIPE_SYNCING) | (1 << STRIPE_REPLACED) | - (1 << STRIPE_PREREAD_ACTIVE) | (1 << STRIPE_DELAYED) | (1 << STRIPE_BIT_DELAY) | (1 << STRIPE_FULL_WRITE) | @@ -4253,6 +4255,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, (1 << STRIPE_REPLACED))); set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | + (1 << STRIPE_PREREAD_ACTIVE) | (1 << STRIPE_DEGRADED)), head_sh->state & (1 << STRIPE_INSYNC)); @@ -6414,6 +6417,12 @@ static int raid5_alloc_percpu(struct r5conf *conf) } put_online_cpus(); + if (!err) { + conf->scribble_disks = max(conf->raid_disks, + conf->previous_raid_disks); + conf->scribble_sectors = max(conf->chunk_sectors, + conf->prev_chunk_sectors); + } return err; } @@ -6504,9 +6513,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) seqcount_init(&conf->gen_lock); mutex_init(&conf->cache_size_mutex); init_waitqueue_head(&conf->wait_for_quiescent); - for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) { - init_waitqueue_head(&conf->wait_for_stripe[i]); - } + init_waitqueue_head(&conf->wait_for_stripe); init_waitqueue_head(&conf->wait_for_overlap); INIT_LIST_HEAD(&conf->handle_list); INIT_LIST_HEAD(&conf->hold_list); @@ -7015,8 +7022,8 @@ static int run(struct mddev *mddev) } if (discard_supported && - mddev->queue->limits.max_discard_sectors >= stripe && - mddev->queue->limits.discard_granularity >= stripe) + mddev->queue->limits.max_discard_sectors >= (stripe >> 9) && + mddev->queue->limits.discard_granularity >= stripe) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); else diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index a415e1cd39b8..517d4b68a1be 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -510,6 +510,8 @@ struct r5conf { * conversions */ } __percpu *percpu; + int scribble_disks; + int scribble_sectors; #ifdef CONFIG_HOTPLUG_CPU struct notifier_block cpu_notify; #endif @@ -522,7 +524,7 @@ struct r5conf { atomic_t empty_inactive_list_nr; struct llist_head released_stripes; wait_queue_head_t wait_for_quiescent; - wait_queue_head_t wait_for_stripe[NR_STRIPE_HASH_LOCKS]; + wait_queue_head_t wait_for_stripe; wait_queue_head_t wait_for_overlap; unsigned long cache_state; #define R5_INACTIVE_BLOCKED 1 /* release of inactive stripes blocked, diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index c38ef1a72b4a..e2a3833170e3 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -2313,9 +2313,9 @@ static int dvb_frontend_ioctl_legacy(struct file *file, dev_dbg(fe->dvb->device, "%s: current delivery system on cache: %d, V3 type: %d\n", __func__, c->delivery_system, fe->ops.info.type); - /* Force the CAN_INVERSION_AUTO bit on. If the frontend doesn't - * do it, it is done for it. */ - info->caps |= FE_CAN_INVERSION_AUTO; + /* Set CAN_INVERSION_AUTO bit on in other than oneshot mode */ + if (!(fepriv->tune_mode_flags & FE_TUNE_MODE_ONESHOT)) + info->caps |= FE_CAN_INVERSION_AUTO; err = 0; break; } diff --git a/drivers/media/dvb-frontends/tda1004x.c b/drivers/media/dvb-frontends/tda1004x.c index 0e209b56c76c..c6abeb4fba9d 100644 --- a/drivers/media/dvb-frontends/tda1004x.c +++ b/drivers/media/dvb-frontends/tda1004x.c @@ -903,9 +903,18 @@ static int tda1004x_get_fe(struct dvb_frontend *fe) { struct dtv_frontend_properties *fe_params = &fe->dtv_property_cache; struct tda1004x_state* state = fe->demodulator_priv; + int status; dprintk("%s\n", __func__); + status = tda1004x_read_byte(state, TDA1004X_STATUS_CD); + if (status == -1) + return -EIO; + + /* Only update the properties cache if device is locked */ + if (!(status & 8)) + return 0; + // inversion status fe_params->inversion = INVERSION_OFF; if (tda1004x_read_byte(state, TDA1004X_CONFC1) & 0x20) diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c index e4900df1140b..c24839cfcc35 100644 --- a/drivers/media/i2c/adv7511.c +++ b/drivers/media/i2c/adv7511.c @@ -1161,12 +1161,23 @@ static void adv7511_dbg_dump_edid(int lvl, int debug, struct v4l2_subdev *sd, in } } +static void adv7511_notify_no_edid(struct v4l2_subdev *sd) +{ + struct adv7511_state *state = get_adv7511_state(sd); + struct adv7511_edid_detect ed; + + /* We failed to read the EDID, so send an event for this. */ + ed.present = false; + ed.segment = adv7511_rd(sd, 0xc4); + v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed); + v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, 0x0); +} + static void adv7511_edid_handler(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct adv7511_state *state = container_of(dwork, struct adv7511_state, edid_handler); struct v4l2_subdev *sd = &state->sd; - struct adv7511_edid_detect ed; v4l2_dbg(1, debug, sd, "%s:\n", __func__); @@ -1191,9 +1202,7 @@ static void adv7511_edid_handler(struct work_struct *work) } /* We failed to read the EDID, so send an event for this. */ - ed.present = false; - ed.segment = adv7511_rd(sd, 0xc4); - v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed); + adv7511_notify_no_edid(sd); v4l2_dbg(1, debug, sd, "%s: no edid found\n", __func__); } @@ -1264,7 +1273,6 @@ static void adv7511_check_monitor_present_status(struct v4l2_subdev *sd) /* update read only ctrls */ v4l2_ctrl_s_ctrl(state->hotplug_ctrl, adv7511_have_hotplug(sd) ? 0x1 : 0x0); v4l2_ctrl_s_ctrl(state->rx_sense_ctrl, adv7511_have_rx_sense(sd) ? 0x1 : 0x0); - v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, state->edid.segments ? 0x1 : 0x0); if ((status & MASK_ADV7511_HPD_DETECT) && ((status & MASK_ADV7511_MSEN_DETECT) || state->edid.segments)) { v4l2_dbg(1, debug, sd, "%s: hotplug and (rx-sense or edid)\n", __func__); @@ -1294,6 +1302,7 @@ static void adv7511_check_monitor_present_status(struct v4l2_subdev *sd) } adv7511_s_power(sd, false); memset(&state->edid, 0, sizeof(struct adv7511_state_edid)); + adv7511_notify_no_edid(sd); } } @@ -1370,6 +1379,7 @@ static bool adv7511_check_edid_status(struct v4l2_subdev *sd) } /* one more segment read ok */ state->edid.segments = segment + 1; + v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, 0x1); if (((state->edid.data[0x7e] >> 1) + 1) > state->edid.segments) { /* Request next EDID segment */ v4l2_dbg(1, debug, sd, "%s: request segment %d\n", __func__, state->edid.segments); @@ -1389,7 +1399,6 @@ static bool adv7511_check_edid_status(struct v4l2_subdev *sd) ed.present = true; ed.segment = 0; state->edid_detect_counter++; - v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, state->edid.segments ? 0x1 : 0x0); v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed); return ed.present; } diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index 5631ec004eed..01adcdc52346 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -1960,10 +1960,9 @@ static int adv76xx_isr(struct v4l2_subdev *sd, u32 status, bool *handled) } /* tx 5v detect */ - tx_5v = io_read(sd, 0x70) & info->cable_det_mask; + tx_5v = irq_reg_0x70 & info->cable_det_mask; if (tx_5v) { v4l2_dbg(1, debug, sd, "%s: tx_5v: 0x%x\n", __func__, tx_5v); - io_write(sd, 0x71, tx_5v); adv76xx_s_detect_tx_5v_ctrl(sd); if (handled) *handled = true; diff --git a/drivers/media/i2c/ir-kbd-i2c.c b/drivers/media/i2c/ir-kbd-i2c.c index 728d2cc8a3e7..175a76114953 100644 --- a/drivers/media/i2c/ir-kbd-i2c.c +++ b/drivers/media/i2c/ir-kbd-i2c.c @@ -478,7 +478,6 @@ static const struct i2c_device_id ir_kbd_id[] = { { "ir_rx_z8f0811_hdpvr", 0 }, { } }; -MODULE_DEVICE_TABLE(i2c, ir_kbd_id); static struct i2c_driver ir_kbd_driver = { .driver = { diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c index 15a4ebc2844d..51dbef2f9a48 100644 --- a/drivers/media/pci/bt8xx/bttv-driver.c +++ b/drivers/media/pci/bt8xx/bttv-driver.c @@ -2334,6 +2334,19 @@ static int bttv_g_fmt_vid_overlay(struct file *file, void *priv, return 0; } +static void bttv_get_width_mask_vid_cap(const struct bttv_format *fmt, + unsigned int *width_mask, + unsigned int *width_bias) +{ + if (fmt->flags & FORMAT_FLAGS_PLANAR) { + *width_mask = ~15; /* width must be a multiple of 16 pixels */ + *width_bias = 8; /* nearest */ + } else { + *width_mask = ~3; /* width must be a multiple of 4 pixels */ + *width_bias = 2; /* nearest */ + } +} + static int bttv_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { @@ -2343,6 +2356,7 @@ static int bttv_try_fmt_vid_cap(struct file *file, void *priv, enum v4l2_field field; __s32 width, height; __s32 height2; + unsigned int width_mask, width_bias; int rc; fmt = format_by_fourcc(f->fmt.pix.pixelformat); @@ -2375,9 +2389,9 @@ static int bttv_try_fmt_vid_cap(struct file *file, void *priv, width = f->fmt.pix.width; height = f->fmt.pix.height; + bttv_get_width_mask_vid_cap(fmt, &width_mask, &width_bias); rc = limit_scaled_size_lock(fh, &width, &height, field, - /* width_mask: 4 pixels */ ~3, - /* width_bias: nearest */ 2, + width_mask, width_bias, /* adjust_size */ 1, /* adjust_crop */ 0); if (0 != rc) @@ -2410,6 +2424,7 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv, struct bttv_fh *fh = priv; struct bttv *btv = fh->btv; __s32 width, height; + unsigned int width_mask, width_bias; enum v4l2_field field; retval = bttv_switch_type(fh, f->type); @@ -2424,9 +2439,10 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv, height = f->fmt.pix.height; field = f->fmt.pix.field; + fmt = format_by_fourcc(f->fmt.pix.pixelformat); + bttv_get_width_mask_vid_cap(fmt, &width_mask, &width_bias); retval = limit_scaled_size_lock(fh, &width, &height, f->fmt.pix.field, - /* width_mask: 4 pixels */ ~3, - /* width_bias: nearest */ 2, + width_mask, width_bias, /* adjust_size */ 1, /* adjust_crop */ 1); if (0 != retval) @@ -2434,8 +2450,6 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv, f->fmt.pix.field = field; - fmt = format_by_fourcc(f->fmt.pix.pixelformat); - /* update our state informations */ fh->fmt = fmt; fh->cap.field = f->fmt.pix.field; diff --git a/drivers/media/pci/saa7134/saa7134-alsa.c b/drivers/media/pci/saa7134/saa7134-alsa.c index 1d2c310ce838..94f816244407 100644 --- a/drivers/media/pci/saa7134/saa7134-alsa.c +++ b/drivers/media/pci/saa7134/saa7134-alsa.c @@ -1211,6 +1211,8 @@ static int alsa_device_init(struct saa7134_dev *dev) static int alsa_device_exit(struct saa7134_dev *dev) { + if (!snd_saa7134_cards[dev->nr]) + return 1; snd_card_free(snd_saa7134_cards[dev->nr]); snd_saa7134_cards[dev->nr] = NULL; @@ -1260,7 +1262,8 @@ static void saa7134_alsa_exit(void) int idx; for (idx = 0; idx < SNDRV_CARDS; idx++) { - snd_card_free(snd_saa7134_cards[idx]); + if (snd_saa7134_cards[idx]) + snd_card_free(snd_saa7134_cards[idx]); } saa7134_dmasound_init = NULL; diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c index 518086c7aed5..15e56c07b217 100644 --- a/drivers/media/pci/saa7134/saa7134-video.c +++ b/drivers/media/pci/saa7134/saa7134-video.c @@ -1219,10 +1219,13 @@ static int saa7134_g_fmt_vid_cap(struct file *file, void *priv, f->fmt.pix.height = dev->height; f->fmt.pix.field = dev->field; f->fmt.pix.pixelformat = dev->fmt->fourcc; - f->fmt.pix.bytesperline = - (f->fmt.pix.width * dev->fmt->depth) >> 3; + if (dev->fmt->planar) + f->fmt.pix.bytesperline = f->fmt.pix.width; + else + f->fmt.pix.bytesperline = + (f->fmt.pix.width * dev->fmt->depth) / 8; f->fmt.pix.sizeimage = - f->fmt.pix.height * f->fmt.pix.bytesperline; + (f->fmt.pix.height * f->fmt.pix.width * dev->fmt->depth) / 8; f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M; return 0; } @@ -1298,10 +1301,13 @@ static int saa7134_try_fmt_vid_cap(struct file *file, void *priv, if (f->fmt.pix.height > maxh) f->fmt.pix.height = maxh; f->fmt.pix.width &= ~0x03; - f->fmt.pix.bytesperline = - (f->fmt.pix.width * fmt->depth) >> 3; + if (fmt->planar) + f->fmt.pix.bytesperline = f->fmt.pix.width; + else + f->fmt.pix.bytesperline = + (f->fmt.pix.width * fmt->depth) / 8; f->fmt.pix.sizeimage = - f->fmt.pix.height * f->fmt.pix.bytesperline; + (f->fmt.pix.height * f->fmt.pix.width * fmt->depth) / 8; f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M; return 0; diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c index 654e964f84a2..d76511c1c1e3 100644 --- a/drivers/media/platform/coda/coda-bit.c +++ b/drivers/media/platform/coda/coda-bit.c @@ -1342,7 +1342,7 @@ static void coda_finish_encode(struct coda_ctx *ctx) /* Calculate bytesused field */ if (dst_buf->sequence == 0) { - vb2_set_plane_payload(&dst_buf->vb2_buf, 0, + vb2_set_plane_payload(&dst_buf->vb2_buf, 0, wr_ptr - start_ptr + ctx->vpu_header_size[0] + ctx->vpu_header_size[1] + ctx->vpu_header_size[2]); diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c index 15516a6e3a39..323aad3c89de 100644 --- a/drivers/media/platform/coda/coda-common.c +++ b/drivers/media/platform/coda/coda-common.c @@ -2119,14 +2119,12 @@ static int coda_probe(struct platform_device *pdev) pdev_id = of_id ? of_id->data : platform_get_device_id(pdev); - if (of_id) { + if (of_id) dev->devtype = of_id->data; - } else if (pdev_id) { + else if (pdev_id) dev->devtype = &coda_devdata[pdev_id->driver_data]; - } else { - ret = -EINVAL; - goto err_v4l2_register; - } + else + return -EINVAL; spin_lock_init(&dev->irqlock); INIT_LIST_HEAD(&dev->instances); diff --git a/drivers/media/platform/vsp1/vsp1_sru.c b/drivers/media/platform/vsp1/vsp1_sru.c index 6310acab60e7..d41ae950d1a1 100644 --- a/drivers/media/platform/vsp1/vsp1_sru.c +++ b/drivers/media/platform/vsp1/vsp1_sru.c @@ -154,6 +154,7 @@ static int sru_s_stream(struct v4l2_subdev *subdev, int enable) mutex_lock(sru->ctrls.lock); ctrl0 |= vsp1_sru_read(sru, VI6_SRU_CTRL0) & (VI6_SRU_CTRL0_PARAM0_MASK | VI6_SRU_CTRL0_PARAM1_MASK); + vsp1_sru_write(sru, VI6_SRU_CTRL0, ctrl0); mutex_unlock(sru->ctrls.lock); vsp1_sru_write(sru, VI6_SRU_CTRL1, VI6_SRU_CTRL1_PARAM5); diff --git a/drivers/media/rc/sunxi-cir.c b/drivers/media/rc/sunxi-cir.c index 7830aef3db45..40f77685cc4a 100644 --- a/drivers/media/rc/sunxi-cir.c +++ b/drivers/media/rc/sunxi-cir.c @@ -153,6 +153,8 @@ static int sunxi_ir_probe(struct platform_device *pdev) if (!ir) return -ENOMEM; + spin_lock_init(&ir->ir_lock); + if (of_device_is_compatible(dn, "allwinner,sun5i-a13-ir")) ir->fifo_size = 64; else diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c index ce157edd45fa..0e1ca2b00e61 100644 --- a/drivers/media/tuners/si2157.c +++ b/drivers/media/tuners/si2157.c @@ -168,6 +168,7 @@ static int si2157_init(struct dvb_frontend *fe) len = fw->data[fw->size - remaining]; if (len > SI2157_ARGLEN) { dev_err(&client->dev, "Bad firmware length\n"); + ret = -EINVAL; goto err_release_firmware; } memcpy(cmd.args, &fw->data[(fw->size - remaining) + 1], len); diff --git a/drivers/media/usb/au0828/au0828-core.c b/drivers/media/usb/au0828/au0828-core.c index 0934024fb89d..d91ded795c93 100644 --- a/drivers/media/usb/au0828/au0828-core.c +++ b/drivers/media/usb/au0828/au0828-core.c @@ -159,7 +159,7 @@ static void au0828_usb_disconnect(struct usb_interface *interface) Set the status so poll routines can check and avoid access after disconnect. */ - dev->dev_state = DEV_DISCONNECTED; + set_bit(DEV_DISCONNECTED, &dev->dev_state); au0828_rc_unregister(dev); /* Digital TV */ diff --git a/drivers/media/usb/au0828/au0828-input.c b/drivers/media/usb/au0828/au0828-input.c index b0f067971979..3d6687f0407d 100644 --- a/drivers/media/usb/au0828/au0828-input.c +++ b/drivers/media/usb/au0828/au0828-input.c @@ -130,7 +130,7 @@ static int au0828_get_key_au8522(struct au0828_rc *ir) bool first = true; /* do nothing if device is disconnected */ - if (ir->dev->dev_state == DEV_DISCONNECTED) + if (test_bit(DEV_DISCONNECTED, &ir->dev->dev_state)) return 0; /* Check IR int */ @@ -260,7 +260,7 @@ static void au0828_rc_stop(struct rc_dev *rc) cancel_delayed_work_sync(&ir->work); /* do nothing if device is disconnected */ - if (ir->dev->dev_state != DEV_DISCONNECTED) { + if (!test_bit(DEV_DISCONNECTED, &ir->dev->dev_state)) { /* Disable IR */ au8522_rc_clear(ir, 0xe0, 1 << 4); } diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c index 45c622e234f7..7b2fe1b56039 100644 --- a/drivers/media/usb/au0828/au0828-video.c +++ b/drivers/media/usb/au0828/au0828-video.c @@ -104,14 +104,13 @@ static inline void print_err_status(struct au0828_dev *dev, static int check_dev(struct au0828_dev *dev) { - if (dev->dev_state & DEV_DISCONNECTED) { + if (test_bit(DEV_DISCONNECTED, &dev->dev_state)) { pr_info("v4l2 ioctl: device not present\n"); return -ENODEV; } - if (dev->dev_state & DEV_MISCONFIGURED) { - pr_info("v4l2 ioctl: device is misconfigured; " - "close and open it again\n"); + if (test_bit(DEV_MISCONFIGURED, &dev->dev_state)) { + pr_info("v4l2 ioctl: device is misconfigured; close and open it again\n"); return -EIO; } return 0; @@ -519,8 +518,8 @@ static inline int au0828_isoc_copy(struct au0828_dev *dev, struct urb *urb) if (!dev) return 0; - if ((dev->dev_state & DEV_DISCONNECTED) || - (dev->dev_state & DEV_MISCONFIGURED)) + if (test_bit(DEV_DISCONNECTED, &dev->dev_state) || + test_bit(DEV_MISCONFIGURED, &dev->dev_state)) return 0; if (urb->status < 0) { @@ -766,10 +765,10 @@ static int au0828_stream_interrupt(struct au0828_dev *dev) int ret = 0; dev->stream_state = STREAM_INTERRUPT; - if (dev->dev_state == DEV_DISCONNECTED) + if (test_bit(DEV_DISCONNECTED, &dev->dev_state)) return -ENODEV; else if (ret) { - dev->dev_state = DEV_MISCONFIGURED; + set_bit(DEV_MISCONFIGURED, &dev->dev_state); dprintk(1, "%s device is misconfigured!\n", __func__); return ret; } @@ -958,7 +957,7 @@ static int au0828_v4l2_open(struct file *filp) int ret; dprintk(1, - "%s called std_set %d dev_state %d stream users %d users %d\n", + "%s called std_set %d dev_state %ld stream users %d users %d\n", __func__, dev->std_set_in_tuner_core, dev->dev_state, dev->streaming_users, dev->users); @@ -977,7 +976,7 @@ static int au0828_v4l2_open(struct file *filp) au0828_analog_stream_enable(dev); au0828_analog_stream_reset(dev); dev->stream_state = STREAM_OFF; - dev->dev_state |= DEV_INITIALIZED; + set_bit(DEV_INITIALIZED, &dev->dev_state); } dev->users++; mutex_unlock(&dev->lock); @@ -991,7 +990,7 @@ static int au0828_v4l2_close(struct file *filp) struct video_device *vdev = video_devdata(filp); dprintk(1, - "%s called std_set %d dev_state %d stream users %d users %d\n", + "%s called std_set %d dev_state %ld stream users %d users %d\n", __func__, dev->std_set_in_tuner_core, dev->dev_state, dev->streaming_users, dev->users); @@ -1007,7 +1006,7 @@ static int au0828_v4l2_close(struct file *filp) del_timer_sync(&dev->vbi_timeout); } - if (dev->dev_state == DEV_DISCONNECTED) + if (test_bit(DEV_DISCONNECTED, &dev->dev_state)) goto end; if (dev->users == 1) { @@ -1036,7 +1035,7 @@ static void au0828_init_tuner(struct au0828_dev *dev) .type = V4L2_TUNER_ANALOG_TV, }; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); if (dev->std_set_in_tuner_core) @@ -1108,7 +1107,7 @@ static int vidioc_querycap(struct file *file, void *priv, struct video_device *vdev = video_devdata(file); struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); strlcpy(cap->driver, "au0828", sizeof(cap->driver)); @@ -1151,7 +1150,7 @@ static int vidioc_g_fmt_vid_cap(struct file *file, void *priv, { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); f->fmt.pix.width = dev->width; @@ -1170,7 +1169,7 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *priv, { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); return au0828_set_format(dev, VIDIOC_TRY_FMT, f); @@ -1182,7 +1181,7 @@ static int vidioc_s_fmt_vid_cap(struct file *file, void *priv, struct au0828_dev *dev = video_drvdata(file); int rc; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); rc = check_dev(dev); @@ -1204,7 +1203,7 @@ static int vidioc_s_std(struct file *file, void *priv, v4l2_std_id norm) { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); if (norm == dev->std) @@ -1236,7 +1235,7 @@ static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *norm) { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); *norm = dev->std; @@ -1259,7 +1258,7 @@ static int vidioc_enum_input(struct file *file, void *priv, [AU0828_VMUX_DEBUG] = "tv debug" }; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); tmp = input->index; @@ -1289,7 +1288,7 @@ static int vidioc_g_input(struct file *file, void *priv, unsigned int *i) { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); *i = dev->ctrl_input; @@ -1300,7 +1299,7 @@ static void au0828_s_input(struct au0828_dev *dev, int index) { int i; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); switch (AUVI_INPUT(index).type) { @@ -1385,7 +1384,7 @@ static int vidioc_g_audio(struct file *file, void *priv, struct v4l2_audio *a) { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); a->index = dev->ctrl_ainput; @@ -1405,7 +1404,7 @@ static int vidioc_s_audio(struct file *file, void *priv, const struct v4l2_audio if (a->index != dev->ctrl_ainput) return -EINVAL; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); return 0; } @@ -1417,7 +1416,7 @@ static int vidioc_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t) if (t->index != 0) return -EINVAL; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); strcpy(t->name, "Auvitek tuner"); @@ -1437,7 +1436,7 @@ static int vidioc_s_tuner(struct file *file, void *priv, if (t->index != 0) return -EINVAL; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); au0828_init_tuner(dev); @@ -1459,7 +1458,7 @@ static int vidioc_g_frequency(struct file *file, void *priv, if (freq->tuner != 0) return -EINVAL; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); freq->frequency = dev->ctrl_freq; return 0; @@ -1474,7 +1473,7 @@ static int vidioc_s_frequency(struct file *file, void *priv, if (freq->tuner != 0) return -EINVAL; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); au0828_init_tuner(dev); @@ -1500,7 +1499,7 @@ static int vidioc_g_fmt_vbi_cap(struct file *file, void *priv, { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); format->fmt.vbi.samples_per_line = dev->vbi_width; @@ -1526,7 +1525,7 @@ static int vidioc_cropcap(struct file *file, void *priv, if (cc->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) return -EINVAL; - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); cc->bounds.left = 0; @@ -1548,7 +1547,7 @@ static int vidioc_g_register(struct file *file, void *priv, { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); reg->val = au0828_read(dev, reg->reg); @@ -1561,7 +1560,7 @@ static int vidioc_s_register(struct file *file, void *priv, { struct au0828_dev *dev = video_drvdata(file); - dprintk(1, "%s called std_set %d dev_state %d\n", __func__, + dprintk(1, "%s called std_set %d dev_state %ld\n", __func__, dev->std_set_in_tuner_core, dev->dev_state); return au0828_writereg(dev, reg->reg, reg->val); diff --git a/drivers/media/usb/au0828/au0828.h b/drivers/media/usb/au0828/au0828.h index 60b59391ea2a..d1b6405a05a4 100644 --- a/drivers/media/usb/au0828/au0828.h +++ b/drivers/media/usb/au0828/au0828.h @@ -21,6 +21,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/bitops.h> #include <linux/usb.h> #include <linux/i2c.h> #include <linux/i2c-algo-bit.h> @@ -122,9 +123,9 @@ enum au0828_stream_state { /* device state */ enum au0828_dev_state { - DEV_INITIALIZED = 0x01, - DEV_DISCONNECTED = 0x02, - DEV_MISCONFIGURED = 0x04 + DEV_INITIALIZED = 0, + DEV_DISCONNECTED = 1, + DEV_MISCONFIGURED = 2 }; struct au0828_dev; @@ -248,7 +249,7 @@ struct au0828_dev { int input_type; int std_set_in_tuner_core; unsigned int ctrl_input; - enum au0828_dev_state dev_state; + long unsigned int dev_state; /* defined at enum au0828_dev_state */; enum au0828_stream_state stream_state; wait_queue_head_t open; diff --git a/drivers/media/usb/gspca/ov534.c b/drivers/media/usb/gspca/ov534.c index 146071b8e116..bfff1d1c70ab 100644 --- a/drivers/media/usb/gspca/ov534.c +++ b/drivers/media/usb/gspca/ov534.c @@ -1491,8 +1491,13 @@ static void sd_set_streamparm(struct gspca_dev *gspca_dev, struct v4l2_fract *tpf = &cp->timeperframe; struct sd *sd = (struct sd *) gspca_dev; - /* Set requested framerate */ - sd->frame_rate = tpf->denominator / tpf->numerator; + if (tpf->numerator == 0 || tpf->denominator == 0) + /* Set default framerate */ + sd->frame_rate = 30; + else + /* Set requested framerate */ + sd->frame_rate = tpf->denominator / tpf->numerator; + if (gspca_dev->streaming) set_frame_rate(gspca_dev); diff --git a/drivers/media/usb/gspca/topro.c b/drivers/media/usb/gspca/topro.c index c70ff406b07a..c028a5c2438e 100644 --- a/drivers/media/usb/gspca/topro.c +++ b/drivers/media/usb/gspca/topro.c @@ -4802,7 +4802,11 @@ static void sd_set_streamparm(struct gspca_dev *gspca_dev, struct v4l2_fract *tpf = &cp->timeperframe; int fr, i; - sd->framerate = tpf->denominator / tpf->numerator; + if (tpf->numerator == 0 || tpf->denominator == 0) + sd->framerate = 30; + else + sd->framerate = tpf->denominator / tpf->numerator; + if (gspca_dev->streaming) setframerate(gspca_dev, v4l2_ctrl_g_ctrl(gspca_dev->exposure)); diff --git a/drivers/media/usb/pwc/pwc-if.c b/drivers/media/usb/pwc/pwc-if.c index b79c36fd8cd2..58f23bcfe94e 100644 --- a/drivers/media/usb/pwc/pwc-if.c +++ b/drivers/media/usb/pwc/pwc-if.c @@ -91,6 +91,7 @@ static const struct usb_device_id pwc_device_table [] = { { USB_DEVICE(0x0471, 0x0312) }, { USB_DEVICE(0x0471, 0x0313) }, /* the 'new' 720K */ { USB_DEVICE(0x0471, 0x0329) }, /* Philips SPC 900NC PC Camera */ + { USB_DEVICE(0x0471, 0x032C) }, /* Philips SPC 880NC PC Camera */ { USB_DEVICE(0x069A, 0x0001) }, /* Askey */ { USB_DEVICE(0x046D, 0x08B0) }, /* Logitech QuickCam Pro 3000 */ { USB_DEVICE(0x046D, 0x08B1) }, /* Logitech QuickCam Notebook Pro */ @@ -811,6 +812,11 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id name = "Philips SPC 900NC webcam"; type_id = 740; break; + case 0x032C: + PWC_INFO("Philips SPC 880NC USB webcam detected.\n"); + name = "Philips SPC 880NC webcam"; + type_id = 740; + break; default: return -ENODEV; break; diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c index b693206f66dd..d1dc1a198e3e 100644 --- a/drivers/media/usb/usbvision/usbvision-video.c +++ b/drivers/media/usb/usbvision/usbvision-video.c @@ -1463,9 +1463,23 @@ static int usbvision_probe(struct usb_interface *intf, if (usbvision_device_data[model].interface >= 0) interface = &dev->actconfig->interface[usbvision_device_data[model].interface]->altsetting[0]; - else + else if (ifnum < dev->actconfig->desc.bNumInterfaces) interface = &dev->actconfig->interface[ifnum]->altsetting[0]; + else { + dev_err(&intf->dev, "interface %d is invalid, max is %d\n", + ifnum, dev->actconfig->desc.bNumInterfaces - 1); + ret = -ENODEV; + goto err_usb; + } + + if (interface->desc.bNumEndpoints < 2) { + dev_err(&intf->dev, "interface %d has %d endpoints, but must" + " have minimum 2\n", ifnum, interface->desc.bNumEndpoints); + ret = -ENODEV; + goto err_usb; + } endpoint = &interface->endpoint[1].desc; + if (!usb_endpoint_xfer_isoc(endpoint)) { dev_err(&intf->dev, "%s: interface %d. has non-ISO endpoint!\n", __func__, ifnum); diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 327e83ac2469..f38c076752ce 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -415,7 +415,8 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user get_user(kp->index, &up->index) || get_user(kp->type, &up->type) || get_user(kp->flags, &up->flags) || - get_user(kp->memory, &up->memory)) + get_user(kp->memory, &up->memory) || + get_user(kp->length, &up->length)) return -EFAULT; if (V4L2_TYPE_IS_OUTPUT(kp->type)) @@ -427,9 +428,6 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user return -EFAULT; if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) { - if (get_user(kp->length, &up->length)) - return -EFAULT; - num_planes = kp->length; if (num_planes == 0) { kp->m.planes = NULL; @@ -462,16 +460,14 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user } else { switch (kp->memory) { case V4L2_MEMORY_MMAP: - if (get_user(kp->length, &up->length) || - get_user(kp->m.offset, &up->m.offset)) + if (get_user(kp->m.offset, &up->m.offset)) return -EFAULT; break; case V4L2_MEMORY_USERPTR: { compat_long_t tmp; - if (get_user(kp->length, &up->length) || - get_user(tmp, &up->m.userptr)) + if (get_user(tmp, &up->m.userptr)) return -EFAULT; kp->m.userptr = (unsigned long)compat_ptr(tmp); @@ -513,7 +509,8 @@ static int put_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user copy_to_user(&up->timecode, &kp->timecode, sizeof(struct v4l2_timecode)) || put_user(kp->sequence, &up->sequence) || put_user(kp->reserved2, &up->reserved2) || - put_user(kp->reserved, &up->reserved)) + put_user(kp->reserved, &up->reserved) || + put_user(kp->length, &up->length)) return -EFAULT; if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) { @@ -536,13 +533,11 @@ static int put_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user } else { switch (kp->memory) { case V4L2_MEMORY_MMAP: - if (put_user(kp->length, &up->length) || - put_user(kp->m.offset, &up->m.offset)) + if (put_user(kp->m.offset, &up->m.offset)) return -EFAULT; break; case V4L2_MEMORY_USERPTR: - if (put_user(kp->length, &up->length) || - put_user(kp->m.userptr, &up->m.userptr)) + if (put_user(kp->m.userptr, &up->m.userptr)) return -EFAULT; break; case V4L2_MEMORY_OVERLAY: diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index 33bdd81065e8..11f39791ec33 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -1502,7 +1502,7 @@ static int __vb2_wait_for_done_vb(struct vb2_queue *q, int nonblocking) * Will sleep if required for nonblocking == false. */ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb, - int nonblocking) + void *pb, int nonblocking) { unsigned long flags; int ret; @@ -1523,10 +1523,10 @@ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb, /* * Only remove the buffer from done_list if v4l2_buffer can handle all * the planes. - * Verifying planes is NOT necessary since it already has been checked - * before the buffer is queued/prepared. So it can never fail. */ - list_del(&(*vb)->done_entry); + ret = call_bufop(q, verify_planes_array, *vb, pb); + if (!ret) + list_del(&(*vb)->done_entry); spin_unlock_irqrestore(&q->done_lock, flags); return ret; @@ -1604,7 +1604,7 @@ int vb2_core_dqbuf(struct vb2_queue *q, void *pb, bool nonblocking) struct vb2_buffer *vb = NULL; int ret; - ret = __vb2_get_done_vb(q, &vb, nonblocking); + ret = __vb2_get_done_vb(q, &vb, pb, nonblocking); if (ret < 0) return ret; diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c index dbec5923fcf0..3c3b517f1d1c 100644 --- a/drivers/media/v4l2-core/videobuf2-memops.c +++ b/drivers/media/v4l2-core/videobuf2-memops.c @@ -49,7 +49,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start, vec = frame_vector_create(nr); if (!vec) return ERR_PTR(-ENOMEM); - ret = get_vaddr_frames(start, nr, write, 1, vec); + ret = get_vaddr_frames(start & PAGE_MASK, nr, write, true, vec); if (ret < 0) goto out_destroy; /* We accept only complete set of PFNs */ diff --git a/drivers/media/v4l2-core/videobuf2-v4l2.c b/drivers/media/v4l2-core/videobuf2-v4l2.c index 27b4b9e7c0c2..6c441be8f893 100644 --- a/drivers/media/v4l2-core/videobuf2-v4l2.c +++ b/drivers/media/v4l2-core/videobuf2-v4l2.c @@ -67,6 +67,11 @@ static int __verify_planes_array(struct vb2_buffer *vb, const struct v4l2_buffer return 0; } +static int __verify_planes_array_core(struct vb2_buffer *vb, const void *pb) +{ + return __verify_planes_array(vb, pb); +} + /** * __verify_length() - Verify that the bytesused value for each plane fits in * the plane length and that the data offset doesn't exceed the bytesused value. @@ -432,6 +437,7 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb, } static const struct vb2_buf_ops v4l2_buf_ops = { + .verify_planes_array = __verify_planes_array_core, .fill_user_buffer = __fill_v4l2_buffer, .fill_vb2_buffer = __fill_vb2_buffer, .set_timestamp = __set_timestamp, @@ -822,10 +828,10 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait) return res | POLLERR; /* - * For output streams you can write as long as there are fewer buffers - * queued than there are buffers available. + * For output streams you can call write() as long as there are fewer + * buffers queued than there are buffers available. */ - if (q->is_output && q->queued_count < q->num_buffers) + if (q->is_output && q->fileio && q->queued_count < q->num_buffers) return res | POLLOUT | POLLWRNORM; if (list_empty(&q->done_list)) { diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c index 6255513f54c7..68aa31ae553a 100644 --- a/drivers/mfd/intel-lpss.c +++ b/drivers/mfd/intel-lpss.c @@ -445,6 +445,7 @@ int intel_lpss_probe(struct device *dev, err_remove_ltr: intel_lpss_debugfs_remove(lpss); intel_lpss_ltr_hide(lpss); + intel_lpss_unregister_clock(lpss); err_clk_register: ida_simple_remove(&intel_lpss_devid_ida, lpss->devid); diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 83e5f852eabb..43bdc2e25033 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -412,10 +412,6 @@ config TI_DAC7512 This driver can also be built as a module. If so, the module will be called ti_dac7512. -config UID_STAT - bool "UID based statistics tracking exported to /proc/uid_stat" - default n - config VMWARE_BALLOON tristate "VMware Balloon Driver" depends on VMWARE_VMCI && X86 && HYPERVISOR_GUEST @@ -443,7 +439,7 @@ config ARM_CHARLCD still useful. config BMP085 - bool + tristate depends on SYSFS config BMP085_I2C diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 7b9b45f1f33a..77c93b6a7a7c 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -36,7 +36,6 @@ obj-$(CONFIG_ISL29020) += isl29020.o obj-$(CONFIG_SENSORS_TSL2550) += tsl2550.o obj-$(CONFIG_DS1682) += ds1682.o obj-$(CONFIG_TI_DAC7512) += ti_dac7512.o -obj-$(CONFIG_UID_STAT) += uid_stat.o obj-$(CONFIG_C2PORT) += c2port/ obj-$(CONFIG_HMC6352) += hmc6352.o obj-y += eeprom/ diff --git a/drivers/misc/ad525x_dpot.c b/drivers/misc/ad525x_dpot.c index 15e88078ba1e..f1a0b99f5a9a 100644 --- a/drivers/misc/ad525x_dpot.c +++ b/drivers/misc/ad525x_dpot.c @@ -216,7 +216,7 @@ static s32 dpot_read_i2c(struct dpot_data *dpot, u8 reg) */ value = swab16(value); - if (dpot->uid == DPOT_UID(AD5271_ID)) + if (dpot->uid == DPOT_UID(AD5274_ID)) value = value >> 2; return value; default: diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c index 09a406058c46..efbb6945eb18 100644 --- a/drivers/misc/cxl/irq.c +++ b/drivers/misc/cxl/irq.c @@ -288,7 +288,6 @@ unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq, void cxl_unmap_irq(unsigned int virq, void *cookie) { free_irq(virq, cookie); - irq_dispose_mapping(virq); } static int cxl_register_one_irq(struct cxl *adapter, diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 85761d7eb333..be2c8e248e2e 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -414,7 +414,7 @@ static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev) delta = mftb() - psl_tb; if (delta < 0) delta = -delta; - } while (cputime_to_usecs(delta) > 16); + } while (tb_to_ns(delta) > 16000); return 0; } diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index c241e15cacb1..cbd4331fb45c 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -203,7 +203,7 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn, mask <<= shift; val <<= shift; - v = (in_le32(ioaddr) & ~mask) || (val & mask); + v = (in_le32(ioaddr) & ~mask) | (val & mask); out_le32(ioaddr, v); return PCIBIOS_SUCCESSFUL; diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 0b05aa938799..1a173d0af694 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -53,6 +53,11 @@ ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length, bus = cl->dev; mutex_lock(&bus->device_lock); + if (bus->dev_state != MEI_DEV_ENABLED) { + rets = -ENODEV; + goto out; + } + if (!mei_cl_is_connected(cl)) { rets = -ENODEV; goto out; @@ -109,6 +114,10 @@ ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length) bus = cl->dev; mutex_lock(&bus->device_lock); + if (bus->dev_state != MEI_DEV_ENABLED) { + rets = -ENODEV; + goto out; + } cb = mei_cl_read_cb(cl, NULL); if (cb) diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index b2f2486b3d75..80f9afcb1382 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -458,7 +458,11 @@ static int mei_ioctl_client_notify_request(struct file *file, u32 request) { struct mei_cl *cl = file->private_data; - return mei_cl_notify_request(cl, file, request); + if (request != MEI_HBM_NOTIFICATION_START && + request != MEI_HBM_NOTIFICATION_STOP) + return -EINVAL; + + return mei_cl_notify_request(cl, file, (u8)request); } /** @@ -657,7 +661,9 @@ out: * @file: pointer to file structure * @band: band bitmap * - * Return: poll mask + * Return: negative on error, + * 0 if it did no changes, + * and positive a process was added or deleted */ static int mei_fasync(int fd, struct file *file, int band) { @@ -665,7 +671,7 @@ static int mei_fasync(int fd, struct file *file, int band) struct mei_cl *cl = file->private_data; if (!mei_cl_is_connected(cl)) - return POLLERR; + return -ENODEV; return fasync_helper(fd, file, band, &cl->ev_async); } diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c index 8310b4dbff06..6a451bd65bf3 100644 --- a/drivers/misc/mic/scif/scif_rma.c +++ b/drivers/misc/mic/scif/scif_rma.c @@ -1511,7 +1511,7 @@ off_t scif_register_pinned_pages(scif_epd_t epd, if ((map_flags & SCIF_MAP_FIXED) && ((ALIGN(offset, PAGE_SIZE) != offset) || (offset < 0) || - (offset + (off_t)len < offset))) + (len > LONG_MAX - offset))) return -EINVAL; might_sleep(); @@ -1614,7 +1614,7 @@ off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset, if ((map_flags & SCIF_MAP_FIXED) && ((ALIGN(offset, PAGE_SIZE) != offset) || (offset < 0) || - (offset + (off_t)len < offset))) + (len > LONG_MAX - offset))) return -EINVAL; /* Unsupported protection requested */ @@ -1732,7 +1732,8 @@ scif_unregister(scif_epd_t epd, off_t offset, size_t len) /* Offset is not page aligned or offset+len wraps around */ if ((ALIGN(offset, PAGE_SIZE) != offset) || - (offset + (off_t)len < offset)) + (offset < 0) || + (len > LONG_MAX - offset)) return -EINVAL; err = scif_verify_epd(ep); diff --git a/drivers/misc/uid_stat.c b/drivers/misc/uid_stat.c deleted file mode 100644 index 185c69c9738a..000000000000 --- a/drivers/misc/uid_stat.c +++ /dev/null @@ -1,153 +0,0 @@ -/* drivers/misc/uid_stat.c - * - * Copyright (C) 2008 - 2009 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#include <linux/atomic.h> - -#include <linux/err.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/list.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/stat.h> -#include <linux/uid_stat.h> -#include <net/activity_stats.h> - -static DEFINE_SPINLOCK(uid_lock); -static LIST_HEAD(uid_list); -static struct proc_dir_entry *parent; - -struct uid_stat { - struct list_head link; - uid_t uid; - atomic_t tcp_rcv; - atomic_t tcp_snd; -}; - -static struct uid_stat *find_uid_stat(uid_t uid) { - struct uid_stat *entry; - - list_for_each_entry(entry, &uid_list, link) { - if (entry->uid == uid) { - return entry; - } - } - return NULL; -} - -static int uid_stat_atomic_int_show(struct seq_file *m, void *v) -{ - unsigned int bytes; - atomic_t *counter = m->private; - - bytes = (unsigned int) (atomic_read(counter) + INT_MIN); - seq_printf(m, "%u\n", bytes); - return seq_has_overflowed(m) ? -ENOSPC : 0; -} - -static int uid_stat_read_atomic_int_open(struct inode *inode, struct file *file) -{ - return single_open(file, uid_stat_atomic_int_show, PDE_DATA(inode)); -} - -static const struct file_operations uid_stat_read_atomic_int_fops = { - .open = uid_stat_read_atomic_int_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* Create a new entry for tracking the specified uid. */ -static struct uid_stat *create_stat(uid_t uid) { - struct uid_stat *new_uid; - /* Create the uid stat struct and append it to the list. */ - new_uid = kmalloc(sizeof(struct uid_stat), GFP_ATOMIC); - if (!new_uid) - return NULL; - - new_uid->uid = uid; - /* Counters start at INT_MIN, so we can track 4GB of network traffic. */ - atomic_set(&new_uid->tcp_rcv, INT_MIN); - atomic_set(&new_uid->tcp_snd, INT_MIN); - - list_add_tail(&new_uid->link, &uid_list); - return new_uid; -} - -static void create_stat_proc(struct uid_stat *new_uid) -{ - char uid_s[32]; - struct proc_dir_entry *entry; - sprintf(uid_s, "%d", new_uid->uid); - entry = proc_mkdir(uid_s, parent); - - /* Keep reference to uid_stat so we know what uid to read stats from. */ - proc_create_data("tcp_snd", S_IRUGO, entry, - &uid_stat_read_atomic_int_fops, &new_uid->tcp_snd); - - proc_create_data("tcp_rcv", S_IRUGO, entry, - &uid_stat_read_atomic_int_fops, &new_uid->tcp_rcv); -} - -static struct uid_stat *find_or_create_uid_stat(uid_t uid) -{ - struct uid_stat *entry; - unsigned long flags; - spin_lock_irqsave(&uid_lock, flags); - entry = find_uid_stat(uid); - if (entry) { - spin_unlock_irqrestore(&uid_lock, flags); - return entry; - } - entry = create_stat(uid); - spin_unlock_irqrestore(&uid_lock, flags); - if (entry) - create_stat_proc(entry); - return entry; -} - -int uid_stat_tcp_snd(uid_t uid, int size) { - struct uid_stat *entry; - activity_stats_update(); - entry = find_or_create_uid_stat(uid); - if (!entry) - return -1; - atomic_add(size, &entry->tcp_snd); - return 0; -} - -int uid_stat_tcp_rcv(uid_t uid, int size) { - struct uid_stat *entry; - activity_stats_update(); - entry = find_or_create_uid_stat(uid); - if (!entry) - return -1; - atomic_add(size, &entry->tcp_rcv); - return 0; -} - -static int __init uid_stat_init(void) -{ - parent = proc_mkdir("uid_stat", NULL); - if (!parent) { - pr_err("uid_stat: failed to create proc entry\n"); - return -1; - } - return 0; -} - -__initcall(uid_stat_init); diff --git a/drivers/mmc/card/Kconfig b/drivers/mmc/card/Kconfig index 5562308699bc..6142ec1b9dfb 100644 --- a/drivers/mmc/card/Kconfig +++ b/drivers/mmc/card/Kconfig @@ -68,3 +68,15 @@ config MMC_TEST This driver is only of interest to those developing or testing a host driver. Most people should say N here. + +config MMC_SIMULATE_MAX_SPEED + bool "Turn on maximum speed control per block device" + depends on MMC_BLOCK + help + Say Y here to enable MMC device speed limiting. Used to test and + simulate the behavior of the system when confronted with a slow MMC. + + Enables max_read_speed, max_write_speed and cache_size attributes to + control the write or read maximum KB/second speed behaviors. + + If unsure, say N here. diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index f2ce13ab7ae6..c15d3f380524 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -288,6 +288,250 @@ out: return ret; } +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + +static int max_read_speed, max_write_speed, cache_size = 4; + +module_param(max_read_speed, int, S_IRUSR | S_IRGRP); +MODULE_PARM_DESC(max_read_speed, "maximum KB/s read speed 0=off"); +module_param(max_write_speed, int, S_IRUSR | S_IRGRP); +MODULE_PARM_DESC(max_write_speed, "maximum KB/s write speed 0=off"); +module_param(cache_size, int, S_IRUSR | S_IRGRP); +MODULE_PARM_DESC(cache_size, "MB high speed memory or SLC cache"); + +/* + * helper macros and expectations: + * size - unsigned long number of bytes + * jiffies - unsigned long HZ timestamp difference + * speed - unsigned KB/s transfer rate + */ +#define size_and_speed_to_jiffies(size, speed) \ + ((size) * HZ / (speed) / 1024UL) +#define jiffies_and_speed_to_size(jiffies, speed) \ + (((speed) * (jiffies) * 1024UL) / HZ) +#define jiffies_and_size_to_speed(jiffies, size) \ + ((size) * HZ / (jiffies) / 1024UL) + +/* Limits to report warning */ +/* jiffies_and_size_to_speed(10*HZ, queue_max_hw_sectors(q) * 512UL) ~ 25 */ +#define MIN_SPEED(q) 250 /* 10 times faster than a floppy disk */ +#define MAX_SPEED(q) jiffies_and_size_to_speed(1, queue_max_sectors(q) * 512UL) + +#define speed_valid(speed) ((speed) > 0) + +static const char off[] = "off\n"; + +static int max_speed_show(int speed, char *buf) +{ + if (speed) + return scnprintf(buf, PAGE_SIZE, "%uKB/s\n", speed); + else + return scnprintf(buf, PAGE_SIZE, off); +} + +static int max_speed_store(const char *buf, struct request_queue *q) +{ + unsigned int limit, set = 0; + + if (!strncasecmp(off, buf, sizeof(off) - 2)) + return set; + if (kstrtouint(buf, 0, &set) || (set > INT_MAX)) + return -EINVAL; + if (set == 0) + return set; + limit = MAX_SPEED(q); + if (set > limit) + pr_warn("max speed %u ineffective above %u\n", set, limit); + limit = MIN_SPEED(q); + if (set < limit) + pr_warn("max speed %u painful below %u\n", set, limit); + return set; +} + +static ssize_t max_write_speed_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + int ret = max_speed_show(atomic_read(&md->queue.max_write_speed), buf); + + mmc_blk_put(md); + return ret; +} + +static ssize_t max_write_speed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + int set = max_speed_store(buf, md->queue.queue); + + if (set < 0) { + mmc_blk_put(md); + return set; + } + + atomic_set(&md->queue.max_write_speed, set); + mmc_blk_put(md); + return count; +} + +static const DEVICE_ATTR(max_write_speed, S_IRUGO | S_IWUSR, + max_write_speed_show, max_write_speed_store); + +static ssize_t max_read_speed_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + int ret = max_speed_show(atomic_read(&md->queue.max_read_speed), buf); + + mmc_blk_put(md); + return ret; +} + +static ssize_t max_read_speed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + int set = max_speed_store(buf, md->queue.queue); + + if (set < 0) { + mmc_blk_put(md); + return set; + } + + atomic_set(&md->queue.max_read_speed, set); + mmc_blk_put(md); + return count; +} + +static const DEVICE_ATTR(max_read_speed, S_IRUGO | S_IWUSR, + max_read_speed_show, max_read_speed_store); + +static ssize_t cache_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + struct mmc_queue *mq = &md->queue; + int cache_size = atomic_read(&mq->cache_size); + int ret; + + if (!cache_size) + ret = scnprintf(buf, PAGE_SIZE, off); + else { + int speed = atomic_read(&mq->max_write_speed); + + if (!speed_valid(speed)) + ret = scnprintf(buf, PAGE_SIZE, "%uMB\n", cache_size); + else { /* We accept race between cache_jiffies and cache_used */ + unsigned long size = jiffies_and_speed_to_size( + jiffies - mq->cache_jiffies, speed); + long used = atomic_long_read(&mq->cache_used); + + if (size >= used) + size = 0; + else + size = (used - size) * 100 / cache_size + / 1024UL / 1024UL; + + ret = scnprintf(buf, PAGE_SIZE, "%uMB %lu%% used\n", + cache_size, size); + } + } + + mmc_blk_put(md); + return ret; +} + +static ssize_t cache_size_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mmc_blk_data *md; + unsigned int set = 0; + + if (strncasecmp(off, buf, sizeof(off) - 2) + && (kstrtouint(buf, 0, &set) || (set > INT_MAX))) + return -EINVAL; + + md = mmc_blk_get(dev_to_disk(dev)); + atomic_set(&md->queue.cache_size, set); + mmc_blk_put(md); + return count; +} + +static const DEVICE_ATTR(cache_size, S_IRUGO | S_IWUSR, + cache_size_show, cache_size_store); + +/* correct for write-back */ +static long mmc_blk_cache_used(struct mmc_queue *mq, unsigned long waitfor) +{ + long used = 0; + int speed = atomic_read(&mq->max_write_speed); + + if (speed_valid(speed)) { + unsigned long size = jiffies_and_speed_to_size( + waitfor - mq->cache_jiffies, speed); + used = atomic_long_read(&mq->cache_used); + + if (size >= used) + used = 0; + else + used -= size; + } + + atomic_long_set(&mq->cache_used, used); + mq->cache_jiffies = waitfor; + + return used; +} + +static void mmc_blk_simulate_delay( + struct mmc_queue *mq, + struct request *req, + unsigned long waitfor) +{ + int max_speed; + + if (!req) + return; + + max_speed = (rq_data_dir(req) == READ) + ? atomic_read(&mq->max_read_speed) + : atomic_read(&mq->max_write_speed); + if (speed_valid(max_speed)) { + unsigned long bytes = blk_rq_bytes(req); + + if (rq_data_dir(req) != READ) { + int cache_size = atomic_read(&mq->cache_size); + + if (cache_size) { + unsigned long size = cache_size * 1024L * 1024L; + long used = mmc_blk_cache_used(mq, waitfor); + + used += bytes; + atomic_long_set(&mq->cache_used, used); + bytes = 0; + if (used > size) + bytes = used - size; + } + } + waitfor += size_and_speed_to_jiffies(bytes, max_speed); + if (time_is_after_jiffies(waitfor)) { + long msecs = jiffies_to_msecs(waitfor - jiffies); + + if (likely(msecs > 0)) + msleep(msecs); + } + } +} + +#else + +#define mmc_blk_simulate_delay(mq, req, waitfor) + +#endif + static int mmc_blk_open(struct block_device *bdev, fmode_t mode) { struct mmc_blk_data *md = mmc_blk_get(bdev->bd_disk); @@ -1264,6 +1508,23 @@ static int mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req) if (ret) ret = -EIO; +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + else if (atomic_read(&mq->cache_size)) { + long used = mmc_blk_cache_used(mq, jiffies); + + if (used) { + int speed = atomic_read(&mq->max_write_speed); + + if (speed_valid(speed)) { + unsigned long msecs = jiffies_to_msecs( + size_and_speed_to_jiffies( + used, speed)); + if (msecs) + msleep(msecs); + } + } + } +#endif blk_end_request_all(req, ret); return ret ? 0 : 1; @@ -1943,6 +2204,9 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) struct mmc_async_req *areq; const u8 packed_nr = 2; u8 reqs = 0; +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + unsigned long waitfor = jiffies; +#endif if (!rqc && !mq->mqrq_prev->req) return 0; @@ -1993,6 +2257,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) */ mmc_blk_reset_success(md, type); + mmc_blk_simulate_delay(mq, rqc, waitfor); + if (mmc_packed_cmd(mq_rq->cmd_type)) { ret = mmc_blk_end_packed_req(mq_rq); break; @@ -2411,6 +2677,14 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md) card->ext_csd.boot_ro_lockable) device_remove_file(disk_to_dev(md->disk), &md->power_ro_lock); +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + device_remove_file(disk_to_dev(md->disk), + &dev_attr_max_write_speed); + device_remove_file(disk_to_dev(md->disk), + &dev_attr_max_read_speed); + device_remove_file(disk_to_dev(md->disk), + &dev_attr_cache_size); +#endif del_gendisk(md->disk); } @@ -2446,6 +2720,24 @@ static int mmc_add_disk(struct mmc_blk_data *md) ret = device_create_file(disk_to_dev(md->disk), &md->force_ro); if (ret) goto force_ro_fail; +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + atomic_set(&md->queue.max_write_speed, max_write_speed); + ret = device_create_file(disk_to_dev(md->disk), + &dev_attr_max_write_speed); + if (ret) + goto max_write_speed_fail; + atomic_set(&md->queue.max_read_speed, max_read_speed); + ret = device_create_file(disk_to_dev(md->disk), + &dev_attr_max_read_speed); + if (ret) + goto max_read_speed_fail; + atomic_set(&md->queue.cache_size, cache_size); + atomic_long_set(&md->queue.cache_used, 0); + md->queue.cache_jiffies = jiffies; + ret = device_create_file(disk_to_dev(md->disk), &dev_attr_cache_size); + if (ret) + goto cache_size_fail; +#endif if ((md->area_type & MMC_BLK_DATA_AREA_BOOT) && card->ext_csd.boot_ro_lockable) { @@ -2470,6 +2762,14 @@ static int mmc_add_disk(struct mmc_blk_data *md) return ret; power_ro_lock_fail: +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + device_remove_file(disk_to_dev(md->disk), &dev_attr_cache_size); +cache_size_fail: + device_remove_file(disk_to_dev(md->disk), &dev_attr_max_read_speed); +max_read_speed_fail: + device_remove_file(disk_to_dev(md->disk), &dev_attr_max_write_speed); +max_write_speed_fail: +#endif device_remove_file(disk_to_dev(md->disk), &md->force_ro); force_ro_fail: del_gendisk(md->disk); diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index 36cddab57d77..d890d8832e21 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -58,6 +58,14 @@ struct mmc_queue { struct mmc_queue_req mqrq[2]; struct mmc_queue_req *mqrq_cur; struct mmc_queue_req *mqrq_prev; +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + atomic_t max_write_speed; + atomic_t max_read_speed; + atomic_t cache_size; + /* i/o tracking */ + atomic_long_t cache_used; + unsigned long cache_jiffies; +#endif }; extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *, diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 3a9a79ec4343..3d5087b03999 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1076,8 +1076,7 @@ static int mmc_select_hs400(struct mmc_card *card) mmc_set_clock(host, max_dtr); /* Switch card to HS mode */ - val = EXT_CSD_TIMING_HS | - card->drive_strength << EXT_CSD_DRV_STR_SHIFT; + val = EXT_CSD_TIMING_HS; err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING, val, card->ext_csd.generic_cmd6_time, @@ -1160,8 +1159,7 @@ int mmc_hs400_to_hs200(struct mmc_card *card) mmc_set_clock(host, max_dtr); /* Switch HS400 to HS DDR */ - val = EXT_CSD_TIMING_HS | - card->drive_strength << EXT_CSD_DRV_STR_SHIFT; + val = EXT_CSD_TIMING_HS; err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING, val, card->ext_csd.generic_cmd6_time, true, send_status, true); diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 4ac721fea4ef..ee145d4cc541 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -626,9 +626,9 @@ static int mmc_sd_init_uhs_card(struct mmc_card *card) * SDR104 mode SD-cards. Note that tuning is mandatory for SDR104. */ if (!mmc_host_is_spi(card->host) && - (card->sd_bus_speed == UHS_SDR50_BUS_SPEED || - card->sd_bus_speed == UHS_DDR50_BUS_SPEED || - card->sd_bus_speed == UHS_SDR104_BUS_SPEED)) { + (card->host->ios.timing == MMC_TIMING_UHS_SDR50 || + card->host->ios.timing == MMC_TIMING_UHS_DDR50 || + card->host->ios.timing == MMC_TIMING_UHS_SDR104)) { err = mmc_execute_tuning(card); /* @@ -638,7 +638,7 @@ static int mmc_sd_init_uhs_card(struct mmc_card *card) * difference between v3.00 and 3.01 spec means that CMD19 * tuning is also available for DDR50 mode. */ - if (err && card->sd_bus_speed == UHS_DDR50_BUS_SPEED) { + if (err && card->host->ios.timing == MMC_TIMING_UHS_DDR50) { pr_warn("%s: ddr50 tuning failed\n", mmc_hostname(card->host)); err = 0; diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index b5a1c0220493..b47957122fd7 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -541,8 +541,8 @@ static int mmc_sdio_init_uhs_card(struct mmc_card *card) * SDR104 mode SD-cards. Note that tuning is mandatory for SDR104. */ if (!mmc_host_is_spi(card->host) && - ((card->sw_caps.sd3_bus_mode & SD_MODE_UHS_SDR50) || - (card->sw_caps.sd3_bus_mode & SD_MODE_UHS_SDR104))) + ((card->host->ios.timing == MMC_TIMING_UHS_SDR50) || + (card->host->ios.timing == MMC_TIMING_UHS_SDR104))) err = mmc_execute_tuning(card); out: return err; @@ -636,7 +636,7 @@ try_again: */ if (!powered_resume && (rocr & ocr & R4_18V_PRESENT)) { err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180, - ocr); + ocr_card); if (err == -EAGAIN) { sdio_reset(host); mmc_go_idle(host); diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 1c1b45ef3faf..aad3243a48fc 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1436,6 +1436,12 @@ static int mmc_spi_probe(struct spi_device *spi) host->pdata->cd_debounce); if (status != 0) goto fail_add_host; + + /* The platform has a CD GPIO signal that may support + * interrupts, so let mmc_gpiod_request_cd_irq() decide + * if polling is needed or not. + */ + mmc->caps &= ~MMC_CAP_NEEDS_POLL; mmc_gpiod_request_cd_irq(mmc); } diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index fb266745f824..acece3299756 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1886,7 +1886,7 @@ static struct amba_id mmci_ids[] = { { .id = 0x00280180, .mask = 0x00ffffff, - .data = &variant_u300, + .data = &variant_nomadik, }, { .id = 0x00480180, diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index ce08896b9d69..28a057fae0a1 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -804,7 +804,7 @@ static int pxamci_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro); goto out; } else { - mmc->caps |= host->pdata->gpio_card_ro_invert ? + mmc->caps2 |= host->pdata->gpio_card_ro_invert ? 0 : MMC_CAP2_RO_ACTIVE_HIGH; } diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index f6047fc94062..a5cda926d38e 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -146,6 +146,33 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = { .ops = &sdhci_acpi_ops_int, }; +static int bxt_get_cd(struct mmc_host *mmc) +{ + int gpio_cd = mmc_gpio_get_cd(mmc); + struct sdhci_host *host = mmc_priv(mmc); + unsigned long flags; + int ret = 0; + + if (!gpio_cd) + return 0; + + pm_runtime_get_sync(mmc->parent); + + spin_lock_irqsave(&host->lock, flags); + + if (host->flags & SDHCI_DEVICE_DEAD) + goto out; + + ret = !!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT); +out: + spin_unlock_irqrestore(&host->lock, flags); + + pm_runtime_mark_last_busy(mmc->parent); + pm_runtime_put_autosuspend(mmc->parent); + + return ret; +} + static int sdhci_acpi_emmc_probe_slot(struct platform_device *pdev, const char *hid, const char *uid) { @@ -196,6 +223,9 @@ static int sdhci_acpi_sd_probe_slot(struct platform_device *pdev, /* Platform specific code during sd probe slot goes here */ + if (hid && !strcmp(hid, "80865ACA")) + host->mmc_host_ops.get_cd = bxt_get_cd; + return 0; } diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index cf7ad458b4f4..610154836d79 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -277,7 +277,7 @@ static int spt_select_drive_strength(struct sdhci_host *host, if (sdhci_pci_spt_drive_strength > 0) drive_strength = sdhci_pci_spt_drive_strength & 0xf; else - drive_strength = 1; /* 33-ohm */ + drive_strength = 0; /* Default 50-ohm */ if ((mmc_driver_type_mask(drive_strength) & card_drv) == 0) drive_strength = 0; /* Default 50-ohm */ @@ -330,6 +330,33 @@ static void spt_read_drive_strength(struct sdhci_host *host) sdhci_pci_spt_drive_strength = 0x10 | ((val >> 12) & 0xf); } +static int bxt_get_cd(struct mmc_host *mmc) +{ + int gpio_cd = mmc_gpio_get_cd(mmc); + struct sdhci_host *host = mmc_priv(mmc); + unsigned long flags; + int ret = 0; + + if (!gpio_cd) + return 0; + + pm_runtime_get_sync(mmc->parent); + + spin_lock_irqsave(&host->lock, flags); + + if (host->flags & SDHCI_DEVICE_DEAD) + goto out; + + ret = !!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT); +out: + spin_unlock_irqrestore(&host->lock, flags); + + pm_runtime_mark_last_busy(mmc->parent); + pm_runtime_put_autosuspend(mmc->parent); + + return ret; +} + static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) { slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE | @@ -362,6 +389,11 @@ static int byt_sd_probe_slot(struct sdhci_pci_slot *slot) slot->cd_con_id = NULL; slot->cd_idx = 0; slot->cd_override_level = true; + if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXT_SD || + slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXTM_SD || + slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_APL_SD) + slot->host->mmc_host_ops.get_cd = bxt_get_cd; + return 0; } @@ -1142,6 +1174,30 @@ static const struct pci_device_id pci_ids[] = { { .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BXTM_EMMC, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .driver_data = (kernel_ulong_t)&sdhci_intel_byt_emmc, + }, + + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BXTM_SDIO, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .driver_data = (kernel_ulong_t)&sdhci_intel_byt_sdio, + }, + + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BXTM_SD, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .driver_data = (kernel_ulong_t)&sdhci_intel_byt_sd, + }, + + { + .vendor = PCI_VENDOR_ID_INTEL, .device = PCI_DEVICE_ID_INTEL_APL_EMMC, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h index d1a0b4db60db..89e7151684a1 100644 --- a/drivers/mmc/host/sdhci-pci.h +++ b/drivers/mmc/host/sdhci-pci.h @@ -28,6 +28,9 @@ #define PCI_DEVICE_ID_INTEL_BXT_SD 0x0aca #define PCI_DEVICE_ID_INTEL_BXT_EMMC 0x0acc #define PCI_DEVICE_ID_INTEL_BXT_SDIO 0x0ad0 +#define PCI_DEVICE_ID_INTEL_BXTM_SD 0x1aca +#define PCI_DEVICE_ID_INTEL_BXTM_EMMC 0x1acc +#define PCI_DEVICE_ID_INTEL_BXTM_SDIO 0x1ad0 #define PCI_DEVICE_ID_INTEL_APL_SD 0x5aca #define PCI_DEVICE_ID_INTEL_APL_EMMC 0x5acc #define PCI_DEVICE_ID_INTEL_APL_SDIO 0x5ad0 diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index b48565ed5616..1a802af827ed 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -540,9 +540,12 @@ static int sdhci_adma_table_pre(struct sdhci_host *host, BUG_ON(len > 65536); - /* tran, valid */ - sdhci_adma_write_desc(host, desc, addr, len, ADMA2_TRAN_VALID); - desc += host->desc_sz; + if (len) { + /* tran, valid */ + sdhci_adma_write_desc(host, desc, addr, len, + ADMA2_TRAN_VALID); + desc += host->desc_sz; + } /* * If this triggers then we have a calculation bug @@ -663,9 +666,20 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd) if (!data) target_timeout = cmd->busy_timeout * 1000; else { - target_timeout = data->timeout_ns / 1000; - if (host->clock) - target_timeout += data->timeout_clks / host->clock; + target_timeout = DIV_ROUND_UP(data->timeout_ns, 1000); + if (host->clock && data->timeout_clks) { + unsigned long long val; + + /* + * data->timeout_clks is in units of clock cycles. + * host->clock is in Hz. target_timeout is in us. + * Hence, us = 1000000 * cycles / Hz. Round up. + */ + val = 1000000 * data->timeout_clks; + if (do_div(val, host->clock)) + target_timeout++; + target_timeout += val; + } } /* @@ -1364,7 +1378,7 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) sdhci_runtime_pm_get(host); /* Firstly check card presence */ - present = sdhci_do_get_cd(host); + present = mmc->ops->get_cd(mmc); spin_lock_irqsave(&host->lock, flags); @@ -2760,7 +2774,7 @@ static int sdhci_runtime_pm_put(struct sdhci_host *host) static void sdhci_runtime_pm_bus_on(struct sdhci_host *host) { - if (host->runtime_suspended || host->bus_on) + if (host->bus_on) return; host->bus_on = true; pm_runtime_get_noresume(host->mmc->parent); @@ -2768,7 +2782,7 @@ static void sdhci_runtime_pm_bus_on(struct sdhci_host *host) static void sdhci_runtime_pm_bus_off(struct sdhci_host *host) { - if (host->runtime_suspended || !host->bus_on) + if (!host->bus_on) return; host->bus_on = false; pm_runtime_put_noidle(host->mmc->parent); @@ -2861,6 +2875,8 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev, host = mmc_priv(mmc); host->mmc = mmc; + host->mmc_host_ops = sdhci_ops; + mmc->ops = &host->mmc_host_ops; return host; } @@ -3057,7 +3073,6 @@ int sdhci_add_host(struct sdhci_host *host) /* * Set host parameters. */ - mmc->ops = &sdhci_ops; max_clk = host->max_clk; if (host->ops->get_min_clock) @@ -3091,14 +3106,14 @@ int sdhci_add_host(struct sdhci_host *host) if (caps[0] & SDHCI_TIMEOUT_CLK_UNIT) host->timeout_clk *= 1000; + if (override_timeout_clk) + host->timeout_clk = override_timeout_clk; + mmc->max_busy_timeout = host->ops->get_max_timeout_count ? host->ops->get_max_timeout_count(host) : 1 << 27; mmc->max_busy_timeout /= host->timeout_clk; } - if (override_timeout_clk) - host->timeout_clk = override_timeout_clk; - mmc->caps |= MMC_CAP_SDIO_IRQ | MMC_CAP_ERASE | MMC_CAP_CMD23; mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD; diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index 9d4aa31b683a..9c331ac5ad6b 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -425,6 +425,7 @@ struct sdhci_host { /* Internal data */ struct mmc_host *mmc; /* MMC structure */ + struct mmc_host_ops mmc_host_ops; /* MMC host ops */ u64 dma_mask; /* custom DMA mask */ #if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE) diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index ad9ffea7d659..6234eab38ff3 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -397,38 +397,26 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host) } static struct dma_chan * -sh_mmcif_request_dma_one(struct sh_mmcif_host *host, - struct sh_mmcif_plat_data *pdata, - enum dma_transfer_direction direction) +sh_mmcif_request_dma_pdata(struct sh_mmcif_host *host, uintptr_t slave_id) { - struct dma_slave_config cfg = { 0, }; - struct dma_chan *chan; - void *slave_data = NULL; - struct resource *res; - struct device *dev = sh_mmcif_host_to_dev(host); dma_cap_mask_t mask; - int ret; dma_cap_zero(mask); dma_cap_set(DMA_SLAVE, mask); + if (slave_id <= 0) + return NULL; - if (pdata) - slave_data = direction == DMA_MEM_TO_DEV ? - (void *)pdata->slave_id_tx : - (void *)pdata->slave_id_rx; - - chan = dma_request_slave_channel_compat(mask, shdma_chan_filter, - slave_data, dev, - direction == DMA_MEM_TO_DEV ? "tx" : "rx"); - - dev_dbg(dev, "%s: %s: got channel %p\n", __func__, - direction == DMA_MEM_TO_DEV ? "TX" : "RX", chan); + return dma_request_channel(mask, shdma_chan_filter, (void *)slave_id); +} - if (!chan) - return NULL; +static int sh_mmcif_dma_slave_config(struct sh_mmcif_host *host, + struct dma_chan *chan, + enum dma_transfer_direction direction) +{ + struct resource *res; + struct dma_slave_config cfg = { 0, }; res = platform_get_resource(host->pd, IORESOURCE_MEM, 0); - cfg.direction = direction; if (direction == DMA_DEV_TO_MEM) { @@ -439,38 +427,42 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host, cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; } - ret = dmaengine_slave_config(chan, &cfg); - if (ret < 0) { - dma_release_channel(chan); - return NULL; - } - - return chan; + return dmaengine_slave_config(chan, &cfg); } -static void sh_mmcif_request_dma(struct sh_mmcif_host *host, - struct sh_mmcif_plat_data *pdata) +static void sh_mmcif_request_dma(struct sh_mmcif_host *host) { struct device *dev = sh_mmcif_host_to_dev(host); host->dma_active = false; - if (pdata) { - if (pdata->slave_id_tx <= 0 || pdata->slave_id_rx <= 0) - return; - } else if (!dev->of_node) { - return; + /* We can only either use DMA for both Tx and Rx or not use it at all */ + if (IS_ENABLED(CONFIG_SUPERH) && dev->platform_data) { + struct sh_mmcif_plat_data *pdata = dev->platform_data; + + host->chan_tx = sh_mmcif_request_dma_pdata(host, + pdata->slave_id_tx); + host->chan_rx = sh_mmcif_request_dma_pdata(host, + pdata->slave_id_rx); + } else { + host->chan_tx = dma_request_slave_channel(dev, "tx"); + host->chan_rx = dma_request_slave_channel(dev, "rx"); } + dev_dbg(dev, "%s: got channel TX %p RX %p\n", __func__, host->chan_tx, + host->chan_rx); - /* We can only either use DMA for both Tx and Rx or not use it at all */ - host->chan_tx = sh_mmcif_request_dma_one(host, pdata, DMA_MEM_TO_DEV); - if (!host->chan_tx) - return; + if (!host->chan_tx || !host->chan_rx || + sh_mmcif_dma_slave_config(host, host->chan_tx, DMA_MEM_TO_DEV) || + sh_mmcif_dma_slave_config(host, host->chan_rx, DMA_DEV_TO_MEM)) + goto error; - host->chan_rx = sh_mmcif_request_dma_one(host, pdata, DMA_DEV_TO_MEM); - if (!host->chan_rx) { + return; + +error: + if (host->chan_tx) dma_release_channel(host->chan_tx); - host->chan_tx = NULL; - } + if (host->chan_rx) + dma_release_channel(host->chan_rx); + host->chan_tx = host->chan_rx = NULL; } static void sh_mmcif_release_dma(struct sh_mmcif_host *host) @@ -1102,7 +1094,7 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) if (ios->power_mode == MMC_POWER_UP) { if (!host->card_present) { /* See if we also get DMA */ - sh_mmcif_request_dma(host, dev->platform_data); + sh_mmcif_request_dma(host); host->card_present = true; } sh_mmcif_set_power(host, ios); diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c index 4498e92116b8..b47122d3e8d8 100644 --- a/drivers/mmc/host/usdhi6rol0.c +++ b/drivers/mmc/host/usdhi6rol0.c @@ -1634,7 +1634,7 @@ static void usdhi6_timeout_work(struct work_struct *work) struct usdhi6_host *host = container_of(d, struct usdhi6_host, timeout_work); struct mmc_request *mrq = host->mrq; struct mmc_data *data = mrq ? mrq->data : NULL; - struct scatterlist *sg = host->sg ?: data->sg; + struct scatterlist *sg; dev_warn(mmc_dev(host->mmc), "%s timeout wait %u CMD%d: IRQ 0x%08x:0x%08x, last IRQ 0x%08x\n", @@ -1666,6 +1666,7 @@ static void usdhi6_timeout_work(struct work_struct *work) case USDHI6_WAIT_FOR_MWRITE: case USDHI6_WAIT_FOR_READ: case USDHI6_WAIT_FOR_WRITE: + sg = host->sg ?: data->sg; dev_dbg(mmc_dev(host->mmc), "%c: page #%u @ +0x%zx %ux%u in SG%u. Current SG %u bytes @ %u\n", data->flags & MMC_DATA_READ ? 'R' : 'W', host->page_idx, diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c index 12c6190c6e33..4a07ba1195b5 100644 --- a/drivers/mtd/nand/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/brcmnand/brcmnand.c @@ -309,6 +309,36 @@ static const u16 brcmnand_regs_v60[] = { [BRCMNAND_FC_BASE] = 0x400, }; +/* BRCMNAND v7.1 */ +static const u16 brcmnand_regs_v71[] = { + [BRCMNAND_CMD_START] = 0x04, + [BRCMNAND_CMD_EXT_ADDRESS] = 0x08, + [BRCMNAND_CMD_ADDRESS] = 0x0c, + [BRCMNAND_INTFC_STATUS] = 0x14, + [BRCMNAND_CS_SELECT] = 0x18, + [BRCMNAND_CS_XOR] = 0x1c, + [BRCMNAND_LL_OP] = 0x20, + [BRCMNAND_CS0_BASE] = 0x50, + [BRCMNAND_CS1_BASE] = 0, + [BRCMNAND_CORR_THRESHOLD] = 0xdc, + [BRCMNAND_CORR_THRESHOLD_EXT] = 0xe0, + [BRCMNAND_UNCORR_COUNT] = 0xfc, + [BRCMNAND_CORR_COUNT] = 0x100, + [BRCMNAND_CORR_EXT_ADDR] = 0x10c, + [BRCMNAND_CORR_ADDR] = 0x110, + [BRCMNAND_UNCORR_EXT_ADDR] = 0x114, + [BRCMNAND_UNCORR_ADDR] = 0x118, + [BRCMNAND_SEMAPHORE] = 0x150, + [BRCMNAND_ID] = 0x194, + [BRCMNAND_ID_EXT] = 0x198, + [BRCMNAND_LL_RDATA] = 0x19c, + [BRCMNAND_OOB_READ_BASE] = 0x200, + [BRCMNAND_OOB_READ_10_BASE] = 0, + [BRCMNAND_OOB_WRITE_BASE] = 0x280, + [BRCMNAND_OOB_WRITE_10_BASE] = 0, + [BRCMNAND_FC_BASE] = 0x400, +}; + enum brcmnand_cs_reg { BRCMNAND_CS_CFG_EXT = 0, BRCMNAND_CS_CFG, @@ -404,7 +434,9 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl) } /* Register offsets */ - if (ctrl->nand_version >= 0x0600) + if (ctrl->nand_version >= 0x0701) + ctrl->reg_offsets = brcmnand_regs_v71; + else if (ctrl->nand_version >= 0x0600) ctrl->reg_offsets = brcmnand_regs_v60; else if (ctrl->nand_version >= 0x0500) ctrl->reg_offsets = brcmnand_regs_v50; diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index ece544efccc3..ce7b2cab5762 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -3979,7 +3979,6 @@ static int nand_dt_init(struct mtd_info *mtd, struct nand_chip *chip, * This is the first phase of the normal nand_scan() function. It reads the * flash ID and sets up MTD fields accordingly. * - * The mtd->owner field must be set to the module of the caller. */ int nand_scan_ident(struct mtd_info *mtd, int maxchips, struct nand_flash_dev *table) @@ -3995,6 +3994,9 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips, return ret; } + if (!mtd->name && mtd->dev.parent) + mtd->name = dev_name(mtd->dev.parent); + /* Set the default functions */ nand_set_defaults(chip, chip->options & NAND_BUSWIDTH_16); @@ -4400,19 +4402,12 @@ EXPORT_SYMBOL(nand_scan_tail); * * This fills out all the uninitialized function pointers with the defaults. * The flash ID is read and the mtd/chip structures are filled with the - * appropriate values. The mtd->owner field must be set to the module of the - * caller. + * appropriate values. */ int nand_scan(struct mtd_info *mtd, int maxchips) { int ret; - /* Many callers got this wrong, so check for it for a while... */ - if (!mtd->owner && caller_is_module()) { - pr_crit("%s called with NULL mtd->owner!\n", __func__); - BUG(); - } - ret = nand_scan_ident(mtd, maxchips, NULL); if (!ret) ret = nand_scan_tail(mtd); diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c index 43b3392ffee7..652d01832873 100644 --- a/drivers/mtd/onenand/onenand_base.c +++ b/drivers/mtd/onenand/onenand_base.c @@ -2599,6 +2599,7 @@ static int onenand_default_block_markbad(struct mtd_info *mtd, loff_t ofs) */ static int onenand_block_markbad(struct mtd_info *mtd, loff_t ofs) { + struct onenand_chip *this = mtd->priv; int ret; ret = onenand_block_isbad(mtd, ofs); @@ -2610,7 +2611,7 @@ static int onenand_block_markbad(struct mtd_info *mtd, loff_t ofs) } onenand_get_device(mtd, FL_WRITING); - ret = mtd_block_markbad(mtd, ofs); + ret = this->block_markbad(mtd, ofs); onenand_release_device(mtd); return ret; } diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 32477c4eb421..37e4135ab213 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1067,45 +1067,6 @@ static int spansion_quad_enable(struct spi_nor *nor) return 0; } -static int micron_quad_enable(struct spi_nor *nor) -{ - int ret; - u8 val; - - ret = nor->read_reg(nor, SPINOR_OP_RD_EVCR, &val, 1); - if (ret < 0) { - dev_err(nor->dev, "error %d reading EVCR\n", ret); - return ret; - } - - write_enable(nor); - - /* set EVCR, enable quad I/O */ - nor->cmd_buf[0] = val & ~EVCR_QUAD_EN_MICRON; - ret = nor->write_reg(nor, SPINOR_OP_WD_EVCR, nor->cmd_buf, 1); - if (ret < 0) { - dev_err(nor->dev, "error while writing EVCR register\n"); - return ret; - } - - ret = spi_nor_wait_till_ready(nor); - if (ret) - return ret; - - /* read EVCR and check it */ - ret = nor->read_reg(nor, SPINOR_OP_RD_EVCR, &val, 1); - if (ret < 0) { - dev_err(nor->dev, "error %d reading EVCR\n", ret); - return ret; - } - if (val & EVCR_QUAD_EN_MICRON) { - dev_err(nor->dev, "Micron EVCR Quad bit not clear\n"); - return -EINVAL; - } - - return 0; -} - static int set_quad_mode(struct spi_nor *nor, const struct flash_info *info) { int status; @@ -1119,12 +1080,7 @@ static int set_quad_mode(struct spi_nor *nor, const struct flash_info *info) } return status; case SNOR_MFR_MICRON: - status = micron_quad_enable(nor); - if (status) { - dev_err(nor->dev, "Micron quad-read not enabled\n"); - return -EINVAL; - } - return status; + return 0; default: status = spansion_quad_enable(nor); if (status) { diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index 2a1b6e037e1a..0134ba32a057 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -193,7 +193,7 @@ int ubi_start_leb_change(struct ubi_device *ubi, struct ubi_volume *vol, vol->changing_leb = 1; vol->ch_lnum = req->lnum; - vol->upd_buf = vmalloc(req->bytes); + vol->upd_buf = vmalloc(ALIGN((int)req->bytes, ubi->min_io_size)); if (!vol->upd_buf) return -ENOMEM; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 9e0f8a7ef8b1..b3d70a7a5262 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -214,6 +214,8 @@ static void bond_uninit(struct net_device *bond_dev); static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats); static void bond_slave_arr_handler(struct work_struct *work); +static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, + int mod); /*---------------------------- General routines -----------------------------*/ @@ -1207,7 +1209,6 @@ static int bond_master_upper_dev_link(struct net_device *bond_dev, err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave); if (err) return err; - slave_dev->flags |= IFF_SLAVE; rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL); return 0; } @@ -1465,6 +1466,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } } + /* set slave flag before open to prevent IPv6 addrconf */ + slave_dev->flags |= IFF_SLAVE; + /* open the slave since the application closed it */ res = dev_open(slave_dev); if (res) { @@ -1725,6 +1729,7 @@ err_close: dev_close(slave_dev); err_restore_mac: + slave_dev->flags &= ~IFF_SLAVE; if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* XXX TODO - fom follow mode needs to change master's @@ -2415,7 +2420,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct arphdr *arp = (struct arphdr *)skb->data; - struct slave *curr_active_slave; + struct slave *curr_active_slave, *curr_arp_slave; unsigned char *arp_ptr; __be32 sip, tip; int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); @@ -2462,26 +2467,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, &sip, &tip); curr_active_slave = rcu_dereference(bond->curr_active_slave); + curr_arp_slave = rcu_dereference(bond->current_arp_slave); - /* Backup slaves won't see the ARP reply, but do come through - * here for each ARP probe (so we swap the sip/tip to validate - * the probe). In a "redundant switch, common router" type of - * configuration, the ARP probe will (hopefully) travel from - * the active, through one switch, the router, then the other - * switch before reaching the backup. + /* We 'trust' the received ARP enough to validate it if: + * + * (a) the slave receiving the ARP is active (which includes the + * current ARP slave, if any), or + * + * (b) the receiving slave isn't active, but there is a currently + * active slave and it received valid arp reply(s) after it became + * the currently active slave, or * - * We 'trust' the arp requests if there is an active slave and - * it received valid arp reply(s) after it became active. This - * is done to avoid endless looping when we can't reach the + * (c) there is an ARP slave that sent an ARP during the prior ARP + * interval, and we receive an ARP reply on any slave. We accept + * these because switch FDB update delays may deliver the ARP + * reply to a slave other than the sender of the ARP request. + * + * Note: for (b), backup slaves are receiving the broadcast ARP + * request, not a reply. This request passes from the sending + * slave through the L2 switch(es) to the receiving slave. Since + * this is checking the request, sip/tip are swapped for + * validation. + * + * This is done to avoid endless looping when we can't reach the * arp_ip_target and fool ourselves with our own arp requests. */ - if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); + else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) && + bond_time_in_interval(bond, + dev_trans_start(curr_arp_slave->dev), 1)) + bond_validate_arp(bond, slave, sip, tip); out_unlock: if (arp != (struct arphdr *)skb->data) @@ -3240,6 +3260,30 @@ static int bond_close(struct net_device *bond_dev) return 0; } +/* fold stats, assuming all rtnl_link_stats64 fields are u64, but + * that some drivers can provide 32bit values only. + */ +static void bond_fold_stats(struct rtnl_link_stats64 *_res, + const struct rtnl_link_stats64 *_new, + const struct rtnl_link_stats64 *_old) +{ + const u64 *new = (const u64 *)_new; + const u64 *old = (const u64 *)_old; + u64 *res = (u64 *)_res; + int i; + + for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) { + u64 nv = new[i]; + u64 ov = old[i]; + + /* detects if this particular field is 32bit only */ + if (((nv | ov) >> 32) == 0) + res[i] += (u32)nv - (u32)ov; + else + res[i] += nv - ov; + } +} + static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3248,43 +3292,23 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct list_head *iter; struct slave *slave; + spin_lock(&bond->stats_lock); memcpy(stats, &bond->bond_stats, sizeof(*stats)); - bond_for_each_slave(bond, slave, iter) { - const struct rtnl_link_stats64 *sstats = + rcu_read_lock(); + bond_for_each_slave_rcu(bond, slave, iter) { + const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); - struct rtnl_link_stats64 *pstats = &slave->slave_stats; - - stats->rx_packets += sstats->rx_packets - pstats->rx_packets; - stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes; - stats->rx_errors += sstats->rx_errors - pstats->rx_errors; - stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped; - - stats->tx_packets += sstats->tx_packets - pstats->tx_packets;; - stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes; - stats->tx_errors += sstats->tx_errors - pstats->tx_errors; - stats->tx_dropped += sstats->tx_dropped - pstats->tx_dropped; - - stats->multicast += sstats->multicast - pstats->multicast; - stats->collisions += sstats->collisions - pstats->collisions; - - stats->rx_length_errors += sstats->rx_length_errors - pstats->rx_length_errors; - stats->rx_over_errors += sstats->rx_over_errors - pstats->rx_over_errors; - stats->rx_crc_errors += sstats->rx_crc_errors - pstats->rx_crc_errors; - stats->rx_frame_errors += sstats->rx_frame_errors - pstats->rx_frame_errors; - stats->rx_fifo_errors += sstats->rx_fifo_errors - pstats->rx_fifo_errors; - stats->rx_missed_errors += sstats->rx_missed_errors - pstats->rx_missed_errors; - - stats->tx_aborted_errors += sstats->tx_aborted_errors - pstats->tx_aborted_errors; - stats->tx_carrier_errors += sstats->tx_carrier_errors - pstats->tx_carrier_errors; - stats->tx_fifo_errors += sstats->tx_fifo_errors - pstats->tx_fifo_errors; - stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors - pstats->tx_heartbeat_errors; - stats->tx_window_errors += sstats->tx_window_errors - pstats->tx_window_errors; + + bond_fold_stats(stats, new, &slave->slave_stats); /* save off the slave stats for the next run */ - memcpy(pstats, sstats, sizeof(*sstats)); + memcpy(&slave->slave_stats, new, sizeof(*new)); } + rcu_read_unlock(); + memcpy(&bond->bond_stats, stats, sizeof(*stats)); + spin_unlock(&bond->stats_lock); return stats; } @@ -4098,6 +4122,7 @@ void bond_setup(struct net_device *bond_dev) struct bonding *bond = netdev_priv(bond_dev); spin_lock_init(&bond->mode_lock); + spin_lock_init(&bond->stats_lock); bond->params = bonding_defaults; /* Initialize pointers */ diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index fc5b75675cd8..eb7192fab593 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -117,6 +117,9 @@ MODULE_LICENSE("GPL v2"); */ #define EMS_USB_ARM7_CLOCK 8000000 +#define CPC_TX_QUEUE_TRIGGER_LOW 25 +#define CPC_TX_QUEUE_TRIGGER_HIGH 35 + /* * CAN-Message representation in a CPC_MSG. Message object type is * CPC_MSG_TYPE_CAN_FRAME or CPC_MSG_TYPE_RTR_FRAME or @@ -278,6 +281,11 @@ static void ems_usb_read_interrupt_callback(struct urb *urb) switch (urb->status) { case 0: dev->free_slots = dev->intr_in_buffer[1]; + if(dev->free_slots > CPC_TX_QUEUE_TRIGGER_HIGH){ + if (netif_queue_stopped(netdev)){ + netif_wake_queue(netdev); + } + } break; case -ECONNRESET: /* unlink */ @@ -526,8 +534,6 @@ static void ems_usb_write_bulk_callback(struct urb *urb) /* Release context */ context->echo_index = MAX_TX_URBS; - if (netif_queue_stopped(netdev)) - netif_wake_queue(netdev); } /* @@ -587,7 +593,7 @@ static int ems_usb_start(struct ems_usb *dev) int err, i; dev->intr_in_buffer[0] = 0; - dev->free_slots = 15; /* initial size */ + dev->free_slots = 50; /* initial size */ for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; @@ -835,7 +841,7 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne /* Slow down tx path */ if (atomic_read(&dev->active_tx_urbs) >= MAX_TX_URBS || - dev->free_slots < 5) { + dev->free_slots < CPC_TX_QUEUE_TRIGGER_LOW) { netif_stop_queue(netdev); } } diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 5eee62badf45..cbc99d5649af 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -826,9 +826,8 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface static void gs_destroy_candev(struct gs_can *dev) { unregister_candev(dev->netdev); - free_candev(dev->netdev); usb_kill_anchored_urbs(&dev->tx_submitted); - kfree(dev); + free_candev(dev->netdev); } static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) @@ -913,12 +912,15 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id * for (i = 0; i < icount; i++) { dev->canch[i] = gs_make_candev(i, intf); if (IS_ERR_OR_NULL(dev->canch[i])) { + /* save error code to return later */ + rc = PTR_ERR(dev->canch[i]); + /* on failure destroy previously created candevs */ icount = i; - for (i = 0; i < icount; i++) { + for (i = 0; i < icount; i++) gs_destroy_candev(dev->canch[i]); - dev->canch[i] = NULL; - } + + usb_kill_anchored_urbs(&dev->rx_submitted); kfree(dev); return rc; } @@ -939,16 +941,12 @@ static void gs_usb_disconnect(struct usb_interface *intf) return; } - for (i = 0; i < GS_MAX_INTF; i++) { - struct gs_can *can = dev->canch[i]; - - if (!can) - continue; - - gs_destroy_candev(can); - } + for (i = 0; i < GS_MAX_INTF; i++) + if (dev->canch[i]) + gs_destroy_candev(dev->canch[i]); usb_kill_anchored_urbs(&dev->rx_submitted); + kfree(dev); } static const struct usb_device_id gs_usb_table[] = { diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index b06dba05594a..2dea39b5cb0b 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1519,7 +1519,7 @@ int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, /* no PVID with ranges, otherwise it's a bug */ if (pvid) - err = _mv88e6xxx_port_pvid_set(ds, port, vid); + err = _mv88e6xxx_port_pvid_set(ds, port, vlan->vid_end); unlock: mutex_unlock(&ps->smi_mutex); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 17f017ab4dac..0fb3f8de88e9 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1197,7 +1197,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, dev->stats.tx_bytes += tx_cb_ptr->skb->len; dma_unmap_single(&dev->dev, dma_unmap_addr(tx_cb_ptr, dma_addr), - tx_cb_ptr->skb->len, + dma_unmap_len(tx_cb_ptr, dma_len), DMA_TO_DEVICE); bcmgenet_free_cb(tx_cb_ptr); } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { @@ -1308,7 +1308,7 @@ static int bcmgenet_xmit_single(struct net_device *dev, } dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); - dma_unmap_len_set(tx_cb_ptr, dma_len, skb->len); + dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len); length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) | DMA_TX_APPEND_CRC; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 79789d8e52da..ca5ac5d6f4e6 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -7833,6 +7833,14 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, return ret; } +static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb) +{ + /* Check if we will never have enough descriptors, + * as gso_segs can be more than current ring size + */ + return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3; +} + static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *); /* Use GSO to workaround all TSO packets that meet HW bug conditions @@ -7936,14 +7944,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) * vlan encapsulated. */ if (skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD)) - return tg3_tso_bug(tp, tnapi, txq, skb); + skb->protocol == htons(ETH_P_8021AD)) { + if (tg3_tso_bug_gso_check(tnapi, skb)) + return tg3_tso_bug(tp, tnapi, txq, skb); + goto drop; + } if (!skb_is_gso_v6(skb)) { if (unlikely((ETH_HLEN + hdr_len) > 80) && - tg3_flag(tp, TSO_BUG)) - return tg3_tso_bug(tp, tnapi, txq, skb); - + tg3_flag(tp, TSO_BUG)) { + if (tg3_tso_bug_gso_check(tnapi, skb)) + return tg3_tso_bug(tp, tnapi, txq, skb); + goto drop; + } ip_csum = iph->check; ip_tot_len = iph->tot_len; iph->check = 0; @@ -8075,7 +8088,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) if (would_hit_hwbug) { tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i); - if (mss) { + if (mss && tg3_tso_bug_gso_check(tnapi, skb)) { /* If it's a TSO packet, do GSO instead of * allocating and copying to a large linear SKB */ diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 1671fa3332c2..7ba6d530b0c0 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -33,7 +33,7 @@ #define DRV_NAME "enic" #define DRV_DESCRIPTION "Cisco VIC Ethernet NIC Driver" -#define DRV_VERSION "2.3.0.12" +#define DRV_VERSION "2.3.0.20" #define DRV_COPYRIGHT "Copyright 2008-2013 Cisco Systems, Inc" #define ENIC_BARS_MAX 6 diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c index 1ffd1050860b..1fdf5fe12a95 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_dev.c +++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c @@ -298,7 +298,8 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, int wait) { struct devcmd2_controller *dc2c = vdev->devcmd2; - struct devcmd2_result *result = dc2c->result + dc2c->next_result; + struct devcmd2_result *result; + u8 color; unsigned int i; int delay, err; u32 fetch_index, new_posted; @@ -336,13 +337,17 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, if (dc2c->cmd_ring[posted].flags & DEVCMD2_FNORESULT) return 0; + result = dc2c->result + dc2c->next_result; + color = dc2c->color; + + dc2c->next_result++; + if (dc2c->next_result == dc2c->result_size) { + dc2c->next_result = 0; + dc2c->color = dc2c->color ? 0 : 1; + } + for (delay = 0; delay < wait; delay++) { - if (result->color == dc2c->color) { - dc2c->next_result++; - if (dc2c->next_result == dc2c->result_size) { - dc2c->next_result = 0; - dc2c->color = dc2c->color ? 0 : 1; - } + if (result->color == color) { if (result->error) { err = result->error; if (err != ERR_ECMDUNKNOWN || diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 060dd3922974..1257b18e6b90 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme) } static inline void -jme_clear_pm(struct jme_adapter *jme) +jme_clear_pm_enable_wol(struct jme_adapter *jme) { jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs); } +static inline void +jme_clear_pm_disable_wol(struct jme_adapter *jme) +{ + jwrite32(jme, JME_PMCS, PMCS_STMASK); +} + static int jme_reload_eeprom(struct jme_adapter *jme) { @@ -1853,7 +1859,7 @@ jme_open(struct net_device *netdev) struct jme_adapter *jme = netdev_priv(netdev); int rc; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); JME_NAPI_ENABLE(jme); tasklet_init(&jme->linkch_task, jme_link_change_tasklet, @@ -1925,11 +1931,11 @@ jme_wait_link(struct jme_adapter *jme) static void jme_powersave_phy(struct jme_adapter *jme) { - if (jme->reg_pmcs) { + if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) { jme_set_100m_half(jme); if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN)) jme_wait_link(jme); - jme_clear_pm(jme); + jme_clear_pm_enable_wol(jme); } else { jme_phy_off(jme); } @@ -2646,9 +2652,6 @@ jme_set_wol(struct net_device *netdev, if (wol->wolopts & WAKE_MAGIC) jme->reg_pmcs |= PMCS_MFEN; - jwrite32(jme, JME_PMCS, jme->reg_pmcs); - device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs)); - return 0; } @@ -3172,8 +3175,8 @@ jme_init_one(struct pci_dev *pdev, jme->mii_if.mdio_read = jme_mdio_read; jme->mii_if.mdio_write = jme_mdio_write; - jme_clear_pm(jme); - device_set_wakeup_enable(&pdev->dev, true); + jme_clear_pm_disable_wol(jme); + device_init_wakeup(&pdev->dev, true); jme_set_phyfifo_5level(jme); jme->pcirev = pdev->revision; @@ -3304,7 +3307,7 @@ jme_resume(struct device *dev) if (!netif_running(netdev)) return 0; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); jme_phy_on(jme); if (test_bit(JME_FLAG_SSET, &jme->flags)) jme_set_settings(netdev, &jme->old_ecmd); @@ -3312,13 +3315,14 @@ jme_resume(struct device *dev) jme_reset_phy_processor(jme); jme_phy_calibration(jme); jme_phy_setEA(jme); - jme_start_irq(jme); netif_device_attach(netdev); atomic_inc(&jme->link_changing); jme_reset_link(jme); + jme_start_irq(jme); + return 0; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index ed622fa29dfa..a4ac6fedac75 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3404,7 +3404,7 @@ static int mvneta_probe(struct platform_device *pdev) dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; dev->hw_features |= dev->features; dev->vlan_features |= dev->features; - dev->priv_flags |= IFF_UNICAST_FLT; + dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; dev->gso_max_segs = MVNETA_MAX_TSO_SEGS; err = register_netdev(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 038f9ce391e6..1494997c4f7e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -236,6 +236,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = { .enable = mlx4_en_phc_enable, }; +#define MLX4_EN_WRAP_AROUND_SEC 10ULL + +/* This function calculates the max shift that enables the user range + * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register. + */ +static u32 freq_to_shift(u16 freq) +{ + u32 freq_khz = freq * 1000; + u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC; + u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ? + max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1; + /* calculate max possible multiplier in order to fit in 64bit */ + u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded); + + /* This comes from the reverse of clocksource_khz2mult */ + return ilog2(div_u64(max_mul * freq_khz, 1000000)); +} + void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) { struct mlx4_dev *dev = mdev->dev; @@ -254,12 +272,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) memset(&mdev->cycles, 0, sizeof(mdev->cycles)); mdev->cycles.read = mlx4_en_read_clock; mdev->cycles.mask = CLOCKSOURCE_MASK(48); - /* Using shift to make calculation more accurate. Since current HW - * clock frequency is 427 MHz, and cycles are given using a 48 bits - * register, the biggest shift when calculating using u64, is 14 - * (max_cycles * multiplier < 2^64) - */ - mdev->cycles.shift = 14; + mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock); mdev->cycles.mult = clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift); mdev->nominal_c_mult = mdev->cycles.mult; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 7869f97de5da..67e9633ea9c7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2381,8 +2381,6 @@ out: /* set offloads */ priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL; - priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - priv->dev->features |= NETIF_F_GSO_UDP_TUNNEL; } static void mlx4_en_del_vxlan_offloads(struct work_struct *work) @@ -2393,8 +2391,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work) /* unset offloads */ priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL); - priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL; - priv->dev->features &= ~NETIF_F_GSO_UDP_TUNNEL; ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 0); @@ -3020,6 +3016,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->rss_hash_fn = ETH_RSS_HASH_TOP; } + if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + dev->features |= NETIF_F_GSO_UDP_TUNNEL; + } + mdev->pndev[port] = dev; mdev->upper[port] = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index ee99e67187f5..3904b5fc0b7c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -238,11 +238,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) stats->collisions = 0; stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP); stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength); - stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); + stats->rx_over_errors = 0; stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC); stats->rx_frame_errors = 0; stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); - stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); + stats->rx_missed_errors = 0; stats->tx_aborted_errors = 0; stats->tx_carrier_errors = 0; stats->tx_fifo_errors = 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index cad6c44df91c..d314d96dcb1c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3132,7 +3132,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, case QP_TRANS_RTS2RTS: case QP_TRANS_SQD2SQD: case QP_TRANS_SQD2RTS: - if (slave != mlx4_master_func_num(dev)) + if (slave != mlx4_master_func_num(dev)) { if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) { port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1; if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) @@ -3151,6 +3151,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, if (qp_ctx->alt_path.mgid_index >= num_gids) return -EINVAL; } + } break; default: break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1e52db32c73d..1203d892e842 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -746,7 +746,7 @@ static int mlx5e_create_cq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; int eqn_not_used; - int irqn; + unsigned int irqn; int err; u32 i; @@ -800,7 +800,7 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) void *in; void *cqc; int inlen; - int irqn_not_used; + unsigned int irqn_not_used; int eqn; int err; @@ -1504,7 +1504,7 @@ static int mlx5e_create_drop_cq(struct mlx5e_priv *priv, struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; int eqn_not_used; - int irqn; + unsigned int irqn; int err; err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 4ac8d4cc4973..6cf6d93d8831 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -568,7 +568,8 @@ static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev) mlx5_irq_clear_affinity_hint(mdev, i); } -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn) +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, + unsigned int *irqn) { struct mlx5_eq_table *table = &dev->priv.eq_table; struct mlx5_eq *eq, *n; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 4365c8bccc6d..605f6410f867 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -61,6 +61,8 @@ struct mlxsw_sp { #define MLXSW_SP_DEFAULT_LEARNING_INTERVAL 100 unsigned int interval; /* ms */ } fdb_notify; +#define MLXSW_SP_MIN_AGEING_TIME 10 +#define MLXSW_SP_MAX_AGEING_TIME 1000000 #define MLXSW_SP_DEFAULT_AGEING_TIME 300 u32 ageing_time; struct { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 617fb22b5d81..d4c4c2b5156c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -45,6 +45,7 @@ #include <linux/if_bridge.h> #include <linux/workqueue.h> #include <linux/jiffies.h> +#include <linux/rtnetlink.h> #include <net/switchdev.h> #include "spectrum.h" @@ -231,8 +232,13 @@ static int mlxsw_sp_port_attr_br_ageing_set(struct mlxsw_sp_port *mlxsw_sp_port, unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t); u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000; - if (switchdev_trans_ph_prepare(trans)) - return 0; + if (switchdev_trans_ph_prepare(trans)) { + if (ageing_time < MLXSW_SP_MIN_AGEING_TIME || + ageing_time > MLXSW_SP_MAX_AGEING_TIME) + return -ERANGE; + else + return 0; + } return mlxsw_sp_ageing_set(mlxsw_sp, ageing_time); } @@ -812,6 +818,7 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work) mlxsw_sp = container_of(work, struct mlxsw_sp, fdb_notify.dw.work); + rtnl_lock(); do { mlxsw_reg_sfn_pack(sfn_pl); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl); @@ -824,6 +831,7 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work) mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i); } while (num_rec); + rtnl_unlock(); kfree(sfn_pl); mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 46bbea8e023c..55007f1e6bbc 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -566,6 +566,7 @@ struct qlcnic_adapter_stats { u64 tx_dma_map_error; u64 spurious_intr; u64 mac_filter_limit_overrun; + u64 mbx_spurious_intr; }; /* @@ -1099,7 +1100,7 @@ struct qlcnic_mailbox { unsigned long status; spinlock_t queue_lock; /* Mailbox queue lock */ spinlock_t aen_lock; /* Mailbox response/AEN lock */ - atomic_t rsp_status; + u32 rsp_status; u32 num_cmds; }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 37a731be7d39..f9640d5ce6ba 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -491,7 +491,7 @@ irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *adapter) static inline void qlcnic_83xx_notify_mbx_response(struct qlcnic_mailbox *mbx) { - atomic_set(&mbx->rsp_status, QLC_83XX_MBX_RESPONSE_ARRIVED); + mbx->rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED; complete(&mbx->completion); } @@ -510,7 +510,7 @@ static void qlcnic_83xx_poll_process_aen(struct qlcnic_adapter *adapter) if (event & QLCNIC_MBX_ASYNC_EVENT) { __qlcnic_83xx_process_aen(adapter); } else { - if (atomic_read(&mbx->rsp_status) != rsp_status) + if (mbx->rsp_status != rsp_status) qlcnic_83xx_notify_mbx_response(mbx); } out: @@ -1023,7 +1023,7 @@ static void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) if (event & QLCNIC_MBX_ASYNC_EVENT) { __qlcnic_83xx_process_aen(adapter); } else { - if (atomic_read(&mbx->rsp_status) != rsp_status) + if (mbx->rsp_status != rsp_status) qlcnic_83xx_notify_mbx_response(mbx); } } @@ -2338,9 +2338,9 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter, static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data) { + u32 mask, resp, event, rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED; struct qlcnic_adapter *adapter = data; struct qlcnic_mailbox *mbx; - u32 mask, resp, event; unsigned long flags; mbx = adapter->ahw->mailbox; @@ -2350,10 +2350,14 @@ static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data) goto out; event = readl(QLCNIC_MBX_FW(adapter->ahw, 0)); - if (event & QLCNIC_MBX_ASYNC_EVENT) + if (event & QLCNIC_MBX_ASYNC_EVENT) { __qlcnic_83xx_process_aen(adapter); - else - qlcnic_83xx_notify_mbx_response(mbx); + } else { + if (mbx->rsp_status != rsp_status) + qlcnic_83xx_notify_mbx_response(mbx); + else + adapter->stats.mbx_spurious_intr++; + } out: mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK); @@ -4050,10 +4054,10 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) struct qlcnic_adapter *adapter = mbx->adapter; const struct qlcnic_mbx_ops *mbx_ops = mbx->ops; struct device *dev = &adapter->pdev->dev; - atomic_t *rsp_status = &mbx->rsp_status; struct list_head *head = &mbx->cmd_q; struct qlcnic_hardware_context *ahw; struct qlcnic_cmd_args *cmd = NULL; + unsigned long flags; ahw = adapter->ahw; @@ -4063,7 +4067,9 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) return; } - atomic_set(rsp_status, QLC_83XX_MBX_RESPONSE_WAIT); + spin_lock_irqsave(&mbx->aen_lock, flags); + mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT; + spin_unlock_irqrestore(&mbx->aen_lock, flags); spin_lock(&mbx->queue_lock); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 494e8105adee..0a2318cad34d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -59,7 +59,8 @@ static const struct qlcnic_stats qlcnic_gstrings_stats[] = { QLC_OFF(stats.mac_filter_limit_overrun)}, {"spurious intr", QLC_SIZEOF(stats.spurious_intr), QLC_OFF(stats.spurious_intr)}, - + {"mbx spurious intr", QLC_SIZEOF(stats.mbx_spurious_intr), + QLC_OFF(stats.mbx_spurious_intr)}, }; static const char qlcnic_device_gstrings_stats[][ETH_GSTRING_LEN] = { diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 997976426799..b28e73ea2c25 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -1648,7 +1648,18 @@ static void ql_process_mac_rx_skb(struct ql_adapter *qdev, return; } skb_reserve(new_skb, NET_IP_ALIGN); + + pci_dma_sync_single_for_cpu(qdev->pdev, + dma_unmap_addr(sbq_desc, mapaddr), + dma_unmap_len(sbq_desc, maplen), + PCI_DMA_FROMDEVICE); + memcpy(skb_put(new_skb, length), skb->data, length); + + pci_dma_sync_single_for_device(qdev->pdev, + dma_unmap_addr(sbq_desc, mapaddr), + dma_unmap_len(sbq_desc, maplen), + PCI_DMA_FROMDEVICE); skb = new_skb; /* Frame error, so drop the packet. */ diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 689a4a5c8dcf..1ef03939d25f 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -811,7 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev) dev->netdev_ops = &qcaspi_netdev_ops; qcaspi_set_ethtool_ops(dev); dev->watchdog_timeo = QCASPI_TX_TIMEOUT; - dev->flags = IFF_MULTICAST; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->tx_queue_len = 100; qca = netdev_priv(dev); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 6a8fc0f341ff..36fc9427418f 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1185,11 +1185,8 @@ static void sh_eth_ring_format(struct net_device *ndev) break; sh_eth_set_receive_align(skb); - /* RX descriptor */ - rxdesc = &mdp->rx_ring[i]; /* The size of the buffer is a multiple of 32 bytes. */ buf_len = ALIGN(mdp->rx_buf_sz, 32); - rxdesc->len = cpu_to_edmac(mdp, buf_len << 16); dma_addr = dma_map_single(&ndev->dev, skb->data, buf_len, DMA_FROM_DEVICE); if (dma_mapping_error(&ndev->dev, dma_addr)) { @@ -1197,6 +1194,10 @@ static void sh_eth_ring_format(struct net_device *ndev) break; } mdp->rx_skbuff[i] = skb; + + /* RX descriptor */ + rxdesc = &mdp->rx_ring[i]; + rxdesc->len = cpu_to_edmac(mdp, buf_len << 16); rxdesc->addr = cpu_to_edmac(mdp, dma_addr); rxdesc->status = cpu_to_edmac(mdp, RD_RACT | RD_RFP); @@ -1212,7 +1213,8 @@ static void sh_eth_ring_format(struct net_device *ndev) mdp->dirty_rx = (u32) (i - mdp->num_rx_ring); /* Mark the last entry as wrapping the ring. */ - rxdesc->status |= cpu_to_edmac(mdp, RD_RDLE); + if (rxdesc) + rxdesc->status |= cpu_to_edmac(mdp, RD_RDLE); memset(mdp->tx_ring, 0, tx_ringsize); diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index e9f2349e98bc..2b34622a4bfe 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -239,6 +239,7 @@ struct rocker { struct { u64 id; } hw; + unsigned long ageing_time; spinlock_t cmd_ring_lock; /* for cmd ring accesses */ struct rocker_dma_ring_info cmd_ring; struct rocker_dma_ring_info event_ring; @@ -3531,12 +3532,14 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) info.addr = lw->addr; info.vid = lw->vid; + rtnl_lock(); if (learned && removing) call_switchdev_notifiers(SWITCHDEV_FDB_DEL, lw->rocker_port->dev, &info.info); else if (learned && !removing) call_switchdev_notifiers(SWITCHDEV_FDB_ADD, lw->rocker_port->dev, &info.info); + rtnl_unlock(); rocker_port_kfree(lw->trans, work); } @@ -3702,7 +3705,7 @@ static void rocker_fdb_cleanup(unsigned long data) struct rocker_port *rocker_port; struct rocker_fdb_tbl_entry *entry; struct hlist_node *tmp; - unsigned long next_timer = jiffies + BR_MIN_AGEING_TIME; + unsigned long next_timer = jiffies + rocker->ageing_time; unsigned long expires; unsigned long lock_flags; int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE | @@ -4365,8 +4368,12 @@ static int rocker_port_bridge_ageing_time(struct rocker_port *rocker_port, struct switchdev_trans *trans, u32 ageing_time) { + struct rocker *rocker = rocker_port->rocker; + if (!switchdev_trans_ph_prepare(trans)) { rocker_port->ageing_time = clock_t_to_jiffies(ageing_time); + if (rocker_port->ageing_time < rocker->ageing_time) + rocker->ageing_time = rocker_port->ageing_time; mod_timer(&rocker_port->rocker->fdb_cleanup_timer, jiffies); } @@ -5204,10 +5211,13 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_init_tbls; } + rocker->ageing_time = BR_DEFAULT_AGEING_TIME; setup_timer(&rocker->fdb_cleanup_timer, rocker_fdb_cleanup, (unsigned long) rocker); mod_timer(&rocker->fdb_cleanup_timer, jiffies); + rocker->ageing_time = BR_DEFAULT_AGEING_TIME; + err = rocker_probe_ports(rocker); if (err) { dev_err(&pdev->dev, "failed to probe ports\n"); diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 9066d7a8483c..f96c6b3606f2 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -2107,7 +2107,7 @@ static int dwceqos_tx_frags(struct sk_buff *skb, struct net_local *lp, dd = &lp->tx_descs[lp->tx_next]; /* Set DMA Descriptor fields */ - dd->des0 = dma_handle; + dd->des0 = dma_handle + consumed_size; dd->des1 = 0; dd->des2 = dma_size; diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c index 696852eb23c3..7a3f990c1935 100644 --- a/drivers/net/irda/irtty-sir.c +++ b/drivers/net/irda/irtty-sir.c @@ -430,16 +430,6 @@ static int irtty_open(struct tty_struct *tty) /* Module stuff handled via irda_ldisc.owner - Jean II */ - /* First make sure we're not already connected. */ - if (tty->disc_data != NULL) { - priv = tty->disc_data; - if (priv && priv->magic == IRTTY_MAGIC) { - ret = -EEXIST; - goto out; - } - tty->disc_data = NULL; /* ### */ - } - /* stop the underlying driver */ irtty_stop_receiver(tty, TRUE); if (tty->ops->stop) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 0fc521941c71..159a68782bec 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -760,6 +760,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN; if (copylen > good_linear) copylen = good_linear; + else if (copylen < ETH_HLEN) + copylen = ETH_HLEN; linear = copylen; i = *from; iov_iter_advance(&i, copylen); @@ -769,10 +771,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (!zerocopy) { copylen = len; - if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear) + linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len); + if (linear > good_linear) linear = good_linear; - else - linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len); + else if (linear < ETH_HLEN) + linear = ETH_HLEN; } skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen, diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 47b711739ba9..e6cefd0e3262 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -845,6 +845,11 @@ static void decode_rxts(struct dp83640_private *dp83640, struct skb_shared_hwtstamps *shhwtstamps = NULL; struct sk_buff *skb; unsigned long flags; + u8 overflow; + + overflow = (phy_rxts->ns_hi >> 14) & 0x3; + if (overflow) + pr_debug("rx timestamp queue overflow, count %d\n", overflow); spin_lock_irqsave(&dp83640->rx_lock, flags); @@ -887,6 +892,7 @@ static void decode_txts(struct dp83640_private *dp83640, struct skb_shared_hwtstamps shhwtstamps; struct sk_buff *skb; u64 ns; + u8 overflow; /* We must already have the skb that triggered this. */ @@ -896,6 +902,17 @@ static void decode_txts(struct dp83640_private *dp83640, pr_debug("have timestamp but tx_queue empty\n"); return; } + + overflow = (phy_txts->ns_hi >> 14) & 0x3; + if (overflow) { + pr_debug("tx timestamp queue overflow, count %d\n", overflow); + while (skb) { + skb_complete_tx_timestamp(skb, NULL); + skb = skb_dequeue(&dp83640->tx_queue); + } + return; + } + ns = phy2txts(phy_txts); memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ns_to_ktime(ns); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 9a863c6a6a33..174e06ec7c2f 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -567,7 +567,7 @@ static int get_filter(void __user *arg, struct sock_filter **p) static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct ppp_file *pf = file->private_data; + struct ppp_file *pf; struct ppp *ppp; int err = -EFAULT, val, val2, i; struct ppp_idle idle; @@ -577,9 +577,14 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) void __user *argp = (void __user *)arg; int __user *p = argp; - if (!pf) - return ppp_unattached_ioctl(current->nsproxy->net_ns, - pf, file, cmd, arg); + mutex_lock(&ppp_mutex); + + pf = file->private_data; + if (!pf) { + err = ppp_unattached_ioctl(current->nsproxy->net_ns, + pf, file, cmd, arg); + goto out; + } if (cmd == PPPIOCDETACH) { /* @@ -594,7 +599,6 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) * this fd and reopening /dev/ppp. */ err = -EINVAL; - mutex_lock(&ppp_mutex); if (pf->kind == INTERFACE) { ppp = PF_TO_PPP(pf); rtnl_lock(); @@ -608,15 +612,13 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } else pr_warn("PPPIOCDETACH file->f_count=%ld\n", atomic_long_read(&file->f_count)); - mutex_unlock(&ppp_mutex); - return err; + goto out; } if (pf->kind == CHANNEL) { struct channel *pch; struct ppp_channel *chan; - mutex_lock(&ppp_mutex); pch = PF_TO_CHANNEL(pf); switch (cmd) { @@ -638,17 +640,16 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) err = chan->ops->ioctl(chan, cmd, arg); up_read(&pch->chan_sem); } - mutex_unlock(&ppp_mutex); - return err; + goto out; } if (pf->kind != INTERFACE) { /* can't happen */ pr_err("PPP: not interface or channel??\n"); - return -EINVAL; + err = -EINVAL; + goto out; } - mutex_lock(&ppp_mutex); ppp = PF_TO_PPP(pf); switch (cmd) { case PPPIOCSMRU: @@ -823,7 +824,10 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) default: err = -ENOTTY; } + +out: mutex_unlock(&ppp_mutex); + return err; } @@ -836,7 +840,6 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct ppp_net *pn; int __user *p = (int __user *)arg; - mutex_lock(&ppp_mutex); switch (cmd) { case PPPIOCNEWUNIT: /* Create a new ppp unit */ @@ -886,7 +889,7 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, default: err = -ENOTTY; } - mutex_unlock(&ppp_mutex); + return err; } @@ -2290,7 +2293,7 @@ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan) pch->ppp = NULL; pch->chan = chan; - pch->chan_net = net; + pch->chan_net = get_net(net); chan->ppp = pch; init_ppp_file(&pch->file, CHANNEL); pch->file.hdrlen = chan->hdrlen; @@ -2387,6 +2390,8 @@ ppp_unregister_channel(struct ppp_channel *chan) spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); + put_net(pch->chan_net); + pch->chan_net = NULL; pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); @@ -2803,6 +2808,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, out2: mutex_unlock(&pn->all_ppp_mutex); + rtnl_unlock(); free_netdev(dev); out1: *retp = ret; diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 0a37f840fcc5..4e0068e775f9 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -395,6 +395,8 @@ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb) if (!__pppoe_xmit(sk_pppox(relay_po), skb)) goto abort_put; + + sock_put(sk_pppox(relay_po)); } else { if (sock_queue_rcv_skb(sk, skb)) goto abort_kfree; diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 597c53e0a2ec..f7e8c79349ad 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -129,24 +129,27 @@ static int lookup_chan_dst(u16 call_id, __be32 d_addr) return i < MAX_CALLID; } -static int add_chan(struct pppox_sock *sock) +static int add_chan(struct pppox_sock *sock, + struct pptp_addr *sa) { static int call_id; spin_lock(&chan_lock); - if (!sock->proto.pptp.src_addr.call_id) { + if (!sa->call_id) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1); if (call_id == MAX_CALLID) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1); if (call_id == MAX_CALLID) goto out_err; } - sock->proto.pptp.src_addr.call_id = call_id; - } else if (test_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap)) + sa->call_id = call_id; + } else if (test_bit(sa->call_id, callid_bitmap)) { goto out_err; + } - set_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap); - rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], sock); + sock->proto.pptp.src_addr = *sa; + set_bit(sa->call_id, callid_bitmap); + rcu_assign_pointer(callid_sock[sa->call_id], sock); spin_unlock(&chan_lock); return 0; @@ -416,7 +419,6 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); - struct pptp_opt *opt = &po->proto.pptp; int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) @@ -424,10 +426,22 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); - opt->src_addr = sp->sa_addr.pptp; - if (add_chan(po)) + if (sk->sk_state & PPPOX_DEAD) { + error = -EALREADY; + goto out; + } + + if (sk->sk_state & PPPOX_BOUND) { error = -EBUSY; + goto out; + } + + if (add_chan(po, &sp->sa_addr.pptp)) + error = -EBUSY; + else + sk->sk_state |= PPPOX_BOUND; +out: release_sock(sk); return error; } @@ -498,7 +512,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, } opt->dst_addr = sp->sa_addr.pptp; - sk->sk_state = PPPOX_CONNECTED; + sk->sk_state |= PPPOX_CONNECTED; end: release_sock(sk); diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index 01f08a7751f7..e7034c55e796 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -280,7 +280,7 @@ static void rionet_outb_msg_event(struct rio_mport *mport, void *dev_id, int mbo struct net_device *ndev = dev_id; struct rionet_private *rnet = netdev_priv(ndev); - spin_lock(&rnet->lock); + spin_lock(&rnet->tx_lock); if (netif_msg_intr(rnet)) printk(KERN_INFO @@ -299,7 +299,7 @@ static void rionet_outb_msg_event(struct rio_mport *mport, void *dev_id, int mbo if (rnet->tx_cnt < RIONET_TX_RING_SIZE) netif_wake_queue(ndev); - spin_unlock(&rnet->lock); + spin_unlock(&rnet->tx_lock); } static int rionet_open(struct net_device *ndev) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 651d35ea22c5..59fefca74263 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1845,10 +1845,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) struct team *team = netdev_priv(dev); struct team_port *port; - rcu_read_lock(); - list_for_each_entry_rcu(port, &team->port_list, list) + mutex_lock(&team->lock); + list_for_each_entry(port, &team->port_list, list) vlan_vid_del(port->dev, proto, vid); - rcu_read_unlock(); + mutex_unlock(&team->lock); return 0; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2228a539184a..de0d15e03e03 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -621,7 +621,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte /* Re-attach the filter to persist device */ if (!skip_filter && (tun->filter_attached == true)) { - err = sk_attach_filter(&tun->fprog, tfile->socket.sk); + err = __sk_attach_filter(&tun->fprog, tfile->socket.sk, + lockdep_rtnl_is_held()); if (!err) goto out; } @@ -1000,7 +1001,6 @@ static void tun_net_init(struct net_device *dev) /* Zero header length */ dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; - dev->tx_queue_len = TUN_READQ_SIZE; /* We prefer our own queue length */ break; case IFF_TAP: @@ -1012,7 +1012,6 @@ static void tun_net_init(struct net_device *dev) eth_hw_addr_random(dev); - dev->tx_queue_len = TUN_READQ_SIZE; /* We prefer our own queue length */ break; } } @@ -1463,6 +1462,8 @@ static void tun_setup(struct net_device *dev) dev->ethtool_ops = &tun_ethtool_ops; dev->destructor = tun_free_netdev; + /* We prefer our own queue length */ + dev->tx_queue_len = TUN_READQ_SIZE; } /* Trivial set of netlink ops to allow deleting tun or tap @@ -1804,7 +1805,7 @@ static void tun_detach_filter(struct tun_struct *tun, int n) for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); - sk_detach_filter(tfile->socket.sk); + __sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held()); } tun->filter_attached = false; @@ -1817,7 +1818,8 @@ static int tun_attach_filter(struct tun_struct *tun) for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); - ret = sk_attach_filter(&tun->fprog, tfile->socket.sk); + ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk, + lockdep_rtnl_is_held()); if (ret) { tun_detach_filter(tun, i); return ret; diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 3da70bf9936a..7cba2c3759df 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -160,6 +160,12 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf) info->u = header.usb_cdc_union_desc; info->header = header.usb_cdc_header_desc; info->ether = header.usb_cdc_ether_desc; + if (!info->u) { + if (rndis) + goto skip; + else /* in that case a quirk is mandatory */ + goto bad_desc; + } /* we need a master/control interface (what we're * probed with) and a slave/data interface; union * descriptors sort this all out. @@ -256,7 +262,7 @@ skip: goto bad_desc; } - } else if (!info->header || !info->u || (!rndis && !info->ether)) { + } else if (!info->header || (!rndis && !info->ether)) { dev_dbg(&intf->dev, "missing cdc %s%s%sdescriptor\n", info->header ? "" : "header ", info->u ? "" : "union ", diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index e8a1144c5a8b..8c2bb77db049 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -794,7 +794,11 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; - /* reset data interface */ + /* Reset data interface. Some devices will not reset properly + * unless they are configured first. Toggle the altsetting to + * force a reset + */ + usb_set_interface(dev->udev, iface_no, data_altsetting); temp = usb_set_interface(dev->udev, iface_no, 0); if (temp) { dev_dbg(&intf->dev, "set interface failed\n"); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 5fccc5a8153f..a34f491224c1 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -492,6 +492,7 @@ static const struct usb_device_id products[] = { /* 3. Combined interface devices matching on interface number */ {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ + {QMI_FIXED_INTF(0x05c6, 0x6001, 3)}, /* 4G LTE usb-modem U901 */ {QMI_FIXED_INTF(0x05c6, 0x7000, 0)}, {QMI_FIXED_INTF(0x05c6, 0x7001, 1)}, {QMI_FIXED_INTF(0x05c6, 0x7002, 1)}, @@ -698,6 +699,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x1426, 2)}, /* ZTE MF91 */ {QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */ {QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */ + {QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ @@ -717,8 +719,10 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9070, 8)}, /* Sierra Wireless MC74xx/EM74xx */ {QMI_FIXED_INTF(0x1199, 0x9070, 10)}, /* Sierra Wireless MC74xx/EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx/EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 0744bf2ef2d6..c2ea4e5666fb 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1766,6 +1766,13 @@ out3: if (info->unbind) info->unbind (dev, udev); out1: + /* subdrivers must undo all they did in bind() if they + * fail it, but we may fail later and a deferred kevent + * may trigger an error resubmitting itself and, worse, + * schedule a timer. So we kill it all just in case. + */ + cancel_work_sync(&dev->kevent); + del_timer_sync(&dev->delay); free_netdev(net); out: return status; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 0a242b200df4..903bda437839 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -114,20 +114,23 @@ static struct dst_ops vrf_dst_ops = { #if IS_ENABLED(CONFIG_IPV6) static bool check_ipv6_frame(const struct sk_buff *skb) { - const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data; - size_t hlen = sizeof(*ipv6h); + const struct ipv6hdr *ipv6h; + struct ipv6hdr _ipv6h; bool rc = true; - if (skb->len < hlen) + ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h); + if (!ipv6h) goto out; if (ipv6h->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; + struct icmp6hdr _icmph; - if (skb->len < hlen + sizeof(*icmph)) + icmph = skb_header_pointer(skb, sizeof(_ipv6h), + sizeof(_icmph), &_icmph); + if (!icmph) goto out; - icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h)); switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ba363cedef80..3c0df70e2f53 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1306,8 +1306,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) gbp = (struct vxlanhdr_gbp *)vxh; md->gbp = ntohs(gbp->policy_id); - if (tun_dst) + if (tun_dst) { tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT; + tun_dst->u.tun_info.options_len = sizeof(*md); + } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; @@ -1984,11 +1986,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, vxlan->cfg.port_max, true); if (info) { - if (info->key.tun_flags & TUNNEL_CSUM) - flags |= VXLAN_F_UDP_CSUM; - else - flags &= ~VXLAN_F_UDP_CSUM; - ttl = info->key.ttl; tos = info->key.tos; @@ -2003,8 +2000,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto drop; sk = vxlan->vn4_sock->sock->sk; - if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)) - df = htons(IP_DF); + if (info) { + if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + + if (info->key.tun_flags & TUNNEL_CSUM) + flags |= VXLAN_F_UDP_CSUM; + else + flags &= ~VXLAN_F_UDP_CSUM; + } memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0; @@ -2102,6 +2106,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } + if (info) { + if (info->key.tun_flags & TUNNEL_CSUM) + flags &= ~VXLAN_F_UDP_ZERO_CSUM6_TX; + else + flags |= VXLAN_F_UDP_ZERO_CSUM6_TX; + } + ttl = ttl ? : ip6_dst_hoplimit(ndst); err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr, 0, ttl, src_port, dst_port, htonl(vni << 8), md, @@ -2751,7 +2762,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_config *conf) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); - struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_dev *vxlan = netdev_priv(dev), *tmp; struct vxlan_rdst *dst = &vxlan->default_dst; unsigned short needed_headroom = ETH_HLEN; int err; @@ -2817,9 +2828,15 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, if (!vxlan->cfg.age_interval) vxlan->cfg.age_interval = FDB_AGE_DEFAULT; - if (vxlan_find_vni(src_net, conf->vni, use_ipv6 ? AF_INET6 : AF_INET, - vxlan->cfg.dst_port, vxlan->flags)) + list_for_each_entry(tmp, &vn->vxlan_list, next) { + if (tmp->cfg.vni == conf->vni && + (tmp->default_dst.remote_ip.sa.sa_family == AF_INET6 || + tmp->cfg.saddr.sa.sa_family == AF_INET6) == use_ipv6 && + tmp->cfg.dst_port == vxlan->cfg.dst_port && + (tmp->flags & VXLAN_F_RCV_FLAGS) == + (vxlan->flags & VXLAN_F_RCV_FLAGS)) return -EEXIST; + } dev->ethtool_ops = &vxlan_ethtool_ops; diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 44541dbc5c28..69b994f3b8c5 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -2516,7 +2516,7 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->mem_start = card->phys_mem + BUF_OFFSET ( txBuffer[i][0][0]); dev->mem_end = card->phys_mem - + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]); + + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]); dev->base_addr = card->pci_conf; dev->irq = card->irq; diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c index 8f8793004b9f..1b271b99c49e 100644 --- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c @@ -274,6 +274,9 @@ void ar5008_hw_cmn_spur_mitigate(struct ath_hw *ah, }; static const int inc[4] = { 0, 100, 0, 0 }; + memset(&mask_m, 0, sizeof(int8_t) * 123); + memset(&mask_p, 0, sizeof(int8_t) * 123); + cur_bin = -6000; upper = bin + 100; lower = bin - 100; @@ -424,14 +427,9 @@ static void ar5008_hw_spur_mitigate(struct ath_hw *ah, int tmp, new; int i; - int8_t mask_m[123]; - int8_t mask_p[123]; int cur_bb_spur; bool is2GHz = IS_CHAN_2GHZ(chan); - memset(&mask_m, 0, sizeof(int8_t) * 123); - memset(&mask_p, 0, sizeof(int8_t) * 123); - for (i = 0; i < AR_EEPROM_MODAL_SPURS; i++) { cur_bb_spur = ah->eep_ops->get_spur_channel(ah, i, is2GHz); if (AR_NO_SPUR == cur_bb_spur) diff --git a/drivers/net/wireless/ath/ath9k/ar9002_phy.c b/drivers/net/wireless/ath/ath9k/ar9002_phy.c index db6624527d99..53d7445a5d12 100644 --- a/drivers/net/wireless/ath/ath9k/ar9002_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9002_phy.c @@ -178,14 +178,9 @@ static void ar9002_hw_spur_mitigate(struct ath_hw *ah, int i; struct chan_centers centers; - int8_t mask_m[123]; - int8_t mask_p[123]; int cur_bb_spur; bool is2GHz = IS_CHAN_2GHZ(chan); - memset(&mask_m, 0, sizeof(int8_t) * 123); - memset(&mask_p, 0, sizeof(int8_t) * 123); - ath9k_hw_get_channel_centers(ah, chan, ¢ers); freq = centers.synth_center; diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c index cc81482c934d..113a43fca9cf 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.c +++ b/drivers/net/wireless/ath/ath9k/eeprom.c @@ -403,10 +403,9 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah, if (match) { if (AR_SREV_9287(ah)) { - /* FIXME: array overrun? */ for (i = 0; i < numXpdGains; i++) { minPwrT4[i] = data_9287[idxL].pwrPdg[i][0]; - maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4]; + maxPwrT4[i] = data_9287[idxL].pwrPdg[i][intercepts - 1]; ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i], data_9287[idxL].pwrPdg[i], data_9287[idxL].vpdPdg[i], @@ -416,7 +415,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah, } else if (eeprom_4k) { for (i = 0; i < numXpdGains; i++) { minPwrT4[i] = data_4k[idxL].pwrPdg[i][0]; - maxPwrT4[i] = data_4k[idxL].pwrPdg[i][4]; + maxPwrT4[i] = data_4k[idxL].pwrPdg[i][intercepts - 1]; ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i], data_4k[idxL].pwrPdg[i], data_4k[idxL].vpdPdg[i], @@ -426,7 +425,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah, } else { for (i = 0; i < numXpdGains; i++) { minPwrT4[i] = data_def[idxL].pwrPdg[i][0]; - maxPwrT4[i] = data_def[idxL].pwrPdg[i][4]; + maxPwrT4[i] = data_def[idxL].pwrPdg[i][intercepts - 1]; ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i], data_def[idxL].pwrPdg[i], data_def[idxL].vpdPdg[i], diff --git a/drivers/net/wireless/iwlwifi/dvm/lib.c b/drivers/net/wireless/iwlwifi/dvm/lib.c index e18629a16fb0..0961f33de05e 100644 --- a/drivers/net/wireless/iwlwifi/dvm/lib.c +++ b/drivers/net/wireless/iwlwifi/dvm/lib.c @@ -1154,6 +1154,9 @@ int iwlagn_suspend(struct iwl_priv *priv, struct cfg80211_wowlan *wowlan) priv->ucode_loaded = false; iwl_trans_stop_device(priv->trans); + ret = iwl_trans_start_hw(priv->trans); + if (ret) + goto out; priv->wowlan = true; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c index d906fa13ba97..610c442c7ab2 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/iwlwifi/mvm/fw.c @@ -106,7 +106,7 @@ static int iwl_send_tx_ant_cfg(struct iwl_mvm *mvm, u8 valid_tx_ant) sizeof(tx_ant_cmd), &tx_ant_cmd); } -static void iwl_free_fw_paging(struct iwl_mvm *mvm) +void iwl_free_fw_paging(struct iwl_mvm *mvm) { int i; @@ -126,6 +126,8 @@ static void iwl_free_fw_paging(struct iwl_mvm *mvm) get_order(mvm->fw_paging_db[i].fw_paging_size)); } kfree(mvm->trans->paging_download_buf); + mvm->trans->paging_download_buf = NULL; + memset(mvm->fw_paging_db, 0, sizeof(mvm->fw_paging_db)); } diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index e88afac51c5d..f96ab2f4b90e 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -1557,6 +1557,8 @@ void __iwl_mvm_mac_stop(struct iwl_mvm *mvm) /* the fw is stopped, the aux sta is dead: clean up driver state */ iwl_mvm_del_aux_sta(mvm); + iwl_free_fw_paging(mvm); + /* * Clear IN_HW_RESTART flag when stopping the hw (as restart_complete() * won't be called in this case). diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h index 4bde2d027dcd..244e26c26821 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h @@ -1190,6 +1190,9 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm, void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); +/* Paging */ +void iwl_free_fw_paging(struct iwl_mvm *mvm); + /* MVM debugfs */ #ifdef CONFIG_IWLWIFI_DEBUGFS int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir); diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c index d6e0c1b5c20c..8215d7405f64 100644 --- a/drivers/net/wireless/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/iwlwifi/mvm/scan.c @@ -1267,6 +1267,10 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm, return -EBUSY; } + /* we don't support "match all" in the firmware */ + if (!req->n_match_sets) + return -EOPNOTSUPP; + ret = iwl_mvm_check_running_scans(mvm, type); if (ret) return ret; diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c index c652a66be803..6743edf43aa8 100644 --- a/drivers/net/wireless/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/iwlwifi/mvm/tx.c @@ -421,6 +421,15 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) return -1; } + /* + * Increase the pending frames counter, so that later when a reply comes + * in and the counter is decreased - we don't start getting negative + * values. + * Note that we don't need to make sure it isn't agg'd, since we're + * TXing non-sta + */ + atomic_inc(&mvm->pending_frames[sta_id]); + return 0; } diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index 639761fb2bfb..d58c094f2f04 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -384,6 +384,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x095B, 0x5310, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_n_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5210, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5C10, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5412, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)}, @@ -401,10 +402,10 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x095A, 0x900A, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9112, iwl7265_2ac_cfg)}, - {IWL_PCI_DEVICE(0x095A, 0x9210, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095B, 0x9210, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x9200, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)}, - {IWL_PCI_DEVICE(0x095A, 0x9310, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095B, 0x9310, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9410, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5020, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x502A, iwl7265_2n_cfg)}, diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index 90283453073c..00e0332e2544 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -7,6 +7,7 @@ * * Copyright(c) 2007 - 2015 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -33,6 +34,7 @@ * * Copyright(c) 2005 - 2015 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 Intel Deutschland GmbH * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -729,8 +731,8 @@ static int iwl_pcie_rsa_race_bug_wa(struct iwl_trans *trans) */ val = iwl_read_prph(trans, PREG_AUX_BUS_WPROT_0); if (val & (BIT(1) | BIT(17))) { - IWL_INFO(trans, - "can't access the RSA semaphore it is write protected\n"); + IWL_DEBUG_INFO(trans, + "can't access the RSA semaphore it is write protected\n"); return 0; } @@ -924,9 +926,16 @@ monitor: if (dest->monitor_mode == EXTERNAL_MODE && trans_pcie->fw_mon_size) { iwl_write_prph(trans, le32_to_cpu(dest->base_reg), trans_pcie->fw_mon_phys >> dest->base_shift); - iwl_write_prph(trans, le32_to_cpu(dest->end_reg), - (trans_pcie->fw_mon_phys + - trans_pcie->fw_mon_size) >> dest->end_shift); + if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) + iwl_write_prph(trans, le32_to_cpu(dest->end_reg), + (trans_pcie->fw_mon_phys + + trans_pcie->fw_mon_size - 256) >> + dest->end_shift); + else + iwl_write_prph(trans, le32_to_cpu(dest->end_reg), + (trans_pcie->fw_mon_phys + + trans_pcie->fw_mon_size) >> + dest->end_shift); } } diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c index a6c8a4f7bfe9..d6c4f0f60839 100644 --- a/drivers/net/wireless/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/mwifiex/sta_ioctl.c @@ -313,6 +313,7 @@ int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss, mwifiex_dbg(adapter, ERROR, "Attempt to reconnect on csa closed chan(%d)\n", bss_desc->channel); + ret = -1; goto done; } diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index f46c9d7f6528..7f471bff435c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -801,7 +801,9 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw) hw_queue); if (rx_remained_cnt == 0) return; - + buffer_desc = &rtlpci->rx_ring[rxring_idx].buffer_desc[ + rtlpci->rx_ring[rxring_idx].idx]; + pdesc = (struct rtl_rx_desc *)skb->data; } else { /* rx descriptor */ pdesc = &rtlpci->rx_ring[rxring_idx].desc[ rtlpci->rx_ring[rxring_idx].idx]; @@ -824,13 +826,6 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw) new_skb = dev_alloc_skb(rtlpci->rxbuffersize); if (unlikely(!new_skb)) goto no_new; - if (rtlpriv->use_new_trx_flow) { - buffer_desc = - &rtlpci->rx_ring[rxring_idx].buffer_desc - [rtlpci->rx_ring[rxring_idx].idx]; - /*means rx wifi info*/ - pdesc = (struct rtl_rx_desc *)skb->data; - } memset(&rx_status , 0 , sizeof(rx_status)); rtlpriv->cfg->ops->query_rx_desc(hw, &stats, &rx_status, (u8 *)pdesc, skb); diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c index a62bf0a65c32..5be34118e0af 100644 --- a/drivers/net/wireless/realtek/rtlwifi/regd.c +++ b/drivers/net/wireless/realtek/rtlwifi/regd.c @@ -351,7 +351,6 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select( case COUNTRY_CODE_SPAIN: case COUNTRY_CODE_FRANCE: case COUNTRY_CODE_ISRAEL: - case COUNTRY_CODE_WORLD_WIDE_13: return &rtl_regdom_12_13; case COUNTRY_CODE_MKK: case COUNTRY_CODE_MKK1: @@ -360,6 +359,7 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select( return &rtl_regdom_14_60_64; case COUNTRY_CODE_GLOBAL_DOMAIN: return &rtl_regdom_14; + case COUNTRY_CODE_WORLD_WIDE_13: case COUNTRY_CODE_WORLD_WIDE_13_5G_ALL: return &rtl_regdom_12_13_5g_all; default: diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c index 11344121c55e..47e32cb0ec1a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c @@ -88,8 +88,6 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw) u8 tid; rtl8188ee_bt_reg_init(hw); - rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; - rtlpriv->dm.dm_initialgain_enable = 1; rtlpriv->dm.dm_flag = 0; rtlpriv->dm.disable_framebursting = 0; @@ -138,6 +136,11 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.inactiveps = rtlpriv->cfg->mod_params->inactiveps; rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; + rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; + rtlpriv->cfg->mod_params->sw_crypto = + rtlpriv->cfg->mod_params->sw_crypto; + rtlpriv->cfg->mod_params->disable_watchdog = + rtlpriv->cfg->mod_params->disable_watchdog; if (rtlpriv->cfg->mod_params->disable_watchdog) pr_info("watchdog disabled\n"); if (!rtlpriv->psc.inactiveps) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c index de6cb6c3a48c..4780bdc63b2b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c @@ -139,6 +139,8 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.inactiveps = rtlpriv->cfg->mod_params->inactiveps; rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; + rtlpriv->cfg->mod_params->sw_crypto = + rtlpriv->cfg->mod_params->sw_crypto; if (!rtlpriv->psc.inactiveps) pr_info("rtl8192ce: Power Save off (module option)\n"); if (!rtlpriv->psc.fwctrl_lps) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c index fd4a5353d216..7c6f7f0d18c6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c @@ -65,6 +65,8 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->dm.disable_framebursting = false; rtlpriv->dm.thermalvalue = 0; rtlpriv->dbg.global_debuglevel = rtlpriv->cfg->mod_params->debug; + rtlpriv->cfg->mod_params->sw_crypto = + rtlpriv->cfg->mod_params->sw_crypto; /* for firmware buf */ rtlpriv->rtlhal.pfirmware = vzalloc(0x4000); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c index b19d0398215f..c6e09a19de1a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c @@ -376,8 +376,8 @@ module_param_named(swlps, rtl92de_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl92de_mod_params.fwctrl_lps, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); -MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); -MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); +MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 1)\n"); +MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 0)\n"); MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)"); static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c index e1fd27c888bf..31baca41ac2f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c @@ -187,6 +187,8 @@ static int rtl92s_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.inactiveps = rtlpriv->cfg->mod_params->inactiveps; rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; + rtlpriv->cfg->mod_params->sw_crypto = + rtlpriv->cfg->mod_params->sw_crypto; if (!rtlpriv->psc.inactiveps) pr_info("Power Save off (module option)\n"); if (!rtlpriv->psc.fwctrl_lps) @@ -425,8 +427,8 @@ module_param_named(swlps, rtl92se_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl92se_mod_params.fwctrl_lps, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); -MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); -MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); +MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 1)\n"); +MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 0)\n"); MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)"); static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c index 3859b3e3d158..ff49a8c0ff61 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c @@ -150,6 +150,11 @@ int rtl8723e_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.inactiveps = rtlpriv->cfg->mod_params->inactiveps; rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; + rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; + rtlpriv->cfg->mod_params->sw_crypto = + rtlpriv->cfg->mod_params->sw_crypto; + rtlpriv->cfg->mod_params->disable_watchdog = + rtlpriv->cfg->mod_params->disable_watchdog; if (rtlpriv->cfg->mod_params->disable_watchdog) pr_info("watchdog disabled\n"); rtlpriv->psc.reg_fwctrl_lps = 3; @@ -267,6 +272,8 @@ static struct rtl_mod_params rtl8723e_mod_params = { .swctrl_lps = false, .fwctrl_lps = true, .debug = DBG_EMERG, + .msi_support = false, + .disable_watchdog = false, }; static struct rtl_hal_cfg rtl8723e_hal_cfg = { @@ -383,12 +390,14 @@ module_param_named(debug, rtl8723e_mod_params.debug, int, 0444); module_param_named(ips, rtl8723e_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl8723e_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl8723e_mod_params.fwctrl_lps, bool, 0444); +module_param_named(msi, rtl8723e_mod_params.msi_support, bool, 0444); module_param_named(disable_watchdog, rtl8723e_mod_params.disable_watchdog, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); +MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n"); MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c index d091f1d5f91e..a78eaeda0008 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c @@ -93,7 +93,6 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw) struct rtl_mac *mac = rtl_mac(rtl_priv(hw)); rtl8723be_bt_reg_init(hw); - rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer(); rtlpriv->dm.dm_initialgain_enable = 1; @@ -151,6 +150,10 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; + rtlpriv->cfg->mod_params->sw_crypto = + rtlpriv->cfg->mod_params->sw_crypto; + rtlpriv->cfg->mod_params->disable_watchdog = + rtlpriv->cfg->mod_params->disable_watchdog; if (rtlpriv->cfg->mod_params->disable_watchdog) pr_info("watchdog disabled\n"); rtlpriv->psc.reg_fwctrl_lps = 3; @@ -267,6 +270,9 @@ static struct rtl_mod_params rtl8723be_mod_params = { .inactiveps = true, .swctrl_lps = false, .fwctrl_lps = true, + .msi_support = false, + .disable_watchdog = false, + .debug = DBG_EMERG, }; static struct rtl_hal_cfg rtl8723be_hal_cfg = { diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c index 142bdff4ed60..4159f9b14db6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c @@ -95,8 +95,6 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); rtl8821ae_bt_reg_init(hw); - rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; - rtlpci->int_clear = rtlpriv->cfg->mod_params->int_clear; rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer(); rtlpriv->dm.dm_initialgain_enable = 1; @@ -168,12 +166,15 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; - rtlpci->msi_support = rtlpriv->cfg->mod_params->int_clear; + rtlpci->int_clear = rtlpriv->cfg->mod_params->int_clear; + rtlpriv->cfg->mod_params->sw_crypto = + rtlpriv->cfg->mod_params->sw_crypto; + rtlpriv->cfg->mod_params->disable_watchdog = + rtlpriv->cfg->mod_params->disable_watchdog; if (rtlpriv->cfg->mod_params->disable_watchdog) pr_info("watchdog disabled\n"); rtlpriv->psc.reg_fwctrl_lps = 3; rtlpriv->psc.reg_max_lps_awakeintvl = 5; - rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; /* for ASPM, you can close aspm through * set const_support_pciaspm = 0 diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index 2721cf89fb16..aac1ed3f7bb4 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -531,6 +531,8 @@ static void _rtl_usb_rx_process_noagg(struct ieee80211_hw *hw, ieee80211_rx(hw, skb); else dev_kfree_skb_any(skb); + } else { + dev_kfree_skb_any(skb); } } diff --git a/drivers/net/wireless/ti/wlcore/init.c b/drivers/net/wireless/ti/wlcore/init.c index e92f2639af2c..9fd3c6af0a61 100644 --- a/drivers/net/wireless/ti/wlcore/init.c +++ b/drivers/net/wireless/ti/wlcore/init.c @@ -549,6 +549,11 @@ static int wl12xx_init_ap_role(struct wl1271 *wl, struct wl12xx_vif *wlvif) { int ret; + /* Disable filtering */ + ret = wl1271_acx_group_address_tbl(wl, wlvif, false, NULL, 0); + if (ret < 0) + return ret; + ret = wl1271_acx_ap_max_tx_retry(wl, wlvif); if (ret < 0) return ret; diff --git a/drivers/net/wireless/ti/wlcore/io.h b/drivers/net/wireless/ti/wlcore/io.h index 0305729d0986..10cf3747694d 100644 --- a/drivers/net/wireless/ti/wlcore/io.h +++ b/drivers/net/wireless/ti/wlcore/io.h @@ -207,19 +207,23 @@ static inline int __must_check wlcore_write_reg(struct wl1271 *wl, int reg, static inline void wl1271_power_off(struct wl1271 *wl) { - int ret; + int ret = 0; if (!test_bit(WL1271_FLAG_GPIO_POWER, &wl->flags)) return; - ret = wl->if_ops->power(wl->dev, false); + if (wl->if_ops->power) + ret = wl->if_ops->power(wl->dev, false); if (!ret) clear_bit(WL1271_FLAG_GPIO_POWER, &wl->flags); } static inline int wl1271_power_on(struct wl1271 *wl) { - int ret = wl->if_ops->power(wl->dev, true); + int ret = 0; + + if (wl->if_ops->power) + ret = wl->if_ops->power(wl->dev, true); if (ret == 0) set_bit(WL1271_FLAG_GPIO_POWER, &wl->flags); diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c index 236b41090827..44f059f7f34e 100644 --- a/drivers/net/wireless/ti/wlcore/spi.c +++ b/drivers/net/wireless/ti/wlcore/spi.c @@ -73,7 +73,10 @@ */ #define SPI_AGGR_BUFFER_SIZE (4 * PAGE_SIZE) -#define WSPI_MAX_NUM_OF_CHUNKS (SPI_AGGR_BUFFER_SIZE / WSPI_MAX_CHUNK_SIZE) +/* Maximum number of SPI write chunks */ +#define WSPI_MAX_NUM_OF_CHUNKS \ + ((SPI_AGGR_BUFFER_SIZE / WSPI_MAX_CHUNK_SIZE) + 1) + struct wl12xx_spi_glue { struct device *dev; @@ -268,9 +271,10 @@ static int __must_check wl12xx_spi_raw_write(struct device *child, int addr, void *buf, size_t len, bool fixed) { struct wl12xx_spi_glue *glue = dev_get_drvdata(child->parent); - struct spi_transfer t[2 * (WSPI_MAX_NUM_OF_CHUNKS + 1)]; + /* SPI write buffers - 2 for each chunk */ + struct spi_transfer t[2 * WSPI_MAX_NUM_OF_CHUNKS]; struct spi_message m; - u32 commands[WSPI_MAX_NUM_OF_CHUNKS]; + u32 commands[WSPI_MAX_NUM_OF_CHUNKS]; /* 1 command per chunk */ u32 *cmd; u32 chunk_len; int i; diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 7e2c43f701bc..5f47356d6942 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -335,7 +335,7 @@ static const struct nd_cmd_desc __nd_cmd_dimm_descs[] = { [ND_CMD_IMPLEMENTED] = { }, [ND_CMD_SMART] = { .out_num = 2, - .out_sizes = { 4, 8, }, + .out_sizes = { 4, 128, }, }, [ND_CMD_SMART_THRESHOLD] = { .out_num = 2, @@ -513,10 +513,10 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, /* fail write commands (when read-only) */ if (read_only) - switch (ioctl_cmd) { - case ND_IOCTL_VENDOR: - case ND_IOCTL_SET_CONFIG_DATA: - case ND_IOCTL_ARS_START: + switch (cmd) { + case ND_CMD_VENDOR: + case ND_CMD_SET_CONFIG_DATA: + case ND_CMD_ARS_START: dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n", nvdimm ? nvdimm_cmd_name(cmd) : nvdimm_bus_cmd_name(cmd)); diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 0955b2cb10fe..62120c38d56b 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -77,6 +77,59 @@ static bool is_namespace_io(struct device *dev) return dev ? dev->type == &namespace_io_device_type : false; } +static int is_uuid_busy(struct device *dev, void *data) +{ + u8 *uuid1 = data, *uuid2 = NULL; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid2 = nspm->uuid; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + uuid2 = nsblk->uuid; + } else if (is_nd_btt(dev)) { + struct nd_btt *nd_btt = to_nd_btt(dev); + + uuid2 = nd_btt->uuid; + } else if (is_nd_pfn(dev)) { + struct nd_pfn *nd_pfn = to_nd_pfn(dev); + + uuid2 = nd_pfn->uuid; + } + + if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0) + return -EBUSY; + + return 0; +} + +static int is_namespace_uuid_busy(struct device *dev, void *data) +{ + if (is_nd_pmem(dev) || is_nd_blk(dev)) + return device_for_each_child(dev, data, is_uuid_busy); + return 0; +} + +/** + * nd_is_uuid_unique - verify that no other namespace has @uuid + * @dev: any device on a nvdimm_bus + * @uuid: uuid to check + */ +bool nd_is_uuid_unique(struct device *dev, u8 *uuid) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + if (!nvdimm_bus) + return false; + WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev)); + if (device_for_each_child(&nvdimm_bus->dev, uuid, + is_namespace_uuid_busy) != 0) + return false; + return true; +} + bool pmem_should_map_pages(struct device *dev) { struct nd_region *nd_region = to_nd_region(dev->parent); diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 71805a1aa0f3..9d3974591cd6 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -275,7 +275,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn) } else { /* from init we validate */ if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0) - return -EINVAL; + return -ENODEV; } /* diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 529f3f02e7b2..9521696c9385 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -134,62 +134,6 @@ int nd_region_to_nstype(struct nd_region *nd_region) } EXPORT_SYMBOL(nd_region_to_nstype); -static int is_uuid_busy(struct device *dev, void *data) -{ - struct nd_region *nd_region = to_nd_region(dev->parent); - u8 *uuid = data; - - switch (nd_region_to_nstype(nd_region)) { - case ND_DEVICE_NAMESPACE_PMEM: { - struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); - - if (!nspm->uuid) - break; - if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0) - return -EBUSY; - break; - } - case ND_DEVICE_NAMESPACE_BLK: { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - if (!nsblk->uuid) - break; - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) == 0) - return -EBUSY; - break; - } - default: - break; - } - - return 0; -} - -static int is_namespace_uuid_busy(struct device *dev, void *data) -{ - if (is_nd_pmem(dev) || is_nd_blk(dev)) - return device_for_each_child(dev, data, is_uuid_busy); - return 0; -} - -/** - * nd_is_uuid_unique - verify that no other namespace has @uuid - * @dev: any device on a nvdimm_bus - * @uuid: uuid to check - */ -bool nd_is_uuid_unique(struct device *dev, u8 *uuid) -{ - struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - - if (!nvdimm_bus) - return false; - WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev)); - if (device_for_each_child(&nvdimm_bus->dev, uuid, - is_namespace_uuid_busy) != 0) - return false; - return true; -} - static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/drivers/nvmem/mxs-ocotp.c b/drivers/nvmem/mxs-ocotp.c index 8ba19bba3156..2bb3c5799ac4 100644 --- a/drivers/nvmem/mxs-ocotp.c +++ b/drivers/nvmem/mxs-ocotp.c @@ -94,7 +94,7 @@ static int mxs_ocotp_read(void *context, const void *reg, size_t reg_size, if (ret) goto close_banks; - while (val_size) { + while (val_size >= reg_size) { if ((offset < OCOTP_DATA_OFFSET) || (offset % 16)) { /* fill up non-data register */ *buf = 0; @@ -103,7 +103,7 @@ static int mxs_ocotp_read(void *context, const void *reg, size_t reg_size, } buf++; - val_size--; + val_size -= reg_size; offset += reg_size; } diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 4fa916dffc91..72a2c1969646 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -636,6 +636,13 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np, msi_base = be32_to_cpup(msi_map + 2); rid_len = be32_to_cpup(msi_map + 3); + if (rid_base & ~map_mask) { + dev_err(parent_dev, + "Invalid msi-map translation - msi-map-mask (0x%x) ignores rid-base (0x%x)\n", + map_mask, rid_base); + return rid_out; + } + msi_controller_node = of_find_node_by_phandle(phandle); matched = (masked_rid >= rid_base && @@ -655,7 +662,7 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np, if (!matched) return rid_out; - rid_out = masked_rid + msi_base; + rid_out = masked_rid - rid_base + msi_base; dev_dbg(dev, "msi-map at: %s, using mask %08x, rid-base: %08x, msi-base: %08x, length: %08x, rid: %08x -> %08x\n", dev_name(parent_dev), map_mask, rid_base, msi_base, diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 1a3556a9e9ea..ed01c0172e4a 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -32,11 +32,13 @@ int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap, phys_addr_t *res_base) { + phys_addr_t base; /* * We use __memblock_alloc_base() because memblock_alloc_base() * panic()s on allocation failure. */ - phys_addr_t base = __memblock_alloc_base(size, align, end); + end = !end ? MEMBLOCK_ALLOC_ANYWHERE : end; + base = __memblock_alloc_base(size, align, end); if (!base) return -ENOMEM; diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index d3346d23963b..89b3befc7155 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -140,6 +140,8 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res, type_mask |= IORESOURCE_TYPE_BITS; pci_bus_for_each_resource(bus, r, i) { + resource_size_t min_used = min; + if (!r) continue; @@ -163,12 +165,12 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res, * overrides "min". */ if (avail.start) - min = avail.start; + min_used = avail.start; max = avail.end; /* Ok, try it out.. */ - ret = allocate_resource(r, res, size, min, max, + ret = allocate_resource(r, res, size, min_used, max, align, alignf, alignf_data); if (ret == 0) return 0; diff --git a/drivers/pci/host/pci-dra7xx.c b/drivers/pci/host/pci-dra7xx.c index 8c3688046c02..923607bdabc5 100644 --- a/drivers/pci/host/pci-dra7xx.c +++ b/drivers/pci/host/pci-dra7xx.c @@ -302,7 +302,8 @@ static int __init dra7xx_add_pcie_port(struct dra7xx_pcie *dra7xx, } ret = devm_request_irq(&pdev->dev, pp->irq, - dra7xx_pcie_msi_irq_handler, IRQF_SHARED, + dra7xx_pcie_msi_irq_handler, + IRQF_SHARED | IRQF_NO_THREAD, "dra7-pcie-msi", pp); if (ret) { dev_err(&pdev->dev, "failed to request irq\n"); diff --git a/drivers/pci/host/pci-exynos.c b/drivers/pci/host/pci-exynos.c index 01095e1160a4..d997d22d4231 100644 --- a/drivers/pci/host/pci-exynos.c +++ b/drivers/pci/host/pci-exynos.c @@ -522,7 +522,8 @@ static int __init exynos_add_pcie_port(struct pcie_port *pp, ret = devm_request_irq(&pdev->dev, pp->msi_irq, exynos_pcie_msi_irq_handler, - IRQF_SHARED, "exynos-pcie", pp); + IRQF_SHARED | IRQF_NO_THREAD, + "exynos-pcie", pp); if (ret) { dev_err(&pdev->dev, "failed to request msi irq\n"); return ret; diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c index 22e8224126fd..9ce7cd148c86 100644 --- a/drivers/pci/host/pci-imx6.c +++ b/drivers/pci/host/pci-imx6.c @@ -537,7 +537,8 @@ static int __init imx6_add_pcie_port(struct pcie_port *pp, ret = devm_request_irq(&pdev->dev, pp->msi_irq, imx6_pcie_msi_handler, - IRQF_SHARED, "mx6-pcie-msi", pp); + IRQF_SHARED | IRQF_NO_THREAD, + "mx6-pcie-msi", pp); if (ret) { dev_err(&pdev->dev, "failed to request MSI irq\n"); return ret; diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c index ed34c9520a02..6153853ca9c3 100644 --- a/drivers/pci/host/pci-keystone-dw.c +++ b/drivers/pci/host/pci-keystone-dw.c @@ -58,11 +58,6 @@ #define to_keystone_pcie(x) container_of(x, struct keystone_pcie, pp) -static inline struct pcie_port *sys_to_pcie(struct pci_sys_data *sys) -{ - return sys->private_data; -} - static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset, u32 *bit_pos) { @@ -108,7 +103,7 @@ static void ks_dw_pcie_msi_irq_ack(struct irq_data *d) struct pcie_port *pp; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); update_reg_offset_bit_pos(offset, ®_offset, &bit_pos); @@ -146,7 +141,7 @@ static void ks_dw_pcie_msi_irq_mask(struct irq_data *d) u32 offset; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); @@ -167,7 +162,7 @@ static void ks_dw_pcie_msi_irq_unmask(struct irq_data *d) u32 offset; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c index 3018ae52e092..30323114c53c 100644 --- a/drivers/pci/host/pci-tegra.c +++ b/drivers/pci/host/pci-tegra.c @@ -1288,7 +1288,7 @@ static int tegra_pcie_enable_msi(struct tegra_pcie *pcie) msi->irq = err; - err = request_irq(msi->irq, tegra_pcie_msi_irq, 0, + err = request_irq(msi->irq, tegra_pcie_msi_irq, IRQF_NO_THREAD, tegra_msi_irq_chip.name, pcie); if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ: %d\n", err); diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c index f4fa6c537448..414c33686621 100644 --- a/drivers/pci/host/pcie-rcar.c +++ b/drivers/pci/host/pcie-rcar.c @@ -720,14 +720,16 @@ static int rcar_pcie_enable_msi(struct rcar_pcie *pcie) /* Two irqs are for MSI, but they are also used for non-MSI irqs */ err = devm_request_irq(&pdev->dev, msi->irq1, rcar_pcie_msi_irq, - IRQF_SHARED, rcar_msi_irq_chip.name, pcie); + IRQF_SHARED | IRQF_NO_THREAD, + rcar_msi_irq_chip.name, pcie); if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ: %d\n", err); goto err; } err = devm_request_irq(&pdev->dev, msi->irq2, rcar_pcie_msi_irq, - IRQF_SHARED, rcar_msi_irq_chip.name, pcie); + IRQF_SHARED | IRQF_NO_THREAD, + rcar_msi_irq_chip.name, pcie); if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ: %d\n", err); goto err; diff --git a/drivers/pci/host/pcie-spear13xx.c b/drivers/pci/host/pcie-spear13xx.c index b95b7563c052..a6cd8233e8c0 100644 --- a/drivers/pci/host/pcie-spear13xx.c +++ b/drivers/pci/host/pcie-spear13xx.c @@ -279,7 +279,8 @@ static int spear13xx_add_pcie_port(struct pcie_port *pp, return -ENODEV; } ret = devm_request_irq(dev, pp->irq, spear13xx_pcie_irq_handler, - IRQF_SHARED, "spear1340-pcie", pp); + IRQF_SHARED | IRQF_NO_THREAD, + "spear1340-pcie", pp); if (ret) { dev_err(dev, "failed to request irq %d\n", pp->irq); return ret; diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c index 3c7a0d580b1e..4cfa46360d12 100644 --- a/drivers/pci/host/pcie-xilinx.c +++ b/drivers/pci/host/pcie-xilinx.c @@ -781,7 +781,8 @@ static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port) port->irq = irq_of_parse_and_map(node, 0); err = devm_request_irq(dev, port->irq, xilinx_pcie_intr_handler, - IRQF_SHARED, "xilinx-pcie", port); + IRQF_SHARED | IRQF_NO_THREAD, + "xilinx-pcie", port); if (err) { dev_err(dev, "unable to request irq %d\n", port->irq); return err; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index ff538568a617..0b3e0bfa7be5 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -953,8 +953,10 @@ int acpiphp_enable_slot(struct acpiphp_slot *slot) { pci_lock_rescan_remove(); - if (slot->flags & SLOT_IS_GOING_AWAY) + if (slot->flags & SLOT_IS_GOING_AWAY) { + pci_unlock_rescan_remove(); return -ENODEV; + } /* configure all functions */ if (!(slot->flags & SLOT_ENABLED)) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 314db8c1047a..42d8617352ae 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4772,8 +4772,10 @@ int pci_get_new_domain_nr(void) void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent) { static int use_dt_domains = -1; - int domain = of_get_pci_domain_nr(parent->of_node); + int domain = -1; + if (parent) + domain = of_get_pci_domain_nr(parent->of_node); /* * Check DT domain and use_dt_domains values. * diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 0bf82a20a0fb..48d21e0edd56 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -262,7 +262,6 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev) rpc->rpd = dev; INIT_WORK(&rpc->dpc_handler, aer_isr); mutex_init(&rpc->rpc_mutex); - init_waitqueue_head(&rpc->wait_release); /* Use PCIe bus function to store rpc into PCIe device */ set_service_data(dev, rpc); @@ -285,8 +284,7 @@ static void aer_remove(struct pcie_device *dev) if (rpc->isr) free_irq(dev->irq, dev); - wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx); - + flush_work(&rpc->dpc_handler); aer_disable_rootport(rpc); kfree(rpc); set_service_data(dev, NULL); diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h index 84420b7c9456..945c939a86c5 100644 --- a/drivers/pci/pcie/aer/aerdrv.h +++ b/drivers/pci/pcie/aer/aerdrv.h @@ -72,7 +72,6 @@ struct aer_rpc { * recovery on the same * root port hierarchy */ - wait_queue_head_t wait_release; }; struct aer_broadcast_data { diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index fba785e9df75..4e14de0f0f98 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -811,8 +811,6 @@ void aer_isr(struct work_struct *work) while (get_e_source(rpc, &e_src)) aer_isr_one_error(p_device, &e_src); mutex_unlock(&rpc->rpc_mutex); - - wake_up(&rpc->wait_release); } /** diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index edb1984201e9..7aafb5fb9336 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -179,6 +179,9 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, u16 orig_cmd; struct pci_bus_region region, inverted_region; + if (dev->non_compliant_bars) + return 0; + mask = type ? PCI_ROM_ADDRESS_MASK : ~0; /* No printks while decoding is disabled! */ @@ -1174,6 +1177,7 @@ void pci_msi_setup_pci_dev(struct pci_dev *dev) int pci_setup_device(struct pci_dev *dev) { u32 class; + u16 cmd; u8 hdr_type; int pos = 0; struct pci_bus_region region; @@ -1219,6 +1223,16 @@ int pci_setup_device(struct pci_dev *dev) /* device class may be changed after fixup */ class = dev->class >> 8; + if (dev->non_compliant_bars) { + pci_read_config_word(dev, PCI_COMMAND, &cmd); + if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) { + dev_info(&dev->dev, "device has non-compliant BARs; disabling IO/MEM decoding\n"); + cmd &= ~PCI_COMMAND_IO; + cmd &= ~PCI_COMMAND_MEMORY; + pci_write_config_word(dev, PCI_COMMAND, cmd); + } + } + switch (dev->hdr_type) { /* header type */ case PCI_HEADER_TYPE_NORMAL: /* standard header */ if (class == PCI_CLASS_BRIDGE_PCI) diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index c777b97207d5..5f70fee59a94 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -53,7 +53,7 @@ struct pcifront_device { }; struct pcifront_sd { - int domain; + struct pci_sysdata sd; struct pcifront_device *pdev; }; @@ -67,7 +67,9 @@ static inline void pcifront_init_sd(struct pcifront_sd *sd, unsigned int domain, unsigned int bus, struct pcifront_device *pdev) { - sd->domain = domain; + /* Because we do not expose that information via XenBus. */ + sd->sd.node = first_online_node; + sd->sd.domain = domain; sd->pdev = pdev; } @@ -468,8 +470,8 @@ static int pcifront_scan_root(struct pcifront_device *pdev, dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n", domain, bus); - bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL); - sd = kmalloc(sizeof(*sd), GFP_KERNEL); + bus_entry = kzalloc(sizeof(*bus_entry), GFP_KERNEL); + sd = kzalloc(sizeof(*sd), GFP_KERNEL); if (!bus_entry || !sd) { err = -ENOMEM; goto err_out; diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c index 4c2fa05b4589..944674ee3464 100644 --- a/drivers/pcmcia/db1xxx_ss.c +++ b/drivers/pcmcia/db1xxx_ss.c @@ -56,6 +56,7 @@ struct db1x_pcmcia_sock { int stschg_irq; /* card-status-change irq */ int card_irq; /* card irq */ int eject_irq; /* db1200/pb1200 have these */ + int insert_gpio; /* db1000 carddetect gpio */ #define BOARD_TYPE_DEFAULT 0 /* most boards */ #define BOARD_TYPE_DB1200 1 /* IRQs aren't gpios */ @@ -83,7 +84,7 @@ static int db1200_card_inserted(struct db1x_pcmcia_sock *sock) /* carddetect gpio: low-active */ static int db1000_card_inserted(struct db1x_pcmcia_sock *sock) { - return !gpio_get_value(irq_to_gpio(sock->insert_irq)); + return !gpio_get_value(sock->insert_gpio); } static int db1x_card_inserted(struct db1x_pcmcia_sock *sock) @@ -457,9 +458,15 @@ static int db1x_pcmcia_socket_probe(struct platform_device *pdev) r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "card"); sock->card_irq = r ? r->start : 0; - /* insert: irq which triggers on card insertion/ejection */ + /* insert: irq which triggers on card insertion/ejection + * BIG FAT NOTE: on DB1000/1100/1500/1550 we pass a GPIO here! + */ r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "insert"); sock->insert_irq = r ? r->start : -1; + if (sock->board_type == BOARD_TYPE_DEFAULT) { + sock->insert_gpio = r ? r->start : -1; + sock->insert_irq = r ? gpio_to_irq(r->start) : -1; + } /* stschg: irq which trigger on card status change (optional) */ r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "stschg"); diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 8c7f27db6ad3..e7e574dc667a 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -275,20 +275,21 @@ EXPORT_SYMBOL_GPL(phy_exit); int phy_power_on(struct phy *phy) { - int ret; + int ret = 0; if (!phy) - return 0; + goto out; if (phy->pwr) { ret = regulator_enable(phy->pwr); if (ret) - return ret; + goto out; } ret = phy_pm_runtime_get_sync(phy); if (ret < 0 && ret != -ENOTSUPP) - return ret; + goto err_pm_sync; + ret = 0; /* Override possible ret == -ENOTSUPP */ mutex_lock(&phy->mutex); @@ -296,19 +297,20 @@ int phy_power_on(struct phy *phy) ret = phy->ops->power_on(phy); if (ret < 0) { dev_err(&phy->dev, "phy poweron failed --> %d\n", ret); - goto out; + goto err_pwr_on; } } ++phy->power_count; mutex_unlock(&phy->mutex); return 0; -out: +err_pwr_on: mutex_unlock(&phy->mutex); phy_pm_runtime_put_sync(phy); +err_pm_sync: if (phy->pwr) regulator_disable(phy->pwr); - +out: return ret; } EXPORT_SYMBOL_GPL(phy_power_on); diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 3a707dd14238..f96065a81d1e 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -715,6 +715,7 @@ static int twl4030_usb_probe(struct platform_device *pdev) pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_set_autosuspend_delay(&pdev->dev, 2000); pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); /* Our job is to use irqs and status from the power module * to keep the transceiver disabled when nothing's connected. @@ -750,6 +751,7 @@ static int twl4030_usb_remove(struct platform_device *pdev) struct twl4030_usb *twl = platform_get_drvdata(pdev); int val; + usb_remove_phy(&twl->phy); pm_runtime_get_sync(twl->dev); cancel_delayed_work(&twl->id_workaround_work); device_remove_file(twl->dev, &dev_attr_vbus); @@ -757,6 +759,13 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* set transceiver mode to power on defaults */ twl4030_usb_set_mode(twl, -1); + /* idle ulpi before powering off */ + if (cable_present(twl->linkstat)) + pm_runtime_put_noidle(twl->dev); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_sync_suspend(twl->dev); + pm_runtime_disable(twl->dev); + /* autogate 60MHz ULPI clock, * clear dpll clock request for i2c access, * disable 32KHz @@ -771,11 +780,6 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); - if (cable_present(twl->linkstat)) - pm_runtime_put_noidle(twl->dev); - pm_runtime_mark_last_busy(twl->dev); - pm_runtime_put(twl->dev); - return 0; } diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index 2e6ca69635aa..17dd8fe12b54 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -779,7 +779,7 @@ static int bcm2835_pctl_dt_node_to_map(struct pinctrl_dev *pctldev, } if (num_pulls) { err = of_property_read_u32_index(np, "brcm,pull", - (num_funcs > 1) ? i : 0, &pull); + (num_pulls > 1) ? i : 0, &pull); if (err) goto out; err = bcm2835_pctl_dt_node_to_map_pull(pc, np, pin, diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c index a5bb93987378..1029aa7889b5 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx.c +++ b/drivers/pinctrl/freescale/pinctrl-imx.c @@ -726,19 +726,18 @@ int imx_pinctrl_probe(struct platform_device *pdev, if (of_property_read_bool(dev_np, "fsl,input-sel")) { np = of_parse_phandle(dev_np, "fsl,input-sel", 0); - if (np) { - ipctl->input_sel_base = of_iomap(np, 0); - if (IS_ERR(ipctl->input_sel_base)) { - of_node_put(np); - dev_err(&pdev->dev, - "iomuxc input select base address not found\n"); - return PTR_ERR(ipctl->input_sel_base); - } - } else { + if (!np) { dev_err(&pdev->dev, "iomuxc fsl,input-sel property not found\n"); return -EINVAL; } + + ipctl->input_sel_base = of_iomap(np, 0); of_node_put(np); + if (!ipctl->input_sel_base) { + dev_err(&pdev->dev, + "iomuxc input select base address not found\n"); + return -ENOMEM; + } } imx_pinctrl_desc.name = dev_name(&pdev->dev); diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c index 5c717275a7fa..3d8019eb3d84 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c @@ -939,7 +939,8 @@ static int mtk_gpio_set_debounce(struct gpio_chip *chip, unsigned offset, struct mtk_pinctrl *pctl = dev_get_drvdata(chip->dev); int eint_num, virq, eint_offset; unsigned int set_offset, bit, clr_bit, clr_offset, rst, i, unmask, dbnc; - static const unsigned int dbnc_arr[] = {0 , 1, 16, 32, 64, 128, 256}; + static const unsigned int debounce_time[] = {500, 1000, 16000, 32000, 64000, + 128000, 256000}; const struct mtk_desc_pin *pin; struct irq_data *d; @@ -957,9 +958,9 @@ static int mtk_gpio_set_debounce(struct gpio_chip *chip, unsigned offset, if (!mtk_eint_can_en_debounce(pctl, eint_num)) return -ENOSYS; - dbnc = ARRAY_SIZE(dbnc_arr); - for (i = 0; i < ARRAY_SIZE(dbnc_arr); i++) { - if (debounce <= dbnc_arr[i]) { + dbnc = ARRAY_SIZE(debounce_time); + for (i = 0; i < ARRAY_SIZE(debounce_time); i++) { + if (debounce <= debounce_time[i]) { dbnc = i; break; } diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c index eebfae0c9b7c..f844b4ae7f79 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c @@ -995,7 +995,7 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s, int val; if (pull) - pullidx = data_out ? 1 : 2; + pullidx = data_out ? 2 : 1; seq_printf(s, " gpio-%-3d (%-20.20s) in %s %s", gpio, diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index 85c9046c690e..6b1a47f8c096 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -469,27 +469,27 @@ static const char * const pistachio_mips_pll_lock_groups[] = { "mfio83", }; -static const char * const pistachio_sys_pll_lock_groups[] = { +static const char * const pistachio_audio_pll_lock_groups[] = { "mfio84", }; -static const char * const pistachio_wifi_pll_lock_groups[] = { +static const char * const pistachio_rpu_v_pll_lock_groups[] = { "mfio85", }; -static const char * const pistachio_bt_pll_lock_groups[] = { +static const char * const pistachio_rpu_l_pll_lock_groups[] = { "mfio86", }; -static const char * const pistachio_rpu_v_pll_lock_groups[] = { +static const char * const pistachio_sys_pll_lock_groups[] = { "mfio87", }; -static const char * const pistachio_rpu_l_pll_lock_groups[] = { +static const char * const pistachio_wifi_pll_lock_groups[] = { "mfio88", }; -static const char * const pistachio_audio_pll_lock_groups[] = { +static const char * const pistachio_bt_pll_lock_groups[] = { "mfio89", }; @@ -559,12 +559,12 @@ enum pistachio_mux_option { PISTACHIO_FUNCTION_DREQ4, PISTACHIO_FUNCTION_DREQ5, PISTACHIO_FUNCTION_MIPS_PLL_LOCK, + PISTACHIO_FUNCTION_AUDIO_PLL_LOCK, + PISTACHIO_FUNCTION_RPU_V_PLL_LOCK, + PISTACHIO_FUNCTION_RPU_L_PLL_LOCK, PISTACHIO_FUNCTION_SYS_PLL_LOCK, PISTACHIO_FUNCTION_WIFI_PLL_LOCK, PISTACHIO_FUNCTION_BT_PLL_LOCK, - PISTACHIO_FUNCTION_RPU_V_PLL_LOCK, - PISTACHIO_FUNCTION_RPU_L_PLL_LOCK, - PISTACHIO_FUNCTION_AUDIO_PLL_LOCK, PISTACHIO_FUNCTION_DEBUG_RAW_CCA_IND, PISTACHIO_FUNCTION_DEBUG_ED_SEC20_CCA_IND, PISTACHIO_FUNCTION_DEBUG_ED_SEC40_CCA_IND, @@ -620,12 +620,12 @@ static const struct pistachio_function pistachio_functions[] = { FUNCTION(dreq4), FUNCTION(dreq5), FUNCTION(mips_pll_lock), + FUNCTION(audio_pll_lock), + FUNCTION(rpu_v_pll_lock), + FUNCTION(rpu_l_pll_lock), FUNCTION(sys_pll_lock), FUNCTION(wifi_pll_lock), FUNCTION(bt_pll_lock), - FUNCTION(rpu_v_pll_lock), - FUNCTION(rpu_l_pll_lock), - FUNCTION(audio_pll_lock), FUNCTION(debug_raw_cca_ind), FUNCTION(debug_ed_sec20_cca_ind), FUNCTION(debug_ed_sec40_cca_ind), diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index ef04b962c3d5..23b6b8c29a99 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -1273,9 +1273,9 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs, /* Parse pins in each row from LSB */ while (mask) { - bit_pos = ffs(mask); + bit_pos = __ffs(mask); pin_num_from_lsb = bit_pos / pcs->bits_per_pin; - mask_pos = ((pcs->fmask) << (bit_pos - 1)); + mask_pos = ((pcs->fmask) << bit_pos); val_pos = val & mask_pos; submask = mask & mask_pos; @@ -1847,7 +1847,7 @@ static int pcs_probe(struct platform_device *pdev) ret = of_property_read_u32(np, "pinctrl-single,function-mask", &pcs->fmask); if (!ret) { - pcs->fshift = ffs(pcs->fmask) - 1; + pcs->fshift = __ffs(pcs->fmask); pcs->fmax = pcs->fmask >> pcs->fshift; } else { /* If mask property doesn't exist, function mux is invalid. */ diff --git a/drivers/pinctrl/sh-pfc/core.c b/drivers/pinctrl/sh-pfc/core.c index 181ea98a63b7..2b0d70217bbd 100644 --- a/drivers/pinctrl/sh-pfc/core.c +++ b/drivers/pinctrl/sh-pfc/core.c @@ -545,7 +545,9 @@ static int sh_pfc_probe(struct platform_device *pdev) return ret; } - pinctrl_provide_dummies(); + /* Enable dummy states for those platforms without pinctrl support */ + if (!of_have_populated_dt()) + pinctrl_provide_dummies(); ret = sh_pfc_init_ranges(pfc); if (ret < 0) diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a33.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a33.c index 00265f0435a7..8b381d69df86 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a33.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a33.c @@ -485,6 +485,7 @@ static const struct sunxi_pinctrl_desc sun8i_a33_pinctrl_data = { .pins = sun8i_a33_pins, .npins = ARRAY_SIZE(sun8i_a33_pins), .irq_banks = 2, + .irq_bank_base = 1, }; static int sun8i_a33_pinctrl_probe(struct platform_device *pdev) diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index dead97daca35..a4a5b504c532 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -578,7 +578,7 @@ static void sunxi_pinctrl_irq_release_resources(struct irq_data *d) static int sunxi_pinctrl_irq_set_type(struct irq_data *d, unsigned int type) { struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d); - u32 reg = sunxi_irq_cfg_reg(d->hwirq); + u32 reg = sunxi_irq_cfg_reg(d->hwirq, pctl->desc->irq_bank_base); u8 index = sunxi_irq_cfg_offset(d->hwirq); unsigned long flags; u32 regval; @@ -625,7 +625,8 @@ static int sunxi_pinctrl_irq_set_type(struct irq_data *d, unsigned int type) static void sunxi_pinctrl_irq_ack(struct irq_data *d) { struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d); - u32 status_reg = sunxi_irq_status_reg(d->hwirq); + u32 status_reg = sunxi_irq_status_reg(d->hwirq, + pctl->desc->irq_bank_base); u8 status_idx = sunxi_irq_status_offset(d->hwirq); /* Clear the IRQ */ @@ -635,7 +636,7 @@ static void sunxi_pinctrl_irq_ack(struct irq_data *d) static void sunxi_pinctrl_irq_mask(struct irq_data *d) { struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d); - u32 reg = sunxi_irq_ctrl_reg(d->hwirq); + u32 reg = sunxi_irq_ctrl_reg(d->hwirq, pctl->desc->irq_bank_base); u8 idx = sunxi_irq_ctrl_offset(d->hwirq); unsigned long flags; u32 val; @@ -652,7 +653,7 @@ static void sunxi_pinctrl_irq_mask(struct irq_data *d) static void sunxi_pinctrl_irq_unmask(struct irq_data *d) { struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d); - u32 reg = sunxi_irq_ctrl_reg(d->hwirq); + u32 reg = sunxi_irq_ctrl_reg(d->hwirq, pctl->desc->irq_bank_base); u8 idx = sunxi_irq_ctrl_offset(d->hwirq); unsigned long flags; u32 val; @@ -744,7 +745,7 @@ static void sunxi_pinctrl_irq_handler(struct irq_desc *desc) if (bank == pctl->desc->irq_banks) return; - reg = sunxi_irq_status_reg_from_bank(bank); + reg = sunxi_irq_status_reg_from_bank(bank, pctl->desc->irq_bank_base); val = readl(pctl->membase + reg); if (val) { @@ -1023,9 +1024,11 @@ int sunxi_pinctrl_init(struct platform_device *pdev, for (i = 0; i < pctl->desc->irq_banks; i++) { /* Mask and clear all IRQs before registering a handler */ - writel(0, pctl->membase + sunxi_irq_ctrl_reg_from_bank(i)); + writel(0, pctl->membase + sunxi_irq_ctrl_reg_from_bank(i, + pctl->desc->irq_bank_base)); writel(0xffffffff, - pctl->membase + sunxi_irq_status_reg_from_bank(i)); + pctl->membase + sunxi_irq_status_reg_from_bank(i, + pctl->desc->irq_bank_base)); irq_set_chained_handler_and_data(pctl->irq[i], sunxi_pinctrl_irq_handler, diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h index e248e81a0f9e..0afce1ab12d0 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h @@ -97,6 +97,7 @@ struct sunxi_pinctrl_desc { int npins; unsigned pin_base; unsigned irq_banks; + unsigned irq_bank_base; bool irq_read_needs_mux; }; @@ -233,12 +234,12 @@ static inline u32 sunxi_pull_offset(u16 pin) return pin_num * PULL_PINS_BITS; } -static inline u32 sunxi_irq_cfg_reg(u16 irq) +static inline u32 sunxi_irq_cfg_reg(u16 irq, unsigned bank_base) { u8 bank = irq / IRQ_PER_BANK; u8 reg = (irq % IRQ_PER_BANK) / IRQ_CFG_IRQ_PER_REG * 0x04; - return IRQ_CFG_REG + bank * IRQ_MEM_SIZE + reg; + return IRQ_CFG_REG + (bank_base + bank) * IRQ_MEM_SIZE + reg; } static inline u32 sunxi_irq_cfg_offset(u16 irq) @@ -247,16 +248,16 @@ static inline u32 sunxi_irq_cfg_offset(u16 irq) return irq_num * IRQ_CFG_IRQ_BITS; } -static inline u32 sunxi_irq_ctrl_reg_from_bank(u8 bank) +static inline u32 sunxi_irq_ctrl_reg_from_bank(u8 bank, unsigned bank_base) { - return IRQ_CTRL_REG + bank * IRQ_MEM_SIZE; + return IRQ_CTRL_REG + (bank_base + bank) * IRQ_MEM_SIZE; } -static inline u32 sunxi_irq_ctrl_reg(u16 irq) +static inline u32 sunxi_irq_ctrl_reg(u16 irq, unsigned bank_base) { u8 bank = irq / IRQ_PER_BANK; - return sunxi_irq_ctrl_reg_from_bank(bank); + return sunxi_irq_ctrl_reg_from_bank(bank, bank_base); } static inline u32 sunxi_irq_ctrl_offset(u16 irq) @@ -265,16 +266,16 @@ static inline u32 sunxi_irq_ctrl_offset(u16 irq) return irq_num * IRQ_CTRL_IRQ_BITS; } -static inline u32 sunxi_irq_status_reg_from_bank(u8 bank) +static inline u32 sunxi_irq_status_reg_from_bank(u8 bank, unsigned bank_base) { - return IRQ_STATUS_REG + bank * IRQ_MEM_SIZE; + return IRQ_STATUS_REG + (bank_base + bank) * IRQ_MEM_SIZE; } -static inline u32 sunxi_irq_status_reg(u16 irq) +static inline u32 sunxi_irq_status_reg(u16 irq, unsigned bank_base) { u8 bank = irq / IRQ_PER_BANK; - return sunxi_irq_status_reg_from_bank(bank); + return sunxi_irq_status_reg_from_bank(bank, bank_base); } static inline u32 sunxi_irq_status_offset(u16 irq) diff --git a/drivers/platform/Kconfig b/drivers/platform/Kconfig index 5bd93a25d2ce..4f2d93fa6502 100644 --- a/drivers/platform/Kconfig +++ b/drivers/platform/Kconfig @@ -7,3 +7,5 @@ endif source "drivers/platform/goldfish/Kconfig" source "drivers/platform/chrome/Kconfig" + +source "drivers/platform/hisi/Kconfig" diff --git a/drivers/platform/Makefile b/drivers/platform/Makefile index ca2692510733..57bc1d19ab52 100644 --- a/drivers/platform/Makefile +++ b/drivers/platform/Makefile @@ -7,3 +7,4 @@ obj-$(CONFIG_MIPS) += mips/ obj-$(CONFIG_OLPC) += olpc/ obj-$(CONFIG_GOLDFISH) += goldfish/ obj-$(CONFIG_CHROME_PLATFORMS) += chrome/ +obj-$(CONFIG_ARCH_HISI) += hisi/ diff --git a/drivers/platform/hisi/Kconfig b/drivers/platform/hisi/Kconfig new file mode 100644 index 000000000000..776cfe0cc2af --- /dev/null +++ b/drivers/platform/hisi/Kconfig @@ -0,0 +1,6 @@ +config HISI_FIQ_DEBUGGER + bool "Enable the FIQ serial debugger on Hisi" + default n + select FIQ_DEBUGGER + help + Enables the FIQ serial debugger on Hisi diff --git a/drivers/platform/hisi/Makefile b/drivers/platform/hisi/Makefile new file mode 100644 index 000000000000..483c227b18bc --- /dev/null +++ b/drivers/platform/hisi/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_HISI_FIQ_DEBUGGER) += hi6220_fiq_debugger.o + diff --git a/drivers/platform/hisi/hi6220_fiq_debugger.c b/drivers/platform/hisi/hi6220_fiq_debugger.c new file mode 100644 index 000000000000..12bb5ece4156 --- /dev/null +++ b/drivers/platform/hisi/hi6220_fiq_debugger.c @@ -0,0 +1,260 @@ +/* + * platform/hisilicon/hi6220_fiq_debugger.c + * + * Serial Debugger Interface for Hi6220 + * + * Copyright (C) 2016 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdarg.h> +#include <linux/module.h> +#include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/clk.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/irq.h> +#include <linux/slab.h> +#include <linux/stacktrace.h> +#include <linux/uaccess.h> +#include <linux/amba/serial.h> + +#include "../../staging/android/fiq_debugger/fiq_debugger.h" + +struct hi6220_fiq_debugger { + struct fiq_debugger_pdata pdata; + void __iomem *debug_port_base; +}; + +static inline void uart_write(struct hi6220_fiq_debugger *t, + unsigned int val, unsigned int off) +{ + __raw_writew(val, t->debug_port_base + off); +} + +static inline unsigned int uart_read(struct hi6220_fiq_debugger *t, + unsigned int off) +{ + return __raw_readw(t->debug_port_base + off); +} + +static int debug_port_init(struct platform_device *pdev) +{ + struct hi6220_fiq_debugger *t = + container_of(dev_get_platdata(&pdev->dev), typeof(*t), pdata); + + uart_write(t, UART011_OEIS | UART011_BEIS | UART011_PEIS | + UART011_FEIS | UART011_RTIS | UART011_RXIS, UART011_ICR); + uart_write(t, UART011_RTIM | UART011_RXIM, UART011_IMSC); + + /* uart_write(t, 0x1b, UART011_FBRD); */ + + return 0; +} + +static int debug_getc(struct platform_device *pdev) +{ + int ch; + struct hi6220_fiq_debugger *t = + container_of(dev_get_platdata(&pdev->dev), typeof(*t), pdata); + + if (uart_read(t, UART01x_FR) & UART01x_FR_RXFE) + return FIQ_DEBUGGER_NO_CHAR; + ch = uart_read(t, UART01x_DR); + if (ch & UART011_DR_BE) + return FIQ_DEBUGGER_BREAK; + return ch & 0x00FF; +} + +static void debug_putc(struct platform_device *pdev, unsigned int c) +{ + struct hi6220_fiq_debugger *t = + container_of(dev_get_platdata(&pdev->dev), typeof(*t), pdata); + + while (uart_read(t, UART01x_FR) & UART01x_FR_TXFF) + cpu_relax(); + uart_write(t, c, UART01x_DR); + while (uart_read(t, UART01x_FR) & UART01x_FR_BUSY) + cpu_relax(); +} + +static void debug_flush(struct platform_device *pdev) +{ + struct hi6220_fiq_debugger *t = + container_of(dev_get_platdata(&pdev->dev), typeof(*t), pdata); + + while (uart_read(t, UART01x_FR) & UART01x_FR_BUSY) + cpu_relax(); +} + +static int debug_suspend(struct platform_device *pdev) +{ + return 0; +} + +static int debug_resume(struct platform_device *pdev) +{ + return debug_port_init(pdev); +} + +static int hi6220_fiq_debugger_id; + +static int __hi6220_serial_debug_init(unsigned int base, int fiq, int irq, + struct clk *clk, int signal_irq, int wakeup_irq) +{ + struct hi6220_fiq_debugger *t; + struct platform_device *pdev; + struct resource *res; + int res_count = 1; + int ret = -ENOMEM; + + t = kzalloc(sizeof(struct hi6220_fiq_debugger), GFP_KERNEL); + if (!t) { + pr_err("Failed to allocate for fiq debugger\n"); + return ret; + } + + t->pdata.uart_init = debug_port_init; + t->pdata.uart_getc = debug_getc; + t->pdata.uart_putc = debug_putc; + t->pdata.uart_flush = debug_flush; + t->pdata.uart_dev_suspend = debug_suspend; + t->pdata.uart_dev_resume = debug_resume; + + t->debug_port_base = ioremap(base, PAGE_SIZE); + if (!t->debug_port_base) { + pr_err("Failed to ioremap for fiq debugger\n"); + goto out1; + } + + res = kzalloc(sizeof(struct resource) * 3, GFP_KERNEL); + if (!res) { + pr_err("Failed to alloc fiq debugger resources\n"); + goto out2; + } + + pdev = kzalloc(sizeof(struct platform_device), GFP_KERNEL); + if (!pdev) { + pr_err("Failed to alloc fiq debugger platform device\n"); + goto out3; + }; + + if (fiq >= 0) { + res[0].flags = IORESOURCE_IRQ; + res[0].start = fiq; + res[0].end = fiq; + res[0].name = "fiq"; + } else { + res[0].flags = IORESOURCE_IRQ; + res[0].start = irq; + res[0].end = irq; + res[0].name = "uart_irq"; + } + + if (signal_irq >= 0) { + res[1].flags = IORESOURCE_IRQ; + res[1].start = signal_irq; + res[1].end = signal_irq; + res[1].name = "signal"; + res_count++; + } + + if (wakeup_irq >= 0) { + res[2].flags = IORESOURCE_IRQ; + res[2].start = wakeup_irq; + res[2].end = wakeup_irq; + res[2].name = "wakeup"; + res_count++; + } + + pdev->name = "fiq_debugger"; + pdev->id = hi6220_fiq_debugger_id++; + pdev->dev.platform_data = &t->pdata; + pdev->resource = res; + pdev->num_resources = res_count; + + ret = platform_device_register(pdev); + if (ret) { + pr_err("Failed to register fiq debugger\n"); + goto out4; + } + + return 0; + +out4: + kfree(pdev); +out3: + kfree(res); +out2: + iounmap(t->debug_port_base); +out1: + kfree(t); + return ret; +} + +int hi6220_serial_debug_init_irq_mode(unsigned int base, int irq, + struct clk *clk, int signal_irq, int wakeup_irq) +{ + return __hi6220_serial_debug_init(base, -1, irq, clk, signal_irq, + wakeup_irq); +} + +static int hi6220_serial_debug_probe(struct platform_device *pdev) +{ + struct resource *res; + int fiq; + int signal_irq; + int wakeup_irq; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&pdev->dev, "No mem resource\n"); + return -EINVAL; + } + + fiq = platform_get_irq_byname(pdev, "fiq"); + if (fiq < 0) { + dev_err(&pdev->dev, "No IRQ for fiq, error=%d\n", fiq); + return fiq; + } + + signal_irq = platform_get_irq_byname(pdev, "signal"); + if (signal_irq < 0) { + dev_err(&pdev->dev, "No signal IRQ, error=%d\n", signal_irq); + signal_irq = -1; + } + + wakeup_irq = platform_get_irq_byname(pdev, "wakeup"); + if (wakeup_irq < 0) { + dev_err(&pdev->dev, "No wakeup IRQ, error=%d\n", wakeup_irq); + wakeup_irq = -1; + } + + return hi6220_serial_debug_init_irq_mode(res->start, fiq, NULL, + signal_irq, wakeup_irq); +} + +static const struct of_device_id hi6220_serial_debug_match[] = { + { .compatible = "android,irq-hi6220-uart", }, + {} +}; + +static struct platform_driver hi6220_serial_debug_driver = { + .probe = hi6220_serial_debug_probe, + .driver = { + .name = "hi6220-irq-debug", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(hi6220_serial_debug_match), + }, +}; + +module_platform_driver(hi6220_serial_debug_driver); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index a313dfc0245f..be3bc2f4edd4 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -865,6 +865,27 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { }, }, { + .ident = "Lenovo ideapad Y700-15ISK", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad Y700-15ISK"), + }, + }, + { + .ident = "Lenovo ideapad Y700 Touch-15ISK", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad Y700 Touch-15ISK"), + }, + }, + { + .ident = "Lenovo ideapad Y700-17ISK", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad Y700-17ISK"), + }, + }, + { .ident = "Lenovo Yoga 2 11 / 13 / Pro", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), @@ -893,6 +914,13 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { }, }, { + .ident = "Lenovo Yoga 700", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 700"), + }, + }, + { .ident = "Lenovo Yoga 900", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c index 02bc5a6343c3..aa454241489c 100644 --- a/drivers/platform/x86/intel_scu_ipcutil.c +++ b/drivers/platform/x86/intel_scu_ipcutil.c @@ -49,7 +49,7 @@ struct scu_ipc_data { static int scu_reg_access(u32 cmd, struct scu_ipc_data *data) { - int count = data->count; + unsigned int count = data->count; if (count == 0 || count == 3 || count > 4) return -EINVAL; diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index c01302989ee4..f774cb576ffa 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -131,7 +131,7 @@ MODULE_LICENSE("GPL"); /* Field definitions */ #define HCI_ACCEL_MASK 0x7fff #define HCI_HOTKEY_DISABLE 0x0b -#define HCI_HOTKEY_ENABLE 0x01 +#define HCI_HOTKEY_ENABLE 0x09 #define HCI_HOTKEY_SPECIAL_FUNCTIONS 0x10 #define HCI_LCD_BRIGHTNESS_BITS 3 #define HCI_LCD_BRIGHTNESS_SHIFT (16-HCI_LCD_BRIGHTNESS_BITS) @@ -2484,6 +2484,14 @@ static int toshiba_acpi_setup_backlight(struct toshiba_acpi_dev *dev) brightness = __get_lcd_brightness(dev); if (brightness < 0) return 0; + /* + * If transflective backlight is supported and the brightness is zero + * (lowest brightness level), the set_lcd_brightness function will + * activate the transflective backlight, making the LCD appear to be + * turned off, simply increment the brightness level to avoid that. + */ + if (dev->tr_backlight_supported && brightness == 0) + brightness++; ret = set_lcd_brightness(dev, brightness); if (ret) { pr_debug("Backlight method is read-only, disabling backlight support\n"); diff --git a/drivers/pwm/pwm-brcmstb.c b/drivers/pwm/pwm-brcmstb.c index 423ce087cd9c..5d5adee16886 100644 --- a/drivers/pwm/pwm-brcmstb.c +++ b/drivers/pwm/pwm-brcmstb.c @@ -274,8 +274,8 @@ static int brcmstb_pwm_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); p->base = devm_ioremap_resource(&pdev->dev, res); - if (!p->base) { - ret = -ENOMEM; + if (IS_ERR(p->base)) { + ret = PTR_ERR(p->base); goto out_clk; } diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 9fc94de8c1ba..10c46e236e8b 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -461,6 +461,7 @@ config REGULATOR_MC13892 config REGULATOR_MT6311 tristate "MediaTek MT6311 PMIC" depends on I2C + select REGMAP_I2C help Say y here to select this option to enable the power regulator of MediaTek MT6311 PMIC. diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 35de22fdb7a0..f2e1a39ce0f3 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -27,8 +27,8 @@ #define AXP20X_IO_ENABLED 0x03 #define AXP20X_IO_DISABLED 0x07 -#define AXP22X_IO_ENABLED 0x04 -#define AXP22X_IO_DISABLED 0x03 +#define AXP22X_IO_ENABLED 0x03 +#define AXP22X_IO_DISABLED 0x04 #define AXP20X_WORKMODE_DCDC2_MASK BIT(2) #define AXP20X_WORKMODE_DCDC3_MASK BIT(1) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 73b7683355cd..732ac71b82cd 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -132,24 +132,24 @@ static bool have_full_constraints(void) return has_full_constraints || of_have_populated_dt(); } +static inline struct regulator_dev *rdev_get_supply(struct regulator_dev *rdev) +{ + if (rdev && rdev->supply) + return rdev->supply->rdev; + + return NULL; +} + /** * regulator_lock_supply - lock a regulator and its supplies * @rdev: regulator source */ static void regulator_lock_supply(struct regulator_dev *rdev) { - struct regulator *supply; - int i = 0; - - while (1) { - mutex_lock_nested(&rdev->mutex, i++); - supply = rdev->supply; - - if (!rdev->supply) - return; + int i; - rdev = supply->rdev; - } + for (i = 0; rdev; rdev = rdev_get_supply(rdev), i++) + mutex_lock_nested(&rdev->mutex, i); } /** diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c index 58f5d3b8e981..27343e1c43ef 100644 --- a/drivers/regulator/s5m8767.c +++ b/drivers/regulator/s5m8767.c @@ -202,9 +202,10 @@ static int s5m8767_get_register(struct s5m8767_info *s5m8767, int reg_id, } } - if (i < s5m8767->num_regulators) - *enable_ctrl = - s5m8767_opmode_reg[reg_id][mode] << S5M8767_ENCTRL_SHIFT; + if (i >= s5m8767->num_regulators) + return -EINVAL; + + *enable_ctrl = s5m8767_opmode_reg[reg_id][mode] << S5M8767_ENCTRL_SHIFT; return 0; } @@ -937,8 +938,12 @@ static int s5m8767_pmic_probe(struct platform_device *pdev) else regulators[id].vsel_mask = 0xff; - s5m8767_get_register(s5m8767, id, &enable_reg, + ret = s5m8767_get_register(s5m8767, id, &enable_reg, &enable_val); + if (ret) { + dev_err(s5m8767->dev, "error reading registers\n"); + return ret; + } regulators[id].enable_reg = enable_reg; regulators[id].enable_mask = S5M8767_ENCTRL_MASK; regulators[id].enable_val = enable_val; diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 05a51ef52703..d5c1b057a739 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -187,9 +187,9 @@ ds1685_rtc_end_data_access(struct ds1685_priv *rtc) * Only use this where you are certain another lock will not be held. */ static inline void -ds1685_rtc_begin_ctrl_access(struct ds1685_priv *rtc, unsigned long flags) +ds1685_rtc_begin_ctrl_access(struct ds1685_priv *rtc, unsigned long *flags) { - spin_lock_irqsave(&rtc->lock, flags); + spin_lock_irqsave(&rtc->lock, *flags); ds1685_rtc_switch_to_bank1(rtc); } @@ -1304,7 +1304,7 @@ ds1685_rtc_sysfs_ctrl_regs_store(struct device *dev, { struct ds1685_priv *rtc = dev_get_drvdata(dev); u8 reg = 0, bit = 0, tmp; - unsigned long flags = 0; + unsigned long flags; long int val = 0; const struct ds1685_rtc_ctrl_regs *reg_info = ds1685_rtc_sysfs_ctrl_regs_lookup(attr->attr.name); @@ -1325,7 +1325,7 @@ ds1685_rtc_sysfs_ctrl_regs_store(struct device *dev, bit = reg_info->bit; /* Safe to spinlock during a write. */ - ds1685_rtc_begin_ctrl_access(rtc, flags); + ds1685_rtc_begin_ctrl_access(rtc, &flags); tmp = rtc->read(rtc, reg); rtc->write(rtc, reg, (val ? (tmp | bit) : (tmp & ~(bit)))); ds1685_rtc_end_ctrl_access(rtc, flags); diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c index 097325d96db5..b1b4746a0eab 100644 --- a/drivers/rtc/rtc-hym8563.c +++ b/drivers/rtc/rtc-hym8563.c @@ -144,7 +144,7 @@ static int hym8563_rtc_set_time(struct device *dev, struct rtc_time *tm) * it does not seem to carry it over a subsequent write/read. * So we'll limit ourself to 100 years, starting at 2000 for now. */ - buf[6] = tm->tm_year - 100; + buf[6] = bin2bcd(tm->tm_year - 100); /* * CTL1 only contains TEST-mode bits apart from stop, diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c index 7184a0eda793..725dccae24e7 100644 --- a/drivers/rtc/rtc-max77686.c +++ b/drivers/rtc/rtc-max77686.c @@ -465,7 +465,7 @@ static int max77686_rtc_probe(struct platform_device *pdev) info->virq = regmap_irq_get_virq(max77686->rtc_irq_data, MAX77686_RTCIRQ_RTCA1); - if (!info->virq) { + if (info->virq <= 0) { ret = -ENXIO; goto err_rtc; } diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c index bd911bafb809..17341feadad1 100644 --- a/drivers/rtc/rtc-rx8025.c +++ b/drivers/rtc/rtc-rx8025.c @@ -65,7 +65,6 @@ static const struct i2c_device_id rx8025_id[] = { { "rx8025", 0 }, - { "rv8803", 1 }, { } }; MODULE_DEVICE_TABLE(i2c, rx8025_id); diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c index f64c282275b3..e1b86bb01062 100644 --- a/drivers/rtc/rtc-vr41xx.c +++ b/drivers/rtc/rtc-vr41xx.c @@ -272,12 +272,13 @@ static irqreturn_t rtclong1_interrupt(int irq, void *dev_id) } static const struct rtc_class_ops vr41xx_rtc_ops = { - .release = vr41xx_rtc_release, - .ioctl = vr41xx_rtc_ioctl, - .read_time = vr41xx_rtc_read_time, - .set_time = vr41xx_rtc_set_time, - .read_alarm = vr41xx_rtc_read_alarm, - .set_alarm = vr41xx_rtc_set_alarm, + .release = vr41xx_rtc_release, + .ioctl = vr41xx_rtc_ioctl, + .read_time = vr41xx_rtc_read_time, + .set_time = vr41xx_rtc_set_time, + .read_alarm = vr41xx_rtc_read_alarm, + .set_alarm = vr41xx_rtc_set_alarm, + .alarm_irq_enable = vr41xx_rtc_alarm_irq_enable, }; static int rtc_probe(struct platform_device *pdev) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index a263c10359e1..4abfbdb285ec 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -3031,6 +3031,7 @@ static void dasd_setup_queue(struct dasd_block *block) max = block->base->discipline->max_blocks << block->s2b_shift; } queue_flag_set_unlocked(QUEUE_FLAG_NONROT, block->request_queue); + block->request_queue->limits.max_dev_sectors = max; blk_queue_logical_block_size(block->request_queue, block->bp_block); blk_queue_max_hw_sectors(block->request_queue, max); diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 184b1dbeb554..286782c60da4 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -264,8 +264,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device) spin_unlock_irqrestore(&lcu->lock, flags); cancel_work_sync(&lcu->suc_data.worker); spin_lock_irqsave(&lcu->lock, flags); - if (device == lcu->suc_data.device) + if (device == lcu->suc_data.device) { + dasd_put_device(device); lcu->suc_data.device = NULL; + } } was_pending = 0; if (device == lcu->ruac_data.device) { @@ -273,8 +275,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device) was_pending = 1; cancel_delayed_work_sync(&lcu->ruac_data.dwork); spin_lock_irqsave(&lcu->lock, flags); - if (device == lcu->ruac_data.device) + if (device == lcu->ruac_data.device) { + dasd_put_device(device); lcu->ruac_data.device = NULL; + } } private->lcu = NULL; spin_unlock_irqrestore(&lcu->lock, flags); @@ -549,8 +553,10 @@ static void lcu_update_work(struct work_struct *work) if ((rc && (rc != -EOPNOTSUPP)) || (lcu->flags & NEED_UAC_UPDATE)) { DBF_DEV_EVENT(DBF_WARNING, device, "could not update" " alias data in lcu (rc = %d), retry later", rc); - schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ); + if (!schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ)) + dasd_put_device(device); } else { + dasd_put_device(device); lcu->ruac_data.device = NULL; lcu->flags &= ~UPDATE_PENDING; } @@ -593,8 +599,10 @@ static int _schedule_lcu_update(struct alias_lcu *lcu, */ if (!usedev) return -EINVAL; + dasd_get_device(usedev); lcu->ruac_data.device = usedev; - schedule_delayed_work(&lcu->ruac_data.dwork, 0); + if (!schedule_delayed_work(&lcu->ruac_data.dwork, 0)) + dasd_put_device(usedev); return 0; } @@ -723,7 +731,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu, ASCEBC((char *) &cqr->magic, 4); ccw = cqr->cpaddr; ccw->cmd_code = DASD_ECKD_CCW_RSCK; - ccw->flags = 0 ; + ccw->flags = CCW_FLAG_SLI; ccw->count = 16; ccw->cda = (__u32)(addr_t) cqr->data; ((char *)cqr->data)[0] = reason; @@ -930,6 +938,7 @@ static void summary_unit_check_handling_work(struct work_struct *work) /* 3. read new alias configuration */ _schedule_lcu_update(lcu, device); lcu->suc_data.device = NULL; + dasd_put_device(device); spin_unlock_irqrestore(&lcu->lock, flags); } @@ -989,6 +998,8 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device, } lcu->suc_data.reason = reason; lcu->suc_data.device = device; + dasd_get_device(device); spin_unlock(&lcu->lock); - schedule_work(&lcu->suc_data.worker); + if (!schedule_work(&lcu->suc_data.worker)) + dasd_put_device(device); }; diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index cb61f300f8b5..277b5c8c825c 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -67,7 +67,7 @@ static const u8 DASD_DIAG_CMS1[] = { 0xc3, 0xd4, 0xe2, 0xf1 };/* EBCDIC CMS1 */ * and function code cmd. * In case of an exception return 3. Otherwise return result of bitwise OR of * resulting condition code and DIAG return code. */ -static inline int dia250(void *iob, int cmd) +static inline int __dia250(void *iob, int cmd) { register unsigned long reg2 asm ("2") = (unsigned long) iob; typedef union { @@ -77,7 +77,6 @@ static inline int dia250(void *iob, int cmd) int rc; rc = 3; - diag_stat_inc(DIAG_STAT_X250); asm volatile( " diag 2,%2,0x250\n" "0: ipm %0\n" @@ -91,6 +90,12 @@ static inline int dia250(void *iob, int cmd) return rc; } +static inline int dia250(void *iob, int cmd) +{ + diag_stat_inc(DIAG_STAT_X250); + return __dia250(iob, cmd); +} + /* Initialize block I/O to DIAG device using the specified blocksize and * block offset. On success, return zero and set end_block to contain the * number of blocks on the device minus the specified offset. Return non-zero diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 074878b55a0b..d044f3f273be 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -944,6 +944,7 @@ struct fib { */ struct list_head fiblink; void *data; + u32 vector_no; struct hw_fib *hw_fib_va; /* Actual shared object */ dma_addr_t hw_fib_pa; /* physical address of hw_fib*/ }; @@ -2113,6 +2114,7 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor) int aac_acquire_irq(struct aac_dev *dev); void aac_free_irq(struct aac_dev *dev); const char *aac_driverinfo(struct Scsi_Host *); +void aac_fib_vector_assign(struct aac_dev *dev); struct fib *aac_fib_alloc(struct aac_dev *dev); int aac_fib_setup(struct aac_dev *dev); void aac_fib_map_free(struct aac_dev *dev); diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index a1f90fe849c9..4cbf54928640 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -83,13 +83,38 @@ static int fib_map_alloc(struct aac_dev *dev) void aac_fib_map_free(struct aac_dev *dev) { - pci_free_consistent(dev->pdev, - dev->max_fib_size * (dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB), - dev->hw_fib_va, dev->hw_fib_pa); + if (dev->hw_fib_va && dev->max_fib_size) { + pci_free_consistent(dev->pdev, + (dev->max_fib_size * + (dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB)), + dev->hw_fib_va, dev->hw_fib_pa); + } dev->hw_fib_va = NULL; dev->hw_fib_pa = 0; } +void aac_fib_vector_assign(struct aac_dev *dev) +{ + u32 i = 0; + u32 vector = 1; + struct fib *fibptr = NULL; + + for (i = 0, fibptr = &dev->fibs[i]; + i < (dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB); + i++, fibptr++) { + if ((dev->max_msix == 1) || + (i > ((dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB - 1) + - dev->vector_cap))) { + fibptr->vector_no = 0; + } else { + fibptr->vector_no = vector; + vector++; + if (vector == dev->max_msix) + vector = 1; + } + } +} + /** * aac_fib_setup - setup the fibs * @dev: Adapter to set up @@ -151,6 +176,12 @@ int aac_fib_setup(struct aac_dev * dev) hw_fib_pa = hw_fib_pa + dev->max_fib_size + sizeof(struct aac_fib_xporthdr); } + + /* + *Assign vector numbers to fibs + */ + aac_fib_vector_assign(dev); + /* * Add the fib chain to the free list */ diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 3b6e5c67e853..aa6eccb8940b 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1404,8 +1404,18 @@ static int aac_acquire_resources(struct aac_dev *dev) aac_adapter_enable_int(dev); - if (!dev->sync_mode) + /*max msix may change after EEH + * Re-assign vectors to fibs + */ + aac_fib_vector_assign(dev); + + if (!dev->sync_mode) { + /* After EEH recovery or suspend resume, max_msix count + * may change, therfore updating in init as well. + */ aac_adapter_start(dev); + dev->init->Sa_MSIXVectors = cpu_to_le32(dev->max_msix); + } return 0; error_iounmap: diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 2aa34ea8ceb1..bc0203f3d243 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -156,8 +156,8 @@ static irqreturn_t aac_src_intr_message(int irq, void *dev_id) break; if (dev->msi_enabled && dev->max_msix > 1) atomic_dec(&dev->rrq_outstanding[vector_no]); - aac_intr_normal(dev, handle-1, 0, isFastResponse, NULL); dev->host_rrq[index++] = 0; + aac_intr_normal(dev, handle-1, 0, isFastResponse, NULL); if (index == (vector_no + 1) * dev->vector_cap) index = vector_no * dev->vector_cap; dev->host_rrq_idx[vector_no] = index; @@ -452,36 +452,20 @@ static int aac_src_deliver_message(struct fib *fib) #endif u16 hdr_size = le16_to_cpu(fib->hw_fib_va->header.Size); + u16 vector_no; atomic_inc(&q->numpending); if (dev->msi_enabled && fib->hw_fib_va->header.Command != AifRequest && dev->max_msix > 1) { - u_int16_t vector_no, first_choice = 0xffff; - - vector_no = dev->fibs_pushed_no % dev->max_msix; - do { - vector_no += 1; - if (vector_no == dev->max_msix) - vector_no = 1; - if (atomic_read(&dev->rrq_outstanding[vector_no]) < - dev->vector_cap) - break; - if (0xffff == first_choice) - first_choice = vector_no; - else if (vector_no == first_choice) - break; - } while (1); - if (vector_no == first_choice) - vector_no = 0; - atomic_inc(&dev->rrq_outstanding[vector_no]); - if (dev->fibs_pushed_no == 0xffffffff) - dev->fibs_pushed_no = 0; - else - dev->fibs_pushed_no++; + vector_no = fib->vector_no; fib->hw_fib_va->header.Handle += (vector_no << 16); + } else { + vector_no = 0; } + atomic_inc(&dev->rrq_outstanding[vector_no]); + if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) { /* Calculate the amount to the fibsize bits */ fibsize = (hdr_size + 127) / 128 - 1; diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c index b846a4683562..fc6a83188c1e 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -1336,6 +1336,7 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev, case AHC_DEV_Q_TAGGED: scsi_change_queue_depth(sdev, dev->openings + dev->active); + break; default: /* * We allow the OS to queue 2 untagged transactions to diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index fe0c5143f8e6..758f76e88704 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -4470,6 +4470,7 @@ put_shost: scsi_host_put(phba->shost); free_kset: iscsi_boot_destroy_kset(phba->boot_kset); + phba->boot_kset = NULL; return -ENOMEM; } diff --git a/drivers/scsi/device_handler/Kconfig b/drivers/scsi/device_handler/Kconfig index e5647d59224f..0b331c9c0a8f 100644 --- a/drivers/scsi/device_handler/Kconfig +++ b/drivers/scsi/device_handler/Kconfig @@ -13,13 +13,13 @@ menuconfig SCSI_DH config SCSI_DH_RDAC tristate "LSI RDAC Device Handler" - depends on SCSI_DH + depends on SCSI_DH && SCSI help If you have a LSI RDAC select y. Otherwise, say N. config SCSI_DH_HP_SW tristate "HP/COMPAQ MSA Device Handler" - depends on SCSI_DH + depends on SCSI_DH && SCSI help If you have a HP/COMPAQ MSA device that requires START_STOP to be sent to start it and cannot upgrade the firmware then select y. @@ -27,13 +27,13 @@ config SCSI_DH_HP_SW config SCSI_DH_EMC tristate "EMC CLARiiON Device Handler" - depends on SCSI_DH + depends on SCSI_DH && SCSI help If you have a EMC CLARiiON select y. Otherwise, say N. config SCSI_DH_ALUA tristate "SPC-3 ALUA Device Handler" - depends on SCSI_DH + depends on SCSI_DH && SCSI help SCSI Device handler for generic SPC-3 Asymmetric Logical Unit Access (ALUA). diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index 361358134315..93880ed6291c 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -562,7 +562,7 @@ static int mode_select_handle_sense(struct scsi_device *sdev, /* * Command Lock contention */ - err = SCSI_DH_RETRY; + err = SCSI_DH_IMM_RETRY; break; default: break; @@ -612,6 +612,8 @@ retry: err = mode_select_handle_sense(sdev, h->sense); if (err == SCSI_DH_RETRY && retry_cnt--) goto retry; + if (err == SCSI_DH_IMM_RETRY) + goto retry; } if (err == SCSI_DH_OK) { h->state = RDAC_STATE_ACTIVE; diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 536cd5a80422..43ac62623bf2 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -4003,13 +4003,17 @@ static ssize_t ipr_store_update_fw(struct device *dev, struct ipr_sglist *sglist; char fname[100]; char *src; - int len, result, dnld_size; + char *endline; + int result, dnld_size; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - len = snprintf(fname, 99, "%s", buf); - fname[len-1] = '\0'; + snprintf(fname, sizeof(fname), "%s", buf); + + endline = strchr(fname, '\n'); + if (endline) + *endline = '\0'; if (request_firmware(&fw_entry, fname, &ioa_cfg->pdev->dev)) { dev_err(&ioa_cfg->pdev->dev, "Firmware file %s not found\n", fname); diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index db9446c612da..b0d92b84bcdc 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -2855,7 +2855,7 @@ lpfc_online(struct lpfc_hba *phba) } vports = lpfc_create_vport_work_array(phba); - if (vports != NULL) + if (vports != NULL) { for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) { struct Scsi_Host *shost; shost = lpfc_shost_from_vport(vports[i]); @@ -2872,7 +2872,8 @@ lpfc_online(struct lpfc_hba *phba) } spin_unlock_irq(shost->host_lock); } - lpfc_destroy_vport_work_array(phba, vports); + } + lpfc_destroy_vport_work_array(phba, vports); lpfc_unblock_mgmt_io(phba); return 0; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 97a1c1c33b05..00ce3e269a43 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -6282,12 +6282,13 @@ out: } for (i = 0; i < ioc->sge_count; i++) { - if (kbuff_arr[i]) + if (kbuff_arr[i]) { dma_free_coherent(&instance->pdev->dev, le32_to_cpu(kern_sge32[i].length), kbuff_arr[i], le32_to_cpu(kern_sge32[i].phys_addr)); kbuff_arr[i] = NULL; + } } megasas_return_cmd(instance, cmd); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 16a1935cc9c1..e197c6f39de2 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2192,7 +2192,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha) /* Clear outstanding commands array. */ for (que = 0; que < ha->max_req_queues; que++) { req = ha->req_q_map[que]; - if (!req) + if (!req || !test_bit(que, ha->req_qid_map)) continue; req->out_ptr = (void *)(req->ring + req->length); *req->out_ptr = 0; @@ -2209,7 +2209,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha) for (que = 0; que < ha->max_rsp_queues; que++) { rsp = ha->rsp_q_map[que]; - if (!rsp) + if (!rsp || !test_bit(que, ha->rsp_qid_map)) continue; rsp->in_ptr = (void *)(rsp->ring + rsp->length); *rsp->in_ptr = 0; @@ -4961,7 +4961,7 @@ qla25xx_init_queues(struct qla_hw_data *ha) for (i = 1; i < ha->max_rsp_queues; i++) { rsp = ha->rsp_q_map[i]; - if (rsp) { + if (rsp && test_bit(i, ha->rsp_qid_map)) { rsp->options &= ~BIT_0; ret = qla25xx_init_rsp_que(base_vha, rsp); if (ret != QLA_SUCCESS) @@ -4976,8 +4976,8 @@ qla25xx_init_queues(struct qla_hw_data *ha) } for (i = 1; i < ha->max_req_queues; i++) { req = ha->req_q_map[i]; - if (req) { - /* Clear outstanding commands array. */ + if (req && test_bit(i, ha->req_qid_map)) { + /* Clear outstanding commands array. */ req->options &= ~BIT_0; ret = qla25xx_init_req_que(base_vha, req); if (ret != QLA_SUCCESS) diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index ccf6a7f99024..0e59731f95ad 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -3018,9 +3018,9 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp) "MSI-X: Failed to enable support " "-- %d/%d\n Retry with %d vectors.\n", ha->msix_count, ret, ret); + ha->msix_count = ret; + ha->max_rsp_queues = ha->msix_count - 1; } - ha->msix_count = ret; - ha->max_rsp_queues = ha->msix_count - 1; ha->msix_entries = kzalloc(sizeof(struct qla_msix_entry) * ha->msix_count, GFP_KERNEL); if (!ha->msix_entries) { diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index c5dd594f6c31..cf7ba52bae66 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -600,7 +600,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha) /* Delete request queues */ for (cnt = 1; cnt < ha->max_req_queues; cnt++) { req = ha->req_q_map[cnt]; - if (req) { + if (req && test_bit(cnt, ha->req_qid_map)) { ret = qla25xx_delete_req_que(vha, req); if (ret != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x00ea, @@ -614,7 +614,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha) /* Delete response queues */ for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) { rsp = ha->rsp_q_map[cnt]; - if (rsp) { + if (rsp && test_bit(cnt, ha->rsp_qid_map)) { ret = qla25xx_delete_rsp_que(vha, rsp); if (ret != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x00eb, diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index bfa9a64c316b..fc6674db4f2d 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -397,6 +397,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha) int cnt; for (cnt = 0; cnt < ha->max_req_queues; cnt++) { + if (!test_bit(cnt, ha->req_qid_map)) + continue; + req = ha->req_q_map[cnt]; qla2x00_free_req_que(ha, req); } @@ -404,6 +407,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha) ha->req_q_map = NULL; for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) { + if (!test_bit(cnt, ha->rsp_qid_map)) + continue; + rsp = ha->rsp_q_map[cnt]; qla2x00_free_rsp_que(ha, rsp); } diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c index ddbe2e7ac14d..c3e622524604 100644 --- a/drivers/scsi/qla2xxx/qla_tmpl.c +++ b/drivers/scsi/qla2xxx/qla_tmpl.c @@ -395,6 +395,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha, if (ent->t263.queue_type == T263_QUEUE_TYPE_REQ) { for (i = 0; i < vha->hw->max_req_queues; i++) { struct req_que *req = vha->hw->req_q_map[i]; + + if (!test_bit(i, vha->hw->req_qid_map)) + continue; + if (req || !buf) { length = req ? req->length : REQUEST_ENTRY_CNT_24XX; @@ -408,6 +412,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha, } else if (ent->t263.queue_type == T263_QUEUE_TYPE_RSP) { for (i = 0; i < vha->hw->max_rsp_queues; i++) { struct rsp_que *rsp = vha->hw->rsp_q_map[i]; + + if (!test_bit(i, vha->hw->rsp_qid_map)) + continue; + if (rsp || !buf) { length = rsp ? rsp->length : RESPONSE_ENTRY_CNT_MQ; @@ -634,6 +642,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha, if (ent->t274.queue_type == T274_QUEUE_TYPE_REQ_SHAD) { for (i = 0; i < vha->hw->max_req_queues; i++) { struct req_que *req = vha->hw->req_q_map[i]; + + if (!test_bit(i, vha->hw->req_qid_map)) + continue; + if (req || !buf) { qla27xx_insert16(i, buf, len); qla27xx_insert16(1, buf, len); @@ -645,6 +657,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha, } else if (ent->t274.queue_type == T274_QUEUE_TYPE_RSP_SHAD) { for (i = 0; i < vha->hw->max_rsp_queues; i++) { struct rsp_que *rsp = vha->hw->rsp_q_map[i]; + + if (!test_bit(i, vha->hw->rsp_qid_map)) + continue; + if (rsp || !buf) { qla27xx_insert16(i, buf, len); qla27xx_insert16(1, buf, len); diff --git a/drivers/scsi/scsi_common.c b/drivers/scsi/scsi_common.c index c126966130ab..ce79de822e46 100644 --- a/drivers/scsi/scsi_common.c +++ b/drivers/scsi/scsi_common.c @@ -278,8 +278,16 @@ int scsi_set_sense_information(u8 *buf, int buf_len, u64 info) ucp[3] = 0; put_unaligned_be64(info, &ucp[4]); } else if ((buf[0] & 0x7f) == 0x70) { - buf[0] |= 0x80; - put_unaligned_be64(info, &buf[3]); + /* + * Only set the 'VALID' bit if we can represent the value + * correctly; otherwise just fill out the lower bytes and + * clear the 'VALID' flag. + */ + if (info <= 0xffffffffUL) + buf[0] |= 0x80; + else + buf[0] &= 0x7f; + put_unaligned_be32((u32)info, &buf[3]); } return 0; diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 2c1160c7ec92..da2e068ee47d 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -205,6 +205,7 @@ static struct { {"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC}, {"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN}, + {"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES}, {"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, @@ -227,6 +228,7 @@ static struct { {"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC}, {"Promise", "", NULL, BLIST_SPARSELUN}, {"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024}, + {"SYNOLOGY", "iSCSI Storage", NULL, BLIST_MAX_1024}, {"QUANTUM", "XP34301", "1071", BLIST_NOTQ}, {"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN}, {"SanDisk", "ImageMate CF-SD1", NULL, BLIST_FORCELUN}, diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 21930c9ac9cd..c8115b4fe474 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1192,16 +1192,18 @@ static void __scsi_remove_target(struct scsi_target *starget) void scsi_remove_target(struct device *dev) { struct Scsi_Host *shost = dev_to_shost(dev->parent); - struct scsi_target *starget; + struct scsi_target *starget, *last_target = NULL; unsigned long flags; restart: spin_lock_irqsave(shost->host_lock, flags); list_for_each_entry(starget, &shost->__targets, siblings) { - if (starget->state == STARGET_DEL) + if (starget->state == STARGET_DEL || + starget == last_target) continue; if (starget->dev.parent == dev || &starget->dev == dev) { kref_get(&starget->reap_ref); + last_target = starget; spin_unlock_irqrestore(shost->host_lock, flags); __scsi_remove_target(starget); scsi_target_reap(starget); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 4e08d1cd704d..0d7c6e86f149 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -648,7 +648,7 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) */ if (sdkp->lbprz) { q->limits.discard_alignment = 0; - q->limits.discard_granularity = 1; + q->limits.discard_granularity = logical_block_size; } else { q->limits.discard_alignment = sdkp->unmap_alignment * logical_block_size; @@ -1275,18 +1275,19 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); struct scsi_device *sdp = sdkp->device; struct Scsi_Host *host = sdp->host; + sector_t capacity = logical_to_sectors(sdp, sdkp->capacity); int diskinfo[4]; /* default to most commonly used values */ - diskinfo[0] = 0x40; /* 1 << 6 */ - diskinfo[1] = 0x20; /* 1 << 5 */ - diskinfo[2] = sdkp->capacity >> 11; - + diskinfo[0] = 0x40; /* 1 << 6 */ + diskinfo[1] = 0x20; /* 1 << 5 */ + diskinfo[2] = capacity >> 11; + /* override with calculated, extended default, or driver values */ if (host->hostt->bios_param) - host->hostt->bios_param(sdp, bdev, sdkp->capacity, diskinfo); + host->hostt->bios_param(sdp, bdev, capacity, diskinfo); else - scsicam_bios_param(bdev, sdkp->capacity, diskinfo); + scsicam_bios_param(bdev, capacity, diskinfo); geo->heads = diskinfo[0]; geo->sectors = diskinfo[1]; @@ -2337,14 +2338,6 @@ got_data: if (sdkp->capacity > 0xffffffff) sdp->use_16_for_rw = 1; - /* Rescale capacity to 512-byte units */ - if (sector_size == 4096) - sdkp->capacity <<= 3; - else if (sector_size == 2048) - sdkp->capacity <<= 2; - else if (sector_size == 1024) - sdkp->capacity <<= 1; - blk_queue_physical_block_size(sdp->request_queue, sdkp->physical_block_size); sdkp->device->sector_size = sector_size; @@ -2812,11 +2805,6 @@ static int sd_try_extended_inquiry(struct scsi_device *sdp) return 0; } -static inline u32 logical_to_sectors(struct scsi_device *sdev, u32 blocks) -{ - return blocks << (ilog2(sdev->sector_size) - 9); -} - /** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. @@ -2893,14 +2881,14 @@ static int sd_revalidate_disk(struct gendisk *disk) sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS && sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE) rw_max = q->limits.io_opt = - logical_to_sectors(sdp, sdkp->opt_xfer_blocks); + sdkp->opt_xfer_blocks * sdp->sector_size; else rw_max = BLK_DEF_MAX_SECTORS; /* Combine with controller limits */ q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q)); - set_capacity(disk, sdkp->capacity); + set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity)); sd_config_write_same(sdkp); kfree(buffer); @@ -3268,8 +3256,8 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret = 0; - if (!sdkp) - return 0; /* this can happen */ + if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ + return 0; if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); @@ -3308,6 +3296,9 @@ static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); + if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ + return 0; + if (!sdkp->device->manage_start_stop) return 0; diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 5f2a84aff29f..654630bb7d0e 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -65,7 +65,7 @@ struct scsi_disk { struct device dev; struct gendisk *disk; atomic_t openers; - sector_t capacity; /* size in 512-byte sectors */ + sector_t capacity; /* size in logical blocks */ u32 max_xfer_blocks; u32 opt_xfer_blocks; u32 max_ws_blocks; @@ -146,6 +146,11 @@ static inline int scsi_medium_access_command(struct scsi_cmnd *scmd) return 0; } +static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blocks) +{ + return blocks << (ilog2(sdev->sector_size) - 9); +} + /* * A DIF-capable target device can be formatted with different * protection schemes. Currently 0 through 3 are defined: diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 503ab8b46c0b..ae7d9bdf409c 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -652,7 +652,8 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos) else hp->dxfer_direction = (mxsize > 0) ? SG_DXFER_FROM_DEV : SG_DXFER_NONE; hp->dxfer_len = mxsize; - if (hp->dxfer_direction == SG_DXFER_TO_DEV) + if ((hp->dxfer_direction == SG_DXFER_TO_DEV) || + (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV)) hp->dxferp = (char __user *)buf + cmd_size; else hp->dxferp = NULL; @@ -1261,7 +1262,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma) } sfp->mmap_called = 1; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; return 0; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 8bd54a64efd6..64c867405ad4 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -144,6 +144,9 @@ static int sr_runtime_suspend(struct device *dev) { struct scsi_cd *cd = dev_get_drvdata(dev); + if (!cd) /* E.g.: runtime suspend following sr_remove() */ + return 0; + if (cd->media_present) return -EBUSY; else @@ -985,6 +988,7 @@ static int sr_remove(struct device *dev) scsi_autopm_get_device(cd->device); del_gendisk(cd->disk); + dev_set_drvdata(dev, NULL); mutex_lock(&sr_ref_mutex); kref_put(&cd->kref, sr_kref_release); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 3fba42ad9fb8..0f636cc4c809 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -889,8 +889,9 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, do_work = true; process_err_fn = storvsc_remove_lun; break; - case (SRB_STATUS_ABORTED | SRB_STATUS_AUTOSENSE_VALID): - if ((asc == 0x2a) && (ascq == 0x9)) { + case SRB_STATUS_ABORTED: + if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID && + (asc == 0x2a) && (ascq == 0x9)) { do_work = true; process_err_fn = storvsc_device_scan; /* diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c index 91a003011acf..a9bac3bf20de 100644 --- a/drivers/sh/pm_runtime.c +++ b/drivers/sh/pm_runtime.c @@ -34,7 +34,7 @@ static struct pm_clk_notifier_block platform_bus_notifier = { static int __init sh_pm_runtime_init(void) { - if (IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { + if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { if (!of_find_compatible_node(NULL, NULL, "renesas,cpg-mstp-clocks")) return 0; diff --git a/drivers/soc/rockchip/pm_domains.c b/drivers/soc/rockchip/pm_domains.c index 534c58937a56..4a65c5bda146 100644 --- a/drivers/soc/rockchip/pm_domains.c +++ b/drivers/soc/rockchip/pm_domains.c @@ -419,6 +419,7 @@ static int rockchip_pm_domain_probe(struct platform_device *pdev) if (error) { dev_err(dev, "failed to handle node %s: %d\n", node->name, error); + of_node_put(node); goto err_out; } } diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index aebad36391c9..8feac599e9ab 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -1571,6 +1571,7 @@ static int atmel_spi_probe(struct platform_device *pdev) as->use_cs_gpios = true; if (atmel_spi_is_v2(as) && + pdev->dev.of_node && !of_get_property(pdev->dev.of_node, "cs-gpios", NULL)) { as->use_cs_gpios = false; master->num_chipselect = 4; diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 1f8903d356e5..ed8283e7397a 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -1024,6 +1024,16 @@ static int omap2_mcspi_setup(struct spi_device *spi) spi->controller_state = cs; /* Link this to context save list */ list_add_tail(&cs->node, &ctx->cs); + + if (gpio_is_valid(spi->cs_gpio)) { + ret = gpio_request(spi->cs_gpio, dev_name(&spi->dev)); + if (ret) { + dev_err(&spi->dev, "failed to request gpio\n"); + return ret; + } + gpio_direction_output(spi->cs_gpio, + !(spi->mode & SPI_CS_HIGH)); + } } if (!mcspi_dma->dma_rx || !mcspi_dma->dma_tx) { @@ -1032,15 +1042,6 @@ static int omap2_mcspi_setup(struct spi_device *spi) return ret; } - if (gpio_is_valid(spi->cs_gpio)) { - ret = gpio_request(spi->cs_gpio, dev_name(&spi->dev)); - if (ret) { - dev_err(&spi->dev, "failed to request gpio\n"); - return ret; - } - gpio_direction_output(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH)); - } - ret = pm_runtime_get_sync(mcspi->dev); if (ret < 0) return ret; diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 79a8bc4f6cec..035767c02072 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -265,7 +265,10 @@ static inline u32 rx_max(struct rockchip_spi *rs) static void rockchip_spi_set_cs(struct spi_device *spi, bool enable) { u32 ser; - struct rockchip_spi *rs = spi_master_get_devdata(spi->master); + struct spi_master *master = spi->master; + struct rockchip_spi *rs = spi_master_get_devdata(master); + + pm_runtime_get_sync(rs->dev); ser = readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & SER_MASK; @@ -290,6 +293,8 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable) ser &= ~(1 << spi->chip_select); writel_relaxed(ser, rs->regs + ROCKCHIP_SPI_SER); + + pm_runtime_put_sync(rs->dev); } static int rockchip_spi_prepare_message(struct spi_master *master, diff --git a/drivers/staging/android/fiq_debugger/Kconfig b/drivers/staging/android/fiq_debugger/Kconfig index 56f7f999377e..60fc224d4efc 100644 --- a/drivers/staging/android/fiq_debugger/Kconfig +++ b/drivers/staging/android/fiq_debugger/Kconfig @@ -42,6 +42,15 @@ config FIQ_DEBUGGER_CONSOLE_DEFAULT_ENABLE If enabled, this puts the fiq debugger into console mode by default. Otherwise, the fiq debugger will start out in debug mode. +config FIQ_DEBUGGER_UART_OVERLAY + bool "Install uart DT overlay" + depends on FIQ_DEBUGGER + select OF_OVERLAY + default n + help + If enabled, fiq debugger is calling fiq_debugger_uart_overlay() + that will apply overlay uart_overlay@0 to disable proper uart. + config FIQ_WATCHDOG bool select FIQ_DEBUGGER diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger.c b/drivers/staging/android/fiq_debugger/fiq_debugger.c index 7f056831dbff..b132cff14f01 100644 --- a/drivers/staging/android/fiq_debugger/fiq_debugger.c +++ b/drivers/staging/android/fiq_debugger/fiq_debugger.c @@ -39,6 +39,10 @@ #include <asm/fiq_glue.h> #endif +#ifdef CONFIG_FIQ_DEBUGGER_UART_OVERLAY +#include <linux/of.h> +#endif + #include <linux/uaccess.h> #include "fiq_debugger.h" @@ -119,11 +123,13 @@ static bool initial_console_enable; #endif static bool fiq_kgdb_enable; +static bool fiq_debugger_disable; module_param_named(no_sleep, initial_no_sleep, bool, 0644); module_param_named(debug_enable, initial_debug_enable, bool, 0644); module_param_named(console_enable, initial_console_enable, bool, 0644); module_param_named(kgdb_enable, fiq_kgdb_enable, bool, 0644); +module_param_named(disable, fiq_debugger_disable, bool, 0644); #ifdef CONFIG_FIQ_DEBUGGER_WAKEUP_IRQ_ALWAYS_ON static inline @@ -1201,11 +1207,41 @@ static struct platform_driver fiq_debugger_driver = { }, }; +#if defined(CONFIG_FIQ_DEBUGGER_UART_OVERLAY) +int fiq_debugger_uart_overlay(void) +{ + struct device_node *onp = of_find_node_by_path("/uart_overlay@0"); + int ret; + + if (!onp) { + pr_err("serial_debugger: uart overlay not found\n"); + return -ENODEV; + } + + ret = of_overlay_create(onp); + if (ret < 0) { + pr_err("serial_debugger: fail to create overlay: %d\n", ret); + of_node_put(onp); + return ret; + } + + pr_info("serial_debugger: uart overlay applied\n"); + return 0; +} +#endif + static int __init fiq_debugger_init(void) { + if (fiq_debugger_disable) { + pr_err("serial_debugger: disabled\n"); + return -ENODEV; + } #if defined(CONFIG_FIQ_DEBUGGER_CONSOLE) fiq_debugger_tty_init(); #endif +#if defined(CONFIG_FIQ_DEBUGGER_UART_OVERLAY) + fiq_debugger_uart_overlay(); +#endif return platform_driver_register(&fiq_debugger_driver); } diff --git a/drivers/staging/android/ion/ion_test.c b/drivers/staging/android/ion/ion_test.c index b8dcf5a26cc4..58d46893e5ff 100644 --- a/drivers/staging/android/ion/ion_test.c +++ b/drivers/staging/android/ion/ion_test.c @@ -285,8 +285,8 @@ static int __init ion_test_init(void) { ion_test_pdev = platform_device_register_simple("ion-test", -1, NULL, 0); - if (!ion_test_pdev) - return -ENODEV; + if (IS_ERR(ion_test_pdev)) + return PTR_ERR(ion_test_pdev); return platform_driver_probe(&ion_test_platform_driver, ion_test_probe); } diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c index 6cc304a4c59b..27fbf1a81097 100644 --- a/drivers/staging/comedi/drivers/ni_mio_common.c +++ b/drivers/staging/comedi/drivers/ni_mio_common.c @@ -246,24 +246,24 @@ static void ni_writel(struct comedi_device *dev, uint32_t data, int reg) { if (dev->mmio) writel(data, dev->mmio + reg); - - outl(data, dev->iobase + reg); + else + outl(data, dev->iobase + reg); } static void ni_writew(struct comedi_device *dev, uint16_t data, int reg) { if (dev->mmio) writew(data, dev->mmio + reg); - - outw(data, dev->iobase + reg); + else + outw(data, dev->iobase + reg); } static void ni_writeb(struct comedi_device *dev, uint8_t data, int reg) { if (dev->mmio) writeb(data, dev->mmio + reg); - - outb(data, dev->iobase + reg); + else + outb(data, dev->iobase + reg); } static uint32_t ni_readl(struct comedi_device *dev, int reg) diff --git a/drivers/staging/comedi/drivers/ni_tiocmd.c b/drivers/staging/comedi/drivers/ni_tiocmd.c index 437f723bb34d..823e47910004 100644 --- a/drivers/staging/comedi/drivers/ni_tiocmd.c +++ b/drivers/staging/comedi/drivers/ni_tiocmd.c @@ -92,7 +92,7 @@ static int ni_tio_input_inttrig(struct comedi_device *dev, unsigned long flags; int ret = 0; - if (trig_num != cmd->start_src) + if (trig_num != cmd->start_arg) return -EINVAL; spin_lock_irqsave(&counter->lock, flags); diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c index 79ac19246548..70b8f4fabfad 100644 --- a/drivers/staging/panel/panel.c +++ b/drivers/staging/panel/panel.c @@ -825,8 +825,7 @@ static void lcd_write_cmd_s(int cmd) lcd_send_serial(0x1F); /* R/W=W, RS=0 */ lcd_send_serial(cmd & 0x0F); lcd_send_serial((cmd >> 4) & 0x0F); - /* the shortest command takes at least 40 us */ - usleep_range(40, 100); + udelay(40); /* the shortest command takes at least 40 us */ spin_unlock_irq(&pprt_lock); } @@ -837,8 +836,7 @@ static void lcd_write_data_s(int data) lcd_send_serial(0x5F); /* R/W=W, RS=1 */ lcd_send_serial(data & 0x0F); lcd_send_serial((data >> 4) & 0x0F); - /* the shortest data takes at least 40 us */ - usleep_range(40, 100); + udelay(40); /* the shortest data takes at least 40 us */ spin_unlock_irq(&pprt_lock); } @@ -848,20 +846,19 @@ static void lcd_write_cmd_p8(int cmd) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, cmd); - /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); /* maintain the data during 20 us before the strobe */ bits.e = BIT_SET; bits.rs = BIT_CLR; bits.rw = BIT_CLR; set_ctrl_bits(); - usleep_range(40, 100); /* maintain the strobe during 40 us */ + udelay(40); /* maintain the strobe during 40 us */ bits.e = BIT_CLR; set_ctrl_bits(); - usleep_range(120, 500); /* the shortest command takes at least 120 us */ + udelay(120); /* the shortest command takes at least 120 us */ spin_unlock_irq(&pprt_lock); } @@ -871,20 +868,19 @@ static void lcd_write_data_p8(int data) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, data); - /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); /* maintain the data during 20 us before the strobe */ bits.e = BIT_SET; bits.rs = BIT_SET; bits.rw = BIT_CLR; set_ctrl_bits(); - usleep_range(40, 100); /* maintain the strobe during 40 us */ + udelay(40); /* maintain the strobe during 40 us */ bits.e = BIT_CLR; set_ctrl_bits(); - usleep_range(45, 100); /* the shortest data takes at least 45 us */ + udelay(45); /* the shortest data takes at least 45 us */ spin_unlock_irq(&pprt_lock); } @@ -894,7 +890,7 @@ static void lcd_write_cmd_tilcd(int cmd) spin_lock_irq(&pprt_lock); /* present the data to the control port */ w_ctr(pprt, cmd); - usleep_range(60, 120); + udelay(60); spin_unlock_irq(&pprt_lock); } @@ -904,7 +900,7 @@ static void lcd_write_data_tilcd(int data) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, data); - usleep_range(60, 120); + udelay(60); spin_unlock_irq(&pprt_lock); } @@ -947,7 +943,7 @@ static void lcd_clear_fast_s(void) lcd_send_serial(0x5F); /* R/W=W, RS=1 */ lcd_send_serial(' ' & 0x0F); lcd_send_serial((' ' >> 4) & 0x0F); - usleep_range(40, 100); /* the shortest data takes at least 40 us */ + udelay(40); /* the shortest data takes at least 40 us */ } spin_unlock_irq(&pprt_lock); @@ -971,7 +967,7 @@ static void lcd_clear_fast_p8(void) w_dtr(pprt, ' '); /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); bits.e = BIT_SET; bits.rs = BIT_SET; @@ -979,13 +975,13 @@ static void lcd_clear_fast_p8(void) set_ctrl_bits(); /* maintain the strobe during 40 us */ - usleep_range(40, 100); + udelay(40); bits.e = BIT_CLR; set_ctrl_bits(); /* the shortest data takes at least 45 us */ - usleep_range(45, 100); + udelay(45); } spin_unlock_irq(&pprt_lock); @@ -1007,7 +1003,7 @@ static void lcd_clear_fast_tilcd(void) for (pos = 0; pos < lcd.height * lcd.hwidth; pos++) { /* present the data to the data port */ w_dtr(pprt, ' '); - usleep_range(60, 120); + udelay(60); } spin_unlock_irq(&pprt_lock); diff --git a/drivers/staging/rdma/hfi1/TODO b/drivers/staging/rdma/hfi1/TODO index 05de0dad8762..4c6f1d7d2eaf 100644 --- a/drivers/staging/rdma/hfi1/TODO +++ b/drivers/staging/rdma/hfi1/TODO @@ -3,4 +3,4 @@ July, 2015 - Remove unneeded file entries in sysfs - Remove software processing of IB protocol and place in library for use by qib, ipath (if still present), hfi1, and eventually soft-roce - +- Replace incorrect uAPI diff --git a/drivers/staging/rdma/hfi1/file_ops.c b/drivers/staging/rdma/hfi1/file_ops.c index aae9826ec62b..c851e51b1dc3 100644 --- a/drivers/staging/rdma/hfi1/file_ops.c +++ b/drivers/staging/rdma/hfi1/file_ops.c @@ -62,6 +62,8 @@ #include <linux/cred.h> #include <linux/uio.h> +#include <rdma/ib.h> + #include "hfi.h" #include "pio.h" #include "device.h" @@ -214,6 +216,10 @@ static ssize_t hfi1_file_write(struct file *fp, const char __user *data, int uctxt_required = 1; int must_be_root = 0; + /* FIXME: This interface cannot continue out of staging */ + if (WARN_ON_ONCE(!ib_safe_file_access(fp))) + return -EACCES; + if (count < sizeof(cmd)) { ret = -EINVAL; goto bail; diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c index aa5ab6c80ed4..41ef099b7aa6 100644 --- a/drivers/staging/speakup/selection.c +++ b/drivers/staging/speakup/selection.c @@ -142,7 +142,9 @@ static void __speakup_paste_selection(struct work_struct *work) struct tty_ldisc *ld; DECLARE_WAITQUEUE(wait, current); - ld = tty_ldisc_ref_wait(tty); + ld = tty_ldisc_ref(tty); + if (!ld) + goto tty_unref; tty_buffer_lock_exclusive(&vc->port); add_wait_queue(&vc->paste_wait, &wait); @@ -162,6 +164,7 @@ static void __speakup_paste_selection(struct work_struct *work) tty_buffer_unlock_exclusive(&vc->port); tty_ldisc_deref(ld); +tty_unref: tty_kref_put(tty); } diff --git a/drivers/staging/speakup/serialio.c b/drivers/staging/speakup/serialio.c index 3b5835b28128..a5bbb338f275 100644 --- a/drivers/staging/speakup/serialio.c +++ b/drivers/staging/speakup/serialio.c @@ -6,6 +6,11 @@ #include "spk_priv.h" #include "serialio.h" +#include <linux/serial_core.h> +/* WARNING: Do not change this to <linux/serial.h> without testing that + * SERIAL_PORT_DFNS does get defined to the appropriate value. */ +#include <asm/serial.h> + #ifndef SERIAL_PORT_DFNS #define SERIAL_PORT_DFNS #endif @@ -23,9 +28,15 @@ const struct old_serial_port *spk_serial_init(int index) int baud = 9600, quot = 0; unsigned int cval = 0; int cflag = CREAD | HUPCL | CLOCAL | B9600 | CS8; - const struct old_serial_port *ser = rs_table + index; + const struct old_serial_port *ser; int err; + if (index >= ARRAY_SIZE(rs_table)) { + pr_info("no port info for ttyS%d\n", index); + return NULL; + } + ser = rs_table + index; + /* Divisor, bytesize and parity */ quot = ser->baud_base / baud; cval = cflag & (CSIZE | CSTOPB); diff --git a/drivers/switch/Kconfig b/drivers/switch/Kconfig deleted file mode 100644 index 19404b6f7778..000000000000 --- a/drivers/switch/Kconfig +++ /dev/null @@ -1,15 +0,0 @@ -menuconfig SWITCH - tristate "Switch class support" - help - Say Y here to enable switch class support. This allows - monitoring switches by userspace via sysfs and uevent. - -if SWITCH - -config SWITCH_GPIO - tristate "GPIO Swith support" - depends on GPIOLIB - help - Say Y here to enable GPIO based switch support. - -endif # SWITCH diff --git a/drivers/switch/Makefile b/drivers/switch/Makefile deleted file mode 100644 index f7606ed4a719..000000000000 --- a/drivers/switch/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -# Switch Class Driver -obj-$(CONFIG_SWITCH) += switch_class.o -obj-$(CONFIG_SWITCH_GPIO) += switch_gpio.o - diff --git a/drivers/switch/switch_class.c b/drivers/switch/switch_class.c deleted file mode 100644 index e373b625806e..000000000000 --- a/drivers/switch/switch_class.c +++ /dev/null @@ -1,174 +0,0 @@ -/* - * drivers/switch/switch_class.c - * - * Copyright (C) 2008 Google, Inc. - * Author: Mike Lockwood <lockwood@android.com> - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * -*/ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/device.h> -#include <linux/fs.h> -#include <linux/err.h> -#include <linux/switch.h> - -struct class *switch_class; -static atomic_t device_count; - -static ssize_t state_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct switch_dev *sdev = (struct switch_dev *) - dev_get_drvdata(dev); - - if (sdev->print_state) { - int ret = sdev->print_state(sdev, buf); - if (ret >= 0) - return ret; - } - return sprintf(buf, "%d\n", sdev->state); -} - -static ssize_t name_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct switch_dev *sdev = (struct switch_dev *) - dev_get_drvdata(dev); - - if (sdev->print_name) { - int ret = sdev->print_name(sdev, buf); - if (ret >= 0) - return ret; - } - return sprintf(buf, "%s\n", sdev->name); -} - -static DEVICE_ATTR(state, S_IRUGO, state_show, NULL); -static DEVICE_ATTR(name, S_IRUGO, name_show, NULL); - -void switch_set_state(struct switch_dev *sdev, int state) -{ - char name_buf[120]; - char state_buf[120]; - char *prop_buf; - char *envp[3]; - int env_offset = 0; - int length; - - if (sdev->state != state) { - sdev->state = state; - - prop_buf = (char *)get_zeroed_page(GFP_KERNEL); - if (prop_buf) { - length = name_show(sdev->dev, NULL, prop_buf); - if (length > 0) { - if (prop_buf[length - 1] == '\n') - prop_buf[length - 1] = 0; - snprintf(name_buf, sizeof(name_buf), - "SWITCH_NAME=%s", prop_buf); - envp[env_offset++] = name_buf; - } - length = state_show(sdev->dev, NULL, prop_buf); - if (length > 0) { - if (prop_buf[length - 1] == '\n') - prop_buf[length - 1] = 0; - snprintf(state_buf, sizeof(state_buf), - "SWITCH_STATE=%s", prop_buf); - envp[env_offset++] = state_buf; - } - envp[env_offset] = NULL; - kobject_uevent_env(&sdev->dev->kobj, KOBJ_CHANGE, envp); - free_page((unsigned long)prop_buf); - } else { - printk(KERN_ERR "out of memory in switch_set_state\n"); - kobject_uevent(&sdev->dev->kobj, KOBJ_CHANGE); - } - } -} -EXPORT_SYMBOL_GPL(switch_set_state); - -static int create_switch_class(void) -{ - if (!switch_class) { - switch_class = class_create(THIS_MODULE, "switch"); - if (IS_ERR(switch_class)) - return PTR_ERR(switch_class); - atomic_set(&device_count, 0); - } - - return 0; -} - -int switch_dev_register(struct switch_dev *sdev) -{ - int ret; - - if (!switch_class) { - ret = create_switch_class(); - if (ret < 0) - return ret; - } - - sdev->index = atomic_inc_return(&device_count); - sdev->dev = device_create(switch_class, NULL, - MKDEV(0, sdev->index), NULL, sdev->name); - if (IS_ERR(sdev->dev)) - return PTR_ERR(sdev->dev); - - ret = device_create_file(sdev->dev, &dev_attr_state); - if (ret < 0) - goto err_create_file_1; - ret = device_create_file(sdev->dev, &dev_attr_name); - if (ret < 0) - goto err_create_file_2; - - dev_set_drvdata(sdev->dev, sdev); - sdev->state = 0; - return 0; - -err_create_file_2: - device_remove_file(sdev->dev, &dev_attr_state); -err_create_file_1: - device_destroy(switch_class, MKDEV(0, sdev->index)); - printk(KERN_ERR "switch: Failed to register driver %s\n", sdev->name); - - return ret; -} -EXPORT_SYMBOL_GPL(switch_dev_register); - -void switch_dev_unregister(struct switch_dev *sdev) -{ - device_remove_file(sdev->dev, &dev_attr_name); - device_remove_file(sdev->dev, &dev_attr_state); - device_destroy(switch_class, MKDEV(0, sdev->index)); - dev_set_drvdata(sdev->dev, NULL); -} -EXPORT_SYMBOL_GPL(switch_dev_unregister); - -static int __init switch_class_init(void) -{ - return create_switch_class(); -} - -static void __exit switch_class_exit(void) -{ - class_destroy(switch_class); -} - -module_init(switch_class_init); -module_exit(switch_class_exit); - -MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>"); -MODULE_DESCRIPTION("Switch class driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/switch/switch_gpio.c b/drivers/switch/switch_gpio.c deleted file mode 100644 index 621d62d20c99..000000000000 --- a/drivers/switch/switch_gpio.c +++ /dev/null @@ -1,172 +0,0 @@ -/* - * drivers/switch/switch_gpio.c - * - * Copyright (C) 2008 Google, Inc. - * Author: Mike Lockwood <lockwood@android.com> - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * -*/ - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/platform_device.h> -#include <linux/slab.h> -#include <linux/switch.h> -#include <linux/workqueue.h> -#include <linux/gpio.h> - -struct gpio_switch_data { - struct switch_dev sdev; - unsigned gpio; - const char *name_on; - const char *name_off; - const char *state_on; - const char *state_off; - int irq; - struct work_struct work; -}; - -static void gpio_switch_work(struct work_struct *work) -{ - int state; - struct gpio_switch_data *data = - container_of(work, struct gpio_switch_data, work); - - state = gpio_get_value(data->gpio); - switch_set_state(&data->sdev, state); -} - -static irqreturn_t gpio_irq_handler(int irq, void *dev_id) -{ - struct gpio_switch_data *switch_data = - (struct gpio_switch_data *)dev_id; - - schedule_work(&switch_data->work); - return IRQ_HANDLED; -} - -static ssize_t switch_gpio_print_state(struct switch_dev *sdev, char *buf) -{ - struct gpio_switch_data *switch_data = - container_of(sdev, struct gpio_switch_data, sdev); - const char *state; - if (switch_get_state(sdev)) - state = switch_data->state_on; - else - state = switch_data->state_off; - - if (state) - return sprintf(buf, "%s\n", state); - return -1; -} - -static int gpio_switch_probe(struct platform_device *pdev) -{ - struct gpio_switch_platform_data *pdata = pdev->dev.platform_data; - struct gpio_switch_data *switch_data; - int ret = 0; - - if (!pdata) - return -EBUSY; - - switch_data = kzalloc(sizeof(struct gpio_switch_data), GFP_KERNEL); - if (!switch_data) - return -ENOMEM; - - switch_data->sdev.name = pdata->name; - switch_data->gpio = pdata->gpio; - switch_data->name_on = pdata->name_on; - switch_data->name_off = pdata->name_off; - switch_data->state_on = pdata->state_on; - switch_data->state_off = pdata->state_off; - switch_data->sdev.print_state = switch_gpio_print_state; - - ret = switch_dev_register(&switch_data->sdev); - if (ret < 0) - goto err_switch_dev_register; - - ret = gpio_request(switch_data->gpio, pdev->name); - if (ret < 0) - goto err_request_gpio; - - ret = gpio_direction_input(switch_data->gpio); - if (ret < 0) - goto err_set_gpio_input; - - INIT_WORK(&switch_data->work, gpio_switch_work); - - switch_data->irq = gpio_to_irq(switch_data->gpio); - if (switch_data->irq < 0) { - ret = switch_data->irq; - goto err_detect_irq_num_failed; - } - - ret = request_irq(switch_data->irq, gpio_irq_handler, - IRQF_TRIGGER_LOW, pdev->name, switch_data); - if (ret < 0) - goto err_request_irq; - - /* Perform initial detection */ - gpio_switch_work(&switch_data->work); - - return 0; - -err_request_irq: -err_detect_irq_num_failed: -err_set_gpio_input: - gpio_free(switch_data->gpio); -err_request_gpio: - switch_dev_unregister(&switch_data->sdev); -err_switch_dev_register: - kfree(switch_data); - - return ret; -} - -static int gpio_switch_remove(struct platform_device *pdev) -{ - struct gpio_switch_data *switch_data = platform_get_drvdata(pdev); - - cancel_work_sync(&switch_data->work); - gpio_free(switch_data->gpio); - switch_dev_unregister(&switch_data->sdev); - kfree(switch_data); - - return 0; -} - -static struct platform_driver gpio_switch_driver = { - .probe = gpio_switch_probe, - .remove = gpio_switch_remove, - .driver = { - .name = "switch-gpio", - .owner = THIS_MODULE, - }, -}; - -static int __init gpio_switch_init(void) -{ - return platform_driver_register(&gpio_switch_driver); -} - -static void __exit gpio_switch_exit(void) -{ - platform_driver_unregister(&gpio_switch_driver); -} - -module_init(gpio_switch_init); -module_exit(gpio_switch_exit); - -MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>"); -MODULE_DESCRIPTION("GPIO Switch driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 255204cc43e6..b4bfd706ac94 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1593,7 +1593,8 @@ static int lio_tpg_check_prot_fabric_only( } /* - * Called with spin_lock_bh(struct se_portal_group->session_lock) held.. + * Called with spin_lock_irq(struct se_portal_group->session_lock) held + * or not held. * * Also, this function calls iscsit_inc_session_usage_count() on the * struct iscsi_session in question. @@ -1601,19 +1602,32 @@ static int lio_tpg_check_prot_fabric_only( static int lio_tpg_shutdown_session(struct se_session *se_sess) { struct iscsi_session *sess = se_sess->fabric_sess_ptr; + struct se_portal_group *se_tpg = se_sess->se_tpg; + bool local_lock = false; + + if (!spin_is_locked(&se_tpg->session_lock)) { + spin_lock_irq(&se_tpg->session_lock); + local_lock = true; + } spin_lock(&sess->conn_lock); if (atomic_read(&sess->session_fall_back_to_erl0) || atomic_read(&sess->session_logout) || (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) { spin_unlock(&sess->conn_lock); + if (local_lock) + spin_unlock_irq(&sess->conn_lock); return 0; } atomic_set(&sess->session_reinstatement, 1); spin_unlock(&sess->conn_lock); iscsit_stop_time2retain_timer(sess); + spin_unlock_irq(&se_tpg->session_lock); + iscsit_stop_session(sess, 1, 1); + if (!local_lock) + spin_lock_irq(&se_tpg->session_lock); return 1; } diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 88ea4e4f124b..3436a83568ea 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -826,6 +826,49 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) return dev; } +/* + * Check if the underlying struct block_device request_queue supports + * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM + * in ATA and we need to set TPE=1 + */ +bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, + struct request_queue *q, int block_size) +{ + if (!blk_queue_discard(q)) + return false; + + attrib->max_unmap_lba_count = (q->limits.max_discard_sectors << 9) / + block_size; + /* + * Currently hardcoded to 1 in Linux/SCSI code.. + */ + attrib->max_unmap_block_desc_count = 1; + attrib->unmap_granularity = q->limits.discard_granularity / block_size; + attrib->unmap_granularity_alignment = q->limits.discard_alignment / + block_size; + return true; +} +EXPORT_SYMBOL(target_configure_unmap_from_queue); + +/* + * Convert from blocksize advertised to the initiator to the 512 byte + * units unconditionally used by the Linux block layer. + */ +sector_t target_to_linux_sector(struct se_device *dev, sector_t lb) +{ + switch (dev->dev_attrib.block_size) { + case 4096: + return lb << 3; + case 2048: + return lb << 2; + case 1024: + return lb << 1; + default: + return lb; + } +} +EXPORT_SYMBOL(target_to_linux_sector); + int target_configure_device(struct se_device *dev) { struct se_hba *hba = dev->se_hba; diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index e3195700211a..75f0f08b2a34 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -160,25 +160,11 @@ static int fd_configure_device(struct se_device *dev) " block_device blocks: %llu logical_block_size: %d\n", dev_size, div_u64(dev_size, fd_dev->fd_block_size), fd_dev->fd_block_size); - /* - * Check if the underlying struct block_device request_queue supports - * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM - * in ATA and we need to set TPE=1 - */ - if (blk_queue_discard(q)) { - dev->dev_attrib.max_unmap_lba_count = - q->limits.max_discard_sectors; - /* - * Currently hardcoded to 1 in Linux/SCSI code.. - */ - dev->dev_attrib.max_unmap_block_desc_count = 1; - dev->dev_attrib.unmap_granularity = - q->limits.discard_granularity >> 9; - dev->dev_attrib.unmap_granularity_alignment = - q->limits.discard_alignment; + + if (target_configure_unmap_from_queue(&dev->dev_attrib, q, + fd_dev->fd_block_size)) pr_debug("IFILE: BLOCK Discard support available," - " disabled by default\n"); - } + " disabled by default\n"); /* * Enable write same emulation for IBLOCK and use 0xFFFF as * the smaller WRITE_SAME(10) only has a two-byte block count. @@ -490,9 +476,12 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) if (S_ISBLK(inode->i_mode)) { /* The backend is block device, use discard */ struct block_device *bdev = inode->i_bdev; + struct se_device *dev = cmd->se_dev; - ret = blkdev_issue_discard(bdev, lba, - nolb, GFP_KERNEL, 0); + ret = blkdev_issue_discard(bdev, + target_to_linux_sector(dev, lba), + target_to_linux_sector(dev, nolb), + GFP_KERNEL, 0); if (ret < 0) { pr_warn("FILEIO: blkdev_issue_discard() failed: %d\n", ret); diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index f29c69120054..2c53dcefff3e 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -121,27 +121,11 @@ static int iblock_configure_device(struct se_device *dev) dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q); dev->dev_attrib.hw_queue_depth = q->nr_requests; - /* - * Check if the underlying struct block_device request_queue supports - * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM - * in ATA and we need to set TPE=1 - */ - if (blk_queue_discard(q)) { - dev->dev_attrib.max_unmap_lba_count = - q->limits.max_discard_sectors; - - /* - * Currently hardcoded to 1 in Linux/SCSI code.. - */ - dev->dev_attrib.max_unmap_block_desc_count = 1; - dev->dev_attrib.unmap_granularity = - q->limits.discard_granularity >> 9; - dev->dev_attrib.unmap_granularity_alignment = - q->limits.discard_alignment; - + if (target_configure_unmap_from_queue(&dev->dev_attrib, q, + dev->dev_attrib.hw_block_size)) pr_debug("IBLOCK: BLOCK Discard support available," - " disabled by default\n"); - } + " disabled by default\n"); + /* * Enable write same emulation for IBLOCK and use 0xFFFF as * the smaller WRITE_SAME(10) only has a two-byte block count. @@ -413,9 +397,13 @@ static sense_reason_t iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) { struct block_device *bdev = IBLOCK_DEV(cmd->se_dev)->ibd_bd; + struct se_device *dev = cmd->se_dev; int ret; - ret = blkdev_issue_discard(bdev, lba, nolb, GFP_KERNEL, 0); + ret = blkdev_issue_discard(bdev, + target_to_linux_sector(dev, lba), + target_to_linux_sector(dev, nolb), + GFP_KERNEL, 0); if (ret < 0) { pr_err("blkdev_issue_discard() failed: %d\n", ret); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; @@ -431,8 +419,10 @@ iblock_execute_write_same(struct se_cmd *cmd) struct scatterlist *sg; struct bio *bio; struct bio_list list; - sector_t block_lba = cmd->t_task_lba; - sector_t sectors = sbc_get_write_same_sectors(cmd); + struct se_device *dev = cmd->se_dev; + sector_t block_lba = target_to_linux_sector(dev, cmd->t_task_lba); + sector_t sectors = target_to_linux_sector(dev, + sbc_get_write_same_sectors(cmd)); if (cmd->prot_op) { pr_err("WRITE_SAME: Protection information with IBLOCK" @@ -646,12 +636,12 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, enum dma_data_direction data_direction) { struct se_device *dev = cmd->se_dev; + sector_t block_lba = target_to_linux_sector(dev, cmd->t_task_lba); struct iblock_req *ibr; struct bio *bio, *bio_start; struct bio_list list; struct scatterlist *sg; u32 sg_num = sgl_nents; - sector_t block_lba; unsigned bio_cnt; int rw = 0; int i; @@ -677,24 +667,6 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, rw = READ; } - /* - * Convert the blocksize advertised to the initiator to the 512 byte - * units unconditionally used by the Linux block layer. - */ - if (dev->dev_attrib.block_size == 4096) - block_lba = (cmd->t_task_lba << 3); - else if (dev->dev_attrib.block_size == 2048) - block_lba = (cmd->t_task_lba << 2); - else if (dev->dev_attrib.block_size == 1024) - block_lba = (cmd->t_task_lba << 1); - else if (dev->dev_attrib.block_size == 512) - block_lba = cmd->t_task_lba; - else { - pr_err("Unsupported SCSI -> BLOCK LBA conversion:" - " %u\n", dev->dev_attrib.block_size); - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - } - ibr = kzalloc(sizeof(struct iblock_req), GFP_KERNEL); if (!ibr) goto fail; diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 28fb3016370f..46b1991fbb50 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -68,23 +68,25 @@ void core_tmr_release_req(struct se_tmr_req *tmr) if (dev) { spin_lock_irqsave(&dev->se_tmr_lock, flags); - list_del(&tmr->tmr_list); + list_del_init(&tmr->tmr_list); spin_unlock_irqrestore(&dev->se_tmr_lock, flags); } kfree(tmr); } -static void core_tmr_handle_tas_abort( - struct se_node_acl *tmr_nacl, - struct se_cmd *cmd, - int tas) +static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas) { - bool remove = true; + unsigned long flags; + bool remove = true, send_tas; /* * TASK ABORTED status (TAS) bit support */ - if ((tmr_nacl && (tmr_nacl != cmd->se_sess->se_node_acl)) && tas) { + spin_lock_irqsave(&cmd->t_state_lock, flags); + send_tas = (cmd->transport_state & CMD_T_TAS); + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + + if (send_tas) { remove = false; transport_send_task_abort(cmd); } @@ -107,6 +109,46 @@ static int target_check_cdb_and_preempt(struct list_head *list, return 1; } +static bool __target_check_io_state(struct se_cmd *se_cmd, + struct se_session *tmr_sess, int tas) +{ + struct se_session *sess = se_cmd->se_sess; + + assert_spin_locked(&sess->sess_cmd_lock); + WARN_ON_ONCE(!irqs_disabled()); + /* + * If command already reached CMD_T_COMPLETE state within + * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown, + * this se_cmd has been passed to fabric driver and will + * not be aborted. + * + * Otherwise, obtain a local se_cmd->cmd_kref now for TMR + * ABORT_TASK + LUN_RESET for CMD_T_ABORTED processing as + * long as se_cmd->cmd_kref is still active unless zero. + */ + spin_lock(&se_cmd->t_state_lock); + if (se_cmd->transport_state & (CMD_T_COMPLETE | CMD_T_FABRIC_STOP)) { + pr_debug("Attempted to abort io tag: %llu already complete or" + " fabric stop, skipping\n", se_cmd->tag); + spin_unlock(&se_cmd->t_state_lock); + return false; + } + if (sess->sess_tearing_down || se_cmd->cmd_wait_set) { + pr_debug("Attempted to abort io tag: %llu already shutdown," + " skipping\n", se_cmd->tag); + spin_unlock(&se_cmd->t_state_lock); + return false; + } + se_cmd->transport_state |= CMD_T_ABORTED; + + if ((tmr_sess != se_cmd->se_sess) && tas) + se_cmd->transport_state |= CMD_T_TAS; + + spin_unlock(&se_cmd->t_state_lock); + + return kref_get_unless_zero(&se_cmd->cmd_kref); +} + void core_tmr_abort_task( struct se_device *dev, struct se_tmr_req *tmr, @@ -130,34 +172,21 @@ void core_tmr_abort_task( if (tmr->ref_task_tag != ref_tag) continue; - if (!kref_get_unless_zero(&se_cmd->cmd_kref)) - continue; - printk("ABORT_TASK: Found referenced %s task_tag: %llu\n", se_cmd->se_tfo->get_fabric_name(), ref_tag); - spin_lock(&se_cmd->t_state_lock); - if (se_cmd->transport_state & CMD_T_COMPLETE) { - printk("ABORT_TASK: ref_tag: %llu already complete," - " skipping\n", ref_tag); - spin_unlock(&se_cmd->t_state_lock); + if (!__target_check_io_state(se_cmd, se_sess, 0)) { spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); - - target_put_sess_cmd(se_cmd); - goto out; } - se_cmd->transport_state |= CMD_T_ABORTED; - spin_unlock(&se_cmd->t_state_lock); - list_del_init(&se_cmd->se_cmd_list); spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); cancel_work_sync(&se_cmd->work); transport_wait_for_tasks(se_cmd); - target_put_sess_cmd(se_cmd); transport_cmd_finish_abort(se_cmd, true); + target_put_sess_cmd(se_cmd); printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for" " ref_tag: %llu\n", ref_tag); @@ -178,9 +207,11 @@ static void core_tmr_drain_tmr_list( struct list_head *preempt_and_abort_list) { LIST_HEAD(drain_tmr_list); + struct se_session *sess; struct se_tmr_req *tmr_p, *tmr_pp; struct se_cmd *cmd; unsigned long flags; + bool rc; /* * Release all pending and outgoing TMRs aside from the received * LUN_RESET tmr.. @@ -206,17 +237,39 @@ static void core_tmr_drain_tmr_list( if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd)) continue; + sess = cmd->se_sess; + if (WARN_ON_ONCE(!sess)) + continue; + + spin_lock(&sess->sess_cmd_lock); spin_lock(&cmd->t_state_lock); - if (!(cmd->transport_state & CMD_T_ACTIVE)) { + if (!(cmd->transport_state & CMD_T_ACTIVE) || + (cmd->transport_state & CMD_T_FABRIC_STOP)) { spin_unlock(&cmd->t_state_lock); + spin_unlock(&sess->sess_cmd_lock); continue; } if (cmd->t_state == TRANSPORT_ISTATE_PROCESSING) { spin_unlock(&cmd->t_state_lock); + spin_unlock(&sess->sess_cmd_lock); continue; } + if (sess->sess_tearing_down || cmd->cmd_wait_set) { + spin_unlock(&cmd->t_state_lock); + spin_unlock(&sess->sess_cmd_lock); + continue; + } + cmd->transport_state |= CMD_T_ABORTED; spin_unlock(&cmd->t_state_lock); + rc = kref_get_unless_zero(&cmd->cmd_kref); + if (!rc) { + printk("LUN_RESET TMR: non-zero kref_get_unless_zero\n"); + spin_unlock(&sess->sess_cmd_lock); + continue; + } + spin_unlock(&sess->sess_cmd_lock); + list_move_tail(&tmr_p->tmr_list, &drain_tmr_list); } spin_unlock_irqrestore(&dev->se_tmr_lock, flags); @@ -230,20 +283,26 @@ static void core_tmr_drain_tmr_list( (preempt_and_abort_list) ? "Preempt" : "", tmr_p, tmr_p->function, tmr_p->response, cmd->t_state); + cancel_work_sync(&cmd->work); + transport_wait_for_tasks(cmd); + transport_cmd_finish_abort(cmd, 1); + target_put_sess_cmd(cmd); } } static void core_tmr_drain_state_list( struct se_device *dev, struct se_cmd *prout_cmd, - struct se_node_acl *tmr_nacl, + struct se_session *tmr_sess, int tas, struct list_head *preempt_and_abort_list) { LIST_HEAD(drain_task_list); + struct se_session *sess; struct se_cmd *cmd, *next; unsigned long flags; + int rc; /* * Complete outstanding commands with TASK_ABORTED SAM status. @@ -282,6 +341,16 @@ static void core_tmr_drain_state_list( if (prout_cmd == cmd) continue; + sess = cmd->se_sess; + if (WARN_ON_ONCE(!sess)) + continue; + + spin_lock(&sess->sess_cmd_lock); + rc = __target_check_io_state(cmd, tmr_sess, tas); + spin_unlock(&sess->sess_cmd_lock); + if (!rc) + continue; + list_move_tail(&cmd->state_list, &drain_task_list); cmd->state_active = false; } @@ -289,7 +358,7 @@ static void core_tmr_drain_state_list( while (!list_empty(&drain_task_list)) { cmd = list_entry(drain_task_list.next, struct se_cmd, state_list); - list_del(&cmd->state_list); + list_del_init(&cmd->state_list); pr_debug("LUN_RESET: %s cmd: %p" " ITT/CmdSN: 0x%08llx/0x%08x, i_state: %d, t_state: %d" @@ -313,16 +382,11 @@ static void core_tmr_drain_state_list( * loop above, but we do it down here given that * cancel_work_sync may block. */ - if (cmd->t_state == TRANSPORT_COMPLETE) - cancel_work_sync(&cmd->work); - - spin_lock_irqsave(&cmd->t_state_lock, flags); - target_stop_cmd(cmd, &flags); - - cmd->transport_state |= CMD_T_ABORTED; - spin_unlock_irqrestore(&cmd->t_state_lock, flags); + cancel_work_sync(&cmd->work); + transport_wait_for_tasks(cmd); - core_tmr_handle_tas_abort(tmr_nacl, cmd, tas); + core_tmr_handle_tas_abort(cmd, tas); + target_put_sess_cmd(cmd); } } @@ -334,6 +398,7 @@ int core_tmr_lun_reset( { struct se_node_acl *tmr_nacl = NULL; struct se_portal_group *tmr_tpg = NULL; + struct se_session *tmr_sess = NULL; int tas; /* * TASK_ABORTED status bit, this is configurable via ConfigFS @@ -352,8 +417,9 @@ int core_tmr_lun_reset( * or struct se_device passthrough.. */ if (tmr && tmr->task_cmd && tmr->task_cmd->se_sess) { - tmr_nacl = tmr->task_cmd->se_sess->se_node_acl; - tmr_tpg = tmr->task_cmd->se_sess->se_tpg; + tmr_sess = tmr->task_cmd->se_sess; + tmr_nacl = tmr_sess->se_node_acl; + tmr_tpg = tmr_sess->se_tpg; if (tmr_nacl && tmr_tpg) { pr_debug("LUN_RESET: TMR caller fabric: %s" " initiator port %s\n", @@ -366,7 +432,7 @@ int core_tmr_lun_reset( dev->transport->name, tas); core_tmr_drain_tmr_list(dev, tmr, preempt_and_abort_list); - core_tmr_drain_state_list(dev, prout_cmd, tmr_nacl, tas, + core_tmr_drain_state_list(dev, prout_cmd, tmr_sess, tas, preempt_and_abort_list); /* diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 4fdcee2006d1..d151bc3d6971 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -528,9 +528,6 @@ void transport_deregister_session(struct se_session *se_sess) } EXPORT_SYMBOL(transport_deregister_session); -/* - * Called with cmd->t_state_lock held. - */ static void target_remove_from_state_list(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -555,10 +552,6 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists, { unsigned long flags; - spin_lock_irqsave(&cmd->t_state_lock, flags); - if (write_pending) - cmd->t_state = TRANSPORT_WRITE_PENDING; - if (remove_from_lists) { target_remove_from_state_list(cmd); @@ -568,6 +561,10 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists, cmd->se_lun = NULL; } + spin_lock_irqsave(&cmd->t_state_lock, flags); + if (write_pending) + cmd->t_state = TRANSPORT_WRITE_PENDING; + /* * Determine if frontend context caller is requesting the stopping of * this command for frontend exceptions. @@ -621,6 +618,8 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd) void transport_cmd_finish_abort(struct se_cmd *cmd, int remove) { + bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF); + if (cmd->se_cmd_flags & SCF_SE_LUN_CMD) transport_lun_remove_cmd(cmd); /* @@ -632,7 +631,7 @@ void transport_cmd_finish_abort(struct se_cmd *cmd, int remove) if (transport_cmd_check_stop_to_fabric(cmd)) return; - if (remove) + if (remove && ack_kref) transport_put_cmd(cmd); } @@ -700,7 +699,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) * Check for case where an explicit ABORT_TASK has been received * and transport_wait_for_tasks() will be waiting for completion.. */ - if (cmd->transport_state & CMD_T_ABORTED && + if (cmd->transport_state & CMD_T_ABORTED || cmd->transport_state & CMD_T_STOP) { spin_unlock_irqrestore(&cmd->t_state_lock, flags); complete_all(&cmd->t_transport_stop_comp); @@ -1850,19 +1849,21 @@ static bool target_handle_task_attr(struct se_cmd *cmd) return true; } +static int __transport_check_aborted_status(struct se_cmd *, int); + void target_execute_cmd(struct se_cmd *cmd) { /* - * If the received CDB has aleady been aborted stop processing it here. - */ - if (transport_check_aborted_status(cmd, 1)) - return; - - /* * Determine if frontend context caller is requesting the stopping of * this command for frontend exceptions. + * + * If the received CDB has aleady been aborted stop processing it here. */ spin_lock_irq(&cmd->t_state_lock); + if (__transport_check_aborted_status(cmd, 1)) { + spin_unlock_irq(&cmd->t_state_lock); + return; + } if (cmd->transport_state & CMD_T_STOP) { pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08llx\n", __func__, __LINE__, cmd->tag); @@ -2213,20 +2214,14 @@ static inline void transport_free_pages(struct se_cmd *cmd) } /** - * transport_release_cmd - free a command - * @cmd: command to free + * transport_put_cmd - release a reference to a command + * @cmd: command to release * - * This routine unconditionally frees a command, and reference counting - * or list removal must be done in the caller. + * This routine releases our reference to the command and frees it if possible. */ -static int transport_release_cmd(struct se_cmd *cmd) +static int transport_put_cmd(struct se_cmd *cmd) { BUG_ON(!cmd->se_tfo); - - if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) - core_tmr_release_req(cmd->se_tmr_req); - if (cmd->t_task_cdb != cmd->__t_task_cdb) - kfree(cmd->t_task_cdb); /* * If this cmd has been setup with target_get_sess_cmd(), drop * the kref and call ->release_cmd() in kref callback. @@ -2234,18 +2229,6 @@ static int transport_release_cmd(struct se_cmd *cmd) return target_put_sess_cmd(cmd); } -/** - * transport_put_cmd - release a reference to a command - * @cmd: command to release - * - * This routine releases our reference to the command and frees it if possible. - */ -static int transport_put_cmd(struct se_cmd *cmd) -{ - transport_free_pages(cmd); - return transport_release_cmd(cmd); -} - void *transport_kmap_data_sg(struct se_cmd *cmd) { struct scatterlist *sg = cmd->t_data_sg; @@ -2441,34 +2424,58 @@ static void transport_write_pending_qf(struct se_cmd *cmd) } } -int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) +static bool +__transport_wait_for_tasks(struct se_cmd *, bool, bool *, bool *, + unsigned long *flags); + +static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas) { unsigned long flags; + + spin_lock_irqsave(&cmd->t_state_lock, flags); + __transport_wait_for_tasks(cmd, true, aborted, tas, &flags); + spin_unlock_irqrestore(&cmd->t_state_lock, flags); +} + +int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) +{ int ret = 0; + bool aborted = false, tas = false; if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) { if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) - transport_wait_for_tasks(cmd); + target_wait_free_cmd(cmd, &aborted, &tas); - ret = transport_release_cmd(cmd); + if (!aborted || tas) + ret = transport_put_cmd(cmd); } else { if (wait_for_tasks) - transport_wait_for_tasks(cmd); + target_wait_free_cmd(cmd, &aborted, &tas); /* * Handle WRITE failure case where transport_generic_new_cmd() * has already added se_cmd to state_list, but fabric has * failed command before I/O submission. */ - if (cmd->state_active) { - spin_lock_irqsave(&cmd->t_state_lock, flags); + if (cmd->state_active) target_remove_from_state_list(cmd); - spin_unlock_irqrestore(&cmd->t_state_lock, flags); - } if (cmd->se_lun) transport_lun_remove_cmd(cmd); - ret = transport_put_cmd(cmd); + if (!aborted || tas) + ret = transport_put_cmd(cmd); + } + /* + * If the task has been internally aborted due to TMR ABORT_TASK + * or LUN_RESET, target_core_tmr.c is responsible for performing + * the remaining calls to target_put_sess_cmd(), and not the + * callers of this function. + */ + if (aborted) { + pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag); + wait_for_completion(&cmd->cmd_wait_comp); + cmd->se_tfo->release_cmd(cmd); + ret = 1; } return ret; } @@ -2508,26 +2515,46 @@ out: } EXPORT_SYMBOL(target_get_sess_cmd); +static void target_free_cmd_mem(struct se_cmd *cmd) +{ + transport_free_pages(cmd); + + if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) + core_tmr_release_req(cmd->se_tmr_req); + if (cmd->t_task_cdb != cmd->__t_task_cdb) + kfree(cmd->t_task_cdb); +} + static void target_release_cmd_kref(struct kref *kref) { struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref); struct se_session *se_sess = se_cmd->se_sess; unsigned long flags; + bool fabric_stop; spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); if (list_empty(&se_cmd->se_cmd_list)) { spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + target_free_cmd_mem(se_cmd); se_cmd->se_tfo->release_cmd(se_cmd); return; } - if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) { + + spin_lock(&se_cmd->t_state_lock); + fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP); + spin_unlock(&se_cmd->t_state_lock); + + if (se_cmd->cmd_wait_set || fabric_stop) { + list_del_init(&se_cmd->se_cmd_list); spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + target_free_cmd_mem(se_cmd); complete(&se_cmd->cmd_wait_comp); return; } - list_del(&se_cmd->se_cmd_list); + list_del_init(&se_cmd->se_cmd_list); spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + target_free_cmd_mem(se_cmd); se_cmd->se_tfo->release_cmd(se_cmd); } @@ -2539,6 +2566,7 @@ int target_put_sess_cmd(struct se_cmd *se_cmd) struct se_session *se_sess = se_cmd->se_sess; if (!se_sess) { + target_free_cmd_mem(se_cmd); se_cmd->se_tfo->release_cmd(se_cmd); return 1; } @@ -2555,6 +2583,7 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess) { struct se_cmd *se_cmd; unsigned long flags; + int rc; spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); if (se_sess->sess_tearing_down) { @@ -2564,8 +2593,15 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess) se_sess->sess_tearing_down = 1; list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list); - list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) - se_cmd->cmd_wait_set = 1; + list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) { + rc = kref_get_unless_zero(&se_cmd->cmd_kref); + if (rc) { + se_cmd->cmd_wait_set = 1; + spin_lock(&se_cmd->t_state_lock); + se_cmd->transport_state |= CMD_T_FABRIC_STOP; + spin_unlock(&se_cmd->t_state_lock); + } + } spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); } @@ -2578,15 +2614,23 @@ void target_wait_for_sess_cmds(struct se_session *se_sess) { struct se_cmd *se_cmd, *tmp_cmd; unsigned long flags; + bool tas; list_for_each_entry_safe(se_cmd, tmp_cmd, &se_sess->sess_wait_list, se_cmd_list) { - list_del(&se_cmd->se_cmd_list); - pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:" " %d\n", se_cmd, se_cmd->t_state, se_cmd->se_tfo->get_cmd_state(se_cmd)); + spin_lock_irqsave(&se_cmd->t_state_lock, flags); + tas = (se_cmd->transport_state & CMD_T_TAS); + spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); + + if (!target_put_sess_cmd(se_cmd)) { + if (tas) + target_put_sess_cmd(se_cmd); + } + wait_for_completion(&se_cmd->cmd_wait_comp); pr_debug("After cmd_wait_comp: se_cmd: %p t_state: %d" " fabric state: %d\n", se_cmd, se_cmd->t_state, @@ -2608,53 +2652,75 @@ void transport_clear_lun_ref(struct se_lun *lun) wait_for_completion(&lun->lun_ref_comp); } -/** - * transport_wait_for_tasks - wait for completion to occur - * @cmd: command to wait - * - * Called from frontend fabric context to wait for storage engine - * to pause and/or release frontend generated struct se_cmd. - */ -bool transport_wait_for_tasks(struct se_cmd *cmd) +static bool +__transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop, + bool *aborted, bool *tas, unsigned long *flags) + __releases(&cmd->t_state_lock) + __acquires(&cmd->t_state_lock) { - unsigned long flags; - spin_lock_irqsave(&cmd->t_state_lock, flags); + assert_spin_locked(&cmd->t_state_lock); + WARN_ON_ONCE(!irqs_disabled()); + + if (fabric_stop) + cmd->transport_state |= CMD_T_FABRIC_STOP; + + if (cmd->transport_state & CMD_T_ABORTED) + *aborted = true; + + if (cmd->transport_state & CMD_T_TAS) + *tas = true; + if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD) && - !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) { - spin_unlock_irqrestore(&cmd->t_state_lock, flags); + !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) return false; - } if (!(cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) && - !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) { - spin_unlock_irqrestore(&cmd->t_state_lock, flags); + !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) return false; - } - if (!(cmd->transport_state & CMD_T_ACTIVE)) { - spin_unlock_irqrestore(&cmd->t_state_lock, flags); + if (!(cmd->transport_state & CMD_T_ACTIVE)) + return false; + + if (fabric_stop && *aborted) return false; - } cmd->transport_state |= CMD_T_STOP; - pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d, t_state: %d, CMD_T_STOP\n", - cmd, cmd->tag, cmd->se_tfo->get_cmd_state(cmd), cmd->t_state); + pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d," + " t_state: %d, CMD_T_STOP\n", cmd, cmd->tag, + cmd->se_tfo->get_cmd_state(cmd), cmd->t_state); - spin_unlock_irqrestore(&cmd->t_state_lock, flags); + spin_unlock_irqrestore(&cmd->t_state_lock, *flags); wait_for_completion(&cmd->t_transport_stop_comp); - spin_lock_irqsave(&cmd->t_state_lock, flags); + spin_lock_irqsave(&cmd->t_state_lock, *flags); cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP); - pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->t_transport_stop_comp) for ITT: 0x%08llx\n", - cmd->tag); + pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->" + "t_transport_stop_comp) for ITT: 0x%08llx\n", cmd->tag); + + return true; +} + +/** + * transport_wait_for_tasks - wait for completion to occur + * @cmd: command to wait + * + * Called from frontend fabric context to wait for storage engine + * to pause and/or release frontend generated struct se_cmd. + */ +bool transport_wait_for_tasks(struct se_cmd *cmd) +{ + unsigned long flags; + bool ret, aborted = false, tas = false; + spin_lock_irqsave(&cmd->t_state_lock, flags); + ret = __transport_wait_for_tasks(cmd, false, &aborted, &tas, &flags); spin_unlock_irqrestore(&cmd->t_state_lock, flags); - return true; + return ret; } EXPORT_SYMBOL(transport_wait_for_tasks); @@ -2836,28 +2902,49 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd, } EXPORT_SYMBOL(transport_send_check_condition_and_sense); -int transport_check_aborted_status(struct se_cmd *cmd, int send_status) +static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status) + __releases(&cmd->t_state_lock) + __acquires(&cmd->t_state_lock) { + assert_spin_locked(&cmd->t_state_lock); + WARN_ON_ONCE(!irqs_disabled()); + if (!(cmd->transport_state & CMD_T_ABORTED)) return 0; - /* * If cmd has been aborted but either no status is to be sent or it has * already been sent, just return */ - if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS)) + if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS)) { + if (send_status) + cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS; return 1; + } - pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB: 0x%02x ITT: 0x%08llx\n", - cmd->t_task_cdb[0], cmd->tag); + pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB:" + " 0x%02x ITT: 0x%08llx\n", cmd->t_task_cdb[0], cmd->tag); cmd->se_cmd_flags &= ~SCF_SEND_DELAYED_TAS; cmd->scsi_status = SAM_STAT_TASK_ABORTED; trace_target_cmd_complete(cmd); + + spin_unlock_irq(&cmd->t_state_lock); cmd->se_tfo->queue_status(cmd); + spin_lock_irq(&cmd->t_state_lock); return 1; } + +int transport_check_aborted_status(struct se_cmd *cmd, int send_status) +{ + int ret; + + spin_lock_irq(&cmd->t_state_lock); + ret = __transport_check_aborted_status(cmd, send_status); + spin_unlock_irq(&cmd->t_state_lock); + + return ret; +} EXPORT_SYMBOL(transport_check_aborted_status); void transport_send_task_abort(struct se_cmd *cmd) @@ -2879,11 +2966,17 @@ void transport_send_task_abort(struct se_cmd *cmd) */ if (cmd->data_direction == DMA_TO_DEVICE) { if (cmd->se_tfo->write_pending_status(cmd) != 0) { - cmd->transport_state |= CMD_T_ABORTED; + spin_lock_irqsave(&cmd->t_state_lock, flags); + if (cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS) { + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + goto send_abort; + } cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); return; } } +send_abort: cmd->scsi_status = SAM_STAT_TASK_ABORTED; transport_lun_remove_cmd(cmd); @@ -2900,8 +2993,17 @@ static void target_tmr_work(struct work_struct *work) struct se_cmd *cmd = container_of(work, struct se_cmd, work); struct se_device *dev = cmd->se_dev; struct se_tmr_req *tmr = cmd->se_tmr_req; + unsigned long flags; int ret; + spin_lock_irqsave(&cmd->t_state_lock, flags); + if (cmd->transport_state & CMD_T_ABORTED) { + tmr->response = TMR_FUNCTION_REJECTED; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + goto check_stop; + } + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + switch (tmr->function) { case TMR_ABORT_TASK: core_tmr_abort_task(dev, tmr, cmd->se_sess); @@ -2934,9 +3036,17 @@ static void target_tmr_work(struct work_struct *work) break; } + spin_lock_irqsave(&cmd->t_state_lock, flags); + if (cmd->transport_state & CMD_T_ABORTED) { + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + goto check_stop; + } cmd->t_state = TRANSPORT_ISTATE_PROCESSING; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + cmd->se_tfo->queue_tm_rsp(cmd); +check_stop: transport_cmd_check_stop_to_fabric(cmd); } diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index e3fbc5a5d88f..6ceac4f2d4b2 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -377,26 +377,28 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device, * get_load() - get load for a cpu since last updated * @cpufreq_device: &struct cpufreq_cooling_device for this cpu * @cpu: cpu number + * @cpu_idx: index of the cpu in cpufreq_device->allowed_cpus * * Return: The average load of cpu @cpu in percentage since this * function was last called. */ -static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu) +static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu, + int cpu_idx) { u32 load; u64 now, now_idle, delta_time, delta_idle; now_idle = get_cpu_idle_time(cpu, &now, 0); - delta_idle = now_idle - cpufreq_device->time_in_idle[cpu]; - delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu]; + delta_idle = now_idle - cpufreq_device->time_in_idle[cpu_idx]; + delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu_idx]; if (delta_time <= delta_idle) load = 0; else load = div64_u64(100 * (delta_time - delta_idle), delta_time); - cpufreq_device->time_in_idle[cpu] = now_idle; - cpufreq_device->time_in_idle_timestamp[cpu] = now; + cpufreq_device->time_in_idle[cpu_idx] = now_idle; + cpufreq_device->time_in_idle_timestamp[cpu_idx] = now; return load; } @@ -598,7 +600,7 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, u32 load; if (cpu_online(cpu)) - load = get_load(cpufreq_device, cpu); + load = get_load(cpufreq_device, cpu, i); else load = 0; diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c index e845841ab036..7106288efae3 100644 --- a/drivers/thermal/rockchip_thermal.c +++ b/drivers/thermal/rockchip_thermal.c @@ -545,15 +545,14 @@ static int rockchip_configure_from_dt(struct device *dev, thermal->chip->tshut_temp); thermal->tshut_temp = thermal->chip->tshut_temp; } else { + if (shut_temp > INT_MAX) { + dev_err(dev, "Invalid tshut temperature specified: %d\n", + shut_temp); + return -ERANGE; + } thermal->tshut_temp = shut_temp; } - if (thermal->tshut_temp > INT_MAX) { - dev_err(dev, "Invalid tshut temperature specified: %d\n", - thermal->tshut_temp); - return -ERANGE; - } - if (of_property_read_u32(np, "rockchip,hw-tshut-mode", &tshut_mode)) { dev_warn(dev, "Missing tshut mode property, using default (%s)\n", diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index 2f9f7086ac3d..ea9366ad3e6b 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -63,6 +63,19 @@ static unsigned long get_target_state(struct thermal_instance *instance, next_target = instance->target; dev_dbg(&cdev->device, "cur_state=%ld\n", cur_state); + if (!instance->initialized) { + if (throttle) { + next_target = (cur_state + 1) >= instance->upper ? + instance->upper : + ((cur_state + 1) < instance->lower ? + instance->lower : (cur_state + 1)); + } else { + next_target = THERMAL_NO_TARGET; + } + + return next_target; + } + switch (trend) { case THERMAL_TREND_RAISING: if (throttle) { @@ -149,7 +162,7 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) dev_dbg(&instance->cdev->device, "old_target=%d, target=%d\n", old_target, (int)instance->target); - if (old_target == instance->target) + if (instance->initialized && old_target == instance->target) continue; /* Activate a passive thermal instance */ @@ -161,7 +174,7 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) instance->target == THERMAL_NO_TARGET) update_passive_instance(tz, trip_type, -1); - + instance->initialized = true; instance->cdev->updated = false; /* cdev needs update */ } diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index d9e525cc9c1c..3d5f8f432b5b 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -37,6 +37,7 @@ #include <linux/of.h> #include <net/netlink.h> #include <net/genetlink.h> +#include <linux/suspend.h> #define CREATE_TRACE_POINTS #include <trace/events/thermal.h> @@ -59,6 +60,8 @@ static LIST_HEAD(thermal_governor_list); static DEFINE_MUTEX(thermal_list_lock); static DEFINE_MUTEX(thermal_governor_lock); +static atomic_t in_suspend; + static struct thermal_governor *def_governor; static struct thermal_governor *__find_governor(const char *name) @@ -451,6 +454,10 @@ static void handle_thermal_trip(struct thermal_zone_device *tz, int trip) { enum thermal_trip_type type; + /* Ignore disabled trip points */ + if (test_bit(trip, &tz->trips_disabled)) + return; + tz->ops->get_trip_type(tz, trip, &type); if (type == THERMAL_TRIP_CRITICAL || type == THERMAL_TRIP_HOT) @@ -532,14 +539,31 @@ static void update_temperature(struct thermal_zone_device *tz) mutex_unlock(&tz->lock); trace_thermal_temperature(tz); - dev_dbg(&tz->device, "last_temperature=%d, current_temperature=%d\n", - tz->last_temperature, tz->temperature); + if (tz->last_temperature == THERMAL_TEMP_INVALID) + dev_dbg(&tz->device, "last_temperature N/A, current_temperature=%d\n", + tz->temperature); + else + dev_dbg(&tz->device, "last_temperature=%d, current_temperature=%d\n", + tz->last_temperature, tz->temperature); +} + +static void thermal_zone_device_reset(struct thermal_zone_device *tz) +{ + struct thermal_instance *pos; + + tz->temperature = THERMAL_TEMP_INVALID; + tz->passive = 0; + list_for_each_entry(pos, &tz->thermal_instances, tz_node) + pos->initialized = false; } void thermal_zone_device_update(struct thermal_zone_device *tz) { int count; + if (atomic_read(&in_suspend)) + return; + if (!tz->ops->get_temp) return; @@ -1321,6 +1345,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, if (!result) { list_add_tail(&dev->tz_node, &tz->thermal_instances); list_add_tail(&dev->cdev_node, &cdev->thermal_instances); + atomic_set(&tz->need_update, 1); } mutex_unlock(&cdev->lock); mutex_unlock(&tz->lock); @@ -1430,6 +1455,7 @@ __thermal_cooling_device_register(struct device_node *np, const struct thermal_cooling_device_ops *ops) { struct thermal_cooling_device *cdev; + struct thermal_zone_device *pos = NULL; int result; if (type && strlen(type) >= THERMAL_NAME_LENGTH) @@ -1474,6 +1500,12 @@ __thermal_cooling_device_register(struct device_node *np, /* Update binding information for 'this' new cdev */ bind_cdev(cdev); + mutex_lock(&thermal_list_lock); + list_for_each_entry(pos, &thermal_tz_list, node) + if (atomic_cmpxchg(&pos->need_update, 1, 0)) + thermal_zone_device_update(pos); + mutex_unlock(&thermal_list_lock); + return cdev; } @@ -1768,6 +1800,7 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type, { struct thermal_zone_device *tz; enum thermal_trip_type trip_type; + int trip_temp; int result; int count; int passive = 0; @@ -1806,6 +1839,8 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type, tz->trips = trips; tz->passive_delay = passive_delay; tz->polling_delay = polling_delay; + /* A new thermal zone needs to be updated anyway. */ + atomic_set(&tz->need_update, 1); dev_set_name(&tz->device, "thermal_zone%d", tz->id); result = device_register(&tz->device); @@ -1837,9 +1872,15 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type, goto unregister; for (count = 0; count < trips; count++) { - tz->ops->get_trip_type(tz, count, &trip_type); + if (tz->ops->get_trip_type(tz, count, &trip_type)) + set_bit(count, &tz->trips_disabled); if (trip_type == THERMAL_TRIP_PASSIVE) passive = 1; + if (tz->ops->get_trip_temp(tz, count, &trip_temp)) + set_bit(count, &tz->trips_disabled); + /* Check for bogus trip points */ + if (trip_temp == 0) + set_bit(count, &tz->trips_disabled); } if (!passive) { @@ -1900,7 +1941,10 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type, INIT_DELAYED_WORK(&(tz->poll_queue), thermal_zone_device_check); - thermal_zone_device_update(tz); + thermal_zone_device_reset(tz); + /* Update the new thermal zone and mark it as already updated. */ + if (atomic_cmpxchg(&tz->need_update, 1, 0)) + thermal_zone_device_update(tz); return tz; @@ -2140,6 +2184,36 @@ static void thermal_unregister_governors(void) thermal_gov_power_allocator_unregister(); } +static int thermal_pm_notify(struct notifier_block *nb, + unsigned long mode, void *_unused) +{ + struct thermal_zone_device *tz; + + switch (mode) { + case PM_HIBERNATION_PREPARE: + case PM_RESTORE_PREPARE: + case PM_SUSPEND_PREPARE: + atomic_set(&in_suspend, 1); + break; + case PM_POST_HIBERNATION: + case PM_POST_RESTORE: + case PM_POST_SUSPEND: + atomic_set(&in_suspend, 0); + list_for_each_entry(tz, &thermal_tz_list, node) { + thermal_zone_device_reset(tz); + thermal_zone_device_update(tz); + } + break; + default: + break; + } + return 0; +} + +static struct notifier_block thermal_pm_nb = { + .notifier_call = thermal_pm_notify, +}; + static int __init thermal_init(void) { int result; @@ -2160,6 +2234,11 @@ static int __init thermal_init(void) if (result) goto exit_netlink; + result = register_pm_notifier(&thermal_pm_nb); + if (result) + pr_warn("Thermal: Can not register suspend notifier, return %d\n", + result); + return 0; exit_netlink: @@ -2179,6 +2258,7 @@ error: static void __exit thermal_exit(void) { + unregister_pm_notifier(&thermal_pm_nb); of_thermal_destroy_zones(); genetlink_exit(); class_unregister(&thermal_class); diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h index d7ac1fccd659..749d41abfbab 100644 --- a/drivers/thermal/thermal_core.h +++ b/drivers/thermal/thermal_core.h @@ -41,6 +41,7 @@ struct thermal_instance { struct thermal_zone_device *tz; struct thermal_cooling_device *cdev; int trip; + bool initialized; unsigned long upper; /* Highest cooling state for this trip point */ unsigned long lower; /* Lowest cooling state for this trip point */ unsigned long target; /* expected cooling state */ diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index e49c2bce551d..cf000b331eed 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -258,16 +258,13 @@ static void n_tty_check_throttle(struct tty_struct *tty) static void n_tty_check_unthrottle(struct tty_struct *tty) { - if (tty->driver->type == TTY_DRIVER_TYPE_PTY && - tty->link->ldisc->ops->write_wakeup == n_tty_write_wakeup) { + if (tty->driver->type == TTY_DRIVER_TYPE_PTY) { if (chars_in_buffer(tty) > TTY_THRESHOLD_UNTHROTTLE) return; if (!tty->count) return; n_tty_kick_worker(tty); - n_tty_write_wakeup(tty->link); - if (waitqueue_active(&tty->link->write_wait)) - wake_up_interruptible_poll(&tty->link->write_wait, POLLOUT); + tty_wakeup(tty->link); return; } diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index a45660f62db5..78e983677339 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -681,7 +681,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) /* this is called once with whichever end is closed last */ static void pty_unix98_shutdown(struct tty_struct *tty) { - devpts_kill_index(tty->driver_data, tty->index); + struct inode *ptmx_inode; + + if (tty->driver->subtype == PTY_TYPE_MASTER) + ptmx_inode = tty->driver_data; + else + ptmx_inode = tty->link->driver_data; + devpts_kill_index(ptmx_inode, tty->index); + devpts_del_ref(ptmx_inode); } static const struct tty_operations ptm_unix98_ops = { @@ -773,6 +780,18 @@ static int ptmx_open(struct inode *inode, struct file *filp) set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ tty->driver_data = inode; + /* + * In the case where all references to ptmx inode are dropped and we + * still have /dev/tty opened pointing to the master/slave pair (ptmx + * is closed/released before /dev/tty), we must make sure that the inode + * is still valid when we call the final pty_unix98_shutdown, thus we + * hold an additional reference to the ptmx inode. For the same /dev/tty + * last close case, we also need to make sure the super_block isn't + * destroyed (devpts instance unmounted), before /dev/tty is closed and + * on its release devpts_kill_index is called. + */ + devpts_add_ref(inode); + tty_add_file(tty, filp); slave_inode = devpts_pty_new(inode, diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 4097f3f65b3b..7cd6f9a90542 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1379,6 +1379,9 @@ ce4100_serial_setup(struct serial_private *priv, #define PCI_DEVICE_ID_INTEL_BSW_UART1 0x228a #define PCI_DEVICE_ID_INTEL_BSW_UART2 0x228c +#define PCI_DEVICE_ID_INTEL_BDW_UART1 0x9ce3 +#define PCI_DEVICE_ID_INTEL_BDW_UART2 0x9ce4 + #define BYT_PRV_CLK 0x800 #define BYT_PRV_CLK_EN (1 << 0) #define BYT_PRV_CLK_M_VAL_SHIFT 1 @@ -1461,11 +1464,13 @@ byt_serial_setup(struct serial_private *priv, switch (pdev->device) { case PCI_DEVICE_ID_INTEL_BYT_UART1: case PCI_DEVICE_ID_INTEL_BSW_UART1: + case PCI_DEVICE_ID_INTEL_BDW_UART1: rx_param->src_id = 3; tx_param->dst_id = 2; break; case PCI_DEVICE_ID_INTEL_BYT_UART2: case PCI_DEVICE_ID_INTEL_BSW_UART2: + case PCI_DEVICE_ID_INTEL_BDW_UART2: rx_param->src_id = 5; tx_param->dst_id = 4; break; @@ -1936,6 +1941,7 @@ pci_wch_ch38x_setup(struct serial_private *priv, #define PCIE_VENDOR_ID_WCH 0x1c00 #define PCIE_DEVICE_ID_WCH_CH382_2S1P 0x3250 #define PCIE_DEVICE_ID_WCH_CH384_4S 0x3470 +#define PCIE_DEVICE_ID_WCH_CH382_2S 0x3253 #define PCI_VENDOR_ID_PERICOM 0x12D8 #define PCI_DEVICE_ID_PERICOM_PI7C9X7951 0x7951 @@ -2062,6 +2068,20 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = byt_serial_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART1, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART2, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, /* * ITE */ @@ -2618,6 +2638,14 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, + /* WCH CH382 2S card (16850 clone) */ + { + .vendor = PCIE_VENDOR_ID_WCH, + .device = PCIE_DEVICE_ID_WCH_CH382_2S, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_wch_ch38x_setup, + }, /* WCH CH382 2S1P card (16850 clone) */ { .vendor = PCIE_VENDOR_ID_WCH, @@ -2936,6 +2964,7 @@ enum pci_board_num_t { pbn_fintek_4, pbn_fintek_8, pbn_fintek_12, + pbn_wch382_2, pbn_wch384_4, pbn_pericom_PI7C9X7951, pbn_pericom_PI7C9X7952, @@ -3756,6 +3785,13 @@ static struct pciserial_board pci_boards[] = { .base_baud = 115200, .first_offset = 0x40, }, + [pbn_wch382_2] = { + .flags = FL_BASE0, + .num_ports = 2, + .base_baud = 115200, + .uart_offset = 8, + .first_offset = 0xC0, + }, [pbn_wch384_4] = { .flags = FL_BASE0, .num_ports = 4, @@ -5506,6 +5542,16 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, pbn_byt }, + /* Intel Broadwell */ + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART1, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART2, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + /* * Intel Quark x1000 */ @@ -5545,6 +5591,10 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_2_115200 }, + { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, pbn_wch382_2 }, + { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_wch384_4 }, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 52d82d2ac726..56ccbcefdd85 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -713,22 +713,16 @@ static int size_fifo(struct uart_8250_port *up) */ static unsigned int autoconfig_read_divisor_id(struct uart_8250_port *p) { - unsigned char old_dll, old_dlm, old_lcr; - unsigned int id; + unsigned char old_lcr; + unsigned int id, old_dl; old_lcr = serial_in(p, UART_LCR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_A); + old_dl = serial_dl_read(p); + serial_dl_write(p, 0); + id = serial_dl_read(p); + serial_dl_write(p, old_dl); - old_dll = serial_in(p, UART_DLL); - old_dlm = serial_in(p, UART_DLM); - - serial_out(p, UART_DLL, 0); - serial_out(p, UART_DLM, 0); - - id = serial_in(p, UART_DLL) | serial_in(p, UART_DLM) << 8; - - serial_out(p, UART_DLL, old_dll); - serial_out(p, UART_DLM, old_dlm); serial_out(p, UART_LCR, old_lcr); return id; diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 9d4c84f7485f..24280d9a05e9 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1343,7 +1343,7 @@ static inline void serial_omap_add_console_port(struct uart_omap_port *up) /* Enable or disable the rs485 support */ static int -serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) +serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485) { struct uart_omap_port *up = to_uart_omap_port(port); unsigned int mode; @@ -1356,8 +1356,12 @@ serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) up->ier = 0; serial_out(up, UART_IER, 0); + /* Clamp the delays to [0, 100ms] */ + rs485->delay_rts_before_send = min(rs485->delay_rts_before_send, 100U); + rs485->delay_rts_after_send = min(rs485->delay_rts_after_send, 100U); + /* store new config */ - port->rs485 = *rs485conf; + port->rs485 = *rs485; /* * Just as a precaution, only allow rs485 diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 51c7507b0444..63a06ab6ba03 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -38,7 +38,6 @@ #include <linux/major.h> #include <linux/module.h> #include <linux/mm.h> -#include <linux/notifier.h> #include <linux/of.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> @@ -116,8 +115,6 @@ struct sci_port { struct timer_list rx_timer; unsigned int rx_timeout; #endif - - struct notifier_block freq_transition; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -1606,29 +1603,6 @@ static irqreturn_t sci_mpxed_interrupt(int irq, void *ptr) return ret; } -/* - * Here we define a transition notifier so that we can update all of our - * ports' baud rate when the peripheral clock changes. - */ -static int sci_notifier(struct notifier_block *self, - unsigned long phase, void *p) -{ - struct sci_port *sci_port; - unsigned long flags; - - sci_port = container_of(self, struct sci_port, freq_transition); - - if (phase == CPUFREQ_POSTCHANGE) { - struct uart_port *port = &sci_port->port; - - spin_lock_irqsave(&port->lock, flags); - port->uartclk = clk_get_rate(sci_port->iclk); - spin_unlock_irqrestore(&port->lock, flags); - } - - return NOTIFY_OK; -} - static const struct sci_irq_desc { const char *desc; irq_handler_t handler; @@ -2559,9 +2533,6 @@ static int sci_remove(struct platform_device *dev) { struct sci_port *port = platform_get_drvdata(dev); - cpufreq_unregister_notifier(&port->freq_transition, - CPUFREQ_TRANSITION_NOTIFIER); - uart_remove_one_port(&sci_uart_driver, &port->port); sci_cleanup_single(port); @@ -2714,16 +2685,6 @@ static int sci_probe(struct platform_device *dev) if (ret) return ret; - sp->freq_transition.notifier_call = sci_notifier; - - ret = cpufreq_register_notifier(&sp->freq_transition, - CPUFREQ_TRANSITION_NOTIFIER); - if (unlikely(ret < 0)) { - uart_remove_one_port(&sci_uart_driver, &sp->port); - sci_cleanup_single(sp); - return ret; - } - #ifdef CONFIG_SH_STANDARD_BIOS sh_bios_gdb_detach(); #endif diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index bcc8e1e8bb72..7cef54334b12 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1462,13 +1462,13 @@ static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; - if (!tty->count) - return -EIO; - if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) return -EIO; + if (!tty->count) + return -EAGAIN; + if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN)) return -EBUSY; @@ -2069,7 +2069,12 @@ retry_open: if (tty) { mutex_unlock(&tty_mutex); - tty_lock(tty); + retval = tty_lock_interruptible(tty); + if (retval) { + if (retval == -EINTR) + retval = -ERESTARTSYS; + goto err_unref; + } /* safe to drop the kref from tty_driver_lookup_tty() */ tty_kref_put(tty); retval = tty_reopen(tty); @@ -2087,7 +2092,11 @@ retry_open: if (IS_ERR(tty)) { retval = PTR_ERR(tty); - goto err_file; + if (retval != -EAGAIN || signal_pending(current)) + goto err_file; + tty_free_file(filp); + schedule(); + goto retry_open; } tty_add_file(tty, filp); @@ -2156,6 +2165,7 @@ retry_open: return 0; err_unlock: mutex_unlock(&tty_mutex); +err_unref: /* after locks to avoid deadlock */ if (!IS_ERR_OR_NULL(driver)) tty_driver_kref_put(driver); @@ -2653,6 +2663,28 @@ static int tiocsetd(struct tty_struct *tty, int __user *p) } /** + * tiocgetd - get line discipline + * @tty: tty device + * @p: pointer to user data + * + * Retrieves the line discipline id directly from the ldisc. + * + * Locking: waits for ldisc reference (in case the line discipline + * is changing or the tty is being hungup) + */ + +static int tiocgetd(struct tty_struct *tty, int __user *p) +{ + struct tty_ldisc *ld; + int ret; + + ld = tty_ldisc_ref_wait(tty); + ret = put_user(ld->ops->num, p); + tty_ldisc_deref(ld); + return ret; +} + +/** * send_break - performed time break * @tty: device to break on * @duration: timeout in mS @@ -2878,7 +2910,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case TIOCGSID: return tiocgsid(tty, real_tty, p); case TIOCGETD: - return put_user(tty->ldisc->ops->num, (int __user *)p); + return tiocgetd(tty, p); case TIOCSETD: return tiocsetd(tty, p); case TIOCVHANGUP: diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c index 0efcf713b756..d09293bc0e04 100644 --- a/drivers/tty/tty_mutex.c +++ b/drivers/tty/tty_mutex.c @@ -22,6 +22,14 @@ void __lockfunc tty_lock(struct tty_struct *tty) } EXPORT_SYMBOL(tty_lock); +int tty_lock_interruptible(struct tty_struct *tty) +{ + if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty)) + return -EIO; + tty_kref_get(tty); + return mutex_lock_interruptible(&tty->legacy_mutex); +} + void __lockfunc tty_unlock(struct tty_struct *tty) { if (tty->magic != TTY_MAGIC) { diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c index 45f86da1d6d3..03b6743461d1 100644 --- a/drivers/usb/chipidea/otg.c +++ b/drivers/usb/chipidea/otg.c @@ -158,7 +158,7 @@ static void ci_otg_work(struct work_struct *work) int ci_hdrc_otg_init(struct ci_hdrc *ci) { INIT_WORK(&ci->work, ci_otg_work); - ci->wq = create_singlethread_workqueue("ci_otg"); + ci->wq = create_freezable_workqueue("ci_otg"); if (!ci->wq) { dev_err(ci->dev, "can't create workqueue\n"); return -ENODEV; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 26ca4f910cb0..d37fdcc3143c 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -428,7 +428,8 @@ static void acm_read_bulk_callback(struct urb *urb) set_bit(rb->index, &acm->read_urbs_free); dev_dbg(&acm->data->dev, "%s - non-zero urb status: %d\n", __func__, status); - return; + if ((status != -ENOENT) || (urb->actual_length == 0)) + return; } usb_mark_last_busy(acm->dev); @@ -1113,6 +1114,9 @@ static int acm_probe(struct usb_interface *intf, if (quirks == NO_UNION_NORMAL) { data_interface = usb_ifnum_to_if(usb_dev, 1); control_interface = usb_ifnum_to_if(usb_dev, 0); + /* we would crash */ + if (!data_interface || !control_interface) + return -ENODEV; goto skip_normal_probe; } @@ -1404,6 +1408,8 @@ made_compressed_probe: usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress), NULL, acm->writesize, acm_write_bulk, snd); snd->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + if (quirks & SEND_ZERO_PACKET) + snd->urb->transfer_flags |= URB_ZERO_PACKET; snd->instance = acm; } @@ -1838,6 +1844,11 @@ static const struct usb_device_id acm_ids[] = { }, #endif + /*Samsung phone in firmware update mode */ + { USB_DEVICE(0x04e8, 0x685d), + .driver_info = IGNORE_DEVICE, + }, + /* Exclude Infineon Flash Loader utility */ { USB_DEVICE(0x058b, 0x0041), .driver_info = IGNORE_DEVICE, @@ -1861,6 +1872,10 @@ static const struct usb_device_id acm_ids[] = { { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM, USB_CDC_ACM_PROTO_AT_CDMA) }, + { USB_DEVICE(0x1519, 0x0452), /* Intel 7260 modem */ + .driver_info = SEND_ZERO_PACKET, + }, + { } }; diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index dd9af38e7cda..ccfaba9ab4e4 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -134,3 +134,4 @@ struct acm { #define IGNORE_DEVICE BIT(5) #define QUIRK_CONTROL_LINE_STATE BIT(6) #define CLEAR_HALT_CONDITIONS BIT(7) +#define SEND_ZERO_PACKET BIT(8) diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 56593a9a8726..2057d91d8336 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -502,11 +502,15 @@ static int usb_unbind_interface(struct device *dev) int usb_driver_claim_interface(struct usb_driver *driver, struct usb_interface *iface, void *priv) { - struct device *dev = &iface->dev; + struct device *dev; struct usb_device *udev; int retval = 0; int lpm_disable_error; + if (!iface) + return -ENODEV; + + dev = &iface->dev; if (dev->driver) return -EBUSY; diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index 9eb1cff28bd4..b8b580e5ae6e 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -74,6 +74,15 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd, if (companion->bus != pdev->bus || PCI_SLOT(companion->devfn) != slot) continue; + + /* + * Companion device should be either UHCI,OHCI or EHCI host + * controller, otherwise skip. + */ + if (companion->class != CL_UHCI && companion->class != CL_OHCI && + companion->class != CL_EHCI) + continue; + companion_hcd = pci_get_drvdata(companion); if (!companion_hcd || !companion_hcd->self.root_hub) continue; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index ddbf32d599cb..385c182f21ed 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2154,6 +2154,12 @@ void usb_disconnect(struct usb_device **pdev) dev_info(&udev->dev, "USB disconnect, device number %d\n", udev->devnum); + if (udev->speed < USB_SPEED_HIGH) { + struct usb_hcd *hcd = bus_to_hcd(udev->bus); + if (hcd->driver->change_bus_speed) + hcd->driver->change_bus_speed(hcd, 0); + } + usb_lock_device(udev); hub_disconnect_children(udev); @@ -3895,17 +3901,30 @@ static void usb_enable_link_state(struct usb_hcd *hcd, struct usb_device *udev, return; } - if (usb_set_lpm_timeout(udev, state, timeout)) + if (usb_set_lpm_timeout(udev, state, timeout)) { /* If we can't set the parent hub U1/U2 timeout, * device-initiated LPM won't be allowed either, so let the xHCI * host know that this link state won't be enabled. */ hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); + } else { + /* Only a configured device will accept the Set Feature + * U1/U2_ENABLE + */ + if (udev->actconfig) + usb_set_device_initiated_lpm(udev, state, true); - /* Only a configured device will accept the Set Feature U1/U2_ENABLE */ - else if (udev->actconfig) - usb_set_device_initiated_lpm(udev, state, true); - + /* As soon as usb_set_lpm_timeout(timeout) returns 0, the + * hub-initiated LPM is enabled. Thus, LPM is enabled no + * matter the result of usb_set_device_initiated_lpm(). + * The only difference is whether device is able to initiate + * LPM. + */ + if (state == USB3_LPM_U1) + udev->usb3_lpm_u1_enabled = 1; + else if (state == USB3_LPM_U2) + udev->usb3_lpm_u2_enabled = 1; + } } /* @@ -3945,6 +3964,18 @@ static int usb_disable_link_state(struct usb_hcd *hcd, struct usb_device *udev, dev_warn(&udev->dev, "Could not disable xHCI %s timeout, " "bus schedule bandwidth may be impacted.\n", usb3_lpm_names[state]); + + /* As soon as usb_set_lpm_timeout(0) return 0, hub initiated LPM + * is disabled. Hub will disallows link to enter U1/U2 as well, + * even device is initiating LPM. Hence LPM is disabled if hub LPM + * timeout set to 0, no matter device-initiated LPM is disabled or + * not. + */ + if (state == USB3_LPM_U1) + udev->usb3_lpm_u1_enabled = 0; + else if (state == USB3_LPM_U2) + udev->usb3_lpm_u2_enabled = 0; + return 0; } @@ -3979,8 +4010,6 @@ int usb_disable_lpm(struct usb_device *udev) if (usb_disable_link_state(hcd, udev, USB3_LPM_U2)) goto enable_lpm; - udev->usb3_lpm_enabled = 0; - return 0; enable_lpm: @@ -4038,8 +4067,6 @@ void usb_enable_lpm(struct usb_device *udev) usb_enable_link_state(hcd, udev, USB3_LPM_U1); usb_enable_link_state(hcd, udev, USB3_LPM_U2); - - udev->usb3_lpm_enabled = 1; } EXPORT_SYMBOL_GPL(usb_enable_lpm); @@ -4256,7 +4283,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, { struct usb_device *hdev = hub->hdev; struct usb_hcd *hcd = bus_to_hcd(hdev->bus); - int i, j, retval; + int retries, operations, retval, i; unsigned delay = HUB_SHORT_RESET_TIME; enum usb_device_speed oldspeed = udev->speed; const char *speed; @@ -4358,7 +4385,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, * first 8 bytes of the device descriptor to get the ep0 maxpacket * value. */ - for (i = 0; i < GET_DESCRIPTOR_TRIES; (++i, msleep(100))) { + for (retries = 0; retries < GET_DESCRIPTOR_TRIES; (++retries, msleep(100))) { bool did_new_scheme = false; if (use_new_scheme(udev, retry_counter)) { @@ -4385,7 +4412,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, * 255 is for WUSB devices, we actually need to use * 512 (WUSB1.0[4.8.1]). */ - for (j = 0; j < 3; ++j) { + for (operations = 0; operations < 3; ++operations) { buf->bMaxPacketSize0 = 0; r = usb_control_msg(udev, usb_rcvaddr0pipe(), USB_REQ_GET_DESCRIPTOR, USB_DIR_IN, @@ -4405,7 +4432,13 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, r = -EPROTO; break; } - if (r == 0) + /* + * Some devices time out if they are powered on + * when already connected. They need a second + * reset. But only on the first attempt, + * lest we get into a time out/reset loop + */ + if (r == 0 || (r == -ETIMEDOUT && retries == 0)) break; } udev->descriptor.bMaxPacketSize0 = @@ -4437,7 +4470,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, * authorization will assign the final address. */ if (udev->wusb == 0) { - for (j = 0; j < SET_ADDRESS_TRIES; ++j) { + for (operations = 0; operations < SET_ADDRESS_TRIES; ++operations) { retval = hub_set_address(udev, devnum); if (retval >= 0) break; @@ -4831,9 +4864,19 @@ loop: if (hub->hdev->parent || !hcd->driver->port_handed_over || !(hcd->driver->port_handed_over)(hcd, port1)) { - if (status != -ENOTCONN && status != -ENODEV) + if (status != -ENOTCONN && status != -ENODEV) { dev_err(&port_dev->dev, - "unable to enumerate USB device\n"); + "unable to enumerate USB device" + " at %s while bus at %s\n", + usb_speed_string(udev->speed), + hdev->descriptor.bDeviceProtocol == USB_HUB_PR_FS ? + "FULL_SPEED" : "HIGH_SPEED"); + + if (udev->speed < USB_SPEED_HIGH && + hdev->descriptor.bDeviceProtocol != USB_HUB_PR_FS && + hcd->driver->change_bus_speed) + hcd->driver->change_bus_speed(hcd, 1); + } } done: diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index d9ec2de6c4cf..65b6e6b84043 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -531,7 +531,7 @@ static ssize_t usb2_lpm_besl_store(struct device *dev, } static DEVICE_ATTR_RW(usb2_lpm_besl); -static ssize_t usb3_hardware_lpm_show(struct device *dev, +static ssize_t usb3_hardware_lpm_u1_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_device *udev = to_usb_device(dev); @@ -539,7 +539,7 @@ static ssize_t usb3_hardware_lpm_show(struct device *dev, usb_lock_device(udev); - if (udev->usb3_lpm_enabled) + if (udev->usb3_lpm_u1_enabled) p = "enabled"; else p = "disabled"; @@ -548,7 +548,26 @@ static ssize_t usb3_hardware_lpm_show(struct device *dev, return sprintf(buf, "%s\n", p); } -static DEVICE_ATTR_RO(usb3_hardware_lpm); +static DEVICE_ATTR_RO(usb3_hardware_lpm_u1); + +static ssize_t usb3_hardware_lpm_u2_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct usb_device *udev = to_usb_device(dev); + const char *p; + + usb_lock_device(udev); + + if (udev->usb3_lpm_u2_enabled) + p = "enabled"; + else + p = "disabled"; + + usb_unlock_device(udev); + + return sprintf(buf, "%s\n", p); +} +static DEVICE_ATTR_RO(usb3_hardware_lpm_u2); static struct attribute *usb2_hardware_lpm_attr[] = { &dev_attr_usb2_hardware_lpm.attr, @@ -562,7 +581,8 @@ static struct attribute_group usb2_hardware_lpm_attr_group = { }; static struct attribute *usb3_hardware_lpm_attr[] = { - &dev_attr_usb3_hardware_lpm.attr, + &dev_attr_usb3_hardware_lpm_u1.attr, + &dev_attr_usb3_hardware_lpm_u2.attr, NULL, }; static struct attribute_group usb3_hardware_lpm_attr_group = { @@ -592,7 +612,8 @@ static int add_power_attributes(struct device *dev) if (udev->usb2_hw_lpm_capable == 1) rc = sysfs_merge_group(&dev->kobj, &usb2_hardware_lpm_attr_group); - if (udev->lpm_capable == 1) + if (udev->speed == USB_SPEED_SUPER && + udev->lpm_capable == 1) rc = sysfs_merge_group(&dev->kobj, &usb3_hardware_lpm_attr_group); } diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index 571c21727ff9..d26155180df6 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -54,6 +54,19 @@ #include "core.h" #include "hcd.h" +struct wrapper_priv_data { + struct dwc2_hsotg *hsotg; +}; + +/* Gets the dwc2_hsotg from a usb_hcd */ +static struct dwc2_hsotg *dwc2_hcd_to_hsotg(struct usb_hcd *hcd) +{ + struct wrapper_priv_data *p; + + p = (struct wrapper_priv_data *) &hcd->hcd_priv; + return p->hsotg; +} + /** * dwc2_dump_channel_info() - Prints the state of a host channel * @@ -1349,6 +1362,20 @@ void dwc2_hcd_queue_transactions(struct dwc2_hsotg *hsotg, } } } +/* + * 0: high speed + * 1: full speed + */ +static void dwc2_change_bus_speed(struct usb_hcd* hcd, int speed) +{ + struct dwc2_hsotg *hsotg = dwc2_hcd_to_hsotg(hcd); + + if (hsotg->core_params->speed == speed) + return; + + hsotg->core_params->speed = speed; + queue_work(hsotg->wq_otg, &hsotg->wf_otg); +} static void dwc2_conn_id_status_change(struct work_struct *work) { @@ -2121,18 +2148,6 @@ void dwc2_hcd_dump_frrem(struct dwc2_hsotg *hsotg) #endif } -struct wrapper_priv_data { - struct dwc2_hsotg *hsotg; -}; - -/* Gets the dwc2_hsotg from a usb_hcd */ -static struct dwc2_hsotg *dwc2_hcd_to_hsotg(struct usb_hcd *hcd) -{ - struct wrapper_priv_data *p; - - p = (struct wrapper_priv_data *) &hcd->hcd_priv; - return p->hsotg; -} static int _dwc2_hcd_start(struct usb_hcd *hcd); @@ -2905,6 +2920,7 @@ static struct hc_driver dwc2_hc_driver = { .bus_suspend = _dwc2_hcd_suspend, .bus_resume = _dwc2_hcd_resume, + .change_bus_speed = dwc2_change_bus_speed, }; /* diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 000104111a8d..912590c3bd74 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -59,7 +59,7 @@ static const struct dwc2_core_params params_hi6220 = { .otg_ver = 0, /* 1.3 */ .dma_enable = 1, .dma_desc_enable = 0, - .speed = 1, /* High Speed */ + .speed = 0, /* High Speed */ .enable_dynamic_fifo = 1, .en_multiple_tx_fifo = 1, .host_rx_fifo_size = 512, diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 36f1cb74588c..78be201d81f4 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -853,7 +853,6 @@ struct dwc3 { unsigned pullups_connected:1; unsigned resize_fifos:1; unsigned setup_packet_pending:1; - unsigned start_config_issued:1; unsigned three_stage_setup:1; unsigned usb3_lpm_capable:1; diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 5320e939e090..b13912d5fa99 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -555,7 +555,6 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) int ret; u32 reg; - dwc->start_config_issued = false; cfg = le16_to_cpu(ctrl->wValue); switch (state) { @@ -737,10 +736,6 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_ISOCH_DELAY"); ret = dwc3_ep0_set_isoch_delay(dwc, ctrl); break; - case USB_REQ_SET_INTERFACE: - dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_INTERFACE"); - dwc->start_config_issued = false; - /* Fall through */ default: dwc3_trace(trace_dwc3_ep0, "Forwarding to gadget driver"); ret = dwc3_ep0_delegate_req(dwc, ctrl); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index a58376fd65fe..69ffe6e8d77f 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -388,24 +388,66 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep) dep->trb_pool_dma = 0; } +static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep); + +/** + * dwc3_gadget_start_config - Configure EP resources + * @dwc: pointer to our controller context structure + * @dep: endpoint that is being enabled + * + * The assignment of transfer resources cannot perfectly follow the + * data book due to the fact that the controller driver does not have + * all knowledge of the configuration in advance. It is given this + * information piecemeal by the composite gadget framework after every + * SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook + * programming model in this scenario can cause errors. For two + * reasons: + * + * 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION + * and SET_INTERFACE (8.1.5). This is incorrect in the scenario of + * multiple interfaces. + * + * 2) The databook does not mention doing more DEPXFERCFG for new + * endpoint on alt setting (8.1.6). + * + * The following simplified method is used instead: + * + * All hardware endpoints can be assigned a transfer resource and this + * setting will stay persistent until either a core reset or + * hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and + * do DEPXFERCFG for every hardware endpoint as well. We are + * guaranteed that there are as many transfer resources as endpoints. + * + * This function is called for each endpoint when it is being enabled + * but is triggered only when called for EP0-out, which always happens + * first, and which should only happen in one of the above conditions. + */ static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep) { struct dwc3_gadget_ep_cmd_params params; u32 cmd; + int i; + int ret; + + if (dep->number) + return 0; memset(¶ms, 0x00, sizeof(params)); + cmd = DWC3_DEPCMD_DEPSTARTCFG; - if (dep->number != 1) { - cmd = DWC3_DEPCMD_DEPSTARTCFG; - /* XferRscIdx == 0 for ep0 and 2 for the remaining */ - if (dep->number > 1) { - if (dwc->start_config_issued) - return 0; - dwc->start_config_issued = true; - cmd |= DWC3_DEPCMD_PARAM(2); - } + ret = dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + if (ret) + return ret; - return dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) { + struct dwc3_ep *dep = dwc->eps[i]; + + if (!dep) + continue; + + ret = dwc3_gadget_set_xfer_resource(dwc, dep); + if (ret) + return ret; } return 0; @@ -519,10 +561,6 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, struct dwc3_trb *trb_st_hw; struct dwc3_trb *trb_link; - ret = dwc3_gadget_set_xfer_resource(dwc, dep); - if (ret) - return ret; - dep->endpoint.desc = desc; dep->comp_desc = comp_desc; dep->type = usb_endpoint_type(desc); @@ -1604,8 +1642,6 @@ static int dwc3_gadget_start(struct usb_gadget *g, } dwc3_writel(dwc->regs, DWC3_DCFG, reg); - dwc->start_config_issued = false; - /* Start with SuperSpeed Default */ dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512); @@ -2202,7 +2238,6 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_DCTL, reg); dwc3_disconnect_gadget(dwc); - dwc->start_config_issued = false; dwc->gadget.speed = USB_SPEED_UNKNOWN; dwc->setup_packet_pending = false; @@ -2253,7 +2288,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) dwc3_stop_active_transfers(dwc); dwc3_clear_stall_all_ep(dwc); - dwc->start_config_issued = false; /* Reset device address to zero */ reg = dwc3_readl(dwc->regs, DWC3_DCFG); diff --git a/drivers/usb/gadget/function/f_accessory.c b/drivers/usb/gadget/function/f_accessory.c index 1be93a7ca4a1..c62123560143 100644 --- a/drivers/usb/gadget/function/f_accessory.c +++ b/drivers/usb/gadget/function/f_accessory.c @@ -404,12 +404,19 @@ static void acc_hid_close(struct hid_device *hid) { } +static int acc_hid_raw_request(struct hid_device *hid, unsigned char reportnum, + __u8 *buf, size_t len, unsigned char rtype, int reqtype) +{ + return 0; +} + static struct hid_ll_driver acc_hid_ll_driver = { .parse = acc_hid_parse, .start = acc_hid_start, .stop = acc_hid_stop, .open = acc_hid_open, .close = acc_hid_close, + .raw_request = acc_hid_raw_request, }; static struct acc_hid_dev *acc_hid_new(struct acc_dev *dev, diff --git a/drivers/usb/gadget/function/f_audio_source.c b/drivers/usb/gadget/function/f_audio_source.c index 39645be93502..bcd817439dbf 100644 --- a/drivers/usb/gadget/function/f_audio_source.c +++ b/drivers/usb/gadget/function/f_audio_source.c @@ -583,6 +583,11 @@ static void audio_disable(struct usb_function *f) usb_ep_disable(audio->in_ep); } +static void audio_free_func(struct usb_function *f) +{ + /* no-op */ +} + /*-------------------------------------------------------------------------*/ static void audio_build_desc(struct audio_dev *audio) @@ -827,6 +832,7 @@ static struct audio_dev _audio_dev = { .set_alt = audio_set_alt, .setup = audio_setup, .disable = audio_disable, + .free_func = audio_free_func, }, .lock = __SPIN_LOCK_UNLOCKED(_audio_dev.lock), .idle_reqs = LIST_HEAD_INIT(_audio_dev.idle_reqs), diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index cf43e9e18368..79d895c2dd71 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -646,6 +646,7 @@ static void ffs_user_copy_worker(struct work_struct *work) work); int ret = io_data->req->status ? io_data->req->status : io_data->req->actual; + bool kiocb_has_eventfd = io_data->kiocb->ki_flags & IOCB_EVENTFD; if (io_data->read && ret > 0) { use_mm(io_data->mm); @@ -657,13 +658,11 @@ static void ffs_user_copy_worker(struct work_struct *work) io_data->kiocb->ki_complete(io_data->kiocb, ret, ret); - if (io_data->ffs->ffs_eventfd && - !(io_data->kiocb->ki_flags & IOCB_EVENTFD)) + if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd) eventfd_signal(io_data->ffs->ffs_eventfd, 1); usb_ep_free_request(io_data->ep, io_data->req); - io_data->kiocb->private = NULL; if (io_data->read) kfree(io_data->to_free); kfree(io_data->buf); diff --git a/drivers/usb/gadget/function/f_mtp.c b/drivers/usb/gadget/function/f_mtp.c index 8f80a7e91314..74195be9b054 100644 --- a/drivers/usb/gadget/function/f_mtp.c +++ b/drivers/usb/gadget/function/f_mtp.c @@ -135,6 +135,34 @@ static struct usb_interface_descriptor ptp_interface_desc = { .bInterfaceProtocol = 1, }; +static struct usb_endpoint_descriptor mtp_ss_in_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_IN, + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = __constant_cpu_to_le16(1024), +}; + +static struct usb_ss_ep_comp_descriptor mtp_ss_in_comp_desc = { + .bLength = sizeof(mtp_ss_in_comp_desc), + .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + /* .bMaxBurst = DYNAMIC, */ +}; + +static struct usb_endpoint_descriptor mtp_ss_out_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_OUT, + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = __constant_cpu_to_le16(1024), +}; + +static struct usb_ss_ep_comp_descriptor mtp_ss_out_comp_desc = { + .bLength = sizeof(mtp_ss_out_comp_desc), + .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + /* .bMaxBurst = DYNAMIC, */ +}; + static struct usb_endpoint_descriptor mtp_highspeed_in_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, @@ -174,6 +202,12 @@ static struct usb_endpoint_descriptor mtp_intr_desc = { .bInterval = 6, }; +static struct usb_ss_ep_comp_descriptor mtp_intr_ss_comp_desc = { + .bLength = sizeof(mtp_intr_ss_comp_desc), + .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + .wBytesPerInterval = cpu_to_le16(INTR_BUFFER_SIZE), +}; + static struct usb_descriptor_header *fs_mtp_descs[] = { (struct usb_descriptor_header *) &mtp_interface_desc, (struct usb_descriptor_header *) &mtp_fullspeed_in_desc, @@ -190,6 +224,17 @@ static struct usb_descriptor_header *hs_mtp_descs[] = { NULL, }; +static struct usb_descriptor_header *ss_mtp_descs[] = { + (struct usb_descriptor_header *) &mtp_interface_desc, + (struct usb_descriptor_header *) &mtp_ss_in_desc, + (struct usb_descriptor_header *) &mtp_ss_in_comp_desc, + (struct usb_descriptor_header *) &mtp_ss_out_desc, + (struct usb_descriptor_header *) &mtp_ss_out_comp_desc, + (struct usb_descriptor_header *) &mtp_intr_desc, + (struct usb_descriptor_header *) &mtp_intr_ss_comp_desc, + NULL, +}; + static struct usb_descriptor_header *fs_ptp_descs[] = { (struct usb_descriptor_header *) &ptp_interface_desc, (struct usb_descriptor_header *) &mtp_fullspeed_in_desc, @@ -206,6 +251,17 @@ static struct usb_descriptor_header *hs_ptp_descs[] = { NULL, }; +static struct usb_descriptor_header *ss_ptp_descs[] = { + (struct usb_descriptor_header *) &ptp_interface_desc, + (struct usb_descriptor_header *) &mtp_ss_in_desc, + (struct usb_descriptor_header *) &mtp_ss_in_comp_desc, + (struct usb_descriptor_header *) &mtp_ss_out_desc, + (struct usb_descriptor_header *) &mtp_ss_out_comp_desc, + (struct usb_descriptor_header *) &mtp_intr_desc, + (struct usb_descriptor_header *) &mtp_intr_ss_comp_desc, + NULL, +}; + static struct usb_string mtp_string_defs[] = { /* Naming interface "MTP" so libmtp will recognize us */ [INTERFACE_STRING_INDEX].s = "MTP", @@ -290,6 +346,8 @@ struct mtp_instance { struct usb_function_instance func_inst; const char *name; struct mtp_dev *dev; + char mtp_ext_compat_id[16]; + struct usb_os_desc mtp_os_desc; }; /* temporary variable used between mtp_open() and mtp_gadget_bind() */ @@ -1101,6 +1159,7 @@ mtp_function_bind(struct usb_configuration *c, struct usb_function *f) struct mtp_dev *dev = func_to_mtp(f); int id; int ret; + struct mtp_instance *fi_mtp; dev->cdev = cdev; DBG(cdev, "mtp_function_bind dev: %p\n", dev); @@ -1118,6 +1177,18 @@ mtp_function_bind(struct usb_configuration *c, struct usb_function *f) mtp_string_defs[INTERFACE_STRING_INDEX].id = ret; mtp_interface_desc.iInterface = ret; } + + fi_mtp = container_of(f->fi, struct mtp_instance, func_inst); + + if (cdev->use_os_string) { + f->os_desc_table = kzalloc(sizeof(*f->os_desc_table), + GFP_KERNEL); + if (!f->os_desc_table) + return -ENOMEM; + f->os_desc_n = 1; + f->os_desc_table[0].os_desc = &fi_mtp->mtp_os_desc; + } + /* allocate endpoints */ ret = mtp_create_bulk_endpoints(dev, &mtp_fullspeed_in_desc, &mtp_fullspeed_out_desc, &mtp_intr_desc); @@ -1131,10 +1202,24 @@ mtp_function_bind(struct usb_configuration *c, struct usb_function *f) mtp_highspeed_out_desc.bEndpointAddress = mtp_fullspeed_out_desc.bEndpointAddress; } + /* support super speed hardware */ + if (gadget_is_superspeed(c->cdev->gadget)) { + unsigned max_burst; + + /* Calculate bMaxBurst, we know packet size is 1024 */ + max_burst = min_t(unsigned, MTP_BULK_BUFFER_SIZE / 1024, 15); + mtp_ss_in_desc.bEndpointAddress = + mtp_fullspeed_in_desc.bEndpointAddress; + mtp_ss_in_comp_desc.bMaxBurst = max_burst; + mtp_ss_out_desc.bEndpointAddress = + mtp_fullspeed_out_desc.bEndpointAddress; + mtp_ss_out_comp_desc.bMaxBurst = max_burst; + } DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n", - gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full", - f->name, dev->ep_in->name, dev->ep_out->name); + gadget_is_superspeed(c->cdev->gadget) ? "super" : + (gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full"), + f->name, dev->ep_in->name, dev->ep_out->name); return 0; } @@ -1153,6 +1238,8 @@ mtp_function_unbind(struct usb_configuration *c, struct usb_function *f) while ((req = mtp_req_get(dev, &dev->intr_idle))) mtp_request_free(req, dev->ep_intr); dev->state = STATE_OFFLINE; + kfree(f->os_desc_table); + f->os_desc_n = 0; } static int mtp_function_set_alt(struct usb_function *f, @@ -1336,6 +1423,7 @@ static void mtp_free_inst(struct usb_function_instance *fi) fi_mtp = to_fi_mtp(fi); kfree(fi_mtp->name); mtp_cleanup(); + kfree(fi_mtp->mtp_os_desc.group.default_groups); kfree(fi_mtp); } @@ -1343,6 +1431,8 @@ struct usb_function_instance *alloc_inst_mtp_ptp(bool mtp_config) { struct mtp_instance *fi_mtp; int ret = 0; + struct usb_os_desc *descs[1]; + char *names[1]; fi_mtp = kzalloc(sizeof(*fi_mtp), GFP_KERNEL); if (!fi_mtp) @@ -1350,6 +1440,13 @@ struct usb_function_instance *alloc_inst_mtp_ptp(bool mtp_config) fi_mtp->func_inst.set_inst_name = mtp_set_inst_name; fi_mtp->func_inst.free_func_inst = mtp_free_inst; + fi_mtp->mtp_os_desc.ext_compat_id = fi_mtp->mtp_ext_compat_id; + INIT_LIST_HEAD(&fi_mtp->mtp_os_desc.ext_prop); + descs[0] = &fi_mtp->mtp_os_desc; + names[0] = "MTP"; + usb_os_desc_prepare_interf_dir(&fi_mtp->func_inst.group, 1, + descs, names, THIS_MODULE); + if (mtp_config) { ret = mtp_setup_configfs(fi_mtp); if (ret) { @@ -1410,9 +1507,11 @@ struct usb_function *function_alloc_mtp_ptp(struct usb_function_instance *fi, if (mtp_config) { dev->function.fs_descriptors = fs_mtp_descs; dev->function.hs_descriptors = hs_mtp_descs; + dev->function.ss_descriptors = ss_mtp_descs; } else { dev->function.fs_descriptors = fs_ptp_descs; dev->function.hs_descriptors = hs_ptp_descs; + dev->function.ss_descriptors = ss_ptp_descs; } dev->function.bind = mtp_function_bind; dev->function.unbind = mtp_function_unbind; diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index c48cbe731356..d8dbd7e5194b 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1875,6 +1875,12 @@ no_bw: kfree(xhci->rh_bw); kfree(xhci->ext_caps); + xhci->usb2_ports = NULL; + xhci->usb3_ports = NULL; + xhci->port_array = NULL; + xhci->rh_bw = NULL; + xhci->ext_caps = NULL; + xhci->page_size = 0; xhci->page_shift = 0; xhci->bus_state[0].bus_suspended = 0; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index c62109091d12..ea4fb4b0cd44 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -28,7 +28,9 @@ #include "xhci.h" #include "xhci-trace.h" -#define PORT2_SSIC_CONFIG_REG2 0x883c +#define SSIC_PORT_NUM 2 +#define SSIC_PORT_CFG2 0x880c +#define SSIC_PORT_CFG2_OFFSET 0x30 #define PROG_DONE (1 << 30) #define SSIC_PORT_UNUSED (1 << 31) @@ -45,6 +47,8 @@ #define PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI 0x22b5 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI 0xa12f #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI 0x9d2f +#define PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI 0x0aa8 +#define PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI 0x1aa8 static const char hcd_name[] = "xhci_hcd"; @@ -152,7 +156,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI)) { + pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI)) { xhci->quirks |= XHCI_PME_STUCK_QUIRK; } if (pdev->vendor == PCI_VENDOR_ID_ETRON && @@ -295,6 +301,7 @@ static void xhci_pci_remove(struct pci_dev *dev) struct xhci_hcd *xhci; xhci = hcd_to_xhci(pci_get_drvdata(dev)); + xhci->xhc_state |= XHCI_STATE_REMOVING; if (xhci->shared_hcd) { usb_remove_hcd(xhci->shared_hcd); usb_put_hcd(xhci->shared_hcd); @@ -322,28 +329,36 @@ static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend) struct pci_dev *pdev = to_pci_dev(hcd->self.controller); u32 val; void __iomem *reg; + int i; if (pdev->vendor == PCI_VENDOR_ID_INTEL && pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) { - reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2; - - /* Notify SSIC that SSIC profile programming is not done */ - val = readl(reg) & ~PROG_DONE; - writel(val, reg); - - /* Mark SSIC port as unused(suspend) or used(resume) */ - val = readl(reg); - if (suspend) - val |= SSIC_PORT_UNUSED; - else - val &= ~SSIC_PORT_UNUSED; - writel(val, reg); - - /* Notify SSIC that SSIC profile programming is done */ - val = readl(reg) | PROG_DONE; - writel(val, reg); - readl(reg); + for (i = 0; i < SSIC_PORT_NUM; i++) { + reg = (void __iomem *) xhci->cap_regs + + SSIC_PORT_CFG2 + + i * SSIC_PORT_CFG2_OFFSET; + + /* + * Notify SSIC that SSIC profile programming + * is not done. + */ + val = readl(reg) & ~PROG_DONE; + writel(val, reg); + + /* Mark SSIC port as unused(suspend) or used(resume) */ + val = readl(reg); + if (suspend) + val |= SSIC_PORT_UNUSED; + else + val &= ~SSIC_PORT_UNUSED; + writel(val, reg); + + /* Notify SSIC that SSIC profile programming is done */ + val = readl(reg) | PROG_DONE; + writel(val, reg); + readl(reg); + } } reg = (void __iomem *) xhci->cap_regs + 0x80a4; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index eeaa6c6bd540..2b63969c2bbf 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2192,10 +2192,6 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, } /* Fast path - was this the last TRB in the TD for this URB? */ } else if (event_trb == td->last_trb) { - if (td->urb_length_set && trb_comp_code == COMP_SHORT_TX) - return finish_td(xhci, td, event_trb, event, ep, - status, false); - if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) != 0) { td->urb->actual_length = td->urb->transfer_buffer_length - @@ -2247,12 +2243,6 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->actual_length += TRB_LEN(le32_to_cpu(cur_trb->generic.field[2])) - EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); - - if (trb_comp_code == COMP_SHORT_TX) { - xhci_dbg(xhci, "mid bulk/intr SP, wait for last TRB event\n"); - td->urb_length_set = true; - return 0; - } } return finish_td(xhci, td, event_trb, event, ep, status, false); @@ -4018,7 +4008,8 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd, int reserved_trbs = xhci->cmd_ring_reserved_trbs; int ret; - if (xhci->xhc_state) { + if ((xhci->xhc_state & XHCI_STATE_DYING) || + (xhci->xhc_state & XHCI_STATE_HALTED)) { xhci_dbg(xhci, "xHCI dying or halted, can't queue_command\n"); return -ESHUTDOWN; } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 3f912705dcef..ec9e758d5fcd 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -146,7 +146,8 @@ static int xhci_start(struct xhci_hcd *xhci) "waited %u microseconds.\n", XHCI_MAX_HALT_USEC); if (!ret) - xhci->xhc_state &= ~(XHCI_STATE_HALTED | XHCI_STATE_DYING); + /* clear state flags. Including dying, halted or removing */ + xhci->xhc_state = 0; return ret; } @@ -1103,8 +1104,8 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) /* Resume root hubs only when have pending events. */ status = readl(&xhci->op_regs->status); if (status & STS_EINT) { - usb_hcd_resume_root_hub(hcd); usb_hcd_resume_root_hub(xhci->shared_hcd); + usb_hcd_resume_root_hub(hcd); } } @@ -1119,10 +1120,10 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) /* Re-enable port polling. */ xhci_dbg(xhci, "%s: starting port polling.\n", __func__); - set_bit(HCD_FLAG_POLL_RH, &hcd->flags); - usb_hcd_poll_rh_status(hcd); set_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags); usb_hcd_poll_rh_status(xhci->shared_hcd); + set_bit(HCD_FLAG_POLL_RH, &hcd->flags); + usb_hcd_poll_rh_status(hcd); return retval; } @@ -1549,7 +1550,9 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "HW died, freeing TD."); urb_priv = urb->hcpriv; - for (i = urb_priv->td_cnt; i < urb_priv->length; i++) { + for (i = urb_priv->td_cnt; + i < urb_priv->length && xhci->devs[urb->dev->slot_id]; + i++) { td = urb_priv->td[i]; if (!list_empty(&td->td_list)) list_del_init(&td->td_list); @@ -2751,7 +2754,8 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev) if (ret <= 0) return ret; xhci = hcd_to_xhci(hcd); - if (xhci->xhc_state & XHCI_STATE_DYING) + if ((xhci->xhc_state & XHCI_STATE_DYING) || + (xhci->xhc_state & XHCI_STATE_REMOVING)) return -ENODEV; xhci_dbg(xhci, "%s called for udev %p\n", __func__, udev); @@ -3798,7 +3802,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, mutex_lock(&xhci->mutex); - if (xhci->xhc_state) /* dying or halted */ + if (xhci->xhc_state) /* dying, removing or halted */ goto out; if (!udev->slot_id) { @@ -5059,6 +5063,10 @@ static int __init xhci_hcd_init(void) BUILD_BUG_ON(sizeof(struct xhci_intr_reg) != 8*32/8); /* xhci_run_regs has eight fields and embeds 128 xhci_intr_regs */ BUILD_BUG_ON(sizeof(struct xhci_run_regs) != (8+8*128)*32/8); + + if (usb_disabled()) + return -ENODEV; + return 0; } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 0b9451250e33..99ac2289dbf3 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1596,6 +1596,7 @@ struct xhci_hcd { */ #define XHCI_STATE_DYING (1 << 0) #define XHCI_STATE_HALTED (1 << 1) +#define XHCI_STATE_REMOVING (1 << 2) /* Statistics */ int error_bitmask; unsigned int quirks; diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index c6bfd13f6c92..1950e87b4219 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -787,6 +787,12 @@ static int iowarrior_probe(struct usb_interface *interface, iface_desc = interface->cur_altsetting; dev->product_id = le16_to_cpu(udev->descriptor.idProduct); + if (iface_desc->desc.bNumEndpoints < 1) { + dev_err(&interface->dev, "Invalid number of endpoints\n"); + retval = -EINVAL; + goto error; + } + /* set up the endpoint information */ for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 0d19a6d61a71..970a30e155cb 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -1599,6 +1599,8 @@ static int msm_otg_read_dt(struct platform_device *pdev, struct msm_otg *motg) &motg->id.nb); if (ret < 0) { dev_err(&pdev->dev, "register ID notifier failed\n"); + extcon_unregister_notifier(motg->vbus.extcon, + EXTCON_USB, &motg->vbus.nb); return ret; } @@ -1660,15 +1662,6 @@ static int msm_otg_probe(struct platform_device *pdev) if (!motg) return -ENOMEM; - pdata = dev_get_platdata(&pdev->dev); - if (!pdata) { - if (!np) - return -ENXIO; - ret = msm_otg_read_dt(pdev, motg); - if (ret) - return ret; - } - motg->phy.otg = devm_kzalloc(&pdev->dev, sizeof(struct usb_otg), GFP_KERNEL); if (!motg->phy.otg) @@ -1710,6 +1703,15 @@ static int msm_otg_probe(struct platform_device *pdev) if (!motg->regs) return -ENOMEM; + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + if (!np) + return -ENXIO; + ret = msm_otg_read_dt(pdev, motg); + if (ret) + return ret; + } + /* * NOTE: The PHYs can be multiplexed between the chipidea controller * and the dwc3 controller, using a single bit. It is important that @@ -1717,8 +1719,10 @@ static int msm_otg_probe(struct platform_device *pdev) */ if (motg->phy_number) { phy_select = devm_ioremap_nocache(&pdev->dev, USB2_PHY_SEL, 4); - if (!phy_select) - return -ENOMEM; + if (!phy_select) { + ret = -ENOMEM; + goto unregister_extcon; + } /* Enable second PHY with the OTG port */ writel(0x1, phy_select); } @@ -1728,7 +1732,8 @@ static int msm_otg_probe(struct platform_device *pdev) motg->irq = platform_get_irq(pdev, 0); if (motg->irq < 0) { dev_err(&pdev->dev, "platform_get_irq failed\n"); - return motg->irq; + ret = motg->irq; + goto unregister_extcon; } regs[0].supply = "vddcx"; @@ -1737,7 +1742,7 @@ static int msm_otg_probe(struct platform_device *pdev) ret = devm_regulator_bulk_get(motg->phy.dev, ARRAY_SIZE(regs), regs); if (ret) - return ret; + goto unregister_extcon; motg->vddcx = regs[0].consumer; motg->v3p3 = regs[1].consumer; @@ -1834,6 +1839,12 @@ disable_clks: clk_disable_unprepare(motg->clk); if (!IS_ERR(motg->core_clk)) clk_disable_unprepare(motg->core_clk); +unregister_extcon: + extcon_unregister_notifier(motg->id.extcon, + EXTCON_USB_HOST, &motg->id.nb); + extcon_unregister_notifier(motg->vbus.extcon, + EXTCON_USB, &motg->vbus.nb); + return ret; } diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index c0f5c652d272..f1893e08e51a 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -190,7 +190,8 @@ static int usbhsf_pkt_handler(struct usbhs_pipe *pipe, int type) goto __usbhs_pkt_handler_end; } - ret = func(pkt, &is_done); + if (likely(func)) + ret = func(pkt, &is_done); if (is_done) __usbhsf_pkt_del(pkt); @@ -889,6 +890,7 @@ static int usbhsf_dma_prepare_push(struct usbhs_pkt *pkt, int *is_done) pkt->trans = len; + usbhsf_tx_irq_ctrl(pipe, 0); INIT_WORK(&pkt->work, xfer_work); schedule_work(&pkt->work); diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index 8f7a78e70975..fa14198daf77 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -158,10 +158,14 @@ static void usbhsg_queue_done(struct usbhs_priv *priv, struct usbhs_pkt *pkt) struct usbhs_pipe *pipe = pkt->pipe; struct usbhsg_uep *uep = usbhsg_pipe_to_uep(pipe); struct usbhsg_request *ureq = usbhsg_pkt_to_ureq(pkt); + unsigned long flags; ureq->req.actual = pkt->actual; - usbhsg_queue_pop(uep, ureq, 0); + usbhs_lock(priv, flags); + if (uep) + __usbhsg_queue_pop(uep, ureq, 0); + usbhs_unlock(priv, flags); } static void usbhsg_queue_push(struct usbhsg_uep *uep, diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 7d4f51a32e66..a2b43a6e7fa7 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -98,6 +98,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x81AC) }, /* MSD Dash Hawk */ { USB_DEVICE(0x10C4, 0x81AD) }, /* INSYS USB Modem */ { USB_DEVICE(0x10C4, 0x81C8) }, /* Lipowsky Industrie Elektronik GmbH, Baby-JTAG */ + { USB_DEVICE(0x10C4, 0x81D7) }, /* IAI Corp. RCB-CV-USB USB to RS485 Adaptor */ { USB_DEVICE(0x10C4, 0x81E2) }, /* Lipowsky Industrie Elektronik GmbH, Baby-LIN */ { USB_DEVICE(0x10C4, 0x81E7) }, /* Aerocomm Radio */ { USB_DEVICE(0x10C4, 0x81E8) }, /* Zephyr Bioharness */ @@ -107,6 +108,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */ { USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */ { USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */ + { USB_DEVICE(0x10C4, 0x82F4) }, /* Starizona MicroTouch */ { USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */ { USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */ { USB_DEVICE(0x10C4, 0x8382) }, /* Cygnal Integrated Products, Inc. */ @@ -116,6 +118,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */ { USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */ { USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */ + { USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */ { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ @@ -139,6 +142,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */ { USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */ { USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */ + { USB_DEVICE(0x12B8, 0xEC60) }, /* Link G4 ECU */ + { USB_DEVICE(0x12B8, 0xEC62) }, /* Link G4+ ECU */ { USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */ { USB_DEVICE(0x1555, 0x0004) }, /* Owen AC4 USB-RS485 Converter */ { USB_DEVICE(0x166A, 0x0201) }, /* Clipsal 5500PACA C-Bus Pascal Automation Controller */ @@ -160,6 +165,11 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x17F4, 0xAAAA) }, /* Wavesense Jazz blood glucose meter */ { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ + { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ + { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ + { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ + { USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */ + { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c index 01bf53392819..244acb1299a9 100644 --- a/drivers/usb/serial/cypress_m8.c +++ b/drivers/usb/serial/cypress_m8.c @@ -447,6 +447,11 @@ static int cypress_generic_port_probe(struct usb_serial_port *port) struct usb_serial *serial = port->serial; struct cypress_private *priv; + if (!port->interrupt_out_urb || !port->interrupt_in_urb) { + dev_err(&port->dev, "required endpoint is missing\n"); + return -ENODEV; + } + priv = kzalloc(sizeof(struct cypress_private), GFP_KERNEL); if (!priv) return -ENOMEM; @@ -606,12 +611,6 @@ static int cypress_open(struct tty_struct *tty, struct usb_serial_port *port) cypress_set_termios(tty, port, &priv->tmp_termios); /* setup the port and start reading from the device */ - if (!port->interrupt_in_urb) { - dev_err(&port->dev, "%s - interrupt_in_urb is empty!\n", - __func__); - return -1; - } - usb_fill_int_urb(port->interrupt_in_urb, serial->dev, usb_rcvintpipe(serial->dev, port->interrupt_in_endpointAddress), port->interrupt_in_urb->transfer_buffer, diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c index 12b0e67473ba..3df7b7ec178e 100644 --- a/drivers/usb/serial/digi_acceleport.c +++ b/drivers/usb/serial/digi_acceleport.c @@ -1251,8 +1251,27 @@ static int digi_port_init(struct usb_serial_port *port, unsigned port_num) static int digi_startup(struct usb_serial *serial) { + struct device *dev = &serial->interface->dev; struct digi_serial *serial_priv; int ret; + int i; + + /* check whether the device has the expected number of endpoints */ + if (serial->num_port_pointers < serial->type->num_ports + 1) { + dev_err(dev, "OOB endpoints missing\n"); + return -ENODEV; + } + + for (i = 0; i < serial->type->num_ports + 1 ; i++) { + if (!serial->port[i]->read_urb) { + dev_err(dev, "bulk-in endpoint missing\n"); + return -ENODEV; + } + if (!serial->port[i]->write_urb) { + dev_err(dev, "bulk-out endpoint missing\n"); + return -ENODEV; + } + } serial_priv = kzalloc(sizeof(*serial_priv), GFP_KERNEL); if (!serial_priv) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index a5a0376bbd48..b61f12160d37 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -824,6 +824,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_TURTELIZER_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_USB60F) }, + { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_SCU18) }, { USB_DEVICE(FTDI_VID, FTDI_REU_TINY_PID) }, /* Papouch devices based on FTDI chip */ @@ -1003,6 +1004,10 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_DISPLAY_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_LITE_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ANALOG_PID) }, + /* ICP DAS I-756xU devices */ + { USB_DEVICE(ICPDAS_VID, ICPDAS_I7560U_PID) }, + { USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) }, + { USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 67c6d4469730..c5d6c1e73e8e 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -615,6 +615,7 @@ */ #define RATOC_VENDOR_ID 0x0584 #define RATOC_PRODUCT_ID_USB60F 0xb020 +#define RATOC_PRODUCT_ID_SCU18 0xb03a /* * Infineon Technologies @@ -871,6 +872,14 @@ #define NOVITUS_BONO_E_PID 0x6010 /* + * ICPDAS I-756*U devices + */ +#define ICPDAS_VID 0x1b5c +#define ICPDAS_I7560U_PID 0x0103 +#define ICPDAS_I7561U_PID 0x0104 +#define ICPDAS_I7563U_PID 0x0105 + +/* * RT Systems programming cables for various ham radios */ #define RTSYSTEMS_VID 0x2100 /* Vendor ID */ diff --git a/drivers/usb/serial/mct_u232.c b/drivers/usb/serial/mct_u232.c index fd707d6a10e2..89726f702202 100644 --- a/drivers/usb/serial/mct_u232.c +++ b/drivers/usb/serial/mct_u232.c @@ -376,14 +376,21 @@ static void mct_u232_msr_to_state(struct usb_serial_port *port, static int mct_u232_port_probe(struct usb_serial_port *port) { + struct usb_serial *serial = port->serial; struct mct_u232_private *priv; + /* check first to simplify error handling */ + if (!serial->port[1] || !serial->port[1]->interrupt_in_urb) { + dev_err(&port->dev, "expected endpoint missing\n"); + return -ENODEV; + } + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; /* Use second interrupt-in endpoint for reading. */ - priv->read_urb = port->serial->port[1]->interrupt_in_urb; + priv->read_urb = serial->port[1]->interrupt_in_urb; priv->read_urb->context = port; spin_lock_init(&priv->lock); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index f2280606b73c..c6f497f16526 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -268,6 +268,9 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_CC864_SINGLE 0x1006 #define TELIT_PRODUCT_DE910_DUAL 0x1010 #define TELIT_PRODUCT_UE910_V2 0x1012 +#define TELIT_PRODUCT_LE922_USBCFG0 0x1042 +#define TELIT_PRODUCT_LE922_USBCFG3 0x1043 +#define TELIT_PRODUCT_LE922_USBCFG5 0x1045 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 @@ -313,6 +316,7 @@ static void option_instat_callback(struct urb *urb); #define TOSHIBA_PRODUCT_G450 0x0d45 #define ALINK_VENDOR_ID 0x1e0e +#define SIMCOM_PRODUCT_SIM7100E 0x9001 /* Yes, ALINK_VENDOR_ID */ #define ALINK_PRODUCT_PH300 0x9100 #define ALINK_PRODUCT_3GU 0x9200 @@ -605,6 +609,10 @@ static const struct option_blacklist_info zte_1255_blacklist = { .reserved = BIT(3) | BIT(4), }; +static const struct option_blacklist_info simcom_sim7100e_blacklist = { + .reserved = BIT(5) | BIT(6), +}; + static const struct option_blacklist_info telit_le910_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(2), @@ -615,6 +623,16 @@ static const struct option_blacklist_info telit_le920_blacklist = { .reserved = BIT(1) | BIT(5), }; +static const struct option_blacklist_info telit_le922_blacklist_usbcfg0 = { + .sendsetup = BIT(2), + .reserved = BIT(0) | BIT(1) | BIT(3), +}; + +static const struct option_blacklist_info telit_le922_blacklist_usbcfg3 = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(2) | BIT(3), +}; + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -1110,9 +1128,13 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */ + { USB_DEVICE_AND_INTERFACE_INFO(QUALCOMM_VENDOR_ID, 0x6001, 0xff, 0xff, 0xff), /* 4G LTE usb-modem U901 */ + .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */ + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), @@ -1160,6 +1182,12 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), @@ -1629,6 +1657,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(ALINK_VENDOR_ID, 0x9000) }, { USB_DEVICE(ALINK_VENDOR_ID, ALINK_PRODUCT_PH300) }, { USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) }, + { USB_DEVICE(ALINK_VENDOR_ID, SIMCOM_PRODUCT_SIM7100E), + .driver_info = (kernel_ulong_t)&simcom_sim7100e_blacklist }, { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200), .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist }, @@ -1679,7 +1709,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, - { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX, 0xff) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, @@ -1788,6 +1818,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d02, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x02, 0x01) }, { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) }, + { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e19, 0xff), /* D-Link DWM-221 B1 */ + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 9919d2a9faf2..1bc6089b9008 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -157,14 +157,17 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9056)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9060)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9061)}, /* Sierra Wireless Modem */ - {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx/EM74xx */ - {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx/EM74xx */ + {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx */ + {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx */ + {DEVICE_SWI(0x1199, 0x9078)}, /* Sierra Wireless EM74xx */ + {DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a9)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81b1)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c index 60afb39eb73c..337a0be89fcf 100644 --- a/drivers/usb/serial/visor.c +++ b/drivers/usb/serial/visor.c @@ -544,6 +544,11 @@ static int treo_attach(struct usb_serial *serial) (serial->num_interrupt_in == 0)) return 0; + if (serial->num_bulk_in < 2 || serial->num_interrupt_in < 2) { + dev_err(&serial->interface->dev, "missing endpoints\n"); + return -ENODEV; + } + /* * It appears that Treos and Kyoceras want to use the * 1st bulk in endpoint to communicate with the 2nd bulk out endpoint, @@ -597,8 +602,10 @@ static int clie_5_attach(struct usb_serial *serial) */ /* some sanity check */ - if (serial->num_ports < 2) - return -1; + if (serial->num_bulk_out < 2) { + dev_err(&serial->interface->dev, "missing bulk out endpoints\n"); + return -ENODEV; + } /* port 0 now uses the modified endpoint Address */ port = serial->port[0]; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 5c66d3f7a6d0..9baf081174ce 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -2,7 +2,7 @@ * USB Attached SCSI * Note that this is not the same as the USB Mass Storage driver * - * Copyright Hans de Goede <hdegoede@redhat.com> for Red Hat, Inc. 2013 - 2014 + * Copyright Hans de Goede <hdegoede@redhat.com> for Red Hat, Inc. 2013 - 2016 * Copyright Matthew Wilcox for Intel Corp, 2010 * Copyright Sarah Sharp for Intel Corp, 2010 * @@ -757,6 +757,17 @@ static int uas_eh_bus_reset_handler(struct scsi_cmnd *cmnd) return SUCCESS; } +static int uas_target_alloc(struct scsi_target *starget) +{ + struct uas_dev_info *devinfo = (struct uas_dev_info *) + dev_to_shost(starget->dev.parent)->hostdata; + + if (devinfo->flags & US_FL_NO_REPORT_LUNS) + starget->no_report_luns = 1; + + return 0; +} + static int uas_slave_alloc(struct scsi_device *sdev) { struct uas_dev_info *devinfo = @@ -800,7 +811,6 @@ static int uas_slave_configure(struct scsi_device *sdev) if (devinfo->flags & US_FL_BROKEN_FUA) sdev->broken_fua = 1; - scsi_change_queue_depth(sdev, devinfo->qdepth - 2); return 0; } @@ -808,11 +818,12 @@ static struct scsi_host_template uas_host_template = { .module = THIS_MODULE, .name = "uas", .queuecommand = uas_queuecommand, + .target_alloc = uas_target_alloc, .slave_alloc = uas_slave_alloc, .slave_configure = uas_slave_configure, .eh_abort_handler = uas_eh_abort_handler, .eh_bus_reset_handler = uas_eh_bus_reset_handler, - .can_queue = 65536, /* Is there a limit on the _host_ ? */ + .can_queue = MAX_CMNDS, .this_id = -1, .sg_tablesize = SG_NONE, .skip_settle_delay = 1, @@ -932,6 +943,12 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) if (result) goto set_alt0; + /* + * 1 tag is reserved for untagged commands + + * 1 tag to avoid off by one errors in some bridge firmwares + */ + shost->can_queue = devinfo->qdepth - 2; + usb_set_intfdata(intf, shost); result = scsi_add_host(shost, &intf->dev); if (result) diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index ccc113e83d88..53341a77d89f 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -64,6 +64,13 @@ UNUSUAL_DEV(0x0bc2, 0x3312, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_ATA_1X), +/* Reported-by: David Webb <djw@noc.ac.uk> */ +UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999, + "Seagate", + "Expansion Desk", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_LUNS), + /* Reported-by: Hans de Goede <hdegoede@redhat.com> */ UNUSUAL_DEV(0x0bc2, 0x3320, 0x0000, 0x9999, "Seagate", diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index 43576ed31ccd..9de988a0f856 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -482,7 +482,7 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags) US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 | US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE | US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES | - US_FL_MAX_SECTORS_240); + US_FL_MAX_SECTORS_240 | US_FL_NO_REPORT_LUNS); p = quirks; while (*p) { @@ -532,6 +532,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags) case 'i': f |= US_FL_IGNORE_DEVICE; break; + case 'j': + f |= US_FL_NO_REPORT_LUNS; + break; case 'l': f |= US_FL_NOT_LOCKABLE; break; diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index facaaf003f19..e40da7759a0e 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -741,6 +741,17 @@ int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb) if (!(size > 0)) return 0; + if (size > urb->transfer_buffer_length) { + /* should not happen, probably malicious packet */ + if (ud->side == USBIP_STUB) { + usbip_event_add(ud, SDEV_EVENT_ERROR_TCP); + return 0; + } else { + usbip_event_add(ud, VDEV_EVENT_ERROR_TCP); + return -EPIPE; + } + } + ret = usbip_recv(ud->tcp_socket, urb->transfer_buffer, size); if (ret != size) { dev_err(&urb->dev->dev, "recv xbuf, %d\n", ret); diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 56bf6dbb93db..9982cb176ce8 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -446,7 +446,8 @@ static long vfio_pci_ioctl(void *device_data, info.num_regions = VFIO_PCI_NUM_REGIONS; info.num_irqs = VFIO_PCI_NUM_IRQS; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct pci_dev *pdev = vdev->pdev; @@ -520,7 +521,8 @@ static long vfio_pci_ioctl(void *device_data, return -EINVAL; } - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -555,7 +557,8 @@ static long vfio_pci_ioctl(void *device_data, else info.flags |= VFIO_IRQ_INFO_NORESIZE; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index 418cdd9ba3f4..e65b142d3422 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -219,7 +219,8 @@ static long vfio_platform_ioctl(void *device_data, info.num_regions = vdev->num_regions; info.num_irqs = vdev->num_irqs; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct vfio_region_info info; @@ -240,7 +241,8 @@ static long vfio_platform_ioctl(void *device_data, info.size = vdev->regions[info.index].size; info.flags = vdev->regions[info.index].flags; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -259,7 +261,8 @@ static long vfio_platform_ioctl(void *device_data, info.flags = vdev->irqs[info.index].flags; info.count = vdev->irqs[info.index].count; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 59d47cb638d5..ecb826eefe02 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -999,7 +999,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, info.iova_pgsizes = vfio_pgsize_bitmap(iommu); - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_IOMMU_MAP_DMA) { struct vfio_iommu_type1_dma_map map; @@ -1032,7 +1033,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, if (ret) return ret; - return copy_to_user((void __user *)arg, &unmap, minsz); + return copy_to_user((void __user *)arg, &unmap, minsz) ? + -EFAULT : 0; } return -ENOTTY; diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 92f394927f24..6e92917ba77a 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -709,6 +709,7 @@ static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info, } if (!err) { + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; if (vc) @@ -956,6 +957,7 @@ static const char *fbcon_startup(void) ops->currcon = -1; ops->graphics = 1; ops->cur_rotate = -1; + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; p->con_rotate = initial_rotation; set_blitting_type(vc, info); diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index e6d16d65e4e6..f07a0974fda2 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -2249,7 +2249,6 @@ config XEN_FBDEV_FRONTEND select FB_SYS_IMAGEBLIT select FB_SYS_FOPS select FB_DEFERRED_IO - select INPUT_XEN_KBDDEV_FRONTEND if INPUT_MISC select XEN_XENBUS_FRONTEND default y help diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c index 0081725c6b5b..d00510029c93 100644 --- a/drivers/video/fbdev/da8xx-fb.c +++ b/drivers/video/fbdev/da8xx-fb.c @@ -209,8 +209,7 @@ static struct fb_videomode known_lcd_panels[] = { .lower_margin = 2, .hsync_len = 0, .vsync_len = 0, - .sync = FB_SYNC_CLK_INVERT | - FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, + .sync = FB_SYNC_CLK_INVERT, }, /* Sharp LK043T1DG01 */ [1] = { @@ -224,7 +223,7 @@ static struct fb_videomode known_lcd_panels[] = { .lower_margin = 2, .hsync_len = 41, .vsync_len = 10, - .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, + .sync = 0, .flag = 0, }, [2] = { @@ -239,7 +238,7 @@ static struct fb_videomode known_lcd_panels[] = { .lower_margin = 10, .hsync_len = 10, .vsync_len = 10, - .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, + .sync = 0, .flag = 0, }, [3] = { diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 7efc32945810..7d3e5d0e9aa4 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -209,8 +209,8 @@ static unsigned leak_balloon(struct virtio_balloon *vb, size_t num) */ if (vb->num_pfns != 0) tell_host(vb, vb->deflate_vq); - mutex_unlock(&vb->balloon_lock); release_pages_balloon(vb); + mutex_unlock(&vb->balloon_lock); return num_freed_pages; } diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 78f804af6c20..2046a68ad0ba 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -545,6 +545,7 @@ err_enable_device: static void virtio_pci_remove(struct pci_dev *pci_dev) { struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + struct device *dev = get_device(&vp_dev->vdev.dev); unregister_virtio_device(&vp_dev->vdev); @@ -554,6 +555,7 @@ static void virtio_pci_remove(struct pci_dev *pci_dev) virtio_pci_modern_remove(vp_dev); pci_disable_device(pci_dev); + put_device(dev); } static struct pci_driver virtio_pci_driver = { diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 8e5cf194cc0b..4469202eaa8e 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -17,6 +17,7 @@ * */ +#include <linux/delay.h> #define VIRTIO_PCI_NO_LEGACY #include "virtio_pci_common.h" @@ -271,9 +272,13 @@ static void vp_reset(struct virtio_device *vdev) struct virtio_pci_device *vp_dev = to_vp_device(vdev); /* 0 status means a reset. */ vp_iowrite8(0, &vp_dev->common->device_status); - /* Flush out the status write, and flush in device writes, - * including MSI-X interrupts, if any. */ - vp_ioread8(&vp_dev->common->device_status); + /* After writing 0 to device_status, the driver MUST wait for a read of + * device_status to return 0 before reinitializing the device. + * This will flush out the status write, and flush in device writes, + * including MSI-X interrupts, if any. + */ + while (vp_ioread8(&vp_dev->common->device_status)) + msleep(1); /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c index 71e78ef4b736..3a75f3b53452 100644 --- a/drivers/watchdog/rc32434_wdt.c +++ b/drivers/watchdog/rc32434_wdt.c @@ -237,7 +237,7 @@ static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd, return -EINVAL; /* Fall through */ case WDIOC_GETTIMEOUT: - return copy_to_user(argp, &timeout, sizeof(int)); + return copy_to_user(argp, &timeout, sizeof(int)) ? -EFAULT : 0; default: return -ENOTTY; } diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 12eab503efd1..364bc44610c1 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -152,6 +152,8 @@ static DECLARE_WAIT_QUEUE_HEAD(balloon_wq); static void balloon_process(struct work_struct *work); static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); +static void release_memory_resource(struct resource *resource); + /* When ballooning out (allocating memory to return to Xen) we don't really want the kernel to try too hard since that can trigger the oom killer. */ #define GFP_BALLOON \ @@ -268,6 +270,20 @@ static struct resource *additional_memory_resource(phys_addr_t size) return NULL; } +#ifdef CONFIG_SPARSEMEM + { + unsigned long limit = 1UL << (MAX_PHYSMEM_BITS - PAGE_SHIFT); + unsigned long pfn = res->start >> PAGE_SHIFT; + + if (pfn > limit) { + pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n", + pfn, limit); + release_memory_resource(res); + return NULL; + } + } +#endif + return res; } diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 524c22146429..44367783f07a 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -484,9 +484,19 @@ static void eoi_pirq(struct irq_data *data) struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) }; int rc = 0; - irq_move_irq(data); + if (!VALID_EVTCHN(evtchn)) + return; - if (VALID_EVTCHN(evtchn)) + if (unlikely(irqd_is_setaffinity_pending(data))) { + int masked = test_and_set_mask(evtchn); + + clear_evtchn(evtchn); + + irq_move_masked_irq(data); + + if (!masked) + unmask_evtchn(evtchn); + } else clear_evtchn(evtchn); if (pirq_needs_eoi(data->irq)) { @@ -1357,9 +1367,19 @@ static void ack_dynirq(struct irq_data *data) { int evtchn = evtchn_from_irq(data->irq); - irq_move_irq(data); + if (!VALID_EVTCHN(evtchn)) + return; - if (VALID_EVTCHN(evtchn)) + if (unlikely(irqd_is_setaffinity_pending(data))) { + int masked = test_and_set_mask(evtchn); + + clear_evtchn(evtchn); + + irq_move_masked_irq(data); + + if (!masked) + unmask_evtchn(evtchn); + } else clear_evtchn(evtchn); } diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 38272ad24551..f4edd6df3df2 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -316,7 +316,6 @@ static int evtchn_resize_ring(struct per_user_data *u) { unsigned int new_size; evtchn_port_t *new_ring, *old_ring; - unsigned int p, c; /* * Ensure the ring is large enough to capture all possible @@ -346,20 +345,17 @@ static int evtchn_resize_ring(struct per_user_data *u) /* * Copy the old ring contents to the new ring. * - * If the ring contents crosses the end of the current ring, - * it needs to be copied in two chunks. + * To take care of wrapping, a full ring, and the new index + * pointing into the second half, simply copy the old contents + * twice. * * +---------+ +------------------+ - * |34567 12| -> | 1234567 | - * +-----p-c-+ +------------------+ + * |34567 12| -> |34567 1234567 12| + * +-----p-c-+ +-------c------p---+ */ - p = evtchn_ring_offset(u, u->ring_prod); - c = evtchn_ring_offset(u, u->ring_cons); - if (p < c) { - memcpy(new_ring + c, u->ring + c, (u->ring_size - c) * sizeof(*u->ring)); - memcpy(new_ring + u->ring_size, u->ring, p * sizeof(*u->ring)); - } else - memcpy(new_ring + c, u->ring + c, (p - c) * sizeof(*u->ring)); + memcpy(new_ring, old_ring, u->ring_size * sizeof(*u->ring)); + memcpy(new_ring + u->ring_size, old_ring, + u->ring_size * sizeof(*u->ring)); u->ring = new_ring; u->ring_size = new_size; diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 73dafdc494aa..fb0221434f81 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -227,8 +227,9 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, /* * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able * to access the BARs where the MSI-X entries reside. + * But VF devices are unique in which the PF needs to be checked. */ - pci_read_config_word(dev, PCI_COMMAND, &cmd); + pci_read_config_word(pci_physfn(dev), PCI_COMMAND, &cmd); if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY)) return -ENXIO; @@ -332,6 +333,9 @@ void xen_pcibk_do_op(struct work_struct *data) struct xen_pcibk_dev_data *dev_data = NULL; struct xen_pci_op *op = &pdev->op; int test_intx = 0; +#ifdef CONFIG_PCI_MSI + unsigned int nr = 0; +#endif *op = pdev->sh_info->op; barrier(); @@ -360,6 +364,7 @@ void xen_pcibk_do_op(struct work_struct *data) op->err = xen_pcibk_disable_msi(pdev, dev, op); break; case XEN_PCI_OP_enable_msix: + nr = op->value; op->err = xen_pcibk_enable_msix(pdev, dev, op); break; case XEN_PCI_OP_disable_msix: @@ -382,7 +387,7 @@ void xen_pcibk_do_op(struct work_struct *data) if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) { unsigned int i; - for (i = 0; i < op->value; i++) + for (i = 0; i < nr; i++) pdev->sh_info->op.msix_entries[i].vector = op->msix_entries[i].vector; } diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index ad4eb1024d1f..51387d75c7bf 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -939,12 +939,12 @@ out: spin_unlock_irqrestore(&info->v2p_lock, flags); out_free: - mutex_lock(&tpg->tv_tpg_mutex); - tpg->tv_tpg_fe_count--; - mutex_unlock(&tpg->tv_tpg_mutex); - - if (err) + if (err) { + mutex_lock(&tpg->tv_tpg_mutex); + tpg->tv_tpg_fe_count--; + mutex_unlock(&tpg->tv_tpg_mutex); kfree(new); + } return err; } diff --git a/fs/Kconfig b/fs/Kconfig index 6ce72d8d1ee1..a5d2dc39ba07 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -199,6 +199,7 @@ if MISC_FILESYSTEMS source "fs/adfs/Kconfig" source "fs/affs/Kconfig" source "fs/ecryptfs/Kconfig" +source "fs/sdcardfs/Kconfig" source "fs/hfs/Kconfig" source "fs/hfsplus/Kconfig" source "fs/befs/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index 79f522575cba..3b54070cd629 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -3,7 +3,7 @@ # # 14 Sep 2000, Christoph Hellwig <hch@infradead.org> # Rewritten to use lists instead of if-statements. -# +# obj-y := open.o read_write.o file_table.o super.o \ char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ @@ -59,7 +59,7 @@ obj-y += devpts/ obj-$(CONFIG_PROFILING) += dcookies.o obj-$(CONFIG_DLM) += dlm/ - + # Do not add any filesystems before this line obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ @@ -81,6 +81,7 @@ obj-$(CONFIG_ISO9660_FS) += isofs/ obj-$(CONFIG_HFSPLUS_FS) += hfsplus/ # Before hfs to find wrapped HFS+ obj-$(CONFIG_HFS_FS) += hfs/ obj-$(CONFIG_ECRYPT_FS) += ecryptfs/ +obj-$(CONFIG_SDCARD_FS) += sdcardfs/ obj-$(CONFIG_VXFS_FS) += freevxfs/ obj-$(CONFIG_NFS_FS) += nfs/ obj-$(CONFIG_EXPORTFS) += exportfs/ diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 3e36e4adc4a3..9aba42b78253 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq, list_add_tail(&work->ordered_list, &wq->ordered_list); spin_unlock_irqrestore(&wq->list_lock, flags); } - queue_work(wq->normal_wq, &work->normal_work); trace_btrfs_work_queued(work); + queue_work(wq->normal_wq, &work->normal_work); } void btrfs_queue_work(struct btrfs_workqueue *wq, diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index d453d62ab0c6..e2f659dc5745 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1417,7 +1417,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, read_extent_buffer(eb, dest + bytes_left, name_off, name_len); if (eb != eb_in) { - btrfs_tree_read_unlock_blocking(eb); + if (!path->skip_locking) + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); } ret = btrfs_find_item(fs_root, path, parent, 0, @@ -1437,9 +1438,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { - atomic_inc(&eb->refs); - btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + if (!path->skip_locking) + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + path->nodes[0] = NULL; + path->locks[0] = 0; } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 35489e7129a7..385b449fd7ed 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1572,7 +1572,7 @@ struct btrfs_fs_info { spinlock_t delayed_iput_lock; struct list_head delayed_iputs; - struct rw_semaphore delayed_iput_sem; + struct mutex cleaner_delayed_iput_mutex; /* this protects tree_mod_seq_list */ spinlock_t tree_mod_seq_lock; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index e0941fbb913c..02b934d0ee65 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1694,7 +1694,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list, * */ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list) + struct list_head *ins_list, bool *emitted) { struct btrfs_dir_item *di; struct btrfs_delayed_item *curr, *next; @@ -1738,6 +1738,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, if (over) return 1; + *emitted = true; } return 0; } diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index f70119f25421..0167853c84ae 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list, int btrfs_should_delete_dir_index(struct list_head *del_list, u64 index); int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list); + struct list_head *ins_list, bool *emitted); /* for init */ int __init btrfs_delayed_inode_init(void); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 974be09e7556..41fb43183406 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1582,8 +1582,23 @@ int btrfs_init_fs_root(struct btrfs_root *root) ret = get_anon_bdev(&root->anon_dev); if (ret) goto free_writers; + + mutex_lock(&root->objectid_mutex); + ret = btrfs_find_highest_objectid(root, + &root->highest_objectid); + if (ret) { + mutex_unlock(&root->objectid_mutex); + goto free_root_dev; + } + + ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&root->objectid_mutex); + return 0; +free_root_dev: + free_anon_bdev(root->anon_dev); free_writers: btrfs_free_subvolume_writers(root->subv_writers); fail: @@ -1762,7 +1777,6 @@ static int cleaner_kthread(void *arg) int again; struct btrfs_trans_handle *trans; - set_freezable(); do { again = 0; @@ -1782,7 +1796,10 @@ static int cleaner_kthread(void *arg) goto sleep; } + mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex); btrfs_run_delayed_iputs(root); + mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex); + again = btrfs_clean_one_deleted_snapshot(root); mutex_unlock(&root->fs_info->cleaner_mutex); @@ -2542,8 +2559,8 @@ int open_ctree(struct super_block *sb, mutex_init(&fs_info->delete_unused_bgs_mutex); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); + mutex_init(&fs_info->cleaner_delayed_iput_mutex); seqlock_init(&fs_info->profiles_lock); - init_rwsem(&fs_info->delayed_iput_sem); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->space_info); @@ -2668,6 +2685,7 @@ int open_ctree(struct super_block *sb, if (btrfs_check_super_csum(bh->b_data)) { printk(KERN_ERR "BTRFS: superblock checksum mismatch\n"); err = -EINVAL; + brelse(bh); goto fail_alloc; } @@ -2900,6 +2918,18 @@ retry_root_backup: tree_root->commit_root = btrfs_root_node(tree_root); btrfs_set_root_refs(&tree_root->root_item, 1); + mutex_lock(&tree_root->objectid_mutex); + ret = btrfs_find_highest_objectid(tree_root, + &tree_root->highest_objectid); + if (ret) { + mutex_unlock(&tree_root->objectid_mutex); + goto recovery_tree_root; + } + + ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&tree_root->objectid_mutex); + ret = btrfs_read_roots(fs_info, tree_root); if (ret) goto recovery_tree_root; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c4661db2b72a..2368cac1115a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4086,8 +4086,10 @@ commit_trans: !atomic_read(&root->fs_info->open_ioctl_trans)) { need_commit--; - if (need_commit > 0) + if (need_commit > 0) { + btrfs_start_delalloc_roots(fs_info, 0, -1); btrfs_wait_ordered_roots(fs_info, -1); + } trans = btrfs_join_transaction(root); if (IS_ERR(trans)) @@ -4100,11 +4102,12 @@ commit_trans: if (ret) return ret; /* - * make sure that all running delayed iput are - * done + * The cleaner kthread might still be doing iput + * operations. Wait for it to finish so that + * more space is released. */ - down_write(&root->fs_info->delayed_iput_sem); - up_write(&root->fs_info->delayed_iput_sem); + mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex); + mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex); goto again; } else { btrfs_end_transaction(trans, root); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0f09526aa7d9..5e5db3687e34 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1885,7 +1885,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) */ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { - struct dentry *dentry = file->f_path.dentry; + struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 767a6056ac45..07573dc1614a 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -515,7 +515,7 @@ out: return ret; } -static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) +int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) { struct btrfs_path *path; int ret; @@ -555,13 +555,6 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) int ret; mutex_lock(&root->objectid_mutex); - if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) { - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); - if (ret) - goto out; - } - if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) { ret = -ENOSPC; goto out; diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h index ddb347bfee23..c8e864b2d530 100644 --- a/fs/btrfs/inode-map.h +++ b/fs/btrfs/inode-map.h @@ -9,5 +9,6 @@ int btrfs_save_ino_cache(struct btrfs_root *root, struct btrfs_trans_handle *trans); int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a70c5790f8f5..4bc9dbf29a73 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3142,8 +3142,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root) if (empty) return; - down_read(&fs_info->delayed_iput_sem); - spin_lock(&fs_info->delayed_iput_lock); list_splice_init(&fs_info->delayed_iputs, &list); spin_unlock(&fs_info->delayed_iput_lock); @@ -3154,8 +3152,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root) iput(delayed->inode); kfree(delayed); } - - up_read(&root->fs_info->delayed_iput_sem); } /* @@ -5741,6 +5737,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) char *name_ptr; int name_len; int is_curr = 0; /* ctx->pos points to the current index? */ + bool emitted; /* FIXME, use a real flag for deciding about the key type */ if (root->fs_info->tree_root == root) @@ -5769,6 +5766,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (ret < 0) goto err; + emitted = false; while (1) { leaf = path->nodes[0]; slot = path->slots[0]; @@ -5848,6 +5846,7 @@ skip: if (over) goto nopos; + emitted = true; di_len = btrfs_dir_name_len(leaf, di) + btrfs_dir_data_len(leaf, di) + sizeof(*di); di_cur += di_len; @@ -5860,11 +5859,20 @@ next: if (key_type == BTRFS_DIR_INDEX_KEY) { if (is_curr) ctx->pos++; - ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list); + ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted); if (ret) goto nopos; } + /* + * If we haven't emitted any dir entry, we must not touch ctx->pos as + * it was was set to the termination value in previous call. We assume + * that "." and ".." were emitted if we reach this point and set the + * termination value as well for an empty directory. + */ + if (ctx->pos > 2 && !emitted) + goto nopos; + /* Reached end of directory/root. Bump pos past the last item. */ ctx->pos++; @@ -6481,7 +6489,7 @@ out_unlock_inode: static int btrfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { - struct btrfs_trans_handle *trans; + struct btrfs_trans_handle *trans = NULL; struct btrfs_root *root = BTRFS_I(dir)->root; struct inode *inode = d_inode(old_dentry); u64 index; @@ -6507,6 +6515,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, trans = btrfs_start_transaction(root, 5); if (IS_ERR(trans)) { err = PTR_ERR(trans); + trans = NULL; goto fail; } @@ -6540,9 +6549,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, btrfs_log_new_name(trans, inode, NULL, parent); } - btrfs_end_transaction(trans, root); btrfs_balance_delayed_items(root); fail: + if (trans) + btrfs_end_transaction(trans, root); if (drop_inode) { inode_dec_link_count(inode); iput(inode); @@ -7985,6 +7995,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); if (io_bio->end_io) @@ -8030,6 +8041,7 @@ out_test: kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); bio_put(bio); } @@ -8534,15 +8546,28 @@ int btrfs_readpage(struct file *file, struct page *page) static int btrfs_writepage(struct page *page, struct writeback_control *wbc) { struct extent_io_tree *tree; - + struct inode *inode = page->mapping->host; + int ret; if (current->flags & PF_MEMALLOC) { redirty_page_for_writepage(wbc, page); unlock_page(page); return 0; } + + /* + * If we are under memory pressure we will call this directly from the + * VM, we need to make sure we have the inode referenced for the ordered + * extent. If not just return like we didn't do anything. + */ + if (!igrab(inode)) { + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; + } tree = &BTRFS_I(page->mapping->host)->io_tree; - return extent_write_full_page(tree, page, btrfs_get_extent, wbc); + ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc); + btrfs_add_delayed_iput(inode); + return ret; } static int btrfs_writepages(struct address_space *mapping, @@ -9636,9 +9661,11 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, /* * 2 items for inode item and ref * 2 items for dir items + * 1 item for updating parent inode item + * 1 item for the inline extent item * 1 item for xattr if selinux is on */ - trans = btrfs_start_transaction(root, 5); + trans = btrfs_start_transaction(root, 7); if (IS_ERR(trans)) return PTR_ERR(trans); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index da94138eb85e..f07d01bc4875 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -568,6 +568,10 @@ static noinline int create_subvol(struct inode *dir, goto fail; } + mutex_lock(&new_root->objectid_mutex); + new_root->highest_objectid = new_dirid; + mutex_unlock(&new_root->objectid_mutex); + /* * insert the directory item */ @@ -2782,24 +2786,29 @@ out: static struct page *extent_same_get_page(struct inode *inode, pgoff_t index) { struct page *page; - struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; page = grab_cache_page(inode->i_mapping, index); if (!page) - return NULL; + return ERR_PTR(-ENOMEM); if (!PageUptodate(page)) { - if (extent_read_full_page_nolock(tree, page, btrfs_get_extent, - 0)) - return NULL; + int ret; + + ret = btrfs_readpage(NULL, page); + if (ret) + return ERR_PTR(ret); lock_page(page); if (!PageUptodate(page)) { unlock_page(page); page_cache_release(page); - return NULL; + return ERR_PTR(-EIO); + } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + page_cache_release(page); + return ERR_PTR(-EAGAIN); } } - unlock_page(page); return page; } @@ -2811,17 +2820,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages, pgoff_t index = off >> PAGE_CACHE_SHIFT; for (i = 0; i < num_pages; i++) { +again: pages[i] = extent_same_get_page(inode, index + i); - if (!pages[i]) - return -ENOMEM; + if (IS_ERR(pages[i])) { + int err = PTR_ERR(pages[i]); + + if (err == -EAGAIN) + goto again; + pages[i] = NULL; + return err; + } } return 0; } -static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) +static int lock_extent_range(struct inode *inode, u64 off, u64 len, + bool retry_range_locking) { - /* do any pending delalloc/csum calc on src, one way or - another, and lock file content */ + /* + * Do any pending delalloc/csum calculations on inode, one way or + * another, and lock file content. + * The locking order is: + * + * 1) pages + * 2) range in the inode's io tree + */ while (1) { struct btrfs_ordered_extent *ordered; lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); @@ -2839,8 +2862,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); if (ordered) btrfs_put_ordered_extent(ordered); + if (!retry_range_locking) + return -EAGAIN; btrfs_wait_ordered_range(inode, off, len); } + return 0; } static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2) @@ -2865,15 +2891,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1, unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); } -static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1, - struct inode *inode2, u64 loff2, u64 len) +static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len, + bool retry_range_locking) { + int ret; + if (inode1 < inode2) { swap(inode1, inode2); swap(loff1, loff2); } - lock_extent_range(inode1, loff1, len); - lock_extent_range(inode2, loff2, len); + ret = lock_extent_range(inode1, loff1, len, retry_range_locking); + if (ret) + return ret; + ret = lock_extent_range(inode2, loff2, len, retry_range_locking); + if (ret) + unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, + loff1 + len - 1); + return ret; } struct cmp_pages { @@ -2889,11 +2924,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp) for (i = 0; i < cmp->num_pages; i++) { pg = cmp->src_pages[i]; - if (pg) + if (pg) { + unlock_page(pg); page_cache_release(pg); + } pg = cmp->dst_pages[i]; - if (pg) + if (pg) { + unlock_page(pg); page_cache_release(pg); + } } kfree(cmp->src_pages); kfree(cmp->dst_pages); @@ -2954,6 +2993,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, src_page = cmp->src_pages[i]; dst_page = cmp->dst_pages[i]; + ASSERT(PageLocked(src_page)); + ASSERT(PageLocked(dst_page)); addr = kmap_atomic(src_page); dst_addr = kmap_atomic(dst_page); @@ -3066,14 +3107,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, goto out_unlock; } +again: ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp); if (ret) goto out_unlock; if (same_inode) - lock_extent_range(src, same_lock_start, same_lock_len); + ret = lock_extent_range(src, same_lock_start, same_lock_len, + false); else - btrfs_double_extent_lock(src, loff, dst, dst_loff, len); + ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len, + false); + /* + * If one of the inodes has dirty pages in the respective range or + * ordered extents, we need to flush dellaloc and wait for all ordered + * extents in the range. We must unlock the pages and the ranges in the + * io trees to avoid deadlocks when flushing delalloc (requires locking + * pages) and when waiting for ordered extents to complete (they require + * range locking). + */ + if (ret == -EAGAIN) { + /* + * Ranges in the io trees already unlocked. Now unlock all + * pages before waiting for all IO to complete. + */ + btrfs_cmp_data_free(&cmp); + if (same_inode) { + btrfs_wait_ordered_range(src, same_lock_start, + same_lock_len); + } else { + btrfs_wait_ordered_range(src, loff, len); + btrfs_wait_ordered_range(dst, dst_loff, len); + } + goto again; + } + ASSERT(ret == 0); + if (WARN_ON(ret)) { + /* ranges in the io trees already unlocked */ + btrfs_cmp_data_free(&cmp); + return ret; + } /* pass original length for comparison so we stay within i_size */ ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp); @@ -3895,9 +3968,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, u64 lock_start = min_t(u64, off, destoff); u64 lock_len = max_t(u64, off, destoff) + len - lock_start; - lock_extent_range(src, lock_start, lock_len); + ret = lock_extent_range(src, lock_start, lock_len, true); } else { - btrfs_double_extent_lock(src, off, inode, destoff, len); + ret = btrfs_double_extent_lock(src, off, inode, destoff, len, + true); + } + ASSERT(ret == 0); + if (WARN_ON(ret)) { + /* ranges in the io trees already unlocked */ + goto out_unlock; } ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7cf8509deda7..2c849b08a91b 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + if (err == -EEXIST) + err = 0; if (err) { - BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 355a458cba1a..63a6152be04b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1469,7 +1469,21 @@ static int read_symlink(struct btrfs_root *root, ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; - BUG_ON(ret); + if (ret) { + /* + * An empty symlink inode. Can happen in rare error paths when + * creating a symlink (transaction committed before the inode + * eviction handler removed the symlink inode items and a crash + * happened in between or the subvol was snapshoted in between). + * Print an informative message to dmesg/syslog so that the user + * can delete the symlink. + */ + btrfs_err(root->fs_info, + "Found empty symlink inode %llu at root %llu", + ino, root->root_key.objectid); + ret = -EIO; + goto out; + } ei = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_file_extent_item); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 24154e422945..fe609b81dd1b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1956,6 +1956,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) * there are other factors that may change the result (like a new metadata * chunk). * + * If metadata is exhausted, f_bavail will be 0. + * * FIXME: not accurate for mixed block groups, total and free/used are ok, * available appears slightly larger. */ @@ -1967,11 +1969,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) struct btrfs_space_info *found; u64 total_used = 0; u64 total_free_data = 0; + u64 total_free_meta = 0; int bits = dentry->d_sb->s_blocksize_bits; __be32 *fsid = (__be32 *)fs_info->fsid; unsigned factor = 1; struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; int ret; + u64 thresh = 0; /* * holding chunk_muext to avoid allocating new chunks, holding @@ -1997,6 +2001,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) } } } + if (found->flags & BTRFS_BLOCK_GROUP_METADATA) + total_free_meta += found->disk_total - found->disk_used; total_used += found->disk_used; } @@ -2019,6 +2025,24 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail += div_u64(total_free_data, factor); buf->f_bavail = buf->f_bavail >> bits; + /* + * We calculate the remaining metadata space minus global reserve. If + * this is (supposedly) smaller than zero, there's no space. But this + * does not hold in practice, the exhausted state happens where's still + * some positive delta. So we apply some guesswork and compare the + * delta to a 4M threshold. (Practically observed delta was ~2M.) + * + * We probably cannot calculate the exact threshold value because this + * depends on the internal reservations requested by various + * operations, so some operations that consume a few metadata will + * succeed even if the Avail is zero. But this is better than the other + * way around. + */ + thresh = 4 * 1024 * 1024; + + if (total_free_meta - thresh < block_rsv->size) + buf->f_bavail = 0; + buf->f_type = BTRFS_SUPER_MAGIC; buf->f_bsize = dentry->d_sb->s_blocksize; buf->f_namelen = BTRFS_NAME_LEN; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 323e12cc9d2f..0e044d7ee721 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4406,6 +4406,127 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, return ret; } +/* + * When we are logging a new inode X, check if it doesn't have a reference that + * matches the reference from some other inode Y created in a past transaction + * and that was renamed in the current transaction. If we don't do this, then at + * log replay time we can lose inode Y (and all its files if it's a directory): + * + * mkdir /mnt/x + * echo "hello world" > /mnt/x/foobar + * sync + * mv /mnt/x /mnt/y + * mkdir /mnt/x # or touch /mnt/x + * xfs_io -c fsync /mnt/x + * <power fail> + * mount fs, trigger log replay + * + * After the log replay procedure, we would lose the first directory and all its + * files (file foobar). + * For the case where inode Y is not a directory we simply end up losing it: + * + * echo "123" > /mnt/foo + * sync + * mv /mnt/foo /mnt/bar + * echo "abc" > /mnt/foo + * xfs_io -c fsync /mnt/foo + * <power fail> + * + * We also need this for cases where a snapshot entry is replaced by some other + * entry (file or directory) otherwise we end up with an unreplayable log due to + * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as + * if it were a regular entry: + * + * mkdir /mnt/x + * btrfs subvolume snapshot /mnt /mnt/x/snap + * btrfs subvolume delete /mnt/x/snap + * rmdir /mnt/x + * mkdir /mnt/x + * fsync /mnt/x or fsync some new file inside it + * <power fail> + * + * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in + * the same transaction. + */ +static int btrfs_check_ref_name_override(struct extent_buffer *eb, + const int slot, + const struct btrfs_key *key, + struct inode *inode) +{ + int ret; + struct btrfs_path *search_path; + char *name = NULL; + u32 name_len = 0; + u32 item_size = btrfs_item_size_nr(eb, slot); + u32 cur_offset = 0; + unsigned long ptr = btrfs_item_ptr_offset(eb, slot); + + search_path = btrfs_alloc_path(); + if (!search_path) + return -ENOMEM; + search_path->search_commit_root = 1; + search_path->skip_locking = 1; + + while (cur_offset < item_size) { + u64 parent; + u32 this_name_len; + u32 this_len; + unsigned long name_ptr; + struct btrfs_dir_item *di; + + if (key->type == BTRFS_INODE_REF_KEY) { + struct btrfs_inode_ref *iref; + + iref = (struct btrfs_inode_ref *)(ptr + cur_offset); + parent = key->offset; + this_name_len = btrfs_inode_ref_name_len(eb, iref); + name_ptr = (unsigned long)(iref + 1); + this_len = sizeof(*iref) + this_name_len; + } else { + struct btrfs_inode_extref *extref; + + extref = (struct btrfs_inode_extref *)(ptr + + cur_offset); + parent = btrfs_inode_extref_parent(eb, extref); + this_name_len = btrfs_inode_extref_name_len(eb, extref); + name_ptr = (unsigned long)&extref->name; + this_len = sizeof(*extref) + this_name_len; + } + + if (this_name_len > name_len) { + char *new_name; + + new_name = krealloc(name, this_name_len, GFP_NOFS); + if (!new_name) { + ret = -ENOMEM; + goto out; + } + name_len = this_name_len; + name = new_name; + } + + read_extent_buffer(eb, name, name_ptr, this_name_len); + di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root, + search_path, parent, + name, this_name_len, 0); + if (di && !IS_ERR(di)) { + ret = 1; + goto out; + } else if (IS_ERR(di)) { + ret = PTR_ERR(di); + goto out; + } + btrfs_release_path(search_path); + + cur_offset += this_len; + } + ret = 0; +out: + btrfs_free_path(search_path); + kfree(name); + return ret; +} + /* log a single inode in the tree log. * At least one parent directory for this inode must exist in the tree * or be logged already. @@ -4578,6 +4699,22 @@ again: if (min_key.type == BTRFS_INODE_ITEM_KEY) need_log_inode_item = false; + if ((min_key.type == BTRFS_INODE_REF_KEY || + min_key.type == BTRFS_INODE_EXTREF_KEY) && + BTRFS_I(inode)->generation == trans->transid) { + ret = btrfs_check_ref_name_override(path->nodes[0], + path->slots[0], + &min_key, inode); + if (ret < 0) { + err = ret; + goto out_unlock; + } else if (ret > 0) { + err = 1; + btrfs_set_log_full_commit(root->fs_info, trans); + goto out_unlock; + } + } + /* Skip xattrs, we log them later with btrfs_log_all_xattrs() */ if (min_key.type == BTRFS_XATTR_ITEM_KEY) { if (ins_nr == 0) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a23399e8e3ab..9c62a6f9757a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -232,6 +232,7 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); + btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); @@ -1257,6 +1258,15 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction, int ret; int slot; struct extent_buffer *l; + u64 min_search_start; + + /* + * We don't want to overwrite the superblock on the drive nor any area + * used by the boot loader (grub for example), so we make sure to start + * at an offset of at least 1MB. + */ + min_search_start = max(root->fs_info->alloc_start, 1024ull * 1024); + search_start = max(search_start, min_search_start); path = btrfs_alloc_path(); if (!path) @@ -1397,18 +1407,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *len) { - struct btrfs_root *root = device->dev_root; - u64 search_start; - /* FIXME use last free of some kind */ - - /* - * we don't want to overwrite the superblock on the drive, - * so we make sure to start at an offset of at least 1MB - */ - search_start = max(root->fs_info->alloc_start, 1024ull * 1024); return find_free_dev_extent_start(trans->transaction, device, - num_bytes, search_start, start, len); + num_bytes, 0, start, len); } static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans, @@ -6512,6 +6513,14 @@ int btrfs_read_sys_array(struct btrfs_root *root) goto out_short_read; num_stripes = btrfs_chunk_num_stripes(sb, chunk); + if (!num_stripes) { + printk(KERN_ERR + "BTRFS: invalid number of stripes %u in sys_array at offset %u\n", + num_stripes, cur_offset); + ret = -EIO; + break; + } + len = btrfs_chunk_item_size(num_stripes); if (cur_offset + len > array_size) goto out_short_read; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 7febcf2475c5..50b268483302 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -50,7 +50,7 @@ void cifs_vfs_err(const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - pr_err("CIFS VFS: %pV", &vaf); + pr_err_ratelimited("CIFS VFS: %pV", &vaf); va_end(args); } diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index f40fbaca1b2a..66cf0f9fff89 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -51,14 +51,13 @@ __printf(1, 2) void cifs_vfs_err(const char *fmt, ...); /* information message: e.g., configuration, major event */ #define cifs_dbg(type, fmt, ...) \ do { \ - if (type == FYI) { \ - if (cifsFYI & CIFS_INFO) { \ - pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__); \ - } \ + if (type == FYI && cifsFYI & CIFS_INFO) { \ + pr_debug_ratelimited("%s: " \ + fmt, __FILE__, ##__VA_ARGS__); \ } else if (type == VFS) { \ cifs_vfs_err(fmt, ##__VA_ARGS__); \ } else if (type == NOISY && type != 0) { \ - pr_debug(fmt, ##__VA_ARGS__); \ + pr_debug_ratelimited(fmt, ##__VA_ARGS__); \ } \ } while (0) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index afa09fce8151..e682b36a210f 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -714,7 +714,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL); if (!ses->auth_key.response) { - rc = ENOMEM; + rc = -ENOMEM; ses->auth_key.len = 0; goto setup_ntlmv2_rsp_ret; } diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index c3cc1609025f..44b3d4280abb 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -31,19 +31,15 @@ * so that it will fit. We use hash_64 to convert the value to 31 bits, and * then add 1, to ensure that we don't end up with a 0 as the value. */ -#if BITS_PER_LONG == 64 static inline ino_t cifs_uniqueid_to_ino_t(u64 fileid) { + if ((sizeof(ino_t)) < (sizeof(u64))) + return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; + return (ino_t)fileid; + } -#else -static inline ino_t -cifs_uniqueid_to_ino_t(u64 fileid) -{ - return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; -} -#endif extern struct file_system_type cifs_fs_type; extern const struct address_space_operations cifs_addr_ops; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 90b4f9f7de66..76fcb50295a3 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1396,11 +1396,10 @@ openRetry: * current bigbuf. */ static int -cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +discard_remaining_data(struct TCP_Server_Info *server) { unsigned int rfclen = get_rfc1002_length(server->smallbuf); int remaining = rfclen + 4 - server->total_read; - struct cifs_readdata *rdata = mid->callback_data; while (remaining > 0) { int length; @@ -1414,10 +1413,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) remaining -= length; } - dequeue_mid(mid, rdata->result); return 0; } +static int +cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +{ + int length; + struct cifs_readdata *rdata = mid->callback_data; + + length = discard_remaining_data(server); + dequeue_mid(mid, rdata->result); + return length; +} + int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { @@ -1446,6 +1455,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; + if (server->ops->is_status_pending && + server->ops->is_status_pending(buf, server, 0)) { + discard_remaining_data(server); + return -1; + } + /* Was the SMB read successful? */ rdata->result = server->ops->map_error(buf, false); if (rdata->result != 0) { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ecb0803bdb0e..3c194ff0d2f0 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -368,7 +368,6 @@ cifs_reconnect(struct TCP_Server_Info *server) server->session_key.response = NULL; server->session_key.len = 0; server->lstrp = jiffies; - mutex_unlock(&server->srv_mutex); /* mark submitted MIDs for retry and issue callback */ INIT_LIST_HEAD(&retry_list); @@ -381,6 +380,7 @@ cifs_reconnect(struct TCP_Server_Info *server) list_move(&mid_entry->qhead, &retry_list); } spin_unlock(&GlobalMid_Lock); + mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); list_for_each_safe(tmp, tmp2, &retry_list) { diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 0557c45e9c33..b30a4a6d98a0 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -847,6 +847,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) * if buggy server returns . and .. late do we want to * check for that here? */ + *tmp_buf = 0; rc = cifs_filldir(current_entry, file, ctx, tmp_buf, max_len); if (rc) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 767555518d40..373b5cd1c913 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1109,21 +1109,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, { char *data_offset; struct create_context *cc; - unsigned int next = 0; + unsigned int next; + unsigned int remaining; char *name; data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset); + remaining = le32_to_cpu(rsp->CreateContextsLength); cc = (struct create_context *)data_offset; - do { - cc = (struct create_context *)((char *)cc + next); + while (remaining >= sizeof(struct create_context)) { name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) != 4 || - strncmp(name, "RqLs", 4)) { - next = le32_to_cpu(cc->Next); - continue; - } - return server->ops->parse_lease_buf(cc, epoch); - } while (next != 0); + if (le16_to_cpu(cc->NameLength) == 4 && + strncmp(name, "RqLs", 4) == 0) + return server->ops->parse_lease_buf(cc, epoch); + + next = le32_to_cpu(cc->Next); + if (!next) + break; + remaining -= next; + cc = (struct create_context *)((char *)cc + next); + } return 0; } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 2a24c524fb9a..87abe8ed074c 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -576,14 +576,16 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, cifs_in_send_dec(server); cifs_save_when_sent(mid); - if (rc < 0) + if (rc < 0) { server->sequence_number -= 2; + cifs_delete_mid(mid); + } + mutex_unlock(&server->srv_mutex); if (rc == 0) return 0; - cifs_delete_mid(mid); add_credits_and_wake_if(server, credits, optype); return rc; } diff --git a/fs/coredump.c b/fs/coredump.c index 1777331eee76..dfc87c5f5a54 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -32,6 +32,9 @@ #include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/compat.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/path.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -627,6 +630,8 @@ void do_coredump(const siginfo_t *siginfo) } } else { struct inode *inode; + int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW | + O_LARGEFILE | O_EXCL; if (cprm.limit < binfmt->min_coredump) goto fail_unlock; @@ -665,10 +670,27 @@ void do_coredump(const siginfo_t *siginfo) * what matters is that at least one of the two processes * writes its coredump successfully, not which one. */ - cprm.file = filp_open(cn.corename, - O_CREAT | 2 | O_NOFOLLOW | - O_LARGEFILE | O_EXCL, - 0600); + if (need_suid_safe) { + /* + * Using user namespaces, normal user tasks can change + * their current->fs->root to point to arbitrary + * directories. Since the intention of the "only dump + * with a fully qualified path" rule is to control where + * coredumps may be placed using root privileges, + * current->fs->root must not be used. Instead, use the + * root directory of init_task. + */ + struct path root; + + task_lock(&init_task); + get_fs_root(init_task.fs, &root); + task_unlock(&init_task); + cprm.file = file_open_root(root.dentry, root.mnt, + cn.corename, open_flags, 0600); + path_put(&root); + } else { + cprm.file = filp_open(cn.corename, open_flags, 0600); + } if (IS_ERR(cprm.file)) goto fail_unlock; diff --git a/fs/dcache.c b/fs/dcache.c index 5c33aeb0f68f..240935d77844 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } -/* - * Make sure other CPUs see the inode attached before the type is set. - */ static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry, unsigned flags; dentry->d_inode = inode; - smp_wmb(); flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; WRITE_ONCE(dentry->d_flags, flags); } -/* - * Ideally, we want to make sure that other CPUs see the flags cleared before - * the inode is detached, but this is really a violation of RCU principles - * since the ordering suggests we should always set inode before flags. - * - * We should instead replace or discard the entire dentry - but that sucks - * performancewise on mass deletion/rename. - */ static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); - smp_wmb(); dentry->d_inode = NULL; } @@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; + + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -1677,7 +1666,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | - DCACHE_OP_SELECT_INODE)); + DCACHE_OP_SELECT_INODE | + DCACHE_OP_REAL)); dentry->d_op = op; if (!op) return; @@ -1695,6 +1685,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_select_inode) dentry->d_flags |= DCACHE_OP_SELECT_INODE; + if (op->d_real) + dentry->d_flags |= DCACHE_OP_REAL; } EXPORT_SYMBOL(d_set_d_op); @@ -1757,8 +1749,9 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); if (inode) hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); fsnotify_d_instantiate(dentry, inode); } @@ -3027,6 +3020,7 @@ char *d_absolute_path(const struct path *path, return ERR_PTR(error); return res; } +EXPORT_SYMBOL(d_absolute_path); /* * same as __d_path but appends "(deleted)" for unlinked files. diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index b7fcc0de0b2f..0f5d05bf2131 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -457,7 +457,7 @@ struct dentry *debugfs_create_automount(const char *name, if (unlikely(!inode)) return failed_creating(dentry); - inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; dentry->d_fsdata = (void *)f; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index c35ffdc12bba..706de324f2a6 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) mutex_unlock(&allocated_ptys_lock); } +/* + * pty code needs to hold extra references in case of last /dev/tty close + */ + +void devpts_add_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + atomic_inc(&sb->s_active); + ihold(ptmx_inode); +} + +void devpts_del_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + iput(ptmx_inode); + deactivate_super(sb); +} + /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master diff --git a/fs/direct-io.c b/fs/direct-io.c index 602e8441bc0f..01171d8a6ee9 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -472,8 +472,8 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) dio->io_error = -EIO; if (dio->is_async && dio->rw == READ && dio->should_dirty) { - bio_check_pages_dirty(bio); /* transfers ownership */ err = bio->bi_error; + bio_check_pages_dirty(bio); /* transfers ownership */ } else { bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 90001da9abfd..66842e55c48c 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -10,6 +10,7 @@ #include <linux/efi.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/mount.h> #include "internal.h" @@ -103,9 +104,78 @@ out_free: return size; } +static int +efivarfs_ioc_getxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int i_flags; + unsigned int flags = 0; + + i_flags = inode->i_flags; + if (i_flags & S_IMMUTABLE) + flags |= FS_IMMUTABLE_FL; + + if (copy_to_user(arg, &flags, sizeof(flags))) + return -EFAULT; + return 0; +} + +static int +efivarfs_ioc_setxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int flags; + unsigned int i_flags = 0; + int error; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (copy_from_user(&flags, arg, sizeof(flags))) + return -EFAULT; + + if (flags & ~FS_IMMUTABLE_FL) + return -EOPNOTSUPP; + + if (!capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + if (flags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + + + error = mnt_want_write_file(file); + if (error) + return error; + + mutex_lock(&inode->i_mutex); + inode_set_flags(inode, i_flags, S_IMMUTABLE); + mutex_unlock(&inode->i_mutex); + + mnt_drop_write_file(file); + + return 0; +} + +long +efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p) +{ + void __user *arg = (void __user *)p; + + switch (cmd) { + case FS_IOC_GETFLAGS: + return efivarfs_ioc_getxflags(file, arg); + case FS_IOC_SETFLAGS: + return efivarfs_ioc_setxflags(file, arg); + } + + return -ENOTTY; +} + const struct file_operations efivarfs_file_operations = { .open = simple_open, .read = efivarfs_file_read, .write = efivarfs_file_write, .llseek = no_llseek, + .unlocked_ioctl = efivarfs_file_ioctl, }; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 3381b9da9ee6..e2ab6d0497f2 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -15,7 +15,8 @@ #include "internal.h" struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev) + const struct inode *dir, int mode, + dev_t dev, bool is_removable) { struct inode *inode = new_inode(sb); @@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_flags = is_removable ? 0 : S_IMMUTABLE; switch (mode & S_IFMT) { case S_IFREG: inode->i_fop = &efivarfs_file_operations; @@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid) static int efivarfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct inode *inode; + struct inode *inode = NULL; struct efivar_entry *var; int namelen, i = 0, err = 0; + bool is_removable = false; if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len)) return -EINVAL; - inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0); - if (!inode) - return -ENOMEM; - var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); - if (!var) { - err = -ENOMEM; - goto out; - } + if (!var) + return -ENOMEM; /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; @@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + if (efivar_variable_is_removable(var->var.VendorGuid, + dentry->d_name.name, namelen)) + is_removable = true; + + inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable); + if (!inode) { + err = -ENOMEM; + goto out; + } + for (i = 0; i < namelen; i++) var->var.VariableName[i] = dentry->d_name.name[i]; @@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, out: if (err) { kfree(var); - iput(inode); + if (inode) + iput(inode); } return err; } diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index b5ff16addb7c..b4505188e799 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev); + const struct inode *dir, int mode, dev_t dev, + bool is_removable); extern struct list_head efivarfs_list; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 86a2121828c3..abb244b06024 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -118,8 +118,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, struct dentry *dentry, *root = sb->s_root; unsigned long size = 0; char *name; - int len, i; + int len; int err = -ENOMEM; + bool is_removable = false; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) @@ -128,15 +129,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, memcpy(entry->var.VariableName, name16, name_size); memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t)); - len = ucs2_strlen(entry->var.VariableName); + len = ucs2_utf8size(entry->var.VariableName); /* name, plus '-', plus GUID, plus NUL*/ name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL); if (!name) goto fail; - for (i = 0; i < len; i++) - name[i] = entry->var.VariableName[i] & 0xFF; + ucs2_as_utf8(name, entry->var.VariableName, len); + + if (efivar_variable_is_removable(entry->var.VendorGuid, name, len)) + is_removable = true; name[len] = '-'; @@ -144,7 +147,8 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; - inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0); + inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, + is_removable); if (!inode) goto fail_name; @@ -200,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_d_op = &efivarfs_d_ops; sb->s_time_gran = 1; - inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0); + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true); if (!inode) return -ENOMEM; inode->i_op = &efivarfs_dir_inode_operations; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index ec0668a60678..fe1f50fe764f 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { - err = ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init block bitmap for group " + "%u: %d", block_group, err); goto out; + } goto verify; } ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c index c5882b36e558..9a16d1e75a49 100644 --- a/fs/ext4/crypto_key.c +++ b/fs/ext4/crypto_key.c @@ -213,9 +213,11 @@ retry: res = -ENOKEY; goto out; } + down_read(&keyring_key->sem); ukp = user_key_payload(keyring_key); if (ukp->datalen != sizeof(struct ext4_encryption_key)) { res = -EINVAL; + up_read(&keyring_key->sem); goto out; } master_key = (struct ext4_encryption_key *)ukp->data; @@ -226,10 +228,12 @@ retry: "ext4: key size incorrect: %d\n", master_key->size); res = -ENOKEY; + up_read(&keyring_key->sem); goto out; } res = ext4_derive_key_aes(ctx.nonce, master_key->raw, raw_key); + up_read(&keyring_key->sem); if (res) goto out; got_key: diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5cf6d8be48dd..daad932eeb38 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -850,6 +850,29 @@ do { \ #include "extents_status.h" /* + * Lock subclasses for i_data_sem in the ext4_inode_info structure. + * + * These are needed to avoid lockdep false positives when we need to + * allocate blocks to the quota inode during ext4_map_blocks(), while + * holding i_data_sem for a normal (non-quota) inode. Since we don't + * do quota tracking for the quota inode, this avoids deadlock (as + * well as infinite recursion, since it isn't turtles all the way + * down...) + * + * I_DATA_SEM_NORMAL - Used for most inodes + * I_DATA_SEM_OTHER - Used by move_inode.c for the second normal inode + * where the second inode has larger inode number + * than the first + * I_DATA_SEM_QUOTA - Used for quota inodes only + */ +enum { + I_DATA_SEM_NORMAL = 0, + I_DATA_SEM_OTHER, + I_DATA_SEM_QUOTA, +}; + + +/* * fourth extended file system inode data in memory */ struct ext4_inode_info { @@ -910,6 +933,15 @@ struct ext4_inode_info { * by other means, so we have i_data_sem. */ struct rw_semaphore i_data_sem; + /* + * i_mmap_sem is for serializing page faults with truncate / punch hole + * operations. We have to make sure that new page cannot be faulted in + * a section of the inode that is being punched. We cannot easily use + * i_data_sem for this since we need protection for the whole punch + * operation and i_data_sem ranks below transaction start so we have + * to occasionally drop it. + */ + struct rw_semaphore i_mmap_sem; struct inode vfs_inode; struct jbd2_inode *jinode; @@ -2485,6 +2517,7 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); +extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); @@ -2849,6 +2882,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize) return changed; } +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len); + struct ext4_group_info { unsigned long bb_state; struct rb_root bb_free_root; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 551353b1b17a..3578b25fccfd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4685,10 +4685,6 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, if (len <= EXT_UNWRITTEN_MAX_LEN) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - /* * credits to insert 1 extent into extent tree */ @@ -4752,8 +4748,6 @@ retry: goto retry; } - ext4_inode_resume_unlocked_dio(inode); - return ret > 0 ? ret2 : ret; } @@ -4770,7 +4764,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, int partial_begin, partial_end; loff_t start, end; ext4_lblk_t lblk; - struct address_space *mapping = inode->i_mapping; unsigned int blkbits = inode->i_blkbits; trace_ext4_zero_range(inode, offset, len, mode); @@ -4786,17 +4779,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, } /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - ret = filemap_write_and_wait_range(mapping, offset, - offset + len - 1); - if (ret) - return ret; - } - - /* * Round up offset. This is not fallocate, we neet to zero out * blocks, so convert interior block aligned part of the range to * unwritten and possibly manually zero out unaligned parts of the @@ -4839,6 +4821,10 @@ static long ext4_zero_range(struct file *file, loff_t offset, if (mode & FALLOC_FL_KEEP_SIZE) flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4847,7 +4833,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, round_down(offset, 1 << blkbits)) >> blkbits, new_size, flags, mode); if (ret) - goto out_mutex; + goto out_dio; } @@ -4856,16 +4842,23 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); - /* Now release the pages and zero block aligned part of pages*/ + /* + * Prevent page faults from reinstantiating pages we have + * released from page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + ret = ext4_update_disksize_before_punch(inode, offset, len); + if (ret) { + up_write(&EXT4_I(inode)->i_mmap_sem); + goto out_dio; + } + /* Now release the pages and zero block aligned part of pages */ truncate_pagecache_range(inode, start, end - 1); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags, mode); + up_write(&EXT4_I(inode)->i_mmap_sem); if (ret) goto out_dio; } @@ -4998,8 +4991,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto out; } + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags, mode); + ext4_inode_resume_unlocked_dio(inode); if (ret) goto out; @@ -5494,21 +5492,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) return ret; } - /* - * Need to round down offset to be aligned with page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - return ret; - - /* Take mutex lock */ mutex_lock(&inode->i_mutex); - /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation @@ -5524,17 +5508,43 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - truncate_pagecache(inode, ioffset); - /* Wait for existing dio to complete */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + /* + * Need to round down offset to be aligned with page size boundary + * for page size > block size. + */ + ioffset = round_down(offset, PAGE_SIZE); + /* + * Write tail of the last page before removed range since it will get + * removed from the page cache below. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset); + if (ret) + goto out_mmap; + /* + * Write data that will be shifted to preserve them when discarding + * page cache below. We are also protected from pages becoming dirty + * by i_mmap_sem. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset + len, + LLONG_MAX); + if (ret) + goto out_mmap; + truncate_pagecache(inode, ioffset); + credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_dio; + goto out_mmap; } down_write(&EXT4_I(inode)->i_data_sem); @@ -5573,7 +5583,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); -out_dio: +out_mmap: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); @@ -5627,21 +5638,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) return ret; } - /* - * Need to round down to align start offset to page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - return ret; - - /* Take mutex lock */ mutex_lock(&inode->i_mutex); - /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ret = -EOPNOTSUPP; @@ -5660,17 +5657,32 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - truncate_pagecache(inode, ioffset); - /* Wait for existing dio to complete */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + /* + * Need to round down to align start offset to page size boundary + * for page size > block size. + */ + ioffset = round_down(offset, PAGE_SIZE); + /* Write out all dirty pages */ + ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, + LLONG_MAX); + if (ret) + goto out_mmap; + truncate_pagecache(inode, ioffset); + credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_dio; + goto out_mmap; } /* Expand file to avoid data loss if there is error while shifting */ @@ -5741,7 +5753,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); -out_dio: +out_mmap: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 113837e7ba98..0d24ebcd7c9e 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -209,15 +209,18 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { int result; handle_t *handle = NULL; - struct super_block *sb = file_inode(vma->vm_file)->i_sb; + struct inode *inode = file_inode(vma->vm_file); + struct super_block *sb = inode->i_sb; bool write = vmf->flags & FAULT_FLAG_WRITE; if (write) { sb_start_pagefault(sb); file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, EXT4_DATA_TRANS_BLOCKS(sb)); - } + } else + down_read(&EXT4_I(inode)->i_mmap_sem); if (IS_ERR(handle)) result = VM_FAULT_SIGBUS; @@ -228,8 +231,10 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) if (write) { if (!IS_ERR(handle)) ext4_journal_stop(handle); + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); - } + } else + up_read(&EXT4_I(inode)->i_mmap_sem); return result; } @@ -246,10 +251,12 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, if (write) { sb_start_pagefault(sb); file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, ext4_chunk_trans_blocks(inode, PMD_SIZE / PAGE_SIZE)); - } + } else + down_read(&EXT4_I(inode)->i_mmap_sem); if (IS_ERR(handle)) result = VM_FAULT_SIGBUS; @@ -260,30 +267,71 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, if (write) { if (!IS_ERR(handle)) ext4_journal_stop(handle); + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); - } + } else + up_read(&EXT4_I(inode)->i_mmap_sem); return result; } static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { - return dax_mkwrite(vma, vmf, ext4_get_block_dax, - ext4_end_io_unwritten); + int err; + struct inode *inode = file_inode(vma->vm_file); + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); + err = __dax_mkwrite(vma, vmf, ext4_get_block_dax, + ext4_end_io_unwritten); + up_read(&EXT4_I(inode)->i_mmap_sem); + sb_end_pagefault(inode->i_sb); + + return err; +} + +/* + * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite() + * handler we check for races agaist truncate. Note that since we cycle through + * i_mmap_sem, we are sure that also any hole punching that began before we + * were called is finished by now and so if it included part of the file we + * are working on, our pte will get unmapped and the check for pte_same() in + * wp_pfn_shared() fails. Thus fault gets retried and things work out as + * desired. + */ +static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + struct super_block *sb = inode->i_sb; + int ret = VM_FAULT_NOPAGE; + loff_t size; + + sb_start_pagefault(sb); + file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (vmf->pgoff >= size) + ret = VM_FAULT_SIGBUS; + up_read(&EXT4_I(inode)->i_mmap_sem); + sb_end_pagefault(sb); + + return ret; } static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .pmd_fault = ext4_dax_pmd_fault, .page_mkwrite = ext4_dax_mkwrite, - .pfn_mkwrite = dax_pfn_mkwrite, + .pfn_mkwrite = ext4_dax_pfn_mkwrite, }; #else #define ext4_dax_vm_ops ext4_file_vm_ops #endif static const struct vm_operations_struct ext4_file_vm_ops = { - .fault = filemap_fault, + .fault = ext4_filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, }; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 1b8024d26f65..53f2b98a69f3 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks and inodes use to prevent * allocation, essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init inode bitmap for group " + "%u: %d", block_group, err); goto out; + } return bh; } ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ea433a7f4bca..e31d762eedce 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -657,6 +657,34 @@ has_zeroout: return retval; } +/* + * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages + * we have to be careful as someone else may be manipulating b_state as well. + */ +static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) +{ + unsigned long old_state; + unsigned long new_state; + + flags &= EXT4_MAP_FLAGS; + + /* Dummy buffer_head? Set non-atomically. */ + if (!bh->b_page) { + bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags; + return; + } + /* + * Someone else may be modifying b_state. Be careful! This is ugly but + * once we get rid of using bh as a container for mapping information + * to pass to / from get_block functions, this can go away. + */ + do { + old_state = READ_ONCE(bh->b_state); + new_state = (old_state & ~EXT4_MAP_FLAGS) | flags; + } while (unlikely( + cmpxchg(&bh->b_state, old_state, new_state) != old_state)); +} + /* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS 4096 @@ -693,7 +721,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, ext4_io_end_t *io_end = ext4_inode_aio(inode); map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (IS_DAX(inode) && buffer_unwritten(bh)) { /* * dgc: I suspect unwritten conversion on ext4+DAX is @@ -1669,7 +1697,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return ret; map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked @@ -3559,6 +3587,35 @@ int ext4_can_truncate(struct inode *inode) } /* + * We have to make sure i_disksize gets properly updated before we truncate + * page cache due to hole punching or zero range. Otherwise i_disksize update + * can get lost as it may have been postponed to submission of writeback but + * that will never happen after we truncate page cache. + */ +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len) +{ + handle_t *handle; + loff_t size = i_size_read(inode); + + WARN_ON(!mutex_is_locked(&inode->i_mutex)); + if (offset > size || offset + len < size) + return 0; + + if (EXT4_I(inode)->i_disksize >= size) + return 0; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_update_i_disksize(inode, size); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + + return 0; +} + +/* * ext4_punch_hole: punches a hole in a file by releaseing the blocks * associated with the given offset and length * @@ -3623,17 +3680,26 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) } + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); first_block_offset = round_up(offset, sb->s_blocksize); last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; /* Now release the pages and zero block aligned part of pages*/ - if (last_block_offset > first_block_offset) + if (last_block_offset > first_block_offset) { + ret = ext4_update_disksize_before_punch(inode, offset, length); + if (ret) + goto out_dio; truncate_pagecache_range(inode, first_block_offset, last_block_offset); - - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); + } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); @@ -3680,16 +3746,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) if (IS_SYNC(inode)) ext4_handle_sync(handle); - /* Now release the pages again to reduce race window */ - if (last_block_offset > first_block_offset) - truncate_pagecache_range(inode, first_block_offset, - last_block_offset); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); out_stop: ext4_journal_stop(handle); out_dio: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); @@ -4823,6 +4885,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } else ext4_wait_for_tail_page_commit(inode); } + down_write(&EXT4_I(inode)->i_mmap_sem); /* * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. @@ -4830,6 +4893,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) truncate_pagecache(inode, inode->i_size); if (shrink) ext4_truncate(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); } if (!rc) { @@ -5081,6 +5145,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) might_sleep(); trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + return err; if (ext4_handle_valid(handle) && EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize && !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { @@ -5111,9 +5177,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) } } } - if (!err) - err = ext4_mark_iloc_dirty(handle, inode, &iloc); - return err; + return ext4_mark_iloc_dirty(handle, inode, &iloc); } /* @@ -5278,6 +5342,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); + + down_read(&EXT4_I(inode)->i_mmap_sem); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && @@ -5347,6 +5413,19 @@ retry_alloc: out_ret: ret = block_page_mkwrite_return(ret); out: + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(inode->i_sb); return ret; } + +int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + int err; + + down_read(&EXT4_I(inode)->i_mmap_sem); + err = filemap_fault(vma, vmf); + up_read(&EXT4_I(inode)->i_mmap_sem); + + return err; +} diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index fb6f11709ae6..9bdbf98240a0 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -60,10 +60,10 @@ ext4_double_down_write_data_sem(struct inode *first, struct inode *second) { if (first < second) { down_write(&EXT4_I(first)->i_data_sem); - down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING); + down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER); } else { down_write(&EXT4_I(second)->i_data_sem); - down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING); + down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER); } } @@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int tmp_data_size, data_size, replaced_size; - int err2, jblocks, retries = 0; + int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; + struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because @@ -380,8 +381,16 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, replaced_size, - ext4_get_block); + if (!page_has_buffers(pagep[0])) + create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); + bh = page_buffers(pagep[0]); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + for (i = 0; i < block_len_in_page; i++) { + *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); + if (*err < 0) + break; + } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); @@ -474,6 +483,13 @@ mext_check_arguments(struct inode *orig_inode, return -EBUSY; } + if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) { + ext4_debug("ext4 move extent: The argument files should " + "not be quota files [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EBUSY; + } + /* Ext4 move extent supports only extent based file */ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) { ext4_debug("ext4 move extent: orig file is not extents " diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ad62d7acc315..34038e3598d5 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data)) + if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) goto out2; flex_gd->count = flexbg_size; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c9ab67da6e5a..852c26806af2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -958,6 +958,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); init_rwsem(&ei->i_data_sem); + init_rwsem(&ei->i_mmap_sem); inode_init_once(&ei->vfs_inode); } @@ -1292,9 +1293,9 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) return -1; } if (ext4_has_feature_quota(sb)) { - ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options " - "when QUOTA feature is enabled"); - return -1; + ext4_msg(sb, KERN_INFO, "Journaled quota options " + "ignored when QUOTA feature is enabled"); + return 1; } qname = match_strdup(args); if (!qname) { @@ -1657,10 +1658,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, return -1; } if (ext4_has_feature_quota(sb)) { - ext4_msg(sb, KERN_ERR, - "Cannot set journaled quota options " + ext4_msg(sb, KERN_INFO, + "Quota format mount options ignored " "when QUOTA feature is enabled"); - return -1; + return 1; } sbi->s_jquota_fmt = m->mount_opt; #endif @@ -1721,11 +1722,11 @@ static int parse_options(char *options, struct super_block *sb, #ifdef CONFIG_QUOTA if (ext4_has_feature_quota(sb) && (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) { - ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA " - "feature is enabled"); - return 0; - } - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { + ext4_msg(sb, KERN_INFO, "Quota feature enabled, usrquota and grpquota " + "mount options ignored."); + clear_opt(sb, USRQUOTA); + clear_opt(sb, GRPQUOTA); + } else if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) clear_opt(sb, USRQUOTA); @@ -4936,6 +4937,20 @@ static int ext4_quota_on_mount(struct super_block *sb, int type) EXT4_SB(sb)->s_jquota_fmt, type); } +static void lockdep_set_quota_inode(struct inode *inode, int subclass) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + + /* The first argument of lockdep_set_subclass has to be + * *exactly* the same as the argument to init_rwsem() --- in + * this case, in init_once() --- or lockdep gets unhappy + * because the name of the lock is set using the + * stringification of the argument to init_rwsem(). + */ + (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ + lockdep_set_subclass(&ei->i_data_sem, subclass); +} + /* * Standard function to be called on quota_on */ @@ -4975,8 +4990,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, if (err) return err; } - - return dquot_quota_on(sb, type, format_id, path); + lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA); + err = dquot_quota_on(sb, type, format_id, path); + if (err) + lockdep_set_quota_inode(path->dentry->d_inode, + I_DATA_SEM_NORMAL); + return err; } static int ext4_quota_enable(struct super_block *sb, int type, int format_id, @@ -5002,8 +5021,11 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, /* Don't account quota for quota files to avoid recursion */ qf_inode->i_flags |= S_NOQUOTA; + lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA); err = dquot_enable(qf_inode, type, format_id, flags); iput(qf_inode); + if (err) + lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL); return err; } diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h index 011ba6670d99..c70d06a383e2 100644 --- a/fs/ext4/truncate.h +++ b/fs/ext4/truncate.h @@ -10,8 +10,10 @@ */ static inline void ext4_truncate_failed_write(struct inode *inode) { + down_write(&EXT4_I(inode)->i_mmap_sem); truncate_inode_pages(inode->i_mapping, inode->i_size); ext4_truncate(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); } /* diff --git a/fs/fhandle.c b/fs/fhandle.c index d59712dfa3e7..ca3c3dd01789 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -228,7 +228,7 @@ long do_handle_open(int mountdirfd, path_put(&path); return fd; } - file = file_open_root(path.dentry, path.mnt, "", open_flag); + file = file_open_root(path.dentry, path.mnt, "", open_flag, 0); if (IS_ERR(file)) { put_unused_fd(fd); retval = PTR_ERR(file); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 28cd6508f4aa..de11206dda63 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi, #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ +static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); +static struct workqueue_struct *isw_wq; + void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -278,13 +281,15 @@ locked_inode_to_wb_and_lock_list(struct inode *inode) wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); - wb_put(wb); /* not gonna deref it anymore */ /* i_wb may have changed inbetween, can't use inode_to_wb() */ - if (likely(wb == inode->i_wb)) - return wb; /* @inode already has ref */ + if (likely(wb == inode->i_wb)) { + wb_put(wb); /* @inode already has ref */ + return wb; + } spin_unlock(&wb->list_lock); + wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } @@ -424,6 +429,8 @@ skip_switch: iput(inode); kfree(isw); + + atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) @@ -433,7 +440,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); - schedule_work(&isw->work); + queue_work(isw_wq, &isw->work); } /** @@ -469,7 +476,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); - if (inode->i_state & (I_WB_SWITCH | I_FREEING) || + if (!(inode->i_sb->s_flags & MS_ACTIVE) || + inode->i_state & (I_WB_SWITCH | I_FREEING) || inode_to_wb(inode) == isw->new_wb) { spin_unlock(&inode->i_lock); goto out_free; @@ -480,6 +488,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) ihold(inode); isw->inode = inode; + atomic_inc(&isw_nr_in_flight); + /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the mapping's @@ -842,6 +852,33 @@ restart: wb_put(last_wb); } +/** + * cgroup_writeback_umount - flush inode wb switches for umount + * + * This function is called when a super_block is about to be destroyed and + * flushes in-flight inode wb switches. An inode wb switch goes through + * RCU and then workqueue, so the two need to be flushed in order to ensure + * that all previously scheduled switches are finished. As wb switches are + * rare occurrences and synchronize_rcu() can take a while, perform + * flushing iff wb switches are in flight. + */ +void cgroup_writeback_umount(void) +{ + if (atomic_read(&isw_nr_in_flight)) { + synchronize_rcu(); + flush_workqueue(isw_wq); + } +} + +static int __init cgroup_writeback_init(void) +{ + isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); + if (!isw_wq) + return -ENOMEM; + return 0; +} +fs_initcall(cgroup_writeback_init); + #else /* CONFIG_CGROUP_WRITEBACK */ static struct bdi_writeback * @@ -1304,10 +1341,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() * and does more profound writeback list handling in writeback_sb_inodes(). */ -static int -writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, - struct writeback_control *wbc) +static int writeback_single_inode(struct inode *inode, + struct writeback_control *wbc) { + struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); @@ -1345,7 +1382,8 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); - spin_lock(&wb->list_lock); + + wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If inode is clean, remove it from writeback lists. Otherwise don't @@ -1420,6 +1458,7 @@ static long writeback_sb_inodes(struct super_block *sb, while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); + struct bdi_writeback *tmp_wb; if (inode->i_sb != sb) { if (work->sb) { @@ -1510,15 +1549,23 @@ static long writeback_sb_inodes(struct super_block *sb, cond_resched(); } - - spin_lock(&wb->list_lock); + /* + * Requeue @inode if still dirty. Be careful as @inode may + * have been switched to another wb in the meantime. + */ + tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) wrote++; - requeue_inode(inode, wb, &wbc); + requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); + if (unlikely(tmp_wb != wb)) { + spin_unlock(&tmp_wb->list_lock); + spin_lock(&wb->list_lock); + } + /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. @@ -2305,7 +2352,6 @@ EXPORT_SYMBOL(sync_inodes_sb); */ int write_inode_now(struct inode *inode, int sync) { - struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, @@ -2317,7 +2363,7 @@ int write_inode_now(struct inode *inode, int sync) wbc.nr_to_write = 0; might_sleep(); - return writeback_single_inode(inode, wb, &wbc); + return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); @@ -2334,7 +2380,7 @@ EXPORT_SYMBOL(write_inode_now); */ int sync_inode(struct inode *inode, struct writeback_control *wbc) { - return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc); + return writeback_single_inode(inode, wbc); } EXPORT_SYMBOL(sync_inode); diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 8e3ee1936c7e..c5b6b7165489 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -90,7 +90,7 @@ static struct list_head *cuse_conntbl_head(dev_t devt) static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to) { - struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp }; + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp); loff_t pos = 0; return fuse_direct_io(&io, to, &pos, FUSE_DIO_CUSE); @@ -98,7 +98,7 @@ static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to) static ssize_t cuse_write_iter(struct kiocb *kiocb, struct iov_iter *from) { - struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp }; + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp); loff_t pos = 0; /* * No locking or generic_write_checks(), the server is diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 175fcdeabe4c..8932c06e40c1 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -13,6 +13,7 @@ #include <linux/poll.h> #include <linux/uio.h> #include <linux/miscdevice.h> +#include <linux/namei.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/slab.h> @@ -1935,6 +1936,10 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, cs->move_pages = 0; err = copy_out_args(cs, &req->out, nbytes); + if (req->in.h.opcode == FUSE_CANONICAL_PATH) { + req->out.h.error = kern_path((char *)req->out.args[0].value, 0, + req->canonical_path); + } fuse_copy_finish(cs); spin_lock(&fpq->lock); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 5e2e08712d3b..24df0a5df675 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -267,6 +267,50 @@ invalid: goto out; } +/* + * Get the canonical path. Since we must translate to a path, this must be done + * in the context of the userspace daemon, however, the userspace daemon cannot + * look up paths on its own. Instead, we handle the lookup as a special case + * inside of the write request. + */ +static void fuse_dentry_canonical_path(const struct path *path, struct path *canonical_path) { + struct inode *inode = path->dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req; + int err; + char *path_name; + + req = fuse_get_req(fc, 1); + err = PTR_ERR(req); + if (IS_ERR(req)) + goto default_path; + + path_name = (char*)__get_free_page(GFP_KERNEL); + if (!path_name) { + fuse_put_request(fc, req); + goto default_path; + } + + req->in.h.opcode = FUSE_CANONICAL_PATH; + req->in.h.nodeid = get_node_id(inode); + req->in.numargs = 0; + req->out.numargs = 1; + req->out.args[0].size = PATH_MAX; + req->out.args[0].value = path_name; + req->canonical_path = canonical_path; + req->out.argvar = 1; + fuse_request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + free_page((unsigned long)path_name); + if (!err) + return; +default_path: + canonical_path->dentry = path->dentry; + canonical_path->mnt = path->mnt; + path_get(canonical_path); +} + static int invalid_nodeid(u64 nodeid) { return !nodeid || nodeid == FUSE_ROOT_ID; @@ -274,6 +318,7 @@ static int invalid_nodeid(u64 nodeid) const struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, + .d_canonical_path = fuse_dentry_canonical_path, }; int fuse_valid_type(int m) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 570ca4053c80..c2e340d6ec6e 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -528,6 +528,11 @@ static void fuse_release_user_pages(struct fuse_req *req, int write) } } +static void fuse_io_release(struct kref *kref) +{ + kfree(container_of(kref, struct fuse_io_priv, refcnt)); +} + static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io) { if (io->err) @@ -585,8 +590,9 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) } io->iocb->ki_complete(io->iocb, res, 0); - kfree(io); } + + kref_put(&io->refcnt, fuse_io_release); } static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req) @@ -613,6 +619,7 @@ static size_t fuse_async_req_send(struct fuse_conn *fc, struct fuse_req *req, size_t num_bytes, struct fuse_io_priv *io) { spin_lock(&io->lock); + kref_get(&io->refcnt); io->size += num_bytes; io->reqs++; spin_unlock(&io->lock); @@ -691,7 +698,7 @@ static void fuse_short_read(struct fuse_req *req, struct inode *inode, static int fuse_do_readpage(struct file *file, struct page *page) { - struct fuse_io_priv io = { .async = 0, .file = file }; + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file); struct inode *inode = page->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_req *req; @@ -984,7 +991,7 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file, size_t res; unsigned offset; unsigned i; - struct fuse_io_priv io = { .async = 0, .file = file }; + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file); for (i = 0; i < req->num_pages; i++) fuse_wait_on_page_writeback(inode, req->pages[i]->index); @@ -1398,7 +1405,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io, static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct fuse_io_priv io = { .async = 0, .file = iocb->ki_filp }; + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb->ki_filp); return __fuse_direct_read(&io, to, &iocb->ki_pos); } @@ -1406,7 +1413,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - struct fuse_io_priv io = { .async = 0, .file = file }; + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file); ssize_t res; if (is_bad_inode(inode)) @@ -2786,6 +2793,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) loff_t i_size; size_t count = iov_iter_count(iter); struct fuse_io_priv *io; + bool is_sync = is_sync_kiocb(iocb); pos = offset; inode = file->f_mapping->host; @@ -2806,6 +2814,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) if (!io) return -ENOMEM; spin_lock_init(&io->lock); + kref_init(&io->refcnt); io->reqs = 1; io->bytes = -1; io->size = 0; @@ -2825,12 +2834,18 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) * to wait on real async I/O requests, so we must submit this request * synchronously. */ - if (!is_sync_kiocb(iocb) && (offset + count > i_size) && + if (!is_sync && (offset + count > i_size) && iov_iter_rw(iter) == WRITE) io->async = false; - if (io->async && is_sync_kiocb(iocb)) + if (io->async && is_sync) { + /* + * Additional reference to keep io around after + * calling fuse_aio_complete() + */ + kref_get(&io->refcnt); io->done = &wait; + } if (iov_iter_rw(iter) == WRITE) { ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE); @@ -2843,14 +2858,14 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) fuse_aio_complete(io, ret < 0 ? ret : 0, -1); /* we have a non-extending, async request, so return */ - if (!is_sync_kiocb(iocb)) + if (!is_sync) return -EIOCBQUEUED; wait_for_completion(&wait); ret = fuse_get_res_by_io(io); } - kfree(io); + kref_put(&io->refcnt, fuse_io_release); if (iov_iter_rw(iter) == WRITE) { if (ret > 0) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 405113101db8..644687ae04bd 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -22,6 +22,7 @@ #include <linux/rbtree.h> #include <linux/poll.h> #include <linux/workqueue.h> +#include <linux/kref.h> /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32 @@ -243,6 +244,7 @@ struct fuse_args { /** The request IO state (for asynchronous processing) */ struct fuse_io_priv { + struct kref refcnt; int async; spinlock_t lock; unsigned reqs; @@ -256,6 +258,13 @@ struct fuse_io_priv { struct completion *done; }; +#define FUSE_IO_PRIV_SYNC(f) \ +{ \ + .refcnt = { ATOMIC_INIT(1) }, \ + .async = 0, \ + .file = f, \ +} + /** * Request flags * @@ -363,6 +372,9 @@ struct fuse_req { /** Inode used in the request or NULL */ struct inode *inode; + /** Path used for completing d_canonical_path */ + struct path *canonical_path; + /** AIO control block */ struct fuse_io_priv *io; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 2ac99db3750e..5a7b3229b956 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -730,15 +730,13 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, init_special_inode(inode, mode, dev); err = do_mknod(name, mode, MAJOR(dev), MINOR(dev)); - if (!err) + if (err) goto out_free; err = read_name(inode, name); __putname(name); if (err) goto out_put; - if (err) - goto out_put; d_instantiate(dentry, inode); return 0; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index ae4d5a1fa4c9..bffb908acbd4 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -375,12 +375,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = d_inode(dentry); dnode_secno dno; int r; - int rep = 0; int err; hpfs_lock(dir->i_sb); hpfs_adjust_length(name, &len); -again: + err = -ENOENT; de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh); if (!de) @@ -400,33 +399,9 @@ again: hpfs_error(dir->i_sb, "there was error when removing dirent"); err = -EFSERROR; break; - case 2: /* no space for deleting, try to truncate file */ - + case 2: /* no space for deleting */ err = -ENOSPC; - if (rep++) - break; - - dentry_unhash(dentry); - if (!d_unhashed(dentry)) { - hpfs_unlock(dir->i_sb); - return -ENOSPC; - } - if (generic_permission(inode, MAY_WRITE) || - !S_ISREG(inode->i_mode) || - get_write_access(inode)) { - d_rehash(dentry); - } else { - struct iattr newattrs; - /*pr_info("truncating file before delete.\n");*/ - newattrs.ia_size = 0; - newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME; - err = notify_change(dentry, &newattrs, NULL); - put_write_access(inode); - if (!err) - goto again; - } - hpfs_unlock(dir->i_sb); - return -ENOSPC; + break; default: drop_nlink(inode); err = 0; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index de4bdfac0cec..595ebdb41846 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -463,6 +463,7 @@ hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) */ vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) { unsigned long v_offset; + unsigned long v_end; /* * Can the expression below overflow on 32-bit arches? @@ -475,15 +476,17 @@ hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) else v_offset = 0; - if (end) { - end = ((end - start) << PAGE_SHIFT) + - vma->vm_start + v_offset; - if (end > vma->vm_end) - end = vma->vm_end; - } else - end = vma->vm_end; + if (!end) + v_end = vma->vm_end; + else { + v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + + vma->vm_start; + if (v_end > vma->vm_end) + v_end = vma->vm_end; + } - unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL); + unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end, + NULL); } } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 81e622681c82..624a57a9c4aa 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1408,11 +1408,12 @@ out: /** * jbd2_mark_journal_empty() - Mark on disk journal as empty. * @journal: The journal to update. + * @write_op: With which operation should we write the journal sb * * Update a journal's dynamic superblock fields to show that journal is empty. * Write updated superblock to disk waiting for IO to complete. */ -static void jbd2_mark_journal_empty(journal_t *journal) +static void jbd2_mark_journal_empty(journal_t *journal, int write_op) { journal_superblock_t *sb = journal->j_superblock; @@ -1430,7 +1431,7 @@ static void jbd2_mark_journal_empty(journal_t *journal) sb->s_start = cpu_to_be32(0); read_unlock(&journal->j_state_lock); - jbd2_write_superblock(journal, WRITE_FUA); + jbd2_write_superblock(journal, write_op); /* Log is no longer empty */ write_lock(&journal->j_state_lock); @@ -1716,7 +1717,13 @@ int jbd2_journal_destroy(journal_t *journal) if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { mutex_lock(&journal->j_checkpoint_mutex); - jbd2_mark_journal_empty(journal); + + write_lock(&journal->j_state_lock); + journal->j_tail_sequence = + ++journal->j_transaction_sequence; + write_unlock(&journal->j_state_lock); + + jbd2_mark_journal_empty(journal, WRITE_FLUSH_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } else err = -EIO; @@ -1975,7 +1982,7 @@ int jbd2_journal_flush(journal_t *journal) * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ - jbd2_mark_journal_empty(journal); + jbd2_mark_journal_empty(journal, WRITE_FUA); mutex_unlock(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); J_ASSERT(!journal->j_running_transaction); @@ -2021,7 +2028,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) if (write) { /* Lock to make assertions happy... */ mutex_lock(&journal->j_checkpoint_mutex); - jbd2_mark_journal_empty(journal); + jbd2_mark_journal_empty(journal, WRITE_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking index 3ea36554107f..8918ac905a3b 100644 --- a/fs/jffs2/README.Locking +++ b/fs/jffs2/README.Locking @@ -2,10 +2,6 @@ JFFS2 LOCKING DOCUMENTATION --------------------------- -At least theoretically, JFFS2 does not require the Big Kernel Lock -(BKL), which was always helpfully obtained for it by Linux 2.4 VFS -code. It has its own locking, as described below. - This document attempts to describe the existing locking rules for JFFS2. It is not expected to remain perfectly up to date, but ought to be fairly close. @@ -69,6 +65,7 @@ Ordering constraints: any f->sem held. 2. Never attempt to lock two file mutexes in one thread. No ordering rules have been made for doing so. + 3. Never lock a page cache page with f->sem held. erase_completion_lock spinlock diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index a3750f902adc..c1f04947d7dc 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -49,7 +49,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c) static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, - struct jffs2_inode_cache *ic) + struct jffs2_inode_cache *ic, + int *dir_hardlinks) { struct jffs2_full_dirent *fd; @@ -68,19 +69,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n", fd->name, fd->ino, ic->ino); jffs2_mark_node_obsolete(c, fd->raw); + /* Clear the ic/raw union so it doesn't cause problems later. */ + fd->ic = NULL; continue; } + /* From this point, fd->raw is no longer used so we can set fd->ic */ + fd->ic = child_ic; + child_ic->pino_nlink++; + /* If we appear (at this stage) to have hard-linked directories, + * set a flag to trigger a scan later */ if (fd->type == DT_DIR) { - if (child_ic->pino_nlink) { - JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n", - fd->name, fd->ino, ic->ino); - /* TODO: What do we do about it? */ - } else { - child_ic->pino_nlink = ic->ino; - } - } else - child_ic->pino_nlink++; + child_ic->flags |= INO_FLAGS_IS_DIR; + if (child_ic->pino_nlink > 1) + *dir_hardlinks = 1; + } dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino); /* Can't free scan_dents so far. We might need them in pass 2 */ @@ -94,8 +97,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, */ static int jffs2_build_filesystem(struct jffs2_sb_info *c) { - int ret; - int i; + int ret, i, dir_hardlinks = 0; struct jffs2_inode_cache *ic; struct jffs2_full_dirent *fd; struct jffs2_full_dirent *dead_fds = NULL; @@ -119,7 +121,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) /* Now scan the directory tree, increasing nlink according to every dirent found. */ for_each_inode(i, c, ic) { if (ic->scan_dents) { - jffs2_build_inode_pass1(c, ic); + jffs2_build_inode_pass1(c, ic, &dir_hardlinks); cond_resched(); } } @@ -155,6 +157,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) } dbg_fsbuild("pass 2a complete\n"); + + if (dir_hardlinks) { + /* If we detected directory hardlinks earlier, *hopefully* + * they are gone now because some of the links were from + * dead directories which still had some old dirents lying + * around and not yet garbage-collected, but which have + * been discarded above. So clear the pino_nlink field + * in each directory, so that the final scan below can + * print appropriate warnings. */ + for_each_inode(i, c, ic) { + if (ic->flags & INO_FLAGS_IS_DIR) + ic->pino_nlink = 0; + } + } dbg_fsbuild("freeing temporary data structures\n"); /* Finally, we can scan again and free the dirent structs */ @@ -162,6 +178,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) while(ic->scan_dents) { fd = ic->scan_dents; ic->scan_dents = fd->next; + /* We do use the pino_nlink field to count nlink of + * directories during fs build, so set it to the + * parent ino# now. Now that there's hopefully only + * one. */ + if (fd->type == DT_DIR) { + if (!fd->ic) { + /* We'll have complained about it and marked the coresponding + raw node obsolete already. Just skip it. */ + continue; + } + + /* We *have* to have set this in jffs2_build_inode_pass1() */ + BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR)); + + /* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks + * is set. Otherwise, we know this should never trigger anyway, so + * we don't do the check. And ic->pino_nlink still contains the nlink + * value (which is 1). */ + if (dir_hardlinks && fd->ic->pino_nlink) { + JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n", + fd->name, fd->ino, ic->ino, fd->ic->pino_nlink); + /* Should we unlink it from its previous parent? */ + } + + /* For directories, ic->pino_nlink holds that parent inode # */ + fd->ic->pino_nlink = ic->ino; + } jffs2_free_full_dirent(fd); } ic->scan_dents = NULL; @@ -240,11 +283,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c, /* Reduce nlink of the child. If it's now zero, stick it on the dead_fds list to be cleaned up later. Else just free the fd */ - - if (fd->type == DT_DIR) - child_ic->pino_nlink = 0; - else - child_ic->pino_nlink--; + child_ic->pino_nlink--; if (!child_ic->pino_nlink) { dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n", diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index d211b8e18566..30c4c9ebb693 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -843,9 +843,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n", __func__, ret); - /* Might as well let the VFS know */ - d_instantiate(new_dentry, d_inode(old_dentry)); - ihold(d_inode(old_dentry)); + /* + * We can't keep the target in dcache after that. + * For one thing, we can't afford dentry aliases for directories. + * For another, if there was a victim, we _can't_ set new inode + * for that sucker and we have to trigger mount eviction - the + * caller won't do it on its own since we are returning an error. + */ + d_invalidate(new_dentry); new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now); return ret; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index f509f62e12f6..3361979d728c 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -137,39 +137,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - struct jffs2_raw_inode ri; - uint32_t alloc_len = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; uint32_t pageofs = index << PAGE_CACHE_SHIFT; int ret = 0; - jffs2_dbg(1, "%s()\n", __func__); - - if (pageofs > inode->i_size) { - ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, - ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); - if (ret) - return ret; - } - - mutex_lock(&f->sem); pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) { - if (alloc_len) - jffs2_complete_reservation(c); - mutex_unlock(&f->sem); + if (!pg) return -ENOMEM; - } *pagep = pg; - if (alloc_len) { + jffs2_dbg(1, "%s()\n", __func__); + + if (pageofs > inode->i_size) { /* Make new hole frag from old EOF to new page */ + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; + uint32_t alloc_len; jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", (unsigned int)inode->i_size, pageofs); + ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, + ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); + if (ret) + goto out_page; + + mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); @@ -196,6 +190,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, if (IS_ERR(fn)) { ret = PTR_ERR(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); @@ -210,10 +205,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_mark_node_obsolete(c, fn->raw); jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } jffs2_complete_reservation(c); inode->i_size = pageofs; + mutex_unlock(&f->sem); } /* @@ -222,18 +219,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * case of a short-copy. */ if (!PageUptodate(pg)) { + mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); + mutex_unlock(&f->sem); if (ret) goto out_page; } - mutex_unlock(&f->sem); jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); return ret; out_page: unlock_page(pg); page_cache_release(pg); - mutex_unlock(&f->sem); return ret; } diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 5a2dec2b064c..95d5880a63ee 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era BUG_ON(start > orig_start); } - /* First, use readpage() to read the appropriate page into the page cache */ - /* Q: What happens if we actually try to GC the _same_ page for which commit_write() - * triggered garbage collection in the first place? - * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the - * page OK. We'll actually write it out again in commit_write, which is a little - * suboptimal, but at least we're correct. - */ + /* The rules state that we must obtain the page lock *before* f->sem, so + * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's + * actually going to *change* so we're safe; we only allow reading. + * + * It is important to note that jffs2_write_begin() will ensure that its + * page is marked Uptodate before allocating space. That means that if we + * end up here trying to GC the *same* page that jffs2_write_begin() is + * trying to write out, read_cache_page() will not deadlock. */ + mutex_unlock(&f->sem); pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg); + mutex_lock(&f->sem); if (IS_ERR(pg_ptr)) { pr_warn("read_cache_page() returned error: %ld\n", diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h index fa35ff79ab35..0637271f3770 100644 --- a/fs/jffs2/nodelist.h +++ b/fs/jffs2/nodelist.h @@ -194,6 +194,7 @@ struct jffs2_inode_cache { #define INO_STATE_CLEARING 6 /* In clear_inode() */ #define INO_FLAGS_XATTR_CHECKED 0x01 /* has no duplicate xattr_ref */ +#define INO_FLAGS_IS_DIR 0x02 /* is a directory */ #define RAWNODE_CLASS_INODE_CACHE 0 #define RAWNODE_CLASS_XATTR_DATUM 1 @@ -249,7 +250,10 @@ struct jffs2_readinode_info struct jffs2_full_dirent { - struct jffs2_raw_node_ref *raw; + union { + struct jffs2_raw_node_ref *raw; + struct jffs2_inode_cache *ic; /* Just during part of build */ + }; struct jffs2_full_dirent *next; uint32_t version; uint32_t ino; /* == zero for unlink */ diff --git a/fs/locks.c b/fs/locks.c index 0d2b3267e2a3..6333263b7bc8 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2182,7 +2182,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2224,19 +2223,22 @@ again: * Attempt to detect a close/fcntl race and recover by * releasing the lock that was just acquired. */ - /* - * we need that spin_lock here - it prevents reordering between - * update of i_flctx->flc_posix and check for it done in close(). - * rcu_read_lock() wouldn't do. - */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: locks_free_lock(file_lock); return error; @@ -2322,7 +2324,6 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock64_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2364,14 +2365,22 @@ again: * Attempt to detect a close/fcntl race and recover by * releasing the lock that was just acquired. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: locks_free_lock(file_lock); return error; diff --git a/fs/namei.c b/fs/namei.c index 0c3974cd3ecd..d8ee4da93650 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1711,6 +1711,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link, return 0; if (!follow) return 0; + /* make sure that d_is_symlink above matches inode */ + if (nd->flags & LOOKUP_RCU) { + if (read_seqcount_retry(&link->dentry->d_seq, seq)) + return -ECHILD; + } return pick_link(nd, link, inode, seq); } @@ -1742,11 +1747,11 @@ static int walk_component(struct nameidata *nd, int flags) if (err < 0) return err; - inode = d_backing_inode(path.dentry); seq = 0; /* we are already out of RCU mode */ err = -ENOENT; if (d_is_negative(path.dentry)) goto out_path_put; + inode = d_backing_inode(path.dentry); } if (flags & WALK_PUT) @@ -3130,12 +3135,12 @@ retry_lookup: return error; BUG_ON(nd->flags & LOOKUP_RCU); - inode = d_backing_inode(path.dentry); seq = 0; /* out of RCU mode, so the value doesn't matter */ if (unlikely(d_is_negative(path.dentry))) { path_to_nameidata(&path, nd); return -ENOENT; } + inode = d_backing_inode(path.dentry); finish_lookup: if (nd->depth) put_link(nd); @@ -3144,11 +3149,6 @@ finish_lookup: if (unlikely(error)) return error; - if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) { - path_to_nameidata(&path, nd); - return -ELOOP; - } - if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) { path_to_nameidata(&path, nd); } else { @@ -3167,6 +3167,10 @@ finish_open: return error; } audit_inode(nd->name, nd->path.dentry, 0); + if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) { + error = -ELOOP; + goto out; + } error = -EISDIR; if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; @@ -3210,6 +3214,10 @@ opened: goto exit_fput; } out: + if (unlikely(error > 0)) { + WARN_ON(1); + error = -EINVAL; + } if (got_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index f0e3e9e747dd..03446c5a3ec1 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -633,7 +633,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx, d_rehash(newdent); } else { spin_lock(&dentry->d_lock); - NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE; + NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE; spin_unlock(&dentry->d_lock); } } else { diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ce5a21861074..5fc2162afb67 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -377,7 +377,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, again: timestamp = jiffies; gencount = nfs_inc_attr_generation_counter(); - error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, entry->cookie, pages, + error = NFS_PROTO(inode)->readdir(file_dentry(file), cred, entry->cookie, pages, NFS_SERVER(inode)->dtsize, desc->plus); if (error < 0) { /* We requested READDIRPLUS, but the server doesn't grok it */ @@ -560,7 +560,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en count++; if (desc->plus != 0) - nfs_prime_dcache(desc->file->f_path.dentry, entry); + nfs_prime_dcache(file_dentry(desc->file), entry); status = nfs_readdir_add_to_array(entry, page); if (status != 0) @@ -864,7 +864,7 @@ static bool nfs_dir_mapping_need_revalidate(struct inode *dir) */ static int nfs_readdir(struct file *file, struct dir_context *ctx) { - struct dentry *dentry = file->f_path.dentry; + struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); nfs_readdir_descriptor_t my_desc, *desc = &my_desc; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 03516c80855a..2a2e2d8ddee5 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -145,7 +145,7 @@ static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1, return false; for (i = 0; i < m1->fh_versions_cnt; i++) { bool found_fh = false; - for (j = 0; j < m2->fh_versions_cnt; i++) { + for (j = 0; j < m2->fh_versions_cnt; j++) { if (nfs_compare_fh(&m1->fh_versions[i], &m2->fh_versions[j]) == 0) { found_fh = true; @@ -1859,11 +1859,9 @@ ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo, start = xdr_reserve_space(xdr, 4); BUG_ON(!start); - if (ff_layout_encode_ioerr(flo, xdr, args)) - goto out; - + ff_layout_encode_ioerr(flo, xdr, args); ff_layout_encode_iostats(flo, xdr, args); -out: + *start = cpu_to_be32((xdr->p - start - 1) * 4); dprintk("%s: Return\n", __func__); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c7e8b87da5b2..f714b98cfd74 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -927,7 +927,7 @@ int nfs_open(struct inode *inode, struct file *filp) { struct nfs_open_context *ctx; - ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode); + ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode); if (IS_ERR(ctx)) return PTR_ERR(ctx); nfs_file_set_open_context(filp, ctx); @@ -1641,6 +1641,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; + bool cache_revalidated = true; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, @@ -1702,22 +1703,28 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else + } else { nfsi->cache_validity |= save_cache_validity; + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - } else if (server->caps & NFS_CAP_MTIME) + } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - } else if (server->caps & NFS_CAP_CTIME) + } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1737,19 +1744,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) (long long)cur_isize, (long long)new_isize); } - } else + } else { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); - else if (server->caps & NFS_CAP_ATIME) + else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { @@ -1758,36 +1769,42 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; } - } else if (server->caps & NFS_CAP_MODE) + } else if (server->caps & NFS_CAP_MODE) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } - } else if (server->caps & NFS_CAP_OWNER) + } else if (server->caps & NFS_CAP_OWNER) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } - } else if (server->caps & NFS_CAP_OWNER_GROUP) + } else if (server->caps & NFS_CAP_OWNER_GROUP) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { @@ -1796,19 +1813,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_DATA; set_nlink(inode, fattr->nlink); } - } else if (server->caps & NFS_CAP_NLINK) + } else if (server->caps & NFS_CAP_NLINK) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - } - if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; + else + cache_revalidated = false; /* Update attrtimeo value if we're out of the unstable period */ if (invalid & NFS_INO_INVALID_ATTR) { @@ -1818,9 +1838,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { - if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { - if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode)) - nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + if (cache_revalidated) { + if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, + nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { + nfsi->attrtimeo <<= 1; + if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) + nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ @@ -1829,7 +1853,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } /* Don't declare attrcache up to date if there were no attrs! */ - if (fattr->valid != 0) + if (cache_revalidated) invalid &= ~NFS_INO_INVALID_ATTR; /* Don't invalidate the data if we were to blame */ diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index db9b5fea5b3e..679e003818b1 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -26,7 +26,7 @@ static int nfs4_file_open(struct inode *inode, struct file *filp) { struct nfs_open_context *ctx; - struct dentry *dentry = filp->f_path.dentry; + struct dentry *dentry = file_dentry(filp); struct dentry *parent = NULL; struct inode *dir; unsigned openflags = filp->f_flags; @@ -57,7 +57,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) parent = dget_parent(dentry); dir = d_inode(parent); - ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode); + ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 89818036f035..98a44157353a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1385,6 +1385,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s * Protect the call to nfs4_state_set_mode_locked and * serialise the stateid update */ + spin_lock(&state->owner->so_lock); write_seqlock(&state->seqlock); if (deleg_stateid != NULL) { nfs4_stateid_copy(&state->stateid, deleg_stateid); @@ -1393,7 +1394,6 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s if (open_stateid != NULL) nfs_set_open_stateid_locked(state, open_stateid, fmode); write_sequnlock(&state->seqlock); - spin_lock(&state->owner->so_lock); update_open_stateflags(state, fmode); spin_unlock(&state->owner->so_lock); } @@ -2461,9 +2461,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = d_add_unique(dentry, igrab(state->inode)); if (dentry == NULL) { dentry = opendata->dentry; - } else if (dentry != ctx->dentry) { + } else { dput(ctx->dentry); - ctx->dentry = dget(dentry); + ctx->dentry = dentry; } nfs_set_verifier(dentry, nfs_save_change_attribute(d_inode(opendata->dir))); @@ -8054,7 +8054,6 @@ static void nfs4_layoutreturn_release(void *calldata) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); pnfs_clear_layoutreturn_waitbit(lo); - lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_free_lseg_list(&freeme); pnfs_put_layout_hdr(lrp->args.layout); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a9f096c7e99f..7d5351cd67fb 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -877,6 +877,7 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &exp, &dentry); if (err) return err; + fh_unlock(&cstate->current_fh); if (d_really_is_negative(dentry)) { exp_put(exp); err = nfserr_noent; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 51c9e9ca39a4..12935209deca 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1072,8 +1072,9 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename READ_BUF(4); rename->rn_snamelen = be32_to_cpup(p++); - READ_BUF(rename->rn_snamelen + 4); + READ_BUF(rename->rn_snamelen); SAVEMEM(rename->rn_sname, rename->rn_snamelen); + READ_BUF(4); rename->rn_tnamelen = be32_to_cpup(p++); READ_BUF(rename->rn_tnamelen); SAVEMEM(rename->rn_tname, rename->rn_tnamelen); @@ -1155,13 +1156,14 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient READ_BUF(8); setclientid->se_callback_prog = be32_to_cpup(p++); setclientid->se_callback_netid_len = be32_to_cpup(p++); - - READ_BUF(setclientid->se_callback_netid_len + 4); + READ_BUF(setclientid->se_callback_netid_len); SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len); + READ_BUF(4); setclientid->se_callback_addr_len = be32_to_cpup(p++); - READ_BUF(setclientid->se_callback_addr_len + 4); + READ_BUF(setclientid->se_callback_addr_len); SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len); + READ_BUF(4); setclientid->se_callback_ident = be32_to_cpup(p++); DECODE_TAIL; @@ -1815,8 +1817,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) READ_BUF(4); argp->taglen = be32_to_cpup(p++); - READ_BUF(argp->taglen + 8); + READ_BUF(argp->taglen); SAVEMEM(argp->tag, argp->taglen); + READ_BUF(8); argp->minorversion = be32_to_cpup(p++); argp->opcnt = be32_to_cpup(p++); max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index b8d08d0d0a4d..e2893f17dde2 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -702,6 +702,8 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, struct fsnotify_group *group; struct inode *inode; struct path path; + struct path alteredpath; + struct path *canonical_path = &path; struct fd f; int ret; unsigned flags = 0; @@ -741,13 +743,22 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, if (ret) goto fput_and_out; + /* support stacked filesystems */ + if(path.dentry && path.dentry->d_op) { + if (path.dentry->d_op->d_canonical_path) { + path.dentry->d_op->d_canonical_path(&path, &alteredpath); + canonical_path = &alteredpath; + path_put(&path); + } + } + /* inode held in place by reference to path; group by fget on fd */ - inode = path.dentry->d_inode; + inode = canonical_path->dentry->d_inode; group = f.file->private_data; /* create/update an inode mark */ ret = inotify_update_watch(group, inode, mask); - path_put(&path); + path_put(canonical_path); fput_and_out: fdput(f); return ret; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 7f604727f487..e6795c7c76a8 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -956,6 +956,7 @@ clean_orphan: tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, update_isize, end); if (tmp_ret < 0) { + ocfs2_inode_unlock(inode, 1); ret = tmp_ret; mlog_errno(ret); brelse(di_bh); diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index e36d63ff1783..f90931335c6b 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -262,6 +262,7 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, struct dlm_lock *lock, int flags, int type) { enum dlm_status status; + u8 old_owner = res->owner; mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); @@ -287,6 +288,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, status = DLM_DENIED; goto bail; } + + if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) { + mlog(0, "last convert request returned DLM_RECOVERING, but " + "owner has already queued and sent ast to me. res %.*s, " + "(cookie=%u:%llu, type=%d, conv=%d)\n", + res->lockname.len, res->lockname.name, + dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)), + dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)), + lock->ml.type, lock->ml.convert_type); + status = DLM_NORMAL; + goto bail; + } + res->state |= DLM_LOCK_RES_IN_PROGRESS; /* move lock to local convert queue */ /* do not alter lock refcount. switching lists. */ @@ -316,11 +330,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; lock->convert_pending = 0; - /* if it failed, move it back to granted queue */ + /* if it failed, move it back to granted queue. + * if master returns DLM_NORMAL and then down before sending ast, + * it may have already been moved to granted queue, reset to + * DLM_RECOVERING and retry convert */ if (status != DLM_NORMAL) { if (status != DLM_NOTQUEUED) dlm_error(status); dlm_revert_pending_convert(res, lock); + } else if ((res->state & DLM_LOCK_RES_RECOVERING) || + (old_owner != res->owner)) { + mlog(0, "res %.*s is in recovering or has been recovered.\n", + res->lockname.len, res->lockname.name); + status = DLM_RECOVERING; } bail: spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 84f2f8079466..4e2162b355db 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2519,6 +2519,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm, spin_lock(&dlm->master_lock); ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name, namelen, target, dlm->node_num); + /* get an extra reference on the mle. + * otherwise the assert_master from the new + * master will destroy this. + */ + dlm_get_mle_inuse(mle); spin_unlock(&dlm->master_lock); spin_unlock(&dlm->spinlock); @@ -2554,6 +2559,7 @@ fail: if (mle_added) { dlm_mle_detach_hb_events(dlm, mle); dlm_put_mle(mle); + dlm_put_mle_inuse(mle); } else if (mle) { kmem_cache_free(dlm_mle_cache, mle); mle = NULL; @@ -2571,17 +2577,6 @@ fail: * ensure that all assert_master work is flushed. */ flush_workqueue(dlm->dlm_worker); - /* get an extra reference on the mle. - * otherwise the assert_master from the new - * master will destroy this. - * also, make sure that all callers of dlm_get_mle - * take both dlm->spinlock and dlm->master_lock */ - spin_lock(&dlm->spinlock); - spin_lock(&dlm->master_lock); - dlm_get_mle_inuse(mle); - spin_unlock(&dlm->master_lock); - spin_unlock(&dlm->spinlock); - /* notify new node and send all lock state */ /* call send_one_lockres with migration flag. * this serves as notice to the target node that a @@ -3312,6 +3307,15 @@ top: mle->new_master != dead_node) continue; + if (mle->new_master == dead_node && mle->inuse) { + mlog(ML_NOTICE, "%s: target %u died during " + "migration from %u, the MLE is " + "still keep used, ignore it!\n", + dlm->name, dead_node, + mle->master); + continue; + } + /* If we have reached this point, this mle needs to be * removed from the list and freed. */ dlm_clean_migration_mle(dlm, mle); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 9e4f862d20fe..4a338803e7e9 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2064,7 +2064,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm, dlm_lock_get(lock); if (lock->convert_pending) { /* move converting lock back to granted */ - BUG_ON(i != DLM_CONVERTING_LIST); mlog(0, "node died with convert pending " "on %.*s. move back to granted list.\n", res->lockname.len, res->lockname.name); @@ -2360,6 +2359,8 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) break; } } + dlm_lockres_clear_refmap_bit(dlm, res, + dead_node); spin_unlock(&res->spinlock); continue; } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 20276e340339..b002acf50203 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1390,6 +1390,7 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb, unsigned int gen; int noqueue_attempted = 0; int dlm_locked = 0; + int kick_dc = 0; if (!(lockres->l_flags & OCFS2_LOCK_INITIALIZED)) { mlog_errno(-EINVAL); @@ -1524,7 +1525,12 @@ update_holders: unlock: lockres_clear_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING); + /* ocfs2_unblock_lock reques on seeing OCFS2_LOCK_UPCONVERT_FINISHING */ + kick_dc = (lockres->l_flags & OCFS2_LOCK_BLOCKED); + spin_unlock_irqrestore(&lockres->l_lock, flags); + if (kick_dc) + ocfs2_wake_downconvert_thread(osb); out: /* * This is helping work around a lock inversion between the page lock diff --git a/fs/open.c b/fs/open.c index b6f1e96a7c0b..6a24f988d253 100644 --- a/fs/open.c +++ b/fs/open.c @@ -995,14 +995,12 @@ struct file *filp_open(const char *filename, int flags, umode_t mode) EXPORT_SYMBOL(filp_open); struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, - const char *filename, int flags) + const char *filename, int flags, umode_t mode) { struct open_flags op; - int err = build_open_flags(flags, 0, &op); + int err = build_open_flags(flags, mode, &op); if (err) return ERR_PTR(err); - if (flags & O_CREAT) - return ERR_PTR(-EINVAL); return do_file_open_root(dentry, mnt, filename, &op); } EXPORT_SYMBOL(file_open_root); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 0a8983492d91..eff6319d5037 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -22,9 +22,9 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) { - ssize_t list_size, size; - char *buf, *name, *value; - int error; + ssize_t list_size, size, value_size = 0; + char *buf, *name, *value = NULL; + int uninitialized_var(error); if (!old->d_inode->i_op->getxattr || !new->d_inode->i_op->getxattr) @@ -41,29 +41,40 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) if (!buf) return -ENOMEM; - error = -ENOMEM; - value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL); - if (!value) - goto out; - list_size = vfs_listxattr(old, buf, list_size); if (list_size <= 0) { error = list_size; - goto out_free_value; + goto out; } for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { - size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); - if (size <= 0) { +retry: + size = vfs_getxattr(old, name, value, value_size); + if (size == -ERANGE) + size = vfs_getxattr(old, name, NULL, 0); + + if (size < 0) { error = size; - goto out_free_value; + break; + } + + if (size > value_size) { + void *new; + + new = krealloc(value, size, GFP_KERNEL); + if (!new) { + error = -ENOMEM; + break; + } + value = new; + value_size = size; + goto retry; } + error = vfs_setxattr(new, name, value, size, 0); if (error) - goto out_free_value; + break; } - -out_free_value: kfree(value); out: kfree(buf); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 692ceda3bc21..a2b1d7ce3e1a 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -618,7 +618,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir) * sole user of this dentry. Too tricky... Just unhash for * now. */ - d_drop(dentry); + if (!err) + d_drop(dentry); mutex_unlock(&dir->i_mutex); return err; @@ -903,6 +904,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, if (!overwrite && new_is_dir && !old_opaque && new_opaque) ovl_remove_opaque(newdentry); + /* + * Old dentry now lives in different location. Dentries in + * lowerstack are stale. We cannot drop them here because + * access to them is lockless. This could be only pure upper + * or opaque directory - numlower is zero. Or upper non-dir + * entry - its pureness is tracked by flag opaque. + */ if (old_opaque != new_opaque) { ovl_dentry_set_opaque(old, new_opaque); if (!overwrite) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 4060ffde8722..05ac9a95e881 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -42,6 +42,19 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) int err; struct dentry *upperdentry; + /* + * Check for permissions before trying to copy-up. This is redundant + * since it will be rechecked later by ->setattr() on upper dentry. But + * without this, copy-up can be triggered by just about anybody. + * + * We don't initialize inode->size, which just means that + * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not + * check for a swapfile (which this won't be anyway). + */ + err = inode_change_ok(dentry->d_inode, attr); + if (err) + return err; + err = ovl_want_write(dentry); if (err) goto out; @@ -52,6 +65,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) mutex_lock(&upperdentry->d_inode->i_mutex); err = notify_change(upperdentry, attr, NULL); + if (!err) + ovl_copyattr(upperdentry->d_inode, dentry->d_inode); mutex_unlock(&upperdentry->d_inode->i_mutex); } ovl_drop_write(dentry); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 70e9af551600..adcb1398c481 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -571,7 +571,8 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) (int) PTR_ERR(dentry)); continue; } - ovl_cleanup(upper->d_inode, dentry); + if (dentry->d_inode) + ovl_cleanup(upper->d_inode, dentry); dput(dentry); } mutex_unlock(&upper->d_inode->i_mutex); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e38ee0fed24a..a1acc6004a91 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -9,6 +9,7 @@ #include <linux/fs.h> #include <linux/namei.h> +#include <linux/pagemap.h> #include <linux/xattr.h> #include <linux/security.h> #include <linux/mount.h> @@ -75,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry) if (oe->__upperdentry) { type = __OVL_PATH_UPPER; - if (oe->numlower) { - if (S_ISDIR(dentry->d_inode->i_mode)) - type |= __OVL_PATH_MERGE; - } else if (!oe->opaque) { + /* + * Non-dir dentry can hold lower dentry from previous + * location. Its purity depends only on opaque flag. + */ + if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode)) + type |= __OVL_PATH_MERGE; + else if (!oe->opaque) type |= __OVL_PATH_PURE; - } } else { if (oe->numlower > 1) type |= __OVL_PATH_MERGE; @@ -273,6 +276,37 @@ static void ovl_dentry_release(struct dentry *dentry) } } +static struct dentry *ovl_d_real(struct dentry *dentry, struct inode *inode) +{ + struct dentry *real; + + if (d_is_dir(dentry)) { + if (!inode || inode == d_inode(dentry)) + return dentry; + goto bug; + } + + real = ovl_dentry_upper(dentry); + if (real && (!inode || inode == d_inode(real))) + return real; + + real = ovl_dentry_lower(dentry); + if (!real) + goto bug; + + if (!inode || inode == d_inode(real)) + return real; + + /* Handle recursion */ + if (real->d_flags & DCACHE_OP_REAL) + return real->d_op->d_real(real, inode); + +bug: + WARN(1, "ovl_d_real(%pd4, %s:%lu\n): real dentry not found\n", dentry, + inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0); + return dentry; +} + static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags) { struct ovl_entry *oe = dentry->d_fsdata; @@ -317,10 +351,13 @@ static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags) static const struct dentry_operations ovl_dentry_operations = { .d_release = ovl_dentry_release, .d_select_inode = ovl_d_select_inode, + .d_real = ovl_d_real, }; static const struct dentry_operations ovl_reval_dentry_operations = { .d_release = ovl_dentry_release, + .d_select_inode = ovl_d_select_inode, + .d_real = ovl_d_real, .d_revalidate = ovl_dentry_revalidate, .d_weak_revalidate = ovl_dentry_weak_revalidate, }; @@ -910,6 +947,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } sb->s_stack_depth = 0; + sb->s_maxbytes = MAX_LFS_FILESIZE; if (ufs->config.upperdir) { if (!ufs->config.workdir) { pr_err("overlayfs: missing 'workdir'\n"); @@ -1053,6 +1091,9 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) root_dentry->d_fsdata = oe; + ovl_copyattr(ovl_dentry_real(root_dentry)->d_inode, + root_dentry->d_inode); + sb->s_magic = OVERLAYFS_SUPER_MAGIC; sb->s_op = &ovl_super_operations; sb->s_root = root_dentry; diff --git a/fs/pnode.c b/fs/pnode.c index 6367e1e435c6..99899705b105 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -198,10 +198,15 @@ static struct mount *next_group(struct mount *m, struct mount *origin) /* all accesses are serialized by namespace_sem */ static struct user_namespace *user_ns; -static struct mount *last_dest, *last_source, *dest_master; +static struct mount *last_dest, *first_source, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; +static inline bool peers(struct mount *m1, struct mount *m2) +{ + return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; +} + static int propagate_one(struct mount *m) { struct mount *child; @@ -212,24 +217,26 @@ static int propagate_one(struct mount *m) /* skip if mountpoint isn't covered by it */ if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) return 0; - if (m->mnt_group_id == last_dest->mnt_group_id) { + if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { struct mount *n, *p; + bool done; for (n = m; ; n = p) { p = n->mnt_master; - if (p == dest_master || IS_MNT_MARKED(p)) { - while (last_dest->mnt_master != p) { - last_source = last_source->mnt_master; - last_dest = last_source->mnt_parent; - } - if (n->mnt_group_id != last_dest->mnt_group_id) { - last_source = last_source->mnt_master; - last_dest = last_source->mnt_parent; - } + if (p == dest_master || IS_MNT_MARKED(p)) break; - } } + do { + struct mount *parent = last_source->mnt_parent; + if (last_source == first_source) + break; + done = parent->mnt_master == p; + if (done && peers(n, parent)) + break; + last_source = last_source->mnt_master; + } while (!done); + type = CL_SLAVE; /* beginning of peer group among the slaves? */ if (IS_MNT_SHARED(m)) @@ -281,6 +288,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, */ user_ns = current->nsproxy->mnt_ns->user_ns; last_dest = dest_mnt; + first_source = source_mnt; last_source = source_mnt; mp = dest_mp; list = tree_list; diff --git a/fs/proc/array.c b/fs/proc/array.c index d73291f5f0fc..b6c00ce0e29e 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -395,7 +395,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, state = *get_task_state(task); vsize = eip = esp = 0; - permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT); + permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT); mm = get_task_mm(task); if (mm) { vsize = task_vsize(mm); diff --git a/fs/proc/base.c b/fs/proc/base.c index 3b6962c52965..2df808a81035 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -403,7 +403,7 @@ static const struct file_operations proc_pid_cmdline_ops = { static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ); + struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (mm && !IS_ERR(mm)) { unsigned int nwords = 0; do { @@ -430,7 +430,8 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, wchan = get_wchan(task); - if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname)) + if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS) + && !lookup_symbol_name(wchan, symname)) seq_printf(m, "%s", symname); else seq_putc(m, '0'); @@ -444,7 +445,7 @@ static int lock_trace(struct task_struct *task) int err = mutex_lock_killable(&task->signal->cred_guard_mutex); if (err) return err; - if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) { + if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { mutex_unlock(&task->signal->cred_guard_mutex); return -EPERM; } @@ -697,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode) */ task = get_proc_task(inode); if (task) { - allowed = ptrace_may_access(task, PTRACE_MODE_READ); + allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); put_task_struct(task); } return allowed; @@ -732,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid, return true; if (in_group_p(pid->pid_gid)) return true; - return ptrace_may_access(task, PTRACE_MODE_READ); + return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } @@ -809,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) struct mm_struct *mm = ERR_PTR(-ESRCH); if (task) { - mm = mm_access(task, mode); + mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); put_task_struct(task); if (!IS_ERR_OR_NULL(mm)) { @@ -953,7 +954,8 @@ static ssize_t environ_read(struct file *file, char __user *buf, int ret = 0; struct mm_struct *mm = file->private_data; - if (!mm) + /* Ensure the process spawned far enough to have an environment. */ + if (!mm || !mm->env_end) return 0; page = (char *)__get_free_page(GFP_TEMPORARY); @@ -1856,7 +1858,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) if (!task) goto out_notask; - mm = mm_access(task, PTRACE_MODE_READ); + mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR_OR_NULL(mm)) goto out; @@ -2007,7 +2009,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, goto out; result = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; result = -ENOENT; @@ -2060,7 +2062,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) goto out; ret = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; ret = 0; @@ -2530,7 +2532,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh if (result) return result; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) { + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { result = -EACCES; goto out_unlock; } @@ -3077,6 +3079,44 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) } /* + * proc_tid_comm_permission is a special permission function exclusively + * used for the node /proc/<pid>/task/<tid>/comm. + * It bypasses generic permission checks in the case where a task of the same + * task group attempts to access the node. + * The rational behind this is that glibc and bionic access this node for + * cross thread naming (pthread_set/getname_np(!self)). However, if + * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0, + * which locks out the cross thread naming implementation. + * This function makes sure that the node is always accessible for members of + * same thread group. + */ +static int proc_tid_comm_permission(struct inode *inode, int mask) +{ + bool is_same_tgroup; + struct task_struct *task; + + task = get_proc_task(inode); + if (!task) + return -ESRCH; + is_same_tgroup = same_thread_group(current, task); + put_task_struct(task); + + if (likely(is_same_tgroup && !(mask & MAY_EXEC))) { + /* This file (/proc/<pid>/task/<tid>/comm) can always be + * read or written by the members of the corresponding + * thread group. + */ + return 0; + } + + return generic_permission(inode, mask); +} + +static const struct inode_operations proc_tid_comm_inode_operations = { + .permission = proc_tid_comm_permission, +}; + +/* * Tasks */ static const struct pid_entry tid_base_stuff[] = { @@ -3094,7 +3134,9 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_SCHED_DEBUG REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), #endif - REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), + NOD("comm", S_IFREG|S_IRUGO|S_IWUSR, + &proc_tid_comm_inode_operations, + &proc_pid_set_comm_operations, {}), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index f6e8354b8cea..1b0ea4a5d89e 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -42,7 +42,7 @@ static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie) if (!task) return error; - if (ptrace_may_access(task, PTRACE_MODE_READ)) { + if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { error = ns_get_path(&ns_path, task, ns_ops); if (!error) nd_jump_link(&ns_path); @@ -63,7 +63,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (!task) return res; - if (ptrace_may_access(task, PTRACE_MODE_READ)) { + if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { res = ns_get_name(name, sizeof(name), task, ns_ops); if (res >= 0) res = readlink_copy(buffer, buflen, name); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 91698054b965..3e97da37b67c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1497,6 +1497,32 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return page; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static struct page *can_gather_numa_stats_pmd(pmd_t pmd, + struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *page; + int nid; + + if (!pmd_present(pmd)) + return NULL; + + page = vm_normal_page_pmd(vma, addr, pmd); + if (!page) + return NULL; + + if (PageReserved(page)) + return NULL; + + nid = page_to_nid(page); + if (!node_isset(nid, node_states[N_MEMORY])) + return NULL; + + return page; +} +#endif + static int gather_pte_stats(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -1506,13 +1532,13 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, pte_t *orig_pte; pte_t *pte; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { - pte_t huge_pte = *(pte_t *)pmd; struct page *page; - page = can_gather_numa_stats(huge_pte, vma, addr); + page = can_gather_numa_stats_pmd(*pmd, vma, addr); if (page) - gather_stats(page, md, pte_dirty(huge_pte), + gather_stats(page, md, pmd_dirty(*pmd), HPAGE_PMD_SIZE/PAGE_SIZE); spin_unlock(ptl); return 0; @@ -1520,6 +1546,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0; +#endif orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); do { struct page *page = can_gather_numa_stats(*pte, vma, addr); @@ -1535,18 +1562,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pte_t huge_pte = huge_ptep_get(pte); struct numa_maps *md; struct page *page; - if (!pte_present(*pte)) + if (!pte_present(huge_pte)) return 0; - page = pte_page(*pte); + page = pte_page(huge_pte); if (!page) return 0; md = walk->private; - gather_stats(page, md, pte_dirty(*pte), 1); + gather_stats(page, md, pte_dirty(huge_pte), 1); return 0; } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 8ebd9a334085..87645955990d 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -197,6 +197,8 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) if (sb->s_op->show_devname) { seq_puts(m, "device "); err = sb->s_op->show_devname(m, mnt_path.dentry); + if (err) + goto out; } else { if (r->mnt_devname) { seq_puts(m, "device "); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ef0d64b2a6d9..353ff31dcee1 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1398,7 +1398,7 @@ static int dquot_active(const struct inode *inode) static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot **dquots, *got[MAXQUOTAS]; + struct dquot **dquots, *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; @@ -1415,7 +1415,6 @@ static int __dquot_initialize(struct inode *inode, int type) int rc; struct dquot *dquot; - got[cnt] = NULL; if (type != -1 && cnt != type) continue; /* diff --git a/fs/sdcardfs/Kconfig b/fs/sdcardfs/Kconfig new file mode 100644 index 000000000000..a1c103316ac7 --- /dev/null +++ b/fs/sdcardfs/Kconfig @@ -0,0 +1,13 @@ +config SDCARD_FS + tristate "sdcard file system" + depends on CONFIGFS_FS + default n + help + Sdcardfs is based on Wrapfs file system. + +config SDCARD_FS_FADV_NOACTIVE + bool "sdcardfs fadvise noactive support" + depends on FADV_NOACTIVE + default y + help + Sdcardfs supports fadvise noactive mode. diff --git a/fs/sdcardfs/Makefile b/fs/sdcardfs/Makefile new file mode 100644 index 000000000000..b84fbb2b45a4 --- /dev/null +++ b/fs/sdcardfs/Makefile @@ -0,0 +1,7 @@ +SDCARDFS_VERSION="0.1" + +EXTRA_CFLAGS += -DSDCARDFS_VERSION=\"$(SDCARDFS_VERSION)\" + +obj-$(CONFIG_SDCARD_FS) += sdcardfs.o + +sdcardfs-y := dentry.o file.o inode.o main.o super.o lookup.o mmap.o packagelist.o derived_perm.o diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c new file mode 100644 index 000000000000..971928ab6c21 --- /dev/null +++ b/fs/sdcardfs/dentry.c @@ -0,0 +1,186 @@ +/* + * fs/sdcardfs/dentry.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include "linux/ctype.h" + +/* + * returns: -ERRNO if error (returned to user) + * 0: tell VFS to invalidate dentry + * 1: dentry is valid + */ +static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + int err = 1; + struct path parent_lower_path, lower_path; + struct dentry *parent_dentry = NULL; + struct dentry *parent_lower_dentry = NULL; + struct dentry *lower_cur_parent_dentry = NULL; + struct dentry *lower_dentry = NULL; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + spin_lock(&dentry->d_lock); + if (IS_ROOT(dentry)) { + spin_unlock(&dentry->d_lock); + return 1; + } + spin_unlock(&dentry->d_lock); + + /* check uninitialized obb_dentry and + * whether the base obbpath has been changed or not */ + if (is_obbpath_invalid(dentry)) { + d_drop(dentry); + return 0; + } + + parent_dentry = dget_parent(dentry); + sdcardfs_get_lower_path(parent_dentry, &parent_lower_path); + sdcardfs_get_real_lower(dentry, &lower_path); + parent_lower_dentry = parent_lower_path.dentry; + lower_dentry = lower_path.dentry; + lower_cur_parent_dentry = dget_parent(lower_dentry); + + spin_lock(&lower_dentry->d_lock); + if (d_unhashed(lower_dentry)) { + spin_unlock(&lower_dentry->d_lock); + d_drop(dentry); + err = 0; + goto out; + } + spin_unlock(&lower_dentry->d_lock); + + if (parent_lower_dentry != lower_cur_parent_dentry) { + d_drop(dentry); + err = 0; + goto out; + } + + if (dentry < lower_dentry) { + spin_lock(&dentry->d_lock); + spin_lock(&lower_dentry->d_lock); + } else { + spin_lock(&lower_dentry->d_lock); + spin_lock(&dentry->d_lock); + } + + if (dentry->d_name.len != lower_dentry->d_name.len) { + __d_drop(dentry); + err = 0; + } else if (strncasecmp(dentry->d_name.name, lower_dentry->d_name.name, + dentry->d_name.len) != 0) { + __d_drop(dentry); + err = 0; + } + + if (dentry < lower_dentry) { + spin_unlock(&lower_dentry->d_lock); + spin_unlock(&dentry->d_lock); + } else { + spin_unlock(&dentry->d_lock); + spin_unlock(&lower_dentry->d_lock); + } + +out: + dput(parent_dentry); + dput(lower_cur_parent_dentry); + sdcardfs_put_lower_path(parent_dentry, &parent_lower_path); + sdcardfs_put_real_lower(dentry, &lower_path); + return err; +} + +static void sdcardfs_d_release(struct dentry *dentry) +{ + /* release and reset the lower paths */ + if(has_graft_path(dentry)) { + sdcardfs_put_reset_orig_path(dentry); + } + sdcardfs_put_reset_lower_path(dentry); + free_dentry_private_data(dentry); + return; +} + +static int sdcardfs_hash_ci(const struct dentry *dentry, + struct qstr *qstr) +{ + /* + * This function is copy of vfat_hashi. + * FIXME Should we support national language? + * Refer to vfat_hashi() + * struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io; + */ + const unsigned char *name; + unsigned int len; + unsigned long hash; + + name = qstr->name; + //len = vfat_striptail_len(qstr); + len = qstr->len; + + hash = init_name_hash(); + while (len--) + //hash = partial_name_hash(nls_tolower(t, *name++), hash); + hash = partial_name_hash(tolower(*name++), hash); + qstr->hash = end_name_hash(hash); + + return 0; +} + +/* + * Case insensitive compare of two vfat names. + */ +static int sdcardfs_cmp_ci(const struct dentry *parent, + const struct dentry *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + /* This function is copy of vfat_cmpi */ + // FIXME Should we support national language? + //struct nls_table *t = MSDOS_SB(parent->d_sb)->nls_io; + //unsigned int alen, blen; + + /* A filename cannot end in '.' or we treat it like it has none */ + /* + alen = vfat_striptail_len(name); + blen = __vfat_striptail_len(len, str); + if (alen == blen) { + if (nls_strnicmp(t, name->name, str, alen) == 0) + return 0; + } + */ + if (name->len == len) { + if (strncasecmp(name->name, str, len) == 0) + return 0; + } + return 1; +} + +static void sdcardfs_canonical_path(const struct path *path, struct path *actual_path) { + sdcardfs_get_real_lower(path->dentry, actual_path); +} + +const struct dentry_operations sdcardfs_ci_dops = { + .d_revalidate = sdcardfs_d_revalidate, + .d_release = sdcardfs_d_release, + .d_hash = sdcardfs_hash_ci, + .d_compare = sdcardfs_cmp_ci, + .d_canonical_path = sdcardfs_canonical_path, +}; + diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c new file mode 100644 index 000000000000..128b3e56851f --- /dev/null +++ b/fs/sdcardfs/derived_perm.c @@ -0,0 +1,265 @@ +/* + * fs/sdcardfs/derived_perm.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +/* copy derived state from parent inode */ +static void inherit_derived_state(struct inode *parent, struct inode *child) +{ + struct sdcardfs_inode_info *pi = SDCARDFS_I(parent); + struct sdcardfs_inode_info *ci = SDCARDFS_I(child); + + ci->perm = PERM_INHERIT; + ci->userid = pi->userid; + ci->d_uid = pi->d_uid; + ci->under_android = pi->under_android; +} + +/* helper function for derived state */ +void setup_derived_state(struct inode *inode, perm_t perm, + userid_t userid, uid_t uid, bool under_android) +{ + struct sdcardfs_inode_info *info = SDCARDFS_I(inode); + + info->perm = perm; + info->userid = userid; + info->d_uid = uid; + info->under_android = under_android; +} + +/* While renaming, there is a point where we want the path from dentry, but the name from newdentry */ +void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, struct dentry *newdentry) +{ + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct sdcardfs_inode_info *info = SDCARDFS_I(dentry->d_inode); + struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + appid_t appid; + + /* By default, each inode inherits from its parent. + * the properties are maintained on its private fields + * because the inode attributes will be modified with that of + * its lower inode. + * The derived state will be updated on the last + * stage of each system call by fix_derived_permission(inode). + */ + + inherit_derived_state(parent->d_inode, dentry->d_inode); + + /* Derive custom permissions based on parent and current node */ + switch (parent_info->perm) { + case PERM_INHERIT: + /* Already inherited above */ + break; + case PERM_PRE_ROOT: + /* Legacy internal layout places users at top level */ + info->perm = PERM_ROOT; + info->userid = simple_strtoul(newdentry->d_name.name, NULL, 10); + break; + case PERM_ROOT: + /* Assume masked off by default. */ + if (!strcasecmp(newdentry->d_name.name, "Android")) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID; + info->under_android = true; + } + break; + case PERM_ANDROID: + if (!strcasecmp(newdentry->d_name.name, "data")) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_DATA; + } else if (!strcasecmp(newdentry->d_name.name, "obb")) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_OBB; + /* Single OBB directory is always shared */ + } else if (!strcasecmp(newdentry->d_name.name, "media")) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_MEDIA; + } + break; + case PERM_ANDROID_DATA: + case PERM_ANDROID_OBB: + case PERM_ANDROID_MEDIA: + appid = get_appid(sbi->pkgl_id, newdentry->d_name.name); + if (appid != 0) { + info->d_uid = multiuser_get_uid(parent_info->userid, appid); + } + break; + } +} + +void get_derived_permission(struct dentry *parent, struct dentry *dentry) +{ + get_derived_permission_new(parent, dentry, dentry); +} + +void get_derive_permissions_recursive(struct dentry *parent) { + struct dentry *dentry; + list_for_each_entry(dentry, &parent->d_subdirs, d_child) { + if (dentry && dentry->d_inode) { + mutex_lock(&dentry->d_inode->i_mutex); + get_derived_permission(parent, dentry); + fix_derived_permission(dentry->d_inode); + get_derive_permissions_recursive(dentry); + mutex_unlock(&dentry->d_inode->i_mutex); + } + } +} + +/* main function for updating derived permission */ +inline void update_derived_permission_lock(struct dentry *dentry) +{ + struct dentry *parent; + + if(!dentry || !dentry->d_inode) { + printk(KERN_ERR "sdcardfs: %s: invalid dentry\n", __func__); + return; + } + /* FIXME: + * 1. need to check whether the dentry is updated or not + * 2. remove the root dentry update + */ + mutex_lock(&dentry->d_inode->i_mutex); + if(IS_ROOT(dentry)) { + //setup_default_pre_root_state(dentry->d_inode); + } else { + parent = dget_parent(dentry); + if(parent) { + get_derived_permission(parent, dentry); + dput(parent); + } + } + fix_derived_permission(dentry->d_inode); + mutex_unlock(&dentry->d_inode->i_mutex); +} + +int need_graft_path(struct dentry *dentry) +{ + int ret = 0; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + if(parent_info->perm == PERM_ANDROID && + !strcasecmp(dentry->d_name.name, "obb")) { + + /* /Android/obb is the base obbpath of DERIVED_UNIFIED */ + if(!(sbi->options.multiuser == false + && parent_info->userid == 0)) { + ret = 1; + } + } + dput(parent); + return ret; +} + +int is_obbpath_invalid(struct dentry *dent) +{ + int ret = 0; + struct sdcardfs_dentry_info *di = SDCARDFS_D(dent); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dent->d_sb); + char *path_buf, *obbpath_s; + + /* check the base obbpath has been changed. + * this routine can check an uninitialized obb dentry as well. + * regarding the uninitialized obb, refer to the sdcardfs_mkdir() */ + spin_lock(&di->lock); + if(di->orig_path.dentry) { + if(!di->lower_path.dentry) { + ret = 1; + } else { + path_get(&di->lower_path); + //lower_parent = lock_parent(lower_path->dentry); + + path_buf = kmalloc(PATH_MAX, GFP_ATOMIC); + if(!path_buf) { + ret = 1; + printk(KERN_ERR "sdcardfs: fail to allocate path_buf in %s.\n", __func__); + } else { + obbpath_s = d_path(&di->lower_path, path_buf, PATH_MAX); + if (d_unhashed(di->lower_path.dentry) || + strcasecmp(sbi->obbpath_s, obbpath_s)) { + ret = 1; + } + kfree(path_buf); + } + + //unlock_dir(lower_parent); + path_put(&di->lower_path); + } + } + spin_unlock(&di->lock); + return ret; +} + +int is_base_obbpath(struct dentry *dentry) +{ + int ret = 0; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + spin_lock(&SDCARDFS_D(dentry)->lock); + if (sbi->options.multiuser) { + if(parent_info->perm == PERM_PRE_ROOT && + !strcasecmp(dentry->d_name.name, "obb")) { + ret = 1; + } + } else if (parent_info->perm == PERM_ANDROID && + !strcasecmp(dentry->d_name.name, "obb")) { + ret = 1; + } + spin_unlock(&SDCARDFS_D(dentry)->lock); + return ret; +} + +/* The lower_path will be stored to the dentry's orig_path + * and the base obbpath will be copyed to the lower_path variable. + * if an error returned, there's no change in the lower_path + * returns: -ERRNO if error (0: no error) */ +int setup_obb_dentry(struct dentry *dentry, struct path *lower_path) +{ + int err = 0; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct path obbpath; + + /* A local obb dentry must have its own orig_path to support rmdir + * and mkdir of itself. Usually, we expect that the sbi->obbpath + * is avaiable on this stage. */ + sdcardfs_set_orig_path(dentry, lower_path); + + err = kern_path(sbi->obbpath_s, + LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &obbpath); + + if(!err) { + /* the obbpath base has been found */ + printk(KERN_INFO "sdcardfs: the sbi->obbpath is found\n"); + pathcpy(lower_path, &obbpath); + } else { + /* if the sbi->obbpath is not available, we can optionally + * setup the lower_path with its orig_path. + * but, the current implementation just returns an error + * because the sdcard daemon also regards this case as + * a lookup fail. */ + printk(KERN_INFO "sdcardfs: the sbi->obbpath is not available\n"); + } + return err; +} + + diff --git a/fs/sdcardfs/file.c b/fs/sdcardfs/file.c new file mode 100644 index 000000000000..c249fa982d3c --- /dev/null +++ b/fs/sdcardfs/file.c @@ -0,0 +1,356 @@ +/* + * fs/sdcardfs/file.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE +#include <linux/backing-dev.h> +#endif + +static ssize_t sdcardfs_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + int err; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE + struct backing_dev_info *bdi; +#endif + + lower_file = sdcardfs_lower_file(file); + +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE + if (file->f_mode & FMODE_NOACTIVE) { + if (!(lower_file->f_mode & FMODE_NOACTIVE)) { + bdi = lower_file->f_mapping->backing_dev_info; + lower_file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&lower_file->f_lock); + lower_file->f_mode |= FMODE_NOACTIVE; + spin_unlock(&lower_file->f_lock); + } + } +#endif + + err = vfs_read(lower_file, buf, count, ppos); + /* update our inode atime upon a successful lower read */ + if (err >= 0) + fsstack_copy_attr_atime(d_inode(dentry), + file_inode(lower_file)); + + return err; +} + +static ssize_t sdcardfs_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + int err; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + + /* check disk space */ + if (!check_min_free_space(dentry, count, 0)) { + printk(KERN_INFO "No minimum free space.\n"); + return -ENOSPC; + } + + lower_file = sdcardfs_lower_file(file); + err = vfs_write(lower_file, buf, count, ppos); + /* update our inode times+sizes upon a successful lower write */ + if (err >= 0) { + fsstack_copy_inode_size(d_inode(dentry), + file_inode(lower_file)); + fsstack_copy_attr_times(d_inode(dentry), + file_inode(lower_file)); + } + + return err; +} + +static int sdcardfs_readdir(struct file *file, struct dir_context *ctx) +{ + int err; + struct file *lower_file = NULL; + struct dentry *dentry = file->f_path.dentry; + + lower_file = sdcardfs_lower_file(file); + + lower_file->f_pos = file->f_pos; + err = iterate_dir(lower_file, ctx); + file->f_pos = lower_file->f_pos; + if (err >= 0) /* copy the atime */ + fsstack_copy_attr_atime(d_inode(dentry), + file_inode(lower_file)); + return err; +} + +static long sdcardfs_unlocked_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long err = -ENOTTY; + struct file *lower_file; + + lower_file = sdcardfs_lower_file(file); + + /* XXX: use vfs_ioctl if/when VFS exports it */ + if (!lower_file || !lower_file->f_op) + goto out; + if (lower_file->f_op->unlocked_ioctl) + err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg); + +out: + return err; +} + +#ifdef CONFIG_COMPAT +static long sdcardfs_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long err = -ENOTTY; + struct file *lower_file; + + lower_file = sdcardfs_lower_file(file); + + /* XXX: use vfs_ioctl if/when VFS exports it */ + if (!lower_file || !lower_file->f_op) + goto out; + if (lower_file->f_op->compat_ioctl) + err = lower_file->f_op->compat_ioctl(lower_file, cmd, arg); + +out: + return err; +} +#endif + +static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err = 0; + bool willwrite; + struct file *lower_file; + const struct vm_operations_struct *saved_vm_ops = NULL; + + /* this might be deferred to mmap's writepage */ + willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags); + + /* + * File systems which do not implement ->writepage may use + * generic_file_readonly_mmap as their ->mmap op. If you call + * generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL. + * But we cannot call the lower ->mmap op, so we can't tell that + * writeable mappings won't work. Therefore, our only choice is to + * check if the lower file system supports the ->writepage, and if + * not, return EINVAL (the same error that + * generic_file_readonly_mmap returns in that case). + */ + lower_file = sdcardfs_lower_file(file); + if (willwrite && !lower_file->f_mapping->a_ops->writepage) { + err = -EINVAL; + printk(KERN_ERR "sdcardfs: lower file system does not " + "support writeable mmap\n"); + goto out; + } + + /* + * find and save lower vm_ops. + * + * XXX: the VFS should have a cleaner way of finding the lower vm_ops + */ + if (!SDCARDFS_F(file)->lower_vm_ops) { + err = lower_file->f_op->mmap(lower_file, vma); + if (err) { + printk(KERN_ERR "sdcardfs: lower mmap failed %d\n", err); + goto out; + } + saved_vm_ops = vma->vm_ops; /* save: came from lower ->mmap */ + err = do_munmap(current->mm, vma->vm_start, + vma->vm_end - vma->vm_start); + if (err) { + printk(KERN_ERR "sdcardfs: do_munmap failed %d\n", err); + goto out; + } + } + + /* + * Next 3 lines are all I need from generic_file_mmap. I definitely + * don't want its test for ->readpage which returns -ENOEXEC. + */ + file_accessed(file); + vma->vm_ops = &sdcardfs_vm_ops; + + file->f_mapping->a_ops = &sdcardfs_aops; /* set our aops */ + if (!SDCARDFS_F(file)->lower_vm_ops) /* save for our ->fault */ + SDCARDFS_F(file)->lower_vm_ops = saved_vm_ops; + +out: + return err; +} + +static int sdcardfs_open(struct inode *inode, struct file *file) +{ + int err = 0; + struct file *lower_file = NULL; + struct path lower_path; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + const struct cred *saved_cred = NULL; + + /* don't open unhashed/deleted files */ + if (d_unhashed(dentry)) { + err = -ENOENT; + goto out_err; + } + + if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_err; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(sbi, saved_cred); + + file->private_data = + kzalloc(sizeof(struct sdcardfs_file_info), GFP_KERNEL); + if (!SDCARDFS_F(file)) { + err = -ENOMEM; + goto out_revert_cred; + } + + /* open lower object and link sdcardfs's file struct to lower's */ + sdcardfs_get_lower_path(file->f_path.dentry, &lower_path); + lower_file = dentry_open(&lower_path, file->f_flags, current_cred()); + path_put(&lower_path); + if (IS_ERR(lower_file)) { + err = PTR_ERR(lower_file); + lower_file = sdcardfs_lower_file(file); + if (lower_file) { + sdcardfs_set_lower_file(file, NULL); + fput(lower_file); /* fput calls dput for lower_dentry */ + } + } else { + sdcardfs_set_lower_file(file, lower_file); + } + + if (err) + kfree(SDCARDFS_F(file)); + else { + sdcardfs_copy_and_fix_attrs(inode, sdcardfs_lower_inode(inode)); + } + +out_revert_cred: + REVERT_CRED(saved_cred); +out_err: + dput(parent); + return err; +} + +static int sdcardfs_flush(struct file *file, fl_owner_t id) +{ + int err = 0; + struct file *lower_file = NULL; + + lower_file = sdcardfs_lower_file(file); + if (lower_file && lower_file->f_op && lower_file->f_op->flush) { + filemap_write_and_wait(file->f_mapping); + err = lower_file->f_op->flush(lower_file, id); + } + + return err; +} + +/* release all lower object references & free the file info structure */ +static int sdcardfs_file_release(struct inode *inode, struct file *file) +{ + struct file *lower_file; + + lower_file = sdcardfs_lower_file(file); + if (lower_file) { + sdcardfs_set_lower_file(file, NULL); + fput(lower_file); + } + + kfree(SDCARDFS_F(file)); + return 0; +} + +static int sdcardfs_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct file *lower_file; + struct path lower_path; + struct dentry *dentry = file->f_path.dentry; + + err = __generic_file_fsync(file, start, end, datasync); + if (err) + goto out; + + lower_file = sdcardfs_lower_file(file); + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_fsync_range(lower_file, start, end, datasync); + sdcardfs_put_lower_path(dentry, &lower_path); +out: + return err; +} + +static int sdcardfs_fasync(int fd, struct file *file, int flag) +{ + int err = 0; + struct file *lower_file = NULL; + + lower_file = sdcardfs_lower_file(file); + if (lower_file->f_op && lower_file->f_op->fasync) + err = lower_file->f_op->fasync(fd, lower_file, flag); + + return err; +} + +const struct file_operations sdcardfs_main_fops = { + .llseek = generic_file_llseek, + .read = sdcardfs_read, + .write = sdcardfs_write, + .unlocked_ioctl = sdcardfs_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = sdcardfs_compat_ioctl, +#endif + .mmap = sdcardfs_mmap, + .open = sdcardfs_open, + .flush = sdcardfs_flush, + .release = sdcardfs_file_release, + .fsync = sdcardfs_fsync, + .fasync = sdcardfs_fasync, +}; + +/* trimmed directory options */ +const struct file_operations sdcardfs_dir_fops = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate = sdcardfs_readdir, + .unlocked_ioctl = sdcardfs_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = sdcardfs_compat_ioctl, +#endif + .open = sdcardfs_open, + .release = sdcardfs_file_release, + .flush = sdcardfs_flush, + .fsync = sdcardfs_fsync, + .fasync = sdcardfs_fasync, +}; diff --git a/fs/sdcardfs/inode.c b/fs/sdcardfs/inode.c new file mode 100644 index 000000000000..2528da0d3ae1 --- /dev/null +++ b/fs/sdcardfs/inode.c @@ -0,0 +1,802 @@ +/* + * fs/sdcardfs/inode.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +/* Do not directly use this function. Use OVERRIDE_CRED() instead. */ +const struct cred * override_fsids(struct sdcardfs_sb_info* sbi) +{ + struct cred * cred; + const struct cred * old_cred; + + cred = prepare_creds(); + if (!cred) + return NULL; + + cred->fsuid = make_kuid(&init_user_ns, sbi->options.fs_low_uid); + cred->fsgid = make_kgid(&init_user_ns, sbi->options.fs_low_gid); + + old_cred = override_creds(cred); + + return old_cred; +} + +/* Do not directly use this function, use REVERT_CRED() instead. */ +void revert_fsids(const struct cred * old_cred) +{ + const struct cred * cur_cred; + + cur_cred = current->cred; + revert_creds(old_cred); + put_cred(cur_cred); +} + +static int sdcardfs_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool want_excl) +{ + int err; + struct dentry *lower_dentry; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + const struct cred *saved_cred = NULL; + + if(!check_caller_access_to_name(dir, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_parent_dentry = lock_parent(lower_dentry); + + /* set last 16bytes of mode field to 0664 */ + mode = (mode & S_IFMT) | 00664; + err = vfs_create(d_inode(lower_parent_dentry), lower_dentry, mode, want_excl); + if (err) + goto out; + + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, SDCARDFS_I(dir)->userid); + if (err) + goto out; + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + +out: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry) +{ + struct dentry *lower_old_dentry; + struct dentry *lower_new_dentry; + struct dentry *lower_dir_dentry; + u64 file_size_save; + int err; + struct path lower_old_path, lower_new_path; + + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb)); + + file_size_save = i_size_read(d_inode(old_dentry)); + sdcardfs_get_lower_path(old_dentry, &lower_old_path); + sdcardfs_get_lower_path(new_dentry, &lower_new_path); + lower_old_dentry = lower_old_path.dentry; + lower_new_dentry = lower_new_path.dentry; + lower_dir_dentry = lock_parent(lower_new_dentry); + + err = vfs_link(lower_old_dentry, d_inode(lower_dir_dentry), + lower_new_dentry, NULL); + if (err || !d_inode(lower_new_dentry)) + goto out; + + err = sdcardfs_interpose(new_dentry, dir->i_sb, &lower_new_path); + if (err) + goto out; + fsstack_copy_attr_times(dir, d_inode(lower_new_dentry)); + fsstack_copy_inode_size(dir, d_inode(lower_new_dentry)); + set_nlink(d_inode(old_dentry), + sdcardfs_lower_inode(d_inode(old_dentry))->i_nlink); + i_size_write(d_inode(new_dentry), file_size_save); +out: + unlock_dir(lower_dir_dentry); + sdcardfs_put_lower_path(old_dentry, &lower_old_path); + sdcardfs_put_lower_path(new_dentry, &lower_new_path); + REVERT_CRED(); + return err; +} +#endif + +static int sdcardfs_unlink(struct inode *dir, struct dentry *dentry) +{ + int err; + struct dentry *lower_dentry; + struct inode *lower_dir_inode = sdcardfs_lower_inode(dir); + struct dentry *lower_dir_dentry; + struct path lower_path; + const struct cred *saved_cred = NULL; + + if(!check_caller_access_to_name(dir, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + dget(lower_dentry); + lower_dir_dentry = lock_parent(lower_dentry); + + err = vfs_unlink(lower_dir_inode, lower_dentry, NULL); + + /* + * Note: unlinking on top of NFS can cause silly-renamed files. + * Trying to delete such files results in EBUSY from NFS + * below. Silly-renamed files will get deleted by NFS later on, so + * we just need to detect them here and treat such EBUSY errors as + * if the upper file was successfully deleted. + */ + if (err == -EBUSY && lower_dentry->d_flags & DCACHE_NFSFS_RENAMED) + err = 0; + if (err) + goto out; + fsstack_copy_attr_times(dir, lower_dir_inode); + fsstack_copy_inode_size(dir, lower_dir_inode); + set_nlink(d_inode(dentry), + sdcardfs_lower_inode(d_inode(dentry))->i_nlink); + d_inode(dentry)->i_ctime = dir->i_ctime; + d_drop(dentry); /* this is needed, else LTP fails (VFS won't do it) */ +out: + unlock_dir(lower_dir_dentry); + dput(lower_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_symlink(struct inode *dir, struct dentry *dentry, + const char *symname) +{ + int err; + struct dentry *lower_dentry; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb)); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_parent_dentry = lock_parent(lower_dentry); + + err = vfs_symlink(d_inode(lower_parent_dentry), lower_dentry, symname); + if (err) + goto out; + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path); + if (err) + goto out; + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + +out: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(); + return err; +} +#endif + +static int touch(char *abs_path, mode_t mode) { + struct file *filp = filp_open(abs_path, O_RDWR|O_CREAT|O_EXCL|O_NOFOLLOW, mode); + if (IS_ERR(filp)) { + if (PTR_ERR(filp) == -EEXIST) { + return 0; + } + else { + printk(KERN_ERR "sdcardfs: failed to open(%s): %ld\n", + abs_path, PTR_ERR(filp)); + return PTR_ERR(filp); + } + } + filp_close(filp, current->files); + return 0; +} + +static int sdcardfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int err; + int make_nomedia_in_obb = 0; + struct dentry *lower_dentry; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + const struct cred *saved_cred = NULL; + struct sdcardfs_inode_info *pi = SDCARDFS_I(dir); + char *page_buf; + char *nomedia_dir_name; + char *nomedia_fullpath; + int fullpath_namelen; + int touch_err = 0; + + if(!check_caller_access_to_name(dir, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + + /* check disk space */ + if (!check_min_free_space(dentry, 0, 1)) { + printk(KERN_INFO "sdcardfs: No minimum free space.\n"); + err = -ENOSPC; + goto out_revert; + } + + /* the lower_dentry is negative here */ + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_parent_dentry = lock_parent(lower_dentry); + + /* set last 16bytes of mode field to 0775 */ + mode = (mode & S_IFMT) | 00775; + err = vfs_mkdir(d_inode(lower_parent_dentry), lower_dentry, mode); + + if (err) + goto out; + + /* if it is a local obb dentry, setup it with the base obbpath */ + if(need_graft_path(dentry)) { + + err = setup_obb_dentry(dentry, &lower_path); + if(err) { + /* if the sbi->obbpath is not available, the lower_path won't be + * changed by setup_obb_dentry() but the lower path is saved to + * its orig_path. this dentry will be revalidated later. + * but now, the lower_path should be NULL */ + sdcardfs_put_reset_lower_path(dentry); + + /* the newly created lower path which saved to its orig_path or + * the lower_path is the base obbpath. + * therefore, an additional path_get is required */ + path_get(&lower_path); + } else + make_nomedia_in_obb = 1; + } + + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, pi->userid); + if (err) + goto out; + + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + /* update number of links on parent directory */ + set_nlink(dir, sdcardfs_lower_inode(dir)->i_nlink); + + if ((!sbi->options.multiuser) && (!strcasecmp(dentry->d_name.name, "obb")) + && (pi->perm == PERM_ANDROID) && (pi->userid == 0)) + make_nomedia_in_obb = 1; + + /* When creating /Android/data and /Android/obb, mark them as .nomedia */ + if (make_nomedia_in_obb || + ((pi->perm == PERM_ANDROID) && (!strcasecmp(dentry->d_name.name, "data")))) { + + page_buf = (char *)__get_free_page(GFP_KERNEL); + if (!page_buf) { + printk(KERN_ERR "sdcardfs: failed to allocate page buf\n"); + goto out; + } + + nomedia_dir_name = d_absolute_path(&lower_path, page_buf, PAGE_SIZE); + if (IS_ERR(nomedia_dir_name)) { + free_page((unsigned long)page_buf); + printk(KERN_ERR "sdcardfs: failed to get .nomedia dir name\n"); + goto out; + } + + fullpath_namelen = page_buf + PAGE_SIZE - nomedia_dir_name - 1; + fullpath_namelen += strlen("/.nomedia"); + nomedia_fullpath = kzalloc(fullpath_namelen + 1, GFP_KERNEL); + if (!nomedia_fullpath) { + free_page((unsigned long)page_buf); + printk(KERN_ERR "sdcardfs: failed to allocate .nomedia fullpath buf\n"); + goto out; + } + + strcpy(nomedia_fullpath, nomedia_dir_name); + free_page((unsigned long)page_buf); + strcat(nomedia_fullpath, "/.nomedia"); + touch_err = touch(nomedia_fullpath, 0664); + if (touch_err) { + printk(KERN_ERR "sdcardfs: failed to touch(%s): %d\n", + nomedia_fullpath, touch_err); + kfree(nomedia_fullpath); + goto out; + } + kfree(nomedia_fullpath); + } +out: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); +out_revert: + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +static int sdcardfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct dentry *lower_dentry; + struct dentry *lower_dir_dentry; + int err; + struct path lower_path; + const struct cred *saved_cred = NULL; + + if(!check_caller_access_to_name(dir, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + + /* sdcardfs_get_real_lower(): in case of remove an user's obb dentry + * the dentry on the original path should be deleted. */ + sdcardfs_get_real_lower(dentry, &lower_path); + + lower_dentry = lower_path.dentry; + lower_dir_dentry = lock_parent(lower_dentry); + + err = vfs_rmdir(d_inode(lower_dir_dentry), lower_dentry); + if (err) + goto out; + + d_drop(dentry); /* drop our dentry on success (why not VFS's job?) */ + if (d_inode(dentry)) + clear_nlink(d_inode(dentry)); + fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry)); + fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry)); + set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink); + +out: + unlock_dir(lower_dir_dentry); + sdcardfs_put_real_lower(dentry, &lower_path); + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t dev) +{ + int err; + struct dentry *lower_dentry; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb)); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_parent_dentry = lock_parent(lower_dentry); + + err = vfs_mknod(d_inode(lower_parent_dentry), lower_dentry, mode, dev); + if (err) + goto out; + + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path); + if (err) + goto out; + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + +out: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(); + return err; +} +#endif + +/* + * The locking rules in sdcardfs_rename are complex. We could use a simpler + * superblock-level name-space lock for renames and copy-ups. + */ +static int sdcardfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + int err = 0; + struct dentry *lower_old_dentry = NULL; + struct dentry *lower_new_dentry = NULL; + struct dentry *lower_old_dir_dentry = NULL; + struct dentry *lower_new_dir_dentry = NULL; + struct dentry *trap = NULL; + struct dentry *new_parent = NULL; + struct path lower_old_path, lower_new_path; + const struct cred *saved_cred = NULL; + + if(!check_caller_access_to_name(old_dir, old_dentry->d_name.name) || + !check_caller_access_to_name(new_dir, new_dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " new_dentry: %s, task:%s\n", + __func__, new_dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(old_dir->i_sb), saved_cred); + + sdcardfs_get_real_lower(old_dentry, &lower_old_path); + sdcardfs_get_lower_path(new_dentry, &lower_new_path); + lower_old_dentry = lower_old_path.dentry; + lower_new_dentry = lower_new_path.dentry; + lower_old_dir_dentry = dget_parent(lower_old_dentry); + lower_new_dir_dentry = dget_parent(lower_new_dentry); + + trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + /* source should not be ancestor of target */ + if (trap == lower_old_dentry) { + err = -EINVAL; + goto out; + } + /* target should not be ancestor of source */ + if (trap == lower_new_dentry) { + err = -ENOTEMPTY; + goto out; + } + + err = vfs_rename(d_inode(lower_old_dir_dentry), lower_old_dentry, + d_inode(lower_new_dir_dentry), lower_new_dentry, + NULL, 0); + if (err) + goto out; + + /* Copy attrs from lower dir, but i_uid/i_gid */ + sdcardfs_copy_and_fix_attrs(new_dir, d_inode(lower_new_dir_dentry)); + fsstack_copy_inode_size(new_dir, d_inode(lower_new_dir_dentry)); + + if (new_dir != old_dir) { + sdcardfs_copy_and_fix_attrs(old_dir, d_inode(lower_old_dir_dentry)); + fsstack_copy_inode_size(old_dir, d_inode(lower_old_dir_dentry)); + + /* update the derived permission of the old_dentry + * with its new parent + */ + new_parent = dget_parent(new_dentry); + if(new_parent) { + if(d_inode(old_dentry)) { + update_derived_permission_lock(old_dentry); + } + dput(new_parent); + } + } + /* At this point, not all dentry information has been moved, so + * we pass along new_dentry for the name.*/ + mutex_lock(&d_inode(old_dentry)->i_mutex); + get_derived_permission_new(new_dentry->d_parent, old_dentry, new_dentry); + fix_derived_permission(d_inode(old_dentry)); + get_derive_permissions_recursive(old_dentry); + mutex_unlock(&d_inode(old_dentry)->i_mutex); +out: + unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + dput(lower_old_dir_dentry); + dput(lower_new_dir_dentry); + sdcardfs_put_real_lower(old_dentry, &lower_old_path); + sdcardfs_put_lower_path(new_dentry, &lower_new_path); + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +{ + int err; + struct dentry *lower_dentry; + struct path lower_path; + /* XXX readlink does not requires overriding credential */ + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + if (!d_inode(lower_dentry)->i_op || + !d_inode(lower_dentry)->i_op->readlink) { + err = -EINVAL; + goto out; + } + + err = d_inode(lower_dentry)->i_op->readlink(lower_dentry, + buf, bufsiz); + if (err < 0) + goto out; + fsstack_copy_attr_atime(d_inode(dentry), d_inode(lower_dentry)); + +out: + sdcardfs_put_lower_path(dentry, &lower_path); + return err; +} +#endif + +#if 0 +static const char *sdcardfs_follow_link(struct dentry *dentry, void **cookie) +{ + char *buf; + int len = PAGE_SIZE, err; + mm_segment_t old_fs; + + /* This is freed by the put_link method assuming a successful call. */ + buf = kmalloc(len, GFP_KERNEL); + if (!buf) { + buf = ERR_PTR(-ENOMEM); + return buf; + } + + /* read the symlink, and then we will follow it */ + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = sdcardfs_readlink(dentry, buf, len); + set_fs(old_fs); + if (err < 0) { + kfree(buf); + buf = ERR_PTR(err); + } else { + buf[err] = '\0'; + } + return *cookie = buf; +} +#endif + +static int sdcardfs_permission(struct inode *inode, int mask) +{ + int err; + + /* + * Permission check on sdcardfs inode. + * Calling process should have AID_SDCARD_RW permission + */ + err = generic_permission(inode, mask); + + /* XXX + * Original sdcardfs code calls inode_permission(lower_inode,.. ) + * for checking inode permission. But doing such things here seems + * duplicated work, because the functions called after this func, + * such as vfs_create, vfs_unlink, vfs_rename, and etc, + * does exactly same thing, i.e., they calls inode_permission(). + * So we just let they do the things. + * If there are any security hole, just uncomment following if block. + */ +#if 0 + if (!err) { + /* + * Permission check on lower_inode(=EXT4). + * we check it with AID_MEDIA_RW permission + */ + struct inode *lower_inode; + OVERRIDE_CRED(SDCARDFS_SB(inode->sb)); + + lower_inode = sdcardfs_lower_inode(inode); + err = inode_permission(lower_inode, mask); + + REVERT_CRED(); + } +#endif + return err; + +} + +static int sdcardfs_setattr(struct dentry *dentry, struct iattr *ia) +{ + int err; + struct dentry *lower_dentry; + struct inode *inode; + struct inode *lower_inode; + struct path lower_path; + struct iattr lower_ia; + struct dentry *parent; + + inode = d_inode(dentry); + + /* + * Check if user has permission to change inode. We don't check if + * this user can change the lower inode: that should happen when + * calling notify_change on the lower inode. + */ + err = inode_change_ok(inode, ia); + + /* no vfs_XXX operations required, cred overriding will be skipped. wj*/ + if (!err) { + /* check the Android group ID */ + parent = dget_parent(dentry); + if(!check_caller_access_to_name(d_inode(parent), dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + } + dput(parent); + } + + if (err) + goto out_err; + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_inode = sdcardfs_lower_inode(inode); + + /* prepare our own lower struct iattr (with the lower file) */ + memcpy(&lower_ia, ia, sizeof(lower_ia)); + if (ia->ia_valid & ATTR_FILE) + lower_ia.ia_file = sdcardfs_lower_file(ia->ia_file); + + lower_ia.ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE); + + /* + * If shrinking, first truncate upper level to cancel writing dirty + * pages beyond the new eof; and also if its' maxbytes is more + * limiting (fail with -EFBIG before making any change to the lower + * level). There is no need to vmtruncate the upper level + * afterwards in the other cases: we fsstack_copy_inode_size from + * the lower level. + */ + if (current->mm) + down_write(¤t->mm->mmap_sem); + if (ia->ia_valid & ATTR_SIZE) { + err = inode_newsize_ok(inode, ia->ia_size); + if (err) { + if (current->mm) + up_write(¤t->mm->mmap_sem); + goto out; + } + truncate_setsize(inode, ia->ia_size); + } + + /* + * mode change is for clearing setuid/setgid bits. Allow lower fs + * to interpret this in its own way. + */ + if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + lower_ia.ia_valid &= ~ATTR_MODE; + + /* notify the (possibly copied-up) lower inode */ + /* + * Note: we use d_inode(lower_dentry), because lower_inode may be + * unlinked (no inode->i_sb and i_ino==0. This happens if someone + * tries to open(), unlink(), then ftruncate() a file. + */ + mutex_lock(&d_inode(lower_dentry)->i_mutex); + err = notify_change(lower_dentry, &lower_ia, /* note: lower_ia */ + NULL); + mutex_unlock(&d_inode(lower_dentry)->i_mutex); + if (current->mm) + up_write(¤t->mm->mmap_sem); + if (err) + goto out; + + /* get attributes from the lower inode and update derived permissions */ + sdcardfs_copy_and_fix_attrs(inode, lower_inode); + + /* + * Not running fsstack_copy_inode_size(inode, lower_inode), because + * VFS should update our inode size, and notify_change on + * lower_inode should update its size. + */ + +out: + sdcardfs_put_lower_path(dentry, &lower_path); +out_err: + return err; +} + +static int sdcardfs_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct dentry *lower_dentry; + struct inode *inode; + struct inode *lower_inode; + struct path lower_path; + struct dentry *parent; + + parent = dget_parent(dentry); + if(!check_caller_access_to_name(d_inode(parent), dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + dput(parent); + return -EACCES; + } + dput(parent); + + inode = d_inode(dentry); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_inode = sdcardfs_lower_inode(inode); + + + sdcardfs_copy_and_fix_attrs(inode, lower_inode); + fsstack_copy_inode_size(inode, lower_inode); + + + generic_fillattr(inode, stat); + sdcardfs_put_lower_path(dentry, &lower_path); + return 0; +} + +const struct inode_operations sdcardfs_symlink_iops = { + .permission = sdcardfs_permission, + .setattr = sdcardfs_setattr, + /* XXX Following operations are implemented, + * but FUSE(sdcard) or FAT does not support them + * These methods are *NOT* perfectly tested. + .readlink = sdcardfs_readlink, + .follow_link = sdcardfs_follow_link, + .put_link = kfree_put_link, + */ +}; + +const struct inode_operations sdcardfs_dir_iops = { + .create = sdcardfs_create, + .lookup = sdcardfs_lookup, +#if 0 + .permission = sdcardfs_permission, +#endif + .unlink = sdcardfs_unlink, + .mkdir = sdcardfs_mkdir, + .rmdir = sdcardfs_rmdir, + .rename = sdcardfs_rename, + .setattr = sdcardfs_setattr, + .getattr = sdcardfs_getattr, + /* XXX Following operations are implemented, + * but FUSE(sdcard) or FAT does not support them + * These methods are *NOT* perfectly tested. + .symlink = sdcardfs_symlink, + .link = sdcardfs_link, + .mknod = sdcardfs_mknod, + */ +}; + +const struct inode_operations sdcardfs_main_iops = { + .permission = sdcardfs_permission, + .setattr = sdcardfs_setattr, + .getattr = sdcardfs_getattr, +}; diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c new file mode 100644 index 000000000000..a01b06a514fd --- /dev/null +++ b/fs/sdcardfs/lookup.c @@ -0,0 +1,384 @@ +/* + * fs/sdcardfs/lookup.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include "linux/delay.h" + +/* The dentry cache is just so we have properly sized dentries */ +static struct kmem_cache *sdcardfs_dentry_cachep; + +int sdcardfs_init_dentry_cache(void) +{ + sdcardfs_dentry_cachep = + kmem_cache_create("sdcardfs_dentry", + sizeof(struct sdcardfs_dentry_info), + 0, SLAB_RECLAIM_ACCOUNT, NULL); + + return sdcardfs_dentry_cachep ? 0 : -ENOMEM; +} + +void sdcardfs_destroy_dentry_cache(void) +{ + if (sdcardfs_dentry_cachep) + kmem_cache_destroy(sdcardfs_dentry_cachep); +} + +void free_dentry_private_data(struct dentry *dentry) +{ + if (!dentry || !dentry->d_fsdata) + return; + kmem_cache_free(sdcardfs_dentry_cachep, dentry->d_fsdata); + dentry->d_fsdata = NULL; +} + +/* allocate new dentry private data */ +int new_dentry_private_data(struct dentry *dentry) +{ + struct sdcardfs_dentry_info *info = SDCARDFS_D(dentry); + + /* use zalloc to init dentry_info.lower_path */ + info = kmem_cache_zalloc(sdcardfs_dentry_cachep, GFP_ATOMIC); + if (!info) + return -ENOMEM; + + spin_lock_init(&info->lock); + dentry->d_fsdata = info; + + return 0; +} + +struct inode_data { + struct inode *lower_inode; + userid_t id; +}; + +static int sdcardfs_inode_test(struct inode *inode, void *candidate_data/*void *candidate_lower_inode*/) +{ + struct inode *current_lower_inode = sdcardfs_lower_inode(inode); + userid_t current_userid = SDCARDFS_I(inode)->userid; + if (current_lower_inode == ((struct inode_data *)candidate_data)->lower_inode && + current_userid == ((struct inode_data *)candidate_data)->id) + return 1; /* found a match */ + else + return 0; /* no match */ +} + +static int sdcardfs_inode_set(struct inode *inode, void *lower_inode) +{ + /* we do actual inode initialization in sdcardfs_iget */ + return 0; +} + +struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, userid_t id) +{ + struct sdcardfs_inode_info *info; + struct inode_data data; + struct inode *inode; /* the new inode to return */ + int err; + + data.id = id; + data.lower_inode = lower_inode; + inode = iget5_locked(sb, /* our superblock */ + /* + * hashval: we use inode number, but we can + * also use "(unsigned long)lower_inode" + * instead. + */ + lower_inode->i_ino, /* hashval */ + sdcardfs_inode_test, /* inode comparison function */ + sdcardfs_inode_set, /* inode init function */ + &data); /* data passed to test+set fxns */ + if (!inode) { + err = -EACCES; + iput(lower_inode); + return ERR_PTR(err); + } + /* if found a cached inode, then just return it */ + if (!(inode->i_state & I_NEW)) + return inode; + + /* initialize new inode */ + info = SDCARDFS_I(inode); + + inode->i_ino = lower_inode->i_ino; + if (!igrab(lower_inode)) { + err = -ESTALE; + return ERR_PTR(err); + } + sdcardfs_set_lower_inode(inode, lower_inode); + + inode->i_version++; + + /* use different set of inode ops for symlinks & directories */ + if (S_ISDIR(lower_inode->i_mode)) + inode->i_op = &sdcardfs_dir_iops; + else if (S_ISLNK(lower_inode->i_mode)) + inode->i_op = &sdcardfs_symlink_iops; + else + inode->i_op = &sdcardfs_main_iops; + + /* use different set of file ops for directories */ + if (S_ISDIR(lower_inode->i_mode)) + inode->i_fop = &sdcardfs_dir_fops; + else + inode->i_fop = &sdcardfs_main_fops; + + inode->i_mapping->a_ops = &sdcardfs_aops; + + inode->i_atime.tv_sec = 0; + inode->i_atime.tv_nsec = 0; + inode->i_mtime.tv_sec = 0; + inode->i_mtime.tv_nsec = 0; + inode->i_ctime.tv_sec = 0; + inode->i_ctime.tv_nsec = 0; + + /* properly initialize special inodes */ + if (S_ISBLK(lower_inode->i_mode) || S_ISCHR(lower_inode->i_mode) || + S_ISFIFO(lower_inode->i_mode) || S_ISSOCK(lower_inode->i_mode)) + init_special_inode(inode, lower_inode->i_mode, + lower_inode->i_rdev); + + /* all well, copy inode attributes */ + sdcardfs_copy_and_fix_attrs(inode, lower_inode); + fsstack_copy_inode_size(inode, lower_inode); + + unlock_new_inode(inode); + return inode; +} + +/* + * Connect a sdcardfs inode dentry/inode with several lower ones. This is + * the classic stackable file system "vnode interposition" action. + * + * @dentry: sdcardfs's dentry which interposes on lower one + * @sb: sdcardfs's super_block + * @lower_path: the lower path (caller does path_get/put) + */ +int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, + struct path *lower_path, userid_t id) +{ + int err = 0; + struct inode *inode; + struct inode *lower_inode; + struct super_block *lower_sb; + + lower_inode = lower_path->dentry->d_inode; + lower_sb = sdcardfs_lower_super(sb); + + /* check that the lower file system didn't cross a mount point */ + if (lower_inode->i_sb != lower_sb) { + err = -EXDEV; + goto out; + } + + /* + * We allocate our new inode below by calling sdcardfs_iget, + * which will initialize some of the new inode's fields + */ + + /* inherit lower inode number for sdcardfs's inode */ + inode = sdcardfs_iget(sb, lower_inode, id); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out; + } + + d_add(dentry, inode); + update_derived_permission_lock(dentry); +out: + return err; +} + +/* + * Main driver function for sdcardfs's lookup. + * + * Returns: NULL (ok), ERR_PTR if an error occurred. + * Fills in lower_parent_path with <dentry,mnt> on success. + */ +static struct dentry *__sdcardfs_lookup(struct dentry *dentry, + unsigned int flags, struct path *lower_parent_path, userid_t id) +{ + int err = 0; + struct vfsmount *lower_dir_mnt; + struct dentry *lower_dir_dentry = NULL; + struct dentry *lower_dentry; + const char *name; + struct path lower_path; + struct qstr this; + struct sdcardfs_sb_info *sbi; + + sbi = SDCARDFS_SB(dentry->d_sb); + /* must initialize dentry operations */ + d_set_d_op(dentry, &sdcardfs_ci_dops); + + if (IS_ROOT(dentry)) + goto out; + + name = dentry->d_name.name; + + /* now start the actual lookup procedure */ + lower_dir_dentry = lower_parent_path->dentry; + lower_dir_mnt = lower_parent_path->mnt; + + /* Use vfs_path_lookup to check if the dentry exists or not */ + err = vfs_path_lookup(lower_dir_dentry, lower_dir_mnt, name, 0, + &lower_path); + + /* no error: handle positive dentries */ + if (!err) { + /* check if the dentry is an obb dentry + * if true, the lower_inode must be replaced with + * the inode of the graft path */ + + if(need_graft_path(dentry)) { + + /* setup_obb_dentry() + * The lower_path will be stored to the dentry's orig_path + * and the base obbpath will be copyed to the lower_path variable. + * if an error returned, there's no change in the lower_path + * returns: -ERRNO if error (0: no error) */ + err = setup_obb_dentry(dentry, &lower_path); + + if(err) { + /* if the sbi->obbpath is not available, we can optionally + * setup the lower_path with its orig_path. + * but, the current implementation just returns an error + * because the sdcard daemon also regards this case as + * a lookup fail. */ + printk(KERN_INFO "sdcardfs: base obbpath is not available\n"); + sdcardfs_put_reset_orig_path(dentry); + goto out; + } + } + + sdcardfs_set_lower_path(dentry, &lower_path); + err = sdcardfs_interpose(dentry, dentry->d_sb, &lower_path, id); + if (err) /* path_put underlying path on error */ + sdcardfs_put_reset_lower_path(dentry); + goto out; + } + + /* + * We don't consider ENOENT an error, and we want to return a + * negative dentry. + */ + if (err && err != -ENOENT) + goto out; + + /* instatiate a new negative dentry */ + this.name = name; + this.len = strlen(name); + this.hash = full_name_hash(this.name, this.len); + lower_dentry = d_lookup(lower_dir_dentry, &this); + if (lower_dentry) + goto setup_lower; + + lower_dentry = d_alloc(lower_dir_dentry, &this); + if (!lower_dentry) { + err = -ENOMEM; + goto out; + } + d_add(lower_dentry, NULL); /* instantiate and hash */ + +setup_lower: + lower_path.dentry = lower_dentry; + lower_path.mnt = mntget(lower_dir_mnt); + sdcardfs_set_lower_path(dentry, &lower_path); + + /* + * If the intent is to create a file, then don't return an error, so + * the VFS will continue the process of making this negative dentry + * into a positive one. + */ + if (flags & (LOOKUP_CREATE|LOOKUP_RENAME_TARGET)) + err = 0; + +out: + return ERR_PTR(err); +} + +/* + * On success: + * fills dentry object appropriate values and returns NULL. + * On fail (== error) + * returns error ptr + * + * @dir : Parent inode. It is locked (dir->i_mutex) + * @dentry : Target dentry to lookup. we should set each of fields. + * (dentry->d_name is initialized already) + * @nd : nameidata of parent inode + */ +struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct dentry *ret = NULL, *parent; + struct path lower_parent_path; + int err = 0; + const struct cred *saved_cred = NULL; + + parent = dget_parent(dentry); + + if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) { + ret = ERR_PTR(-EACCES); + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + goto out_err; + } + + /* save current_cred and override it */ + OVERRIDE_CRED_PTR(SDCARDFS_SB(dir->i_sb), saved_cred); + + sdcardfs_get_lower_path(parent, &lower_parent_path); + + /* allocate dentry private data. We free it in ->d_release */ + err = new_dentry_private_data(dentry); + if (err) { + ret = ERR_PTR(err); + goto out; + } + + ret = __sdcardfs_lookup(dentry, flags, &lower_parent_path, SDCARDFS_I(dir)->userid); + if (IS_ERR(ret)) + { + goto out; + } + if (ret) + dentry = ret; + if (dentry->d_inode) { + fsstack_copy_attr_times(dentry->d_inode, + sdcardfs_lower_inode(dentry->d_inode)); + /* get drived permission */ + mutex_lock(&dentry->d_inode->i_mutex); + get_derived_permission(parent, dentry); + fix_derived_permission(dentry->d_inode); + mutex_unlock(&dentry->d_inode->i_mutex); + } + /* update parent directory's atime */ + fsstack_copy_attr_atime(parent->d_inode, + sdcardfs_lower_inode(parent->d_inode)); + +out: + sdcardfs_put_lower_path(parent, &lower_parent_path); + REVERT_CRED(saved_cred); +out_err: + dput(parent); + return ret; +} diff --git a/fs/sdcardfs/main.c b/fs/sdcardfs/main.c new file mode 100644 index 000000000000..a6522286d731 --- /dev/null +++ b/fs/sdcardfs/main.c @@ -0,0 +1,402 @@ +/* + * fs/sdcardfs/main.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include <linux/module.h> +#include <linux/types.h> +#include <linux/parser.h> + +enum { + Opt_fsuid, + Opt_fsgid, + Opt_gid, + Opt_debug, + Opt_lower_fs, + Opt_mask, + Opt_multiuser, // May need? + Opt_userid, + Opt_reserved_mb, + Opt_err, +}; + +static const match_table_t sdcardfs_tokens = { + {Opt_fsuid, "fsuid=%u"}, + {Opt_fsgid, "fsgid=%u"}, + {Opt_gid, "gid=%u"}, + {Opt_debug, "debug"}, + {Opt_mask, "mask=%u"}, + {Opt_userid, "userid=%d"}, + {Opt_multiuser, "multiuser"}, + {Opt_reserved_mb, "reserved_mb=%u"}, + {Opt_err, NULL} +}; + +static int parse_options(struct super_block *sb, char *options, int silent, + int *debug, struct sdcardfs_mount_options *opts) +{ + char *p; + substring_t args[MAX_OPT_ARGS]; + int option; + + /* by default, we use AID_MEDIA_RW as uid, gid */ + opts->fs_low_uid = AID_MEDIA_RW; + opts->fs_low_gid = AID_MEDIA_RW; + opts->mask = 0; + opts->multiuser = false; + opts->fs_user_id = 0; + opts->gid = 0; + /* by default, 0MB is reserved */ + opts->reserved_mb = 0; + + *debug = 0; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + if (!*p) + continue; + + token = match_token(p, sdcardfs_tokens, args); + + switch (token) { + case Opt_debug: + *debug = 1; + break; + case Opt_fsuid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_low_uid = option; + break; + case Opt_fsgid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_low_gid = option; + break; + case Opt_gid: + if (match_int(&args[0], &option)) + return 0; + opts->gid = option; + break; + case Opt_userid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_user_id = option; + break; + case Opt_mask: + if (match_int(&args[0], &option)) + return 0; + opts->mask = option; + break; + case Opt_multiuser: + opts->multiuser = true; + break; + case Opt_reserved_mb: + if (match_int(&args[0], &option)) + return 0; + opts->reserved_mb = option; + break; + /* unknown option */ + default: + if (!silent) { + printk( KERN_ERR "Unrecognized mount option \"%s\" " + "or missing value", p); + } + return -EINVAL; + } + } + + if (*debug) { + printk( KERN_INFO "sdcardfs : options - debug:%d\n", *debug); + printk( KERN_INFO "sdcardfs : options - uid:%d\n", + opts->fs_low_uid); + printk( KERN_INFO "sdcardfs : options - gid:%d\n", + opts->fs_low_gid); + } + + return 0; +} + +#if 0 +/* + * our custom d_alloc_root work-alike + * + * we can't use d_alloc_root if we want to use our own interpose function + * unchanged, so we simply call our own "fake" d_alloc_root + */ +static struct dentry *sdcardfs_d_alloc_root(struct super_block *sb) +{ + struct dentry *ret = NULL; + + if (sb) { + static const struct qstr name = { + .name = "/", + .len = 1 + }; + + ret = d_alloc(NULL, &name); + if (ret) { + d_set_d_op(ret, &sdcardfs_ci_dops); + ret->d_sb = sb; + ret->d_parent = ret; + } + } + return ret; +} +#endif + +DEFINE_MUTEX(sdcardfs_super_list_lock); +LIST_HEAD(sdcardfs_super_list); +EXPORT_SYMBOL_GPL(sdcardfs_super_list_lock); +EXPORT_SYMBOL_GPL(sdcardfs_super_list); + +/* + * There is no need to lock the sdcardfs_super_info's rwsem as there is no + * way anyone can have a reference to the superblock at this point in time. + */ +static int sdcardfs_read_super(struct super_block *sb, const char *dev_name, + void *raw_data, int silent) +{ + int err = 0; + int debug; + struct super_block *lower_sb; + struct path lower_path; + struct sdcardfs_sb_info *sb_info; + struct inode *inode; + + printk(KERN_INFO "sdcardfs version 2.0\n"); + + if (!dev_name) { + printk(KERN_ERR + "sdcardfs: read_super: missing dev_name argument\n"); + err = -EINVAL; + goto out; + } + + printk(KERN_INFO "sdcardfs: dev_name -> %s\n", dev_name); + printk(KERN_INFO "sdcardfs: options -> %s\n", (char *)raw_data); + + /* parse lower path */ + err = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, + &lower_path); + if (err) { + printk(KERN_ERR "sdcardfs: error accessing lower directory '%s'\n", dev_name); + goto out; + } + + /* allocate superblock private data */ + sb->s_fs_info = kzalloc(sizeof(struct sdcardfs_sb_info), GFP_KERNEL); + if (!SDCARDFS_SB(sb)) { + printk(KERN_CRIT "sdcardfs: read_super: out of memory\n"); + err = -ENOMEM; + goto out_free; + } + + sb_info = sb->s_fs_info; + /* parse options */ + err = parse_options(sb, raw_data, silent, &debug, &sb_info->options); + if (err) { + printk(KERN_ERR "sdcardfs: invalid options\n"); + goto out_freesbi; + } + + /* set the lower superblock field of upper superblock */ + lower_sb = lower_path.dentry->d_sb; + atomic_inc(&lower_sb->s_active); + sdcardfs_set_lower_super(sb, lower_sb); + + /* inherit maxbytes from lower file system */ + sb->s_maxbytes = lower_sb->s_maxbytes; + + /* + * Our c/m/atime granularity is 1 ns because we may stack on file + * systems whose granularity is as good. + */ + sb->s_time_gran = 1; + + sb->s_magic = SDCARDFS_SUPER_MAGIC; + sb->s_op = &sdcardfs_sops; + + /* get a new inode and allocate our root dentry */ + inode = sdcardfs_iget(sb, lower_path.dentry->d_inode, 0); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_sput; + } + sb->s_root = d_make_root(inode); + if (!sb->s_root) { + err = -ENOMEM; + goto out_iput; + } + d_set_d_op(sb->s_root, &sdcardfs_ci_dops); + + /* link the upper and lower dentries */ + sb->s_root->d_fsdata = NULL; + err = new_dentry_private_data(sb->s_root); + if (err) + goto out_freeroot; + + /* set the lower dentries for s_root */ + sdcardfs_set_lower_path(sb->s_root, &lower_path); + + /* + * No need to call interpose because we already have a positive + * dentry, which was instantiated by d_make_root. Just need to + * d_rehash it. + */ + d_rehash(sb->s_root); + + /* setup permission policy */ + sb_info->obbpath_s = kzalloc(PATH_MAX, GFP_KERNEL); + mutex_lock(&sdcardfs_super_list_lock); + if(sb_info->options.multiuser) { + setup_derived_state(sb->s_root->d_inode, PERM_PRE_ROOT, sb_info->options.fs_user_id, AID_ROOT, false); + snprintf(sb_info->obbpath_s, PATH_MAX, "%s/obb", dev_name); + /*err = prepare_dir(sb_info->obbpath_s, + sb_info->options.fs_low_uid, + sb_info->options.fs_low_gid, 00755);*/ + } else { + setup_derived_state(sb->s_root->d_inode, PERM_ROOT, sb_info->options.fs_low_uid, AID_ROOT, false); + snprintf(sb_info->obbpath_s, PATH_MAX, "%s/Android/obb", dev_name); + } + fix_derived_permission(sb->s_root->d_inode); + sb_info->sb = sb; + list_add(&sb_info->list, &sdcardfs_super_list); + mutex_unlock(&sdcardfs_super_list_lock); + + if (!silent) + printk(KERN_INFO "sdcardfs: mounted on top of %s type %s\n", + dev_name, lower_sb->s_type->name); + goto out; /* all is well */ + + /* no longer needed: free_dentry_private_data(sb->s_root); */ +out_freeroot: + dput(sb->s_root); +out_iput: + iput(inode); +out_sput: + /* drop refs we took earlier */ + atomic_dec(&lower_sb->s_active); +out_freesbi: + kfree(SDCARDFS_SB(sb)); + sb->s_fs_info = NULL; +out_free: + path_put(&lower_path); + +out: + return err; +} + +/* A feature which supports mount_nodev() with options */ +static struct dentry *mount_nodev_with_options(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, + int (*fill_super)(struct super_block *, const char *, void *, int)) + +{ + int error; + struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL); + + if (IS_ERR(s)) + return ERR_CAST(s); + + s->s_flags = flags; + + error = fill_super(s, dev_name, data, flags & MS_SILENT ? 1 : 0); + if (error) { + deactivate_locked_super(s); + return ERR_PTR(error); + } + s->s_flags |= MS_ACTIVE; + return dget(s->s_root); +} + +struct dentry *sdcardfs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + /* + * dev_name is a lower_path_name, + * raw_data is a option string. + */ + return mount_nodev_with_options(fs_type, flags, dev_name, + raw_data, sdcardfs_read_super); +} + +void sdcardfs_kill_sb(struct super_block *sb) { + struct sdcardfs_sb_info *sbi; + if (sb->s_magic == SDCARDFS_SUPER_MAGIC) { + sbi = SDCARDFS_SB(sb); + mutex_lock(&sdcardfs_super_list_lock); + list_del(&sbi->list); + mutex_unlock(&sdcardfs_super_list_lock); + } + generic_shutdown_super(sb); +} + +static struct file_system_type sdcardfs_fs_type = { + .owner = THIS_MODULE, + .name = SDCARDFS_NAME, + .mount = sdcardfs_mount, + .kill_sb = sdcardfs_kill_sb, + .fs_flags = 0, +}; + +static int __init init_sdcardfs_fs(void) +{ + int err; + + pr_info("Registering sdcardfs " SDCARDFS_VERSION "\n"); + + err = sdcardfs_init_inode_cache(); + if (err) + goto out; + err = sdcardfs_init_dentry_cache(); + if (err) + goto out; + err = packagelist_init(); + if (err) + goto out; + err = register_filesystem(&sdcardfs_fs_type); +out: + if (err) { + sdcardfs_destroy_inode_cache(); + sdcardfs_destroy_dentry_cache(); + packagelist_exit(); + } + return err; +} + +static void __exit exit_sdcardfs_fs(void) +{ + sdcardfs_destroy_inode_cache(); + sdcardfs_destroy_dentry_cache(); + packagelist_exit(); + unregister_filesystem(&sdcardfs_fs_type); + pr_info("Completed sdcardfs module unload\n"); +} + +MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University" + " (http://www.fsl.cs.sunysb.edu/)"); +MODULE_DESCRIPTION("Wrapfs " SDCARDFS_VERSION + " (http://wrapfs.filesystems.org/)"); +MODULE_LICENSE("GPL"); + +module_init(init_sdcardfs_fs); +module_exit(exit_sdcardfs_fs); diff --git a/fs/sdcardfs/mmap.c b/fs/sdcardfs/mmap.c new file mode 100644 index 000000000000..e21f64675a80 --- /dev/null +++ b/fs/sdcardfs/mmap.c @@ -0,0 +1,81 @@ +/* + * fs/sdcardfs/mmap.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +static int sdcardfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + int err; + struct file *file, *lower_file; + const struct vm_operations_struct *lower_vm_ops; + struct vm_area_struct lower_vma; + + memcpy(&lower_vma, vma, sizeof(struct vm_area_struct)); + file = lower_vma.vm_file; + lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops; + BUG_ON(!lower_vm_ops); + + lower_file = sdcardfs_lower_file(file); + /* + * XXX: vm_ops->fault may be called in parallel. Because we have to + * resort to temporarily changing the vma->vm_file to point to the + * lower file, a concurrent invocation of sdcardfs_fault could see a + * different value. In this workaround, we keep a different copy of + * the vma structure in our stack, so we never expose a different + * value of the vma->vm_file called to us, even temporarily. A + * better fix would be to change the calling semantics of ->fault to + * take an explicit file pointer. + */ + lower_vma.vm_file = lower_file; + err = lower_vm_ops->fault(&lower_vma, vmf); + return err; +} + +static ssize_t sdcardfs_direct_IO(struct kiocb *iocb, + struct iov_iter *iter, loff_t pos) +{ + /* + * This function returns zero on purpose in order to support direct IO. + * __dentry_open checks a_ops->direct_IO and returns EINVAL if it is null. + * + * However, this function won't be called by certain file operations + * including generic fs functions. * reads and writes are delivered to + * the lower file systems and the direct IOs will be handled by them. + * + * NOTE: exceptionally, on the recent kernels (since Linux 3.8.x), + * swap_writepage invokes this function directly. + */ + printk(KERN_INFO "%s, operation is not supported\n", __func__); + return 0; +} + +/* + * XXX: the default address_space_ops for sdcardfs is empty. We cannot set + * our inode->i_mapping->a_ops to NULL because too many code paths expect + * the a_ops vector to be non-NULL. + */ +const struct address_space_operations sdcardfs_aops = { + /* empty on purpose */ + .direct_IO = sdcardfs_direct_IO, +}; + +const struct vm_operations_struct sdcardfs_vm_ops = { + .fault = sdcardfs_fault, +}; diff --git a/fs/sdcardfs/multiuser.h b/fs/sdcardfs/multiuser.h new file mode 100644 index 000000000000..923ba101dfa9 --- /dev/null +++ b/fs/sdcardfs/multiuser.h @@ -0,0 +1,37 @@ +/* + * fs/sdcardfs/multiuser.h + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#define MULTIUSER_APP_PER_USER_RANGE 100000 + +typedef uid_t userid_t; +typedef uid_t appid_t; + +static inline userid_t multiuser_get_user_id(uid_t uid) { + return uid / MULTIUSER_APP_PER_USER_RANGE; +} + +static inline appid_t multiuser_get_app_id(uid_t uid) { + return uid % MULTIUSER_APP_PER_USER_RANGE; +} + +static inline uid_t multiuser_get_uid(userid_t userId, appid_t appId) { + return userId * MULTIUSER_APP_PER_USER_RANGE + (appId % MULTIUSER_APP_PER_USER_RANGE); +} + diff --git a/fs/sdcardfs/packagelist.c b/fs/sdcardfs/packagelist.c new file mode 100644 index 000000000000..10f0d6be718b --- /dev/null +++ b/fs/sdcardfs/packagelist.c @@ -0,0 +1,437 @@ +/* + * fs/sdcardfs/packagelist.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include <linux/hashtable.h> +#include <linux/delay.h> + + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/slab.h> + +#include <linux/configfs.h> + +#define STRING_BUF_SIZE (512) + +struct hashtable_entry { + struct hlist_node hlist; + void *key; + unsigned int value; +}; + +struct sb_list { + struct super_block *sb; + struct list_head list; +}; + +struct packagelist_data { + DECLARE_HASHTABLE(package_to_appid,8); + struct mutex hashtable_lock; + +}; + +static struct packagelist_data *pkgl_data_all; + +static struct kmem_cache *hashtable_entry_cachep; + +static unsigned int str_hash(const char *key) { + int i; + unsigned int h = strlen(key); + char *data = (char *)key; + + for (i = 0; i < strlen(key); i++) { + h = h * 31 + *data; + data++; + } + return h; +} + +appid_t get_appid(void *pkgl_id, const char *app_name) +{ + struct packagelist_data *pkgl_dat = pkgl_data_all; + struct hashtable_entry *hash_cur; + unsigned int hash = str_hash(app_name); + appid_t ret_id; + + mutex_lock(&pkgl_dat->hashtable_lock); + hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { + if (!strcasecmp(app_name, hash_cur->key)) { + ret_id = (appid_t)hash_cur->value; + mutex_unlock(&pkgl_dat->hashtable_lock); + return ret_id; + } + } + mutex_unlock(&pkgl_dat->hashtable_lock); + return 0; +} + +/* Kernel has already enforced everything we returned through + * derive_permissions_locked(), so this is used to lock down access + * even further, such as enforcing that apps hold sdcard_rw. */ +int check_caller_access_to_name(struct inode *parent_node, const char* name) { + + /* Always block security-sensitive files at root */ + if (parent_node && SDCARDFS_I(parent_node)->perm == PERM_ROOT) { + if (!strcasecmp(name, "autorun.inf") + || !strcasecmp(name, ".android_secure") + || !strcasecmp(name, "android_secure")) { + return 0; + } + } + + /* Root always has access; access for any other UIDs should always + * be controlled through packages.list. */ + if (from_kuid(&init_user_ns, current_fsuid()) == 0) { + return 1; + } + + /* No extra permissions to enforce */ + return 1; +} + +/* This function is used when file opening. The open flags must be + * checked before calling check_caller_access_to_name() */ +int open_flags_to_access_mode(int open_flags) { + if((open_flags & O_ACCMODE) == O_RDONLY) { + return 0; /* R_OK */ + } else if ((open_flags & O_ACCMODE) == O_WRONLY) { + return 1; /* W_OK */ + } else { + /* Probably O_RDRW, but treat as default to be safe */ + return 1; /* R_OK | W_OK */ + } +} + +static int insert_str_to_int_lock(struct packagelist_data *pkgl_dat, char *key, + unsigned int value) +{ + struct hashtable_entry *hash_cur; + struct hashtable_entry *new_entry; + unsigned int hash = str_hash(key); + + hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { + if (!strcasecmp(key, hash_cur->key)) { + hash_cur->value = value; + return 0; + } + } + new_entry = kmem_cache_alloc(hashtable_entry_cachep, GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->key = kstrdup(key, GFP_KERNEL); + new_entry->value = value; + hash_add(pkgl_dat->package_to_appid, &new_entry->hlist, hash); + return 0; +} + +static void fixup_perms(struct super_block *sb) { + if (sb && sb->s_magic == SDCARDFS_SUPER_MAGIC) { + mutex_lock(&sb->s_root->d_inode->i_mutex); + get_derive_permissions_recursive(sb->s_root); + mutex_unlock(&sb->s_root->d_inode->i_mutex); + } +} + +static int insert_str_to_int(struct packagelist_data *pkgl_dat, char *key, + unsigned int value) { + int ret; + struct sdcardfs_sb_info *sbinfo; + mutex_lock(&sdcardfs_super_list_lock); + mutex_lock(&pkgl_dat->hashtable_lock); + ret = insert_str_to_int_lock(pkgl_dat, key, value); + mutex_unlock(&pkgl_dat->hashtable_lock); + + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo) { + fixup_perms(sbinfo->sb); + } + } + mutex_unlock(&sdcardfs_super_list_lock); + return ret; +} + +static void remove_str_to_int_lock(struct hashtable_entry *h_entry) { + kfree(h_entry->key); + hash_del(&h_entry->hlist); + kmem_cache_free(hashtable_entry_cachep, h_entry); +} + +static void remove_str_to_int(struct packagelist_data *pkgl_dat, const char *key) +{ + struct sdcardfs_sb_info *sbinfo; + struct hashtable_entry *hash_cur; + unsigned int hash = str_hash(key); + mutex_lock(&sdcardfs_super_list_lock); + mutex_lock(&pkgl_dat->hashtable_lock); + hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { + if (!strcasecmp(key, hash_cur->key)) { + remove_str_to_int_lock(hash_cur); + break; + } + } + mutex_unlock(&pkgl_dat->hashtable_lock); + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo) { + fixup_perms(sbinfo->sb); + } + } + mutex_unlock(&sdcardfs_super_list_lock); + return; +} + +static void remove_all_hashentrys(struct packagelist_data *pkgl_dat) +{ + struct hashtable_entry *hash_cur; + struct hlist_node *h_t; + int i; + mutex_lock(&pkgl_dat->hashtable_lock); + hash_for_each_safe(pkgl_dat->package_to_appid, i, h_t, hash_cur, hlist) + remove_str_to_int_lock(hash_cur); + mutex_unlock(&pkgl_dat->hashtable_lock); + hash_init(pkgl_dat->package_to_appid); +} + +static struct packagelist_data * packagelist_create(void) +{ + struct packagelist_data *pkgl_dat; + + pkgl_dat = kmalloc(sizeof(*pkgl_dat), GFP_KERNEL | __GFP_ZERO); + if (!pkgl_dat) { + printk(KERN_ERR "sdcardfs: Failed to create hash\n"); + return ERR_PTR(-ENOMEM); + } + + mutex_init(&pkgl_dat->hashtable_lock); + hash_init(pkgl_dat->package_to_appid); + + return pkgl_dat; +} + +static void packagelist_destroy(struct packagelist_data *pkgl_dat) +{ + remove_all_hashentrys(pkgl_dat); + printk(KERN_INFO "sdcardfs: destroyed packagelist pkgld\n"); + kfree(pkgl_dat); +} + +struct package_appid { + struct config_item item; + int add_pid; +}; + +static inline struct package_appid *to_package_appid(struct config_item *item) +{ + return item ? container_of(item, struct package_appid, item) : NULL; +} + +static ssize_t package_appid_attr_show(struct config_item *item, + char *page) +{ + ssize_t count; + count = sprintf(page, "%d\n", get_appid(pkgl_data_all, item->ci_name)); + return count; +} + +static ssize_t package_appid_attr_store(struct config_item *item, + const char *page, size_t count) +{ + struct package_appid *package_appid = to_package_appid(item); + unsigned long tmp; + char *p = (char *) page; + int ret; + + tmp = simple_strtoul(p, &p, 10); + if (!p || (*p && (*p != '\n'))) + return -EINVAL; + + if (tmp > INT_MAX) + return -ERANGE; + ret = insert_str_to_int(pkgl_data_all, item->ci_name, (unsigned int)tmp); + package_appid->add_pid = tmp; + if (ret) + return ret; + + return count; +} + +static struct configfs_attribute package_appid_attr_add_pid = { + .ca_owner = THIS_MODULE, + .ca_name = "appid", + .ca_mode = S_IRUGO | S_IWUGO, + .show = package_appid_attr_show, + .store = package_appid_attr_store, +}; + +static struct configfs_attribute *package_appid_attrs[] = { + &package_appid_attr_add_pid, + NULL, +}; + +static void package_appid_release(struct config_item *item) +{ + printk(KERN_INFO "sdcardfs: removing %s\n", item->ci_dentry->d_name.name); + /* item->ci_name is freed already, so we rely on the dentry */ + remove_str_to_int(pkgl_data_all, item->ci_dentry->d_name.name); + kfree(to_package_appid(item)); +} + +static struct configfs_item_operations package_appid_item_ops = { + .release = package_appid_release, +}; + +static struct config_item_type package_appid_type = { + .ct_item_ops = &package_appid_item_ops, + .ct_attrs = package_appid_attrs, + .ct_owner = THIS_MODULE, +}; + + +struct sdcardfs_packages { + struct config_group group; +}; + +static inline struct sdcardfs_packages *to_sdcardfs_packages(struct config_item *item) +{ + return item ? container_of(to_config_group(item), struct sdcardfs_packages, group) : NULL; +} + +static struct config_item *sdcardfs_packages_make_item(struct config_group *group, const char *name) +{ + struct package_appid *package_appid; + + package_appid = kzalloc(sizeof(struct package_appid), GFP_KERNEL); + if (!package_appid) + return ERR_PTR(-ENOMEM); + + config_item_init_type_name(&package_appid->item, name, + &package_appid_type); + + package_appid->add_pid = 0; + + return &package_appid->item; +} + +static ssize_t packages_attr_show(struct config_item *item, + char *page) +{ + struct hashtable_entry *hash_cur; + struct hlist_node *h_t; + int i; + int count = 0; + mutex_lock(&pkgl_data_all->hashtable_lock); + hash_for_each_safe(pkgl_data_all->package_to_appid, i, h_t, hash_cur, hlist) + count += snprintf(page + count, PAGE_SIZE - count, "%s %d\n", (char *)hash_cur->key, hash_cur->value); + mutex_unlock(&pkgl_data_all->hashtable_lock); + + + return count; +} + +static struct configfs_attribute sdcardfs_packages_attr_description = { + .ca_owner = THIS_MODULE, + .ca_name = "packages_gid.list", + .ca_mode = S_IRUGO, + .show = packages_attr_show, +}; + +static struct configfs_attribute *sdcardfs_packages_attrs[] = { + &sdcardfs_packages_attr_description, + NULL, +}; + +static void sdcardfs_packages_release(struct config_item *item) +{ + + printk(KERN_INFO "sdcardfs: destroyed something?\n"); + kfree(to_sdcardfs_packages(item)); +} + +static struct configfs_item_operations sdcardfs_packages_item_ops = { + .release = sdcardfs_packages_release, +}; + +/* + * Note that, since no extra work is required on ->drop_item(), + * no ->drop_item() is provided. + */ +static struct configfs_group_operations sdcardfs_packages_group_ops = { + .make_item = sdcardfs_packages_make_item, +}; + +static struct config_item_type sdcardfs_packages_type = { + .ct_item_ops = &sdcardfs_packages_item_ops, + .ct_group_ops = &sdcardfs_packages_group_ops, + .ct_attrs = sdcardfs_packages_attrs, + .ct_owner = THIS_MODULE, +}; + +static struct configfs_subsystem sdcardfs_packages_subsys = { + .su_group = { + .cg_item = { + .ci_namebuf = "sdcardfs", + .ci_type = &sdcardfs_packages_type, + }, + }, +}; + +static int configfs_sdcardfs_init(void) +{ + int ret; + struct configfs_subsystem *subsys = &sdcardfs_packages_subsys; + + config_group_init(&subsys->su_group); + mutex_init(&subsys->su_mutex); + ret = configfs_register_subsystem(subsys); + if (ret) { + printk(KERN_ERR "Error %d while registering subsystem %s\n", + ret, + subsys->su_group.cg_item.ci_namebuf); + } + return ret; +} + +static void configfs_sdcardfs_exit(void) +{ + configfs_unregister_subsystem(&sdcardfs_packages_subsys); +} + +int packagelist_init(void) +{ + hashtable_entry_cachep = + kmem_cache_create("packagelist_hashtable_entry", + sizeof(struct hashtable_entry), 0, 0, NULL); + if (!hashtable_entry_cachep) { + printk(KERN_ERR "sdcardfs: failed creating pkgl_hashtable entry slab cache\n"); + return -ENOMEM; + } + + pkgl_data_all = packagelist_create(); + configfs_sdcardfs_init(); + return 0; +} + +void packagelist_exit(void) +{ + configfs_sdcardfs_exit(); + packagelist_destroy(pkgl_data_all); + if (hashtable_entry_cachep) + kmem_cache_destroy(hashtable_entry_cachep); +} diff --git a/fs/sdcardfs/sdcardfs.h b/fs/sdcardfs/sdcardfs.h new file mode 100644 index 000000000000..f111f898b630 --- /dev/null +++ b/fs/sdcardfs/sdcardfs.h @@ -0,0 +1,530 @@ +/* + * fs/sdcardfs/sdcardfs.h + * + * The sdcardfs v2.0 + * This file system replaces the sdcard daemon on Android + * On version 2.0, some of the daemon functions have been ported + * to support the multi-user concepts of Android 4.4 + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#ifndef _SDCARDFS_H_ +#define _SDCARDFS_H_ + +#include <linux/dcache.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/seq_file.h> +#include <linux/statfs.h> +#include <linux/fs_stack.h> +#include <linux/magic.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <linux/security.h> +#include <linux/string.h> +#include <linux/list.h> +#include "multiuser.h" + +/* the file system name */ +#define SDCARDFS_NAME "sdcardfs" + +/* sdcardfs root inode number */ +#define SDCARDFS_ROOT_INO 1 + +/* useful for tracking code reachability */ +#define UDBG printk(KERN_DEFAULT "DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__) + +#define SDCARDFS_DIRENT_SIZE 256 + +/* temporary static uid settings for development */ +#define AID_ROOT 0 /* uid for accessing /mnt/sdcard & extSdcard */ +#define AID_MEDIA_RW 1023 /* internal media storage write access */ + +#define AID_SDCARD_RW 1015 /* external storage write access */ +#define AID_SDCARD_R 1028 /* external storage read access */ +#define AID_SDCARD_PICS 1033 /* external storage photos access */ +#define AID_SDCARD_AV 1034 /* external storage audio/video access */ +#define AID_SDCARD_ALL 1035 /* access all users external storage */ + +#define AID_PACKAGE_INFO 1027 + +#define fix_derived_permission(x) \ + do { \ + (x)->i_uid = make_kuid(&init_user_ns, SDCARDFS_I(x)->d_uid); \ + (x)->i_gid = make_kgid(&init_user_ns, get_gid(SDCARDFS_I(x))); \ + (x)->i_mode = ((x)->i_mode & S_IFMT) | get_mode(SDCARDFS_I(x));\ + } while (0) + + +/* OVERRIDE_CRED() and REVERT_CRED() + * OVERRID_CRED() + * backup original task->cred + * and modifies task->cred->fsuid/fsgid to specified value. + * REVERT_CRED() + * restore original task->cred->fsuid/fsgid. + * These two macro should be used in pair, and OVERRIDE_CRED() should be + * placed at the beginning of a function, right after variable declaration. + */ +#define OVERRIDE_CRED(sdcardfs_sbi, saved_cred) \ + saved_cred = override_fsids(sdcardfs_sbi); \ + if (!saved_cred) { return -ENOMEM; } + +#define OVERRIDE_CRED_PTR(sdcardfs_sbi, saved_cred) \ + saved_cred = override_fsids(sdcardfs_sbi); \ + if (!saved_cred) { return ERR_PTR(-ENOMEM); } + +#define REVERT_CRED(saved_cred) revert_fsids(saved_cred) + +#define DEBUG_CRED() \ + printk("KAKJAGI: %s:%d fsuid %d fsgid %d\n", \ + __FUNCTION__, __LINE__, \ + (int)current->cred->fsuid, \ + (int)current->cred->fsgid); + +/* Android 5.0 support */ + +/* Permission mode for a specific node. Controls how file permissions + * are derived for children nodes. */ +typedef enum { + /* Nothing special; this node should just inherit from its parent. */ + PERM_INHERIT, + /* This node is one level above a normal root; used for legacy layouts + * which use the first level to represent user_id. */ + PERM_PRE_ROOT, + /* This node is "/" */ + PERM_ROOT, + /* This node is "/Android" */ + PERM_ANDROID, + /* This node is "/Android/data" */ + PERM_ANDROID_DATA, + /* This node is "/Android/obb" */ + PERM_ANDROID_OBB, + /* This node is "/Android/media" */ + PERM_ANDROID_MEDIA, +} perm_t; + +struct sdcardfs_sb_info; +struct sdcardfs_mount_options; + +/* Do not directly use this function. Use OVERRIDE_CRED() instead. */ +const struct cred * override_fsids(struct sdcardfs_sb_info* sbi); +/* Do not directly use this function, use REVERT_CRED() instead. */ +void revert_fsids(const struct cred * old_cred); + +/* operations vectors defined in specific files */ +extern const struct file_operations sdcardfs_main_fops; +extern const struct file_operations sdcardfs_dir_fops; +extern const struct inode_operations sdcardfs_main_iops; +extern const struct inode_operations sdcardfs_dir_iops; +extern const struct inode_operations sdcardfs_symlink_iops; +extern const struct super_operations sdcardfs_sops; +extern const struct dentry_operations sdcardfs_ci_dops; +extern const struct address_space_operations sdcardfs_aops, sdcardfs_dummy_aops; +extern const struct vm_operations_struct sdcardfs_vm_ops; + +extern int sdcardfs_init_inode_cache(void); +extern void sdcardfs_destroy_inode_cache(void); +extern int sdcardfs_init_dentry_cache(void); +extern void sdcardfs_destroy_dentry_cache(void); +extern int new_dentry_private_data(struct dentry *dentry); +extern void free_dentry_private_data(struct dentry *dentry); +extern struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags); +extern struct inode *sdcardfs_iget(struct super_block *sb, + struct inode *lower_inode, userid_t id); +extern int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, + struct path *lower_path, userid_t id); + +/* file private data */ +struct sdcardfs_file_info { + struct file *lower_file; + const struct vm_operations_struct *lower_vm_ops; +}; + +/* sdcardfs inode data in memory */ +struct sdcardfs_inode_info { + struct inode *lower_inode; + /* state derived based on current position in hierachy */ + perm_t perm; + userid_t userid; + uid_t d_uid; + bool under_android; + + struct inode vfs_inode; +}; + + +/* sdcardfs dentry data in memory */ +struct sdcardfs_dentry_info { + spinlock_t lock; /* protects lower_path */ + struct path lower_path; + struct path orig_path; +}; + +struct sdcardfs_mount_options { + uid_t fs_low_uid; + gid_t fs_low_gid; + userid_t fs_user_id; + gid_t gid; + mode_t mask; + bool multiuser; + unsigned int reserved_mb; +}; + +/* sdcardfs super-block data in memory */ +struct sdcardfs_sb_info { + struct super_block *sb; + struct super_block *lower_sb; + /* derived perm policy : some of options have been added + * to sdcardfs_mount_options (Android 4.4 support) */ + struct sdcardfs_mount_options options; + spinlock_t lock; /* protects obbpath */ + char *obbpath_s; + struct path obbpath; + void *pkgl_id; + struct list_head list; +}; + +/* + * inode to private data + * + * Since we use containers and the struct inode is _inside_ the + * sdcardfs_inode_info structure, SDCARDFS_I will always (given a non-NULL + * inode pointer), return a valid non-NULL pointer. + */ +static inline struct sdcardfs_inode_info *SDCARDFS_I(const struct inode *inode) +{ + return container_of(inode, struct sdcardfs_inode_info, vfs_inode); +} + +/* dentry to private data */ +#define SDCARDFS_D(dent) ((struct sdcardfs_dentry_info *)(dent)->d_fsdata) + +/* superblock to private data */ +#define SDCARDFS_SB(super) ((struct sdcardfs_sb_info *)(super)->s_fs_info) + +/* file to private Data */ +#define SDCARDFS_F(file) ((struct sdcardfs_file_info *)((file)->private_data)) + +/* file to lower file */ +static inline struct file *sdcardfs_lower_file(const struct file *f) +{ + return SDCARDFS_F(f)->lower_file; +} + +static inline void sdcardfs_set_lower_file(struct file *f, struct file *val) +{ + SDCARDFS_F(f)->lower_file = val; +} + +/* inode to lower inode. */ +static inline struct inode *sdcardfs_lower_inode(const struct inode *i) +{ + return SDCARDFS_I(i)->lower_inode; +} + +static inline void sdcardfs_set_lower_inode(struct inode *i, struct inode *val) +{ + SDCARDFS_I(i)->lower_inode = val; +} + +/* superblock to lower superblock */ +static inline struct super_block *sdcardfs_lower_super( + const struct super_block *sb) +{ + return SDCARDFS_SB(sb)->lower_sb; +} + +static inline void sdcardfs_set_lower_super(struct super_block *sb, + struct super_block *val) +{ + SDCARDFS_SB(sb)->lower_sb = val; +} + +/* path based (dentry/mnt) macros */ +static inline void pathcpy(struct path *dst, const struct path *src) +{ + dst->dentry = src->dentry; + dst->mnt = src->mnt; +} + +/* sdcardfs_get_pname functions calls path_get() + * therefore, the caller must call "proper" path_put functions + */ +#define SDCARDFS_DENT_FUNC(pname) \ +static inline void sdcardfs_get_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + pathcpy(pname, &SDCARDFS_D(dent)->pname); \ + path_get(pname); \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_put_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + path_put(pname); \ + return; \ +} \ +static inline void sdcardfs_set_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + pathcpy(&SDCARDFS_D(dent)->pname, pname); \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_reset_##pname(const struct dentry *dent) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + SDCARDFS_D(dent)->pname.dentry = NULL; \ + SDCARDFS_D(dent)->pname.mnt = NULL; \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_put_reset_##pname(const struct dentry *dent) \ +{ \ + struct path pname; \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + if(SDCARDFS_D(dent)->pname.dentry) { \ + pathcpy(&pname, &SDCARDFS_D(dent)->pname); \ + SDCARDFS_D(dent)->pname.dentry = NULL; \ + SDCARDFS_D(dent)->pname.mnt = NULL; \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + path_put(&pname); \ + } else \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} + +SDCARDFS_DENT_FUNC(lower_path) +SDCARDFS_DENT_FUNC(orig_path) + +static inline int get_gid(struct sdcardfs_inode_info *info) { + struct sdcardfs_sb_info *sb_info = SDCARDFS_SB(info->vfs_inode.i_sb); + if (sb_info->options.gid == AID_SDCARD_RW) { + /* As an optimization, certain trusted system components only run + * as owner but operate across all users. Since we're now handing + * out the sdcard_rw GID only to trusted apps, we're okay relaxing + * the user boundary enforcement for the default view. The UIDs + * assigned to app directories are still multiuser aware. */ + return AID_SDCARD_RW; + } else { + return multiuser_get_uid(info->userid, sb_info->options.gid); + } +} +static inline int get_mode(struct sdcardfs_inode_info *info) { + int owner_mode; + int filtered_mode; + struct sdcardfs_sb_info *sb_info = SDCARDFS_SB(info->vfs_inode.i_sb); + int visible_mode = 0775 & ~sb_info->options.mask; + + if (info->perm == PERM_PRE_ROOT) { + /* Top of multi-user view should always be visible to ensure + * secondary users can traverse inside. */ + visible_mode = 0711; + } else if (info->under_android) { + /* Block "other" access to Android directories, since only apps + * belonging to a specific user should be in there; we still + * leave +x open for the default view. */ + if (sb_info->options.gid == AID_SDCARD_RW) { + visible_mode = visible_mode & ~0006; + } else { + visible_mode = visible_mode & ~0007; + } + } + owner_mode = info->lower_inode->i_mode & 0700; + filtered_mode = visible_mode & (owner_mode | (owner_mode >> 3) | (owner_mode >> 6)); + return filtered_mode; +} + +static inline int has_graft_path(const struct dentry *dent) +{ + int ret = 0; + + spin_lock(&SDCARDFS_D(dent)->lock); + if (SDCARDFS_D(dent)->orig_path.dentry != NULL) + ret = 1; + spin_unlock(&SDCARDFS_D(dent)->lock); + + return ret; +} + +static inline void sdcardfs_get_real_lower(const struct dentry *dent, + struct path *real_lower) +{ + /* in case of a local obb dentry + * the orig_path should be returned + */ + if(has_graft_path(dent)) + sdcardfs_get_orig_path(dent, real_lower); + else + sdcardfs_get_lower_path(dent, real_lower); +} + +static inline void sdcardfs_put_real_lower(const struct dentry *dent, + struct path *real_lower) +{ + if(has_graft_path(dent)) + sdcardfs_put_orig_path(dent, real_lower); + else + sdcardfs_put_lower_path(dent, real_lower); +} + +extern struct mutex sdcardfs_super_list_lock; +extern struct list_head sdcardfs_super_list; + +/* for packagelist.c */ +extern appid_t get_appid(void *pkgl_id, const char *app_name); +extern int check_caller_access_to_name(struct inode *parent_node, const char* name); +extern int open_flags_to_access_mode(int open_flags); +extern int packagelist_init(void); +extern void packagelist_exit(void); + +/* for derived_perm.c */ +extern void setup_derived_state(struct inode *inode, perm_t perm, + userid_t userid, uid_t uid, bool under_android); +extern void get_derived_permission(struct dentry *parent, struct dentry *dentry); +extern void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, struct dentry *newdentry); +extern void get_derive_permissions_recursive(struct dentry *parent); + +extern void update_derived_permission_lock(struct dentry *dentry); +extern int need_graft_path(struct dentry *dentry); +extern int is_base_obbpath(struct dentry *dentry); +extern int is_obbpath_invalid(struct dentry *dentry); +extern int setup_obb_dentry(struct dentry *dentry, struct path *lower_path); + +/* locking helpers */ +static inline struct dentry *lock_parent(struct dentry *dentry) +{ + struct dentry *dir = dget_parent(dentry); + mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT); + return dir; +} + +static inline void unlock_dir(struct dentry *dir) +{ + mutex_unlock(&d_inode(dir)->i_mutex); + dput(dir); +} + +static inline int prepare_dir(const char *path_s, uid_t uid, gid_t gid, mode_t mode) +{ + int err; + struct dentry *dent; + struct iattr attrs; + struct path parent; + + dent = kern_path_locked(path_s, &parent); + if (IS_ERR(dent)) { + err = PTR_ERR(dent); + if (err == -EEXIST) + err = 0; + goto out_unlock; + } + + err = vfs_mkdir(d_inode(parent.dentry), dent, mode); + if (err) { + if (err == -EEXIST) + err = 0; + goto out_dput; + } + + attrs.ia_uid = make_kuid(&init_user_ns, uid); + attrs.ia_gid = make_kgid(&init_user_ns, gid); + attrs.ia_valid = ATTR_UID | ATTR_GID; + mutex_lock(&d_inode(dent)->i_mutex); + notify_change(dent, &attrs, NULL); + mutex_unlock(&d_inode(dent)->i_mutex); + +out_dput: + dput(dent); + +out_unlock: + /* parent dentry locked by lookup_create */ + mutex_unlock(&d_inode(parent.dentry)->i_mutex); + path_put(&parent); + return err; +} + +/* + * Return 1, if a disk has enough free space, otherwise 0. + * We assume that any files can not be overwritten. + */ +static inline int check_min_free_space(struct dentry *dentry, size_t size, int dir) +{ + int err; + struct path lower_path; + struct kstatfs statfs; + u64 avail; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + if (sbi->options.reserved_mb) { + /* Get fs stat of lower filesystem. */ + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_statfs(&lower_path, &statfs); + sdcardfs_put_lower_path(dentry, &lower_path); + + if (unlikely(err)) + return 0; + + /* Invalid statfs informations. */ + if (unlikely(statfs.f_bsize == 0)) + return 0; + + /* if you are checking directory, set size to f_bsize. */ + if (unlikely(dir)) + size = statfs.f_bsize; + + /* available size */ + avail = statfs.f_bavail * statfs.f_bsize; + + /* not enough space */ + if ((u64)size > avail) + return 0; + + /* enough space */ + if ((avail - size) > (sbi->options.reserved_mb * 1024 * 1024)) + return 1; + + return 0; + } else + return 1; +} + +/* Copies attrs and maintains sdcardfs managed attrs */ +static inline void sdcardfs_copy_and_fix_attrs(struct inode *dest, const struct inode *src) +{ + dest->i_mode = (src->i_mode & S_IFMT) | get_mode(SDCARDFS_I(dest)); + dest->i_uid = make_kuid(&init_user_ns, SDCARDFS_I(dest)->d_uid); + dest->i_gid = make_kgid(&init_user_ns, get_gid(SDCARDFS_I(dest))); + dest->i_rdev = src->i_rdev; + dest->i_atime = src->i_atime; + dest->i_mtime = src->i_mtime; + dest->i_ctime = src->i_ctime; + dest->i_blkbits = src->i_blkbits; + dest->i_flags = src->i_flags; + set_nlink(dest, src->i_nlink); +} +#endif /* not _SDCARDFS_H_ */ diff --git a/fs/sdcardfs/super.c b/fs/sdcardfs/super.c new file mode 100644 index 000000000000..1d6490128c99 --- /dev/null +++ b/fs/sdcardfs/super.c @@ -0,0 +1,222 @@ +/* + * fs/sdcardfs/super.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +/* + * The inode cache is used with alloc_inode for both our inode info and the + * vfs inode. + */ +static struct kmem_cache *sdcardfs_inode_cachep; + +/* final actions when unmounting a file system */ +static void sdcardfs_put_super(struct super_block *sb) +{ + struct sdcardfs_sb_info *spd; + struct super_block *s; + + spd = SDCARDFS_SB(sb); + if (!spd) + return; + + if(spd->obbpath_s) { + kfree(spd->obbpath_s); + path_put(&spd->obbpath); + } + + /* decrement lower super references */ + s = sdcardfs_lower_super(sb); + sdcardfs_set_lower_super(sb, NULL); + atomic_dec(&s->s_active); + + kfree(spd); + sb->s_fs_info = NULL; +} + +static int sdcardfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + int err; + struct path lower_path; + u32 min_blocks; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_statfs(&lower_path, buf); + sdcardfs_put_lower_path(dentry, &lower_path); + + if (sbi->options.reserved_mb) { + /* Invalid statfs informations. */ + if (buf->f_bsize == 0) { + printk(KERN_ERR "Returned block size is zero.\n"); + return -EINVAL; + } + + min_blocks = ((sbi->options.reserved_mb * 1024 * 1024)/buf->f_bsize); + buf->f_blocks -= min_blocks; + + if (buf->f_bavail > min_blocks) + buf->f_bavail -= min_blocks; + else + buf->f_bavail = 0; + + /* Make reserved blocks invisiable to media storage */ + buf->f_bfree = buf->f_bavail; + } + + /* set return buf to our f/s to avoid confusing user-level utils */ + buf->f_type = SDCARDFS_SUPER_MAGIC; + + return err; +} + +/* + * @flags: numeric mount options + * @options: mount options string + */ +static int sdcardfs_remount_fs(struct super_block *sb, int *flags, char *options) +{ + int err = 0; + + /* + * The VFS will take care of "ro" and "rw" flags among others. We + * can safely accept a few flags (RDONLY, MANDLOCK), and honor + * SILENT, but anything else left over is an error. + */ + if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT)) != 0) { + printk(KERN_ERR + "sdcardfs: remount flags 0x%x unsupported\n", *flags); + err = -EINVAL; + } + + return err; +} + +/* + * Called by iput() when the inode reference count reached zero + * and the inode is not hashed anywhere. Used to clear anything + * that needs to be, before the inode is completely destroyed and put + * on the inode free list. + */ +static void sdcardfs_evict_inode(struct inode *inode) +{ + struct inode *lower_inode; + + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); + /* + * Decrement a reference to a lower_inode, which was incremented + * by our read_inode when it was created initially. + */ + lower_inode = sdcardfs_lower_inode(inode); + sdcardfs_set_lower_inode(inode, NULL); + iput(lower_inode); +} + +static struct inode *sdcardfs_alloc_inode(struct super_block *sb) +{ + struct sdcardfs_inode_info *i; + + i = kmem_cache_alloc(sdcardfs_inode_cachep, GFP_KERNEL); + if (!i) + return NULL; + + /* memset everything up to the inode to 0 */ + memset(i, 0, offsetof(struct sdcardfs_inode_info, vfs_inode)); + + i->vfs_inode.i_version = 1; + return &i->vfs_inode; +} + +static void sdcardfs_destroy_inode(struct inode *inode) +{ + kmem_cache_free(sdcardfs_inode_cachep, SDCARDFS_I(inode)); +} + +/* sdcardfs inode cache constructor */ +static void init_once(void *obj) +{ + struct sdcardfs_inode_info *i = obj; + + inode_init_once(&i->vfs_inode); +} + +int sdcardfs_init_inode_cache(void) +{ + int err = 0; + + sdcardfs_inode_cachep = + kmem_cache_create("sdcardfs_inode_cache", + sizeof(struct sdcardfs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT, init_once); + if (!sdcardfs_inode_cachep) + err = -ENOMEM; + return err; +} + +/* sdcardfs inode cache destructor */ +void sdcardfs_destroy_inode_cache(void) +{ + if (sdcardfs_inode_cachep) + kmem_cache_destroy(sdcardfs_inode_cachep); +} + +/* + * Used only in nfs, to kill any pending RPC tasks, so that subsequent + * code can actually succeed and won't leave tasks that need handling. + */ +static void sdcardfs_umount_begin(struct super_block *sb) +{ + struct super_block *lower_sb; + + lower_sb = sdcardfs_lower_super(sb); + if (lower_sb && lower_sb->s_op && lower_sb->s_op->umount_begin) + lower_sb->s_op->umount_begin(lower_sb); +} + +static int sdcardfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(root->d_sb); + struct sdcardfs_mount_options *opts = &sbi->options; + + if (opts->fs_low_uid != 0) + seq_printf(m, ",uid=%u", opts->fs_low_uid); + if (opts->fs_low_gid != 0) + seq_printf(m, ",gid=%u", opts->fs_low_gid); + + if (opts->multiuser) + seq_printf(m, ",multiuser"); + + if (opts->reserved_mb != 0) + seq_printf(m, ",reserved=%uMB", opts->reserved_mb); + + return 0; +}; + +const struct super_operations sdcardfs_sops = { + .put_super = sdcardfs_put_super, + .statfs = sdcardfs_statfs, + .remount_fs = sdcardfs_remount_fs, + .evict_inode = sdcardfs_evict_inode, + .umount_begin = sdcardfs_umount_begin, + .show_options = sdcardfs_show_options, + .alloc_inode = sdcardfs_alloc_inode, + .destroy_inode = sdcardfs_destroy_inode, + .drop_inode = generic_delete_inode, +}; diff --git a/fs/splice.c b/fs/splice.c index 4cf700d50b40..0f77e9682857 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -185,6 +185,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, unsigned int spd_pages = spd->nr_pages; int ret, do_wakeup, page_nr; + if (!spd_pages) + return 0; + ret = 0; do_wakeup = 0; page_nr = 0; diff --git a/fs/super.c b/fs/super.c index 1014e7cc355f..8d99a7b948ff 100644 --- a/fs/super.c +++ b/fs/super.c @@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb) sb->s_flags &= ~MS_ACTIVE; fsnotify_unmount_inodes(sb); + cgroup_writeback_umount(); evict_inodes(sb); diff --git a/fs/timerfd.c b/fs/timerfd.c index b94fa6c3c6eb..053818dd6c18 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) if (isalarm(ctx)) remaining = alarm_expires_remaining(&ctx->t.alarm); else - remaining = hrtimer_expires_remaining(&ctx->t.tmr); + remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8d0b3ade0ff0..566df9b5a6cb 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -2047,14 +2047,29 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, epos->offset += adsize; } +/* + * Only 1 indirect extent in a row really makes sense but allow upto 16 in case + * someone does some weird stuff. + */ +#define UDF_MAX_INDIR_EXTS 16 + int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t *elen, int inc) { int8_t etype; + unsigned int indirections = 0; while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) == (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) { int block; + + if (++indirections > UDF_MAX_INDIR_EXTS) { + udf_err(inode->i_sb, + "too many indirect extents in inode %lu\n", + inode->i_ino); + return -1; + } + epos->block = *eloc; epos->offset = sizeof(struct allocExtDesc); brelse(epos->bh); diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index ab478e62baae..e788a05aab83 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -128,11 +128,15 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) if (c < 0x80U) utf_o->u_name[utf_o->u_len++] = (uint8_t)c; else if (c < 0x800U) { + if (utf_o->u_len > (UDF_NAME_LEN - 4)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xc0 | (c >> 6)); utf_o->u_name[utf_o->u_len++] = (uint8_t)(0x80 | (c & 0x3f)); } else { + if (utf_o->u_len > (UDF_NAME_LEN - 5)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xe0 | (c >> 12)); utf_o->u_name[utf_o->u_len++] = @@ -173,17 +177,22 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length) { unsigned c, i, max_val, utf_char; - int utf_cnt, u_len; + int utf_cnt, u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; utf_char = 0U; utf_cnt = 0U; for (i = 0U; i < utf->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; + c = (uint8_t)utf->u_name[i]; /* Complete a multi-byte UTF-8 character */ @@ -225,6 +234,7 @@ try_again: if (max_val == 0xffU) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } goto error_out; @@ -277,7 +287,7 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o, c = (c << 8) | ocu[i++]; len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len], - UDF_NAME_LEN - utf_o->u_len); + UDF_NAME_LEN - 2 - utf_o->u_len); /* Valid character? */ if (len >= 0) utf_o->u_len += len; @@ -295,15 +305,19 @@ static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni, int len; unsigned i, max_val; uint16_t uni_char; - int u_len; + int u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; for (i = 0U; i < uni->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char); if (!len) continue; @@ -316,6 +330,7 @@ try_again: if (uni_char > max_val) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 68a62457e685..d473e6e07a7e 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -287,6 +287,12 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address, goto out; /* + * We don't do userfault handling for the final child pid update. + */ + if (current->flags & PF_EXITING) + goto out; + + /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 8774498ce0ff..e2536bb1c760 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -786,7 +786,7 @@ typedef struct xfs_agfl { __be64 agfl_lsn; __be32 agfl_crc; __be32 agfl_bno[]; /* actually XFS_AGFL_SIZE(mp) */ -} xfs_agfl_t; +} __attribute__((packed)) xfs_agfl_t; #define XFS_AGFL_CRC_OFF offsetof(struct xfs_agfl, agfl_crc) diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 268c00f4f83a..65485cfc4ade 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -62,11 +62,12 @@ xfs_inobp_check( * has not had the inode cores stamped into it. Hence for readahead, the buffer * may be potentially invalid. * - * If the readahead buffer is invalid, we don't want to mark it with an error, - * but we do want to clear the DONE status of the buffer so that a followup read - * will re-read it from disk. This will ensure that we don't get an unnecessary - * warnings during log recovery and we don't get unnecssary panics on debug - * kernels. + * If the readahead buffer is invalid, we need to mark it with an error and + * clear the DONE status of the buffer so that a followup read will re-read it + * from disk. We don't report the error otherwise to avoid warnings during log + * recovery and we don't get unnecssary panics on debug kernels. We use EIO here + * because all we want to do is say readahead failed; there is no-one to report + * the error to, so this will distinguish it from a non-ra verifier failure. */ static void xfs_inode_buf_verify( @@ -93,6 +94,7 @@ xfs_inode_buf_verify( XFS_RANDOM_ITOBP_INOTOBP))) { if (readahead) { bp->b_flags &= ~XBF_DONE; + xfs_buf_ioerror(bp, -EIO); return; } diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 0ef7c2ed3f8a..4fa14820e2e2 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -202,8 +202,10 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context) sbp->namelen, sbp->valuelen, &sbp->name[sbp->namelen]); - if (error) + if (error) { + kmem_free(sbuf); return error; + } if (context->seen_enough) break; cursor->offset++; @@ -454,14 +456,13 @@ xfs_attr3_leaf_list_int( args.rmtblkcnt = xfs_attr3_rmt_blocks( args.dp->i_mount, valuelen); retval = xfs_attr_rmtval_get(&args); - if (retval) - return retval; - retval = context->put_listent(context, - entry->flags, - name_rmt->name, - (int)name_rmt->namelen, - valuelen, - args.value); + if (!retval) + retval = context->put_listent(context, + entry->flags, + name_rmt->name, + (int)name_rmt->namelen, + valuelen, + args.value); kmem_free(args.value); } else { retval = context->put_listent(context, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 3243cdf97f33..39090fc56f09 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -604,6 +604,13 @@ found: } } + /* + * Clear b_error if this is a lookup from a caller that doesn't expect + * valid data to be found in the buffer. + */ + if (!(flags & XBF_READ)) + xfs_buf_ioerror(bp, 0); + XFS_STATS_INC(target->bt_mount, xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); return bp; @@ -1520,6 +1527,16 @@ xfs_wait_buftarg( LIST_HEAD(dispose); int loop = 0; + /* + * We need to flush the buffer workqueue to ensure that all IO + * completion processing is 100% done. Just waiting on buffer locks is + * not sufficient for async IO as the reference count held over IO is + * not released until after the buffer lock is dropped. Hence we need to + * ensure here that all reference counts have been dropped before we + * start walking the LRU list. + */ + drain_workqueue(btp->bt_mount->m_buf_workqueue); + /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index aa67339b9537..4f18fd92ca13 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -497,7 +497,6 @@ xfsaild( long tout = 0; /* milliseconds */ current->flags |= PF_MEMALLOC; - set_freezable(); while (!kthread_should_stop()) { if (tout && tout <= 20) diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index c30266e94806..8ef0ccbf8167 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -29,16 +29,16 @@ do { \ * @nr: the bit to set * @addr: the address to start counting from * - * This operation is like clear_bit_unlock, however it is not atomic. - * It does provide release barrier semantics so it can be used to unlock - * a bit lock, however it would only be used if no other CPU can modify - * any bits in the memory until the lock is released (a good example is - * if the bit lock itself protects access to the other bits in the word). + * A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all + * the bits in the word are protected by this lock some archs can use weaker + * ops to safely unlock. + * + * See for example x86's implementation. */ #define __clear_bit_unlock(nr, addr) \ do { \ - smp_mb(); \ - __clear_bit(nr, addr); \ + smp_mb__before_atomic(); \ + clear_bit(nr, addr); \ } while (0) #endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h index 0419485891f2..0f1c6f315cdc 100644 --- a/include/asm-generic/cputime_nsecs.h +++ b/include/asm-generic/cputime_nsecs.h @@ -75,7 +75,7 @@ typedef u64 __nocast cputime64_t; */ static inline cputime_t timespec_to_cputime(const struct timespec *val) { - u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec; + u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + val->tv_nsec; return (__force cputime_t) ret; } static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) @@ -91,7 +91,8 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) */ static inline cputime_t timeval_to_cputime(const struct timeval *val) { - u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC; + u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + + val->tv_usec * NSEC_PER_USEC; return (__force cputime_t) ret; } static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val) diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h index e56272c919b5..bf2d34c9d804 100644 --- a/include/asm-generic/futex.h +++ b/include/asm-generic/futex.h @@ -108,11 +108,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 val; preempt_disable(); - if (unlikely(get_user(val, uaddr) != 0)) + if (unlikely(get_user(val, uaddr) != 0)) { + preempt_enable(); return -EFAULT; + } - if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) + if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) { + preempt_enable(); return -EFAULT; + } *uval = val; preempt_enable(); diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 3d69c93d50e8..6361892ea737 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -204,6 +204,7 @@ struct crypto_ahash { unsigned int keylen); unsigned int reqsize; + bool has_setkey; struct crypto_tfm base; }; @@ -375,6 +376,11 @@ static inline void *ahash_request_ctx(struct ahash_request *req) int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); +static inline bool crypto_ahash_has_setkey(struct crypto_ahash *tfm) +{ + return tfm->has_setkey; +} + /** * crypto_ahash_finup() - update and finalize message digest * @req: reference to the ahash_request handle that holds all information diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 018afb264ac2..a2bfd7843f18 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -30,6 +30,9 @@ struct alg_sock { struct sock *parent; + unsigned int refcnt; + unsigned int nokey_refcnt; + const struct af_alg_type *type; void *private; }; @@ -50,9 +53,11 @@ struct af_alg_type { void (*release)(void *private); int (*setkey)(void *private, const u8 *key, unsigned int keylen); int (*accept)(void *private, struct sock *sk); + int (*accept_nokey)(void *private, struct sock *sk); int (*setauthsize)(void *private, unsigned int authsize); struct proto_ops *ops; + struct proto_ops *ops_nokey; struct module *owner; char name[14]; }; @@ -67,6 +72,7 @@ int af_alg_register_type(const struct af_alg_type *type); int af_alg_unregister_type(const struct af_alg_type *type); int af_alg_release(struct socket *sock); +void af_alg_release_parent(struct sock *sk); int af_alg_accept(struct sock *sk, struct socket *newsock); int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); @@ -83,11 +89,6 @@ static inline struct alg_sock *alg_sk(struct sock *sk) return (struct alg_sock *)sk; } -static inline void af_alg_release_parent(struct sock *sk) -{ - sock_put(alg_sk(sk)->parent); -} - static inline void af_alg_init_completion(struct af_alg_completion *completion) { init_completion(&completion->completion); diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index d8dd41fb034f..fd8742a40ff3 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -61,6 +61,8 @@ struct crypto_skcipher { unsigned int ivsize; unsigned int reqsize; + bool has_setkey; + struct crypto_tfm base; }; @@ -305,6 +307,11 @@ static inline int crypto_skcipher_setkey(struct crypto_skcipher *tfm, return tfm->setkey(tfm, key, keylen); } +static inline bool crypto_skcipher_has_setkey(struct crypto_skcipher *tfm) +{ + return tfm->has_setkey; +} + /** * crypto_skcipher_reqtfm() - obtain cipher handle from request * @req: skcipher_request out of which the cipher handle is to be obtained diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h index 7bfb063029d8..cebecff536a3 100644 --- a/include/drm/drm_cache.h +++ b/include/drm/drm_cache.h @@ -35,4 +35,15 @@ void drm_clflush_pages(struct page *pages[], unsigned long num_pages); +static inline bool drm_arch_can_wc_memory(void) +{ +#if defined(CONFIG_PPC) && !defined(CONFIG_NOT_COHERENT_CACHE) + return false; +#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3) + return false; +#else + return true; +#endif +} + #endif diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index 5340099741ae..f356f9716474 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -44,8 +44,6 @@ struct drm_dp_vcpi { /** * struct drm_dp_mst_port - MST port * @kref: reference count for this port. - * @guid_valid: for DP 1.2 devices if we have validated the GUID. - * @guid: guid for DP 1.2 device on this port. * @port_num: port number * @input: if this port is an input port. * @mcs: message capability status - DP 1.2 spec. @@ -70,10 +68,6 @@ struct drm_dp_vcpi { struct drm_dp_mst_port { struct kref kref; - /* if dpcd 1.2 device is on this port - its GUID info */ - bool guid_valid; - u8 guid[16]; - u8 port_num; bool input; bool mcs; @@ -109,10 +103,12 @@ struct drm_dp_mst_port { * @tx_slots: transmission slots for this device. * @last_seqno: last sequence number used to talk to this. * @link_address_sent: if a link address message has been sent to this device yet. + * @guid: guid for DP 1.2 branch device. port under this branch can be + * identified by port #. * * This structure represents an MST branch device, there is one - * primary branch device at the root, along with any others connected - * to downstream ports + * primary branch device at the root, along with any other branches connected + * to downstream port of parent branches. */ struct drm_dp_mst_branch { struct kref kref; @@ -131,6 +127,9 @@ struct drm_dp_mst_branch { struct drm_dp_sideband_msg_tx *tx_slots[2]; int last_seqno; bool link_address_sent; + + /* global unique identifier to identify branch devices */ + u8 guid[16]; }; @@ -405,11 +404,9 @@ struct drm_dp_payload { * @conn_base_id: DRM connector ID this mgr is connected to. * @down_rep_recv: msg receiver state for down replies. * @up_req_recv: msg receiver state for up requests. - * @lock: protects mst state, primary, guid, dpcd. + * @lock: protects mst state, primary, dpcd. * @mst_state: if this manager is enabled for an MST capable port. * @mst_primary: pointer to the primary branch device. - * @guid_valid: GUID valid for the primary branch device. - * @guid: GUID for primary port. * @dpcd: cache of DPCD for primary port. * @pbn_div: PBN to slots divisor. * @@ -431,13 +428,11 @@ struct drm_dp_mst_topology_mgr { struct drm_dp_sideband_msg_rx up_req_recv; /* pointer to info about the initial MST device */ - struct mutex lock; /* protects mst_state + primary + guid + dpcd */ + struct mutex lock; /* protects mst_state + primary + dpcd */ bool mst_state; struct drm_dp_mst_branch *mst_primary; - /* primary MST device GUID */ - bool guid_valid; - u8 guid[16]; + u8 dpcd[DP_RECEIVER_CAP_SIZE]; u8 sink_count; int pbn_div; @@ -450,9 +445,7 @@ struct drm_dp_mst_topology_mgr { the mstb tx_slots and txmsg->state once they are queued */ struct mutex qlock; struct list_head tx_msg_downq; - struct list_head tx_msg_upq; bool tx_down_in_progress; - bool tx_up_in_progress; /* payload info + lock for it */ struct mutex payload_lock; diff --git a/include/drm/drm_fixed.h b/include/drm/drm_fixed.h index d639049a613d..553210c02ee0 100644 --- a/include/drm/drm_fixed.h +++ b/include/drm/drm_fixed.h @@ -73,18 +73,28 @@ static inline u32 dfixed_div(fixed20_12 A, fixed20_12 B) #define DRM_FIXED_ONE (1ULL << DRM_FIXED_POINT) #define DRM_FIXED_DECIMAL_MASK (DRM_FIXED_ONE - 1) #define DRM_FIXED_DIGITS_MASK (~DRM_FIXED_DECIMAL_MASK) +#define DRM_FIXED_EPSILON 1LL +#define DRM_FIXED_ALMOST_ONE (DRM_FIXED_ONE - DRM_FIXED_EPSILON) static inline s64 drm_int2fixp(int a) { return ((s64)a) << DRM_FIXED_POINT; } -static inline int drm_fixp2int(int64_t a) +static inline int drm_fixp2int(s64 a) { return ((s64)a) >> DRM_FIXED_POINT; } -static inline unsigned drm_fixp_msbset(int64_t a) +static inline int drm_fixp2int_ceil(s64 a) +{ + if (a > 0) + return drm_fixp2int(a + DRM_FIXED_ALMOST_ONE); + else + return drm_fixp2int(a - DRM_FIXED_ALMOST_ONE); +} + +static inline unsigned drm_fixp_msbset(s64 a) { unsigned shift, sign = (a >> 63) & 1; @@ -136,6 +146,45 @@ static inline s64 drm_fixp_div(s64 a, s64 b) return result; } +static inline s64 drm_fixp_from_fraction(s64 a, s64 b) +{ + s64 res; + bool a_neg = a < 0; + bool b_neg = b < 0; + u64 a_abs = a_neg ? -a : a; + u64 b_abs = b_neg ? -b : b; + u64 rem; + + /* determine integer part */ + u64 res_abs = div64_u64_rem(a_abs, b_abs, &rem); + + /* determine fractional part */ + { + u32 i = DRM_FIXED_POINT; + + do { + rem <<= 1; + res_abs <<= 1; + if (rem >= b_abs) { + res_abs |= 1; + rem -= b_abs; + } + } while (--i != 0); + } + + /* round up LSB */ + { + u64 summand = (rem << 1) >= b_abs; + + res_abs += summand; + } + + res = (s64) res_abs; + if (a_neg ^ b_neg) + res = -res; + return res; +} + static inline s64 drm_fixp_exp(s64 x) { s64 tolerance = div64_s64(DRM_FIXED_ONE, 1000000); diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index 8bfd21c13d59..eff56cb0016a 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -40,10 +40,7 @@ struct mmci_platform_data { int gpio_wp; int gpio_cd; bool cd_invert; - unsigned int status_irq; struct embedded_sdio_data *embedded_sdio; - int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id); - }; #endif diff --git a/include/linux/ata.h b/include/linux/ata.h index d2992bfa1706..c1a2f345cbe6 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -487,8 +487,8 @@ enum ata_tf_protocols { }; enum ata_ioctls { - ATA_IOC_GET_IO32 = 0x309, - ATA_IOC_SET_IO32 = 0x324, + ATA_IOC_GET_IO32 = 0x309, /* HDIO_GET_32BIT */ + ATA_IOC_SET_IO32 = 0x324, /* HDIO_SET_32BIT */ }; /* core structures */ diff --git a/include/linux/bio.h b/include/linux/bio.h index b9b6e046b52e..fbe47bc700bd 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -310,6 +310,38 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) bio->bi_flags &= ~(1U << bit); } +static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) +{ + *bv = bio_iovec(bio); +} + +static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) +{ + struct bvec_iter iter = bio->bi_iter; + int idx; + + if (unlikely(!bio_multiple_segments(bio))) { + *bv = bio_iovec(bio); + return; + } + + bio_advance_iter(bio, &iter, iter.bi_size); + + if (!iter.bi_bvec_done) + idx = iter.bi_idx - 1; + else /* in the middle of bvec */ + idx = iter.bi_idx; + + *bv = bio->bi_io_vec[idx]; + + /* + * iter.bi_bvec_done records actual length of the last bvec + * if this bio ends in the middle of one io vector + */ + if (iter.bi_bvec_done) + bv->bv_len = iter.bi_bvec_done; +} + enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c70e3588a48c..168755791ec8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1367,6 +1367,13 @@ static inline void put_dev_sector(Sector p) page_cache_release(p.v); } +static inline bool __bvec_gap_to_prev(struct request_queue *q, + struct bio_vec *bprv, unsigned int offset) +{ + return offset || + ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); +} + /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. @@ -1376,18 +1383,22 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, { if (!queue_virt_boundary(q)) return false; - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); + return __bvec_gap_to_prev(q, bprv, offset); } static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, struct bio *next) { - if (!bio_has_data(prev)) - return false; + if (bio_has_data(prev) && queue_virt_boundary(q)) { + struct bio_vec pb, nb; + + bio_get_last_bvec(prev, &pb); + bio_get_first_bvec(next, &nb); - return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); + return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + } + + return false; } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 71b1d6cdcb5d..8dbd7879fdc6 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -220,6 +220,7 @@ struct ceph_connection { struct ceph_entity_addr actual_peer_addr; /* message out temps */ + struct ceph_msg_header out_hdr; struct ceph_msg *out_msg; /* sending message (== tail of out_sent) */ bool out_msg_done; @@ -229,7 +230,6 @@ struct ceph_connection { int out_kvec_left; /* kvec's left in out_kvec */ int out_skip; /* skip this many bytes */ int out_kvec_bytes; /* total bytes left */ - bool out_kvec_is_msg; /* kvec refers to out_msg */ int out_more; /* there is more data after the kvecs */ __le64 out_temp_ack; /* for writing an ack */ struct ceph_timespec out_temp_keepalive2; /* for writing keepalive2 diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4a4eea01956c..788c7c49a673 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -133,6 +133,12 @@ struct cgroup_subsys_state { */ u64 serial_nr; + /* + * Incremented by online self and children. Used to guarantee that + * parents are not offlined before their children. + */ + atomic_t online_cnt; + /* percpu_ref killing and RCU release */ struct rcu_head rcu_head; struct work_struct destroy_work; @@ -210,6 +216,9 @@ struct css_set { /* all css_task_iters currently walking this cset */ struct list_head task_iters; + /* dead and being drained, ignore for migration */ + bool dead; + /* For RCU-protected deletion */ struct rcu_head rcu_head; }; @@ -426,6 +435,7 @@ struct cgroup_subsys { int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); + void (*post_attach)(void); int (*can_fork)(struct task_struct *task, void **priv_p); void (*cancel_fork)(struct task_struct *task, void *priv); void (*fork)(struct task_struct *task, void *priv); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index c56988ac63f7..7cd0171963ae 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -384,6 +384,7 @@ struct clk_divider { #define CLK_DIVIDER_MAX_AT_ZERO BIT(6) extern const struct clk_ops clk_divider_ops; +extern const struct clk_ops clk_divider_ro_ops; unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate, unsigned int val, const struct clk_div_table *table, diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 904976ea1ca7..8f4ff956ec84 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -199,7 +199,7 @@ #define unreachable() __builtin_unreachable() /* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__)) +#define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) #endif /* GCC_VERSION >= 40500 */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4dac1036594f..6fc9a6dd5ed2 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -144,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) #define __trace_if(cond) \ - if (__builtin_constant_p((cond)) ? !!(cond) : \ + if (__builtin_constant_p(!!(cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ diff --git a/include/linux/console.h b/include/linux/console.h index bd194343c346..ea731af2451e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -150,6 +150,7 @@ extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); +extern void console_flush_on_panic(void); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d67ae119cf4e..da48880a76c6 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -161,6 +161,8 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); struct inode *(*d_select_inode)(struct dentry *, unsigned); + struct dentry *(*d_real)(struct dentry *, struct inode *); + void (*d_canonical_path)(const struct path *, struct path *); } ____cacheline_aligned; /* @@ -227,6 +229,7 @@ struct dentry_operations { #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ #define DCACHE_OP_SELECT_INODE 0x02000000 /* Unioned entry: dcache op selects inode */ +#define DCACHE_OP_REAL 0x08000000 extern seqlock_t rename_lock; @@ -409,9 +412,7 @@ static inline bool d_mountpoint(const struct dentry *dentry) */ static inline unsigned __d_entry_type(const struct dentry *dentry) { - unsigned type = READ_ONCE(dentry->d_flags); - smp_rmb(); - return type & DCACHE_ENTRY_TYPE; + return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) @@ -584,4 +585,12 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) return upper; } +static inline struct dentry *d_real(struct dentry *dentry) +{ + if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) + return dentry->d_op->d_real(dentry, NULL); + else + return dentry; +} + #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ec1c61c87d89..899ab9f8549e 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -124,6 +124,8 @@ struct dm_dev { char name[16]; }; +dev_t dm_get_dev_t(const char *path); + /* * Constructors should call these functions to ensure destination devices * are opened/closed correctly. diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 251a2090a554..e0ee0b3000b2 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,6 +19,8 @@ int devpts_new_index(struct inode *ptmx_inode); void devpts_kill_index(struct inode *ptmx_inode, int idx); +void devpts_add_ref(struct inode *ptmx_inode); +void devpts_del_ref(struct inode *ptmx_inode); /* mknod in devpts */ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv); @@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode); /* Dummy stubs in the no-pty case */ static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; } static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { } +static inline void devpts_add_ref(struct inode *ptmx_inode) { } +static inline void devpts_del_ref(struct inode *ptmx_inode) { } static inline struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv) { diff --git a/include/linux/efi.h b/include/linux/efi.h index 569b5a866bb1..47be3ad7d3e5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1199,7 +1199,10 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, struct list_head *head, bool remove); -bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len); +bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, + unsigned long data_size); +bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, + size_t len); extern struct work_struct efivar_work; void efivar_run_worker(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index 5972ffe5719a..5110d4211866 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -446,8 +446,12 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_detach_filter(struct sock *sk); +int __sk_detach_filter(struct sock *sk, bool locked); + int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..ab3d8d9bb3ef 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1207,6 +1207,16 @@ static inline struct inode *file_inode(const struct file *f) return f->f_inode; } +static inline struct dentry *file_dentry(const struct file *file) +{ + struct dentry *dentry = file->f_path.dentry; + + if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) + return dentry->d_op->d_real(dentry, file_inode(file)); + else + return dentry; +} + static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); @@ -2217,7 +2227,7 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags, extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, - const char *, int); + const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); diff --git a/include/linux/hash.h b/include/linux/hash.h index 1afde47e1528..79c52fa81cac 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -32,12 +32,28 @@ #error Wordsize not 32 or 64 #endif +/* + * The above primes are actively bad for hashing, since they are + * too sparse. The 32-bit one is mostly ok, the 64-bit one causes + * real problems. Besides, the "prime" part is pointless for the + * multiplicative hash. + * + * Although a random odd number will do, it turns out that the golden + * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice + * properties. + * + * These are the negative, (1 - phi) = (phi^2) = (3 - sqrt(5))/2. + * (See Knuth vol 3, section 6.4, exercise 9.) + */ +#define GOLDEN_RATIO_32 0x61C88647 +#define GOLDEN_RATIO_64 0x61C8864680B583EBull + static __always_inline u64 hash_64(u64 val, unsigned int bits) { u64 hash = val; -#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64 - hash = hash * GOLDEN_RATIO_PRIME_64; +#if BITS_PER_LONG == 64 + hash = hash * GOLDEN_RATIO_64; #else /* Sigh, gcc can't optimise this alone like it does for 32 bits. */ u64 n = hash; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 76dd4f0da5ca..2ead22dd74a0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -87,7 +87,8 @@ enum hrtimer_restart { * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) - * @start_pid: timer statistics field to store the pid of the task which + * @is_rel: Set if the timer was armed relative + * @start_pid: timer statistics field to store the pid of the task which * started the timer * @start_site: timer statistics field to store the site where the timer * was started @@ -101,7 +102,8 @@ struct hrtimer { ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; - unsigned long state; + u8 state; + u8 is_rel; #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; @@ -321,6 +323,27 @@ static inline void clock_was_set_delayed(void) { } #endif +static inline ktime_t +__hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) +{ + ktime_t rem = ktime_sub(timer->node.expires, now); + + /* + * Adjust relative timers for the extra we added in + * hrtimer_start_range_ns() to prevent short timeouts. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) + rem.tv64 -= hrtimer_resolution; + return rem; +} + +static inline ktime_t +hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) +{ + return __hrtimer_expires_remaining_adjusted(timer, + timer->base->get_time()); +} + extern void clock_was_set(void); #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); @@ -390,7 +413,12 @@ static inline void hrtimer_restart(struct hrtimer *timer) } /* Query timers: */ -extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); +extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); + +static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +{ + return __hrtimer_get_remaining(timer, false); +} extern u64 hrtimer_get_next_event(void); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 8fdc17b84739..ae6a711dcd1d 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -630,6 +630,11 @@ struct hv_input_signal_event_buffer { struct hv_input_signal_event event; }; +enum hv_signal_policy { + HV_SIGNAL_POLICY_DEFAULT = 0, + HV_SIGNAL_POLICY_EXPLICIT, +}; + struct vmbus_channel { /* Unique channel id */ int id; @@ -757,8 +762,21 @@ struct vmbus_channel { * link up channels based on their CPU affinity. */ struct list_head percpu_list; + /* + * Host signaling policy: The default policy will be + * based on the ring buffer state. We will also support + * a policy where the client driver can have explicit + * signaling control. + */ + enum hv_signal_policy signal_policy; }; +static inline void set_channel_signal_state(struct vmbus_channel *c, + enum hv_signal_policy policy) +{ + c->signal_policy = policy; +} + static inline void set_channel_read_state(struct vmbus_channel *c, bool state) { c->batched_reading = state; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index a338a688ee4a..dcb89e3515db 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,10 +46,6 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) -/* values as per ieee8021QBridgeFdbAgingTime */ -#define BR_MIN_AGEING_TIME (10 * HZ) -#define BR_MAX_AGEING_TIME (1000000 * HZ) - #define BR_DEFAULT_AGEING_TIME (300 * HZ) extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 821273ca4873..2d9b650047a5 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -235,6 +235,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* low 64 bit */ #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT)) +/* PRS_REG */ +#define DMA_PRS_PPR ((u32)1) + #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ cycles_t start_time = get_cycles(); \ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 1eaf3d81f5c1..2955e672391d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -607,7 +607,7 @@ do { \ #define do_trace_printk(fmt, args...) \ do { \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ @@ -651,7 +651,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); */ #define trace_puts(str) ({ \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(str) ? str : NULL; \ \ @@ -673,7 +673,7 @@ extern void trace_dump_stack(int skip); #define ftrace_vprintk(fmt, vargs) \ do { \ if (__builtin_constant_p(fmt)) { \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ diff --git a/include/linux/libata.h b/include/linux/libata.h index 600c1e0626a5..b20a2752f934 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -718,7 +718,7 @@ struct ata_device { union { u16 id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */ u32 gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */ - }; + } ____cacheline_aligned; /* DEVSLP Timing Variables from Identify Device Data Log */ u8 devslp_timing[ATA_LOG_DEVSLP_SIZE]; diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index abc4767695e4..b2c9fada8eac 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -45,7 +45,7 @@ struct mlx5_core_cq { atomic_t refcount; struct completion free; unsigned vector; - int irqn; + unsigned int irqn; void (*comp) (struct mlx5_core_cq *); void (*event) (struct mlx5_core_cq *, enum mlx5_event); struct mlx5_uar *uar; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0b473cbfa7ef..a91b67b18a73 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -334,6 +334,17 @@ enum { MLX5_CAP_OFF_CMDIF_CSUM = 46, }; +enum { + /* + * Max wqe size for rdma read is 512 bytes, so this + * limits our max_sge_rd as the wqe needs to fit: + * - ctrl segment (16 bytes) + * - rdma segment (16 bytes) + * - scatter elements (16 bytes each) + */ + MLX5_MAX_SGE_RD = (512 - 16 - 16) / 16 +}; + struct mlx5_inbox_hdr { __be16 opcode; u8 rsvd[4]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5c857f2a20d7..af3efd9157f0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -303,7 +303,7 @@ struct mlx5_eq { u32 cons_index; struct mlx5_buf buf; int size; - u8 irqn; + unsigned int irqn; u8 eqn; int nent; u64 mask; @@ -762,7 +762,8 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_start_eqs(struct mlx5_core_dev *dev); int mlx5_stop_eqs(struct mlx5_core_dev *dev); -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn); +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, + unsigned int *irqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); diff --git a/include/linux/mm.h b/include/linux/mm.h index f4c35e8125d1..fb987b2e5abd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1096,6 +1096,8 @@ struct zap_details { struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd); int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); diff --git a/include/linux/module.h b/include/linux/module.h index 3a19c79918e0..b229a9961d02 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -302,6 +302,12 @@ struct mod_tree_node { struct latch_tree_node node; }; +struct mod_kallsyms { + Elf_Sym *symtab; + unsigned int num_symtab; + char *strtab; +}; + struct module { enum module_state state; @@ -411,14 +417,9 @@ struct module { #endif #ifdef CONFIG_KALLSYMS - /* - * We keep the symbol and string tables for kallsyms. - * The core_* fields below are temporary, loader-only (they - * could really be discarded after module init). - */ - Elf_Sym *symtab, *core_symtab; - unsigned int num_symtab, core_num_syms; - char *strtab, *core_strtab; + /* Protected by RCU and/or module_mutex: use rcu_dereference() */ + struct mod_kallsyms *kallsyms; + struct mod_kallsyms core_kallsyms; /* Section attributes */ struct module_sect_attrs *sect_attrs; diff --git a/include/linux/namei.h b/include/linux/namei.h index d8c6334cd150..d53c25453aca 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -75,6 +75,8 @@ extern struct dentry *user_path_create(int, const char __user *, struct path *, extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); +extern int vfs_path_lookup(struct dentry *, struct vfsmount *, + const char *, unsigned int, struct path *); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3143c847bddb..04c068e55353 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -265,6 +265,7 @@ struct header_ops { void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); + bool (*validate)(const char *ll_header, unsigned int len); }; /* These flag bits are private to the generic network queueing @@ -1398,8 +1399,7 @@ enum netdev_priv_flags { * @dma: DMA channel * @mtu: Interface MTU value * @type: Interface hardware type - * @hard_header_len: Hardware header length, which means that this is the - * minimum size of a packet. + * @hard_header_len: Maximum hardware header length. * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -2493,6 +2493,24 @@ static inline int dev_parse_header(const struct sk_buff *skb, return dev->header_ops->parse(skb, haddr); } +/* ll_header must have at least hard_header_len allocated */ +static inline bool dev_validate_header(const struct net_device *dev, + char *ll_header, int len) +{ + if (likely(len >= dev->hard_header_len)) + return true; + + if (capable(CAP_SYS_RAWIO)) { + memset(ll_header + len, 0, dev->hard_header_len - len); + return true; + } + + if (dev->header_ops && dev->header_ops->validate) + return dev->header_ops->validate(ll_header, len); + + return false; +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c0e961474a52..5455b660bd88 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -544,9 +544,7 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, static inline loff_t nfs_size_to_loff_t(__u64 size) { - if (size > (__u64) OFFSET_MAX - 1) - return OFFSET_MAX - 1; - return (loff_t) size; + return min_t(u64, size, OFFSET_MAX); } static inline ino_t diff --git a/include/linux/pci.h b/include/linux/pci.h index 6ae25aae88fd..e89c7ee7e803 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -359,6 +359,7 @@ struct pci_dev { unsigned int io_window_1k:1; /* Intel P2P bridge 1K I/O windows */ unsigned int irq_managed:1; unsigned int has_secondary_link:1; + unsigned int non_compliant_bars:1; /* broken BARs; ignore them */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -988,23 +989,6 @@ static inline int pci_is_managed(struct pci_dev *pdev) return pdev->is_managed; } -static inline void pci_set_managed_irq(struct pci_dev *pdev, unsigned int irq) -{ - pdev->irq = irq; - pdev->irq_managed = 1; -} - -static inline void pci_reset_managed_irq(struct pci_dev *pdev) -{ - pdev->irq = 0; - pdev->irq_managed = 0; -} - -static inline bool pci_has_managed_irq(struct pci_dev *pdev) -{ - return pdev->irq_managed && pdev->irq > 0; -} - void pci_disable_device(struct pci_dev *dev); extern unsigned int pcibios_max_latency; diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h index 5e0bc779e6c5..33f88b4479e4 100644 --- a/include/linux/platform_data/asoc-s3c.h +++ b/include/linux/platform_data/asoc-s3c.h @@ -39,6 +39,10 @@ struct samsung_i2s { */ struct s3c_audio_pdata { int (*cfg_gpio)(struct platform_device *); + void *dma_playback; + void *dma_capture; + void *dma_play_sec; + void *dma_capture_mic; union { struct samsung_i2s i2s; } type; diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 061265f92876..504c98a278d4 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -57,7 +57,29 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 -/* Returns true on success, false on denial. */ +#define PTRACE_MODE_FSCREDS 0x08 +#define PTRACE_MODE_REALCREDS 0x10 + +/* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ +#define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) +#define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) + +/** + * ptrace_may_access - check whether the caller is permitted to access + * a target task. + * @task: target task + * @mode: selects type of access and caller credentials + * + * Returns true on success, false on denial. + * + * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must + * be set in @mode to specify whether the access was requested through + * a filesystem syscall (should use effective capabilities and fsuid + * of the caller) or through an explicit syscall such as + * process_vm_writev or ptrace (and should use the real credentials). + */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); static inline int ptrace_reparented(struct task_struct *child) diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 33170dbd9db4..5d5174b59802 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -370,12 +370,28 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags); /** + * radix_tree_iter_retry - retry this chunk of the iteration + * @iter: iterator state + * + * If we iterate over a tree protected only by the RCU lock, a race + * against deletion or creation may result in seeing a slot for which + * radix_tree_deref_retry() returns true. If so, call this function + * and continue the iteration. + */ +static inline __must_check +void **radix_tree_iter_retry(struct radix_tree_iter *iter) +{ + iter->next_index = iter->index; + return NULL; +} + +/** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator * Returns: current chunk size */ -static __always_inline unsigned +static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; @@ -409,9 +425,9 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) return slot + offset + 1; } } else { - unsigned size = radix_tree_chunk_size(iter) - 1; + long size = radix_tree_chunk_size(iter); - while (size--) { + while (--size > 0) { slot++; iter->index++; if (likely(*slot)) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 29446aeef36e..ddda2ac3446e 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -108,20 +108,6 @@ static inline void put_anon_vma(struct anon_vma *anon_vma) __put_anon_vma(anon_vma); } -static inline void vma_lock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - down_write(&anon_vma->root->rwsem); -} - -static inline void vma_unlock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - up_write(&anon_vma->root->rwsem); -} - static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); diff --git a/include/linux/sched.h b/include/linux/sched.h index fa39434e3fdd..21a6e9649012 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -830,6 +830,7 @@ struct user_struct { unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ #endif unsigned long locked_shm; /* How many pages of mlocked shm ? */ + unsigned long unix_inflight; /* How many files in flight in unix sockets */ #ifdef CONFIG_KEYS struct key *uid_keyring; /* UID specific keyring */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 50777b5b1e4c..92d112aeec68 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -15,10 +15,7 @@ struct shmem_inode_info { unsigned int seals; /* shmem seals */ unsigned long flags; unsigned long alloced; /* data pages alloced to file */ - union { - unsigned long swapped; /* subtotal assigned to swap */ - char *symlink; /* unswappable short symlink */ - }; + unsigned long swapped; /* subtotal assigned to swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct list_head swaplist; /* chain of maybes on swap */ struct simple_xattrs xattrs; /* list of xattrs */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4355129fff91..4fde61804191 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -219,6 +219,7 @@ struct sk_buff; #else #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1) #endif +extern int sysctl_max_skb_frags; typedef struct skb_frag_struct skb_frag_t; @@ -1907,6 +1908,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +/** + * skb_tailroom_reserve - adjust reserved_tailroom + * @skb: buffer to alter + * @mtu: maximum amount of headlen permitted + * @needed_tailroom: minimum amount of reserved_tailroom + * + * Set reserved_tailroom so that headlen can be as large as possible but + * not larger than mtu and tailroom cannot be smaller than + * needed_tailroom. + * The required headroom should already have been reserved before using + * this function. + */ +static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, + unsigned int needed_tailroom) +{ + SKB_LINEAR_ASSERT(skb); + if (mtu < skb_tailroom(skb) - needed_tailroom) + /* use at most mtu */ + skb->reserved_tailroom = skb_tailroom(skb) - mtu; + else + /* use up to all available space */ + skb->reserved_tailroom = needed_tailroom; +} + #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 @@ -2723,6 +2748,23 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +static inline void skb_postpush_rcsum(struct sk_buff *skb, + const void *start, unsigned int len) +{ + /* For performing the reverse operation to skb_postpull_rcsum(), + * we can instead of ... + * + * skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); + * + * ... just use this equivalent version here to save a few + * instructions. Feeding csum of 0 in csum_partial() and later + * on adding skb->csum is equivalent to feed skb->csum in the + * first place. + */ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_partial(start, len, skb->csum); +} + /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim @@ -3446,7 +3488,8 @@ struct skb_gso_cb { int encap_level; __u16 csum_start; }; -#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb) +#define SKB_SGO_CB_OFFSET 32 +#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_SGO_CB_OFFSET)) static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) { diff --git a/include/linux/switch.h b/include/linux/switch.h deleted file mode 100644 index 3e4c748e343a..000000000000 --- a/include/linux/switch.h +++ /dev/null @@ -1,53 +0,0 @@ -/* - * Switch class driver - * - * Copyright (C) 2008 Google, Inc. - * Author: Mike Lockwood <lockwood@android.com> - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * -*/ - -#ifndef __LINUX_SWITCH_H__ -#define __LINUX_SWITCH_H__ - -struct switch_dev { - const char *name; - struct device *dev; - int index; - int state; - - ssize_t (*print_name)(struct switch_dev *sdev, char *buf); - ssize_t (*print_state)(struct switch_dev *sdev, char *buf); -}; - -struct gpio_switch_platform_data { - const char *name; - unsigned gpio; - - /* if NULL, switch_dev.name will be printed */ - const char *name_on; - const char *name_off; - /* if NULL, "0" or "1" will be printed */ - const char *state_on; - const char *state_off; -}; - -extern int switch_dev_register(struct switch_dev *sdev); -extern void switch_dev_unregister(struct switch_dev *sdev); - -static inline int switch_get_state(struct switch_dev *sdev) -{ - return sdev->state; -} - -extern void switch_set_state(struct switch_dev *sdev, int state); - -#endif /* __LINUX_SWITCH_H__ */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 613c29bd6baf..4a849f19e6c9 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -43,6 +43,9 @@ /* Default weight of a bound cooling device */ #define THERMAL_WEIGHT_DEFAULT 0 +/* use value, which < 0K, to indicate an invalid/uninitialized temperature */ +#define THERMAL_TEMP_INVALID -274000 + /* Unit conversion macros */ #define DECI_KELVIN_TO_CELSIUS(t) ({ \ long _t = (t); \ @@ -153,6 +156,7 @@ struct thermal_attr { * @trip_hyst_attrs: attributes for trip points for sysfs: trip hysteresis * @devdata: private pointer for device private data * @trips: number of trip points the thermal zone supports + * @trips_disabled; bitmap for disabled trips * @passive_delay: number of milliseconds to wait between polls when * performing passive cooling. * @polling_delay: number of milliseconds to wait between polls when @@ -167,6 +171,7 @@ struct thermal_attr { * @forced_passive: If > 0, temperature at which to switch on all ACPI * processor cooling devices. Currently only used by the * step-wise governor. + * @need_update: if equals 1, thermal_zone_device_update needs to be invoked. * @ops: operations this &thermal_zone_device supports * @tzp: thermal zone parameters * @governor: pointer to the governor for this thermal zone @@ -187,6 +192,7 @@ struct thermal_zone_device { struct thermal_attr *trip_hyst_attrs; void *devdata; int trips; + unsigned long trips_disabled; /* bitmap for disabled trips */ int passive_delay; int polling_delay; int temperature; @@ -194,6 +200,7 @@ struct thermal_zone_device { int emul_temperature; int passive; unsigned int forced_passive; + atomic_t need_update; struct thermal_zone_device_ops *ops; struct thermal_zone_params *tzp; struct thermal_governor *governor; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 429fdfc3baf5..925730bc9fc1 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -568,6 +568,8 @@ enum { FILTER_DYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, + FILTER_COMM, + FILTER_CPU, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c592c..27e32b2b602f 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -14,8 +14,10 @@ * See the file COPYING for more details. */ +#include <linux/smp.h> #include <linux/errno.h> #include <linux/types.h> +#include <linux/cpumask.h> #include <linux/rcupdate.h> #include <linux/static_key.h> @@ -352,15 +354,19 @@ extern void syscall_unregfunc(void); * "void *__data, proto" as the callback prototype. */ #define DECLARE_TRACE_NOARGS(name) \ - __DECLARE_TRACE(name, void, , 1, void *__data, __data) + __DECLARE_TRACE(name, void, , \ + cpu_online(raw_smp_processor_id()), \ + void *__data, __data) #define DECLARE_TRACE(name, proto, args) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1, \ - PARAMS(void *__data, proto), \ - PARAMS(__data, args)) + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + cpu_online(raw_smp_processor_id()), \ + PARAMS(void *__data, proto), \ + PARAMS(__data, args)) #define DECLARE_TRACE_CONDITION(name, proto, args, cond) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \ PARAMS(void *__data, proto), \ PARAMS(__data, args)) diff --git a/include/linux/tty.h b/include/linux/tty.h index 5e31f1b99037..3bf03b6b52e9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -594,7 +594,7 @@ static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, count = ld->ops->receive_buf2(ld->tty, p, f, count); else { count = min_t(int, count, ld->tty->receive_room); - if (count) + if (count && ld->ops->receive_buf) ld->ops->receive_buf(ld->tty, p, f, count); } return count; @@ -654,6 +654,7 @@ extern long vt_compat_ioctl(struct tty_struct *tty, /* tty_mutex.c */ /* functions for preparation of BKL removal */ extern void __lockfunc tty_lock(struct tty_struct *tty); +extern int tty_lock_interruptible(struct tty_struct *tty); extern void __lockfunc tty_unlock(struct tty_struct *tty); extern void __lockfunc tty_lock_slave(struct tty_struct *tty); extern void __lockfunc tty_unlock_slave(struct tty_struct *tty); diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h index cbb20afdbc01..bb679b48f408 100644 --- a/include/linux/ucs2_string.h +++ b/include/linux/ucs2_string.h @@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s); unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); +unsigned long ucs2_utf8size(const ucs2_char_t *src); +unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, + unsigned long maxlength); + #endif /* _LINUX_UCS2_STRING_H_ */ diff --git a/include/linux/uid_stat.h b/include/linux/uid_stat.h deleted file mode 100644 index 6bd6c4e52d17..000000000000 --- a/include/linux/uid_stat.h +++ /dev/null @@ -1,29 +0,0 @@ -/* include/linux/uid_stat.h - * - * Copyright (C) 2008-2009 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef __uid_stat_h -#define __uid_stat_h - -/* Contains definitions for resource tracking per uid. */ - -#ifdef CONFIG_UID_STAT -int uid_stat_tcp_snd(uid_t uid, int size); -int uid_stat_tcp_rcv(uid_t uid, int size); -#else -#define uid_stat_tcp_snd(uid, size) do {} while (0); -#define uid_stat_tcp_rcv(uid, size) do {} while (0); -#endif - -#endif /* _LINUX_UID_STAT_H */ diff --git a/include/linux/usb.h b/include/linux/usb.h index b9a28074210f..b79925dd2b41 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -511,6 +511,8 @@ struct usb3_lpm_parameters { * @usb2_hw_lpm_enabled: USB2 hardware LPM is enabled * @usb2_hw_lpm_allowed: Userspace allows USB 2.0 LPM to be enabled * @usb3_lpm_enabled: USB3 hardware LPM enabled + * @usb3_lpm_u1_enabled: USB3 hardware U1 LPM enabled + * @usb3_lpm_u2_enabled: USB3 hardware U2 LPM enabled * @string_langid: language ID for strings * @product: iProduct string, if present (static) * @manufacturer: iManufacturer string, if present (static) @@ -584,6 +586,8 @@ struct usb_device { unsigned usb2_hw_lpm_enabled:1; unsigned usb2_hw_lpm_allowed:1; unsigned usb3_lpm_enabled:1; + unsigned usb3_lpm_u1_enabled:1; + unsigned usb3_lpm_u2_enabled:1; int string_langid; /* static strings from the device */ diff --git a/include/linux/usb/class-dual-role.h b/include/linux/usb/class-dual-role.h index af42ed34944a..c6df2238012e 100644 --- a/include/linux/usb/class-dual-role.h +++ b/include/linux/usb/class-dual-role.h @@ -109,18 +109,19 @@ extern int dual_role_property_is_writeable(struct dual_role_phy_instance enum dual_role_property prop); extern void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role); #else /* CONFIG_DUAL_ROLE_USB_INTF */ -static void dual_role_instance_changed(struct dual_role_phy_instance +static inline void dual_role_instance_changed(struct dual_role_phy_instance *dual_role){} -static struct dual_role_phy_instance *__must_check +static inline struct dual_role_phy_instance *__must_check devm_dual_role_instance_register(struct device *parent, const struct dual_role_phy_desc *desc) { return ERR_PTR(-ENOSYS); } -static void devm_dual_role_instance_unregister(struct device *dev, +static inline void devm_dual_role_instance_unregister(struct device *dev, struct dual_role_phy_instance *dual_role){} -static void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role) +static inline void *dual_role_get_drvdata(struct dual_role_phy_instance + *dual_role) { return ERR_PTR(-ENOSYS); } diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index f89c24bd53a4..bdd02cc5d856 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -396,6 +396,7 @@ struct hc_driver { /* Call for power on/off the port if necessary */ int (*port_power)(struct usb_hcd *hcd, int portnum, bool enable); + void (*change_bus_speed)(struct usb_hcd *hcd, int speed); }; static inline int hcd_giveback_urb_in_bh(struct usb_hcd *hcd) diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index 7f5f78bd15ad..245f57dbbb61 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -79,6 +79,8 @@ /* Cannot handle MI_REPORT_SUPPORTED_OPERATION_CODES */ \ US_FLAG(MAX_SECTORS_240, 0x08000000) \ /* Sets max_sectors to 240 */ \ + US_FLAG(NO_REPORT_LUNS, 0x10000000) \ + /* Cannot handle REPORT_LUNS */ \ #define US_FLAG(name, value) US_FL_##name = value , enum { US_DO_ALL_FLAGS }; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b333c945e571..d0b5ca5d4e08 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -198,6 +198,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_io(struct writeback_control *wbc, struct page *page, size_t bytes); +void cgroup_writeback_umount(void); /** * inode_attach_wb - associate an inode with its wb @@ -301,6 +302,10 @@ static inline void wbc_account_io(struct writeback_control *wbc, { } +static inline void cgroup_writeback_umount(void) +{ +} + #endif /* CONFIG_CGROUP_WRITEBACK */ /* diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 647ebfe5174f..d4227a8a2a23 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -363,6 +363,7 @@ struct vb2_ops { }; struct vb2_buf_ops { + int (*verify_planes_array)(struct vb2_buffer *vb, const void *pb); int (*fill_user_buffer)(struct vb2_buffer *vb, void *pb); int (*fill_vb2_buffer)(struct vb2_buffer *vb, const void *pb, struct vb2_plane *planes); diff --git a/include/net/activity_stats.h b/include/net/activity_stats.h deleted file mode 100644 index 10e4c1506eeb..000000000000 --- a/include/net/activity_stats.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * Copyright (C) 2010 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Author: Mike Chan (mike@android.com) - */ - -#ifndef __activity_stats_h -#define __activity_stats_h - -#ifdef CONFIG_NET_ACTIVITY_STATS -void activity_stats_update(void); -#else -#define activity_stats_update(void) {} -#endif - -#endif /* _NET_ACTIVITY_STATS_H */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 2a91a0561a47..9b4c418bebd8 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -6,8 +6,8 @@ #include <linux/mutex.h> #include <net/sock.h> -void unix_inflight(struct file *fp); -void unix_notinflight(struct file *fp); +void unix_inflight(struct user_struct *user, struct file *fp); +void unix_notinflight(struct user_struct *user, struct file *fp); void unix_gc(void); void wait_for_unix_gc(void); struct sock *unix_get_socket(struct file *filp); diff --git a/include/net/bonding.h b/include/net/bonding.h index c1740a2794a3..93abe5f6188d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -214,6 +214,7 @@ struct bonding { * ALB mode (6) - to sync the use and modifications of its hash table */ spinlock_t mode_lock; + spinlock_t stats_lock; u8 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 6816f0fa5693..30a56ab2ccfb 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -44,6 +44,24 @@ static inline bool skb_valid_dst(const struct sk_buff *skb) return dst && !(dst->flags & DST_METADATA); } +static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + const struct metadata_dst *a, *b; + + if (!(skb_a->_skb_refdst | skb_b->_skb_refdst)) + return 0; + + a = (const struct metadata_dst *) skb_dst(skb_a); + b = (const struct metadata_dst *) skb_dst(skb_b); + + if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len) + return 1; + + return memcmp(&a->u.tun_info, &b->u.tun_info, + sizeof(a->u.tun_info) + a->u.tun_info.options_len); +} + struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags); struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 481fe1c9044c..49dcad4fe99e 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -270,8 +270,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child); +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child); void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 84b20835b736..0dc0a51da38f 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -111,11 +111,24 @@ static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner) struct ipv6hdr; -static inline int IP6_ECN_set_ce(struct ipv6hdr *iph) +/* Note: + * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE, + * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE + * In IPv6 case, no checksum compensates the change in IPv6 header, + * so we have to update skb->csum. + */ +static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) { + __be32 from, to; + if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph))) return 0; - *(__be32*)iph |= htonl(INET_ECN_CE << 20); + + from = *(__be32 *)iph; + to = from | htonl(INET_ECN_CE << 20); + *(__be32 *)iph = to; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, from), to); return 1; } @@ -142,7 +155,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) case cpu_to_be16(ETH_P_IPV6): if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= skb_tail_pointer(skb)) - return IP6_ECN_set_ce(ipv6_hdr(skb)); + return IP6_ECN_set_ce(skb, ipv6_hdr(skb)); break; } diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 4bbd221637cd..ba82feec2590 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -64,8 +64,16 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) void ip6_route_input(struct sk_buff *skb); -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6); +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags); + +static inline struct dst_entry *ip6_route_output(struct net *net, + const struct sock *sk, + struct flowi6 *fl6) +{ + return ip6_route_output_flags(net, sk, fl6, 0); +} + struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, int flags); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 9f4df68105ab..3f98233388fb 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -61,6 +61,7 @@ struct fib_nh_exception { struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; + struct rcu_head rcu; }; struct fnhe_hash_bucket { diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0816c872b689..a6cc576fd467 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1588,6 +1588,23 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) } #endif /* CONFIG_IP_VS_NFCT */ +/* Really using conntrack? */ +static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp, + struct sk_buff *skb) +{ +#ifdef CONFIG_IP_VS_NFCT + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + if (!(cp->flags & IP_VS_CONN_F_NFCT)) + return false; + ct = nf_ct_get(skb, &ctinfo); + if (ct && !nf_ct_is_untracked(ct)) + return true; +#endif + return false; +} + static inline int ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) { diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index 8f81bbbc38fc..e0f4109e64c6 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length); /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); +#ifdef CONFIG_WEXT_CORE +/* flush all previous wext events - if work is done from netdev notifiers */ +void wireless_nlevent_flush(void); +#else +static inline void wireless_nlevent_flush(void) {} +#endif /* We may need a function to send a stream of events to user space. * More on that later... */ diff --git a/include/net/scm.h b/include/net/scm.h index 262532d111f5..59fa93c01d2a 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -21,6 +21,7 @@ struct scm_creds { struct scm_fp_list { short count; short max; + struct user_struct *user; struct file *fp[SCM_MAX_FD]; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 984e59d99deb..b36cebad6b2f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -450,7 +450,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); -void tcp_req_err(struct sock *sk, u32 seq); +void tcp_req_err(struct sock *sk, u32 seq, bool abort); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, @@ -1681,8 +1681,6 @@ static inline bool tcp_stream_memory_free(const struct sock *sk) return notsent_bytes < tcp_notsent_lowat(tp); } -extern int tcp_nuke_addr(struct net *net, struct sockaddr *addr); - #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); void tcp4_proc_exit(void); diff --git a/include/rdma/ib.h b/include/rdma/ib.h index cf8f9e700e48..a6b93706b0fc 100644 --- a/include/rdma/ib.h +++ b/include/rdma/ib.h @@ -34,6 +34,7 @@ #define _RDMA_IB_H #include <linux/types.h> +#include <linux/sched.h> struct ib_addr { union { @@ -86,4 +87,19 @@ struct sockaddr_ib { __u64 sib_scope_id; }; +/* + * The IB interfaces that use write() as bi-directional ioctl() are + * fundamentally unsafe, since there are lots of ways to trigger "write()" + * calls from various contexts with elevated privileges. That includes the + * traditional suid executable error message writes, but also various kernel + * interfaces that can write to file descriptors. + * + * This function provides protection for the legacy API by restricting the + * calling context. + */ +static inline bool ib_safe_file_access(struct file *filp) +{ + return filp->f_cred == current_cred() && segment_eq(get_fs(), USER_DS); +} + #endif /* _RDMA_IB_H */ diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index f6cbef78db62..3b91ad5d5115 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -167,6 +167,10 @@ int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, int snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count); int snd_rawmidi_transmit(struct snd_rawmidi_substream *substream, unsigned char *buffer, int count); +int __snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, + unsigned char *buffer, int count); +int __snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, + int count); /* main midi functions */ diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 56cf8e485ef2..28ee5c2e6bcd 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -94,5 +94,8 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, sense_reason_t (*exec_cmd)(struct se_cmd *cmd)); bool target_sense_desc_format(struct se_device *dev); +sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); +bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, + struct request_queue *q, int block_size); #endif /* TARGET_CORE_BACKEND_H */ diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index aabf0aca0171..689f4d207122 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -138,6 +138,7 @@ enum se_cmd_flags_table { SCF_COMPARE_AND_WRITE = 0x00080000, SCF_COMPARE_AND_WRITE_POST = 0x00100000, SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC = 0x00200000, + SCF_ACK_KREF = 0x00400000, }; /* struct se_dev_entry->lun_flags and struct se_lun->lun_access */ @@ -490,6 +491,8 @@ struct se_cmd { #define CMD_T_DEV_ACTIVE (1 << 7) #define CMD_T_REQUEST_STOP (1 << 8) #define CMD_T_BUSY (1 << 9) +#define CMD_T_TAS (1 << 10) +#define CMD_T_FABRIC_STOP (1 << 11) spinlock_t t_state_lock; struct kref cmd_kref; struct completion t_transport_stop_comp; diff --git a/include/trace/events/power.h b/include/trace/events/power.h index de77035567c4..9af0d898016a 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -135,7 +135,7 @@ TRACE_EVENT(cpu_frequency_limits, TP_fast_assign( __entry->min_freq = min_freq; - __entry->max_freq = min_freq; + __entry->max_freq = max_freq; __entry->cpu_id = cpu_id; ), diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index c2e5d6cb34e3..ebd10e624598 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -307,7 +307,7 @@ header-y += nfs_mount.h header-y += nl80211.h header-y += n_r3964.h header-y += nubus.h -header-y += nvme.h +header-y += nvme_ioctl.h header-y += nvram.h header-y += omap3isp.h header-y += omapfb.h diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index c9aca042e61d..8485dd4300b8 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -358,6 +358,7 @@ enum fuse_opcode { FUSE_FALLOCATE = 43, FUSE_READDIRPLUS = 44, FUSE_RENAME2 = 45, + FUSE_CANONICAL_PATH= 2016, /* CUSE specific operations */ CUSE_INIT = 4096, diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index accb036bbc9c..cfb5c406f344 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -52,6 +52,8 @@ #define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs" #define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs" +#define SDCARDFS_SUPER_MAGIC 0xb550ca10 + #define SMB_SUPER_MAGIC 0x517B #define CGROUP_SUPER_MAGIC 0x27e0eb diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h index 623e9aab645e..e888b1aed69f 100644 --- a/include/uapi/linux/sockios.h +++ b/include/uapi/linux/sockios.h @@ -65,7 +65,6 @@ #define SIOCDIFADDR 0x8936 /* delete PA address */ #define SIOCSIFHWBROADCAST 0x8937 /* set hardware broadcast addr */ #define SIOCGIFCOUNT 0x8938 /* get number of devices */ -#define SIOCKILLADDR 0x8939 /* kill sockets with this local addr */ #define SIOCGIFBR 0x8940 /* Bridging support */ #define SIOCSIFBR 0x8941 /* Set bridging options */ diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h index c039f1d68a09..086168e18ca8 100644 --- a/include/uapi/linux/v4l2-dv-timings.h +++ b/include/uapi/linux/v4l2-dv-timings.h @@ -183,7 +183,8 @@ #define V4L2_DV_BT_CEA_3840X2160P24 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1276, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -191,14 +192,16 @@ #define V4L2_DV_BT_CEA_3840X2160P25 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_3840X2160P30 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -206,14 +209,16 @@ #define V4L2_DV_BT_CEA_3840X2160P50 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_3840X2160P60 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -221,7 +226,8 @@ #define V4L2_DV_BT_CEA_4096X2160P24 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1020, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -229,14 +235,16 @@ #define V4L2_DV_BT_CEA_4096X2160P25 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_4096X2160P30 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -244,14 +252,16 @@ #define V4L2_DV_BT_CEA_4096X2160P50 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_4096X2160P60 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ diff --git a/include/xen/page.h b/include/xen/page.h index 96294ac93755..9dc46cb8a0fd 100644 --- a/include/xen/page.h +++ b/include/xen/page.h @@ -15,9 +15,9 @@ */ #define xen_pfn_to_page(xen_pfn) \ - ((pfn_to_page(((unsigned long)(xen_pfn) << XEN_PAGE_SHIFT) >> PAGE_SHIFT))) + (pfn_to_page((unsigned long)(xen_pfn) >> (PAGE_SHIFT - XEN_PAGE_SHIFT))) #define page_to_xen_pfn(page) \ - (((page_to_pfn(page)) << PAGE_SHIFT) >> XEN_PAGE_SHIFT) + ((page_to_pfn(page)) << (PAGE_SHIFT - XEN_PAGE_SHIFT)) #define XEN_PFN_PER_PAGE (PAGE_SIZE / XEN_PAGE_SIZE) diff --git a/ipc/shm.c b/ipc/shm.c index 41787276e141..3174634ca4e5 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -156,11 +156,12 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id); /* - * We raced in the idr lookup or with shm_destroy(). Either way, the - * ID is busted. + * Callers of shm_lock() must validate the status of the returned ipc + * object pointer (as returned by ipc_lock()), and error out as + * appropriate. */ - WARN_ON(IS_ERR(ipcp)); - + if (IS_ERR(ipcp)) + return (void *)ipcp; return container_of(ipcp, struct shmid_kernel, shm_perm); } @@ -186,18 +187,33 @@ static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) } -/* This is called by fork, once for every shm attach. */ -static void shm_open(struct vm_area_struct *vma) +static int __shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); + + if (IS_ERR(shp)) + return PTR_ERR(shp); + shp->shm_atim = get_seconds(); shp->shm_lprid = task_tgid_vnr(current); shp->shm_nattch++; shm_unlock(shp); + return 0; +} + +/* This is called by fork, once for every shm attach. */ +static void shm_open(struct vm_area_struct *vma) +{ + int err = __shm_open(vma); + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + WARN_ON_ONCE(err); } /* @@ -260,6 +276,14 @@ static void shm_close(struct vm_area_struct *vma) down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); + + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + if (WARN_ON_ONCE(IS_ERR(shp))) + goto done; /* no-op */ + shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = get_seconds(); shp->shm_nattch--; @@ -267,6 +291,7 @@ static void shm_close(struct vm_area_struct *vma) shm_destroy(ns, shp); else shm_unlock(shp); +done: up_write(&shm_ids(ns).rwsem); } @@ -388,17 +413,25 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) struct shm_file_data *sfd = shm_file_data(file); int ret; + /* + * In case of remap_file_pages() emulation, the file can represent + * removed IPC ID: propogate shm_lock() error to caller. + */ + ret =__shm_open(vma); + if (ret) + return ret; + ret = sfd->file->f_op->mmap(sfd->file, vma); - if (ret != 0) + if (ret) { + shm_close(vma); return ret; + } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; - shm_open(vma); - - return ret; + return 0; } static int shm_release(struct inode *ino, struct file *file) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 4504ca66118d..50da680c479f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -166,7 +166,7 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5) if (!task) return -EINVAL; - memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm))); + strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm))); return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a7945d10b378..2e7f7ab739e4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1121,6 +1121,16 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + if ((opcode == BPF_LSH || opcode == BPF_RSH || + opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { + int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; + + if (insn->imm < 0 || insn->imm >= size) { + verbose("invalid shift %d\n", insn->imm); + return -EINVAL; + } + } + /* pattern match 'bpf_add Rx, imm' instruction */ if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 && regs[insn->dst_reg].type == FRAME_PTR && @@ -2072,7 +2082,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta) /* adjust offset of jmps if necessary */ if (i < pos && i + insn->off + 1 > pos) insn->off += delta; - else if (i > pos && i + insn->off + 1 < pos) + else if (i > pos + delta && i + insn->off + 1 <= pos + delta) insn->off -= delta; } } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a57b7c86871c..47851dbc893d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -57,7 +57,7 @@ #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */ #include <linux/kthread.h> #include <linux/delay.h> - +#include <linux/cpuset.h> #include <linux/atomic.h> /* @@ -2498,6 +2498,14 @@ static void cgroup_migrate_add_src(struct css_set *src_cset, lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); + /* + * If ->dead, @src_set is associated with one or more dead cgroups + * and doesn't contain any migratable tasks. Ignore it early so + * that the rest of migration path doesn't get confused by it. + */ + if (src_cset->dead) + return; + src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); if (!list_empty(&src_cset->mg_preload_node)) @@ -2768,9 +2776,10 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct task_struct *tsk; + struct cgroup_subsys *ss; struct cgroup *cgrp; pid_t pid; - int ret; + int ssid, ret; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; @@ -2818,6 +2827,9 @@ out_unlock_rcu: rcu_read_unlock(); out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); + for_each_subsys(ss, ssid) + if (ss->post_attach) + ss->post_attach(); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } @@ -4735,14 +4747,15 @@ static void css_free_work_fn(struct work_struct *work) if (ss) { /* css free path */ + struct cgroup_subsys_state *parent = css->parent; int id = css->id; - if (css->parent) - css_put(css->parent); - ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); + + if (parent) + css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); @@ -4838,6 +4851,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; + atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); @@ -4860,6 +4874,10 @@ static int online_css(struct cgroup_subsys_state *css) if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); + + atomic_inc(&css->online_cnt); + if (css->parent) + atomic_inc(&css->parent->online_cnt); } return ret; } @@ -5091,10 +5109,15 @@ static void css_killed_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); mutex_lock(&cgroup_mutex); - offline_css(css); - mutex_unlock(&cgroup_mutex); - css_put(css); + do { + offline_css(css); + css_put(css); + /* @css can't go away while we're holding cgroup_mutex */ + css = css->parent; + } while (css && atomic_dec_and_test(&css->online_cnt)); + + mutex_unlock(&cgroup_mutex); } /* css kill confirmation processing requires process context, bounce */ @@ -5103,8 +5126,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref) struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); - INIT_WORK(&css->destroy_work, css_killed_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + if (atomic_dec_and_test(&css->online_cnt)) { + INIT_WORK(&css->destroy_work, css_killed_work_fn); + queue_work(cgroup_destroy_wq, &css->destroy_work); + } } /** @@ -5173,6 +5198,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup_subsys_state *css; + struct cgrp_cset_link *link; int ssid; lockdep_assert_held(&cgroup_mutex); @@ -5193,11 +5219,18 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) return -EBUSY; /* - * Mark @cgrp dead. This prevents further task migration and child - * creation by disabling cgroup_lock_live_group(). + * Mark @cgrp and the associated csets dead. The former prevents + * further task migration and child creation by disabling + * cgroup_lock_live_group(). The latter makes the csets ignored by + * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; + spin_lock_bh(&css_set_lock); + list_for_each_entry(link, &cgrp->cset_links, cset_link) + link->cset->dead = true; + spin_unlock_bh(&css_set_lock); + /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 02a8ea5c9963..11eaf14b52c2 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -57,7 +57,6 @@ #include <asm/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h> -#include <linux/workqueue.h> #include <linux/cgroup.h> #include <linux/wait.h> @@ -286,6 +285,8 @@ static struct cpuset top_cpuset = { static DEFINE_MUTEX(cpuset_mutex); static DEFINE_SPINLOCK(callback_lock); +static struct workqueue_struct *cpuset_migrate_mm_wq; + /* * CPU / memory hotplug is handled asynchronously. */ @@ -971,31 +972,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, } /* - * cpuset_migrate_mm - * - * Migrate memory region from one set of nodes to another. - * - * Temporarilly set tasks mems_allowed to target nodes of migration, - * so that the migration code can allocate pages on these nodes. - * - * While the mm_struct we are migrating is typically from some - * other task, the task_struct mems_allowed that we are hacking - * is for our current task, which must allocate new pages for that - * migrating memory region. + * Migrate memory region from one set of nodes to another. This is + * performed asynchronously as it can be called from process migration path + * holding locks involved in process management. All mm migrations are + * performed in the queued order and can be waited for by flushing + * cpuset_migrate_mm_wq. */ +struct cpuset_migrate_mm_work { + struct work_struct work; + struct mm_struct *mm; + nodemask_t from; + nodemask_t to; +}; + +static void cpuset_migrate_mm_workfn(struct work_struct *work) +{ + struct cpuset_migrate_mm_work *mwork = + container_of(work, struct cpuset_migrate_mm_work, work); + + /* on a wq worker, no need to worry about %current's mems_allowed */ + do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); + mmput(mwork->mm); + kfree(mwork); +} + static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { - struct task_struct *tsk = current; - - tsk->mems_allowed = *to; + struct cpuset_migrate_mm_work *mwork; - do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); + mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); + if (mwork) { + mwork->mm = mm; + mwork->from = *from; + mwork->to = *to; + INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); + queue_work(cpuset_migrate_mm_wq, &mwork->work); + } else { + mmput(mm); + } +} - rcu_read_lock(); - guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed); - rcu_read_unlock(); +static void cpuset_post_attach(void) +{ + flush_workqueue(cpuset_migrate_mm_wq); } /* @@ -1096,7 +1117,8 @@ static void update_tasks_nodemask(struct cpuset *cs) mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); - mmput(mm); + else + mmput(mm); } css_task_iter_end(&it); @@ -1541,11 +1563,11 @@ static void cpuset_attach(struct cgroup_taskset *tset) * @old_mems_allowed is the right nodesets that we * migrate mm from. */ - if (is_memory_migrate(cs)) { + if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); - } - mmput(mm); + else + mmput(mm); } } @@ -1710,6 +1732,7 @@ out_unlock: mutex_unlock(&cpuset_mutex); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); + flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } @@ -2059,6 +2082,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = { .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, + .post_attach = cpuset_post_attach, .bind = cpuset_bind, .legacy_cftypes = files, .early_init = 1, @@ -2355,6 +2379,9 @@ void __init cpuset_init_smp(void) top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); + + cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); + BUG_ON(!cpuset_migrate_mm_wq); } /** diff --git a/kernel/events/core.c b/kernel/events/core.c index cfc227ccfceb..1e889a078dbc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1580,14 +1580,14 @@ event_sched_out(struct perf_event *event, perf_pmu_disable(event->pmu); + event->tstamp_stopped = tstamp; + event->pmu->del(event, 0); + event->oncpu = -1; event->state = PERF_EVENT_STATE_INACTIVE; if (event->pending_disable) { event->pending_disable = 0; event->state = PERF_EVENT_STATE_OFF; } - event->tstamp_stopped = tstamp; - event->pmu->del(event, 0); - event->oncpu = -1; if (!is_software_event(event)) cpuctx->active_oncpu--; @@ -3434,7 +3434,7 @@ find_lively_task_by_vpid(pid_t vpid) /* Reuse ptrace permission checks for now. */ err = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) goto errout; return task; @@ -7979,6 +7979,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, } } + /* symmetric to unaccount_event() in _free_event() */ + account_event(event); + return event; err_per_task: @@ -8342,8 +8345,6 @@ SYSCALL_DEFINE5(perf_event_open, } } - account_event(event); - /* * Special case software events and allow them to be part of * any hardware group. @@ -8582,7 +8583,12 @@ err_context: perf_unpin_context(ctx); put_ctx(ctx); err_alloc: - free_event(event); + /* + * If event_file is set, the fput() above will have called ->release() + * and that will take care of freeing the event. + */ + if (!event_file) + free_event(event); err_cpus: put_online_cpus(); err_task: @@ -8626,8 +8632,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, /* Mark owner so we could distinguish it from user events. */ event->owner = EVENT_OWNER_KERNEL; - account_event(event); - ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); diff --git a/kernel/futex.c b/kernel/futex.c index 684d7549825a..9d8163afd87c 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1244,10 +1244,20 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, if (unlikely(should_fail_futex(true))) ret = -EFAULT; - if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) { ret = -EFAULT; - else if (curval != uval) - ret = -EINVAL; + } else if (curval != uval) { + /* + * If a unconditional UNLOCK_PI operation (user space did not + * try the TID->0 transition) raced with a waiter setting the + * FUTEX_WAITERS flag between get_user() and locking the hash + * bucket lock, retry the operation. + */ + if ((FUTEX_TID_MASK & curval) == uval) + ret = -EAGAIN; + else + ret = -EINVAL; + } if (ret) { raw_spin_unlock(&pi_state->pi_mutex.wait_lock); return ret; @@ -1474,8 +1484,8 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, if (likely(&hb1->chain != &hb2->chain)) { plist_del(&q->list, &hb1->chain); hb_waiters_dec(hb1); - plist_add(&q->list, &hb2->chain); hb_waiters_inc(hb2); + plist_add(&q->list, &hb2->chain); q->lock_ptr = &hb2->lock; } get_futex_key_refs(key2); @@ -2538,6 +2548,15 @@ retry: if (ret == -EFAULT) goto pi_faulted; /* + * A unconditional UNLOCK_PI op raced against a waiter + * setting the FUTEX_WAITERS bit. Try again. + */ + if (ret == -EAGAIN) { + spin_unlock(&hb->lock); + put_futex_key(&key); + goto retry; + } + /* * wake_futex_pi has detected invalid state. Tell user * space. */ @@ -2755,6 +2774,11 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ + free_pi_state(q.pi_state); spin_unlock(q.lock_ptr); } } else { @@ -2881,7 +2905,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid, } ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ)) + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->robust_list; diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 55c8c9349cfe..4ae3232e7a28 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -155,7 +155,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, } ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ)) + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->compat_robust_list; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a302cf9a2126..57bff7857e87 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -138,7 +138,8 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) unsigned int flags = 0, irq = desc->irq_data.irq; struct irqaction *action = desc->action; - do { + /* action might have become NULL since we dropped the lock */ + while (action) { irqreturn_t res; trace_irq_handler_entry(irq, action); @@ -173,7 +174,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) retval |= res; action = action->next; - } while (action); + } add_interrupt_randomness(irq, flags); diff --git a/kernel/kcmp.c b/kernel/kcmp.c index 0aa69ea1d8fd..3a47fa998fe0 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -122,8 +122,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, &task2->signal->cred_guard_mutex); if (ret) goto err; - if (!ptrace_may_access(task1, PTRACE_MODE_READ) || - !ptrace_may_access(task2, PTRACE_MODE_READ)) { + if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) || + !ptrace_may_access(task2, PTRACE_MODE_READ_REALCREDS)) { ret = -EPERM; goto err_unlock; } diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 5b9102a47ea5..c835270f0c2f 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -67,7 +67,13 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) node->locked = 0; node->next = NULL; - prev = xchg_acquire(lock, node); + /* + * We rely on the full barrier with global transitivity implied by the + * below xchg() to order the initialization stores above against any + * observation of @node. And to provide the ACQUIRE ordering associated + * with a LOCK primitive. + */ + prev = xchg(lock, node); if (likely(prev == NULL)) { /* * Lock acquired, don't need to set node->locked to 1. Threads diff --git a/kernel/memremap.c b/kernel/memremap.c index 7658d32c5c78..25ced161ebeb 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -111,7 +111,7 @@ EXPORT_SYMBOL(memunmap); static void devm_memremap_release(struct device *dev, void *res) { - memunmap(res); + memunmap(*(void **)res); } static int devm_memremap_match(struct device *dev, void *res, void *match_data) @@ -133,8 +133,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset, if (addr) { *ptr = addr; devres_add(dev, ptr); - } else + } else { devres_free(ptr); + return ERR_PTR(-ENXIO); + } return addr; } diff --git a/kernel/module.c b/kernel/module.c index 38c7bd5583ff..0e5c71195f18 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -327,6 +327,9 @@ struct load_info { struct _ddebug *debug; unsigned int num_debug; bool sig_ok; +#ifdef CONFIG_KALLSYMS + unsigned long mod_kallsyms_init_off; +#endif struct { unsigned int sym, str, mod, vers, info, pcpu; } index; @@ -2492,10 +2495,21 @@ static void layout_symtab(struct module *mod, struct load_info *info) strsect->sh_flags |= SHF_ALLOC; strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, info->index.str) | INIT_OFFSET_MASK; - mod->init_size = debug_align(mod->init_size); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); + + /* We'll tack temporary mod_kallsyms on the end. */ + mod->init_size = ALIGN(mod->init_size, + __alignof__(struct mod_kallsyms)); + info->mod_kallsyms_init_off = mod->init_size; + mod->init_size += sizeof(struct mod_kallsyms); + mod->init_size = debug_align(mod->init_size); } +/* + * We use the full symtab and strtab which layout_symtab arranged to + * be appended to the init section. Later we switch to the cut-down + * core-only ones. + */ static void add_kallsyms(struct module *mod, const struct load_info *info) { unsigned int i, ndst; @@ -2504,28 +2518,33 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; - mod->symtab = (void *)symsec->sh_addr; - mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + /* Set up to point into init section. */ + mod->kallsyms = mod->module_init + info->mod_kallsyms_init_off; + + mod->kallsyms->symtab = (void *)symsec->sh_addr; + mod->kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ - mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr; + mod->kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr; /* Set types up while we still have access to sections. */ - for (i = 0; i < mod->num_symtab; i++) - mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - - mod->core_symtab = dst = mod->module_core + info->symoffs; - mod->core_strtab = s = mod->module_core + info->stroffs; - src = mod->symtab; - for (ndst = i = 0; i < mod->num_symtab; i++) { + for (i = 0; i < mod->kallsyms->num_symtab; i++) + mod->kallsyms->symtab[i].st_info + = elf_type(&mod->kallsyms->symtab[i], info); + + /* Now populate the cut down core kallsyms for after init. */ + mod->core_kallsyms.symtab = dst = mod->module_core + info->symoffs; + mod->core_kallsyms.strtab = s = mod->module_core + info->stroffs; + src = mod->kallsyms->symtab; + for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) { if (i == 0 || is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { dst[ndst] = src[i]; - dst[ndst++].st_name = s - mod->core_strtab; - s += strlcpy(s, &mod->strtab[src[i].st_name], + dst[ndst++].st_name = s - mod->core_kallsyms.strtab; + s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name], KSYM_NAME_LEN) + 1; } } - mod->core_num_syms = ndst; + mod->core_kallsyms.num_symtab = ndst; } #else static inline void layout_symtab(struct module *mod, struct load_info *info) @@ -3274,9 +3293,8 @@ static noinline int do_init_module(struct module *mod) module_put(mod); trim_init_extable(mod); #ifdef CONFIG_KALLSYMS - mod->num_symtab = mod->core_num_syms; - mod->symtab = mod->core_symtab; - mod->strtab = mod->core_strtab; + /* Switch to core kallsyms now init is done: kallsyms may be walking! */ + rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms); #endif mod_tree_remove_init(mod); unset_module_init_ro_nx(mod); @@ -3515,7 +3533,7 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Module is ready to execute: parsing args may do that. */ after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, - -32768, 32767, NULL, + -32768, 32767, mod, unknown_module_param_cb); if (IS_ERR(after_dashes)) { err = PTR_ERR(after_dashes); @@ -3646,6 +3664,11 @@ static inline int is_arm_mapping_symbol(const char *str) && (str[2] == '\0' || str[2] == '.'); } +static const char *symname(struct mod_kallsyms *kallsyms, unsigned int symnum) +{ + return kallsyms->strtab + kallsyms->symtab[symnum].st_name; +} + static const char *get_ksymbol(struct module *mod, unsigned long addr, unsigned long *size, @@ -3653,6 +3676,7 @@ static const char *get_ksymbol(struct module *mod, { unsigned int i, best = 0; unsigned long nextval; + struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) @@ -3662,32 +3686,32 @@ static const char *get_ksymbol(struct module *mod, /* Scan for closest preceding symbol, and next symbol. (ELF starts real symbols at 1). */ - for (i = 1; i < mod->num_symtab; i++) { - if (mod->symtab[i].st_shndx == SHN_UNDEF) + for (i = 1; i < kallsyms->num_symtab; i++) { + if (kallsyms->symtab[i].st_shndx == SHN_UNDEF) continue; /* We ignore unnamed symbols: they're uninformative * and inserted at a whim. */ - if (mod->symtab[i].st_value <= addr - && mod->symtab[i].st_value > mod->symtab[best].st_value - && *(mod->strtab + mod->symtab[i].st_name) != '\0' - && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + if (*symname(kallsyms, i) == '\0' + || is_arm_mapping_symbol(symname(kallsyms, i))) + continue; + + if (kallsyms->symtab[i].st_value <= addr + && kallsyms->symtab[i].st_value > kallsyms->symtab[best].st_value) best = i; - if (mod->symtab[i].st_value > addr - && mod->symtab[i].st_value < nextval - && *(mod->strtab + mod->symtab[i].st_name) != '\0' - && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) - nextval = mod->symtab[i].st_value; + if (kallsyms->symtab[i].st_value > addr + && kallsyms->symtab[i].st_value < nextval) + nextval = kallsyms->symtab[i].st_value; } if (!best) return NULL; if (size) - *size = nextval - mod->symtab[best].st_value; + *size = nextval - kallsyms->symtab[best].st_value; if (offset) - *offset = addr - mod->symtab[best].st_value; - return mod->strtab + mod->symtab[best].st_name; + *offset = addr - kallsyms->symtab[best].st_value; + return symname(kallsyms, best); } /* For kallsyms to ask for address resolution. NULL means not found. Careful @@ -3777,19 +3801,21 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + struct mod_kallsyms *kallsyms; + if (mod->state == MODULE_STATE_UNFORMED) continue; - if (symnum < mod->num_symtab) { - *value = mod->symtab[symnum].st_value; - *type = mod->symtab[symnum].st_info; - strlcpy(name, mod->strtab + mod->symtab[symnum].st_name, - KSYM_NAME_LEN); + kallsyms = rcu_dereference_sched(mod->kallsyms); + if (symnum < kallsyms->num_symtab) { + *value = kallsyms->symtab[symnum].st_value; + *type = kallsyms->symtab[symnum].st_info; + strlcpy(name, symname(kallsyms, symnum), KSYM_NAME_LEN); strlcpy(module_name, mod->name, MODULE_NAME_LEN); *exported = is_exported(name, *value, mod); preempt_enable(); return 0; } - symnum -= mod->num_symtab; + symnum -= kallsyms->num_symtab; } preempt_enable(); return -ERANGE; @@ -3798,11 +3824,12 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, static unsigned long mod_find_symname(struct module *mod, const char *name) { unsigned int i; + struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); - for (i = 0; i < mod->num_symtab; i++) - if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 && - mod->symtab[i].st_info != 'U') - return mod->symtab[i].st_value; + for (i = 0; i < kallsyms->num_symtab; i++) + if (strcmp(name, symname(kallsyms, i)) == 0 && + kallsyms->symtab[i].st_info != 'U') + return kallsyms->symtab[i].st_value; return 0; } @@ -3841,11 +3868,14 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, module_assert_mutex(); list_for_each_entry(mod, &modules, list) { + /* We hold module_mutex: no need for rcu_dereference_sched */ + struct mod_kallsyms *kallsyms = mod->kallsyms; + if (mod->state == MODULE_STATE_UNFORMED) continue; - for (i = 0; i < mod->num_symtab; i++) { - ret = fn(data, mod->strtab + mod->symtab[i].st_name, - mod, mod->symtab[i].st_value); + for (i = 0; i < kallsyms->num_symtab; i++) { + ret = fn(data, symname(kallsyms, i), + mod, kallsyms->symtab[i].st_value); if (ret != 0) return ret; } diff --git a/kernel/panic.c b/kernel/panic.c index f07bfc9fe613..223564d3e1f8 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -160,8 +160,7 @@ void panic(const char *fmt, ...) * panic() is not being callled from OOPS. */ debug_locks_off(); - console_trylock(); - console_unlock(); + console_flush_on_panic(); if (!panic_blink) panic_blink = no_blink; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index b7342a24f559..b7dd5718836e 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -339,6 +339,7 @@ int hibernation_snapshot(int platform_mode) pm_message_t msg; int error; + pm_suspend_clear_flags(); error = platform_begin(platform_mode); if (error) goto Close; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 28fb44dccbad..e7e586bb2022 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2241,13 +2241,24 @@ void console_unlock(void) static u64 seen_seq; unsigned long flags; bool wake_klogd = false; - bool retry; + bool do_cond_resched, retry; if (console_suspended) { up_console_sem(); return; } + /* + * Console drivers are called under logbuf_lock, so + * @console_may_schedule should be cleared before; however, we may + * end up dumping a lot of lines, for example, if called from + * console registration path, and should invoke cond_resched() + * between lines if allowable. Not doing so can cause a very long + * scheduling stall on a slow console leading to RCU stall and + * softlockup warnings which exacerbate the issue with more + * messages practically incapacitating the system. + */ + do_cond_resched = console_may_schedule; console_may_schedule = 0; /* flush buffered message fragment immediately to console */ @@ -2319,6 +2330,9 @@ skip: call_console_drivers(level, ext_text, ext_len, text, len); start_critical_timings(); local_irq_restore(flags); + + if (do_cond_resched) + cond_resched(); } console_locked = 0; @@ -2386,6 +2400,25 @@ void console_unblank(void) console_unlock(); } +/** + * console_flush_on_panic - flush console content on panic + * + * Immediately output all pending messages no matter what. + */ +void console_flush_on_panic(void) +{ + /* + * If someone else is holding the console lock, trylock will fail + * and may_schedule may be set. Ignore and proceed to unlock so + * that messages are flushed out. As this can be called from any + * context and we don't want to get preempted while flushing, + * ensure may_schedule is cleared. + */ + console_trylock(); + console_may_schedule = 0; + console_unlock(); +} + /* * Return the console tty driver structure and its associated index */ diff --git a/kernel/ptrace.c b/kernel/ptrace.c index b760bae64cf1..3189e51db7e8 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -219,6 +219,14 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; + int dumpable = 0; + kuid_t caller_uid; + kgid_t caller_gid; + + if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { + WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); + return -EPERM; + } /* May we inspect the given task? * This check is used both for attaching with ptrace @@ -228,18 +236,33 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ - int dumpable = 0; + /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); + if (mode & PTRACE_MODE_FSCREDS) { + caller_uid = cred->fsuid; + caller_gid = cred->fsgid; + } else { + /* + * Using the euid would make more sense here, but something + * in userland might rely on the old behavior, and this + * shouldn't be a security problem since + * PTRACE_MODE_REALCREDS implies that the caller explicitly + * used a syscall that requests access to another process + * (and not a filesystem syscall to procfs). + */ + caller_uid = cred->uid; + caller_gid = cred->gid; + } tcred = __task_cred(task); - if (uid_eq(cred->uid, tcred->euid) && - uid_eq(cred->uid, tcred->suid) && - uid_eq(cred->uid, tcred->uid) && - gid_eq(cred->gid, tcred->egid) && - gid_eq(cred->gid, tcred->sgid) && - gid_eq(cred->gid, tcred->gid)) + if (uid_eq(caller_uid, tcred->euid) && + uid_eq(caller_uid, tcred->suid) && + uid_eq(caller_uid, tcred->uid) && + gid_eq(caller_gid, tcred->egid) && + gid_eq(caller_gid, tcred->sgid) && + gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; @@ -306,7 +329,7 @@ static int ptrace_attach(struct task_struct *task, long request, goto out; task_lock(task); - retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH); + retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); task_unlock(task); if (retval) goto unlock_creds; diff --git a/kernel/resource.c b/kernel/resource.c index f150dbbe6f62..249b1eb1e6e1 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1083,9 +1083,10 @@ struct resource * __request_region(struct resource *parent, if (!conflict) break; if (conflict != parent) { - parent = conflict; - if (!(conflict->flags & IORESOURCE_BUSY)) + if (!(conflict->flags & IORESOURCE_BUSY)) { + parent = conflict; continue; + } } if (conflict->flags & flags & IORESOURCE_MUXED) { add_wait_queue(&muxed_resource_wait, &wait); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 61b0914cc7aa..ff6b870315b7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5525,6 +5525,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_UP_PREPARE: rq->calc_load_update = calc_load_update; + account_reset_rq(rq); break; case CPU_ONLINE: @@ -6738,7 +6739,7 @@ static void sched_init_numa(void) sched_domains_numa_masks[i][j] = mask; - for (k = 0; k < nr_node_ids; k++) { + for_each_node(k) { if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; @@ -7702,7 +7703,7 @@ void set_curr_task(int cpu, struct task_struct *p) /* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); -static void free_sched_group(struct task_group *tg) +static void sched_free_group(struct task_group *tg) { free_fair_sched_group(tg); free_rt_sched_group(tg); @@ -7728,7 +7729,7 @@ struct task_group *sched_create_group(struct task_group *parent) return tg; err: - free_sched_group(tg); + sched_free_group(tg); return ERR_PTR(-ENOMEM); } @@ -7748,17 +7749,16 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) } /* rcu callback to free various structures associated with a task group */ -static void free_sched_group_rcu(struct rcu_head *rhp) +static void sched_free_group_rcu(struct rcu_head *rhp) { /* now it should be safe to free those cfs_rqs */ - free_sched_group(container_of(rhp, struct task_group, rcu)); + sched_free_group(container_of(rhp, struct task_group, rcu)); } -/* Destroy runqueue etc associated with a task group */ void sched_destroy_group(struct task_group *tg) { /* wait for possible concurrent references to cfs_rqs complete */ - call_rcu(&tg->rcu, free_sched_group_rcu); + call_rcu(&tg->rcu, sched_free_group_rcu); } void sched_offline_group(struct task_group *tg) @@ -8219,31 +8219,26 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); + sched_online_group(tg, parent); + return &tg->css; } -static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); - struct task_group *parent = css_tg(css->parent); - if (parent) - sched_online_group(tg, parent); - return 0; + sched_offline_group(tg); } static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); - sched_destroy_group(tg); -} - -static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) -{ - struct task_group *tg = css_tg(css); - - sched_offline_group(tg); + /* + * Relies on the RCU grace period between css_released() and this. + */ + sched_free_group(tg); } static void cpu_cgroup_fork(struct task_struct *task, void *private) @@ -8603,9 +8598,8 @@ static struct cftype cpu_files[] = { struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, + .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, - .css_online = cpu_cgroup_css_online, - .css_offline = cpu_cgroup_css_offline, .fork = cpu_cgroup_fork, .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 05de80b48586..f74ea89e77a8 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -259,21 +259,21 @@ static __always_inline bool steal_account_process_tick(void) #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { u64 steal; - cputime_t steal_ct; + unsigned long steal_jiffies; steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; /* - * cputime_t may be less precise than nsecs (eg: if it's - * based on jiffies). Lets cast the result to cputime + * steal is in nsecs but our caller is expecting steal + * time in jiffies. Lets cast the result to jiffies * granularity and account the rest on the next rounds. */ - steal_ct = nsecs_to_cputime(steal); - this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); + steal_jiffies = nsecs_to_jiffies(steal); + this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies); - account_steal_time(steal_ct); - return steal_ct; + account_steal_time(jiffies_to_cputime(steal_jiffies)); + return steal_jiffies; } #endif return false; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b242775bf670..0517abd7dd73 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1770,3 +1770,16 @@ static inline u64 irq_time_read(int cpu) } #endif /* CONFIG_64BIT */ #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +static inline void account_reset_rq(struct rq *rq) +{ +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + rq->prev_irq_time = 0; +#endif +#ifdef CONFIG_PARAVIRT + rq->prev_steal_time = 0; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + rq->prev_steal_time_rq = 0; +#endif +} diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 580ac2d4024f..15a1795bbba1 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -316,24 +316,24 @@ static inline void seccomp_sync_threads(void) put_seccomp_filter(thread); smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); + + /* + * Don't let an unprivileged task work around + * the no_new_privs restriction by creating + * a thread that sets it up, enters seccomp, + * then dies. + */ + if (task_no_new_privs(caller)) + task_set_no_new_privs(thread); + /* * Opt the other thread into seccomp if needed. * As threads are considered to be trust-realm * equivalent (see ptrace_may_access), it is safe to * allow one thread to transition the other. */ - if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) { - /* - * Don't let an unprivileged task work around - * the no_new_privs restriction by creating - * a thread that sets it up, enters seccomp, - * then dies. - */ - if (task_no_new_privs(caller)) - task_set_no_new_privs(thread); - + if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) seccomp_assign_mode(thread, SECCOMP_MODE_FILTER); - } } } diff --git a/kernel/sys.c b/kernel/sys.c index 11333311cf1c..b5a8e844a968 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1855,11 +1855,13 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } - if (prctl_map.exe_fd != (u32)-1) + if (prctl_map.exe_fd != (u32)-1) { error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); - down_read(&mm->mmap_sem); - if (error) - goto out; + if (error) + return error; + } + + down_write(&mm->mmap_sem); /* * We don't validate if these members are pointing to @@ -1896,10 +1898,8 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); - error = 0; -out: - up_read(&mm->mmap_sem); - return error; + up_write(&mm->mmap_sem); + return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ @@ -1965,7 +1965,7 @@ static int prctl_set_mm(int opt, unsigned long addr, error = -EINVAL; - down_read(&mm->mmap_sem); + down_write(&mm->mmap_sem); vma = find_vma(mm, addr); prctl_map.start_code = mm->start_code; @@ -2058,7 +2058,7 @@ static int prctl_set_mm(int opt, unsigned long addr, error = 0; out: - up_read(&mm->mmap_sem); + up_write(&mm->mmap_sem); return error; } diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 7e7746a42a62..10a1d7dc9313 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1321,7 +1321,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, } mnt = task_active_pid_ns(current)->proc_mnt; - file = file_open_root(mnt->mnt_root, mnt, pathname, flags); + file = file_open_root(mnt->mnt_root, mnt, pathname, flags, 0); result = PTR_ERR(file); if (IS_ERR(file)) goto out_putname; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 435b8850dd80..fa909f9fd559 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -897,10 +897,10 @@ static int enqueue_hrtimer(struct hrtimer *timer, */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, - unsigned long newstate, int reprogram) + u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; - unsigned int state = timer->state; + u8 state = timer->state; timer->state = newstate; if (!(state & HRTIMER_STATE_ENQUEUED)) @@ -930,7 +930,7 @@ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { if (hrtimer_is_queued(timer)) { - unsigned long state = timer->state; + u8 state = timer->state; int reprogram; /* @@ -954,6 +954,22 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest return 0; } +static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, + const enum hrtimer_mode mode) +{ +#ifdef CONFIG_TIME_LOW_RES + /* + * CONFIG_TIME_LOW_RES indicates that the system has no way to return + * granular time values. For relative timers we add hrtimer_resolution + * (i.e. one jiffie) to prevent short timeouts. + */ + timer->is_rel = mode & HRTIMER_MODE_REL; + if (timer->is_rel) + tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); +#endif + return tim; +} + /** * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU * @timer: the timer to be added @@ -974,19 +990,10 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* Remove an active timer from the queue: */ remove_hrtimer(timer, base, true); - if (mode & HRTIMER_MODE_REL) { + if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); - /* - * CONFIG_TIME_LOW_RES is a temporary way for architectures - * to signal that they simply return xtime in - * do_gettimeoffset(). In this case we want to round up by - * resolution when starting a relative timer, to avoid short - * timeouts. This will go away with the GTOD framework. - */ -#ifdef CONFIG_TIME_LOW_RES - tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); -#endif - } + + tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); @@ -1074,19 +1081,23 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read + * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ -ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); - rem = hrtimer_expires_remaining(timer); + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) + rem = hrtimer_expires_remaining_adjusted(timer); + else + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } -EXPORT_SYMBOL_GPL(hrtimer_get_remaining); +EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** @@ -1220,6 +1231,14 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, fn = timer->function; /* + * Clear the 'is relative' flag for the TIME_LOW_RES case. If the + * timer is restarted with a period then it becomes an absolute + * timer. If its not restarted it does not matter. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES)) + timer->is_rel = false; + + /* * Because we run timers from hardirq context, there is no chance * they get migrated to another cpu, therefore its safe to unlock * the timer base. diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 8d262b467573..1d5c7204ddc9 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -26,7 +26,7 @@ */ static struct timeval itimer_get_remtime(struct hrtimer *timer) { - ktime_t rem = hrtimer_get_remaining(timer); + ktime_t rem = __hrtimer_get_remaining(timer, true); /* * Racy but safe: if the itimer expires after the above diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index ce033c7aa2e8..9cff0ab82b63 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -69,10 +69,10 @@ static ssize_t posix_clock_read(struct file *fp, char __user *buf, static unsigned int posix_clock_poll(struct file *fp, poll_table *wait) { struct posix_clock *clk = get_posix_clock(fp); - int result = 0; + unsigned int result = 0; if (!clk) - return -ENODEV; + return POLLERR; if (clk->ops.poll) result = clk->ops.poll(clk, fp, wait); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 31d11ac9fa47..f2826c35e918 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -760,7 +760,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(hrtimer_get_expires(timer), now); + remaining = __hrtimer_expires_remaining_adjusted(timer, now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 7c7ec4515983..22c57e191a23 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -977,9 +977,9 @@ static void tick_nohz_switch_to_nohz(void) /* Get the next period */ next = tick_init_jiffy_update(); - hrtimer_forward_now(&ts->sched_timer, tick_period); hrtimer_set_expires(&ts->sched_timer, next); - tick_program_event(next, 1); + hrtimer_forward_now(&ts->sched_timer, tick_period); + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index d563c1960302..99188ee5d9d0 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -305,8 +305,7 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) delta = timekeeping_get_delta(tkr); - nsec = delta * tkr->mult + tkr->xtime_nsec; - nsec >>= tkr->shift; + nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift; /* If arch requires, add in get_arch_timeoffset() */ return nsec + arch_gettimeoffset(); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index f75e35b60149..ba7d8b288bb3 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -69,7 +69,7 @@ print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, print_name_offset(m, taddr); SEQ_printf(m, ", "); print_name_offset(m, timer->function); - SEQ_printf(m, ", S:%02lx", timer->state); + SEQ_printf(m, ", S:%02x", timer->state); #ifdef CONFIG_TIMER_STATS SEQ_printf(m, ", "); print_name_offset(m, timer->start_site); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5f375d4c05fb..dd4d86ae8e21 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1771,7 +1771,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 6, pc, regs); + ftrace_trace_stack(tr, buffer, flags, 0, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); @@ -5038,7 +5038,10 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, spd.nr_pages = i; - ret = splice_to_pipe(pipe, &spd); + if (i) + ret = splice_to_pipe(pipe, &spd); + else + ret = 0; out: splice_shrink_spd(&spd); return ret; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4f6ef6912e00..996f0fd34312 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name) struct ftrace_event_field *field; struct list_head *head; - field = __find_event_field(&ftrace_generic_fields, name); + head = trace_get_fields(call); + field = __find_event_field(head, name); if (field) return field; - field = __find_event_field(&ftrace_common_fields, name); + field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; - head = trace_get_fields(call); - return __find_event_field(head, name); + return __find_event_field(&ftrace_common_fields, name); } static int __trace_define_field(struct list_head *head, const char *type, @@ -171,8 +171,10 @@ static int trace_define_generic_fields(void) { int ret; - __generic_field(int, cpu, FILTER_OTHER); - __generic_field(char *, comm, FILTER_PTR_STRING); + __generic_field(int, CPU, FILTER_CPU); + __generic_field(int, cpu, FILTER_CPU); + __generic_field(char *, COMM, FILTER_COMM); + __generic_field(char *, comm, FILTER_COMM); return ret; } @@ -869,7 +871,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ - if (call->class && call->class->reg) + if (call->class && call->class->reg && + !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) return file; } @@ -2104,8 +2107,13 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) trace_create_file("filter", 0644, file->dir, file, &ftrace_event_filter_fops); - trace_create_file("trigger", 0644, file->dir, file, - &event_trigger_fops); + /* + * Only event directories that can be enabled should have + * triggers. + */ + if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) + trace_create_file("trigger", 0644, file->dir, file, + &event_trigger_fops); trace_create_file("format", 0444, file->dir, call, &ftrace_event_format_fops); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index f93a219b18da..6816302542b2 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps, return -EINVAL; } - if (is_string_field(field)) { + if (field->filter_type == FILTER_COMM) { + filter_build_regex(pred); + fn = filter_pred_comm; + pred->regex.field_len = TASK_COMM_LEN; + } else if (is_string_field(field)) { filter_build_regex(pred); - if (!strcmp(field->name, "comm")) { - fn = filter_pred_comm; - pred->regex.field_len = TASK_COMM_LEN; - } else if (field->filter_type == FILTER_STATIC_STRING) { + if (field->filter_type == FILTER_STATIC_STRING) { fn = filter_pred_string; pred->regex.field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) @@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps, } pred->val = val; - if (!strcmp(field->name, "cpu")) + if (field->filter_type == FILTER_CPU) fn = filter_pred_cpu; else fn = select_comparison_fn(pred->op, field->size, diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index e4e56589ec1d..be3222b7d72e 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -109,8 +109,12 @@ static int func_prolog_dec(struct trace_array *tr, return 0; local_save_flags(*flags); - /* slight chance to get a false positive on tracing_cpu */ - if (!irqs_disabled_flags(*flags)) + /* + * Slight chance to get a false positive on tracing_cpu, + * although I'm starting to think there isn't a chance. + * Leave this for now just to be paranoid. + */ + if (!irqs_disabled_flags(*flags) && !preempt_count()) return 0; *data = per_cpu_ptr(tr->trace_buffer.data, cpu); diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 060df67dbdd1..f96f0383f6c6 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -296,6 +296,9 @@ static int t_show(struct seq_file *m, void *v) const char *str = *fmt; int i; + if (!*fmt) + return 0; + seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt); /* diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index dda9e6742950..202df6cffcca 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -126,6 +126,13 @@ check_stack(unsigned long ip, unsigned long *stack) } /* + * Some archs may not have the passed in ip in the dump. + * If that happens, we need to show everything. + */ + if (i == stack_trace_max.nr_entries) + i = 0; + + /* * Now find where in the stack these are. */ x = 0; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index e864906af3fc..1f1b05f5a94b 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -1020,6 +1020,9 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, * both lockup detectors are disabled if proc_watchdog_update() * returns an error. */ + if (old == new) + goto out; + err = proc_watchdog_update(); } out: @@ -1064,7 +1067,7 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old; + int err, old, new; get_online_cpus(); mutex_lock(&watchdog_proc_mutex); @@ -1084,6 +1087,10 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, /* * Update the sample period. Restore on failure. */ + new = ACCESS_ONCE(watchdog_thresh); + if (old == new) + goto out; + set_sample_period(); err = proc_watchdog_update(); if (err) { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c579dbab2e36..0ec05948a97b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -568,6 +568,16 @@ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, int node) { assert_rcu_or_wq_mutex_or_pool_mutex(wq); + + /* + * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a + * delayed item is pending. The plan is to keep CPU -> NODE + * mapping valid and stable across CPU on/offlines. Once that + * happens, this workaround can be removed. + */ + if (unlikely(node == NUMA_NO_NODE)) + return wq->dfl_pwq; + return rcu_dereference_raw(wq->numa_pwq_tbl[node]); } @@ -639,6 +649,35 @@ static void set_work_pool_and_clear_pending(struct work_struct *work, */ smp_wmb(); set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); + /* + * The following mb guarantees that previous clear of a PENDING bit + * will not be reordered with any speculative LOADS or STORES from + * work->current_func, which is executed afterwards. This possible + * reordering can lead to a missed execution on attempt to qeueue + * the same @work. E.g. consider this case: + * + * CPU#0 CPU#1 + * ---------------------------- -------------------------------- + * + * 1 STORE event_indicated + * 2 queue_work_on() { + * 3 test_and_set_bit(PENDING) + * 4 } set_..._and_clear_pending() { + * 5 set_work_data() # clear bit + * 6 smp_mb() + * 7 work->current_func() { + * 8 LOAD event_indicated + * } + * + * Without an explicit full barrier speculative LOAD on line 8 can + * be executed before CPU#0 does STORE on line 1. If that happens, + * CPU#0 observes the PENDING bit is still set and new execution of + * a @work is not queued in a hope, that CPU#1 will eventually + * finish the queued @work. Meanwhile CPU#1 does not see + * event_indicated is set, because speculative LOAD was executed + * before actual STORE. + */ + smp_mb(); } static void clear_work_data(struct work_struct *work) @@ -1458,13 +1497,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); dwork->wq = wq; - /* timer isn't guaranteed to run in this cpu, record earlier */ - if (cpu == WORK_CPU_UNBOUND) - cpu = raw_smp_processor_id(); dwork->cpu = cpu; timer->expires = jiffies + delay; - add_timer_on(timer, cpu); + if (unlikely(cpu != WORK_CPU_UNBOUND)) + add_timer_on(timer, cpu); + else + add_timer(timer); } /** diff --git a/lib/Kconfig b/lib/Kconfig index f0df318104e7..1a48744253d7 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -210,9 +210,11 @@ config RANDOM32_SELFTEST # compression support is select'ed if needed # config 842_COMPRESS + select CRC32 tristate config 842_DECOMPRESS + select CRC32 tristate config ZLIB_INFLATE diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 03dd576e6773..59fd7c0b119c 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -524,7 +524,9 @@ static bool assoc_array_insert_into_terminal_node(struct assoc_array_edit *edit, free_slot = i; continue; } - if (ops->compare_object(assoc_array_ptr_to_leaf(ptr), index_key)) { + if (assoc_array_ptr_is_leaf(ptr) && + ops->compare_object(assoc_array_ptr_to_leaf(ptr), + index_key)) { pr_devel("replace in slot %d\n", i); edit->leaf_p = &node->slots[i]; edit->dead_leaf = node->slots[i]; diff --git a/lib/dma-debug.c b/lib/dma-debug.c index d34bd24c2c84..4a1515f4b452 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1181,7 +1181,7 @@ static inline bool overlap(void *addr, unsigned long len, void *start, void *end static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len) { - if (overlap(addr, len, _text, _etext) || + if (overlap(addr, len, _stext, _etext) || overlap(addr, len, __start_rodata, __end_rodata)) err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); } diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 6745c6230db3..c30d07e99dba 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -25,6 +25,7 @@ static atomic_t dump_lock = ATOMIC_INIT(-1); asmlinkage __visible void dump_stack(void) { + unsigned long flags; int was_locked; int old; int cpu; @@ -33,9 +34,8 @@ asmlinkage __visible void dump_stack(void) * Permit this cpu to perform nested stack dumps while serialising * against other CPUs */ - preempt_disable(); - retry: + local_irq_save(flags); cpu = smp_processor_id(); old = atomic_cmpxchg(&dump_lock, -1, cpu); if (old == -1) { @@ -43,6 +43,7 @@ retry: } else if (old == cpu) { was_locked = 1; } else { + local_irq_restore(flags); cpu_relax(); goto retry; } @@ -52,7 +53,7 @@ retry: if (!was_locked) atomic_set(&dump_lock, -1); - preempt_enable(); + local_irq_restore(flags); } #else asmlinkage __visible void dump_stack(void) diff --git a/lib/klist.c b/lib/klist.c index d74cf7a29afd..0507fa5d84c5 100644 --- a/lib/klist.c +++ b/lib/klist.c @@ -282,9 +282,9 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n) { i->i_klist = k; - i->i_cur = n; - if (n) - kref_get(&n->n_ref); + i->i_cur = NULL; + if (n && kref_get_unless_zero(&n->n_ref)) + i->i_cur = n; } EXPORT_SYMBOL_GPL(klist_iter_init_node); diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c index 6a08ce7d6adc..acf9da449f81 100644 --- a/lib/libcrc32c.c +++ b/lib/libcrc32c.c @@ -74,3 +74,4 @@ module_exit(libcrc32c_mod_fini); MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>"); MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: crc32c"); diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index abcecdc2d0f2..0710a62ad2f6 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -11,8 +11,7 @@ /* * Detects 64 bits mode */ -#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) \ - || defined(__ppc64__) || defined(__LP64__)) +#if defined(CONFIG_64BIT) #define LZ4_ARCH64 1 #else #define LZ4_ARCH64 0 @@ -35,6 +34,10 @@ typedef struct _U64_S { u64 v; } U64_S; #define PUT4(s, d) (A32(d) = A32(s)) #define PUT8(s, d) (A64(d) = A64(s)) + +#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \ + (d = s - A16(p)) + #define LZ4_WRITE_LITTLEENDIAN_16(p, v) \ do { \ A16(p) = v; \ @@ -51,10 +54,13 @@ typedef struct _U64_S { u64 v; } U64_S; #define PUT8(s, d) \ put_unaligned(get_unaligned((const u64 *) s), (u64 *) d) -#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \ - do { \ - put_unaligned(v, (u16 *)(p)); \ - p += 2; \ +#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \ + (d = s - get_unaligned_le16(p)) + +#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \ + do { \ + put_unaligned_le16(v, (u16 *)(p)); \ + p += 2; \ } while (0) #endif @@ -140,9 +146,6 @@ typedef struct _U64_S { u64 v; } U64_S; #endif -#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \ - (d = s - get_unaligned_le16(p)) - #define LZ4_WILDCOPY(s, d, e) \ do { \ LZ4_COPYPACKET(s, d); \ diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c index 3db76b8c1115..e00ff00e861c 100644 --- a/lib/mpi/mpicoder.c +++ b/lib/mpi/mpicoder.c @@ -128,6 +128,23 @@ leave: } EXPORT_SYMBOL_GPL(mpi_read_from_buffer); +static int count_lzeros(MPI a) +{ + mpi_limb_t alimb; + int i, lzeros = 0; + + for (i = a->nlimbs - 1; i >= 0; i--) { + alimb = a->d[i]; + if (alimb == 0) { + lzeros += sizeof(mpi_limb_t); + } else { + lzeros += count_leading_zeros(alimb) / 8; + break; + } + } + return lzeros; +} + /** * mpi_read_buffer() - read MPI to a bufer provided by user (msb first) * @@ -146,7 +163,7 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, uint8_t *p; mpi_limb_t alimb; unsigned int n = mpi_get_size(a); - int i, lzeros = 0; + int i, lzeros; if (buf_len < n || !buf || !nbytes) return -EINVAL; @@ -154,14 +171,7 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, if (sign) *sign = a->sign; - p = (void *)&a->d[a->nlimbs] - 1; - - for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) { - if (!*p) - lzeros++; - else - break; - } + lzeros = count_lzeros(a); p = buf; *nbytes = n - lzeros; @@ -343,7 +353,7 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes, u8 *p, *p2; mpi_limb_t alimb, alimb2; unsigned int n = mpi_get_size(a); - int i, x, y = 0, lzeros = 0, buf_len; + int i, x, y = 0, lzeros, buf_len; if (!nbytes || *nbytes < n) return -EINVAL; @@ -351,14 +361,7 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes, if (sign) *sign = a->sign; - p = (void *)&a->d[a->nlimbs] - 1; - - for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) { - if (!*p) - lzeros++; - else - break; - } + lzeros = count_lzeros(a); *nbytes = n - lzeros; buf_len = sgl->length; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index fcf5d98574ce..6b79e9026e24 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } @@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 5939f63d90cd..5c88204b6f1f 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -43,50 +43,73 @@ void string_get_size(u64 size, u64 blk_size, const enum string_size_units units, [STRING_UNITS_10] = 1000, [STRING_UNITS_2] = 1024, }; - int i, j; - u32 remainder = 0, sf_cap, exp; + static const unsigned int rounding[] = { 500, 50, 5 }; + int i = 0, j; + u32 remainder = 0, sf_cap; char tmp[8]; const char *unit; tmp[0] = '\0'; - i = 0; - if (!size) + + if (blk_size == 0) + size = 0; + if (size == 0) goto out; - while (blk_size >= divisor[units]) { - remainder = do_div(blk_size, divisor[units]); + /* This is Napier's algorithm. Reduce the original block size to + * + * coefficient * divisor[units]^i + * + * we do the reduction so both coefficients are just under 32 bits so + * that multiplying them together won't overflow 64 bits and we keep + * as much precision as possible in the numbers. + * + * Note: it's safe to throw away the remainders here because all the + * precision is in the coefficients. + */ + while (blk_size >> 32) { + do_div(blk_size, divisor[units]); i++; } - exp = divisor[units] / (u32)blk_size; - /* - * size must be strictly greater than exp here to ensure that remainder - * is greater than divisor[units] coming out of the if below. - */ - if (size > exp) { - remainder = do_div(size, divisor[units]); - remainder *= blk_size; + while (size >> 32) { + do_div(size, divisor[units]); i++; - } else { - remainder *= size; } + /* now perform the actual multiplication keeping i as the sum of the + * two logarithms */ size *= blk_size; - size += remainder / divisor[units]; - remainder %= divisor[units]; + /* and logarithmically reduce it until it's just under the divisor */ while (size >= divisor[units]) { remainder = do_div(size, divisor[units]); i++; } + /* work out in j how many digits of precision we need from the + * remainder */ sf_cap = size; for (j = 0; sf_cap*10 < 1000; j++) sf_cap *= 10; - if (j) { + if (units == STRING_UNITS_2) { + /* express the remainder as a decimal. It's currently the + * numerator of a fraction whose denominator is + * divisor[units], which is 1 << 10 for STRING_UNITS_2 */ remainder *= 1000; - remainder /= divisor[units]; + remainder >>= 10; + } + + /* add a 5 to the digit below what will be printed to ensure + * an arithmetical round up and carry it through to size */ + remainder += rounding[j]; + if (remainder >= 1000) { + remainder -= 1000; + size += 1; + } + + if (j) { snprintf(tmp, sizeof(tmp), ".%03u", remainder); tmp[j+1] = '\0'; } diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c index 98866a770770..25b5cbfb7615 100644 --- a/lib/test-string_helpers.c +++ b/lib/test-string_helpers.c @@ -327,36 +327,67 @@ out: } #define string_get_size_maxbuf 16 -#define test_string_get_size_one(size, blk_size, units, exp_result) \ +#define test_string_get_size_one(size, blk_size, exp_result10, exp_result2) \ do { \ - BUILD_BUG_ON(sizeof(exp_result) >= string_get_size_maxbuf); \ - __test_string_get_size((size), (blk_size), (units), \ - (exp_result)); \ + BUILD_BUG_ON(sizeof(exp_result10) >= string_get_size_maxbuf); \ + BUILD_BUG_ON(sizeof(exp_result2) >= string_get_size_maxbuf); \ + __test_string_get_size((size), (blk_size), (exp_result10), \ + (exp_result2)); \ } while (0) -static __init void __test_string_get_size(const u64 size, const u64 blk_size, - const enum string_size_units units, - const char *exp_result) +static __init void test_string_get_size_check(const char *units, + const char *exp, + char *res, + const u64 size, + const u64 blk_size) { - char buf[string_get_size_maxbuf]; - - string_get_size(size, blk_size, units, buf, sizeof(buf)); - if (!memcmp(buf, exp_result, strlen(exp_result) + 1)) + if (!memcmp(res, exp, strlen(exp) + 1)) return; - buf[sizeof(buf) - 1] = '\0'; - pr_warn("Test 'test_string_get_size_one' failed!\n"); - pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %d\n", + res[string_get_size_maxbuf - 1] = '\0'; + + pr_warn("Test 'test_string_get_size' failed!\n"); + pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %s)\n", size, blk_size, units); - pr_warn("expected: '%s', got '%s'\n", exp_result, buf); + pr_warn("expected: '%s', got '%s'\n", exp, res); +} + +static __init void __test_string_get_size(const u64 size, const u64 blk_size, + const char *exp_result10, + const char *exp_result2) +{ + char buf10[string_get_size_maxbuf]; + char buf2[string_get_size_maxbuf]; + + string_get_size(size, blk_size, STRING_UNITS_10, buf10, sizeof(buf10)); + string_get_size(size, blk_size, STRING_UNITS_2, buf2, sizeof(buf2)); + + test_string_get_size_check("STRING_UNITS_10", exp_result10, buf10, + size, blk_size); + + test_string_get_size_check("STRING_UNITS_2", exp_result2, buf2, + size, blk_size); } static __init void test_string_get_size(void) { - test_string_get_size_one(16384, 512, STRING_UNITS_2, "8.00 MiB"); - test_string_get_size_one(8192, 4096, STRING_UNITS_10, "32.7 MB"); - test_string_get_size_one(1, 512, STRING_UNITS_10, "512 B"); + /* small values */ + test_string_get_size_one(0, 512, "0 B", "0 B"); + test_string_get_size_one(1, 512, "512 B", "512 B"); + test_string_get_size_one(1100, 1, "1.10 kB", "1.07 KiB"); + + /* normal values */ + test_string_get_size_one(16384, 512, "8.39 MB", "8.00 MiB"); + test_string_get_size_one(500118192, 512, "256 GB", "238 GiB"); + test_string_get_size_one(8192, 4096, "33.6 MB", "32.0 MiB"); + + /* weird block sizes */ + test_string_get_size_one(3000, 1900, "5.70 MB", "5.44 MiB"); + + /* huge values */ + test_string_get_size_one(U64_MAX, 4096, "75.6 ZB", "64.0 ZiB"); + test_string_get_size_one(4096, U64_MAX, "75.6 ZB", "64.0 ZiB"); } static int __init test_string_helpers_init(void) diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c index 6f500ef2301d..f0b323abb4c6 100644 --- a/lib/ucs2_string.c +++ b/lib/ucs2_string.c @@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len) } } EXPORT_SYMBOL(ucs2_strncmp); + +unsigned long +ucs2_utf8size(const ucs2_char_t *src) +{ + unsigned long i; + unsigned long j = 0; + + for (i = 0; i < ucs2_strlen(src); i++) { + u16 c = src[i]; + + if (c >= 0x800) + j += 3; + else if (c >= 0x80) + j += 2; + else + j += 1; + } + + return j; +} +EXPORT_SYMBOL(ucs2_utf8size); + +/* + * copy at most maxlength bytes of whole utf8 characters to dest from the + * ucs2 string src. + * + * The return value is the number of characters copied, not including the + * final NUL character. + */ +unsigned long +ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength) +{ + unsigned int i; + unsigned long j = 0; + unsigned long limit = ucs2_strnlen(src, maxlength); + + for (i = 0; maxlength && i < limit; i++) { + u16 c = src[i]; + + if (c >= 0x800) { + if (maxlength < 3) + break; + maxlength -= 3; + dest[j++] = 0xe0 | (c & 0xf000) >> 12; + dest[j++] = 0x80 | (c & 0x0fc0) >> 6; + dest[j++] = 0x80 | (c & 0x003f); + } else if (c >= 0x80) { + if (maxlength < 2) + break; + maxlength -= 2; + dest[j++] = 0xc0 | (c & 0x7c0) >> 6; + dest[j++] = 0x80 | (c & 0x03f); + } else { + maxlength -= 1; + dest[j++] = c & 0x7f; + } + } + if (maxlength) + dest[j] = '\0'; + return j; +} +EXPORT_SYMBOL(ucs2_as_utf8); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7340353f8aea..cbe6f0b96f29 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -989,7 +989,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) * here rather than calling cond_resched(). */ if (current->flags & PF_WQ_WORKER) - schedule_timeout(1); + schedule_timeout_uninterruptible(1); else cond_resched(); diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index d3116be5a00f..300117f1a08f 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -61,6 +61,7 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) bool dequeued_page; dequeued_page = false; + spin_lock_irqsave(&b_dev_info->pages_lock, flags); list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) { /* * Block others from accessing the 'page' while we get around @@ -75,15 +76,14 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) continue; } #endif - spin_lock_irqsave(&b_dev_info->pages_lock, flags); balloon_page_delete(page); __count_vm_event(BALLOON_DEFLATE); - spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); unlock_page(page); dequeued_page = true; break; } } + spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); if (!dequeued_page) { /* diff --git a/mm/compaction.c b/mm/compaction.c index de3e1e71cd9f..7881e072dc33 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -880,16 +880,8 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, ISOLATE_UNEVICTABLE); - /* - * In case of fatal failure, release everything that might - * have been isolated in the previous iteration, and signal - * the failure back to caller. - */ - if (!pfn) { - putback_movable_pages(&cc->migratepages); - cc->nr_migratepages = 0; + if (!pfn) break; - } if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) break; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 62fe06bb7d04..530e6427f823 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2134,10 +2134,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma, * page fault if needed. */ return 0; - if (vma->vm_ops) + if (vma->vm_ops || (vm_flags & VM_NO_THP)) /* khugepaged not yet working on file or special mappings */ return 0; - VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) @@ -2498,8 +2497,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma) return false; if (is_vma_temporary_stack(vma)) return false; - VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma); - return true; + return !(vma->vm_flags & VM_NO_THP); } static void collapse_huge_page(struct mm_struct *mm, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5c714f33f494..b7d8315541e3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -196,6 +196,7 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); /* "mc" and its members are protected by cgroup_mutex */ static struct move_charge_struct { spinlock_t lock; /* for from, to */ + struct mm_struct *mm; struct mem_cgroup *from; struct mem_cgroup *to; unsigned long flags; @@ -1332,7 +1333,7 @@ static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) return limit; } -static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, +static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order) { struct oom_control oc = { @@ -1410,6 +1411,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, } unlock: mutex_unlock(&oom_lock); + return chosen; } #if MAX_NUMNODES > 1 @@ -4799,6 +4801,8 @@ static void __mem_cgroup_clear_mc(void) static void mem_cgroup_clear_mc(void) { + struct mm_struct *mm = mc.mm; + /* * we must clear moving_task before waking up waiters at the end of * task migration. @@ -4808,7 +4812,10 @@ static void mem_cgroup_clear_mc(void) spin_lock(&mc.lock); mc.from = NULL; mc.to = NULL; + mc.mm = NULL; spin_unlock(&mc.lock); + + mmput(mm); } static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4865,6 +4872,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) VM_BUG_ON(mc.moved_swap); spin_lock(&mc.lock); + mc.mm = mm; mc.from = from; mc.to = memcg; mc.flags = move_flags; @@ -4874,8 +4882,9 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) ret = mem_cgroup_precharge_mc(mm); if (ret) mem_cgroup_clear_mc(); + } else { + mmput(mm); } - mmput(mm); return ret; } @@ -4989,11 +4998,11 @@ put: /* get_mctgt_type() gets the page */ return ret; } -static void mem_cgroup_move_charge(struct mm_struct *mm) +static void mem_cgroup_move_charge(void) { struct mm_walk mem_cgroup_move_charge_walk = { .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mm, + .mm = mc.mm, }; lru_add_drain_all(); @@ -5005,7 +5014,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) atomic_inc(&mc.from->moving_account); synchronize_rcu(); retry: - if (unlikely(!down_read_trylock(&mm->mmap_sem))) { + if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) { /* * Someone who are holding the mmap_sem might be waiting in * waitq. So we cancel all extra charges, wake up all waiters, @@ -5022,23 +5031,16 @@ retry: * additional charge, the page walk just aborts. */ walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk); - up_read(&mm->mmap_sem); + up_read(&mc.mm->mmap_sem); atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { - struct cgroup_subsys_state *css; - struct task_struct *p = cgroup_taskset_first(tset, &css); - struct mm_struct *mm = get_task_mm(p); - - if (mm) { - if (mc.to) - mem_cgroup_move_charge(mm); - mmput(mm); - } - if (mc.to) + if (mc.to) { + mem_cgroup_move_charge(); mem_cgroup_clear_mc(); + } } #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -5052,7 +5054,7 @@ static int mem_cgroup_allow_attach(struct cgroup_taskset *tset) static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { } #endif @@ -5130,6 +5132,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long nr_pages; unsigned long high; int err; @@ -5140,6 +5143,11 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, memcg->high = high; + nr_pages = page_counter_read(&memcg->memory); + if (nr_pages > high) + try_to_free_mem_cgroup_pages(memcg, nr_pages - high, + GFP_KERNEL, true); + memcg_wb_domain_size_changed(memcg); return nbytes; } @@ -5161,6 +5169,8 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned int nr_reclaims = MEM_CGROUP_RECLAIM_RETRIES; + bool drained = false; unsigned long max; int err; @@ -5169,9 +5179,36 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (err) return err; - err = mem_cgroup_resize_limit(memcg, max); - if (err) - return err; + xchg(&memcg->memory.limit, max); + + for (;;) { + unsigned long nr_pages = page_counter_read(&memcg->memory); + + if (nr_pages <= max) + break; + + if (signal_pending(current)) { + err = -EINTR; + break; + } + + if (!drained) { + drain_all_stock(memcg); + drained = true; + continue; + } + + if (nr_reclaims) { + if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, + GFP_KERNEL, true)) + nr_reclaims--; + continue; + } + + mem_cgroup_events(memcg, MEMCG_OOM, 1); + if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) + break; + } memcg_wb_domain_size_changed(memcg); return nbytes; @@ -5231,7 +5268,7 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, - .attach = mem_cgroup_move_task, + .post_attach = mem_cgroup_move_task, .allow_attach = mem_cgroup_allow_attach, .bind = mem_cgroup_bind, .dfl_cftypes = memory_files, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8424b64711ac..750b7893ee3a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1572,7 +1572,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) * Did it turn free? */ ret = __get_any_page(page, pfn, 0); - if (!PageLRU(page)) { + if (ret == 1 && !PageLRU(page)) { /* Drop page reference which is from __get_any_page() */ put_hwpoison_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", diff --git a/mm/memory.c b/mm/memory.c index c387430f06c3..76dcee317714 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -797,6 +797,46 @@ out: return pfn_to_page(pfn); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + /* + * There is no pmd_special() but there may be special pmds, e.g. + * in a direct-access (dax) mapping, so let's just replicate the + * !HAVE_PTE_SPECIAL case from vm_normal_page() here. + */ + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + if (is_zero_pfn(pfn)) + return NULL; + if (unlikely(pfn > highest_memmap_pfn)) + return NULL; + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} +#endif + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range @@ -3399,8 +3439,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(pmd_none(*pmd)) && unlikely(__pte_alloc(mm, vma, pmd, address))) return VM_FAULT_OOM; - /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd))) + /* + * If a huge pmd materialized under us just retry later. Use + * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd + * didn't become pmd_trans_huge under us and then back to pmd_none, as + * a result of MADV_DONTNEED running immediately after a huge pmd fault + * in a different thread of this mm, in turn leading to a misleading + * pmd_trans_huge() retval. All we have to ensure is that it is a + * regular pmd that we can walk with pte_offset_map() and we can do that + * through an atomic read in C, which is what pmd_trans_unstable() + * provides. + */ + if (unlikely(pmd_trans_unstable(pmd))) return 0; /* * A regular pmd is established and it can't morph into a huge pmd diff --git a/mm/migrate.c b/mm/migrate.c index 7890d0bb5e23..bbeb0b71fcf4 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -963,7 +963,13 @@ out: dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); /* Soft-offlined page shouldn't go through lru cache list */ - if (reason == MR_MEMORY_FAILURE) { + if (reason == MR_MEMORY_FAILURE && rc == MIGRATEPAGE_SUCCESS) { + /* + * With this release, we free successfully migrated + * page and set PG_HWPoison on just freed page + * intentionally. Although it's rather weird, it's how + * HWPoison flag works at the moment. + */ put_page(page); if (!test_set_page_hwpoison(page)) num_poisoned_pages_inc(); @@ -1578,7 +1584,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, (GFP_HIGHUSER_MOVABLE | __GFP_THISNODE | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & - ~(__GFP_IO | __GFP_FS), 0); + ~__GFP_RECLAIM, 0); return newpage; } diff --git a/mm/mlock.c b/mm/mlock.c index a6617735f2f4..d843bc9d32dd 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -172,7 +172,7 @@ static void __munlock_isolation_failed(struct page *page) */ unsigned int munlock_vma_page(struct page *page) { - unsigned int nr_pages; + int nr_pages; struct zone *zone = page_zone(page); /* For try_to_munlock() and to serialize with page migration */ diff --git a/mm/mmap.c b/mm/mmap.c index 2b1143008793..a089cca8d79a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -453,12 +453,16 @@ static void validate_mm(struct mm_struct *mm) struct vm_area_struct *vma = mm->mmap; while (vma) { + struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; - vma_lock_anon_vma(vma); - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_verify(avc); - vma_unlock_anon_vma(vma); + if (anon_vma) { + anon_vma_lock_read(anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_verify(avc); + anon_vma_unlock_read(anon_vma); + } + highest_address = vma->vm_end; vma = vma->vm_next; i++; @@ -2168,32 +2172,27 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; - int error; + int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ + /* Guard against wrapping around to address 0. */ + if (address < PAGE_ALIGN(address+4)) + address = PAGE_ALIGN(address+4); + else + return -ENOMEM; + + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; - vma_lock_anon_vma(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. - * Also guard against wrapping around to address 0. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else { - vma_unlock_anon_vma(vma); - return -ENOMEM; - } - error = 0; + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { @@ -2211,7 +2210,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2235,7 +2234,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; @@ -2251,25 +2250,21 @@ int expand_downwards(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; int error; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ - if (unlikely(anon_vma_prepare(vma))) - return -ENOMEM; - address &= PAGE_MASK; error = security_mmap_addr(address); if (error) return error; - vma_lock_anon_vma(vma); + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) + return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { @@ -2287,7 +2282,7 @@ int expand_downwards(struct vm_area_struct *vma, * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2309,7 +2304,7 @@ int expand_downwards(struct vm_area_struct *vma, } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; @@ -2639,6 +2634,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) return 0; } +EXPORT_SYMBOL(do_munmap); int vm_munmap(unsigned long start, size_t len) { @@ -2694,12 +2690,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; - if (start < vma->vm_start || start + size > vma->vm_end) + if (start < vma->vm_start) goto out; - if (pgoff == linear_page_index(vma, start)) { - ret = 0; - goto out; + if (start + size > vma->vm_end) { + struct vm_area_struct *next; + + for (next = vma->vm_next; next; next = next->vm_next) { + /* hole between vmas ? */ + if (next->vm_start != next->vm_prev->vm_end) + goto out; + + if (next->vm_file != vma->vm_file) + goto out; + + if (next->vm_flags != vma->vm_flags) + goto out; + + if (start + size <= next->vm_end) + break; + } + + if (!next) + goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; @@ -2709,9 +2722,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) { + struct vm_area_struct *tmp; flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ - munlock_vma_pages_range(vma, start, start + size); + for (tmp = vma; tmp->vm_start >= start + size; + tmp = tmp->vm_next) { + munlock_vma_pages_range(tmp, + max(tmp->vm_start, start), + min(tmp->vm_end, start + size)); + } } file = get_file(vma->vm_file); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d15d88c8efa1..e40c9364582d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1899,7 +1899,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (gdtc->dirty > gdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(gdtc)) + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) return true; if (mdtc) { @@ -1913,7 +1914,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (mdtc->dirty > mdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(mdtc)) + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) return true; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 89ef8347900c..755f29fac22f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -674,34 +674,28 @@ static inline void __free_one_page(struct page *page, unsigned long combined_idx; unsigned long uninitialized_var(buddy_idx); struct page *buddy; - unsigned int max_order = MAX_ORDER; + unsigned int max_order; + + max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); VM_BUG_ON(!zone_is_initialized(zone)); VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); VM_BUG_ON(migratetype == -1); - if (is_migrate_isolate(migratetype)) { - /* - * We restrict max order of merging to prevent merge - * between freepages on isolate pageblock and normal - * pageblock. Without this, pageblock isolation - * could cause incorrect freepage accounting. - */ - max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); - } else { + if (likely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); - } - page_idx = pfn & ((1 << max_order) - 1); + page_idx = pfn & ((1 << MAX_ORDER) - 1); VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); +continue_merging: while (order < max_order - 1) { buddy_idx = __find_buddy_index(page_idx, order); buddy = page + (buddy_idx - page_idx); if (!page_is_buddy(page, buddy, order)) - break; + goto done_merging; /* * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page, * merge with it and move up one order. @@ -718,6 +712,32 @@ static inline void __free_one_page(struct page *page, page_idx = combined_idx; order++; } + if (max_order < MAX_ORDER) { + /* If we are here, it means order is >= pageblock_order. + * We want to prevent merge between freepages on isolate + * pageblock and normal pageblock. Without this, pageblock + * isolation could cause incorrect freepage or CMA accounting. + * + * We don't want to hit this code for the more frequent + * low-order merging. + */ + if (unlikely(has_isolate_pageblock(zone))) { + int buddy_mt; + + buddy_idx = __find_buddy_index(page_idx, order); + buddy = page + (buddy_idx - page_idx); + buddy_mt = get_pageblock_migratetype(buddy); + + if (migratetype != buddy_mt + && (is_migrate_isolate(migratetype) || + is_migrate_isolate(buddy_mt))) + goto done_merging; + } + max_order++; + goto continue_merging; + } + +done_merging: set_page_order(page, order); /* @@ -6191,7 +6211,7 @@ int __meminit init_per_zone_wmark_min(void) setup_per_zone_inactive_ratio(); return 0; } -module_init(init_per_zone_wmark_min) +core_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 4568fd58f70a..00c96462cc36 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -283,11 +283,11 @@ struct page *alloc_migrate_target(struct page *page, unsigned long private, * now as a simple work-around, we use the next node for destination. */ if (PageHuge(page)) { - nodemask_t src = nodemask_of_node(page_to_nid(page)); - nodemask_t dst; - nodes_complement(dst, src); + int node = next_online_node(page_to_nid(page)); + if (node == MAX_NUMNODES) + node = first_online_node; return alloc_huge_page_node(page_hstate(compound_head(page)), - next_node(page_to_nid(page), dst)); + node); } if (PageHighMem(page)) diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 7d3db0247983..1ba58213ad65 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -210,7 +210,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_trans_huge(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); - flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + + /* collapse entails shooting down ptes not pmd */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #endif diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index e88d071648c2..5d453e58ddbf 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -194,7 +194,7 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, goto free_proc_pages; } - mm = mm_access(task, PTRACE_MODE_ATTACH); + mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (!mm || IS_ERR(mm)) { rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; /* diff --git a/mm/shmem.c b/mm/shmem.c index 40d1d3b0ea2f..b82e56ebabdd 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -620,8 +620,7 @@ static void shmem_evict_inode(struct inode *inode) list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } - } else - kfree(info->symlink); + } simple_xattrs_free(&info->xattrs); WARN_ON(inode->i_blocks); @@ -2462,13 +2461,12 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s info = SHMEM_I(inode); inode->i_size = len-1; if (len <= SHORT_SYMLINK_LEN) { - info->symlink = kmemdup(symname, len, GFP_KERNEL); - if (!info->symlink) { + inode->i_link = kmemdup(symname, len, GFP_KERNEL); + if (!inode->i_link) { iput(inode); return -ENOMEM; } inode->i_op = &shmem_short_symlink_operations; - inode->i_link = info->symlink; } else { error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL); if (error) { @@ -3083,6 +3081,7 @@ static struct inode *shmem_alloc_inode(struct super_block *sb) static void shmem_destroy_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); + kfree(inode->i_link); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } diff --git a/mm/slub.c b/mm/slub.c index 46997517406e..65d5f92d51d2 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2819,6 +2819,7 @@ struct detached_freelist { void *tail; void *freelist; int cnt; + struct kmem_cache *s; }; /* @@ -2833,8 +2834,9 @@ struct detached_freelist { * synchronization primitive. Look ahead in the array is limited due * to performance reasons. */ -static int build_detached_freelist(struct kmem_cache *s, size_t size, - void **p, struct detached_freelist *df) +static inline +int build_detached_freelist(struct kmem_cache *s, size_t size, + void **p, struct detached_freelist *df) { size_t first_skipped_index = 0; int lookahead = 3; @@ -2850,8 +2852,11 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size, if (!object) return 0; + /* Support for memcg, compiler can optimize this out */ + df->s = cache_from_obj(s, object); + /* Start new detached freelist */ - set_freepointer(s, object, NULL); + set_freepointer(df->s, object, NULL); df->page = virt_to_head_page(object); df->tail = object; df->freelist = object; @@ -2866,7 +2871,7 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size, /* df->page is always set at this point */ if (df->page == virt_to_head_page(object)) { /* Opportunity build freelist */ - set_freepointer(s, object, df->freelist); + set_freepointer(df->s, object, df->freelist); df->freelist = object; df->cnt++; p[size] = NULL; /* mark object processed */ @@ -2885,25 +2890,20 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size, return first_skipped_index; } - /* Note that interrupts must be enabled when calling this function. */ -void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p) +void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) { if (WARN_ON(!size)) return; do { struct detached_freelist df; - struct kmem_cache *s; - - /* Support for memcg */ - s = cache_from_obj(orig_s, p[size - 1]); size = build_detached_freelist(s, size, p, &df); if (unlikely(!df.page)) continue; - slab_free(s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_); + slab_free(df.s, df.page, df.freelist, df.tail, df.cnt,_RET_IP_); } while (likely(size)); } EXPORT_SYMBOL(kmem_cache_free_bulk); diff --git a/mm/vmscan.c b/mm/vmscan.c index 0c56f6a812bc..0c114e2b01d3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -46,7 +46,6 @@ #include <linux/oom.h> #include <linux/prefetch.h> #include <linux/printk.h> -#include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -221,39 +220,6 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru); } -struct dentry *debug_file; - -static int debug_shrinker_show(struct seq_file *s, void *unused) -{ - struct shrinker *shrinker; - struct shrink_control sc; - - sc.gfp_mask = -1; - sc.nr_to_scan = 0; - - down_read(&shrinker_rwsem); - list_for_each_entry(shrinker, &shrinker_list, list) { - int num_objs; - - num_objs = shrinker->count_objects(shrinker, &sc); - seq_printf(s, "%pf %d\n", shrinker->scan_objects, num_objs); - } - up_read(&shrinker_rwsem); - return 0; -} - -static int debug_shrinker_open(struct inode *inode, struct file *file) -{ - return single_open(file, debug_shrinker_show, inode->i_private); -} - -static const struct file_operations debug_shrinker_fops = { - .open = debug_shrinker_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - /* * Add a shrinker callback to be called from the vm. */ @@ -283,15 +249,6 @@ int register_shrinker(struct shrinker *shrinker) } EXPORT_SYMBOL(register_shrinker); -static int __init add_shrinker_debug(void) -{ - debugfs_create_file("shrinker", 0644, NULL, NULL, - &debug_shrinker_fops); - return 0; -} - -late_initcall(add_shrinker_debug); - /* * Remove one */ @@ -2577,7 +2534,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) sc->gfp_mask |= __GFP_HIGHMEM; for_each_zone_zonelist_nodemask(zone, z, zonelist, - requested_highidx, sc->nodemask) { + gfp_zone(sc->gfp_mask), sc->nodemask) { enum zone_type classzone_idx; if (!populated_zone(zone)) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9f15bdd9163c..fc083996e40a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -309,7 +309,12 @@ static void free_handle(struct zs_pool *pool, unsigned long handle) static void record_obj(unsigned long handle, unsigned long obj) { - *(unsigned long *)handle = obj; + /* + * lsb of @obj represents handle lock while other bits + * represent object value the handle is pointing so + * updating shouldn't do store tearing. + */ + WRITE_ONCE(*(unsigned long *)handle, obj); } /* zpool driver */ @@ -1635,6 +1640,13 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, free_obj = obj_malloc(d_page, class, handle); zs_object_copy(free_obj, used_obj, class); index++; + /* + * record_obj updates handle's value to free_obj and it will + * invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which + * breaks synchronization using pin_tag(e,g, zs_free) so + * let's keep the lock bit. + */ + free_obj |= BIT(HANDLE_PIN_BIT); record_obj(handle, free_obj); unpin_tag(handle); obj_free(pool, class, used_obj); diff --git a/mm/zswap.c b/mm/zswap.c index bf14508afd64..340261946fda 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -170,6 +170,8 @@ static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; static LIST_HEAD(zswap_pools); /* protects zswap_pools list modification */ static DEFINE_SPINLOCK(zswap_pools_lock); +/* pool counter to provide unique names to zpool */ +static atomic_t zswap_pools_count = ATOMIC_INIT(0); /* used by param callback function */ static bool zswap_init_started; @@ -565,6 +567,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) static struct zswap_pool *zswap_pool_create(char *type, char *compressor) { struct zswap_pool *pool; + char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; pool = kzalloc(sizeof(*pool), GFP_KERNEL); @@ -573,7 +576,10 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) return NULL; } - pool->zpool = zpool_create_pool(type, "zswap", gfp, &zswap_zpool_ops); + /* unique name for each pool specifically required by zsmalloc */ + snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count)); + + pool->zpool = zpool_create_pool(type, name, gfp, &zswap_zpool_ops); if (!pool->zpool) { pr_err("%s zpool not available\n", type); goto error; diff --git a/net/Kconfig b/net/Kconfig index 043fe1dc0860..ce9585cf343a 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -92,14 +92,6 @@ config ANDROID_PARANOID_NETWORK help none -config NET_ACTIVITY_STATS - bool "Network activity statistics tracking" - default y - help - Network activity statistics are useful for tracking wireless - modem activity on 2G, 3G, 4G wireless networks. Counts number of - transmissions and groups them in specified time buckets. - config NETWORK_SECMARK bool "Security Marking" help diff --git a/net/Makefile b/net/Makefile index eeb9d5db454f..a5d04098dfce 100644 --- a/net/Makefile +++ b/net/Makefile @@ -77,4 +77,3 @@ endif ifneq ($(CONFIG_NET_L3_MASTER_DEV),) obj-y += l3mdev/ endif -obj-$(CONFIG_NET_ACTIVITY_STATS) += activity_stats.o diff --git a/net/activity_stats.c b/net/activity_stats.c deleted file mode 100644 index 3bf92d80b8b9..000000000000 --- a/net/activity_stats.c +++ /dev/null @@ -1,118 +0,0 @@ -/* net/activity_stats.c - * - * Copyright (C) 2010 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Author: Mike Chan (mike@android.com) - */ - -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/suspend.h> -#include <net/net_namespace.h> - -/* - * Track transmission rates in buckets (power of 2). - * 1,2,4,8...512 seconds. - * - * Buckets represent the count of network transmissions at least - * N seconds apart, where N is 1 << bucket index. - */ -#define BUCKET_MAX 10 - -/* Track network activity frequency */ -static unsigned long activity_stats[BUCKET_MAX]; -static ktime_t last_transmit; -static ktime_t suspend_time; -static DEFINE_SPINLOCK(activity_lock); - -void activity_stats_update(void) -{ - int i; - unsigned long flags; - ktime_t now; - s64 delta; - - spin_lock_irqsave(&activity_lock, flags); - now = ktime_get(); - delta = ktime_to_ns(ktime_sub(now, last_transmit)); - - for (i = BUCKET_MAX - 1; i >= 0; i--) { - /* - * Check if the time delta between network activity is within the - * minimum bucket range. - */ - if (delta < (1000000000ULL << i)) - continue; - - activity_stats[i]++; - last_transmit = now; - break; - } - spin_unlock_irqrestore(&activity_lock, flags); -} - -static int activity_stats_show(struct seq_file *m, void *v) -{ - int i; - - seq_printf(m, "Min Bucket(sec) Count\n"); - - for (i = 0; i < BUCKET_MAX; i++) { - seq_printf(m, "%15d %lu\n", 1 << i, activity_stats[i]); - if (seq_has_overflowed(m)) - return -ENOSPC; - } - - return 0; -} - -static int activity_stats_notifier(struct notifier_block *nb, - unsigned long event, void *dummy) -{ - switch (event) { - case PM_SUSPEND_PREPARE: - suspend_time = ktime_get_real(); - break; - - case PM_POST_SUSPEND: - suspend_time = ktime_sub(ktime_get_real(), suspend_time); - last_transmit = ktime_sub(last_transmit, suspend_time); - } - - return 0; -} - -static int activity_stats_open(struct inode *inode, struct file *file) -{ - return single_open(file, activity_stats_show, PDE_DATA(inode)); -} - -static const struct file_operations activity_stats_fops = { - .open = activity_stats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static struct notifier_block activity_stats_notifier_block = { - .notifier_call = activity_stats_notifier, -}; - -static int __init activity_stats_init(void) -{ - proc_create("activity", S_IRUGO, - init_net.proc_net_stat, &activity_stats_fops); - return register_pm_notifier(&activity_stats_notifier_block); -} - -subsys_initcall(activity_stats_init); - diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index b563a3f5f2a8..2fa3be965101 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -228,8 +228,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) } #endif +static bool ax25_validate_header(const char *header, unsigned int len) +{ + ax25_digi digi; + + if (!len) + return false; + + if (header[0]) + return true; + + return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL, + NULL); +} + const struct header_ops ax25_header_ops = { .create = ax25_hard_header, + .validate = ax25_validate_header, }; EXPORT_SYMBOL(ax25_header_ops); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 191a70290dca..f5d2fe5e31cc 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -127,21 +127,17 @@ batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw) } /* finally deinitialize the claim */ -static void batadv_claim_free_rcu(struct rcu_head *rcu) +static void batadv_claim_release(struct batadv_bla_claim *claim) { - struct batadv_bla_claim *claim; - - claim = container_of(rcu, struct batadv_bla_claim, rcu); - batadv_backbone_gw_free_ref(claim->backbone_gw); - kfree(claim); + kfree_rcu(claim, rcu); } /* free a claim, call claim_free_rcu if its the last reference */ static void batadv_claim_free_ref(struct batadv_bla_claim *claim) { if (atomic_dec_and_test(&claim->refcount)) - call_rcu(&claim->rcu, batadv_claim_free_rcu); + batadv_claim_release(claim); } /** diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index a49c705fb86b..5f19133c5530 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -553,6 +553,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, * be sent to * @bat_priv: the bat priv with all the soft interface information * @ip_dst: ipv4 to look up in the DHT + * @vid: VLAN identifier * * An originator O is selected if and only if its DHT_ID value is one of three * closest values (from the LEFT, with wrap around if needed) then the hash @@ -561,7 +562,8 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, * Returns the candidate array of size BATADV_DAT_CANDIDATE_NUM. */ static struct batadv_dat_candidate * -batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) +batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst, + unsigned short vid) { int select; batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key; @@ -577,7 +579,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) return NULL; dat.ip = ip_dst; - dat.vid = 0; + dat.vid = vid; ip_key = (batadv_dat_addr_t)batadv_hash_dat(&dat, BATADV_DAT_ADDR_MAX); @@ -597,6 +599,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @ip: the DHT key + * @vid: VLAN identifier * @packet_subtype: unicast4addr packet subtype to use * * This function copies the skb with pskb_copy() and is sent as unicast packet @@ -607,7 +610,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) */ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, struct sk_buff *skb, __be32 ip, - int packet_subtype) + unsigned short vid, int packet_subtype) { int i; bool ret = false; @@ -616,7 +619,7 @@ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, struct sk_buff *tmp_skb; struct batadv_dat_candidate *cand; - cand = batadv_dat_select_candidates(bat_priv, ip); + cand = batadv_dat_select_candidates(bat_priv, ip, vid); if (!cand) goto out; @@ -1004,7 +1007,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, ret = true; } else { /* Send the request to the DHT */ - ret = batadv_dat_send_data(bat_priv, skb, ip_dst, + ret = batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_GET); } out: @@ -1132,8 +1135,8 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, /* Send the ARP reply to the candidates for both the IP addresses that * the node obtained from the ARP reply */ - batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT); - batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_src, vid, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT); } /** diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 5a31420513e1..7b12ea8ea29d 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -75,18 +75,6 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu); } -/** - * batadv_hardif_free_ref_now - decrement the hard interface refcounter and - * possibly free it (without rcu callback) - * @hard_iface: the hard interface to free - */ -static inline void -batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface) -{ - if (atomic_dec_and_test(&hard_iface->refcount)) - batadv_hardif_free_rcu(&hard_iface->rcu); -} - static inline struct batadv_hard_iface * batadv_primary_if_get_selected(struct batadv_priv *bat_priv) { diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index f5276be2c77c..d0956f726547 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -203,28 +203,25 @@ void batadv_nc_init_orig(struct batadv_orig_node *orig_node) } /** - * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove - * its refcount on the orig_node - * @rcu: rcu pointer of the nc node + * batadv_nc_node_release - release nc_node from lists and queue for free after + * rcu grace period + * @nc_node: the nc node to free */ -static void batadv_nc_node_free_rcu(struct rcu_head *rcu) +static void batadv_nc_node_release(struct batadv_nc_node *nc_node) { - struct batadv_nc_node *nc_node; - - nc_node = container_of(rcu, struct batadv_nc_node, rcu); batadv_orig_node_free_ref(nc_node->orig_node); - kfree(nc_node); + kfree_rcu(nc_node, rcu); } /** - * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly - * frees it + * batadv_nc_node_free_ref - decrement the nc node refcounter and possibly + * release it * @nc_node: the nc node to free */ static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node) { if (atomic_dec_and_test(&nc_node->refcount)) - call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu); + batadv_nc_node_release(nc_node); } /** diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 7486df9ed48d..17851d3aaf22 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -163,92 +163,66 @@ err: } /** - * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object - * @rcu: rcu pointer of the neigh_ifinfo object - */ -static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu) -{ - struct batadv_neigh_ifinfo *neigh_ifinfo; - - neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu); - - if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) - batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing); - - kfree(neigh_ifinfo); -} - -/** - * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free - * the neigh_ifinfo (without rcu callback) + * batadv_neigh_ifinfo_release - release neigh_ifinfo from lists and queue for + * free after rcu grace period * @neigh_ifinfo: the neigh_ifinfo object to release */ static void -batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo) +batadv_neigh_ifinfo_release(struct batadv_neigh_ifinfo *neigh_ifinfo) { - if (atomic_dec_and_test(&neigh_ifinfo->refcount)) - batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu); + if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) + batadv_hardif_free_ref(neigh_ifinfo->if_outgoing); + + kfree_rcu(neigh_ifinfo, rcu); } /** - * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free + * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly release * the neigh_ifinfo * @neigh_ifinfo: the neigh_ifinfo object to release */ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo) { if (atomic_dec_and_test(&neigh_ifinfo->refcount)) - call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu); + batadv_neigh_ifinfo_release(neigh_ifinfo); } /** * batadv_neigh_node_free_rcu - free the neigh_node - * @rcu: rcu pointer of the neigh_node + * batadv_neigh_node_release - release neigh_node from lists and queue for + * free after rcu grace period + * @neigh_node: neigh neighbor to free */ -static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) +static void batadv_neigh_node_release(struct batadv_neigh_node *neigh_node) { struct hlist_node *node_tmp; - struct batadv_neigh_node *neigh_node; struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_algo_ops *bao; - neigh_node = container_of(rcu, struct batadv_neigh_node, rcu); bao = neigh_node->orig_node->bat_priv->bat_algo_ops; hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, &neigh_node->ifinfo_list, list) { - batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo); + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); } if (bao->bat_neigh_free) bao->bat_neigh_free(neigh_node); - batadv_hardif_free_ref_now(neigh_node->if_incoming); + batadv_hardif_free_ref(neigh_node->if_incoming); - kfree(neigh_node); -} - -/** - * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter - * and possibly free it (without rcu callback) - * @neigh_node: neigh neighbor to free - */ -static void -batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node) -{ - if (atomic_dec_and_test(&neigh_node->refcount)) - batadv_neigh_node_free_rcu(&neigh_node->rcu); + kfree_rcu(neigh_node, rcu); } /** * batadv_neigh_node_free_ref - decrement the neighbors refcounter - * and possibly free it + * and possibly release it * @neigh_node: neigh neighbor to free */ void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node) { if (atomic_dec_and_test(&neigh_node->refcount)) - call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu); + batadv_neigh_node_release(neigh_node); } /** @@ -532,108 +506,99 @@ out: } /** - * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object - * @rcu: rcu pointer of the orig_ifinfo object + * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for + * free after rcu grace period + * @orig_ifinfo: the orig_ifinfo object to release */ -static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) +static void batadv_orig_ifinfo_release(struct batadv_orig_ifinfo *orig_ifinfo) { - struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router; - orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); - if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) - batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + batadv_hardif_free_ref(orig_ifinfo->if_outgoing); /* this is the last reference to this object */ router = rcu_dereference_protected(orig_ifinfo->router, true); if (router) - batadv_neigh_node_free_ref_now(router); - kfree(orig_ifinfo); + batadv_neigh_node_free_ref(router); + + kfree_rcu(orig_ifinfo, rcu); } /** - * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free - * the orig_ifinfo (without rcu callback) + * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly release + * the orig_ifinfo * @orig_ifinfo: the orig_ifinfo object to release */ -static void -batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo) +void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) { if (atomic_dec_and_test(&orig_ifinfo->refcount)) - batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu); + batadv_orig_ifinfo_release(orig_ifinfo); } /** - * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free - * the orig_ifinfo - * @orig_ifinfo: the orig_ifinfo object to release + * batadv_orig_node_free_rcu - free the orig_node + * @rcu: rcu pointer of the orig_node */ -void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) +static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { - if (atomic_dec_and_test(&orig_ifinfo->refcount)) - call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu); + struct batadv_orig_node *orig_node; + + orig_node = container_of(rcu, struct batadv_orig_node, rcu); + + batadv_mcast_purge_orig(orig_node); + + batadv_frag_purge_orig(orig_node, NULL); + + if (orig_node->bat_priv->bat_algo_ops->bat_orig_free) + orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node); + + kfree(orig_node->tt_buff); + kfree(orig_node); } -static void batadv_orig_node_free_rcu(struct rcu_head *rcu) +/** + * batadv_orig_node_release - release orig_node from lists and queue for + * free after rcu grace period + * @orig_node: the orig node to free + */ +static void batadv_orig_node_release(struct batadv_orig_node *orig_node) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; - struct batadv_orig_node *orig_node; struct batadv_orig_ifinfo *orig_ifinfo; - orig_node = container_of(rcu, struct batadv_orig_node, rcu); - spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); - batadv_neigh_node_free_ref_now(neigh_node); + batadv_neigh_node_free_ref(neigh_node); } hlist_for_each_entry_safe(orig_ifinfo, node_tmp, &orig_node->ifinfo_list, list) { hlist_del_rcu(&orig_ifinfo->list); - batadv_orig_ifinfo_free_ref_now(orig_ifinfo); + batadv_orig_ifinfo_free_ref(orig_ifinfo); } spin_unlock_bh(&orig_node->neigh_list_lock); - batadv_mcast_purge_orig(orig_node); - /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); - batadv_frag_purge_orig(orig_node, NULL); - - if (orig_node->bat_priv->bat_algo_ops->bat_orig_free) - orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node); - - kfree(orig_node->tt_buff); - kfree(orig_node); + call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); } /** * batadv_orig_node_free_ref - decrement the orig node refcounter and possibly - * schedule an rcu callback for freeing it + * release it * @orig_node: the orig node to free */ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node) { if (atomic_dec_and_test(&orig_node->refcount)) - call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); -} - -/** - * batadv_orig_node_free_ref_now - decrement the orig node refcounter and - * possibly free it (without rcu callback) - * @orig_node: the orig node to free - */ -void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node) -{ - if (atomic_dec_and_test(&orig_node->refcount)) - batadv_orig_node_free_rcu(&orig_node->rcu); + batadv_orig_node_release(orig_node); } void batadv_originator_free(struct batadv_priv *bat_priv) diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index fa18f9bf266b..a5c37882b409 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -38,7 +38,6 @@ int batadv_originator_init(struct batadv_priv *bat_priv); void batadv_originator_free(struct batadv_priv *bat_priv); void batadv_purge_orig_ref(struct batadv_priv *bat_priv); void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node); -void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr); struct batadv_neigh_node * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 3207667e69de..d8a2f33e60e5 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -104,6 +104,15 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, neigh_node = NULL; spin_lock_bh(&orig_node->neigh_list_lock); + /* curr_router used earlier may not be the current orig_ifinfo->router + * anymore because it was dereferenced outside of the neigh_list_lock + * protected region. After the new best neighbor has replace the current + * best neighbor the reference counter needs to decrease. Consequently, + * the code needs to ensure the curr_router variable contains a pointer + * to the replaced best neighbor. + */ + curr_router = rcu_dereference_protected(orig_ifinfo->router, true); + rcu_assign_pointer(orig_ifinfo->router, neigh_node); spin_unlock_bh(&orig_node->neigh_list_lock); batadv_orig_ifinfo_free_ref(orig_ifinfo); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index f664324805eb..0e0c3b8ed927 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -630,6 +630,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); + if (!forw_packet->own) + atomic_inc(&bat_priv->bcast_queue_left); + batadv_forw_packet_free(forw_packet); } } @@ -657,6 +660,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); + if (!forw_packet->own) + atomic_inc(&bat_priv->batman_queue_left); + batadv_forw_packet_free(forw_packet); } } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index ac4d08de5df4..720f1a5b81ac 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -407,11 +407,17 @@ void batadv_interface_rx(struct net_device *soft_iface, */ nf_reset(skb); + if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) + goto dropped; + vid = batadv_get_vid(skb, 0); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, VLAN_ETH_HLEN)) + goto dropped; + vhdr = (struct vlan_ethhdr *)skb->data; if (vhdr->h_vlan_encapsulated_proto != ethertype) @@ -423,8 +429,6 @@ void batadv_interface_rx(struct net_device *soft_iface, } /* skb->dev & skb->pkt_type are set here */ - if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) - goto dropped; skb->protocol = eth_type_trans(skb, soft_iface); /* should not be necessary anymore as we use skb_pull_rcsum() diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 76f19ba62462..83b0ca27a45e 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -240,20 +240,6 @@ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, return count; } -static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) -{ - struct batadv_tt_orig_list_entry *orig_entry; - - orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); - - /* We are in an rcu callback here, therefore we cannot use - * batadv_orig_node_free_ref() and its call_rcu(): - * An rcu_barrier() wouldn't wait for that to finish - */ - batadv_orig_node_free_ref_now(orig_entry->orig_node); - kfree(orig_entry); -} - /** * batadv_tt_local_size_mod - change the size by v of the local table identified * by vid @@ -349,13 +335,25 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node, batadv_tt_global_size_mod(orig_node, vid, -1); } +/** + * batadv_tt_orig_list_entry_release - release tt orig entry from lists and + * queue for free after rcu grace period + * @orig_entry: tt orig entry to be free'd + */ +static void +batadv_tt_orig_list_entry_release(struct batadv_tt_orig_list_entry *orig_entry) +{ + batadv_orig_node_free_ref(orig_entry->orig_node); + kfree_rcu(orig_entry, rcu); +} + static void batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry) { if (!atomic_dec_and_test(&orig_entry->refcount)) return; - call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); + batadv_tt_orig_list_entry_release(orig_entry); } /** diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 9e9cca3689a0..795ddd8b2f77 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -307,6 +307,9 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, /* check that it's our buffer */ if (lowpan_is_ipv6(*skb_network_header(skb))) { + /* Pull off the 1-byte of 6lowpan header. */ + skb_pull(skb, 1); + /* Copy the packet so that the IPv6 header is * properly aligned. */ @@ -317,6 +320,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; + local_skb->dev = dev; skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); @@ -335,6 +339,8 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, if (!local_skb) goto drop; + local_skb->dev = dev; + ret = iphc_decompress(local_skb, dev, chan); if (ret < 0) { kfree_skb(local_skb); @@ -343,7 +349,6 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; - local_skb->dev = dev; if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 85b82f7adbd2..24e9410923d0 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -722,8 +722,12 @@ static void hci_req_add_le_create_conn(struct hci_request *req, if (hci_update_random_address(req, false, &own_addr_type)) return; + /* Set window to be the same value as the interval to enable + * continuous scanning. + */ cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); - cp.scan_window = cpu_to_le16(hdev->le_scan_window); + cp.scan_window = cp.scan_interval; + bacpy(&cp.peer_addr, &conn->dst); cp.peer_addr_type = conn->dst_type; cp.own_address_type = own_addr_type; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 981f8a202c27..02778c5bc149 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -175,21 +175,29 @@ static u8 update_white_list(struct hci_request *req) * command to remove it from the controller. */ list_for_each_entry(b, &hdev->le_white_list, list) { - struct hci_cp_le_del_from_white_list cp; + /* If the device is neither in pend_le_conns nor + * pend_le_reports then remove it from the whitelist. + */ + if (!hci_pend_le_action_lookup(&hdev->pend_le_conns, + &b->bdaddr, b->bdaddr_type) && + !hci_pend_le_action_lookup(&hdev->pend_le_reports, + &b->bdaddr, b->bdaddr_type)) { + struct hci_cp_le_del_from_white_list cp; + + cp.bdaddr_type = b->bdaddr_type; + bacpy(&cp.bdaddr, &b->bdaddr); - if (hci_pend_le_action_lookup(&hdev->pend_le_conns, - &b->bdaddr, b->bdaddr_type) || - hci_pend_le_action_lookup(&hdev->pend_le_reports, - &b->bdaddr, b->bdaddr_type)) { - white_list_entries++; + hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, + sizeof(cp), &cp); continue; } - cp.bdaddr_type = b->bdaddr_type; - bacpy(&cp.bdaddr, &b->bdaddr); + if (hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) { + /* White list can not be used with RPAs */ + return 0x00; + } - hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, - sizeof(cp), &cp); + white_list_entries++; } /* Since all no longer valid white list entries have been diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7f22119276f3..b1b0a1c0bd8d 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7155,6 +7155,10 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, status); + if (data_len != sizeof(*cp) + cp->adv_data_len + cp->scan_rsp_len) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, + MGMT_STATUS_INVALID_PARAMS); + flags = __le32_to_cpu(cp->flags); timeout = __le16_to_cpu(cp->timeout); duration = __le16_to_cpu(cp->duration); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ffed8a1d4f27..4b175df35184 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1072,22 +1072,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) hcon->dst_type = smp->remote_irk->addr_type; queue_work(hdev->workqueue, &conn->id_addr_update_work); } - - /* When receiving an indentity resolving key for - * a remote device that does not use a resolvable - * private address, just remove the key so that - * it is possible to use the controller white - * list for scanning. - * - * Userspace will have been told to not store - * this key at this point. So it is safe to - * just remove it. - */ - if (!bacmp(&smp->remote_irk->rpa, BDADDR_ANY)) { - list_del_rcu(&smp->remote_irk->list); - kfree_rcu(smp->remote_irk, rcu); - smp->remote_irk = NULL; - } } if (smp->csrk) { diff --git a/net/bridge/br.c b/net/bridge/br.c index a1abe4936fe1..3addc05b9a16 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,6 +121,7 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; +/* called with RTNL */ static int br_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -130,7 +131,6 @@ static int br_switchdev_event(struct notifier_block *unused, struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; - rtnl_lock(); p = br_port_get_rtnl(dev); if (!p) goto out; @@ -155,7 +155,6 @@ static int br_switchdev_event(struct notifier_block *unused, } out: - rtnl_unlock(); return err; } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 689b8412c58e..0346c215ff6a 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -28,6 +28,8 @@ const struct nf_br_ops __rcu *nf_br_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_br_ops); +static struct lock_class_key bridge_netdev_addr_lock_key; + /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -88,6 +90,11 @@ out: return NETDEV_TX_OK; } +static void br_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); +} + static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -100,6 +107,7 @@ static int br_dev_init(struct net_device *dev) err = br_vlan_init(br); if (err) free_percpu(br->stats); + br_set_lockdep_class(dev); return err; } diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 5f3f64553179..eff69cb270d2 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -567,6 +567,14 @@ int br_set_max_age(struct net_bridge *br, unsigned long val) } +/* Set time interval that dynamic forwarding entries live + * For pure software bridge, allow values outside the 802.1 + * standard specification for special cases: + * 0 - entry never ages (all permanant) + * 1 - entry disappears (no persistance) + * + * Offloaded switch entries maybe more restrictive + */ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) { struct switchdev_attr attr = { @@ -577,11 +585,8 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) unsigned long t = clock_t_to_jiffies(ageing_time); int err; - if (t < BR_MIN_AGEING_TIME || t > BR_MAX_AGEING_TIME) - return -ERANGE; - err = switchdev_port_attr_set(br->dev, &attr); - if (err) + if (err && err != -EOPNOTSUPP) return err; br->ageing_time = t; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9981039ef4ff..63ae5dd24fc5 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -672,6 +672,8 @@ static void reset_connection(struct ceph_connection *con) } con->in_seq = 0; con->in_seq_acked = 0; + + con->out_skip = 0; } /* @@ -771,6 +773,8 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt) static void con_out_kvec_reset(struct ceph_connection *con) { + BUG_ON(con->out_skip); + con->out_kvec_left = 0; con->out_kvec_bytes = 0; con->out_kvec_cur = &con->out_kvec[0]; @@ -779,9 +783,9 @@ static void con_out_kvec_reset(struct ceph_connection *con) static void con_out_kvec_add(struct ceph_connection *con, size_t size, void *data) { - int index; + int index = con->out_kvec_left; - index = con->out_kvec_left; + BUG_ON(con->out_skip); BUG_ON(index >= ARRAY_SIZE(con->out_kvec)); con->out_kvec[index].iov_len = size; @@ -790,6 +794,27 @@ static void con_out_kvec_add(struct ceph_connection *con, con->out_kvec_bytes += size; } +/* + * Chop off a kvec from the end. Return residual number of bytes for + * that kvec, i.e. how many bytes would have been written if the kvec + * hadn't been nuked. + */ +static int con_out_kvec_skip(struct ceph_connection *con) +{ + int off = con->out_kvec_cur - con->out_kvec; + int skip = 0; + + if (con->out_kvec_bytes > 0) { + skip = con->out_kvec[off + con->out_kvec_left - 1].iov_len; + BUG_ON(con->out_kvec_bytes < skip); + BUG_ON(!con->out_kvec_left); + con->out_kvec_bytes -= skip; + con->out_kvec_left--; + } + + return skip; +} + #ifdef CONFIG_BLOCK /* @@ -1175,6 +1200,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, return new_piece; } +static size_t sizeof_footer(struct ceph_connection *con) +{ + return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ? + sizeof(struct ceph_msg_footer) : + sizeof(struct ceph_msg_footer_old); +} + static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { BUG_ON(!msg); @@ -1197,7 +1229,6 @@ static void prepare_write_message_footer(struct ceph_connection *con) m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE; dout("prepare_write_message_footer %p\n", con); - con->out_kvec_is_msg = true; con->out_kvec[v].iov_base = &m->footer; if (con->peer_features & CEPH_FEATURE_MSG_AUTH) { if (con->ops->sign_message) @@ -1225,7 +1256,6 @@ static void prepare_write_message(struct ceph_connection *con) u32 crc; con_out_kvec_reset(con); - con->out_kvec_is_msg = true; con->out_msg_done = false; /* Sneak an ack in there first? If we can get it into the same @@ -1265,18 +1295,19 @@ static void prepare_write_message(struct ceph_connection *con) /* tag + hdr + front + middle */ con_out_kvec_add(con, sizeof (tag_msg), &tag_msg); - con_out_kvec_add(con, sizeof (m->hdr), &m->hdr); + con_out_kvec_add(con, sizeof(con->out_hdr), &con->out_hdr); con_out_kvec_add(con, m->front.iov_len, m->front.iov_base); if (m->middle) con_out_kvec_add(con, m->middle->vec.iov_len, m->middle->vec.iov_base); - /* fill in crc (except data pages), footer */ + /* fill in hdr crc and finalize hdr */ crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc)); con->out_msg->hdr.crc = cpu_to_le32(crc); - con->out_msg->footer.flags = 0; + memcpy(&con->out_hdr, &con->out_msg->hdr, sizeof(con->out_hdr)); + /* fill in front and middle crc, footer */ crc = crc32c(0, m->front.iov_base, m->front.iov_len); con->out_msg->footer.front_crc = cpu_to_le32(crc); if (m->middle) { @@ -1288,6 +1319,7 @@ static void prepare_write_message(struct ceph_connection *con) dout("%s front_crc %u middle_crc %u\n", __func__, le32_to_cpu(con->out_msg->footer.front_crc), le32_to_cpu(con->out_msg->footer.middle_crc)); + con->out_msg->footer.flags = 0; /* is there a data payload? */ con->out_msg->footer.data_crc = 0; @@ -1492,7 +1524,6 @@ static int write_partial_kvec(struct ceph_connection *con) } } con->out_kvec_left = 0; - con->out_kvec_is_msg = false; ret = 1; out: dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con, @@ -1584,6 +1615,7 @@ static int write_partial_skip(struct ceph_connection *con) { int ret; + dout("%s %p %d left\n", __func__, con, con->out_skip); while (con->out_skip > 0) { size_t size = min(con->out_skip, (int) PAGE_CACHE_SIZE); @@ -2313,9 +2345,9 @@ static int read_partial_message(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), seq, con->in_seq + 1); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; - return 0; + return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { pr_err("read_partial_message bad seq %lld expected %lld\n", seq, con->in_seq + 1); @@ -2338,10 +2370,10 @@ static int read_partial_message(struct ceph_connection *con) /* skip this message */ dout("alloc_msg said skip message\n"); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; - return 0; + return 1; } BUG_ON(!con->in_msg); @@ -2506,13 +2538,13 @@ more: more_kvec: /* kvec data queued? */ - if (con->out_skip) { - ret = write_partial_skip(con); + if (con->out_kvec_left) { + ret = write_partial_kvec(con); if (ret <= 0) goto out; } - if (con->out_kvec_left) { - ret = write_partial_kvec(con); + if (con->out_skip) { + ret = write_partial_skip(con); if (ret <= 0) goto out; } @@ -3050,16 +3082,31 @@ void ceph_msg_revoke(struct ceph_msg *msg) ceph_msg_put(msg); } if (con->out_msg == msg) { - dout("%s %p msg %p - was sending\n", __func__, con, msg); - con->out_msg = NULL; - if (con->out_kvec_is_msg) { - con->out_skip = con->out_kvec_bytes; - con->out_kvec_is_msg = false; + BUG_ON(con->out_skip); + /* footer */ + if (con->out_msg_done) { + con->out_skip += con_out_kvec_skip(con); + } else { + BUG_ON(!msg->data_length); + if (con->peer_features & CEPH_FEATURE_MSG_AUTH) + con->out_skip += sizeof(msg->footer); + else + con->out_skip += sizeof(msg->old_footer); } + /* data, middle, front */ + if (msg->data_length) + con->out_skip += msg->cursor.total_resid; + if (msg->middle) + con->out_skip += con_out_kvec_skip(con); + con->out_skip += con_out_kvec_skip(con); + + dout("%s %p msg %p - was sending, will write %d skip %d\n", + __func__, con, msg, con->out_kvec_bytes, con->out_skip); msg->hdr.seq = 0; - + con->out_msg = NULL; ceph_msg_put(msg); } + mutex_unlock(&con->mutex); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index f8f235930d88..a28e47ff1b1b 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2843,8 +2843,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); if (!req) { - pr_warn("%s osd%d tid %llu unknown, skipping\n", - __func__, osd->o_osd, tid); + dout("%s osd%d tid %llu unknown, skipping\n", __func__, + osd->o_osd, tid); m = NULL; *skip = 1; goto out; diff --git a/net/core/dev.c b/net/core/dev.c index ae00b894e675..9efbdb3ff78a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2542,6 +2542,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. + * + * Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) @@ -2556,6 +2558,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return ERR_PTR(err); } + BUILD_BUG_ON(SKB_SGO_CB_OFFSET + + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); SKB_GSO_CB(skb)->encap_level = 0; @@ -4140,6 +4145,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; + diffs |= skb_metadata_dst_cmp(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); @@ -4337,10 +4343,12 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) break; case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { + skb_dst_drop(skb); kmem_cache_free(skbuff_head_cache, skb); - else + } else { __kfree_skb(skb); + } break; case GRO_HELD: @@ -7120,8 +7128,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); - if (!dev->tx_queue_len) + if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; + dev->tx_queue_len = 1; + } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; diff --git a/net/core/filter.c b/net/core/filter.c index 672eefbfbe99..f393a22b9d50 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -777,6 +777,11 @@ static int bpf_check_classic(const struct sock_filter *filter, if (ftest->k == 0) return -EINVAL; break; + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + if (ftest->k >= 32) + return -EINVAL; + break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: @@ -1134,7 +1139,8 @@ void bpf_prog_destroy(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(bpf_prog_destroy); -static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) +static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk, + bool locked) { struct sk_filter *fp, *old_fp; @@ -1150,10 +1156,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) return -ENOMEM; } - old_fp = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + old_fp = rcu_dereference_protected(sk->sk_filter, locked); rcu_assign_pointer(sk->sk_filter, fp); - if (old_fp) sk_filter_uncharge(sk, old_fp); @@ -1170,7 +1174,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ -int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked) { unsigned int fsize = bpf_classic_proglen(fprog); unsigned int bpf_fsize = bpf_prog_size(fprog->len); @@ -1208,7 +1213,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, locked); if (err < 0) { __bpf_prog_release(prog); return err; @@ -1216,7 +1221,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return 0; } -EXPORT_SYMBOL_GPL(sk_attach_filter); +EXPORT_SYMBOL_GPL(__sk_attach_filter); + +int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +{ + return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk)); +} int sk_attach_bpf(u32 ufd, struct sock *sk) { @@ -1235,7 +1245,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) return -EINVAL; } - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk)); if (err < 0) { bpf_prog_put(prog); return err; @@ -1908,7 +1918,7 @@ static int __init register_sk_filter_ops(void) } late_initcall(register_sk_filter_ops); -int sk_detach_filter(struct sock *sk) +int __sk_detach_filter(struct sock *sk, bool locked) { int ret = -ENOENT; struct sk_filter *filter; @@ -1916,8 +1926,7 @@ int sk_detach_filter(struct sock *sk) if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; - filter = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + filter = rcu_dereference_protected(sk->sk_filter, locked); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); @@ -1926,7 +1935,12 @@ int sk_detach_filter(struct sock *sk) return ret; } -EXPORT_SYMBOL_GPL(sk_detach_filter); +EXPORT_SYMBOL_GPL(__sk_detach_filter); + +int sk_detach_filter(struct sock *sk) +{ + return __sk_detach_filter(sk, sock_owned_by_user(sk)); +} int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d79699c9d1b9..12e700332010 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -208,7 +208,6 @@ ip: case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; - __be32 flow_label; ipv6: iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); @@ -230,8 +229,12 @@ ipv6: key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - flow_label = ip6_flowlabel(iph); - if (flow_label) { + if ((dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL) || + (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) && + ip6_flowlabel(iph)) { + __be32 flow_label = ip6_flowlabel(iph); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, @@ -396,6 +399,13 @@ ip_proto_again: goto out_bad; proto = eth->h_proto; nhoff += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + hlen = nhoff; } key_control->flags |= FLOW_DIS_ENCAPSULATION; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index de8d5cc5eb24..4da4d51a2ccf 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2787,7 +2787,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, } else { skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); } - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + + if (likely(skb)) + skb_reserve(skb, LL_RESERVED_SPACE(dev)); return skb; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 34ba7a08876d..ca966f7de351 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -905,6 +905,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } diff --git a/net/core/scm.c b/net/core/scm.c index 8a1741b14302..dce0acb929f1 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fplp = fpl; fpl->count = 0; fpl->max = SCM_MAX_FD; + fpl->user = NULL; } fpp = &fpl->fp[fpl->count]; @@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fpp++ = file; fpl->count++; } + + if (!fpl->user) + fpl->user = get_uid(current_user()); + return num; } @@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm) scm->fp = NULL; for (i=fpl->count-1; i>=0; i--) fput(fpl->fp[i]); + free_uid(fpl->user); kfree(fpl); } } @@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); new_fpl->max = new_fpl->count; + new_fpl->user = get_uid(fpl->user); } return new_fpl; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b2df375ec9c2..8616d1147c93 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -79,6 +79,8 @@ struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; +int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; +EXPORT_SYMBOL(sysctl_max_skb_frags); /** * skb_panic - private function for out-of-line support @@ -2946,6 +2948,24 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + +/** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled @@ -4082,9 +4102,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, if (!pskb_may_pull(skb_chk, offset)) goto err; - __skb_pull(skb_chk, offset); + skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); - __skb_push(skb_chk, offset); + skb_push_rcsum(skb_chk, offset); if (ret) goto err; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 95b6139d710c..a6beb7b6ae55 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -26,6 +26,7 @@ static int zero = 0; static int one = 1; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; +static int max_skb_frags = MAX_SKB_FRAGS; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "max_skb_frags", + .data = &sysctl_max_skb_frags, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &max_skb_frags, + }, { } }; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5684e14932bd..8be8f27bfacc 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -204,8 +204,6 @@ void dccp_req_err(struct sock *sk, u64 seq) * ICMPs are not backlogged, hence we cannot get an established * socket here. */ - WARN_ON(req->sk); - if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); } else { @@ -824,26 +822,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v4_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c6d0508e63a..b8608b71a66d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -691,26 +691,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v6_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 671eb0092915..eb12bd0ff9d3 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -886,7 +886,6 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCSIFPFLAGS: case SIOCGIFPFLAGS: case SIOCSIFFLAGS: - case SIOCKILLADDR: err = devinet_ioctl(net, cmd, (void __user *)arg); break; default: diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 3792624af316..0212591b0077 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -59,7 +59,6 @@ #include <net/arp.h> #include <net/ip.h> -#include <net/tcp.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/rtnetlink.h> @@ -335,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, ASSERT_RTNL(); + if (in_dev->dead) + goto no_promotions; + /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ @@ -381,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, fib_del_ifaddr(ifa, ifa1); } +no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; @@ -965,7 +968,6 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSIFBRDADDR: /* Set the broadcast address */ case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ - case SIOCKILLADDR: /* Nuke all sockets on this address */ ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; @@ -1017,8 +1019,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) } ret = -EADDRNOTAVAIL; - if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS - && cmd != SIOCKILLADDR) + if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS) goto done; switch (cmd) { @@ -1145,9 +1146,6 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) inet_insert_ifa(ifa); } break; - case SIOCKILLADDR: /* Nuke all connections on this address */ - ret = tcp_nuke_addr(net, (struct sockaddr *) sin); - break; } done: rtnl_unlock(); @@ -1853,7 +1851,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e10edb5e78b0..f97ae9d93ee9 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -280,7 +280,6 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) struct in_device *in_dev; struct fib_result res; struct rtable *rt; - struct flowi4 fl4; struct net *net; int scope; @@ -296,14 +295,13 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { - fl4.flowi4_oif = 0; - fl4.flowi4_iif = LOOPBACK_IFINDEX; - fl4.daddr = ip_hdr(skb)->saddr; - fl4.saddr = 0; - fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); - fl4.flowi4_scope = scope; - fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; - fl4.flowi4_tun_key.tun_id = 0; + struct flowi4 fl4 = { + .flowi4_iif = LOOPBACK_IFINDEX, + .daddr = ip_hdr(skb)->saddr, + .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), + .flowi4_scope = scope, + .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0, + }; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); } else { @@ -923,6 +921,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) subnet = 1; } + if (in_dev->dead) + goto no_promotions; + /* Deletion is more complicated than add. * We should take care of not to delete too much :-) * @@ -998,6 +999,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) } } +no_promotions: if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); if (subnet && ifa->ifa_prefixlen < 31) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 05e4cba14162..b3086cf27027 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -356,9 +356,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 728414dcea3b..030cd09dd2a2 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, reqsk_put(req); } -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child) +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; spin_lock(&queue->rskq_lock); if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_child_forget(sk, req, child); + child = NULL; } else { req->sk = child; req->dl_next = NULL; @@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, sk_acceptq_added(sk); } spin_unlock(&queue->rskq_lock); + return child; } EXPORT_SYMBOL(inet_csk_reqsk_queue_add); @@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, if (own_req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - inet_csk_reqsk_queue_add(sk, req, child); - /* Warning: caller must not call reqsk_put(req); - * child stole last reference on it. - */ - return child; + if (inet_csk_reqsk_queue_add(sk, req, child)) + return child; } /* Too bad, another child took ownership of the request, undo. */ bh_unlock_sock(child); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 1fe55ae81781..b8a0607dab96 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -661,6 +661,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); + skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 33bef2763c72..dbf7f7ee2958 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -240,6 +240,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, * from host network stack. */ features = netif_skb_features(skb); + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); @@ -921,7 +922,7 @@ static int __ip_append_data(struct sock *sk, if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && - (sk->sk_type == SOCK_DGRAM)) { + (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); @@ -1236,13 +1237,16 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (!skb) return -EINVAL; - cork->length += size; if ((size + skb->len > mtu) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { + if (skb->ip_summed != CHECKSUM_PARTIAL) + return -EOPNOTSUPP; + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } + cork->length += size; while (size > 0) { if (skb_is_gso(skb)) { diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5f73a7c03e27..a50124260f5a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); + + /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); if (err) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index cbb51f3fac06..ce30c8b72457 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -663,6 +663,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ @@ -760,7 +762,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 6fb869f646bf..a04dee536b8e 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -27,8 +27,6 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, { int err; - skb_orphan(skb); - local_bh_disable(); err = ip_defrag(net, skb, user); local_bh_enable(); diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index c6eb42100e9a..ea91058b5f6f 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev; + struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev; struct netdev_notifier_info info; - netdev_notifier_info_init(&info, dev); + /* The masq_dev_notifier will catch the case of the device going + * down. So if the inetdev is dead and being destroyed we have + * no work to do. Otherwise this is an individual address removal + * and we have to perform the flush. + */ + if (idev->dead) + return NOTIFY_DONE; + + netdev_notifier_info_init(&info, idev->dev); return masq_device_event(this, event, &info); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b27e98010dea..0d5278ca4777 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 865895d3fb27..a9b479a1c4a0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(net, msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); goto out; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a0d842f4e9cf..79a957ea6545 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; +static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ @@ -757,7 +758,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, 0); + 0, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1558,6 +1559,36 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1611,11 +1642,20 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) + if (fnhe) { rth = rcu_dereference(fnhe->fnhe_rth_input); - else - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(&FIB_RES_NH(*res), daddr); + fnhe = NULL; + } else { + goto rt_cache; + } + } + + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); +rt_cache: if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -2016,19 +2056,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); - if (fnhe) + if (fnhe) { prth = &fnhe->fnhe_rth_output; - else { - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; + rth = rcu_dereference(*prth); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(nh, fl4->daddr); + fnhe = NULL; + } else { + goto rt_cache; } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } + + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; + } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); + +rt_cache: if (rt_cache_valid(rth)) { dst_hold(&rth->dst); return rth; @@ -2582,7 +2632,6 @@ void ip_rt_multicast_event(struct in_device *in_dev) } #ifdef CONFIG_SYSCTL -static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b799f20387c6..6ecfc9de599c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -269,20 +269,17 @@ #include <linux/crypto.h> #include <linux/time.h> #include <linux/slab.h> -#include <linux/uid_stat.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/tcp.h> #include <net/xfrm.h> #include <net/ip.h> -#include <net/ip6_route.h> -#include <net/ipv6.h> -#include <net/transp_v6.h> #include <net/sock.h> #include <asm/uaccess.h> #include <asm/ioctls.h> +#include <asm/unaligned.h> #include <net/busy_poll.h> int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; @@ -942,7 +939,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= MAX_SKB_FRAGS) { + if (!can_coalesce && i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1215,7 +1212,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == MAX_SKB_FRAGS || !sg) { + if (i == sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1287,10 +1284,6 @@ out: tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); out_nopush: release_sock(sk); - - if (copied + copied_syn) - uid_stat_tcp_snd(from_kuid(&init_user_ns, current_uid()), - copied + copied_syn); return copied + copied_syn; do_fault: @@ -1565,8 +1558,6 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, if (copied > 0) { tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); - uid_stat_tcp_rcv(from_kuid(&init_user_ns, current_uid()), - copied); } return copied; } @@ -1900,10 +1891,6 @@ skip_copy: tcp_cleanup_rbuf(sk, copied); release_sock(sk); - - if (copied > 0) - uid_stat_tcp_rcv(from_kuid(&init_user_ns, current_uid()), - copied); return copied; out: @@ -1912,9 +1899,6 @@ out: recv_urg: err = tcp_recv_urg(sk, msg, len, flags); - if (err > 0) - uid_stat_tcp_rcv(from_kuid(&init_user_ns, current_uid()), - err); goto out; recv_sndq: @@ -2654,6 +2638,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; unsigned int start; + u64 rate64; u32 rate; memset(info, 0, sizeof(*info)); @@ -2719,15 +2704,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_retrans = tp->total_retrans; rate = READ_ONCE(sk->sk_pacing_rate); - info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_pacing_rate); rate = READ_ONCE(sk->sk_max_pacing_rate); - info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_max_pacing_rate); do { start = u64_stats_fetch_begin_irq(&tp->syncp); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; + put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked); + put_unaligned(tp->bytes_received, &info->tcpi_bytes_received); } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); info->tcpi_segs_out = tp->segs_out; info->tcpi_segs_in = tp->segs_in; @@ -3250,119 +3237,3 @@ void __init tcp_init(void) BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); } - -static int tcp_is_local(struct net *net, __be32 addr) { - struct rtable *rt; - struct flowi4 fl4 = { .daddr = addr }; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR_OR_NULL(rt)) - return 0; - return rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK); -} - -#if defined(CONFIG_IPV6) -static int tcp_is_local6(struct net *net, struct in6_addr *addr) { - struct rt6_info *rt6 = rt6_lookup(net, addr, addr, 0, 0); - return rt6 && rt6->dst.dev && (rt6->dst.dev->flags & IFF_LOOPBACK); -} -#endif - -/* - * tcp_nuke_addr - destroy all sockets on the given local address - * if local address is the unspecified address (0.0.0.0 or ::), destroy all - * sockets with local addresses that are not configured. - */ -int tcp_nuke_addr(struct net *net, struct sockaddr *addr) -{ - int family = addr->sa_family; - unsigned int bucket; - - struct in_addr *in; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - struct in6_addr *in6 = NULL; -#endif - if (family == AF_INET) { - in = &((struct sockaddr_in *)addr)->sin_addr; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - } else if (family == AF_INET6) { - in6 = &((struct sockaddr_in6 *)addr)->sin6_addr; -#endif - } else { - return -EAFNOSUPPORT; - } - - for (bucket = 0; bucket <= tcp_hashinfo.ehash_mask; bucket++) { - struct hlist_nulls_node *node; - struct sock *sk; - spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, bucket); - -restart: - spin_lock_bh(lock); - sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[bucket].chain) { - struct inet_sock *inet = inet_sk(sk); - - if (sk->sk_state == TCP_TIME_WAIT) { - /* - * Sockets that are in TIME_WAIT state are - * instances of lightweight inet_timewait_sock, - * we should simply skip them (or we'll try to - * access non-existing fields and crash). - */ - continue; - } - - if (sysctl_ip_dynaddr && sk->sk_state == TCP_SYN_SENT) - continue; - - if (sock_flag(sk, SOCK_DEAD)) - continue; - - if (family == AF_INET) { - __be32 s4 = inet->inet_rcv_saddr; - if (s4 == LOOPBACK4_IPV6) - continue; - - if (in->s_addr != s4 && - !(in->s_addr == INADDR_ANY && - !tcp_is_local(net, s4))) - continue; - } - -#if defined(CONFIG_IPV6) - if (family == AF_INET6) { - struct in6_addr *s6; - if (!inet->pinet6) - continue; - - s6 = &sk->sk_v6_rcv_saddr; - if (ipv6_addr_type(s6) == IPV6_ADDR_MAPPED) - continue; - - if (!ipv6_addr_equal(in6, s6) && - !(ipv6_addr_equal(in6, &in6addr_any) && - !tcp_is_local6(net, s6))) - continue; - } -#endif - - sock_hold(sk); - spin_unlock_bh(lock); - - local_bh_disable(); - bh_lock_sock(sk); - sk->sk_err = ETIMEDOUT; - sk->sk_error_report(sk); - - tcp_done(sk); - bh_unlock_sock(sk); - local_bh_enable(); - sock_put(sk); - - goto restart; - } - spin_unlock_bh(lock); - } - - return 0; -} -EXPORT_SYMBOL_GPL(tcp_nuke_addr); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 205e6745393f..7decaa439360 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -312,7 +312,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk) /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ -void tcp_req_err(struct sock *sk, u32 seq) +void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); @@ -320,11 +320,9 @@ void tcp_req_err(struct sock *sk, u32 seq) /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ - WARN_ON(req->sk); - if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - } else { + } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly @@ -384,7 +382,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, + type == ICMP_PARAMETERPROB || + type == ICMP_TIME_EXCEEDED || + (type == ICMP_DEST_UNREACH && + (code == ICMP_NET_UNREACH || + code == ICMP_HOST_UNREACH))); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy @@ -705,7 +708,8 @@ release_sk1: outside socket context is ugly, certainly. What can I do? */ -static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, +static void tcp_v4_send_ack(struct net *net, + struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) @@ -720,7 +724,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, ]; } rep; struct ip_reply_arg arg; - struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -782,7 +785,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v4_send_ack(sock_net(sk), skb, + tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, @@ -801,8 +805,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? - tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : + tcp_sk(sk)->snd_nxt; + + tcp_v4_send_ack(sock_net(sk), skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, tcp_time_stamp, req->ts_recent, @@ -1586,28 +1592,30 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (tcp_v4_inbound_md5_hash(sk, skb)) - goto discard_and_relse; - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { + reqsk_put(req); + goto discard_it; + } + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c8cbc2b4b792..a726d7853ce5 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -550,7 +550,7 @@ reset: */ if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt /= 8 * USEC_PER_MSEC; + crtt /= 8 * USEC_PER_SEC / HZ; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ac6b1961ffeb..9475a2748a9a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -458,7 +458,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 0; + newtp->segs_in = 1; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; @@ -818,6 +818,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; + tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 17d35662930d..3e6a472e6b88 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) yeah->fast_count = 0; yeah->reno_count = max(yeah->reno_count>>1, 2U); - return tp->snd_cwnd - reduction; + return max_t(int, tp->snd_cwnd - reduction, 2); } static struct tcp_congestion_ops tcp_yeah __read_mostly = { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d8946929813e..2ef43a102951 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -966,8 +966,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, sk->sk_family == AF_INET6); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; connected = 0; @@ -1989,10 +1991,14 @@ void udp_v4_early_demux(struct sk_buff *skb) if (!in_dev) return; - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return; + /* we are supposed to accept bcast packets */ + if (skb->pkt_type == PACKET_MULTICAST) { + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return; + } + sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); } else if (skb->pkt_type == PACKET_HOST) { diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index aba428626b52..280a9bdeddee 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -89,6 +89,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, uh->source = src_port; uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + udp_set_csum(nocheck, skb, src, dst, skb->len); return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4f7d6e0189cc..3cdf59161a7e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -585,7 +585,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; @@ -3533,6 +3533,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; + bool notify = false; addrconf_join_solict(dev, &ifp->addr); @@ -3578,7 +3579,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ - ipv6_ifa_notify(RTM_NEWADDR, ifp); + notify = true; } } @@ -3586,6 +3587,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) out: spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); + if (notify) + ipv6_ifa_notify(RTM_NEWADDR, ifp); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 99fccad391e0..d9b25bd17bf1 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -495,21 +495,6 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, } EXPORT_SYMBOL(inet6_getname); -int inet6_killaddr_ioctl(struct net *net, void __user *arg) { - struct in6_ifreq ireq; - struct sockaddr_in6 sin6; - - if (!capable(CAP_NET_ADMIN)) - return -EACCES; - - if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) - return -EFAULT; - - sin6.sin6_family = AF_INET6; - sin6.sin6_addr = ireq.ifr6_addr; - return tcp_nuke_addr(net, (struct sockaddr *) &sin6); -} - int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; @@ -533,8 +518,6 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return addrconf_del_ifaddr(net, (void __user *) arg); case SIOCSIFDSTADDR: return addrconf_set_dstaddr(net, (void __user *) arg); - case SIOCKILLADDR: - return inet6_killaddr_ioctl(net, (void __user *) arg); default: if (!sk->sk_prot->ioctl) return -ENOIOCTLCMD; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 0743a5f4c533..183ff87dacf3 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -163,6 +163,9 @@ ipv4_connected: fl6.fl6_sport = inet->inet_sport; fl6.flowi6_uid = sock_i_uid(sk); + if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) fl6.flowi6_oif = np->mcast_oif; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 835ec57c233b..840a4388f860 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -260,7 +260,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, return -EINVAL; } } - return -ENOENT; + if (!found) + return -ENOENT; + if (fragoff) + *fragoff = _frag_off; + break; } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 1f9ebe3cbb4a..dc2db4f7b182 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; - (sfl = rcu_dereference(*sflp)) != NULL; + (sfl = rcu_dereference_protected(*sflp, + lockdep_is_held(&ip6_sk_fl_lock))) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = rcu_dereference(sfl->next); + *sflp = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e5ea177d34c6..4650c6824783 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -778,6 +778,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) __u32 mtu; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e6a7bd15b9b7..a175152d3e46 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -909,6 +909,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct rt6_info *rt; #endif int err; + int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, @@ -940,10 +941,13 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, dst_release(*dst); *dst = NULL; } + + if (fl6->flowi6_oif) + flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) - *dst = ip6_route_output(net, sk, fl6); + *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) @@ -1087,8 +1091,8 @@ static inline int ip6_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, - int transhdrlen, int mtu, unsigned int flags, - const struct flowi6 *fl6) + int exthdrlen, int transhdrlen, int mtu, + unsigned int flags, const struct flowi6 *fl6) { struct sk_buff *skb; @@ -1113,7 +1117,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb_put(skb, fragheaderlen + transhdrlen); /* initialize network header pointer */ - skb_reset_network_header(skb); + skb_set_network_header(skb, exthdrlen); /* initialize protocol header pointer */ skb->transport_header = skb->network_header + fragheaderlen; @@ -1353,9 +1357,9 @@ emsgsize: (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && - (sk->sk_type == SOCK_DGRAM)) { + (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, - hh_len, fragheaderlen, + hh_len, fragheaderlen, exthdrlen, transhdrlen, mtu, flags, fl6); if (err) goto error; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 137fca42aaa6..3991b21e24ad 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -343,12 +343,12 @@ static int ip6_tnl_create2(struct net_device *dev) t = netdev_priv(dev); + dev->rtnl_link_ops = &ip6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); - dev->rtnl_link_ops = &ip6_link_ops; dev_hold(dev); ip6_tnl_link(ip6n, t); @@ -1180,6 +1180,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + tproto = ACCESS_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 5ee56d0a8699..d64ee7e83664 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) return NULL; skb->priority = TC_PRIO_CONTROL; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 02ba70201e05..dd76806358fe 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1170,11 +1170,10 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); } -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6) +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags) { struct dst_entry *dst; - int flags = 0; bool any_src; dst = l3mdev_rt6_dst_by_oif(net, fl6); @@ -1195,7 +1194,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); } -EXPORT_SYMBOL(ip6_route_output); +EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e6b044480333..f85b4c44c00d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -329,6 +329,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; + bool fatal; int err; sk = __inet6_lookup_established(net, &tcp_hashinfo, @@ -347,8 +348,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; } seq = ntohl(th->seq); + fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, fatal); bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) @@ -402,7 +404,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; } - icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { @@ -463,8 +464,10 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + rcu_read_lock(); err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass); + rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1386,7 +1389,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; tcp_v6_fill_cb(skb, hdr, th); @@ -1394,24 +1397,24 @@ process: reqsk_put(req); goto discard_it; } - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); tcp_v6_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index a1b6adc20e1e..9cb0ff304336 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -837,8 +837,8 @@ start_lookup: flush_stack(stack, count, skb, count - 1); } else { if (!inner_flushed) - UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, - proto == IPPROTO_UDPLITE); + UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, + proto == IPPROTO_UDPLITE); consume_skb(skb); } return 0; @@ -916,11 +916,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ + /* a return value > 0 means to resubmit the input */ if (ret > 0) - return -ret; + return ret; return 0; } diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index f7fbdbabe50e..372855eeaf42 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -23,7 +23,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) struct ipv6hdr *inner_iph = ipipv6_hdr(skb); if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) - IP6_ECN_set_ce(inner_iph); + IP6_ECN_set_ce(skb, inner_iph); } /* Add encapsulation header. diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 435608c4306d..20ab7b2ec463 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -708,6 +708,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, if (!addr || addr->sa_family != AF_IUCV) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_iucv)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != IUCV_OPEN) { err = -EBADFD; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index ec22078b0914..42de4ccd159f 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -123,12 +123,11 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; int length; - /* Point to L2TP header */ - optr = ptr = skb->data; - if (!pskb_may_pull(skb, 4)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; session_id = ntohl(*((__be32 *) ptr)); ptr += 4; @@ -156,6 +155,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) if (!pskb_may_pull(skb, length)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; + ptr += 4; pr_debug("%s: ip recv\n", tunnel->name); print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index a2c8747d2936..9ee4ddb6b397 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -135,12 +135,11 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; int length; - /* Point to L2TP header */ - optr = ptr = skb->data; - if (!pskb_may_pull(skb, 4)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; session_id = ntohl(*((__be32 *) ptr)); ptr += 4; @@ -168,6 +167,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) if (!pskb_may_pull(skb, length)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; + ptr += 4; pr_debug("%s: ip recv\n", tunnel->name); print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index f93c5be612a7..2caaa84ce92d 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family, ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, tunnel, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); @@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family, ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, session, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 10ad4ac1fa0b..367784be5df2 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -291,7 +291,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, } /* prepare A-MPDU MLME for Rx aggregation */ - tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL); + tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL); if (!tid_agg_rx) goto end; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 337bb5d78003..980e9e9b6684 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -7,6 +7,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2009, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright(c) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1484,14 +1485,21 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) sdata_info(sdata, "Trigger new scan to find an IBSS to join\n"); - num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy, - &ifibss->chandef, - channels, - ARRAY_SIZE(channels)); scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef); - ieee80211_request_ibss_scan(sdata, ifibss->ssid, - ifibss->ssid_len, channels, num, - scan_width); + + if (ifibss->fixed_channel) { + num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy, + &ifibss->chandef, + channels, + ARRAY_SIZE(channels)); + ieee80211_request_ibss_scan(sdata, ifibss->ssid, + ifibss->ssid_len, channels, + num, scan_width); + } else { + ieee80211_request_ibss_scan(sdata, ifibss->ssid, + ifibss->ssid_len, NULL, + 0, scan_width); + } } else { int interval = IEEE80211_SCAN_INTERVAL; @@ -1732,7 +1740,6 @@ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local) if (sdata->vif.type != NL80211_IFTYPE_ADHOC) continue; sdata->u.ibss.last_scan_completed = jiffies; - ieee80211_queue_work(&local->hw, &sdata->work); } mutex_unlock(&local->iflist_mtx); } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 5322b4c71630..6837a46ca4a2 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -92,7 +92,7 @@ struct ieee80211_fragment_entry { u16 extra_len; u16 last_frag; u8 rx_queue; - bool ccmp; /* Whether fragments were encrypted with CCMP */ + bool check_sequential_pn; /* needed for CCMP/GCMP */ u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ }; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index c9e325d2e120..bcb0a1b64556 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -977,7 +977,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, if (sdata->vif.txq) { struct txq_info *txqi = to_txq_info(sdata->vif.txq); + spin_lock_bh(&txqi->queue.lock); ieee80211_purge_tx_queue(&local->hw, &txqi->queue); + spin_unlock_bh(&txqi->queue.lock); + atomic_set(&sdata->txqs_len[txqi->txq.ac], 0); } @@ -1747,7 +1750,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) { - free_netdev(ndev); + ieee80211_if_free(ndev); return ret; } @@ -1833,7 +1836,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = register_netdevice(ndev); if (ret) { - free_netdev(ndev); + ieee80211_if_free(ndev); return ret; } } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index fa28500f28fd..6f85b6ab8e51 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1370,17 +1370,6 @@ out: sdata_unlock(sdata); } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - if (ieee80211_vif_is_mesh(&sdata->vif) && - ieee80211_sdata_running(sdata)) - ieee80211_queue_work(&local->hw, &sdata->work); - rcu_read_unlock(); -} void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) { diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index a1596344c3ba..4a8019f79fb2 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -362,14 +362,10 @@ static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP; } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local); - void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata); void ieee80211s_stop(void); #else -static inline void -ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) {} static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3aa04344942b..83097c3832d1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4003,8 +4003,6 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) if (!ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR)) ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.monitor_work); - /* and do all the other regular work too */ - ieee80211_queue_work(&sdata->local->hw, &sdata->work); } } diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 3ece7d1034c8..b54f398cda5d 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -711,7 +711,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta) * computing cur_tp */ tmp_mrs = &mi->r[idx].stats; - tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma); + tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10; tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024; return tmp_cur_tp; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 3928dbd24e25..239ed6e92b89 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -691,7 +691,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) if (likely(sta->ampdu_mlme.tid_tx[tid])) return; - ieee80211_start_tx_ba_session(pubsta, tid, 5000); + ieee80211_start_tx_ba_session(pubsta, tid, 0); } static void @@ -871,7 +871,7 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, * - if station is in dynamic SMPS (and streams > 1) * - for fallback rates, to increase chances of getting through */ - if (offset > 0 && + if (offset > 0 || (mi->sta->smps_mode == IEEE80211_SMPS_DYNAMIC && group->streams > 1)) { ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts; @@ -1334,7 +1334,8 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) prob = mi->groups[i].rates[j].prob_ewma; /* convert tp_avg from pkt per second in kbps */ - tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024; + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10; + tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024; return tp_avg; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 82af407fea7a..a3bb8f7f5fc5 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1754,7 +1754,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, entry->seq = seq; entry->rx_queue = rx_queue; entry->last_frag = frag; - entry->ccmp = 0; + entry->check_sequential_pn = false; entry->extra_len = 0; return entry; @@ -1850,15 +1850,27 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) rx->seqno_idx, &(rx->skb)); if (rx->key && (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) && + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && ieee80211_has_protected(fc)) { int queue = rx->security_idx; - /* Store CCMP PN so that we can verify that the next - * fragment has a sequential PN value. */ - entry->ccmp = 1; + + /* Store CCMP/GCMP PN so that we can verify that the + * next fragment has a sequential PN value. + */ + entry->check_sequential_pn = true; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); + BUILD_BUG_ON(offsetof(struct ieee80211_key, + u.ccmp.rx_pn) != + offsetof(struct ieee80211_key, + u.gcmp.rx_pn)); + BUILD_BUG_ON(sizeof(rx->key->u.ccmp.rx_pn[queue]) != + sizeof(rx->key->u.gcmp.rx_pn[queue])); + BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != + IEEE80211_GCMP_PN_LEN); } return RX_QUEUED; } @@ -1873,15 +1885,21 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } - /* Verify that MPDUs within one MSDU have sequential PN values. - * (IEEE 802.11i, 8.3.3.4.5) */ - if (entry->ccmp) { + /* "The receiver shall discard MSDUs and MMPDUs whose constituent + * MPDU PN values are not incrementing in steps of 1." + * see IEEE P802.11-REVmc/D5.0, 12.5.3.4.4, item d (for CCMP) + * and IEEE P802.11-REVmc/D5.0, 12.5.5.4.4, item d (for GCMP) + */ + if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; int queue; + if (!rx->key || (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256)) + rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) return RX_DROP_UNUSABLE; memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { @@ -2232,7 +2250,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211_local *local = rx->local; struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - u16 q, hdrlen; + u16 ac, q, hdrlen; hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -2301,7 +2319,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) ether_addr_equal(sdata->vif.addr, hdr->addr3)) return RX_CONTINUE; - q = ieee80211_select_queue_80211(sdata, skb, hdr); + ac = ieee80211_select_queue_80211(sdata, skb, hdr); + q = sdata->vif.hw_queue[ac]; if (ieee80211_queue_stopped(&local->hw, q)) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion); return RX_DROP_MONITOR; @@ -3367,6 +3386,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) return false; /* ignore action frames to TDLS-peers */ if (ieee80211_is_action(hdr->frame_control) && + !is_broadcast_ether_addr(bssid) && !ether_addr_equal(bssid, hdr->addr1)) return false; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index a413e52f7691..acbe182b75d1 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -314,6 +314,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) bool was_scanning = local->scanning; struct cfg80211_scan_request *scan_req; struct ieee80211_sub_if_data *scan_sdata; + struct ieee80211_sub_if_data *sdata; lockdep_assert_held(&local->mtx); @@ -373,7 +374,16 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); - ieee80211_mesh_notify_scan_completed(local); + + /* Requeue all the work that might have been ignored while + * the scan was in progress; if there was none this will + * just be a no-op for the particular interface. + */ + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (ieee80211_sdata_running(sdata)) + ieee80211_queue_work(&sdata->local->hw, &sdata->work); + } + if (was_scanning) ieee80211_start_next_roc(local); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f91d1873218c..67066d048e6f 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -256,11 +256,11 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) } /* Caller must hold local->sta_mtx */ -static void sta_info_hash_add(struct ieee80211_local *local, - struct sta_info *sta) +static int sta_info_hash_add(struct ieee80211_local *local, + struct sta_info *sta) { - rhashtable_insert_fast(&local->sta_hash, &sta->hash_node, - sta_rht_params); + return rhashtable_insert_fast(&local->sta_hash, &sta->hash_node, + sta_rht_params); } static void sta_deliver_ps_frames(struct work_struct *wk) @@ -484,11 +484,17 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - struct station_info sinfo; + struct station_info *sinfo; int err = 0; lockdep_assert_held(&local->sta_mtx); + sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL); + if (!sinfo) { + err = -ENOMEM; + goto out_err; + } + /* check if STA exists already */ if (sta_info_get_bss(sdata, sta->sta.addr)) { err = -EEXIST; @@ -503,7 +509,9 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) set_sta_flag(sta, WLAN_STA_BLOCK_BA); /* make the station visible */ - sta_info_hash_add(local, sta); + err = sta_info_hash_add(local, sta); + if (err) + goto out_drop_sta; list_add_tail_rcu(&sta->list, &local->sta_list); @@ -520,10 +528,9 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) ieee80211_sta_debugfs_add(sta); rate_control_add_sta_debugfs(sta); - memset(&sinfo, 0, sizeof(sinfo)); - sinfo.filled = 0; - sinfo.generation = local->sta_generation; - cfg80211_new_sta(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL); + sinfo->generation = local->sta_generation; + cfg80211_new_sta(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); + kfree(sinfo); sta_dbg(sdata, "Inserted STA %pM\n", sta->sta.addr); @@ -538,6 +545,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_remove: sta_info_hash_del(local, sta); list_del_rcu(&sta->list); + out_drop_sta: local->num_sta--; synchronize_net(); __cleanup_single_sta(sta); @@ -882,7 +890,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - struct station_info sinfo = {}; + struct station_info *sinfo; int ret; /* @@ -920,8 +928,11 @@ static void __sta_info_destroy_part2(struct sta_info *sta) sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr); - sta_set_sinfo(sta, &sinfo); - cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL); + sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL); + if (sinfo) + sta_set_sinfo(sta, sinfo); + cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); + kfree(sinfo); rate_control_remove_sta_debugfs(sta); ieee80211_sta_debugfs_remove(sta); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c32fc411a911..881bc2072809 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -518,6 +518,9 @@ static struct net_device *find_outdev(struct net *net, if (!dev) return ERR_PTR(-ENODEV); + if (IS_ERR(dev)) + return dev; + /* The caller is holding rtnl anyways, so release the dev reference */ dev_put(dev); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index f57b4dcdb233..4da560005b0e 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1757,15 +1757,34 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int cp = pp->conn_in_get(ipvs, af, skb, &iph); conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && - is_new_conn(skb, &iph) && cp && - ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && - unlikely(!atomic_read(&cp->dest->weight))) || - unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) { - if (!atomic_read(&cp->n_control)) - ip_vs_conn_expire_now(cp); - __ip_vs_conn_put(cp); - cp = NULL; + if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + bool uses_ct = false, resched = false; + + if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && + unlikely(!atomic_read(&cp->dest->weight))) { + resched = true; + uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + if (!atomic_read(&cp->n_control)) { + resched = true; + } else { + /* Do not reschedule controlling connection + * that uses conntrack while it is still + * referenced by controlled connection(s). + */ + resched = !uses_ct; + } + } + + if (resched) { + if (!atomic_read(&cp->n_control)) + ip_vs_conn_expire_now(cp); + __ip_vs_conn_put(cp); + if (uses_ct) + return NF_DROP; + cp = NULL; + } } if (unlikely(!cp)) { diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index 1b8d594e493a..0a6eb5c0d9e9 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -70,10 +70,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) const char *dptr; int retc; - ip_vs_fill_iph_skb(p->af, skb, false, &iph); + retc = ip_vs_fill_iph_skb(p->af, skb, false, &iph); /* Only useful with UDP */ - if (iph.protocol != IPPROTO_UDP) + if (!retc || iph.protocol != IPPROTO_UDP) return -EINVAL; /* todo: IPv6 fragments: * I think this only should be done for the first fragment. /HS @@ -88,7 +88,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) dptr = skb->data + dataoff; datalen = skb->len - dataoff; - if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen)) + if (get_callid(dptr, 0, datalen, &matchoff, &matchlen)) return -EINVAL; /* N.B: pe_data is only set on success, diff --git a/net/netfilter/xt_qtaguid.c b/net/netfilter/xt_qtaguid.c index e1442bfb668d..822dc3c3bce1 100644 --- a/net/netfilter/xt_qtaguid.c +++ b/net/netfilter/xt_qtaguid.c @@ -1689,7 +1689,7 @@ static bool qtaguid_mt(const struct sk_buff *skb, struct xt_action_param *par) /* default: Fall through and do UID releated work */ } - sk = skb->sk; + sk = skb_to_full_sk(skb); /* * When in TCP_TIME_WAIT the sk is not a "struct sock" but * "struct inet_timewait_sock" which is missing fields. diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 59651af8cc27..992b35fb8615 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1305,7 +1305,7 @@ static int netlink_release(struct socket *sock) skb_queue_purge(&sk->sk_write_queue); - if (nlk->portid) { + if (nlk->portid && nlk->bound) { struct netlink_notify n = { .net = sock_net(sk), .protocol = sk->sk_protocol, diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 91a8b004dc51..deadfdab1bc3 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -336,12 +336,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, unsigned short gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; struct sk_buff *segs, *nskb; - struct ovs_skb_cb ovs_cb; int err; - ovs_cb = *OVS_CB(skb); + BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET); segs = __skb_gso_segment(skb, NETIF_F_SG, false); - *OVS_CB(skb) = ovs_cb; if (IS_ERR(segs)) return PTR_ERR(segs); if (segs == NULL) @@ -359,7 +357,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, /* Queue all of the segments. */ skb = segs; do { - *OVS_CB(skb) = ovs_cb; if (gso_type & SKB_GSO_UDP && skb != segs) key = &later_key; diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 1605691d9414..d933cb89efac 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -90,7 +90,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) int err; struct vxlan_config conf = { .no_share = true, - .flags = VXLAN_F_COLLECT_METADATA, + .flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX, }; if (!options) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 992396aa635c..da1ae0e13cb5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1916,6 +1916,10 @@ retry: goto retry; } + if (!dev_validate_header(dev, skb->data, len)) { + err = -EINVAL; + goto out_unlock; + } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; @@ -2326,18 +2330,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } -static bool ll_header_truncated(const struct net_device *dev, int len) -{ - /* net device doesn't like empty head */ - if (unlikely(len < dev->hard_header_len)) { - net_warn_ratelimited("%s: packet size is too short (%d < %d)\n", - current->comm, len, dev->hard_header_len); - return true; - } - - return false; -} - static void tpacket_set_protocol(const struct net_device *dev, struct sk_buff *skb) { @@ -2420,19 +2412,19 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, if (unlikely(err < 0)) return -EINVAL; } else if (dev->hard_header_len) { - if (ll_header_truncated(dev, tp_len)) - return -EINVAL; + int hdrlen = min_t(int, dev->hard_header_len, tp_len); skb_push(skb, dev->hard_header_len); - err = skb_store_bits(skb, 0, data, - dev->hard_header_len); + err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; + if (!dev_validate_header(dev, skb->data, hdrlen)) + return -EINVAL; if (!skb->protocol) tpacket_set_protocol(dev, skb); - data += dev->hard_header_len; - to_write -= dev->hard_header_len; + data += hdrlen; + to_write -= hdrlen; } offset = offset_in_page(data); @@ -2763,9 +2755,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; - } else { - if (ll_header_truncated(dev, len)) - goto out_free; } /* Returns -EFAULT on error */ @@ -2773,6 +2762,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (err) goto out_free; + if (sock->type == SOCK_RAW && + !dev_validate_header(dev, skb->data, len)) { + err = -EINVAL; + goto out_free; + } + sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); if (!gso_type && (len > dev->mtu + reserve + extra_len) && diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 10d42f3220ab..f925753668a7 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -377,6 +377,10 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, struct sockaddr_pn sa; u16 len; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; + /* check we have at least a full Phonet header */ if (!pskb_pull(skb, sizeof(struct phonethdr))) goto out; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 9f843bbe8c10..d778d99326df 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1097,17 +1097,6 @@ static unsigned int rfkill_fop_poll(struct file *file, poll_table *wait) return res; } -static bool rfkill_readable(struct rfkill_data *data) -{ - bool r; - - mutex_lock(&data->mtx); - r = !list_empty(&data->events); - mutex_unlock(&data->mtx); - - return r; -} - static ssize_t rfkill_fop_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { @@ -1124,8 +1113,11 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, goto out; } mutex_unlock(&data->mtx); + /* since we re-check and it just compares pointers, + * using !list_empty() without locking isn't a problem + */ ret = wait_event_interruptible(data->read_wait, - rfkill_readable(data)); + !list_empty(&data->events)); mutex_lock(&data->mtx); if (ret) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 57692947ebbe..95b021243233 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -252,23 +252,28 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC, mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, sizeof(key->eth.src)); + fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE, &mask->basic.n_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.n_proto)); + if (key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) { fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.ip_proto)); } - if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + + if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) { + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, sizeof(key->ipv4.src)); fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST, &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK, sizeof(key->ipv4.dst)); - } else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + } else if (tb[TCA_FLOWER_KEY_IPV6_SRC] || tb[TCA_FLOWER_KEY_IPV6_DST]) { + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC, &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK, sizeof(key->ipv6.src)); @@ -276,6 +281,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK, sizeof(key->ipv6.dst)); } + if (key->basic.ip_proto == IPPROTO_TCP) { fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, &mask->tp.src, TCA_FLOWER_UNSPEC, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b5c2cf2aa6d4..af1acf009866 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1852,6 +1852,7 @@ reset: } tp = old_tp; + protocol = tc_skb_protocol(skb); goto reclassify; #endif } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ec529121f38a..ce46f1c7f133 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -526,6 +526,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1, } return 0; } + if (addr1->v6.sin6_port != addr2->v6.sin6_port) + return 0; if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; /* If this is a linklocal address, compare the scope_id. */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 3d9ea9a48289..8b4ff315695e 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -60,6 +60,8 @@ #include <net/inet_common.h> #include <net/inet_ecn.h> +#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) + /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; @@ -1352,6 +1354,8 @@ static __init int sctp_init(void) unsigned long limit; int max_share; int order; + int num_entries; + int max_entry_order; sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); @@ -1404,14 +1408,24 @@ static __init int sctp_init(void) /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. + * Though not identical. Start by getting a goal size */ if (totalram_pages >= (128 * 1024)) goal = totalram_pages >> (22 - PAGE_SHIFT); else goal = totalram_pages >> (24 - PAGE_SHIFT); - for (order = 0; (1UL << order) < goal; order++) - ; + /* Then compute the page order for said goal */ + order = get_order(goal); + + /* Now compute the required page order for the maximum sized table we + * want to create + */ + max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES * + sizeof(struct sctp_bind_hashbucket)); + + /* Limit the page order by that maximum hash table size */ + order = min(order, max_entry_order); do { sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE / @@ -1445,20 +1459,35 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } - /* Allocate and initialize the SCTP port hash table. */ + /* Allocate and initialize the SCTP port hash table. + * Note that order is initalized to start at the max sized + * table we want to support. If we can't get that many pages + * reduce the order and try again + */ do { - sctp_port_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_bind_hashbucket); - if ((sctp_port_hashsize > (64 * 1024)) && order > 0) - continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); + if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); status = -ENOMEM; goto err_bhash_alloc; } + + /* Now compute the number of entries that will fit in the + * port hash space we allocated + */ + num_entries = (1UL << order) * PAGE_SIZE / + sizeof(struct sctp_bind_hashbucket); + + /* And finish by rounding it down to the nearest power of two + * this wastes some memory of course, but its needed because + * the hash function operates based on the assumption that + * that the number of entries is a power of two + */ + sctp_port_hashsize = rounddown_pow_of_two(num_entries); + for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ef1d90fdc773..be1489fc3234 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5542,6 +5542,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; + int i; if (!ep->auth_enable) return -EACCES; @@ -5559,8 +5560,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, return -EFAULT; if (put_user(num_idents, &p->shmac_num_idents)) return -EFAULT; - if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len)) - return -EFAULT; + for (i = 0; i < num_idents; i++) { + __u16 hmacid = ntohs(hmacs->hmac_ids[i]); + + if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16))) + return -EFAULT; + } return 0; } @@ -6640,6 +6645,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -6663,6 +6669,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 26d50c565f54..3e0fc5127225 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -320,7 +320,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, struct ctl_table tbl; bool changed = false; char *none = "none"; - char tmp[8]; + char tmp[8] = {0}; int ret; memset(&tbl, 0, sizeof(struct ctl_table)); diff --git a/net/socket.c b/net/socket.c index d730ef9dfbf0..263b334ec5e4 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2238,31 +2238,31 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, break; } -out_put: - fput_light(sock->file, fput_needed); - if (err == 0) - return datagrams; + goto out_put; - if (datagrams != 0) { + if (datagrams == 0) { + datagrams = err; + goto out_put; + } + + /* + * We may return less entries than requested (vlen) if the + * sock is non block and there aren't enough datagrams... + */ + if (err != -EAGAIN) { /* - * We may return less entries than requested (vlen) if the - * sock is non block and there aren't enough datagrams... + * ... or if recvmsg returns an error after we + * received some datagrams, where we record the + * error to return on the next call or if the + * app asks about it using getsockopt(SO_ERROR). */ - if (err != -EAGAIN) { - /* - * ... or if recvmsg returns an error after we - * received some datagrams, where we record the - * error to return on the next call or if the - * app asks about it using getsockopt(SO_ERROR). - */ - sock->sk->sk_err = -err; - } - - return datagrams; + sock->sk->sk_err = -err; } +out_put: + fput_light(sock->file, fput_needed); - return err; + return datagrams; } SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 5e4f815c2b34..63fb5ee212cf 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1182,14 +1182,14 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h) } crq->q.reader = 0; - crq->item = cache_get(h); crq->buf = buf; crq->len = 0; crq->readers = 0; spin_lock(&queue_lock); - if (test_bit(CACHE_PENDING, &h->flags)) + if (test_bit(CACHE_PENDING, &h->flags)) { + crq->item = cache_get(h); list_add_tail(&crq->q.list, &detail->queue); - else + } else /* Lost a race, no longer PENDING, so don't enqueue */ ret = -EAGAIN; spin_unlock(&queue_lock); @@ -1225,7 +1225,7 @@ int qword_get(char **bpp, char *dest, int bufsize) if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; - while (len < bufsize) { + while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2ffaf6a79499..027c9ef8a263 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -398,7 +398,6 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (unlikely(!sock)) return -ENOTSOCK; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags); if (base != 0) { addr = NULL; addrlen = 0; @@ -442,7 +441,6 @@ static void xs_nospace_callback(struct rpc_task *task) struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); transport->inet->sk_write_pending--; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } /** @@ -467,20 +465,11 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { - if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) { - /* - * Notify TCP that we're limited by the application - * window size - */ - set_bit(SOCK_NOSPACE, &transport->sock->flags); - sk->sk_write_pending++; - /* ...and wait for more buffer space */ - xprt_wait_for_buffer_space(task, xs_nospace_callback); - } - } else { - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + /* wait for more buffer space */ + sk->sk_write_pending++; + xprt_wait_for_buffer_space(task, xs_nospace_callback); + } else ret = -ENOTCONN; - } spin_unlock_bh(&xprt->transport_lock); @@ -616,9 +605,6 @@ process_status: case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ENETUNREACH: case -ENOBUFS: case -EPIPE: @@ -626,7 +612,10 @@ process_status: case -EPERM: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -706,16 +695,16 @@ static int xs_tcp_send_request(struct rpc_task *task) case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ECONNRESET: case -ECONNREFUSED: case -ENOTCONN: case -EADDRINUSE: case -ENOBUFS: case -EPIPE: - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -1609,19 +1598,23 @@ static void xs_tcp_state_change(struct sock *sk) static void xs_write_space(struct sock *sk) { - struct socket *sock; + struct socket_wq *wq; struct rpc_xprt *xprt; - if (unlikely(!(sock = sk->sk_socket))) + if (!sk->sk_socket) return; - clear_bit(SOCK_NOSPACE, &sock->flags); + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); if (unlikely(!(xprt = xprt_from_sock(sk)))) return; - if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0) - return; + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) + goto out; xprt_write_space(xprt); +out: + rcu_read_unlock(); } /** diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index f34e535e93bd..d5d7132ac847 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -20,6 +20,7 @@ #include <linux/list.h> #include <linux/workqueue.h> #include <linux/if_vlan.h> +#include <linux/rtnetlink.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -565,7 +566,6 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, } EXPORT_SYMBOL_GPL(switchdev_port_obj_dump); -static DEFINE_MUTEX(switchdev_mutex); static RAW_NOTIFIER_HEAD(switchdev_notif_chain); /** @@ -580,9 +580,9 @@ int register_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&switchdev_mutex); + rtnl_lock(); err = raw_notifier_chain_register(&switchdev_notif_chain, nb); - mutex_unlock(&switchdev_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(register_switchdev_notifier); @@ -598,9 +598,9 @@ int unregister_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&switchdev_mutex); + rtnl_lock(); err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb); - mutex_unlock(&switchdev_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); @@ -614,16 +614,17 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * Call all network notifier blocks. This should be called by driver * when it needs to propagate hardware event. * Return values are same as for atomic_notifier_call_chain(). + * rtnl_lock must be held. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info) { int err; + ASSERT_RTNL(); + info->dev = dev; - mutex_lock(&switchdev_mutex); err = raw_notifier_call_chain(&switchdev_notif_chain, val, info); - mutex_unlock(&switchdev_mutex); return err; } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 9dc239dfe192..92e367a0a5ce 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -399,8 +399,10 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_LINK_GET); - if (!hdr) + if (!hdr) { + tipc_bcast_unlock(net); return -EMSGSIZE; + } attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK); if (!attrs) diff --git a/net/tipc/node.c b/net/tipc/node.c index 20cddec0a43c..3926b561f873 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -168,12 +168,6 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) skb_queue_head_init(&n_ptr->bc_entry.inputq1); __skb_queue_head_init(&n_ptr->bc_entry.arrvq); skb_queue_head_init(&n_ptr->bc_entry.inputq2); - hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); - list_for_each_entry_rcu(temp_node, &tn->node_list, list) { - if (n_ptr->addr < temp_node->addr) - break; - } - list_add_tail_rcu(&n_ptr->list, &temp_node->list); n_ptr->state = SELF_DOWN_PEER_LEAVING; n_ptr->signature = INVALID_NODE_SIG; n_ptr->active_links[0] = INVALID_BEARER_ID; @@ -193,6 +187,12 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) tipc_node_get(n_ptr); setup_timer(&n_ptr->timer, tipc_node_timeout, (unsigned long)n_ptr); n_ptr->keepalive_intv = U32_MAX; + hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { + if (n_ptr->addr < temp_node->addr) + break; + } + list_add_tail_rcu(&n_ptr->list, &temp_node->list); exit: spin_unlock_bh(&tn->node_list_lock); return n_ptr; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b53246fb0412..e53003cf7703 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -673,7 +673,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct iov_iter save = msg->msg_iter; uint mtu; int rc; @@ -687,14 +687,16 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, msg_set_nameupper(mhdr, seq->upper); msg_set_hdr_sz(mhdr, MCAST_H_SIZE); + skb_queue_head_init(&pktchain); + new_mtu: mtu = tipc_bcast_get_mtu(net); - rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain); if (unlikely(rc < 0)) return rc; do { - rc = tipc_bcast_xmit(net, pktchain); + rc = tipc_bcast_xmit(net, &pktchain); if (likely(!rc)) return dsz; @@ -704,7 +706,7 @@ new_mtu: if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { msg->msg_iter = save; goto new_mtu; @@ -863,7 +865,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; u32 dnode, dport; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct sk_buff *skb; struct tipc_name_seq *seq; struct iov_iter save; @@ -924,17 +926,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) msg_set_hdr_sz(mhdr, BASIC_H_SIZE); } + skb_queue_head_init(&pktchain); save = m->msg_iter; new_mtu: mtu = tipc_node_get_mtu(net, dnode, tsk->portid); - rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain); if (rc < 0) return rc; do { - skb = skb_peek(pktchain); + skb = skb_peek(&pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid); + rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid); if (likely(!rc)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; @@ -946,7 +949,7 @@ new_mtu: if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { m->msg_iter = save; goto new_mtu; @@ -1016,7 +1019,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); u32 portid = tsk->portid; int rc = -EINVAL; @@ -1044,17 +1047,19 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); dnode = tsk_peer_node(tsk); + skb_queue_head_init(&pktchain); next: save = m->msg_iter; mtu = tsk->max_pkt; send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); - rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, sent, send, mtu, &pktchain); if (unlikely(rc < 0)) return rc; + do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_node_xmit(net, pktchain, dnode, portid); + rc = tipc_node_xmit(net, &pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; @@ -1063,7 +1068,7 @@ next: goto next; } if (rc == -EMSGSIZE) { - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); m->msg_iter = save; @@ -1077,7 +1082,7 @@ next: rc = tipc_wait_for_sndpkt(sock, &timeo); } while (!rc); - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); return sent ? sent : rc; } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 350cca33ee0a..69ee2eeef968 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -289,15 +289,14 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid, struct sockaddr_tipc *addr, void *usr_data, void *buf, size_t len) { - struct tipc_subscriber *subscriber = usr_data; + struct tipc_subscriber *subscrb = usr_data; struct tipc_subscription *sub = NULL; struct tipc_net *tn = net_generic(net, tipc_net_id); - tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscriber, &sub); - if (sub) - tipc_nametbl_subscribe(sub); - else - tipc_conn_terminate(tn->topsrv, subscriber->conid); + if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub)) + return tipc_conn_terminate(tn->topsrv, subscrb->conid); + + tipc_nametbl_subscribe(sub); } /* Handle one request to establish a new subscriber */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ef05cd9403d4..898a53a562b8 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1496,7 +1496,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) UNIXCB(skb).fp = NULL; for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->fp[i]); + unix_notinflight(scm->fp->user, scm->fp->fp[i]); } static void unix_destruct_scm(struct sk_buff *skb) @@ -1513,6 +1513,21 @@ static void unix_destruct_scm(struct sk_buff *skb) sock_wfree(skb); } +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + #define MAX_RECURSION_LEVEL 4 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) @@ -1521,6 +1536,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) unsigned char max_level = 0; int unix_sock_count = 0; + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + for (i = scm->fp->count - 1; i >= 0; i--) { struct sock *sk = unix_get_socket(scm->fp->fp[i]); @@ -1542,10 +1560,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) if (!UNIXCB(skb).fp) return -ENOMEM; - if (unix_sock_count) { - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); - } + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); return max_level; } @@ -1765,7 +1781,12 @@ restart_locked: goto out_unlock; } - if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + /* other == sk && unix_peer(other) != sk if + * - unix_peer(sk) == NULL, destination address bound to sk + * - unix_peer(sk) == sk by time of get but disconnected before lock + */ + if (other != sk && + unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); @@ -2254,13 +2275,15 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) size_t size = state->size; unsigned int last_len; - err = -EINVAL; - if (sk->sk_state != TCP_ESTABLISHED) + if (unlikely(sk->sk_state != TCP_ESTABLISHED)) { + err = -EINVAL; goto out; + } - err = -EOPNOTSUPP; - if (flags & MSG_OOB) + if (unlikely(flags & MSG_OOB)) { + err = -EOPNOTSUPP; goto out; + } target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, noblock); @@ -2306,9 +2329,11 @@ again: goto unlock; unix_state_unlock(sk); - err = -EAGAIN; - if (!timeo) + if (!timeo) { + err = -EAGAIN; break; + } + mutex_unlock(&u->readlock); timeo = unix_stream_data_wait(sk, timeo, last, @@ -2316,6 +2341,7 @@ again: if (signal_pending(current)) { err = sock_intr_errno(timeo); + scm_destroy(&scm); goto out; } diff --git a/net/unix/diag.c b/net/unix/diag.c index c512f64d5287..4d9679701a6d 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -220,7 +220,7 @@ done: return skb->len; } -static struct sock *unix_lookup_by_ino(int ino) +static struct sock *unix_lookup_by_ino(unsigned int ino) { int i; struct sock *sk; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index a73a226f2d33..6a0d48525fcf 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -116,15 +116,15 @@ struct sock *unix_get_socket(struct file *filp) * descriptor if it is for an AF_UNIX socket. */ -void unix_inflight(struct file *fp) +void unix_inflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); - if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); @@ -132,25 +132,28 @@ void unix_inflight(struct file *fp) BUG_ON(list_empty(&u->link)); } unix_tot_inflight++; - spin_unlock(&unix_gc_lock); } + user->unix_inflight++; + spin_unlock(&unix_gc_lock); } -void unix_notinflight(struct file *fp) +void unix_notinflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; - spin_unlock(&unix_gc_lock); } + user->unix_inflight--; + spin_unlock(&unix_gc_lock); } static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), diff --git a/net/wireless/core.c b/net/wireless/core.c index b0915515640e..8f0bac7e03c4 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1147,6 +1147,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, return NOTIFY_DONE; } + wireless_nlevent_flush(); + return NOTIFY_OK; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 75b0d23ee882..5d89f13a98db 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13161,7 +13161,7 @@ static int nl80211_netlink_notify(struct notifier_block * nb, struct wireless_dev *wdev; struct cfg80211_beacon_registration *reg, *tmp; - if (state != NETLINK_URELEASE) + if (state != NETLINK_URELEASE || notify->protocol != NETLINK_GENERIC) return NOTIFY_DONE; rcu_read_lock(); diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index c8717c1d082e..b50ee5d622e1 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -342,6 +342,40 @@ static const int compat_event_type_size[] = { /* IW event code */ +void wireless_nlevent_flush(void) +{ + struct sk_buff *skb; + struct net *net; + + ASSERT_RTNL(); + + for_each_net(net) { + while ((skb = skb_dequeue(&net->wext_nlevents))) + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, + GFP_KERNEL); + } +} +EXPORT_SYMBOL_GPL(wireless_nlevent_flush); + +static int wext_netdev_notifier_call(struct notifier_block *nb, + unsigned long state, void *ptr) +{ + /* + * When a netdev changes state in any way, flush all pending messages + * to avoid them going out in a strange order, e.g. RTM_NEWLINK after + * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close() + * or similar - all of which could otherwise happen due to delays from + * schedule_work(). + */ + wireless_nlevent_flush(); + + return NOTIFY_OK; +} + +static struct notifier_block wext_netdev_notifier = { + .notifier_call = wext_netdev_notifier_call, +}; + static int __net_init wext_pernet_init(struct net *net) { skb_queue_head_init(&net->wext_nlevents); @@ -360,7 +394,12 @@ static struct pernet_operations wext_pernet_ops = { static int __init wireless_nlevent_init(void) { - return register_pernet_subsys(&wext_pernet_ops); + int err = register_pernet_subsys(&wext_pernet_ops); + + if (err) + return err; + + return register_netdevice_notifier(&wext_netdev_notifier); } subsys_initcall(wireless_nlevent_init); @@ -368,17 +407,8 @@ subsys_initcall(wireless_nlevent_init); /* Process events generated by the wireless layer or the driver. */ static void wireless_nlevent_process(struct work_struct *work) { - struct sk_buff *skb; - struct net *net; - rtnl_lock(); - - for_each_net(net) { - while ((skb = skb_dequeue(&net->wext_nlevents))) - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, - GFP_KERNEL); - } - + wireless_nlevent_flush(); rtnl_unlock(); } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index ad7f5b3f9b61..1c4ad477ce93 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; skb_dst_force(skb); + dev_hold(skb->dev); nexthdr = x->type->input(x, skb); if (nexthdr == -EINPROGRESS) return 0; resume: + dev_put(skb->dev); + spin_lock(&x->lock); if (nexthdr <= 0) { if (nexthdr == -EBADMSG) { diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index cc3676eb6239..ff4a91fcab9f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -167,6 +167,8 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb { struct sk_buff *segs; + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); + BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, 0); kfree_skb(skb); if (IS_ERR(segs)) diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter index 23e78dcd12bf..38b64f487315 100755 --- a/scripts/bloat-o-meter +++ b/scripts/bloat-o-meter @@ -58,8 +58,8 @@ for name in common: delta.sort() delta.reverse() -print "add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ - (add, remove, grow, shrink, up, -down, up-down) -print "%-40s %7s %7s %+7s" % ("function", "old", "new", "delta") +print("add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ + (add, remove, grow, shrink, up, -down, up-down)) +print("%-40s %7s %7s %+7s" % ("function", "old", "new", "delta")) for d, n in delta: - if d: print "%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d) + if d: print("%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d)) diff --git a/scripts/coccinelle/iterators/use_after_iter.cocci b/scripts/coccinelle/iterators/use_after_iter.cocci index f085f5968c52..ce8cc9c006e5 100644 --- a/scripts/coccinelle/iterators/use_after_iter.cocci +++ b/scripts/coccinelle/iterators/use_after_iter.cocci @@ -123,7 +123,7 @@ list_remove_head(x,c,...) | sizeof(<+...c...+>) | -&c->member + &c->member | c = E | diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index d79cba4ce3eb..ebced77deb9c 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -96,13 +96,15 @@ savedefconfig: $(obj)/conf defconfig: $(obj)/conf ifeq ($(KBUILD_DEFCONFIG),) $< $(silent) --defconfig $(Kconfig) -else ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG)),) +else +ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG)),) @$(kecho) "*** Default configuration is based on '$(KBUILD_DEFCONFIG)'" $(Q)$< $(silent) --defconfig=arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG) $(Kconfig) else @$(kecho) "*** Default configuration is based on target '$(KBUILD_DEFCONFIG)'" $(Q)$(MAKE) -f $(srctree)/Makefile $(KBUILD_DEFCONFIG) endif +endif %_defconfig: $(obj)/conf $(Q)$< $(silent) --defconfig=arch/$(SRCARCH)/configs/$@ $(Kconfig) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 0b7dc2fd7bac..dd243d2abd87 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -267,10 +267,8 @@ int conf_read_simple(const char *name, int def) if (in) goto load; sym_add_change_count(1); - if (!sym_defconfig_list) { - sym_calc_value(modules_sym); + if (!sym_defconfig_list) return 1; - } for_all_defaults(sym_defconfig_list, prop) { if (expr_calc_value(prop->visible.expr) == no || @@ -403,7 +401,6 @@ setsym: } free(line); fclose(in); - sym_calc_value(modules_sym); return 0; } @@ -414,8 +411,12 @@ int conf_read(const char *name) sym_set_change_count(0); - if (conf_read_simple(name, S_DEF_USER)) + if (conf_read_simple(name, S_DEF_USER)) { + sym_calc_value(modules_sym); return 1; + } + + sym_calc_value(modules_sym); for_all_symbols(i, sym) { sym_calc_value(sym); @@ -846,6 +847,7 @@ static int conf_split_config(void) name = conf_get_autoconfig_name(); conf_read_simple(name, S_DEF_AUTO); + sym_calc_value(modules_sym); if (chdir("include/config")) return 1; diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh index 198580d245e0..1659b409ef10 100755 --- a/scripts/ld-version.sh +++ b/scripts/ld-version.sh @@ -1,7 +1,7 @@ #!/usr/bin/awk -f # extract linker version number from stdin and turn into single number { - gsub(".*)", ""); + gsub(".*\\)", ""); split($1,a, "."); print a[1]*10000000 + a[2]*100000 + a[3]*10000 + a[4]*100 + a[5]; exit diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index dacf71a43ad4..ba6c34ea5429 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -62,7 +62,7 @@ vmlinux_link() -Wl,--start-group \ ${KBUILD_VMLINUX_MAIN} \ -Wl,--end-group \ - -lutil -lrt ${1} + -lutil -lrt -lpthread ${1} rm -f linux fi } diff --git a/scripts/package/mkspec b/scripts/package/mkspec index 71004daefe31..fe44d68e9344 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -131,11 +131,11 @@ echo 'rm -rf $RPM_BUILD_ROOT' echo "" echo "%post" echo "if [ -x /sbin/installkernel -a -r /boot/vmlinuz-$KERNELRELEASE -a -r /boot/System.map-$KERNELRELEASE ]; then" -echo "cp /boot/vmlinuz-$KERNELRELEASE /boot/vmlinuz-$KERNELRELEASE-rpm" -echo "cp /boot/System.map-$KERNELRELEASE /boot/System.map-$KERNELRELEASE-rpm" +echo "cp /boot/vmlinuz-$KERNELRELEASE /boot/.vmlinuz-$KERNELRELEASE-rpm" +echo "cp /boot/System.map-$KERNELRELEASE /boot/.System.map-$KERNELRELEASE-rpm" echo "rm -f /boot/vmlinuz-$KERNELRELEASE /boot/System.map-$KERNELRELEASE" -echo "/sbin/installkernel $KERNELRELEASE /boot/vmlinuz-$KERNELRELEASE-rpm /boot/System.map-$KERNELRELEASE-rpm" -echo "rm -f /boot/vmlinuz-$KERNELRELEASE-rpm /boot/System.map-$KERNELRELEASE-rpm" +echo "/sbin/installkernel $KERNELRELEASE /boot/.vmlinuz-$KERNELRELEASE-rpm /boot/.System.map-$KERNELRELEASE-rpm" +echo "rm -f /boot/.vmlinuz-$KERNELRELEASE-rpm /boot/.System.map-$KERNELRELEASE-rpm" echo "fi" echo "" echo "%files" diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 826470d7f000..96e2486a6fc4 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -263,7 +263,8 @@ if ($arch eq "x86_64") { } elsif ($arch eq "powerpc") { $local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; - $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:"; + # See comment in the sparc64 section for why we use '\w'. + $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?\\w*?)>:"; $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$"; if ($bits == 64) { diff --git a/security/commoncap.c b/security/commoncap.c index f035b84b3601..7fa251aea32f 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -148,12 +148,17 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; + const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); + if (mode & PTRACE_MODE_FSCREDS) + caller_caps = &cred->cap_effective; + else + caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && - cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) + cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 1334e02ae8f4..3d145a3ffccf 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -23,6 +23,7 @@ #include <linux/integrity.h> #include <linux/evm.h> #include <crypto/hash.h> +#include <crypto/algapi.h> #include "evm.h" int evm_initialized; @@ -148,7 +149,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry, xattr_value_len, calc.digest); if (rc) break; - rc = memcmp(xattr_data->digest, calc.digest, + rc = crypto_memneq(xattr_data->digest, calc.digest, sizeof(calc.digest)); if (rc) rc = -EINVAL; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 7c22a15c7e4b..94a0bfc748d1 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -420,6 +420,7 @@ static int selinux_is_sblabel_mnt(struct super_block *sb) !strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "debugfs") || + !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "rootfs"); } @@ -464,13 +465,6 @@ static int sb_finish_set_opts(struct super_block *sb) if (selinux_is_sblabel_mnt(sb)) sbsec->flags |= SBLABEL_MNT; - /* - * Special handling for rootfs. Is genfs but supports - * setting SELinux context on in-core inodes. - */ - if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0) - sbsec->flags |= SBLABEL_MNT; - /* Initialize the root inode. */ rc = inode_doinit_with_dentry(root_inode, root); @@ -3660,6 +3654,38 @@ static int selinux_kernel_module_request(char *kmod_name) SYSTEM__MODULE_REQUEST, &ad); } +static int selinux_kernel_module_from_file(struct file *file) +{ + struct common_audit_data ad; + struct inode_security_struct *isec; + struct file_security_struct *fsec; + struct inode *inode; + u32 sid = current_sid(); + int rc; + + /* init_module */ + if (file == NULL) + return avc_has_perm(sid, sid, SECCLASS_SYSTEM, + SYSTEM__MODULE_LOAD, NULL); + + /* finit_module */ + ad.type = LSM_AUDIT_DATA_PATH; + ad.u.path = file->f_path; + + inode = file_inode(file); + isec = inode->i_security; + fsec = file->f_security; + + if (sid != fsec->sid) { + rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); + if (rc) + return rc; + } + + return avc_has_perm(sid, isec->sid, SECCLASS_SYSTEM, + SYSTEM__MODULE_LOAD, &ad); +} + static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) { return current_has_perm(p, PROCESS__SETPGID); @@ -5950,6 +5976,7 @@ static struct security_hook_list selinux_hooks[] = { LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as), LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request), + LSM_HOOK_INIT(kernel_module_from_file, selinux_kernel_module_from_file), LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 5a4eef59aeff..b393d29ae857 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -32,7 +32,7 @@ struct security_class_mapping secclass_map[] = { "setsockcreate", NULL } }, { "system", { "ipc_info", "syslog_read", "syslog_mod", - "syslog_console", "module_request", NULL } }, + "syslog_console", "module_request", "module_load", NULL } }, { "capability", { "chown", "dac_override", "dac_read_search", "fowner", "fsetid", "kill", "setgid", "setuid", "setpcap", diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index ff81026f6ddb..7c57c7fcf5a2 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -398,12 +398,10 @@ static int smk_copy_relabel(struct list_head *nhead, struct list_head *ohead, */ static inline unsigned int smk_ptrace_mode(unsigned int mode) { - switch (mode) { - case PTRACE_MODE_READ: - return MAY_READ; - case PTRACE_MODE_ATTACH: + if (mode & PTRACE_MODE_ATTACH) return MAY_READWRITE; - } + if (mode & PTRACE_MODE_READ) + return MAY_READ; return 0; } diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index d3c19c970a06..cb6ed10816d4 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -281,7 +281,7 @@ static int yama_ptrace_access_check(struct task_struct *child, int rc = 0; /* require ptrace target be a child of ptracer on attach */ - if (mode == PTRACE_MODE_ATTACH) { + if (mode & PTRACE_MODE_ATTACH) { switch (ptrace_scope) { case YAMA_SCOPE_DISABLED: /* No additional restrictions. */ @@ -307,7 +307,7 @@ static int yama_ptrace_access_check(struct task_struct *child, } } - if (rc) { + if (rc && (mode & PTRACE_MODE_NOAUDIT) == 0) { printk_ratelimited(KERN_NOTICE "ptrace of pid %d was attempted by: %s (pid %d)\n", child->pid, current->comm, current->pid); diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index b123c42e7dc8..b554d7f9e3be 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -44,6 +44,13 @@ #include <sound/compress_offload.h> #include <sound/compress_driver.h> +/* struct snd_compr_codec_caps overflows the ioctl bit size for some + * architectures, so we need to disable the relevant ioctls. + */ +#if _IOC_SIZEBITS < 14 +#define COMPR_CODEC_CAPS_OVERFLOW +#endif + /* TODO: * - add substream support for multiple devices in case of * SND_DYNAMIC_MINORS is not used @@ -438,6 +445,7 @@ out: return retval; } +#ifndef COMPR_CODEC_CAPS_OVERFLOW static int snd_compr_get_codec_caps(struct snd_compr_stream *stream, unsigned long arg) { @@ -461,6 +469,7 @@ out: kfree(caps); return retval; } +#endif /* !COMPR_CODEC_CAPS_OVERFLOW */ /* revisit this with snd_pcm_preallocate_xxx */ static int snd_compr_allocate_buffer(struct snd_compr_stream *stream, @@ -799,9 +808,11 @@ static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg) case _IOC_NR(SNDRV_COMPRESS_GET_CAPS): retval = snd_compr_get_caps(stream, arg); break; +#ifndef COMPR_CODEC_CAPS_OVERFLOW case _IOC_NR(SNDRV_COMPRESS_GET_CODEC_CAPS): retval = snd_compr_get_codec_caps(stream, arg); break; +#endif case _IOC_NR(SNDRV_COMPRESS_SET_PARAMS): retval = snd_compr_set_params(stream, arg); break; diff --git a/sound/core/control.c b/sound/core/control.c index 196a6fe100ca..a85d45595d02 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1405,6 +1405,8 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file, return -EFAULT; if (tlv.length < sizeof(unsigned int) * 2) return -EINVAL; + if (!tlv.numid) + return -EINVAL; down_read(&card->controls_rwsem); kctl = snd_ctl_find_numid(card, tlv.numid); if (kctl == NULL) { diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index b9c0910fb8c4..0608f216f359 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -170,6 +170,19 @@ struct snd_ctl_elem_value32 { unsigned char reserved[128]; }; +#ifdef CONFIG_X86_X32 +/* x32 has a different alignment for 64bit values from ia32 */ +struct snd_ctl_elem_value_x32 { + struct snd_ctl_elem_id id; + unsigned int indirect; /* bit-field causes misalignment */ + union { + s32 integer[128]; + unsigned char data[512]; + s64 integer64[64]; + } value; + unsigned char reserved[128]; +}; +#endif /* CONFIG_X86_X32 */ /* get the value type and count of the control */ static int get_ctl_type(struct snd_card *card, struct snd_ctl_elem_id *id, @@ -219,9 +232,11 @@ static int get_elem_size(int type, int count) static int copy_ctl_value_from_user(struct snd_card *card, struct snd_ctl_elem_value *data, - struct snd_ctl_elem_value32 __user *data32, + void __user *userdata, + void __user *valuep, int *typep, int *countp) { + struct snd_ctl_elem_value32 __user *data32 = userdata; int i, type, size; int uninitialized_var(count); unsigned int indirect; @@ -239,8 +254,9 @@ static int copy_ctl_value_from_user(struct snd_card *card, if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || type == SNDRV_CTL_ELEM_TYPE_INTEGER) { for (i = 0; i < count; i++) { + s32 __user *intp = valuep; int val; - if (get_user(val, &data32->value.integer[i])) + if (get_user(val, &intp[i])) return -EFAULT; data->value.integer.value[i] = val; } @@ -250,8 +266,7 @@ static int copy_ctl_value_from_user(struct snd_card *card, dev_err(card->dev, "snd_ioctl32_ctl_elem_value: unknown type %d\n", type); return -EINVAL; } - if (copy_from_user(data->value.bytes.data, - data32->value.data, size)) + if (copy_from_user(data->value.bytes.data, valuep, size)) return -EFAULT; } @@ -261,7 +276,8 @@ static int copy_ctl_value_from_user(struct snd_card *card, } /* restore the value to 32bit */ -static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32, +static int copy_ctl_value_to_user(void __user *userdata, + void __user *valuep, struct snd_ctl_elem_value *data, int type, int count) { @@ -270,22 +286,22 @@ static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32, if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || type == SNDRV_CTL_ELEM_TYPE_INTEGER) { for (i = 0; i < count; i++) { + s32 __user *intp = valuep; int val; val = data->value.integer.value[i]; - if (put_user(val, &data32->value.integer[i])) + if (put_user(val, &intp[i])) return -EFAULT; } } else { size = get_elem_size(type, count); - if (copy_to_user(data32->value.data, - data->value.bytes.data, size)) + if (copy_to_user(valuep, data->value.bytes.data, size)) return -EFAULT; } return 0; } -static int snd_ctl_elem_read_user_compat(struct snd_card *card, - struct snd_ctl_elem_value32 __user *data32) +static int ctl_elem_read_user(struct snd_card *card, + void __user *userdata, void __user *valuep) { struct snd_ctl_elem_value *data; int err, type, count; @@ -294,7 +310,9 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card, if (data == NULL) return -ENOMEM; - if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0) + err = copy_ctl_value_from_user(card, data, userdata, valuep, + &type, &count); + if (err < 0) goto error; snd_power_lock(card); @@ -303,14 +321,15 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card, err = snd_ctl_elem_read(card, data); snd_power_unlock(card); if (err >= 0) - err = copy_ctl_value_to_user(data32, data, type, count); + err = copy_ctl_value_to_user(userdata, valuep, data, + type, count); error: kfree(data); return err; } -static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, - struct snd_ctl_elem_value32 __user *data32) +static int ctl_elem_write_user(struct snd_ctl_file *file, + void __user *userdata, void __user *valuep) { struct snd_ctl_elem_value *data; struct snd_card *card = file->card; @@ -320,7 +339,9 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, if (data == NULL) return -ENOMEM; - if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0) + err = copy_ctl_value_from_user(card, data, userdata, valuep, + &type, &count); + if (err < 0) goto error; snd_power_lock(card); @@ -329,12 +350,39 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, err = snd_ctl_elem_write(card, file, data); snd_power_unlock(card); if (err >= 0) - err = copy_ctl_value_to_user(data32, data, type, count); + err = copy_ctl_value_to_user(userdata, valuep, data, + type, count); error: kfree(data); return err; } +static int snd_ctl_elem_read_user_compat(struct snd_card *card, + struct snd_ctl_elem_value32 __user *data32) +{ + return ctl_elem_read_user(card, data32, &data32->value); +} + +static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, + struct snd_ctl_elem_value32 __user *data32) +{ + return ctl_elem_write_user(file, data32, &data32->value); +} + +#ifdef CONFIG_X86_X32 +static int snd_ctl_elem_read_user_x32(struct snd_card *card, + struct snd_ctl_elem_value_x32 __user *data32) +{ + return ctl_elem_read_user(card, data32, &data32->value); +} + +static int snd_ctl_elem_write_user_x32(struct snd_ctl_file *file, + struct snd_ctl_elem_value_x32 __user *data32) +{ + return ctl_elem_write_user(file, data32, &data32->value); +} +#endif /* CONFIG_X86_X32 */ + /* add or replace a user control */ static int snd_ctl_elem_add_compat(struct snd_ctl_file *file, struct snd_ctl_elem_info32 __user *data32, @@ -393,6 +441,10 @@ enum { SNDRV_CTL_IOCTL_ELEM_WRITE32 = _IOWR('U', 0x13, struct snd_ctl_elem_value32), SNDRV_CTL_IOCTL_ELEM_ADD32 = _IOWR('U', 0x17, struct snd_ctl_elem_info32), SNDRV_CTL_IOCTL_ELEM_REPLACE32 = _IOWR('U', 0x18, struct snd_ctl_elem_info32), +#ifdef CONFIG_X86_X32 + SNDRV_CTL_IOCTL_ELEM_READ_X32 = _IOWR('U', 0x12, struct snd_ctl_elem_value_x32), + SNDRV_CTL_IOCTL_ELEM_WRITE_X32 = _IOWR('U', 0x13, struct snd_ctl_elem_value_x32), +#endif /* CONFIG_X86_X32 */ }; static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -431,6 +483,12 @@ static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, uns return snd_ctl_elem_add_compat(ctl, argp, 0); case SNDRV_CTL_IOCTL_ELEM_REPLACE32: return snd_ctl_elem_add_compat(ctl, argp, 1); +#ifdef CONFIG_X86_X32 + case SNDRV_CTL_IOCTL_ELEM_READ_X32: + return snd_ctl_elem_read_user_x32(ctl->card, argp); + case SNDRV_CTL_IOCTL_ELEM_WRITE_X32: + return snd_ctl_elem_write_user_x32(ctl, argp); +#endif /* CONFIG_X86_X32 */ } down_read(&snd_ioctl_rwsem); diff --git a/sound/core/hrtimer.c b/sound/core/hrtimer.c index f845ecf7e172..656d9a9032dc 100644 --- a/sound/core/hrtimer.c +++ b/sound/core/hrtimer.c @@ -90,7 +90,7 @@ static int snd_hrtimer_start(struct snd_timer *t) struct snd_hrtimer *stime = t->private_data; atomic_set(&stime->running, 0); - hrtimer_cancel(&stime->hrt); + hrtimer_try_to_cancel(&stime->hrt); hrtimer_start(&stime->hrt, ns_to_ktime(t->sticks * resolution), HRTIMER_MODE_REL); atomic_set(&stime->running, 1); @@ -101,6 +101,7 @@ static int snd_hrtimer_stop(struct snd_timer *t) { struct snd_hrtimer *stime = t->private_data; atomic_set(&stime->running, 0); + hrtimer_try_to_cancel(&stime->hrt); return 0; } diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 58550cc93f28..33e72c809e50 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -834,7 +834,8 @@ static int choose_rate(struct snd_pcm_substream *substream, return snd_pcm_hw_param_near(substream, params, SNDRV_PCM_HW_PARAM_RATE, best_rate, NULL); } -static int snd_pcm_oss_change_params(struct snd_pcm_substream *substream) +static int snd_pcm_oss_change_params(struct snd_pcm_substream *substream, + bool trylock) { struct snd_pcm_runtime *runtime = substream->runtime; struct snd_pcm_hw_params *params, *sparams; @@ -848,7 +849,10 @@ static int snd_pcm_oss_change_params(struct snd_pcm_substream *substream) struct snd_mask sformat_mask; struct snd_mask mask; - if (mutex_lock_interruptible(&runtime->oss.params_lock)) + if (trylock) { + if (!(mutex_trylock(&runtime->oss.params_lock))) + return -EAGAIN; + } else if (mutex_lock_interruptible(&runtime->oss.params_lock)) return -EINTR; sw_params = kmalloc(sizeof(*sw_params), GFP_KERNEL); params = kmalloc(sizeof(*params), GFP_KERNEL); @@ -1092,7 +1096,7 @@ static int snd_pcm_oss_get_active_substream(struct snd_pcm_oss_file *pcm_oss_fil if (asubstream == NULL) asubstream = substream; if (substream->runtime->oss.params) { - err = snd_pcm_oss_change_params(substream); + err = snd_pcm_oss_change_params(substream, false); if (err < 0) return err; } @@ -1132,7 +1136,7 @@ static int snd_pcm_oss_make_ready(struct snd_pcm_substream *substream) return 0; runtime = substream->runtime; if (runtime->oss.params) { - err = snd_pcm_oss_change_params(substream); + err = snd_pcm_oss_change_params(substream, false); if (err < 0) return err; } @@ -2163,7 +2167,7 @@ static int snd_pcm_oss_get_space(struct snd_pcm_oss_file *pcm_oss_file, int stre runtime = substream->runtime; if (runtime->oss.params && - (err = snd_pcm_oss_change_params(substream)) < 0) + (err = snd_pcm_oss_change_params(substream, false)) < 0) return err; info.fragsize = runtime->oss.period_bytes; @@ -2800,7 +2804,12 @@ static int snd_pcm_oss_mmap(struct file *file, struct vm_area_struct *area) return -EIO; if (runtime->oss.params) { - if ((err = snd_pcm_oss_change_params(substream)) < 0) + /* use mutex_trylock() for params_lock for avoiding a deadlock + * between mmap_sem and params_lock taken by + * copy_from/to_user() in snd_pcm_oss_write/read() + */ + err = snd_pcm_oss_change_params(substream, true); + if (err < 0) return err; } #ifdef CONFIG_SND_PCM_OSS_PLUGINS diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index b48b434444ed..1f64ab0c2a95 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -183,6 +183,14 @@ static int snd_pcm_ioctl_channel_info_compat(struct snd_pcm_substream *substream return err; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has the same struct as x86-64 for snd_pcm_channel_info */ +static int snd_pcm_channel_info_user(struct snd_pcm_substream *substream, + struct snd_pcm_channel_info __user *src); +#define snd_pcm_ioctl_channel_info_x32(s, p) \ + snd_pcm_channel_info_user(s, p) +#endif /* CONFIG_X86_X32 */ + struct snd_pcm_status32 { s32 state; struct compat_timespec trigger_tstamp; @@ -243,6 +251,71 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream, return err; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_pcm_status_x32 { + s32 state; + u32 rsvd; /* alignment */ + struct timespec trigger_tstamp; + struct timespec tstamp; + u32 appl_ptr; + u32 hw_ptr; + s32 delay; + u32 avail; + u32 avail_max; + u32 overrange; + s32 suspended_state; + u32 audio_tstamp_data; + struct timespec audio_tstamp; + struct timespec driver_tstamp; + u32 audio_tstamp_accuracy; + unsigned char reserved[52-2*sizeof(struct timespec)]; +} __packed; + +#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst)) + +static int snd_pcm_status_user_x32(struct snd_pcm_substream *substream, + struct snd_pcm_status_x32 __user *src, + bool ext) +{ + struct snd_pcm_status status; + int err; + + memset(&status, 0, sizeof(status)); + /* + * with extension, parameters are read/write, + * get audio_tstamp_data from user, + * ignore rest of status structure + */ + if (ext && get_user(status.audio_tstamp_data, + (u32 __user *)(&src->audio_tstamp_data))) + return -EFAULT; + err = snd_pcm_status(substream, &status); + if (err < 0) + return err; + + if (clear_user(src, sizeof(*src))) + return -EFAULT; + if (put_user(status.state, &src->state) || + put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) || + put_timespec(&status.tstamp, &src->tstamp) || + put_user(status.appl_ptr, &src->appl_ptr) || + put_user(status.hw_ptr, &src->hw_ptr) || + put_user(status.delay, &src->delay) || + put_user(status.avail, &src->avail) || + put_user(status.avail_max, &src->avail_max) || + put_user(status.overrange, &src->overrange) || + put_user(status.suspended_state, &src->suspended_state) || + put_user(status.audio_tstamp_data, &src->audio_tstamp_data) || + put_timespec(&status.audio_tstamp, &src->audio_tstamp) || + put_timespec(&status.driver_tstamp, &src->driver_tstamp) || + put_user(status.audio_tstamp_accuracy, &src->audio_tstamp_accuracy)) + return -EFAULT; + + return err; +} +#endif /* CONFIG_X86_X32 */ + /* both for HW_PARAMS and HW_REFINE */ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, int refine, @@ -255,10 +328,15 @@ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, if (! (runtime = substream->runtime)) return -ENOTTY; - /* only fifo_size is different, so just copy all */ - data = memdup_user(data32, sizeof(*data32)); - if (IS_ERR(data)) - return PTR_ERR(data); + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* only fifo_size (RO from userspace) is different, so just copy all */ + if (copy_from_user(data, data32, sizeof(*data32))) { + err = -EFAULT; + goto error; + } if (refine) err = snd_pcm_hw_refine(substream, data); @@ -464,6 +542,93 @@ static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_pcm_mmap_status_x32 { + s32 state; + s32 pad1; + u32 hw_ptr; + u32 pad2; /* alignment */ + struct timespec tstamp; + s32 suspended_state; + struct timespec audio_tstamp; +} __packed; + +struct snd_pcm_mmap_control_x32 { + u32 appl_ptr; + u32 avail_min; +}; + +struct snd_pcm_sync_ptr_x32 { + u32 flags; + u32 rsvd; /* alignment */ + union { + struct snd_pcm_mmap_status_x32 status; + unsigned char reserved[64]; + } s; + union { + struct snd_pcm_mmap_control_x32 control; + unsigned char reserved[64]; + } c; +} __packed; + +static int snd_pcm_ioctl_sync_ptr_x32(struct snd_pcm_substream *substream, + struct snd_pcm_sync_ptr_x32 __user *src) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + volatile struct snd_pcm_mmap_status *status; + volatile struct snd_pcm_mmap_control *control; + u32 sflags; + struct snd_pcm_mmap_control scontrol; + struct snd_pcm_mmap_status sstatus; + snd_pcm_uframes_t boundary; + int err; + + if (snd_BUG_ON(!runtime)) + return -EINVAL; + + if (get_user(sflags, &src->flags) || + get_user(scontrol.appl_ptr, &src->c.control.appl_ptr) || + get_user(scontrol.avail_min, &src->c.control.avail_min)) + return -EFAULT; + if (sflags & SNDRV_PCM_SYNC_PTR_HWSYNC) { + err = snd_pcm_hwsync(substream); + if (err < 0) + return err; + } + status = runtime->status; + control = runtime->control; + boundary = recalculate_boundary(runtime); + if (!boundary) + boundary = 0x7fffffff; + snd_pcm_stream_lock_irq(substream); + /* FIXME: we should consider the boundary for the sync from app */ + if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) + control->appl_ptr = scontrol.appl_ptr; + else + scontrol.appl_ptr = control->appl_ptr % boundary; + if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) + control->avail_min = scontrol.avail_min; + else + scontrol.avail_min = control->avail_min; + sstatus.state = status->state; + sstatus.hw_ptr = status->hw_ptr % boundary; + sstatus.tstamp = status->tstamp; + sstatus.suspended_state = status->suspended_state; + sstatus.audio_tstamp = status->audio_tstamp; + snd_pcm_stream_unlock_irq(substream); + if (put_user(sstatus.state, &src->s.status.state) || + put_user(sstatus.hw_ptr, &src->s.status.hw_ptr) || + put_timespec(&sstatus.tstamp, &src->s.status.tstamp) || + put_user(sstatus.suspended_state, &src->s.status.suspended_state) || + put_timespec(&sstatus.audio_tstamp, &src->s.status.audio_tstamp) || + put_user(scontrol.appl_ptr, &src->c.control.appl_ptr) || + put_user(scontrol.avail_min, &src->c.control.avail_min)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_X86_X32 */ /* */ @@ -482,7 +647,12 @@ enum { SNDRV_PCM_IOCTL_WRITEN_FRAMES32 = _IOW('A', 0x52, struct snd_xfern32), SNDRV_PCM_IOCTL_READN_FRAMES32 = _IOR('A', 0x53, struct snd_xfern32), SNDRV_PCM_IOCTL_SYNC_PTR32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr32), - +#ifdef CONFIG_X86_X32 + SNDRV_PCM_IOCTL_CHANNEL_INFO_X32 = _IOR('A', 0x32, struct snd_pcm_channel_info), + SNDRV_PCM_IOCTL_STATUS_X32 = _IOR('A', 0x20, struct snd_pcm_status_x32), + SNDRV_PCM_IOCTL_STATUS_EXT_X32 = _IOWR('A', 0x24, struct snd_pcm_status_x32), + SNDRV_PCM_IOCTL_SYNC_PTR_X32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr_x32), +#endif /* CONFIG_X86_X32 */ }; static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -554,6 +724,16 @@ static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned l return snd_pcm_ioctl_rewind_compat(substream, argp); case SNDRV_PCM_IOCTL_FORWARD32: return snd_pcm_ioctl_forward_compat(substream, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_PCM_IOCTL_STATUS_X32: + return snd_pcm_status_user_x32(substream, argp, false); + case SNDRV_PCM_IOCTL_STATUS_EXT_X32: + return snd_pcm_status_user_x32(substream, argp, true); + case SNDRV_PCM_IOCTL_SYNC_PTR_X32: + return snd_pcm_ioctl_sync_ptr_x32(substream, argp); + case SNDRV_PCM_IOCTL_CHANNEL_INFO_X32: + return snd_pcm_ioctl_channel_info_x32(substream, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 6b5a811e01a5..3a9b66c6e09c 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -322,7 +322,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream, char name[16]; snd_pcm_debug_name(substream, name, sizeof(name)); pcm_err(substream->pcm, - "BUG: %s, pos = %ld, buffer size = %ld, period size = %ld\n", + "invalid position: %s, pos = %ld, buffer size = %ld, period size = %ld\n", name, pos, runtime->buffer_size, runtime->period_size); } diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index a8b27cdc2844..4ba64fd49759 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -74,6 +74,18 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream); static DEFINE_RWLOCK(snd_pcm_link_rwlock); static DECLARE_RWSEM(snd_pcm_link_rwsem); +/* Writer in rwsem may block readers even during its waiting in queue, + * and this may lead to a deadlock when the code path takes read sem + * twice (e.g. one in snd_pcm_action_nonatomic() and another in + * snd_pcm_stream_lock()). As a (suboptimal) workaround, let writer to + * spin until it gets the lock. + */ +static inline void down_write_nonblock(struct rw_semaphore *lock) +{ + while (!down_write_trylock(lock)) + cond_resched(); +} + /** * snd_pcm_stream_lock - Lock the PCM stream * @substream: PCM substream @@ -1813,7 +1825,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) res = -ENOMEM; goto _nolock; } - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN || substream->runtime->status->state != substream1->runtime->status->state || @@ -1860,7 +1872,7 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) struct snd_pcm_substream *s; int res = 0; - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (!snd_pcm_stream_linked(substream)) { res = -EALREADY; diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index a7759846fbaa..795437b10082 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -942,31 +942,36 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, unsigned long flags; long result = 0, count1; struct snd_rawmidi_runtime *runtime = substream->runtime; + unsigned long appl_ptr; + spin_lock_irqsave(&runtime->lock, flags); while (count > 0 && runtime->avail) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) count1 = count; - spin_lock_irqsave(&runtime->lock, flags); if (count1 > (int)runtime->avail) count1 = runtime->avail; + + /* update runtime->appl_ptr before unlocking for userbuf */ + appl_ptr = runtime->appl_ptr; + runtime->appl_ptr += count1; + runtime->appl_ptr %= runtime->buffer_size; + runtime->avail -= count1; + if (kernelbuf) - memcpy(kernelbuf + result, runtime->buffer + runtime->appl_ptr, count1); + memcpy(kernelbuf + result, runtime->buffer + appl_ptr, count1); if (userbuf) { spin_unlock_irqrestore(&runtime->lock, flags); if (copy_to_user(userbuf + result, - runtime->buffer + runtime->appl_ptr, count1)) { + runtime->buffer + appl_ptr, count1)) { return result > 0 ? result : -EFAULT; } spin_lock_irqsave(&runtime->lock, flags); } - runtime->appl_ptr += count1; - runtime->appl_ptr %= runtime->buffer_size; - runtime->avail -= count1; - spin_unlock_irqrestore(&runtime->lock, flags); result += count1; count -= count1; } + spin_unlock_irqrestore(&runtime->lock, flags); return result; } @@ -1055,23 +1060,16 @@ int snd_rawmidi_transmit_empty(struct snd_rawmidi_substream *substream) EXPORT_SYMBOL(snd_rawmidi_transmit_empty); /** - * snd_rawmidi_transmit_peek - copy data from the internal buffer + * __snd_rawmidi_transmit_peek - copy data from the internal buffer * @substream: the rawmidi substream * @buffer: the buffer pointer * @count: data size to transfer * - * Copies data from the internal output buffer to the given buffer. - * - * Call this in the interrupt handler when the midi output is ready, - * and call snd_rawmidi_transmit_ack() after the transmission is - * finished. - * - * Return: The size of copied data, or a negative error code on failure. + * This is a variant of snd_rawmidi_transmit_peek() without spinlock. */ -int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, +int __snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, unsigned char *buffer, int count) { - unsigned long flags; int result, count1; struct snd_rawmidi_runtime *runtime = substream->runtime; @@ -1081,7 +1079,6 @@ int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, return -EINVAL; } result = 0; - spin_lock_irqsave(&runtime->lock, flags); if (runtime->avail >= runtime->buffer_size) { /* warning: lowlevel layer MUST trigger down the hardware */ goto __skip; @@ -1106,25 +1103,47 @@ int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, } } __skip: + return result; +} +EXPORT_SYMBOL(__snd_rawmidi_transmit_peek); + +/** + * snd_rawmidi_transmit_peek - copy data from the internal buffer + * @substream: the rawmidi substream + * @buffer: the buffer pointer + * @count: data size to transfer + * + * Copies data from the internal output buffer to the given buffer. + * + * Call this in the interrupt handler when the midi output is ready, + * and call snd_rawmidi_transmit_ack() after the transmission is + * finished. + * + * Return: The size of copied data, or a negative error code on failure. + */ +int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, + unsigned char *buffer, int count) +{ + struct snd_rawmidi_runtime *runtime = substream->runtime; + int result; + unsigned long flags; + + spin_lock_irqsave(&runtime->lock, flags); + result = __snd_rawmidi_transmit_peek(substream, buffer, count); spin_unlock_irqrestore(&runtime->lock, flags); return result; } EXPORT_SYMBOL(snd_rawmidi_transmit_peek); /** - * snd_rawmidi_transmit_ack - acknowledge the transmission + * __snd_rawmidi_transmit_ack - acknowledge the transmission * @substream: the rawmidi substream * @count: the transferred count * - * Advances the hardware pointer for the internal output buffer with - * the given size and updates the condition. - * Call after the transmission is finished. - * - * Return: The advanced size if successful, or a negative error code on failure. + * This is a variant of __snd_rawmidi_transmit_ack() without spinlock. */ -int snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count) +int __snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count) { - unsigned long flags; struct snd_rawmidi_runtime *runtime = substream->runtime; if (runtime->buffer == NULL) { @@ -1132,7 +1151,6 @@ int snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count) "snd_rawmidi_transmit_ack: output is not active!!!\n"); return -EINVAL; } - spin_lock_irqsave(&runtime->lock, flags); snd_BUG_ON(runtime->avail + count > runtime->buffer_size); runtime->hw_ptr += count; runtime->hw_ptr %= runtime->buffer_size; @@ -1142,9 +1160,32 @@ int snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count) if (runtime->drain || snd_rawmidi_ready(substream)) wake_up(&runtime->sleep); } - spin_unlock_irqrestore(&runtime->lock, flags); return count; } +EXPORT_SYMBOL(__snd_rawmidi_transmit_ack); + +/** + * snd_rawmidi_transmit_ack - acknowledge the transmission + * @substream: the rawmidi substream + * @count: the transferred count + * + * Advances the hardware pointer for the internal output buffer with + * the given size and updates the condition. + * Call after the transmission is finished. + * + * Return: The advanced size if successful, or a negative error code on failure. + */ +int snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count) +{ + struct snd_rawmidi_runtime *runtime = substream->runtime; + int result; + unsigned long flags; + + spin_lock_irqsave(&runtime->lock, flags); + result = __snd_rawmidi_transmit_ack(substream, count); + spin_unlock_irqrestore(&runtime->lock, flags); + return result; +} EXPORT_SYMBOL(snd_rawmidi_transmit_ack); /** @@ -1160,12 +1201,22 @@ EXPORT_SYMBOL(snd_rawmidi_transmit_ack); int snd_rawmidi_transmit(struct snd_rawmidi_substream *substream, unsigned char *buffer, int count) { + struct snd_rawmidi_runtime *runtime = substream->runtime; + int result; + unsigned long flags; + + spin_lock_irqsave(&runtime->lock, flags); if (!substream->opened) - return -EBADFD; - count = snd_rawmidi_transmit_peek(substream, buffer, count); - if (count < 0) - return count; - return snd_rawmidi_transmit_ack(substream, count); + result = -EBADFD; + else { + count = __snd_rawmidi_transmit_peek(substream, buffer, count); + if (count <= 0) + result = count; + else + result = __snd_rawmidi_transmit_ack(substream, count); + } + spin_unlock_irqrestore(&runtime->lock, flags); + return result; } EXPORT_SYMBOL(snd_rawmidi_transmit); @@ -1177,8 +1228,9 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, unsigned long flags; long count1, result; struct snd_rawmidi_runtime *runtime = substream->runtime; + unsigned long appl_ptr; - if (snd_BUG_ON(!kernelbuf && !userbuf)) + if (!kernelbuf && !userbuf) return -EINVAL; if (snd_BUG_ON(!runtime->buffer)) return -EINVAL; @@ -1197,12 +1249,19 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, count1 = count; if (count1 > (long)runtime->avail) count1 = runtime->avail; + + /* update runtime->appl_ptr before unlocking for userbuf */ + appl_ptr = runtime->appl_ptr; + runtime->appl_ptr += count1; + runtime->appl_ptr %= runtime->buffer_size; + runtime->avail -= count1; + if (kernelbuf) - memcpy(runtime->buffer + runtime->appl_ptr, + memcpy(runtime->buffer + appl_ptr, kernelbuf + result, count1); else if (userbuf) { spin_unlock_irqrestore(&runtime->lock, flags); - if (copy_from_user(runtime->buffer + runtime->appl_ptr, + if (copy_from_user(runtime->buffer + appl_ptr, userbuf + result, count1)) { spin_lock_irqsave(&runtime->lock, flags); result = result > 0 ? result : -EFAULT; @@ -1210,9 +1269,6 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, } spin_lock_irqsave(&runtime->lock, flags); } - runtime->appl_ptr += count1; - runtime->appl_ptr %= runtime->buffer_size; - runtime->avail -= count1; result += count1; count -= count1; } diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c index 5268c1f58c25..09a89094dcf7 100644 --- a/sound/core/rawmidi_compat.c +++ b/sound/core/rawmidi_compat.c @@ -94,9 +94,58 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_rawmidi_status_x32 { + s32 stream; + u32 rsvd; /* alignment */ + struct timespec tstamp; + u32 avail; + u32 xruns; + unsigned char reserved[16]; +} __attribute__((packed)); + +#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst)) + +static int snd_rawmidi_ioctl_status_x32(struct snd_rawmidi_file *rfile, + struct snd_rawmidi_status_x32 __user *src) +{ + int err; + struct snd_rawmidi_status status; + + if (rfile->output == NULL) + return -EINVAL; + if (get_user(status.stream, &src->stream)) + return -EFAULT; + + switch (status.stream) { + case SNDRV_RAWMIDI_STREAM_OUTPUT: + err = snd_rawmidi_output_status(rfile->output, &status); + break; + case SNDRV_RAWMIDI_STREAM_INPUT: + err = snd_rawmidi_input_status(rfile->input, &status); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + if (put_timespec(&status.tstamp, &src->tstamp) || + put_user(status.avail, &src->avail) || + put_user(status.xruns, &src->xruns)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_X86_X32 */ + enum { SNDRV_RAWMIDI_IOCTL_PARAMS32 = _IOWR('W', 0x10, struct snd_rawmidi_params32), SNDRV_RAWMIDI_IOCTL_STATUS32 = _IOWR('W', 0x20, struct snd_rawmidi_status32), +#ifdef CONFIG_X86_X32 + SNDRV_RAWMIDI_IOCTL_STATUS_X32 = _IOWR('W', 0x20, struct snd_rawmidi_status_x32), +#endif /* CONFIG_X86_X32 */ }; static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -115,6 +164,10 @@ static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsign return snd_rawmidi_ioctl_params_compat(rfile, argp); case SNDRV_RAWMIDI_IOCTL_STATUS32: return snd_rawmidi_ioctl_status_compat(rfile, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_RAWMIDI_IOCTL_STATUS_X32: + return snd_rawmidi_ioctl_status_x32(rfile, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; } diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c index 7354b8bed860..cb23899100ee 100644 --- a/sound/core/seq/oss/seq_oss.c +++ b/sound/core/seq/oss/seq_oss.c @@ -148,8 +148,6 @@ odev_release(struct inode *inode, struct file *file) if ((dp = file->private_data) == NULL) return 0; - snd_seq_oss_drain_write(dp); - mutex_lock(®ister_mutex); snd_seq_oss_release(dp); mutex_unlock(®ister_mutex); diff --git a/sound/core/seq/oss/seq_oss_device.h b/sound/core/seq/oss/seq_oss_device.h index b43924325249..d7b4d016b547 100644 --- a/sound/core/seq/oss/seq_oss_device.h +++ b/sound/core/seq/oss/seq_oss_device.h @@ -127,7 +127,6 @@ int snd_seq_oss_write(struct seq_oss_devinfo *dp, const char __user *buf, int co unsigned int snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wait); void snd_seq_oss_reset(struct seq_oss_devinfo *dp); -void snd_seq_oss_drain_write(struct seq_oss_devinfo *dp); /* */ void snd_seq_oss_process_queue(struct seq_oss_devinfo *dp, abstime_t time); diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c index b1221b29728e..92c96a95a903 100644 --- a/sound/core/seq/oss/seq_oss_init.c +++ b/sound/core/seq/oss/seq_oss_init.c @@ -202,7 +202,7 @@ snd_seq_oss_open(struct file *file, int level) dp->index = i; if (i >= SNDRV_SEQ_OSS_MAX_CLIENTS) { - pr_err("ALSA: seq_oss: too many applications\n"); + pr_debug("ALSA: seq_oss: too many applications\n"); rc = -ENOMEM; goto _error; } @@ -436,22 +436,6 @@ snd_seq_oss_release(struct seq_oss_devinfo *dp) /* - * Wait until the queue is empty (if we don't have nonblock) - */ -void -snd_seq_oss_drain_write(struct seq_oss_devinfo *dp) -{ - if (! dp->timer->running) - return; - if (is_write_mode(dp->file_mode) && !is_nonblock_mode(dp->file_mode) && - dp->writeq) { - while (snd_seq_oss_writeq_sync(dp->writeq)) - ; - } -} - - -/* * reset sequencer devices */ void diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index 0f3b38184fe5..b16dbef04174 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -308,7 +308,7 @@ snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp) struct seq_oss_synth *rec; struct seq_oss_synthinfo *info; - if (snd_BUG_ON(dp->max_synthdev >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) + if (snd_BUG_ON(dp->max_synthdev > SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) return; for (i = 0; i < dp->max_synthdev; i++) { info = &dp->synths[i]; diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index b64f20deba90..58e79e02f217 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -678,6 +678,9 @@ static int deliver_to_subscribers(struct snd_seq_client *client, else down_read(&grp->list_mutex); list_for_each_entry(subs, &grp->list_head, src_list) { + /* both ports ready? */ + if (atomic_read(&subs->ref_count) != 2) + continue; event->dest = subs->info.dest; if (subs->info.flags & SNDRV_SEQ_PORT_SUBS_TIMESTAMP) /* convert time according to flag with subscription */ @@ -1962,7 +1965,7 @@ static int snd_seq_ioctl_remove_events(struct snd_seq_client *client, * No restrictions so for a user client we can clear * the whole fifo */ - if (client->type == USER_CLIENT) + if (client->type == USER_CLIENT && client->data.user.fifo) snd_seq_fifo_clear(client->data.user.fifo); } diff --git a/sound/core/seq/seq_compat.c b/sound/core/seq/seq_compat.c index 81f7c109dc46..65175902a68a 100644 --- a/sound/core/seq/seq_compat.c +++ b/sound/core/seq/seq_compat.c @@ -49,11 +49,12 @@ static int snd_seq_call_port_info_ioctl(struct snd_seq_client *client, unsigned struct snd_seq_port_info *data; mm_segment_t fs; - data = memdup_user(data32, sizeof(*data32)); - if (IS_ERR(data)) - return PTR_ERR(data); + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; - if (get_user(data->flags, &data32->flags) || + if (copy_from_user(data, data32, sizeof(*data32)) || + get_user(data->flags, &data32->flags) || get_user(data->time_queue, &data32->time_queue)) goto error; data->kernel = NULL; diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index 801076687bb1..c850345c43b5 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -383,15 +383,20 @@ int snd_seq_pool_init(struct snd_seq_pool *pool) if (snd_BUG_ON(!pool)) return -EINVAL; - if (pool->ptr) /* should be atomic? */ - return 0; - pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); - if (!pool->ptr) + cellptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); + if (!cellptr) return -ENOMEM; /* add new cells to the free cell list */ spin_lock_irqsave(&pool->lock, flags); + if (pool->ptr) { + spin_unlock_irqrestore(&pool->lock, flags); + vfree(cellptr); + return 0; + } + + pool->ptr = cellptr; pool->free = NULL; for (cell = 0; cell < pool->size; cell++) { diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 55170a20ae72..fe686ee41c6d 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -173,10 +173,6 @@ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client, } /* */ -enum group_type { - SRC_LIST, DEST_LIST -}; - static int subscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, @@ -203,6 +199,20 @@ static struct snd_seq_client_port *get_client_port(struct snd_seq_addr *addr, return NULL; } +static void delete_and_unsubscribe_port(struct snd_seq_client *client, + struct snd_seq_client_port *port, + struct snd_seq_subscribers *subs, + bool is_src, bool ack); + +static inline struct snd_seq_subscribers * +get_subscriber(struct list_head *p, bool is_src) +{ + if (is_src) + return list_entry(p, struct snd_seq_subscribers, src_list); + else + return list_entry(p, struct snd_seq_subscribers, dest_list); +} + /* * remove all subscribers on the list * this is called from port_delete, for each src and dest list. @@ -210,7 +220,7 @@ static struct snd_seq_client_port *get_client_port(struct snd_seq_addr *addr, static void clear_subscriber_list(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, - int grptype) + int is_src) { struct list_head *p, *n; @@ -219,15 +229,13 @@ static void clear_subscriber_list(struct snd_seq_client *client, struct snd_seq_client *c; struct snd_seq_client_port *aport; - if (grptype == SRC_LIST) { - subs = list_entry(p, struct snd_seq_subscribers, src_list); + subs = get_subscriber(p, is_src); + if (is_src) aport = get_client_port(&subs->info.dest, &c); - } else { - subs = list_entry(p, struct snd_seq_subscribers, dest_list); + else aport = get_client_port(&subs->info.sender, &c); - } - list_del(p); - unsubscribe_port(client, port, grp, &subs->info, 0); + delete_and_unsubscribe_port(client, port, subs, is_src, false); + if (!aport) { /* looks like the connected port is being deleted. * we decrease the counter, and when both ports are deleted @@ -235,21 +243,14 @@ static void clear_subscriber_list(struct snd_seq_client *client, */ if (atomic_dec_and_test(&subs->ref_count)) kfree(subs); - } else { - /* ok we got the connected port */ - struct snd_seq_port_subs_info *agrp; - agrp = (grptype == SRC_LIST) ? &aport->c_dest : &aport->c_src; - down_write(&agrp->list_mutex); - if (grptype == SRC_LIST) - list_del(&subs->dest_list); - else - list_del(&subs->src_list); - up_write(&agrp->list_mutex); - unsubscribe_port(c, aport, agrp, &subs->info, 1); - kfree(subs); - snd_seq_port_unlock(aport); - snd_seq_client_unlock(c); + continue; } + + /* ok we got the connected port */ + delete_and_unsubscribe_port(c, aport, subs, !is_src, true); + kfree(subs); + snd_seq_port_unlock(aport); + snd_seq_client_unlock(c); } } @@ -262,8 +263,8 @@ static int port_delete(struct snd_seq_client *client, snd_use_lock_sync(&port->use_lock); /* clear subscribers info */ - clear_subscriber_list(client, port, &port->c_src, SRC_LIST); - clear_subscriber_list(client, port, &port->c_dest, DEST_LIST); + clear_subscriber_list(client, port, &port->c_src, true); + clear_subscriber_list(client, port, &port->c_dest, false); if (port->private_free) port->private_free(port->private_data); @@ -479,85 +480,123 @@ static int match_subs_info(struct snd_seq_port_subscribe *r, return 0; } - -/* connect two ports */ -int snd_seq_port_connect(struct snd_seq_client *connector, - struct snd_seq_client *src_client, - struct snd_seq_client_port *src_port, - struct snd_seq_client *dest_client, - struct snd_seq_client_port *dest_port, - struct snd_seq_port_subscribe *info) +static int check_and_subscribe_port(struct snd_seq_client *client, + struct snd_seq_client_port *port, + struct snd_seq_subscribers *subs, + bool is_src, bool exclusive, bool ack) { - struct snd_seq_port_subs_info *src = &src_port->c_src; - struct snd_seq_port_subs_info *dest = &dest_port->c_dest; - struct snd_seq_subscribers *subs, *s; - int err, src_called = 0; - unsigned long flags; - int exclusive; - - subs = kzalloc(sizeof(*subs), GFP_KERNEL); - if (! subs) - return -ENOMEM; - - subs->info = *info; - atomic_set(&subs->ref_count, 2); + struct snd_seq_port_subs_info *grp; + struct list_head *p; + struct snd_seq_subscribers *s; + int err; - down_write(&src->list_mutex); - down_write_nested(&dest->list_mutex, SINGLE_DEPTH_NESTING); - - exclusive = info->flags & SNDRV_SEQ_PORT_SUBS_EXCLUSIVE ? 1 : 0; + grp = is_src ? &port->c_src : &port->c_dest; err = -EBUSY; + down_write(&grp->list_mutex); if (exclusive) { - if (! list_empty(&src->list_head) || ! list_empty(&dest->list_head)) + if (!list_empty(&grp->list_head)) goto __error; } else { - if (src->exclusive || dest->exclusive) + if (grp->exclusive) goto __error; /* check whether already exists */ - list_for_each_entry(s, &src->list_head, src_list) { - if (match_subs_info(info, &s->info)) - goto __error; - } - list_for_each_entry(s, &dest->list_head, dest_list) { - if (match_subs_info(info, &s->info)) + list_for_each(p, &grp->list_head) { + s = get_subscriber(p, is_src); + if (match_subs_info(&subs->info, &s->info)) goto __error; } } - if ((err = subscribe_port(src_client, src_port, src, info, - connector->number != src_client->number)) < 0) - goto __error; - src_called = 1; - - if ((err = subscribe_port(dest_client, dest_port, dest, info, - connector->number != dest_client->number)) < 0) + err = subscribe_port(client, port, grp, &subs->info, ack); + if (err < 0) { + grp->exclusive = 0; goto __error; + } /* add to list */ - write_lock_irqsave(&src->list_lock, flags); - // write_lock(&dest->list_lock); // no other lock yet - list_add_tail(&subs->src_list, &src->list_head); - list_add_tail(&subs->dest_list, &dest->list_head); - // write_unlock(&dest->list_lock); // no other lock yet - write_unlock_irqrestore(&src->list_lock, flags); + write_lock_irq(&grp->list_lock); + if (is_src) + list_add_tail(&subs->src_list, &grp->list_head); + else + list_add_tail(&subs->dest_list, &grp->list_head); + grp->exclusive = exclusive; + atomic_inc(&subs->ref_count); + write_unlock_irq(&grp->list_lock); + err = 0; - src->exclusive = dest->exclusive = exclusive; + __error: + up_write(&grp->list_mutex); + return err; +} + +static void delete_and_unsubscribe_port(struct snd_seq_client *client, + struct snd_seq_client_port *port, + struct snd_seq_subscribers *subs, + bool is_src, bool ack) +{ + struct snd_seq_port_subs_info *grp; + struct list_head *list; + bool empty; + + grp = is_src ? &port->c_src : &port->c_dest; + list = is_src ? &subs->src_list : &subs->dest_list; + down_write(&grp->list_mutex); + write_lock_irq(&grp->list_lock); + empty = list_empty(list); + if (!empty) + list_del_init(list); + grp->exclusive = 0; + write_unlock_irq(&grp->list_lock); + up_write(&grp->list_mutex); + + if (!empty) + unsubscribe_port(client, port, grp, &subs->info, ack); +} + +/* connect two ports */ +int snd_seq_port_connect(struct snd_seq_client *connector, + struct snd_seq_client *src_client, + struct snd_seq_client_port *src_port, + struct snd_seq_client *dest_client, + struct snd_seq_client_port *dest_port, + struct snd_seq_port_subscribe *info) +{ + struct snd_seq_subscribers *subs; + bool exclusive; + int err; + + subs = kzalloc(sizeof(*subs), GFP_KERNEL); + if (!subs) + return -ENOMEM; + + subs->info = *info; + atomic_set(&subs->ref_count, 0); + INIT_LIST_HEAD(&subs->src_list); + INIT_LIST_HEAD(&subs->dest_list); + + exclusive = !!(info->flags & SNDRV_SEQ_PORT_SUBS_EXCLUSIVE); + + err = check_and_subscribe_port(src_client, src_port, subs, true, + exclusive, + connector->number != src_client->number); + if (err < 0) + goto error; + err = check_and_subscribe_port(dest_client, dest_port, subs, false, + exclusive, + connector->number != dest_client->number); + if (err < 0) + goto error_dest; - up_write(&dest->list_mutex); - up_write(&src->list_mutex); return 0; - __error: - if (src_called) - unsubscribe_port(src_client, src_port, src, info, - connector->number != src_client->number); + error_dest: + delete_and_unsubscribe_port(src_client, src_port, subs, true, + connector->number != src_client->number); + error: kfree(subs); - up_write(&dest->list_mutex); - up_write(&src->list_mutex); return err; } - /* remove the connection */ int snd_seq_port_disconnect(struct snd_seq_client *connector, struct snd_seq_client *src_client, @@ -567,37 +606,28 @@ int snd_seq_port_disconnect(struct snd_seq_client *connector, struct snd_seq_port_subscribe *info) { struct snd_seq_port_subs_info *src = &src_port->c_src; - struct snd_seq_port_subs_info *dest = &dest_port->c_dest; struct snd_seq_subscribers *subs; int err = -ENOENT; - unsigned long flags; down_write(&src->list_mutex); - down_write_nested(&dest->list_mutex, SINGLE_DEPTH_NESTING); - /* look for the connection */ list_for_each_entry(subs, &src->list_head, src_list) { if (match_subs_info(info, &subs->info)) { - write_lock_irqsave(&src->list_lock, flags); - // write_lock(&dest->list_lock); // no lock yet - list_del(&subs->src_list); - list_del(&subs->dest_list); - // write_unlock(&dest->list_lock); - write_unlock_irqrestore(&src->list_lock, flags); - src->exclusive = dest->exclusive = 0; - unsubscribe_port(src_client, src_port, src, info, - connector->number != src_client->number); - unsubscribe_port(dest_client, dest_port, dest, info, - connector->number != dest_client->number); - kfree(subs); + atomic_dec(&subs->ref_count); /* mark as not ready */ err = 0; break; } } - - up_write(&dest->list_mutex); up_write(&src->list_mutex); - return err; + if (err < 0) + return err; + + delete_and_unsubscribe_port(src_client, src_port, subs, true, + connector->number != src_client->number); + delete_and_unsubscribe_port(dest_client, dest_port, subs, false, + connector->number != dest_client->number); + kfree(subs); + return 0; } diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c index 7dfd0f429410..0bec02e89d51 100644 --- a/sound/core/seq/seq_queue.c +++ b/sound/core/seq/seq_queue.c @@ -142,8 +142,10 @@ static struct snd_seq_queue *queue_new(int owner, int locked) static void queue_delete(struct snd_seq_queue *q) { /* stop and release the timer */ + mutex_lock(&q->timer_mutex); snd_seq_timer_stop(q->timer); snd_seq_timer_close(q); + mutex_unlock(&q->timer_mutex); /* wait until access free */ snd_use_lock_sync(&q->use_lock); /* release resources... */ diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c index 82b220c769c1..293104926098 100644 --- a/sound/core/seq/seq_timer.c +++ b/sound/core/seq/seq_timer.c @@ -90,6 +90,9 @@ void snd_seq_timer_delete(struct snd_seq_timer **tmr) void snd_seq_timer_defaults(struct snd_seq_timer * tmr) { + unsigned long flags; + + spin_lock_irqsave(&tmr->lock, flags); /* setup defaults */ tmr->ppq = 96; /* 96 PPQ */ tmr->tempo = 500000; /* 120 BPM */ @@ -105,21 +108,25 @@ void snd_seq_timer_defaults(struct snd_seq_timer * tmr) tmr->preferred_resolution = seq_default_timer_resolution; tmr->skew = tmr->skew_base = SKEW_BASE; + spin_unlock_irqrestore(&tmr->lock, flags); } -void snd_seq_timer_reset(struct snd_seq_timer * tmr) +static void seq_timer_reset(struct snd_seq_timer *tmr) { - unsigned long flags; - - spin_lock_irqsave(&tmr->lock, flags); - /* reset time & songposition */ tmr->cur_time.tv_sec = 0; tmr->cur_time.tv_nsec = 0; tmr->tick.cur_tick = 0; tmr->tick.fraction = 0; +} + +void snd_seq_timer_reset(struct snd_seq_timer *tmr) +{ + unsigned long flags; + spin_lock_irqsave(&tmr->lock, flags); + seq_timer_reset(tmr); spin_unlock_irqrestore(&tmr->lock, flags); } @@ -138,8 +145,11 @@ static void snd_seq_timer_interrupt(struct snd_timer_instance *timeri, tmr = q->timer; if (tmr == NULL) return; - if (!tmr->running) + spin_lock_irqsave(&tmr->lock, flags); + if (!tmr->running) { + spin_unlock_irqrestore(&tmr->lock, flags); return; + } resolution *= ticks; if (tmr->skew != tmr->skew_base) { @@ -148,8 +158,6 @@ static void snd_seq_timer_interrupt(struct snd_timer_instance *timeri, (((resolution & 0xffff) * tmr->skew) >> 16); } - spin_lock_irqsave(&tmr->lock, flags); - /* update timer */ snd_seq_inc_time_nsec(&tmr->cur_time, resolution); @@ -296,26 +304,30 @@ int snd_seq_timer_open(struct snd_seq_queue *q) t->callback = snd_seq_timer_interrupt; t->callback_data = q; t->flags |= SNDRV_TIMER_IFLG_AUTO; + spin_lock_irq(&tmr->lock); tmr->timeri = t; + spin_unlock_irq(&tmr->lock); return 0; } int snd_seq_timer_close(struct snd_seq_queue *q) { struct snd_seq_timer *tmr; + struct snd_timer_instance *t; tmr = q->timer; if (snd_BUG_ON(!tmr)) return -EINVAL; - if (tmr->timeri) { - snd_timer_stop(tmr->timeri); - snd_timer_close(tmr->timeri); - tmr->timeri = NULL; - } + spin_lock_irq(&tmr->lock); + t = tmr->timeri; + tmr->timeri = NULL; + spin_unlock_irq(&tmr->lock); + if (t) + snd_timer_close(t); return 0; } -int snd_seq_timer_stop(struct snd_seq_timer * tmr) +static int seq_timer_stop(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; @@ -326,6 +338,17 @@ int snd_seq_timer_stop(struct snd_seq_timer * tmr) return 0; } +int snd_seq_timer_stop(struct snd_seq_timer *tmr) +{ + unsigned long flags; + int err; + + spin_lock_irqsave(&tmr->lock, flags); + err = seq_timer_stop(tmr); + spin_unlock_irqrestore(&tmr->lock, flags); + return err; +} + static int initialize_timer(struct snd_seq_timer *tmr) { struct snd_timer *t; @@ -358,13 +381,13 @@ static int initialize_timer(struct snd_seq_timer *tmr) return 0; } -int snd_seq_timer_start(struct snd_seq_timer * tmr) +static int seq_timer_start(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; if (tmr->running) - snd_seq_timer_stop(tmr); - snd_seq_timer_reset(tmr); + seq_timer_stop(tmr); + seq_timer_reset(tmr); if (initialize_timer(tmr) < 0) return -EINVAL; snd_timer_start(tmr->timeri, tmr->ticks); @@ -373,14 +396,25 @@ int snd_seq_timer_start(struct snd_seq_timer * tmr) return 0; } -int snd_seq_timer_continue(struct snd_seq_timer * tmr) +int snd_seq_timer_start(struct snd_seq_timer *tmr) +{ + unsigned long flags; + int err; + + spin_lock_irqsave(&tmr->lock, flags); + err = seq_timer_start(tmr); + spin_unlock_irqrestore(&tmr->lock, flags); + return err; +} + +static int seq_timer_continue(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; if (tmr->running) return -EBUSY; if (! tmr->initialized) { - snd_seq_timer_reset(tmr); + seq_timer_reset(tmr); if (initialize_timer(tmr) < 0) return -EINVAL; } @@ -390,11 +424,24 @@ int snd_seq_timer_continue(struct snd_seq_timer * tmr) return 0; } +int snd_seq_timer_continue(struct snd_seq_timer *tmr) +{ + unsigned long flags; + int err; + + spin_lock_irqsave(&tmr->lock, flags); + err = seq_timer_continue(tmr); + spin_unlock_irqrestore(&tmr->lock, flags); + return err; +} + /* return current 'real' time. use timeofday() to get better granularity. */ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) { snd_seq_real_time_t cur_time; + unsigned long flags; + spin_lock_irqsave(&tmr->lock, flags); cur_time = tmr->cur_time; if (tmr->running) { struct timeval tm; @@ -410,7 +457,7 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) } snd_seq_sanity_real_time(&cur_time); } - + spin_unlock_irqrestore(&tmr->lock, flags); return cur_time; } diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 56e0f4cd3f82..81134e067184 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -155,21 +155,26 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, struct snd_virmidi *vmidi = substream->runtime->private_data; int count, res; unsigned char buf[32], *pbuf; + unsigned long flags; if (up) { vmidi->trigger = 1; if (vmidi->seq_mode == SNDRV_VIRMIDI_SEQ_DISPATCH && !(vmidi->rdev->flags & SNDRV_VIRMIDI_SUBSCRIBE)) { - snd_rawmidi_transmit_ack(substream, substream->runtime->buffer_size - substream->runtime->avail); - return; /* ignored */ + while (snd_rawmidi_transmit(substream, buf, + sizeof(buf)) > 0) { + /* ignored */ + } + return; } if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) { if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0) return; vmidi->event.type = SNDRV_SEQ_EVENT_NONE; } + spin_lock_irqsave(&substream->runtime->lock, flags); while (1) { - count = snd_rawmidi_transmit_peek(substream, buf, sizeof(buf)); + count = __snd_rawmidi_transmit_peek(substream, buf, sizeof(buf)); if (count <= 0) break; pbuf = buf; @@ -179,16 +184,18 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, snd_midi_event_reset_encode(vmidi->parser); continue; } - snd_rawmidi_transmit_ack(substream, res); + __snd_rawmidi_transmit_ack(substream, res); pbuf += res; count -= res; if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) { if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0) - return; + goto out; vmidi->event.type = SNDRV_SEQ_EVENT_NONE; } } } + out: + spin_unlock_irqrestore(&substream->runtime->lock, flags); } else { vmidi->trigger = 0; } @@ -254,9 +261,13 @@ static int snd_virmidi_output_open(struct snd_rawmidi_substream *substream) */ static int snd_virmidi_input_close(struct snd_rawmidi_substream *substream) { + struct snd_virmidi_dev *rdev = substream->rmidi->private_data; struct snd_virmidi *vmidi = substream->runtime->private_data; - snd_midi_event_free(vmidi->parser); + + write_lock_irq(&rdev->filelist_lock); list_del(&vmidi->list); + write_unlock_irq(&rdev->filelist_lock); + snd_midi_event_free(vmidi->parser); substream->runtime->private_data = NULL; kfree(vmidi); return 0; diff --git a/sound/core/timer.c b/sound/core/timer.c index 8b06413e967e..b982d1b089bd 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -65,6 +65,7 @@ struct snd_timer_user { int qtail; int qused; int queue_size; + bool disconnected; struct snd_timer_read *queue; struct snd_timer_tread *tqueue; spinlock_t qlock; @@ -73,7 +74,7 @@ struct snd_timer_user { struct timespec tstamp; /* trigger tstamp */ wait_queue_head_t qchange_sleep; struct fasync_struct *fasync; - struct mutex tread_sem; + struct mutex ioctl_lock; }; /* list of timers */ @@ -290,6 +291,9 @@ int snd_timer_open(struct snd_timer_instance **ti, mutex_unlock(®ister_mutex); return -ENOMEM; } + /* take a card refcount for safe disconnection */ + if (timer->card) + get_device(&timer->card->card_dev); timeri->slave_class = tid->dev_sclass; timeri->slave_id = slave_id; if (list_empty(&timer->open_list_head) && timer->hw.open) @@ -301,8 +305,7 @@ int snd_timer_open(struct snd_timer_instance **ti, return 0; } -static int _snd_timer_stop(struct snd_timer_instance *timeri, - int keep_flag, int event); +static int _snd_timer_stop(struct snd_timer_instance *timeri, int event); /* * close a timer instance @@ -344,7 +347,7 @@ int snd_timer_close(struct snd_timer_instance *timeri) spin_unlock_irq(&timer->lock); mutex_lock(®ister_mutex); list_del(&timeri->open_list); - if (timer && list_empty(&timer->open_list_head) && + if (list_empty(&timer->open_list_head) && timer->hw.close) timer->hw.close(timer); /* remove slave links */ @@ -360,6 +363,9 @@ int snd_timer_close(struct snd_timer_instance *timeri) } spin_unlock(&timer->lock); spin_unlock_irq(&slave_active_lock); + /* release a card refcount for safe disconnection */ + if (timer->card) + put_device(&timer->card->card_dev); mutex_unlock(®ister_mutex); } out: @@ -416,7 +422,7 @@ static void snd_timer_notify1(struct snd_timer_instance *ti, int event) spin_lock_irqsave(&timer->lock, flags); list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) - ts->ccallback(ti, event + 100, &tstamp, resolution); + ts->ccallback(ts, event + 100, &tstamp, resolution); spin_unlock_irqrestore(&timer->lock, flags); } @@ -445,6 +451,10 @@ static int snd_timer_start_slave(struct snd_timer_instance *timeri) unsigned long flags; spin_lock_irqsave(&slave_active_lock, flags); + if (timeri->flags & SNDRV_TIMER_IFLG_RUNNING) { + spin_unlock_irqrestore(&slave_active_lock, flags); + return -EBUSY; + } timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; if (timeri->master && timeri->timer) { spin_lock(&timeri->timer->lock); @@ -469,23 +479,32 @@ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) { result = snd_timer_start_slave(timeri); - snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_START); + if (result >= 0) + snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_START); return result; } timer = timeri->timer; if (timer == NULL) return -EINVAL; + if (timer->card && timer->card->shutdown) + return -ENODEV; spin_lock_irqsave(&timer->lock, flags); + if (timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | + SNDRV_TIMER_IFLG_START)) { + result = -EBUSY; + goto unlock; + } timeri->ticks = timeri->cticks = ticks; timeri->pticks = 0; result = snd_timer_start1(timer, timeri, ticks); + unlock: spin_unlock_irqrestore(&timer->lock, flags); - snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_START); + if (result >= 0) + snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_START); return result; } -static int _snd_timer_stop(struct snd_timer_instance * timeri, - int keep_flag, int event) +static int _snd_timer_stop(struct snd_timer_instance *timeri, int event) { struct snd_timer *timer; unsigned long flags; @@ -494,21 +513,36 @@ static int _snd_timer_stop(struct snd_timer_instance * timeri, return -ENXIO; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) { - if (!keep_flag) { - spin_lock_irqsave(&slave_active_lock, flags); - timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; - list_del_init(&timeri->ack_list); - list_del_init(&timeri->active_list); + spin_lock_irqsave(&slave_active_lock, flags); + if (!(timeri->flags & SNDRV_TIMER_IFLG_RUNNING)) { spin_unlock_irqrestore(&slave_active_lock, flags); + return -EBUSY; } + if (timeri->timer) + spin_lock(&timeri->timer->lock); + timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; + list_del_init(&timeri->ack_list); + list_del_init(&timeri->active_list); + if (timeri->timer) + spin_unlock(&timeri->timer->lock); + spin_unlock_irqrestore(&slave_active_lock, flags); goto __end; } timer = timeri->timer; if (!timer) return -EINVAL; spin_lock_irqsave(&timer->lock, flags); + if (!(timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | + SNDRV_TIMER_IFLG_START))) { + spin_unlock_irqrestore(&timer->lock, flags); + return -EBUSY; + } list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); + if (timer->card && timer->card->shutdown) { + spin_unlock_irqrestore(&timer->lock, flags); + return 0; + } if ((timeri->flags & SNDRV_TIMER_IFLG_RUNNING) && !(--timer->running)) { timer->hw.stop(timer); @@ -521,9 +555,7 @@ static int _snd_timer_stop(struct snd_timer_instance * timeri, } } } - if (!keep_flag) - timeri->flags &= - ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START); + timeri->flags &= ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START); spin_unlock_irqrestore(&timer->lock, flags); __end: if (event != SNDRV_TIMER_EVENT_RESOLUTION) @@ -542,7 +574,7 @@ int snd_timer_stop(struct snd_timer_instance *timeri) unsigned long flags; int err; - err = _snd_timer_stop(timeri, 0, SNDRV_TIMER_EVENT_STOP); + err = _snd_timer_stop(timeri, SNDRV_TIMER_EVENT_STOP); if (err < 0) return err; timer = timeri->timer; @@ -571,11 +603,18 @@ int snd_timer_continue(struct snd_timer_instance *timeri) timer = timeri->timer; if (! timer) return -EINVAL; + if (timer->card && timer->card->shutdown) + return -ENODEV; spin_lock_irqsave(&timer->lock, flags); + if (timeri->flags & SNDRV_TIMER_IFLG_RUNNING) { + result = -EBUSY; + goto unlock; + } if (!timeri->cticks) timeri->cticks = 1; timeri->pticks = 0; result = snd_timer_start1(timer, timeri, timer->sticks); + unlock: spin_unlock_irqrestore(&timer->lock, flags); snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_CONTINUE); return result; @@ -586,7 +625,7 @@ int snd_timer_continue(struct snd_timer_instance *timeri) */ int snd_timer_pause(struct snd_timer_instance * timeri) { - return _snd_timer_stop(timeri, 0, SNDRV_TIMER_EVENT_PAUSE); + return _snd_timer_stop(timeri, SNDRV_TIMER_EVENT_PAUSE); } /* @@ -634,6 +673,9 @@ static void snd_timer_tasklet(unsigned long arg) unsigned long resolution, ticks; unsigned long flags; + if (timer->card && timer->card->shutdown) + return; + spin_lock_irqsave(&timer->lock, flags); /* now process all callbacks */ while (!list_empty(&timer->sack_list_head)) { @@ -674,6 +716,9 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) if (timer == NULL) return; + if (timer->card && timer->card->shutdown) + return; + spin_lock_irqsave(&timer->lock, flags); /* remember the current resolution */ @@ -703,8 +748,8 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) ti->cticks = ti->ticks; } else { ti->flags &= ~SNDRV_TIMER_IFLG_RUNNING; - if (--timer->running) - list_del(&ti->active_list); + --timer->running; + list_del_init(&ti->active_list); } if ((timer->hw.flags & SNDRV_TIMER_HW_TASKLET) || (ti->flags & SNDRV_TIMER_IFLG_FAST)) @@ -884,11 +929,28 @@ static int snd_timer_dev_register(struct snd_device *dev) return 0; } +/* just for reference in snd_timer_dev_disconnect() below */ +static void snd_timer_user_ccallback(struct snd_timer_instance *timeri, + int event, struct timespec *tstamp, + unsigned long resolution); + static int snd_timer_dev_disconnect(struct snd_device *device) { struct snd_timer *timer = device->device_data; + struct snd_timer_instance *ti; + mutex_lock(®ister_mutex); list_del_init(&timer->device_list); + /* wake up pending sleepers */ + list_for_each_entry(ti, &timer->open_list_head, open_list) { + /* FIXME: better to have a ti.disconnect() op */ + if (ti->ccallback == snd_timer_user_ccallback) { + struct snd_timer_user *tu = ti->callback_data; + + tu->disconnected = true; + wake_up(&tu->qchange_sleep); + } + } mutex_unlock(®ister_mutex); return 0; } @@ -899,6 +961,8 @@ void snd_timer_notify(struct snd_timer *timer, int event, struct timespec *tstam unsigned long resolution = 0; struct snd_timer_instance *ti, *ts; + if (timer->card && timer->card->shutdown) + return; if (! (timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) return; if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_MSTART || @@ -987,8 +1051,8 @@ static int snd_timer_s_start(struct snd_timer * timer) njiff += timer->sticks - priv->correction; priv->correction = 0; } - priv->last_expires = priv->tlist.expires = njiff; - add_timer(&priv->tlist); + priv->last_expires = njiff; + mod_timer(&priv->tlist, njiff); return 0; } @@ -1057,6 +1121,8 @@ static void snd_timer_proc_read(struct snd_info_entry *entry, mutex_lock(®ister_mutex); list_for_each_entry(timer, &snd_timer_list, device_list) { + if (timer->card && timer->card->shutdown) + continue; switch (timer->tmr_class) { case SNDRV_TIMER_CLASS_GLOBAL: snd_iprintf(buffer, "G%i: ", timer->tmr_device); @@ -1263,7 +1329,7 @@ static int snd_timer_user_open(struct inode *inode, struct file *file) return -ENOMEM; spin_lock_init(&tu->qlock); init_waitqueue_head(&tu->qchange_sleep); - mutex_init(&tu->tread_sem); + mutex_init(&tu->ioctl_lock); tu->ticks = 1; tu->queue_size = 128; tu->queue = kmalloc(tu->queue_size * sizeof(struct snd_timer_read), @@ -1283,8 +1349,10 @@ static int snd_timer_user_release(struct inode *inode, struct file *file) if (file->private_data) { tu = file->private_data; file->private_data = NULL; + mutex_lock(&tu->ioctl_lock); if (tu->timeri) snd_timer_close(tu->timeri); + mutex_unlock(&tu->ioctl_lock); kfree(tu->queue); kfree(tu->tqueue); kfree(tu); @@ -1522,7 +1590,6 @@ static int snd_timer_user_tselect(struct file *file, int err = 0; tu = file->private_data; - mutex_lock(&tu->tread_sem); if (tu->timeri) { snd_timer_close(tu->timeri); tu->timeri = NULL; @@ -1566,7 +1633,6 @@ static int snd_timer_user_tselect(struct file *file, } __err: - mutex_unlock(&tu->tread_sem); return err; } @@ -1779,7 +1845,7 @@ enum { SNDRV_TIMER_IOCTL_PAUSE_OLD = _IO('T', 0x23), }; -static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, +static long __snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_timer_user *tu; @@ -1796,17 +1862,11 @@ static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, { int xarg; - mutex_lock(&tu->tread_sem); - if (tu->timeri) { /* too late */ - mutex_unlock(&tu->tread_sem); + if (tu->timeri) /* too late */ return -EBUSY; - } - if (get_user(xarg, p)) { - mutex_unlock(&tu->tread_sem); + if (get_user(xarg, p)) return -EFAULT; - } tu->tread = xarg ? 1 : 0; - mutex_unlock(&tu->tread_sem); return 0; } case SNDRV_TIMER_IOCTL_GINFO: @@ -1839,6 +1899,18 @@ static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, return -ENOTTY; } +static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct snd_timer_user *tu = file->private_data; + long ret; + + mutex_lock(&tu->ioctl_lock); + ret = __snd_timer_user_ioctl(file, cmd, arg); + mutex_unlock(&tu->ioctl_lock); + return ret; +} + static int snd_timer_user_fasync(int fd, struct file * file, int on) { struct snd_timer_user *tu; @@ -1852,6 +1924,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, { struct snd_timer_user *tu; long result = 0, unit; + int qhead; int err = 0; tu = file->private_data; @@ -1863,7 +1936,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; - break; + goto _error; } set_current_state(TASK_INTERRUPTIBLE); @@ -1876,40 +1949,39 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, remove_wait_queue(&tu->qchange_sleep, &wait); + if (tu->disconnected) { + err = -ENODEV; + goto _error; + } if (signal_pending(current)) { err = -ERESTARTSYS; - break; + goto _error; } } + qhead = tu->qhead++; + tu->qhead %= tu->queue_size; spin_unlock_irq(&tu->qlock); - if (err < 0) - goto _error; if (tu->tread) { - if (copy_to_user(buffer, &tu->tqueue[tu->qhead++], - sizeof(struct snd_timer_tread))) { + if (copy_to_user(buffer, &tu->tqueue[qhead], + sizeof(struct snd_timer_tread))) err = -EFAULT; - goto _error; - } } else { - if (copy_to_user(buffer, &tu->queue[tu->qhead++], - sizeof(struct snd_timer_read))) { + if (copy_to_user(buffer, &tu->queue[qhead], + sizeof(struct snd_timer_read))) err = -EFAULT; - goto _error; - } } - tu->qhead %= tu->queue_size; - - result += unit; - buffer += unit; - spin_lock_irq(&tu->qlock); tu->qused--; + if (err < 0) + goto _error; + result += unit; + buffer += unit; } - spin_unlock_irq(&tu->qlock); _error: + spin_unlock_irq(&tu->qlock); return result > 0 ? result : err; } @@ -1925,6 +1997,8 @@ static unsigned int snd_timer_user_poll(struct file *file, poll_table * wait) mask = 0; if (tu->qused) mask |= POLLIN | POLLRDNORM; + if (tu->disconnected) + mask |= POLLERR; return mask; } diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c index e05802ae6e1b..2e908225d754 100644 --- a/sound/core/timer_compat.c +++ b/sound/core/timer_compat.c @@ -70,13 +70,14 @@ static int snd_timer_user_status_compat(struct file *file, struct snd_timer_status32 __user *_status) { struct snd_timer_user *tu; - struct snd_timer_status status; + struct snd_timer_status32 status; tu = file->private_data; if (snd_BUG_ON(!tu->timeri)) return -ENXIO; memset(&status, 0, sizeof(status)); - status.tstamp = tu->tstamp; + status.tstamp.tv_sec = tu->tstamp.tv_sec; + status.tstamp.tv_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; @@ -88,12 +89,21 @@ static int snd_timer_user_status_compat(struct file *file, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has the same struct as x86-64 */ +#define snd_timer_user_status_x32(file, s) \ + snd_timer_user_status(file, s) +#endif /* CONFIG_X86_X32 */ + /* */ enum { SNDRV_TIMER_IOCTL_INFO32 = _IOR('T', 0x11, struct snd_timer_info32), SNDRV_TIMER_IOCTL_STATUS32 = _IOW('T', 0x14, struct snd_timer_status32), +#ifdef CONFIG_X86_X32 + SNDRV_TIMER_IOCTL_STATUS_X32 = _IOW('T', 0x14, struct snd_timer_status), +#endif /* CONFIG_X86_X32 */ }; static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -122,6 +132,10 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns return snd_timer_user_info_compat(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: return snd_timer_user_status_compat(file, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_TIMER_IOCTL_STATUS_X32: + return snd_timer_user_status_x32(file, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; } diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index 016e451ed506..a9f7a75702d2 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -109,6 +109,9 @@ struct dummy_timer_ops { snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *); }; +#define get_dummy_ops(substream) \ + (*(const struct dummy_timer_ops **)(substream)->runtime->private_data) + struct dummy_model { const char *name; int (*playback_constraints)(struct snd_pcm_runtime *runtime); @@ -137,7 +140,6 @@ struct snd_dummy { int iobox; struct snd_kcontrol *cd_volume_ctl; struct snd_kcontrol *cd_switch_ctl; - const struct dummy_timer_ops *timer_ops; }; /* @@ -231,6 +233,8 @@ static struct dummy_model *dummy_models[] = { */ struct dummy_systimer_pcm { + /* ops must be the first item */ + const struct dummy_timer_ops *timer_ops; spinlock_t lock; struct timer_list timer; unsigned long base_time; @@ -366,6 +370,8 @@ static struct dummy_timer_ops dummy_systimer_ops = { */ struct dummy_hrtimer_pcm { + /* ops must be the first item */ + const struct dummy_timer_ops *timer_ops; ktime_t base_time; ktime_t period_time; atomic_t running; @@ -492,31 +498,25 @@ static struct dummy_timer_ops dummy_hrtimer_ops = { static int dummy_pcm_trigger(struct snd_pcm_substream *substream, int cmd) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: - return dummy->timer_ops->start(substream); + return get_dummy_ops(substream)->start(substream); case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: - return dummy->timer_ops->stop(substream); + return get_dummy_ops(substream)->stop(substream); } return -EINVAL; } static int dummy_pcm_prepare(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - - return dummy->timer_ops->prepare(substream); + return get_dummy_ops(substream)->prepare(substream); } static snd_pcm_uframes_t dummy_pcm_pointer(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - - return dummy->timer_ops->pointer(substream); + return get_dummy_ops(substream)->pointer(substream); } static struct snd_pcm_hardware dummy_pcm_hardware = { @@ -562,17 +562,19 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) struct snd_dummy *dummy = snd_pcm_substream_chip(substream); struct dummy_model *model = dummy->model; struct snd_pcm_runtime *runtime = substream->runtime; + const struct dummy_timer_ops *ops; int err; - dummy->timer_ops = &dummy_systimer_ops; + ops = &dummy_systimer_ops; #ifdef CONFIG_HIGH_RES_TIMERS if (hrtimer) - dummy->timer_ops = &dummy_hrtimer_ops; + ops = &dummy_hrtimer_ops; #endif - err = dummy->timer_ops->create(substream); + err = ops->create(substream); if (err < 0) return err; + get_dummy_ops(substream) = ops; runtime->hw = dummy->pcm_hw; if (substream->pcm->device & 1) { @@ -594,7 +596,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) err = model->capture_constraints(substream->runtime); } if (err < 0) { - dummy->timer_ops->free(substream); + get_dummy_ops(substream)->free(substream); return err; } return 0; @@ -602,8 +604,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) static int dummy_pcm_close(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - dummy->timer_ops->free(substream); + get_dummy_ops(substream)->free(substream); return 0; } diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c index 926e5dcbb66a..5022c9b97ddf 100644 --- a/sound/firewire/bebob/bebob_stream.c +++ b/sound/firewire/bebob/bebob_stream.c @@ -47,14 +47,16 @@ static const unsigned int bridgeco_freq_table[] = { [6] = 0x07, }; -static unsigned int -get_formation_index(unsigned int rate) +static int +get_formation_index(unsigned int rate, unsigned int *index) { unsigned int i; for (i = 0; i < ARRAY_SIZE(snd_bebob_rate_table); i++) { - if (snd_bebob_rate_table[i] == rate) - return i; + if (snd_bebob_rate_table[i] == rate) { + *index = i; + return 0; + } } return -EINVAL; } @@ -425,7 +427,9 @@ make_both_connections(struct snd_bebob *bebob, unsigned int rate) goto end; /* confirm params for both streams */ - index = get_formation_index(rate); + err = get_formation_index(rate, &index); + if (err < 0) + goto end; pcm_channels = bebob->tx_stream_formations[index].pcm; midi_channels = bebob->tx_stream_formations[index].midi; err = amdtp_am824_set_parameters(&bebob->tx_stream, rate, diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig index 0216475fc759..37adcc6cbe6b 100644 --- a/sound/isa/Kconfig +++ b/sound/isa/Kconfig @@ -3,6 +3,7 @@ config SND_WSS_LIB tristate select SND_PCM + select SND_TIMER config SND_SB_COMMON tristate @@ -42,6 +43,7 @@ config SND_AD1816A select SND_OPL3_LIB select SND_MPU401_UART select SND_PCM + select SND_TIMER help Say Y here to include support for Analog Devices SoundPort AD1816A or compatible sound chips. @@ -209,6 +211,7 @@ config SND_GUSCLASSIC tristate "Gravis UltraSound Classic" select SND_RAWMIDI select SND_PCM + select SND_TIMER help Say Y here to include support for Gravis UltraSound Classic soundcards. @@ -221,6 +224,7 @@ config SND_GUSEXTREME select SND_OPL3_LIB select SND_MPU401_UART select SND_PCM + select SND_TIMER help Say Y here to include support for Gravis UltraSound Extreme soundcards. diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig index 656ce39bddbc..8f6594a7d37f 100644 --- a/sound/pci/Kconfig +++ b/sound/pci/Kconfig @@ -155,6 +155,7 @@ config SND_AZT3328 select SND_PCM select SND_RAWMIDI select SND_AC97_CODEC + select SND_TIMER depends on ZONE_DMA help Say Y here to include support for Aztech AZF3328 (PCI168) @@ -463,6 +464,7 @@ config SND_EMU10K1 select SND_HWDEP select SND_RAWMIDI select SND_AC97_CODEC + select SND_TIMER depends on ZONE_DMA help Say Y to include support for Sound Blaster PCI 512, Live!, @@ -889,6 +891,7 @@ config SND_YMFPCI select SND_OPL3_LIB select SND_MPU401_UART select SND_AC97_CODEC + select SND_TIMER help Say Y here to include support for Yamaha PCI audio chips - YMF724, YMF724F, YMF740, YMF740C, YMF744, YMF754. diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 70671ad65d24..6efadbfb3fe3 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -174,14 +174,40 @@ static inline bool codec_probed(struct hda_codec *codec) return device_attach(hda_codec_dev(codec)) > 0 && codec->preset; } -/* try to auto-load and bind the codec module */ -static void codec_bind_module(struct hda_codec *codec) +/* try to auto-load codec module */ +static void request_codec_module(struct hda_codec *codec) { #ifdef MODULE char modalias[32]; + const char *mod = NULL; + + switch (codec->probe_id) { + case HDA_CODEC_ID_GENERIC_HDMI: +#if IS_MODULE(CONFIG_SND_HDA_CODEC_HDMI) + mod = "snd-hda-codec-hdmi"; +#endif + break; + case HDA_CODEC_ID_GENERIC: +#if IS_MODULE(CONFIG_SND_HDA_GENERIC) + mod = "snd-hda-codec-generic"; +#endif + break; + default: + snd_hdac_codec_modalias(&codec->core, modalias, sizeof(modalias)); + mod = modalias; + break; + } + + if (mod) + request_module(mod); +#endif /* MODULE */ +} - snd_hdac_codec_modalias(&codec->core, modalias, sizeof(modalias)); - request_module(modalias); +/* try to auto-load and bind the codec module */ +static void codec_bind_module(struct hda_codec *codec) +{ +#ifdef MODULE + request_codec_module(codec); if (codec_probed(codec)) return; #endif @@ -218,17 +244,13 @@ static int codec_bind_generic(struct hda_codec *codec) if (is_likely_hdmi_codec(codec)) { codec->probe_id = HDA_CODEC_ID_GENERIC_HDMI; -#if IS_MODULE(CONFIG_SND_HDA_CODEC_HDMI) - request_module("snd-hda-codec-hdmi"); -#endif + request_codec_module(codec); if (codec_probed(codec)) return 0; } codec->probe_id = HDA_CODEC_ID_GENERIC; -#if IS_MODULE(CONFIG_SND_HDA_GENERIC) - request_module("snd-hda-codec-generic"); -#endif + request_codec_module(codec); if (codec_probed(codec)) return 0; return -ENODEV; diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index c6e8a651cea1..367dbf0d285e 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -771,9 +771,6 @@ static void activate_amp(struct hda_codec *codec, hda_nid_t nid, int dir, unsigned int caps; unsigned int mask, val; - if (!enable && is_active_nid(codec, nid, dir, idx_to_check)) - return; - caps = query_amp_caps(codec, nid, dir); val = get_amp_val_to_activate(codec, nid, dir, caps, enable); mask = get_amp_mask_to_modify(codec, nid, dir, idx_to_check, caps); @@ -784,12 +781,22 @@ static void activate_amp(struct hda_codec *codec, hda_nid_t nid, int dir, update_amp(codec, nid, dir, idx, mask, val); } +static void check_and_activate_amp(struct hda_codec *codec, hda_nid_t nid, + int dir, int idx, int idx_to_check, + bool enable) +{ + /* check whether the given amp is still used by others */ + if (!enable && is_active_nid(codec, nid, dir, idx_to_check)) + return; + activate_amp(codec, nid, dir, idx, idx_to_check, enable); +} + static void activate_amp_out(struct hda_codec *codec, struct nid_path *path, int i, bool enable) { hda_nid_t nid = path->path[i]; init_amp(codec, nid, HDA_OUTPUT, 0); - activate_amp(codec, nid, HDA_OUTPUT, 0, 0, enable); + check_and_activate_amp(codec, nid, HDA_OUTPUT, 0, 0, enable); } static void activate_amp_in(struct hda_codec *codec, struct nid_path *path, @@ -817,9 +824,16 @@ static void activate_amp_in(struct hda_codec *codec, struct nid_path *path, * when aa-mixer is available, we need to enable the path as well */ for (n = 0; n < nums; n++) { - if (n != idx && (!add_aamix || conn[n] != spec->mixer_merge_nid)) - continue; - activate_amp(codec, nid, HDA_INPUT, n, idx, enable); + if (n != idx) { + if (conn[n] != spec->mixer_merge_nid) + continue; + /* when aamix is disabled, force to off */ + if (!add_aamix) { + activate_amp(codec, nid, HDA_INPUT, n, n, false); + continue; + } + } + check_and_activate_amp(codec, nid, HDA_INPUT, n, idx, enable); } } @@ -829,7 +843,7 @@ static hda_nid_t path_power_update(struct hda_codec *codec, bool allow_powerdown) { hda_nid_t nid, changed = 0; - int i, state; + int i, state, power; for (i = 0; i < path->depth; i++) { nid = path->path[i]; @@ -841,7 +855,9 @@ static hda_nid_t path_power_update(struct hda_codec *codec, state = AC_PWRST_D0; else state = AC_PWRST_D3; - if (!snd_hda_check_power_state(codec, nid, state)) { + power = snd_hda_codec_read(codec, nid, 0, + AC_VERB_GET_POWER_STATE, 0); + if (power != (state | (state << 4))) { snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_POWER_STATE, state); changed = nid; @@ -1580,6 +1596,12 @@ static bool map_singles(struct hda_codec *codec, int outs, return found; } +static inline bool has_aamix_out_paths(struct hda_gen_spec *spec) +{ + return spec->aamix_out_paths[0] || spec->aamix_out_paths[1] || + spec->aamix_out_paths[2]; +} + /* create a new path including aamix if available, and return its index */ static int check_aamix_out_path(struct hda_codec *codec, int path_idx) { @@ -2422,25 +2444,51 @@ static void update_aamix_paths(struct hda_codec *codec, bool do_mix, } } +/* re-initialize the output paths; only called from loopback_mixing_put() */ +static void update_output_paths(struct hda_codec *codec, int num_outs, + const int *paths) +{ + struct hda_gen_spec *spec = codec->spec; + struct nid_path *path; + int i; + + for (i = 0; i < num_outs; i++) { + path = snd_hda_get_path_from_idx(codec, paths[i]); + if (path) + snd_hda_activate_path(codec, path, path->active, + spec->aamix_mode); + } +} + static int loopback_mixing_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct hda_codec *codec = snd_kcontrol_chip(kcontrol); struct hda_gen_spec *spec = codec->spec; + const struct auto_pin_cfg *cfg = &spec->autocfg; unsigned int val = ucontrol->value.enumerated.item[0]; if (val == spec->aamix_mode) return 0; spec->aamix_mode = val; - update_aamix_paths(codec, val, spec->out_paths[0], - spec->aamix_out_paths[0], - spec->autocfg.line_out_type); - update_aamix_paths(codec, val, spec->hp_paths[0], - spec->aamix_out_paths[1], - AUTO_PIN_HP_OUT); - update_aamix_paths(codec, val, spec->speaker_paths[0], - spec->aamix_out_paths[2], - AUTO_PIN_SPEAKER_OUT); + if (has_aamix_out_paths(spec)) { + update_aamix_paths(codec, val, spec->out_paths[0], + spec->aamix_out_paths[0], + cfg->line_out_type); + update_aamix_paths(codec, val, spec->hp_paths[0], + spec->aamix_out_paths[1], + AUTO_PIN_HP_OUT); + update_aamix_paths(codec, val, spec->speaker_paths[0], + spec->aamix_out_paths[2], + AUTO_PIN_SPEAKER_OUT); + } else { + update_output_paths(codec, cfg->line_outs, spec->out_paths); + if (cfg->line_out_type != AUTO_PIN_HP_OUT) + update_output_paths(codec, cfg->hp_outs, spec->hp_paths); + if (cfg->line_out_type != AUTO_PIN_SPEAKER_OUT) + update_output_paths(codec, cfg->speaker_outs, + spec->speaker_paths); + } return 1; } @@ -2458,12 +2506,13 @@ static int create_loopback_mixing_ctl(struct hda_codec *codec) if (!spec->mixer_nid) return 0; - if (!(spec->aamix_out_paths[0] || spec->aamix_out_paths[1] || - spec->aamix_out_paths[2])) - return 0; if (!snd_hda_gen_add_kctl(spec, NULL, &loopback_mixing_enum)) return -ENOMEM; spec->have_aamix_ctl = 1; + /* if no explicit aamix path is present (e.g. for Realtek codecs), + * enable aamix as default -- just for compatibility + */ + spec->aamix_mode = !has_aamix_out_paths(spec); return 0; } @@ -3998,9 +4047,9 @@ static void pin_power_callback(struct hda_codec *codec, struct hda_jack_callback *jack, bool on) { - if (jack && jack->tbl->nid) + if (jack && jack->nid) sync_power_state_change(codec, - set_pin_power_jack(codec, jack->tbl->nid, on)); + set_pin_power_jack(codec, jack->nid, on)); } /* callback only doing power up -- called at first */ @@ -5664,6 +5713,8 @@ static void init_aamix_paths(struct hda_codec *codec) if (!spec->have_aamix_ctl) return; + if (!has_aamix_out_paths(spec)) + return; update_aamix_paths(codec, spec->aamix_mode, spec->out_paths[0], spec->aamix_out_paths[0], spec->autocfg.line_out_type); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 3b3658297070..411630e9c034 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -90,6 +90,8 @@ enum { #define NVIDIA_HDA_ENABLE_COHBIT 0x01 /* Defines for Intel SCH HDA snoop control */ +#define INTEL_HDA_CGCTL 0x48 +#define INTEL_HDA_CGCTL_MISCBDCGE (0x1 << 6) #define INTEL_SCH_HDA_DEVC 0x78 #define INTEL_SCH_HDA_DEVC_NOSNOOP (0x1<<11) @@ -355,7 +357,10 @@ enum { ((pci)->device == 0x0d0c) || \ ((pci)->device == 0x160c)) -#define IS_BROXTON(pci) ((pci)->device == 0x5a98) +#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) +#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) +#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) +#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) static char *driver_short_names[] = { [AZX_DRIVER_ICH] = "HDA Intel", @@ -528,15 +533,26 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) { struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; + u32 val; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); + if (IS_SKL_PLUS(pci)) { + pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); + val = val & ~INTEL_HDA_CGCTL_MISCBDCGE; + pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); + } azx_init_chip(chip, full_reset); + if (IS_SKL_PLUS(pci)) { + pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); + val = val | INTEL_HDA_CGCTL_MISCBDCGE; + pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); + } if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, false); /* reduce dma latency to avoid noise */ - if (IS_BROXTON(pci)) + if (IS_BXT(pci)) bxt_reduce_dma_latency(chip); } @@ -958,11 +974,6 @@ static int azx_resume(struct device *dev) /* put codec down to D3 at hibernation for Intel SKL+; * otherwise BIOS may still access the codec and screw up the driver */ -#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) -#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) -#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) -#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) - static int azx_freeze_noirq(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); @@ -2126,9 +2137,17 @@ i915_power_fail: static void azx_remove(struct pci_dev *pci) { struct snd_card *card = pci_get_drvdata(pci); + struct azx *chip; + struct hda_intel *hda; + + if (card) { + /* cancel the pending probing work */ + chip = card->private_data; + hda = container_of(chip, struct hda_intel, chip); + cancel_work_sync(&hda->probe_work); - if (card) snd_card_free(card); + } } static void azx_shutdown(struct pci_dev *pci) @@ -2188,6 +2207,9 @@ static const struct pci_device_id azx_ids[] = { /* Broxton-P(Apollolake) */ { PCI_DEVICE(0x8086, 0x5a98), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON }, + /* Broxton-T */ + { PCI_DEVICE(0x8086, 0x1a98), + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON }, /* Haswell */ { PCI_DEVICE(0x8086, 0x0a0c), .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_HASWELL }, diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c index c945e257d368..a33234e04d4f 100644 --- a/sound/pci/hda/hda_jack.c +++ b/sound/pci/hda/hda_jack.c @@ -259,7 +259,7 @@ snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid, if (!callback) return ERR_PTR(-ENOMEM); callback->func = func; - callback->tbl = jack; + callback->nid = jack->nid; callback->next = jack->callback; jack->callback = callback; } diff --git a/sound/pci/hda/hda_jack.h b/sound/pci/hda/hda_jack.h index 858708a044f5..e9814c0168ea 100644 --- a/sound/pci/hda/hda_jack.h +++ b/sound/pci/hda/hda_jack.h @@ -21,7 +21,7 @@ struct hda_jack_callback; typedef void (*hda_jack_callback_fn) (struct hda_codec *, struct hda_jack_callback *); struct hda_jack_callback { - struct hda_jack_tbl *tbl; + hda_nid_t nid; hda_jack_callback_fn func; unsigned int private_data; /* arbitrary data */ struct hda_jack_callback *next; diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 4ef2259f88ca..9ceb2bc36e68 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -4427,13 +4427,16 @@ static void ca0132_process_dsp_response(struct hda_codec *codec, static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) { struct ca0132_spec *spec = codec->spec; + struct hda_jack_tbl *tbl; /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ cancel_delayed_work_sync(&spec->unsol_hp_work); schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); - cb->tbl->block_report = 1; + tbl = snd_hda_jack_tbl_get(codec, cb->nid); + if (tbl) + tbl->block_report = 1; } static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb) diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index a12ae8ac0914..80bbadc83721 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -174,8 +174,12 @@ static void cs_automute(struct hda_codec *codec) snd_hda_gen_update_outputs(codec); if (spec->gpio_eapd_hp || spec->gpio_eapd_speaker) { - spec->gpio_data = spec->gen.hp_jack_present ? - spec->gpio_eapd_hp : spec->gpio_eapd_speaker; + if (spec->gen.automute_speaker) + spec->gpio_data = spec->gen.hp_jack_present ? + spec->gpio_eapd_hp : spec->gpio_eapd_speaker; + else + spec->gpio_data = + spec->gpio_eapd_hp | spec->gpio_eapd_speaker; snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA, spec->gpio_data); } @@ -357,6 +361,7 @@ static int cs_parse_auto_config(struct hda_codec *codec) { struct cs_spec *spec = codec->spec; int err; + int i; err = snd_hda_parse_pin_defcfg(codec, &spec->gen.autocfg, NULL, 0); if (err < 0) @@ -366,6 +371,19 @@ static int cs_parse_auto_config(struct hda_codec *codec) if (err < 0) return err; + /* keep the ADCs powered up when it's dynamically switchable */ + if (spec->gen.dyn_adc_switch) { + unsigned int done = 0; + for (i = 0; i < spec->gen.input_mux.num_items; i++) { + int idx = spec->gen.dyn_adc_idx[i]; + if (done & (1 << idx)) + continue; + snd_hda_gen_fix_pin_power(codec, + spec->gen.adc_nids[idx]); + done |= 1 << idx; + } + } + return 0; } @@ -614,6 +632,7 @@ enum { CS4208_MAC_AUTO, CS4208_MBA6, CS4208_MBP11, + CS4208_MACMINI, CS4208_GPIO0, }; @@ -621,6 +640,7 @@ static const struct hda_model_fixup cs4208_models[] = { { .id = CS4208_GPIO0, .name = "gpio0" }, { .id = CS4208_MBA6, .name = "mba6" }, { .id = CS4208_MBP11, .name = "mbp11" }, + { .id = CS4208_MACMINI, .name = "macmini" }, {} }; @@ -632,6 +652,7 @@ static const struct snd_pci_quirk cs4208_fixup_tbl[] = { /* codec SSID matching */ static const struct snd_pci_quirk cs4208_mac_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x5e00, "MacBookPro 11,2", CS4208_MBP11), + SND_PCI_QUIRK(0x106b, 0x6c00, "MacMini 7,1", CS4208_MACMINI), SND_PCI_QUIRK(0x106b, 0x7100, "MacBookAir 6,1", CS4208_MBA6), SND_PCI_QUIRK(0x106b, 0x7200, "MacBookAir 6,2", CS4208_MBA6), SND_PCI_QUIRK(0x106b, 0x7b00, "MacBookPro 12,1", CS4208_MBP11), @@ -666,6 +687,24 @@ static void cs4208_fixup_mac(struct hda_codec *codec, snd_hda_apply_fixup(codec, action); } +/* MacMini 7,1 has the inverted jack detection */ +static void cs4208_fixup_macmini(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const struct hda_pintbl pincfgs[] = { + { 0x18, 0x00ab9150 }, /* mic (audio-in) jack: disable detect */ + { 0x21, 0x004be140 }, /* SPDIF: disable detect */ + { } + }; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + /* HP pin (0x10) has an inverted detection */ + codec->inv_jack_detect = 1; + /* disable the bogus Mic and SPDIF jack detections */ + snd_hda_apply_pincfgs(codec, pincfgs); + } +} + static int cs4208_spdif_sw_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { @@ -709,6 +748,12 @@ static const struct hda_fixup cs4208_fixups[] = { .chained = true, .chain_id = CS4208_GPIO0, }, + [CS4208_MACMINI] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs4208_fixup_macmini, + .chained = true, + .chain_id = CS4208_GPIO0, + }, [CS4208_GPIO0] = { .type = HDA_FIXUP_FUNC, .v.func = cs4208_fixup_gpio0, diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index ef198903c0c3..600af5878e75 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -204,8 +204,13 @@ static void cx_auto_reboot_notify(struct hda_codec *codec) { struct conexant_spec *spec = codec->spec; - if (codec->core.vendor_id != 0x14f150f2) + switch (codec->core.vendor_id) { + case 0x14f150f2: /* CX20722 */ + case 0x14f150f4: /* CX20724 */ + break; + default: return; + } /* Turn the CX20722 codec into D3 to avoid spurious noises from the internal speaker during (and after) reboot */ diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 4b6fb668c91c..f7bcd8dbac14 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -438,7 +438,8 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol, eld = &per_pin->sink_eld; mutex_lock(&per_pin->lock); - if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data)) { + if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data) || + eld->eld_size > ELD_MAX_SIZE) { mutex_unlock(&per_pin->lock); snd_BUG(); return -EINVAL; @@ -1183,7 +1184,7 @@ static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid) static void jack_callback(struct hda_codec *codec, struct hda_jack_callback *jack) { - check_presence_and_report(codec, jack->tbl->nid); + check_presence_and_report(codec, jack->nid); } static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res) @@ -2352,6 +2353,10 @@ static void intel_pin_eld_notify(void *audio_ptr, int port) struct hda_codec *codec = audio_ptr; int pin_nid = port + 0x04; + /* we assume only from port-B to port-D */ + if (port < 1 || port > 3) + return; + /* skip notification during system suspend (but not in runtime PM); * the state will be updated at resume */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3a89d82f8057..ac4490a96863 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -282,7 +282,7 @@ static void alc_update_knob_master(struct hda_codec *codec, uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (!uctl) return; - val = snd_hda_codec_read(codec, jack->tbl->nid, 0, + val = snd_hda_codec_read(codec, jack->nid, 0, AC_VERB_GET_VOLUME_KNOB_CONTROL, 0); val &= HDA_AMP_VOLMASK; uctl->value.integer.value[0] = val; @@ -327,6 +327,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0292: alc_update_coef_idx(codec, 0x4, 1<<15, 0); break; + case 0x10ec0225: case 0x10ec0233: case 0x10ec0255: case 0x10ec0256: @@ -900,6 +901,7 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = { { 0x10ec0899, 0x1028, 0, "ALC3861" }, { 0x10ec0298, 0x1028, 0, "ALC3266" }, { 0x10ec0256, 0x1028, 0, "ALC3246" }, + { 0x10ec0225, 0x1028, 0, "ALC3253" }, { 0x10ec0670, 0x1025, 0, "ALC669X" }, { 0x10ec0676, 0x1025, 0, "ALC679X" }, { 0x10ec0282, 0x1043, 0, "ALC3229" }, @@ -1785,7 +1787,6 @@ enum { ALC882_FIXUP_NO_PRIMARY_HP, ALC887_FIXUP_ASUS_BASS, ALC887_FIXUP_BASS_CHMAP, - ALC882_FIXUP_DISABLE_AAMIX, }; static void alc889_fixup_coef(struct hda_codec *codec, @@ -1947,8 +1948,6 @@ static void alc882_fixup_no_primary_hp(struct hda_codec *codec, static void alc_fixup_bass_chmap(struct hda_codec *codec, const struct hda_fixup *fix, int action); -static void alc_fixup_disable_aamix(struct hda_codec *codec, - const struct hda_fixup *fix, int action); static const struct hda_fixup alc882_fixups[] = { [ALC882_FIXUP_ABIT_AW9D_MAX] = { @@ -2186,10 +2185,6 @@ static const struct hda_fixup alc882_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_bass_chmap, }, - [ALC882_FIXUP_DISABLE_AAMIX] = { - .type = HDA_FIXUP_FUNC, - .v.func = alc_fixup_disable_aamix, - }, }; static const struct snd_pci_quirk alc882_fixup_tbl[] = { @@ -2228,6 +2223,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT), SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP), SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP), + SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP), /* All Apple entries are in codec SSIDs */ SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF), @@ -2257,7 +2253,6 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE), - SND_PCI_QUIRK(0x1458, 0xa182, "Gigabyte Z170X-UD3", ALC882_FIXUP_DISABLE_AAMIX), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), @@ -2651,6 +2646,7 @@ enum { ALC269_TYPE_ALC298, ALC269_TYPE_ALC255, ALC269_TYPE_ALC256, + ALC269_TYPE_ALC225, }; /* @@ -2680,6 +2676,7 @@ static int alc269_parse_auto_config(struct hda_codec *codec) case ALC269_TYPE_ALC298: case ALC269_TYPE_ALC255: case ALC269_TYPE_ALC256: + case ALC269_TYPE_ALC225: ssids = alc269_ssids; break; default: @@ -3658,6 +3655,16 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec) WRITE_COEF(0xb7, 0x802b), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x4a, 1<<8, 0), + UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), + UPDATE_COEF(0x63, 3<<14, 3<<14), + UPDATE_COEF(0x4a, 3<<4, 2<<4), + UPDATE_COEF(0x4a, 3<<10, 3<<10), + UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10), + UPDATE_COEF(0x4a, 3<<10, 0), + {} + }; switch (codec->core.vendor_id) { case 0x10ec0255: @@ -3682,6 +3689,9 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec) case 0x10ec0668: alc_process_coef_fw(codec, coef0668); break; + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; } codec_dbg(codec, "Headset jack set to unplugged mode.\n"); } @@ -3727,6 +3737,13 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, UPDATE_COEF(0xc3, 0, 1<<12), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEFEX(0x57, 0x05, 1<<14, 1<<14), + UPDATE_COEF(0x4a, 3<<4, 2<<4), + UPDATE_COEF(0x63, 3<<14, 0), + {} + }; + switch (codec->core.vendor_id) { case 0x10ec0255: @@ -3772,12 +3789,22 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, alc_process_coef_fw(codec, coef0688); snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50); break; + case 0x10ec0225: + alc_update_coef_idx(codec, 0x45, 0x3f<<10, 0x31<<10); + snd_hda_set_pin_ctl_cache(codec, hp_pin, 0); + alc_process_coef_fw(codec, coef0225); + snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50); + break; } codec_dbg(codec, "Headset jack set to mic-in mode.\n"); } static void alc_headset_mode_default(struct hda_codec *codec) { + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10), + {} + }; static struct coef_fw coef0255[] = { WRITE_COEF(0x45, 0xc089), WRITE_COEF(0x45, 0xc489), @@ -3819,6 +3846,9 @@ static void alc_headset_mode_default(struct hda_codec *codec) }; switch (codec->core.vendor_id) { + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; case 0x10ec0255: case 0x10ec0256: alc_process_coef_fw(codec, coef0255); @@ -3884,6 +3914,13 @@ static void alc_headset_mode_ctia(struct hda_codec *codec) WRITE_COEF(0xc3, 0x0000), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x35<<10), + UPDATE_COEF(0x49, 1<<8, 1<<8), + UPDATE_COEF(0x4a, 7<<6, 7<<6), + UPDATE_COEF(0x4a, 3<<4, 3<<4), + {} + }; switch (codec->core.vendor_id) { case 0x10ec0255: @@ -3912,6 +3949,9 @@ static void alc_headset_mode_ctia(struct hda_codec *codec) case 0x10ec0668: alc_process_coef_fw(codec, coef0688); break; + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; } codec_dbg(codec, "Headset jack set to iPhone-style headset mode.\n"); } @@ -3955,6 +3995,13 @@ static void alc_headset_mode_omtp(struct hda_codec *codec) WRITE_COEF(0xc3, 0x0000), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x39<<10), + UPDATE_COEF(0x49, 1<<8, 1<<8), + UPDATE_COEF(0x4a, 7<<6, 7<<6), + UPDATE_COEF(0x4a, 3<<4, 3<<4), + {} + }; switch (codec->core.vendor_id) { case 0x10ec0255: @@ -3983,6 +4030,9 @@ static void alc_headset_mode_omtp(struct hda_codec *codec) case 0x10ec0668: alc_process_coef_fw(codec, coef0688); break; + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; } codec_dbg(codec, "Headset jack set to Nokia-style headset mode.\n"); } @@ -4014,6 +4064,11 @@ static void alc_determine_headset_type(struct hda_codec *codec) WRITE_COEF(0xc3, 0x0c00), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10), + UPDATE_COEF(0x49, 1<<8, 1<<8), + {} + }; switch (codec->core.vendor_id) { case 0x10ec0255: @@ -4058,6 +4113,12 @@ static void alc_determine_headset_type(struct hda_codec *codec) val = alc_read_coef_idx(codec, 0xbe); is_ctia = (val & 0x1c02) == 0x1c02; break; + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + msleep(800); + val = alc_read_coef_idx(codec, 0x46); + is_ctia = (val & 0x00f0) == 0x00f0; + break; } codec_dbg(codec, "Headset jack detected iPhone-style headset: %s\n", @@ -4666,6 +4727,7 @@ enum { ALC290_FIXUP_SUBWOOFER, ALC290_FIXUP_SUBWOOFER_HSJACK, ALC269_FIXUP_THINKPAD_ACPI, + ALC269_FIXUP_DMIC_THINKPAD_ACPI, ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, ALC255_FIXUP_HEADSET_MODE, @@ -4694,6 +4756,11 @@ enum { ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, ALC293_FIXUP_LENOVO_SPK_NOISE, ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, + ALC255_FIXUP_DELL_SPK_NOISE, + ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC280_FIXUP_HP_HEADSET_MIC, + ALC221_FIXUP_HP_FRONT_MIC, + ALC292_FIXUP_TPT460, }; static const struct hda_fixup alc269_fixups[] = { @@ -5103,6 +5170,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = hda_fixup_thinkpad_acpi, }, + [ALC269_FIXUP_DMIC_THINKPAD_ACPI] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_inv_dmic, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + }, [ALC255_FIXUP_DELL1_MIC_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -5307,6 +5380,42 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_fixup_lenovo_line2_mic_hotkey, }, + [ALC255_FIXUP_DELL_SPK_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, + [ALC225_FIXUP_DELL1_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Disable pass-through path for FRONT 14h */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x36 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 }, + {} + }, + .chained = true, + .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE + }, + [ALC280_FIXUP_HP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MIC, + }, + [ALC221_FIXUP_HP_FRONT_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x02a19020 }, /* Front Mic */ + { } + }, + }, + [ALC292_FIXUP_TPT460] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_tpt440_dock, + .chained = true, + .chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5318,12 +5427,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK), SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK), + SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), SND_PCI_QUIRK(0x1028, 0x05bd, "Dell Latitude E6440", ALC292_FIXUP_DELL_E7X), + SND_PCI_QUIRK(0x1028, 0x05be, "Dell Latitude E6540", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x05ca, "Dell Latitude E7240", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x05cb, "Dell Latitude E7440", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x05da, "Dell Vostro 5460", ALC290_FIXUP_SUBWOOFER), @@ -5332,11 +5443,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x05f6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), + SND_PCI_QUIRK(0x1028, 0x062c, "Dell Latitude E5550", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x062e, "Dell Latitude E7450", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK), SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0665, "Dell XPS 13", ALC288_FIXUP_DELL_XPS_13), + SND_PCI_QUIRK(0x1028, 0x0669, "Dell Optiplex 9020m", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x069a, "Dell Vostro 5480", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), @@ -5347,6 +5460,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -5407,6 +5521,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC), + SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -5455,8 +5571,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2218, "Thinkpad X1 Carbon 2nd", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), + SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), + SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), + SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -5466,6 +5584,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK), + SND_PCI_QUIRK(0x17aa, 0x504a, "ThinkPad X260", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), @@ -5548,8 +5667,12 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"}, {.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"}, {.id = ALC292_FIXUP_TPT440, .name = "tpt440"}, + {.id = ALC292_FIXUP_TPT460, .name = "tpt460"}, {} }; +#define ALC225_STANDARD_PINS \ + {0x12, 0xb7a60130}, \ + {0x21, 0x04211020} #define ALC256_STANDARD_PINS \ {0x12, 0x90a60140}, \ @@ -5571,6 +5694,12 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {0x21, 0x03211020} static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC225_STANDARD_PINS, + {0x14, 0x901701a0}), + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC225_STANDARD_PINS, + {0x14, 0x901701b0}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), @@ -5617,6 +5746,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x21, 0x02211040}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x12, 0x90a60170}, + {0x14, 0x90171130}, + {0x21, 0x02211040}), + SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60170}, {0x14, 0x90170140}, {0x21, 0x02211050}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell Inspiron 5548", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, @@ -5892,6 +6025,9 @@ static int patch_alc269(struct hda_codec *codec) spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/ break; + case 0x10ec0225: + spec->codec_variant = ALC269_TYPE_ALC225; + break; } if (snd_hda_codec_read(codec, 0x51, 0, AC_VERB_PARAMETERS, 0) == 0x10ec5505) { @@ -6289,6 +6425,7 @@ enum { ALC668_FIXUP_AUTO_MUTE, ALC668_FIXUP_DELL_DISABLE_AAMIX, ALC668_FIXUP_DELL_XPS13, + ALC662_FIXUP_ASUS_Nx50, }; static const struct hda_fixup alc662_fixups[] = { @@ -6529,6 +6666,12 @@ static const struct hda_fixup alc662_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_bass_chmap, }, + [ALC662_FIXUP_ASUS_Nx50] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_auto_mute_via_amp, + .chained = true, + .chain_id = ALC662_FIXUP_BASS_1A + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -6551,7 +6694,9 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0698, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x069f, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), - SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A), + SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_ASUS_Nx50), + SND_PCI_QUIRK(0x1043, 0x13df, "Asus N550JX", ALC662_FIXUP_BASS_1A), + SND_PCI_QUIRK(0x1043, 0x129d, "Asus N750", ALC662_FIXUP_ASUS_Nx50), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_MODE4_CHMAP), SND_PCI_QUIRK(0x1043, 0x15a7, "ASUS UX51VZH", ALC662_FIXUP_BASS_16), SND_PCI_QUIRK(0x1043, 0x1b73, "ASUS N55SF", ALC662_FIXUP_BASS_16), @@ -6781,6 +6926,7 @@ static int patch_alc680(struct hda_codec *codec) */ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0221, "ALC221", patch_alc269), + HDA_CODEC_ENTRY(0x10ec0225, "ALC225", patch_alc269), HDA_CODEC_ENTRY(0x10ec0231, "ALC231", patch_alc269), HDA_CODEC_ENTRY(0x10ec0233, "ALC233", patch_alc269), HDA_CODEC_ENTRY(0x10ec0235, "ALC233", patch_alc269), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 2c7c5eb8b1e9..37b70f8e878f 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -493,9 +493,9 @@ static void jack_update_power(struct hda_codec *codec, if (!spec->num_pwrs) return; - if (jack && jack->tbl->nid) { - stac_toggle_power_map(codec, jack->tbl->nid, - snd_hda_jack_detect(codec, jack->tbl->nid), + if (jack && jack->nid) { + stac_toggle_power_map(codec, jack->nid, + snd_hda_jack_detect(codec, jack->nid), true); return; } diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c index 42bcbac801a3..ccdab29a8b66 100644 --- a/sound/pci/intel8x0.c +++ b/sound/pci/intel8x0.c @@ -2879,6 +2879,7 @@ static void intel8x0_measure_ac97_clock(struct intel8x0 *chip) static struct snd_pci_quirk intel8x0_clock_list[] = { SND_PCI_QUIRK(0x0e11, 0x008a, "AD1885", 41000), + SND_PCI_QUIRK(0x1014, 0x0581, "AD1981B", 48000), SND_PCI_QUIRK(0x1028, 0x00be, "AD1885", 44100), SND_PCI_QUIRK(0x1028, 0x0177, "AD1980", 48000), SND_PCI_QUIRK(0x1028, 0x01ad, "AD1981B", 48000), diff --git a/sound/pci/pcxhr/pcxhr_core.c b/sound/pci/pcxhr/pcxhr_core.c index c5194f5b150a..d7e71f309299 100644 --- a/sound/pci/pcxhr/pcxhr_core.c +++ b/sound/pci/pcxhr/pcxhr_core.c @@ -1341,5 +1341,6 @@ irqreturn_t pcxhr_threaded_irq(int irq, void *dev_id) } pcxhr_msg_thread(mgr); + mutex_unlock(&mgr->lock); return IRQ_HANDLED; } diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 2875b4f6d8c9..7c8941b8b2de 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -2879,7 +2879,7 @@ static int snd_hdsp_get_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl { struct hdsp *hdsp = snd_kcontrol_chip(kcontrol); - ucontrol->value.enumerated.item[0] = hdsp_dds_offset(hdsp); + ucontrol->value.integer.value[0] = hdsp_dds_offset(hdsp); return 0; } @@ -2891,7 +2891,7 @@ static int snd_hdsp_put_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl if (!snd_hdsp_use_is_exclusive(hdsp)) return -EBUSY; - val = ucontrol->value.enumerated.item[0]; + val = ucontrol->value.integer.value[0]; spin_lock_irq(&hdsp->lock); if (val != hdsp_dds_offset(hdsp)) change = (hdsp_set_dds_offset(hdsp, val) == 0) ? 1 : 0; diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index 8bc8016c173d..a4a999a0317e 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -1601,6 +1601,9 @@ static void hdspm_set_dds_value(struct hdspm *hdspm, int rate) { u64 n; + if (snd_BUG_ON(rate <= 0)) + return; + if (rate >= 112000) rate /= 4; else if (rate >= 56000) @@ -2215,6 +2218,8 @@ static int hdspm_get_system_sample_rate(struct hdspm *hdspm) } else { /* slave mode, return external sample rate */ rate = hdspm_external_sample_rate(hdspm); + if (!rate) + rate = hdspm->system_sample_rate; } } @@ -2260,8 +2265,11 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol, ucontrol) { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); + int rate = ucontrol->value.integer.value[0]; - hdspm_set_dds_value(hdspm, ucontrol->value.enumerated.item[0]); + if (rate < 27000 || rate > 207000) + return -EINVAL; + hdspm_set_dds_value(hdspm, ucontrol->value.integer.value[0]); return 0; } @@ -4449,7 +4457,7 @@ static int snd_hdspm_get_tco_word_term(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - ucontrol->value.enumerated.item[0] = hdspm->tco->term; + ucontrol->value.integer.value[0] = hdspm->tco->term; return 0; } @@ -4460,8 +4468,8 @@ static int snd_hdspm_put_tco_word_term(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - if (hdspm->tco->term != ucontrol->value.enumerated.item[0]) { - hdspm->tco->term = ucontrol->value.enumerated.item[0]; + if (hdspm->tco->term != ucontrol->value.integer.value[0]) { + hdspm->tco->term = ucontrol->value.integer.value[0]; hdspm_tco_write(hdspm); diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index f2beb1aa5763..b1c8bb39cdf1 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -359,7 +359,7 @@ static const DECLARE_TLV_DB_RANGE(bst_tlv, /* Interface data select */ static const char * const rt5640_data_select[] = { - "Normal", "left copy to right", "right copy to left", "Swap"}; + "Normal", "Swap", "left copy to right", "right copy to left"}; static SOC_ENUM_SINGLE_DECL(rt5640_if1_dac_enum, RT5640_DIG_INF_DATA, RT5640_IF1_DAC_SEL_SFT, rt5640_data_select); diff --git a/sound/soc/codecs/rt5640.h b/sound/soc/codecs/rt5640.h index 3deb8babeabb..243f42633989 100644 --- a/sound/soc/codecs/rt5640.h +++ b/sound/soc/codecs/rt5640.h @@ -442,39 +442,39 @@ #define RT5640_IF1_DAC_SEL_MASK (0x3 << 14) #define RT5640_IF1_DAC_SEL_SFT 14 #define RT5640_IF1_DAC_SEL_NOR (0x0 << 14) -#define RT5640_IF1_DAC_SEL_L2R (0x1 << 14) -#define RT5640_IF1_DAC_SEL_R2L (0x2 << 14) -#define RT5640_IF1_DAC_SEL_SWAP (0x3 << 14) +#define RT5640_IF1_DAC_SEL_SWAP (0x1 << 14) +#define RT5640_IF1_DAC_SEL_L2R (0x2 << 14) +#define RT5640_IF1_DAC_SEL_R2L (0x3 << 14) #define RT5640_IF1_ADC_SEL_MASK (0x3 << 12) #define RT5640_IF1_ADC_SEL_SFT 12 #define RT5640_IF1_ADC_SEL_NOR (0x0 << 12) -#define RT5640_IF1_ADC_SEL_L2R (0x1 << 12) -#define RT5640_IF1_ADC_SEL_R2L (0x2 << 12) -#define RT5640_IF1_ADC_SEL_SWAP (0x3 << 12) +#define RT5640_IF1_ADC_SEL_SWAP (0x1 << 12) +#define RT5640_IF1_ADC_SEL_L2R (0x2 << 12) +#define RT5640_IF1_ADC_SEL_R2L (0x3 << 12) #define RT5640_IF2_DAC_SEL_MASK (0x3 << 10) #define RT5640_IF2_DAC_SEL_SFT 10 #define RT5640_IF2_DAC_SEL_NOR (0x0 << 10) -#define RT5640_IF2_DAC_SEL_L2R (0x1 << 10) -#define RT5640_IF2_DAC_SEL_R2L (0x2 << 10) -#define RT5640_IF2_DAC_SEL_SWAP (0x3 << 10) +#define RT5640_IF2_DAC_SEL_SWAP (0x1 << 10) +#define RT5640_IF2_DAC_SEL_L2R (0x2 << 10) +#define RT5640_IF2_DAC_SEL_R2L (0x3 << 10) #define RT5640_IF2_ADC_SEL_MASK (0x3 << 8) #define RT5640_IF2_ADC_SEL_SFT 8 #define RT5640_IF2_ADC_SEL_NOR (0x0 << 8) -#define RT5640_IF2_ADC_SEL_L2R (0x1 << 8) -#define RT5640_IF2_ADC_SEL_R2L (0x2 << 8) -#define RT5640_IF2_ADC_SEL_SWAP (0x3 << 8) +#define RT5640_IF2_ADC_SEL_SWAP (0x1 << 8) +#define RT5640_IF2_ADC_SEL_L2R (0x2 << 8) +#define RT5640_IF2_ADC_SEL_R2L (0x3 << 8) #define RT5640_IF3_DAC_SEL_MASK (0x3 << 6) #define RT5640_IF3_DAC_SEL_SFT 6 #define RT5640_IF3_DAC_SEL_NOR (0x0 << 6) -#define RT5640_IF3_DAC_SEL_L2R (0x1 << 6) -#define RT5640_IF3_DAC_SEL_R2L (0x2 << 6) -#define RT5640_IF3_DAC_SEL_SWAP (0x3 << 6) +#define RT5640_IF3_DAC_SEL_SWAP (0x1 << 6) +#define RT5640_IF3_DAC_SEL_L2R (0x2 << 6) +#define RT5640_IF3_DAC_SEL_R2L (0x3 << 6) #define RT5640_IF3_ADC_SEL_MASK (0x3 << 4) #define RT5640_IF3_ADC_SEL_SFT 4 #define RT5640_IF3_ADC_SEL_NOR (0x0 << 4) -#define RT5640_IF3_ADC_SEL_L2R (0x1 << 4) -#define RT5640_IF3_ADC_SEL_R2L (0x2 << 4) -#define RT5640_IF3_ADC_SEL_SWAP (0x3 << 4) +#define RT5640_IF3_ADC_SEL_SWAP (0x1 << 4) +#define RT5640_IF3_ADC_SEL_L2R (0x2 << 4) +#define RT5640_IF3_ADC_SEL_R2L (0x3 << 4) /* REC Left Mixer Control 1 (0x3b) */ #define RT5640_G_HP_L_RM_L_MASK (0x7 << 13) diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 3e3c7f6be29d..b74840b5becf 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -621,7 +621,7 @@ static const struct snd_kcontrol_new rt5645_snd_controls[] = { /* IN1/IN2 Control */ SOC_SINGLE_TLV("IN1 Boost", RT5645_IN1_CTRL1, - RT5645_BST_SFT1, 8, 0, bst_tlv), + RT5645_BST_SFT1, 12, 0, bst_tlv), SOC_SINGLE_TLV("IN2 Boost", RT5645_IN2_CTRL, RT5645_BST_SFT2, 8, 0, bst_tlv), diff --git a/sound/soc/codecs/ssm4567.c b/sound/soc/codecs/ssm4567.c index e619d5651b09..080c78e88e10 100644 --- a/sound/soc/codecs/ssm4567.c +++ b/sound/soc/codecs/ssm4567.c @@ -352,6 +352,11 @@ static int ssm4567_set_power(struct ssm4567 *ssm4567, bool enable) regcache_cache_only(ssm4567->regmap, !enable); if (enable) { + ret = regmap_write(ssm4567->regmap, SSM4567_REG_SOFT_RESET, + 0x00); + if (ret) + return ret; + ret = regmap_update_bits(ssm4567->regmap, SSM4567_REG_POWER_CTRL, SSM4567_POWER_SPWDN, 0x00); diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index c04c0bc6f58a..52b9ccf6d389 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -360,15 +360,13 @@ static int wm5110_hp_ev(struct snd_soc_dapm_widget *w, static int wm5110_clear_pga_volume(struct arizona *arizona, int output) { - struct reg_sequence clear_pga = { - ARIZONA_OUTPUT_PATH_CONFIG_1L + output * 4, 0x80 - }; + unsigned int reg = ARIZONA_OUTPUT_PATH_CONFIG_1L + output * 4; int ret; - ret = regmap_multi_reg_write_bypassed(arizona->regmap, &clear_pga, 1); + ret = regmap_write(arizona->regmap, reg, 0x80); if (ret) dev_err(arizona->dev, "Failed to clear PGA (0x%x): %d\n", - clear_pga.reg, ret); + reg, ret); return ret; } diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index c799cca5abeb..6b864c0fc2b6 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -459,7 +459,7 @@ static int wm8958_put_mbc_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -549,7 +549,7 @@ static int wm8958_put_vss_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -582,7 +582,7 @@ static int wm8958_put_vss_hpf_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -749,7 +749,7 @@ static int wm8958_put_enh_eq_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index 2ccbb322df77..a18aecb49935 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -362,7 +362,7 @@ static int wm8994_put_drc_enum(struct snd_kcontrol *kcontrol, struct wm8994 *control = wm8994->wm8994; struct wm8994_pdata *pdata = &control->pdata; int drc = wm8994_get_drc(kcontrol->id.name); - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (drc < 0) return drc; @@ -469,7 +469,7 @@ static int wm8994_put_retune_mobile_enum(struct snd_kcontrol *kcontrol, struct wm8994 *control = wm8994->wm8994; struct wm8994_pdata *pdata = &control->pdata; int block = wm8994_get_retune_mobile_block(kcontrol->id.name); - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (block < 0) return block; diff --git a/sound/soc/samsung/ac97.c b/sound/soc/samsung/ac97.c index e4145509d63c..9c5219392460 100644 --- a/sound/soc/samsung/ac97.c +++ b/sound/soc/samsung/ac97.c @@ -324,7 +324,7 @@ static const struct snd_soc_component_driver s3c_ac97_component = { static int s3c_ac97_probe(struct platform_device *pdev) { - struct resource *mem_res, *dmatx_res, *dmarx_res, *dmamic_res, *irq_res; + struct resource *mem_res, *irq_res; struct s3c_audio_pdata *ac97_pdata; int ret; @@ -335,24 +335,6 @@ static int s3c_ac97_probe(struct platform_device *pdev) } /* Check for availability of necessary resource */ - dmatx_res = platform_get_resource(pdev, IORESOURCE_DMA, 0); - if (!dmatx_res) { - dev_err(&pdev->dev, "Unable to get AC97-TX dma resource\n"); - return -ENXIO; - } - - dmarx_res = platform_get_resource(pdev, IORESOURCE_DMA, 1); - if (!dmarx_res) { - dev_err(&pdev->dev, "Unable to get AC97-RX dma resource\n"); - return -ENXIO; - } - - dmamic_res = platform_get_resource(pdev, IORESOURCE_DMA, 2); - if (!dmamic_res) { - dev_err(&pdev->dev, "Unable to get AC97-MIC dma resource\n"); - return -ENXIO; - } - irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); if (!irq_res) { dev_err(&pdev->dev, "AC97 IRQ not provided!\n"); @@ -364,11 +346,11 @@ static int s3c_ac97_probe(struct platform_device *pdev) if (IS_ERR(s3c_ac97.regs)) return PTR_ERR(s3c_ac97.regs); - s3c_ac97_pcm_out.channel = dmatx_res->start; + s3c_ac97_pcm_out.slave = ac97_pdata->dma_playback; s3c_ac97_pcm_out.dma_addr = mem_res->start + S3C_AC97_PCM_DATA; - s3c_ac97_pcm_in.channel = dmarx_res->start; + s3c_ac97_pcm_in.slave = ac97_pdata->dma_capture; s3c_ac97_pcm_in.dma_addr = mem_res->start + S3C_AC97_PCM_DATA; - s3c_ac97_mic_in.channel = dmamic_res->start; + s3c_ac97_mic_in.slave = ac97_pdata->dma_capture_mic; s3c_ac97_mic_in.dma_addr = mem_res->start + S3C_AC97_MIC_DATA; init_completion(&s3c_ac97.done); diff --git a/sound/soc/samsung/dma.h b/sound/soc/samsung/dma.h index 0e85dcfec023..085ef30f5ca2 100644 --- a/sound/soc/samsung/dma.h +++ b/sound/soc/samsung/dma.h @@ -15,7 +15,7 @@ #include <sound/dmaengine_pcm.h> struct s3c_dma_params { - int channel; /* Channel ID */ + void *slave; /* Channel ID */ dma_addr_t dma_addr; int dma_size; /* Size of the DMA transfer */ char *ch_name; diff --git a/sound/soc/samsung/dmaengine.c b/sound/soc/samsung/dmaengine.c index 506f5bf6d082..727008d57d14 100644 --- a/sound/soc/samsung/dmaengine.c +++ b/sound/soc/samsung/dmaengine.c @@ -50,14 +50,14 @@ void samsung_asoc_init_dma_data(struct snd_soc_dai *dai, if (playback) { playback_data = &playback->dma_data; - playback_data->filter_data = (void *)playback->channel; + playback_data->filter_data = playback->slave; playback_data->chan_name = playback->ch_name; playback_data->addr = playback->dma_addr; playback_data->addr_width = playback->dma_size; } if (capture) { capture_data = &capture->dma_data; - capture_data->filter_data = (void *)capture->channel; + capture_data->filter_data = capture->slave; capture_data->chan_name = capture->ch_name; capture_data->addr = capture->dma_addr; capture_data->addr_width = capture->dma_size; diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index ea4ab374a223..e163b0148c4b 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -480,10 +480,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai, unsigned int cdcon_mask = 1 << i2s_regs->cdclkcon_off; unsigned int rsrc_mask = 1 << i2s_regs->rclksrc_off; u32 mod, mask, val = 0; + unsigned long flags; - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); switch (clk_id) { case SAMSUNG_I2S_OPCLK: @@ -574,11 +575,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); mod = (mod & ~mask) | val; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); return 0; } @@ -589,6 +590,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, struct i2s_dai *i2s = to_info(dai); int lrp_shift, sdf_shift, sdf_mask, lrp_rlow, mod_slave; u32 mod, tmp = 0; + unsigned long flags; lrp_shift = i2s->variant_regs->lrp_off; sdf_shift = i2s->variant_regs->sdf_off; @@ -648,7 +650,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); /* * Don't change the I2S mode if any controller is active on this @@ -656,7 +658,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, */ if (any_active(i2s) && ((mod & (sdf_mask | lrp_rlow | mod_slave)) != tmp)) { - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); dev_err(&i2s->pdev->dev, "%s:%d Other DAI busy\n", __func__, __LINE__); return -EAGAIN; @@ -665,7 +667,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, mod &= ~(sdf_mask | lrp_rlow | mod_slave); mod |= tmp; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); return 0; } @@ -675,6 +677,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, { struct i2s_dai *i2s = to_info(dai); u32 mod, mask = 0, val = 0; + unsigned long flags; if (!is_secondary(i2s)) mask |= (MOD_DC2_EN | MOD_DC1_EN); @@ -743,11 +746,11 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); mod = (mod & ~mask) | val; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); samsung_asoc_init_dma_data(dai, &i2s->dma_playback, &i2s->dma_capture); @@ -1257,27 +1260,14 @@ static int samsung_i2s_probe(struct platform_device *pdev) pri_dai->lock = &pri_dai->spinlock; if (!np) { - res = platform_get_resource(pdev, IORESOURCE_DMA, 0); - if (!res) { - dev_err(&pdev->dev, - "Unable to get I2S-TX dma resource\n"); - return -ENXIO; - } - pri_dai->dma_playback.channel = res->start; - - res = platform_get_resource(pdev, IORESOURCE_DMA, 1); - if (!res) { - dev_err(&pdev->dev, - "Unable to get I2S-RX dma resource\n"); - return -ENXIO; - } - pri_dai->dma_capture.channel = res->start; - if (i2s_pdata == NULL) { dev_err(&pdev->dev, "Can't work without s3c_audio_pdata\n"); return -EINVAL; } + pri_dai->dma_playback.slave = i2s_pdata->dma_playback; + pri_dai->dma_capture.slave = i2s_pdata->dma_capture; + if (&i2s_pdata->type) i2s_cfg = &i2s_pdata->type.i2s; @@ -1338,11 +1328,8 @@ static int samsung_i2s_probe(struct platform_device *pdev) sec_dai->dma_playback.dma_addr = regs_base + I2STXDS; sec_dai->dma_playback.ch_name = "tx-sec"; - if (!np) { - res = platform_get_resource(pdev, IORESOURCE_DMA, 2); - if (res) - sec_dai->dma_playback.channel = res->start; - } + if (!np) + sec_dai->dma_playback.slave = i2s_pdata->dma_play_sec; sec_dai->dma_playback.dma_size = 4; sec_dai->addr = pri_dai->addr; diff --git a/sound/soc/samsung/pcm.c b/sound/soc/samsung/pcm.c index b320a9d3fbf8..c77f324e0bb8 100644 --- a/sound/soc/samsung/pcm.c +++ b/sound/soc/samsung/pcm.c @@ -486,7 +486,7 @@ static const struct snd_soc_component_driver s3c_pcm_component = { static int s3c_pcm_dev_probe(struct platform_device *pdev) { struct s3c_pcm_info *pcm; - struct resource *mem_res, *dmatx_res, *dmarx_res; + struct resource *mem_res; struct s3c_audio_pdata *pcm_pdata; int ret; @@ -499,18 +499,6 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev) pcm_pdata = pdev->dev.platform_data; /* Check for availability of necessary resource */ - dmatx_res = platform_get_resource(pdev, IORESOURCE_DMA, 0); - if (!dmatx_res) { - dev_err(&pdev->dev, "Unable to get PCM-TX dma resource\n"); - return -ENXIO; - } - - dmarx_res = platform_get_resource(pdev, IORESOURCE_DMA, 1); - if (!dmarx_res) { - dev_err(&pdev->dev, "Unable to get PCM-RX dma resource\n"); - return -ENXIO; - } - mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!mem_res) { dev_err(&pdev->dev, "Unable to get register resource\n"); @@ -568,8 +556,10 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev) s3c_pcm_stereo_out[pdev->id].dma_addr = mem_res->start + S3C_PCM_TXFIFO; - s3c_pcm_stereo_in[pdev->id].channel = dmarx_res->start; - s3c_pcm_stereo_out[pdev->id].channel = dmatx_res->start; + if (pcm_pdata) { + s3c_pcm_stereo_in[pdev->id].slave = pcm_pdata->dma_capture; + s3c_pcm_stereo_out[pdev->id].slave = pcm_pdata->dma_playback; + } pcm->dma_capture = &s3c_pcm_stereo_in[pdev->id]; pcm->dma_playback = &s3c_pcm_stereo_out[pdev->id]; diff --git a/sound/soc/samsung/s3c-i2s-v2.c b/sound/soc/samsung/s3c-i2s-v2.c index df65c5b494b1..b6ab3fc5789e 100644 --- a/sound/soc/samsung/s3c-i2s-v2.c +++ b/sound/soc/samsung/s3c-i2s-v2.c @@ -709,7 +709,7 @@ static int s3c2412_i2s_resume(struct snd_soc_dai *dai) #endif int s3c_i2sv2_register_component(struct device *dev, int id, - struct snd_soc_component_driver *cmp_drv, + const struct snd_soc_component_driver *cmp_drv, struct snd_soc_dai_driver *dai_drv) { struct snd_soc_dai_ops *ops = (struct snd_soc_dai_ops *)dai_drv->ops; diff --git a/sound/soc/samsung/s3c-i2s-v2.h b/sound/soc/samsung/s3c-i2s-v2.h index 90abab364b49..d0684145ed1f 100644 --- a/sound/soc/samsung/s3c-i2s-v2.h +++ b/sound/soc/samsung/s3c-i2s-v2.h @@ -101,7 +101,7 @@ extern int s3c_i2sv2_probe(struct snd_soc_dai *dai, * soc core. */ extern int s3c_i2sv2_register_component(struct device *dev, int id, - struct snd_soc_component_driver *cmp_drv, + const struct snd_soc_component_driver *cmp_drv, struct snd_soc_dai_driver *dai_drv); #endif /* __SND_SOC_S3C24XX_S3C_I2SV2_I2S_H */ diff --git a/sound/soc/samsung/s3c2412-i2s.c b/sound/soc/samsung/s3c2412-i2s.c index 2b766d212ce0..77d27c85a32a 100644 --- a/sound/soc/samsung/s3c2412-i2s.c +++ b/sound/soc/samsung/s3c2412-i2s.c @@ -34,13 +34,13 @@ #include "s3c2412-i2s.h" static struct s3c_dma_params s3c2412_i2s_pcm_stereo_out = { - .channel = DMACH_I2S_OUT, + .slave = (void *)(uintptr_t)DMACH_I2S_OUT, .ch_name = "tx", .dma_size = 4, }; static struct s3c_dma_params s3c2412_i2s_pcm_stereo_in = { - .channel = DMACH_I2S_IN, + .slave = (void *)(uintptr_t)DMACH_I2S_IN, .ch_name = "rx", .dma_size = 4, }; diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c index 5bf723689692..9da3a77ea2c7 100644 --- a/sound/soc/samsung/s3c24xx-i2s.c +++ b/sound/soc/samsung/s3c24xx-i2s.c @@ -32,13 +32,13 @@ #include "s3c24xx-i2s.h" static struct s3c_dma_params s3c24xx_i2s_pcm_stereo_out = { - .channel = DMACH_I2S_OUT, + .slave = (void *)(uintptr_t)DMACH_I2S_OUT, .ch_name = "tx", .dma_size = 2, }; static struct s3c_dma_params s3c24xx_i2s_pcm_stereo_in = { - .channel = DMACH_I2S_IN, + .slave = (void *)(uintptr_t)DMACH_I2S_IN, .ch_name = "rx", .dma_size = 2, }; diff --git a/sound/soc/samsung/spdif.c b/sound/soc/samsung/spdif.c index 36dbc0e96004..9dd7ee6d03ff 100644 --- a/sound/soc/samsung/spdif.c +++ b/sound/soc/samsung/spdif.c @@ -359,7 +359,7 @@ static const struct snd_soc_component_driver samsung_spdif_component = { static int spdif_probe(struct platform_device *pdev) { struct s3c_audio_pdata *spdif_pdata; - struct resource *mem_res, *dma_res; + struct resource *mem_res; struct samsung_spdif_info *spdif; int ret; @@ -367,12 +367,6 @@ static int spdif_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "Entered %s\n", __func__); - dma_res = platform_get_resource(pdev, IORESOURCE_DMA, 0); - if (!dma_res) { - dev_err(&pdev->dev, "Unable to get dma resource.\n"); - return -ENXIO; - } - mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!mem_res) { dev_err(&pdev->dev, "Unable to get register resource.\n"); @@ -432,7 +426,7 @@ static int spdif_probe(struct platform_device *pdev) spdif_stereo_out.dma_size = 2; spdif_stereo_out.dma_addr = mem_res->start + DATA_OUTBUF; - spdif_stereo_out.channel = dma_res->start; + spdif_stereo_out.slave = spdif_pdata ? spdif_pdata->dma_playback : NULL; spdif->dma_playback = &spdif_stereo_out; diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 12a9820feac1..bb82bb966000 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -630,6 +630,7 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) struct snd_pcm *be_pcm; char new_name[64]; int ret = 0, direction = 0; + int playback = 0, capture = 0; if (rtd->num_codecs > 1) { dev_err(rtd->card->dev, "Multicodec not supported for compressed stream\n"); @@ -641,11 +642,27 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->dai_link->stream_name, codec_dai->name, num); if (codec_dai->driver->playback.channels_min) + playback = 1; + if (codec_dai->driver->capture.channels_min) + capture = 1; + + capture = capture && cpu_dai->driver->capture.channels_min; + playback = playback && cpu_dai->driver->playback.channels_min; + + /* + * Compress devices are unidirectional so only one of the directions + * should be set, check for that (xor) + */ + if (playback + capture != 1) { + dev_err(rtd->card->dev, "Invalid direction for compress P %d, C %d\n", + playback, capture); + return -EINVAL; + } + + if(playback) direction = SND_COMPRESS_PLAYBACK; - else if (codec_dai->driver->capture.channels_min) - direction = SND_COMPRESS_CAPTURE; else - return -EINVAL; + direction = SND_COMPRESS_CAPTURE; compr = kzalloc(sizeof(*compr), GFP_KERNEL); if (compr == NULL) { diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 7d009428934a..afb70a5d4fd3 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2188,6 +2188,13 @@ static ssize_t dapm_widget_show_component(struct snd_soc_component *cmpnt, int count = 0; char *state = "not set"; + /* card won't be set for the dummy component, as a spot fix + * we're checking for that case specifically here but in future + * we will ensure that the dummy component looks like others. + */ + if (!cmpnt->card) + return 0; + list_for_each_entry(w, &cmpnt->card->widgets, list) { if (w->dapm != dapm) continue; @@ -3568,7 +3575,7 @@ static int snd_soc_dapm_dai_link_get(struct snd_kcontrol *kcontrol, { struct snd_soc_dapm_widget *w = snd_kcontrol_chip(kcontrol); - ucontrol->value.integer.value[0] = w->params_select; + ucontrol->value.enumerated.item[0] = w->params_select; return 0; } @@ -3582,13 +3589,13 @@ static int snd_soc_dapm_dai_link_put(struct snd_kcontrol *kcontrol, if (w->power) return -EBUSY; - if (ucontrol->value.integer.value[0] == w->params_select) + if (ucontrol->value.enumerated.item[0] == w->params_select) return 0; - if (ucontrol->value.integer.value[0] >= w->num_params) + if (ucontrol->value.enumerated.item[0] >= w->num_params) return -EINVAL; - w->params_select = ucontrol->value.integer.value[0]; + w->params_select = ucontrol->value.enumerated.item[0]; return 0; } diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index c86dc96e8986..65b936e251ea 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1743,7 +1743,8 @@ int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream) (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_FREE) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED) && - (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP)) + (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) && + (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND)) continue; dev_dbg(be->dev, "ASoC: hw_free BE %s\n", diff --git a/sound/sparc/Kconfig b/sound/sparc/Kconfig index d75deba5617d..dfcd38647606 100644 --- a/sound/sparc/Kconfig +++ b/sound/sparc/Kconfig @@ -22,6 +22,7 @@ config SND_SUN_AMD7930 config SND_SUN_CS4231 tristate "Sun CS4231" select SND_PCM + select SND_TIMER help Say Y here to include support for CS4231 sound device on Sun. diff --git a/sound/usb/card.c b/sound/usb/card.c index 18f56646ce86..1f09d9591276 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -675,6 +675,8 @@ int snd_usb_autoresume(struct snd_usb_audio *chip) void snd_usb_autosuspend(struct snd_usb_audio *chip) { + if (atomic_read(&chip->shutdown)) + return; if (atomic_dec_and_test(&chip->active)) usb_autopm_put_interface(chip->pm_intf); } diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 2ed260b10f6d..7ccbcaf6a147 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -285,6 +285,8 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip, int iface, unsigned char data[3]; int err, crate; + if (get_iface_desc(alts)->bNumEndpoints < 1) + return -EINVAL; ep = get_endpoint(alts, 0)->bEndpointAddress; /* if endpoint doesn't have sampling rate control, bail out */ diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 7b1cb365ffab..c07a7eda42a2 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -438,6 +438,9 @@ exit_clear: * * New endpoints will be added to chip->ep_list and must be freed by * calling snd_usb_endpoint_free(). + * + * For SND_USB_ENDPOINT_TYPE_SYNC, the caller needs to guarantee that + * bNumEndpoints > 1 beforehand. */ struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip, struct usb_host_interface *alts, diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 5b4c58c3e2c5..b21b76690b31 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -2454,7 +2454,6 @@ int snd_usbmidi_create(struct snd_card *card, else err = snd_usbmidi_create_endpoints(umidi, endpoints); if (err < 0) { - snd_usbmidi_free(umidi); return err; } diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index ddca6547399b..1f8fb0d904e0 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -349,6 +349,16 @@ static struct usbmix_name_map bose_companion5_map[] = { }; /* + * Dell usb dock with ALC4020 codec had a firmware problem where it got + * screwed up when zero volume is passed; just skip it as a workaround + */ +static const struct usbmix_name_map dell_alc4020_map[] = { + { 16, NULL }, + { 19, NULL }, + { 0 } +}; + +/* * Control map entries */ @@ -431,6 +441,10 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = { .map = aureon_51_2_map, }, { + .id = USB_ID(0x0bda, 0x4014), + .map = dell_alc4020_map, + }, + { .id = USB_ID(0x0dba, 0x1000), .map = mbox1_map, }, diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 0ce888dceed0..f6c3bf79af9a 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -793,7 +793,7 @@ static int snd_nativeinstruments_control_put(struct snd_kcontrol *kcontrol, return 0; kcontrol->private_value &= ~(0xff << 24); - kcontrol->private_value |= newval; + kcontrol->private_value |= (unsigned int)newval << 24; err = snd_ni_update_cur_val(list); return err < 0 ? err : 1; } @@ -1519,7 +1519,11 @@ static int snd_microii_spdif_default_get(struct snd_kcontrol *kcontrol, /* use known values for that card: interface#1 altsetting#1 */ iface = usb_ifnum_to_if(chip->dev, 1); + if (!iface || iface->num_altsetting < 2) + return -EINVAL; alts = &iface->altsetting[1]; + if (get_iface_desc(alts)->bNumEndpoints < 1) + return -EINVAL; ep = get_endpoint(alts, 0)->bEndpointAddress; err = snd_usb_ctl_msg(chip->dev, diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 9245f52d43bd..44d178ee9177 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -159,6 +159,8 @@ static int init_pitch_v1(struct snd_usb_audio *chip, int iface, unsigned char data[1]; int err; + if (get_iface_desc(alts)->bNumEndpoints < 1) + return -EINVAL; ep = get_endpoint(alts, 0)->bEndpointAddress; data[0] = 1; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index b6c0c8e3b450..001fb4dc0722 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -150,6 +150,7 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip, usb_audio_err(chip, "cannot memdup\n"); return -ENOMEM; } + INIT_LIST_HEAD(&fp->list); if (fp->nr_rates > MAX_NR_RATES) { kfree(fp); return -EINVAL; @@ -167,19 +168,20 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip, stream = (fp->endpoint & USB_DIR_IN) ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK; err = snd_usb_add_audio_stream(chip, stream, fp); - if (err < 0) { - kfree(fp); - kfree(rate_table); - return err; - } + if (err < 0) + goto error; if (fp->iface != get_iface_desc(&iface->altsetting[0])->bInterfaceNumber || fp->altset_idx >= iface->num_altsetting) { - kfree(fp); - kfree(rate_table); - return -EINVAL; + err = -EINVAL; + goto error; } alts = &iface->altsetting[fp->altset_idx]; altsd = get_iface_desc(alts); + if (altsd->bNumEndpoints < 1) { + err = -EINVAL; + goto error; + } + fp->protocol = altsd->bInterfaceProtocol; if (fp->datainterval == 0) @@ -190,6 +192,12 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip, snd_usb_init_pitch(chip, fp->iface, alts, fp); snd_usb_init_sample_rate(chip, fp->iface, alts, fp, fp->rate_max); return 0; + + error: + list_del(&fp->list); /* unlink for avoiding double-free */ + kfree(fp); + kfree(rate_table); + return err; } static int create_auto_pcm_quirk(struct snd_usb_audio *chip, @@ -462,6 +470,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip, fp->ep_attr = get_endpoint(alts, 0)->bmAttributes; fp->datainterval = 0; fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize); + INIT_LIST_HEAD(&fp->list); switch (fp->maxpacksize) { case 0x120: @@ -485,6 +494,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip, ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK; err = snd_usb_add_audio_stream(chip, stream, fp); if (err < 0) { + list_del(&fp->list); /* unlink for avoiding double-free */ kfree(fp); return err; } @@ -1121,10 +1131,15 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) switch (chip->usb_id) { case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */ case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ + case USB_ID(0x045E, 0x076E): /* MS Lifecam HD-5001 */ + case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ + case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */ + case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ + case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */ case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */ return true; } @@ -1205,8 +1220,12 @@ void snd_usb_set_interface_quirk(struct usb_device *dev) * "Playback Design" products need a 50ms delay after setting the * USB interface. */ - if (le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) + switch (le16_to_cpu(dev->descriptor.idVendor)) { + case 0x23ba: /* Playback Design */ + case 0x0644: /* TEAC Corp. */ mdelay(50); + break; + } } void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, @@ -1221,6 +1240,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) mdelay(20); + /* + * "TEAC Corp." products need a 20ms delay after each + * class compliant request + */ + if ((le16_to_cpu(dev->descriptor.idVendor) == 0x0644) && + (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) + mdelay(20); + /* Marantz/Denon devices with USB DAC functionality need a delay * after each class compliant request */ @@ -1269,6 +1296,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x20b1, 0x3008): /* iFi Audio micro/nano iDSD */ case USB_ID(0x20b1, 0x2008): /* Matrix Audio X-Sabre */ case USB_ID(0x20b1, 0x300a): /* Matrix Audio Mini-i Pro */ + case USB_ID(0x22d9, 0x0416): /* OPPO HA-1 */ if (fp->altsetting == 2) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; @@ -1277,6 +1305,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x20b1, 0x2009): /* DIYINHK DSD DXD 384kHz USB to I2S/DSD */ case USB_ID(0x20b1, 0x2023): /* JLsounds I2SoverUSB */ case USB_ID(0x20b1, 0x3023): /* Aune X1S 32BIT/384 DSD DAC */ + case USB_ID(0x2616, 0x0106): /* PS Audio NuWave DAC */ if (fp->altsetting == 3) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; diff --git a/sound/usb/stream.c b/sound/usb/stream.c index 8ee14f2365e7..3b23102230c0 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -316,7 +316,9 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits, /* * add this endpoint to the chip instance. * if a stream with the same endpoint already exists, append to it. - * if not, create a new pcm stream. + * if not, create a new pcm stream. note, fp is added to the substream + * fmt_list and will be freed on the chip instance release. do not free + * fp or do remove it from the substream fmt_list to avoid double-free. */ int snd_usb_add_audio_stream(struct snd_usb_audio *chip, int stream, @@ -677,6 +679,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no) * (fp->maxpacksize & 0x7ff); fp->attributes = parse_uac_endpoint_attributes(chip, alts, protocol, iface_no); fp->clock = clock; + INIT_LIST_HEAD(&fp->list); /* some quirks for attributes here */ @@ -725,6 +728,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no) dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint); err = snd_usb_add_audio_stream(chip, stream, fp); if (err < 0) { + list_del(&fp->list); /* unlink for avoiding double-free */ kfree(fp->rate_table); kfree(fp->chmap); kfree(fp); diff --git a/tools/hv/Makefile b/tools/hv/Makefile index a8ab79556926..a8c4644022a6 100644 --- a/tools/hv/Makefile +++ b/tools/hv/Makefile @@ -5,6 +5,8 @@ PTHREAD_LIBS = -lpthread WARNINGS = -Wall -Wextra CFLAGS = $(WARNINGS) -g $(PTHREAD_LIBS) $(shell getconf LFS_CFLAGS) +CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include + all: hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon %: %.c $(CC) $(CFLAGS) -o $@ $^ diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c index 96234b638249..5d51d6ff08e6 100644 --- a/tools/hv/hv_vss_daemon.c +++ b/tools/hv/hv_vss_daemon.c @@ -254,7 +254,7 @@ int main(int argc, char *argv[]) syslog(LOG_ERR, "Illegal op:%d\n", op); } vss_msg->error = error; - len = write(vss_fd, &error, sizeof(struct hv_vss_msg)); + len = write(vss_fd, vss_msg, sizeof(struct hv_vss_msg)); if (len != sizeof(struct hv_vss_msg)) { syslog(LOG_ERR, "write failed; error: %d %s", errno, strerror(errno)); diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 2a912df6771b..68276f35e323 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4968,13 +4968,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event sizeof(long) != 8) { char *p; - ls = 2; /* make %l into %ll */ - p = strchr(format, 'l'); - if (p) + if (ls == 1 && (p = strchr(format, 'l'))) memmove(p+1, p, strlen(p)+1); else if (strcmp(format, "%p") == 0) strcpy(format, "0x%llx"); + ls = 2; } switch (ls) { case -2: diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 4e074a660826..90c3558c2c12 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -62,6 +62,14 @@ OPTIONS --scale:: scale/normalize counter values +-d:: +--detailed:: + print more detailed statistics, can be specified up to 3 times + + -d: detailed events, L1 and LLC data cache + -d -d: more detailed events, dTLB and iTLB events + -d -d -d: very detailed events, adding prefetch events + -r:: --repeat=<n>:: repeat command and print average + stddev (max: 100). 0 means forever. diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 81def6c3f24b..3900386a3629 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2059,10 +2059,12 @@ skip_annotation: * * See hist_browser__show_entry. */ - nr_options += add_script_opt(browser, - &actions[nr_options], - &options[nr_options], - NULL, browser->selection->sym); + if (sort__has_sym && browser->selection->sym) { + nr_options += add_script_opt(browser, + &actions[nr_options], + &options[nr_options], + NULL, browser->selection->sym); + } } nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], NULL, NULL); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 8b10621b415c..956187bf1a85 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -274,7 +274,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n", + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n", &event->mmap2.start, &event->mmap2.len, prot, &event->mmap2.pgoff, &event->mmap2.maj, &event->mmap2.min, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d1392194a9a9..b4b96120fc3b 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1211,12 +1211,12 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, */ if (cpus != evlist->cpus) { cpu_map__put(evlist->cpus); - evlist->cpus = cpus; + evlist->cpus = cpu_map__get(cpus); } if (threads != evlist->threads) { thread_map__put(evlist->threads); - evlist->threads = threads; + evlist->threads = thread_map__get(threads); } perf_evlist__propagate_maps(evlist); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 97f963a3dcb9..9227c2f076c3 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1127,7 +1127,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n", ret); - if (pt->synth_opts.callchain) + if (pt->synth_opts.last_branch) intel_pt_reset_last_branch_rb(ptq); return ret; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 6fc8cd753e1a..a35db828bd0d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -399,6 +399,9 @@ static void tracepoint_error(struct parse_events_error *e, int err, { char help[BUFSIZ]; + if (!e) + return; + /* * We get error directly from syscall errno ( > 0), * or from encoded pointer's error ( < 0). @@ -2098,11 +2101,11 @@ char *parse_events_formats_error_string(char *additional_terms) /* valid terms */ if (additional_terms) { - if (!asprintf(&str, "valid terms: %s,%s", - additional_terms, static_terms)) + if (asprintf(&str, "valid terms: %s,%s", + additional_terms, static_terms) < 0) goto fail; } else { - if (!asprintf(&str, "valid terms: %s", static_terms)) + if (asprintf(&str, "valid terms: %s", static_terms) < 0) goto fail; } return str; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index e4b173dec4b9..6f2a0279476c 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -283,13 +283,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) { struct dirent *evt_ent; DIR *event_dir; - int ret = 0; event_dir = opendir(dir); if (!event_dir) return -EINVAL; - while (!ret && (evt_ent = readdir(event_dir))) { + while ((evt_ent = readdir(event_dir))) { char path[PATH_MAX]; char *name = evt_ent->d_name; FILE *file; @@ -305,17 +304,19 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) snprintf(path, PATH_MAX, "%s/%s", dir, name); - ret = -EINVAL; file = fopen(path, "r"); - if (!file) - break; + if (!file) { + pr_debug("Cannot open %s\n", path); + continue; + } - ret = perf_pmu__new_alias(head, dir, name, file); + if (perf_pmu__new_alias(head, dir, name, file) < 0) + pr_debug("Cannot set up %s\n", name); fclose(file); } closedir(event_dir); - return ret; + return 0; } /* diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c35ffdd360fe..468de95bc8bb 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -972,7 +972,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines, machine = machines__find(machines, pid); if (!machine) - machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID); + machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 1833103768cb..c8680984d2d6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -22,6 +22,7 @@ cflags = getenv('CFLAGS', '').split() # switch off several checks (need to be at the end of cflags list) cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ] +src_perf = getenv('srctree') + '/tools/perf' build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') libtraceevent = getenv('LIBTRACEEVENT') @@ -30,6 +31,9 @@ libapikfs = getenv('LIBAPI') ext_sources = [f.strip() for f in file('util/python-ext-sources') if len(f.strip()) > 0 and f[0] != '#'] +# use full paths with source files +ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources) + perf = Extension('perf', sources = ext_sources, include_dirs = ['util/include'], diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 2d9d8306dbd3..4a3a72cb5805 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -310,7 +310,6 @@ int perf_stat_process_counter(struct perf_stat_config *config, int i, ret; aggr->val = aggr->ena = aggr->run = 0; - init_stats(ps->res_stats); if (counter->per_pkg) zero_per_pkg(counter); diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh index 77edcdcc016b..057278448515 100755 --- a/tools/testing/selftests/efivarfs/efivarfs.sh +++ b/tools/testing/selftests/efivarfs/efivarfs.sh @@ -88,7 +88,11 @@ test_delete() exit 1 fi - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi if [ -e $file ]; then echo "$file couldn't be deleted" >&2 @@ -111,6 +115,7 @@ test_zero_size_delete() exit 1 fi + chattr -i $file printf "$attrs" > $file if [ -e $file ]; then @@ -141,7 +146,11 @@ test_valid_filenames() echo "$file could not be created" >&2 ret=1 else - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi fi done @@ -174,7 +183,11 @@ test_invalid_filenames() if [ -e $file ]; then echo "Creating $file should have failed" >&2 - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi ret=1 fi done diff --git a/tools/testing/selftests/efivarfs/open-unlink.c b/tools/testing/selftests/efivarfs/open-unlink.c index 8c0764407b3c..4af74f733036 100644 --- a/tools/testing/selftests/efivarfs/open-unlink.c +++ b/tools/testing/selftests/efivarfs/open-unlink.c @@ -1,10 +1,68 @@ +#include <errno.h> #include <stdio.h> #include <stdint.h> #include <stdlib.h> #include <unistd.h> +#include <sys/ioctl.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> +#include <linux/fs.h> + +static int set_immutable(const char *path, int immutable) +{ + unsigned int flags; + int fd; + int rc; + int error; + + fd = open(path, O_RDONLY); + if (fd < 0) + return fd; + + rc = ioctl(fd, FS_IOC_GETFLAGS, &flags); + if (rc < 0) { + error = errno; + close(fd); + errno = error; + return rc; + } + + if (immutable) + flags |= FS_IMMUTABLE_FL; + else + flags &= ~FS_IMMUTABLE_FL; + + rc = ioctl(fd, FS_IOC_SETFLAGS, &flags); + error = errno; + close(fd); + errno = error; + return rc; +} + +static int get_immutable(const char *path) +{ + unsigned int flags; + int fd; + int rc; + int error; + + fd = open(path, O_RDONLY); + if (fd < 0) + return fd; + + rc = ioctl(fd, FS_IOC_GETFLAGS, &flags); + if (rc < 0) { + error = errno; + close(fd); + errno = error; + return rc; + } + close(fd); + if (flags & FS_IMMUTABLE_FL) + return 1; + return 0; +} int main(int argc, char **argv) { @@ -27,7 +85,7 @@ int main(int argc, char **argv) buf[4] = 0; /* create a test variable */ - fd = open(path, O_WRONLY | O_CREAT); + fd = open(path, O_WRONLY | O_CREAT, 0600); if (fd < 0) { perror("open(O_WRONLY)"); return EXIT_FAILURE; @@ -41,6 +99,18 @@ int main(int argc, char **argv) close(fd); + rc = get_immutable(path); + if (rc < 0) { + perror("ioctl(FS_IOC_GETFLAGS)"); + return EXIT_FAILURE; + } else if (rc) { + rc = set_immutable(path, 0); + if (rc < 0) { + perror("ioctl(FS_IOC_SETFLAGS)"); + return EXIT_FAILURE; + } + } + fd = open(path, O_RDONLY); if (fd < 0) { perror("open"); diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 69bca185c471..a7b9022b5c8f 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -86,6 +86,8 @@ static void kvm_timer_inject_irq_work(struct work_struct *work) vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired); vcpu->arch.timer_cpu.armed = false; + WARN_ON(!kvm_timer_should_fire(vcpu)); + /* * If the vcpu is blocked we want to wake it up so that it will see * the timer has expired when entering the guest. @@ -93,10 +95,46 @@ static void kvm_timer_inject_irq_work(struct work_struct *work) kvm_vcpu_kick(vcpu); } +static u64 kvm_timer_compute_delta(struct kvm_vcpu *vcpu) +{ + cycle_t cval, now; + + cval = vcpu->arch.timer_cpu.cntv_cval; + now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; + + if (now < cval) { + u64 ns; + + ns = cyclecounter_cyc2ns(timecounter->cc, + cval - now, + timecounter->mask, + &timecounter->frac); + return ns; + } + + return 0; +} + static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt) { struct arch_timer_cpu *timer; + struct kvm_vcpu *vcpu; + u64 ns; + timer = container_of(hrt, struct arch_timer_cpu, timer); + vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu); + + /* + * Check that the timer has really expired from the guest's + * PoV (NTP on the host may have forced it to expire + * early). If we should have slept longer, restart it. + */ + ns = kvm_timer_compute_delta(vcpu); + if (unlikely(ns)) { + hrtimer_forward_now(hrt, ns_to_ktime(ns)); + return HRTIMER_RESTART; + } + queue_work(wqueue, &timer->expired); return HRTIMER_NORESTART; } @@ -143,7 +181,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level) * Check if there was a change in the timer state (should we raise or lower * the line level to the GIC). */ -static void kvm_timer_update_state(struct kvm_vcpu *vcpu) +static int kvm_timer_update_state(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -154,10 +192,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) * until we call this function from kvm_timer_flush_hwstate. */ if (!vgic_initialized(vcpu->kvm)) - return; + return -ENODEV; if (kvm_timer_should_fire(vcpu) != timer->irq.level) kvm_timer_update_irq(vcpu, !timer->irq.level); + + return 0; } /* @@ -168,8 +208,6 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) void kvm_timer_schedule(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - u64 ns; - cycle_t cval, now; BUG_ON(timer_is_armed(timer)); @@ -189,14 +227,7 @@ void kvm_timer_schedule(struct kvm_vcpu *vcpu) return; /* The timer has not yet expired, schedule a background timer */ - cval = timer->cntv_cval; - now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; - - ns = cyclecounter_cyc2ns(timecounter->cc, - cval - now, - timecounter->mask, - &timecounter->frac); - timer_arm(timer, ns); + timer_arm(timer, kvm_timer_compute_delta(vcpu)); } void kvm_timer_unschedule(struct kvm_vcpu *vcpu) @@ -218,7 +249,8 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) bool phys_active; int ret; - kvm_timer_update_state(vcpu); + if (kvm_timer_update_state(vcpu)) + return; /* * If we enter the guest with the virtual input level to the VGIC diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 7a2f449bd85d..5d10f104f3eb 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1875,8 +1875,8 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8; + int nr_longs = BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS); + int sz = nr_longs * sizeof(unsigned long); vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL); diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 77d42be6970e..4f70d12e392d 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -173,7 +173,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, * do alloc nowait since if we are going to sleep anyway we * may as well sleep faulting in page */ - work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT); + work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN); if (!work) return 0; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 484079efea5b..fefbf2d148ef 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -547,6 +547,16 @@ static struct kvm *kvm_create_vm(unsigned long type) if (!kvm) return ERR_PTR(-ENOMEM); + spin_lock_init(&kvm->mmu_lock); + atomic_inc(¤t->mm->mm_count); + kvm->mm = current->mm; + kvm_eventfd_init(kvm); + mutex_init(&kvm->lock); + mutex_init(&kvm->irq_lock); + mutex_init(&kvm->slots_lock); + atomic_set(&kvm->users_count, 1); + INIT_LIST_HEAD(&kvm->devices); + r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_disable; @@ -579,16 +589,6 @@ static struct kvm *kvm_create_vm(unsigned long type) goto out_err; } - spin_lock_init(&kvm->mmu_lock); - kvm->mm = current->mm; - atomic_inc(&kvm->mm->mm_count); - kvm_eventfd_init(kvm); - mutex_init(&kvm->lock); - mutex_init(&kvm->irq_lock); - mutex_init(&kvm->slots_lock); - atomic_set(&kvm->users_count, 1); - INIT_LIST_HEAD(&kvm->devices); - r = kvm_init_mmu_notifier(kvm); if (r) goto out_err; @@ -613,6 +613,7 @@ out_err_no_disable: for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) kvm_free_memslots(kvm, kvm->memslots[i]); kvm_arch_free_vm(kvm); + mmdrop(current->mm); return ERR_PTR(r); } @@ -1961,6 +1962,9 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) else val *= halt_poll_ns_grow; + if (val > halt_poll_ns) + val = halt_poll_ns; + vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); } |