diff options
Diffstat (limited to 'arch/arm')
143 files changed, 6941 insertions, 859 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 8468902333a0..366658cf7cb6 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1588,6 +1588,91 @@ 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). + +config SCHED_HMP_PRIO_FILTER + bool "(EXPERIMENTAL) Filter HMP migrations by task priority" + depends on SCHED_HMP + default y + 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 thresholds and load average + period value for the load tracking patches through sysfs. + The values can be modified to change the rate of load accumulation + and the thresholds used for HMP migration. + The 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 that start a busy loop. + The up_threshold and down_threshold is the value to go to a faster + CPU or to go back to a slower cpu. + The {up,down}_threshold are devided by 1024 before being compared + to the load average. + For examples, 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 it remove intermadiate overflows in computation. + +config HMP_FREQUENCY_INVARIANT_SCALE + bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP" + depends on HMP_VARIABLE_SCALE && 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 HAVE_ARM_SCU bool help @@ -1606,6 +1691,39 @@ config HAVE_ARM_TWD help This options enables support for the ARM timer and watchdog unit +config MCPM + bool "Multi-Cluster Power Management" + depends on CPU_V7 && SMP + help + This option provides the common power management infrastructure + for (multi-)cluster based systems, such as big.LITTLE based + systems. + +config BIG_LITTLE + bool "big.LITTLE support (Experimental)" + depends on CPU_V7 && SMP + select MCPM + 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 @@ -1693,8 +1811,9 @@ config SCHED_HRTICK def_bool HIGH_RES_TIMERS config THUMB2_KERNEL - bool "Compile the kernel in Thumb-2 mode" + bool "Compile the kernel in Thumb-2 mode" if !CPU_THUMBONLY depends on CPU_V7 && !CPU_V6 && !CPU_V6K + default y if CPU_THUMBONLY select AEABI select ARM_ASM_UNIFIED select ARM_UNWIND diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index afed28e37ea5..27f360421340 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -121,7 +121,7 @@ KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) endif ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj) -asflags-y := -Wa,-march=all -DZIMAGE +asflags-y := -DZIMAGE # Supply kernel BSS size to the decompressor via a linker symbol. KBSS_SZ = $(shell $(CROSS_COMPILE)size $(obj)/../../../../vmlinux | \ diff --git a/arch/arm/boot/compressed/head-sa1100.S b/arch/arm/boot/compressed/head-sa1100.S index 6179d94dd5c6..3115e313d9f6 100644 --- a/arch/arm/boot/compressed/head-sa1100.S +++ b/arch/arm/boot/compressed/head-sa1100.S @@ -11,6 +11,7 @@ #include <asm/mach-types.h> .section ".start", "ax" + .arch armv4 __SA1100_start: diff --git a/arch/arm/boot/compressed/head-shark.S b/arch/arm/boot/compressed/head-shark.S index 089c560e07f1..92b56897ed64 100644 --- a/arch/arm/boot/compressed/head-shark.S +++ b/arch/arm/boot/compressed/head-shark.S @@ -18,6 +18,7 @@ .section ".start", "ax" + .arch armv4 b __beginning __ofw_data: .long 0 @ the number of memory blocks diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 9a94f344df41..2581642d64ed 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -11,6 +11,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> + .arch armv7-a /* * Debugging stuff * diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 9c6255884cbb..2fc92bf10cc4 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -169,7 +169,14 @@ dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \ vexpress-v2p-ca9.dtb \ vexpress-v2p-ca15-tc1.dtb \ vexpress-v2p-ca15_a7.dtb \ - xenvm-4.2.dtb + xenvm-4.2.dtb \ + rtsm_ve-cortex_a9x2.dtb \ + rtsm_ve-cortex_a9x4.dtb \ + rtsm_ve-cortex_a15x1.dtb \ + rtsm_ve-cortex_a15x2.dtb \ + rtsm_ve-cortex_a15x4.dtb \ + rtsm_ve-v2p-ca15x1-ca7x1.dtb \ + rtsm_ve-v2p-ca15x4-ca7x4.dtb dtb-$(CONFIG_ARCH_VT8500) += vt8500-bv07.dtb \ wm8505-ref.dtb \ wm8650-mid.dtb \ diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi index cb7bcc51608d..755a61e8ca89 100644 --- a/arch/arm/boot/dts/at91sam9260.dtsi +++ b/arch/arm/boot/dts/at91sam9260.dtsi @@ -158,8 +158,8 @@ usart1 { pinctrl_usart1: usart1-0 { atmel,pins = - <2 6 0x1 0x1 /* PB6 periph A with pullup */ - 2 7 0x1 0x0>; /* PB7 periph A */ + <1 6 0x1 0x1 /* PB6 periph A with pullup */ + 1 7 0x1 0x0>; /* PB7 periph A */ }; pinctrl_usart1_rts: usart1_rts-0 { @@ -194,18 +194,18 @@ usart3 { pinctrl_usart3: usart3-0 { atmel,pins = - <2 10 0x1 0x1 /* PB10 periph A with pullup */ - 2 11 0x1 0x0>; /* PB11 periph A */ + <1 10 0x1 0x1 /* PB10 periph A with pullup */ + 1 11 0x1 0x0>; /* PB11 periph A */ }; pinctrl_usart3_rts: usart3_rts-0 { atmel,pins = - <3 8 0x2 0x0>; /* PB8 periph B */ + <2 8 0x2 0x0>; /* PC8 periph B */ }; pinctrl_usart3_cts: usart3_cts-0 { atmel,pins = - <3 10 0x2 0x0>; /* PB10 periph B */ + <2 10 0x2 0x0>; /* PC10 periph B */ }; }; @@ -220,8 +220,8 @@ uart1 { pinctrl_uart1: uart1-0 { atmel,pins = - <2 12 0x1 0x1 /* PB12 periph A with pullup */ - 2 13 0x1 0x0>; /* PB13 periph A */ + <1 12 0x1 0x1 /* PB12 periph A with pullup */ + 1 13 0x1 0x0>; /* PB13 periph A */ }; }; @@ -264,7 +264,7 @@ atmel,pins = <0 10 0x2 0x0 /* PA10 periph B */ 0 11 0x2 0x0 /* PA11 periph B */ - 0 24 0x2 0x0 /* PA24 periph B */ + 0 22 0x2 0x0 /* PA22 periph B */ 0 25 0x2 0x0 /* PA25 periph B */ 0 26 0x2 0x0 /* PA26 periph B */ 0 27 0x2 0x0 /* PA27 periph B */ diff --git a/arch/arm/boot/dts/at91sam9g15.dtsi b/arch/arm/boot/dts/at91sam9g15.dtsi index fbe7a7089c2a..28467fd6bf96 100644 --- a/arch/arm/boot/dts/at91sam9g15.dtsi +++ b/arch/arm/boot/dts/at91sam9g15.dtsi @@ -10,7 +10,7 @@ / { model = "Atmel AT91SAM9G15 SoC"; - compatible = "atmel, at91sam9g15, atmel,at91sam9x5"; + compatible = "atmel,at91sam9g15", "atmel,at91sam9x5"; ahb { apb { diff --git a/arch/arm/boot/dts/at91sam9g15ek.dts b/arch/arm/boot/dts/at91sam9g15ek.dts index 86dd3f6d938f..5427b2dba87e 100644 --- a/arch/arm/boot/dts/at91sam9g15ek.dts +++ b/arch/arm/boot/dts/at91sam9g15ek.dts @@ -11,6 +11,6 @@ /include/ "at91sam9x5ek.dtsi" / { - model = "Atmel AT91SAM9G25-EK"; + model = "Atmel AT91SAM9G15-EK"; compatible = "atmel,at91sam9g15ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9"; }; diff --git a/arch/arm/boot/dts/at91sam9g25.dtsi b/arch/arm/boot/dts/at91sam9g25.dtsi index 05a718fb83c4..5fd32df03f25 100644 --- a/arch/arm/boot/dts/at91sam9g25.dtsi +++ b/arch/arm/boot/dts/at91sam9g25.dtsi @@ -10,7 +10,7 @@ / { model = "Atmel AT91SAM9G25 SoC"; - compatible = "atmel, at91sam9g25, atmel,at91sam9x5"; + compatible = "atmel,at91sam9g25", "atmel,at91sam9x5"; ahb { apb { diff --git a/arch/arm/boot/dts/at91sam9g35.dtsi b/arch/arm/boot/dts/at91sam9g35.dtsi index f9d14a722794..d6fa8af50724 100644 --- a/arch/arm/boot/dts/at91sam9g35.dtsi +++ b/arch/arm/boot/dts/at91sam9g35.dtsi @@ -10,7 +10,7 @@ / { model = "Atmel AT91SAM9G35 SoC"; - compatible = "atmel, at91sam9g35, atmel,at91sam9x5"; + compatible = "atmel,at91sam9g35", "atmel,at91sam9x5"; ahb { apb { diff --git a/arch/arm/boot/dts/at91sam9x25.dtsi b/arch/arm/boot/dts/at91sam9x25.dtsi index 54eb33ba6d22..9ac2bc2b4f07 100644 --- a/arch/arm/boot/dts/at91sam9x25.dtsi +++ b/arch/arm/boot/dts/at91sam9x25.dtsi @@ -10,7 +10,7 @@ / { model = "Atmel AT91SAM9X25 SoC"; - compatible = "atmel, at91sam9x25, atmel,at91sam9x5"; + compatible = "atmel,at91sam9x25", "atmel,at91sam9x5"; ahb { apb { diff --git a/arch/arm/boot/dts/at91sam9x25ek.dts b/arch/arm/boot/dts/at91sam9x25ek.dts index af907eaa1f25..80015b0d4c12 100644 --- a/arch/arm/boot/dts/at91sam9x25ek.dts +++ b/arch/arm/boot/dts/at91sam9x25ek.dts @@ -11,6 +11,6 @@ /include/ "at91sam9x5ek.dtsi" / { - model = "Atmel AT91SAM9G25-EK"; + model = "Atmel AT91SAM9X25-EK"; compatible = "atmel,at91sam9x25ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9"; }; diff --git a/arch/arm/boot/dts/at91sam9x35.dtsi b/arch/arm/boot/dts/at91sam9x35.dtsi index fb102d6126ce..ba67d83d17ac 100644 --- a/arch/arm/boot/dts/at91sam9x35.dtsi +++ b/arch/arm/boot/dts/at91sam9x35.dtsi @@ -10,7 +10,7 @@ / { model = "Atmel AT91SAM9X35 SoC"; - compatible = "atmel, at91sam9x35, atmel,at91sam9x5"; + compatible = "atmel,at91sam9x35", "atmel,at91sam9x5"; ahb { apb { diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi index 8a7cf1d9cf5d..ccab2568b0d7 100644 --- a/arch/arm/boot/dts/at91sam9x5ek.dtsi +++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi @@ -13,7 +13,7 @@ compatible = "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9"; chosen { - bootargs = "128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs"; + bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs"; }; ahb { diff --git a/arch/arm/boot/dts/clcd-panels.dtsi b/arch/arm/boot/dts/clcd-panels.dtsi new file mode 100644 index 000000000000..0b0ff6ead4b2 --- /dev/null +++ b/arch/arm/boot/dts/clcd-panels.dtsi @@ -0,0 +1,52 @@ +/* + * ARM Ltd. Versatile Express + * + */ + +/ { + panels { + panel@0 { + compatible = "panel"; + mode = "VGA"; + refresh = <60>; + xres = <640>; + yres = <480>; + pixclock = <39721>; + left_margin = <40>; + right_margin = <24>; + upper_margin = <32>; + lower_margin = <11>; + hsync_len = <96>; + vsync_len = <2>; + sync = <0>; + vmode = "FB_VMODE_NONINTERLACED"; + + tim2 = "TIM2_BCD", "TIM2_IPC"; + cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)"; + caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888"; + bpp = <16>; + }; + + panel@1 { + compatible = "panel"; + mode = "XVGA"; + refresh = <60>; + xres = <1024>; + yres = <768>; + pixclock = <15748>; + left_margin = <152>; + right_margin = <48>; + upper_margin = <23>; + lower_margin = <3>; + hsync_len = <104>; + vsync_len = <4>; + sync = <0>; + vmode = "FB_VMODE_NONINTERLACED"; + + tim2 = "TIM2_BCD", "TIM2_IPC"; + cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)"; + caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888"; + bpp = <16>; + }; + }; +}; diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts new file mode 100644 index 000000000000..c9eee916aa7e --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts @@ -0,0 +1,159 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x1CT + * + * RTSM_VE_Cortex_A15x1.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA15x1"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x1", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts new file mode 100644 index 000000000000..853a166e3c32 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts @@ -0,0 +1,165 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x2CT + * + * RTSM_VE_Cortex_A15x2.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA15x2"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x2", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <1>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts new file mode 100644 index 000000000000..c1947a3a5c88 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts @@ -0,0 +1,177 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x4CT + * + * RTSM_VE_Cortex_A15x4.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA15x4"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x4", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <1>; + }; + + cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <2>; + }; + + cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <3>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts new file mode 100644 index 000000000000..fca6b2f79677 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts @@ -0,0 +1,171 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA9MPx2CT + * + * RTSM_VE_Cortex_A9x2.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA9x2"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a9x2", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <1>; + #size-cells = <1>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <1>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x80000000>; + }; + + scu@2c000000 { + compatible = "arm,cortex-a9-scu"; + reg = <0x2c000000 0x58>; + }; + + timer@2c000600 { + compatible = "arm,cortex-a9-twd-timer"; + reg = <0x2c000600 0x20>; + interrupts = <1 13 0xf04>; + }; + + watchdog@2c000620 { + compatible = "arm,cortex-a9-twd-wdt"; + reg = <0x2c000620 0x20>; + interrupts = <1 14 0xf04>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0x2c001000 0x1000>, + <0x2c000100 0x100>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0x08000000 0x04000000>, + <1 0 0x14000000 0x04000000>, + <2 0 0x18000000 0x04000000>, + <3 0 0x1c000000 0x04000000>, + <4 0 0x0c000000 0x04000000>, + <5 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts new file mode 100644 index 000000000000..fd8a6ed97a04 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts @@ -0,0 +1,183 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA9MPx4CT + * + * RTSM_VE_Cortex_A9x4.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA9x4"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a9x4", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <1>; + #size-cells = <1>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <1>; + }; + + cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <2>; + }; + + cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <3>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x80000000>; + }; + + scu@2c000000 { + compatible = "arm,cortex-a9-scu"; + reg = <0x2c000000 0x58>; + }; + + timer@2c000600 { + compatible = "arm,cortex-a9-twd-timer"; + reg = <0x2c000600 0x20>; + interrupts = <1 13 0xf04>; + }; + + watchdog@2c000620 { + compatible = "arm,cortex-a9-twd-wdt"; + reg = <0x2c000620 0x20>; + interrupts = <1 14 0xf04>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0x2c001000 0x1000>, + <0x2c000100 0x100>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0x08000000 0x04000000>, + <1 0 0x14000000 0x04000000>, + <2 0 0x18000000 0x04000000>, + <3 0 0x1c000000 0x04000000>, + <4 0 0x0c000000 0x04000000>, + <5 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi new file mode 100644 index 000000000000..6d1256626125 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi @@ -0,0 +1,224 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * Motherboard component + * + * VEMotherBoard.lisa + */ + + motherboard { + compatible = "arm,vexpress,v2m-p1", "simple-bus"; + arm,hbi = <0x190>; + arm,vexpress,site = <0>; + arm,v2m-memory-map = "rs1"; + #address-cells = <2>; /* SMB chipselect number and offset */ + #size-cells = <1>; + #interrupt-cells = <1>; + ranges; + + flash@0,00000000 { + compatible = "arm,vexpress-flash", "cfi-flash"; + reg = <0 0x00000000 0x04000000>, + <4 0x00000000 0x04000000>; + bank-width = <4>; + }; + + vram@2,00000000 { + compatible = "arm,vexpress-vram"; + reg = <2 0x00000000 0x00800000>; + }; + + ethernet@2,02000000 { + compatible = "smsc,lan91c111"; + reg = <2 0x02000000 0x10000>; + interrupts = <15>; + }; + + iofpga@3,00000000 { + compatible = "arm,amba-bus", "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 3 0 0x200000>; + + v2m_sysreg: sysreg@010000 { + compatible = "arm,vexpress-sysreg"; + reg = <0x010000 0x1000>; + gpio-controller; + #gpio-cells = <2>; + }; + + v2m_sysctl: sysctl@020000 { + compatible = "arm,sp810", "arm,primecell"; + reg = <0x020000 0x1000>; + clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&smbclk>; + clock-names = "refclk", "timclk", "apb_pclk"; + #clock-cells = <1>; + clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3"; + }; + + aaci@040000 { + compatible = "arm,pl041", "arm,primecell"; + reg = <0x040000 0x1000>; + interrupts = <11>; + clocks = <&smbclk>; + clock-names = "apb_pclk"; + }; + + mmci@050000 { + compatible = "arm,pl180", "arm,primecell"; + reg = <0x050000 0x1000>; + interrupts = <9 10>; + cd-gpios = <&v2m_sysreg 0 0>; + wp-gpios = <&v2m_sysreg 1 0>; + max-frequency = <12000000>; + vmmc-supply = <&v2m_fixed_3v3>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "mclk", "apb_pclk"; + }; + + kmi@060000 { + compatible = "arm,pl050", "arm,primecell"; + reg = <0x060000 0x1000>; + interrupts = <12>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "KMIREFCLK", "apb_pclk"; + }; + + kmi@070000 { + compatible = "arm,pl050", "arm,primecell"; + reg = <0x070000 0x1000>; + interrupts = <13>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "KMIREFCLK", "apb_pclk"; + }; + + v2m_serial0: uart@090000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x090000 0x1000>; + interrupts = <5>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "uartclk", "apb_pclk"; + }; + + v2m_serial1: uart@0a0000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0a0000 0x1000>; + interrupts = <6>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "uartclk", "apb_pclk"; + }; + + v2m_serial2: uart@0b0000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0b0000 0x1000>; + interrupts = <7>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "uartclk", "apb_pclk"; + }; + + v2m_serial3: uart@0c0000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0c0000 0x1000>; + interrupts = <8>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "uartclk", "apb_pclk"; + }; + + wdt@0f0000 { + compatible = "arm,sp805", "arm,primecell"; + reg = <0x0f0000 0x1000>; + interrupts = <0>; + clocks = <&v2m_refclk32khz>, <&smbclk>; + clock-names = "wdogclk", "apb_pclk"; + }; + + v2m_timer01: timer@110000 { + compatible = "arm,sp804", "arm,primecell"; + reg = <0x110000 0x1000>; + interrupts = <2>; + clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&smbclk>; + clock-names = "timclken1", "timclken2", "apb_pclk"; + }; + + v2m_timer23: timer@120000 { + compatible = "arm,sp804", "arm,primecell"; + reg = <0x120000 0x1000>; + interrupts = <3>; + clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&smbclk>; + clock-names = "timclken1", "timclken2", "apb_pclk"; + }; + + rtc@170000 { + compatible = "arm,pl031", "arm,primecell"; + reg = <0x170000 0x1000>; + interrupts = <4>; + clocks = <&smbclk>; + clock-names = "apb_pclk"; + }; + + clcd@1f0000 { + compatible = "arm,pl111", "arm,primecell"; + reg = <0x1f0000 0x1000>; + interrupts = <14>; + clocks = <&v2m_oscclk1>, <&smbclk>; + clock-names = "v2m:oscclk1", "apb_pclk"; + mode = "VGA"; + use_dma = <0>; + framebuffer = <0x18000000 0x00180000>; + }; + }; + + v2m_fixed_3v3: fixedregulator@0 { + compatible = "regulator-fixed"; + regulator-name = "3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + v2m_clk24mhz: clk24mhz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <24000000>; + clock-output-names = "v2m:clk24mhz"; + }; + + v2m_refclk1mhz: refclk1mhz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <1000000>; + clock-output-names = "v2m:refclk1mhz"; + }; + + v2m_refclk32khz: refclk32khz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <32768>; + clock-output-names = "v2m:refclk32khz"; + }; + + mcc { + compatible = "simple-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + v2m_oscclk1: osc@1 { + /* CLCD clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <23750000 63500000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk1"; + }; + + muxfpga@0 { + compatible = "arm,vexpress-muxfpga"; + arm,vexpress-sysreg,func = <7 0>; + }; + + shutdown@0 { + compatible = "arm,vexpress-shutdown"; + arm,vexpress-sysreg,func = <8 0>; + }; + }; + }; diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts new file mode 100644 index 000000000000..55d4f5ce019e --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts @@ -0,0 +1,227 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x4CT + * ARMCortexA7x4CT + * RTSM_VE_Cortex_A15x1_A7x1.lisa + */ + +/dts-v1/; + +/memreserve/ 0xff000000 0x01000000; + +/ { + model = "RTSM_VE_CortexA15x1-A7x1"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x1_a7x1", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + clusters { + #address-cells = <1>; + #size-cells = <0>; + + cluster0: cluster@0 { + reg = <0>; +// freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core0: core@0 { + reg = <0>; + }; + + }; + }; + + cluster1: cluster@1 { + reg = <1>; +// freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core1: core@0 { + reg = <0>; + }; + + }; + }; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + cluster = <&cluster0>; + core = <&core0>; +// clock-frequency = <1000000000>; + }; + + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x100>; + cluster = <&cluster1>; + core = <&core1>; +// clock-frequency = <800000000>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + cci@2c090000 { + compatible = "arm,cci"; + reg = <0 0x2c090000 0 0x8000>; + }; + + dcscb@60000000 { + compatible = "arm,rtsm,dcscb"; + reg = <0 0x60000000 0 0x1000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + + gic-cpuif@0 { + compatible = "arm,gic-cpuif"; + cpuif-id = <0>; + cpu = <&cpu0>; + }; + gic-cpuif@1 { + compatible = "arm,gic-cpuif"; + cpuif-id = <1>; + cpu = <&cpu1>; + }; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts new file mode 100644 index 000000000000..a2d4441568a0 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts @@ -0,0 +1,335 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x4CT + * ARMCortexA7x4CT + * RTSM_VE_Cortex_A15x4_A7x4.lisa + */ + +/dts-v1/; + +/memreserve/ 0xff000000 0x01000000; + +/ { + model = "RTSM_VE_CortexA15x4-A7x4"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x4_a7x4", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + clusters { + #address-cells = <1>; + #size-cells = <0>; + + cluster0: cluster@0 { + reg = <0>; +// freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core0: core@0 { + reg = <0>; + }; + + core1: core@1 { + reg = <1>; + }; + + core2: core@2 { + reg = <2>; + }; + + core3: core@3 { + reg = <3>; + }; + + }; + }; + + cluster1: cluster@1 { + reg = <1>; +// freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core4: core@0 { + reg = <0>; + }; + + core5: core@1 { + reg = <1>; + }; + + core6: core@2 { + reg = <2>; + }; + + core7: core@3 { + reg = <3>; + }; + + }; + }; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + cluster = <&cluster0>; + core = <&core0>; +// clock-frequency = <1000000000>; + }; + + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <1>; + cluster = <&cluster0>; + core = <&core1>; +// clock-frequency = <1000000000>; + }; + + cpu2: cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <2>; + cluster = <&cluster0>; + core = <&core2>; +// clock-frequency = <1000000000>; + }; + + cpu3: cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <3>; + cluster = <&cluster0>; + core = <&core3>; +// clock-frequency = <1000000000>; + }; + + cpu4: cpu@4 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x100>; + cluster = <&cluster1>; + core = <&core4>; +// clock-frequency = <800000000>; + }; + + cpu5: cpu@5 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x101>; + cluster = <&cluster1>; + core = <&core5>; +// clock-frequency = <800000000>; + }; + + cpu6: cpu@6 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x102>; + cluster = <&cluster1>; + core = <&core6>; +// clock-frequency = <800000000>; + }; + + cpu7: cpu@7 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x103>; + cluster = <&cluster1>; + core = <&core7>; +// clock-frequency = <800000000>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + cci@2c090000 { + compatible = "arm,cci"; + reg = <0 0x2c090000 0 0x8000>; + }; + + dcscb@60000000 { + compatible = "arm,rtsm,dcscb"; + reg = <0 0x60000000 0 0x1000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + + gic-cpuif@0 { + compatible = "arm,gic-cpuif"; + cpuif-id = <0>; + cpu = <&cpu0>; + }; + gic-cpuif@1 { + compatible = "arm,gic-cpuif"; + cpuif-id = <1>; + cpu = <&cpu1>; + }; + gic-cpuif@2 { + compatible = "arm,gic-cpuif"; + cpuif-id = <2>; + cpu = <&cpu2>; + }; + gic-cpuif@3 { + compatible = "arm,gic-cpuif"; + cpuif-id = <3>; + cpu = <&cpu3>; + }; + gic-cpuif@4 { + compatible = "arm,gic-cpuif"; + cpuif-id = <4>; + cpu = <&cpu4>; + }; + gic-cpuif@5 { + compatible = "arm,gic-cpuif"; + cpuif-id = <5>; + cpu = <&cpu5>; + }; + gic-cpuif@6 { + compatible = "arm,gic-cpuif"; + cpuif-id = <6>; + cpu = <&cpu6>; + }; + gic-cpuif@7 { + compatible = "arm,gic-cpuif"; + cpuif-id = <7>; + cpu = <&cpu7>; + }; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi index ac870fb3fa0d..9584232ee6b6 100644 --- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi @@ -228,6 +228,7 @@ }; clcd@1f0000 { + status = "disabled"; compatible = "arm,pl111", "arm,primecell"; reg = <0x1f0000 0x1000>; interrupts = <14>; diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi index f1420368355b..6593398c11ae 100644 --- a/arch/arm/boot/dts/vexpress-v2m.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m.dtsi @@ -227,6 +227,7 @@ }; clcd@1f000 { + status = "disabled"; compatible = "arm,pl111", "arm,primecell"; reg = <0x1f000 0x1000>; interrupts = <14>; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts index 73187173117c..cc6a8c0cfe33 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts @@ -9,6 +9,8 @@ /dts-v1/; +/memreserve/ 0xbf000000 0x01000000; + / { model = "V2P-CA15"; arm,hbi = <0x237>; @@ -57,6 +59,8 @@ interrupts = <0 85 4>; clocks = <&oscclk5>; clock-names = "pxlclk"; + mode = "1024x768-16@60"; + framebuffer = <0 0xff000000 0 0x01000000>; }; memory-controller@2b0a0000 { @@ -117,7 +121,7 @@ }; pmu { - compatible = "arm,cortex-a15-pmu", "arm,cortex-a9-pmu"; + compatible = "arm,cortex-a15-pmu"; interrupts = <0 68 4>, <0 69 4>; }; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts index dfe371ec2749..b37fdd8c1468 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts @@ -9,11 +9,13 @@ /dts-v1/; +/memreserve/ 0xff000000 0x01000000; + / { model = "V2P-CA15_CA7"; arm,hbi = <0x249>; arm,vexpress,site = <0xf>; - compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress"; + compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress", "arm,generic"; interrupt-parent = <&gic>; #address-cells = <2>; #size-cells = <2>; @@ -29,6 +31,48 @@ i2c1 = &v2m_i2c_pcie; }; + clusters { + #address-cells = <1>; + #size-cells = <0>; + + cluster0: cluster@0 { + reg = <0>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core0: core@0 { + reg = <0>; + }; + + core1: core@1 { + reg = <1>; + }; + + }; + }; + + cluster1: cluster@1 { + reg = <1>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core2: core@0 { + reg = <0>; + }; + + core3: core@1 { + reg = <1>; + }; + + core4: core@2 { + reg = <2>; + }; + }; + }; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -37,36 +81,51 @@ device_type = "cpu"; compatible = "arm,cortex-a15"; reg = <0>; + cluster = <&cluster0>; + core = <&core0>; + clock-frequency = <1000000000>; }; cpu1: cpu@1 { device_type = "cpu"; compatible = "arm,cortex-a15"; reg = <1>; + cluster = <&cluster0>; + core = <&core1>; + clock-frequency = <1000000000>; }; cpu2: cpu@2 { device_type = "cpu"; compatible = "arm,cortex-a7"; reg = <0x100>; + cluster = <&cluster1>; + core = <&core2>; + clock-frequency = <800000000>; }; cpu3: cpu@3 { device_type = "cpu"; compatible = "arm,cortex-a7"; reg = <0x101>; + cluster = <&cluster1>; + core = <&core3>; + clock-frequency = <800000000>; }; cpu4: cpu@4 { device_type = "cpu"; compatible = "arm,cortex-a7"; reg = <0x102>; + cluster = <&cluster1>; + core = <&core4>; + clock-frequency = <800000000>; }; }; memory@80000000 { device_type = "memory"; - reg = <0 0x80000000 0 0x40000000>; + reg = <0 0x80000000 0 0x80000000>; }; wdt@2a490000 { @@ -81,6 +140,8 @@ compatible = "arm,hdlcd"; reg = <0 0x2b000000 0 0x1000>; interrupts = <0 85 4>; + mode = "1024x768-16@60"; + framebuffer = <0 0xff000000 0 0x01000000>; clocks = <&oscclk5>; clock-names = "pxlclk"; }; @@ -102,6 +163,44 @@ <0 0x2c004000 0 0x2000>, <0 0x2c006000 0 0x2000>; interrupts = <1 9 0xf04>; + + gic-cpuif@0 { + compatible = "arm,gic-cpuif"; + cpuif-id = <0>; + cpu = <&cpu0>; + }; + gic-cpuif@1 { + compatible = "arm,gic-cpuif"; + cpuif-id = <1>; + cpu = <&cpu1>; + }; + gic-cpuif@2 { + compatible = "arm,gic-cpuif"; + cpuif-id = <2>; + cpu = <&cpu2>; + }; + + gic-cpuif@3 { + compatible = "arm,gic-cpuif"; + cpuif-id = <3>; + cpu = <&cpu3>; + }; + + gic-cpuif@4 { + compatible = "arm,gic-cpuif"; + cpuif-id = <4>; + cpu = <&cpu4>; + }; + }; + + cci@2c090000 { + compatible = "arm,cci"; + reg = <0 0x2c090000 0 0x10000>; + interrupts = <0 101 4>, + <0 102 4>, + <0 103 4>, + <0 104 4>, + <0 105 4>; }; memory-controller@7ffd0000 { @@ -125,6 +224,12 @@ clock-names = "apb_pclk"; }; + spc@7fff0000 { + compatible = "arm,spc"; + reg = <0 0x7fff0000 0 0x1000>; + interrupts = <0 95 4>; + }; + timer { compatible = "arm,armv7-timer"; interrupts = <1 13 0xf08>, @@ -133,12 +238,21 @@ <1 10 0xf08>; }; - pmu { - compatible = "arm,cortex-a15-pmu", "arm,cortex-a9-pmu"; + pmu_a15 { + compatible = "arm,cortex-a15-pmu"; + cluster = <&cluster0>; interrupts = <0 68 4>, <0 69 4>; }; + pmu_a7 { + compatible = "arm,cortex-a7-pmu"; + cluster = <&cluster1>; + interrupts = <0 128 4>, + <0 129 4>, + <0 130 4>; + }; + oscclk6a: oscclk6a { /* Reference 24MHz clock */ compatible = "fixed-clock"; @@ -147,6 +261,15 @@ clock-output-names = "oscclk6a"; }; + psci { + compatible = "arm,psci"; + method = "smc"; + cpu_suspend = <0x80100001>; + cpu_off = <0x80100002>; + cpu_on = <0x80100003>; + migrate = <0x80100004>; + }; + dcc { compatible = "arm,vexpress,config-bus"; arm,vexpress,config-bridge = <&v2m_sysreg>; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts index 6328cbc71d30..cf633ed6a1b4 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts @@ -9,6 +9,8 @@ /dts-v1/; +/memreserve/ 0xbf000000 0x01000000; + / { model = "V2P-CA5s"; arm,hbi = <0x225>; @@ -59,6 +61,8 @@ interrupts = <0 85 4>; clocks = <&oscclk3>; clock-names = "pxlclk"; + mode = "640x480-16@60"; + framebuffer = <0xbf000000 0x01000000>; }; memory-controller@2a150000 { @@ -111,7 +115,7 @@ }; pmu { - compatible = "arm,cortex-a5-pmu", "arm,cortex-a9-pmu"; + compatible = "arm,cortex-a5-pmu"; interrupts = <0 68 4>, <0 69 4>; }; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts index 1420bb14d95c..663fa5927e7e 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts @@ -9,6 +9,8 @@ /dts-v1/; +/include/ "clcd-panels.dtsi" + / { model = "V2P-CA9"; arm,hbi = <0x191>; @@ -73,6 +75,8 @@ interrupts = <0 44 4>; clocks = <&oscclk1>, <&oscclk2>; clock-names = "clcdclk", "apb_pclk"; + mode = "XVGA"; + use_dma = <1>; }; memory-controller@100e0000 { diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile index 8d024cf08f08..c187710c1fe5 100644 --- a/arch/arm/common/Makefile +++ b/arch/arm/common/Makefile @@ -11,5 +11,11 @@ obj-$(CONFIG_SHARP_PARAM) += sharpsl_param.o 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 +CFLAGS_REMOVE_mcpm_entry.o = -pg +AFLAGS_mcpm_head.o := -march=armv7-a +AFLAGS_vlock.o := -march=armv7-a +obj-$(CONFIG_BL_SWITCHER) += bL_switcher.o +obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o obj-$(CONFIG_FIQ_GLUE) += fiq_glue.o fiq_glue_setup.o obj-$(CONFIG_FIQ_DEBUGGER) += fiq_debugger.o diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c new file mode 100644 index 000000000000..c3b9427f0a08 --- /dev/null +++ b/arch/arm/common/bL_switcher.c @@ -0,0 +1,783 @@ +/* + * 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/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/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. + */ + +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); + + /* 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 { + struct task_struct *task; + wait_queue_head_t wq; + int wanted_cluster; + struct completion started; +}; + +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; + + 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()); + cluster = xchg(&t->wanted_cluster, -1); + if (cluster != -1) + bL_switch_to(cluster); + } 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 - Switch to a specific cluster for the given CPU + * + * @cpu: the CPU to switch + * @new_cluster_id: the ID of the cluster to switch to. + * + * 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. + */ +int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id) +{ + 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; + + t->wanted_cluster = new_cluster_id; + wake_up(&t->wq); + return 0; +} + +EXPORT_SYMBOL_GPL(bL_switch_request); + +/* + * 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]; + 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 }; + +static bool no_bL_switcher; +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 000000000000..5e2dd197e728 --- /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 new file mode 100644 index 000000000000..4a2b32fd53a1 --- /dev/null +++ b/arch/arm/common/mcpm_entry.c @@ -0,0 +1,275 @@ +/* + * arch/arm/common/mcpm_entry.c -- entry point for multi-cluster PM + * + * Created by: Nicolas Pitre, March 2012 + * Copyright: (C) 2012-2013 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. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/irqflags.h> + +#include <asm/mcpm.h> +#include <asm/cacheflush.h> +#include <asm/idmap.h> +#include <asm/cputype.h> + +extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER]; + +void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr) +{ + unsigned long val = ptr ? virt_to_phys(ptr) : 0; + mcpm_entry_vectors[cluster][cpu] = val; + 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) +{ + if (platform_ops) + return -EBUSY; + platform_ops = ops; + return 0; +} + +int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster) +{ + if (!platform_ops) + return -EUNATCH; /* try not to shadow power_up errors */ + might_sleep(); + return platform_ops->power_up(cpu, cluster); +} + +typedef void (*phys_reset_t)(unsigned long); + +void mcpm_cpu_power_down(void) +{ + phys_reset_t phys_reset; + + BUG_ON(!platform_ops); + BUG_ON(!irqs_disabled()); + + /* + * Do this before calling into the power_down method, + * as it might not always be safe to do afterwards. + */ + setup_mm_for_reboot(); + + platform_ops->power_down(); + + /* + * It is possible for a power_up request to happen concurrently + * with a power_down request for the same CPU. In this case the + * power_down method might not be able to actually enter a + * powered down state with the WFI instruction if the power_up + * method has removed the required reset condition. The + * power_down method is then allowed to return. We must perform + * a re-entry in the kernel as if the power_up method just had + * deasserted reset on the CPU. + * + * To simplify race issues, the platform specific implementation + * must accommodate for the possibility of unordered calls to + * power_down and power_up with a usage count. Therefore, if a + * call to power_up is issued for a CPU that is not down, then + * the next call to power_down must not attempt a full shutdown + * but only do the minimum (normally disabling L1 cache and CPU + * coherency) and return just as if a concurrent power_up request + * had happened as described above. + */ + + phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset); + phys_reset(virt_to_phys(mcpm_entry_point)); + + /* should never get here */ + BUG(); +} + +void mcpm_cpu_suspend(u64 expected_residency) +{ + phys_reset_t phys_reset; + + BUG_ON(!platform_ops); + BUG_ON(!irqs_disabled()); + + /* Very similar to mcpm_cpu_power_down() */ + setup_mm_for_reboot(); + platform_ops->suspend(expected_residency); + phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset); + phys_reset(virt_to_phys(mcpm_entry_point)); + BUG(); +} + +int mcpm_cpu_powered_up(void) +{ + if (!platform_ops) + return -EUNATCH; + if (platform_ops->powered_up) + platform_ops->powered_up(); + return 0; +} + +struct sync_struct mcpm_sync; + +/* + * __mcpm_cpu_going_down: Indicates that the cpu is being torn down. + * This must be called at the point of committing to teardown of a CPU. + * The CPU cache (SCTRL.C bit) is expected to still be active. + */ +void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster) +{ + mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_GOING_DOWN; + sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu); +} + +/* + * __mcpm_cpu_down: Indicates that cpu teardown is complete and that the + * cluster can be torn down without disrupting this CPU. + * To avoid deadlocks, this must be called before a CPU is powered down. + * The CPU cache (SCTRL.C bit) is expected to be off. + * However L2 cache might or might not be active. + */ +void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster) +{ + dmb(); + mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_DOWN; + sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu); + dsb_sev(); +} + +/* + * __mcpm_outbound_leave_critical: Leave the cluster teardown critical section. + * @state: the final state of the cluster: + * CLUSTER_UP: no destructive teardown was done and the cluster has been + * restored to the previous state (CPU cache still active); or + * CLUSTER_DOWN: the cluster has been torn-down, ready for power-off + * (CPU cache disabled, L2 cache either enabled or disabled). + */ +void __mcpm_outbound_leave_critical(unsigned int cluster, int state) +{ + dmb(); + mcpm_sync.clusters[cluster].cluster = state; + sync_cache_w(&mcpm_sync.clusters[cluster].cluster); + dsb_sev(); +} + +/* + * __mcpm_outbound_enter_critical: Enter the cluster teardown critical section. + * This function should be called by the last man, after local CPU teardown + * is complete. CPU cache expected to be active. + * + * Returns: + * false: the critical section was not entered because an inbound CPU was + * observed, or the cluster is already being set up; + * true: the critical section was entered: it is now safe to tear down the + * cluster. + */ +bool __mcpm_outbound_enter_critical(unsigned int cpu, unsigned int cluster) +{ + unsigned int i; + struct mcpm_sync_struct *c = &mcpm_sync.clusters[cluster]; + + /* Warn inbound CPUs that the cluster is being torn down: */ + c->cluster = CLUSTER_GOING_DOWN; + sync_cache_w(&c->cluster); + + /* Back out if the inbound cluster is already in the critical region: */ + sync_cache_r(&c->inbound); + if (c->inbound == INBOUND_COMING_UP) + goto abort; + + /* + * Wait for all CPUs to get out of the GOING_DOWN state, so that local + * teardown is complete on each CPU before tearing down the cluster. + * + * If any CPU has been woken up again from the DOWN state, then we + * shouldn't be taking the cluster down at all: abort in that case. + */ + sync_cache_r(&c->cpus); + for (i = 0; i < MAX_CPUS_PER_CLUSTER; i++) { + int cpustate; + + if (i == cpu) + continue; + + while (1) { + cpustate = c->cpus[i].cpu; + if (cpustate != CPU_GOING_DOWN) + break; + + wfe(); + sync_cache_r(&c->cpus[i].cpu); + } + + switch (cpustate) { + case CPU_DOWN: + continue; + + default: + goto abort; + } + } + + return true; + +abort: + __mcpm_outbound_leave_critical(cluster, CLUSTER_UP); + return false; +} + +int __mcpm_cluster_state(unsigned int cluster) +{ + sync_cache_r(&mcpm_sync.clusters[cluster].cluster); + return mcpm_sync.clusters[cluster].cluster; +} + +extern unsigned long mcpm_power_up_setup_phys; + +int __init mcpm_sync_init( + void (*power_up_setup)(unsigned int affinity_level)) +{ + unsigned int i, j, mpidr, this_cluster; + + BUILD_BUG_ON(MCPM_SYNC_CLUSTER_SIZE * MAX_NR_CLUSTERS != sizeof mcpm_sync); + BUG_ON((unsigned long)&mcpm_sync & (__CACHE_WRITEBACK_GRANULE - 1)); + + /* + * Set initial CPU and cluster states. + * Only one cluster is assumed to be active at this point. + */ + for (i = 0; i < MAX_NR_CLUSTERS; i++) { + mcpm_sync.clusters[i].cluster = CLUSTER_DOWN; + mcpm_sync.clusters[i].inbound = INBOUND_NOT_COMING_UP; + for (j = 0; j < MAX_CPUS_PER_CLUSTER; j++) + mcpm_sync.clusters[i].cpus[j].cpu = CPU_DOWN; + } + mpidr = read_cpuid_mpidr(); + this_cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + for_each_online_cpu(i) + mcpm_sync.clusters[this_cluster].cpus[i].cpu = CPU_UP; + mcpm_sync.clusters[this_cluster].cluster = CLUSTER_UP; + sync_cache_w(&mcpm_sync); + + if (power_up_setup) { + mcpm_power_up_setup_phys = virt_to_phys(power_up_setup); + sync_cache_w(&mcpm_power_up_setup_phys); + } + + return 0; +} diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S new file mode 100644 index 000000000000..057e9c5a9e1f --- /dev/null +++ b/arch/arm/common/mcpm_head.S @@ -0,0 +1,231 @@ +/* + * arch/arm/common/mcpm_head.S -- kernel entry point for multi-cluster PM + * + * Created by: Nicolas Pitre, March 2012 + * Copyright: (C) 2012-2013 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. + * + * + * Refer to Documentation/arm/cluster-pm-race-avoidance.txt + * for details of the synchronisation algorithms used here. + */ + +#include <linux/linkage.h> +#include <asm/mcpm.h> + +#include "vlock.h" + +.if MCPM_SYNC_CLUSTER_CPUS +.error "cpus must be the first member of struct mcpm_sync_struct" +.endif + + .macro pr_dbg string +#if defined(CONFIG_DEBUG_LL) && defined(DEBUG) + b 1901f +1902: .asciz "CPU" +1903: .asciz " cluster" +1904: .asciz ": \string" + .align +1901: adr r0, 1902b + bl printascii + mov r0, r9 + bl printhex8 + adr r0, 1903b + bl printascii + mov r0, r10 + bl printhex8 + adr r0, 1904b + bl printascii +#endif + .endm + + .arm + .align + +ENTRY(mcpm_entry_point) + + THUMB( adr r12, BSYM(1f) ) + THUMB( bx r12 ) + THUMB( .thumb ) +1: + mrc p15, 0, r0, c0, c0, 5 @ MPIDR + ubfx r9, r0, #0, #8 @ r9 = cpu + ubfx r10, r0, #8, #8 @ r10 = cluster + mov r3, #MAX_CPUS_PER_CLUSTER + mla r4, r3, r10, r9 @ r4 = canonical CPU index + cmp r4, #(MAX_CPUS_PER_CLUSTER * MAX_NR_CLUSTERS) + blo 2f + + /* We didn't expect this CPU. Try to cheaply make it quiet. */ +1: wfi + wfe + b 1b + +2: pr_dbg "kernel mcpm_entry_point\n" + + /* + * MMU is off so we need to get to various variables in a + * position independent way. + */ + adr r5, 3f + 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 + + @ Signal that this CPU is coming UP: + mov r0, #CPU_COMING_UP + mov r5, #MCPM_SYNC_CPU_SIZE + mla r5, r9, r5, r8 @ r5 = sync cpu address + strb r0, [r5] + + @ At this point, the cluster cannot unexpectedly enter the GOING_DOWN + @ state, because there is at least one active CPU (this CPU). + + mov r0, #VLOCK_SIZE + mla r11, r0, r10, r11 @ r11 = cluster first man lock + mov r0, r11 + mov r1, r9 @ cpu + bl vlock_trylock @ implies DMB + + cmp r0, #0 @ failed to get the lock? + bne mcpm_setup_wait @ wait for cluster setup if so + + ldrb r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER] + cmp r0, #CLUSTER_UP @ cluster already up? + bne mcpm_setup @ if not, set up the cluster + + @ Otherwise, release the first man lock and skip setup: + mov r0, r11 + bl vlock_unlock + b mcpm_setup_complete + +mcpm_setup: + @ Control dependency implies strb not observable before previous ldrb. + + @ Signal that the cluster is being brought up: + mov r0, #INBOUND_COMING_UP + strb r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND] + dmb + + @ Any CPU trying to take the cluster into CLUSTER_GOING_DOWN from this + @ point onwards will observe INBOUND_COMING_UP and abort. + + @ Wait for any previously-pending cluster teardown operations to abort + @ or complete: +mcpm_teardown_wait: + ldrb r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER] + cmp r0, #CLUSTER_GOING_DOWN + bne first_man_setup + wfe + b mcpm_teardown_wait + +first_man_setup: + dmb + + @ If the outbound gave up before teardown started, skip cluster setup: + + cmp r0, #CLUSTER_UP + beq mcpm_setup_leave + + @ power_up_setup is now responsible for setting up the cluster: + + cmp r7, #0 + mov r0, #1 @ second (cluster) affinity level + blxne r7 @ Call power_up_setup if defined + dmb + + mov r0, #CLUSTER_UP + strb r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER] + dmb + +mcpm_setup_leave: + @ Leave the cluster setup critical section: + + mov r0, #INBOUND_NOT_COMING_UP + strb r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND] + dsb + sev + + mov r0, r11 + bl vlock_unlock @ implies DMB + b mcpm_setup_complete + + @ In the contended case, non-first men wait here for cluster setup + @ to complete: +mcpm_setup_wait: + ldrb r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER] + cmp r0, #CLUSTER_UP + wfene + bne mcpm_setup_wait + dmb + +mcpm_setup_complete: + @ If a platform-specific CPU setup hook is needed, it is + @ called from here. + + cmp r7, #0 + mov r0, #0 @ first (CPU) affinity level + blxne r7 @ Call power_up_setup if defined + dmb + + @ Mark the CPU as up: + + mov r0, #CPU_UP + strb r0, [r5] + + @ Observability order of CPU_UP and opening of the gate does not matter. + +mcpm_entry_gated: + ldr r5, [r6, r4, lsl #2] @ r5 = CPU entry vector + cmp r5, #0 + wfeeq + beq mcpm_entry_gated + dmb + + pr_dbg "released\n" + bx r5 + + .align 2 + +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 + +ENDPROC(mcpm_entry_point) + + .bss + + .align CACHE_WRITEBACK_ORDER + .type first_man_locks, #object +first_man_locks: + .space VLOCK_SIZE * MAX_NR_CLUSTERS + .align CACHE_WRITEBACK_ORDER + + .type mcpm_entry_vectors, #object +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/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c new file mode 100644 index 000000000000..3caed0db6986 --- /dev/null +++ b/arch/arm/common/mcpm_platsmp.c @@ -0,0 +1,89 @@ +/* + * linux/arch/arm/mach-vexpress/mcpm_platsmp.c + * + * Created by: Nicolas Pitre, November 2012 + * Copyright: (C) 2012-2013 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. + * + * Code to handle secondary CPU bringup and hotplug for the cluster power API. + */ + +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/spinlock.h> + +#include <asm/mcpm.h> +#include <asm/smp.h> +#include <asm/smp_plat.h> + +static void __init simple_smp_init_cpus(void) +{ +} + +static int __cpuinit mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle) +{ + unsigned int mpidr, pcpu, pcluster, ret; + extern void secondary_startup(void); + + mpidr = cpu_logical_map(cpu); + pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + pr_debug("%s: logical CPU %d is physical CPU %d cluster %d\n", + __func__, cpu, pcpu, pcluster); + + mcpm_set_entry_vector(pcpu, pcluster, NULL); + ret = mcpm_cpu_power_up(pcpu, pcluster); + if (ret) + return ret; + mcpm_set_entry_vector(pcpu, pcluster, secondary_startup); + arch_send_wakeup_ipi_mask(cpumask_of(cpu)); + dsb_sev(); + return 0; +} + +static void __cpuinit mcpm_secondary_init(unsigned int cpu) +{ + mcpm_cpu_powered_up(); +} + +#ifdef CONFIG_HOTPLUG_CPU + +static int mcpm_cpu_disable(unsigned int cpu) +{ + /* + * We assume all CPUs may be shut down. + * This would be the hook to use for eventual Secure + * OS migration requests as described in the PSCI spec. + */ + return 0; +} + +static void mcpm_cpu_die(unsigned int cpu) +{ + unsigned int mpidr, pcpu, pcluster; + mpidr = read_cpuid_mpidr(); + pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + mcpm_set_entry_vector(pcpu, pcluster, NULL); + mcpm_cpu_power_down(); +} + +#endif + +static struct smp_operations __initdata mcpm_smp_ops = { + .smp_init_cpus = simple_smp_init_cpus, + .smp_boot_secondary = mcpm_boot_secondary, + .smp_secondary_init = mcpm_secondary_init, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = mcpm_cpu_disable, + .cpu_die = mcpm_cpu_die, +#endif +}; + +void __init mcpm_smp_set_ops(void) +{ + smp_set_ops(&mcpm_smp_ops); +} diff --git a/arch/arm/common/vlock.S b/arch/arm/common/vlock.S new file mode 100644 index 000000000000..ff198583f683 --- /dev/null +++ b/arch/arm/common/vlock.S @@ -0,0 +1,108 @@ +/* + * vlock.S - simple voting lock implementation for ARM + * + * Created by: Dave Martin, 2012-08-16 + * Copyright: (C) 2012-2013 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. + * + * + * This algorithm is described in more detail in + * Documentation/arm/vlocks.txt. + */ + +#include <linux/linkage.h> +#include "vlock.h" + +/* Select different code if voting flags can fit in a single word. */ +#if VLOCK_VOTING_SIZE > 4 +#define FEW(x...) +#define MANY(x...) x +#else +#define FEW(x...) x +#define MANY(x...) +#endif + +@ voting lock for first-man coordination + +.macro voting_begin rbase:req, rcpu:req, rscratch:req + mov \rscratch, #1 + strb \rscratch, [\rbase, \rcpu] + dmb +.endm + +.macro voting_end rbase:req, rcpu:req, rscratch:req + dmb + mov \rscratch, #0 + strb \rscratch, [\rbase, \rcpu] + dsb + sev +.endm + +/* + * The vlock structure must reside in Strongly-Ordered or Device memory. + * This implementation deliberately eliminates most of the barriers which + * would be required for other memory types, and assumes that independent + * writes to neighbouring locations within a cacheline do not interfere + * with one another. + */ + +@ r0: lock structure base +@ r1: CPU ID (0-based index within cluster) +ENTRY(vlock_trylock) + add r1, r1, #VLOCK_VOTING_OFFSET + + voting_begin r0, r1, r2 + + ldrb r2, [r0, #VLOCK_OWNER_OFFSET] @ check whether lock is held + cmp r2, #VLOCK_OWNER_NONE + bne trylock_fail @ fail if so + + @ Control dependency implies strb not observable before previous ldrb. + + strb r1, [r0, #VLOCK_OWNER_OFFSET] @ submit my vote + + voting_end r0, r1, r2 @ implies DMB + + @ Wait for the current round of voting to finish: + + MANY( mov r3, #VLOCK_VOTING_OFFSET ) +0: + MANY( ldr r2, [r0, r3] ) + FEW( ldr r2, [r0, #VLOCK_VOTING_OFFSET] ) + cmp r2, #0 + wfene + bne 0b + MANY( add r3, r3, #4 ) + MANY( cmp r3, #VLOCK_VOTING_OFFSET + VLOCK_VOTING_SIZE ) + MANY( bne 0b ) + + @ Check who won: + + dmb + ldrb r2, [r0, #VLOCK_OWNER_OFFSET] + eor r0, r1, r2 @ zero if I won, else nonzero + bx lr + +trylock_fail: + voting_end r0, r1, r2 + mov r0, #1 @ nonzero indicates that I lost + bx lr +ENDPROC(vlock_trylock) + +@ r0: lock structure base +ENTRY(vlock_unlock) + dmb + mov r1, #VLOCK_OWNER_NONE + strb r1, [r0, #VLOCK_OWNER_OFFSET] + dsb + sev + bx lr +ENDPROC(vlock_unlock) diff --git a/arch/arm/common/vlock.h b/arch/arm/common/vlock.h new file mode 100644 index 000000000000..3b441475a59b --- /dev/null +++ b/arch/arm/common/vlock.h @@ -0,0 +1,29 @@ +/* + * vlock.h - simple voting lock implementation + * + * Created by: Dave Martin, 2012-08-16 + * Copyright: (C) 2012-2013 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. + */ + +#ifndef __VLOCK_H +#define __VLOCK_H + +#include <asm/mcpm.h> + +/* Offsets and sizes are rounded to a word (4 bytes) */ +#define VLOCK_OWNER_OFFSET 0 +#define VLOCK_VOTING_OFFSET 4 +#define VLOCK_VOTING_SIZE ((MAX_CPUS_PER_CLUSTER + 3) / 4 * 4) +#define VLOCK_SIZE (VLOCK_VOTING_OFFSET + VLOCK_VOTING_SIZE) +#define VLOCK_OWNER_NONE 0 + +#endif /* ! __VLOCK_H */ diff --git a/arch/arm/configs/at91sam9g45_defconfig b/arch/arm/configs/at91sam9g45_defconfig index 606d48f3b8f8..8aab786863df 100644 --- a/arch/arm/configs/at91sam9g45_defconfig +++ b/arch/arm/configs/at91sam9g45_defconfig @@ -173,7 +173,6 @@ CONFIG_MMC=y # CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_SDIO_UART=m CONFIG_MMC_ATMELMCI=y -CONFIG_MMC_ATMELMCI_DMA=y CONFIG_LEDS_ATMEL_PWM=y CONFIG_LEDS_GPIO=y CONFIG_LEDS_TRIGGER_TIMER=y diff --git a/arch/arm/configs/vexpress_bL_defconfig b/arch/arm/configs/vexpress_bL_defconfig new file mode 100644 index 000000000000..0d18cbd3f7c0 --- /dev/null +++ b/arch/arm/configs/vexpress_bL_defconfig @@ -0,0 +1,157 @@ +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_RCU_FAST_NO_HZ=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_CGROUPS=y +CONFIG_CPUSETS=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_PROFILING=y +CONFIG_OPROFILE=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA is not set +CONFIG_ARCH_VEXPRESS_TC2=y +CONFIG_ARCH_VEXPRESS_DCSCB=y +CONFIG_ARM_ERRATA_720789=y +CONFIG_PL310_ERRATA_753970=y +CONFIG_SMP=y +CONFIG_HAVE_ARM_ARCH_TIMER=y +CONFIG_BIG_LITTLE=y +CONFIG_BL_SWITCHER=y +CONFIG_BL_SWITCHER_DUMMY_IF=y +CONFIG_NR_CPUS=8 +CONFIG_AEABI=y +# CONFIG_OABI_COMPAT is not set +CONFIG_HIGHMEM=y +CONFIG_HIGHPTE=y +# CONFIG_COMPACTION is not set +# CONFIG_ATAGS is not set +CONFIG_ZBOOT_ROM_TEXT=0x0 +CONFIG_ZBOOT_ROM_BSS=0x0 +CONFIG_ARM_APPENDED_DTB=y +CONFIG_ARM_ATAG_DTB_COMPAT=y +CONFIG_CMDLINE="console=ttyAMA0,38400" +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE=y +CONFIG_CPU_FREQ_GOV_PERFORMANCE=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +CONFIG_ARM_VEXPRESS_BL_CPUFREQ=y +CONFIG_CPU_IDLE=y +CONFIG_VFP=y +CONFIG_NEON=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +# CONFIG_IPV6 is not set +# CONFIG_WIRELESS is not set +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_CHAR=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_PROC_DEVICETREE=y +CONFIG_SCSI=y +# CONFIG_SCSI_PROC_FS is not set +CONFIG_BLK_DEV_SD=y +# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_NETDEVICES=y +CONFIG_SMSC911X=y +# CONFIG_WLAN is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIO_AMBAKMI=y +CONFIG_LEGACY_PTY_COUNT=16 +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +# CONFIG_HW_RANDOM is not set +CONFIG_SENSORS_VEXPRESS=y +CONFIG_REGULATOR=y +CONFIG_REGULATOR_VEXPRESS=y +CONFIG_FB=y +CONFIG_FB_ARMCLCD=y +CONFIG_FB_ARMHDLCD=y +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_MIXER_OSS=y +CONFIG_SND_PCM_OSS=y +# CONFIG_SND_DRIVERS is not set +CONFIG_SND_ARMAACI=y +CONFIG_HID_DRAGONRISE=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_LOGITECH_DJ=m +CONFIG_HID_NTRIG=y +CONFIG_HID_PANTHERLORD=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SONY=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_ZEROPLUS=y +CONFIG_USB=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y +CONFIG_USB_MON=y +CONFIG_USB_ISP1760_HCD=y +CONFIG_USB_STORAGE=y +CONFIG_MMC=y +CONFIG_MMC_ARMMMCI=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_PL031=y +CONFIG_STAGING=y +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_LOGGER=y +CONFIG_ANDROID_TIMED_GPIO=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_ANDROID_INTF_ALARM_DEV=y +CONFIG_EXT4_FS=y +CONFIG_FUSE_FS=y +CONFIG_CUSE=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_CRAMFS=y +CONFIG_NFS_FS=y +CONFIG_ROOT_NFS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +CONFIG_PRINTK_TIME=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_DEBUG_INFO=y +# CONFIG_FTRACE is not set +CONFIG_DEBUG_USER=y +# CONFIG_CRYPTO_ANSI_CPRNG is not set +# CONFIG_CRYPTO_HW is not set diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S index 92c6eed7aac9..99207c45ec10 100644 --- a/arch/arm/crypto/sha1-armv4-large.S +++ b/arch/arm/crypto/sha1-armv4-large.S @@ -195,6 +195,7 @@ ENTRY(sha1_block_data_order) add r3,r3,r10 @ E+=F_00_19(B,C,D) cmp r14,sp bne .L_00_15 @ [((11+4)*5+2)*3] + sub sp,sp,#25*4 #if __ARM_ARCH__<7 ldrb r10,[r1,#2] ldrb r9,[r1,#3] @@ -290,7 +291,6 @@ ENTRY(sha1_block_data_order) add r3,r3,r10 @ E+=F_00_19(B,C,D) ldr r8,.LK_20_39 @ [+15+16*4] - sub sp,sp,#25*4 cmn sp,#0 @ [+3], clear carry to denote 20_39 .L_20_39_or_60_79: ldr r9,[r14,#15*4] diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h new file mode 100644 index 000000000000..ebf8d9872a61 --- /dev/null +++ b/arch/arm/include/asm/bL_switcher.h @@ -0,0 +1,69 @@ +/* + * 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> + +int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id); + +/* + * 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 + +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 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/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 4e8217b204af..1fb8d5d41fc7 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -364,4 +364,79 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) flush_cache_all(); } +/* + * Memory synchronization helpers for mixed cached vs non cached accesses. + * + * Some synchronization algorithms have to set states in memory with the + * cache enabled or disabled depending on the code path. It is crucial + * to always ensure proper cache maintenance to update main memory right + * away in that case. + * + * Any cached write must be followed by a cache clean operation. + * Any cached read must be preceded by a cache invalidate operation. + * Yet, in the read case, a cache flush i.e. atomic clean+invalidate + * operation is needed to avoid discarding possible concurrent writes to the + * accessed memory. + * + * Also, in order to prevent a cached writer from interfering with an + * adjacent non-cached writer, each state variable must be located to + * a separate cache line. + */ + +/* + * This needs to be >= the max cache writeback size of all + * supported platforms included in the current kernel configuration. + * This is used to align state variables to their own cache lines. + */ +#define __CACHE_WRITEBACK_ORDER 6 /* guessed from existing platforms */ +#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER) + +/* + * There is no __cpuc_clean_dcache_area but we use it anyway for + * code intent clarity, and alias it to __cpuc_flush_dcache_area. + */ +#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area + +/* + * Ensure preceding writes to *p by this CPU are visible to + * subsequent reads by other CPUs: + */ +static inline void __sync_cache_range_w(volatile void *p, size_t size) +{ + char *_p = (char *)p; + + __cpuc_clean_dcache_area(_p, size); + outer_clean_range(__pa(_p), __pa(_p + size)); +} + +/* + * Ensure preceding writes to *p by other CPUs are visible to + * subsequent reads by this CPU. We must be careful not to + * discard data simultaneously written by another CPU, hence the + * usage of flush rather than invalidate operations. + */ +static inline void __sync_cache_range_r(volatile void *p, size_t size) +{ + char *_p = (char *)p; + +#ifdef CONFIG_OUTER_CACHE + if (outer_cache.flush_range) { + /* + * Ensure dirty data migrated from other CPUs into our cache + * are cleaned out safely before the outer cache is cleaned: + */ + __cpuc_clean_dcache_area(_p, size); + + /* Clean and invalidate stale data for *p from outer ... */ + outer_flush_range(__pa(_p), __pa(_p + size)); + } +#endif + + /* ... and inner cache: */ + __cpuc_flush_dcache_area(_p, size); +} + +#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr)) +#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr)) + #endif diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h index 7eb18c1d8d6c..4f009c10540d 100644 --- a/arch/arm/include/asm/cmpxchg.h +++ b/arch/arm/include/asm/cmpxchg.h @@ -233,15 +233,15 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr, ((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr), \ atomic64_t, \ counter), \ - (unsigned long)(o), \ - (unsigned long)(n))) + (unsigned long long)(o), \ + (unsigned long long)(n))) #define cmpxchg64_local(ptr, o, n) \ ((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr), \ local64_t, \ a), \ - (unsigned long)(o), \ - (unsigned long)(n))) + (unsigned long long)(o), \ + (unsigned long long)(n))) #endif /* __LINUX_ARM_ARCH__ >= 6 */ diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h index 5ef4d8015a60..cedd3721318b 100644 --- a/arch/arm/include/asm/cp15.h +++ b/arch/arm/include/asm/cp15.h @@ -42,6 +42,8 @@ #define vectors_high() (0) #endif +#ifdef CONFIG_CPU_CP15 + extern unsigned long cr_no_alignment; /* defined in entry-armv.S */ extern unsigned long cr_alignment; /* defined in entry-armv.S */ @@ -59,6 +61,20 @@ static inline void set_cr(unsigned int val) isb(); } +static inline unsigned int get_auxcr(void) +{ + unsigned int val; + asm("mrc p15, 0, %0, c1, c0, 1 @ get AUXCR" : "=r" (val)); + return val; +} + +static inline void set_auxcr(unsigned int val) +{ + asm volatile("mcr p15, 0, %0, c1, c0, 1 @ set AUXCR" + : : "r" (val)); + isb(); +} + #ifndef CONFIG_SMP extern void adjust_cr(unsigned long mask, unsigned long set); #endif @@ -82,6 +98,18 @@ static inline void set_copro_access(unsigned int val) isb(); } -#endif +#else /* ifdef CONFIG_CPU_CP15 */ + +/* + * cr_alignment and cr_no_alignment are tightly coupled to cp15 (at least in the + * minds of the developers). Yielding 0 for machines without a cp15 (and making + * it read-only) is fine for most cases and saves quite some #ifdeffery. + */ +#define cr_no_alignment UL(0) +#define cr_alignment UL(0) + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + +#endif /* ifndef __ASSEMBLY__ */ #endif diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index ad41ec2471e8..7652712d1d14 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -38,6 +38,24 @@ #define MPIDR_AFFINITY_LEVEL(mpidr, level) \ ((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK) +#define ARM_CPU_IMP_ARM 0x41 +#define ARM_CPU_IMP_INTEL 0x69 + +#define ARM_CPU_PART_ARM1136 0xB360 +#define ARM_CPU_PART_ARM1156 0xB560 +#define ARM_CPU_PART_ARM1176 0xB760 +#define ARM_CPU_PART_ARM11MPCORE 0xB020 +#define ARM_CPU_PART_CORTEX_A8 0xC080 +#define ARM_CPU_PART_CORTEX_A9 0xC090 +#define ARM_CPU_PART_CORTEX_A5 0xC050 +#define ARM_CPU_PART_CORTEX_A15 0xC0F0 +#define ARM_CPU_PART_CORTEX_A7 0xC070 + +#define ARM_CPU_XSCALE_ARCH_MASK 0xe000 +#define ARM_CPU_XSCALE_ARCH_V1 0x2000 +#define ARM_CPU_XSCALE_ARCH_V2 0x4000 +#define ARM_CPU_XSCALE_ARCH_V3 0x6000 + extern unsigned int processor_id; #ifdef CONFIG_CPU_CP15 @@ -50,6 +68,7 @@ extern unsigned int processor_id; : "cc"); \ __val; \ }) + #define read_cpuid_ext(ext_reg) \ ({ \ unsigned int __val; \ @@ -59,29 +78,24 @@ extern unsigned int processor_id; : "cc"); \ __val; \ }) -#else -#define read_cpuid(reg) (processor_id) -#define read_cpuid_ext(reg) 0 -#endif -#define ARM_CPU_IMP_ARM 0x41 -#define ARM_CPU_IMP_INTEL 0x69 +#else /* ifdef CONFIG_CPU_CP15 */ -#define ARM_CPU_PART_ARM1136 0xB360 -#define ARM_CPU_PART_ARM1156 0xB560 -#define ARM_CPU_PART_ARM1176 0xB760 -#define ARM_CPU_PART_ARM11MPCORE 0xB020 -#define ARM_CPU_PART_CORTEX_A8 0xC080 -#define ARM_CPU_PART_CORTEX_A9 0xC090 -#define ARM_CPU_PART_CORTEX_A5 0xC050 -#define ARM_CPU_PART_CORTEX_A15 0xC0F0 -#define ARM_CPU_PART_CORTEX_A7 0xC070 +/* + * read_cpuid and read_cpuid_ext should only ever be called on machines that + * have cp15 so warn on other usages. + */ +#define read_cpuid(reg) \ + ({ \ + WARN_ON_ONCE(1); \ + 0; \ + }) -#define ARM_CPU_XSCALE_ARCH_MASK 0xe000 -#define ARM_CPU_XSCALE_ARCH_V1 0x2000 -#define ARM_CPU_XSCALE_ARCH_V2 0x4000 -#define ARM_CPU_XSCALE_ARCH_V3 0x6000 +#define read_cpuid_ext(reg) read_cpuid(reg) + +#endif /* ifdef CONFIG_CPU_CP15 / else */ +#ifdef CONFIG_CPU_CP15 /* * The CPU ID never changes at run time, so we might as well tell the * compiler that it's constant. Use this function to read the CPU ID @@ -92,6 +106,15 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void) return read_cpuid(CPUID_ID); } +#else /* ifdef CONFIG_CPU_CP15 */ + +static inline unsigned int __attribute_const__ read_cpuid_id(void) +{ + return processor_id; +} + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + static inline unsigned int __attribute_const__ read_cpuid_implementor(void) { return (read_cpuid_id() & 0xFF000000) >> 24; diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h index 8cacbcda76da..b6e9f2c108b5 100644 --- a/arch/arm/include/asm/glue-df.h +++ b/arch/arm/include/asm/glue-df.h @@ -18,12 +18,12 @@ * ================ * * We have the following to choose from: - * arm6 - ARM6 style * arm7 - ARM7 style * v4_early - ARMv4 without Thumb early abort handler * v4t_late - ARMv4 with Thumb late abort handler * v4t_early - ARMv4 with Thumb early abort handler - * v5tej_early - ARMv5 with Thumb and Java early abort handler + * v5t_early - ARMv5 with Thumb early abort handler + * v5tj_early - ARMv5 with Thumb and Java early abort handler * xscale - ARMv5 with Thumb with Xscale extensions * v6_early - ARMv6 generic early abort handler * v7_early - ARMv7 generic early abort handler @@ -39,19 +39,19 @@ # endif #endif -#ifdef CONFIG_CPU_ABRT_LV4T +#ifdef CONFIG_CPU_ABRT_EV4 # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v4t_late_abort +# define CPU_DABORT_HANDLER v4_early_abort # endif #endif -#ifdef CONFIG_CPU_ABRT_EV4 +#ifdef CONFIG_CPU_ABRT_LV4T # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v4_early_abort +# define CPU_DABORT_HANDLER v4t_late_abort # endif #endif @@ -63,19 +63,19 @@ # endif #endif -#ifdef CONFIG_CPU_ABRT_EV5TJ +#ifdef CONFIG_CPU_ABRT_EV5T # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v5tj_early_abort +# define CPU_DABORT_HANDLER v5t_early_abort # endif #endif -#ifdef CONFIG_CPU_ABRT_EV5T +#ifdef CONFIG_CPU_ABRT_EV5TJ # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v5t_early_abort +# define CPU_DABORT_HANDLER v5tj_early_abort # endif #endif diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h index 3d7351c844aa..fe3ea776dc34 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 7 +#define NR_IPI 8 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index 3e0857a6248e..809203a4b71b 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -30,6 +30,11 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *); void handle_IRQ(unsigned int, struct pt_regs *); void init_IRQ(void); +#ifdef CONFIG_MULTI_IRQ_HANDLER +extern void (*handle_arch_irq)(struct pt_regs *); +extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); +#endif + void arch_trigger_all_cpu_backtrace(void); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 7c3d813e15df..124623e5ef14 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -211,4 +211,8 @@ #define HSR_HVC_IMM_MASK ((1UL << 16) - 1) +#define HSR_DABT_S1PTW (1U << 7) +#define HSR_DABT_CM (1U << 8) +#define HSR_DABT_EA (1U << 9) + #endif /* __ARM_KVM_ARM_H__ */ diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index e4956f4e23e1..18d50322a9e2 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -75,7 +75,7 @@ extern char __kvm_hyp_code_end[]; extern void __kvm_tlb_flush_vmid(struct kvm *kvm); extern void __kvm_flush_vm_context(void); -extern void __kvm_tlb_flush_vmid(struct kvm *kvm); +extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); #endif diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index fd611996bfb5..82b4babead2c 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -22,11 +22,12 @@ #include <linux/kvm_host.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> +#include <asm/kvm_arm.h> -u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); -u32 *vcpu_spsr(struct kvm_vcpu *vcpu); +unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); +unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu); -int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run); +bool kvm_condition_valid(struct kvm_vcpu *vcpu); void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr); void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); @@ -37,14 +38,14 @@ static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) return 1; } -static inline u32 *vcpu_pc(struct kvm_vcpu *vcpu) +static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu) { - return (u32 *)&vcpu->arch.regs.usr_regs.ARM_pc; + return &vcpu->arch.regs.usr_regs.ARM_pc; } -static inline u32 *vcpu_cpsr(struct kvm_vcpu *vcpu) +static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu) { - return (u32 *)&vcpu->arch.regs.usr_regs.ARM_cpsr; + return &vcpu->arch.regs.usr_regs.ARM_cpsr; } static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) @@ -69,4 +70,96 @@ static inline bool kvm_vcpu_reg_is_pc(struct kvm_vcpu *vcpu, int reg) return reg == 15; } +static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hsr; +} + +static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hxfar; +} + +static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu) +{ + return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8; +} + +static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hyp_pc; +} + +static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_ISV; +} + +static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_WNR; +} + +static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_SSE; +} + +static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu) +{ + return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT; +} + +static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_EA; +} + +static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; +} + +/* Get Access Size from a data abort */ +static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu) +{ + switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) { + case 0: + return 1; + case 1: + return 2; + case 2: + return 4; + default: + kvm_err("Hardware is weird: SAS 0b11 is reserved\n"); + return -EFAULT; + } +} + +/* This one is not specific to Data Abort */ +static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_IL; +} + +static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT; +} + +static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT; +} + +static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE; +} + +static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; +} + #endif /* __ARM_KVM_EMULATE_H__ */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index d1736a53b12d..0c4e643d939e 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -80,6 +80,15 @@ struct kvm_mmu_memory_cache { void *objects[KVM_NR_MEM_OBJS]; }; +struct kvm_vcpu_fault_info { + u32 hsr; /* Hyp Syndrome Register */ + u32 hxfar; /* Hyp Data/Inst. Fault Address Register */ + u32 hpfar; /* Hyp IPA Fault Address Register */ + u32 hyp_pc; /* PC when exception was taken from Hyp mode */ +}; + +typedef struct vfp_hard_struct kvm_kernel_vfp_t; + struct kvm_vcpu_arch { struct kvm_regs regs; @@ -93,13 +102,11 @@ struct kvm_vcpu_arch { u32 midr; /* Exception Information */ - u32 hsr; /* Hyp Syndrome Register */ - u32 hxfar; /* Hyp Data/Inst Fault Address Register */ - u32 hpfar; /* Hyp IPA Fault Address Register */ + struct kvm_vcpu_fault_info fault; /* Floating point registers (VFP and Advanced SIMD/NEON) */ - struct vfp_hard_struct vfp_guest; - struct vfp_hard_struct *vfp_host; + kvm_kernel_vfp_t vfp_guest; + kvm_kernel_vfp_t *vfp_host; /* VGIC state */ struct vgic_cpu vgic_cpu; @@ -122,9 +129,6 @@ struct kvm_vcpu_arch { /* Interrupt related fields */ u32 irq_lines; /* IRQ and FIQ levels */ - /* Hyp exception information */ - u32 hyp_pc; /* PC when exception was taken from Hyp mode */ - /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; @@ -181,4 +185,26 @@ struct kvm_one_reg; int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); +int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, + int exception_index); + +static inline void __cpu_init_hyp_mode(unsigned long long pgd_ptr, + unsigned long hyp_stack_ptr, + unsigned long vector_ptr) +{ + unsigned long pgd_low, pgd_high; + + pgd_low = (pgd_ptr & ((1ULL << 32) - 1)); + pgd_high = (pgd_ptr >> 32ULL); + + /* + * Call initialization code, and switch to the full blown + * HYP code. The init code doesn't need to preserve these registers as + * r1-r3 and r12 are already callee save according to the AAPCS. + * Note that we slightly misuse the prototype by casing the pgd_low to + * a void *. + */ + kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr); +} + #endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 421a20b34874..970f3b5fa109 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -19,6 +19,18 @@ #ifndef __ARM_KVM_MMU_H__ #define __ARM_KVM_MMU_H__ +#include <asm/cacheflush.h> +#include <asm/pgalloc.h> +#include <asm/idmap.h> + +/* + * We directly use the kernel VA for the HYP, as we can directly share + * the mapping (HTTBR "covers" TTBR1). + */ +#define HYP_PAGE_OFFSET_MASK (~0UL) +#define HYP_PAGE_OFFSET PAGE_OFFSET +#define KERN_TO_HYP(kva) (kva) + int create_hyp_mappings(void *from, void *to); int create_hyp_io_mappings(void *from, void *to, phys_addr_t); void free_hyp_pmds(void); @@ -36,6 +48,16 @@ phys_addr_t kvm_mmu_get_httbr(void); int kvm_mmu_init(void); void kvm_clear_hyp_idmap(void); +static inline void kvm_set_pte(pte_t *pte, pte_t new_pte) +{ + pte_val(*pte) = new_pte; + /* + * flush_pmd_entry just takes a void pointer and cleans the necessary + * cache entries, so we can reuse the function for ptes. + */ + flush_pmd_entry(pte); +} + static inline bool kvm_is_write_fault(unsigned long hsr) { unsigned long hsr_ec = hsr >> HSR_EC_SHIFT; @@ -47,4 +69,49 @@ static inline bool kvm_is_write_fault(unsigned long hsr) return true; } +static inline void kvm_clean_pgd(pgd_t *pgd) +{ + clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t)); +} + +static inline void kvm_clean_pmd_entry(pmd_t *pmd) +{ + clean_pmd_entry(pmd); +} + +static inline void kvm_clean_pte(pte_t *pte) +{ + clean_pte_table(pte); +} + +static inline void kvm_set_s2pte_writable(pte_t *pte) +{ + pte_val(*pte) |= L_PTE_S2_RDWR; +} + +struct kvm; + +static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn) +{ + /* + * If we are going to insert an instruction page and the icache is + * either VIPT or PIPT, there is a potential problem where the host + * (or another VM) may have used the same page as this guest, and we + * read incorrect data from the icache. If we're using a PIPT cache, + * we can invalidate just that page, but if we are using a VIPT cache + * we need to invalidate the entire icache - damn shame - as written + * in the ARM ARM (DDI 0406C.b - Page B3-1393). + * + * VIVT caches are tagged using both the ASID and the VMID and doesn't + * need any kind of flushing (DDI 0406C.b - Page B3-1392). + */ + if (icache_is_pipt()) { + unsigned long hva = gfn_to_hva(kvm, gfn); + __cpuc_coherent_user_range(hva, hva + PAGE_SIZE); + } else if (!icache_is_vivt_asid_tagged()) { + /* any kind of VIPT cache */ + __flush_icache_all(); + } +} + #endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/include/asm/kvm_vgic.h b/arch/arm/include/asm/kvm_vgic.h index ab97207d9cd3..343744e4809c 100644 --- a/arch/arm/include/asm/kvm_vgic.h +++ b/arch/arm/include/asm/kvm_vgic.h @@ -21,7 +21,6 @@ #include <linux/kernel.h> #include <linux/kvm.h> -#include <linux/kvm_host.h> #include <linux/irqreturn.h> #include <linux/spinlock.h> #include <linux/types.h> diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 308ad7d6f98b..75bf07910b81 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -8,6 +8,8 @@ * published by the Free Software Foundation. */ +#include <linux/types.h> + #ifndef __ASSEMBLY__ struct tag; @@ -16,8 +18,10 @@ struct pt_regs; struct smp_operations; #ifdef CONFIG_SMP #define smp_ops(ops) (&(ops)) +#define smp_init_ops(ops) (&(ops)) #else #define smp_ops(ops) (struct smp_operations *)NULL +#define smp_init_ops(ops) (bool (*)(void))NULL #endif struct machine_desc { @@ -41,6 +45,7 @@ struct machine_desc { unsigned char reserve_lp2 :1; /* never has lp2 */ char restart_mode; /* default restart mode */ struct smp_operations *smp; /* SMP operations */ + bool (*smp_init)(void); void (*fixup)(struct tag *, char **, struct meminfo *); void (*reserve)(void);/* reserve mem blocks */ diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h index 18c883023339..2092ee1e1300 100644 --- a/arch/arm/include/asm/mach/irq.h +++ b/arch/arm/include/asm/mach/irq.h @@ -20,11 +20,6 @@ struct seq_file; extern void init_FIQ(int); extern int show_fiq_list(struct seq_file *, int); -#ifdef CONFIG_MULTI_IRQ_HANDLER -extern void (*handle_arch_irq)(struct pt_regs *); -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); -#endif - /* * This is for easy migration, but should be changed in the source */ @@ -35,35 +30,4 @@ do { \ raw_spin_unlock(&desc->lock); \ } while(0) -#ifndef __ASSEMBLY__ -/* - * Entry/exit functions for chained handlers where the primary IRQ chip - * may implement either fasteoi or level-trigger flow control. - */ -static inline void chained_irq_enter(struct irq_chip *chip, - struct irq_desc *desc) -{ - /* FastEOI controllers require no action on entry. */ - if (chip->irq_eoi) - return; - - if (chip->irq_mask_ack) { - chip->irq_mask_ack(&desc->irq_data); - } else { - chip->irq_mask(&desc->irq_data); - if (chip->irq_ack) - chip->irq_ack(&desc->irq_data); - } -} - -static inline void chained_irq_exit(struct irq_chip *chip, - struct irq_desc *desc) -{ - if (chip->irq_eoi) - chip->irq_eoi(&desc->irq_data); - else - chip->irq_unmask(&desc->irq_data); -} -#endif - #endif diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h new file mode 100644 index 000000000000..7626a7fd4938 --- /dev/null +++ b/arch/arm/include/asm/mcpm.h @@ -0,0 +1,217 @@ +/* + * arch/arm/include/asm/mcpm.h + * + * Created by: Nicolas Pitre, April 2012 + * Copyright: (C) 2012-2013 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. + */ + +#ifndef MCPM_H +#define MCPM_H + +/* + * Maximum number of possible clusters / CPUs per cluster. + * + * This should be sufficient for quite a while, while keeping the + * (assembly) code simpler. When this starts to grow then we'll have + * to consider dynamic allocation. + */ +#define MAX_CPUS_PER_CLUSTER 4 +#define MAX_NR_CLUSTERS 2 + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> +#include <asm/cacheflush.h> + +/* + * Platform specific code should use this symbol to set up secondary + * entry location for processors to use when released from reset. + */ +extern void mcpm_entry_point(void); + +/* + * This is used to indicate where the given CPU from given cluster should + * branch once it is ready to re-enter the kernel using ptr, or NULL if it + * should be gated. A gated CPU is held in a WFE loop until its vector + * becomes non NULL. + */ +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. + */ + +/** + * mcpm_cpu_power_up - make given CPU in given cluster runable + * + * @cpu: CPU number within given cluster + * @cluster: cluster number for the CPU + * + * The identified CPU is brought out of reset. If the cluster was powered + * down then it is brought up as well, taking care not to let the other CPUs + * in the cluster run, and ensuring appropriate cluster setup. + * + * Caller must ensure the appropriate entry vector is initialized with + * mcpm_set_entry_vector() prior to calling this. + * + * This must be called in a sleepable context. However, the implementation + * is strongly encouraged to return early and let the operation happen + * asynchronously, especially when significant delays are expected. + * + * If the operation cannot be performed then an error code is returned. + */ +int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster); + +/** + * mcpm_cpu_power_down - power the calling CPU down + * + * The calling CPU is powered down. + * + * If this CPU is found to be the "last man standing" in the cluster + * then the cluster is prepared for power-down too. + * + * This must be called with interrupts disabled. + * + * This does not return. Re-entry in the kernel is expected via + * mcpm_entry_point. + */ +void mcpm_cpu_power_down(void); + +/** + * mcpm_cpu_suspend - bring the calling CPU in a suspended state + * + * @expected_residency: duration in microseconds the CPU is expected + * to remain suspended, or 0 if unknown/infinity. + * + * The calling CPU is suspended. The expected residency argument is used + * as a hint by the platform specific backend to implement the appropriate + * sleep state level according to the knowledge it has on wake-up latency + * for the given hardware. + * + * If this CPU is found to be the "last man standing" in the cluster + * then the cluster may be prepared for power-down too, if the expected + * residency makes it worthwhile. + * + * This must be called with interrupts disabled. + * + * This does not return. Re-entry in the kernel is expected via + * mcpm_entry_point. + */ +void mcpm_cpu_suspend(u64 expected_residency); + +/** + * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up + * + * This lets the platform specific backend code perform needed housekeeping + * work. This must be called by the newly activated CPU as soon as it is + * fully operational in kernel space, before it enables interrupts. + * + * If the operation cannot be performed then an error code is returned. + */ +int mcpm_cpu_powered_up(void); + +/* + * Platform specific methods used in the implementation of the above API. + */ +struct mcpm_platform_ops { + int (*power_up)(unsigned int cpu, unsigned int cluster); + void (*power_down)(void); + void (*suspend)(u64); + void (*powered_up)(void); +}; + +/** + * mcpm_platform_register - register platform specific power methods + * + * @ops: mcpm_platform_ops structure to register + * + * An error is returned if the registration has been done previously. + */ +int __init mcpm_platform_register(const struct mcpm_platform_ops *ops); + +/* Synchronisation structures for coordinating safe cluster setup/teardown: */ + +/* + * When modifying this structure, make sure you update the MCPM_SYNC_ defines + * to match. + */ +struct mcpm_sync_struct { + /* individual CPU states */ + struct { + s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE); + } cpus[MAX_CPUS_PER_CLUSTER]; + + /* cluster state */ + s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE); + + /* inbound-side state */ + s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE); +}; + +struct sync_struct { + struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS]; +}; + +extern unsigned long sync_phys; /* physical address of *mcpm_sync */ + +void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster); +void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster); +void __mcpm_outbound_leave_critical(unsigned int cluster, int state); +bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster); +int __mcpm_cluster_state(unsigned int cluster); + +int __init mcpm_sync_init( + void (*power_up_setup)(unsigned int affinity_level)); + +void __init mcpm_smp_set_ops(void); + +#else + +/* + * asm-offsets.h causes trouble when included in .c files, and cacheflush.h + * cannot be included in asm files. Let's work around the conflict like this. + */ +#include <asm/asm-offsets.h> +#define __CACHE_WRITEBACK_GRANULE CACHE_WRITEBACK_GRANULE + +#endif /* ! __ASSEMBLY__ */ + +/* Definitions for mcpm_sync_struct */ +#define CPU_DOWN 0x11 +#define CPU_COMING_UP 0x12 +#define CPU_UP 0x13 +#define CPU_GOING_DOWN 0x14 + +#define CLUSTER_DOWN 0x21 +#define CLUSTER_UP 0x22 +#define CLUSTER_GOING_DOWN 0x23 + +#define INBOUND_NOT_COMING_UP 0x31 +#define INBOUND_COMING_UP 0x32 + +/* + * Offsets for the mcpm_sync_struct members, for use in asm. + * We don't want to make them global to the kernel via asm-offsets.c. + */ +#define MCPM_SYNC_CLUSTER_CPUS 0 +#define MCPM_SYNC_CPU_SIZE __CACHE_WRITEBACK_GRANULE +#define MCPM_SYNC_CLUSTER_CLUSTER \ + (MCPM_SYNC_CLUSTER_CPUS + MCPM_SYNC_CPU_SIZE * MAX_CPUS_PER_CLUSTER) +#define MCPM_SYNC_CLUSTER_INBOUND \ + (MCPM_SYNC_CLUSTER_CLUSTER + __CACHE_WRITEBACK_GRANULE) +#define MCPM_SYNC_CLUSTER_SIZE \ + (MCPM_SYNC_CLUSTER_INBOUND + __CACHE_WRITEBACK_GRANULE) + +#endif diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h index 968c0a14e0a3..209e6504922e 100644 --- a/arch/arm/include/asm/percpu.h +++ b/arch/arm/include/asm/percpu.h @@ -30,8 +30,15 @@ static inline void set_my_cpu_offset(unsigned long off) static inline unsigned long __my_cpu_offset(void) { unsigned long off; - /* Read TPIDRPRW */ - asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) : : "memory"); + register unsigned long *sp asm ("sp"); + + /* + * Read TPIDRPRW. + * We want to allow caching the value, so avoid using volatile and + * instead use a fake stack read to hazard against barrier(). + */ + asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) : "Q" (*sp)); + return off; } #define __my_cpu_offset __my_cpu_offset() diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 80d6fc4dbe4a..9bcd262a9008 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -61,6 +61,15 @@ extern void __pgd_error(const char *file, int line, pgd_t); #define FIRST_USER_ADDRESS PAGE_SIZE /* + * Use TASK_SIZE as the ceiling argument for free_pgtables() and + * free_pgd_range() to avoid freeing the modules pmd when LPAE is enabled (pmd + * page shared between user and kernel). + */ +#ifdef CONFIG_ARM_LPAE +#define USER_PGTABLES_CEILING TASK_SIZE +#endif + +/* * The pgprot_* and protection_map entries will be fixed up in runtime * to include the cachable and bufferable bits based on memory policy, * as well as any architecture dependent bits like global/ASID and SMP diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index f24edad26c70..a7eaad37497f 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -13,7 +13,9 @@ #define __ARM_PMU_H__ #include <linux/interrupt.h> +#include <linux/percpu.h> #include <linux/perf_event.h> +#include <linux/types.h> /* * struct arm_pmu_platdata - ARM PMU platform data @@ -62,9 +64,34 @@ 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_cpu_pmu { + bool valid; + bool active; + + u32 mpidr; + int irq; + + struct perf_event *hw_events[ARMPMU_MAX_HWEVENTS]; + unsigned long used_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)]; + struct pmu_hw_events cpu_hw_events; + struct cpupmu_regs cpu_pmu_regs; + + void *logical_state; +}; + 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); @@ -81,16 +108,26 @@ 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 *); + void (*cpu_init)(struct arm_pmu *, struct arm_cpu_pmu *); int num_events; atomic_t active_events; struct mutex reserve_mutex; u64 max_period; struct platform_device *plat_device; - struct pmu_hw_events *(*get_hw_events)(void); + struct pmu_hw_events *(*get_hw_events)(struct arm_pmu *); + + struct list_head class_pmus_list; + struct arm_cpu_pmu __percpu *cpu_pmus; }; #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) +#define for_each_pmu(pmu, head) list_for_each_entry(pmu, head, class_pmus_list) + +#define to_this_cpu_pmu(arm_pmu) this_cpu_ptr((arm_pmu)->cpu_pmus) + extern const struct dev_pm_ops armpmu_dev_pm_ops; int armpmu_register(struct arm_pmu *armpmu, int type); diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h index ce0dbe7c1625..a079cbee4275 100644 --- a/arch/arm/include/asm/psci.h +++ b/arch/arm/include/asm/psci.h @@ -16,6 +16,10 @@ #define PSCI_POWER_STATE_TYPE_STANDBY 0 #define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 +#define PSCI_POWER_STATE_AFFINITY_LEVEL0 0 +#define PSCI_POWER_STATE_AFFINITY_LEVEL1 1 +#define PSCI_POWER_STATE_AFFINITY_LEVEL2 2 +#define PSCI_POWER_STATE_AFFINITY_LEVEL3 3 struct psci_power_state { u16 id; @@ -33,4 +37,12 @@ struct psci_operations { extern struct psci_operations psci_ops; +#ifdef CONFIG_ARM_PSCI +extern int __init psci_probe(void); +#else +static inline int psci_probe(void) +{ + return -ENODEV; +} +#endif #endif /* __ASM_ARM_PSCI_H */ diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index c5aa088c0a8b..7a9cc0948a37 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); + extern void smp_send_all_cpu_backtrace(void); struct smp_operations { diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 58b8b84adcd2..983fa7c153a2 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/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 023bfeb367bf..c1ee007523d7 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -53,12 +53,12 @@ #define KVM_ARM_FIQ_spsr fiq_regs[7] struct kvm_regs { - struct pt_regs usr_regs;/* R0_usr - R14_usr, PC, CPSR */ - __u32 svc_regs[3]; /* SP_svc, LR_svc, SPSR_svc */ - __u32 abt_regs[3]; /* SP_abt, LR_abt, SPSR_abt */ - __u32 und_regs[3]; /* SP_und, LR_und, SPSR_und */ - __u32 irq_regs[3]; /* SP_irq, LR_irq, SPSR_irq */ - __u32 fiq_regs[8]; /* R8_fiq - R14_fiq, SPSR_fiq */ + struct pt_regs usr_regs; /* R0_usr - R14_usr, PC, CPSR */ + unsigned long svc_regs[3]; /* SP_svc, LR_svc, SPSR_svc */ + unsigned long abt_regs[3]; /* SP_abt, LR_abt, SPSR_abt */ + unsigned long und_regs[3]; /* SP_und, LR_und, SPSR_und */ + unsigned long irq_regs[3]; /* SP_irq, LR_irq, SPSR_irq */ + unsigned long fiq_regs[8]; /* R8_fiq - R14_fiq, SPSR_fiq */ }; /* Supported Processor Types */ diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 923eec7105cf..a53efa993690 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -149,6 +149,10 @@ int main(void) DEFINE(DMA_BIDIRECTIONAL, DMA_BIDIRECTIONAL); DEFINE(DMA_TO_DEVICE, DMA_TO_DEVICE); DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE); + BLANK(); + DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER); + DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE); + BLANK(); #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); DEFINE(VCPU_MIDR, offsetof(struct kvm_vcpu, arch.midr)); @@ -165,10 +169,10 @@ int main(void) DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc)); DEFINE(VCPU_CPSR, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr)); DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines)); - DEFINE(VCPU_HSR, offsetof(struct kvm_vcpu, arch.hsr)); - DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.hxfar)); - DEFINE(VCPU_HPFAR, offsetof(struct kvm_vcpu, arch.hpfar)); - DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.hyp_pc)); + DEFINE(VCPU_HSR, offsetof(struct kvm_vcpu, arch.fault.hsr)); + DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.fault.hxfar)); + DEFINE(VCPU_HPFAR, offsetof(struct kvm_vcpu, arch.fault.hpfar)); + DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.fault.hyp_pc)); #ifdef CONFIG_KVM_ARM_VGIC DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); DEFINE(VGIC_CPU_HCR, offsetof(struct vgic_cpu, vgic_hcr)); diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index 854bd22380d3..5b391a689b47 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -98,8 +98,9 @@ __mmap_switched: str r9, [r4] @ Save processor ID str r1, [r5] @ Save machine type str r2, [r6] @ Save atags pointer - bic r4, r0, #CR_A @ Clear 'A' bit - stmia r7, {r0, r4} @ Save control register values + cmp r7, #0 + bicne r4, r0, #CR_A @ Clear 'A' bit + stmneia r7, {r0, r4} @ Save control register values b start_kernel ENDPROC(__mmap_switched) @@ -113,7 +114,11 @@ __mmap_switched_data: .long processor_id @ r4 .long __machine_arch_type @ r5 .long __atags_pointer @ r6 +#ifdef CONFIG_CPU_CP15 .long cr_alignment @ r7 +#else + .long 0 @ r7 +#endif .long init_thread_union + THREAD_START_SP @ sp .size __mmap_switched_data, . - __mmap_switched_data diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index 2c228a07e58c..6a2e09c952c7 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -32,15 +32,21 @@ * numbers for r1. * */ - .arm __HEAD + +#ifdef CONFIG_CPU_THUMBONLY + .thumb +ENTRY(stext) +#else + .arm ENTRY(stext) THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM. THUMB( bx r9 ) @ If this is a Thumb-2 kernel, THUMB( .thumb ) @ switch to Thumb now. THUMB(1: ) +#endif setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode @ and irqs disabled diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 1fd749ee4a1b..1b803117ed91 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/perf_event.c b/arch/arm/kernel/perf_event.c index 8c3094d0f7b7..3d753cc4aa08 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> @@ -81,6 +82,9 @@ 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 +162,8 @@ 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 +180,8 @@ 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. @@ -197,10 +205,13 @@ static void armpmu_del(struct perf_event *event, int flags) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct pmu_hw_events *hw_events = armpmu->get_hw_events(); + struct pmu_hw_events *hw_events = armpmu->get_hw_events(armpmu); 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); @@ -212,11 +223,15 @@ static int armpmu_add(struct perf_event *event, int flags) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct pmu_hw_events *hw_events = armpmu->get_hw_events(); + struct pmu_hw_events *hw_events = armpmu->get_hw_events(armpmu); struct hw_perf_event *hwc = &event->hw; 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. */ @@ -416,6 +431,10 @@ 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; @@ -448,8 +467,14 @@ static int armpmu_event_init(struct perf_event *event) static void armpmu_enable(struct pmu *pmu) { struct arm_pmu *armpmu = to_arm_pmu(pmu); - struct pmu_hw_events *hw_events = armpmu->get_hw_events(); - int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events); + struct pmu_hw_events *hw_events = armpmu->get_hw_events(armpmu); + int enabled; + + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; + + BUG_ON(!hw_events->used_mask); /* TEMPORARY */ + enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events); if (enabled) armpmu->start(armpmu); @@ -458,6 +483,10 @@ static void armpmu_enable(struct pmu *pmu) static void armpmu_disable(struct pmu *pmu) { struct arm_pmu *armpmu = to_arm_pmu(pmu); + + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; + armpmu->stop(armpmu); } diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 1f2740e3dbc0..b3ae24f6afab 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -19,23 +19,40 @@ #define pr_fmt(fmt) "CPU PMU: " fmt #include <linux/bitmap.h> +#include <linux/cpumask.h> +#include <linux/cpu_pm.h> #include <linux/export.h> #include <linux/kernel.h> +#include <linux/list.h> #include <linux/of.h> +#include <linux/percpu.h> #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <asm/bL_switcher.h> #include <asm/cputype.h> #include <asm/irq_regs.h> #include <asm/pmu.h> +#include <asm/smp_plat.h> +#include <asm/topology.h> -/* Set at runtime when we know what CPU type we are. */ -static struct arm_pmu *cpu_pmu; +static LIST_HEAD(cpu_pmus_list); -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); +#define cpu_for_each_pmu(pmu, cpu_pmu, cpu) \ + for_each_pmu(pmu, &cpu_pmus_list) \ + if (((cpu_pmu) = per_cpu_ptr((pmu)->cpu_pmus, cpu))->valid) + +static struct arm_pmu *__cpu_find_any_pmu(unsigned int cpu) +{ + struct arm_pmu *pmu; + struct arm_cpu_pmu *cpu_pmu; + + cpu_for_each_pmu(pmu, cpu_pmu, cpu) + return pmu; + + return NULL; +} /* * Despite the names, these two functions are CPU-specific and are used @@ -43,21 +60,22 @@ static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events); */ const char *perf_pmu_name(void) { - if (!cpu_pmu) + struct arm_pmu *pmu = __cpu_find_any_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 = __cpu_find_any_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); @@ -66,89 +84,125 @@ EXPORT_SYMBOL_GPL(perf_num_counters); #include "perf_event_v6.c" #include "perf_event_v7.c" -static struct pmu_hw_events *cpu_pmu_get_cpu_events(void) +static struct pmu_hw_events *cpu_pmu_get_cpu_events(struct arm_pmu *pmu) { - return &__get_cpu_var(cpu_hw_events); + return &this_cpu_ptr(pmu->cpu_pmus)->cpu_hw_events; } -static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu) +static int find_logical_cpu(u32 mpidr) { - int i, irq, irqs; - struct platform_device *pmu_device = cpu_pmu->plat_device; + int cpu = bL_switcher_get_logical_index(mpidr); - irqs = min(pmu_device->num_resources, num_possible_cpus()); + if (cpu != -EUNATCH) + return cpu; - for (i = 0; i < irqs; ++i) { - if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs)) + return get_logical_index(mpidr); +} + +static void cpu_pmu_free_irq(struct arm_pmu *pmu) +{ + int i; + int cpu; + struct arm_cpu_pmu *cpu_pmu; + + for_each_possible_cpu(i) { + if (!(cpu_pmu = per_cpu_ptr(pmu->cpu_pmus, i))) continue; - irq = platform_get_irq(pmu_device, i); - if (irq >= 0) - free_irq(irq, cpu_pmu); + + if (cpu_pmu->mpidr == -1) + continue; + + cpu = find_logical_cpu(cpu_pmu->mpidr); + if (cpu < 0) + continue; + + if (!cpumask_test_and_clear_cpu(cpu, &pmu->active_irqs)) + continue; + if (cpu_pmu->irq >= 0) + free_irq(cpu_pmu->irq, pmu); } } -static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) +static int cpu_pmu_request_irq(struct arm_pmu *pmu, irq_handler_t handler) { int i, err, irq, irqs; - struct platform_device *pmu_device = cpu_pmu->plat_device; + int cpu; + struct arm_cpu_pmu *cpu_pmu; - if (!pmu_device) - return -ENODEV; + irqs = 0; + for_each_possible_cpu(i) + if (per_cpu_ptr(pmu->cpu_pmus, i)) + ++irqs; - irqs = min(pmu_device->num_resources, num_possible_cpus()); if (irqs < 1) { pr_err("no irqs for PMUs defined\n"); return -ENODEV; } - for (i = 0; i < irqs; ++i) { - err = 0; - irq = platform_get_irq(pmu_device, i); + for_each_possible_cpu(i) { + if (!(cpu_pmu = per_cpu_ptr(pmu->cpu_pmus, i))) + continue; + + irq = cpu_pmu->irq; if (irq < 0) continue; + cpu = find_logical_cpu(cpu_pmu->mpidr); + if (cpu < 0 || cpu != i) + continue; + /* * If we have a single PMU interrupt that we can't shift, * 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); + irq, cpu); continue; } + pr_debug("%s: requesting IRQ %d for CPU%d\n", + pmu->name, irq, cpu); + err = request_irq(irq, handler, IRQF_NOBALANCING, "arm-pmu", - cpu_pmu); + pmu); if (err) { pr_err("unable to request IRQ%d for ARM PMU counters\n", irq); return err; } - cpumask_set_cpu(i, &cpu_pmu->active_irqs); + cpumask_set_cpu(cpu, &pmu->active_irqs); } return 0; } -static void cpu_pmu_init(struct arm_pmu *cpu_pmu) +static void cpu_pmu_init(struct arm_pmu *pmu) { int cpu; - for_each_possible_cpu(cpu) { - 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); + for_each_cpu_mask(cpu, pmu->valid_cpus) { + struct arm_cpu_pmu *cpu_pmu = per_cpu_ptr(pmu->cpu_pmus, cpu); + struct pmu_hw_events *events = &cpu_pmu->cpu_hw_events; + + events->events = cpu_pmu->hw_events; + events->used_mask = cpu_pmu->used_mask; raw_spin_lock_init(&events->pmu_lock); + + if (pmu->cpu_init) + pmu->cpu_init(pmu, cpu_pmu); + + cpu_pmu->valid = true; } - cpu_pmu->get_hw_events = cpu_pmu_get_cpu_events; - cpu_pmu->request_irq = cpu_pmu_request_irq; - cpu_pmu->free_irq = cpu_pmu_free_irq; + pmu->get_hw_events = cpu_pmu_get_cpu_events; + pmu->request_irq = cpu_pmu_request_irq; + pmu->free_irq = cpu_pmu_free_irq; /* Ensure the PMU has sane values out of reset. */ - if (cpu_pmu->reset) - on_each_cpu(cpu_pmu->reset, cpu_pmu, 1); + if (pmu->reset) + on_each_cpu_mask(&pmu->valid_cpus, pmu->reset, pmu, 1); } /* @@ -160,21 +214,52 @@ 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; + struct arm_cpu_pmu *cpu_pmu; + int ret = NOTIFY_DONE; + if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING) return NOTIFY_DONE; - if (cpu_pmu && cpu_pmu->reset) - cpu_pmu->reset(cpu_pmu); - else - return NOTIFY_DONE; + cpu_for_each_pmu(pmu, cpu_pmu, (unsigned int)hcpu) + if (pmu->reset) { + pmu->reset(pmu); + ret = NOTIFY_OK; + } - return NOTIFY_OK; + return ret; +} + +static int cpu_pmu_pm_notify(struct notifier_block *b, + unsigned long action, void *hcpu) +{ + int cpu = smp_processor_id(); + struct arm_pmu *pmu; + struct arm_cpu_pmu *cpu_pmu; + int ret = NOTIFY_DONE; + + cpu_for_each_pmu(pmu, cpu_pmu, cpu) { + struct cpupmu_regs *pmuregs = &cpu_pmu->cpu_pmu_regs; + + 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); + + ret = NOTIFY_OK; + } + + return ret; } 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. */ @@ -246,52 +331,197 @@ 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; } +static void cpu_pmu_free(struct arm_pmu *pmu) +{ + if (!pmu) + return; + + free_percpu(pmu->cpu_pmus); + kfree(pmu); +} + +/* + * HACK: Find a b.L switcher partner for CPU cpu on the specified cluster + * This information should be obtained from an interface provided by the + * Switcher itself, if possible. + */ +#ifdef CONFIG_BL_SWITCHER +static int bL_get_partner(int cpu, int cluster) +{ + unsigned int i; + + + for_each_possible_cpu(i) { + if (cpu_topology[i].thread_id == cpu_topology[cpu].thread_id && + cpu_topology[i].core_id == cpu_topology[cpu].core_id && + cpu_topology[i].socket_id == cluster) + return i; + } + + return -1; /* no partner found */ +} +#else +static int bL_get_partner(int __always_unused cpu, int __always_unused cluster) +{ + return -1; +} +#endif + +static int find_irq(struct platform_device *pdev, + struct device_node *pmu_node, + struct device_node *cluster_node, + u32 mpidr) +{ + int irq = -1; + u32 cluster; + u32 core; + struct device_node *cores_node; + struct device_node *core_node = NULL; + + if (of_property_read_u32(cluster_node, "reg", &cluster) || + cluster != MPIDR_AFFINITY_LEVEL(mpidr, 1)) + goto error; + + cores_node = of_get_child_by_name(cluster_node, "cores"); + if (!cores_node) + goto error; + + for_each_child_of_node(cores_node, core_node) + if (!of_property_read_u32(core_node, "reg", &core) && + core == MPIDR_AFFINITY_LEVEL(mpidr, 0)) + break; + + if (!core_node) + goto error; + + irq = platform_get_irq(pdev, core); + +error: + of_node_put(core_node); + of_node_put(cores_node); + return irq; +} + 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; - } + struct arm_cpu_pmu __percpu *cpu_pmus; + int ret = 0; pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL); - if (!pmu) { - pr_info("failed to allocate PMU device!"); - return -ENOMEM; - } + if (!pmu) + goto error_nomem; + + pmu->cpu_pmus = cpu_pmus = alloc_percpu(struct arm_cpu_pmu); + if (!cpu_pmus) + goto error_nomem; 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; + cpumask_t phys_sibling_mask; + unsigned int i; + + 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 */ + /* + * In a switcher kernel, we affine all PMUs to CPUs and + * abstract the runtime presence/absence of PMUs at a lower + * level. + */ + if (cluster == -1 || IS_ENABLED(CONFIG_BL_SWITCHER) || + cluster_to_logical_mask(cluster, &sibling_mask)) + cpumask_copy(&sibling_mask, cpu_possible_mask); + + if (bL_switcher_get_enabled()) + /* + * The switcher initialises late now, so it should not + * have initialised yet: + */ + BUG(); + + cpumask_copy(&phys_sibling_mask, cpu_possible_mask); + + /* + * HACK: Deduce how the switcher will modify the topology + * in order to fill in PMU<->CPU combinations which don't + * make sense when the switcher is disabled. Ideally, this + * knowledge should come from the swithcer somehow. + */ + for_each_possible_cpu(i) { + int cpu = i; + + per_cpu_ptr(cpu_pmus, i)->mpidr = -1; + per_cpu_ptr(cpu_pmus, i)->irq = -1; + + if (cpu_topology[i].socket_id != cluster) { + cpumask_clear_cpu(i, &phys_sibling_mask); + cpu = bL_get_partner(i, cluster); + } + + if (cpu == -1) + cpumask_clear_cpu(i, &sibling_mask); + else { + int irq = find_irq(pdev, node, ncluster, + cpu_logical_map(cpu)); + per_cpu_ptr(cpu_pmus, i)->mpidr = + cpu_logical_map(cpu); + per_cpu_ptr(cpu_pmus, i)->irq = irq; + } + } + + /* + * This relies on an MP view of the system to choose the right + * CPU to run init_fn: + */ + smp_call_function_any(&phys_sibling_mask, init_fn, pmu, 1); + + bL_switcher_put_enabled(); + + /* now set the valid_cpus after init */ + cpumask_copy(&pmu->valid_cpus, &sibling_mask); } else { ret = probe_current_pmu(pmu); } - if (ret) { - pr_info("failed to probe PMU!"); - goto out_free; - } + if (ret) + goto error; - cpu_pmu = pmu; - cpu_pmu->plat_device = pdev; - cpu_pmu_init(cpu_pmu); - ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW); + pmu->plat_device = pdev; + cpu_pmu_init(pmu); + ret = armpmu_register(pmu, -1); - if (!ret) - return 0; + if (ret) + goto error; -out_free: - pr_info("failed to register PMU devices!"); - kfree(pmu); + list_add(&pmu->class_pmus_list, &cpu_pmus_list); + goto out; + +error_nomem: + pr_warn("out of memory\n"); + ret = -ENOMEM; +error: + pr_warn("failed to register PMU device(s)!\n"); + cpu_pmu_free(pmu); +out: return ret; } @@ -313,9 +543,17 @@ 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_v6.c b/arch/arm/kernel/perf_event_v6.c index 03664b0e8fa4..a191bdb9ebd6 100644 --- a/arch/arm/kernel/perf_event_v6.c +++ b/arch/arm/kernel/perf_event_v6.c @@ -439,7 +439,7 @@ static void armv6pmu_enable_event(struct perf_event *event) unsigned long val, mask, evt, flags; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); int idx = hwc->idx; if (ARMV6_CYCLE_COUNTER == idx) { @@ -477,7 +477,7 @@ armv6pmu_handle_irq(int irq_num, unsigned long pmcr = armv6_pmcr_read(); struct perf_sample_data data; struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev; - struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events(); + struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events(cpu_pmu); struct pt_regs *regs; int idx; @@ -533,7 +533,7 @@ armv6pmu_handle_irq(int irq_num, static void armv6pmu_start(struct arm_pmu *cpu_pmu) { unsigned long flags, val; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); raw_spin_lock_irqsave(&events->pmu_lock, flags); val = armv6_pmcr_read(); @@ -545,7 +545,7 @@ static void armv6pmu_start(struct arm_pmu *cpu_pmu) static void armv6pmu_stop(struct arm_pmu *cpu_pmu) { unsigned long flags, val; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); raw_spin_lock_irqsave(&events->pmu_lock, flags); val = armv6_pmcr_read(); @@ -586,7 +586,7 @@ static void armv6pmu_disable_event(struct perf_event *event) unsigned long val, mask, evt, flags; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); int idx = hwc->idx; if (ARMV6_CYCLE_COUNTER == idx) { @@ -621,7 +621,7 @@ static void armv6mpcore_pmu_disable_event(struct perf_event *event) unsigned long val, mask, flags, evt = 0; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); int idx = hwc->idx; if (ARMV6_CYCLE_COUNTER == idx) { diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 039cffb053a7..25762a548f26 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -18,6 +18,175 @@ #ifdef CONFIG_CPU_V7 +struct armv7_pmu_logical_state { + u32 PMCR; + u32 PMCNTENSET; + u32 PMCNTENCLR; + u32 PMOVSR; + u32 PMSWINC; + u32 PMSELR; + u32 PMCEID0; + u32 PMCEID1; + + u32 PMCCNTR; + + u32 PMUSERENR; + u32 PMINTENSET; + u32 PMINTENCLR; + u32 PMOVSSET; + + struct armv7_pmu_logical_cntr_state { + u32 PMXEVTYPER; + u32 PMXEVCNTR; + } cntrs[1]; /* we will grow this during allocation */ +}; + +#define __v7_logical_state(cpupmu) \ + ((struct armv7_pmu_logical_state *)(cpupmu)->logical_state) + +#define __v7_logical_state_single(cpupmu, name) \ + __v7_logical_state(cpupmu)->name +#define __v7_logical_state_cntr(cpupmu, name) \ + __v7_logical_state(cpupmu)->cntrs[__v7_logical_state(cpupmu)->PMSELR].name + +#define __def_v7_pmu_reg_W(kind, name, op1, Cm, op2) \ + static inline u32 __v7_pmu_write_physical_##name(u32 value) \ + { \ + asm volatile ( \ + "mcr p15, " #op1 ", %0, c9, " #Cm ", " #op2 \ + :: "r" (value) \ + ); \ + \ + return value; \ + } \ + \ + static inline u32 __v7_pmu_write_logical_##name( \ + struct arm_cpu_pmu *cpupmu, u32 value) \ + { \ + __v7_logical_state_##kind(cpupmu, name) = value; \ + return value; \ + } + +#define __def_v7_pmu_reg_R(kind, name, op1, Cm, op2) \ + static inline u32 __v7_pmu_read_physical_##name(void) \ + { \ + u32 result; \ + \ + asm volatile ( \ + "mrc p15, " #op1 ", %0, c9, " #Cm ", " #op2 \ + : "=r" (result) \ + ); \ + \ + return result; \ + } \ + \ + static inline u32 __v7_pmu_read_logical_##name( \ + struct arm_cpu_pmu *cpupmu) \ + { \ + return __v7_logical_state_##kind(cpupmu, name); \ + } + +#define __def_v7_pmu_reg_WO(name, op1, Cm, op2) \ + __def_v7_pmu_reg_W(single, name, op1, Cm, op2) +#define __def_v7_pmu_reg_RO(name, op1, Cm, op2) \ + __def_v7_pmu_reg_R(single, name, op1, Cm, op2) + +#define __def_v7_pmu_reg_RW(name, op1, Cm, op2) \ + __def_v7_pmu_reg_WO(name, op1, Cm, op2) \ + __def_v7_pmu_reg_RO(name, op1, Cm, op2) + +#define __def_v7_pmu_cntr_WO(name, op1, Cm, op2) \ + __def_v7_pmu_reg_W(cntr, name, op1, Cm, op2) +#define __def_v7_pmu_cntr_RO(name, op1, Cm, op2) \ + __def_v7_pmu_reg_R(cntr, name, op1, Cm, op2) + +#define __def_v7_pmu_cntr_RW(name, op1, Cm, op2) \ + __def_v7_pmu_cntr_WO(name, op1, Cm, op2) \ + __def_v7_pmu_cntr_RO(name, op1, Cm, op2) + +#define __def_v7_pmu_reg(name, prot, op1, Cm, op2) \ + __def_v7_pmu_reg_##prot(name, op1, Cm, op2) +#define __def_v7_pmu_cntr(name, prot, op1, Cm, op2) \ + __def_v7_pmu_cntr_##prot(name, op1, Cm, op2) + +__def_v7_pmu_reg(PMCR, RW, 0, c12, 0) +__def_v7_pmu_reg(PMCNTENSET, RW, 0, c12, 1) +__def_v7_pmu_reg(PMCNTENCLR, RW, 0, c12, 2) +__def_v7_pmu_reg(PMOVSR, RW, 0, c12, 3) +__def_v7_pmu_reg(PMSWINC, WO, 0, c12, 4) +__def_v7_pmu_reg(PMSELR, RW, 0, c12, 5) +__def_v7_pmu_reg(PMCEID0, RO, 0, c12, 6) +__def_v7_pmu_reg(PMCEID1, RO, 0, c12, 7) + +__def_v7_pmu_reg(PMCCNTR, RW, 0, c13, 0) +__def_v7_pmu_cntr(PMXEVTYPER, RW, 0, c13, 1) +__def_v7_pmu_cntr(PMXEVCNTR, RW, 0, c13, 2) + +__def_v7_pmu_reg(PMUSERENR, RW, 0, c14, 0) +__def_v7_pmu_reg(PMINTENSET, RW, 0, c14, 1) +__def_v7_pmu_reg(PMINTENCLR, RW, 0, c14, 2) +__def_v7_pmu_reg(PMOVSSET, RW, 0, c14, 3) + +#define __v7_pmu_write_physical(name, value) \ + __v7_pmu_write_physical_##name(value) +#define __v7_pmu_read_physical(name) \ + __v7_pmu_read_physical_##name() + +#define __v7_pmu_write_logical(cpupmu, name, value) \ + __v7_pmu_write_logical_##name(cpupmu, value) +#define __v7_pmu_read_logical(cpupmu, name) \ + __v7_pmu_read_logical_##name(cpupmu) + +#define __v7_pmu_write_reg(cpupmu, name, value) do { \ + if ((cpupmu)->active) \ + __v7_pmu_write_physical(name, value); \ + else \ + __v7_pmu_write_logical(cpupmu, name, value); \ +} while(0) + +#define __v7_pmu_read_reg(cpupmu, name) ( \ + (cpupmu)->active ? \ + __v7_pmu_read_physical(name) : \ + __v7_pmu_read_logical(cpupmu, name) \ +) + +#define __v7_pmu_reg_set(cpupmu, name, logical_name, mask) do { \ + if ((cpupmu)->active) \ + __v7_pmu_write_physical(name, mask); \ + else { \ + u32 __value; \ + __value =__v7_pmu_read_logical(cpupmu, logical_name) | (mask); \ + __v7_pmu_write_logical(cpupmu, logical_name, __value); \ + } \ +} while(0) + +#define __v7_pmu_reg_clr(cpupmu, name, logical_name, mask) do { \ + if ((cpupmu)->active) \ + __v7_pmu_write_physical(name, mask); \ + else { \ + u32 __value; \ + __value = __v7_pmu_read_logical(cpupmu, logical_name) & ~(mask); \ + __v7_pmu_write_logical(cpupmu, logical_name, __value); \ + } \ +} while(0) + +#define __v7_pmu_save_reg(cpupmu, name) \ + __v7_pmu_write_logical(cpupmu, name, \ + __v7_pmu_read_physical(name)) +#define __v7_pmu_restore_reg(cpupmu, name) \ + __v7_pmu_write_physical(name, \ + __v7_pmu_read_logical(cpupmu, name)) +static u32 read_mpidr(void) +{ + u32 result; + + asm volatile ("mrc p15, 0, %0, c0, c0, 5" : "=r" (result)); + + return result; +} + +static void armv7pmu_reset(void *info); + /* * Common ARMv7 event types * @@ -784,18 +953,16 @@ static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] #define ARMV7_EXCLUDE_USER (1 << 30) #define ARMV7_INCLUDE_HYP (1 << 27) -static inline u32 armv7_pmnc_read(void) +static inline u32 armv7_pmnc_read(struct arm_cpu_pmu *cpupmu) { - u32 val; - asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val)); - return val; + return __v7_pmu_read_reg(cpupmu, PMCR); } -static inline void armv7_pmnc_write(u32 val) +static inline void armv7_pmnc_write(struct arm_cpu_pmu *cpupmu, u32 val) { val &= ARMV7_PMNC_MASK; isb(); - asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val)); + __v7_pmu_write_reg(cpupmu, PMCR, val); } static inline int armv7_pmnc_has_overflowed(u32 pmnc) @@ -814,10 +981,10 @@ static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx) return pmnc & BIT(ARMV7_IDX_TO_COUNTER(idx)); } -static inline int armv7_pmnc_select_counter(int idx) +static inline int armv7_pmnc_select_counter(struct arm_cpu_pmu *cpupmu, int idx) { u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter)); + __v7_pmu_write_reg(cpupmu, PMSELR, counter); isb(); return idx; @@ -825,140 +992,197 @@ static inline int armv7_pmnc_select_counter(int idx) static inline u32 armv7pmu_read_counter(struct perf_event *event) { - struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct arm_pmu *pmu = to_arm_pmu(event->pmu); + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; u32 value = 0; - if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) + if (!armv7_pmnc_counter_valid(pmu, idx)) pr_err("CPU%u reading wrong counter %d\n", smp_processor_id(), idx); else if (idx == ARMV7_IDX_CYCLE_COUNTER) - asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value)); - else if (armv7_pmnc_select_counter(idx) == idx) - asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (value)); + value = __v7_pmu_read_reg(cpupmu, PMCCNTR); + else if (armv7_pmnc_select_counter(cpupmu, idx) == idx) + value = __v7_pmu_read_reg(cpupmu, PMXEVCNTR); return value; } static inline void armv7pmu_write_counter(struct perf_event *event, u32 value) { - struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct arm_pmu *pmu = to_arm_pmu(event->pmu); + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; - if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) + if (!armv7_pmnc_counter_valid(pmu, idx)) pr_err("CPU%u writing wrong counter %d\n", smp_processor_id(), idx); else if (idx == ARMV7_IDX_CYCLE_COUNTER) - asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value)); - else if (armv7_pmnc_select_counter(idx) == idx) - asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value)); + __v7_pmu_write_reg(cpupmu, PMCCNTR, value); + else if (armv7_pmnc_select_counter(cpupmu, idx) == idx) + __v7_pmu_write_reg(cpupmu, PMXEVCNTR, value); } -static inline void armv7_pmnc_write_evtsel(int idx, u32 val) +static inline void armv7_pmnc_write_evtsel(struct arm_cpu_pmu *cpupmu, int idx, u32 val) { - if (armv7_pmnc_select_counter(idx) == idx) { + if (armv7_pmnc_select_counter(cpupmu, idx) == idx) { val &= ARMV7_EVTYPE_MASK; - asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val)); + __v7_pmu_write_reg(cpupmu, PMXEVTYPER, val); } } -static inline int armv7_pmnc_enable_counter(int idx) +static inline int armv7_pmnc_enable_counter(struct arm_cpu_pmu *cpupmu, int idx) { u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter))); + __v7_pmu_reg_set(cpupmu, PMCNTENSET, PMCNTENSET, BIT(counter)); return idx; } -static inline int armv7_pmnc_disable_counter(int idx) +static inline int armv7_pmnc_disable_counter(struct arm_cpu_pmu *cpupmu, int idx) { u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter))); + __v7_pmu_reg_clr(cpupmu, PMCNTENCLR, PMCNTENSET, BIT(counter)); return idx; } -static inline int armv7_pmnc_enable_intens(int idx) +static inline int armv7_pmnc_enable_intens(struct arm_cpu_pmu *cpupmu, int idx) { u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter))); + __v7_pmu_reg_set(cpupmu, PMINTENSET, PMCNTENSET, BIT(counter)); return idx; } -static inline int armv7_pmnc_disable_intens(int idx) +static inline int armv7_pmnc_disable_intens(struct arm_cpu_pmu *cpupmu, int idx) { u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter))); + __v7_pmu_reg_clr(cpupmu, PMINTENCLR, PMINTENSET, BIT(counter)); isb(); /* Clear the overflow flag in case an interrupt is pending. */ - asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(counter))); + __v7_pmu_reg_clr(cpupmu, PMOVSR, PMOVSR, BIT(counter)); isb(); return idx; } -static inline u32 armv7_pmnc_getreset_flags(void) +static inline u32 armv7_pmnc_getreset_flags(struct arm_cpu_pmu *cpupmu) { u32 val; /* Read */ - asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val)); + val = __v7_pmu_read_reg(cpupmu, PMOVSR); /* Write to clear flags */ val &= ARMV7_FLAG_MASK; - asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val)); + __v7_pmu_reg_clr(cpupmu, PMOVSR, PMOVSR, val); return val; } #ifdef DEBUG -static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu) +static void armv7_pmnc_dump_regs(struct arm_pmu *pmu) { u32 val; unsigned int cnt; + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); printk(KERN_INFO "PMNC registers dump:\n"); + printk(KERN_INFO "PMNC =0x%08x\n", __v7_pmu_read_reg(PMCR)); + printk(KERN_INFO "CNTENS=0x%08x\n", __v7_pmu_read_reg(PMCNTENSET)); + printk(KERN_INFO "INTENS=0x%08x\n", __v7_pmu_read_reg(PMINTENSET)); + printk(KERN_INFO "FLAGS =0x%08x\n", __v7_pmu_read_reg(PMOVSR)); + printk(KERN_INFO "SELECT=0x%08x\n", __v7_pmu_read_reg(PMSELR)); + printk(KERN_INFO "CCNT =0x%08x\n", __v7_pmu_read_reg(PMCCNTR)); - asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val)); - printk(KERN_INFO "PMNC =0x%08x\n", val); + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(pmu); cnt++) { + armv7_pmnc_select_counter(cpupmu, cnt); + printk(KERN_INFO "CNT[%d] count =0x%08x\n", + ARMV7_IDX_TO_COUNTER(cnt), + __v7_pmu_read_reg(cpupmu, PMXEVCNTR)); + printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n", + ARMV7_IDX_TO_COUNTER(cnt), + __v7_pmu_read_reg(cpupmu, PMXEVTYPER)); + } +} +#endif - asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val)); - printk(KERN_INFO "CNTENS=0x%08x\n", val); +static void armv7pmu_save_regs(struct arm_pmu *pmu, + struct cpupmu_regs *regs) +{ + unsigned int cnt; + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); - asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val)); - printk(KERN_INFO "INTENS=0x%08x\n", val); + if (!cpupmu->active) + return; - asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val)); - printk(KERN_INFO "FLAGS =0x%08x\n", val); + if (!*cpupmu->cpu_hw_events.used_mask) + return; - asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val)); - printk(KERN_INFO "SELECT=0x%08x\n", val); + if (!__v7_pmu_save_reg(cpupmu, PMCR) & ARMV7_PMNC_E) + return; - asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); - printk(KERN_INFO "CCNT =0x%08x\n", val); + __v7_pmu_save_reg(cpupmu, PMCNTENSET); + __v7_pmu_save_reg(cpupmu, PMUSERENR); + __v7_pmu_save_reg(cpupmu, PMINTENSET); + __v7_pmu_save_reg(cpupmu, PMCCNTR); 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, 2" : "=r" (val)); - printk(KERN_INFO "CNT[%d] count =0x%08x\n", - ARMV7_IDX_TO_COUNTER(cnt), val); - asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val)); - printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n", - ARMV7_IDX_TO_COUNTER(cnt), val); + cnt <= ARMV7_IDX_COUNTER_LAST(pmu); cnt++) { + armv7_pmnc_select_counter(cpupmu, cnt); + __v7_pmu_save_reg(cpupmu, PMSELR); /* mirror physical PMSELR */ + __v7_pmu_save_reg(cpupmu, PMXEVTYPER); + __v7_pmu_save_reg(cpupmu, PMXEVCNTR); } + return; +} + +/* armv7pmu_reset() must be called before calling this funtion */ +static void armv7pmu_restore_regs(struct arm_pmu *pmu, + struct cpupmu_regs *regs) +{ + unsigned int cnt; + u32 pmcr; + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); + + armv7pmu_reset(pmu); + + if (!cpupmu->active) + return; + + if (!*cpupmu->cpu_hw_events.used_mask) + return; + + pmcr = __v7_pmu_read_logical(cpupmu, PMCR); + if (!pmcr & ARMV7_PMNC_E) + return; + + __v7_pmu_restore_reg(cpupmu, PMCNTENSET); + __v7_pmu_restore_reg(cpupmu, PMUSERENR); + __v7_pmu_restore_reg(cpupmu, PMINTENSET); + __v7_pmu_restore_reg(cpupmu, PMCCNTR); + + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(pmu); cnt++) { + armv7_pmnc_select_counter(cpupmu, cnt); + __v7_pmu_save_reg(cpupmu, PMSELR); /* mirror physical PMSELR */ + __v7_pmu_restore_reg(cpupmu, PMXEVTYPER); + __v7_pmu_restore_reg(cpupmu, PMXEVCNTR); + } + __v7_pmu_write_reg(cpupmu, PMCR, pmcr); } -#endif static void armv7pmu_enable_event(struct perf_event *event) { unsigned long flags; struct hw_perf_event *hwc = &event->hw; - struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct arm_pmu *pmu = to_arm_pmu(event->pmu); + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); + struct pmu_hw_events *events = pmu->get_hw_events(pmu); int idx = hwc->idx; - if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) { + if (!armv7_pmnc_counter_valid(pmu, idx)) { pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n", smp_processor_id(), idx); return; @@ -973,25 +1197,25 @@ static void armv7pmu_enable_event(struct perf_event *event) /* * Disable counter */ - armv7_pmnc_disable_counter(idx); + armv7_pmnc_disable_counter(cpupmu, idx); /* * Set event (if destined for PMNx counters) * We only need to set the event for the cycle counter if we * have the ability to perform event filtering. */ - if (cpu_pmu->set_event_filter || idx != ARMV7_IDX_CYCLE_COUNTER) - armv7_pmnc_write_evtsel(idx, hwc->config_base); + if (pmu->set_event_filter || idx != ARMV7_IDX_CYCLE_COUNTER) + armv7_pmnc_write_evtsel(cpupmu, idx, hwc->config_base); /* * Enable interrupt for this counter */ - armv7_pmnc_enable_intens(idx); + armv7_pmnc_enable_intens(cpupmu, idx); /* * Enable counter */ - armv7_pmnc_enable_counter(idx); + armv7_pmnc_enable_counter(cpupmu,idx); raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } @@ -1000,11 +1224,12 @@ static void armv7pmu_disable_event(struct perf_event *event) { unsigned long flags; struct hw_perf_event *hwc = &event->hw; - struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct arm_pmu *pmu = to_arm_pmu(event->pmu); + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); + struct pmu_hw_events *events = pmu->get_hw_events(pmu); int idx = hwc->idx; - if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) { + if (!armv7_pmnc_counter_valid(pmu, idx)) { pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n", smp_processor_id(), idx); return; @@ -1018,12 +1243,12 @@ static void armv7pmu_disable_event(struct perf_event *event) /* * Disable counter */ - armv7_pmnc_disable_counter(idx); + armv7_pmnc_disable_counter(cpupmu, idx); /* * Disable interrupt for this counter */ - armv7_pmnc_disable_intens(idx); + armv7_pmnc_disable_intens(cpupmu, idx); raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } @@ -1032,15 +1257,23 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) { u32 pmnc; struct perf_sample_data data; - struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev; - struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events(); + struct arm_pmu *pmu = (struct arm_pmu *)dev; + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); + struct pmu_hw_events *cpuc = pmu->get_hw_events(pmu); struct pt_regs *regs; int idx; + if (!cpupmu->active) { + pr_warn_ratelimited("%s: Spurious interrupt for inactive PMU %s: event counts will be wrong.\n", + __func__, pmu->name); + pr_warn_once("This is a known interrupt affinity bug in the b.L switcher perf support.\n"); + return IRQ_NONE; + } + /* * Get and reset the IRQ flags */ - pmnc = armv7_pmnc_getreset_flags(); + pmnc = armv7_pmnc_getreset_flags(cpupmu); /* * Did an overflow occur? @@ -1053,7 +1286,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); - for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + for (idx = 0; idx < pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -1075,7 +1308,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) continue; if (perf_event_overflow(event, &data, regs)) - cpu_pmu->disable(event); + pmu->disable(event); } /* @@ -1090,25 +1323,27 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) return IRQ_HANDLED; } -static void armv7pmu_start(struct arm_pmu *cpu_pmu) +static void armv7pmu_start(struct arm_pmu *pmu) { unsigned long flags; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); + struct pmu_hw_events *events = pmu->get_hw_events(pmu); raw_spin_lock_irqsave(&events->pmu_lock, flags); /* Enable all counters */ - armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E); + armv7_pmnc_write(cpupmu, armv7_pmnc_read(cpupmu) | ARMV7_PMNC_E); raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } -static void armv7pmu_stop(struct arm_pmu *cpu_pmu) +static void armv7pmu_stop(struct arm_pmu *pmu) { unsigned long flags; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); + struct pmu_hw_events *events = pmu->get_hw_events(pmu); raw_spin_lock_irqsave(&events->pmu_lock, flags); /* Disable all counters */ - armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E); + armv7_pmnc_write(cpupmu, armv7_pmnc_read(cpupmu) & ~ARMV7_PMNC_E); raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } @@ -1167,19 +1402,33 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event, return 0; } +static bool check_active(struct arm_cpu_pmu *cpupmu) +{ + u32 mpidr = read_mpidr(); + + BUG_ON(!(mpidr & 0x80000000)); /* this won't work on uniprocessor */ + + cpupmu->active = ((mpidr ^ cpupmu->mpidr) & 0xFFFFFF) == 0; + return cpupmu->active; +} + static void armv7pmu_reset(void *info) { - struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; - u32 idx, nb_cnt = cpu_pmu->num_events; + struct arm_pmu *pmu = (struct arm_pmu *)info; + struct arm_cpu_pmu *cpupmu = to_this_cpu_pmu(pmu); + u32 idx, nb_cnt = pmu->num_events; + + if (!check_active(cpupmu)) + return; /* The counter and interrupt enable registers are unknown at reset. */ for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { - armv7_pmnc_disable_counter(idx); - armv7_pmnc_disable_intens(idx); + armv7_pmnc_disable_counter(cpupmu, idx); + armv7_pmnc_disable_intens(cpupmu, idx); } /* Initialize & Reset PMNC: C and P bits */ - armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C); + armv7_pmnc_write(cpupmu, ARMV7_PMNC_P | ARMV7_PMNC_C); } static int armv7_a8_map_event(struct perf_event *event) @@ -1212,8 +1461,13 @@ static int armv7_a7_map_event(struct perf_event *event) &armv7_a7_perf_cache_map, 0xFF); } +static void armv7pmu_cpu_init(struct arm_pmu *pmu, + struct arm_cpu_pmu *cpupmu); + static void armv7pmu_init(struct arm_pmu *cpu_pmu) { + struct arm_cpu_pmu *cpu_pmus = cpu_pmu->cpu_pmus; + cpu_pmu->handle_irq = armv7pmu_handle_irq; cpu_pmu->enable = armv7pmu_enable_event; cpu_pmu->disable = armv7pmu_disable_event; @@ -1223,7 +1477,12 @@ 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->cpu_init = armv7pmu_cpu_init; cpu_pmu->max_period = (1LLU << 32) - 1; + + cpu_pmu->cpu_pmus = cpu_pmus; }; static u32 armv7_read_num_pmnc_events(void) @@ -1231,16 +1490,42 @@ static u32 armv7_read_num_pmnc_events(void) u32 nb_cnt; /* Read the nb of CNTx counters supported from PMNC */ - nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK; + nb_cnt = (__v7_pmu_read_physical(PMCR) >> ARMV7_PMNC_N_SHIFT); + nb_cnt &= ARMV7_PMNC_N_MASK; /* Add the CPU cycles counter and return */ return nb_cnt + 1; } +static void armv7pmu_cpu_init(struct arm_pmu *pmu, + struct arm_cpu_pmu *cpupmu) +{ + size_t size = offsetof(struct armv7_pmu_logical_state, cntrs) + + pmu->num_events * sizeof(*__v7_logical_state(cpupmu)); + + cpupmu->logical_state = kzalloc(size, GFP_KERNEL); + + /* + * We need a proper error return mechanism for these init functions. + * Until then, panicking the kernel is acceptable, since a failure + * here is indicative of crippling memory contstraints which will + * likely make the system unusable anyway: + */ + BUG_ON(!cpupmu->logical_state); + + /* + * Save the "read-only" ID registers in logical_state. + * Because they are read-only, there are no direct accessors, + * so poke them directly into the logical_state structure: + */ + __v7_logical_state(cpupmu)->PMCEID0 = __v7_pmu_read_physical(PMCEID0); + __v7_logical_state(cpupmu)->PMCEID1 = __v7_pmu_read_physical(PMCEID1); +} + 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 +1534,7 @@ 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 +1543,7 @@ 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 +1552,7 @@ 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 +1562,7 @@ 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/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c index 63990c42fac9..cd670eafbb56 100644 --- a/arch/arm/kernel/perf_event_xscale.c +++ b/arch/arm/kernel/perf_event_xscale.c @@ -225,7 +225,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev) unsigned long pmnc; struct perf_sample_data data; struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev; - struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events(); + struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events(cpu_pmu); struct pt_regs *regs; int idx; @@ -285,7 +285,7 @@ static void xscale1pmu_enable_event(struct perf_event *event) unsigned long val, mask, evt, flags; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); int idx = hwc->idx; switch (idx) { @@ -321,7 +321,7 @@ static void xscale1pmu_disable_event(struct perf_event *event) unsigned long val, mask, evt, flags; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); int idx = hwc->idx; switch (idx) { @@ -374,7 +374,7 @@ xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc, static void xscale1pmu_start(struct arm_pmu *cpu_pmu) { unsigned long flags, val; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale1pmu_read_pmnc(); @@ -386,7 +386,7 @@ static void xscale1pmu_start(struct arm_pmu *cpu_pmu) static void xscale1pmu_stop(struct arm_pmu *cpu_pmu) { unsigned long flags, val; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale1pmu_read_pmnc(); @@ -572,7 +572,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev) unsigned long pmnc, of_flags; struct perf_sample_data data; struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev; - struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events(); + struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events(cpu_pmu); struct pt_regs *regs; int idx; @@ -626,7 +626,7 @@ static void xscale2pmu_enable_event(struct perf_event *event) unsigned long flags, ien, evtsel; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); int idx = hwc->idx; ien = xscale2pmu_read_int_enable(); @@ -672,7 +672,7 @@ static void xscale2pmu_disable_event(struct perf_event *event) unsigned long flags, ien, evtsel, of_flags; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); int idx = hwc->idx; ien = xscale2pmu_read_int_enable(); @@ -738,7 +738,7 @@ out: static void xscale2pmu_start(struct arm_pmu *cpu_pmu) { unsigned long flags, val; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64; @@ -750,7 +750,7 @@ static void xscale2pmu_start(struct arm_pmu *cpu_pmu) static void xscale2pmu_stop(struct arm_pmu *cpu_pmu) { unsigned long flags, val; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = cpu_pmu->get_hw_events(cpu_pmu); raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale2pmu_read_pmnc(); diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c index 36531643cc2c..1180801468d8 100644 --- a/arch/arm/kernel/psci.c +++ b/arch/arm/kernel/psci.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/of.h> +#include <linux/string.h> #include <asm/compiler.h> #include <asm/errno.h> @@ -26,6 +27,11 @@ struct psci_operations psci_ops; +/* Type of psci support. Currently can only be enabled or disabled */ +#define PSCI_SUP_DISABLED 0 +#define PSCI_SUP_ENABLED 1 + +static unsigned int psci; static int (*invoke_psci_fn)(u32, u32, u32, u32); enum psci_function { @@ -42,6 +48,7 @@ static u32 psci_function_id[PSCI_FN_MAX]; #define PSCI_RET_EOPNOTSUPP -1 #define PSCI_RET_EINVAL -2 #define PSCI_RET_EPERM -3 +#define PSCI_RET_EALREADYON -4 static int psci_to_linux_errno(int errno) { @@ -54,6 +61,8 @@ static int psci_to_linux_errno(int errno) return -EINVAL; case PSCI_RET_EPERM: return -EPERM; + case PSCI_RET_EALREADYON: + return -EAGAIN; }; return -EINVAL; @@ -164,6 +173,9 @@ static int __init psci_init(void) const char *method; u32 id; + if (psci == PSCI_SUP_DISABLED) + return 0; + np = of_find_matching_node(NULL, psci_of_match); if (!np) return 0; @@ -209,3 +221,33 @@ out_put_node: return 0; } early_initcall(psci_init); + +int __init psci_probe(void) +{ + struct device_node *np; + int ret = -ENODEV; + + if (psci == PSCI_SUP_ENABLED) { + np = of_find_matching_node(NULL, psci_of_match); + if (np) + ret = 0; + } + + of_node_put(np); + return ret; +} + +static int __init early_psci(char *val) +{ + int ret = 0; + + if (strcmp(val, "enable") == 0) + psci = PSCI_SUP_ENABLED; + else if (strcmp(val, "disable") == 0) + psci = PSCI_SUP_DISABLED; + else + ret = -EINVAL; + + return ret; +} +early_param("psci", early_psci); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 234e339196c0..7c9fd36be1d7 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -260,6 +260,19 @@ static int cpu_has_aliasing_icache(unsigned int arch) int aliasing_icache; unsigned int id_reg, num_sets, line_size; +#ifdef CONFIG_BIG_LITTLE + /* + * We expect a combination of Cortex-A15 and Cortex-A7 cores. + * A7 = VIPT aliasing I-cache + * A15 = PIPT (non-aliasing) I-cache + * To cater for this discrepancy, let's assume aliasing I-cache + * all the time. This means unneeded extra work on the A15 but + * only ptrace is affected which is not performance critical. + */ + if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0) + return 1; +#endif + /* PIPT caches never alias. */ if (icache_is_pipt()) return 0; @@ -290,10 +303,10 @@ static int cpu_has_aliasing_icache(unsigned int arch) static void __init cacheid_init(void) { - unsigned int cachetype = read_cpuid_cachetype(); unsigned int arch = cpu_architecture(); if (arch >= CPU_ARCH_ARMv6) { + unsigned int cachetype = read_cpuid_cachetype(); if ((cachetype & (7 << 29)) == 4 << 29) { /* ARMv7 register format */ arch = CPU_ARCH_ARMv7; @@ -389,7 +402,7 @@ static void __init feat_v6_fixup(void) * * cpu_init sets up the per-CPU stacks. */ -void cpu_init(void) +void notrace cpu_init(void) { unsigned int cpu = smp_processor_id(); struct stack *stk = &stacks[cpu]; @@ -787,7 +800,10 @@ void __init setup_arch(char **cmdline_p) arm_dt_init_cpu_maps(); #ifdef CONFIG_SMP if (is_smp()) { - smp_set_ops(mdesc->smp); + if (!mdesc->smp_init || !mdesc->smp_init()) { + if(mdesc->smp) + smp_set_ops(mdesc->smp); + } smp_init_cpus(); } #endif diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 987dcf33415c..b5c1e636ed85 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -4,6 +4,7 @@ #include <asm/assembler.h> #include <asm/glue-cache.h> #include <asm/glue-proc.h> +#include "entry-header.S" .text /* @@ -30,9 +31,8 @@ ENTRY(__cpu_suspend) mov r2, r5 @ virtual SP ldr r3, =sleep_save_sp #ifdef CONFIG_SMP - ALT_SMP(mrc p15, 0, lr, c0, c0, 5) - ALT_UP(mov lr, #0) - and lr, lr, #15 + get_thread_info r5 + ldr lr, [r5, #TI_CPU] @ cpu logical index add r3, r3, lr, lsl #2 #endif bl __cpu_suspend_save @@ -82,10 +82,13 @@ ENDPROC(cpu_resume_after_mmu) .align ENTRY(cpu_resume) #ifdef CONFIG_SMP + mov r1, #0 @ fall-back logical index for UP + ALT_SMP(mrc p15, 0, r0, c0, c0, 5) + ALT_UP_B(1f) + bic r0, #0xff000000 + bl cpu_logical_index @ return logical index in r1 +1: adr r0, sleep_save_sp - ALT_SMP(mrc p15, 0, r1, c0, c0, 5) - ALT_UP(mov r1, #0) - and r1, r1, #15 ldr r0, [r0, r1, lsl #2] @ stack phys addr #else ldr r0, sleep_save_sp @ stack phys addr @@ -102,3 +105,20 @@ sleep_save_sp: .rept CONFIG_NR_CPUS .long 0 @ preserve stack phys ptr here .endr + +#ifdef CONFIG_SMP +cpu_logical_index: + adr r3, cpu_map_ptr + ldr r2, [r3] + add r3, r3, r2 @ virt_to_phys(__cpu_logical_map) + mov r1, #0 +1: + ldr r2, [r3, r1, lsl #2] + cmp r2, r0 + moveq pc, lr + add r1, r1, #1 + b 1b + +cpu_map_ptr: + .long __cpu_logical_map - . +#endif diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index ef366e34bdbe..e9905a57b89a 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -66,6 +66,7 @@ enum ipi_msg_type { IPI_CALL_FUNC, IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, + IPI_COMPLETION, IPI_CPU_BACKTRACE, }; @@ -430,6 +431,7 @@ 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"), S(IPI_CPU_BACKTRACE, "CPU backtrace"), }; @@ -556,6 +558,19 @@ 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)); +} + static cpumask_t backtrace_mask; static DEFINE_RAW_SPINLOCK(backtrace_lock); @@ -658,6 +673,12 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; + case IPI_COMPLETION: + irq_enter(); + ipi_complete(cpu); + irq_exit(); + break; + case IPI_CPU_BACKTRACE: ipi_cpu_backtrace(cpu, regs); break; diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 45eac87ed66a..5bc1a63284e3 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -41,7 +41,7 @@ void scu_enable(void __iomem *scu_base) #ifdef CONFIG_ARM_ERRATA_764369 /* Cortex-A9 only */ - if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) { + if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) { scu_ctrl = __raw_readl(scu_base + 0x30); if (!(scu_ctrl & 1)) __raw_writel(scu_ctrl | 0x1, scu_base + 0x30); diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 79282ebcd939..8df74d630ca3 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -13,6 +13,7 @@ #include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/percpu.h> #include <linux/node.h> @@ -22,6 +23,7 @@ #include <linux/slab.h> #include <asm/cputype.h> +#include <asm/smp_plat.h> #include <asm/topology.h> /* @@ -200,6 +202,7 @@ static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {} * cpu topology table */ struct cputopo_arm cpu_topology[NR_CPUS]; +EXPORT_SYMBOL_GPL(cpu_topology); const struct cpumask *cpu_coregroup_mask(int cpu) { @@ -287,6 +290,137 @@ 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); +} + +void __init arch_get_hmp_domains(struct list_head *hmp_domains_list) +{ + struct cpumask hmp_fast_cpu_mask; + struct cpumask hmp_slow_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->cpus, &hmp_slow_cpu_mask); + list_add(&domain->hmp_domains, hmp_domains_list); + } + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->cpus, &hmp_fast_cpu_mask); + 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/kvm/Makefile b/arch/arm/kvm/Makefile index fc96ce6f2357..8dc5e76cb789 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -17,7 +17,7 @@ AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) kvm-arm-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) obj-y += kvm-arm.o init.o interrupts.o -obj-y += arm.o guest.o mmu.o emulate.o reset.o +obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o obj-y += coproc.o coproc_a15.o mmio.o psci.o obj-$(CONFIG_KVM_ARM_VGIC) += vgic.o obj-$(CONFIG_KVM_ARM_TIMER) += arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index c1fe498983ac..a0dfc2a53f91 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -30,11 +30,9 @@ #define CREATE_TRACE_POINTS #include "trace.h" -#include <asm/unified.h> #include <asm/uaccess.h> #include <asm/ptrace.h> #include <asm/mman.h> -#include <asm/cputype.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> #include <asm/virt.h> @@ -44,14 +42,13 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> #include <asm/kvm_psci.h> -#include <asm/opcodes.h> #ifdef REQUIRES_VIRT __asm__(".arch_extension virt"); #endif static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); -static struct vfp_hard_struct __percpu *kvm_host_vfp_state; +static kvm_kernel_vfp_t __percpu *kvm_host_vfp_state; static unsigned long hyp_default_vectors; /* Per-CPU variable containing the currently running vcpu. */ @@ -304,22 +301,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) return 0; } -int __attribute_const__ kvm_target_cpu(void) -{ - unsigned long implementor = read_cpuid_implementor(); - unsigned long part_number = read_cpuid_part_number(); - - if (implementor != ARM_CPU_IMP_ARM) - return -EINVAL; - - switch (part_number) { - case ARM_CPU_PART_CORTEX_A15: - return KVM_ARM_TARGET_CORTEX_A15; - default: - return -EINVAL; - } -} - int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { int ret; @@ -482,163 +463,6 @@ static void update_vttbr(struct kvm *kvm) spin_unlock(&kvm_vmid_lock); } -static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* SVC called from Hyp mode should never get here */ - kvm_debug("SVC called from Hyp mode shouldn't go here\n"); - BUG(); - return -EINVAL; /* Squash warning */ -} - -static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), - vcpu->arch.hsr & HSR_HVC_IMM_MASK); - - if (kvm_psci_call(vcpu)) - return 1; - - kvm_inject_undefined(vcpu); - return 1; -} - -static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - if (kvm_psci_call(vcpu)) - return 1; - - kvm_inject_undefined(vcpu); - return 1; -} - -static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* The hypervisor should never cause aborts */ - kvm_err("Prefetch Abort taken from Hyp mode at %#08x (HSR: %#08x)\n", - vcpu->arch.hxfar, vcpu->arch.hsr); - return -EFAULT; -} - -static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* This is either an error in the ws. code or an external abort */ - kvm_err("Data Abort taken from Hyp mode at %#08x (HSR: %#08x)\n", - vcpu->arch.hxfar, vcpu->arch.hsr); - return -EFAULT; -} - -typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); -static exit_handle_fn arm_exit_handlers[] = { - [HSR_EC_WFI] = kvm_handle_wfi, - [HSR_EC_CP15_32] = kvm_handle_cp15_32, - [HSR_EC_CP15_64] = kvm_handle_cp15_64, - [HSR_EC_CP14_MR] = kvm_handle_cp14_access, - [HSR_EC_CP14_LS] = kvm_handle_cp14_load_store, - [HSR_EC_CP14_64] = kvm_handle_cp14_access, - [HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access, - [HSR_EC_CP10_ID] = kvm_handle_cp10_id, - [HSR_EC_SVC_HYP] = handle_svc_hyp, - [HSR_EC_HVC] = handle_hvc, - [HSR_EC_SMC] = handle_smc, - [HSR_EC_IABT] = kvm_handle_guest_abort, - [HSR_EC_IABT_HYP] = handle_pabt_hyp, - [HSR_EC_DABT] = kvm_handle_guest_abort, - [HSR_EC_DABT_HYP] = handle_dabt_hyp, -}; - -/* - * A conditional instruction is allowed to trap, even though it - * wouldn't be executed. So let's re-implement the hardware, in - * software! - */ -static bool kvm_condition_valid(struct kvm_vcpu *vcpu) -{ - unsigned long cpsr, cond, insn; - - /* - * Exception Code 0 can only happen if we set HCR.TGE to 1, to - * catch undefined instructions, and then we won't get past - * the arm_exit_handlers test anyway. - */ - BUG_ON(((vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT) == 0); - - /* Top two bits non-zero? Unconditional. */ - if (vcpu->arch.hsr >> 30) - return true; - - cpsr = *vcpu_cpsr(vcpu); - - /* Is condition field valid? */ - if ((vcpu->arch.hsr & HSR_CV) >> HSR_CV_SHIFT) - cond = (vcpu->arch.hsr & HSR_COND) >> HSR_COND_SHIFT; - else { - /* This can happen in Thumb mode: examine IT state. */ - unsigned long it; - - it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); - - /* it == 0 => unconditional. */ - if (it == 0) - return true; - - /* The cond for this insn works out as the top 4 bits. */ - cond = (it >> 4); - } - - /* Shift makes it look like an ARM-mode instruction */ - insn = cond << 28; - return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL; -} - -/* - * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on - * proper exit to QEMU. - */ -static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, - int exception_index) -{ - unsigned long hsr_ec; - - switch (exception_index) { - case ARM_EXCEPTION_IRQ: - return 1; - case ARM_EXCEPTION_UNDEFINED: - kvm_err("Undefined exception in Hyp mode at: %#08x\n", - vcpu->arch.hyp_pc); - BUG(); - panic("KVM: Hypervisor undefined exception!\n"); - case ARM_EXCEPTION_DATA_ABORT: - case ARM_EXCEPTION_PREF_ABORT: - case ARM_EXCEPTION_HVC: - hsr_ec = (vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT; - - if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) - || !arm_exit_handlers[hsr_ec]) { - kvm_err("Unkown exception class: %#08lx, " - "hsr: %#08x\n", hsr_ec, - (unsigned int)vcpu->arch.hsr); - BUG(); - } - - /* - * See ARM ARM B1.14.1: "Hyp traps on instructions - * that fail their condition code check" - */ - if (!kvm_condition_valid(vcpu)) { - bool is_wide = vcpu->arch.hsr & HSR_IL; - kvm_skip_instr(vcpu, is_wide); - return 1; - } - - return arm_exit_handlers[hsr_ec](vcpu, run); - default: - kvm_pr_unimpl("Unsupported exception type: %d", - exception_index); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - return 0; - } -} - static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) { if (likely(vcpu->arch.has_run_once)) @@ -973,7 +797,6 @@ long kvm_arch_vm_ioctl(struct file *filp, static void cpu_init_hyp_mode(void *vector) { unsigned long long pgd_ptr; - unsigned long pgd_low, pgd_high; unsigned long hyp_stack_ptr; unsigned long stack_page; unsigned long vector_ptr; @@ -982,20 +805,11 @@ static void cpu_init_hyp_mode(void *vector) __hyp_set_vectors((unsigned long)vector); pgd_ptr = (unsigned long long)kvm_mmu_get_httbr(); - pgd_low = (pgd_ptr & ((1ULL << 32) - 1)); - pgd_high = (pgd_ptr >> 32ULL); stack_page = __get_cpu_var(kvm_arm_hyp_stack_page); hyp_stack_ptr = stack_page + PAGE_SIZE; vector_ptr = (unsigned long)__kvm_hyp_vector; - /* - * Call initialization code, and switch to the full blown - * HYP code. The init code doesn't need to preserve these registers as - * r1-r3 and r12 are already callee save according to the AAPCS. - * Note that we slightly misuse the prototype by casing the pgd_low to - * a void *. - */ - kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr); + __cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr); } /** @@ -1078,7 +892,7 @@ static int init_hyp_mode(void) /* * Map the host VFP structures */ - kvm_host_vfp_state = alloc_percpu(struct vfp_hard_struct); + kvm_host_vfp_state = alloc_percpu(kvm_kernel_vfp_t); if (!kvm_host_vfp_state) { err = -ENOMEM; kvm_err("Cannot allocate host VFP state\n"); @@ -1086,7 +900,7 @@ static int init_hyp_mode(void) } for_each_possible_cpu(cpu) { - struct vfp_hard_struct *vfp; + kvm_kernel_vfp_t *vfp; vfp = per_cpu_ptr(kvm_host_vfp_state, cpu); err = create_hyp_mappings(vfp, vfp + 1); diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 7bed7556077a..8eea97be1ed5 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -76,7 +76,7 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, const struct coproc_params *p, const struct coproc_reg *r) { - u32 val; + unsigned long val; int cpu; if (!p->is_write) @@ -293,12 +293,12 @@ static int emulate_cp15(struct kvm_vcpu *vcpu, if (likely(r->access(vcpu, params, r))) { /* Skip instruction, since it was emulated */ - kvm_skip_instr(vcpu, (vcpu->arch.hsr >> 25) & 1); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 1; } /* If access function fails, it should complain. */ } else { - kvm_err("Unsupported guest CP15 access at: %08x\n", + kvm_err("Unsupported guest CP15 access at: %08lx\n", *vcpu_pc(vcpu)); print_cp_instr(params); } @@ -315,14 +315,14 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct coproc_params params; - params.CRm = (vcpu->arch.hsr >> 1) & 0xf; - params.Rt1 = (vcpu->arch.hsr >> 5) & 0xf; - params.is_write = ((vcpu->arch.hsr & 1) == 0); + params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; + params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; + params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); params.is_64bit = true; - params.Op1 = (vcpu->arch.hsr >> 16) & 0xf; + params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf; params.Op2 = 0; - params.Rt2 = (vcpu->arch.hsr >> 10) & 0xf; + params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; params.CRn = 0; return emulate_cp15(vcpu, ¶ms); @@ -347,14 +347,14 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct coproc_params params; - params.CRm = (vcpu->arch.hsr >> 1) & 0xf; - params.Rt1 = (vcpu->arch.hsr >> 5) & 0xf; - params.is_write = ((vcpu->arch.hsr & 1) == 0); + params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; + params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; + params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); params.is_64bit = false; - params.CRn = (vcpu->arch.hsr >> 10) & 0xf; - params.Op1 = (vcpu->arch.hsr >> 14) & 0x7; - params.Op2 = (vcpu->arch.hsr >> 17) & 0x7; + params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; + params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 14) & 0x7; + params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7; params.Rt2 = 0; return emulate_cp15(vcpu, ¶ms); diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h index 992adfafa2ff..b7301d3e4799 100644 --- a/arch/arm/kvm/coproc.h +++ b/arch/arm/kvm/coproc.h @@ -84,7 +84,7 @@ static inline bool read_zero(struct kvm_vcpu *vcpu, static inline bool write_to_read_only(struct kvm_vcpu *vcpu, const struct coproc_params *params) { - kvm_debug("CP15 write to read-only register at: %08x\n", + kvm_debug("CP15 write to read-only register at: %08lx\n", *vcpu_pc(vcpu)); print_cp_instr(params); return false; @@ -93,7 +93,7 @@ static inline bool write_to_read_only(struct kvm_vcpu *vcpu, static inline bool read_from_write_only(struct kvm_vcpu *vcpu, const struct coproc_params *params) { - kvm_debug("CP15 read to write-only register at: %08x\n", + kvm_debug("CP15 read to write-only register at: %08lx\n", *vcpu_pc(vcpu)); print_cp_instr(params); return false; diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c index d61450ac6665..bdede9e7da51 100644 --- a/arch/arm/kvm/emulate.c +++ b/arch/arm/kvm/emulate.c @@ -20,6 +20,7 @@ #include <linux/kvm_host.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> +#include <asm/opcodes.h> #include <trace/events/kvm.h> #include "trace.h" @@ -109,10 +110,10 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = { * Return a pointer to the register number valid in the current mode of * the virtual CPU. */ -u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) +unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) { - u32 *reg_array = (u32 *)&vcpu->arch.regs; - u32 mode = *vcpu_cpsr(vcpu) & MODE_MASK; + unsigned long *reg_array = (unsigned long *)&vcpu->arch.regs; + unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; switch (mode) { case USR_MODE...SVC_MODE: @@ -141,9 +142,9 @@ u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) /* * Return the SPSR for the current mode of the virtual CPU. */ -u32 *vcpu_spsr(struct kvm_vcpu *vcpu) +unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu) { - u32 mode = *vcpu_cpsr(vcpu) & MODE_MASK; + unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; switch (mode) { case SVC_MODE: return &vcpu->arch.regs.KVM_ARM_SVC_spsr; @@ -160,20 +161,48 @@ u32 *vcpu_spsr(struct kvm_vcpu *vcpu) } } -/** - * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest - * @vcpu: the vcpu pointer - * @run: the kvm_run structure pointer - * - * Simply sets the wait_for_interrupts flag on the vcpu structure, which will - * halt execution of world-switches and schedule other host processes until - * there is an incoming IRQ or FIQ to the VM. +/* + * A conditional instruction is allowed to trap, even though it + * wouldn't be executed. So let's re-implement the hardware, in + * software! */ -int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) +bool kvm_condition_valid(struct kvm_vcpu *vcpu) { - trace_kvm_wfi(*vcpu_pc(vcpu)); - kvm_vcpu_block(vcpu); - return 1; + unsigned long cpsr, cond, insn; + + /* + * Exception Code 0 can only happen if we set HCR.TGE to 1, to + * catch undefined instructions, and then we won't get past + * the arm_exit_handlers test anyway. + */ + BUG_ON(!kvm_vcpu_trap_get_class(vcpu)); + + /* Top two bits non-zero? Unconditional. */ + if (kvm_vcpu_get_hsr(vcpu) >> 30) + return true; + + cpsr = *vcpu_cpsr(vcpu); + + /* Is condition field valid? */ + if ((kvm_vcpu_get_hsr(vcpu) & HSR_CV) >> HSR_CV_SHIFT) + cond = (kvm_vcpu_get_hsr(vcpu) & HSR_COND) >> HSR_COND_SHIFT; + else { + /* This can happen in Thumb mode: examine IT state. */ + unsigned long it; + + it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); + + /* it == 0 => unconditional. */ + if (it == 0) + return true; + + /* The cond for this insn works out as the top 4 bits. */ + cond = (it >> 4); + } + + /* Shift makes it look like an ARM-mode instruction */ + insn = cond << 28; + return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL; } /** @@ -257,9 +286,9 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu) */ void kvm_inject_undefined(struct kvm_vcpu *vcpu) { - u32 new_lr_value; - u32 new_spsr_value; - u32 cpsr = *vcpu_cpsr(vcpu); + unsigned long new_lr_value; + unsigned long new_spsr_value; + unsigned long cpsr = *vcpu_cpsr(vcpu); u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; bool is_thumb = (cpsr & PSR_T_BIT); u32 vect_offset = 4; @@ -291,9 +320,9 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu) */ static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr) { - u32 new_lr_value; - u32 new_spsr_value; - u32 cpsr = *vcpu_cpsr(vcpu); + unsigned long new_lr_value; + unsigned long new_spsr_value; + unsigned long cpsr = *vcpu_cpsr(vcpu); u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; bool is_thumb = (cpsr & PSR_T_BIT); u32 vect_offset; diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 2339d9609d36..152d03612181 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -22,6 +22,7 @@ #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/fs.h> +#include <asm/cputype.h> #include <asm/uaccess.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> @@ -180,6 +181,22 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return -EINVAL; } +int __attribute_const__ kvm_target_cpu(void) +{ + unsigned long implementor = read_cpuid_implementor(); + unsigned long part_number = read_cpuid_part_number(); + + if (implementor != ARM_CPU_IMP_ARM) + return -EINVAL; + + switch (part_number) { + case ARM_CPU_PART_CORTEX_A15: + return KVM_ARM_TARGET_CORTEX_A15; + default: + return -EINVAL; + } +} + int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c new file mode 100644 index 000000000000..26ad17310a1e --- /dev/null +++ b/arch/arm/kvm/handle_exit.c @@ -0,0 +1,164 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + * + * 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. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_coproc.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_psci.h> +#include <trace/events/kvm.h> + +#include "trace.h" + +#include "trace.h" + +typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); + +static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* SVC called from Hyp mode should never get here */ + kvm_debug("SVC called from Hyp mode shouldn't go here\n"); + BUG(); + return -EINVAL; /* Squash warning */ +} + +static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), + kvm_vcpu_hvc_get_imm(vcpu)); + + if (kvm_psci_call(vcpu)) + return 1; + + kvm_inject_undefined(vcpu); + return 1; +} + +static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + if (kvm_psci_call(vcpu)) + return 1; + + kvm_inject_undefined(vcpu); + return 1; +} + +static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* The hypervisor should never cause aborts */ + kvm_err("Prefetch Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n", + kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu)); + return -EFAULT; +} + +static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* This is either an error in the ws. code or an external abort */ + kvm_err("Data Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n", + kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu)); + return -EFAULT; +} + +/** + * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest + * @vcpu: the vcpu pointer + * @run: the kvm_run structure pointer + * + * Simply sets the wait_for_interrupts flag on the vcpu structure, which will + * halt execution of world-switches and schedule other host processes until + * there is an incoming IRQ or FIQ to the VM. + */ +static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + trace_kvm_wfi(*vcpu_pc(vcpu)); + kvm_vcpu_block(vcpu); + return 1; +} + +static exit_handle_fn arm_exit_handlers[] = { + [HSR_EC_WFI] = kvm_handle_wfi, + [HSR_EC_CP15_32] = kvm_handle_cp15_32, + [HSR_EC_CP15_64] = kvm_handle_cp15_64, + [HSR_EC_CP14_MR] = kvm_handle_cp14_access, + [HSR_EC_CP14_LS] = kvm_handle_cp14_load_store, + [HSR_EC_CP14_64] = kvm_handle_cp14_access, + [HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access, + [HSR_EC_CP10_ID] = kvm_handle_cp10_id, + [HSR_EC_SVC_HYP] = handle_svc_hyp, + [HSR_EC_HVC] = handle_hvc, + [HSR_EC_SMC] = handle_smc, + [HSR_EC_IABT] = kvm_handle_guest_abort, + [HSR_EC_IABT_HYP] = handle_pabt_hyp, + [HSR_EC_DABT] = kvm_handle_guest_abort, + [HSR_EC_DABT_HYP] = handle_dabt_hyp, +}; + +static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) +{ + u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); + + if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) || + !arm_exit_handlers[hsr_ec]) { + kvm_err("Unkown exception class: hsr: %#08x\n", + (unsigned int)kvm_vcpu_get_hsr(vcpu)); + BUG(); + } + + return arm_exit_handlers[hsr_ec]; +} + +/* + * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on + * proper exit to userspace. + */ +int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, + int exception_index) +{ + exit_handle_fn exit_handler; + + switch (exception_index) { + case ARM_EXCEPTION_IRQ: + return 1; + case ARM_EXCEPTION_UNDEFINED: + kvm_err("Undefined exception in Hyp mode at: %#08lx\n", + kvm_vcpu_get_hyp_pc(vcpu)); + BUG(); + panic("KVM: Hypervisor undefined exception!\n"); + case ARM_EXCEPTION_DATA_ABORT: + case ARM_EXCEPTION_PREF_ABORT: + case ARM_EXCEPTION_HVC: + /* + * See ARM ARM B1.14.1: "Hyp traps on instructions + * that fail their condition code check" + */ + if (!kvm_condition_valid(vcpu)) { + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; + } + + exit_handler = kvm_get_exit_handler(vcpu); + + return exit_handler(vcpu, run); + default: + kvm_pr_unimpl("Unsupported exception type: %d", + exception_index); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return 0; + } +} diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 8ca87ab0919d..f7793df62f58 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -35,15 +35,18 @@ __kvm_hyp_code_start: /******************************************************************** * Flush per-VMID TLBs * - * void __kvm_tlb_flush_vmid(struct kvm *kvm); + * void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); * * We rely on the hardware to broadcast the TLB invalidation to all CPUs * inside the inner-shareable domain (which is the case for all v7 * implementations). If we come across a non-IS SMP implementation, we'll * have to use an IPI based mechanism. Until then, we stick to the simple * hardware assisted version. + * + * As v7 does not support flushing per IPA, just nuke the whole TLB + * instead, ignoring the ipa value. */ -ENTRY(__kvm_tlb_flush_vmid) +ENTRY(__kvm_tlb_flush_vmid_ipa) push {r2, r3} add r0, r0, #KVM_VTTBR @@ -60,7 +63,7 @@ ENTRY(__kvm_tlb_flush_vmid) pop {r2, r3} bx lr -ENDPROC(__kvm_tlb_flush_vmid) +ENDPROC(__kvm_tlb_flush_vmid_ipa) /******************************************************************** * Flush TLBs and instruction caches of all CPUs inside the inner-shareable @@ -235,9 +238,9 @@ ENTRY(kvm_call_hyp) * instruction is issued since all traps are disabled when running the host * kernel as per the Hyp-mode initialization at boot time. * - * HVC instructions cause a trap to the vector page + offset 0x18 (see hyp_hvc + * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc * below) when the HVC instruction is called from SVC mode (i.e. a guest or the - * host kernel) and they cause a trap to the vector page + offset 0xc when HVC + * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC * instructions are called from within Hyp-mode. * * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode): diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 98a870ff1a5c..72a12f2171b2 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -33,16 +33,16 @@ */ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) { - __u32 *dest; + unsigned long *dest; unsigned int len; int mask; if (!run->mmio.is_write) { dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt); - memset(dest, 0, sizeof(int)); + *dest = 0; len = run->mmio.len; - if (len > 4) + if (len > sizeof(unsigned long)) return -EINVAL; memcpy(dest, run->mmio.data, len); @@ -50,7 +50,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, *((u64 *)run->mmio.data)); - if (vcpu->arch.mmio_decode.sign_extend && len < 4) { + if (vcpu->arch.mmio_decode.sign_extend && + len < sizeof(unsigned long)) { mask = 1U << ((len * 8) - 1); *dest = (*dest ^ mask) - mask; } @@ -65,40 +66,29 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long rt, len; bool is_write, sign_extend; - if ((vcpu->arch.hsr >> 8) & 1) { + if (kvm_vcpu_dabt_isextabt(vcpu)) { /* cache operation on I/O addr, tell guest unsupported */ - kvm_inject_dabt(vcpu, vcpu->arch.hxfar); + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 1; } - if ((vcpu->arch.hsr >> 7) & 1) { + if (kvm_vcpu_dabt_iss1tw(vcpu)) { /* page table accesses IO mem: tell guest to fix its TTBR */ - kvm_inject_dabt(vcpu, vcpu->arch.hxfar); + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 1; } - switch ((vcpu->arch.hsr >> 22) & 0x3) { - case 0: - len = 1; - break; - case 1: - len = 2; - break; - case 2: - len = 4; - break; - default: - kvm_err("Hardware is weird: SAS 0b11 is reserved\n"); - return -EFAULT; - } + len = kvm_vcpu_dabt_get_as(vcpu); + if (unlikely(len < 0)) + return len; - is_write = vcpu->arch.hsr & HSR_WNR; - sign_extend = vcpu->arch.hsr & HSR_SSE; - rt = (vcpu->arch.hsr & HSR_SRT_MASK) >> HSR_SRT_SHIFT; + is_write = kvm_vcpu_dabt_iswrite(vcpu); + sign_extend = kvm_vcpu_dabt_issext(vcpu); + rt = kvm_vcpu_dabt_get_rd(vcpu); if (kvm_vcpu_reg_is_pc(vcpu, rt)) { /* IO memory trying to read/write pc */ - kvm_inject_pabt(vcpu, vcpu->arch.hxfar); + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 1; } @@ -112,7 +102,7 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * The MMIO instruction is emulated and should not be re-executed * in the guest. */ - kvm_skip_instr(vcpu, (vcpu->arch.hsr >> 25) & 1); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 0; } @@ -130,7 +120,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, * space do its magic. */ - if (vcpu->arch.hsr & HSR_ISV) { + if (kvm_vcpu_dabt_isvalid(vcpu)) { ret = decode_hsr(vcpu, fault_ipa, &mmio); if (ret) return ret; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 99e07c7dd745..2f12e4056408 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -20,7 +20,6 @@ #include <linux/kvm_host.h> #include <linux/io.h> #include <trace/events/kvm.h> -#include <asm/idmap.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/kvm_arm.h> @@ -28,8 +27,6 @@ #include <asm/kvm_mmio.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> -#include <asm/mach/map.h> -#include <trace/events/kvm.h> #include "trace.h" @@ -37,19 +34,9 @@ extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; static DEFINE_MUTEX(kvm_hyp_pgd_mutex); -static void kvm_tlb_flush_vmid(struct kvm *kvm) +static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { - kvm_call_hyp(__kvm_tlb_flush_vmid, kvm); -} - -static void kvm_set_pte(pte_t *pte, pte_t new_pte) -{ - pte_val(*pte) = new_pte; - /* - * flush_pmd_entry just takes a void pointer and cleans the necessary - * cache entries, so we can reuse the function for ptes. - */ - flush_pmd_entry(pte); + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); } static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, @@ -98,33 +85,42 @@ static void free_ptes(pmd_t *pmd, unsigned long addr) } } +static void free_hyp_pgd_entry(unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + unsigned long hyp_addr = KERN_TO_HYP(addr); + + pgd = hyp_pgd + pgd_index(hyp_addr); + pud = pud_offset(pgd, hyp_addr); + + if (pud_none(*pud)) + return; + BUG_ON(pud_bad(*pud)); + + pmd = pmd_offset(pud, hyp_addr); + free_ptes(pmd, addr); + pmd_free(NULL, pmd); + pud_clear(pud); +} + /** * free_hyp_pmds - free a Hyp-mode level-2 tables and child level-3 tables * * Assumes this is a page table used strictly in Hyp-mode and therefore contains - * only mappings in the kernel memory area, which is above PAGE_OFFSET. + * either mappings in the kernel memory area (above PAGE_OFFSET), or + * device mappings in the vmalloc range (from VMALLOC_START to VMALLOC_END). */ void free_hyp_pmds(void) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; unsigned long addr; mutex_lock(&kvm_hyp_pgd_mutex); - for (addr = PAGE_OFFSET; addr != 0; addr += PGDIR_SIZE) { - pgd = hyp_pgd + pgd_index(addr); - pud = pud_offset(pgd, addr); - - if (pud_none(*pud)) - continue; - BUG_ON(pud_bad(*pud)); - - pmd = pmd_offset(pud, addr); - free_ptes(pmd, addr); - pmd_free(NULL, pmd); - pud_clear(pud); - } + for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE) + free_hyp_pgd_entry(addr); + for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE) + free_hyp_pgd_entry(addr); mutex_unlock(&kvm_hyp_pgd_mutex); } @@ -136,7 +132,9 @@ static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start, struct page *page; for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) { - pte = pte_offset_kernel(pmd, addr); + unsigned long hyp_addr = KERN_TO_HYP(addr); + + pte = pte_offset_kernel(pmd, hyp_addr); BUG_ON(!virt_addr_valid(addr)); page = virt_to_page(addr); kvm_set_pte(pte, mk_pte(page, PAGE_HYP)); @@ -151,7 +149,9 @@ static void create_hyp_io_pte_mappings(pmd_t *pmd, unsigned long start, unsigned long addr; for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) { - pte = pte_offset_kernel(pmd, addr); + unsigned long hyp_addr = KERN_TO_HYP(addr); + + pte = pte_offset_kernel(pmd, hyp_addr); BUG_ON(pfn_valid(*pfn_base)); kvm_set_pte(pte, pfn_pte(*pfn_base, PAGE_HYP_DEVICE)); (*pfn_base)++; @@ -166,12 +166,13 @@ static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start, unsigned long addr, next; for (addr = start; addr < end; addr = next) { - pmd = pmd_offset(pud, addr); + unsigned long hyp_addr = KERN_TO_HYP(addr); + pmd = pmd_offset(pud, hyp_addr); BUG_ON(pmd_sect(*pmd)); if (pmd_none(*pmd)) { - pte = pte_alloc_one_kernel(NULL, addr); + pte = pte_alloc_one_kernel(NULL, hyp_addr); if (!pte) { kvm_err("Cannot allocate Hyp pte\n"); return -ENOMEM; @@ -206,17 +207,23 @@ static int __create_hyp_mappings(void *from, void *to, unsigned long *pfn_base) unsigned long addr, next; int err = 0; - BUG_ON(start > end); - if (start < PAGE_OFFSET) + if (start >= end) + return -EINVAL; + /* Check for a valid kernel memory mapping */ + if (!pfn_base && (!virt_addr_valid(from) || !virt_addr_valid(to - 1))) + return -EINVAL; + /* Check for a valid kernel IO mapping */ + if (pfn_base && (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1))) return -EINVAL; mutex_lock(&kvm_hyp_pgd_mutex); for (addr = start; addr < end; addr = next) { - pgd = hyp_pgd + pgd_index(addr); - pud = pud_offset(pgd, addr); + unsigned long hyp_addr = KERN_TO_HYP(addr); + pgd = hyp_pgd + pgd_index(hyp_addr); + pud = pud_offset(pgd, hyp_addr); if (pud_none_or_clear_bad(pud)) { - pmd = pmd_alloc_one(NULL, addr); + pmd = pmd_alloc_one(NULL, hyp_addr); if (!pmd) { kvm_err("Cannot allocate Hyp pmd\n"); err = -ENOMEM; @@ -236,12 +243,13 @@ out: } /** - * create_hyp_mappings - map a kernel virtual address range in Hyp mode + * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range * @to: The virtual kernel end address of the range (exclusive) * - * The same virtual address as the kernel virtual address is also used in - * Hyp-mode mapping to the same underlying physical pages. + * The same virtual address as the kernel virtual address is also used + * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying + * physical pages. * * Note: Wrapping around zero in the "to" address is not supported. */ @@ -251,10 +259,13 @@ int create_hyp_mappings(void *from, void *to) } /** - * create_hyp_io_mappings - map a physical IO range in Hyp mode - * @from: The virtual HYP start address of the range - * @to: The virtual HYP end address of the range (exclusive) + * create_hyp_io_mappings - duplicate a kernel IO mapping into Hyp mode + * @from: The kernel start VA of the range + * @to: The kernel end VA of the range (exclusive) * @addr: The physical start address which gets mapped + * + * The resulting HYP VA is the same as the kernel VA, modulo + * HYP_PAGE_OFFSET. */ int create_hyp_io_mappings(void *from, void *to, phys_addr_t addr) { @@ -290,7 +301,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) VM_BUG_ON((unsigned long)pgd & (S2_PGD_SIZE - 1)); memset(pgd, 0, PTRS_PER_S2_PGD * sizeof(pgd_t)); - clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t)); + kvm_clean_pgd(pgd); kvm->arch.pgd = pgd; return 0; @@ -422,22 +433,22 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, return 0; /* ignore calls from kvm_set_spte_hva */ pmd = mmu_memory_cache_alloc(cache); pud_populate(NULL, pud, pmd); - pmd += pmd_index(addr); get_page(virt_to_page(pud)); - } else - pmd = pmd_offset(pud, addr); + } + + pmd = pmd_offset(pud, addr); /* Create 2nd stage page table mapping - Level 2 */ if (pmd_none(*pmd)) { if (!cache) return 0; /* ignore calls from kvm_set_spte_hva */ pte = mmu_memory_cache_alloc(cache); - clean_pte_table(pte); + kvm_clean_pte(pte); pmd_populate_kernel(NULL, pmd, pte); - pte += pte_index(addr); get_page(virt_to_page(pmd)); - } else - pte = pte_offset_kernel(pmd, addr); + } + + pte = pte_offset_kernel(pmd, addr); if (iomap && pte_present(*pte)) return -EFAULT; @@ -446,7 +457,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, old_pte = *pte; kvm_set_pte(pte, *new_pte); if (pte_present(old_pte)) - kvm_tlb_flush_vmid(kvm); + kvm_tlb_flush_vmid_ipa(kvm, addr); else get_page(virt_to_page(pte)); @@ -473,7 +484,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, pfn = __phys_to_pfn(pa); for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) { - pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE | L_PTE_S2_RDWR); + pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE); + kvm_set_s2pte_writable(&pte); ret = mmu_topup_memory_cache(&cache, 2, 2); if (ret) @@ -492,29 +504,6 @@ out: return ret; } -static void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn) -{ - /* - * If we are going to insert an instruction page and the icache is - * either VIPT or PIPT, there is a potential problem where the host - * (or another VM) may have used the same page as this guest, and we - * read incorrect data from the icache. If we're using a PIPT cache, - * we can invalidate just that page, but if we are using a VIPT cache - * we need to invalidate the entire icache - damn shame - as written - * in the ARM ARM (DDI 0406C.b - Page B3-1393). - * - * VIVT caches are tagged using both the ASID and the VMID and doesn't - * need any kind of flushing (DDI 0406C.b - Page B3-1392). - */ - if (icache_is_pipt()) { - unsigned long hva = gfn_to_hva(kvm, gfn); - __cpuc_coherent_user_range(hva, hva + PAGE_SIZE); - } else if (!icache_is_vivt_asid_tagged()) { - /* any kind of VIPT cache */ - __flush_icache_all(); - } -} - static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, gfn_t gfn, struct kvm_memory_slot *memslot, unsigned long fault_status) @@ -526,7 +515,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long mmu_seq; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; - write_fault = kvm_is_write_fault(vcpu->arch.hsr); + write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu)); if (fault_status == FSC_PERM && !write_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; @@ -560,7 +549,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; if (writable) { - pte_val(new_pte) |= L_PTE_S2_RDWR; + kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn); } stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte, false); @@ -585,7 +574,6 @@ out_unlock: */ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) { - unsigned long hsr_ec; unsigned long fault_status; phys_addr_t fault_ipa; struct kvm_memory_slot *memslot; @@ -593,18 +581,17 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) gfn_t gfn; int ret, idx; - hsr_ec = vcpu->arch.hsr >> HSR_EC_SHIFT; - is_iabt = (hsr_ec == HSR_EC_IABT); - fault_ipa = ((phys_addr_t)vcpu->arch.hpfar & HPFAR_MASK) << 8; + is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); - trace_kvm_guest_fault(*vcpu_pc(vcpu), vcpu->arch.hsr, - vcpu->arch.hxfar, fault_ipa); + trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu), + kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ - fault_status = (vcpu->arch.hsr & HSR_FSC_TYPE); + fault_status = kvm_vcpu_trap_get_fault(vcpu); if (fault_status != FSC_FAULT && fault_status != FSC_PERM) { - kvm_err("Unsupported fault status: EC=%#lx DFCS=%#lx\n", - hsr_ec, fault_status); + kvm_err("Unsupported fault status: EC=%#x DFCS=%#lx\n", + kvm_vcpu_trap_get_class(vcpu), fault_status); return -EFAULT; } @@ -614,7 +601,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) if (!kvm_is_visible_gfn(vcpu->kvm, gfn)) { if (is_iabt) { /* Prefetch Abort on I/O address */ - kvm_inject_pabt(vcpu, vcpu->arch.hxfar); + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); ret = 1; goto out_unlock; } @@ -626,8 +613,13 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) goto out_unlock; } - /* Adjust page offset */ - fault_ipa |= vcpu->arch.hxfar & ~PAGE_MASK; + /* + * The IPA is reported as [MAX:12], so we need to + * complement it with the bottom 12 bits from the + * faulting VA. This is always 12 bits, irrespective + * of the page size. + */ + fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1); ret = io_mem_abort(vcpu, run, fault_ipa); goto out_unlock; } @@ -682,7 +674,7 @@ static void handle_hva_to_gpa(struct kvm *kvm, static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) { unmap_stage2_range(kvm, gpa, PAGE_SIZE); - kvm_tlb_flush_vmid(kvm); + kvm_tlb_flush_vmid_ipa(kvm, gpa); } int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) @@ -776,7 +768,7 @@ void kvm_clear_hyp_idmap(void) pmd = pmd_offset(pud, addr); pud_clear(pud); - clean_pmd_entry(pmd); + kvm_clean_pmd_entry(pmd); pmd_free(NULL, (pmd_t *)((unsigned long)pmd & PAGE_MASK)); } while (pgd++, addr = next, addr < end); } diff --git a/arch/arm/kvm/vgic.c b/arch/arm/kvm/vgic.c index 0e4cfe123b38..17c5ac7d10ed 100644 --- a/arch/arm/kvm/vgic.c +++ b/arch/arm/kvm/vgic.c @@ -1477,7 +1477,7 @@ int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr) if (addr & ~KVM_PHYS_MASK) return -E2BIG; - if (addr & ~PAGE_MASK) + if (addr & (SZ_4K - 1)) return -EINVAL; mutex_lock(&kvm->lock); diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c index 2acdff4c1dfe..180b3024bec3 100644 --- a/arch/arm/mach-at91/at91rm9200_time.c +++ b/arch/arm/mach-at91/at91rm9200_time.c @@ -174,6 +174,7 @@ clkevt32k_next_event(unsigned long delta, struct clock_event_device *dev) static struct clock_event_device clkevt = { .name = "at91_tick", .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, + .shift = 32, .rating = 150, .set_next_event = clkevt32k_next_event, .set_mode = clkevt32k_mode, @@ -264,9 +265,11 @@ void __init at91rm9200_timer_init(void) at91_st_write(AT91_ST_RTMR, 1); /* Setup timer clockevent, with minimum of two ticks (important!!) */ + clkevt.mult = div_sc(AT91_SLOW_CLOCK, NSEC_PER_SEC, clkevt.shift); + clkevt.max_delta_ns = clockevent_delta2ns(AT91_ST_ALMV, &clkevt); + clkevt.min_delta_ns = clockevent_delta2ns(2, &clkevt) + 1; clkevt.cpumask = cpumask_of(0); - clockevents_config_and_register(&clkevt, AT91_SLOW_CLOCK, - 2, AT91_ST_ALMV); + clockevents_register_device(&clkevt); /* register clocksource */ clocksource_register_hz(&clk32k, AT91_SLOW_CLOCK); diff --git a/arch/arm/mach-at91/gpio.c b/arch/arm/mach-at91/gpio.c index c5d7e1e9d757..a5afcf76550e 100644 --- a/arch/arm/mach-at91/gpio.c +++ b/arch/arm/mach-at91/gpio.c @@ -22,10 +22,9 @@ #include <linux/module.h> #include <linux/io.h> #include <linux/irqdomain.h> +#include <linux/irqchip/chained_irq.h> #include <linux/of_address.h> -#include <asm/mach/irq.h> - #include <mach/hardware.h> #include <mach/at91_pio.h> diff --git a/arch/arm/mach-at91/setup.c b/arch/arm/mach-at91/setup.c index 4b678478cf95..6b4608d58da2 100644 --- a/arch/arm/mach-at91/setup.c +++ b/arch/arm/mach-at91/setup.c @@ -333,7 +333,7 @@ static void at91_dt_rstc(void) of_id = of_match_node(rstc_ids, np); if (!of_id) - panic("AT91: rtsc no restart function availlable\n"); + panic("AT91: rtsc no restart function available\n"); arm_pm_restart = of_id->data; diff --git a/arch/arm/mach-exynos/common.c b/arch/arm/mach-exynos/common.c index d63d399c7bae..7bc0f9aa8b33 100644 --- a/arch/arm/mach-exynos/common.c +++ b/arch/arm/mach-exynos/common.c @@ -26,6 +26,7 @@ #include <linux/irqchip.h> #include <linux/of_address.h> #include <linux/irqchip/arm-gic.h> +#include <linux/irqchip/chained_irq.h> #include <asm/proc-fns.h> #include <asm/exception.h> diff --git a/arch/arm/mach-exynos/include/mach/regs-pmu.h b/arch/arm/mach-exynos/include/mach/regs-pmu.h index 3f30aa1ae354..57344b7e98ce 100644 --- a/arch/arm/mach-exynos/include/mach/regs-pmu.h +++ b/arch/arm/mach-exynos/include/mach/regs-pmu.h @@ -344,6 +344,7 @@ #define EXYNOS5_FSYS_ARM_OPTION S5P_PMUREG(0x2208) #define EXYNOS5_ISP_ARM_OPTION S5P_PMUREG(0x2288) #define EXYNOS5_ARM_COMMON_OPTION S5P_PMUREG(0x2408) +#define EXYNOS5_ARM_L2_OPTION S5P_PMUREG(0x2608) #define EXYNOS5_TOP_PWR_OPTION S5P_PMUREG(0x2C48) #define EXYNOS5_TOP_PWR_SYSMEM_OPTION S5P_PMUREG(0x2CC8) #define EXYNOS5_JPEG_MEM_OPTION S5P_PMUREG(0x2F48) diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c index 60f7c5be057d..95e04bd5813f 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -20,7 +20,6 @@ #include <linux/jiffies.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -76,13 +75,6 @@ static DEFINE_SPINLOCK(boot_lock); static void __cpuinit exynos_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/mach-exynos/pmu.c b/arch/arm/mach-exynos/pmu.c index daebc1abc966..97d688526258 100644 --- a/arch/arm/mach-exynos/pmu.c +++ b/arch/arm/mach-exynos/pmu.c @@ -228,6 +228,7 @@ static struct exynos_pmu_conf exynos5250_pmu_config[] = { { EXYNOS5_DIS_IRQ_ISP_ARM_CENTRAL_SYS_PWR_REG, { 0x0, 0x0, 0x0} }, { EXYNOS5_ARM_COMMON_SYS_PWR_REG, { 0x0, 0x0, 0x2} }, { EXYNOS5_ARM_L2_SYS_PWR_REG, { 0x3, 0x3, 0x3} }, + { EXYNOS5_ARM_L2_OPTION, { 0x10, 0x10, 0x0 } }, { EXYNOS5_CMU_ACLKSTOP_SYS_PWR_REG, { 0x1, 0x0, 0x1} }, { EXYNOS5_CMU_SCLKSTOP_SYS_PWR_REG, { 0x1, 0x0, 0x1} }, { EXYNOS5_CMU_RESET_SYS_PWR_REG, { 0x1, 0x1, 0x0} }, @@ -353,11 +354,9 @@ static void exynos5_init_pmu(void) /* * SKIP_DEACTIVATE_ACEACP_IN_PWDN_BITFIELD Enable - * MANUAL_L2RSTDISABLE_CONTROL_BITFIELD Enable */ tmp = __raw_readl(EXYNOS5_ARM_COMMON_OPTION); - tmp |= (EXYNOS5_MANUAL_L2RSTDISABLE_CONTROL | - EXYNOS5_SKIP_DEACTIVATE_ACEACP_IN_PWDN); + tmp |= EXYNOS5_SKIP_DEACTIVATE_ACEACP_IN_PWDN; __raw_writel(tmp, EXYNOS5_ARM_COMMON_OPTION); /* diff --git a/arch/arm/mach-highbank/platsmp.c b/arch/arm/mach-highbank/platsmp.c index 8797a7001720..a984573e0d02 100644 --- a/arch/arm/mach-highbank/platsmp.c +++ b/arch/arm/mach-highbank/platsmp.c @@ -17,7 +17,6 @@ #include <linux/init.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <asm/smp_scu.h> @@ -25,11 +24,6 @@ extern void secondary_startup(void); -static void __cpuinit highbank_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - static int __cpuinit highbank_boot_secondary(unsigned int cpu, struct task_struct *idle) { highbank_set_cpu_jump(cpu, secondary_startup); @@ -67,7 +61,6 @@ static void __init highbank_smp_prepare_cpus(unsigned int max_cpus) struct smp_operations highbank_smp_ops __initdata = { .smp_init_cpus = highbank_smp_init_cpus, .smp_prepare_cpus = highbank_smp_prepare_cpus, - .smp_secondary_init = highbank_secondary_init, .smp_boot_secondary = highbank_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_die = highbank_cpu_die, diff --git a/arch/arm/mach-imx/platsmp.c b/arch/arm/mach-imx/platsmp.c index 7c0b03f67b05..77e9a25ed0f6 100644 --- a/arch/arm/mach-imx/platsmp.c +++ b/arch/arm/mach-imx/platsmp.c @@ -12,7 +12,6 @@ #include <linux/init.h> #include <linux/smp.h> -#include <linux/irqchip/arm-gic.h> #include <asm/page.h> #include <asm/smp_scu.h> #include <asm/mach/map.h> @@ -52,16 +51,6 @@ void imx_scu_standby_enable(void) writel_relaxed(val, scu_base); } -static void __cpuinit imx_secondary_init(unsigned int cpu) -{ - /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); -} - static int __cpuinit imx_boot_secondary(unsigned int cpu, struct task_struct *idle) { imx_set_cpu_jump(cpu, v7_secondary_startup); @@ -96,7 +85,6 @@ static void __init imx_smp_prepare_cpus(unsigned int max_cpus) struct smp_operations imx_smp_ops __initdata = { .smp_init_cpus = imx_smp_init_cpus, .smp_prepare_cpus = imx_smp_prepare_cpus, - .smp_secondary_init = imx_secondary_init, .smp_boot_secondary = imx_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_die = imx_cpu_die, diff --git a/arch/arm/mach-kirkwood/board-ts219.c b/arch/arm/mach-kirkwood/board-ts219.c index acb0187c7ee1..4695d5f35fc9 100644 --- a/arch/arm/mach-kirkwood/board-ts219.c +++ b/arch/arm/mach-kirkwood/board-ts219.c @@ -41,13 +41,3 @@ void __init qnap_dt_ts219_init(void) pm_power_off = qnap_tsx1x_power_off; } - -/* FIXME: Will not work with DT. Maybe use MPP40_GPIO? */ -static int __init ts219_pci_init(void) -{ - if (machine_is_ts219()) - kirkwood_pcie_init(KW_PCIE0); - - return 0; -} -subsys_initcall(ts219_pci_init); diff --git a/arch/arm/mach-kirkwood/ts219-setup.c b/arch/arm/mach-kirkwood/ts219-setup.c index 283abff90228..e1267d6b468f 100644 --- a/arch/arm/mach-kirkwood/ts219-setup.c +++ b/arch/arm/mach-kirkwood/ts219-setup.c @@ -124,7 +124,7 @@ static void __init qnap_ts219_init(void) static int __init ts219_pci_init(void) { if (machine_is_ts219()) - kirkwood_pcie_init(KW_PCIE0); + kirkwood_pcie_init(KW_PCIE1 | KW_PCIE0); return 0; } diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c index 42932865416a..00cdb0a5dac8 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -15,7 +15,6 @@ #include <linux/jiffies.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/cputype.h> @@ -42,13 +41,6 @@ static inline int get_core_count(void) static void __cpuinit msm_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c index 3a077df6b8df..9bc9f191f9c9 100644 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ b/arch/arm/mach-omap2/board-rx51-peripherals.c @@ -73,11 +73,11 @@ #define LIS302_IRQ1_GPIO 181 #define LIS302_IRQ2_GPIO 180 /* Not yet in use */ -/* list all spi devices here */ +/* List all SPI devices here. Note that the list/probe order seems to matter! */ enum { RX51_SPI_WL1251, - RX51_SPI_MIPID, /* LCD panel */ RX51_SPI_TSC2005, /* Touch Controller */ + RX51_SPI_MIPID, /* LCD panel */ }; static struct wl12xx_platform_data wl1251_pdata; diff --git a/arch/arm/mach-omap2/cclock33xx_data.c b/arch/arm/mach-omap2/cclock33xx_data.c index 476b82066cb6..832772147f3e 100644 --- a/arch/arm/mach-omap2/cclock33xx_data.c +++ b/arch/arm/mach-omap2/cclock33xx_data.c @@ -446,9 +446,29 @@ DEFINE_CLK_GATE(cefuse_fck, "sys_clkin_ck", &sys_clkin_ck, 0x0, */ DEFINE_CLK_FIXED_FACTOR(clkdiv32k_ck, "clk_24mhz", &clk_24mhz, 0x0, 1, 732); -DEFINE_CLK_GATE(clkdiv32k_ick, "clkdiv32k_ck", &clkdiv32k_ck, 0x0, - AM33XX_CM_PER_CLKDIV32K_CLKCTRL, AM33XX_MODULEMODE_SWCTRL_SHIFT, - 0x0, NULL); +static struct clk clkdiv32k_ick; + +static const char *clkdiv32k_ick_parent_names[] = { + "clkdiv32k_ck", +}; + +static const struct clk_ops clkdiv32k_ick_ops = { + .enable = &omap2_dflt_clk_enable, + .disable = &omap2_dflt_clk_disable, + .is_enabled = &omap2_dflt_clk_is_enabled, + .init = &omap2_init_clk_clkdm, +}; + +static struct clk_hw_omap clkdiv32k_ick_hw = { + .hw = { + .clk = &clkdiv32k_ick, + }, + .enable_reg = AM33XX_CM_PER_CLKDIV32K_CLKCTRL, + .enable_bit = AM33XX_MODULEMODE_SWCTRL_SHIFT, + .clkdm_name = "clk_24mhz_clkdm", +}; + +DEFINE_STRUCT_CLK(clkdiv32k_ick, clkdiv32k_ick_parent_names, clkdiv32k_ick_ops); /* "usbotg_fck" is an additional clock and not really a modulemode */ DEFINE_CLK_GATE(usbotg_fck, "dpll_per_ck", &dpll_per_ck, 0x0, diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c index 80392fca86c6..4f67a5b9bc52 100644 --- a/arch/arm/mach-omap2/cpuidle34xx.c +++ b/arch/arm/mach-omap2/cpuidle34xx.c @@ -274,8 +274,9 @@ static int omap3_enter_idle_bm(struct cpuidle_device *dev, static DEFINE_PER_CPU(struct cpuidle_device, omap3_idle_dev); static struct cpuidle_driver omap3_idle_driver = { - .name = "omap3_idle", - .owner = THIS_MODULE, + .name = "omap3_idle", + .owner = THIS_MODULE, + .en_core_tk_irqen = 1, .states = { { .enter = omap3_enter_idle_bm, diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 8a68f1ec66b9..577298ed5a44 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -300,7 +300,7 @@ void __init omap3xxx_check_revision(void) * If the processor type is Cortex-A8 and the revision is 0x0 * it means its Cortex r0p0 which is 3430 ES1.0. */ - cpuid = read_cpuid(CPUID_ID); + cpuid = read_cpuid_id(); if ((((cpuid >> 4) & 0xfff) == 0xc08) && ((cpuid & 0xf) == 0x0)) { omap_revision = OMAP3430_REV_ES1_0; cpu_rev = "1.0"; @@ -460,7 +460,7 @@ void __init omap4xxx_check_revision(void) * Use ARM register to detect the correct ES version */ if (!rev && (hawkeye != 0xb94e) && (hawkeye != 0xb975)) { - idcode = read_cpuid(CPUID_ID); + idcode = read_cpuid_id(); rev = (idcode & 0xf) - 1; } diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index d9727218dd0a..f0897732a962 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -67,13 +67,6 @@ static void __cpuinit omap4_secondary_init(unsigned int cpu) 4, 0, 0, 0, 0, 0); /* - * If any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * Synchronise with the boot thread. */ spin_lock(&boot_lock); @@ -209,7 +202,7 @@ static void __init omap4_smp_init_cpus(void) unsigned int i = 0, ncores = 1, cpu_id; /* Use ARM cpuid check here, as SoC detection will not work so early */ - cpu_id = read_cpuid(CPUID_ID) & CPU_MASK; + cpu_id = read_cpuid_id() & CPU_MASK; if (cpu_id == CPU_CORTEX_A9) { /* * Currently we can't call ioremap here because diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index a202a4785104..3a750de656ce 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -2066,7 +2066,7 @@ static int _omap4_get_context_lost(struct omap_hwmod *oh) * do so is present in the hwmod data, then call it and pass along the * return value; otherwise, return 0. */ -static int __init _enable_preprogram(struct omap_hwmod *oh) +static int _enable_preprogram(struct omap_hwmod *oh) { if (!oh->class->enable_preprogram) return 0; diff --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c index 4b788310f6a6..c7c92e78f0cf 100644 --- a/arch/arm/mach-prima2/platsmp.c +++ b/arch/arm/mach-prima2/platsmp.c @@ -11,7 +11,6 @@ #include <linux/delay.h> #include <linux/of.h> #include <linux/of_address.h> -#include <linux/irqchip/arm-gic.h> #include <asm/page.h> #include <asm/mach/map.h> #include <asm/smp_plat.h> @@ -49,13 +48,6 @@ void __init sirfsoc_map_scu(void) static void __cpuinit sirfsoc_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/mach-s3c24xx/irq.c b/arch/arm/mach-s3c24xx/irq.c index d8ba9bee4c7e..6b0b6047785c 100644 --- a/arch/arm/mach-s3c24xx/irq.c +++ b/arch/arm/mach-s3c24xx/irq.c @@ -25,6 +25,7 @@ #include <linux/ioport.h> #include <linux/device.h> #include <linux/irqdomain.h> +#include <linux/irqchip/chained_irq.h> #include <asm/mach/irq.h> diff --git a/arch/arm/mach-shmobile/smp-emev2.c b/arch/arm/mach-shmobile/smp-emev2.c index 953eb1f9388d..384e27dd3601 100644 --- a/arch/arm/mach-shmobile/smp-emev2.c +++ b/arch/arm/mach-shmobile/smp-emev2.c @@ -23,7 +23,6 @@ #include <linux/spinlock.h> #include <linux/io.h> #include <linux/delay.h> -#include <linux/irqchip/arm-gic.h> #include <mach/common.h> #include <mach/emev2.h> #include <asm/smp_plat.h> @@ -85,11 +84,6 @@ static int __maybe_unused emev2_cpu_kill(unsigned int cpu) } -static void __cpuinit emev2_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - static int __cpuinit emev2_boot_secondary(unsigned int cpu, struct task_struct *idle) { cpu = cpu_logical_map(cpu); @@ -124,7 +118,6 @@ static void __init emev2_smp_init_cpus(void) struct smp_operations emev2_smp_ops __initdata = { .smp_init_cpus = emev2_smp_init_cpus, .smp_prepare_cpus = emev2_smp_prepare_cpus, - .smp_secondary_init = emev2_secondary_init, .smp_boot_secondary = emev2_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_kill = emev2_cpu_kill, diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c index 3a4acf23edcf..994906560edd 100644 --- a/arch/arm/mach-shmobile/smp-r8a7779.c +++ b/arch/arm/mach-shmobile/smp-r8a7779.c @@ -23,7 +23,6 @@ #include <linux/spinlock.h> #include <linux/io.h> #include <linux/delay.h> -#include <linux/irqchip/arm-gic.h> #include <mach/common.h> #include <mach/r8a7779.h> #include <asm/smp_plat.h> @@ -132,11 +131,6 @@ static int __maybe_unused r8a7779_cpu_kill(unsigned int cpu) } -static void __cpuinit r8a7779_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - static int __cpuinit r8a7779_boot_secondary(unsigned int cpu, struct task_struct *idle) { struct r8a7779_pm_ch *ch = NULL; @@ -186,7 +180,6 @@ static void __init r8a7779_smp_init_cpus(void) struct smp_operations r8a7779_smp_ops __initdata = { .smp_init_cpus = r8a7779_smp_init_cpus, .smp_prepare_cpus = r8a7779_smp_prepare_cpus, - .smp_secondary_init = r8a7779_secondary_init, .smp_boot_secondary = r8a7779_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_kill = r8a7779_cpu_kill, diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c index acb46a94ccdf..d0f9aca22477 100644 --- a/arch/arm/mach-shmobile/smp-sh73a0.c +++ b/arch/arm/mach-shmobile/smp-sh73a0.c @@ -23,7 +23,6 @@ #include <linux/spinlock.h> #include <linux/io.h> #include <linux/delay.h> -#include <linux/irqchip/arm-gic.h> #include <mach/common.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -59,11 +58,6 @@ static unsigned int __init sh73a0_get_core_count(void) return scu_get_core_count(scu_base); } -static void __cpuinit sh73a0_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - static int __cpuinit sh73a0_boot_secondary(unsigned int cpu, struct task_struct *idle) { cpu = cpu_logical_map(cpu); @@ -138,7 +132,6 @@ static void sh73a0_cpu_die(unsigned int cpu) struct smp_operations sh73a0_smp_ops __initdata = { .smp_init_cpus = sh73a0_smp_init_cpus, .smp_prepare_cpus = sh73a0_smp_prepare_cpus, - .smp_secondary_init = sh73a0_secondary_init, .smp_boot_secondary = sh73a0_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_kill = sh73a0_cpu_kill, diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c index 84c60fa8daa0..ca14d1d5ac7f 100644 --- a/arch/arm/mach-socfpga/platsmp.c +++ b/arch/arm/mach-socfpga/platsmp.c @@ -22,7 +22,6 @@ #include <linux/io.h> #include <linux/of.h> #include <linux/of_address.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_scu.h> @@ -33,16 +32,6 @@ extern void __iomem *sys_manager_base_addr; extern void __iomem *rst_manager_base_addr; -static void __cpuinit socfpga_secondary_init(unsigned int cpu) -{ - /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); -} - static int __cpuinit socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) { int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; @@ -109,7 +98,6 @@ static void socfpga_cpu_die(unsigned int cpu) struct smp_operations socfpga_smp_ops __initdata = { .smp_init_cpus = socfpga_smp_init_cpus, .smp_prepare_cpus = socfpga_smp_prepare_cpus, - .smp_secondary_init = socfpga_secondary_init, .smp_boot_secondary = socfpga_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_die = socfpga_cpu_die, diff --git a/arch/arm/mach-spear13xx/platsmp.c b/arch/arm/mach-spear13xx/platsmp.c index af4ade61cd95..551c69c9a228 100644 --- a/arch/arm/mach-spear13xx/platsmp.c +++ b/arch/arm/mach-spear13xx/platsmp.c @@ -15,7 +15,6 @@ #include <linux/jiffies.h> #include <linux/io.h> #include <linux/smp.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_scu.h> #include <mach/spear.h> @@ -28,13 +27,6 @@ static void __iomem *scu_base = IOMEM(VA_SCU_BASE); static void __cpuinit spear13xx_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c index 2c6b3d55213b..9348d3c496a9 100644 --- a/arch/arm/mach-tegra/platsmp.c +++ b/arch/arm/mach-tegra/platsmp.c @@ -18,7 +18,6 @@ #include <linux/jiffies.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <linux/clk/tegra.h> #include <asm/cacheflush.h> @@ -44,13 +43,6 @@ static cpumask_t tegra_cpu_init_mask; static void __cpuinit tegra_secondary_init(unsigned int cpu) { - /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - cpumask_set_cpu(cpu, &tegra_cpu_init_mask); } diff --git a/arch/arm/mach-u300/include/mach/u300-regs.h b/arch/arm/mach-u300/include/mach/u300-regs.h index 1e49d901f2c9..0320495efc4d 100644 --- a/arch/arm/mach-u300/include/mach/u300-regs.h +++ b/arch/arm/mach-u300/include/mach/u300-regs.h @@ -95,7 +95,7 @@ #define U300_SPI_BASE (U300_FAST_PER_PHYS_BASE+0x6000) /* Fast UART1 on U335 only */ -#define U300_UART1_BASE (U300_SLOW_PER_PHYS_BASE+0x7000) +#define U300_UART1_BASE (U300_FAST_PER_PHYS_BASE+0x7000) /* * SLOW peripherals diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c index 18f7af339dc9..152b1309b9af 100644 --- a/arch/arm/mach-ux500/platsmp.c +++ b/arch/arm/mach-ux500/platsmp.c @@ -16,7 +16,6 @@ #include <linux/device.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -58,13 +57,6 @@ static DEFINE_SPINLOCK(boot_lock); static void __cpuinit ux500_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig index 52d315b792c8..7b2ebc29ce3a 100644 --- a/arch/arm/mach-vexpress/Kconfig +++ b/arch/arm/mach-vexpress/Kconfig @@ -1,5 +1,6 @@ config ARCH_VEXPRESS bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7 + select ARCH_HAS_CPUFREQ select ARCH_REQUIRE_GPIOLIB select ARM_AMBA select ARM_GIC @@ -52,4 +53,21 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA config ARCH_VEXPRESS_CA9X4 bool "Versatile Express Cortex-A9x4 tile" +config ARCH_VEXPRESS_DCSCB + bool "Dual Cluster System Control Block (DCSCB) support" + depends on MCPM + select ARM_CCI + help + Support for the Dual Cluster System Configuration Block (DCSCB). + This is needed to provide CPU and cluster power management + on RTSM. + +config ARCH_VEXPRESS_TC2 + bool "TC2 cluster management" + depends on MCPM + select ARM_SPC + select ARM_CCI + help + Support for CPU and cluster power management on TC2. + endmenu diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile index 80b64971fbdd..b4117dbfe85a 100644 --- a/arch/arm/mach-vexpress/Makefile +++ b/arch/arm/mach-vexpress/Makefile @@ -6,5 +6,13 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \ obj-y := v2m.o reset.o obj-$(CONFIG_ARCH_VEXPRESS_CA9X4) += ct-ca9x4.o +obj-$(CONFIG_ARCH_VEXPRESS_DCSCB) += dcscb.o dcscb_setup.o +CFLAGS_REMOVE_dcscb.o = -pg +obj-$(CONFIG_ARCH_VEXPRESS_TC2) += tc2_pm.o tc2_pm_setup.o +CFLAGS_REMOVE_tc2_pm.o = -pg +ifeq ($(CONFIG_ARCH_VEXPRESS_TC2),y) +obj-$(CONFIG_ARM_PSCI) += tc2_pm_psci.o +CFLAGS_REMOVE_tc2_pm_psci.o = -pg +endif obj-$(CONFIG_SMP) += platsmp.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o diff --git a/arch/arm/mach-vexpress/core.h b/arch/arm/mach-vexpress/core.h index f134cd4a85f1..bde4374ab6d5 100644 --- a/arch/arm/mach-vexpress/core.h +++ b/arch/arm/mach-vexpress/core.h @@ -6,6 +6,8 @@ void vexpress_dt_smp_map_io(void); +bool vexpress_smp_init_ops(void); + extern struct smp_operations vexpress_smp_ops; extern void vexpress_cpu_die(unsigned int cpu); diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c new file mode 100644 index 000000000000..0dc3caca227b --- /dev/null +++ b/arch/arm/mach-vexpress/dcscb.c @@ -0,0 +1,256 @@ +/* + * arch/arm/mach-vexpress/dcscb.c - Dual Cluster System Configuration Block + * + * Created by: Nicolas Pitre, May 2012 + * Copyright: (C) 2012-2013 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. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/io.h> +#include <linux/spinlock.h> +#include <linux/errno.h> +#include <linux/of_address.h> +#include <linux/vexpress.h> +#include <linux/arm-cci.h> + +#include <asm/mcpm.h> +#include <asm/proc-fns.h> +#include <asm/cacheflush.h> +#include <asm/cputype.h> +#include <asm/cp15.h> +#include <asm/psci.h> + + +#define RST_HOLD0 0x0 +#define RST_HOLD1 0x4 +#define SYS_SWRESET 0x8 +#define RST_STAT0 0xc +#define RST_STAT1 0x10 +#define EAG_CFG_R 0x20 +#define EAG_CFG_W 0x24 +#define KFC_CFG_R 0x28 +#define KFC_CFG_W 0x2c +#define DCS_CFG_R 0x30 + +/* + * We can't use regular spinlocks. In the switcher case, it is possible + * for an outbound CPU to call power_down() after its inbound counterpart + * is already live using the same logical CPU number which trips lockdep + * debugging. + */ +static arch_spinlock_t dcscb_lock = __ARCH_SPIN_LOCK_UNLOCKED; + +static void __iomem *dcscb_base; +static int dcscb_use_count[4][2]; +static int dcscb_mcpm_cpu_mask[2]; + +static int dcscb_power_up(unsigned int cpu, unsigned int cluster) +{ + unsigned int rst_hold, cpumask = (1 << cpu); + unsigned int mcpm_mask = dcscb_mcpm_cpu_mask[cluster]; + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + if (cpu >= 4 || cluster >= 2) + return -EINVAL; + + /* + * Since this is called with IRQs enabled, and no arch_spin_lock_irq + * variant exists, we need to disable IRQs manually here. + */ + local_irq_disable(); + arch_spin_lock(&dcscb_lock); + + dcscb_use_count[cpu][cluster]++; + if (dcscb_use_count[cpu][cluster] == 1) { + rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4); + if (rst_hold & (1 << 8)) { + /* remove cluster reset and add individual CPU's reset */ + rst_hold &= ~(1 << 8); + rst_hold |= mcpm_mask; + } + rst_hold &= ~(cpumask | (cpumask << 4)); + writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4); + } else if (dcscb_use_count[cpu][cluster] != 2) { + /* + * The only possible values are: + * 0 = CPU down + * 1 = CPU (still) up + * 2 = CPU requested to be up before it had a chance + * to actually make itself down. + * Any other value is a bug. + */ + BUG(); + } + + arch_spin_unlock(&dcscb_lock); + local_irq_enable(); + + return 0; +} + +static void dcscb_power_down(void) +{ + unsigned int mpidr, cpu, cluster, rst_hold, cpumask, mcpm_mask; + bool last_man = false, skip_wfi = false; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + cpumask = (1 << cpu); + mcpm_mask = dcscb_mcpm_cpu_mask[cluster]; + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cpu >= 4 || cluster >= 2); + + __mcpm_cpu_going_down(cpu, cluster); + + arch_spin_lock(&dcscb_lock); + BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP); + dcscb_use_count[cpu][cluster]--; + if (dcscb_use_count[cpu][cluster] == 0) { + rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4); + rst_hold |= cpumask; + if (((rst_hold | (rst_hold >> 4)) & mcpm_mask) == mcpm_mask) { + rst_hold |= (1 << 8); + last_man = true; + } + writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4); + } else if (dcscb_use_count[cpu][cluster] == 1) { + /* + * A power_up request went ahead of us. + * Even if we do not want to shut this CPU down, + * the caller expects a certain state as if the WFI + * was aborted. So let's continue with cache cleaning. + */ + skip_wfi = true; + } else + BUG(); + + if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) { + arch_spin_unlock(&dcscb_lock); + + /* + * Flush all cache levels for this cluster. + * + * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need + * a preliminary flush here for those CPUs. At least, that's + * the theory -- without the extra flush, Linux explodes on + * RTSM (maybe not needed anymore, to be investigated). + */ + flush_cache_all(); + set_cr(get_cr() & ~CR_C); + flush_cache_all(); + + /* + * This is a harmless no-op. On platforms with a real + * outer cache this might either be needed or not, + * depending on where the outer cache sits. + */ + outer_flush_all(); + + /* Disable local coherency by clearing the ACTLR "SMP" bit: */ + set_auxcr(get_auxcr() & ~(1 << 6)); + + /* + * Disable cluster-level coherency by masking + * incoming snoops and DVM messages: + */ + disable_cci(cluster); + + __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN); + } else { + arch_spin_unlock(&dcscb_lock); + + /* + * Flush the local CPU cache. + * + * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need + * a preliminary flush here for those CPUs. At least, that's + * the theory -- without the extra flush, Linux explodes on + * RTSM (maybe not needed anymore, to be investigated). + */ + flush_cache_louis(); + set_cr(get_cr() & ~CR_C); + flush_cache_louis(); + + /* Disable local coherency by clearing the ACTLR "SMP" bit: */ + set_auxcr(get_auxcr() & ~(1 << 6)); + } + + __mcpm_cpu_down(cpu, cluster); + + /* Now we are prepared for power-down, do it: */ + if (!skip_wfi) { + dsb(); + wfi(); + } + + /* Not dead at this point? Let our caller cope. */ +} + +static const struct mcpm_platform_ops dcscb_power_ops = { + .power_up = dcscb_power_up, + .power_down = dcscb_power_down, +}; + +static void __init dcscb_usage_count_init(void) +{ + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cpu >= 4 || cluster >= 2); + dcscb_use_count[cpu][cluster] = 1; +} + +extern void dcscb_power_up_setup(unsigned int affinity_level); + +static int __init dcscb_init(void) +{ + struct device_node *node; + unsigned int cfg; + int ret; + + ret = psci_probe(); + if (!ret) { + pr_debug("psci found. Aborting native init\n"); + return -ENODEV; + } + + node = of_find_compatible_node(NULL, NULL, "arm,rtsm,dcscb"); + if (!node) + return -ENODEV; + dcscb_base= of_iomap(node, 0); + if (!dcscb_base) + return -EADDRNOTAVAIL; + cfg = readl_relaxed(dcscb_base + DCS_CFG_R); + dcscb_mcpm_cpu_mask[0] = (1 << (((cfg >> 16) >> (0 << 2)) & 0xf)) - 1; + dcscb_mcpm_cpu_mask[1] = (1 << (((cfg >> 16) >> (1 << 2)) & 0xf)) - 1; + dcscb_usage_count_init(); + + ret = mcpm_platform_register(&dcscb_power_ops); + if (!ret) + ret = mcpm_sync_init(dcscb_power_up_setup); + if (ret) { + iounmap(dcscb_base); + return ret; + } + + /* + * Future entries into the kernel can now go + * through the cluster entry vectors. + */ + vexpress_flags_set(virt_to_phys(mcpm_entry_point)); + + return 0; +} + +early_initcall(dcscb_init); diff --git a/arch/arm/mach-vexpress/dcscb_setup.S b/arch/arm/mach-vexpress/dcscb_setup.S new file mode 100644 index 000000000000..93bd13f458aa --- /dev/null +++ b/arch/arm/mach-vexpress/dcscb_setup.S @@ -0,0 +1,80 @@ +/* + * arch/arm/include/asm/dcscb_setup.S + * + * Created by: Dave Martin, 2012-06-22 + * Copyright: (C) 2012-2013 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. + */ + + +#include <linux/linkage.h> +#include <asm/mcpm.h> + + +#define SLAVE_SNOOPCTL_OFFSET 0 +#define SNOOPCTL_SNOOP_ENABLE (1 << 0) +#define SNOOPCTL_DVM_ENABLE (1 << 1) + +#define CCI_STATUS_OFFSET 0xc +#define STATUS_CHANGE_PENDING (1 << 0) + +#define CCI_SLAVE_OFFSET(n) (0x1000 + 0x1000 * (n)) + +#define RTSM_CCI_PHYS_BASE 0x2c090000 +#define RTSM_CCI_SLAVE_A15 3 +#define RTSM_CCI_SLAVE_A7 4 + +#define RTSM_CCI_A15_OFFSET CCI_SLAVE_OFFSET(RTSM_CCI_SLAVE_A15) +#define RTSM_CCI_A7_OFFSET CCI_SLAVE_OFFSET(RTSM_CCI_SLAVE_A7) + + +ENTRY(dcscb_power_up_setup) + + cmp r0, #0 @ check affinity level + beq 2f + +/* + * Enable cluster-level coherency, in preparation for turning on the MMU. + * The ACTLR SMP bit does not need to be set here, because cpu_resume() + * already restores that. + */ + + mrc p15, 0, r0, c0, c0, 5 @ MPIDR + ubfx r0, r0, #8, #4 @ cluster + + @ A15/A7 may not require explicit L2 invalidation on reset, dependent + @ on hardware integration desicions. + @ For now, this code assumes that L2 is either already invalidated, or + @ invalidation is not required. + + ldr r3, =RTSM_CCI_PHYS_BASE + RTSM_CCI_A15_OFFSET + cmp r0, #0 @ A15 cluster? + addne r3, r3, #RTSM_CCI_A7_OFFSET - RTSM_CCI_A15_OFFSET + + @ r3 now points to the correct CCI slave register block + + ldr r0, [r3, #SLAVE_SNOOPCTL_OFFSET] + orr r0, r0, #SNOOPCTL_SNOOP_ENABLE | SNOOPCTL_DVM_ENABLE + str r0, [r3, #SLAVE_SNOOPCTL_OFFSET] @ enable CCI snoops + + @ Wait for snoop control change to complete: + + ldr r3, =RTSM_CCI_PHYS_BASE + +1: ldr r0, [r3, #CCI_STATUS_OFFSET] + tst r0, #STATUS_CHANGE_PENDING + bne 1b + + dsb @ Synchronise side-effects of enabling CCI + + bx lr + +2: @ Implementation-specific local CPU setup operations should go here, + @ if any. In this case, there is nothing to do. + + bx lr + +ENDPROC(dcscb_power_up_setup) diff --git a/arch/arm/mach-vexpress/include/mach/tc2.h b/arch/arm/mach-vexpress/include/mach/tc2.h new file mode 100644 index 000000000000..d3b5a2225a0e --- /dev/null +++ b/arch/arm/mach-vexpress/include/mach/tc2.h @@ -0,0 +1,10 @@ +#ifndef __MACH_TC2_H +#define __MACH_TC2_H + +/* + * cpu and cluster limits + */ +#define TC2_MAX_CPUS 3 +#define TC2_MAX_CLUSTERS 2 + +#endif diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c index dc1ace55d557..21368ba6ca2f 100644 --- a/arch/arm/mach-vexpress/platsmp.c +++ b/arch/arm/mach-vexpress/platsmp.c @@ -12,9 +12,11 @@ #include <linux/errno.h> #include <linux/smp.h> #include <linux/io.h> +#include <linux/of.h> #include <linux/of_fdt.h> #include <linux/vexpress.h> +#include <asm/mcpm.h> #include <asm/smp_scu.h> #include <asm/mach/map.h> @@ -203,3 +205,14 @@ struct smp_operations __initdata vexpress_smp_ops = { .cpu_die = vexpress_cpu_die, #endif }; + +bool __init vexpress_smp_init_ops(void) +{ +#ifdef CONFIG_MCPM + if(of_find_compatible_node(NULL, NULL, "arm,cci")) { + mcpm_smp_set_ops(); + return true; + } +#endif + return false; +} diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c new file mode 100644 index 000000000000..f2e9959fb26c --- /dev/null +++ b/arch/arm/mach-vexpress/tc2_pm.c @@ -0,0 +1,271 @@ +/* + * arch/arm/mach-vexpress/tc2_pm.c - TC2 power management support + * + * Created by: Nicolas Pitre, October 2012 + * Copyright: (C) 2012 Linaro Limited + * + * Some portions of this file were originally written by Achin Gupta + * Copyright: (C) 2012 ARM 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/init.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/errno.h> +#include <linux/irqchip/arm-gic.h> + +#include <asm/mcpm.h> +#include <asm/proc-fns.h> +#include <asm/cacheflush.h> +#include <asm/cputype.h> +#include <asm/cp15.h> +#include <asm/psci.h> + +#include <mach/motherboard.h> +#include <mach/tc2.h> + +#include <linux/vexpress.h> +#include <linux/arm-cci.h> + +/* + * We can't use regular spinlocks. In the switcher case, it is possible + * for an outbound CPU to call power_down() after its inbound counterpart + * is already live using the same logical CPU number which trips lockdep + * debugging. + */ +static arch_spinlock_t tc2_pm_lock = __ARCH_SPIN_LOCK_UNLOCKED; + +static int tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS]; + +static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster) +{ + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + if (cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)) + return -EINVAL; + + /* + * Since this is called with IRQs enabled, and no arch_spin_lock_irq + * variant exists, we need to disable IRQs manually here. + */ + local_irq_disable(); + arch_spin_lock(&tc2_pm_lock); + + if (!tc2_pm_use_count[0][cluster] && + !tc2_pm_use_count[1][cluster] && + !tc2_pm_use_count[2][cluster]) + vexpress_spc_powerdown_enable(cluster, 0); + + tc2_pm_use_count[cpu][cluster]++; + if (tc2_pm_use_count[cpu][cluster] == 1) { + vexpress_spc_write_bxaddr_reg(cluster, cpu, + virt_to_phys(mcpm_entry_point)); + vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1); + } else if (tc2_pm_use_count[cpu][cluster] != 2) { + /* + * The only possible values are: + * 0 = CPU down + * 1 = CPU (still) up + * 2 = CPU requested to be up before it had a chance + * to actually make itself down. + * Any other value is a bug. + */ + BUG(); + } + + arch_spin_unlock(&tc2_pm_lock); + local_irq_enable(); + + return 0; +} + +static void tc2_pm_down(u64 residency) +{ + unsigned int mpidr, cpu, cluster; + bool last_man = false, skip_wfi = false; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)); + + __mcpm_cpu_going_down(cpu, cluster); + + arch_spin_lock(&tc2_pm_lock); + BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP); + tc2_pm_use_count[cpu][cluster]--; + if (tc2_pm_use_count[cpu][cluster] == 0) { + vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1); + if (!tc2_pm_use_count[0][cluster] && + !tc2_pm_use_count[1][cluster] && + !tc2_pm_use_count[2][cluster] && + (!residency || residency > 5000)) { + vexpress_spc_powerdown_enable(cluster, 1); + vexpress_spc_set_global_wakeup_intr(1); + last_man = true; + } + } else if (tc2_pm_use_count[cpu][cluster] == 1) { + /* + * A power_up request went ahead of us. + * Even if we do not want to shut this CPU down, + * the caller expects a certain state as if the WFI + * was aborted. So let's continue with cache cleaning. + */ + skip_wfi = true; + } else + BUG(); + + gic_cpu_if_down(); + + if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) { + arch_spin_unlock(&tc2_pm_lock); + + set_cr(get_cr() & ~CR_C); + flush_cache_all(); + asm volatile ("clrex"); + set_auxcr(get_auxcr() & ~(1 << 6)); + + disable_cci(cluster); + + /* + * Ensure that both C & I bits are disabled in the SCTLR + * before disabling ACE snoops. This ensures that no + * coherency traffic will originate from this cpu after + * ACE snoops are turned off. + */ + cpu_proc_fin(); + + __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN); + } else { + /* + * If last man then undo any setup done previously. + */ + if (last_man) { + vexpress_spc_powerdown_enable(cluster, 0); + vexpress_spc_set_global_wakeup_intr(0); + } + + arch_spin_unlock(&tc2_pm_lock); + + set_cr(get_cr() & ~CR_C); + flush_cache_louis(); + asm volatile ("clrex"); + set_auxcr(get_auxcr() & ~(1 << 6)); + } + + __mcpm_cpu_down(cpu, cluster); + + /* Now we are prepared for power-down, do it: */ + if (!skip_wfi) + wfi(); + + /* Not dead at this point? Let our caller cope. */ +} + +static void tc2_pm_power_down(void) +{ + tc2_pm_down(0); +} + +static void tc2_pm_suspend(u64 residency) +{ + extern void tc2_resume(void); + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + vexpress_spc_write_bxaddr_reg(cluster, cpu, + virt_to_phys(tc2_resume)); + + tc2_pm_down(residency); +} + +static void tc2_pm_powered_up(void) +{ + unsigned int mpidr, cpu, cluster; + unsigned long flags; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)); + + local_irq_save(flags); + arch_spin_lock(&tc2_pm_lock); + + if (!tc2_pm_use_count[0][cluster] && + !tc2_pm_use_count[1][cluster] && + !tc2_pm_use_count[2][cluster]) { + vexpress_spc_powerdown_enable(cluster, 0); + vexpress_spc_set_global_wakeup_intr(0); + } + + if (!tc2_pm_use_count[cpu][cluster]) + tc2_pm_use_count[cpu][cluster] = 1; + + vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 0); + vexpress_spc_write_bxaddr_reg(cluster, cpu, 0); + + arch_spin_unlock(&tc2_pm_lock); + local_irq_restore(flags); +} + +static const struct mcpm_platform_ops tc2_pm_power_ops = { + .power_up = tc2_pm_power_up, + .power_down = tc2_pm_power_down, + .suspend = tc2_pm_suspend, + .powered_up = tc2_pm_powered_up, +}; + +static void __init tc2_pm_usage_count_init(void) +{ + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)); + + tc2_pm_use_count[cpu][cluster] = 1; +} + +extern void tc2_pm_power_up_setup(unsigned int affinity_level); + +static int __init tc2_pm_init(void) +{ + int ret; + + ret = psci_probe(); + if (!ret) { + pr_debug("psci found. Aborting native init\n"); + return -ENODEV; + } + + if (!vexpress_spc_check_loaded()) + return -ENODEV; + + tc2_pm_usage_count_init(); + + ret = mcpm_platform_register(&tc2_pm_power_ops); + if (!ret) + ret = mcpm_sync_init(tc2_pm_power_up_setup); + if (!ret) + pr_info("TC2 power management initialized\n"); + return ret; +} + +early_initcall(tc2_pm_init); diff --git a/arch/arm/mach-vexpress/tc2_pm_psci.c b/arch/arm/mach-vexpress/tc2_pm_psci.c new file mode 100644 index 000000000000..5a5e4f568497 --- /dev/null +++ b/arch/arm/mach-vexpress/tc2_pm_psci.c @@ -0,0 +1,168 @@ +/* + * arch/arm/mach-vexpress/tc2_pm_psci.c - TC2 PSCI support + * + * Created by: Achin Gupta, December 2012 + * Copyright: (C) 2012 ARM Limited + * + * Some portions of this file were originally written by Nicolas Pitre + * 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/init.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/errno.h> + +#include <asm/mcpm.h> +#include <asm/proc-fns.h> +#include <asm/cacheflush.h> +#include <asm/psci.h> +#include <asm/atomic.h> +#include <asm/cputype.h> +#include <asm/cp15.h> + +#include <mach/motherboard.h> +#include <mach/tc2.h> + +#include <linux/vexpress.h> + +/* + * Platform specific state id understood by the firmware and used to + * program the power controller + */ +#define PSCI_POWER_STATE_ID 0 + +static atomic_t tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS]; + +static int tc2_pm_psci_power_up(unsigned int cpu, unsigned int cluster) +{ + unsigned int mpidr = (cluster << 8) | cpu; + int ret = 0; + + BUG_ON(!psci_ops.cpu_on); + + switch (atomic_inc_return(&tc2_pm_use_count[cpu][cluster])) { + case 1: + /* + * This is a request to power up a cpu that linux thinks has + * been powered down. Retries are needed if the firmware has + * seen the power down request as yet. + */ + do + ret = psci_ops.cpu_on(mpidr, + virt_to_phys(mcpm_entry_point)); + while (ret == -EAGAIN); + + return ret; + case 2: + /* This power up request has overtaken a power down request */ + return ret; + default: + /* Any other value is a bug */ + BUG(); + } +} + +static void tc2_pm_psci_power_down(void) +{ + struct psci_power_state power_state; + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + BUG_ON(!psci_ops.cpu_off); + + switch (atomic_dec_return(&tc2_pm_use_count[cpu][cluster])) { + case 1: + /* + * Overtaken by a power up. Flush caches, exit coherency, + * return & fake a reset + */ + set_cr(get_cr() & ~CR_C); + + flush_cache_louis(); + + asm volatile ("clrex"); + set_auxcr(get_auxcr() & ~(1 << 6)); + + return; + case 0: + /* A normal request to possibly power down the cluster */ + power_state.id = PSCI_POWER_STATE_ID; + power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN; + power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1; + + psci_ops.cpu_off(power_state); + + /* On success this function never returns */ + default: + /* Any other value is a bug */ + BUG(); + } +} + +static void tc2_pm_psci_suspend(u64 unused) +{ + struct psci_power_state power_state; + + BUG_ON(!psci_ops.cpu_suspend); + + /* On TC2 always attempt to power down the cluster */ + power_state.id = PSCI_POWER_STATE_ID; + power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN; + power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1; + + psci_ops.cpu_suspend(power_state, virt_to_phys(mcpm_entry_point)); + + /* On success this function never returns */ + BUG(); +} + +static const struct mcpm_platform_ops tc2_pm_power_ops = { + .power_up = tc2_pm_psci_power_up, + .power_down = tc2_pm_psci_power_down, + .suspend = tc2_pm_psci_suspend, +}; + +static void __init tc2_pm_usage_count_init(void) +{ + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)); + + atomic_set(&tc2_pm_use_count[cpu][cluster], 1); +} + +static int __init tc2_pm_psci_init(void) +{ + int ret; + + ret = psci_probe(); + if (ret) { + pr_debug("psci not found. Aborting psci init\n"); + return -ENODEV; + } + + tc2_pm_usage_count_init(); + + ret = mcpm_platform_register(&tc2_pm_power_ops); + if (!ret) + ret = mcpm_sync_init(NULL); + if (!ret) + pr_info("TC2 power management initialized\n"); + return ret; +} + +early_initcall(tc2_pm_psci_init); diff --git a/arch/arm/mach-vexpress/tc2_pm_setup.S b/arch/arm/mach-vexpress/tc2_pm_setup.S new file mode 100644 index 000000000000..4728f83731a4 --- /dev/null +++ b/arch/arm/mach-vexpress/tc2_pm_setup.S @@ -0,0 +1,102 @@ +/* + * arch/arm/include/asm/tc2_pm_setup.S + * + * Created by: Nicolas Pitre, October 2012 + ( (based on dcscb_setup.S by Dave Martin) + * 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/linkage.h> +#include <asm/mcpm.h> + + +#define SPC_PHYS_BASE 0x7FFF0000 +#define SPC_WAKE_INT_STAT 0xb2c + +#define SNOOP_CTL_A15 0x404 +#define SNOOP_CTL_A7 0x504 + +#define A15_SNOOP_MASK (0x3 << 7) +#define A7_SNOOP_MASK (0x1 << 13) + +#define A15_BX_ADDR0 0xB68 + + +#define CCI_PHYS_BASE 0x2c090000 + +#define SLAVE_SNOOPCTL_OFFSET 0 +#define SNOOPCTL_SNOOP_ENABLE (1 << 0) +#define SNOOPCTL_DVM_ENABLE (1 << 1) + +#define CCI_STATUS_OFFSET 0xc +#define STATUS_CHANGE_PENDING (1 << 0) + +#define CCI_SLAVE_OFFSET(n) (0x1000 + 0x1000 * (n)) +#define CCI_SLAVE_A15 3 +#define CCI_SLAVE_A7 4 +#define CCI_A15_OFFSET CCI_SLAVE_OFFSET(CCI_SLAVE_A15) +#define CCI_A7_OFFSET CCI_SLAVE_OFFSET(CCI_SLAVE_A7) + + +ENTRY(tc2_resume) + mrc p15, 0, r0, c0, c0, 5 + ubfx r1, r0, #0, #4 @ r1 = cpu + ubfx r2, r0, #8, #4 @ r2 = cluster + add r1, r1, r2, lsl #2 @ r1 = index of CPU in WAKE_INT_STAT + ldr r3, =SPC_PHYS_BASE + SPC_WAKE_INT_STAT + ldr r3, [r3] + lsr r3, r1 + tst r3, #1 + wfieq @ if no pending IRQ reenters wfi + b mcpm_entry_point +ENDPROC(tc2_resume) + +/* + * Enable cluster-level coherency, in preparation for turning on the MMU. + * The ACTLR SMP bit does not need to be set here, because cpu_resume() + * already restores that. + */ + +ENTRY(tc2_pm_power_up_setup) + + cmp r0, #0 + beq 2f + + @ Enable CCI snoops + mrc p15, 0, r0, c0, c0, 5 @ MPIDR + ubfx r0, r0, #8, #4 @ cluster + ldr r3, =CCI_PHYS_BASE + CCI_A15_OFFSET + cmp r0, #0 @ A15 cluster? + addne r3, r3, #CCI_A7_OFFSET - CCI_A15_OFFSET + + @ r3 now points to the correct CCI slave register block + ldr r0, [r3, #SLAVE_SNOOPCTL_OFFSET] + orr r0, r0, #SNOOPCTL_SNOOP_ENABLE | SNOOPCTL_DVM_ENABLE + str r0, [r3, #SLAVE_SNOOPCTL_OFFSET] @ enable CCI snoops + + @ Wait for snoop control change to complete: + ldr r3, =CCI_PHYS_BASE +1: ldr r0, [r3, #CCI_STATUS_OFFSET] + tst r0, #STATUS_CHANGE_PENDING + bne 1b + + bx lr + +2: @ Clear the BX addr register + ldr r3, =SPC_PHYS_BASE + A15_BX_ADDR0 + mrc p15, 0, r0, c0, c0, 5 @ MPIDR + ubfx r1, r0, #8, #4 @ cluster + ubfx r0, r0, #0, #4 @ cpu + add r3, r3, r1, lsl #4 + mov r1, #0 + str r1, [r3, r0, lsl #2] + dsb + + bx lr + +ENDPROC(tc2_pm_power_up_setup) diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 915683cb67d6..772b7a179dde 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -8,6 +8,7 @@ #include <linux/smp.h> #include <linux/init.h> #include <linux/irqchip.h> +#include <linux/memblock.h> #include <linux/of_address.h> #include <linux/of_fdt.h> #include <linux/of_irq.h> @@ -377,6 +378,31 @@ MACHINE_START(VEXPRESS, "ARM-Versatile Express") .restart = vexpress_restart, MACHINE_END +static void __init v2m_dt_hdlcd_init(void) +{ + struct device_node *node; + int len, na, ns; + const __be32 *prop; + phys_addr_t fb_base, fb_size; + + node = of_find_compatible_node(NULL, NULL, "arm,hdlcd"); + if (!node) + return; + + na = of_n_addr_cells(node); + ns = of_n_size_cells(node); + + prop = of_get_property(node, "framebuffer", &len); + if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop))) + return; + + fb_base = of_read_number(prop, na); + fb_size = of_read_number(prop + na, ns); + + if (WARN_ON(memblock_remove(fb_base, fb_size))) + return; +}; + static struct map_desc v2m_rs1_io_desc __initdata = { .virtual = V2M_PERIPH, .pfn = __phys_to_pfn(0x1c000000), @@ -427,6 +453,8 @@ void __init v2m_dt_init_early(void) pr_warning("vexpress: DT HBI (%x) is not matching " "hardware (%x)!\n", dt_hbi, hbi); } + + v2m_dt_hdlcd_init(); } static void __init v2m_dt_timer_init(void) @@ -476,6 +504,7 @@ static const char * const v2m_dt_match[] __initconst = { DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express") .dt_compat = v2m_dt_match, .smp = smp_ops(vexpress_smp_ops), + .smp_init = smp_init_ops(vexpress_smp_init_ops), .map_io = v2m_dt_map_io, .init_early = v2m_dt_init_early, .init_irq = irqchip_init, diff --git a/arch/arm/mach-virt/platsmp.c b/arch/arm/mach-virt/platsmp.c index 8badaabe70a1..f4143f5bfa5b 100644 --- a/arch/arm/mach-virt/platsmp.c +++ b/arch/arm/mach-virt/platsmp.c @@ -21,8 +21,6 @@ #include <linux/smp.h> #include <linux/of.h> -#include <linux/irqchip/arm-gic.h> - #include <asm/psci.h> #include <asm/smp_plat.h> @@ -45,14 +43,8 @@ static int __cpuinit virt_boot_secondary(unsigned int cpu, return -ENODEV; } -static void __cpuinit virt_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - struct smp_operations __initdata virt_smp_ops = { .smp_init_cpus = virt_smp_init_cpus, .smp_prepare_cpus = virt_smp_prepare_cpus, - .smp_secondary_init = virt_secondary_init, .smp_boot_secondary = virt_boot_secondary, }; diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 4045c4931a30..35955b54944c 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -397,6 +397,13 @@ config CPU_V7 select CPU_PABRT_V7 select CPU_TLB_V7 if MMU +config CPU_THUMBONLY + bool + # There are no CPUs available with MMU that don't implement an ARM ISA: + depends on !MMU + help + Select this if your CPU doesn't support the 32 bit ARM instructions. + # Figure out what processor architecture version we should be using. # This defines the compiler instruction set which depends on the machine type. config CPU_32v3 @@ -605,7 +612,7 @@ config ARCH_DMA_ADDR_T_64BIT bool config ARM_THUMB - bool "Support Thumb user binaries" + bool "Support Thumb user binaries" if !CPU_THUMBONLY depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON default y help diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index db26e2e543f4..6f4585b89078 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -961,12 +961,14 @@ static int __init alignment_init(void) return -ENOMEM; #endif +#ifdef CONFIG_CPU_CP15 if (cpu_is_v6_unaligned()) { cr_alignment &= ~CR_A; cr_no_alignment &= ~CR_A; set_cr(cr_alignment); ai_usermode = safe_usermode(ai_usermode, false); } +#endif hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN, "alignment exception"); diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 5dbf13f954f6..e207aa5f846f 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -446,8 +446,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr, if (pud_none(*pud_k)) goto bad_area; - if (!pud_present(*pud)) + if (!pud_present(*pud)) { set_pud(pud, *pud_k); + /* + * There is a small window during free_pgtables() where the + * user *pud entry is 0 but the TLB has not been invalidated + * and we get a level 2 (pmd) translation fault caused by the + * intermediate TLB caching of the old level 1 (pud) entry. + */ + flush_tlb_kernel_page(addr); + } pmd = pmd_offset(pud, addr); pmd_k = pmd_offset(pud_k, addr); @@ -470,8 +478,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, #endif if (pmd_none(pmd_k[index])) goto bad_area; + if (!pmd_present(pmd[index])) + copy_pmd(pmd, pmd_k); - copy_pmd(pmd, pmd_k); return 0; bad_area: diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index a3da603504d8..76a30333ec6e 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -113,6 +113,7 @@ static struct cachepolicy cache_policies[] __initdata = { } }; +#ifdef CONFIG_CPU_CP15 /* * These are useful for identifying cache coherency * problems by allowing the cache or the cache and @@ -211,6 +212,22 @@ void adjust_cr(unsigned long mask, unsigned long set) } #endif +#else /* ifdef CONFIG_CPU_CP15 */ + +static int __init early_cachepolicy(char *p) +{ + pr_warning("cachepolicy kernel parameter not supported without cp15\n"); +} +early_param("cachepolicy", early_cachepolicy); + +static int __init noalign_setup(char *__unused) +{ + pr_warning("noalign kernel parameter not supported without cp15\n"); +} +__setup("noalign", noalign_setup); + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + #define PROT_PTE_DEVICE L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index 78f520bc0e99..2f76880060d4 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -110,7 +110,9 @@ ENTRY(cpu_v7_set_pte_ext) ARM( str r3, [r0, #2048]! ) THUMB( add r0, r0, #2048 ) THUMB( str r3, [r0] ) - mcr p15, 0, r0, c7, c10, 1 @ flush_pte + mrc p15, 0, r3, c0, c1, 7 @ read ID_MMFR3 + tst r3, #0xf << 20 @ check the coherent walk bits + mcreq p15, 0, r0, c7, c10, 1 @ clean D-cache to PoU #endif mov pc, lr ENDPROC(cpu_v7_set_pte_ext) diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 6ffd78c0f9ab..2098e026632f 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -73,7 +73,9 @@ ENTRY(cpu_v7_set_pte_ext) tst r3, #1 << (55 - 32) @ L_PTE_DIRTY orreq r2, #L_PTE_RDONLY 1: strd r2, r3, [r0] - mcr p15, 0, r0, c7, c10, 1 @ flush_pte + mrc p15, 0, r3, c0, c1, 7 @ read ID_MMFR3 + tst r3, #0xf << 20 @ check the coherent walk bits + mcreq p15, 0, r0, c7, c10, 1 @ clean D-cache to PoU #endif mov pc, lr ENDPROC(cpu_v7_set_pte_ext) diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index 2d4b6414609f..7bb961918c8b 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -373,7 +373,7 @@ static struct resource orion_ge10_shared_resources[] = { static struct platform_device orion_ge10_shared = { .name = MV643XX_ETH_SHARED_NAME, - .id = 1, + .id = 2, .dev = { .platform_data = &orion_ge10_shared_data, }, @@ -388,8 +388,8 @@ static struct resource orion_ge10_resources[] = { static struct platform_device orion_ge10 = { .name = MV643XX_ETH_NAME, - .id = 1, - .num_resources = 2, + .id = 2, + .num_resources = 1, .resource = orion_ge10_resources, .dev = { .coherent_dma_mask = DMA_BIT_MASK(32), @@ -425,7 +425,7 @@ static struct resource orion_ge11_shared_resources[] = { static struct platform_device orion_ge11_shared = { .name = MV643XX_ETH_SHARED_NAME, - .id = 1, + .id = 3, .dev = { .platform_data = &orion_ge11_shared_data, }, @@ -440,8 +440,8 @@ static struct resource orion_ge11_resources[] = { static struct platform_device orion_ge11 = { .name = MV643XX_ETH_NAME, - .id = 1, - .num_resources = 2, + .id = 3, + .num_resources = 1, .resource = orion_ge11_resources, .dev = { .coherent_dma_mask = DMA_BIT_MASK(32), diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c index f980cf3d2baa..5d205e74e495 100644 --- a/arch/arm/plat-samsung/irq-vic-timer.c +++ b/arch/arm/plat-samsung/irq-vic-timer.c @@ -16,6 +16,7 @@ #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> #include <linux/io.h> #include <mach/map.h> @@ -23,8 +24,6 @@ #include <plat/irq-vic-timer.h> #include <plat/regs-timer.h> -#include <asm/mach/irq.h> - static void s3c_irq_demux_vic_timer(unsigned int irq, struct irq_desc *desc) { struct irq_chip *chip = irq_get_chip(irq); diff --git a/arch/arm/plat-samsung/s5p-irq-gpioint.c b/arch/arm/plat-samsung/s5p-irq-gpioint.c index bae56131a50a..fafdb059043a 100644 --- a/arch/arm/plat-samsung/s5p-irq-gpioint.c +++ b/arch/arm/plat-samsung/s5p-irq-gpioint.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> #include <linux/io.h> #include <linux/gpio.h> #include <linux/slab.h> @@ -22,8 +23,6 @@ #include <plat/gpio-core.h> #include <plat/gpio-cfg.h> -#include <asm/mach/irq.h> - #define GPIO_BASE(chip) ((void __iomem *)((unsigned long)((chip)->base) & 0xFFFFF000u)) #define CON_OFFSET 0x700 diff --git a/arch/arm/plat-samsung/setup-mipiphy.c b/arch/arm/plat-samsung/setup-mipiphy.c index 147459327601..66df315990a7 100644 --- a/arch/arm/plat-samsung/setup-mipiphy.c +++ b/arch/arm/plat-samsung/setup-mipiphy.c @@ -8,6 +8,7 @@ * published by the Free Software Foundation. */ +#include <linux/export.h> #include <linux/kernel.h> #include <linux/platform_device.h> #include <linux/io.h> @@ -50,8 +51,10 @@ int s5p_csis_phy_enable(int id, bool on) { return __s5p_mipi_phy_control(id, on, S5P_MIPI_DPHY_SRESETN); } +EXPORT_SYMBOL(s5p_csis_phy_enable); int s5p_dsim_phy_enable(struct platform_device *pdev, bool on) { return __s5p_mipi_phy_control(pdev->id, on, S5P_MIPI_DPHY_MRESETN); } +EXPORT_SYMBOL(s5p_dsim_phy_enable); diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c index f2ac15561778..1e1b2d769748 100644 --- a/arch/arm/plat-versatile/platsmp.c +++ b/arch/arm/plat-versatile/platsmp.c @@ -14,7 +14,6 @@ #include <linux/device.h> #include <linux/jiffies.h> #include <linux/smp.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -37,13 +36,6 @@ static DEFINE_SPINLOCK(boot_lock); void __cpuinit versatile_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 8dc0605a9ce9..99ce18915a89 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -239,7 +239,7 @@ static int __init xen_init_events(void) xen_init_IRQ(); if (request_percpu_irq(xen_events_irq, xen_arm_callback, - "events", xen_vcpu)) { + "events", &xen_vcpu)) { pr_err("Error requesting IRQ %d\n", xen_events_irq); return -EINVAL; } |