diff options
Diffstat (limited to 'arch')
87 files changed, 932 insertions, 308 deletions
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S index 99c1047..9c548c7 100644 --- a/arch/arc/lib/strchr-700.S +++ b/arch/arc/lib/strchr-700.S @@ -39,9 +39,18 @@ ARC_ENTRY strchr ld.a r2,[r0,4] sub r12,r6,r7 bic r12,r12,r6 +#ifdef __LITTLE_ENDIAN__ and r7,r12,r4 breq r7,0,.Loop ; For speed, we want this branch to be unaligned. b .Lfound_char ; Likewise this one. +#else + and r12,r12,r4 + breq r12,0,.Loop ; For speed, we want this branch to be unaligned. + lsr_s r12,r12,7 + bic r2,r7,r6 + b.d .Lfound_char_b + and_s r2,r2,r12 +#endif ; /* We require this code address to be unaligned for speed... */ .Laligned: ld_s r2,[r0] @@ -95,6 +104,7 @@ ARC_ENTRY strchr lsr r7,r7,7 bic r2,r7,r6 +.Lfound_char_b: norm r2,r2 sub_s r0,r0,4 asr_s r2,r2,3 diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 43594d5..053c78c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -52,6 +52,7 @@ config ARM select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 + select IRQ_FORCED_THREADING select KTIME_SCALAR select PERF_USE_VMALLOC select RTC_LIB @@ -1372,6 +1373,15 @@ config ARM_ERRATA_798181 which sends an IPI to the CPUs that are running the same ASID as the one being invalidated. +config ARM_ERRATA_773022 + bool "ARM errata: incorrect instructions may be executed from loop buffer" + depends on CPU_V7 + help + This option enables the workaround for the 773022 Cortex-A15 + (up to r0p4) erratum. In certain rare sequences of code, the + loop buffer may deliver incorrect instructions. This + workaround disables the loop buffer to avoid the erratum. + endmenu source "arch/arm/common/Kconfig" @@ -1613,13 +1623,49 @@ config ARCH_NR_GPIO source kernel/Kconfig.preempt -config HZ +config HZ_FIXED int default 200 if ARCH_EBSA110 || ARCH_S3C24XX || ARCH_S5P64X0 || \ ARCH_S5PV210 || ARCH_EXYNOS4 default AT91_TIMER_HZ if ARCH_AT91 default SHMOBILE_TIMER_HZ if ARCH_SHMOBILE - default 100 + +choice + depends on !HZ_FIXED + prompt "Timer frequency" + +config HZ_100 + bool "100 Hz" + +config HZ_200 + bool "200 Hz" + +config HZ_250 + bool "250 Hz" + +config HZ_300 + bool "300 Hz" + +config HZ_500 + bool "500 Hz" + +config HZ_1000 + bool "1000 Hz" + +endchoice + +config HZ + int + default HZ_FIXED if HZ_FIXED + default 100 if HZ_100 + default 200 if HZ_200 + default 250 if HZ_250 + default 300 if HZ_300 + default 500 if HZ_500 + default 1000 + +config SCHED_HRTICK + def_bool HIGH_RES_TIMERS config SCHED_HRTICK def_bool HIGH_RES_TIMERS @@ -1756,6 +1802,9 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y depends on ARM_LPAE +config ARCH_WANT_GENERAL_HUGETLB + def_bool y + source "mm/Kconfig" config FORCE_MAX_ZONEORDER @@ -2175,6 +2224,13 @@ config NEON Say Y to include support code for NEON, the ARMv7 Advanced SIMD Extension. +config KERNEL_MODE_NEON + bool "Support for NEON in kernel mode" + default n + depends on NEON + help + Say Y to include support for NEON in kernel mode. + endmenu menu "Userspace binary formats" @@ -2199,7 +2255,7 @@ source "kernel/power/Kconfig" config ARCH_SUSPEND_POSSIBLE depends on !ARCH_S5PC100 - depends on CPU_ARM920T || CPU_ARM926T || CPU_SA1100 || \ + depends on CPU_ARM920T || CPU_ARM926T || CPU_FEROCEON || CPU_SA1100 || \ CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE || CPU_MOHAWK def_bool y diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index d59b70c..3d77dbe 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -14,11 +14,11 @@ compatible = "atmel,at91sam9n12ek", "atmel,at91sam9n12", "atmel,at91sam9"; chosen { - bootargs = "mem=128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2"; + bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2"; }; memory { - reg = <0x20000000 0x10000000>; + reg = <0x20000000 0x8000000>; }; clocks { diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi index b753855..49e3c45 100644 --- a/arch/arm/boot/dts/at91sam9x5ek.dtsi +++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi @@ -94,8 +94,9 @@ usb0: ohci@00600000 { status = "okay"; - num-ports = <2>; - atmel,vbus-gpio = <&pioD 19 GPIO_ACTIVE_LOW + num-ports = <3>; + atmel,vbus-gpio = <0 /* &pioD 18 GPIO_ACTIVE_LOW *//* Activate to have access to port A */ + &pioD 19 GPIO_ACTIVE_LOW &pioD 20 GPIO_ACTIVE_LOW >; }; diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts index 365760b..40e6fb2 100644 --- a/arch/arm/boot/dts/tegra20-seaboard.dts +++ b/arch/arm/boot/dts/tegra20-seaboard.dts @@ -830,6 +830,8 @@ regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&gpio 24 0>; /* PD0 */ + regulator-always-on; + regulator-boot-on; }; }; diff --git a/arch/arm/boot/dts/tegra20-trimslice.dts b/arch/arm/boot/dts/tegra20-trimslice.dts index ed4b901..37c93d3 100644 --- a/arch/arm/boot/dts/tegra20-trimslice.dts +++ b/arch/arm/boot/dts/tegra20-trimslice.dts @@ -412,6 +412,8 @@ regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&gpio 170 0>; /* PV2 */ + regulator-always-on; + regulator-boot-on; }; }; diff --git a/arch/arm/boot/dts/tegra20-whistler.dts b/arch/arm/boot/dts/tegra20-whistler.dts index ab67c94..a3d0eba 100644 --- a/arch/arm/boot/dts/tegra20-whistler.dts +++ b/arch/arm/boot/dts/tegra20-whistler.dts @@ -588,6 +588,8 @@ regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&tca6416 0 0>; /* GPIO_PMU0 */ + regulator-always-on; + regulator-boot-on; }; vbus3_reg: regulator@3 { @@ -598,6 +600,8 @@ regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&tca6416 1 0>; /* GPIO_PMU1 */ + regulator-always-on; + regulator-boot-on; }; }; diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S index 80f033614..39c96df 100644 --- a/arch/arm/common/mcpm_head.S +++ b/arch/arm/common/mcpm_head.S @@ -151,7 +151,7 @@ mcpm_setup_leave: mov r0, #INBOUND_NOT_COMING_UP strb r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND] - dsb + dsb st sev mov r0, r11 diff --git a/arch/arm/common/vlock.S b/arch/arm/common/vlock.S index ff19858..8b7df28 100644 --- a/arch/arm/common/vlock.S +++ b/arch/arm/common/vlock.S @@ -42,7 +42,7 @@ dmb mov \rscratch, #0 strb \rscratch, [\rbase, \rcpu] - dsb + dsb st sev .endm @@ -102,7 +102,7 @@ ENTRY(vlock_unlock) dmb mov r1, #VLOCK_OWNER_NONE strb r1, [r0, #VLOCK_OWNER_OFFSET] - dsb + dsb st sev bx lr ENDPROC(vlock_unlock) diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index a5fef71..fcc1b5b 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -220,9 +220,9 @@ #ifdef CONFIG_SMP #if __LINUX_ARM_ARCH__ >= 7 .ifeqs "\mode","arm" - ALT_SMP(dmb) + ALT_SMP(dmb ish) .else - ALT_SMP(W(dmb)) + ALT_SMP(W(dmb) ish) .endif #elif __LINUX_ARM_ARCH__ == 6 ALT_SMP(mcr p15, 0, r0, c7, c10, 5) @ dmb diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h index 8dcd9c7..60f15e2 100644 --- a/arch/arm/include/asm/barrier.h +++ b/arch/arm/include/asm/barrier.h @@ -14,27 +14,27 @@ #endif #if __LINUX_ARM_ARCH__ >= 7 -#define isb() __asm__ __volatile__ ("isb" : : : "memory") -#define dsb() __asm__ __volatile__ ("dsb" : : : "memory") -#define dmb() __asm__ __volatile__ ("dmb" : : : "memory") +#define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory") +#define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory") +#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory") #elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6 -#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \ +#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \ : : "r" (0) : "memory") -#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ +#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ : : "r" (0) : "memory") -#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \ +#define dmb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \ : : "r" (0) : "memory") #elif defined(CONFIG_CPU_FA526) -#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \ +#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \ : : "r" (0) : "memory") -#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ +#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ : : "r" (0) : "memory") -#define dmb() __asm__ __volatile__ ("" : : : "memory") +#define dmb(x) __asm__ __volatile__ ("" : : : "memory") #else -#define isb() __asm__ __volatile__ ("" : : : "memory") -#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ +#define isb(x) __asm__ __volatile__ ("" : : : "memory") +#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ : : "r" (0) : "memory") -#define dmb() __asm__ __volatile__ ("" : : : "memory") +#define dmb(x) __asm__ __volatile__ ("" : : : "memory") #endif #ifdef CONFIG_ARCH_HAS_BARRIERS @@ -42,7 +42,7 @@ #elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP) #define mb() do { dsb(); outer_sync(); } while (0) #define rmb() dsb() -#define wmb() mb() +#define wmb() do { dsb(st); outer_sync(); } while (0) #else #define mb() barrier() #define rmb() barrier() @@ -54,9 +54,9 @@ #define smp_rmb() barrier() #define smp_wmb() barrier() #else -#define smp_mb() dmb() -#define smp_rmb() dmb() -#define smp_wmb() dmb() +#define smp_mb() dmb(ish) +#define smp_rmb() smp_mb() +#define smp_wmb() dmb(ishst) #endif #define read_barrier_depends() do { } while(0) diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 17d0ae8..15f2d5b 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -268,8 +268,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr * Harvard caches are synchronised for the user space address range. * This is used for the ARM private sys_cacheflush system call. */ -#define flush_cache_user_range(start,end) \ - __cpuc_coherent_user_range((start) & PAGE_MASK, PAGE_ALIGN(end)) +#define flush_cache_user_range(s,e) __cpuc_coherent_user_range(s,e) /* * Perform necessary cache operations to ensure that data previously @@ -352,7 +351,7 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) * set_pte_at() called from vmap_pte_range() does not * have a DSB after cleaning the cache line. */ - dsb(); + dsb(ishst); } static inline void flush_cache_vunmap(unsigned long start, unsigned long end) diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 441efc4..69b879a 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -65,12 +65,12 @@ struct machine_desc { /* * Current machine - only accessible during boot. */ -extern struct machine_desc *machine_desc; +extern const struct machine_desc *machine_desc; /* * Machine type table - also only accessible during boot */ -extern struct machine_desc __arch_info_begin[], __arch_info_end[]; +extern const struct machine_desc __arch_info_begin[], __arch_info_end[]; #define for_each_machine_desc(p) \ for (p = __arch_info_begin; p < __arch_info_end; p++) diff --git a/arch/arm/include/asm/memblock.h b/arch/arm/include/asm/memblock.h index 00ca5f9..c2f5102 100644 --- a/arch/arm/include/asm/memblock.h +++ b/arch/arm/include/asm/memblock.h @@ -4,8 +4,7 @@ struct meminfo; struct machine_desc; -extern void arm_memblock_init(struct meminfo *, struct machine_desc *); - +void arm_memblock_init(struct meminfo *, const struct machine_desc *); phys_addr_t arm_memblock_steal(phys_addr_t size, phys_addr_t align); #endif diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index 0d3a28d..ed690c4 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -12,6 +12,8 @@ enum { ARM_SEC_CORE, ARM_SEC_EXIT, ARM_SEC_DEVEXIT, + ARM_SEC_HOT, + ARM_SEC_UNLIKELY, ARM_SEC_MAX, }; diff --git a/arch/arm/include/asm/neon.h b/arch/arm/include/asm/neon.h new file mode 100644 index 0000000..8f730fe --- /dev/null +++ b/arch/arm/include/asm/neon.h @@ -0,0 +1,36 @@ +/* + * linux/arch/arm/include/asm/neon.h + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * 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 <asm/hwcap.h> + +#define cpu_has_neon() (!!(elf_hwcap & HWCAP_NEON)) + +#ifdef __ARM_NEON__ + +/* + * If you are affected by the BUILD_BUG below, it probably means that you are + * using NEON code /and/ calling the kernel_neon_begin() function from the same + * compilation unit. To prevent issues that may arise from GCC reordering or + * generating(1) NEON instructions outside of these begin/end functions, the + * only supported way of using NEON code in the kernel is by isolating it in a + * separate compilation unit, and calling it from another unit from inside a + * kernel_neon_begin/kernel_neon_end pair. + * + * (1) Current GCC (4.7) might generate NEON instructions at O3 level if + * -mpfu=neon is set. + */ + +#define kernel_neon_begin() \ + BUILD_BUG_ON_MSG(1, "kernel_neon_begin() called from NEON code") + +#else +void kernel_neon_begin(void); +#endif +void kernel_neon_end(void); diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 04aeb02..be956db 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -100,7 +100,7 @@ extern pgprot_t pgprot_s2_device; #define PAGE_HYP _MOD_PROT(pgprot_kernel, L_PTE_HYP) #define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP) #define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY) -#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_USER | L_PTE_S2_RDONLY) +#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDWR) #define __PAGE_NONE __pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE) #define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN) diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h index a219227..4a2985e 100644 --- a/arch/arm/include/asm/prom.h +++ b/arch/arm/include/asm/prom.h @@ -15,13 +15,13 @@ #ifdef CONFIG_OF -extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys); +extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys); extern void arm_dt_memblock_reserve(void); extern void __init arm_dt_init_cpu_maps(void); #else /* CONFIG_OF */ -static inline struct machine_desc *setup_machine_fdt(unsigned int dt_phys) +static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys) { return NULL; } diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index b07c09e..4f2c280 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -46,7 +46,7 @@ static inline void dsb_sev(void) { #if __LINUX_ARM_ARCH__ >= 7 __asm__ __volatile__ ( - "dsb\n" + "dsb ishst\n" SEV ); #else diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h index fa09e6b..c99e259 100644 --- a/arch/arm/include/asm/switch_to.h +++ b/arch/arm/include/asm/switch_to.h @@ -4,6 +4,16 @@ #include <linux/thread_info.h> /* + * For v7 SMP cores running a preemptible kernel we may be pre-empted + * during a TLB maintenance operation, so execute an inner-shareable dsb + * to ensure that the maintenance completes in case we migrate to another + * CPU. + */ +#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7) +#define finish_arch_switch(prev) dsb(ish) +#endif + +/* * switch_to(prev, next) should switch from task `prev' to `next' * `prev' will never be the same as `next'. schedule() itself * contains the memory barrier to tell GCC not to cache `current'. diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 2b8114f..df5e13d 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -43,6 +43,16 @@ struct cpu_context_save { __u32 extra[2]; /* Xscale 'acc' register, etc */ }; +struct arm_restart_block { + union { + /* For user cache flushing */ + struct { + unsigned long start; + unsigned long end; + } cache; + }; +}; + /* * low level task data that entry.S needs immediate access to. * __switch_to() assumes cpu_context follows immediately after cpu_domain. @@ -68,6 +78,7 @@ struct thread_info { unsigned long thumbee_state; /* ThumbEE Handler Base register */ #endif struct restart_block restart_block; + struct arm_restart_block arm_restart_block; }; #define INIT_THREAD_INFO(tsk) \ diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index f467e9b..3896026 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -319,67 +319,110 @@ extern struct cpu_tlb_fns cpu_tlb; #define tlb_op(f, regs, arg) __tlb_op(f, "p15, 0, %0, " regs, arg) #define tlb_l2_op(f, regs, arg) __tlb_op(f, "p15, 1, %0, " regs, arg) -static inline void local_flush_tlb_all(void) +static inline void __local_flush_tlb_all(void) { const int zero = 0; const unsigned int __tlb_flag = __cpu_tlb_flags; - if (tlb_flag(TLB_WB)) - dsb(); - tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero); - tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero); +} + +static inline void local_flush_tlb_all(void) +{ + const int zero = 0; + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (tlb_flag(TLB_WB)) + dsb(nshst); + + __local_flush_tlb_all(); + tlb_op(TLB_V7_UIS_FULL, "c8, c7, 0", zero); if (tlb_flag(TLB_BARRIER)) { - dsb(); + dsb(nsh); isb(); } } -static inline void local_flush_tlb_mm(struct mm_struct *mm) +static inline void __flush_tlb_all(void) { const int zero = 0; - const int asid = ASID(mm); const unsigned int __tlb_flag = __cpu_tlb_flags; if (tlb_flag(TLB_WB)) - dsb(); + dsb(ishst); + + __local_flush_tlb_all(); + tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero); + + if (tlb_flag(TLB_BARRIER)) { + dsb(ish); + isb(); + } +} + +static inline void __local_flush_tlb_mm(struct mm_struct *mm) +{ + const int zero = 0; + const int asid = ASID(mm); + const unsigned int __tlb_flag = __cpu_tlb_flags; if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { - if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { + if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) { tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero); } - put_cpu(); } tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid); tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid); tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid); +} + +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + const int asid = ASID(mm); + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (tlb_flag(TLB_WB)) + dsb(nshst); + + __local_flush_tlb_mm(mm); + tlb_op(TLB_V7_UIS_ASID, "c8, c7, 2", asid); + + if (tlb_flag(TLB_BARRIER)) + dsb(nsh); +} + +static inline void __flush_tlb_mm(struct mm_struct *mm) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (tlb_flag(TLB_WB)) + dsb(ishst); + + __local_flush_tlb_mm(mm); #ifdef CONFIG_ARM_ERRATA_720789 - tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero); + tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", 0); #else - tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid); + tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", ASID(mm)); #endif if (tlb_flag(TLB_BARRIER)) - dsb(); + dsb(ish); } static inline void -local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { const int zero = 0; const unsigned int __tlb_flag = __cpu_tlb_flags; uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm); - if (tlb_flag(TLB_WB)) - dsb(); - if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr); @@ -392,6 +435,36 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr); tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr); tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr); +} + +static inline void +local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm); + + if (tlb_flag(TLB_WB)) + dsb(nshst); + + __local_flush_tlb_page(vma, uaddr); + tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", uaddr); + + if (tlb_flag(TLB_BARRIER)) + dsb(nsh); +} + +static inline void +__flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm); + + if (tlb_flag(TLB_WB)) + dsb(ishst); + + __local_flush_tlb_page(vma, uaddr); #ifdef CONFIG_ARM_ERRATA_720789 tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK); #else @@ -399,19 +472,14 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) #endif if (tlb_flag(TLB_BARRIER)) - dsb(); + dsb(ish); } -static inline void local_flush_tlb_kernel_page(unsigned long kaddr) +static inline void __local_flush_tlb_kernel_page(unsigned long kaddr) { const int zero = 0; const unsigned int __tlb_flag = __cpu_tlb_flags; - kaddr &= PAGE_MASK; - - if (tlb_flag(TLB_WB)) - dsb(); - tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr); @@ -421,26 +489,75 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr); +} + +static inline void local_flush_tlb_kernel_page(unsigned long kaddr) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + kaddr &= PAGE_MASK; + + if (tlb_flag(TLB_WB)) + dsb(nshst); + + __local_flush_tlb_kernel_page(kaddr); + tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", kaddr); + + if (tlb_flag(TLB_BARRIER)) { + dsb(nsh); + isb(); + } +} + +static inline void __flush_tlb_kernel_page(unsigned long kaddr) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + kaddr &= PAGE_MASK; + + if (tlb_flag(TLB_WB)) + dsb(ishst); + + __local_flush_tlb_kernel_page(kaddr); tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr); if (tlb_flag(TLB_BARRIER)) { - dsb(); + dsb(ish); isb(); } } +/* + * Branch predictor maintenance is paired with full TLB invalidation, so + * there is no need for any barriers here. + */ +static inline void __local_flush_bp_all(void) +{ + const int zero = 0; + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (tlb_flag(TLB_V6_BP)) + asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero)); +} + static inline void local_flush_bp_all(void) { const int zero = 0; const unsigned int __tlb_flag = __cpu_tlb_flags; + __local_flush_bp_all(); if (tlb_flag(TLB_V7_UIS_BP)) - asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero)); - else if (tlb_flag(TLB_V6_BP)) asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero)); +} - if (tlb_flag(TLB_BARRIER)) - isb(); +static inline void __flush_bp_all(void) +{ + const int zero = 0; + const unsigned int __tlb_flag = __cpu_tlb_flags; + + __local_flush_bp_all(); + if (tlb_flag(TLB_V7_UIS_BP)) + asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero)); } #include <asm/cputype.h> @@ -461,7 +578,7 @@ static inline void dummy_flush_tlb_a15_erratum(void) * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0. */ asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); - dsb(); + dsb(ish); } #else static inline int erratum_a15_798181(void) @@ -495,7 +612,7 @@ static inline void flush_pmd_entry(void *pmd) tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1 @ L2 flush_pmd", pmd); if (tlb_flag(TLB_WB)) - dsb(); + dsb(ishst); } static inline void clean_pmd_entry(void *pmd) diff --git a/arch/arm/include/asm/types.h b/arch/arm/include/asm/types.h new file mode 100644 index 0000000..a53cdb8 --- /dev/null +++ b/arch/arm/include/asm/types.h @@ -0,0 +1,40 @@ +#ifndef _ASM_TYPES_H +#define _ASM_TYPES_H + +#include <asm-generic/int-ll64.h> + +/* + * The C99 types uintXX_t that are usually defined in 'stdint.h' are not as + * unambiguous on ARM as you would expect. For the types below, there is a + * difference on ARM between GCC built for bare metal ARM, GCC built for glibc + * and the kernel itself, which results in build errors if you try to build with + * -ffreestanding and include 'stdint.h' (such as when you include 'arm_neon.h' + * in order to use NEON intrinsics) + * + * As the typedefs for these types in 'stdint.h' are based on builtin defines + * supplied by GCC, we can tweak these to align with the kernel's idea of those + * types, so 'linux/types.h' and 'stdint.h' can be safely included from the same + * source file (provided that -ffreestanding is used). + * + * int32_t uint32_t uintptr_t + * bare metal GCC long unsigned long unsigned int + * glibc GCC int unsigned int unsigned int + * kernel int unsigned int unsigned long + */ + +#ifdef __INT32_TYPE__ +#undef __INT32_TYPE__ +#define __INT32_TYPE__ int +#endif + +#ifdef __UINT32_TYPE__ +#undef __UINT32_TYPE__ +#define __UINT32_TYPE__ unsigned int +#endif + +#ifdef __UINTPTR_TYPE__ +#undef __UINTPTR_TYPE__ +#define __UINTPTR_TYPE__ unsigned long +#endif + +#endif /* _ASM_TYPES_H */ diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h index fa88d09..615781c 100644 --- a/arch/arm/include/asm/v7m.h +++ b/arch/arm/include/asm/v7m.h @@ -15,6 +15,10 @@ #define V7M_SCB_VTOR 0x08 +#define V7M_SCB_AIRCR 0x0c +#define V7M_SCB_AIRCR_VECTKEY (0x05fa << 16) +#define V7M_SCB_AIRCR_SYSRESETREQ (1 << 2) + #define V7M_SCB_SCR 0x10 #define V7M_SCB_SCR_SLEEPDEEP (1 << 2) @@ -42,3 +46,11 @@ */ #define EXC_RET_STACK_MASK 0x00000004 #define EXC_RET_THREADMODE_PROCESSSTACK 0xfffffffd + +#ifndef __ASSEMBLY__ + +enum reboot_mode; + +void armv7m_restart(enum reboot_mode mode, const char *cmd); + +#endif /* __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/xor.h b/arch/arm/include/asm/xor.h index 7604673..4ffb26d 100644 --- a/arch/arm/include/asm/xor.h +++ b/arch/arm/include/asm/xor.h @@ -7,7 +7,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/hardirq.h> #include <asm-generic/xor.h> +#include <asm/hwcap.h> +#include <asm/neon.h> #define __XOR(a1, a2) a1 ^= a2 @@ -138,4 +141,74 @@ static struct xor_block_template xor_block_arm4regs = { xor_speed(&xor_block_arm4regs); \ xor_speed(&xor_block_8regs); \ xor_speed(&xor_block_32regs); \ + NEON_TEMPLATES; \ } while (0) + +#ifdef CONFIG_KERNEL_MODE_NEON + +extern struct xor_block_template const xor_block_neon_inner; + +static void +xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +{ + if (in_interrupt()) { + xor_arm4regs_2(bytes, p1, p2); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_2(bytes, p1, p2); + kernel_neon_end(); + } +} + +static void +xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3) +{ + if (in_interrupt()) { + xor_arm4regs_3(bytes, p1, p2, p3); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_3(bytes, p1, p2, p3); + kernel_neon_end(); + } +} + +static void +xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4) +{ + if (in_interrupt()) { + xor_arm4regs_4(bytes, p1, p2, p3, p4); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4); + kernel_neon_end(); + } +} + +static void +xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4, unsigned long *p5) +{ + if (in_interrupt()) { + xor_arm4regs_5(bytes, p1, p2, p3, p4, p5); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5); + kernel_neon_end(); + } +} + +static struct xor_block_template xor_block_neon = { + .name = "neon", + .do_2 = xor_neon_2, + .do_3 = xor_neon_3, + .do_4 = xor_neon_4, + .do_5 = xor_neon_5 +}; + +#define NEON_TEMPLATES \ + do { if (cpu_has_neon()) xor_speed(&xor_block_neon); } while (0) +#else +#define NEON_TEMPLATES +#endif diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 86d10dd..5140df5f 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -24,7 +24,7 @@ obj-$(CONFIG_ATAGS_PROC) += atags_proc.o obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o ifeq ($(CONFIG_CPU_V7M),y) -obj-y += entry-v7m.o +obj-y += entry-v7m.o v7m.o else obj-y += entry-armv.o endif diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h index 9edc969..ec4164d 100644 --- a/arch/arm/kernel/atags.h +++ b/arch/arm/kernel/atags.h @@ -7,9 +7,10 @@ static inline void save_atags(struct tag *tags) { } void convert_to_tag_list(struct tag *tags); #ifdef CONFIG_ATAGS -struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr); +const struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer, + unsigned int machine_nr); #else -static inline struct machine_desc * +static inline const struct machine_desc * setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) { early_print("no ATAGS support: can't continue\n"); diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c index 14512e6..8c14de8 100644 --- a/arch/arm/kernel/atags_parse.c +++ b/arch/arm/kernel/atags_parse.c @@ -178,11 +178,11 @@ static void __init squash_mem_tags(struct tag *tag) tag->hdr.tag = ATAG_NONE; } -struct machine_desc * __init setup_machine_tags(phys_addr_t __atags_pointer, - unsigned int machine_nr) +const struct machine_desc * __init +setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) { struct tag *tags = (struct tag *)&default_tags; - struct machine_desc *mdesc = NULL, *p; + const struct machine_desc *mdesc = NULL, *p; char *from = default_command_line; default_tags.mem.start = PHYS_OFFSET; diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index 5859c8b..eae1976 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -176,10 +176,10 @@ void __init arm_dt_init_cpu_maps(void) * If a dtb was passed to the kernel in r2, then use it to choose the * correct machine_desc and to setup the system. */ -struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) +const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) { struct boot_param_header *devtree; - struct machine_desc *mdesc, *mdesc_best = NULL; + const struct machine_desc *mdesc, *mdesc_best = NULL; unsigned int score, mdesc_score = ~1; unsigned long dt_root; const char *model; @@ -188,7 +188,7 @@ struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) DT_MACHINE_START(GENERIC_DT, "Generic DT based system") MACHINE_END - mdesc_best = (struct machine_desc *)&__mach_desc_GENERIC_DT; + mdesc_best = &__mach_desc_GENERIC_DT; #endif if (!dt_phys) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 94104bf..74ad15d1 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -442,10 +442,10 @@ local_restart: ldrcc pc, [tbl, scno, lsl #2] @ call sys_* routine add r1, sp, #S_OFF -2: mov why, #0 @ no longer a real syscall cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) eor r0, scno, #__NR_SYSCALL_BASE @ put OS number back - bcs arm_syscall + bcs arm_syscall +2: mov why, #0 @ no longer a real syscall b sys_ni_syscall @ not private func #if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI) diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c index fc79202..918875d 100644 --- a/arch/arm/kernel/fiq.c +++ b/arch/arm/kernel/fiq.c @@ -89,7 +89,8 @@ void set_fiq_handler(void *start, unsigned int length) memcpy(base + offset, start, length); if (!cache_is_vipt_nonaliasing()) - flush_icache_range(base + offset, offset + length); + flush_icache_range((unsigned long)base + offset, offset + + length); flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length); } diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index d7c82df..57221e3 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -82,6 +82,7 @@ void machine_crash_nonpanic_core(void *unused) crash_save_cpu(®s, smp_processor_id()); flush_cache_all(); + set_cpu_online(smp_processor_id(), false); atomic_dec(&waiting_for_crash_ipi); while (1) cpu_relax(); diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 85c3fb6..084dc88 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -292,12 +292,20 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, maps[ARM_SEC_CORE].unw_sec = s; else if (strcmp(".ARM.exidx.exit.text", secname) == 0) maps[ARM_SEC_EXIT].unw_sec = s; + else if (strcmp(".ARM.exidx.text.unlikely", secname) == 0) + maps[ARM_SEC_UNLIKELY].unw_sec = s; + else if (strcmp(".ARM.exidx.text.hot", secname) == 0) + maps[ARM_SEC_HOT].unw_sec = s; else if (strcmp(".init.text", secname) == 0) maps[ARM_SEC_INIT].txt_sec = s; else if (strcmp(".text", secname) == 0) maps[ARM_SEC_CORE].txt_sec = s; else if (strcmp(".exit.text", secname) == 0) maps[ARM_SEC_EXIT].txt_sec = s; + else if (strcmp(".text.unlikely", secname) == 0) + maps[ARM_SEC_UNLIKELY].txt_sec = s; + else if (strcmp(".text.hot", secname) == 0) + maps[ARM_SEC_HOT].txt_sec = s; } for (i = 0; i < ARM_SEC_MAX; i++) diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index aebe0e9..8d6147b 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -118,7 +118,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) continue; } - err = request_irq(irq, handler, IRQF_NOBALANCING, "arm-pmu", + err = request_irq(irq, handler, + IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu", cpu_pmu); if (err) { pr_err("unable to request IRQ%d for ARM PMU counters\n", diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index afc2489..0e1e2b3 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -72,10 +72,10 @@ static int __init fpe_setup(char *line) __setup("fpe=", fpe_setup); #endif -extern void paging_init(struct machine_desc *desc); +extern void paging_init(const struct machine_desc *desc); extern void sanity_check_meminfo(void); extern enum reboot_mode reboot_mode; -extern void setup_dma_zone(struct machine_desc *desc); +extern void setup_dma_zone(const struct machine_desc *desc); unsigned int processor_id; EXPORT_SYMBOL(processor_id); @@ -139,7 +139,7 @@ EXPORT_SYMBOL(elf_platform); static const char *cpu_name; static const char *machine_name; static char __initdata cmd_line[COMMAND_LINE_SIZE]; -struct machine_desc *machine_desc __initdata; +const struct machine_desc *machine_desc __initdata; static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } }; #define ENDIANNESS ((char)endian_test.l) @@ -607,7 +607,7 @@ static void __init setup_processor(void) void __init dump_machine_table(void) { - struct machine_desc *p; + const struct machine_desc *p; early_print("Available machine support:\n\nID (hex)\tNAME\n"); for_each_machine_desc(p) @@ -694,7 +694,7 @@ static int __init early_mem(char *p) } early_param("mem", early_mem); -static void __init request_standard_resources(struct machine_desc *mdesc) +static void __init request_standard_resources(const struct machine_desc *mdesc) { struct memblock_region *region; struct resource *res; @@ -852,7 +852,7 @@ void __init hyp_mode_check(void) void __init setup_arch(char **cmdline_p) { - struct machine_desc *mdesc; + const struct machine_desc *mdesc; setup_processor(); mdesc = setup_machine_fdt(__atags_pointer); @@ -994,15 +994,6 @@ static int c_show(struct seq_file *m, void *v) seq_printf(m, "model name\t: %s rev %d (%s)\n", cpu_name, cpuid & 15, elf_platform); -#if defined(CONFIG_SMP) - seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", - per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ), - (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100); -#else - seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", - loops_per_jiffy / (500000/HZ), - (loops_per_jiffy / (5000/HZ)) % 100); -#endif /* dump out the processor features */ seq_puts(m, "Features\t: "); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 2dc19349e..92d10e5 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -398,17 +398,8 @@ asmlinkage void secondary_start_kernel(void) void __init smp_cpus_done(unsigned int max_cpus) { - int cpu; - unsigned long bogosum = 0; - - for_each_online_cpu(cpu) - bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy; - - printk(KERN_INFO "SMP: Total of %d processors activated " - "(%lu.%02lu BogoMIPS).\n", - num_online_cpus(), - bogosum / (500000/HZ), - (bogosum / (5000/HZ)) % 100); + printk(KERN_INFO "SMP: Total of %d processors activated.\n", + num_online_cpus()); hyp_mode_check(); } diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index c2edfff..83ccca3 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -104,7 +104,7 @@ void flush_tlb_all(void) if (tlb_ops_need_broadcast()) on_each_cpu(ipi_flush_tlb_all, NULL, 1); else - local_flush_tlb_all(); + __flush_tlb_all(); broadcast_tlb_a15_erratum(); } @@ -113,7 +113,7 @@ void flush_tlb_mm(struct mm_struct *mm) if (tlb_ops_need_broadcast()) on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1); else - local_flush_tlb_mm(mm); + __flush_tlb_mm(mm); broadcast_tlb_mm_a15_erratum(mm); } @@ -126,7 +126,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page, &ta, 1); } else - local_flush_tlb_page(vma, uaddr); + __flush_tlb_page(vma, uaddr); broadcast_tlb_mm_a15_erratum(vma->vm_mm); } @@ -137,7 +137,7 @@ void flush_tlb_kernel_page(unsigned long kaddr) ta.ta_start = kaddr; on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1); } else - local_flush_tlb_kernel_page(kaddr); + __flush_tlb_kernel_page(kaddr); broadcast_tlb_a15_erratum(); } @@ -173,5 +173,5 @@ void flush_bp_all(void) if (tlb_ops_need_broadcast()) on_each_cpu(ipi_flush_bp_all, NULL, 1); else - local_flush_bp_all(); + __flush_bp_all(); } diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index ab517fc..8fcda14 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -497,28 +497,64 @@ static int bad_syscall(int n, struct pt_regs *regs) return regs->ARM_r0; } +static long do_cache_op_restart(struct restart_block *); + static inline int -do_cache_op(unsigned long start, unsigned long end, int flags) +__do_cache_op(unsigned long start, unsigned long end) { - struct mm_struct *mm = current->active_mm; - struct vm_area_struct *vma; + int ret; + unsigned long chunk = PAGE_SIZE; + + do { + if (signal_pending(current)) { + struct thread_info *ti = current_thread_info(); + + ti->restart_block = (struct restart_block) { + .fn = do_cache_op_restart, + }; + + ti->arm_restart_block = (struct arm_restart_block) { + { + .cache = { + .start = start, + .end = end, + }, + }, + }; + + return -ERESTART_RESTARTBLOCK; + } + + ret = flush_cache_user_range(start, start + chunk); + if (ret) + return ret; + cond_resched(); + start += chunk; + } while (start < end); + + return 0; +} + +static long do_cache_op_restart(struct restart_block *unused) +{ + struct arm_restart_block *restart_block; + + restart_block = ¤t_thread_info()->arm_restart_block; + return __do_cache_op(restart_block->cache.start, + restart_block->cache.end); +} + +static inline int +do_cache_op(unsigned long start, unsigned long end, int flags) +{ if (end < start || flags) return -EINVAL; - down_read(&mm->mmap_sem); - vma = find_vma(mm, start); - if (vma && vma->vm_start < end) { - if (start < vma->vm_start) - start = vma->vm_start; - if (end > vma->vm_end) - end = vma->vm_end; + if (!access_ok(VERIFY_READ, start, end - start)) + return -EFAULT; - up_read(&mm->mmap_sem); - return flush_cache_user_range(start, end); - } - up_read(&mm->mmap_sem); - return -EINVAL; + return __do_cache_op(start, end); } /* diff --git a/arch/arm/kernel/v7m.c b/arch/arm/kernel/v7m.c new file mode 100644 index 0000000..4d2cba9 --- /dev/null +++ b/arch/arm/kernel/v7m.c @@ -0,0 +1,19 @@ +/* + * Copyright (C) 2013 Uwe Kleine-Koenig for Pengutronix + * + * 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/io.h> +#include <linux/reboot.h> +#include <asm/barrier.h> +#include <asm/v7m.h> + +void armv7m_restart(enum reboot_mode mode, const char *cmd) +{ + dsb(); + __raw_writel(V7M_SCB_AIRCR_VECTKEY | V7M_SCB_AIRCR_SYSRESETREQ, + BASEADDR_V7M_SCB + V7M_SCB_AIRCR); + dsb(); +} diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 4a51990..db9cf69 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -146,7 +146,11 @@ static bool pm_fake(struct kvm_vcpu *vcpu, #define access_pmintenclr pm_fake /* Architected CP15 registers. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. */ static const struct coproc_reg cp15_regs[] = { /* CSSELR: swapped by interrupt.S. */ @@ -154,8 +158,8 @@ static const struct coproc_reg cp15_regs[] = { NULL, reset_unknown, c0_CSSELR }, /* TTBR0/TTBR1: swapped by interrupt.S. */ - { CRm( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 }, - { CRm( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 }, + { CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 }, + { CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 }, /* TTBCR: swapped by interrupt.S. */ { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32, @@ -182,7 +186,7 @@ static const struct coproc_reg cp15_regs[] = { NULL, reset_unknown, c6_IFAR }, /* PAR swapped by interrupt.S */ - { CRn( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, + { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, /* * DC{C,I,CI}SW operations: @@ -399,12 +403,13 @@ static bool index_to_params(u64 id, struct coproc_params *params) | KVM_REG_ARM_OPC1_MASK)) return false; params->is_64bit = true; - params->CRm = ((id & KVM_REG_ARM_CRM_MASK) + /* CRm to CRn: see cp15_to_index for details */ + params->CRn = ((id & KVM_REG_ARM_CRM_MASK) >> KVM_REG_ARM_CRM_SHIFT); params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) >> KVM_REG_ARM_OPC1_SHIFT); params->Op2 = 0; - params->CRn = 0; + params->CRm = 0; return true; default: return false; @@ -898,7 +903,14 @@ static u64 cp15_to_index(const struct coproc_reg *reg) if (reg->is_64) { val |= KVM_REG_SIZE_U64; val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); - val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT); + /* + * CRn always denotes the primary coproc. reg. nr. for the + * in-kernel representation, but the user space API uses the + * CRm for the encoding, because it is modelled after the + * MRRC/MCRR instructions: see the ARM ARM rev. c page + * B3-1445 + */ + val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT); } else { val |= KVM_REG_SIZE_U32; val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h index b7301d3..0461d5c 100644 --- a/arch/arm/kvm/coproc.h +++ b/arch/arm/kvm/coproc.h @@ -135,6 +135,8 @@ static inline int cmp_reg(const struct coproc_reg *i1, return -1; if (i1->CRn != i2->CRn) return i1->CRn - i2->CRn; + if (i1->is_64 != i2->is_64) + return i2->is_64 - i1->is_64; if (i1->CRm != i2->CRm) return i1->CRm - i2->CRm; if (i1->Op1 != i2->Op1) @@ -145,6 +147,7 @@ static inline int cmp_reg(const struct coproc_reg *i1, #define CRn(_x) .CRn = _x #define CRm(_x) .CRm = _x +#define CRm64(_x) .CRn = _x, .CRm = 0 #define Op1(_x) .Op1 = _x #define Op2(_x) .Op2 = _x #define is64 .is_64 = true diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c index 685063a..cf93472 100644 --- a/arch/arm/kvm/coproc_a15.c +++ b/arch/arm/kvm/coproc_a15.c @@ -114,7 +114,11 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu, /* * A15-specific CP15 registers. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. */ static const struct coproc_reg a15_regs[] = { /* MPIDR: we use VMPIDR for guest access. */ diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S index f048338..1b9844d 100644 --- a/arch/arm/kvm/init.S +++ b/arch/arm/kvm/init.S @@ -142,7 +142,7 @@ target: @ We're now in the trampoline code, switch page tables @ Invalidate the old TLBs mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH - dsb + dsb ish eret diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 16cd4ba..f85052f 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -55,7 +55,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa) mcrr p15, 6, r2, r3, c2 @ Write VTTBR isb mcr p15, 0, r0, c8, c3, 0 @ TLBIALLIS (rt ignored) - dsb + dsb ish isb mov r2, #0 mov r3, #0 @@ -79,7 +79,7 @@ ENTRY(__kvm_flush_vm_context) mcr p15, 4, r0, c8, c3, 4 /* Invalidate instruction caches Inner Shareable (ICIALLUIS) */ mcr p15, 0, r0, c7, c1, 0 - dsb + dsb ish isb @ Not necessary if followed by eret bx lr diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index b8e06b7..0c25d94 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -63,7 +63,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_exit_mmio *mmio) { - unsigned long rt, len; + unsigned long rt; + int len; bool is_write, sign_extend; if (kvm_vcpu_dabt_isextabt(vcpu)) { diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index ca6bea4..b0de86b 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -85,6 +85,12 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) return p; } +static bool page_empty(void *ptr) +{ + struct page *ptr_page = virt_to_page(ptr); + return page_count(ptr_page) == 1; +} + static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr) { pmd_t *pmd_table = pmd_offset(pud, 0); @@ -103,12 +109,6 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) put_page(virt_to_page(pmd)); } -static bool pmd_empty(pmd_t *pmd) -{ - struct page *pmd_page = virt_to_page(pmd); - return page_count(pmd_page) == 1; -} - static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr) { if (pte_present(*pte)) { @@ -118,12 +118,6 @@ static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr) } } -static bool pte_empty(pte_t *pte) -{ - struct page *pte_page = virt_to_page(pte); - return page_count(pte_page) == 1; -} - static void unmap_range(struct kvm *kvm, pgd_t *pgdp, unsigned long long start, u64 size) { @@ -132,37 +126,37 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, pmd_t *pmd; pte_t *pte; unsigned long long addr = start, end = start + size; - u64 range; + u64 next; while (addr < end) { pgd = pgdp + pgd_index(addr); pud = pud_offset(pgd, addr); if (pud_none(*pud)) { - addr += PUD_SIZE; + addr = pud_addr_end(addr, end); continue; } pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { - addr += PMD_SIZE; + addr = pmd_addr_end(addr, end); continue; } pte = pte_offset_kernel(pmd, addr); clear_pte_entry(kvm, pte, addr); - range = PAGE_SIZE; + next = addr + PAGE_SIZE; /* If we emptied the pte, walk back up the ladder */ - if (pte_empty(pte)) { + if (page_empty(pte)) { clear_pmd_entry(kvm, pmd, addr); - range = PMD_SIZE; - if (pmd_empty(pmd)) { + next = pmd_addr_end(addr, end); + if (page_empty(pmd) && !page_empty(pud)) { clear_pud_entry(kvm, pud, addr); - range = PUD_SIZE; + next = pud_addr_end(addr, end); } } - addr += range; + addr = next; } } @@ -495,7 +489,6 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) { pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE); - kvm_set_s2pte_writable(&pte); ret = mmu_topup_memory_cache(&cache, 2, 2); if (ret) diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index af72969..aaf3a87 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -45,3 +45,9 @@ lib-$(CONFIG_ARCH_SHARK) += io-shark.o $(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S $(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S + +ifeq ($(CONFIG_KERNEL_MODE_NEON),y) + NEON_FLAGS := -mfloat-abi=softfp -mfpu=neon + CFLAGS_xor-neon.o += $(NEON_FLAGS) + lib-$(CONFIG_XOR_BLOCKS) += xor-neon.o +endif diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c new file mode 100644 index 0000000..f485e5a --- /dev/null +++ b/arch/arm/lib/xor-neon.c @@ -0,0 +1,42 @@ +/* + * linux/arch/arm/lib/xor-neon.c + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * 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/raid/xor.h> + +#ifndef __ARM_NEON__ +#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon' +#endif + +/* + * Pull in the reference implementations while instructing GCC (through + * -ftree-vectorize) to attempt to exploit implicit parallelism and emit + * NEON instructions. + */ +#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6) +#pragma GCC optimize "tree-vectorize" +#else +/* + * While older versions of GCC do not generate incorrect code, they fail to + * recognize the parallel nature of these functions, and emit plain ARM code, + * which is known to be slower than the optimized ARM code in asm-arm/xor.h. + */ +#warning This code requires at least version 4.6 of GCC +#endif + +#pragma GCC diagnostic ignored "-Wunused-variable" +#include <asm-generic/xor.h> + +struct xor_block_template const xor_block_neon_inner = { + .name = "__inner_neon__", + .do_2 = xor_8regs_2, + .do_3 = xor_8regs_3, + .do_4 = xor_8regs_4, + .do_5 = xor_8regs_5, +}; diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c index 2abee66..916e5a1 100644 --- a/arch/arm/mach-at91/at91sam9x5.c +++ b/arch/arm/mach-at91/at91sam9x5.c @@ -227,6 +227,8 @@ static struct clk_lookup periph_clocks_lookups[] = { CLKDEV_CON_DEV_ID("usart", "f8020000.serial", &usart1_clk), CLKDEV_CON_DEV_ID("usart", "f8024000.serial", &usart2_clk), CLKDEV_CON_DEV_ID("usart", "f8028000.serial", &usart3_clk), + CLKDEV_CON_DEV_ID("usart", "f8040000.serial", &uart0_clk), + CLKDEV_CON_DEV_ID("usart", "f8044000.serial", &uart1_clk), CLKDEV_CON_DEV_ID("t0_clk", "f8008000.timer", &tcb0_clk), CLKDEV_CON_DEV_ID("t0_clk", "f800c000.timer", &tcb0_clk), CLKDEV_CON_DEV_ID("mci_clk", "f0008000.mmc", &mmc0_clk), diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c index dff4ddc..139e42d 100644 --- a/arch/arm/mach-davinci/board-dm355-leopard.c +++ b/arch/arm/mach-davinci/board-dm355-leopard.c @@ -75,6 +75,7 @@ static struct davinci_nand_pdata davinci_nand_data = { .parts = davinci_nand_partitions, .nr_parts = ARRAY_SIZE(davinci_nand_partitions), .ecc_mode = NAND_ECC_HW_SYNDROME, + .ecc_bits = 4, .bbt_options = NAND_BBT_USE_FLASH, }; diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c index a33686a..fa4bfaf 100644 --- a/arch/arm/mach-davinci/board-dm644x-evm.c +++ b/arch/arm/mach-davinci/board-dm644x-evm.c @@ -153,6 +153,7 @@ static struct davinci_nand_pdata davinci_evm_nandflash_data = { .parts = davinci_evm_nandflash_partition, .nr_parts = ARRAY_SIZE(davinci_evm_nandflash_partition), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .bbt_options = NAND_BBT_USE_FLASH, .timing = &davinci_evm_nandflash_timing, }; diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c index fbb8e5a..0c005e8 100644 --- a/arch/arm/mach-davinci/board-dm646x-evm.c +++ b/arch/arm/mach-davinci/board-dm646x-evm.c @@ -90,6 +90,7 @@ static struct davinci_nand_pdata davinci_nand_data = { .parts = davinci_nand_partitions, .nr_parts = ARRAY_SIZE(davinci_nand_partitions), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .options = 0, }; diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c index 2bc112a..808233b 100644 --- a/arch/arm/mach-davinci/board-neuros-osd2.c +++ b/arch/arm/mach-davinci/board-neuros-osd2.c @@ -88,6 +88,7 @@ static struct davinci_nand_pdata davinci_ntosd2_nandflash_data = { .parts = davinci_ntosd2_nandflash_partition, .nr_parts = ARRAY_SIZE(davinci_ntosd2_nandflash_partition), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .bbt_options = NAND_BBT_USE_FLASH, }; diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index f6eeb87..827d150 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -122,11 +122,7 @@ static struct musb_hdrc_config musb_config = { }; static struct musb_hdrc_platform_data tusb_data = { -#ifdef CONFIG_USB_GADGET_MUSB_HDRC .mode = MUSB_OTG, -#else - .mode = MUSB_HOST, -#endif .set_power = tusb_set_power, .min_power = 25, /* x2 = 50 mA drawn from VBUS as peripheral */ .power = 100, /* Max 100 mA VBUS for host mode */ diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c index d2ea68e..773510556 100644 --- a/arch/arm/mach-omap2/board-rx51.c +++ b/arch/arm/mach-omap2/board-rx51.c @@ -85,7 +85,7 @@ static struct omap_board_mux board_mux[] __initdata = { static struct omap_musb_board_data musb_board_data = { .interface_type = MUSB_INTERFACE_ULPI, - .mode = MUSB_PERIPHERAL, + .mode = MUSB_OTG, .power = 0, }; diff --git a/arch/arm/mach-omap2/usb-musb.c b/arch/arm/mach-omap2/usb-musb.c index 8c4de27..bc89723 100644 --- a/arch/arm/mach-omap2/usb-musb.c +++ b/arch/arm/mach-omap2/usb-musb.c @@ -38,11 +38,8 @@ static struct musb_hdrc_config musb_config = { }; static struct musb_hdrc_platform_data musb_plat = { -#ifdef CONFIG_USB_GADGET_MUSB_HDRC .mode = MUSB_OTG, -#else - .mode = MUSB_HOST, -#endif + /* .clock is set dynamically */ .config = &musb_config, diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index db5c2ca..cd2c88e 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -809,15 +809,18 @@ config KUSER_HELPERS the CPU type fitted to the system. This permits binaries to be run on ARMv4 through to ARMv7 without modification. + See Documentation/arm/kernel_user_helpers.txt for details. + However, the fixed address nature of these helpers can be used by ROP (return orientated programming) authors when creating exploits. If all of the binaries and libraries which run on your platform are built specifically for your platform, and make no use of - these helpers, then you can turn this option off. However, - when such an binary or library is run, it will receive a SIGILL - signal, which will terminate the program. + these helpers, then you can turn this option off to hinder + such exploits. However, in that case, if a binary or library + relying on those helpers is run, it will receive a SIGILL signal, + which will terminate the program. Say N here only if you are absolutely certain that you do not need these helpers; otherwise, the safe option is to say Y. diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index d70e0ab..447da6f 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -290,7 +290,7 @@ static void l2x0_disable(void) raw_spin_lock_irqsave(&l2x0_lock, flags); __l2x0_flush_all(); writel_relaxed(0, l2x0_base + L2X0_CTRL); - dsb(); + dsb(st); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } @@ -417,9 +417,9 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) outer_cache.disable = l2x0_disable; } - printk(KERN_INFO "%s cache controller enabled\n", type); - printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n", - ways, cache_id, aux, l2x0_size); + pr_info("%s cache controller enabled\n", type); + pr_info("l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d kB\n", + ways, cache_id, aux, l2x0_size >> 10); } #ifdef CONFIG_OF @@ -929,7 +929,9 @@ static const struct of_device_id l2x0_ids[] __initconst = { .data = (void *)&aurora_no_outer_data}, { .compatible = "marvell,aurora-outer-cache", .data = (void *)&aurora_with_outer_data}, - { .compatible = "bcm,bcm11351-a2-pl310-cache", + { .compatible = "brcm,bcm11351-a2-pl310-cache", + .data = (void *)&bcm_l2x0_data}, + { .compatible = "bcm,bcm11351-a2-pl310-cache", /* deprecated name */ .data = (void *)&bcm_l2x0_data}, {} }; diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 515b000..b5c467a 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -282,7 +282,7 @@ ENTRY(v7_coherent_user_range) add r12, r12, r2 cmp r12, r1 blo 1b - dsb + dsb ishst icache_line_size r2, r3 sub r3, r2, #1 bic r12, r0, r3 @@ -294,7 +294,7 @@ ENTRY(v7_coherent_user_range) mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 6) @ invalidate BTB Inner Shareable ALT_UP(mcr p15, 0, r0, c7, c5, 6) @ invalidate BTB - dsb + dsb ishst isb mov pc, lr diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 4a05444..84e6f77 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -162,10 +162,7 @@ static void flush_context(unsigned int cpu) } /* Queue a TLB invalidate and flush the I-cache if necessary. */ - if (!tlb_ops_need_broadcast()) - cpumask_set_cpu(cpu, &tlb_flush_pending); - else - cpumask_setall(&tlb_flush_pending); + cpumask_setall(&tlb_flush_pending); if (icache_is_vivt_asid_tagged()) __flush_icache_all(); @@ -245,8 +242,6 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) { local_flush_bp_all(); local_flush_tlb_all(); - if (erratum_a15_798181()) - dummy_flush_tlb_a15_erratum(); } atomic64_set(&per_cpu(active_asids, cpu), asid); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 7f9b179..0c17f69 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -455,7 +455,6 @@ static void __dma_remap(struct page *page, size_t size, pgprot_t prot) unsigned end = start + size; apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot); - dsb(); flush_tlb_kernel_range(start, end); } diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index 3d1e4a2..66781bf3 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -36,22 +36,6 @@ * of type casting from pmd_t * to pte_t *. */ -pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd = NULL; - - pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) - pmd = pmd_offset(pud, addr); - } - - return (pte_t *)pmd; -} - struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) { @@ -68,33 +52,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 0; } -pte_t *huge_pte_alloc(struct mm_struct *mm, - unsigned long addr, unsigned long sz) -{ - pgd_t *pgd; - pud_t *pud; - pte_t *pte = NULL; - - pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); - if (pud) - pte = (pte_t *)pmd_alloc(mm, pud, addr); - - return pte; -} - -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~PMD_MASK) >> PAGE_SHIFT); - return page; -} - int pmd_huge(pmd_t pmd) { return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 15225d8..2958e74 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -231,7 +231,7 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, } #endif -void __init setup_dma_zone(struct machine_desc *mdesc) +void __init setup_dma_zone(const struct machine_desc *mdesc) { #ifdef CONFIG_ZONE_DMA if (mdesc->dma_zone_size) { @@ -335,7 +335,8 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align) return phys; } -void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) +void __init arm_memblock_init(struct meminfo *mi, + const struct machine_desc *mdesc) { int i; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 53cdbd3..b1d17ee 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1186,7 +1186,7 @@ void __init arm_mm_memblock_reserve(void) * called function. This means you can't use any function or debugging * method which may touch any device, otherwise the kernel _will_ crash. */ -static void __init devicemaps_init(struct machine_desc *mdesc) +static void __init devicemaps_init(const struct machine_desc *mdesc) { struct map_desc map; unsigned long addr; @@ -1319,7 +1319,7 @@ static void __init map_lowmem(void) * paging_init() sets up the page tables, initialises the zone memory * maps, and sets up the zero page, bad page and bad page tables. */ -void __init paging_init(struct machine_desc *mdesc) +void __init paging_init(const struct machine_desc *mdesc) { void *zero_page; diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 1fa5010..34d4ab2 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -299,7 +299,7 @@ void __init sanity_check_meminfo(void) * paging_init() sets up the page tables, initialises the zone memory * maps, and sets up the zero page, bad page and bad page tables. */ -void __init paging_init(struct machine_desc *mdesc) +void __init paging_init(const struct machine_desc *mdesc) { early_trap_init((void *)CONFIG_VECTORS_BASE); mpu_setup(); diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index d5146b9..db79b62 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -514,6 +514,32 @@ ENTRY(cpu_feroceon_set_pte_ext) #endif mov pc, lr +/* Suspend/resume support: taken from arch/arm/mm/proc-arm926.S */ +.globl cpu_feroceon_suspend_size +.equ cpu_feroceon_suspend_size, 4 * 3 +#ifdef CONFIG_ARM_CPU_SUSPEND +ENTRY(cpu_feroceon_do_suspend) + stmfd sp!, {r4 - r6, lr} + mrc p15, 0, r4, c13, c0, 0 @ PID + mrc p15, 0, r5, c3, c0, 0 @ Domain ID + mrc p15, 0, r6, c1, c0, 0 @ Control register + stmia r0, {r4 - r6} + ldmfd sp!, {r4 - r6, pc} +ENDPROC(cpu_feroceon_do_suspend) + +ENTRY(cpu_feroceon_do_resume) + mov ip, #0 + mcr p15, 0, ip, c8, c7, 0 @ invalidate I+D TLBs + mcr p15, 0, ip, c7, c7, 0 @ invalidate I+D caches + ldmia r0, {r4 - r6} + mcr p15, 0, r4, c13, c0, 0 @ PID + mcr p15, 0, r5, c3, c0, 0 @ Domain ID + mcr p15, 0, r1, c2, c0, 0 @ TTB address + mov r0, r6 @ control register + b cpu_resume_mmu +ENDPROC(cpu_feroceon_do_resume) +#endif + .type __feroceon_setup, #function __feroceon_setup: mov r0, #0 diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 73398bc..c63d9bd 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -83,7 +83,7 @@ ENTRY(cpu_v7_dcache_clean_area) add r0, r0, r2 subs r1, r1, r2 bhi 2b - dsb + dsb ishst mov pc, lr ENDPROC(cpu_v7_dcache_clean_area) @@ -330,7 +330,19 @@ __v7_setup: 1: #endif -3: mov r10, #0 + /* Cortex-A15 Errata */ +3: ldr r10, =0x00000c0f @ Cortex-A15 primary part number + teq r0, r10 + bne 4f + +#ifdef CONFIG_ARM_ERRATA_773022 + cmp r6, #0x4 @ only present up to r0p4 + mrcle p15, 0, r10, c1, c0, 1 @ read aux control register + orrle r10, r10, #1 << 1 @ disable loop buffer + mcrle p15, 0, r10, c1, c0, 1 @ write aux control register +#endif + +4: mov r10, #0 mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate dsb #ifdef CONFIG_MMU diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index ea94765..3553087 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -35,7 +35,7 @@ ENTRY(v7wbi_flush_user_tlb_range) vma_vm_mm r3, r2 @ get vma->vm_mm mmid r3, r3 @ get vm_mm->context.id - dsb + dsb ish mov r0, r0, lsr #PAGE_SHIFT @ align address mov r1, r1, lsr #PAGE_SHIFT asid r3, r3 @ mask ASID @@ -56,7 +56,7 @@ ENTRY(v7wbi_flush_user_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - dsb + dsb ish mov pc, lr ENDPROC(v7wbi_flush_user_tlb_range) @@ -69,7 +69,7 @@ ENDPROC(v7wbi_flush_user_tlb_range) * - end - end address (exclusive, may not be aligned) */ ENTRY(v7wbi_flush_kern_tlb_range) - dsb + dsb ish mov r0, r0, lsr #PAGE_SHIFT @ align address mov r1, r1, lsr #PAGE_SHIFT mov r0, r0, lsl #PAGE_SHIFT @@ -84,7 +84,7 @@ ENTRY(v7wbi_flush_kern_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - dsb + dsb ish isb mov pc, lr ENDPROC(v7wbi_flush_kern_tlb_range) diff --git a/arch/arm/plat-samsung/init.c b/arch/arm/plat-samsung/init.c index 3e5c461..50a3ea0 100644 --- a/arch/arm/plat-samsung/init.c +++ b/arch/arm/plat-samsung/init.c @@ -55,12 +55,13 @@ void __init s3c_init_cpu(unsigned long idcode, printk("CPU %s (id 0x%08lx)\n", cpu->name, idcode); - if (cpu->map_io == NULL || cpu->init == NULL) { + if (cpu->init == NULL) { printk(KERN_ERR "CPU %s support not enabled\n", cpu->name); panic("Unsupported Samsung CPU"); } - cpu->map_io(); + if (cpu->map_io) + cpu->map_io(); } /* s3c24xx_init_clocks diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index 8d10dc8..3e5d311 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -78,6 +78,11 @@ ENTRY(vfp_support_entry) DBGSTR3 "instr %08x pc %08x state %p", r0, r2, r10 + ldr r3, [sp, #S_PSR] @ Neither lazy restore nor FP exceptions + and r3, r3, #MODE_MASK @ are supported in kernel mode + teq r3, #USR_MODE + bne vfp_kmode_exception @ Returns through lr + VFPFMRX r1, FPEXC @ Is the VFP enabled? DBGSTR1 "fpexc %08x", r1 tst r1, #FPEXC_EN diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 5dfbb0b..52b8f40 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/uaccess.h> #include <linux/user.h> +#include <linux/export.h> #include <asm/cp15.h> #include <asm/cputype.h> @@ -648,6 +649,72 @@ static int vfp_hotplug(struct notifier_block *b, unsigned long action, return NOTIFY_OK; } +void vfp_kmode_exception(void) +{ + /* + * If we reach this point, a floating point exception has been raised + * while running in kernel mode. If the NEON/VFP unit was enabled at the + * time, it means a VFP instruction has been issued that requires + * software assistance to complete, something which is not currently + * supported in kernel mode. + * If the NEON/VFP unit was disabled, and the location pointed to below + * is properly preceded by a call to kernel_neon_begin(), something has + * caused the task to be scheduled out and back in again. In this case, + * rebuilding and running with CONFIG_DEBUG_ATOMIC_SLEEP enabled should + * be helpful in localizing the problem. + */ + if (fmrx(FPEXC) & FPEXC_EN) + pr_crit("BUG: unsupported FP instruction in kernel mode\n"); + else + pr_crit("BUG: FP instruction issued in kernel mode with FP unit disabled\n"); +} + +#ifdef CONFIG_KERNEL_MODE_NEON + +/* + * Kernel-side NEON support functions + */ +void kernel_neon_begin(void) +{ + struct thread_info *thread = current_thread_info(); + unsigned int cpu; + u32 fpexc; + + /* + * Kernel mode NEON is only allowed outside of interrupt context + * with preemption disabled. This will make sure that the kernel + * mode NEON register contents never need to be preserved. + */ + BUG_ON(in_interrupt()); + cpu = get_cpu(); + + fpexc = fmrx(FPEXC) | FPEXC_EN; + fmxr(FPEXC, fpexc); + + /* + * Save the userland NEON/VFP state. Under UP, + * the owner could be a task other than 'current' + */ + if (vfp_state_in_hw(cpu, thread)) + vfp_save_state(&thread->vfpstate, fpexc); +#ifndef CONFIG_SMP + else if (vfp_current_hw_state[cpu] != NULL) + vfp_save_state(vfp_current_hw_state[cpu], fpexc); +#endif + vfp_current_hw_state[cpu] = NULL; +} +EXPORT_SYMBOL(kernel_neon_begin); + +void kernel_neon_end(void) +{ + /* Disable the NEON/VFP unit. */ + fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN); + put_cpu(); +} +EXPORT_SYMBOL(kernel_neon_end); + +#endif /* CONFIG_KERNEL_MODE_NEON */ + /* * VFP support code initialisation. */ @@ -731,4 +798,4 @@ static int __init vfp_init(void) return 0; } -late_initcall(vfp_init); +core_initcall(vfp_init); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index c9770ba..8a6295c 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -170,6 +170,7 @@ static void __init xen_percpu_init(void *unused) per_cpu(xen_vcpu, cpu) = vcpup; enable_percpu_irq(xen_events_irq, 0); + put_cpu(); } static void xen_restart(enum reboot_mode reboot_mode, const char *cmd) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index c92de41..b25763b 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -42,14 +42,15 @@ #define TPIDR_EL1 18 /* Thread ID, Privileged */ #define AMAIR_EL1 19 /* Aux Memory Attribute Indirection Register */ #define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */ +#define PAR_EL1 21 /* Physical Address Register */ /* 32bit specific registers. Keep them at the end of the range */ -#define DACR32_EL2 21 /* Domain Access Control Register */ -#define IFSR32_EL2 22 /* Instruction Fault Status Register */ -#define FPEXC32_EL2 23 /* Floating-Point Exception Control Register */ -#define DBGVCR32_EL2 24 /* Debug Vector Catch Register */ -#define TEECR32_EL1 25 /* ThumbEE Configuration Register */ -#define TEEHBR32_EL1 26 /* ThumbEE Handler Base Register */ -#define NR_SYS_REGS 27 +#define DACR32_EL2 22 /* Domain Access Control Register */ +#define IFSR32_EL2 23 /* Instruction Fault Status Register */ +#define FPEXC32_EL2 24 /* Floating-Point Exception Control Register */ +#define DBGVCR32_EL2 25 /* Debug Vector Catch Register */ +#define TEECR32_EL1 26 /* ThumbEE Configuration Register */ +#define TEEHBR32_EL1 27 /* ThumbEE Handler Base Register */ +#define NR_SYS_REGS 28 /* 32bit mapping */ #define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */ @@ -69,6 +70,8 @@ #define c5_AIFSR (AFSR1_EL1 * 2) /* Auxiliary Instr Fault Status R */ #define c6_DFAR (FAR_EL1 * 2) /* Data Fault Address Register */ #define c6_IFAR (c6_DFAR + 1) /* Instruction Fault Address Register */ +#define c7_PAR (PAR_EL1 * 2) /* Physical Address Register */ +#define c7_PAR_high (c7_PAR + 1) /* PAR top 32 bits */ #define c10_PRRR (MAIR_EL1 * 2) /* Primary Region Remap Register */ #define c10_NMRR (c10_PRRR + 1) /* Normal Memory Remap Register */ #define c12_VBAR (VBAR_EL1 * 2) /* Vector Base Address Register */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 644d739..0859a4d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -129,7 +129,7 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_page_cache; /* Target CPU and feature flags */ - u32 target; + int target; DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); /* Detect first run of a vcpu */ diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 9ba33c4..12e6ccb 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -107,7 +107,12 @@ armpmu_map_cache_event(const unsigned (*cache_map) static int armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config) { - int mapping = (*event_map)[config]; + int mapping; + + if (config >= PERF_COUNT_HW_MAX) + return -EINVAL; + + mapping = (*event_map)[config]; return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping; } @@ -317,6 +322,9 @@ validate_event(struct pmu_hw_events *hw_events, struct hw_perf_event fake_event = event->hw; struct pmu *leader_pmu = event->group_leader->pmu; + if (is_software_event(event)) + return 1; + if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) return 1; diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index ff985e3..1ac0bbb 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -214,6 +214,7 @@ __kvm_hyp_code_start: mrs x21, tpidr_el1 mrs x22, amair_el1 mrs x23, cntkctl_el1 + mrs x24, par_el1 stp x4, x5, [x3] stp x6, x7, [x3, #16] @@ -225,6 +226,7 @@ __kvm_hyp_code_start: stp x18, x19, [x3, #112] stp x20, x21, [x3, #128] stp x22, x23, [x3, #144] + str x24, [x3, #160] .endm .macro restore_sysregs @@ -243,6 +245,7 @@ __kvm_hyp_code_start: ldp x18, x19, [x3, #112] ldp x20, x21, [x3, #128] ldp x22, x23, [x3, #144] + ldr x24, [x3, #160] msr vmpidr_el2, x4 msr csselr_el1, x5 @@ -264,6 +267,7 @@ __kvm_hyp_code_start: msr tpidr_el1, x21 msr amair_el1, x22 msr cntkctl_el1, x23 + msr par_el1, x24 .endm .macro skip_32bit_state tmp, target @@ -600,6 +604,8 @@ END(__kvm_vcpu_run) // void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); ENTRY(__kvm_tlb_flush_vmid_ipa) + dsb ishst + kern_hyp_va x0 ldr x2, [x0, #KVM_VTTBR] msr vttbr_el2, x2 @@ -621,6 +627,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa) ENDPROC(__kvm_tlb_flush_vmid_ipa) ENTRY(__kvm_flush_vm_context) + dsb ishst tlbi alle1is ic ialluis dsb sy @@ -753,6 +760,10 @@ el1_trap: */ tbnz x1, #7, 1f // S1PTW is set + /* Preserve PAR_EL1 */ + mrs x3, par_el1 + push x3, xzr + /* * Permission fault, HPFAR_EL2 is invalid. * Resolve the IPA the hard way using the guest VA. @@ -766,6 +777,8 @@ el1_trap: /* Read result */ mrs x3, par_el1 + pop x0, xzr // Restore PAR_EL1 from the stack + msr par_el1, x0 tbnz x3, #0, 3f // Bail out if we failed the translation ubfx x3, x3, #12, #36 // Extract IPA lsl x3, x3, #4 // and present it like HPFAR diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 9492360..02e9d09 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -211,6 +211,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* FAR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000), NULL, reset_unknown, FAR_EL1 }, + /* PAR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000), + NULL, reset_unknown, PAR_EL1 }, /* PMINTENSET_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001), diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index e773659..46048d2 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -803,6 +803,32 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, dec_insn.next_pc_inc; return 1; break; +#ifdef CONFIG_CPU_CAVIUM_OCTEON + case lwc2_op: /* This is bbit0 on Octeon */ + if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) == 0) + *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2); + else + *contpc = regs->cp0_epc + 8; + return 1; + case ldc2_op: /* This is bbit032 on Octeon */ + if ((regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32))) == 0) + *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2); + else + *contpc = regs->cp0_epc + 8; + return 1; + case swc2_op: /* This is bbit1 on Octeon */ + if (regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) + *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2); + else + *contpc = regs->cp0_epc + 8; + return 1; + case sdc2_op: /* This is bbit132 on Octeon */ + if (regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32))) + *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2); + else + *contpc = regs->cp0_epc + 8; + return 1; +#endif case cop0_op: case cop1_op: case cop2_op: diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 653668d..4a8cb8d 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -35,9 +35,9 @@ static void sanitize_boot_params(struct boot_params *boot_params) */ if (boot_params->sentinel) { /* fields in boot_params are left uninitialized, clear them */ - memset(&boot_params->olpc_ofw_header, 0, + memset(&boot_params->ext_ramdisk_image, 0, (char *)&boot_params->efi_info - - (char *)&boot_params->olpc_ofw_header); + (char *)&boot_params->ext_ramdisk_image); memset(&boot_params->kbd_status, 0, (char *)&boot_params->hdr - (char *)&boot_params->kbd_status); diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 50e5c58..4c01917 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, extern int __apply_microcode_amd(struct microcode_amd *mc_amd); extern int apply_microcode_amd(int cpu); -extern enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size); +extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); #ifdef CONFIG_MICROCODE_AMD_EARLY #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f654ece..08a0890 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -512,7 +512,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) static const int amd_erratum_383[]; static const int amd_erratum_400[]; -static bool cpu_has_amd_erratum(const int *erratum); +static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); static void init_amd(struct cpuinfo_x86 *c) { @@ -729,11 +729,11 @@ static void init_amd(struct cpuinfo_x86 *c) value &= ~(1ULL << 24); wrmsrl_safe(MSR_AMD64_BU_CFG2, value); - if (cpu_has_amd_erratum(amd_erratum_383)) + if (cpu_has_amd_erratum(c, amd_erratum_383)) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } - if (cpu_has_amd_erratum(amd_erratum_400)) + if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_APIC_C1E); rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); @@ -878,23 +878,13 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); -static bool cpu_has_amd_erratum(const int *erratum) + +static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { - struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info); int osvw_id = *erratum++; u32 range; u32 ms; - /* - * If called early enough that current_cpu_data hasn't been initialized - * yet, fall back to boot_cpu_data. - */ - if (cpu->x86 == 0) - cpu = &boot_cpu_data; - - if (cpu->x86_vendor != X86_VENDOR_AMD) - return false; - if (osvw_id >= 0 && osvw_id < 65536 && cpu_has(cpu, X86_FEATURE_OSVW)) { u64 osvw_len; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7a0adb7..7123b5d 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -145,10 +145,9 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) return 0; } -static unsigned int verify_patch_size(int cpu, u32 patch_size, +static unsigned int verify_patch_size(u8 family, u32 patch_size, unsigned int size) { - struct cpuinfo_x86 *c = &cpu_data(cpu); u32 max_size; #define F1XH_MPB_MAX_SIZE 2048 @@ -156,7 +155,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size, #define F15H_MPB_MAX_SIZE 4096 #define F16H_MPB_MAX_SIZE 3458 - switch (c->x86) { + switch (family) { case 0x14: max_size = F14H_MPB_MAX_SIZE; break; @@ -277,9 +276,8 @@ static void cleanup(void) * driver cannot continue functioning normally. In such cases, we tear * down everything we've used up so far and exit. */ -static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) +static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover) { - struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_header_amd *mc_hdr; struct ucode_patch *patch; unsigned int patch_size, crnt_size, ret; @@ -299,7 +297,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) /* check if patch is for the current family */ proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff); - if (proc_fam != c->x86) + if (proc_fam != family) return crnt_size; if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { @@ -308,7 +306,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) return crnt_size; } - ret = verify_patch_size(cpu, patch_size, leftover); + ret = verify_patch_size(family, patch_size, leftover); if (!ret) { pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id); return crnt_size; @@ -339,7 +337,8 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) return crnt_size; } -static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t size) +static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, + size_t size) { enum ucode_state ret = UCODE_ERROR; unsigned int leftover; @@ -362,7 +361,7 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz } while (leftover) { - crnt_size = verify_and_add_patch(cpu, fw, leftover); + crnt_size = verify_and_add_patch(family, fw, leftover); if (crnt_size < 0) return ret; @@ -373,22 +372,22 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz return UCODE_OK; } -enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size) +enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) { enum ucode_state ret; /* free old equiv table */ free_equiv_cpu_table(); - ret = __load_microcode_amd(cpu, data, size); + ret = __load_microcode_amd(family, data, size); if (ret != UCODE_OK) cleanup(); #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32) /* save BSP's matching patch for early load */ - if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { - struct ucode_patch *p = find_patch(cpu); + if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) { + struct ucode_patch *p = find_patch(smp_processor_id()); if (p) { memset(amd_bsp_mpb, 0, MPB_MAX_SIZE); memcpy(amd_bsp_mpb, p->data, min_t(u32, ksize(p->data), @@ -441,7 +440,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - ret = load_microcode_amd(cpu, fw->data, fw->size); + ret = load_microcode_amd(c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/microcode_amd_early.c index 1d14ffe..6073104 100644 --- a/arch/x86/kernel/microcode_amd_early.c +++ b/arch/x86/kernel/microcode_amd_early.c @@ -238,25 +238,17 @@ static void __init collect_cpu_sig_on_bsp(void *arg) uci->cpu_sig.sig = cpuid_eax(0x00000001); } #else -static void collect_cpu_info_amd_early(struct cpuinfo_x86 *c, - struct ucode_cpu_info *uci) +void load_ucode_amd_ap(void) { + unsigned int cpu = smp_processor_id(); + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; u32 rev, eax; rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); eax = cpuid_eax(0x00000001); - uci->cpu_sig.sig = eax; uci->cpu_sig.rev = rev; - c->microcode = rev; - c->x86 = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); -} - -void load_ucode_amd_ap(void) -{ - unsigned int cpu = smp_processor_id(); - - collect_cpu_info_amd_early(&cpu_data(cpu), ucode_cpu_info + cpu); + uci->cpu_sig.sig = eax; if (cpu && !ucode_loaded) { void *ucode; @@ -265,8 +257,10 @@ void load_ucode_amd_ap(void) return; ucode = (void *)(initrd_start + ucode_offset); - if (load_microcode_amd(0, ucode, ucode_size) != UCODE_OK) + eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); + if (load_microcode_amd(eax, ucode, ucode_size) != UCODE_OK) return; + ucode_loaded = true; } @@ -278,6 +272,8 @@ int __init save_microcode_in_initrd_amd(void) { enum ucode_state ret; void *ucode; + u32 eax; + #ifdef CONFIG_X86_32 unsigned int bsp = boot_cpu_data.cpu_index; struct ucode_cpu_info *uci = ucode_cpu_info + bsp; @@ -293,7 +289,10 @@ int __init save_microcode_in_initrd_amd(void) return 0; ucode = (void *)(initrd_start + ucode_offset); - ret = load_microcode_amd(0, ucode, ucode_size); + eax = cpuid_eax(0x00000001); + eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); + + ret = load_microcode_amd(eax, ucode, ucode_size); if (ret != UCODE_OK) return -EINVAL; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 48f8375..30277e2 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = mmap_legacy_base(); + *begin = current->mm->mmap_legacy_base; *end = TASK_SIZE; } } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index f63778c..25e7e13 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -98,7 +98,7 @@ static unsigned long mmap_base(void) * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64 * does, but not when emulating X86_32 */ -unsigned long mmap_legacy_base(void) +static unsigned long mmap_legacy_base(void) { if (mmap_is_ia32()) return TASK_UNMAPPED_BASE; @@ -112,11 +112,13 @@ unsigned long mmap_legacy_base(void) */ void arch_pick_mmap_layout(struct mm_struct *mm) { + mm->mmap_legacy_base = mmap_legacy_base(); + mm->mmap_base = mmap_base(); + if (mmap_is_legacy()) { - mm->mmap_base = mmap_legacy_base(); + mm->mmap_base = mm->mmap_legacy_base; mm->get_unmapped_area = arch_get_unmapped_area; } else { - mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 056d11f..8f3eea6 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -313,6 +313,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type) e820_add_region(start, end - start, type); } +void xen_ignore_unusable(struct e820entry *list, size_t map_size) +{ + struct e820entry *entry; + unsigned int i; + + for (i = 0, entry = list; i < map_size; i++, entry++) { + if (entry->type == E820_UNUSABLE) + entry->type = E820_RAM; + } +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ @@ -353,6 +364,17 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); + /* + * Xen won't allow a 1:1 mapping to be created to UNUSABLE + * regions, so if we're using the machine memory map leave the + * region as RAM as it is in the pseudo-physical map. + * + * UNUSABLE regions in domUs are not handled and will need + * a patch in the future. + */ + if (xen_initial_domain()) + xen_ignore_unusable(map, memmap.nr_entries); + /* Make sure the Xen-supplied memory map is well-ordered. */ sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index ca92754..b81c88e 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -694,8 +694,15 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) { int rc; - rc = native_cpu_up(cpu, tidle); - WARN_ON (xen_smp_intr_init(cpu)); + /* + * xen_smp_intr_init() needs to run before native_cpu_up() + * so that IPI vectors are set up on the booting CPU before + * it is marked online in native_cpu_up(). + */ + rc = xen_smp_intr_init(cpu); + WARN_ON(rc); + if (!rc) + rc = native_cpu_up(cpu, tidle); return rc; } |
