diff options
Diffstat (limited to 'arch/arm')
167 files changed, 3081 insertions, 736 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c24b364bb8c..1e9cca81eea 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -19,7 +19,6 @@ config ARM select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HARDIRQS_SW_RESEND - select HAVE_AOUT select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER @@ -213,7 +212,8 @@ config VECTORS_BASE default DRAM_BASE if REMAP_VECTORS_TO_RAM default 0x00000000 help - The base address of exception vectors. + The base address of exception vectors. This must be two pages + in size. config ARM_PATCH_PHYS_VIRT bool "Patch physical to virtual translations at runtime" if EMBEDDED @@ -474,6 +474,7 @@ config ARCH_IXP4XX bool "IXP4xx-based" depends on MMU select ARCH_HAS_DMA_SET_COHERENT_MASK + select ARCH_SUPPORTS_BIG_ENDIAN select ARCH_REQUIRE_GPIOLIB select CLKSRC_MMIO select CPU_XSCALE @@ -1494,6 +1495,109 @@ config SCHED_SMT MultiThreading at a cost of slightly increased overhead in some places. If unsure say N here. +config DISABLE_CPU_SCHED_DOMAIN_BALANCE + bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing" + help + Disables scheduler load-balancing at CPU sched domain level. + +config SCHED_HMP + bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling" + depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP + help + Experimental scheduler optimizations for heterogeneous platforms. + Attempts to introspectively select task affinity to optimize power + and performance. Basic support for multiple (>2) cpu types is in place, + but it has only been tested with two types of cpus. + There is currently no support for migration of task groups, hence + !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled + between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE). + When turned on, this option adds sys/kernel/hmp directory which + contains the following files: + up_threshold - the load average threshold used for up migration + (0 - 1023) + down_threshold - the load average threshold used for down migration + (0 - 1023) + hmp_domains - a list of cpumasks for the present HMP domains, + starting with the 'biggest' and ending with the + 'smallest'. + Note that both the threshold files can be written at runtime to + control scheduler behaviour. + +config SCHED_HMP_PRIO_FILTER + bool "(EXPERIMENTAL) Filter HMP migrations by task priority" + depends on SCHED_HMP + help + Enables task priority based HMP migration filter. Any task with + a NICE value above the threshold will always be on low-power cpus + with less compute capacity. + +config SCHED_HMP_PRIO_FILTER_VAL + int "NICE priority threshold" + default 5 + depends on SCHED_HMP_PRIO_FILTER + +config HMP_FAST_CPU_MASK + string "HMP scheduler fast CPU mask" + depends on SCHED_HMP + help + Leave empty to use device tree information. + Specify the cpuids of the fast CPUs in the system as a list string, + e.g. cpuid 0+1 should be specified as 0-1. + +config HMP_SLOW_CPU_MASK + string "HMP scheduler slow CPU mask" + depends on SCHED_HMP + help + Leave empty to use device tree information. + Specify the cpuids of the slow CPUs in the system as a list string, + e.g. cpuid 0+1 should be specified as 0-1. + +config HMP_VARIABLE_SCALE + bool "Allows changing the load tracking scale through sysfs" + depends on SCHED_HMP + help + When turned on, this option exports the load average period value + for the load tracking patches through sysfs. + The values can be modified to change the rate of load accumulation + used for HMP migration. 'load_avg_period_ms' is the time in ms to + reach a load average of 0.5 for an idle task of 0 load average + ratio which becomes 100% busy. + For example, with load_avg_period_ms = 128 and up_threshold = 512, + a running task with a load of 0 will be migrated to a bigger CPU after + 128ms, because after 128ms its load_avg_ratio is 0.5 and the real + up_threshold is 0.5. + This patch has the same behavior as changing the Y of the load + average computation to + (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms) + but removes intermediate overflows in computation. + +config HMP_FREQUENCY_INVARIANT_SCALE + bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP" + depends on SCHED_HMP && CPU_FREQ + help + Scales the current load contribution in line with the frequency + of the CPU that the task was executed on. + In this version, we use a simple linear scale derived from the + maximum frequency reported by CPUFreq. + Restricting tracked load to be scaled by the CPU's frequency + represents the consumption of possible compute capacity + (rather than consumption of actual instantaneous capacity as + normal) and allows the HMP migration's simple threshold + migration strategy to interact more predictably with CPUFreq's + asynchronous compute capacity changes. + +config SCHED_HMP_LITTLE_PACKING + bool "Small task packing for HMP" + depends on SCHED_HMP + default n + help + Allows the HMP Scheduler to pack small tasks into CPUs in the + smallest HMP domain. + Controlled by two sysfs files in sys/kernel/hmp. + packing_enable: 1 to enable, 0 to disable packing. Default 1. + packing_limit: runqueue load ratio where a RQ is considered + to be full. Default is NICE_0_LOAD * 9/8. + config HAVE_ARM_SCU bool help @@ -1528,6 +1632,24 @@ config BIG_LITTLE help This option enables support for the big.LITTLE architecture. +config BL_SWITCHER + bool "big.LITTLE switcher support" + depends on BIG_LITTLE && MCPM && HOTPLUG_CPU + select CPU_PM + select ARM_CPU_SUSPEND + help + The big.LITTLE "switcher" provides the core functionality to + transparently handle transition between a cluster of A15's + and a cluster of A7's in a big.LITTLE system. + +config BL_SWITCHER_DUMMY_IF + tristate "Simple big.LITTLE switcher user interface" + depends on BL_SWITCHER && DEBUG_KERNEL + help + This is a simple and dummy char dev interface to control + the big.LITTLE switcher core code. It is meant for + debugging purposes only. + choice prompt "Memory split" default VMSPLIT_3G diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 1ba358ba16b..70bc19e2274 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -16,6 +16,7 @@ LDFLAGS := LDFLAGS_vmlinux :=-p --no-undefined -X ifeq ($(CONFIG_CPU_ENDIAN_BE8),y) LDFLAGS_vmlinux += --be8 +LDFLAGS_MODULE += --be8 endif OBJCOPYFLAGS :=-O binary -R .comment -S diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c index aabc02a6848..d1153c8a765 100644 --- a/arch/arm/boot/compressed/atags_to_fdt.c +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -53,6 +53,17 @@ static const void *getprop(const void *fdt, const char *node_path, return fdt_getprop(fdt, offset, property, len); } +static uint32_t get_cell_size(const void *fdt) +{ + int len; + uint32_t cell_size = 1; + const uint32_t *size_len = getprop(fdt, "/", "#size-cells", &len); + + if (size_len) + cell_size = fdt32_to_cpu(*size_len); + return cell_size; +} + static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline) { char cmdline[COMMAND_LINE_SIZE]; @@ -95,9 +106,11 @@ static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline) int atags_to_fdt(void *atag_list, void *fdt, int total_space) { struct tag *atag = atag_list; - uint32_t mem_reg_property[2 * NR_BANKS]; + /* In the case of 64 bits memory size, need to reserve 2 cells for + * address and size for each bank */ + uint32_t mem_reg_property[2 * 2 * NR_BANKS]; int memcount = 0; - int ret; + int ret, memsize; /* make sure we've got an aligned pointer */ if ((u32)atag_list & 0x3) @@ -137,8 +150,25 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space) continue; if (!atag->u.mem.size) continue; - mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start); - mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size); + memsize = get_cell_size(fdt); + + if (memsize == 2) { + /* if memsize is 2, that means that + * each data needs 2 cells of 32 bits, + * so the data are 64 bits */ + uint64_t *mem_reg_prop64 = + (uint64_t *)mem_reg_property; + mem_reg_prop64[memcount++] = + cpu_to_fdt64(atag->u.mem.start); + mem_reg_prop64[memcount++] = + cpu_to_fdt64(atag->u.mem.size); + } else { + mem_reg_property[memcount++] = + cpu_to_fdt32(atag->u.mem.start); + mem_reg_property[memcount++] = + cpu_to_fdt32(atag->u.mem.size); + } + } else if (atag->hdr.tag == ATAG_INITRD2) { uint32_t initrd_start, initrd_size; initrd_start = atag->u.initrd.start; @@ -150,8 +180,10 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space) } } - if (memcount) - setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount); + if (memcount) { + setprop(fdt, "/memory", "reg", mem_reg_property, + 4 * memcount * memsize); + } return fdt_pack(fdt); } diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 032a8d98714..f6e34be012f 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -135,6 +135,7 @@ start: .word _edata @ zImage end address THUMB( .thumb ) 1: + ARM_BE8( setend be ) @ go BE8 if compiled for BE8 mrs r9, cpsr #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install @ get into SVC mode, reversibly @@ -679,9 +680,7 @@ __armv4_mmu_cache_on: mrc p15, 0, r0, c1, c0, 0 @ read control reg orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement orr r0, r0, #0x0030 -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r0, r0, #1 << 25 @ big-endian page tables -#endif + ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables bl __common_mmu_cache_on mov r0, #0 mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs @@ -708,9 +707,7 @@ __armv7_mmu_cache_on: orr r0, r0, #1 << 22 @ U (v6 unaligned access model) @ (needed for ARM1176) #ifdef CONFIG_MMU -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r0, r0, #1 << 25 @ big-endian page tables -#endif + ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables mrcne p15, 0, r6, c2, c0, 2 @ read ttb control reg orrne r0, r0, #1 @ MMU enabled movne r1, #0xfffffffd @ domain 0 = client diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi index 550eb772c30..4d12d2347c1 100644 --- a/arch/arm/boot/dts/armada-370-xp.dtsi +++ b/arch/arm/boot/dts/armada-370-xp.dtsi @@ -51,7 +51,7 @@ coherency-fabric@20200 { compatible = "marvell,coherency-fabric"; - reg = <0x20200 0xb0>, <0x21810 0x1c>; + reg = <0x20200 0xb0>, <0x21010 0x1c>; }; serial@12000 { diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi index f8eaa383e07..f94cdbc579c 100644 --- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi @@ -81,7 +81,7 @@ /* * MV78230 has 2 PCIe units Gen2.0: One unit can be * configured as x4 or quad x1 lanes. One unit is - * x4/x1. + * x1 only. */ pcie-controller { compatible = "marvell,armada-xp-pcie"; @@ -94,10 +94,10 @@ bus-range = <0x00 0xff>; ranges = <0x82000000 0 0x40000 0x40000 0 0x00002000 /* Port 0.0 registers */ - 0x82000000 0 0x42000 0x42000 0 0x00002000 /* Port 2.0 registers */ 0x82000000 0 0x44000 0x44000 0 0x00002000 /* Port 0.1 registers */ 0x82000000 0 0x48000 0x48000 0 0x00002000 /* Port 0.2 registers */ 0x82000000 0 0x4c000 0x4c000 0 0x00002000 /* Port 0.3 registers */ + 0x82000000 0 0x80000 0x80000 0 0x00002000 /* Port 1.0 registers */ 0x82000000 0 0xe0000000 0xe0000000 0 0x08000000 /* non-prefetchable memory */ 0x81000000 0 0 0xe8000000 0 0x00100000>; /* downstream I/O */ @@ -165,19 +165,19 @@ status = "disabled"; }; - pcie@9,0 { + pcie@5,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x42000 0 0x2000>; - reg = <0x4800 0 0 0 0>; + assigned-addresses = <0x82000800 0 0x80000 0 0x2000>; + reg = <0x2800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; #interrupt-cells = <1>; ranges; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &mpic 99>; - marvell,pcie-port = <2>; + interrupt-map = <0 0 0 0 &mpic 62>; + marvell,pcie-port = <1>; marvell,pcie-lane = <0>; - clocks = <&gateclk 26>; + clocks = <&gateclk 9>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi index f4029f015af..55cdd58c155 100644 --- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi @@ -101,7 +101,7 @@ /* * MV78260 has 3 PCIe units Gen2.0: Two units can be * configured as x4 or quad x1 lanes. One unit is - * x4/x1. + * x4 only. */ pcie-controller { compatible = "marvell,armada-xp-pcie"; @@ -119,7 +119,9 @@ 0x82000000 0 0x48000 0x48000 0 0x00002000 /* Port 0.2 registers */ 0x82000000 0 0x4c000 0x4c000 0 0x00002000 /* Port 0.3 registers */ 0x82000000 0 0x80000 0x80000 0 0x00002000 /* Port 1.0 registers */ - 0x82000000 0 0x82000 0x82000 0 0x00002000 /* Port 3.0 registers */ + 0x82000000 0 0x84000 0x84000 0 0x00002000 /* Port 1.1 registers */ + 0x82000000 0 0x88000 0x88000 0 0x00002000 /* Port 1.2 registers */ + 0x82000000 0 0x8c000 0x8c000 0 0x00002000 /* Port 1.3 registers */ 0x82000000 0 0xe0000000 0xe0000000 0 0x08000000 /* non-prefetchable memory */ 0x81000000 0 0 0xe8000000 0 0x00100000>; /* downstream I/O */ @@ -187,35 +189,83 @@ status = "disabled"; }; - pcie@9,0 { + pcie@5,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x42000 0 0x2000>; - reg = <0x4800 0 0 0 0>; + assigned-addresses = <0x82000800 0 0x80000 0 0x2000>; + reg = <0x2800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; #interrupt-cells = <1>; ranges; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &mpic 99>; - marvell,pcie-port = <2>; + interrupt-map = <0 0 0 0 &mpic 62>; + marvell,pcie-port = <1>; marvell,pcie-lane = <0>; - clocks = <&gateclk 26>; + clocks = <&gateclk 9>; + status = "disabled"; + }; + + pcie@6,0 { + device_type = "pci"; + assigned-addresses = <0x82000800 0 0x84000 0 0x2000>; + reg = <0x3000 0 0 0 0>; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + ranges; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &mpic 63>; + marvell,pcie-port = <1>; + marvell,pcie-lane = <1>; + clocks = <&gateclk 10>; + status = "disabled"; + }; + + pcie@7,0 { + device_type = "pci"; + assigned-addresses = <0x82000800 0 0x88000 0 0x2000>; + reg = <0x3800 0 0 0 0>; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + ranges; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &mpic 64>; + marvell,pcie-port = <1>; + marvell,pcie-lane = <2>; + clocks = <&gateclk 11>; status = "disabled"; }; - pcie@10,0 { + pcie@8,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x82000 0 0x2000>; - reg = <0x5000 0 0 0 0>; + assigned-addresses = <0x82000800 0 0x8c000 0 0x2000>; + reg = <0x4000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; #interrupt-cells = <1>; ranges; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &mpic 103>; - marvell,pcie-port = <3>; + interrupt-map = <0 0 0 0 &mpic 65>; + marvell,pcie-port = <1>; + marvell,pcie-lane = <3>; + clocks = <&gateclk 12>; + status = "disabled"; + }; + + pcie@9,0 { + device_type = "pci"; + assigned-addresses = <0x82000800 0 0x42000 0 0x2000>; + reg = <0x4800 0 0 0 0>; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + ranges; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &mpic 99>; + marvell,pcie-port = <2>; marvell,pcie-lane = <0>; - clocks = <&gateclk 27>; + clocks = <&gateclk 26>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi index 5d3ed5aafc6..0af879a4eaf 100644 --- a/arch/arm/boot/dts/at91rm9200.dtsi +++ b/arch/arm/boot/dts/at91rm9200.dtsi @@ -35,8 +35,12 @@ ssc2 = &ssc2; }; cpus { - cpu@0 { + #address-cells = <0>; + #size-cells = <0>; + + cpu { compatible = "arm,arm920t"; + device_type = "cpu"; }; }; diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi index 84c4bef2d72..0dbdb846f90 100644 --- a/arch/arm/boot/dts/at91sam9260.dtsi +++ b/arch/arm/boot/dts/at91sam9260.dtsi @@ -32,8 +32,12 @@ ssc0 = &ssc0; }; cpus { - cpu@0 { - compatible = "arm,arm926ejs"; + #address-cells = <0>; + #size-cells = <0>; + + cpu { + compatible = "arm,arm926ej-s"; + device_type = "cpu"; }; }; @@ -340,6 +344,14 @@ }; }; + i2c_gpio0 { + pinctrl_i2c_gpio0: i2c_gpio0-0 { + atmel,pins = + <0 23 0x0 0x3 /* PA23 gpio I2C_SDA pin */ + 0 24 0x0 0x3>; /* PA24 gpio I2C_SCL pin */ + }; + }; + pioA: gpio@fffff400 { compatible = "atmel,at91rm9200-gpio"; reg = <0xfffff400 0x200>; @@ -592,6 +604,8 @@ i2c-gpio,delay-us = <2>; /* ~100 kHz */ #address-cells = <1>; #size-cells = <0>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c_gpio0>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index 94b58ab2cc0..fcd38f89904 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -29,8 +29,12 @@ ssc1 = &ssc1; }; cpus { - cpu@0 { - compatible = "arm,arm926ejs"; + #address-cells = <0>; + #size-cells = <0>; + + cpu { + compatible = "arm,arm926ej-s"; + device_type = "cpu"; }; }; diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi index bf18a735c37..479a0622cdb 100644 --- a/arch/arm/boot/dts/at91sam9g45.dtsi +++ b/arch/arm/boot/dts/at91sam9g45.dtsi @@ -35,8 +35,12 @@ ssc1 = &ssc1; }; cpus { - cpu@0 { - compatible = "arm,arm926ejs"; + #address-cells = <0>; + #size-cells = <0>; + + cpu { + compatible = "arm,arm926ej-s"; + device_type = "cpu"; }; }; diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi index 8d25f889928..a92ec78349a 100644 --- a/arch/arm/boot/dts/at91sam9n12.dtsi +++ b/arch/arm/boot/dts/at91sam9n12.dtsi @@ -31,8 +31,12 @@ ssc0 = &ssc0; }; cpus { - cpu@0 { - compatible = "arm,arm926ejs"; + #address-cells = <0>; + #size-cells = <0>; + + cpu { + compatible = "arm,arm926ej-s"; + device_type = "cpu"; }; }; diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index d30e48bd1e9..28ba7989387 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -14,11 +14,11 @@ compatible = "atmel,at91sam9n12ek", "atmel,at91sam9n12", "atmel,at91sam9"; chosen { - bootargs = "mem=128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2"; + bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2"; }; memory { - reg = <0x20000000 0x10000000>; + reg = <0x20000000 0x8000000>; }; clocks { diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index 1145ac330fb..2b2b6923d16 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -33,8 +33,12 @@ ssc0 = &ssc0; }; cpus { - cpu@0 { - compatible = "arm,arm926ejs"; + #address-cells = <0>; + #size-cells = <0>; + + cpu { + compatible = "arm,arm926ej-s"; + device_type = "cpu"; }; }; @@ -643,7 +647,7 @@ }; rtc@fffffeb0 { - compatible = "atmel,at91rm9200-rtc"; + compatible = "atmel,at91sam9x5-rtc"; reg = <0xfffffeb0 0x40>; interrupts = <1 4 7>; status = "disabled"; diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi index 1e12aeff403..aa537ed13f0 100644 --- a/arch/arm/boot/dts/bcm2835.dtsi +++ b/arch/arm/boot/dts/bcm2835.dtsi @@ -85,6 +85,8 @@ reg = <0x7e205000 0x1000>; interrupts = <2 21>; clocks = <&clk_i2c>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -93,6 +95,8 @@ reg = <0x7e804000 0x1000>; interrupts = <2 21>; clocks = <&clk_i2c>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/cros5250-common.dtsi b/arch/arm/boot/dts/cros5250-common.dtsi index 3f0239ec1bc..49d8da2779a 100644 --- a/arch/arm/boot/dts/cros5250-common.dtsi +++ b/arch/arm/boot/dts/cros5250-common.dtsi @@ -27,6 +27,13 @@ i2c2_bus: i2c2-bus { samsung,pin-pud = <0>; }; + + max77686_irq: max77686-irq { + samsung,pins = "gpx3-2"; + samsung,pin-function = <0>; + samsung,pin-pud = <0>; + samsung,pin-drv = <0>; + }; }; i2c@12C60000 { @@ -35,6 +42,11 @@ max77686@09 { compatible = "maxim,max77686"; + interrupt-parent = <&gpx3>; + interrupts = <2 0>; + pinctrl-names = "default"; + pinctrl-0 = <&max77686_irq>; + wakeup-source; reg = <0x09>; voltage-regulators { diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi index fc9fb3d526e..cdbdc4dfef2 100644 --- a/arch/arm/boot/dts/exynos5250.dtsi +++ b/arch/arm/boot/dts/exynos5250.dtsi @@ -545,7 +545,7 @@ compatible = "arm,pl330", "arm,primecell"; reg = <0x10800000 0x1000>; interrupts = <0 33 0>; - clocks = <&clock 271>; + clocks = <&clock 346>; clock-names = "apb_pclk"; #dma-cells = <1>; #dma-channels = <8>; diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi index 73fd7d0887b..587ceef81e4 100644 --- a/arch/arm/boot/dts/imx23.dtsi +++ b/arch/arm/boot/dts/imx23.dtsi @@ -23,8 +23,12 @@ }; cpus { - cpu@0 { - compatible = "arm,arm926ejs"; + #address-cells = <0>; + #size-cells = <0>; + + cpu { + compatible = "arm,arm926ej-s"; + device_type = "cpu"; }; }; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index 600f7cb51f3..4c10a1968c0 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -32,8 +32,12 @@ }; cpus { - cpu@0 { - compatible = "arm,arm926ejs"; + #address-cells = <0>; + #size-cells = <0>; + + cpu { + compatible = "arm,arm926ej-s"; + device_type = "cpu"; }; }; diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi index 5bcdf3a90bb..62dc7812679 100644 --- a/arch/arm/boot/dts/imx6dl.dtsi +++ b/arch/arm/boot/dts/imx6dl.dtsi @@ -18,12 +18,14 @@ cpu@0 { compatible = "arm,cortex-a9"; + device_type = "cpu"; reg = <0>; next-level-cache = <&L2>; }; cpu@1 { compatible = "arm,cortex-a9"; + device_type = "cpu"; reg = <1>; next-level-cache = <&L2>; }; diff --git a/arch/arm/boot/dts/imx6q.dtsi b/arch/arm/boot/dts/imx6q.dtsi index 21e675848bd..dc54a72a3bc 100644 --- a/arch/arm/boot/dts/imx6q.dtsi +++ b/arch/arm/boot/dts/imx6q.dtsi @@ -18,6 +18,7 @@ cpu@0 { compatible = "arm,cortex-a9"; + device_type = "cpu"; reg = <0>; next-level-cache = <&L2>; operating-points = < @@ -39,18 +40,21 @@ cpu@1 { compatible = "arm,cortex-a9"; + device_type = "cpu"; reg = <1>; next-level-cache = <&L2>; }; cpu@2 { compatible = "arm,cortex-a9"; + device_type = "cpu"; reg = <2>; next-level-cache = <&L2>; }; cpu@3 { compatible = "arm,cortex-a9"; + device_type = "cpu"; reg = <3>; next-level-cache = <&L2>; }; diff --git a/arch/arm/boot/dts/integratorcp.dts b/arch/arm/boot/dts/integratorcp.dts index ff1aea0ee04..72693a69f83 100644 --- a/arch/arm/boot/dts/integratorcp.dts +++ b/arch/arm/boot/dts/integratorcp.dts @@ -9,11 +9,6 @@ model = "ARM Integrator/CP"; compatible = "arm,integrator-cp"; - aliases { - arm,timer-primary = &timer2; - arm,timer-secondary = &timer1; - }; - chosen { bootargs = "root=/dev/ram0 console=ttyAMA0,38400n8 earlyprintk"; }; @@ -24,14 +19,18 @@ }; timer0: timer@13000000 { + /* TIMER0 runs @ 25MHz */ compatible = "arm,integrator-cp-timer"; + status = "disabled"; }; timer1: timer@13000100 { + /* TIMER1 runs @ 1MHz */ compatible = "arm,integrator-cp-timer"; }; timer2: timer@13000200 { + /* TIMER2 runs @ 1MHz */ compatible = "arm,integrator-cp-timer"; }; diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi index 5000e0d4284..642775d7ca6 100644 --- a/arch/arm/boot/dts/sama5d3.dtsi +++ b/arch/arm/boot/dts/sama5d3.dtsi @@ -35,8 +35,12 @@ ssc1 = &ssc1; }; cpus { + #address-cells = <1>; + #size-cells = <0>; cpu@0 { + device_type = "cpu"; compatible = "arm,cortex-a5"; + reg = <0x0>; }; }; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index e7ef619a70a..06ef8b625db 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -16,8 +16,12 @@ interrupt-parent = <&intc>; cpus { + #address-cells = <1>; + #size-cells = <0>; cpu@0 { + device_type = "cpu"; compatible = "arm,cortex-a8"; + reg = <0x0>; }; }; diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi index 31fa38f8cc9..d2852547b57 100644 --- a/arch/arm/boot/dts/sun5i-a13.dtsi +++ b/arch/arm/boot/dts/sun5i-a13.dtsi @@ -17,8 +17,12 @@ interrupt-parent = <&intc>; cpus { + #address-cells = <1>; + #size-cells = <0>; cpu@0 { + device_type = "cpu"; compatible = "arm,cortex-a8"; + reg = <0x0>; }; }; diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile index f27d6a7af57..462cd580fc2 100644 --- a/arch/arm/common/Makefile +++ b/arch/arm/common/Makefile @@ -14,6 +14,9 @@ obj-$(CONFIG_SHARP_SCOOP) += scoop.o obj-$(CONFIG_PCI_HOST_ITE8152) += it8152.o obj-$(CONFIG_ARM_TIMER_SP804) += timer-sp.o obj-$(CONFIG_MCPM) += mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o +obj-$(CONFIG_BL_SWITCHER) += bL_switcher.o +obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o + AFLAGS_mcpm_head.o := -march=armv7-a AFLAGS_vlock.o := -march=armv7-a CFLAGS_REMOVE_mcpm_entry.o = -pg diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c new file mode 100644 index 00000000000..8fee70dfb30 --- /dev/null +++ b/arch/arm/common/bL_switcher.c @@ -0,0 +1,864 @@ +/* + * arch/arm/common/bL_switcher.c -- big.LITTLE cluster switcher core driver + * + * Created by: Nicolas Pitre, March 2012 + * Copyright: (C) 2012 Linaro Limited + * + * 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 + * published by the Free Software Foundation. + */ + +#include <linux/atomic.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/interrupt.h> +#include <linux/cpu_pm.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/kthread.h> +#include <linux/wait.h> +#include <linux/time.h> +#include <linux/clockchips.h> +#include <linux/hrtimer.h> +#include <linux/tick.h> +#include <linux/notifier.h> +#include <linux/mm.h> +#include <linux/mutex.h> +#include <linux/smp.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/sysfs.h> +#include <linux/irqchip/arm-gic.h> +#include <linux/moduleparam.h> + +#include <asm/smp_plat.h> +#include <asm/cacheflush.h> +#include <asm/cputype.h> +#include <asm/suspend.h> +#include <asm/mcpm.h> +#include <asm/bL_switcher.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/power_cpu_migrate.h> + + +/* + * Use our own MPIDR accessors as the generic ones in asm/cputype.h have + * __attribute_const__ and we don't want the compiler to assume any + * constness here as the value _does_ change along some code paths. + */ + +static int read_mpidr(void) +{ + unsigned int id; + asm volatile ("mrc\tp15, 0, %0, c0, c0, 5" : "=r" (id)); + return id & MPIDR_HWID_BITMASK; +} + +/* + * Get a global nanosecond time stamp for tracing. + */ +static s64 get_ns(void) +{ + struct timespec ts; + getnstimeofday(&ts); + return timespec_to_ns(&ts); +} + +/* + * bL switcher core code. + */ + +static void bL_do_switch(void *_arg) +{ + unsigned ib_mpidr, ib_cpu, ib_cluster; + long volatile handshake, **handshake_ptr = _arg; + + pr_debug("%s\n", __func__); + + ib_mpidr = cpu_logical_map(smp_processor_id()); + ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0); + ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1); + + /* Advertise our handshake location */ + if (handshake_ptr) { + handshake = 0; + *handshake_ptr = &handshake; + } else + handshake = -1; + + /* + * Our state has been saved at this point. Let's release our + * inbound CPU. + */ + mcpm_set_entry_vector(ib_cpu, ib_cluster, cpu_resume); + sev(); + + /* + * From this point, we must assume that our counterpart CPU might + * have taken over in its parallel world already, as if execution + * just returned from cpu_suspend(). It is therefore important to + * be very careful not to make any change the other guy is not + * expecting. This is why we need stack isolation. + * + * Fancy under cover tasks could be performed here. For now + * we have none. + */ + + /* + * Let's wait until our inbound is alive. + */ + while (!handshake) { + wfe(); + smp_mb(); + } + + /* Let's put ourself down. */ + mcpm_cpu_power_down(); + + /* should never get here */ + BUG(); +} + +/* + * Stack isolation. To ensure 'current' remains valid, we just use another + * piece of our thread's stack space which should be fairly lightly used. + * The selected area starts just above the thread_info structure located + * at the very bottom of the stack, aligned to a cache line, and indexed + * with the cluster number. + */ +#define STACK_SIZE 512 +extern void call_with_stack(void (*fn)(void *), void *arg, void *sp); +static int bL_switchpoint(unsigned long _arg) +{ + unsigned int mpidr = read_mpidr(); + unsigned int clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1); + void *stack = current_thread_info() + 1; + stack = PTR_ALIGN(stack, L1_CACHE_BYTES); + stack += clusterid * STACK_SIZE + STACK_SIZE; + call_with_stack(bL_do_switch, (void *)_arg, stack); + BUG(); +} + +/* + * Generic switcher interface + */ + +static unsigned int bL_gic_id[MAX_CPUS_PER_CLUSTER][MAX_NR_CLUSTERS]; +static int bL_switcher_cpu_pairing[NR_CPUS]; + +/* + * bL_switch_to - Switch to a specific cluster for the current CPU + * @new_cluster_id: the ID of the cluster to switch to. + * + * This function must be called on the CPU to be switched. + * Returns 0 on success, else a negative status code. + */ +static int bL_switch_to(unsigned int new_cluster_id) +{ + unsigned int mpidr, this_cpu, that_cpu; + unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster; + struct completion inbound_alive; + struct tick_device *tdev; + enum clock_event_mode tdev_mode; + long volatile *handshake_ptr; + int ipi_nr, ret; + + this_cpu = smp_processor_id(); + ob_mpidr = read_mpidr(); + ob_cpu = MPIDR_AFFINITY_LEVEL(ob_mpidr, 0); + ob_cluster = MPIDR_AFFINITY_LEVEL(ob_mpidr, 1); + BUG_ON(cpu_logical_map(this_cpu) != ob_mpidr); + + if (new_cluster_id == ob_cluster) + return 0; + + that_cpu = bL_switcher_cpu_pairing[this_cpu]; + ib_mpidr = cpu_logical_map(that_cpu); + ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0); + ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1); + + pr_debug("before switch: CPU %d MPIDR %#x -> %#x\n", + this_cpu, ob_mpidr, ib_mpidr); + + this_cpu = smp_processor_id(); + + /* Close the gate for our entry vectors */ + mcpm_set_entry_vector(ob_cpu, ob_cluster, NULL); + mcpm_set_entry_vector(ib_cpu, ib_cluster, NULL); + + /* Install our "inbound alive" notifier. */ + init_completion(&inbound_alive); + ipi_nr = register_ipi_completion(&inbound_alive, this_cpu); + ipi_nr |= ((1 << 16) << bL_gic_id[ob_cpu][ob_cluster]); + mcpm_set_early_poke(ib_cpu, ib_cluster, gic_get_sgir_physaddr(), ipi_nr); + + /* + * Let's wake up the inbound CPU now in case it requires some delay + * to come online, but leave it gated in our entry vector code. + */ + ret = mcpm_cpu_power_up(ib_cpu, ib_cluster); + if (ret) { + pr_err("%s: mcpm_cpu_power_up() returned %d\n", __func__, ret); + return ret; + } + + /* + * Raise a SGI on the inbound CPU to make sure it doesn't stall + * in a possible WFI, such as in bL_power_down(). + */ + gic_send_sgi(bL_gic_id[ib_cpu][ib_cluster], 0); + + /* + * Wait for the inbound to come up. This allows for other + * tasks to be scheduled in the mean time. + */ + wait_for_completion(&inbound_alive); + mcpm_set_early_poke(ib_cpu, ib_cluster, 0, 0); + + /* + * From this point we are entering the switch critical zone + * and can't sleep/schedule anymore. + */ + local_irq_disable(); + local_fiq_disable(); + trace_cpu_migrate_begin(get_ns(), ob_mpidr); + + /* redirect GIC's SGIs to our counterpart */ + gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]); + + tdev = tick_get_device(this_cpu); + if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu))) + tdev = NULL; + if (tdev) { + tdev_mode = tdev->evtdev->mode; + clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN); + } + + ret = cpu_pm_enter(); + + /* we can not tolerate errors at this point */ + if (ret) + panic("%s: cpu_pm_enter() returned %d\n", __func__, ret); + + /* + * Swap the physical CPUs in the logical map for this logical CPU. + * This must be flushed to RAM as the resume code + * needs to access it while the caches are still disabled. + */ + cpu_logical_map(this_cpu) = ib_mpidr; + cpu_logical_map(that_cpu) = ob_mpidr; + sync_cache_w(&cpu_logical_map(this_cpu)); + + /* Let's do the actual CPU switch. */ + ret = cpu_suspend((unsigned long)&handshake_ptr, bL_switchpoint); + if (ret > 0) + panic("%s: cpu_suspend() returned %d\n", __func__, ret); + + /* We are executing on the inbound CPU at this point */ + mpidr = read_mpidr(); + pr_debug("after switch: CPU %d MPIDR %#x\n", this_cpu, mpidr); + BUG_ON(mpidr != ib_mpidr); + + mcpm_cpu_powered_up(); + + ret = cpu_pm_exit(); + + if (tdev) { + clockevents_set_mode(tdev->evtdev, tdev_mode); + clockevents_program_event(tdev->evtdev, + tdev->evtdev->next_event, 1); + } + + trace_cpu_migrate_finish(get_ns(), ib_mpidr); + local_fiq_enable(); + local_irq_enable(); + + *handshake_ptr = 1; + dsb_sev(); + + if (ret) + pr_err("%s exiting with error %d\n", __func__, ret); + return ret; +} + +struct bL_thread { + spinlock_t lock; + struct task_struct *task; + wait_queue_head_t wq; + int wanted_cluster; + struct completion started; + bL_switch_completion_handler completer; + void *completer_cookie; +}; + +static struct bL_thread bL_threads[NR_CPUS]; + +static int bL_switcher_thread(void *arg) +{ + struct bL_thread *t = arg; + struct sched_param param = { .sched_priority = 1 }; + int cluster; + bL_switch_completion_handler completer; + void *completer_cookie; + + sched_setscheduler_nocheck(current, SCHED_FIFO, ¶m); + complete(&t->started); + + do { + if (signal_pending(current)) + flush_signals(current); + wait_event_interruptible(t->wq, + t->wanted_cluster != -1 || + kthread_should_stop()); + + spin_lock(&t->lock); + cluster = t->wanted_cluster; + completer = t->completer; + completer_cookie = t->completer_cookie; + t->wanted_cluster = -1; + t->completer = NULL; + spin_unlock(&t->lock); + + if (cluster != -1) { + bL_switch_to(cluster); + + if (completer) + completer(completer_cookie); + } + } while (!kthread_should_stop()); + + return 0; +} + +static struct task_struct * bL_switcher_thread_create(int cpu, void *arg) +{ + struct task_struct *task; + + task = kthread_create_on_node(bL_switcher_thread, arg, + cpu_to_node(cpu), "kswitcher_%d", cpu); + if (!IS_ERR(task)) { + kthread_bind(task, cpu); + wake_up_process(task); + } else + pr_err("%s failed for CPU %d\n", __func__, cpu); + return task; +} + +/* + * bL_switch_request_cb - Switch to a specific cluster for the given CPU, + * with completion notification via a callback + * + * @cpu: the CPU to switch + * @new_cluster_id: the ID of the cluster to switch to. + * @completer: switch completion callback. if non-NULL, + * @completer(@completer_cookie) will be called on completion of + * the switch, in non-atomic context. + * @completer_cookie: opaque context argument for @completer. + * + * This function causes a cluster switch on the given CPU by waking up + * the appropriate switcher thread. This function may or may not return + * before the switch has occurred. + * + * If a @completer callback function is supplied, it will be called when + * the switch is complete. This can be used to determine asynchronously + * when the switch is complete, regardless of when bL_switch_request() + * returns. When @completer is supplied, no new switch request is permitted + * for the affected CPU until after the switch is complete, and @completer + * has returned. + */ +int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id, + bL_switch_completion_handler completer, + void *completer_cookie) +{ + struct bL_thread *t; + + if (cpu >= ARRAY_SIZE(bL_threads)) { + pr_err("%s: cpu %d out of bounds\n", __func__, cpu); + return -EINVAL; + } + + t = &bL_threads[cpu]; + + if (IS_ERR(t->task)) + return PTR_ERR(t->task); + if (!t->task) + return -ESRCH; + + spin_lock(&t->lock); + if (t->completer) { + spin_unlock(&t->lock); + return -EBUSY; + } + t->completer = completer; + t->completer_cookie = completer_cookie; + t->wanted_cluster = new_cluster_id; + spin_unlock(&t->lock); + wake_up(&t->wq); + return 0; +} + +EXPORT_SYMBOL_GPL(bL_switch_request_cb); + +/* + * Detach an outstanding switch request. + * + * The switcher will continue with the switch request in the background, + * but the completer function will not be called. + * + * This may be necessary if the completer is in a kernel module which is + * about to be unloaded. + */ +void bL_switch_request_detach(unsigned int cpu, + bL_switch_completion_handler completer) +{ + struct bL_thread *t; + + if (cpu >= ARRAY_SIZE(bL_threads)) { + pr_err("%s: cpu %d out of bounds\n", __func__, cpu); + return; + } + + t = &bL_threads[cpu]; + + if (IS_ERR(t->task) || !t->task) + return; + + spin_lock(&t->lock); + if (t->completer == completer) + t->completer = NULL; + spin_unlock(&t->lock); +} + +EXPORT_SYMBOL_GPL(bL_switch_request_detach); + +/* + * Activation and configuration code. + */ + +static DEFINE_MUTEX(bL_switcher_activation_lock); +static BLOCKING_NOTIFIER_HEAD(bL_activation_notifier); +static unsigned int bL_switcher_active; +static unsigned int bL_switcher_cpu_original_cluster[NR_CPUS]; +static cpumask_t bL_switcher_removed_logical_cpus; + +int bL_switcher_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&bL_activation_notifier, nb); +} +EXPORT_SYMBOL_GPL(bL_switcher_register_notifier); + +int bL_switcher_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&bL_activation_notifier, nb); +} +EXPORT_SYMBOL_GPL(bL_switcher_unregister_notifier); + +static int bL_activation_notify(unsigned long val) +{ + int ret; + + ret = blocking_notifier_call_chain(&bL_activation_notifier, val, NULL); + if (ret & NOTIFY_STOP_MASK) + pr_err("%s: notifier chain failed with status 0x%x\n", + __func__, ret); + return notifier_to_errno(ret); +} + +static void bL_switcher_restore_cpus(void) +{ + int i; + + for_each_cpu(i, &bL_switcher_removed_logical_cpus) + cpu_up(i); +} + +static int bL_switcher_halve_cpus(void) +{ + int i, j, cluster_0, gic_id, ret; + unsigned int cpu, cluster, mask; + cpumask_t available_cpus; + + /* First pass to validate what we have */ + mask = 0; + for_each_online_cpu(i) { + cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0); + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1); + if (cluster >= 2) { + pr_err("%s: only dual cluster systems are supported\n", __func__); + return -EINVAL; + } + if (WARN_ON(cpu >= MAX_CPUS_PER_CLUSTER)) + return -EINVAL; + mask |= (1 << cluster); + } + if (mask != 3) { + pr_err("%s: no CPU pairing possible\n", __func__); + return -EINVAL; + } + + /* + * Now let's do the pairing. We match each CPU with another CPU + * from a different cluster. To get a uniform scheduling behavior + * without fiddling with CPU topology and compute capacity data, + * we'll use logical CPUs initially belonging to the same cluster. + */ + memset(bL_switcher_cpu_pairing, -1, sizeof(bL_switcher_cpu_pairing)); + cpumask_copy(&available_cpus, cpu_online_mask); + cluster_0 = -1; + for_each_cpu(i, &available_cpus) { + int match = -1; + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1); + if (cluster_0 == -1) + cluster_0 = cluster; + if (cluster != cluster_0) + continue; + cpumask_clear_cpu(i, &available_cpus); + for_each_cpu(j, &available_cpus) { + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(j), 1); + /* + * Let's remember the last match to create "odd" + * pairing on purpose in order for other code not + * to assume any relation between physical and + * logical CPU numbers. + */ + if (cluster != cluster_0) + match = j; + } + if (match != -1) { + bL_switcher_cpu_pairing[i] = match; + cpumask_clear_cpu(match, &available_cpus); + pr_info("CPU%d paired with CPU%d\n", i, match); + } + } + + /* + * Now we disable the unwanted CPUs i.e. everything that has no + * pairing information (that includes the pairing counterparts). + */ + cpumask_clear(&bL_switcher_removed_logical_cpus); + for_each_online_cpu(i) { + cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0); + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1); + + /* Let's take note of the GIC ID for this CPU */ + gic_id = gic_get_cpu_id(i); + if (gic_id < 0) { + pr_err("%s: bad GIC ID for CPU %d\n", __func__, i); + bL_switcher_restore_cpus(); + return -EINVAL; + } + bL_gic_id[cpu][cluster] = gic_id; + pr_info("GIC ID for CPU %u cluster %u is %u\n", + cpu, cluster, gic_id); + + if (bL_switcher_cpu_pairing[i] != -1) { + bL_switcher_cpu_original_cluster[i] = cluster; + continue; + } + + ret = cpu_down(i); + if (ret) { + bL_switcher_restore_cpus(); + return ret; + } + cpumask_set_cpu(i, &bL_switcher_removed_logical_cpus); + } + + return 0; +} + +/* Determine the logical CPU a given physical CPU is grouped on. */ +int bL_switcher_get_logical_index(u32 mpidr) +{ + int cpu; + + if (!bL_switcher_active) + return -EUNATCH; + + mpidr &= MPIDR_HWID_BITMASK; + for_each_online_cpu(cpu) { + int pairing = bL_switcher_cpu_pairing[cpu]; + if (pairing == -1) + continue; + if ((mpidr == cpu_logical_map(cpu)) || + (mpidr == cpu_logical_map(pairing))) + return cpu; + } + return -EINVAL; +} + +static void bL_switcher_trace_trigger_cpu(void *__always_unused info) +{ + trace_cpu_migrate_current(get_ns(), read_mpidr()); +} + +int bL_switcher_trace_trigger(void) +{ + int ret; + + preempt_disable(); + + bL_switcher_trace_trigger_cpu(NULL); + ret = smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true); + + preempt_enable(); + + return ret; +} +EXPORT_SYMBOL_GPL(bL_switcher_trace_trigger); + +static int bL_switcher_enable(void) +{ + int cpu, ret; + + mutex_lock(&bL_switcher_activation_lock); + cpu_hotplug_driver_lock(); + if (bL_switcher_active) { + cpu_hotplug_driver_unlock(); + mutex_unlock(&bL_switcher_activation_lock); + return 0; + } + + pr_info("big.LITTLE switcher initializing\n"); + + ret = bL_activation_notify(BL_NOTIFY_PRE_ENABLE); + if (ret) + goto error; + + ret = bL_switcher_halve_cpus(); + if (ret) + goto error; + + bL_switcher_trace_trigger(); + + for_each_online_cpu(cpu) { + struct bL_thread *t = &bL_threads[cpu]; + spin_lock_init(&t->lock); + init_waitqueue_head(&t->wq); + init_completion(&t->started); + t->wanted_cluster = -1; + t->task = bL_switcher_thread_create(cpu, t); + } + + bL_switcher_active = 1; + bL_activation_notify(BL_NOTIFY_POST_ENABLE); + pr_info("big.LITTLE switcher initialized\n"); + goto out; + +error: + pr_warning("big.LITTLE switcher initialization failed\n"); + bL_activation_notify(BL_NOTIFY_POST_DISABLE); + +out: + cpu_hotplug_driver_unlock(); + mutex_unlock(&bL_switcher_activation_lock); + return ret; +} + +#ifdef CONFIG_SYSFS + +static void bL_switcher_disable(void) +{ + unsigned int cpu, cluster; + struct bL_thread *t; + struct task_struct *task; + + mutex_lock(&bL_switcher_activation_lock); + cpu_hotplug_driver_lock(); + + if (!bL_switcher_active) + goto out; + + if (bL_activation_notify(BL_NOTIFY_PRE_DISABLE) != 0) { + bL_activation_notify(BL_NOTIFY_POST_ENABLE); + goto out; + } + + bL_switcher_active = 0; + + /* + * To deactivate the switcher, we must shut down the switcher + * threads to prevent any other requests from being accepted. + * Then, if the final cluster for given logical CPU is not the + * same as the original one, we'll recreate a switcher thread + * just for the purpose of switching the CPU back without any + * possibility for interference from external requests. + */ + for_each_online_cpu(cpu) { + t = &bL_threads[cpu]; + task = t->task; + t->task = NULL; + if (!task || IS_ERR(task)) + continue; + kthread_stop(task); + /* no more switch may happen on this CPU at this point */ + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1); + if (cluster == bL_switcher_cpu_original_cluster[cpu]) + continue; + init_completion(&t->started); + t->wanted_cluster = bL_switcher_cpu_original_cluster[cpu]; + task = bL_switcher_thread_create(cpu, t); + if (!IS_ERR(task)) { + wait_for_completion(&t->started); + kthread_stop(task); + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1); + if (cluster == bL_switcher_cpu_original_cluster[cpu]) + continue; + } + /* If execution gets here, we're in trouble. */ + pr_crit("%s: unable to restore original cluster for CPU %d\n", + __func__, cpu); + pr_crit("%s: CPU %d can't be restored\n", + __func__, bL_switcher_cpu_pairing[cpu]); + cpumask_clear_cpu(bL_switcher_cpu_pairing[cpu], + &bL_switcher_removed_logical_cpus); + } + + bL_switcher_restore_cpus(); + bL_switcher_trace_trigger(); + + bL_activation_notify(BL_NOTIFY_POST_DISABLE); + +out: + cpu_hotplug_driver_unlock(); + mutex_unlock(&bL_switcher_activation_lock); +} + +static ssize_t bL_switcher_active_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", bL_switcher_active); +} + +static ssize_t bL_switcher_active_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int ret; + + switch (buf[0]) { + case '0': + bL_switcher_disable(); + ret = 0; + break; + case '1': + ret = bL_switcher_enable(); + break; + default: + ret = -EINVAL; + } + + return (ret >= 0) ? count : ret; +} + +static ssize_t bL_switcher_trace_trigger_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int ret = bL_switcher_trace_trigger(); + + return ret ? ret : count; +} + +static struct kobj_attribute bL_switcher_active_attr = + __ATTR(active, 0644, bL_switcher_active_show, bL_switcher_active_store); + +static struct kobj_attribute bL_switcher_trace_trigger_attr = + __ATTR(trace_trigger, 0200, NULL, bL_switcher_trace_trigger_store); + +static struct attribute *bL_switcher_attrs[] = { + &bL_switcher_active_attr.attr, + &bL_switcher_trace_trigger_attr.attr, + NULL, +}; + +static struct attribute_group bL_switcher_attr_group = { + .attrs = bL_switcher_attrs, +}; + +static struct kobject *bL_switcher_kobj; + +static int __init bL_switcher_sysfs_init(void) +{ + int ret; + + bL_switcher_kobj = kobject_create_and_add("bL_switcher", kernel_kobj); + if (!bL_switcher_kobj) + return -ENOMEM; + ret = sysfs_create_group(bL_switcher_kobj, &bL_switcher_attr_group); + if (ret) + kobject_put(bL_switcher_kobj); + return ret; +} + +#endif /* CONFIG_SYSFS */ + +bool bL_switcher_get_enabled(void) +{ + mutex_lock(&bL_switcher_activation_lock); + + return bL_switcher_active; +} +EXPORT_SYMBOL_GPL(bL_switcher_get_enabled); + +void bL_switcher_put_enabled(void) +{ + mutex_unlock(&bL_switcher_activation_lock); +} +EXPORT_SYMBOL_GPL(bL_switcher_put_enabled); + +/* + * Veto any CPU hotplug operation while the switcher is active. + * We're just not ready to deal with that given the trickery involved. + */ +static int bL_switcher_hotplug_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action) { + case CPU_UP_PREPARE: + case CPU_DOWN_PREPARE: + if (bL_switcher_active) + return NOTIFY_BAD; + } + return NOTIFY_DONE; +} + +static struct notifier_block bL_switcher_hotplug_notifier = + { &bL_switcher_hotplug_callback, NULL, 0 }; + +#ifdef CONFIG_SCHED_HMP +static bool no_bL_switcher = true; +#else +static bool no_bL_switcher; +#endif +core_param(no_bL_switcher, no_bL_switcher, bool, 0644); + +static int __init bL_switcher_init(void) +{ + int ret; + + if (MAX_NR_CLUSTERS != 2) { + pr_err("%s: only dual cluster systems are supported\n", __func__); + return -EINVAL; + } + + register_cpu_notifier(&bL_switcher_hotplug_notifier); + + if (!no_bL_switcher) { + ret = bL_switcher_enable(); + if (ret) + return ret; + } + +#ifdef CONFIG_SYSFS + ret = bL_switcher_sysfs_init(); + if (ret) + pr_err("%s: unable to create sysfs entry\n", __func__); +#endif + + return 0; +} + +late_initcall(bL_switcher_init); diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c new file mode 100644 index 00000000000..5e2dd197e72 --- /dev/null +++ b/arch/arm/common/bL_switcher_dummy_if.c @@ -0,0 +1,71 @@ +/* + * arch/arm/common/bL_switcher_dummy_if.c -- b.L switcher dummy interface + * + * Created by: Nicolas Pitre, November 2012 + * Copyright: (C) 2012 Linaro Limited + * + * Dummy interface to user space for debugging purpose only. + * + * 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 + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/miscdevice.h> +#include <asm/uaccess.h> +#include <asm/bL_switcher.h> + +static ssize_t bL_switcher_write(struct file *file, const char __user *buf, + size_t len, loff_t *pos) +{ + unsigned char val[3]; + unsigned int cpu, cluster; + int ret; + + pr_debug("%s\n", __func__); + + if (len < 3) + return -EINVAL; + + if (copy_from_user(val, buf, 3)) + return -EFAULT; + + /* format: <cpu#>,<cluster#> */ + if (val[0] < '0' || val[0] > '4' || + val[1] != ',' || + val[2] < '0' || val[2] > '1') + return -EINVAL; + + cpu = val[0] - '0'; + cluster = val[2] - '0'; + ret = bL_switch_request(cpu, cluster); + + return ret ? : len; +} + +static const struct file_operations bL_switcher_fops = { + .write = bL_switcher_write, + .owner = THIS_MODULE, +}; + +static struct miscdevice bL_switcher_device = { + MISC_DYNAMIC_MINOR, + "b.L_switcher", + &bL_switcher_fops +}; + +static int __init bL_switcher_dummy_if_init(void) +{ + return misc_register(&bL_switcher_device); +} + +static void __exit bL_switcher_dummy_if_exit(void) +{ + misc_deregister(&bL_switcher_device); +} + +module_init(bL_switcher_dummy_if_init); +module_exit(bL_switcher_dummy_if_exit); diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c index 370236dd1a0..4a2b32fd53a 100644 --- a/arch/arm/common/mcpm_entry.c +++ b/arch/arm/common/mcpm_entry.c @@ -27,6 +27,18 @@ void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr) sync_cache_w(&mcpm_entry_vectors[cluster][cpu]); } +extern unsigned long mcpm_entry_early_pokes[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER][2]; + +void mcpm_set_early_poke(unsigned cpu, unsigned cluster, + unsigned long poke_phys_addr, unsigned long poke_val) +{ + unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0]; + poke[0] = poke_phys_addr; + poke[1] = poke_val; + __cpuc_flush_dcache_area((void *)poke, 8); + outer_clean_range(__pa(poke), __pa(poke + 2)); +} + static const struct mcpm_platform_ops *platform_ops; int __init mcpm_platform_register(const struct mcpm_platform_ops *ops) diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S index 8178705c4b2..0decb3c0716 100644 --- a/arch/arm/common/mcpm_head.S +++ b/arch/arm/common/mcpm_head.S @@ -15,6 +15,7 @@ #include <linux/linkage.h> #include <asm/mcpm.h> +#include <asm/assembler.h> #include "vlock.h" @@ -47,6 +48,7 @@ ENTRY(mcpm_entry_point) + ARM_BE8(setend be) THUMB( adr r12, BSYM(1f) ) THUMB( bx r12 ) THUMB( .thumb ) @@ -71,12 +73,19 @@ ENTRY(mcpm_entry_point) * position independent way. */ adr r5, 3f - ldmia r5, {r6, r7, r8, r11} + ldmia r5, {r0, r6, r7, r8, r11} + add r0, r5, r0 @ r0 = mcpm_entry_early_pokes add r6, r5, r6 @ r6 = mcpm_entry_vectors ldr r7, [r5, r7] @ r7 = mcpm_power_up_setup_phys add r8, r5, r8 @ r8 = mcpm_sync add r11, r5, r11 @ r11 = first_man_locks + @ Perform an early poke, if any + add r0, r0, r4, lsl #3 + ldmia r0, {r0, r1} + teq r0, #0 + strne r1, [r0] + mov r0, #MCPM_SYNC_CLUSTER_SIZE mla r8, r0, r10, r8 @ r8 = sync cluster base @@ -195,7 +204,8 @@ mcpm_entry_gated: .align 2 -3: .word mcpm_entry_vectors - . +3: .word mcpm_entry_early_pokes - . + .word mcpm_entry_vectors - 3b .word mcpm_power_up_setup_phys - 3b .word mcpm_sync - 3b .word first_man_locks - 3b @@ -214,6 +224,10 @@ first_man_locks: ENTRY(mcpm_entry_vectors) .space 4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER + .type mcpm_entry_early_pokes, #object +ENTRY(mcpm_entry_early_pokes) + .space 8 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER + .type mcpm_power_up_setup_phys, #object ENTRY(mcpm_power_up_setup_phys) .space 4 @ set by mcpm_sync_init() diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S index 19d6cd6f29f..3a14ea8fe97 100644 --- a/arch/arm/crypto/aes-armv4.S +++ b/arch/arm/crypto/aes-armv4.S @@ -148,7 +148,7 @@ AES_Te: @ const AES_KEY *key) { .align 5 ENTRY(AES_encrypt) - sub r3,pc,#8 @ AES_encrypt + adr r3,AES_encrypt stmdb sp!,{r1,r4-r12,lr} mov r12,r0 @ inp mov r11,r2 @@ -381,7 +381,7 @@ _armv4_AES_encrypt: .align 5 ENTRY(private_AES_set_encrypt_key) _armv4_AES_set_encrypt_key: - sub r3,pc,#8 @ AES_set_encrypt_key + adr r3,_armv4_AES_set_encrypt_key teq r0,#0 moveq r0,#-1 beq .Labrt @@ -843,7 +843,7 @@ AES_Td: @ const AES_KEY *key) { .align 5 ENTRY(AES_decrypt) - sub r3,pc,#8 @ AES_decrypt + adr r3,AES_decrypt stmdb sp!,{r1,r4-r12,lr} mov r12,r0 @ inp mov r11,r2 diff --git a/arch/arm/include/asm/a.out-core.h b/arch/arm/include/asm/a.out-core.h deleted file mode 100644 index 92f10cb5c70..00000000000 --- a/arch/arm/include/asm/a.out-core.h +++ /dev/null @@ -1,45 +0,0 @@ -/* a.out coredump register dumper - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -#ifndef _ASM_A_OUT_CORE_H -#define _ASM_A_OUT_CORE_H - -#ifdef __KERNEL__ - -#include <linux/user.h> -#include <linux/elfcore.h> - -/* - * fill in the user structure for an a.out core dump - */ -static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) -{ - struct task_struct *tsk = current; - - dump->magic = CMAGIC; - dump->start_code = tsk->mm->start_code; - dump->start_stack = regs->ARM_sp & ~(PAGE_SIZE - 1); - - dump->u_tsize = (tsk->mm->end_code - tsk->mm->start_code) >> PAGE_SHIFT; - dump->u_dsize = (tsk->mm->brk - tsk->mm->start_data + PAGE_SIZE - 1) >> PAGE_SHIFT; - dump->u_ssize = 0; - - memset(dump->u_debugreg, 0, sizeof(dump->u_debugreg)); - - if (dump->start_stack < 0x04000000) - dump->u_ssize = (0x04000000 - dump->start_stack) >> PAGE_SHIFT; - - dump->regs = *regs; - dump->u_fpvalid = dump_fpu (regs, &dump->u_fp); -} - -#endif /* __KERNEL__ */ -#endif /* _ASM_A_OUT_CORE_H */ diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h index 4928cdacedf..f693038b888 100644 --- a/arch/arm/include/asm/arch_timer.h +++ b/arch/arm/include/asm/arch_timer.h @@ -80,15 +80,6 @@ static inline u32 arch_timer_get_cntfrq(void) return val; } -static inline u64 arch_counter_get_cntpct(void) -{ - u64 cval; - - isb(); - asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval)); - return cval; -} - static inline u64 arch_counter_get_cntvct(void) { u64 cval; diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 05ee9eebad6..e780afbcee5 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -53,6 +53,13 @@ #define put_byte_3 lsl #0 #endif +/* Select code for any configuration running in BE8 mode */ +#ifdef CONFIG_CPU_ENDIAN_BE8 +#define ARM_BE8(code...) code +#else +#define ARM_BE8(code...) +#endif + /* * Data preload for architectures that support it */ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index da1c77d3932..6447a0b7b12 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -301,8 +301,8 @@ static inline void atomic64_add(u64 i, atomic64_t *v) __asm__ __volatile__("@ atomic64_add\n" "1: ldrexd %0, %H0, [%3]\n" -" adds %0, %0, %4\n" -" adc %H0, %H0, %H4\n" +" adds %Q0, %Q0, %Q4\n" +" adc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -320,8 +320,8 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v) __asm__ __volatile__("@ atomic64_add_return\n" "1: ldrexd %0, %H0, [%3]\n" -" adds %0, %0, %4\n" -" adc %H0, %H0, %H4\n" +" adds %Q0, %Q0, %Q4\n" +" adc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -341,8 +341,8 @@ static inline void atomic64_sub(u64 i, atomic64_t *v) __asm__ __volatile__("@ atomic64_sub\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, %4\n" -" sbc %H0, %H0, %H4\n" +" subs %Q0, %Q0, %Q4\n" +" sbc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -360,8 +360,8 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v) __asm__ __volatile__("@ atomic64_sub_return\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, %4\n" -" sbc %H0, %H0, %H4\n" +" subs %Q0, %Q0, %Q4\n" +" sbc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -428,9 +428,9 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v) __asm__ __volatile__("@ atomic64_dec_if_positive\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, #1\n" -" sbc %H0, %H0, #0\n" -" teq %H0, #0\n" +" subs %Q0, %Q0, #1\n" +" sbc %R0, %R0, #0\n" +" teq %R0, #0\n" " bmi 2f\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" @@ -459,8 +459,8 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u) " teqeq %H0, %H5\n" " moveq %1, #0\n" " beq 2f\n" -" adds %0, %0, %6\n" -" adc %H0, %H0, %H6\n" +" adds %Q0, %Q0, %Q6\n" +" adc %R0, %R0, %R6\n" " strexd %2, %0, %H0, [%4]\n" " teq %2, #0\n" " bne 1b\n" diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h new file mode 100644 index 00000000000..482383b45c9 --- /dev/null +++ b/arch/arm/include/asm/bL_switcher.h @@ -0,0 +1,83 @@ +/* + * arch/arm/include/asm/bL_switcher.h + * + * Created by: Nicolas Pitre, April 2012 + * Copyright: (C) 2012 Linaro Limited + * + * 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 + * published by the Free Software Foundation. + */ + +#ifndef ASM_BL_SWITCHER_H +#define ASM_BL_SWITCHER_H + +#include <linux/compiler.h> +#include <linux/types.h> + +typedef void (*bL_switch_completion_handler)(void *cookie); + +int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id, + bL_switch_completion_handler completer, + void *completer_cookie); +static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id) +{ + return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL); +} + +/* + * Register here to be notified about runtime enabling/disabling of + * the switcher. + * + * The notifier chain is called with the switcher activation lock held: + * the switcher will not be enabled or disabled during callbacks. + * Callbacks must not call bL_switcher_{get,put}_enabled(). + */ +#define BL_NOTIFY_PRE_ENABLE 0 +#define BL_NOTIFY_POST_ENABLE 1 +#define BL_NOTIFY_PRE_DISABLE 2 +#define BL_NOTIFY_POST_DISABLE 3 + +#ifdef CONFIG_BL_SWITCHER + +void bL_switch_request_detach(unsigned int cpu, + bL_switch_completion_handler completer); + +int bL_switcher_register_notifier(struct notifier_block *nb); +int bL_switcher_unregister_notifier(struct notifier_block *nb); + +/* + * Use these functions to temporarily prevent enabling/disabling of + * the switcher. + * bL_switcher_get_enabled() returns true if the switcher is currently + * enabled. Each call to bL_switcher_get_enabled() must be followed + * by a call to bL_switcher_put_enabled(). These functions are not + * recursive. + */ +bool bL_switcher_get_enabled(void); +void bL_switcher_put_enabled(void); + +int bL_switcher_trace_trigger(void); +int bL_switcher_get_logical_index(u32 mpidr); + +#else +static void bL_switch_request_detach(unsigned int cpu, + bL_switch_completion_handler completer) { } + +static inline int bL_switcher_register_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int bL_switcher_unregister_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline bool bL_switcher_get_enabled(void) { return false; } +static inline void bL_switcher_put_enabled(void) { } +static inline int bL_switcher_trace_trigger(void) { return 0; } +static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; } +#endif /* CONFIG_BL_SWITCHER */ + +#endif diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index 7af5c6c3653..b274bde2490 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -2,6 +2,8 @@ #define _ASMARM_BUG_H #include <linux/linkage.h> +#include <linux/types.h> +#include <asm/opcodes.h> #ifdef CONFIG_BUG @@ -12,10 +14,10 @@ */ #ifdef CONFIG_THUMB2_KERNEL #define BUG_INSTR_VALUE 0xde02 -#define BUG_INSTR_TYPE ".hword " +#define BUG_INSTR(__value) __inst_thumb16(__value) #else #define BUG_INSTR_VALUE 0xe7f001f2 -#define BUG_INSTR_TYPE ".word " +#define BUG_INSTR(__value) __inst_arm(__value) #endif @@ -33,7 +35,7 @@ #define __BUG(__file, __line, __value) \ do { \ - asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \ + asm volatile("1:\t" BUG_INSTR(__value) "\n" \ ".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \ "2:\t.asciz " #__file "\n" \ ".popsection\n" \ @@ -48,7 +50,7 @@ do { \ #define __BUG(__file, __line, __value) \ do { \ - asm volatile(BUG_INSTR_TYPE #__value); \ + asm volatile(BUG_INSTR(__value) "\n"); \ unreachable(); \ } while (0) #endif /* CONFIG_DEBUG_BUGVERBOSE */ diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index beb87022178..2059f019bef 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -212,6 +212,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, static inline void __flush_icache_all(void) { __flush_icache_preferred(); + dsb(); } /* diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index 38050b1c480..56211f2084e 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -130,4 +130,10 @@ struct mm_struct; extern unsigned long arch_randomize_brk(struct mm_struct *mm); #define arch_randomize_brk arch_randomize_brk +#ifdef CONFIG_MMU +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 +struct linux_binprm; +int arch_setup_additional_pages(struct linux_binprm *, int); +#endif + #endif diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h index 2740c2a2df6..3d7351c844a 100644 --- a/arch/arm/include/asm/hardirq.h +++ b/arch/arm/include/asm/hardirq.h @@ -5,7 +5,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 6 +#define NR_IPI 7 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h index 0cf7a6b842f..ad774f37c47 100644 --- a/arch/arm/include/asm/hardware/coresight.h +++ b/arch/arm/include/asm/hardware/coresight.h @@ -24,8 +24,8 @@ #define TRACER_TIMEOUT 10000 #define etm_writel(t, v, x) \ - (__raw_writel((v), (t)->etm_regs + (x))) -#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x))) + (writel_relaxed((v), (t)->etm_regs + (x))) +#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x))) /* CoreSight Management Registers */ #define CSMR_LOCKACCESS 0xfb0 @@ -142,8 +142,8 @@ #define ETBFF_TRIGFL BIT(10) #define etb_writel(t, v, x) \ - (__raw_writel((v), (t)->etb_regs + (x))) -#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x))) + (writel_relaxed((v), (t)->etb_regs + (x))) +#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x))) #define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0) #define etm_unlock(t) \ diff --git a/arch/arm/include/asm/hardware/debug-pl01x.S b/arch/arm/include/asm/hardware/debug-pl01x.S index f9fd083eff6..6489d1ffe3c 100644 --- a/arch/arm/include/asm/hardware/debug-pl01x.S +++ b/arch/arm/include/asm/hardware/debug-pl01x.S @@ -18,12 +18,14 @@ .macro waituart,rd,rx 1001: ldr \rd, [\rx, #UART01x_FR] + ARM_BE8( rev \rd, \rd ) tst \rd, #UART01x_FR_TXFF bne 1001b .endm .macro busyuart,rd,rx 1001: ldr \rd, [\rx, #UART01x_FR] + ARM_BE8( rev \rd, \rd ) tst \rd, #UART01x_FR_BUSY bne 1001b .endm diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h index bfc198c7591..863c892b4aa 100644 --- a/arch/arm/include/asm/jump_label.h +++ b/arch/arm/include/asm/jump_label.h @@ -16,7 +16,7 @@ static __always_inline bool arch_static_branch(struct static_key *key) { - asm goto("1:\n\t" + asm_volatile_goto("1:\n\t" JUMP_LABEL_NOP "\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h index 48066ce9ea3..0a9d5dd9329 100644 --- a/arch/arm/include/asm/kgdb.h +++ b/arch/arm/include/asm/kgdb.h @@ -11,6 +11,7 @@ #define __ARM_KGDB_H__ #include <linux/ptrace.h> +#include <asm/opcodes.h> /* * GDB assumes that we're a user process being debugged, so @@ -41,7 +42,7 @@ static inline void arch_kgdb_breakpoint(void) { - asm(".word 0xe7ffdeff"); + asm(__inst_arm(0xe7ffdeff)); } extern void kgdb_handle_bus_error(void); diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index 18d50322a9e..4bb08e3e52b 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -37,16 +37,18 @@ #define c5_AIFSR 15 /* Auxilary Instrunction Fault Status R */ #define c6_DFAR 16 /* Data Fault Address Register */ #define c6_IFAR 17 /* Instruction Fault Address Register */ -#define c9_L2CTLR 18 /* Cortex A15 L2 Control Register */ -#define c10_PRRR 19 /* Primary Region Remap Register */ -#define c10_NMRR 20 /* Normal Memory Remap Register */ -#define c12_VBAR 21 /* Vector Base Address Register */ -#define c13_CID 22 /* Context ID Register */ -#define c13_TID_URW 23 /* Thread ID, User R/W */ -#define c13_TID_URO 24 /* Thread ID, User R/O */ -#define c13_TID_PRIV 25 /* Thread ID, Privileged */ -#define c14_CNTKCTL 26 /* Timer Control Register (PL1) */ -#define NR_CP15_REGS 27 /* Number of regs (incl. invalid) */ +#define c7_PAR 18 /* Physical Address Register */ +#define c7_PAR_high 19 /* PAR top 32 bits */ +#define c9_L2CTLR 20 /* Cortex A15 L2 Control Register */ +#define c10_PRRR 21 /* Primary Region Remap Register */ +#define c10_NMRR 22 /* Normal Memory Remap Register */ +#define c12_VBAR 23 /* Vector Base Address Register */ +#define c13_CID 24 /* Context ID Register */ +#define c13_TID_URW 25 /* Thread ID, User R/W */ +#define c13_TID_URO 26 /* Thread ID, User R/O */ +#define c13_TID_PRIV 27 /* Thread ID, Privileged */ +#define c14_CNTKCTL 28 /* Timer Control Register (PL1) */ +#define NR_CP15_REGS 29 /* Number of regs (incl. invalid) */ #define ARM_EXCEPTION_RESET 0 #define ARM_EXCEPTION_UNDEFINED 1 diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h index 0f7b7620e9a..7626a7fd493 100644 --- a/arch/arm/include/asm/mcpm.h +++ b/arch/arm/include/asm/mcpm.h @@ -42,6 +42,14 @@ extern void mcpm_entry_point(void); void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr); /* + * This sets an early poke i.e a value to be poked into some address + * from very early assembly code before the CPU is ungated. The + * address must be physical, and if 0 then nothing will happen. + */ +void mcpm_set_early_poke(unsigned cpu, unsigned cluster, + unsigned long poke_phys_addr, unsigned long poke_val); + +/* * CPU/cluster power operations API for higher subsystems to use. */ diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h index e3d55547e75..64fd15159b7 100644 --- a/arch/arm/include/asm/mmu.h +++ b/arch/arm/include/asm/mmu.h @@ -6,14 +6,17 @@ typedef struct { #ifdef CONFIG_CPU_HAS_ASID atomic64_t id; +#else + int switch_pending; #endif unsigned int vmalloc_seq; + unsigned long sigpage; } mm_context_t; #ifdef CONFIG_CPU_HAS_ASID #define ASID_BITS 8 #define ASID_MASK ((~0ULL) << ASID_BITS) -#define ASID(mm) ((mm)->context.id.counter & ~ASID_MASK) +#define ASID(mm) ((unsigned int)((mm)->context.id.counter & ~ASID_MASK)) #else #define ASID(mm) (0) #endif diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index a7b85e0d0cc..e0b10f19d67 100644 --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -27,7 +27,15 @@ void __check_vmalloc_seq(struct mm_struct *mm); void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk); #define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) -DECLARE_PER_CPU(atomic64_t, active_asids); +#ifdef CONFIG_ARM_ERRATA_798181 +void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask); +#else /* !CONFIG_ARM_ERRATA_798181 */ +static inline void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask) +{ +} +#endif /* CONFIG_ARM_ERRATA_798181 */ #else /* !CONFIG_CPU_HAS_ASID */ @@ -47,7 +55,7 @@ static inline void check_and_switch_context(struct mm_struct *mm, * on non-ASID CPUs, the old mm will remain valid until the * finish_arch_post_lock_switch() call. */ - set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM); + mm->context.switch_pending = 1; else cpu_switch_mm(mm->pgd, mm); } @@ -56,9 +64,21 @@ static inline void check_and_switch_context(struct mm_struct *mm, finish_arch_post_lock_switch static inline void finish_arch_post_lock_switch(void) { - if (test_and_clear_thread_flag(TIF_SWITCH_MM)) { - struct mm_struct *mm = current->mm; - cpu_switch_mm(mm->pgd, mm); + struct mm_struct *mm = current->mm; + + if (mm && mm->context.switch_pending) { + /* + * Preemption must be disabled during cpu_switch_mm() as we + * have some stateful cache flush implementations. Check + * switch_pending again in case we were preempted and the + * switch to this mm was already done. + */ + preempt_disable(); + if (mm->context.switch_pending) { + mm->context.switch_pending = 0; + cpu_switch_mm(mm->pgd, mm); + } + preempt_enable_no_resched(); } } diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h index 12f71a19042..f94784f0e3a 100644 --- a/arch/arm/include/asm/outercache.h +++ b/arch/arm/include/asm/outercache.h @@ -37,10 +37,10 @@ struct outer_cache_fns { void (*resume)(void); }; -#ifdef CONFIG_OUTER_CACHE - extern struct outer_cache_fns outer_cache; +#ifdef CONFIG_OUTER_CACHE + static inline void outer_inv_range(phys_addr_t start, phys_addr_t end) { if (outer_cache.inv_range) diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index 812a4944e78..cbdc7a21f86 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -142,7 +142,9 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from, #define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) extern void copy_page(void *to, const void *from); +#ifdef CONFIG_KUSER_HELPERS #define __HAVE_ARCH_GATE_AREA 1 +#endif #ifdef CONFIG_ARM_LPAE #include <asm/pgtable-3level-types.h> diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 9bcd262a900..5aac06fcc97 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -58,7 +58,7 @@ extern void __pgd_error(const char *file, int line, pgd_t); * mapping to be mapped at. This is particularly important for * non-high vector CPUs. */ -#define FIRST_USER_ADDRESS PAGE_SIZE +#define FIRST_USER_ADDRESS (PAGE_SIZE * 2) /* * Use TASK_SIZE as the ceiling argument for free_pgtables() and diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index f24edad26c7..0cd7824ca76 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -62,9 +62,19 @@ struct pmu_hw_events { raw_spinlock_t pmu_lock; }; +struct cpupmu_regs { + u32 pmc; + u32 pmcntenset; + u32 pmuseren; + u32 pmintenset; + u32 pmxevttype[8]; + u32 pmxevtcnt[8]; +}; + struct arm_pmu { struct pmu pmu; cpumask_t active_irqs; + cpumask_t valid_cpus; char *name; irqreturn_t (*handle_irq)(int irq_num, void *dev); void (*enable)(struct perf_event *event); @@ -81,6 +91,8 @@ struct arm_pmu { int (*request_irq)(struct arm_pmu *, irq_handler_t handler); void (*free_irq)(struct arm_pmu *); int (*map_event)(struct perf_event *event); + void (*save_regs)(struct arm_pmu *, struct cpupmu_regs *); + void (*restore_regs)(struct arm_pmu *, struct cpupmu_regs *); int num_events; atomic_t active_events; struct mutex reserve_mutex; diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 06e7d509eaa..413f3876341 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -54,7 +54,6 @@ struct thread_struct { #define start_thread(regs,pc,sp) \ ({ \ - unsigned long *stack = (unsigned long *)sp; \ memset(regs->uregs, 0, sizeof(regs->uregs)); \ if (current->personality & ADDR_LIMIT_32BIT) \ regs->ARM_cpsr = USR_MODE; \ @@ -65,9 +64,6 @@ struct thread_struct { regs->ARM_cpsr |= PSR_ENDSTATE; \ regs->ARM_pc = pc & ~1; /* pc */ \ regs->ARM_sp = sp; /* sp */ \ - regs->ARM_r2 = stack[2]; /* r2 (envp) */ \ - regs->ARM_r1 = stack[1]; /* r1 (argv) */ \ - regs->ARM_r0 = stack[0]; /* r0 (argc) */ \ nommu_start_thread(regs); \ }) diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index d3a22bebe6c..610ccf33f5e 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -81,6 +81,8 @@ extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask); +extern int register_ipi_completion(struct completion *completion, int cpu); + struct smp_operations { #ifdef CONFIG_SMP /* diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 6220e9fdf4c..b07c09e5a0a 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -97,19 +97,22 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) static inline int arch_spin_trylock(arch_spinlock_t *lock) { - unsigned long tmp; + unsigned long contended, res; u32 slock; - __asm__ __volatile__( -" ldrex %0, [%2]\n" -" subs %1, %0, %0, ror #16\n" -" addeq %0, %0, %3\n" -" strexeq %1, %0, [%2]" - : "=&r" (slock), "=&r" (tmp) - : "r" (&lock->slock), "I" (1 << TICKET_SHIFT) - : "cc"); - - if (tmp == 0) { + do { + __asm__ __volatile__( + " ldrex %0, [%3]\n" + " mov %2, #0\n" + " subs %1, %0, %0, ror #16\n" + " addeq %0, %0, %4\n" + " strexeq %2, %0, [%3]" + : "=&r" (slock), "=&r" (contended), "=&r" (res) + : "r" (&lock->slock), "I" (1 << TICKET_SHIFT) + : "cc"); + } while (res); + + if (!contended) { smp_mb(); return 1; } else { @@ -165,17 +168,20 @@ static inline void arch_write_lock(arch_rwlock_t *rw) static inline int arch_write_trylock(arch_rwlock_t *rw) { - unsigned long tmp; - - __asm__ __volatile__( -" ldrex %0, [%1]\n" -" teq %0, #0\n" -" strexeq %0, %2, [%1]" - : "=&r" (tmp) - : "r" (&rw->lock), "r" (0x80000000) - : "cc"); - - if (tmp == 0) { + unsigned long contended, res; + + do { + __asm__ __volatile__( + " ldrex %0, [%2]\n" + " mov %1, #0\n" + " teq %0, #0\n" + " strexeq %1, %3, [%2]" + : "=&r" (contended), "=&r" (res) + : "r" (&rw->lock), "r" (0x80000000) + : "cc"); + } while (res); + + if (!contended) { smp_mb(); return 1; } else { @@ -251,18 +257,26 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) static inline int arch_read_trylock(arch_rwlock_t *rw) { - unsigned long tmp, tmp2 = 1; - - __asm__ __volatile__( -" ldrex %0, [%2]\n" -" adds %0, %0, #1\n" -" strexpl %1, %0, [%2]\n" - : "=&r" (tmp), "+r" (tmp2) - : "r" (&rw->lock) - : "cc"); - - smp_mb(); - return tmp2 == 0; + unsigned long contended, res; + + do { + __asm__ __volatile__( + " ldrex %0, [%2]\n" + " mov %1, #0\n" + " adds %0, %0, #1\n" + " strexpl %1, %0, [%2]" + : "=&r" (contended), "=&r" (res) + : "r" (&rw->lock) + : "cc"); + } while (res); + + /* If the lock is negative, then it is already held for write. */ + if (contended < 0x80000000) { + smp_mb(); + return 1; + } else { + return 0; + } } /* read_can_lock - would read_trylock() succeed? */ diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index f1d96d4e809..73ddd7239b3 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -57,6 +57,9 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned int i, unsigned int n, unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i; unsigned int n_bad = n + i - SYSCALL_MAX_ARGS; @@ -81,6 +84,9 @@ static inline void syscall_set_arguments(struct task_struct *task, unsigned int i, unsigned int n, const unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { pr_warning("%s called with max args %d, handling only %d\n", __func__, i + n, SYSCALL_MAX_ARGS); diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 1995d1a8406..f00b5692cd9 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -156,7 +156,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 20 -#define TIF_SWITCH_MM 22 /* deferred switch_mm */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index bdf2b8458ec..aa9b4ac3fdf 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -43,6 +43,7 @@ struct mmu_gather { struct mm_struct *mm; unsigned int fullmm; struct vm_area_struct *vma; + unsigned long start, end; unsigned long range_start; unsigned long range_end; unsigned int nr; @@ -107,10 +108,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb) } static inline void -tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm) +tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) { tlb->mm = mm; - tlb->fullmm = fullmm; + tlb->fullmm = !(start | (end+1)); + tlb->start = start; + tlb->end = end; tlb->vma = NULL; tlb->max = ARRAY_SIZE(tlb->local); tlb->pages = tlb->local; diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 58b8b84adcd..983fa7c153a 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -26,11 +26,45 @@ extern struct cputopo_arm cpu_topology[NR_CPUS]; void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); +int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask); + +#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE +/* Common values for CPUs */ +#ifndef SD_CPU_INIT +#define SD_CPU_INIT (struct sched_domain) { \ + .min_interval = 1, \ + .max_interval = 4, \ + .busy_factor = 64, \ + .imbalance_pct = 125, \ + .cache_nice_tries = 1, \ + .busy_idx = 2, \ + .idle_idx = 1, \ + .newidle_idx = 0, \ + .wake_idx = 0, \ + .forkexec_idx = 0, \ + \ + .flags = 0*SD_LOAD_BALANCE \ + | 1*SD_BALANCE_NEWIDLE \ + | 1*SD_BALANCE_EXEC \ + | 1*SD_BALANCE_FORK \ + | 0*SD_BALANCE_WAKE \ + | 1*SD_WAKE_AFFINE \ + | 0*SD_SHARE_CPUPOWER \ + | 0*SD_SHARE_PKG_RESOURCES \ + | 0*SD_SERIALIZE \ + , \ + .last_balance = jiffies, \ + .balance_interval = 1, \ +} +#endif +#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */ #else static inline void init_cpu_topology(void) { } static inline void store_cpu_topology(unsigned int cpuid) { } +static inline int cluster_to_logical_mask(unsigned int socket_id, + cpumask_t *cluster_mask) { return -EINVAL; } #endif diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild index 47bcb2d254a..18d76fd5a2a 100644 --- a/arch/arm/include/uapi/asm/Kbuild +++ b/arch/arm/include/uapi/asm/Kbuild @@ -1,7 +1,6 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm -header-y += a.out.h header-y += byteorder.h header-y += fcntl.h header-y += hwcap.h diff --git a/arch/arm/include/uapi/asm/a.out.h b/arch/arm/include/uapi/asm/a.out.h deleted file mode 100644 index 083894b2e3b..00000000000 --- a/arch/arm/include/uapi/asm/a.out.h +++ /dev/null @@ -1,34 +0,0 @@ -#ifndef __ARM_A_OUT_H__ -#define __ARM_A_OUT_H__ - -#include <linux/personality.h> -#include <linux/types.h> - -struct exec -{ - __u32 a_info; /* Use macros N_MAGIC, etc for access */ - __u32 a_text; /* length of text, in bytes */ - __u32 a_data; /* length of data, in bytes */ - __u32 a_bss; /* length of uninitialized data area for file, in bytes */ - __u32 a_syms; /* length of symbol table data in file, in bytes */ - __u32 a_entry; /* start address */ - __u32 a_trsize; /* length of relocation info for text, in bytes */ - __u32 a_drsize; /* length of relocation info for data, in bytes */ -}; - -/* - * This is always the same - */ -#define N_TXTADDR(a) (0x00008000) - -#define N_TRSIZE(a) ((a).a_trsize) -#define N_DRSIZE(a) ((a).a_drsize) -#define N_SYMSIZE(a) ((a).a_syms) - -#define M_ARM 103 - -#ifndef LIBRARY_START_TEXT -#define LIBRARY_START_TEXT (0x00c00000) -#endif - -#endif /* __A_OUT_GNU_H__ */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index dd9d90ab65d..aa775438388 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -17,7 +17,8 @@ CFLAGS_REMOVE_return_address.o = -pg obj-y := elf.o entry-armv.o entry-common.o irq.o opcodes.o \ process.o ptrace.o return_address.o sched_clock.o \ - setup.o signal.o stacktrace.o sys_arm.o time.o traps.o + setup.o signal.o sigreturn_codes.o \ + stacktrace.o sys_arm.o time.o traps.o obj-$(CONFIG_ATAGS) += atags_parse.o obj-$(CONFIG_ATAGS_PROC) += atags_proc.o diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 582b405befc..45a68d6bb2a 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -192,6 +192,7 @@ __dabt_svc: svc_entry mov r2, sp dabt_helper + THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__dabt_svc) @@ -415,9 +416,8 @@ __und_usr: bne __und_usr_thumb sub r4, r2, #4 @ ARM instr at LR - 4 1: ldrt r0, [r4] -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r0, r0 @ little endian instruction -#endif + ARM_BE8(rev r0, r0) @ little endian instruction + @ r0 = 32-bit ARM instruction which caused the exception @ r2 = PC value for the following instruction (:= regs->ARM_pc) @ r4 = PC value for the faulting instruction @@ -741,6 +741,18 @@ ENDPROC(__switch_to) #endif .endm + .macro kuser_pad, sym, size + .if (. - \sym) & 3 + .rept 4 - (. - \sym) & 3 + .byte 0 + .endr + .endif + .rept (\size - (. - \sym)) / 4 + .word 0xe7fddef1 + .endr + .endm + +#ifdef CONFIG_KUSER_HELPERS .align 5 .globl __kuser_helper_start __kuser_helper_start: @@ -831,18 +843,13 @@ kuser_cmpxchg64_fixup: #error "incoherent kernel configuration" #endif - /* pad to next slot */ - .rept (16 - (. - __kuser_cmpxchg64)/4) - .word 0 - .endr - - .align 5 + kuser_pad __kuser_cmpxchg64, 64 __kuser_memory_barrier: @ 0xffff0fa0 smp_dmb arm usr_ret lr - .align 5 + kuser_pad __kuser_memory_barrier, 32 __kuser_cmpxchg: @ 0xffff0fc0 @@ -915,13 +922,14 @@ kuser_cmpxchg32_fixup: #endif - .align 5 + kuser_pad __kuser_cmpxchg, 32 __kuser_get_tls: @ 0xffff0fe0 ldr r0, [pc, #(16 - 8)] @ read TLS, set in kuser_get_tls_init usr_ret lr mrc p15, 0, r0, c13, c0, 3 @ 0xffff0fe8 hardware TLS code - .rep 4 + kuser_pad __kuser_get_tls, 16 + .rep 3 .word 0 @ 0xffff0ff0 software TLS value, then .endr @ pad up to __kuser_helper_version @@ -931,14 +939,16 @@ __kuser_helper_version: @ 0xffff0ffc .globl __kuser_helper_end __kuser_helper_end: +#endif + THUMB( .thumb ) /* * Vector stubs. * - * This code is copied to 0xffff0200 so we can use branches in the - * vectors, rather than ldr's. Note that this code must not - * exceed 0x300 bytes. + * This code is copied to 0xffff1000 so we can use branches in the + * vectors, rather than ldr's. Note that this code must not exceed + * a page size. * * Common stub entry macro: * Enter in IRQ mode, spsr = SVC/USR CPSR, lr = SVC/USR PC @@ -985,8 +995,17 @@ ENDPROC(vector_\name) 1: .endm - .globl __stubs_start + .section .stubs, "ax", %progbits __stubs_start: + @ This must be the first word + .word vector_swi + +vector_rst: + ARM( swi SYS_ERROR0 ) + THUMB( svc #0 ) + THUMB( nop ) + b vector_und + /* * Interrupt dispatcher */ @@ -1081,6 +1100,16 @@ __stubs_start: .align 5 /*============================================================================= + * Address exception handler + *----------------------------------------------------------------------------- + * These aren't too critical. + * (they're not supposed to happen, and won't happen in 32-bit data mode). + */ + +vector_addrexcptn: + b vector_addrexcptn + +/*============================================================================= * Undefined FIQs *----------------------------------------------------------------------------- * Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC @@ -1093,45 +1122,19 @@ __stubs_start: vector_fiq: subs pc, lr, #4 -/*============================================================================= - * Address exception handler - *----------------------------------------------------------------------------- - * These aren't too critical. - * (they're not supposed to happen, and won't happen in 32-bit data mode). - */ + .globl vector_fiq_offset + .equ vector_fiq_offset, vector_fiq -vector_addrexcptn: - b vector_addrexcptn - -/* - * We group all the following data together to optimise - * for CPUs with separate I & D caches. - */ - .align 5 - -.LCvswi: - .word vector_swi - - .globl __stubs_end -__stubs_end: - - .equ stubs_offset, __vectors_start + 0x200 - __stubs_start - - .globl __vectors_start + .section .vectors, "ax", %progbits __vectors_start: - ARM( swi SYS_ERROR0 ) - THUMB( svc #0 ) - THUMB( nop ) - W(b) vector_und + stubs_offset - W(ldr) pc, .LCvswi + stubs_offset - W(b) vector_pabt + stubs_offset - W(b) vector_dabt + stubs_offset - W(b) vector_addrexcptn + stubs_offset - W(b) vector_irq + stubs_offset - W(b) vector_fiq + stubs_offset - - .globl __vectors_end -__vectors_end: + W(b) vector_rst + W(b) vector_und + W(ldr) pc, __vectors_start + 0x1000 + W(b) vector_pabt + W(b) vector_dabt + W(b) vector_addrexcptn + W(b) vector_irq + W(b) vector_fiq .data diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index bc5bc0a9713..8c79344552d 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -379,9 +379,7 @@ ENTRY(vector_swi) #else ldr r10, [lr, #-4] @ get SWI instruction #endif -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r10, r10 @ little endian instruction -#endif + ARM_BE8(rev r10, r10) @ little endian instruction #elif defined(CONFIG_AEABI) diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c index 2adda11f712..25442f45114 100644 --- a/arch/arm/kernel/fiq.c +++ b/arch/arm/kernel/fiq.c @@ -47,6 +47,11 @@ #include <asm/irq.h> #include <asm/traps.h> +#define FIQ_OFFSET ({ \ + extern void *vector_fiq_offset; \ + (unsigned)&vector_fiq_offset; \ + }) + static unsigned long no_fiq_insn; /* Default reacquire function @@ -80,13 +85,16 @@ int show_fiq_list(struct seq_file *p, int prec) void set_fiq_handler(void *start, unsigned int length) { #if defined(CONFIG_CPU_USE_DOMAINS) - memcpy((void *)0xffff001c, start, length); + void *base = (void *)0xffff0000; #else - memcpy(vectors_page + 0x1c, start, length); + void *base = vectors_page; #endif - flush_icache_range(0xffff001c, 0xffff001c + length); + unsigned offset = FIQ_OFFSET; + + memcpy(base + offset, start, length); + flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length); if (!vectors_high()) - flush_icache_range(0x1c, 0x1c + length); + flush_icache_range(offset, offset + length); } int claim_fiq(struct fiq_handler *f) @@ -144,6 +152,7 @@ EXPORT_SYMBOL(disable_fiq); void __init init_FIQ(int start) { - no_fiq_insn = *(unsigned long *)0xffff001c; + unsigned offset = FIQ_OFFSET; + no_fiq_insn = *(unsigned long *)(0xffff0000 + offset); fiq_start = start; } diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 8bac553fe21..11284e744c8 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -77,6 +77,7 @@ __HEAD ENTRY(stext) + ARM_BE8(setend be ) @ ensure we are in BE8 mode THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM. THUMB( bx r9 ) @ If this is a Thumb-2 kernel, @@ -342,7 +343,6 @@ __turn_mmu_on_loc: .long __turn_mmu_on_end #if defined(CONFIG_SMP) - __CPUINIT ENTRY(secondary_startup) /* * Common entry point for secondary CPUs. @@ -351,6 +351,9 @@ ENTRY(secondary_startup) * the processor type - there is no need to check the machine type * as it has already been validated by the primary processor. */ + + ARM_BE8(setend be) @ ensure we are in BE8 mode + #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install_secondary #endif @@ -584,8 +587,10 @@ __fixup_a_pv_table: b 2f 1: add r7, r3 ldrh ip, [r7, #2] +ARM_BE8(rev16 ip, ip) and ip, 0x8f00 orr ip, r6 @ mask in offset bits 31-24 +ARM_BE8(rev16 ip, ip) strh ip, [r7, #2] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot @@ -594,8 +599,14 @@ __fixup_a_pv_table: #else b 2f 1: ldr ip, [r7, r3] +#ifdef CONFIG_CPU_ENDIAN_BE8 + @ in BE8, we load data in BE, but instructions still in LE + bic ip, ip, #0xff000000 + orr ip, ip, r6, lsl#24 +#else bic ip, ip, #0x000000ff orr ip, ip, r6 @ mask in offset bits 31-24 +#endif str ip, [r7, r3] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 1fd749ee4a1..1b803117ed9 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -1049,7 +1049,8 @@ static struct notifier_block dbg_cpu_pm_nb = { static void __init pm_init(void) { - cpu_pm_register_notifier(&dbg_cpu_pm_nb); + if (has_ossr) + cpu_pm_register_notifier(&dbg_cpu_pm_nb); } #else static inline void pm_init(void) diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 1315c4ccfa5..dbe21107945 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -153,6 +153,8 @@ THUMB( orr r7, #(1 << 30) ) @ HSCTLR.TE mrc p15, 4, r7, c14, c1, 0 @ CNTHCTL orr r7, r7, #3 @ PL1PCEN | PL1PCTEN mcr p15, 4, r7, c14, c1, 0 @ CNTHCTL + mov r7, #0 + mcrr p15, 4, r7, r7, c14 @ CNTVOFF 1: #endif diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 4fb074c446b..163b160c69e 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -73,6 +73,7 @@ void machine_crash_nonpanic_core(void *unused) crash_save_cpu(®s, smp_processor_id()); flush_cache_all(); + set_cpu_online(smp_processor_id(), false); atomic_dec(&waiting_for_crash_ipi); while (1) cpu_relax(); diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 1e9be5d25e5..7e137873083 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -24,6 +24,7 @@ #include <asm/sections.h> #include <asm/smp_plat.h> #include <asm/unwind.h> +#include <asm/opcodes.h> #ifdef CONFIG_XIP_KERNEL /* @@ -60,6 +61,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, Elf32_Sym *sym; const char *symname; s32 offset; + u32 tmp; #ifdef CONFIG_THUMB2_KERNEL u32 upper, lower, sign, j1, j2; #endif @@ -95,7 +97,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: - offset = (*(u32 *)loc & 0x00ffffff) << 2; + offset = __mem_to_opcode_arm(*(u32 *)loc); + offset = (offset & 0x00ffffff) << 2; if (offset & 0x02000000) offset -= 0x04000000; @@ -111,9 +114,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, } offset >>= 2; + offset &= 0x00ffffff; - *(u32 *)loc &= 0xff000000; - *(u32 *)loc |= offset & 0x00ffffff; + *(u32 *)loc &= __opcode_to_mem_arm(0xff000000); + *(u32 *)loc |= __opcode_to_mem_arm(offset); break; case R_ARM_V4BX: @@ -121,8 +125,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, * other bits to re-code instruction as * MOV PC,Rm. */ - *(u32 *)loc &= 0xf000000f; - *(u32 *)loc |= 0x01a0f000; + *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f); + *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000); break; case R_ARM_PREL31: @@ -132,7 +136,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: - offset = *(u32 *)loc; + offset = tmp = __mem_to_opcode_arm(*(u32 *)loc); offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff); offset = (offset ^ 0x8000) - 0x8000; @@ -140,16 +144,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS) offset >>= 16; - *(u32 *)loc &= 0xfff0f000; - *(u32 *)loc |= ((offset & 0xf000) << 4) | - (offset & 0x0fff); + tmp &= 0xfff0f000; + tmp |= ((offset & 0xf000) << 4) | + (offset & 0x0fff); + + *(u32 *)loc = __opcode_to_mem_arm(tmp); break; #ifdef CONFIG_THUMB2_KERNEL case R_ARM_THM_CALL: case R_ARM_THM_JUMP24: - upper = *(u16 *)loc; - lower = *(u16 *)(loc + 2); + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); /* * 25 bit signed address range (Thumb-2 BL and B.W @@ -198,17 +204,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, sign = (offset >> 24) & 1; j1 = sign ^ (~(offset >> 23) & 1); j2 = sign ^ (~(offset >> 22) & 1); - *(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) | + upper = (u16)((upper & 0xf800) | (sign << 10) | ((offset >> 12) & 0x03ff)); - *(u16 *)(loc + 2) = (u16)((lower & 0xd000) | - (j1 << 13) | (j2 << 11) | - ((offset >> 1) & 0x07ff)); + lower = (u16)((lower & 0xd000) | + (j1 << 13) | (j2 << 11) | + ((offset >> 1) & 0x07ff)); + + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); break; case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: - upper = *(u16 *)loc; - lower = *(u16 *)(loc + 2); + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); /* * MOVT/MOVW instructions encoding in Thumb-2: @@ -229,12 +238,14 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS) offset >>= 16; - *(u16 *)loc = (u16)((upper & 0xfbf0) | - ((offset & 0xf000) >> 12) | - ((offset & 0x0800) >> 1)); - *(u16 *)(loc + 2) = (u16)((lower & 0x8f00) | - ((offset & 0x0700) << 4) | - (offset & 0x00ff)); + upper = (u16)((upper & 0xfbf0) | + ((offset & 0xf000) >> 12) | + ((offset & 0x0800) >> 1)); + lower = (u16)((lower & 0x8f00) | + ((offset & 0x0700) << 4) | + (offset & 0x00ff)); + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); break; #endif diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 8c3094d0f7b..3a9d627cab6 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -12,6 +12,7 @@ */ #define pr_fmt(fmt) "hw perfevents: " fmt +#include <linux/cpumask.h> #include <linux/kernel.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> @@ -53,7 +54,12 @@ armpmu_map_cache_event(const unsigned (*cache_map) static int armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config) { - int mapping = (*event_map)[config]; + int mapping; + + if (config >= PERF_COUNT_HW_MAX) + return -ENOENT; + + mapping = (*event_map)[config]; return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping; } @@ -81,6 +87,9 @@ armpmu_map_event(struct perf_event *event, return armpmu_map_cache_event(cache_map, config); case PERF_TYPE_RAW: return armpmu_map_raw_event(raw_event_mask, config); + default: + if (event->attr.type >= PERF_TYPE_MAX) + return armpmu_map_raw_event(raw_event_mask, config); } return -ENOENT; @@ -158,6 +167,8 @@ armpmu_stop(struct perf_event *event, int flags) struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; /* * ARM pmu always has to update the counter, so ignore * PERF_EF_UPDATE, see comments in armpmu_start(). @@ -174,6 +185,8 @@ static void armpmu_start(struct perf_event *event, int flags) struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; /* * ARM pmu always has to reprogram the period, so ignore * PERF_EF_RELOAD, see the comment below. @@ -201,6 +214,9 @@ armpmu_del(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; + armpmu_stop(event, PERF_EF_UPDATE); hw_events->events[idx] = NULL; clear_bit(idx, hw_events->used_mask); @@ -217,6 +233,10 @@ armpmu_add(struct perf_event *event, int flags) int idx; int err = 0; + /* An event following a process won't be stopped earlier */ + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return 0; + perf_pmu_disable(event->pmu); /* If we don't have a space for the counter then finish early. */ @@ -253,6 +273,9 @@ validate_event(struct pmu_hw_events *hw_events, struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu *leader_pmu = event->group_leader->pmu; + if (is_software_event(event)) + return 1; + if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) return 1; @@ -416,6 +439,10 @@ static int armpmu_event_init(struct perf_event *event) int err = 0; atomic_t *active_events = &armpmu->active_events; + if (event->cpu != -1 && + !cpumask_test_cpu(event->cpu, &armpmu->valid_cpus)) + return -ENOENT; + /* does not support taken branch sampling */ if (has_branch_stack(event)) return -EOPNOTSUPP; @@ -569,6 +596,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) return; } + perf_callchain_store(entry, regs->ARM_pc); tail = (struct frame_tail __user *)regs->ARM_fp - 1; while ((entry->nr < PERF_MAX_STACK_DEPTH) && diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 1f2740e3dbc..0b48a38e3cf 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -19,6 +19,7 @@ #define pr_fmt(fmt) "CPU PMU: " fmt #include <linux/bitmap.h> +#include <linux/cpu_pm.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/of.h> @@ -31,33 +32,36 @@ #include <asm/pmu.h> /* Set at runtime when we know what CPU type we are. */ -static struct arm_pmu *cpu_pmu; +static DEFINE_PER_CPU(struct arm_pmu *, cpu_pmu); static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events); static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask); static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events); +static DEFINE_PER_CPU(struct cpupmu_regs, cpu_pmu_regs); + /* * Despite the names, these two functions are CPU-specific and are used * by the OProfile/perf code. */ const char *perf_pmu_name(void) { - if (!cpu_pmu) + struct arm_pmu *pmu = per_cpu(cpu_pmu, 0); + if (!pmu) return NULL; - return cpu_pmu->name; + return pmu->name; } EXPORT_SYMBOL_GPL(perf_pmu_name); int perf_num_counters(void) { - int max_events = 0; + struct arm_pmu *pmu = per_cpu(cpu_pmu, 0); - if (cpu_pmu != NULL) - max_events = cpu_pmu->num_events; + if (!pmu) + return 0; - return max_events; + return pmu->num_events; } EXPORT_SYMBOL_GPL(perf_num_counters); @@ -75,11 +79,13 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu) { int i, irq, irqs; struct platform_device *pmu_device = cpu_pmu->plat_device; + int cpu = -1; irqs = min(pmu_device->num_resources, num_possible_cpus()); for (i = 0; i < irqs; ++i) { - if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs)) + cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus); + if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs)) continue; irq = platform_get_irq(pmu_device, i); if (irq >= 0) @@ -91,6 +97,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) { int i, err, irq, irqs; struct platform_device *pmu_device = cpu_pmu->plat_device; + int cpu = -1; if (!pmu_device) return -ENODEV; @@ -103,6 +110,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) for (i = 0; i < irqs; ++i) { err = 0; + cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus); irq = platform_get_irq(pmu_device, i); if (irq < 0) continue; @@ -112,7 +120,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) * assume that we're running on a uniprocessor machine and * continue. Otherwise, continue without this interrupt. */ - if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) { + if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) { pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n", irq, i); continue; @@ -126,7 +134,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) return err; } - cpumask_set_cpu(i, &cpu_pmu->active_irqs); + cpumask_set_cpu(cpu, &cpu_pmu->active_irqs); } return 0; @@ -135,7 +143,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) static void cpu_pmu_init(struct arm_pmu *cpu_pmu) { int cpu; - for_each_possible_cpu(cpu) { + for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) { struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu); events->events = per_cpu(hw_events, cpu); events->used_mask = per_cpu(used_mask, cpu); @@ -148,7 +156,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu) /* Ensure the PMU has sane values out of reset. */ if (cpu_pmu->reset) - on_each_cpu(cpu_pmu->reset, cpu_pmu, 1); + on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1); } /* @@ -160,21 +168,46 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu) static int __cpuinit cpu_pmu_notify(struct notifier_block *b, unsigned long action, void *hcpu) { + struct arm_pmu *pmu = per_cpu(cpu_pmu, (long)hcpu); + if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING) return NOTIFY_DONE; - if (cpu_pmu && cpu_pmu->reset) - cpu_pmu->reset(cpu_pmu); + if (pmu && pmu->reset) + pmu->reset(pmu); else return NOTIFY_DONE; return NOTIFY_OK; } +static int cpu_pmu_pm_notify(struct notifier_block *b, + unsigned long action, void *hcpu) +{ + int cpu = smp_processor_id(); + struct arm_pmu *pmu = per_cpu(cpu_pmu, cpu); + struct cpupmu_regs *pmuregs = &per_cpu(cpu_pmu_regs, cpu); + + if (!pmu) + return NOTIFY_DONE; + + if (action == CPU_PM_ENTER && pmu->save_regs) { + pmu->save_regs(pmu, pmuregs); + } else if (action == CPU_PM_EXIT && pmu->restore_regs) { + pmu->restore_regs(pmu, pmuregs); + } + + return NOTIFY_OK; +} + static struct notifier_block __cpuinitdata cpu_pmu_hotplug_notifier = { .notifier_call = cpu_pmu_notify, }; +static struct notifier_block __cpuinitdata cpu_pmu_pm_notifier = { + .notifier_call = cpu_pmu_pm_notify, +}; + /* * PMU platform driver and devicetree bindings. */ @@ -246,6 +279,9 @@ static int probe_current_pmu(struct arm_pmu *pmu) } } + /* assume PMU support all the CPUs in this case */ + cpumask_setall(&pmu->valid_cpus); + put_cpu(); return ret; } @@ -253,15 +289,10 @@ static int probe_current_pmu(struct arm_pmu *pmu) static int cpu_pmu_device_probe(struct platform_device *pdev) { const struct of_device_id *of_id; - int (*init_fn)(struct arm_pmu *); struct device_node *node = pdev->dev.of_node; struct arm_pmu *pmu; - int ret = -ENODEV; - - if (cpu_pmu) { - pr_info("attempt to register multiple PMU devices!"); - return -ENOSPC; - } + int ret = 0; + int cpu; pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL); if (!pmu) { @@ -270,8 +301,28 @@ static int cpu_pmu_device_probe(struct platform_device *pdev) } if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) { - init_fn = of_id->data; - ret = init_fn(pmu); + smp_call_func_t init_fn = (smp_call_func_t)of_id->data; + struct device_node *ncluster; + int cluster = -1; + cpumask_t sibling_mask; + + ncluster = of_parse_phandle(node, "cluster", 0); + if (ncluster) { + int len; + const u32 *hwid; + hwid = of_get_property(ncluster, "reg", &len); + if (hwid && len == 4) + cluster = be32_to_cpup(hwid); + } + /* set sibling mask to all cpu mask if socket is not specified */ + if (cluster == -1 || + cluster_to_logical_mask(cluster, &sibling_mask)) + cpumask_setall(&sibling_mask); + + smp_call_function_any(&sibling_mask, init_fn, pmu, 1); + + /* now set the valid_cpus after init */ + cpumask_copy(&pmu->valid_cpus, &sibling_mask); } else { ret = probe_current_pmu(pmu); } @@ -281,10 +332,12 @@ static int cpu_pmu_device_probe(struct platform_device *pdev) goto out_free; } - cpu_pmu = pmu; - cpu_pmu->plat_device = pdev; - cpu_pmu_init(cpu_pmu); - ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW); + for_each_cpu_mask(cpu, pmu->valid_cpus) + per_cpu(cpu_pmu, cpu) = pmu; + + pmu->plat_device = pdev; + cpu_pmu_init(pmu); + ret = armpmu_register(pmu, -1); if (!ret) return 0; @@ -313,9 +366,17 @@ static int __init register_pmu_driver(void) if (err) return err; + err = cpu_pm_register_notifier(&cpu_pmu_pm_notifier); + if (err) { + unregister_cpu_notifier(&cpu_pmu_hotplug_notifier); + return err; + } + err = platform_driver_register(&cpu_pmu_driver); - if (err) + if (err) { + cpu_pm_unregister_notifier(&cpu_pmu_pm_notifier); unregister_cpu_notifier(&cpu_pmu_hotplug_notifier); + } return err; } diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 039cffb053a..654db5030c3 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -950,6 +950,51 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu) } #endif +static void armv7pmu_save_regs(struct arm_pmu *cpu_pmu, + struct cpupmu_regs *regs) +{ + unsigned int cnt; + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (regs->pmc)); + if (!(regs->pmc & ARMV7_PMNC_E)) + return; + + asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (regs->pmcntenset)); + asm volatile("mrc p15, 0, %0, c9, c14, 0" : "=r" (regs->pmuseren)); + asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (regs->pmintenset)); + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (regs->pmxevtcnt[0])); + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) { + armv7_pmnc_select_counter(cnt); + asm volatile("mrc p15, 0, %0, c9, c13, 1" + : "=r"(regs->pmxevttype[cnt])); + asm volatile("mrc p15, 0, %0, c9, c13, 2" + : "=r"(regs->pmxevtcnt[cnt])); + } + return; +} + +static void armv7pmu_restore_regs(struct arm_pmu *cpu_pmu, + struct cpupmu_regs *regs) +{ + unsigned int cnt; + if (!(regs->pmc & ARMV7_PMNC_E)) + return; + + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (regs->pmcntenset)); + asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r" (regs->pmuseren)); + asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (regs->pmintenset)); + asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (regs->pmxevtcnt[0])); + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) { + armv7_pmnc_select_counter(cnt); + asm volatile("mcr p15, 0, %0, c9, c13, 1" + : : "r"(regs->pmxevttype[cnt])); + asm volatile("mcr p15, 0, %0, c9, c13, 2" + : : "r"(regs->pmxevtcnt[cnt])); + } + asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (regs->pmc)); +} + static void armv7pmu_enable_event(struct perf_event *event) { unsigned long flags; @@ -1223,6 +1268,8 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->start = armv7pmu_start; cpu_pmu->stop = armv7pmu_stop; cpu_pmu->reset = armv7pmu_reset; + cpu_pmu->save_regs = armv7pmu_save_regs; + cpu_pmu->restore_regs = armv7pmu_restore_regs; cpu_pmu->max_period = (1LLU << 32) - 1; }; @@ -1240,7 +1287,7 @@ static u32 armv7_read_num_pmnc_events(void) static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A8"; + cpu_pmu->name = "ARMv7_Cortex_A8"; cpu_pmu->map_event = armv7_a8_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1249,7 +1296,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A9"; + cpu_pmu->name = "ARMv7_Cortex_A9"; cpu_pmu->map_event = armv7_a9_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1258,7 +1305,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A5"; + cpu_pmu->name = "ARMv7_Cortex_A5"; cpu_pmu->map_event = armv7_a5_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1267,7 +1314,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A15"; + cpu_pmu->name = "ARMv7_Cortex_A15"; cpu_pmu->map_event = armv7_a15_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); cpu_pmu->set_event_filter = armv7pmu_set_event_filter; @@ -1277,7 +1324,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A7"; + cpu_pmu->name = "ARMv7_Cortex_A7"; cpu_pmu->map_event = armv7_a7_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); cpu_pmu->set_event_filter = armv7pmu_set_event_filter; diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 6e8931ccf13..ac4c2e5e17e 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -408,6 +408,7 @@ EXPORT_SYMBOL(dump_fpu); unsigned long get_wchan(struct task_struct *p) { struct stackframe frame; + unsigned long stack_page; int count = 0; if (!p || p == current || p->state == TASK_RUNNING) return 0; @@ -416,9 +417,11 @@ unsigned long get_wchan(struct task_struct *p) frame.sp = thread_saved_sp(p); frame.lr = 0; /* recovered from the stack */ frame.pc = thread_saved_pc(p); + stack_page = (unsigned long)task_stack_page(p); do { - int ret = unwind_frame(&frame); - if (ret < 0) + if (frame.sp < stack_page || + frame.sp >= stack_page + THREAD_SIZE || + unwind_frame(&frame) < 0) return 0; if (!in_sched_functions(frame.pc)) return frame.pc; @@ -433,10 +436,11 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } #ifdef CONFIG_MMU +#ifdef CONFIG_KUSER_HELPERS /* * The vectors page is always readable from user space for the - * atomic helpers and the signal restart code. Insert it into the - * gate_vma so that it is visible through ptrace and /proc/<pid>/mem. + * atomic helpers. Insert it into the gate_vma so that it is visible + * through ptrace and /proc/<pid>/mem. */ static struct vm_area_struct gate_vma = { .vm_start = 0xffff0000, @@ -465,9 +469,48 @@ int in_gate_area_no_mm(unsigned long addr) { return in_gate_area(NULL, addr); } +#define is_gate_vma(vma) ((vma) == &gate_vma) +#else +#define is_gate_vma(vma) 0 +#endif const char *arch_vma_name(struct vm_area_struct *vma) { - return (vma == &gate_vma) ? "[vectors]" : NULL; + return is_gate_vma(vma) ? "[vectors]" : + (vma->vm_mm && vma->vm_start == vma->vm_mm->context.sigpage) ? + "[sigpage]" : NULL; +} + +static struct page *signal_page; +extern struct page *get_signal_page(void); + +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + struct mm_struct *mm = current->mm; + unsigned long addr; + int ret; + + if (!signal_page) + signal_page = get_signal_page(); + if (!signal_page) + return -ENOMEM; + + down_write(&mm->mmap_sem); + addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0); + if (IS_ERR_VALUE(addr)) { + ret = addr; + goto up_fail; + } + + ret = install_special_mapping(mm, addr, PAGE_SIZE, + VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, + &signal_page); + + if (ret == 0) + mm->context.sigpage = addr; + + up_fail: + up_write(&mm->mmap_sem); + return ret; } #endif diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 6002fe06b12..1e839e0ed5b 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -544,6 +544,7 @@ void __init dump_machine_table(void) int __init arm_add_memory(phys_addr_t start, phys_addr_t size) { struct membank *bank = &meminfo.bank[meminfo.nr_banks]; + u64 aligned_start; if (meminfo.nr_banks >= NR_BANKS) { printk(KERN_CRIT "NR_BANKS too low, " @@ -556,10 +557,16 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) * Size is appropriately rounded down, start is rounded up. */ size -= start & ~PAGE_MASK; - bank->start = PAGE_ALIGN(start); + aligned_start = PAGE_ALIGN(start); -#ifndef CONFIG_ARM_LPAE - if (bank->start + size < bank->start) { +#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT + if (aligned_start > ULONG_MAX) { + printk(KERN_CRIT "Ignoring memory at 0x%08llx outside " + "32-bit physical address space\n", (long long)start); + return -EINVAL; + } + + if (aligned_start + size > ULONG_MAX) { printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in " "32-bit physical address space\n", (long long)start); /* @@ -567,10 +574,25 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB. * This means we lose a page after masking. */ - size = ULONG_MAX - bank->start; + size = ULONG_MAX - aligned_start; } #endif + if (aligned_start < PHYS_OFFSET) { + if (aligned_start + size <= PHYS_OFFSET) { + pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n", + aligned_start, aligned_start + size); + return -EINVAL; + } + + pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n", + aligned_start, (u64)PHYS_OFFSET); + + size -= PHYS_OFFSET - aligned_start; + aligned_start = PHYS_OFFSET; + } + + bank->start = aligned_start; bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1); /* diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 296786bdbb7..3c23086dc8e 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -8,6 +8,7 @@ * published by the Free Software Foundation. */ #include <linux/errno.h> +#include <linux/random.h> #include <linux/signal.h> #include <linux/personality.h> #include <linux/uaccess.h> @@ -15,35 +16,14 @@ #include <asm/elf.h> #include <asm/cacheflush.h> +#include <asm/traps.h> #include <asm/ucontext.h> #include <asm/unistd.h> #include <asm/vfp.h> -#include "signal.h" +extern const unsigned long sigreturn_codes[7]; -/* - * For ARM syscalls, we encode the syscall number into the instruction. - */ -#define SWI_SYS_SIGRETURN (0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)) -#define SWI_SYS_RT_SIGRETURN (0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)) - -/* - * With EABI, the syscall number has to be loaded into r7. - */ -#define MOV_R7_NR_SIGRETURN (0xe3a07000 | (__NR_sigreturn - __NR_SYSCALL_BASE)) -#define MOV_R7_NR_RT_SIGRETURN (0xe3a07000 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE)) - -/* - * For Thumb syscalls, we pass the syscall number via r7. We therefore - * need two 16-bit instructions. - */ -#define SWI_THUMB_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE)) -#define SWI_THUMB_RT_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE)) - -const unsigned long sigreturn_codes[7] = { - MOV_R7_NR_SIGRETURN, SWI_SYS_SIGRETURN, SWI_THUMB_SIGRETURN, - MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN, -}; +static unsigned long signal_return_offset; #ifdef CONFIG_CRUNCH static int preserve_crunch_context(struct crunch_sigframe __user *frame) @@ -396,13 +376,19 @@ setup_return(struct pt_regs *regs, struct ksignal *ksig, __put_user(sigreturn_codes[idx+1], rc+1)) return 1; +#ifdef CONFIG_MMU if (cpsr & MODE32_BIT) { + struct mm_struct *mm = current->mm; /* - * 32-bit code can use the new high-page - * signal return code support. + * 32-bit code can use the signal return page + * except when the MPU has protected the vectors + * page from PL0 */ - retcode = KERN_SIGRETURN_CODE + (idx << 2) + thumb; - } else { + retcode = mm->context.sigpage + signal_return_offset + + (idx << 2) + thumb; + } else +#endif + { /* * Ensure that the instruction cache sees * the return code written onto the stack. @@ -603,3 +589,33 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) } while (thread_flags & _TIF_WORK_MASK); return 0; } + +struct page *get_signal_page(void) +{ + unsigned long ptr; + unsigned offset; + struct page *page; + void *addr; + + page = alloc_pages(GFP_KERNEL, 0); + + if (!page) + return NULL; + + addr = page_address(page); + + /* Give the signal return code some randomness */ + offset = 0x200 + (get_random_int() & 0x7fc); + signal_return_offset = offset; + + /* + * Copy signal return handlers into the vector page, and + * set sigreturn to be a pointer to these. + */ + memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes)); + + ptr = (unsigned long)addr + offset; + flush_icache_range(ptr, ptr + sizeof(sigreturn_codes)); + + return page; +} diff --git a/arch/arm/kernel/signal.h b/arch/arm/kernel/signal.h deleted file mode 100644 index 5ff067b7c75..00000000000 --- a/arch/arm/kernel/signal.h +++ /dev/null @@ -1,12 +0,0 @@ -/* - * linux/arch/arm/kernel/signal.h - * - * Copyright (C) 2005-2009 Russell King. - * - * 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 - * published by the Free Software Foundation. - */ -#define KERN_SIGRETURN_CODE (CONFIG_VECTORS_BASE + 0x00000500) - -extern const unsigned long sigreturn_codes[7]; diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S new file mode 100644 index 00000000000..3c5d0f2170f --- /dev/null +++ b/arch/arm/kernel/sigreturn_codes.S @@ -0,0 +1,80 @@ +/* + * sigreturn_codes.S - code sinpets for sigreturn syscalls + * + * Created by: Victor Kamensky, 2013-08-13 + * Copyright: (C) 2013 Linaro Limited + * + * 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 + * published by the Free Software Foundation. + * + * 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 <asm/unistd.h> + +/* + * For ARM syscalls, we encode the syscall number into the instruction. + * With EABI, the syscall number has to be loaded into r7. As result + * ARM syscall sequence snippet will have move and svc in .arm encoding + * + * For Thumb syscalls, we pass the syscall number via r7. We therefore + * need two 16-bit instructions in .thumb encoding + * + * Please note sigreturn_codes code are not executed in place. Instead + * they just copied by kernel into appropriate places. Code inside of + * arch/arm/kernel/signal.c is very sensitive to layout of these code + * snippets. + */ + +#if __LINUX_ARM_ARCH__ <= 4 + /* + * Note we manually set minimally required arch that supports + * required thumb opcodes for early arch versions. It is OK + * for this file to be used in combination with other + * lower arch variants, since these code snippets are only + * used as input data. + */ + .arch armv4t +#endif + + .section .rodata + .global sigreturn_codes + .type sigreturn_codes, #object + + .arm + +sigreturn_codes: + + /* ARM sigreturn syscall code snippet */ + mov r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE) + + /* Thumb sigreturn syscall code snippet */ + .thumb + movs r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* ARM sigreturn_rt syscall code snippet */ + .arm + mov r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE) + + /* Thumb sigreturn_rt syscall code snippet */ + .thumb + movs r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* + * Note on addtional space: setup_return in signal.c + * algorithm uses two words copy regardless whether + * it is thumb case or not, so we need additional + * word after real last entry. + */ + .arm + .space 4 + + .size sigreturn_codes, . - sigreturn_codes diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index b5c1e636ed8..baf4d28213a 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -81,6 +81,7 @@ ENDPROC(cpu_resume_after_mmu) .data .align ENTRY(cpu_resume) +ARM_BE8(setend be) @ ensure we are in BE mode #ifdef CONFIG_SMP mov r1, #0 @ fall-back logical index for UP ALT_SMP(mrc p15, 0, r0, c0, c0, 5) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 5919eb451bb..dc2843f337a 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -46,6 +46,9 @@ #include <asm/virt.h> #include <asm/mach/arch.h> +#define CREATE_TRACE_POINTS +#include <trace/events/arm-ipi.h> + /* * as from 2.5, kernels no longer have an init_tasks structure * so we need some other way of telling a new secondary core @@ -57,7 +60,7 @@ struct secondary_data secondary_data; * control for which core is the next to come out of the secondary * boot "holding pen" */ -volatile int __cpuinitdata pen_release = -1; +volatile int pen_release = -1; enum ipi_msg_type { IPI_WAKEUP, @@ -66,6 +69,7 @@ enum ipi_msg_type { IPI_CALL_FUNC, IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, + IPI_COMPLETION, }; static DECLARE_COMPLETION(cpu_running); @@ -463,6 +467,7 @@ static const char *ipi_types[NR_IPI] = { S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_COMPLETION, "completion interrupts"), }; void show_ipi_list(struct seq_file *p, int prec) @@ -588,6 +593,19 @@ static void ipi_cpu_stop(unsigned int cpu) cpu_relax(); } +static DEFINE_PER_CPU(struct completion *, cpu_completion); + +int register_ipi_completion(struct completion *completion, int cpu) +{ + per_cpu(cpu_completion, cpu) = completion; + return IPI_COMPLETION; +} + +static void ipi_complete(unsigned int cpu) +{ + complete(per_cpu(cpu_completion, cpu)); +} + /* * Main handler for inter-processor interrupts */ @@ -604,6 +622,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) if (ipinr < NR_IPI) __inc_irq_stat(cpu, ipi_irqs[ipinr]); + trace_arm_ipi_entry(ipinr); switch (ipinr) { case IPI_WAKEUP: break; @@ -638,11 +657,18 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; + case IPI_COMPLETION: + irq_enter(); + ipi_complete(cpu); + irq_exit(); + break; + default: printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); break; } + trace_arm_ipi_exit(ipinr); set_irq_regs(old_regs); } diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 5bc1a63284e..1aafa0d785e 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -28,7 +28,7 @@ */ unsigned int __init scu_get_core_count(void __iomem *scu_base) { - unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG); + unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG); return (ncores & 0x03) + 1; } @@ -42,19 +42,19 @@ void scu_enable(void __iomem *scu_base) #ifdef CONFIG_ARM_ERRATA_764369 /* Cortex-A9 only */ if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) { - scu_ctrl = __raw_readl(scu_base + 0x30); + scu_ctrl = readl_relaxed(scu_base + 0x30); if (!(scu_ctrl & 1)) - __raw_writel(scu_ctrl | 0x1, scu_base + 0x30); + writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30); } #endif - scu_ctrl = __raw_readl(scu_base + SCU_CTRL); + scu_ctrl = readl_relaxed(scu_base + SCU_CTRL); /* already enabled? */ if (scu_ctrl & 1) return; scu_ctrl |= 1; - __raw_writel(scu_ctrl, scu_base + SCU_CTRL); + writel_relaxed(scu_ctrl, scu_base + SCU_CTRL); /* * Ensure that the data accessed by CPU0 before the SCU was @@ -80,9 +80,9 @@ int scu_power_mode(void __iomem *scu_base, unsigned int mode) if (mode > 3 || mode == 1 || cpu > 3) return -EINVAL; - val = __raw_readb(scu_base + SCU_CPU_STATUS + cpu) & ~0x03; + val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu) & ~0x03; val |= mode; - __raw_writeb(val, scu_base + SCU_CPU_STATUS + cpu); + writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu); return 0; } diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index 9a52a07aa40..a98b62dca2f 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -103,7 +103,7 @@ static void broadcast_tlb_a15_erratum(void) static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) { - int cpu, this_cpu; + int this_cpu; cpumask_t mask = { CPU_BITS_NONE }; if (!erratum_a15_798181()) @@ -111,21 +111,7 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) dummy_flush_tlb_a15_erratum(); this_cpu = get_cpu(); - for_each_online_cpu(cpu) { - if (cpu == this_cpu) - continue; - /* - * We only need to send an IPI if the other CPUs are running - * the same ASID as the one being invalidated. There is no - * need for locking around the active_asids check since the - * switch_mm() function has at least one dmb() (as required by - * this workaround) in case a context switch happens on - * another CPU after the condition below. - */ - if (atomic64_read(&mm->context.id) == - atomic64_read(&per_cpu(active_asids, cpu))) - cpumask_set_cpu(cpu, &mask); - } + a15_erratum_get_cpumask(this_cpu, mm, &mask); smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1); put_cpu(); } diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 90525d9d290..4971ccf012c 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -45,7 +45,7 @@ static void twd_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_PERIODIC: ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_PERIODIC; - __raw_writel(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), + writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), twd_base + TWD_TIMER_LOAD); break; case CLOCK_EVT_MODE_ONESHOT: @@ -58,18 +58,18 @@ static void twd_set_mode(enum clock_event_mode mode, ctrl = 0; } - __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); } static int twd_set_next_event(unsigned long evt, struct clock_event_device *unused) { - unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL); + unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL); ctrl |= TWD_TIMER_CONTROL_ENABLE; - __raw_writel(evt, twd_base + TWD_TIMER_COUNTER); - __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); return 0; } @@ -82,8 +82,8 @@ static int twd_set_next_event(unsigned long evt, */ static int twd_timer_ack(void) { - if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) { - __raw_writel(1, twd_base + TWD_TIMER_INTSTAT); + if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) { + writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT); return 1; } @@ -120,7 +120,7 @@ static int twd_rate_change(struct notifier_block *nb, * changing cpu. */ if (flags == POST_RATE_CHANGE) - smp_call_function(twd_update_frequency, + on_each_cpu(twd_update_frequency, (void *)&cnd->new_rate, 1); return NOTIFY_OK; @@ -209,15 +209,15 @@ static void __cpuinit twd_calibrate_rate(void) waitjiffies += 5; /* enable, no interrupt or reload */ - __raw_writel(0x1, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL); /* maximum value */ - __raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); while (get_jiffies_64() < waitjiffies) udelay(10); - count = __raw_readl(twd_base + TWD_TIMER_COUNTER); + count = readl_relaxed(twd_base + TWD_TIMER_COUNTER); twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5); @@ -275,7 +275,7 @@ static int __cpuinit twd_timer_setup(struct clock_event_device *clk) * bother with the below. */ if (per_cpu(percpu_setup_called, cpu)) { - __raw_writel(0, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); clockevents_register_device(*__this_cpu_ptr(twd_evt)); enable_percpu_irq(clk->irq, 0); return 0; @@ -288,7 +288,7 @@ static int __cpuinit twd_timer_setup(struct clock_event_device *clk) * The following is done once per CPU the first time .setup() is * called. */ - __raw_writel(0, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); clk->name = "local_timer"; clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT | diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index 00f79e59985..af4e8c8a542 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -31,7 +31,7 @@ int notrace unwind_frame(struct stackframe *frame) high = ALIGN(low, THREAD_SIZE); /* check current frame pointer is within bounds */ - if (fp < (low + 12) || fp + 4 >= high) + if (fp < low + 12 || fp > high - 4) return -EINVAL; /* restore the registers from the stack frame */ diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index c5a59546a25..677da58d9e8 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <asm/cputype.h> +#include <asm/smp_plat.h> #include <asm/topology.h> /* @@ -289,6 +290,140 @@ void store_cpu_topology(unsigned int cpuid) cpu_topology[cpuid].socket_id, mpidr); } + +#ifdef CONFIG_SCHED_HMP + +static const char * const little_cores[] = { + "arm,cortex-a7", + NULL, +}; + +static bool is_little_cpu(struct device_node *cn) +{ + const char * const *lc; + for (lc = little_cores; *lc; lc++) + if (of_device_is_compatible(cn, *lc)) + return true; + return false; +} + +void __init arch_get_fast_and_slow_cpus(struct cpumask *fast, + struct cpumask *slow) +{ + struct device_node *cn = NULL; + int cpu; + + cpumask_clear(fast); + cpumask_clear(slow); + + /* + * Use the config options if they are given. This helps testing + * HMP scheduling on systems without a big.LITTLE architecture. + */ + if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) { + if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast)) + WARN(1, "Failed to parse HMP fast cpu mask!\n"); + if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow)) + WARN(1, "Failed to parse HMP slow cpu mask!\n"); + return; + } + + /* + * Else, parse device tree for little cores. + */ + while ((cn = of_find_node_by_type(cn, "cpu"))) { + + const u32 *mpidr; + int len; + + mpidr = of_get_property(cn, "reg", &len); + if (!mpidr || len != 4) { + pr_err("* %s missing reg property\n", cn->full_name); + continue; + } + + cpu = get_logical_index(be32_to_cpup(mpidr)); + if (cpu == -EINVAL) { + pr_err("couldn't get logical index for mpidr %x\n", + be32_to_cpup(mpidr)); + break; + } + + if (is_little_cpu(cn)) + cpumask_set_cpu(cpu, slow); + else + cpumask_set_cpu(cpu, fast); + } + + if (!cpumask_empty(fast) && !cpumask_empty(slow)) + return; + + /* + * We didn't find both big and little cores so let's call all cores + * fast as this will keep the system running, with all cores being + * treated equal. + */ + cpumask_setall(fast); + cpumask_clear(slow); +} + +struct cpumask hmp_slow_cpu_mask; + +void __init arch_get_hmp_domains(struct list_head *hmp_domains_list) +{ + struct cpumask hmp_fast_cpu_mask; + struct hmp_domain *domain; + + arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask); + + /* + * Initialize hmp_domains + * Must be ordered with respect to compute capacity. + * Fastest domain at head of list. + */ + if(!cpumask_empty(&hmp_slow_cpu_mask)) { + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask); + cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus); + list_add(&domain->hmp_domains, hmp_domains_list); + } + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask); + cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus); + list_add(&domain->hmp_domains, hmp_domains_list); +} +#endif /* CONFIG_SCHED_HMP */ + + +/* + * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster + * @socket_id: cluster HW identifier + * @cluster_mask: the cpumask location to be initialized, modified by the + * function only if return value == 0 + * + * Return: + * + * 0 on success + * -EINVAL if cluster_mask is NULL or there is no record matching socket_id + */ +int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask) +{ + int cpu; + + if (!cluster_mask) + return -EINVAL; + + for_each_online_cpu(cpu) + if (socket_id == topology_physical_package_id(cpu)) { + cpumask_copy(cluster_mask, topology_core_cpumask(cpu)); + return 0; + } + + return -EINVAL; +} + /* * init_cpu_topology is called at boot when only one cpu is running * which prevent simultaneous write access to cpu_topology array diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 18b32e8e449..b4fd850c34b 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -34,10 +34,15 @@ #include <asm/unwind.h> #include <asm/tls.h> #include <asm/system_misc.h> - -#include "signal.h" - -static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" }; +#include <asm/opcodes.h> + +static const char *handler[]= { + "prefetch abort", + "data abort", + "address exception", + "interrupt", + "undefined instruction", +}; void *vectors_page; @@ -343,15 +348,17 @@ void arm_notify_die(const char *str, struct pt_regs *regs, int is_valid_bugaddr(unsigned long pc) { #ifdef CONFIG_THUMB2_KERNEL - unsigned short bkpt; + u16 bkpt; + u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE); #else - unsigned long bkpt; + u32 bkpt; + u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE); #endif if (probe_kernel_address((unsigned *)pc, bkpt)) return 0; - return bkpt == BUG_INSTR_VALUE; + return bkpt == insn; } #endif @@ -404,25 +411,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if (processor_mode(regs) == SVC_MODE) { #ifdef CONFIG_THUMB2_KERNEL if (thumb_mode(regs)) { - instr = ((u16 *)pc)[0]; + instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]); if (is_wide_instruction(instr)) { - instr <<= 16; - instr |= ((u16 *)pc)[1]; + u16 inst2; + inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]); + instr = __opcode_thumb32_compose(instr, inst2); } } else #endif - instr = *(u32 *) pc; + instr = __mem_to_opcode_arm(*(u32 *) pc); } else if (thumb_mode(regs)) { if (get_user(instr, (u16 __user *)pc)) goto die_sig; + instr = __mem_to_opcode_thumb16(instr); if (is_wide_instruction(instr)) { unsigned int instr2; if (get_user(instr2, (u16 __user *)pc+1)) goto die_sig; - instr <<= 16; - instr |= instr2; + instr2 = __mem_to_opcode_thumb16(instr2); + instr = __opcode_thumb32_compose(instr, instr2); } } else if (get_user(instr, (u32 __user *)pc)) { + instr = __mem_to_opcode_arm(instr); goto die_sig; } @@ -800,47 +810,55 @@ void __init trap_init(void) return; } -static void __init kuser_get_tls_init(unsigned long vectors) +#ifdef CONFIG_KUSER_HELPERS +static void __init kuser_init(void *vectors) { + extern char __kuser_helper_start[], __kuser_helper_end[]; + int kuser_sz = __kuser_helper_end - __kuser_helper_start; + + memcpy(vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz); + /* * vectors + 0xfe0 = __kuser_get_tls * vectors + 0xfe8 = hardware TLS instruction at 0xffff0fe8 */ if (tls_emu || has_tls_reg) - memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4); + memcpy(vectors + 0xfe0, vectors + 0xfe8, 4); } +#else +static void __init kuser_init(void *vectors) +{ +} +#endif void __init early_trap_init(void *vectors_base) { unsigned long vectors = (unsigned long)vectors_base; extern char __stubs_start[], __stubs_end[]; extern char __vectors_start[], __vectors_end[]; - extern char __kuser_helper_start[], __kuser_helper_end[]; - int kuser_sz = __kuser_helper_end - __kuser_helper_start; + unsigned i; vectors_page = vectors_base; /* + * Poison the vectors page with an undefined instruction. This + * instruction is chosen to be undefined for both ARM and Thumb + * ISAs. The Thumb version is an undefined instruction with a + * branch back to the undefined instruction. + */ + for (i = 0; i < PAGE_SIZE / sizeof(u32); i++) + ((u32 *)vectors_base)[i] = 0xe7fddef1; + + /* * Copy the vectors, stubs and kuser helpers (in entry-armv.S) * into the vector page, mapped at 0xffff0000, and ensure these * are visible to the instruction stream. */ memcpy((void *)vectors, __vectors_start, __vectors_end - __vectors_start); - memcpy((void *)vectors + 0x200, __stubs_start, __stubs_end - __stubs_start); - memcpy((void *)vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz); + memcpy((void *)vectors + 0x1000, __stubs_start, __stubs_end - __stubs_start); - /* - * Do processor specific fixups for the kuser helpers - */ - kuser_get_tls_init(vectors); - - /* - * Copy signal return handlers into the vector page, and - * set sigreturn to be a pointer to these. - */ - memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE), - sigreturn_codes, sizeof(sigreturn_codes)); + kuser_init(vectors_base); - flush_icache_range(vectors, vectors + PAGE_SIZE); + flush_icache_range(vectors, vectors + PAGE_SIZE * 2); modify_domain(DOMAIN_USER, DOMAIN_CLIENT); } diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index a871b8e00fc..33f2ea32f5a 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -152,6 +152,23 @@ SECTIONS . = ALIGN(PAGE_SIZE); __init_begin = .; #endif + /* + * The vectors and stubs are relocatable code, and the + * only thing that matters is their relative offsets + */ + __vectors_start = .; + .vectors 0 : AT(__vectors_start) { + *(.vectors) + } + . = __vectors_start + SIZEOF(.vectors); + __vectors_end = .; + + __stubs_start = .; + .stubs 0x1000 : AT(__stubs_start) { + *(.stubs) + } + . = __stubs_start + SIZEOF(.stubs); + __stubs_end = .; INIT_TEXT_SECTION(8) .exit.text : { diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index ef1703b9587..1d55afe7fd4 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -17,6 +17,7 @@ */ #include <linux/cpu.h> +#include <linux/cpu_pm.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> @@ -835,6 +836,33 @@ static struct notifier_block hyp_init_cpu_nb = { .notifier_call = hyp_init_cpu_notify, }; +#ifdef CONFIG_CPU_PM +static int hyp_init_cpu_pm_notifier(struct notifier_block *self, + unsigned long cmd, + void *v) +{ + if (cmd == CPU_PM_EXIT) { + cpu_init_hyp_mode(NULL); + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + +static struct notifier_block hyp_init_cpu_pm_nb = { + .notifier_call = hyp_init_cpu_pm_notifier, +}; + +static void __init hyp_cpu_pm_init(void) +{ + cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); +} +#else +static inline void hyp_cpu_pm_init(void) +{ +} +#endif + /** * Inits Hyp-mode on all online CPUs */ @@ -995,6 +1023,8 @@ int kvm_arch_init(void *opaque) goto out_err; } + hyp_cpu_pm_init(); + kvm_coproc_table_init(); return 0; out_err: diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 8eea97be1ed..db9cf692d4d 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -146,7 +146,11 @@ static bool pm_fake(struct kvm_vcpu *vcpu, #define access_pmintenclr pm_fake /* Architected CP15 registers. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. */ static const struct coproc_reg cp15_regs[] = { /* CSSELR: swapped by interrupt.S. */ @@ -154,8 +158,8 @@ static const struct coproc_reg cp15_regs[] = { NULL, reset_unknown, c0_CSSELR }, /* TTBR0/TTBR1: swapped by interrupt.S. */ - { CRm( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 }, - { CRm( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 }, + { CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 }, + { CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 }, /* TTBCR: swapped by interrupt.S. */ { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32, @@ -180,6 +184,10 @@ static const struct coproc_reg cp15_regs[] = { NULL, reset_unknown, c6_DFAR }, { CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32, NULL, reset_unknown, c6_IFAR }, + + /* PAR swapped by interrupt.S */ + { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, + /* * DC{C,I,CI}SW operations: */ @@ -395,12 +403,13 @@ static bool index_to_params(u64 id, struct coproc_params *params) | KVM_REG_ARM_OPC1_MASK)) return false; params->is_64bit = true; - params->CRm = ((id & KVM_REG_ARM_CRM_MASK) + /* CRm to CRn: see cp15_to_index for details */ + params->CRn = ((id & KVM_REG_ARM_CRM_MASK) >> KVM_REG_ARM_CRM_SHIFT); params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) >> KVM_REG_ARM_OPC1_SHIFT); params->Op2 = 0; - params->CRn = 0; + params->CRm = 0; return true; default: return false; @@ -894,7 +903,14 @@ static u64 cp15_to_index(const struct coproc_reg *reg) if (reg->is_64) { val |= KVM_REG_SIZE_U64; val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); - val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT); + /* + * CRn always denotes the primary coproc. reg. nr. for the + * in-kernel representation, but the user space API uses the + * CRm for the encoding, because it is modelled after the + * MRRC/MCRR instructions: see the ARM ARM rev. c page + * B3-1445 + */ + val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT); } else { val |= KVM_REG_SIZE_U32; val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h index b7301d3e479..0461d5c8d3d 100644 --- a/arch/arm/kvm/coproc.h +++ b/arch/arm/kvm/coproc.h @@ -135,6 +135,8 @@ static inline int cmp_reg(const struct coproc_reg *i1, return -1; if (i1->CRn != i2->CRn) return i1->CRn - i2->CRn; + if (i1->is_64 != i2->is_64) + return i2->is_64 - i1->is_64; if (i1->CRm != i2->CRm) return i1->CRm - i2->CRm; if (i1->Op1 != i2->Op1) @@ -145,6 +147,7 @@ static inline int cmp_reg(const struct coproc_reg *i1, #define CRn(_x) .CRn = _x #define CRm(_x) .CRm = _x +#define CRm64(_x) .CRn = _x, .CRm = 0 #define Op1(_x) .Op1 = _x #define Op2(_x) .Op2 = _x #define is64 .is_64 = true diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c index 685063a6d0c..cf93472b9dd 100644 --- a/arch/arm/kvm/coproc_a15.c +++ b/arch/arm/kvm/coproc_a15.c @@ -114,7 +114,11 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu, /* * A15-specific CP15 registers. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. */ static const struct coproc_reg a15_regs[] = { /* MPIDR: we use VMPIDR for guest access. */ diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index f7793df62f5..16cd4ba5d7f 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -49,6 +49,7 @@ __kvm_hyp_code_start: ENTRY(__kvm_tlb_flush_vmid_ipa) push {r2, r3} + dsb ishst add r0, r0, #KVM_VTTBR ldrd r2, r3, [r0] mcrr p15, 6, r2, r3, c2 @ Write VTTBR @@ -291,6 +292,7 @@ THUMB( orr r2, r2, #PSR_T_BIT ) ldr r2, =BSYM(panic) msr ELR_hyp, r2 ldr r0, =\panic_str + clrex @ Clear exclusive monitor eret .endm @@ -414,6 +416,10 @@ guest_trap: mrcne p15, 4, r2, c6, c0, 4 @ HPFAR bne 3f + /* Preserve PAR */ + mrrc p15, 0, r0, r1, c7 @ PAR + push {r0, r1} + /* Resolve IPA using the xFAR */ mcr p15, 0, r2, c7, c8, 0 @ ATS1CPR isb @@ -424,13 +430,20 @@ guest_trap: lsl r2, r2, #4 orr r2, r2, r1, lsl #24 + /* Restore PAR */ + pop {r0, r1} + mcrr p15, 0, r0, r1, c7 @ PAR + 3: load_vcpu @ Load VCPU pointer to r0 str r2, [r0, #VCPU_HPFAR] 1: mov r1, #ARM_EXCEPTION_HVC b __kvm_vcpu_return -4: pop {r0, r1, r2} @ Failed translation, return to guest +4: pop {r0, r1} @ Failed translation, return to guest + mcrr p15, 0, r0, r1, c7 @ PAR + clrex + pop {r0, r1, r2} eret /* @@ -456,6 +469,7 @@ switch_to_guest_vfp: pop {r3-r7} pop {r0-r2} + clrex eret #endif diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 3c8f2f0b4c5..6f18695a09c 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -302,11 +302,14 @@ vcpu .req r0 @ vcpu pointer always in r0 .endif mrc p15, 0, r2, c14, c1, 0 @ CNTKCTL + mrrc p15, 0, r4, r5, c7 @ PAR .if \store_to_vcpu == 0 - push {r2} + push {r2,r4-r5} .else str r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)] + add r12, vcpu, #CP15_OFFSET(c7_PAR) + strd r4, r5, [r12] .endif .endm @@ -319,12 +322,15 @@ vcpu .req r0 @ vcpu pointer always in r0 */ .macro write_cp15_state read_from_vcpu .if \read_from_vcpu == 0 - pop {r2} + pop {r2,r4-r5} .else ldr r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)] + add r12, vcpu, #CP15_OFFSET(c7_PAR) + ldrd r4, r5, [r12] .endif mcr p15, 0, r2, c14, c1, 0 @ CNTKCTL + mcrr p15, 0, r4, r5, c7 @ PAR .if \read_from_vcpu == 0 pop {r2-r12} @@ -497,6 +503,10 @@ vcpu .req r0 @ vcpu pointer always in r0 add r5, vcpu, r4 strd r2, r3, [r5] + @ Ensure host CNTVCT == CNTPCT + mov r2, #0 + mcrr p15, 4, r2, r2, c14 @ CNTVOFF + 1: #endif @ Allow physical timer/counter access for the host diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 84ba67b982c..e04613906f1 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -313,6 +313,17 @@ out: return err; } +static phys_addr_t kvm_kaddr_to_phys(void *kaddr) +{ + if (!is_vmalloc_addr(kaddr)) { + BUG_ON(!virt_addr_valid(kaddr)); + return __pa(kaddr); + } else { + return page_to_phys(vmalloc_to_page(kaddr)) + + offset_in_page(kaddr); + } +} + /** * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range @@ -324,16 +335,27 @@ out: */ int create_hyp_mappings(void *from, void *to) { - unsigned long phys_addr = virt_to_phys(from); + phys_addr_t phys_addr; + unsigned long virt_addr; unsigned long start = KERN_TO_HYP((unsigned long)from); unsigned long end = KERN_TO_HYP((unsigned long)to); - /* Check for a valid kernel memory mapping */ - if (!virt_addr_valid(from) || !virt_addr_valid(to - 1)) - return -EINVAL; + start = start & PAGE_MASK; + end = PAGE_ALIGN(end); - return __create_hyp_mappings(hyp_pgd, start, end, - __phys_to_pfn(phys_addr), PAGE_HYP); + for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) { + int err; + + phys_addr = kvm_kaddr_to_phys(from + virt_addr - start); + err = __create_hyp_mappings(hyp_pgd, virt_addr, + virt_addr + PAGE_SIZE, + __phys_to_pfn(phys_addr), + PAGE_HYP); + if (err) + return err; + } + + return 0; } /** diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile index 788562dccb4..c336efdf8f1 100644 --- a/arch/arm/mach-at91/Makefile +++ b/arch/arm/mach-at91/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux kernel. # -obj-y := irq.o gpio.o setup.o +obj-y := irq.o gpio.o setup.o sysirq_mask.o obj-m := obj-n := obj- := diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c index a8ce24538da..cdb1fb695ed 100644 --- a/arch/arm/mach-at91/at91sam9260.c +++ b/arch/arm/mach-at91/at91sam9260.c @@ -351,6 +351,8 @@ static void __init at91sam9260_initialize(void) at91_extern_irq = (1 << AT91SAM9260_ID_IRQ0) | (1 << AT91SAM9260_ID_IRQ1) | (1 << AT91SAM9260_ID_IRQ2); + at91_sysirq_mask_rtt(AT91SAM9260_BASE_RTT); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9260_gpio, 3); } diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c index 25efb5ac30f..7c9d2ea5bb8 100644 --- a/arch/arm/mach-at91/at91sam9261.c +++ b/arch/arm/mach-at91/at91sam9261.c @@ -293,6 +293,8 @@ static void __init at91sam9261_initialize(void) at91_extern_irq = (1 << AT91SAM9261_ID_IRQ0) | (1 << AT91SAM9261_ID_IRQ1) | (1 << AT91SAM9261_ID_IRQ2); + at91_sysirq_mask_rtt(AT91SAM9261_BASE_RTT); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9261_gpio, 3); } diff --git a/arch/arm/mach-at91/at91sam9263.c b/arch/arm/mach-at91/at91sam9263.c index f44ffd2105a..c6b2f477c71 100644 --- a/arch/arm/mach-at91/at91sam9263.c +++ b/arch/arm/mach-at91/at91sam9263.c @@ -329,6 +329,9 @@ static void __init at91sam9263_initialize(void) arm_pm_restart = at91sam9_alt_restart; at91_extern_irq = (1 << AT91SAM9263_ID_IRQ0) | (1 << AT91SAM9263_ID_IRQ1); + at91_sysirq_mask_rtt(AT91SAM9263_BASE_RTT0); + at91_sysirq_mask_rtt(AT91SAM9263_BASE_RTT1); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9263_gpio, 5); } diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c index 8b7fce06765..e381fa12501 100644 --- a/arch/arm/mach-at91/at91sam9g45.c +++ b/arch/arm/mach-at91/at91sam9g45.c @@ -376,6 +376,9 @@ static void __init at91sam9g45_initialize(void) arm_pm_restart = at91sam9g45_restart; at91_extern_irq = (1 << AT91SAM9G45_ID_IRQ0); + at91_sysirq_mask_rtc(AT91SAM9G45_BASE_RTC); + at91_sysirq_mask_rtt(AT91SAM9G45_BASE_RTT); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9g45_gpio, 5); } diff --git a/arch/arm/mach-at91/at91sam9n12.c b/arch/arm/mach-at91/at91sam9n12.c index c7d670d1180..4d6001c355f 100644 --- a/arch/arm/mach-at91/at91sam9n12.c +++ b/arch/arm/mach-at91/at91sam9n12.c @@ -223,7 +223,13 @@ static void __init at91sam9n12_map_io(void) at91_init_sram(0, AT91SAM9N12_SRAM_BASE, AT91SAM9N12_SRAM_SIZE); } +static void __init at91sam9n12_initialize(void) +{ + at91_sysirq_mask_rtc(AT91SAM9N12_BASE_RTC); +} + AT91_SOC_START(at91sam9n12) .map_io = at91sam9n12_map_io, .register_clocks = at91sam9n12_register_clocks, + .init = at91sam9n12_initialize, AT91_SOC_END diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c index f77fae5591b..5615d28a5b9 100644 --- a/arch/arm/mach-at91/at91sam9rl.c +++ b/arch/arm/mach-at91/at91sam9rl.c @@ -295,6 +295,9 @@ static void __init at91sam9rl_initialize(void) arm_pm_restart = at91sam9_alt_restart; at91_extern_irq = (1 << AT91SAM9RL_ID_IRQ0); + at91_sysirq_mask_rtc(AT91SAM9RL_BASE_RTC); + at91_sysirq_mask_rtt(AT91SAM9RL_BASE_RTT); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9rl_gpio, 4); } diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c index e631fec040c..7b4f848312e 100644 --- a/arch/arm/mach-at91/at91sam9x5.c +++ b/arch/arm/mach-at91/at91sam9x5.c @@ -318,6 +318,11 @@ static void __init at91sam9x5_map_io(void) at91_init_sram(0, AT91SAM9X5_SRAM_BASE, AT91SAM9X5_SRAM_SIZE); } +static void __init at91sam9x5_initialize(void) +{ + at91_sysirq_mask_rtc(AT91SAM9X5_BASE_RTC); +} + /* -------------------------------------------------------------------- * Interrupt initialization * -------------------------------------------------------------------- */ @@ -325,4 +330,5 @@ static void __init at91sam9x5_map_io(void) AT91_SOC_START(at91sam9x5) .map_io = at91sam9x5_map_io, .register_clocks = at91sam9x5_register_clocks, + .init = at91sam9x5_initialize, AT91_SOC_END diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h index 78ab0654865..d949ab4e26f 100644 --- a/arch/arm/mach-at91/generic.h +++ b/arch/arm/mach-at91/generic.h @@ -33,6 +33,8 @@ extern int __init at91_aic_of_init(struct device_node *node, struct device_node *parent); extern int __init at91_aic5_of_init(struct device_node *node, struct device_node *parent); +extern void __init at91_sysirq_mask_rtc(u32 rtc_base); +extern void __init at91_sysirq_mask_rtt(u32 rtt_base); /* Timer */ diff --git a/arch/arm/mach-at91/include/mach/at91sam9n12.h b/arch/arm/mach-at91/include/mach/at91sam9n12.h index d374b87c045..0151bcf6163 100644 --- a/arch/arm/mach-at91/include/mach/at91sam9n12.h +++ b/arch/arm/mach-at91/include/mach/at91sam9n12.h @@ -49,6 +49,11 @@ #define AT91SAM9N12_BASE_USART3 0xf8028000 /* + * System Peripherals + */ +#define AT91SAM9N12_BASE_RTC 0xfffffeb0 + +/* * Internal Memory. */ #define AT91SAM9N12_SRAM_BASE 0x00300000 /* Internal SRAM base address */ diff --git a/arch/arm/mach-at91/include/mach/at91sam9x5.h b/arch/arm/mach-at91/include/mach/at91sam9x5.h index c75ee19b58d..2fc76c49e97 100644 --- a/arch/arm/mach-at91/include/mach/at91sam9x5.h +++ b/arch/arm/mach-at91/include/mach/at91sam9x5.h @@ -55,6 +55,11 @@ #define AT91SAM9X5_BASE_USART2 0xf8024000 /* + * System Peripherals + */ +#define AT91SAM9X5_BASE_RTC 0xfffffeb0 + +/* * Internal Memory. */ #define AT91SAM9X5_SRAM_BASE 0x00300000 /* Internal SRAM base address */ diff --git a/arch/arm/mach-at91/include/mach/sama5d3.h b/arch/arm/mach-at91/include/mach/sama5d3.h index 6dc81ee3804..3abbc428687 100644 --- a/arch/arm/mach-at91/include/mach/sama5d3.h +++ b/arch/arm/mach-at91/include/mach/sama5d3.h @@ -65,6 +65,11 @@ #define SAMA5D3_ID_IRQ0 47 /* Advanced Interrupt Controller (IRQ0) */ /* + * System Peripherals + */ +#define SAMA5D3_BASE_RTC 0xfffffeb0 + +/* * Internal Memory */ #define SAMA5D3_SRAM_BASE 0x00300000 /* Internal SRAM base address */ diff --git a/arch/arm/mach-at91/sam9_smc.c b/arch/arm/mach-at91/sam9_smc.c index 99a0a1d2b7d..b26156bf15d 100644 --- a/arch/arm/mach-at91/sam9_smc.c +++ b/arch/arm/mach-at91/sam9_smc.c @@ -101,7 +101,7 @@ static void sam9_smc_cs_read(void __iomem *base, /* Pulse register */ val = __raw_readl(base + AT91_SMC_PULSE); - config->nwe_setup = val & AT91_SMC_NWEPULSE; + config->nwe_pulse = val & AT91_SMC_NWEPULSE; config->ncs_write_pulse = (val & AT91_SMC_NCS_WRPULSE) >> 8; config->nrd_pulse = (val & AT91_SMC_NRDPULSE) >> 16; config->ncs_read_pulse = (val & AT91_SMC_NCS_RDPULSE) >> 24; diff --git a/arch/arm/mach-at91/sama5d3.c b/arch/arm/mach-at91/sama5d3.c index 401279715ab..a28873fe304 100644 --- a/arch/arm/mach-at91/sama5d3.c +++ b/arch/arm/mach-at91/sama5d3.c @@ -95,19 +95,19 @@ static struct clk twi0_clk = { .name = "twi0_clk", .pid = SAMA5D3_ID_TWI0, .type = CLK_TYPE_PERIPHERAL, - .div = AT91_PMC_PCR_DIV2, + .div = AT91_PMC_PCR_DIV8, }; static struct clk twi1_clk = { .name = "twi1_clk", .pid = SAMA5D3_ID_TWI1, .type = CLK_TYPE_PERIPHERAL, - .div = AT91_PMC_PCR_DIV2, + .div = AT91_PMC_PCR_DIV8, }; static struct clk twi2_clk = { .name = "twi2_clk", .pid = SAMA5D3_ID_TWI2, .type = CLK_TYPE_PERIPHERAL, - .div = AT91_PMC_PCR_DIV2, + .div = AT91_PMC_PCR_DIV8, }; static struct clk mmc0_clk = { .name = "mci0_clk", @@ -371,7 +371,13 @@ static void __init sama5d3_map_io(void) at91_init_sram(0, SAMA5D3_SRAM_BASE, SAMA5D3_SRAM_SIZE); } +static void __init sama5d3_initialize(void) +{ + at91_sysirq_mask_rtc(SAMA5D3_BASE_RTC); +} + AT91_SOC_START(sama5d3) .map_io = sama5d3_map_io, .register_clocks = sama5d3_register_clocks, + .init = sama5d3_initialize, AT91_SOC_END diff --git a/arch/arm/mach-at91/sysirq_mask.c b/arch/arm/mach-at91/sysirq_mask.c new file mode 100644 index 00000000000..2ba694f9626 --- /dev/null +++ b/arch/arm/mach-at91/sysirq_mask.c @@ -0,0 +1,71 @@ +/* + * sysirq_mask.c - System-interrupt masking + * + * Copyright (C) 2013 Johan Hovold <jhovold@gmail.com> + * + * Functions to disable system interrupts from backup-powered peripherals. + * + * The RTC and RTT-peripherals are generally powered by backup power (VDDBU) + * and are not reset on wake-up, user, watchdog or software reset. This means + * that their interrupts may be enabled during early boot (e.g. after a user + * reset). + * + * As the RTC and RTT share the system-interrupt line with the PIT, an + * interrupt occurring before a handler has been installed would lead to the + * system interrupt being disabled and prevent the system from booting. + * + * 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/io.h> +#include <mach/at91_rtt.h> + +#include "generic.h" + +#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */ +#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */ + +void __init at91_sysirq_mask_rtc(u32 rtc_base) +{ + void __iomem *base; + u32 mask; + + base = ioremap(rtc_base, 64); + if (!base) + return; + + mask = readl_relaxed(base + AT91_RTC_IMR); + if (mask) { + pr_info("AT91: Disabling rtc irq\n"); + writel_relaxed(mask, base + AT91_RTC_IDR); + (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */ + } + + iounmap(base); +} + +void __init at91_sysirq_mask_rtt(u32 rtt_base) +{ + void __iomem *base; + void __iomem *reg; + u32 mode; + + base = ioremap(rtt_base, 16); + if (!base) + return; + + reg = base + AT91_RTT_MR; + + mode = readl_relaxed(reg); + if (mode & (AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN)) { + pr_info("AT91: Disabling rtt irq\n"); + mode &= ~(AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN); + writel_relaxed(mode, reg); + (void)readl_relaxed(reg); /* flush */ + } + + iounmap(base); +} diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c index dff4ddc5ef8..139e42da25f 100644 --- a/arch/arm/mach-davinci/board-dm355-leopard.c +++ b/arch/arm/mach-davinci/board-dm355-leopard.c @@ -75,6 +75,7 @@ static struct davinci_nand_pdata davinci_nand_data = { .parts = davinci_nand_partitions, .nr_parts = ARRAY_SIZE(davinci_nand_partitions), .ecc_mode = NAND_ECC_HW_SYNDROME, + .ecc_bits = 4, .bbt_options = NAND_BBT_USE_FLASH, }; diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c index a33686a6fbb..fa4bfaf952d 100644 --- a/arch/arm/mach-davinci/board-dm644x-evm.c +++ b/arch/arm/mach-davinci/board-dm644x-evm.c @@ -153,6 +153,7 @@ static struct davinci_nand_pdata davinci_evm_nandflash_data = { .parts = davinci_evm_nandflash_partition, .nr_parts = ARRAY_SIZE(davinci_evm_nandflash_partition), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .bbt_options = NAND_BBT_USE_FLASH, .timing = &davinci_evm_nandflash_timing, }; diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c index fbb8e5ab1dc..0c005e876ca 100644 --- a/arch/arm/mach-davinci/board-dm646x-evm.c +++ b/arch/arm/mach-davinci/board-dm646x-evm.c @@ -90,6 +90,7 @@ static struct davinci_nand_pdata davinci_nand_data = { .parts = davinci_nand_partitions, .nr_parts = ARRAY_SIZE(davinci_nand_partitions), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .options = 0, }; diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c index 2bc112adf56..808233b60e3 100644 --- a/arch/arm/mach-davinci/board-neuros-osd2.c +++ b/arch/arm/mach-davinci/board-neuros-osd2.c @@ -88,6 +88,7 @@ static struct davinci_nand_pdata davinci_ntosd2_nandflash_data = { .parts = davinci_ntosd2_nandflash_partition, .nr_parts = ARRAY_SIZE(davinci_ntosd2_nandflash_partition), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .bbt_options = NAND_BBT_USE_FLASH, }; diff --git a/arch/arm/mach-exynos/mach-exynos5-dt.c b/arch/arm/mach-exynos/mach-exynos5-dt.c index 753b94f3fca..d88234e14f9 100644 --- a/arch/arm/mach-exynos/mach-exynos5-dt.c +++ b/arch/arm/mach-exynos/mach-exynos5-dt.c @@ -14,6 +14,7 @@ #include <linux/memblock.h> #include <linux/io.h> #include <linux/clocksource.h> +#include <linux/dma-mapping.h> #include <asm/mach/arch.h> #include <mach/regs-pmu.h> @@ -23,11 +24,31 @@ #include "common.h" +static u64 dma_mask64 = DMA_BIT_MASK(64); + static void __init exynos5_dt_map_io(void) { exynos_init_io(NULL, 0); } +static int exynos5250_platform_notifier(struct notifier_block *nb, + unsigned long event, void *__dev) +{ + struct device *dev = __dev; + + if (event != BUS_NOTIFY_ADD_DEVICE) + return NOTIFY_DONE; + + dev->dma_mask = &dma_mask64; + dev->coherent_dma_mask = DMA_BIT_MASK(64); + + return NOTIFY_OK; +} + +static struct notifier_block exynos5250_platform_nb = { + .notifier_call = exynos5250_platform_notifier, +}; + static void __init exynos5_dt_machine_init(void) { struct device_node *i2c_np; @@ -52,6 +73,11 @@ static void __init exynos5_dt_machine_init(void) } } + if (config_enabled(CONFIG_ARM_LPAE) && + of_machine_is_compatible("samsung,exynos5250")) + bus_register_notifier(&platform_bus_type, + &exynos5250_platform_nb); + of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); } diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c index a42b369bc43..95d0b6e6438 100644 --- a/arch/arm/mach-footbridge/common.c +++ b/arch/arm/mach-footbridge/common.c @@ -15,6 +15,7 @@ #include <linux/init.h> #include <linux/io.h> #include <linux/spinlock.h> +#include <video/vga.h> #include <asm/pgtable.h> #include <asm/page.h> @@ -196,6 +197,8 @@ void __init footbridge_map_io(void) iotable_init(ebsa285_host_io_desc, ARRAY_SIZE(ebsa285_host_io_desc)); pci_map_io_early(__phys_to_pfn(DC21285_PCI_IO)); } + + vga_base = PCIMEM_BASE; } void footbridge_restart(char mode, const char *cmd) diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c index 9ee78f7b499..782f6c71fa0 100644 --- a/arch/arm/mach-footbridge/dc21285-timer.c +++ b/arch/arm/mach-footbridge/dc21285-timer.c @@ -96,11 +96,12 @@ static struct irqaction footbridge_timer_irq = { void __init footbridge_timer_init(void) { struct clock_event_device *ce = &ckevt_dc21285; + unsigned rate = DIV_ROUND_CLOSEST(mem_fclk_21285, 16); - clocksource_register_hz(&cksrc_dc21285, (mem_fclk_21285 + 8) / 16); + clocksource_register_hz(&cksrc_dc21285, rate); setup_irq(ce->irq, &footbridge_timer_irq); ce->cpumask = cpumask_of(smp_processor_id()); - clockevents_config_and_register(ce, mem_fclk_21285, 0x4, 0xffffff); + clockevents_config_and_register(ce, rate, 0x4, 0xffffff); } diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c index a7cd2cf5e08..7c2fdae9a38 100644 --- a/arch/arm/mach-footbridge/dc21285.c +++ b/arch/arm/mach-footbridge/dc21285.c @@ -18,7 +18,6 @@ #include <linux/irq.h> #include <linux/io.h> #include <linux/spinlock.h> -#include <video/vga.h> #include <asm/irq.h> #include <asm/mach/pci.h> @@ -276,8 +275,6 @@ int __init dc21285_setup(int nr, struct pci_sys_data *sys) sys->mem_offset = DC21285_PCI_MEM; - pci_ioremap_io(0, DC21285_PCI_IO); - pci_add_resource_offset(&sys->resources, &res[0], sys->mem_offset); pci_add_resource_offset(&sys->resources, &res[1], sys->mem_offset); @@ -293,7 +290,6 @@ void __init dc21285_preinit(void) int cfn_mode; pcibios_min_mem = 0x81000000; - vga_base = PCIMEM_BASE; mem_size = (unsigned int)high_memory - PAGE_OFFSET; for (mem_mask = 0x00100000; mem_mask < 0x10000000; mem_mask <<= 1) diff --git a/arch/arm/mach-footbridge/ebsa285.c b/arch/arm/mach-footbridge/ebsa285.c index b08243500e2..1a7235fb52a 100644 --- a/arch/arm/mach-footbridge/ebsa285.c +++ b/arch/arm/mach-footbridge/ebsa285.c @@ -30,21 +30,24 @@ static const struct { const char *name; const char *trigger; } ebsa285_leds[] = { - { "ebsa285:amber", "heartbeat", }, - { "ebsa285:green", "cpu0", }, + { "ebsa285:amber", "cpu0", }, + { "ebsa285:green", "heartbeat", }, { "ebsa285:red",}, }; +static unsigned char hw_led_state; + static void ebsa285_led_set(struct led_classdev *cdev, enum led_brightness b) { struct ebsa285_led *led = container_of(cdev, struct ebsa285_led, cdev); - if (b != LED_OFF) - *XBUS_LEDS |= led->mask; + if (b == LED_OFF) + hw_led_state |= led->mask; else - *XBUS_LEDS &= ~led->mask; + hw_led_state &= ~led->mask; + *XBUS_LEDS = hw_led_state; } static enum led_brightness ebsa285_led_get(struct led_classdev *cdev) @@ -52,18 +55,19 @@ static enum led_brightness ebsa285_led_get(struct led_classdev *cdev) struct ebsa285_led *led = container_of(cdev, struct ebsa285_led, cdev); - return (*XBUS_LEDS & led->mask) ? LED_FULL : LED_OFF; + return hw_led_state & led->mask ? LED_OFF : LED_FULL; } static int __init ebsa285_leds_init(void) { int i; - if (machine_is_ebsa285()) + if (!machine_is_ebsa285()) return -ENODEV; - /* 3 LEDS All ON */ - *XBUS_LEDS |= XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED; + /* 3 LEDS all off */ + hw_led_state = XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED; + *XBUS_LEDS = hw_led_state; for (i = 0; i < ARRAY_SIZE(ebsa285_leds); i++) { struct ebsa285_led *led; diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig index cd9fcb1cd7a..b8466fb00f5 100644 --- a/arch/arm/mach-highbank/Kconfig +++ b/arch/arm/mach-highbank/Kconfig @@ -2,6 +2,7 @@ config ARCH_HIGHBANK bool "Calxeda ECX-1000/2000 (Highbank/Midway)" if ARCH_MULTI_V7 select ARCH_HAS_CPUFREQ select ARCH_HAS_OPP + select ARCH_SUPPORTS_BIG_ENDIAN select ARCH_WANT_OPTIONAL_GPIOLIB select ARM_AMBA select ARM_GIC diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c index e7df2dd43a4..35d1029d7c9 100644 --- a/arch/arm/mach-highbank/highbank.c +++ b/arch/arm/mach-highbank/highbank.c @@ -65,13 +65,12 @@ void highbank_set_cpu_jump(int cpu, void *jump_addr) HB_JUMP_TABLE_PHYS(cpu) + 15); } -#ifdef CONFIG_CACHE_L2X0 static void highbank_l2x0_disable(void) { + outer_flush_all(); /* Disable PL310 L2 Cache controller */ highbank_smc1(0x102, 0x0); } -#endif static void __init highbank_init_irq(void) { @@ -80,12 +79,13 @@ static void __init highbank_init_irq(void) if (of_find_compatible_node(NULL, NULL, "arm,cortex-a9")) highbank_scu_map_io(); -#ifdef CONFIG_CACHE_L2X0 /* Enable PL310 L2 Cache controller */ - highbank_smc1(0x102, 0x1); - l2x0_of_init(0, ~0UL); - outer_cache.disable = highbank_l2x0_disable; -#endif + if (IS_ENABLED(CONFIG_CACHE_L2X0) && + of_find_compatible_node(NULL, NULL, "arm,pl310-cache")) { + highbank_smc1(0x102, 0x1); + l2x0_of_init(0, ~0UL); + outer_cache.disable = highbank_l2x0_disable; + } } static void __init highbank_timer_init(void) diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 4e3148ce852..0b9e437719b 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -424,7 +424,7 @@ int __init mx6q_clocks_init(void) clk[asrc_podf] = imx_clk_divider("asrc_podf", "asrc_pred", base + 0x30, 9, 3); clk[spdif_pred] = imx_clk_divider("spdif_pred", "spdif_sel", base + 0x30, 25, 3); clk[spdif_podf] = imx_clk_divider("spdif_podf", "spdif_pred", base + 0x30, 22, 3); - clk[can_root] = imx_clk_divider("can_root", "pll3_usb_otg", base + 0x20, 2, 6); + clk[can_root] = imx_clk_divider("can_root", "pll3_60m", base + 0x20, 2, 6); clk[ecspi_root] = imx_clk_divider("ecspi_root", "pll3_60m", base + 0x38, 19, 6); clk[gpu2d_core_podf] = imx_clk_divider("gpu2d_core_podf", "gpu2d_core_sel", base + 0x18, 23, 3); clk[gpu3d_core_podf] = imx_clk_divider("gpu3d_core_podf", "gpu3d_core_sel", base + 0x18, 26, 3); diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c index 8c60fcb08a9..2f4c92486cf 100644 --- a/arch/arm/mach-integrator/integrator_cp.c +++ b/arch/arm/mach-integrator/integrator_cp.c @@ -199,7 +199,8 @@ static struct mmci_platform_data mmc_data = { static void cp_clcd_enable(struct clcd_fb *fb) { struct fb_var_screeninfo *var = &fb->fb.var; - u32 val = CM_CTRL_STATIC1 | CM_CTRL_STATIC2; + u32 val = CM_CTRL_STATIC1 | CM_CTRL_STATIC2 + | CM_CTRL_LCDEN0 | CM_CTRL_LCDEN1; if (var->bits_per_pixel <= 8 || (var->bits_per_pixel == 16 && var->green.length == 5)) diff --git a/arch/arm/mach-ixp4xx/Kconfig b/arch/arm/mach-ixp4xx/Kconfig index 73a2d905af8..72de05f09cb 100644 --- a/arch/arm/mach-ixp4xx/Kconfig +++ b/arch/arm/mach-ixp4xx/Kconfig @@ -1,9 +1,5 @@ if ARCH_IXP4XX -config ARCH_SUPPORTS_BIG_ENDIAN - bool - default y - menu "Intel IXP4xx Implementation Options" comment "IXP4xx Platforms" diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig index 80a8bcacd9d..317cdb80009 100644 --- a/arch/arm/mach-mvebu/Kconfig +++ b/arch/arm/mach-mvebu/Kconfig @@ -1,5 +1,6 @@ config ARCH_MVEBU bool "Marvell SOCs with Device Tree support" if ARCH_MULTI_V7 + select ARCH_SUPPORTS_BIG_ENDIAN select CLKSRC_MMIO select COMMON_CLK select GENERIC_CLOCKEVENTS diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S index 5476669ba90..ee7598fe75d 100644 --- a/arch/arm/mach-mvebu/coherency_ll.S +++ b/arch/arm/mach-mvebu/coherency_ll.S @@ -20,6 +20,8 @@ #define ARMADA_XP_CFB_CTL_REG_OFFSET 0x0 #define ARMADA_XP_CFB_CFG_REG_OFFSET 0x4 +#include <asm/assembler.h> + .text /* * r0: Coherency fabric base register address @@ -29,6 +31,7 @@ ENTRY(ll_set_cpu_coherent) /* Create bit by cpu index */ mov r3, #(1 << 24) lsl r1, r3, r1 +ARM_BE8(rev r1, r1) /* Add CPU to SMP group - Atomic */ add r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET diff --git a/arch/arm/mach-mvebu/headsmp.S b/arch/arm/mach-mvebu/headsmp.S index a06e0ede8c0..458ed3fb262 100644 --- a/arch/arm/mach-mvebu/headsmp.S +++ b/arch/arm/mach-mvebu/headsmp.S @@ -21,6 +21,8 @@ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> + /* * At this stage the secondary CPUs don't have acces yet to the MMU, so * we have to provide physical addresses @@ -35,6 +37,7 @@ * startup */ ENTRY(armada_xp_secondary_startup) + ARM_BE8(setend be ) @ go BE8 if entered LE /* Read CPU id */ mrc p15, 0, r1, c0, c0, 5 diff --git a/arch/arm/mach-mxs/pm.h b/arch/arm/mach-mxs/pm.h index f57e7cdece2..09d77b00a96 100644 --- a/arch/arm/mach-mxs/pm.h +++ b/arch/arm/mach-mxs/pm.h @@ -9,6 +9,10 @@ #ifndef __ARCH_MXS_PM_H #define __ARCH_MXS_PM_H +#ifdef CONFIG_PM void mxs_pm_init(void); +#else +#define mxs_pm_init NULL +#endif #endif diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c index 6c4da1254f5..55bcb77c623 100644 --- a/arch/arm/mach-omap2/gpmc.c +++ b/arch/arm/mach-omap2/gpmc.c @@ -1335,7 +1335,7 @@ static void __maybe_unused gpmc_read_timings_dt(struct device_node *np, of_property_read_bool(np, "gpmc,time-para-granularity"); } -#ifdef CONFIG_MTD_NAND +#if IS_ENABLED(CONFIG_MTD_NAND) static const char * const nand_ecc_opts[] = { [OMAP_ECC_HAMMING_CODE_DEFAULT] = "sw", @@ -1391,7 +1391,7 @@ static int gpmc_probe_nand_child(struct platform_device *pdev, } #endif -#ifdef CONFIG_MTD_ONENAND +#if IS_ENABLED(CONFIG_MTD_ONENAND) static int gpmc_probe_onenand_child(struct platform_device *pdev, struct device_node *child) { diff --git a/arch/arm/mach-omap2/irq.c b/arch/arm/mach-omap2/irq.c index 3926f370448..e022a869bff 100644 --- a/arch/arm/mach-omap2/irq.c +++ b/arch/arm/mach-omap2/irq.c @@ -233,7 +233,7 @@ static inline void omap_intc_handle_irq(void __iomem *base_addr, struct pt_regs goto out; irqnr = readl_relaxed(base_addr + 0xd8); -#ifdef CONFIG_SOC_TI81XX +#if IS_ENABLED(CONFIG_SOC_TI81XX) || IS_ENABLED(CONFIG_SOC_AM33XX) if (irqnr) goto out; irqnr = readl_relaxed(base_addr + 0xf8); diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c index 13b27ffaf45..ab99ab8fce8 100644 --- a/arch/arm/mach-omap2/omap4-common.c +++ b/arch/arm/mach-omap2/omap4-common.c @@ -162,6 +162,7 @@ void __iomem *omap4_get_l2cache_base(void) static void omap4_l2x0_disable(void) { + outer_flush_all(); /* Disable PL310 L2 Cache controller */ omap_smc1(0x102, 0x0); } diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 7341eff63f5..44c609a1ec5 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -399,7 +399,7 @@ static int _set_clockactivity(struct omap_hwmod *oh, u8 clockact, u32 *v) } /** - * _set_softreset: set OCP_SYSCONFIG.CLOCKACTIVITY bits in @v + * _set_softreset: set OCP_SYSCONFIG.SOFTRESET bit in @v * @oh: struct omap_hwmod * * @v: pointer to register contents to modify * @@ -427,6 +427,36 @@ static int _set_softreset(struct omap_hwmod *oh, u32 *v) } /** + * _clear_softreset: clear OCP_SYSCONFIG.SOFTRESET bit in @v + * @oh: struct omap_hwmod * + * @v: pointer to register contents to modify + * + * Clear the SOFTRESET bit in @v for hwmod @oh. Returns -EINVAL upon + * error or 0 upon success. + */ +static int _clear_softreset(struct omap_hwmod *oh, u32 *v) +{ + u32 softrst_mask; + + if (!oh->class->sysc || + !(oh->class->sysc->sysc_flags & SYSC_HAS_SOFTRESET)) + return -EINVAL; + + if (!oh->class->sysc->sysc_fields) { + WARN(1, + "omap_hwmod: %s: sysc_fields absent for sysconfig class\n", + oh->name); + return -EINVAL; + } + + softrst_mask = (0x1 << oh->class->sysc->sysc_fields->srst_shift); + + *v &= ~softrst_mask; + + return 0; +} + +/** * _wait_softreset_complete - wait for an OCP softreset to complete * @oh: struct omap_hwmod * to wait on * @@ -1909,6 +1939,12 @@ static int _ocp_softreset(struct omap_hwmod *oh) ret = _set_softreset(oh, &v); if (ret) goto dis_opt_clks; + + _write_sysconfig(v, oh); + ret = _clear_softreset(oh, &v); + if (ret) + goto dis_opt_clks; + _write_sysconfig(v, oh); if (oh->class->sysc->srst_udelay) @@ -3148,6 +3184,11 @@ int omap_hwmod_softreset(struct omap_hwmod *oh) goto error; _write_sysconfig(v, oh); + ret = _clear_softreset(oh, &v); + if (ret) + goto error; + _write_sysconfig(v, oh); + error: return ret; } diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c index d05fc7b5456..83735b72895 100644 --- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c @@ -796,7 +796,7 @@ struct omap_hwmod omap2xxx_counter_32k_hwmod = { /* gpmc */ static struct omap_hwmod_irq_info omap2xxx_gpmc_irqs[] = { - { .irq = 20 }, + { .irq = 20 + OMAP_INTC_START, }, { .irq = -1 } }; @@ -841,7 +841,7 @@ static struct omap_hwmod_class omap2_rng_hwmod_class = { }; static struct omap_hwmod_irq_info omap2_rng_mpu_irqs[] = { - { .irq = 52 }, + { .irq = 52 + OMAP_INTC_START, }, { .irq = -1 } }; diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index 31c7126eb3b..9f6238c9dfc 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -1930,7 +1930,8 @@ static struct omap_hwmod_class_sysconfig omap3xxx_usb_host_hs_sysc = { .syss_offs = 0x0014, .sysc_flags = (SYSC_HAS_MIDLEMODE | SYSC_HAS_CLOCKACTIVITY | SYSC_HAS_SIDLEMODE | SYSC_HAS_ENAWAKEUP | - SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE), + SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE | + SYSS_HAS_RESET_STATUS), .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | MSTANDBY_FORCE | MSTANDBY_NO | MSTANDBY_SMART), .sysc_fields = &omap_hwmod_sysc_type1, @@ -2008,15 +2009,7 @@ static struct omap_hwmod omap3xxx_usb_host_hs_hwmod = { * hence HWMOD_SWSUP_MSTANDBY */ - /* - * During system boot; If the hwmod framework resets the module - * the module will have smart idle settings; which can lead to deadlock - * (above Errata Id:i660); so, dont reset the module during boot; - * Use HWMOD_INIT_NO_RESET. - */ - - .flags = HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY | - HWMOD_INIT_NO_RESET, + .flags = HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY, }; /* @@ -2159,7 +2152,7 @@ static struct omap_hwmod_class omap3xxx_gpmc_hwmod_class = { }; static struct omap_hwmod_irq_info omap3xxx_gpmc_irqs[] = { - { .irq = 20 }, + { .irq = 20 + OMAP_INTC_START, }, { .irq = -1 } }; @@ -2993,7 +2986,7 @@ static struct omap_mmu_dev_attr mmu_isp_dev_attr = { static struct omap_hwmod omap3xxx_mmu_isp_hwmod; static struct omap_hwmod_irq_info omap3xxx_mmu_isp_irqs[] = { - { .irq = 24 }, + { .irq = 24 + OMAP_INTC_START, }, { .irq = -1 } }; @@ -3035,7 +3028,7 @@ static struct omap_mmu_dev_attr mmu_iva_dev_attr = { static struct omap_hwmod omap3xxx_mmu_iva_hwmod; static struct omap_hwmod_irq_info omap3xxx_mmu_iva_irqs[] = { - { .irq = 28 }, + { .irq = 28 + OMAP_INTC_START, }, { .irq = -1 } }; diff --git a/arch/arm/mach-pxa/reset.c b/arch/arm/mach-pxa/reset.c index 3fab583755d..0616390b857 100644 --- a/arch/arm/mach-pxa/reset.c +++ b/arch/arm/mach-pxa/reset.c @@ -13,6 +13,7 @@ #include <mach/regs-ost.h> #include <mach/reset.h> +#include <mach/smemc.h> unsigned int reset_status; EXPORT_SYMBOL(reset_status); @@ -81,6 +82,12 @@ static void do_hw_reset(void) writel_relaxed(OSSR_M3, OSSR); /* ... in 100 ms */ writel_relaxed(readl_relaxed(OSCR) + 368640, OSMR3); + /* + * SDRAM hangs on watchdog reset on Marvell PXA270 (erratum 71) + * we put SDRAM into self-refresh to prevent that + */ + while (1) + writel_relaxed(MDREFR_SLFRSH, MDREFR); } void pxa_restart(char mode, const char *cmd) @@ -104,4 +111,3 @@ void pxa_restart(char mode, const char *cmd) break; } } - diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c index 3d91d2e5bf3..d91fcf403ce 100644 --- a/arch/arm/mach-pxa/tosa.c +++ b/arch/arm/mach-pxa/tosa.c @@ -424,57 +424,57 @@ static struct platform_device tosa_power_device = { * Tosa Keyboard */ static const uint32_t tosakbd_keymap[] = { - KEY(0, 2, KEY_W), - KEY(0, 6, KEY_K), - KEY(0, 7, KEY_BACKSPACE), - KEY(0, 8, KEY_P), - KEY(1, 1, KEY_Q), - KEY(1, 2, KEY_E), - KEY(1, 3, KEY_T), - KEY(1, 4, KEY_Y), - KEY(1, 6, KEY_O), - KEY(1, 7, KEY_I), - KEY(1, 8, KEY_COMMA), - KEY(2, 1, KEY_A), - KEY(2, 2, KEY_D), - KEY(2, 3, KEY_G), - KEY(2, 4, KEY_U), - KEY(2, 6, KEY_L), - KEY(2, 7, KEY_ENTER), - KEY(2, 8, KEY_DOT), - KEY(3, 1, KEY_Z), - KEY(3, 2, KEY_C), - KEY(3, 3, KEY_V), - KEY(3, 4, KEY_J), - KEY(3, 5, TOSA_KEY_ADDRESSBOOK), - KEY(3, 6, TOSA_KEY_CANCEL), - KEY(3, 7, TOSA_KEY_CENTER), - KEY(3, 8, TOSA_KEY_OK), - KEY(3, 9, KEY_LEFTSHIFT), - KEY(4, 1, KEY_S), - KEY(4, 2, KEY_R), - KEY(4, 3, KEY_B), - KEY(4, 4, KEY_N), - KEY(4, 5, TOSA_KEY_CALENDAR), - KEY(4, 6, TOSA_KEY_HOMEPAGE), - KEY(4, 7, KEY_LEFTCTRL), - KEY(4, 8, TOSA_KEY_LIGHT), - KEY(4, 10, KEY_RIGHTSHIFT), - KEY(5, 1, KEY_TAB), - KEY(5, 2, KEY_SLASH), - KEY(5, 3, KEY_H), - KEY(5, 4, KEY_M), - KEY(5, 5, TOSA_KEY_MENU), - KEY(5, 7, KEY_UP), - KEY(5, 11, TOSA_KEY_FN), - KEY(6, 1, KEY_X), - KEY(6, 2, KEY_F), - KEY(6, 3, KEY_SPACE), - KEY(6, 4, KEY_APOSTROPHE), - KEY(6, 5, TOSA_KEY_MAIL), - KEY(6, 6, KEY_LEFT), - KEY(6, 7, KEY_DOWN), - KEY(6, 8, KEY_RIGHT), + KEY(0, 1, KEY_W), + KEY(0, 5, KEY_K), + KEY(0, 6, KEY_BACKSPACE), + KEY(0, 7, KEY_P), + KEY(1, 0, KEY_Q), + KEY(1, 1, KEY_E), + KEY(1, 2, KEY_T), + KEY(1, 3, KEY_Y), + KEY(1, 5, KEY_O), + KEY(1, 6, KEY_I), + KEY(1, 7, KEY_COMMA), + KEY(2, 0, KEY_A), + KEY(2, 1, KEY_D), + KEY(2, 2, KEY_G), + KEY(2, 3, KEY_U), + KEY(2, 5, KEY_L), + KEY(2, 6, KEY_ENTER), + KEY(2, 7, KEY_DOT), + KEY(3, 0, KEY_Z), + KEY(3, 1, KEY_C), + KEY(3, 2, KEY_V), + KEY(3, 3, KEY_J), + KEY(3, 4, TOSA_KEY_ADDRESSBOOK), + KEY(3, 5, TOSA_KEY_CANCEL), + KEY(3, 6, TOSA_KEY_CENTER), + KEY(3, 7, TOSA_KEY_OK), + KEY(3, 8, KEY_LEFTSHIFT), + KEY(4, 0, KEY_S), + KEY(4, 1, KEY_R), + KEY(4, 2, KEY_B), + KEY(4, 3, KEY_N), + KEY(4, 4, TOSA_KEY_CALENDAR), + KEY(4, 5, TOSA_KEY_HOMEPAGE), + KEY(4, 6, KEY_LEFTCTRL), + KEY(4, 7, TOSA_KEY_LIGHT), + KEY(4, 9, KEY_RIGHTSHIFT), + KEY(5, 0, KEY_TAB), + KEY(5, 1, KEY_SLASH), + KEY(5, 2, KEY_H), + KEY(5, 3, KEY_M), + KEY(5, 4, TOSA_KEY_MENU), + KEY(5, 6, KEY_UP), + KEY(5, 10, TOSA_KEY_FN), + KEY(6, 0, KEY_X), + KEY(6, 1, KEY_F), + KEY(6, 2, KEY_SPACE), + KEY(6, 3, KEY_APOSTROPHE), + KEY(6, 4, TOSA_KEY_MAIL), + KEY(6, 5, KEY_LEFT), + KEY(6, 6, KEY_DOWN), + KEY(6, 7, KEY_RIGHT), }; static struct matrix_keymap_data tosakbd_keymap_data = { diff --git a/arch/arm/mach-s3c24xx/clock-s3c2410.c b/arch/arm/mach-s3c24xx/clock-s3c2410.c index 34fffdf6fc1..564553694b5 100644 --- a/arch/arm/mach-s3c24xx/clock-s3c2410.c +++ b/arch/arm/mach-s3c24xx/clock-s3c2410.c @@ -119,66 +119,101 @@ static struct clk init_clocks_off[] = { } }; -static struct clk init_clocks[] = { - { - .name = "lcd", - .parent = &clk_h, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_LCDC, - }, { - .name = "gpio", - .parent = &clk_p, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_GPIO, - }, { - .name = "usb-host", - .parent = &clk_h, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_USBH, - }, { - .name = "usb-device", - .parent = &clk_h, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_USBD, - }, { - .name = "timers", - .parent = &clk_p, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_PWMT, - }, { - .name = "uart", - .devname = "s3c2410-uart.0", - .parent = &clk_p, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_UART0, - }, { - .name = "uart", - .devname = "s3c2410-uart.1", - .parent = &clk_p, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_UART1, - }, { - .name = "uart", - .devname = "s3c2410-uart.2", - .parent = &clk_p, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_UART2, - }, { - .name = "rtc", - .parent = &clk_p, - .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2410_CLKCON_RTC, - }, { - .name = "watchdog", - .parent = &clk_p, - .ctrlbit = 0, - }, { - .name = "usb-bus-host", - .parent = &clk_usb_bus, - }, { - .name = "usb-bus-gadget", - .parent = &clk_usb_bus, - }, +static struct clk clk_lcd = { + .name = "lcd", + .parent = &clk_h, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_LCDC, +}; + +static struct clk clk_gpio = { + .name = "gpio", + .parent = &clk_p, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_GPIO, +}; + +static struct clk clk_usb_host = { + .name = "usb-host", + .parent = &clk_h, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_USBH, +}; + +static struct clk clk_usb_device = { + .name = "usb-device", + .parent = &clk_h, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_USBD, +}; + +static struct clk clk_timers = { + .name = "timers", + .parent = &clk_p, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_PWMT, +}; + +struct clk s3c24xx_clk_uart0 = { + .name = "uart", + .devname = "s3c2410-uart.0", + .parent = &clk_p, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_UART0, +}; + +struct clk s3c24xx_clk_uart1 = { + .name = "uart", + .devname = "s3c2410-uart.1", + .parent = &clk_p, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_UART1, +}; + +struct clk s3c24xx_clk_uart2 = { + .name = "uart", + .devname = "s3c2410-uart.2", + .parent = &clk_p, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_UART2, +}; + +static struct clk clk_rtc = { + .name = "rtc", + .parent = &clk_p, + .enable = s3c2410_clkcon_enable, + .ctrlbit = S3C2410_CLKCON_RTC, +}; + +static struct clk clk_watchdog = { + .name = "watchdog", + .parent = &clk_p, + .ctrlbit = 0, +}; + +static struct clk clk_usb_bus_host = { + .name = "usb-bus-host", + .parent = &clk_usb_bus, +}; + +static struct clk clk_usb_bus_gadget = { + .name = "usb-bus-gadget", + .parent = &clk_usb_bus, +}; + +static struct clk *init_clocks[] = { + &clk_lcd, + &clk_gpio, + &clk_usb_host, + &clk_usb_device, + &clk_timers, + &s3c24xx_clk_uart0, + &s3c24xx_clk_uart1, + &s3c24xx_clk_uart2, + &clk_rtc, + &clk_watchdog, + &clk_usb_bus_host, + &clk_usb_bus_gadget, }; /* s3c2410_baseclk_add() @@ -195,7 +230,6 @@ int __init s3c2410_baseclk_add(void) { unsigned long clkslow = __raw_readl(S3C2410_CLKSLOW); unsigned long clkcon = __raw_readl(S3C2410_CLKCON); - struct clk *clkp; struct clk *xtal; int ret; int ptr; @@ -207,8 +241,9 @@ int __init s3c2410_baseclk_add(void) /* register clocks from clock array */ - clkp = init_clocks; - for (ptr = 0; ptr < ARRAY_SIZE(init_clocks); ptr++, clkp++) { + for (ptr = 0; ptr < ARRAY_SIZE(init_clocks); ptr++) { + struct clk *clkp = init_clocks[ptr]; + /* ensure that we note the clock state */ clkp->usage = clkcon & clkp->ctrlbit ? 1 : 0; diff --git a/arch/arm/mach-s3c24xx/clock-s3c2440.c b/arch/arm/mach-s3c24xx/clock-s3c2440.c index 1069b568082..aaf006d1d6d 100644 --- a/arch/arm/mach-s3c24xx/clock-s3c2440.c +++ b/arch/arm/mach-s3c24xx/clock-s3c2440.c @@ -166,6 +166,9 @@ static struct clk_lookup s3c2440_clk_lookup[] = { CLKDEV_INIT(NULL, "clk_uart_baud1", &s3c24xx_uclk), CLKDEV_INIT(NULL, "clk_uart_baud2", &clk_p), CLKDEV_INIT(NULL, "clk_uart_baud3", &s3c2440_clk_fclk_n), + CLKDEV_INIT("s3c2440-uart.0", "uart", &s3c24xx_clk_uart0), + CLKDEV_INIT("s3c2440-uart.1", "uart", &s3c24xx_clk_uart1), + CLKDEV_INIT("s3c2440-uart.2", "uart", &s3c24xx_clk_uart2), CLKDEV_INIT("s3c2440-camif", "camera", &s3c2440_clk_cam_upll), }; diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index e838ba27e44..c9808c68415 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -512,6 +512,9 @@ static void __init assabet_map_io(void) * Its called GPCLKR0 in my SA1110 manual. */ Ser1SDCR0 |= SDCR0_SUS; + MSC1 = (MSC1 & ~0xffff) | + MSC_NonBrst | MSC_32BitStMem | + MSC_RdAcc(2) | MSC_WrAcc(2) | MSC_Rec(0); if (!machine_has_neponset()) sa1100_register_uart_fns(&assabet_port_fns); diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h index f33679d2d3e..50e1d850ee2 100644 --- a/arch/arm/mach-sa1100/include/mach/collie.h +++ b/arch/arm/mach-sa1100/include/mach/collie.h @@ -13,6 +13,8 @@ #ifndef __ASM_ARCH_COLLIE_H #define __ASM_ARCH_COLLIE_H +#include "hardware.h" /* Gives GPIO_MAX */ + extern void locomolcd_power(int on); #define COLLIE_SCOOP_GPIO_BASE (GPIO_MAX + 1) diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index b85b2882dbd..803c9fcfb35 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -437,7 +437,7 @@ static struct platform_device lcdc0_device = { .id = 0, .dev = { .platform_data = &lcdc0_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -534,7 +534,7 @@ static struct platform_device hdmi_lcdc_device = { .id = 1, .dev = { .platform_data = &hdmi_lcdc_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c index e6b775a10aa..4d610e6ea98 100644 --- a/arch/arm/mach-shmobile/board-kzm9g.c +++ b/arch/arm/mach-shmobile/board-kzm9g.c @@ -332,7 +332,7 @@ static struct platform_device lcdc_device = { .resource = lcdc_resources, .dev = { .platform_data = &lcdc_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index fa3407da682..3b917bc76a4 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -421,7 +421,7 @@ static struct platform_device lcdc_device = { .resource = lcdc_resources, .dev = { .platform_data = &lcdc_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -497,7 +497,7 @@ static struct platform_device hdmi_lcdc_device = { .id = 1, .dev = { .platform_data = &hdmi_lcdc_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/arm/mach-shmobile/setup-emev2.c b/arch/arm/mach-shmobile/setup-emev2.c index 899a86c31ec..1ccddd22811 100644 --- a/arch/arm/mach-shmobile/setup-emev2.c +++ b/arch/arm/mach-shmobile/setup-emev2.c @@ -287,14 +287,14 @@ static struct gpio_em_config gio3_config = { static struct resource gio3_resources[] = { [0] = { .name = "GIO_096", - .start = 0xe0050100, - .end = 0xe005012b, + .start = 0xe0050180, + .end = 0xe00501ab, .flags = IORESOURCE_MEM, }, [1] = { .name = "GIO_096", - .start = 0xe0050140, - .end = 0xe005015f, + .start = 0xe00501c0, + .end = 0xe00501df, .flags = IORESOURCE_MEM, }, [2] = { diff --git a/arch/arm/mach-shmobile/setup-r8a73a4.c b/arch/arm/mach-shmobile/setup-r8a73a4.c index c5a75a7a508..7f45c2edbca 100644 --- a/arch/arm/mach-shmobile/setup-r8a73a4.c +++ b/arch/arm/mach-shmobile/setup-r8a73a4.c @@ -62,7 +62,7 @@ enum { SCIFA0, SCIFA1, SCIFB0, SCIFB1, SCIFB2, SCIFB3 }; static const struct plat_sci_port scif[] = { SCIFA_DATA(SCIFA0, 0xe6c40000, gic_spi(144)), /* SCIFA0 */ SCIFA_DATA(SCIFA1, 0xe6c50000, gic_spi(145)), /* SCIFA1 */ - SCIFB_DATA(SCIFB0, 0xe6c50000, gic_spi(145)), /* SCIFB0 */ + SCIFB_DATA(SCIFB0, 0xe6c20000, gic_spi(148)), /* SCIFB0 */ SCIFB_DATA(SCIFB1, 0xe6c30000, gic_spi(149)), /* SCIFB1 */ SCIFB_DATA(SCIFB2, 0xe6ce0000, gic_spi(150)), /* SCIFB2 */ SCIFB_DATA(SCIFB3, 0xe6cf0000, gic_spi(151)), /* SCIFB3 */ diff --git a/arch/arm/mach-tegra/common.c b/arch/arm/mach-tegra/common.c index 9f852c6fe5b..d5ebcd0bb62 100644 --- a/arch/arm/mach-tegra/common.c +++ b/arch/arm/mach-tegra/common.c @@ -22,6 +22,7 @@ #include <linux/io.h> #include <linux/clk.h> #include <linux/delay.h> +#include <linux/of.h> #include <linux/irqchip.h> #include <linux/clk/tegra.h> @@ -80,10 +81,20 @@ void tegra_assert_system_reset(char mode, const char *cmd) static void __init tegra_init_cache(void) { #ifdef CONFIG_CACHE_L2X0 + static const struct of_device_id pl310_ids[] __initconst = { + { .compatible = "arm,pl310-cache", }, + {} + }; + + struct device_node *np; int ret; void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000; u32 aux_ctrl, cache_type; + np = of_find_matching_node(NULL, pl310_ids); + if (!np) + return; + cache_type = readl(p + L2X0_CACHE_TYPE); aux_ctrl = (cache_type & 0x700) << (17-8); aux_ctrl |= 0x7C400001; diff --git a/arch/arm/mach-versatile/include/mach/platform.h b/arch/arm/mach-versatile/include/mach/platform.h index ec087407b16..6f938ccb0c5 100644 --- a/arch/arm/mach-versatile/include/mach/platform.h +++ b/arch/arm/mach-versatile/include/mach/platform.h @@ -231,12 +231,14 @@ /* PCI space */ #define VERSATILE_PCI_BASE 0x41000000 /* PCI Interface */ #define VERSATILE_PCI_CFG_BASE 0x42000000 +#define VERSATILE_PCI_IO_BASE 0x43000000 #define VERSATILE_PCI_MEM_BASE0 0x44000000 #define VERSATILE_PCI_MEM_BASE1 0x50000000 #define VERSATILE_PCI_MEM_BASE2 0x60000000 /* Sizes of above maps */ #define VERSATILE_PCI_BASE_SIZE 0x01000000 #define VERSATILE_PCI_CFG_BASE_SIZE 0x02000000 +#define VERSATILE_PCI_IO_BASE_SIZE 0x01000000 #define VERSATILE_PCI_MEM_BASE0_SIZE 0x0c000000 /* 32Mb */ #define VERSATILE_PCI_MEM_BASE1_SIZE 0x10000000 /* 256Mb */ #define VERSATILE_PCI_MEM_BASE2_SIZE 0x10000000 /* 256Mb */ diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c index e92e5e0705b..c97be4ea76d 100644 --- a/arch/arm/mach-versatile/pci.c +++ b/arch/arm/mach-versatile/pci.c @@ -43,9 +43,9 @@ #define PCI_IMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0) #define PCI_IMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4) #define PCI_IMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8) -#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10) -#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14) -#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18) +#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14) +#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18) +#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x1c) #define PCI_SELFID __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc) #define DEVICE_ID_OFFSET 0x00 @@ -170,8 +170,8 @@ static struct pci_ops pci_versatile_ops = { .write = versatile_write_config, }; -static struct resource io_mem = { - .name = "PCI I/O space", +static struct resource unused_mem = { + .name = "PCI unused", .start = VERSATILE_PCI_MEM_BASE0, .end = VERSATILE_PCI_MEM_BASE0+VERSATILE_PCI_MEM_BASE0_SIZE-1, .flags = IORESOURCE_MEM, @@ -195,9 +195,9 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys) { int ret = 0; - ret = request_resource(&iomem_resource, &io_mem); + ret = request_resource(&iomem_resource, &unused_mem); if (ret) { - printk(KERN_ERR "PCI: unable to allocate I/O " + printk(KERN_ERR "PCI: unable to allocate unused " "memory region (%d)\n", ret); goto out; } @@ -205,7 +205,7 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys) if (ret) { printk(KERN_ERR "PCI: unable to allocate non-prefetchable " "memory region (%d)\n", ret); - goto release_io_mem; + goto release_unused_mem; } ret = request_resource(&iomem_resource, &pre_mem); if (ret) { @@ -225,8 +225,8 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys) release_non_mem: release_resource(&non_mem); - release_io_mem: - release_resource(&io_mem); + release_unused_mem: + release_resource(&unused_mem); out: return ret; } @@ -246,7 +246,7 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys) goto out; } - ret = pci_ioremap_io(0, VERSATILE_PCI_MEM_BASE0); + ret = pci_ioremap_io(0, VERSATILE_PCI_IO_BASE); if (ret) goto out; @@ -295,6 +295,19 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys) __raw_writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_2); /* + * For many years the kernel and QEMU were symbiotically buggy + * in that they both assumed the same broken IRQ mapping. + * QEMU therefore attempts to auto-detect old broken kernels + * so that they still work on newer QEMU as they did on old + * QEMU. Since we now use the correct (ie matching-hardware) + * IRQ mapping we write a definitely different value to a + * PCI_INTERRUPT_LINE register to tell QEMU that we expect + * real hardware behaviour and it need not be backwards + * compatible for us. This write is harmless on real hardware. + */ + __raw_writel(0, VERSATILE_PCI_VIRT_BASE+PCI_INTERRUPT_LINE); + + /* * Do not to map Versatile FPGA PCI device into memory space */ pci_slot_ignore |= (1 << myslot); @@ -327,13 +340,13 @@ static int __init versatile_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { int irq; - /* slot, pin, irq - * 24 1 IRQ_SIC_PCI0 - * 25 1 IRQ_SIC_PCI1 - * 26 1 IRQ_SIC_PCI2 - * 27 1 IRQ_SIC_PCI3 + /* + * Slot INTA INTB INTC INTD + * 31 PCI1 PCI2 PCI3 PCI0 + * 30 PCI0 PCI1 PCI2 PCI3 + * 29 PCI3 PCI0 PCI1 PCI2 */ - irq = IRQ_SIC_PCI0 + ((slot - 24 + pin - 1) & 3); + irq = IRQ_SIC_PCI0 + ((slot + 2 + pin - 1) & 3); return irq; } diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig index dd3d5975a5c..39858ba0308 100644 --- a/arch/arm/mach-vexpress/Kconfig +++ b/arch/arm/mach-vexpress/Kconfig @@ -3,6 +3,7 @@ config ARCH_VEXPRESS select ARCH_HAS_CPUFREQ select ARCH_HAS_OPP select ARCH_REQUIRE_GPIOLIB + select ARCH_SUPPORTS_BIG_ENDIAN select ARM_AMBA select ARM_GIC select ARM_TIMER_SP804 diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 35955b54944..7763900dee8 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -411,24 +411,28 @@ config CPU_32v3 select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP select TLS_REG_EMUL if SMP || !MMU + select NEED_KUSER_HELPERS config CPU_32v4 bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP select TLS_REG_EMUL if SMP || !MMU + select NEED_KUSER_HELPERS config CPU_32v4T bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP select TLS_REG_EMUL if SMP || !MMU + select NEED_KUSER_HELPERS config CPU_32v5 bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP select TLS_REG_EMUL if SMP || !MMU + select NEED_KUSER_HELPERS config CPU_32v6 bool @@ -756,6 +760,7 @@ config CPU_BPREDICT_DISABLE config TLS_REG_EMUL bool + select NEED_KUSER_HELPERS help An SMP system using a pre-ARMv6 processor (there are apparently a few prototypes like that in existence) and therefore access to @@ -763,11 +768,43 @@ config TLS_REG_EMUL config NEEDS_SYSCALL_FOR_CMPXCHG bool + select NEED_KUSER_HELPERS help SMP on a pre-ARMv6 processor? Well OK then. Forget about fast user space cmpxchg support. It is just not possible. +config NEED_KUSER_HELPERS + bool + +config KUSER_HELPERS + bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS + default y + help + Warning: disabling this option may break user programs. + + Provide kuser helpers in the vector page. The kernel provides + helper code to userspace in read only form at a fixed location + in the high vector page to allow userspace to be independent of + the CPU type fitted to the system. This permits binaries to be + run on ARMv4 through to ARMv7 without modification. + + See Documentation/arm/kernel_user_helpers.txt for details. + + However, the fixed address nature of these helpers can be used + by ROP (return orientated programming) authors when creating + exploits. + + If all of the binaries and libraries which run on your platform + are built specifically for your platform, and make no use of + these helpers, then you can turn this option off to hinder + such exploits. However, in that case, if a binary or library + relying on those helpers is run, it will receive a SIGILL signal, + which will terminate the program. + + Say N here only if you are absolutely certain that you do not + need these helpers; otherwise, the safe option is to say Y. + config DMA_CACHE_RWFO bool "Enable read/write for ownership DMA cache maintenance" depends on CPU_V6K && SMP @@ -895,3 +932,9 @@ config ARCH_HAS_BARRIERS help This option allows the use of custom mandatory barriers included via the mach/barriers.h file. + +config ARCH_SUPPORTS_BIG_ENDIAN + bool + help + This option specifies the architecture can support big endian + operation. diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 80741992a9f..3815a8262af 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -38,9 +38,8 @@ ENTRY(v6_early_abort) bne do_DataAbort bic r1, r1, #1 << 11 @ clear bit 11 of FSR ldr r3, [r4] @ read aborted ARM instruction -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r3, r3 -#endif + ARM_BE8(rev r3, r3) + do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 6f4585b8907..924036473b1 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -25,6 +25,7 @@ #include <asm/cp15.h> #include <asm/system_info.h> #include <asm/unaligned.h> +#include <asm/opcodes.h> #include "fault.h" @@ -762,21 +763,25 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (thumb_mode(regs)) { u16 *ptr = (u16 *)(instrptr & ~1); fault = probe_kernel_address(ptr, tinstr); + tinstr = __mem_to_opcode_thumb16(tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ u16 tinst2 = 0; fault = probe_kernel_address(ptr + 1, tinst2); - instr = (tinstr << 16) | tinst2; + tinst2 = __mem_to_opcode_thumb16(tinst2); + instr = __opcode_thumb32_compose(tinstr, tinst2); thumb2_32b = 1; } else { isize = 2; instr = thumb2arm(tinstr); } } - } else + } else { fault = probe_kernel_address(instrptr, instr); + instr = __mem_to_opcode_arm(instr); + } if (fault) { type = TYPE_FAULT; diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 515b00064da..a84e0536ce7 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -146,18 +146,18 @@ flush_levels: ldr r7, =0x7fff ands r7, r7, r1, lsr #13 @ extract max number of the index size loop1: - mov r9, r4 @ create working copy of max way size + mov r9, r7 @ create working copy of max index loop2: - ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11 - THUMB( lsl r6, r9, r5 ) + ARM( orr r11, r10, r4, lsl r5 ) @ factor way and cache number into r11 + THUMB( lsl r6, r4, r5 ) THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11 - ARM( orr r11, r11, r7, lsl r2 ) @ factor index number into r11 - THUMB( lsl r6, r7, r2 ) + ARM( orr r11, r11, r9, lsl r2 ) @ factor index number into r11 + THUMB( lsl r6, r9, r2 ) THUMB( orr r11, r11, r6 ) @ factor index number into r11 mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way - subs r9, r9, #1 @ decrement the way + subs r9, r9, #1 @ decrement the index bge loop2 - subs r7, r7, #1 @ decrement the index + subs r4, r4, #1 @ decrement the way bge loop1 skip: add r10, r10, #2 @ increment cache number diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 2ac37372ef5..eeab06ebd06 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -39,19 +39,43 @@ * non 64-bit operations. */ #define ASID_FIRST_VERSION (1ULL << ASID_BITS) -#define NUM_USER_ASIDS (ASID_FIRST_VERSION - 1) - -#define ASID_TO_IDX(asid) ((asid & ~ASID_MASK) - 1) -#define IDX_TO_ASID(idx) ((idx + 1) & ~ASID_MASK) +#define NUM_USER_ASIDS ASID_FIRST_VERSION static DEFINE_RAW_SPINLOCK(cpu_asid_lock); static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION); static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS); -DEFINE_PER_CPU(atomic64_t, active_asids); +static DEFINE_PER_CPU(atomic64_t, active_asids); static DEFINE_PER_CPU(u64, reserved_asids); static cpumask_t tlb_flush_pending; +#ifdef CONFIG_ARM_ERRATA_798181 +void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask) +{ + int cpu; + unsigned long flags; + u64 context_id, asid; + + raw_spin_lock_irqsave(&cpu_asid_lock, flags); + context_id = mm->context.id.counter; + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + /* + * We only need to send an IPI if the other CPUs are + * running the same ASID as the one being invalidated. + */ + asid = per_cpu(active_asids, cpu).counter; + if (asid == 0) + asid = per_cpu(reserved_asids, cpu); + if (context_id == asid) + cpumask_set_cpu(cpu, mask); + } + raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); +} +#endif + #ifdef CONFIG_ARM_LPAE static void cpu_set_reserved_ttbr0(void) { @@ -128,7 +152,16 @@ static void flush_context(unsigned int cpu) asid = 0; } else { asid = atomic64_xchg(&per_cpu(active_asids, i), 0); - __set_bit(ASID_TO_IDX(asid), asid_map); + /* + * If this CPU has already been through a + * rollover, but hasn't run another task in + * the meantime, we must preserve its reserved + * ASID, as this is the only trace we have of + * the process it is still running. + */ + if (asid == 0) + asid = per_cpu(reserved_asids, i); + __set_bit(asid & ~ASID_MASK, asid_map); } per_cpu(reserved_asids, i) = asid; } @@ -167,17 +200,19 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) /* * Allocate a free ASID. If we can't find one, take a * note of the currently active ASIDs and mark the TLBs - * as requiring flushes. + * as requiring flushes. We always count from ASID #1, + * as we reserve ASID #0 to switch via TTBR0 and indicate + * rollover events. */ - asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS); + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); if (asid == NUM_USER_ASIDS) { generation = atomic64_add_return(ASID_FIRST_VERSION, &asid_generation); flush_context(cpu); - asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS); + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); } __set_bit(asid, asid_map); - asid = generation | IDX_TO_ASID(asid); + asid |= generation; cpumask_clear(mm_cpumask(mm)); } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index ef3e0f3aac9..6c9d7054d99 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1311,7 +1311,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (gfp & GFP_ATOMIC) + if (!(gfp & __GFP_WAIT)) return __iommu_alloc_atomic(dev, size, handle); pages = __iommu_alloc_buffer(dev, size, gfp, attrs); diff --git a/arch/arm/mm/extable.c b/arch/arm/mm/extable.c index 9d285626bc7..312e15e6d00 100644 --- a/arch/arm/mm/extable.c +++ b/arch/arm/mm/extable.c @@ -9,8 +9,13 @@ int fixup_exception(struct pt_regs *regs) const struct exception_table_entry *fixup; fixup = search_exception_tables(instruction_pointer(regs)); - if (fixup) + if (fixup) { regs->ARM_pc = fixup->fixup; +#ifdef CONFIG_THUMB2_KERNEL + /* Clear the IT state to avoid nasty surprises in the fixup */ + regs->ARM_cpsr &= ~PSR_IT_MASK; +#endif + } return fixup != NULL; } diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 9a5cdc01fcd..0ecc43fd622 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -600,7 +600,7 @@ void __init mem_init(void) #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ - free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL); + free_reserved_area(__va(PHYS_OFFSET), swapper_pg_dir, 0, NULL); #endif free_highpages(); diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 10062ceadd1..f0ef2f7d4ad 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -146,7 +146,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = PAGE_SIZE; + info.low_limit = FIRST_USER_ADDRESS; info.high_limit = mm->mmap_base; info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0; info.align_offset = pgoff << PAGE_SHIFT; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4d409e6a552..daf336fe0be 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1175,7 +1175,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) /* * Allocate the vector page early. */ - vectors = early_alloc(PAGE_SIZE); + vectors = early_alloc(PAGE_SIZE * 2); early_trap_init(vectors); @@ -1220,15 +1220,27 @@ static void __init devicemaps_init(struct machine_desc *mdesc) map.pfn = __phys_to_pfn(virt_to_phys(vectors)); map.virtual = 0xffff0000; map.length = PAGE_SIZE; +#ifdef CONFIG_KUSER_HELPERS map.type = MT_HIGH_VECTORS; +#else + map.type = MT_LOW_VECTORS; +#endif create_mapping(&map); if (!vectors_high()) { map.virtual = 0; + map.length = PAGE_SIZE * 2; map.type = MT_LOW_VECTORS; create_mapping(&map); } + /* Now create a kernel read-only mapping */ + map.pfn += 1; + map.virtual = 0xffff0000 + PAGE_SIZE; + map.length = PAGE_SIZE; + map.type = MT_LOW_VECTORS; + create_mapping(&map); + /* * Ask the machine support to map in the statically mapped devices. */ diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index 0acb089d0f7..1046b373d1a 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -87,7 +87,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm) init_pud = pud_offset(init_pgd, 0); init_pmd = pmd_offset(init_pud, 0); init_pte = pte_offset_map(init_pmd, 0); - set_pte_ext(new_pte, *init_pte, 0); + set_pte_ext(new_pte + 0, init_pte[0], 0); + set_pte_ext(new_pte + 1, init_pte[1], 0); pte_unmap(init_pte); pte_unmap(new_pte); } diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 919405e20b8..b96c6e64943 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -206,7 +206,6 @@ __v6_setup: mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c15, 0 @ clean+invalidate cache - mcr p15, 0, r0, c7, c10, 4 @ drain write buffer #ifdef CONFIG_MMU mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs mcr p15, 0, r0, c2, c0, 2 @ TTB control register @@ -216,11 +215,11 @@ __v6_setup: ALT_UP(orr r8, r8, #TTB_FLAGS_UP) mcr p15, 0, r8, c2, c0, 1 @ load TTB1 #endif /* CONFIG_MMU */ + mcr p15, 0, r0, c7, c10, 4 @ drain write buffer and + @ complete invalidations adr r5, v6_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables mrc p15, 0, r0, c1, c0, 0 @ read control register bic r0, r0, r5 @ clear bits them orr r0, r0, r6 @ set them diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index 9704097c450..b3997c70af3 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -110,7 +110,7 @@ ENTRY(cpu_v7_set_pte_ext) ARM( str r3, [r0, #2048]! ) THUMB( add r0, r0, #2048 ) THUMB( str r3, [r0] ) - ALT_SMP(mov pc,lr) + ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif mov pc, lr diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 363027e811d..6ba4bd9118f 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -73,7 +73,7 @@ ENTRY(cpu_v7_set_pte_ext) tst r3, #1 << (55 - 32) @ L_PTE_DIRTY orreq r2, #L_PTE_RDONLY 1: strd r2, r3, [r0] - ALT_SMP(mov pc, lr) + ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif mov pc, lr diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index e35fec34453..769496e6e8e 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -75,13 +75,14 @@ ENTRY(cpu_v7_do_idle) ENDPROC(cpu_v7_do_idle) ENTRY(cpu_v7_dcache_clean_area) - ALT_SMP(mov pc, lr) @ MP extensions imply L1 PTW - ALT_UP(W(nop)) - dcache_line_size r2, r3 -1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry + ALT_SMP(W(nop)) @ MP extensions imply L1 PTW + ALT_UP_B(1f) + mov pc, lr +1: dcache_line_size r2, r3 +2: mcr p15, 0, r0, c7, c10, 1 @ clean D entry add r0, r0, r2 subs r1, r1, r2 - bhi 1b + bhi 2b dsb mov pc, lr ENDPROC(cpu_v7_dcache_clean_area) @@ -328,7 +329,6 @@ __v7_setup: 3: mov r10, #0 mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate - dsb #ifdef CONFIG_MMU mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs v7_ttb_setup r10, r4, r8, r5 @ TTBCR, TTBRx setup @@ -337,6 +337,7 @@ __v7_setup: mcr p15, 0, r5, c10, c2, 0 @ write PRRR mcr p15, 0, r6, c10, c2, 1 @ write NMRR #endif + dsb @ Complete invalidations #ifndef CONFIG_ARM_THUMBEE mrc p15, 0, r0, c0, c1, 0 @ read ID_PFR0 for ThumbEE and r0, r0, #(0xf << 12) @ ThumbEE enabled field @@ -351,9 +352,7 @@ __v7_setup: #endif adr r5, v7_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables #ifdef CONFIG_SWP_EMULATE orr r5, r5, #(1 << 10) @ set SW bit in "clear" bic r6, r6, #(1 << 10) @ clear it in "mmuset" diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1a643ee8e08..78351ca8d51 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -19,6 +19,7 @@ #include <linux/if_vlan.h> #include <asm/cacheflush.h> #include <asm/hwcap.h> +#include <asm/opcodes.h> #include "bpf_jit_32.h" @@ -113,8 +114,11 @@ static u32 jit_udiv(u32 dividend, u32 divisor) static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx) { + inst |= (cond << 28); + inst = __opcode_to_mem_arm(inst); + if (ctx->target != NULL) - ctx->target[ctx->idx] = inst | (cond << 28); + ctx->target[ctx->idx] = inst; ctx->idx++; } @@ -637,10 +641,10 @@ load_ind: emit(ARM_MUL(r_A, r_A, r_X), ctx); break; case BPF_S_ALU_DIV_K: - /* current k == reciprocal_value(userspace k) */ + if (k == 1) + break; emit_mov_i(r_scratch, k, ctx); - /* A = top 32 bits of the product */ - emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx); + emit_udiv(r_A, r_A, r_scratch, ctx); break; case BPF_S_ALU_DIV_X: update_on_xread(ctx); diff --git a/arch/arm/plat-samsung/include/plat/clock.h b/arch/arm/plat-samsung/include/plat/clock.h index a62753dc15b..df45d6edc98 100644 --- a/arch/arm/plat-samsung/include/plat/clock.h +++ b/arch/arm/plat-samsung/include/plat/clock.h @@ -83,6 +83,11 @@ extern struct clk clk_ext; extern struct clksrc_clk clk_epllref; extern struct clksrc_clk clk_esysclk; +/* S3C24XX UART clocks */ +extern struct clk s3c24xx_clk_uart0; +extern struct clk s3c24xx_clk_uart1; +extern struct clk s3c24xx_clk_uart2; + /* S3C64XX specific clocks */ extern struct clk clk_h2; extern struct clk clk_27m; diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S index 2677bc3762d..40f27e52de7 100644 --- a/arch/arm/plat-versatile/headsmp.S +++ b/arch/arm/plat-versatile/headsmp.S @@ -10,6 +10,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> /* * Realview/Versatile Express specific entry point for secondary CPUs. @@ -17,6 +18,7 @@ * until we're ready for them to initialise. */ ENTRY(versatile_secondary_startup) + ARM_BE8(setend be) mrc p15, 0, r0, c0, c0, 5 bic r0, #0xff000000 adr r4, 1f diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 13609e01f4b..81edd31bb4a 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -170,6 +170,7 @@ static void __init xen_percpu_init(void *unused) per_cpu(xen_vcpu, cpu) = vcpup; enable_percpu_irq(xen_events_irq, 0); + put_cpu(); } static void xen_restart(char str, const char *cmd) @@ -272,12 +273,15 @@ core_initcall(xen_guest_init); static int __init xen_pm_init(void) { + if (!xen_domain()) + return -ENODEV; + pm_power_off = xen_power_off; arm_pm_restart = xen_restart; return 0; } -subsys_initcall(xen_pm_init); +late_initcall(xen_pm_init); static irqreturn_t xen_arm_callback(int irq, void *arg) { |