diff options
82 files changed, 2181 insertions, 488 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index befb8f35d6ac..1c0a6bb6f922 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -9,6 +9,7 @@ config ARM select SYS_SUPPORTS_APM_EMULATION select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI) select HAVE_OPROFILE if (HAVE_PERF_EVENTS) + select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_KGDB select HAVE_KPROBES if !XIP_KERNEL select HAVE_KRETPROBES if (HAVE_KPROBES) @@ -21,6 +22,7 @@ config ARM select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZO select HAVE_KERNEL_LZMA + select HAVE_KERNEL_XZ select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select PERF_USE_VMALLOC @@ -31,6 +33,7 @@ config ARM select GENERIC_IRQ_SHOW select CPU_PM if (SUSPEND || CPU_IDLE) select GENERIC_PCI_IOMAP + select HAVE_BPF_JIT if NET help The ARM series is a line of low-power-consumption RISC chip designs licensed by ARM Ltd and targeted at embedded applications and @@ -262,6 +265,7 @@ config ARCH_INTEGRATOR select PLAT_VERSATILE select PLAT_VERSATILE_FPGA_IRQ select NEED_MACH_MEMORY_H + select SPARSE_IRQ help Support for ARM's Integrator platform. @@ -308,6 +312,7 @@ config ARCH_VEXPRESS select HAVE_CLK select HAVE_PATA_PLATFORM select ICST + select NO_IOPORT select PLAT_VERSATILE select PLAT_VERSATILE_CLCD help diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 03646c4c13d1..f279ba9acfd5 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -292,6 +292,22 @@ choice Note that the system will appear to hang during boot if there is nothing connected to read from the DCC. + config DEBUG_SEMIHOSTING + bool "Kernel low-level debug output via semihosting I" + help + Semihosting enables code running on an ARM target to use + the I/O facilities on a host debugger/emulator through a + simple SVC calls. The host debugger or emulator must have + semihosting enabled for the special svc call to be trapped + otherwise the kernel will crash. + + This is known to work with OpenOCD, as wellas + ARM's Fast Models, or any other controlling environment + that implements semihosting. + + For more details about semihosting, please see + chapter 8 of DUI0203I_rvct_developer_guide.pdf from ARM Ltd. + endchoice config EARLY_PRINTK diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 40319d91bb7f..93d63be8fa59 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -253,6 +253,7 @@ core-$(CONFIG_VFP) += arch/arm/vfp/ # If we have a machine-specific directory, then include it in the build. core-y += arch/arm/kernel/ arch/arm/mm/ arch/arm/common/ +core-y += arch/arm/net/ core-y += $(machdirs) $(platdirs) drivers-$(CONFIG_OPROFILE) += arch/arm/oprofile/ diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore index e0936a148516..d0d441c429ae 100644 --- a/arch/arm/boot/compressed/.gitignore +++ b/arch/arm/boot/compressed/.gitignore @@ -1,8 +1,10 @@ +ashldi3.S font.c lib1funcs.S piggy.gzip piggy.lzo piggy.lzma +piggy.xzkern vmlinux vmlinux.lds diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index cf0a64ce4b83..bb267562e7ed 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -92,6 +92,7 @@ SEDFLAGS = s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/ suffix_$(CONFIG_KERNEL_GZIP) = gzip suffix_$(CONFIG_KERNEL_LZO) = lzo suffix_$(CONFIG_KERNEL_LZMA) = lzma +suffix_$(CONFIG_KERNEL_XZ) = xzkern # Borrowed libfdt files for the ATAG compatibility mode @@ -112,10 +113,12 @@ endif targets := vmlinux vmlinux.lds \ piggy.$(suffix_y) piggy.$(suffix_y).o \ - lib1funcs.o lib1funcs.S font.o font.c head.o misc.o $(OBJS) + lib1funcs.o lib1funcs.S ashldi3.o ashldi3.S \ + font.o font.c head.o misc.o $(OBJS) # Make sure files are removed during clean -extra-y += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S $(libfdt) $(libfdt_hdrs) +extra-y += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern \ + lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs) ifeq ($(CONFIG_FUNCTION_TRACER),y) ORIG_CFLAGS := $(KBUILD_CFLAGS) @@ -151,6 +154,12 @@ lib1funcs = $(obj)/lib1funcs.o $(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S $(call cmd,shipped) +# For __aeabi_llsl +ashldi3 = $(obj)/ashldi3.o + +$(obj)/ashldi3.S: $(srctree)/arch/$(SRCARCH)/lib/ashldi3.S + $(call cmd,shipped) + # We need to prevent any GOTOFF relocs being used with references # to symbols in the .bss section since we cannot relocate them # independently from the rest at run time. This can be achieved by @@ -172,7 +181,7 @@ if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \ fi $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \ - $(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE + $(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) FORCE @$(check_for_multiple_zreladdr) $(call if_changed,ld) @$(check_for_bad_syms) diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c index 07be5a2f8302..f41b38cafce8 100644 --- a/arch/arm/boot/compressed/decompress.c +++ b/arch/arm/boot/compressed/decompress.c @@ -44,6 +44,12 @@ extern void error(char *); #include "../../../../lib/decompress_unlzma.c" #endif +#ifdef CONFIG_KERNEL_XZ +#define memmove memmove +#define memcpy memcpy +#include "../../../../lib/decompress_unxz.c" +#endif + int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x)) { return decompress(input, len, NULL, NULL, output, NULL, error); diff --git a/arch/arm/boot/compressed/piggy.xzkern.S b/arch/arm/boot/compressed/piggy.xzkern.S new file mode 100644 index 000000000000..5703f300d027 --- /dev/null +++ b/arch/arm/boot/compressed/piggy.xzkern.S @@ -0,0 +1,6 @@ + .section .piggydata,#alloc + .globl input_data +input_data: + .incbin "arch/arm/boot/compressed/piggy.xzkern" + .globl input_data_end +input_data_end: diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c index b2dc2dd7f1df..a3bc86fa3156 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -697,13 +697,12 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start, * For primary GICs, skip over SGIs. * For secondary GICs, skip over PPIs, too. */ - domain->hwirq_base = 32; - if (gic_nr == 0) { - if ((irq_start & 31) > 0) { - domain->hwirq_base = 16; - if (irq_start != -1) - irq_start = (irq_start & ~31) + 16; - } + if (gic_nr == 0 && (irq_start & 31) > 0) { + domain->hwirq_base = 16; + if (irq_start != -1) + irq_start = (irq_start & ~31) + 16; + } else { + domain->hwirq_base = 32; } /* diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig index 1103f62a1964..a8314c3ee84d 100644 --- a/arch/arm/configs/integrator_defconfig +++ b/arch/arm/configs/integrator_defconfig @@ -57,18 +57,24 @@ CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_E100=y +CONFIG_SMC91X=y # CONFIG_KEYBOARD_ATKBD is not set # CONFIG_SERIO_SERPORT is not set CONFIG_SERIAL_AMBA_PL010=y CONFIG_SERIAL_AMBA_PL010_CONSOLE=y CONFIG_FB=y CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_ARMCLCD=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y CONFIG_FB_MATROX_MYSTIQUE=y +# CONFIG_VGA_CONSOLE is not set +CONFIG_MMC=y +CONFIG_MMC_ARMMMCI=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_PL030=y CONFIG_EXT2_FS=y +CONFIG_VFAT_FS=y CONFIG_TMPFS=y CONFIG_JFFS2_FS=y CONFIG_CRAMFS=y @@ -78,5 +84,7 @@ CONFIG_ROOT_NFS=y CONFIG_NFSD=y CONFIG_NFSD_V3=y CONFIG_PARTITION_ADVANCED=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h new file mode 100644 index 000000000000..3dabd8dd4049 --- /dev/null +++ b/arch/arm/include/asm/cp15.h @@ -0,0 +1,87 @@ +#ifndef __ASM_ARM_CP15_H +#define __ASM_ARM_CP15_H + +#include <asm/system.h> + +/* + * CR1 bits (CP#15 CR1) + */ +#define CR_M (1 << 0) /* MMU enable */ +#define CR_A (1 << 1) /* Alignment abort enable */ +#define CR_C (1 << 2) /* Dcache enable */ +#define CR_W (1 << 3) /* Write buffer enable */ +#define CR_P (1 << 4) /* 32-bit exception handler */ +#define CR_D (1 << 5) /* 32-bit data address range */ +#define CR_L (1 << 6) /* Implementation defined */ +#define CR_B (1 << 7) /* Big endian */ +#define CR_S (1 << 8) /* System MMU protection */ +#define CR_R (1 << 9) /* ROM MMU protection */ +#define CR_F (1 << 10) /* Implementation defined */ +#define CR_Z (1 << 11) /* Implementation defined */ +#define CR_I (1 << 12) /* Icache enable */ +#define CR_V (1 << 13) /* Vectors relocated to 0xffff0000 */ +#define CR_RR (1 << 14) /* Round Robin cache replacement */ +#define CR_L4 (1 << 15) /* LDR pc can set T bit */ +#define CR_DT (1 << 16) +#define CR_IT (1 << 18) +#define CR_ST (1 << 19) +#define CR_FI (1 << 21) /* Fast interrupt (lower latency mode) */ +#define CR_U (1 << 22) /* Unaligned access operation */ +#define CR_XP (1 << 23) /* Extended page tables */ +#define CR_VE (1 << 24) /* Vectored interrupts */ +#define CR_EE (1 << 25) /* Exception (Big) Endian */ +#define CR_TRE (1 << 28) /* TEX remap enable */ +#define CR_AFE (1 << 29) /* Access flag enable */ +#define CR_TE (1 << 30) /* Thumb exception enable */ + +#ifndef __ASSEMBLY__ + +#if __LINUX_ARM_ARCH__ >= 4 +#define vectors_high() (cr_alignment & CR_V) +#else +#define vectors_high() (0) +#endif + +extern unsigned long cr_no_alignment; /* defined in entry-armv.S */ +extern unsigned long cr_alignment; /* defined in entry-armv.S */ + +static inline unsigned int get_cr(void) +{ + unsigned int val; + asm("mrc p15, 0, %0, c1, c0, 0 @ get CR" : "=r" (val) : : "cc"); + return val; +} + +static inline void set_cr(unsigned int val) +{ + asm volatile("mcr p15, 0, %0, c1, c0, 0 @ set CR" + : : "r" (val) : "cc"); + isb(); +} + +#ifndef CONFIG_SMP +extern void adjust_cr(unsigned long mask, unsigned long set); +#endif + +#define CPACC_FULL(n) (3 << (n * 2)) +#define CPACC_SVC(n) (1 << (n * 2)) +#define CPACC_DISABLE(n) (0 << (n * 2)) + +static inline unsigned int get_copro_access(void) +{ + unsigned int val; + asm("mrc p15, 0, %0, c1, c0, 2 @ get copro access" + : "=r" (val) : : "cc"); + return val; +} + +static inline void set_copro_access(unsigned int val) +{ + asm volatile("mcr p15, 0, %0, c1, c0, 2 @ set copro access" + : : "r" (val) : "cc"); + isb(); +} + +#endif + +#endif diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index 0e9ce8d9686e..38050b1c4800 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -130,8 +130,4 @@ struct mm_struct; extern unsigned long arch_randomize_brk(struct mm_struct *mm); #define arch_randomize_brk arch_randomize_brk -extern int vectors_user_mapping(void); -#define arch_setup_additional_pages(bprm, uses_interp) vectors_user_mapping() -#define ARCH_HAS_SETUP_ADDITIONAL_PAGES - #endif diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 7df239bcdf27..c4c87bc12231 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -103,11 +103,11 @@ #define L2X0_ADDR_FILTER_EN 1 #ifndef __ASSEMBLY__ -extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask); +extern void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask); #if defined(CONFIG_CACHE_L2X0) && defined(CONFIG_OF) -extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask); +extern int l2x0_of_init(u32 aux_val, u32 aux_mask); #else -static inline int l2x0_of_init(__u32 aux_val, __u32 aux_mask) +static inline int l2x0_of_init(u32 aux_val, u32 aux_mask) { return -ENODEV; } diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h new file mode 100644 index 000000000000..5c5ca2ea62b0 --- /dev/null +++ b/arch/arm/include/asm/jump_label.h @@ -0,0 +1,41 @@ +#ifndef _ASM_ARM_JUMP_LABEL_H +#define _ASM_ARM_JUMP_LABEL_H + +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <asm/system.h> + +#define JUMP_LABEL_NOP_SIZE 4 + +#ifdef CONFIG_THUMB2_KERNEL +#define JUMP_LABEL_NOP "nop.w" +#else +#define JUMP_LABEL_NOP "nop" +#endif + +static __always_inline bool arch_static_branch(struct jump_label_key *key) +{ + asm goto("1:\n\t" + JUMP_LABEL_NOP "\n\t" + ".pushsection __jump_table, \"aw\"\n\t" + ".word 1b, %l[l_yes], %c0\n\t" + ".popsection\n\t" + : : "i" (key) : : l_yes); + + return false; +l_yes: + return true; +} + +#endif /* __KERNEL__ */ + +typedef u32 jump_label_t; + +struct jump_entry { + jump_label_t code; + jump_label_t target; + jump_label_t key; +}; + +#endif diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index a8997d71084e..fcb575747e5e 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -116,6 +116,8 @@ #define MODULES_END (END_MEM) #define MODULES_VADDR (PHYS_OFFSET) +#define XIP_VIRT_ADDR(physaddr) (physaddr) + #endif /* !CONFIG_MMU */ /* diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index 71605d9f8e42..a0b3cac0547c 100644 --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -18,6 +18,7 @@ #include <asm/cacheflush.h> #include <asm/cachetype.h> #include <asm/proc-fns.h> +#include <asm-generic/mm_hooks.h> void __check_kvm_seq(struct mm_struct *mm); @@ -133,32 +134,4 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, #define deactivate_mm(tsk,mm) do { } while (0) #define activate_mm(prev,next) switch_mm(prev, next, NULL) -/* - * We are inserting a "fake" vma for the user-accessible vector page so - * gdb and friends can get to it through ptrace and /proc/<pid>/mem. - * But we also want to remove it before the generic code gets to see it - * during process exit or the unmapping of it would cause total havoc. - * (the macro is used as remove_vma() is static to mm/mmap.c) - */ -#define arch_exit_mmap(mm) \ -do { \ - struct vm_area_struct *high_vma = find_vma(mm, 0xffff0000); \ - if (high_vma) { \ - BUG_ON(high_vma->vm_next); /* it should be last */ \ - if (high_vma->vm_prev) \ - high_vma->vm_prev->vm_next = NULL; \ - else \ - mm->mmap = NULL; \ - rb_erase(&high_vma->vm_rb, &mm->mm_rb); \ - mm->mmap_cache = NULL; \ - mm->map_count--; \ - remove_vma(high_vma); \ - } \ -} while (0) - -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) -{ -} - #endif diff --git a/arch/arm/include/asm/opcodes.h b/arch/arm/include/asm/opcodes.h index c0efdd60966f..19c48deda70f 100644 --- a/arch/arm/include/asm/opcodes.h +++ b/arch/arm/include/asm/opcodes.h @@ -17,4 +17,63 @@ extern asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr); #define ARM_OPCODE_CONDTEST_PASS 1 #define ARM_OPCODE_CONDTEST_UNCOND 2 + +/* + * Opcode byteswap helpers + * + * These macros help with converting instructions between a canonical integer + * format and in-memory representation, in an endianness-agnostic manner. + * + * __mem_to_opcode_*() convert from in-memory representation to canonical form. + * __opcode_to_mem_*() convert from canonical form to in-memory representation. + * + * + * Canonical instruction representation: + * + * ARM: 0xKKLLMMNN + * Thumb 16-bit: 0x0000KKLL, where KK < 0xE8 + * Thumb 32-bit: 0xKKLLMMNN, where KK >= 0xE8 + * + * There is no way to distinguish an ARM instruction in canonical representation + * from a Thumb instruction (just as these cannot be distinguished in memory). + * Where this distinction is important, it needs to be tracked separately. + * + * Note that values in the range 0x0000E800..0xE7FFFFFF intentionally do not + * represent any valid Thumb-2 instruction. For this range, + * __opcode_is_thumb32() and __opcode_is_thumb16() will both be false. + */ + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> +#include <linux/swab.h> + +#ifdef CONFIG_CPU_ENDIAN_BE8 +#define __opcode_to_mem_arm(x) swab32(x) +#define __opcode_to_mem_thumb16(x) swab16(x) +#define __opcode_to_mem_thumb32(x) swahb32(x) +#else +#define __opcode_to_mem_arm(x) ((u32)(x)) +#define __opcode_to_mem_thumb16(x) ((u16)(x)) +#define __opcode_to_mem_thumb32(x) swahw32(x) +#endif + +#define __mem_to_opcode_arm(x) __opcode_to_mem_arm(x) +#define __mem_to_opcode_thumb16(x) __opcode_to_mem_thumb16(x) +#define __mem_to_opcode_thumb32(x) __opcode_to_mem_thumb32(x) + +/* Operations specific to Thumb opcodes */ + +/* Instruction size checks: */ +#define __opcode_is_thumb32(x) ((u32)(x) >= 0xE8000000UL) +#define __opcode_is_thumb16(x) ((u32)(x) < 0xE800UL) + +/* Operations to construct or split 32-bit Thumb instructions: */ +#define __opcode_thumb32_first(x) ((u16)((x) >> 16)) +#define __opcode_thumb32_second(x) ((u16)(x)) +#define __opcode_thumb32_compose(first, second) \ + (((u32)(u16)(first) << 16) | (u32)(u16)(second)) + +#endif /* __ASSEMBLY__ */ + #endif /* __ASM_ARM_OPCODES_H */ diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index 97b440c25c58..5838361c48b3 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -151,6 +151,8 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from, #define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) extern void copy_page(void *to, const void *from); +#define __HAVE_ARCH_GATE_AREA 1 + #ifdef CONFIG_ARM_LPAE #include <asm/pgtable-3level-types.h> #else diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h index 99cfe3607989..ee7c056be3f4 100644 --- a/arch/arm/include/asm/perf_event.h +++ b/arch/arm/include/asm/perf_event.h @@ -26,6 +26,7 @@ enum arm_perf_pmu_ids { ARM_PERF_PMU_ID_CA9, ARM_PERF_PMU_ID_CA5, ARM_PERF_PMU_ID_CA15, + ARM_PERF_PMU_ID_CA7, ARM_NUM_PMU_IDS, }; diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index ce280b8d613c..d7038fa22343 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -55,7 +55,6 @@ struct thread_struct { #define start_thread(regs,pc,sp) \ ({ \ unsigned long *stack = (unsigned long *)sp; \ - set_fs(USER_DS); \ memset(regs->uregs, 0, sizeof(regs->uregs)); \ if (current->personality & ADDR_LIMIT_32BIT) \ regs->ARM_cpsr = USR_MODE; \ diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h index ee0363307918..aeae9c609df4 100644 --- a/arch/arm/include/asm/prom.h +++ b/arch/arm/include/asm/prom.h @@ -13,8 +13,6 @@ #ifdef CONFIG_OF -#include <asm/irq.h> - extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys); extern void arm_dt_memblock_reserve(void); diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index 424aa458c487..f7263652d2dc 100644 --- a/arch/arm/include/asm/system.h +++ b/arch/arm/include/asm/system.h @@ -15,37 +15,6 @@ #define CPU_ARCH_ARMv7 9 /* - * CR1 bits (CP#15 CR1) - */ -#define CR_M (1 << 0) /* MMU enable */ -#define CR_A (1 << 1) /* Alignment abort enable */ -#define CR_C (1 << 2) /* Dcache enable */ -#define CR_W (1 << 3) /* Write buffer enable */ -#define CR_P (1 << 4) /* 32-bit exception handler */ -#define CR_D (1 << 5) /* 32-bit data address range */ -#define CR_L (1 << 6) /* Implementation defined */ -#define CR_B (1 << 7) /* Big endian */ -#define CR_S (1 << 8) /* System MMU protection */ -#define CR_R (1 << 9) /* ROM MMU protection */ -#define CR_F (1 << 10) /* Implementation defined */ -#define CR_Z (1 << 11) /* Implementation defined */ -#define CR_I (1 << 12) /* Icache enable */ -#define CR_V (1 << 13) /* Vectors relocated to 0xffff0000 */ -#define CR_RR (1 << 14) /* Round Robin cache replacement */ -#define CR_L4 (1 << 15) /* LDR pc can set T bit */ -#define CR_DT (1 << 16) -#define CR_IT (1 << 18) -#define CR_ST (1 << 19) -#define CR_FI (1 << 21) /* Fast interrupt (lower latency mode) */ -#define CR_U (1 << 22) /* Unaligned access operation */ -#define CR_XP (1 << 23) /* Extended page tables */ -#define CR_VE (1 << 24) /* Vectored interrupts */ -#define CR_EE (1 << 25) /* Exception (Big) Endian */ -#define CR_TRE (1 << 28) /* TEX remap enable */ -#define CR_AFE (1 << 29) /* Access flag enable */ -#define CR_TE (1 << 30) /* Thumb exception enable */ - -/* * This is used to ensure the compiler did actually allocate the register we * asked it for some inline assembly sequences. Apparently we can't trust * the compiler from one version to another so a bit of paranoia won't hurt. @@ -120,12 +89,6 @@ extern void (*arm_pm_idle)(void); extern unsigned int user_debug; -#if __LINUX_ARM_ARCH__ >= 4 -#define vectors_high() (cr_alignment & CR_V) -#else -#define vectors_high() (0) -#endif - #if __LINUX_ARM_ARCH__ >= 7 || \ (__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K)) #define sev() __asm__ __volatile__ ("sev" : : : "memory") @@ -186,46 +149,6 @@ extern unsigned int user_debug; #define set_mb(var, value) do { var = value; smp_mb(); } while (0) #define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t"); -extern unsigned long cr_no_alignment; /* defined in entry-armv.S */ -extern unsigned long cr_alignment; /* defined in entry-armv.S */ - -static inline unsigned int get_cr(void) -{ - unsigned int val; - asm("mrc p15, 0, %0, c1, c0, 0 @ get CR" : "=r" (val) : : "cc"); - return val; -} - -static inline void set_cr(unsigned int val) -{ - asm volatile("mcr p15, 0, %0, c1, c0, 0 @ set CR" - : : "r" (val) : "cc"); - isb(); -} - -#ifndef CONFIG_SMP -extern void adjust_cr(unsigned long mask, unsigned long set); -#endif - -#define CPACC_FULL(n) (3 << (n * 2)) -#define CPACC_SVC(n) (1 << (n * 2)) -#define CPACC_DISABLE(n) (0 << (n * 2)) - -static inline unsigned int get_copro_access(void) -{ - unsigned int val; - asm("mrc p15, 0, %0, c1, c0, 2 @ get copro access" - : "=r" (val) : : "cc"); - return val; -} - -static inline void set_copro_access(unsigned int val) -{ - asm volatile("mcr p15, 0, %0, c1, c0, 2 @ set copro access" - : : "r" (val) : "cc"); - isb(); -} - /* * switch_mm() may do a full cache flush over the context switch, * so enable interrupts over the context switch to avoid high diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 02b2f8203982..85fe61e73202 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -318,6 +318,21 @@ extern struct cpu_tlb_fns cpu_tlb; #define tlb_flag(f) ((always_tlb_flags & (f)) || (__tlb_flag & possible_tlb_flags & (f))) +#define __tlb_op(f, insnarg, arg) \ + do { \ + if (always_tlb_flags & (f)) \ + asm("mcr " insnarg \ + : : "r" (arg) : "cc"); \ + else if (possible_tlb_flags & (f)) \ + asm("tst %1, %2\n\t" \ + "mcrne " insnarg \ + : : "r" (arg), "r" (__tlb_flag), "Ir" (f) \ + : "cc"); \ + } while (0) + +#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) { const int zero = 0; @@ -326,16 +341,11 @@ static inline void local_flush_tlb_all(void) if (tlb_flag(TLB_WB)) dsb(); - if (tlb_flag(TLB_V3_FULL)) - asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_V4_U_FULL | TLB_V6_U_FULL)) - asm("mcr p15, 0, %0, c8, c7, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_V4_D_FULL | TLB_V6_D_FULL)) - asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_V4_I_FULL | TLB_V6_I_FULL)) - asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_V7_UIS_FULL)) - asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc"); + tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); + 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); if (tlb_flag(TLB_BARRIER)) { dsb(); @@ -352,29 +362,23 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm) if (tlb_flag(TLB_WB)) dsb(); - if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { - if (tlb_flag(TLB_V3_FULL)) - asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_V4_U_FULL)) - asm("mcr p15, 0, %0, c8, c7, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_V4_D_FULL)) - asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_V4_I_FULL)) - asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc"); + if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { + if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { + tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); + 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(); } - put_cpu(); - - if (tlb_flag(TLB_V6_U_ASID)) - asm("mcr p15, 0, %0, c8, c7, 2" : : "r" (asid) : "cc"); - if (tlb_flag(TLB_V6_D_ASID)) - asm("mcr p15, 0, %0, c8, c6, 2" : : "r" (asid) : "cc"); - if (tlb_flag(TLB_V6_I_ASID)) - asm("mcr p15, 0, %0, c8, c5, 2" : : "r" (asid) : "cc"); - if (tlb_flag(TLB_V7_UIS_ASID)) + + 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); #ifdef CONFIG_ARM_ERRATA_720789 - asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc"); + tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero); #else - asm("mcr p15, 0, %0, c8, c3, 2" : : "r" (asid) : "cc"); + tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid); #endif if (tlb_flag(TLB_BARRIER)) @@ -392,30 +396,23 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) if (tlb_flag(TLB_WB)) dsb(); - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { - if (tlb_flag(TLB_V3_PAGE)) - asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (uaddr) : "cc"); - if (tlb_flag(TLB_V4_U_PAGE)) - asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (uaddr) : "cc"); - if (tlb_flag(TLB_V4_D_PAGE)) - asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc"); - if (tlb_flag(TLB_V4_I_PAGE)) - asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc"); + if (possible_tlb_flags & (TLB_V3_PAGE|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_V3_PAGE, "c6, c0, 0", uaddr); + tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr); + tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr); + tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr); if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL)) asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc"); } - if (tlb_flag(TLB_V6_U_PAGE)) - asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (uaddr) : "cc"); - if (tlb_flag(TLB_V6_D_PAGE)) - asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc"); - if (tlb_flag(TLB_V6_I_PAGE)) - asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc"); - if (tlb_flag(TLB_V7_UIS_PAGE)) + 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); #ifdef CONFIG_ARM_ERRATA_720789 - asm("mcr p15, 0, %0, c8, c3, 3" : : "r" (uaddr & PAGE_MASK) : "cc"); + tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK); #else - asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (uaddr) : "cc"); + tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", uaddr); #endif if (tlb_flag(TLB_BARRIER)) @@ -432,25 +429,17 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) if (tlb_flag(TLB_WB)) dsb(); - if (tlb_flag(TLB_V3_PAGE)) - asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (kaddr) : "cc"); - if (tlb_flag(TLB_V4_U_PAGE)) - asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (kaddr) : "cc"); - if (tlb_flag(TLB_V4_D_PAGE)) - asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc"); - if (tlb_flag(TLB_V4_I_PAGE)) - asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc"); + tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr); + 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); if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL)) asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_V6_U_PAGE)) - asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (kaddr) : "cc"); - if (tlb_flag(TLB_V6_D_PAGE)) - asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc"); - if (tlb_flag(TLB_V6_I_PAGE)) - asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc"); - if (tlb_flag(TLB_V7_UIS_PAGE)) - asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (kaddr) : "cc"); + 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); + tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr); if (tlb_flag(TLB_BARRIER)) { dsb(); @@ -475,13 +464,8 @@ static inline void flush_pmd_entry(void *pmd) { const unsigned int __tlb_flag = __cpu_tlb_flags; - if (tlb_flag(TLB_DCLEAN)) - asm("mcr p15, 0, %0, c7, c10, 1 @ flush_pmd" - : : "r" (pmd) : "cc"); - - if (tlb_flag(TLB_L2CLEAN_FR)) - asm("mcr p15, 1, %0, c15, c9, 1 @ L2 flush_pmd" - : : "r" (pmd) : "cc"); + tlb_op(TLB_DCLEAN, "c7, c10, 1 @ flush_pmd", pmd); + tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1 @ L2 flush_pmd", pmd); if (tlb_flag(TLB_WB)) dsb(); @@ -491,15 +475,11 @@ static inline void clean_pmd_entry(void *pmd) { const unsigned int __tlb_flag = __cpu_tlb_flags; - if (tlb_flag(TLB_DCLEAN)) - asm("mcr p15, 0, %0, c7, c10, 1 @ flush_pmd" - : : "r" (pmd) : "cc"); - - if (tlb_flag(TLB_L2CLEAN_FR)) - asm("mcr p15, 1, %0, c15, c9, 1 @ L2 flush_pmd" - : : "r" (pmd) : "cc"); + tlb_op(TLB_DCLEAN, "c7, c10, 1 @ flush_pmd", pmd); + tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1 @ L2 flush_pmd", pmd); } +#undef tlb_op #undef tlb_flag #undef always_tlb_flags #undef possible_tlb_flags diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h index 5b29a6673625..f555bb3664dc 100644 --- a/arch/arm/include/asm/traps.h +++ b/arch/arm/include/asm/traps.h @@ -46,7 +46,7 @@ static inline int in_exception_text(unsigned long ptr) return in ? : __in_irqentry_text(ptr); } -extern void __init early_trap_init(void); +extern void __init early_trap_init(void *); extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame); extern void ptrace_break(struct task_struct *tsk, struct pt_regs *regs); diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 9b0eb3febcb0..3c1593050eb6 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -7,6 +7,8 @@ AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_ftrace.o = -pg +CFLAGS_REMOVE_insn.o = -pg +CFLAGS_REMOVE_patch.o = -pg endif CFLAGS_REMOVE_return_address.o = -pg @@ -33,10 +35,11 @@ obj-$(CONFIG_ARM_CPU_SUSPEND) += sleep.o suspend.o obj-$(CONFIG_SMP) += smp.o smp_tlb.o obj-$(CONFIG_HAVE_ARM_SCU) += smp_scu.o obj-$(CONFIG_HAVE_ARM_TWD) += smp_twd.o -obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o insn.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o insn.o +obj-$(CONFIG_JUMP_LABEL) += jump_label.o insn.o patch.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o -obj-$(CONFIG_KPROBES) += kprobes.o kprobes-common.o +obj-$(CONFIG_KPROBES) += kprobes.o kprobes-common.o patch.o ifdef CONFIG_THUMB2_KERNEL obj-$(CONFIG_KPROBES) += kprobes-thumb.o else diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S index 204e2160cfcc..e5a765c5f06a 100644 --- a/arch/arm/kernel/debug.S +++ b/arch/arm/kernel/debug.S @@ -100,7 +100,7 @@ #endif /* CONFIG_CPU_V6 */ -#else +#elif !defined(CONFIG_DEBUG_SEMIHOSTING) #include <mach/debug-macro.S> #endif /* CONFIG_DEBUG_ICEDCC */ @@ -155,6 +155,8 @@ hexbuf: .space 16 .ltorg +#ifndef CONFIG_DEBUG_SEMIHOSTING + ENTRY(printascii) addruart_current r3, r1, r2 b 2f @@ -177,3 +179,24 @@ ENTRY(printch) mov r0, #0 b 1b ENDPROC(printch) + +#else + +ENTRY(printascii) + mov r1, r0 + mov r0, #0x04 @ SYS_WRITE0 + ARM( svc #0x123456 ) + THUMB( svc #0xab ) + mov pc, lr +ENDPROC(printascii) + +ENTRY(printch) + adr r1, hexbuf + strb r0, [r1] + mov r0, #0x03 @ SYS_WRITEC + ARM( svc #0x123456 ) + THUMB( svc #0xab ) + mov pc, lr +ENDPROC(printch) + +#endif diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c index 4c164ece5891..c32f8456aa09 100644 --- a/arch/arm/kernel/fiq.c +++ b/arch/arm/kernel/fiq.c @@ -42,9 +42,9 @@ #include <linux/seq_file.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> #include <asm/fiq.h> #include <asm/irq.h> -#include <asm/system.h> #include <asm/traps.h> static unsigned long no_fiq_insn; diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index c0062ad1e847..df0bf0c8cb79 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -16,10 +16,13 @@ #include <linux/uaccess.h> #include <asm/cacheflush.h> +#include <asm/opcodes.h> #include <asm/ftrace.h> +#include "insn.h" + #ifdef CONFIG_THUMB2_KERNEL -#define NOP 0xeb04f85d /* pop.w {lr} */ +#define NOP 0xf85deb04 /* pop.w {lr} */ #else #define NOP 0xe8bd4000 /* pop {lr} */ #endif @@ -60,76 +63,31 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr) } #endif -#ifdef CONFIG_THUMB2_KERNEL -static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr, - bool link) -{ - unsigned long s, j1, j2, i1, i2, imm10, imm11; - unsigned long first, second; - long offset; - - offset = (long)addr - (long)(pc + 4); - if (offset < -16777216 || offset > 16777214) { - WARN_ON_ONCE(1); - return 0; - } - - s = (offset >> 24) & 0x1; - i1 = (offset >> 23) & 0x1; - i2 = (offset >> 22) & 0x1; - imm10 = (offset >> 12) & 0x3ff; - imm11 = (offset >> 1) & 0x7ff; - - j1 = (!i1) ^ s; - j2 = (!i2) ^ s; - - first = 0xf000 | (s << 10) | imm10; - second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11; - if (link) - second |= 1 << 14; - - return (second << 16) | first; -} -#else -static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr, - bool link) -{ - unsigned long opcode = 0xea000000; - long offset; - - if (link) - opcode |= 1 << 24; - - offset = (long)addr - (long)(pc + 8); - if (unlikely(offset < -33554432 || offset > 33554428)) { - /* Can't generate branches that far (from ARM ARM). Ftrace - * doesn't generate branches outside of kernel text. - */ - WARN_ON_ONCE(1); - return 0; - } - - offset = (offset >> 2) & 0x00ffffff; - - return opcode | offset; -} -#endif - static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr) { - return ftrace_gen_branch(pc, addr, true); + return arm_gen_branch_link(pc, addr); } static int ftrace_modify_code(unsigned long pc, unsigned long old, - unsigned long new) + unsigned long new, bool validate) { unsigned long replaced; - if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE)) - return -EFAULT; + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + old = __opcode_to_mem_thumb32(old); + new = __opcode_to_mem_thumb32(new); + } else { + old = __opcode_to_mem_arm(old); + new = __opcode_to_mem_arm(new); + } - if (replaced != old) - return -EINVAL; + if (validate) { + if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE)) + return -EFAULT; + + if (replaced != old) + return -EINVAL; + } if (probe_kernel_write((void *)pc, &new, MCOUNT_INSN_SIZE)) return -EPERM; @@ -141,23 +99,21 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old, int ftrace_update_ftrace_func(ftrace_func_t func) { - unsigned long pc, old; + unsigned long pc; unsigned long new; int ret; pc = (unsigned long)&ftrace_call; - memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE); new = ftrace_call_replace(pc, (unsigned long)func); - ret = ftrace_modify_code(pc, old, new); + ret = ftrace_modify_code(pc, 0, new, false); #ifdef CONFIG_OLD_MCOUNT if (!ret) { pc = (unsigned long)&ftrace_call_old; - memcpy(&old, &ftrace_call_old, MCOUNT_INSN_SIZE); new = ftrace_call_replace(pc, (unsigned long)func); - ret = ftrace_modify_code(pc, old, new); + ret = ftrace_modify_code(pc, 0, new, false); } #endif @@ -172,7 +128,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) old = ftrace_nop_replace(rec); new = ftrace_call_replace(ip, adjust_address(rec, addr)); - return ftrace_modify_code(rec->ip, old, new); + return ftrace_modify_code(rec->ip, old, new, true); } int ftrace_make_nop(struct module *mod, @@ -185,7 +141,7 @@ int ftrace_make_nop(struct module *mod, old = ftrace_call_replace(ip, adjust_address(rec, addr)); new = ftrace_nop_replace(rec); - ret = ftrace_modify_code(ip, old, new); + ret = ftrace_modify_code(ip, old, new, true); #ifdef CONFIG_OLD_MCOUNT if (ret == -EINVAL && addr == MCOUNT_ADDR) { @@ -193,7 +149,7 @@ int ftrace_make_nop(struct module *mod, old = ftrace_call_replace(ip, adjust_address(rec, addr)); new = ftrace_nop_replace(rec); - ret = ftrace_modify_code(ip, old, new); + ret = ftrace_modify_code(ip, old, new, true); } #endif @@ -249,12 +205,12 @@ static int __ftrace_modify_caller(unsigned long *callsite, { unsigned long caller_fn = (unsigned long) func; unsigned long pc = (unsigned long) callsite; - unsigned long branch = ftrace_gen_branch(pc, caller_fn, false); + unsigned long branch = arm_gen_branch(pc, caller_fn); unsigned long nop = 0xe1a00000; /* mov r0, r0 */ unsigned long old = enable ? nop : branch; unsigned long new = enable ? branch : nop; - return ftrace_modify_code(pc, old, new); + return ftrace_modify_code(pc, old, new, true); } static int ftrace_modify_graph_caller(bool enable) diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index d46f25968bec..278cfc144f44 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -17,8 +17,8 @@ #include <asm/assembler.h> #include <asm/ptrace.h> #include <asm/asm-offsets.h> +#include <asm/cp15.h> #include <asm/thread_info.h> -#include <asm/system.h> /* * Kernel startup entry point. diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 6d5791144066..3bf0c7f8b043 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -15,12 +15,12 @@ #include <linux/init.h> #include <asm/assembler.h> +#include <asm/cp15.h> #include <asm/domain.h> #include <asm/ptrace.h> #include <asm/asm-offsets.h> #include <asm/memory.h> #include <asm/thread_info.h> -#include <asm/system.h> #include <asm/pgtable.h> #ifdef CONFIG_DEBUG_LL @@ -265,7 +265,7 @@ __create_page_tables: str r6, [r3] #ifdef CONFIG_DEBUG_LL -#ifndef CONFIG_DEBUG_ICEDCC +#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING) /* * Map in IO space for serial debugging. * This allows debug messages to be output @@ -297,10 +297,10 @@ __create_page_tables: cmp r0, r6 blo 1b -#else /* CONFIG_DEBUG_ICEDCC */ - /* we don't need any serial debugging mappings for ICEDCC */ +#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */ + /* we don't need any serial debugging mappings */ ldr r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags -#endif /* !CONFIG_DEBUG_ICEDCC */ +#endif #if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS) /* diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c new file mode 100644 index 000000000000..ab312e516546 --- /dev/null +++ b/arch/arm/kernel/insn.c @@ -0,0 +1,61 @@ +#include <linux/kernel.h> +#include <asm/opcodes.h> + +static unsigned long +__arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link) +{ + unsigned long s, j1, j2, i1, i2, imm10, imm11; + unsigned long first, second; + long offset; + + offset = (long)addr - (long)(pc + 4); + if (offset < -16777216 || offset > 16777214) { + WARN_ON_ONCE(1); + return 0; + } + + s = (offset >> 24) & 0x1; + i1 = (offset >> 23) & 0x1; + i2 = (offset >> 22) & 0x1; + imm10 = (offset >> 12) & 0x3ff; + imm11 = (offset >> 1) & 0x7ff; + + j1 = (!i1) ^ s; + j2 = (!i2) ^ s; + + first = 0xf000 | (s << 10) | imm10; + second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11; + if (link) + second |= 1 << 14; + + return __opcode_thumb32_compose(first, second); +} + +static unsigned long +__arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link) +{ + unsigned long opcode = 0xea000000; + long offset; + + if (link) + opcode |= 1 << 24; + + offset = (long)addr - (long)(pc + 8); + if (unlikely(offset < -33554432 || offset > 33554428)) { + WARN_ON_ONCE(1); + return 0; + } + + offset = (offset >> 2) & 0x00ffffff; + + return opcode | offset; +} + +unsigned long +__arm_gen_branch(unsigned long pc, unsigned long addr, bool link) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) + return __arm_gen_branch_thumb2(pc, addr, link); + else + return __arm_gen_branch_arm(pc, addr, link); +} diff --git a/arch/arm/kernel/insn.h b/arch/arm/kernel/insn.h new file mode 100644 index 000000000000..e96065da4dae --- /dev/null +++ b/arch/arm/kernel/insn.h @@ -0,0 +1,29 @@ +#ifndef __ASM_ARM_INSN_H +#define __ASM_ARM_INSN_H + +static inline unsigned long +arm_gen_nop(void) +{ +#ifdef CONFIG_THUMB2_KERNEL + return 0xf3af8000; /* nop.w */ +#else + return 0xe1a00000; /* mov r0, r0 */ +#endif +} + +unsigned long +__arm_gen_branch(unsigned long pc, unsigned long addr, bool link); + +static inline unsigned long +arm_gen_branch(unsigned long pc, unsigned long addr) +{ + return __arm_gen_branch(pc, addr, false); +} + +static inline unsigned long +arm_gen_branch_link(unsigned long pc, unsigned long addr) +{ + return __arm_gen_branch(pc, addr, true); +} + +#endif diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 3efd82cc95f0..3f86ee11f54e 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -181,10 +181,7 @@ void migrate_irqs(void) local_irq_save(flags); for_each_irq_desc(i, desc) { - bool affinity_broken = false; - - if (!desc) - continue; + bool affinity_broken; raw_spin_lock(&desc->lock); affinity_broken = migrate_one_irq(desc); diff --git a/arch/arm/kernel/jump_label.c b/arch/arm/kernel/jump_label.c new file mode 100644 index 000000000000..4ce4f789446d --- /dev/null +++ b/arch/arm/kernel/jump_label.c @@ -0,0 +1,39 @@ +#include <linux/kernel.h> +#include <linux/jump_label.h> + +#include "insn.h" +#include "patch.h" + +#ifdef HAVE_JUMP_LABEL + +static void __arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + bool is_static) +{ + void *addr = (void *)entry->code; + unsigned int insn; + + if (type == JUMP_LABEL_ENABLE) + insn = arm_gen_branch(entry->code, entry->target); + else + insn = arm_gen_nop(); + + if (is_static) + __patch_text(addr, insn); + else + patch_text(addr, insn); +} + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + __arch_jump_label_transform(entry, type, false); +} + +void arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type) +{ + __arch_jump_label_transform(entry, type, true); +} + +#endif diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 129c1163248b..ab1869dac97a 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -29,6 +29,7 @@ #include <asm/cacheflush.h> #include "kprobes.h" +#include "patch.h" #define MIN_STACK_SIZE(addr) \ min((unsigned long)MAX_STACK_SIZE, \ @@ -103,57 +104,33 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return 0; } -#ifdef CONFIG_THUMB2_KERNEL - -/* - * For a 32-bit Thumb breakpoint spanning two memory words we need to take - * special precautions to insert the breakpoint atomically, especially on SMP - * systems. This is achieved by calling this arming function using stop_machine. - */ -static int __kprobes set_t32_breakpoint(void *addr) -{ - ((u16 *)addr)[0] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION >> 16; - ((u16 *)addr)[1] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION & 0xffff; - flush_insns(addr, 2*sizeof(u16)); - return 0; -} - void __kprobes arch_arm_kprobe(struct kprobe *p) { - uintptr_t addr = (uintptr_t)p->addr & ~1; /* Remove any Thumb flag */ - - if (!is_wide_instruction(p->opcode)) { - *(u16 *)addr = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION; - flush_insns(addr, sizeof(u16)); - } else if (addr & 2) { - /* A 32-bit instruction spanning two words needs special care */ - stop_machine(set_t32_breakpoint, (void *)addr, &cpu_online_map); + unsigned int brkp; + void *addr; + + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + /* Remove any Thumb flag */ + addr = (void *)((uintptr_t)p->addr & ~1); + + if (is_wide_instruction(p->opcode)) + brkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION; + else + brkp = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION; } else { - /* Word aligned 32-bit instruction can be written atomically */ - u32 bkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION; -#ifndef __ARMEB__ /* Swap halfwords for little-endian */ - bkp = (bkp >> 16) | (bkp << 16); -#endif - *(u32 *)addr = bkp; - flush_insns(addr, sizeof(u32)); - } -} + kprobe_opcode_t insn = p->opcode; -#else /* !CONFIG_THUMB2_KERNEL */ + addr = p->addr; + brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION; -void __kprobes arch_arm_kprobe(struct kprobe *p) -{ - kprobe_opcode_t insn = p->opcode; - kprobe_opcode_t brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION; - if (insn >= 0xe0000000) - brkp |= 0xe0000000; /* Unconditional instruction */ - else - brkp |= insn & 0xf0000000; /* Copy condition from insn */ - *p->addr = brkp; - flush_insns(p->addr, sizeof(p->addr[0])); -} + if (insn >= 0xe0000000) + brkp |= 0xe0000000; /* Unconditional instruction */ + else + brkp |= insn & 0xf0000000; /* Copy condition from insn */ + } -#endif /* !CONFIG_THUMB2_KERNEL */ + patch_text(addr, brkp); +} /* * The actual disarming is done here on each CPU and synchronized using @@ -166,25 +143,10 @@ void __kprobes arch_arm_kprobe(struct kprobe *p) int __kprobes __arch_disarm_kprobe(void *p) { struct kprobe *kp = p; -#ifdef CONFIG_THUMB2_KERNEL - u16 *addr = (u16 *)((uintptr_t)kp->addr & ~1); - kprobe_opcode_t insn = kp->opcode; - unsigned int len; + void *addr = (void *)((uintptr_t)kp->addr & ~1); - if (is_wide_instruction(insn)) { - ((u16 *)addr)[0] = insn>>16; - ((u16 *)addr)[1] = insn; - len = 2*sizeof(u16); - } else { - ((u16 *)addr)[0] = insn; - len = sizeof(u16); - } - flush_insns(addr, len); + __patch_text(addr, kp->opcode); -#else /* !CONFIG_THUMB2_KERNEL */ - *kp->addr = kp->opcode; - flush_insns(kp->addr, sizeof(kp->addr[0])); -#endif return 0; } diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 764bd456d84f..a30004476e70 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -7,6 +7,7 @@ #include <linux/delay.h> #include <linux/reboot.h> #include <linux/io.h> +#include <linux/irq.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/mmu_context.h> @@ -53,6 +54,29 @@ void machine_crash_nonpanic_core(void *unused) cpu_relax(); } +static void machine_kexec_mask_interrupts(void) +{ + unsigned int i; + struct irq_desc *desc; + + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + + chip = irq_desc_get_chip(desc); + if (!chip) + continue; + + if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_mask) + chip->irq_mask(&desc->irq_data); + + if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) + chip->irq_disable(&desc->irq_data); + } +} + void machine_crash_shutdown(struct pt_regs *regs) { unsigned long msecs; @@ -70,6 +94,7 @@ void machine_crash_shutdown(struct pt_regs *regs) printk(KERN_WARNING "Non-crashing CPUs did not react to IPI\n"); crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); printk(KERN_INFO "Loading crashdump kernel...\n"); } diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c new file mode 100644 index 000000000000..07314af47733 --- /dev/null +++ b/arch/arm/kernel/patch.c @@ -0,0 +1,75 @@ +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/stop_machine.h> + +#include <asm/cacheflush.h> +#include <asm/smp_plat.h> +#include <asm/opcodes.h> + +#include "patch.h" + +struct patch { + void *addr; + unsigned int insn; +}; + +void __kprobes __patch_text(void *addr, unsigned int insn) +{ + bool thumb2 = IS_ENABLED(CONFIG_THUMB2_KERNEL); + int size; + + if (thumb2 && __opcode_is_thumb16(insn)) { + *(u16 *)addr = __opcode_to_mem_thumb16(insn); + size = sizeof(u16); + } else if (thumb2 && ((uintptr_t)addr & 2)) { + u16 first = __opcode_thumb32_first(insn); + u16 second = __opcode_thumb32_second(insn); + u16 *addrh = addr; + + addrh[0] = __opcode_to_mem_thumb16(first); + addrh[1] = __opcode_to_mem_thumb16(second); + + size = sizeof(u32); + } else { + if (thumb2) + insn = __opcode_to_mem_thumb32(insn); + else + insn = __opcode_to_mem_arm(insn); + + *(u32 *)addr = insn; + size = sizeof(u32); + } + + flush_icache_range((uintptr_t)(addr), + (uintptr_t)(addr) + size); +} + +static int __kprobes patch_text_stop_machine(void *data) +{ + struct patch *patch = data; + + __patch_text(patch->addr, patch->insn); + + return 0; +} + +void __kprobes patch_text(void *addr, unsigned int insn) +{ + struct patch patch = { + .addr = addr, + .insn = insn, + }; + + if (cache_ops_need_broadcast()) { + stop_machine(patch_text_stop_machine, &patch, cpu_online_mask); + } else { + bool straddles_word = IS_ENABLED(CONFIG_THUMB2_KERNEL) + && __opcode_is_thumb32(insn) + && ((uintptr_t)addr & 2); + + if (straddles_word) + stop_machine(patch_text_stop_machine, &patch, NULL); + else + __patch_text(addr, insn); + } +} diff --git a/arch/arm/kernel/patch.h b/arch/arm/kernel/patch.h new file mode 100644 index 000000000000..b4731f2dac38 --- /dev/null +++ b/arch/arm/kernel/patch.h @@ -0,0 +1,7 @@ +#ifndef _ARM_KERNEL_PATCH_H +#define _ARM_KERNEL_PATCH_H + +void patch_text(void *addr, unsigned int insn); +void __patch_text(void *addr, unsigned int insn); + +#endif diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 5bb91bf3d47f..ab59c3bae5e8 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -712,6 +712,9 @@ init_hw_perf_events(void) case 0xC0F0: /* Cortex-A15 */ cpu_pmu = armv7_a15_pmu_init(); break; + case 0xC070: /* Cortex-A7 */ + cpu_pmu = armv7_a7_pmu_init(); + break; } /* Intel CPUs [xscale]. */ } else if (0x69 == implementor) { diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 460bbbb6b885..b2b764ec011b 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -582,6 +582,130 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] }; /* + * Cortex-A7 HW events mapping + */ +static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_BUS_CYCLES, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED, +}; + +static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + /* + * The performance counters don't differentiate between read + * and write accesses/misses so this isn't strictly correct, + * but it's the best we can do. Writes and reads get + * combined. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_CACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_CACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + +/* * Perf Events' indices */ #define ARMV7_IDX_CYCLE_COUNTER 0 @@ -1067,6 +1191,12 @@ static int armv7_a15_map_event(struct perf_event *event) &armv7_a15_perf_cache_map, 0xFF); } +static int armv7_a7_map_event(struct perf_event *event) +{ + return map_cpu_event(event, &armv7_a7_perf_map, + &armv7_a7_perf_cache_map, 0xFF); +} + static struct arm_pmu armv7pmu = { .handle_irq = armv7pmu_handle_irq, .enable = armv7pmu_enable_event, @@ -1127,6 +1257,16 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void) armv7pmu.set_event_filter = armv7pmu_set_event_filter; return &armv7pmu; } + +static struct arm_pmu *__init armv7_a7_pmu_init(void) +{ + armv7pmu.id = ARM_PERF_PMU_ID_CA7; + armv7pmu.name = "ARMv7 Cortex-A7"; + armv7pmu.map_event = armv7_a7_map_event; + armv7pmu.num_events = armv7_read_num_pmnc_events(); + armv7pmu.set_event_filter = armv7pmu_set_event_filter; + return &armv7pmu; +} #else static struct arm_pmu *__init armv7_a8_pmu_init(void) { @@ -1147,4 +1287,9 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void) { return NULL; } + +static struct arm_pmu *__init armv7_a7_pmu_init(void) +{ + return NULL; +} #endif /* CONFIG_CPU_V7 */ diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 008e7ce766a7..1531480aab48 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -531,22 +531,40 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) #ifdef CONFIG_MMU /* * The vectors page is always readable from user space for the - * atomic helpers and the signal restart code. Let's declare a mapping - * for it so it is visible through ptrace and /proc/<pid>/mem. + * atomic helpers and the signal restart code. Insert it into the + * gate_vma so that it is visible through ptrace and /proc/<pid>/mem. */ +static struct vm_area_struct gate_vma; -int vectors_user_mapping(void) +static int __init gate_vma_init(void) { - struct mm_struct *mm = current->mm; - return install_special_mapping(mm, 0xffff0000, PAGE_SIZE, - VM_READ | VM_EXEC | - VM_MAYREAD | VM_MAYEXEC | - VM_ALWAYSDUMP | VM_RESERVED, - NULL); + gate_vma.vm_start = 0xffff0000; + gate_vma.vm_end = 0xffff0000 + PAGE_SIZE; + gate_vma.vm_page_prot = PAGE_READONLY_EXEC; + gate_vma.vm_flags = VM_READ | VM_EXEC | + VM_MAYREAD | VM_MAYEXEC | + VM_ALWAYSDUMP; + return 0; +} +arch_initcall(gate_vma_init); + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +{ + return &gate_vma; +} + +int in_gate_area(struct mm_struct *mm, unsigned long addr) +{ + return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end); +} + +int in_gate_area_no_mm(unsigned long addr) +{ + return in_gate_area(NULL, addr); } const char *arch_vma_name(struct vm_area_struct *vma) { - return (vma->vm_start == 0xffff0000) ? "[vectors]" : NULL; + return (vma == &gate_vma) ? "[vectors]" : NULL; } #endif diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c index 5416c7c12528..27d186abbc06 100644 --- a/arch/arm/kernel/sched_clock.c +++ b/arch/arm/kernel/sched_clock.c @@ -10,6 +10,7 @@ #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/syscore_ops.h> #include <linux/timer.h> #include <asm/sched_clock.h> @@ -164,3 +165,20 @@ void __init sched_clock_postinit(void) sched_clock_poll(sched_clock_timer.data); } + +static int sched_clock_suspend(void) +{ + sched_clock_poll(sched_clock_timer.data); + return 0; +} + +static struct syscore_ops sched_clock_ops = { + .suspend = sched_clock_suspend, +}; + +static int __init sched_clock_syscore_init(void) +{ + register_syscore_ops(&sched_clock_ops); + return 0; +} +device_initcall(sched_clock_syscore_init); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 129fbd55bde8..e5c37fc1d1d6 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -34,6 +34,7 @@ #include <linux/sort.h> #include <asm/unified.h> +#include <asm/cp15.h> #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/elf.h> @@ -45,7 +46,6 @@ #include <asm/cacheflush.h> #include <asm/cachetype.h> #include <asm/tlbflush.h> -#include <asm/system.h> #include <asm/prom.h> #include <asm/mach/arch.h> @@ -961,7 +961,6 @@ void __init setup_arch(char **cmdline_p) conswitchp = &dummy_con; #endif #endif - early_trap_init(); if (mdesc->init_early) mdesc->init_early(); diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 0340224cf73c..d13e61ac18da 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -66,12 +66,13 @@ const unsigned long syscall_restart_code[2] = { */ asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask) { - mask &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, mask); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + + mask &= _BLOCKABLE; + siginitset(&blocked, mask); + set_current_blocked(&blocked); current->state = TASK_INTERRUPTIBLE; schedule(); @@ -281,10 +282,7 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf) err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set)); if (err == 0) { sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); } __get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err); @@ -637,13 +635,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, /* * Block the signal if we were successful. */ - spin_lock_irq(&tsk->sighand->siglock); - sigorsets(&tsk->blocked, &tsk->blocked, - &ka->sa.sa_mask); - if (!(ka->sa.sa_flags & SA_NODEFER)) - sigaddset(&tsk->blocked, sig); - recalc_sigpending(); - spin_unlock_irq(&tsk->sighand->siglock); + block_sigmask(ka, sig); return 0; } diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 57db122a4f62..2b26dca2168b 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -58,6 +58,8 @@ enum ipi_msg_type { IPI_CPU_STOP, }; +static DECLARE_COMPLETION(cpu_running); + int __cpuinit __cpu_up(unsigned int cpu) { struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu); @@ -98,20 +100,12 @@ int __cpuinit __cpu_up(unsigned int cpu) */ ret = boot_secondary(cpu, idle); if (ret == 0) { - unsigned long timeout; - /* * CPU was successfully started, wait for it * to come online or time out. */ - timeout = jiffies + HZ; - while (time_before(jiffies, timeout)) { - if (cpu_online(cpu)) - break; - - udelay(10); - barrier(); - } + wait_for_completion_timeout(&cpu_running, + msecs_to_jiffies(1000)); if (!cpu_online(cpu)) { pr_crit("CPU%u: failed to come online\n", cpu); @@ -300,9 +294,10 @@ asmlinkage void __cpuinit secondary_start_kernel(void) /* * OK, now it's safe to let the boot CPU continue. Wait for * the CPU migration code to notice that the CPU is online - * before we continue. + * before we continue - which happens after __cpu_up returns. */ set_cpu_online(cpu, true); + complete(&cpu_running); /* * Setup the percpu timer for this CPU. diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 99a572702509..23377a3bf50d 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -227,6 +227,11 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) #else #define S_SMP "" #endif +#ifdef CONFIG_THUMB2_KERNEL +#define S_ISA " THUMB2" +#else +#define S_ISA " ARM" +#endif static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs) { @@ -234,8 +239,8 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt static int die_counter; int ret; - printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n", - str, err, ++die_counter); + printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP + S_ISA "\n", str, err, ++die_counter); /* trap and error numbers are mostly meaningless on ARM */ ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV); @@ -781,18 +786,16 @@ static void __init kuser_get_tls_init(unsigned long vectors) memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4); } -void __init early_trap_init(void) +void __init early_trap_init(void *vectors_base) { -#if defined(CONFIG_CPU_USE_DOMAINS) - unsigned long vectors = CONFIG_VECTORS_BASE; -#else - unsigned long vectors = (unsigned long)vectors_page; -#endif + unsigned long vectors = (unsigned long)vectors_base; extern char __stubs_start[], __stubs_end[]; extern char __vectors_start[], __vectors_end[]; extern char __kuser_helper_start[], __kuser_helper_end[]; int kuser_sz = __kuser_helper_end - __kuser_helper_start; + vectors_page = vectors_base; + /* * Copy the vectors, stubs and kuser helpers (in entry-armv.S) * into the vector page, mapped at 0xffff0000, and ensure these diff --git a/arch/arm/mach-exynos/hotplug.c b/arch/arm/mach-exynos/hotplug.c index da70e7e39937..c9146fa7f22d 100644 --- a/arch/arm/mach-exynos/hotplug.c +++ b/arch/arm/mach-exynos/hotplug.c @@ -16,6 +16,7 @@ #include <linux/io.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> #include <mach/regs-pmu.h> diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c index 15b87f26ac96..304dfb2b346a 100644 --- a/arch/arm/mach-integrator/core.c +++ b/arch/arm/mach-integrator/core.c @@ -25,8 +25,9 @@ #include <mach/hardware.h> #include <mach/platform.h> -#include <asm/irq.h> #include <mach/cm.h> +#include <mach/irqs.h> + #include <asm/system.h> #include <asm/leds.h> #include <asm/mach-types.h> diff --git a/arch/arm/mach-integrator/include/mach/irqs.h b/arch/arm/mach-integrator/include/mach/irqs.h index 1fbe6d190222..a19a1a2fcf6b 100644 --- a/arch/arm/mach-integrator/include/mach/irqs.h +++ b/arch/arm/mach-integrator/include/mach/irqs.h @@ -78,5 +78,6 @@ #define IRQ_SIC_CP_LMINT7 46 #define IRQ_SIC_END 46 -#define NR_IRQS 47 +#define NR_IRQS_INTEGRATOR_AP 34 +#define NR_IRQS_INTEGRATOR_CP 47 diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c index 21a1d6cbef40..871f148ffd72 100644 --- a/arch/arm/mach-integrator/integrator_ap.c +++ b/arch/arm/mach-integrator/integrator_ap.c @@ -38,12 +38,13 @@ #include <mach/hardware.h> #include <mach/platform.h> #include <asm/hardware/arm_timer.h> -#include <asm/irq.h> #include <asm/setup.h> #include <asm/param.h> /* HZ */ #include <asm/mach-types.h> +#include <asm/sched_clock.h> #include <mach/lm.h> +#include <mach/irqs.h> #include <asm/mach/arch.h> #include <asm/mach/irq.h> @@ -325,6 +326,11 @@ static void __init ap_init(void) static unsigned long timer_reload; +static u32 notrace integrator_read_sched_clock(void) +{ + return -readl((void __iomem *) TIMER2_VA_BASE + TIMER_VALUE); +} + static void integrator_clocksource_init(unsigned long inrate) { void __iomem *base = (void __iomem *)TIMER2_VA_BASE; @@ -341,6 +347,7 @@ static void integrator_clocksource_init(unsigned long inrate) clocksource_mmio_init(base + TIMER_VALUE, "timer2", rate, 200, 16, clocksource_mmio_readl_down); + setup_sched_clock(integrator_read_sched_clock, 16, rate); } static void __iomem * const clkevt_base = (void __iomem *)TIMER1_VA_BASE; @@ -468,6 +475,7 @@ MACHINE_START(INTEGRATOR, "ARM-Integrator") .atag_offset = 0x100, .reserve = integrator_reserve, .map_io = ap_map_io, + .nr_irqs = NR_IRQS_INTEGRATOR_AP, .init_early = integrator_init_early, .init_irq = ap_init_irq, .timer = &ap_timer, diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c index be9ead4a3bcc..48a115a91d9d 100644 --- a/arch/arm/mach-integrator/integrator_cp.c +++ b/arch/arm/mach-integrator/integrator_cp.c @@ -26,7 +26,6 @@ #include <mach/hardware.h> #include <mach/platform.h> -#include <asm/irq.h> #include <asm/setup.h> #include <asm/mach-types.h> #include <asm/hardware/arm_timer.h> @@ -34,6 +33,7 @@ #include <mach/cm.h> #include <mach/lm.h> +#include <mach/irqs.h> #include <asm/mach/arch.h> #include <asm/mach/irq.h> @@ -464,6 +464,7 @@ MACHINE_START(CINTEGRATOR, "ARM-IntegratorCP") .atag_offset = 0x100, .reserve = integrator_reserve, .map_io = intcp_map_io, + .nr_irqs = NR_IRQS_INTEGRATOR_CP, .init_early = intcp_init_early, .init_irq = intcp_init_irq, .timer = &cp_timer, diff --git a/arch/arm/mach-integrator/pci.c b/arch/arm/mach-integrator/pci.c index 520b6bf81bb1..e15aa43cfd27 100644 --- a/arch/arm/mach-integrator/pci.c +++ b/arch/arm/mach-integrator/pci.c @@ -26,11 +26,12 @@ #include <linux/interrupt.h> #include <linux/init.h> -#include <asm/irq.h> #include <asm/system.h> #include <asm/mach/pci.h> #include <asm/mach-types.h> +#include <mach/irqs.h> + /* * A small note about bridges and interrupts. The DECchip 21050 (and * later) adheres to the PCI-PCI bridge specification. This says that diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c index 3c82566acece..65e5896630e4 100644 --- a/arch/arm/mach-integrator/pci_v3.c +++ b/arch/arm/mach-integrator/pci_v3.c @@ -30,7 +30,8 @@ #include <mach/hardware.h> #include <mach/platform.h> -#include <asm/irq.h> +#include <mach/irqs.h> + #include <asm/signal.h> #include <asm/system.h> #include <asm/mach/pci.h> diff --git a/arch/arm/mach-realview/hotplug.c b/arch/arm/mach-realview/hotplug.c index ac1aed2a8da4..5e64fbf8d0ec 100644 --- a/arch/arm/mach-realview/hotplug.c +++ b/arch/arm/mach-realview/hotplug.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> extern volatile int pen_release; diff --git a/arch/arm/mach-tegra/hotplug.c b/arch/arm/mach-tegra/hotplug.c index f3294040d357..d8dc9ddd6d18 100644 --- a/arch/arm/mach-tegra/hotplug.c +++ b/arch/arm/mach-tegra/hotplug.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> static inline void cpu_enter_lowpower(void) { diff --git a/arch/arm/mach-vexpress/hotplug.c b/arch/arm/mach-vexpress/hotplug.c index 813ee08f96e6..7a05548544c3 100644 --- a/arch/arm/mach-vexpress/hotplug.c +++ b/arch/arm/mach-vexpress/hotplug.c @@ -13,7 +13,7 @@ #include <linux/smp.h> #include <asm/cacheflush.h> -#include <asm/system.h> +#include <asm/cp15.h> extern volatile int pen_release; diff --git a/arch/arm/mach-vexpress/include/mach/io.h b/arch/arm/mach-vexpress/include/mach/io.h index 13522d86685e..0088cd388a84 100644 --- a/arch/arm/mach-vexpress/include/mach/io.h +++ b/arch/arm/mach-vexpress/include/mach/io.h @@ -20,7 +20,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define __io(a) __typesafe_io(a) #define __mem_pci(a) (a) #endif diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index caf14dc059e5..78459b8a2a1d 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -22,7 +22,7 @@ #include <linux/sched.h> #include <linux/uaccess.h> -#include <asm/system.h> +#include <asm/cp15.h> #include <asm/unaligned.h> #include "fault.h" diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index e0b0e7a4ec68..dd3d59122cc3 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -15,6 +15,7 @@ #include <linux/init.h> #include <linux/highmem.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> #include <plat/cache-feroceon-l2.h> /* diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index b1e192ba8c24..a53fd2aaa2f4 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -30,13 +30,13 @@ static void __iomem *l2x0_base; static DEFINE_RAW_SPINLOCK(l2x0_lock); -static uint32_t l2x0_way_mask; /* Bitmask of active ways */ -static uint32_t l2x0_size; +static u32 l2x0_way_mask; /* Bitmask of active ways */ +static u32 l2x0_size; struct l2x0_regs l2x0_saved_regs; struct l2x0_of_data { - void (*setup)(const struct device_node *, __u32 *, __u32 *); + void (*setup)(const struct device_node *, u32 *, u32 *); void (*save)(void); void (*resume)(void); }; @@ -288,7 +288,7 @@ static void l2x0_disable(void) raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_unlock(__u32 cache_id) +static void l2x0_unlock(u32 cache_id) { int lockregs; int i; @@ -307,11 +307,11 @@ static void l2x0_unlock(__u32 cache_id) } } -void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) +void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) { - __u32 aux; - __u32 cache_id; - __u32 way_size = 0; + u32 aux; + u32 cache_id; + u32 way_size = 0; int ways; const char *type; @@ -388,7 +388,7 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) #ifdef CONFIG_OF static void __init l2x0_of_setup(const struct device_node *np, - __u32 *aux_val, __u32 *aux_mask) + u32 *aux_val, u32 *aux_mask) { u32 data[2] = { 0, 0 }; u32 tag = 0; @@ -422,7 +422,7 @@ static void __init l2x0_of_setup(const struct device_node *np, } static void __init pl310_of_setup(const struct device_node *np, - __u32 *aux_val, __u32 *aux_mask) + u32 *aux_val, u32 *aux_mask) { u32 data[3] = { 0, 0, 0 }; u32 tag[3] = { 0, 0, 0 }; @@ -548,7 +548,7 @@ static const struct of_device_id l2x0_ids[] __initconst = { {} }; -int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask) +int __init l2x0_of_init(u32 aux_val, u32 aux_mask) { struct device_node *np; struct l2x0_of_data *data; diff --git a/arch/arm/mm/cache-tauros2.c b/arch/arm/mm/cache-tauros2.c index 50868651890f..1fbca05fe906 100644 --- a/arch/arm/mm/cache-tauros2.c +++ b/arch/arm/mm/cache-tauros2.c @@ -16,6 +16,7 @@ #include <linux/init.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> #include <asm/hardware/cache-tauros2.h> diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c index 5a32020471e3..6c3edeb66e74 100644 --- a/arch/arm/mm/cache-xsc3l2.c +++ b/arch/arm/mm/cache-xsc3l2.c @@ -18,7 +18,7 @@ */ #include <linux/init.h> #include <linux/highmem.h> -#include <asm/system.h> +#include <asm/cp15.h> #include <asm/cputype.h> #include <asm/cacheflush.h> diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c index 7d0a8c230342..6e06180a8bc0 100644 --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -23,10 +23,6 @@ #include "mm.h" -/* - * 0xffff8000 to 0xffffffff is reserved for any ARM architecture - * specific hacks for copying pages efficiently. - */ #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \ L_PTE_MT_MINICACHE) @@ -78,10 +74,9 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from, raw_spin_lock(&minicache_lock); - set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0); - flush_tlb_kernel_page(0xffff8000); + set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot)); - mc_copy_user_page((void *)0xffff8000, kto); + mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto); raw_spin_unlock(&minicache_lock); diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c index 3d9a1552cef6..29c770463e41 100644 --- a/arch/arm/mm/copypage-v6.c +++ b/arch/arm/mm/copypage-v6.c @@ -24,9 +24,6 @@ #error FIX ME #endif -#define from_address (0xffff8000) -#define to_address (0xffffc000) - static DEFINE_RAW_SPINLOCK(v6_lock); /* @@ -90,14 +87,11 @@ static void v6_copy_user_highpage_aliasing(struct page *to, */ raw_spin_lock(&v6_lock); - set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(page_to_pfn(from), PAGE_KERNEL), 0); - set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(to), PAGE_KERNEL), 0); - - kfrom = from_address + (offset << PAGE_SHIFT); - kto = to_address + (offset << PAGE_SHIFT); + kfrom = COPYPAGE_V6_FROM + (offset << PAGE_SHIFT); + kto = COPYPAGE_V6_TO + (offset << PAGE_SHIFT); - flush_tlb_kernel_page(kfrom); - flush_tlb_kernel_page(kto); + set_top_pte(kfrom, mk_pte(from, PAGE_KERNEL)); + set_top_pte(kto, mk_pte(to, PAGE_KERNEL)); copy_page((void *)kto, (void *)kfrom); @@ -111,8 +105,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to, */ static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vaddr) { - unsigned int offset = CACHE_COLOUR(vaddr); - unsigned long to = to_address + (offset << PAGE_SHIFT); + unsigned long to = COPYPAGE_V6_TO + (CACHE_COLOUR(vaddr) << PAGE_SHIFT); /* FIXME: not highmem safe */ discard_old_kernel_data(page_address(page)); @@ -123,8 +116,7 @@ static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vad */ raw_spin_lock(&v6_lock); - set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(page), PAGE_KERNEL), 0); - flush_tlb_kernel_page(to); + set_top_pte(to, mk_pte(page, PAGE_KERNEL)); clear_page((void *)to); raw_spin_unlock(&v6_lock); diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c index 610c24ced310..804eeddda97f 100644 --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -23,12 +23,6 @@ #include "mm.h" -/* - * 0xffff8000 to 0xffffffff is reserved for any ARM architecture - * specific hacks for copying pages efficiently. - */ -#define COPYPAGE_MINICACHE 0xffff8000 - #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \ L_PTE_MT_MINICACHE) @@ -100,8 +94,7 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from, raw_spin_lock(&minicache_lock); - set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0); - flush_tlb_kernel_page(COPYPAGE_MINICACHE); + set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot)); mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1aa664a1999f..db23ae4aaaab 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -214,7 +214,8 @@ static int __init consistent_init(void) core_initcall(consistent_init); static void * -__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot) +__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, + const void *caller) { struct arm_vmregion *c; size_t align; @@ -241,7 +242,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot) * Allocate a virtual address in the consistent mapping region. */ c = arm_vmregion_alloc(&consistent_head, align, size, - gfp & ~(__GFP_DMA | __GFP_HIGHMEM)); + gfp & ~(__GFP_DMA | __GFP_HIGHMEM), caller); if (c) { pte_t *pte; int idx = CONSISTENT_PTE_INDEX(c->vm_start); @@ -320,14 +321,14 @@ static void __dma_free_remap(void *cpu_addr, size_t size) #else /* !CONFIG_MMU */ -#define __dma_alloc_remap(page, size, gfp, prot) page_address(page) +#define __dma_alloc_remap(page, size, gfp, prot, c) page_address(page) #define __dma_free_remap(addr, size) do { } while (0) #endif /* CONFIG_MMU */ static void * __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, - pgprot_t prot) + pgprot_t prot, const void *caller) { struct page *page; void *addr; @@ -349,7 +350,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, return NULL; if (!arch_is_coherent()) - addr = __dma_alloc_remap(page, size, gfp, prot); + addr = __dma_alloc_remap(page, size, gfp, prot, caller); else addr = page_address(page); @@ -374,7 +375,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gf return memory; return __dma_alloc(dev, size, handle, gfp, - pgprot_dmacoherent(pgprot_kernel)); + pgprot_dmacoherent(pgprot_kernel), + __builtin_return_address(0)); } EXPORT_SYMBOL(dma_alloc_coherent); @@ -386,7 +388,8 @@ void * dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp) { return __dma_alloc(dev, size, handle, gfp, - pgprot_writecombine(pgprot_kernel)); + pgprot_writecombine(pgprot_kernel), + __builtin_return_address(0)); } EXPORT_SYMBOL(dma_alloc_writecombine); @@ -723,6 +726,9 @@ EXPORT_SYMBOL(dma_set_mask); static int __init dma_debug_do_init(void) { +#ifdef CONFIG_MMU + arm_vmregion_create_proc("dma-mappings", &consistent_head); +#endif dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); return 0; } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index bb7eac381a8e..40c43a94ba72 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -164,7 +164,8 @@ __do_user_fault(struct task_struct *tsk, unsigned long addr, struct siginfo si; #ifdef CONFIG_DEBUG_USER - if (user_debug & UDBG_SEGV) { + if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) || + ((user_debug & UDBG_BUS) && (sig == SIGBUS))) { printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n", tsk->comm, sig, addr, fsr); show_pte(tsk->mm, addr); diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 1a8d4aa821be..4d0b70f035eb 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -23,15 +23,12 @@ #ifdef CONFIG_CPU_CACHE_VIPT -#define ALIAS_FLUSH_START 0xffff4000 - static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr) { - unsigned long to = ALIAS_FLUSH_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT); + unsigned long to = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT); const int zero = 0; - set_pte_ext(TOP_PTE(to), pfn_pte(pfn, PAGE_KERNEL), 0); - flush_tlb_kernel_page(to); + set_top_pte(to, pfn_pte(pfn, PAGE_KERNEL)); asm( "mcrr p15, 0, %1, %0, c14\n" " mcr p15, 0, %2, c7, c10, 4" @@ -42,13 +39,12 @@ static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr) static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned long len) { - unsigned long colour = CACHE_COLOUR(vaddr); + unsigned long va = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT); unsigned long offset = vaddr & (PAGE_SIZE - 1); unsigned long to; - set_pte_ext(TOP_PTE(ALIAS_FLUSH_START) + colour, pfn_pte(pfn, PAGE_KERNEL), 0); - to = ALIAS_FLUSH_START + (colour << PAGE_SHIFT) + offset; - flush_tlb_kernel_page(to); + set_top_pte(va, pfn_pte(pfn, PAGE_KERNEL)); + to = va + offset; flush_icache_range(to, to + len); } diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 807c0573abbe..3a9e8aa19759 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -69,15 +69,14 @@ void *__kmap_atomic(struct page *page) * With debugging enabled, kunmap_atomic forces that entry to 0. * Make sure it was indeed properly unmapped. */ - BUG_ON(!pte_none(*(TOP_PTE(vaddr)))); + BUG_ON(!pte_none(get_top_pte(vaddr))); #endif - set_pte_ext(TOP_PTE(vaddr), mk_pte(page, kmap_prot), 0); /* * When debugging is off, kunmap_atomic leaves the previous mapping - * in place, so this TLB flush ensures the TLB is updated with the - * new mapping. + * in place, so the contained TLB flush ensures the TLB is updated + * with the new mapping. */ - local_flush_tlb_kernel_page(vaddr); + set_top_pte(vaddr, mk_pte(page, kmap_prot)); return (void *)vaddr; } @@ -96,8 +95,7 @@ void __kunmap_atomic(void *kvaddr) __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); - set_pte_ext(TOP_PTE(vaddr), __pte(0), 0); - local_flush_tlb_kernel_page(vaddr); + set_top_pte(vaddr, __pte(0)); #else (void) idx; /* to kill a warning */ #endif @@ -121,10 +119,9 @@ void *kmap_atomic_pfn(unsigned long pfn) idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(!pte_none(*(TOP_PTE(vaddr)))); + BUG_ON(!pte_none(get_top_pte(vaddr))); #endif - set_pte_ext(TOP_PTE(vaddr), pfn_pte(pfn, kmap_prot), 0); - local_flush_tlb_kernel_page(vaddr); + set_top_pte(vaddr, pfn_pte(pfn, kmap_prot)); return (void *)vaddr; } @@ -132,11 +129,9 @@ void *kmap_atomic_pfn(unsigned long pfn) struct page *kmap_atomic_to_page(const void *ptr) { unsigned long vaddr = (unsigned long)ptr; - pte_t *pte; if (vaddr < FIXADDR_START) return virt_to_page(ptr); - pte = TOP_PTE(vaddr); - return pte_page(*pte); + return pte_page(get_top_pte(vaddr)); } diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 6ec1226fc62d..42d906f89964 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -659,7 +659,9 @@ void __init mem_init(void) #ifdef CONFIG_HIGHMEM " pkmap : 0x%08lx - 0x%08lx (%4ld MB)\n" #endif +#ifdef CONFIG_MODULES " modules : 0x%08lx - 0x%08lx (%4ld MB)\n" +#endif " .text : 0x%p" " - 0x%p" " (%4d kB)\n" " .init : 0x%p" " - 0x%p" " (%4d kB)\n" " .data : 0x%p" " - 0x%p" " (%4d kB)\n" @@ -678,7 +680,9 @@ void __init mem_init(void) MLM(PKMAP_BASE, (PKMAP_BASE) + (LAST_PKMAP) * (PAGE_SIZE)), #endif +#ifdef CONFIG_MODULES MLM(MODULES_VADDR, MODULES_END), +#endif MLK_ROUNDUP(_text, _etext), MLK_ROUNDUP(__init_begin, __init_end), diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 80632e8d7538..66daf17b5e33 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -26,6 +26,7 @@ #include <linux/vmalloc.h> #include <linux/io.h> +#include <asm/cp15.h> #include <asm/cputype.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 70f6d3ea4834..27f4a619b35d 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -3,7 +3,31 @@ /* the upper-most page table pointer */ extern pmd_t *top_pmd; -#define TOP_PTE(x) pte_offset_kernel(top_pmd, x) +/* + * 0xffff8000 to 0xffffffff is reserved for any ARM architecture + * specific hacks for copying pages efficiently, while 0xffff4000 + * is reserved for VIPT aliasing flushing by generic code. + * + * Note that we don't allow VIPT aliasing caches with SMP. + */ +#define COPYPAGE_MINICACHE 0xffff8000 +#define COPYPAGE_V6_FROM 0xffff8000 +#define COPYPAGE_V6_TO 0xffffc000 +/* PFN alias flushing, for VIPT caches */ +#define FLUSH_ALIAS_START 0xffff4000 + +static inline void set_top_pte(unsigned long va, pte_t pte) +{ + pte_t *ptep = pte_offset_kernel(top_pmd, va); + set_pte_ext(ptep, pte, 0); + local_flush_tlb_kernel_page(va); +} + +static inline pte_t get_top_pte(unsigned long va) +{ + pte_t *ptep = pte_offset_kernel(top_pmd, va); + return *ptep; +} static inline pmd_t *pmd_off_k(unsigned long virt) { diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 94c5a0c94f5e..f77f1dbbdf59 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -17,6 +17,7 @@ #include <linux/fs.h> #include <linux/vmalloc.h> +#include <asm/cp15.h> #include <asm/cputype.h> #include <asm/sections.h> #include <asm/cachetype.h> @@ -997,11 +998,14 @@ static void __init devicemaps_init(struct machine_desc *mdesc) { struct map_desc map; unsigned long addr; + void *vectors; /* * Allocate the vector page early. */ - vectors_page = early_alloc(PAGE_SIZE); + vectors = early_alloc(PAGE_SIZE); + + early_trap_init(vectors); for (addr = VMALLOC_START; addr; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); @@ -1041,7 +1045,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) * location (0xffff0000). If we aren't using high-vectors, also * create a mapping at the low-vectors virtual address. */ - map.pfn = __phys_to_pfn(virt_to_phys(vectors_page)); + map.pfn = __phys_to_pfn(virt_to_phys(vectors)); map.virtual = 0xffff0000; map.length = PAGE_SIZE; map.type = MT_HIGH_VECTORS; diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index a3e78ccabd65..0acb089d0f70 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -12,6 +12,7 @@ #include <linux/highmem.h> #include <linux/slab.h> +#include <asm/cp15.h> #include <asm/pgalloc.h> #include <asm/page.h> #include <asm/tlbflush.h> diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c index 036fdbfdd62f..a631016e1f8f 100644 --- a/arch/arm/mm/vmregion.c +++ b/arch/arm/mm/vmregion.c @@ -1,5 +1,8 @@ +#include <linux/fs.h> #include <linux/spinlock.h> #include <linux/list.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/slab.h> #include "vmregion.h" @@ -36,7 +39,7 @@ struct arm_vmregion * arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align, - size_t size, gfp_t gfp) + size_t size, gfp_t gfp, const void *caller) { unsigned long start = head->vm_start, addr = head->vm_end; unsigned long flags; @@ -52,6 +55,8 @@ arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align, if (!new) goto out; + new->caller = caller; + spin_lock_irqsave(&head->vm_lock, flags); addr = rounddown(addr - size, align); @@ -129,3 +134,72 @@ void arm_vmregion_free(struct arm_vmregion_head *head, struct arm_vmregion *c) kfree(c); } + +#ifdef CONFIG_PROC_FS +static int arm_vmregion_show(struct seq_file *m, void *p) +{ + struct arm_vmregion *c = list_entry(p, struct arm_vmregion, vm_list); + + seq_printf(m, "0x%08lx-0x%08lx %7lu", c->vm_start, c->vm_end, + c->vm_end - c->vm_start); + if (c->caller) + seq_printf(m, " %pS", (void *)c->caller); + seq_putc(m, '\n'); + return 0; +} + +static void *arm_vmregion_start(struct seq_file *m, loff_t *pos) +{ + struct arm_vmregion_head *h = m->private; + spin_lock_irq(&h->vm_lock); + return seq_list_start(&h->vm_list, *pos); +} + +static void *arm_vmregion_next(struct seq_file *m, void *p, loff_t *pos) +{ + struct arm_vmregion_head *h = m->private; + return seq_list_next(p, &h->vm_list, pos); +} + +static void arm_vmregion_stop(struct seq_file *m, void *p) +{ + struct arm_vmregion_head *h = m->private; + spin_unlock_irq(&h->vm_lock); +} + +static const struct seq_operations arm_vmregion_ops = { + .start = arm_vmregion_start, + .stop = arm_vmregion_stop, + .next = arm_vmregion_next, + .show = arm_vmregion_show, +}; + +static int arm_vmregion_open(struct inode *inode, struct file *file) +{ + struct arm_vmregion_head *h = PDE(inode)->data; + int ret = seq_open(file, &arm_vmregion_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = h; + } + return ret; +} + +static const struct file_operations arm_vmregion_fops = { + .open = arm_vmregion_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h) +{ + proc_create_data(path, S_IRUSR, NULL, &arm_vmregion_fops, h); + return 0; +} +#else +int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h) +{ + return 0; +} +#endif diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h index 15e9f044db9f..162be662c088 100644 --- a/arch/arm/mm/vmregion.h +++ b/arch/arm/mm/vmregion.h @@ -19,11 +19,14 @@ struct arm_vmregion { unsigned long vm_end; struct page *vm_pages; int vm_active; + const void *caller; }; -struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t); +struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t, const void *); struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *, unsigned long); struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *, unsigned long); void arm_vmregion_free(struct arm_vmregion_head *, struct arm_vmregion *); +int arm_vmregion_create_proc(const char *, struct arm_vmregion_head *); + #endif diff --git a/arch/arm/net/Makefile b/arch/arm/net/Makefile new file mode 100644 index 000000000000..c2c10841b6be --- /dev/null +++ b/arch/arm/net/Makefile @@ -0,0 +1,3 @@ +# ARM-specific networking code + +obj-$(CONFIG_BPF_JIT) += bpf_jit_32.o diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c new file mode 100644 index 000000000000..62135849f48b --- /dev/null +++ b/arch/arm/net/bpf_jit_32.c @@ -0,0 +1,915 @@ +/* + * Just-In-Time compiler for BPF filters on 32bit ARM + * + * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License. + */ + +#include <linux/bitops.h> +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/filter.h> +#include <linux/moduleloader.h> +#include <linux/netdevice.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <asm/cacheflush.h> +#include <asm/hwcap.h> + +#include "bpf_jit_32.h" + +/* + * ABI: + * + * r0 scratch register + * r4 BPF register A + * r5 BPF register X + * r6 pointer to the skb + * r7 skb->data + * r8 skb_headlen(skb) + */ + +#define r_scratch ARM_R0 +/* r1-r3 are (also) used for the unaligned loads on the non-ARMv7 slowpath */ +#define r_off ARM_R1 +#define r_A ARM_R4 +#define r_X ARM_R5 +#define r_skb ARM_R6 +#define r_skb_data ARM_R7 +#define r_skb_hl ARM_R8 + +#define SCRATCH_SP_OFFSET 0 +#define SCRATCH_OFF(k) (SCRATCH_SP_OFFSET + (k)) + +#define SEEN_MEM ((1 << BPF_MEMWORDS) - 1) +#define SEEN_MEM_WORD(k) (1 << (k)) +#define SEEN_X (1 << BPF_MEMWORDS) +#define SEEN_CALL (1 << (BPF_MEMWORDS + 1)) +#define SEEN_SKB (1 << (BPF_MEMWORDS + 2)) +#define SEEN_DATA (1 << (BPF_MEMWORDS + 3)) + +#define FLAG_NEED_X_RESET (1 << 0) + +struct jit_ctx { + const struct sk_filter *skf; + unsigned idx; + unsigned prologue_bytes; + int ret0_fp_idx; + u32 seen; + u32 flags; + u32 *offsets; + u32 *target; +#if __LINUX_ARM_ARCH__ < 7 + u16 epilogue_bytes; + u16 imm_count; + u32 *imms; +#endif +}; + +int bpf_jit_enable __read_mostly; + +static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset) +{ + u8 ret; + int err; + + err = skb_copy_bits(skb, offset, &ret, 1); + + return (u64)err << 32 | ret; +} + +static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset) +{ + u16 ret; + int err; + + err = skb_copy_bits(skb, offset, &ret, 2); + + return (u64)err << 32 | ntohs(ret); +} + +static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset) +{ + u32 ret; + int err; + + err = skb_copy_bits(skb, offset, &ret, 4); + + return (u64)err << 32 | ntohl(ret); +} + +/* + * Wrapper that handles both OABI and EABI and assures Thumb2 interworking + * (where the assembly routines like __aeabi_uidiv could cause problems). + */ +static u32 jit_udiv(u32 dividend, u32 divisor) +{ + return dividend / divisor; +} + +static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx) +{ + if (ctx->target != NULL) + ctx->target[ctx->idx] = inst | (cond << 28); + + ctx->idx++; +} + +/* + * Emit an instruction that will be executed unconditionally. + */ +static inline void emit(u32 inst, struct jit_ctx *ctx) +{ + _emit(ARM_COND_AL, inst, ctx); +} + +static u16 saved_regs(struct jit_ctx *ctx) +{ + u16 ret = 0; + + if ((ctx->skf->len > 1) || + (ctx->skf->insns[0].code == BPF_S_RET_A)) + ret |= 1 << r_A; + +#ifdef CONFIG_FRAME_POINTER + ret |= (1 << ARM_FP) | (1 << ARM_IP) | (1 << ARM_LR) | (1 << ARM_PC); +#else + if (ctx->seen & SEEN_CALL) + ret |= 1 << ARM_LR; +#endif + if (ctx->seen & (SEEN_DATA | SEEN_SKB)) + ret |= 1 << r_skb; + if (ctx->seen & SEEN_DATA) + ret |= (1 << r_skb_data) | (1 << r_skb_hl); + if (ctx->seen & SEEN_X) + ret |= 1 << r_X; + + return ret; +} + +static inline int mem_words_used(struct jit_ctx *ctx) +{ + /* yes, we do waste some stack space IF there are "holes" in the set" */ + return fls(ctx->seen & SEEN_MEM); +} + +static inline bool is_load_to_a(u16 inst) +{ + switch (inst) { + case BPF_S_LD_W_LEN: + case BPF_S_LD_W_ABS: + case BPF_S_LD_H_ABS: + case BPF_S_LD_B_ABS: + case BPF_S_ANC_CPU: + case BPF_S_ANC_IFINDEX: + case BPF_S_ANC_MARK: + case BPF_S_ANC_PROTOCOL: + case BPF_S_ANC_RXHASH: + case BPF_S_ANC_QUEUE: + return true; + default: + return false; + } +} + +static void build_prologue(struct jit_ctx *ctx) +{ + u16 reg_set = saved_regs(ctx); + u16 first_inst = ctx->skf->insns[0].code; + u16 off; + +#ifdef CONFIG_FRAME_POINTER + emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx); + emit(ARM_PUSH(reg_set), ctx); + emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx); +#else + if (reg_set) + emit(ARM_PUSH(reg_set), ctx); +#endif + + if (ctx->seen & (SEEN_DATA | SEEN_SKB)) + emit(ARM_MOV_R(r_skb, ARM_R0), ctx); + + if (ctx->seen & SEEN_DATA) { + off = offsetof(struct sk_buff, data); + emit(ARM_LDR_I(r_skb_data, r_skb, off), ctx); + /* headlen = len - data_len */ + off = offsetof(struct sk_buff, len); + emit(ARM_LDR_I(r_skb_hl, r_skb, off), ctx); + off = offsetof(struct sk_buff, data_len); + emit(ARM_LDR_I(r_scratch, r_skb, off), ctx); + emit(ARM_SUB_R(r_skb_hl, r_skb_hl, r_scratch), ctx); + } + + if (ctx->flags & FLAG_NEED_X_RESET) + emit(ARM_MOV_I(r_X, 0), ctx); + + /* do not leak kernel data to userspace */ + if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst))) + emit(ARM_MOV_I(r_A, 0), ctx); + + /* stack space for the BPF_MEM words */ + if (ctx->seen & SEEN_MEM) + emit(ARM_SUB_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx); +} + +static void build_epilogue(struct jit_ctx *ctx) +{ + u16 reg_set = saved_regs(ctx); + + if (ctx->seen & SEEN_MEM) + emit(ARM_ADD_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx); + + reg_set &= ~(1 << ARM_LR); + +#ifdef CONFIG_FRAME_POINTER + /* the first instruction of the prologue was: mov ip, sp */ + reg_set &= ~(1 << ARM_IP); + reg_set |= (1 << ARM_SP); + emit(ARM_LDM(ARM_SP, reg_set), ctx); +#else + if (reg_set) { + if (ctx->seen & SEEN_CALL) + reg_set |= 1 << ARM_PC; + emit(ARM_POP(reg_set), ctx); + } + + if (!(ctx->seen & SEEN_CALL)) + emit(ARM_BX(ARM_LR), ctx); +#endif +} + +static int16_t imm8m(u32 x) +{ + u32 rot; + + for (rot = 0; rot < 16; rot++) + if ((x & ~ror32(0xff, 2 * rot)) == 0) + return rol32(x, 2 * rot) | (rot << 8); + + return -1; +} + +#if __LINUX_ARM_ARCH__ < 7 + +static u16 imm_offset(u32 k, struct jit_ctx *ctx) +{ + unsigned i = 0, offset; + u16 imm; + + /* on the "fake" run we just count them (duplicates included) */ + if (ctx->target == NULL) { + ctx->imm_count++; + return 0; + } + + while ((i < ctx->imm_count) && ctx->imms[i]) { + if (ctx->imms[i] == k) + break; + i++; + } + + if (ctx->imms[i] == 0) + ctx->imms[i] = k; + + /* constants go just after the epilogue */ + offset = ctx->offsets[ctx->skf->len]; + offset += ctx->prologue_bytes; + offset += ctx->epilogue_bytes; + offset += i * 4; + + ctx->target[offset / 4] = k; + + /* PC in ARM mode == address of the instruction + 8 */ + imm = offset - (8 + ctx->idx * 4); + + return imm; +} + +#endif /* __LINUX_ARM_ARCH__ */ + +/* + * Move an immediate that's not an imm8m to a core register. + */ +static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx) +{ +#if __LINUX_ARM_ARCH__ < 7 + emit(ARM_LDR_I(rd, ARM_PC, imm_offset(val, ctx)), ctx); +#else + emit(ARM_MOVW(rd, val & 0xffff), ctx); + if (val > 0xffff) + emit(ARM_MOVT(rd, val >> 16), ctx); +#endif +} + +static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx) +{ + int imm12 = imm8m(val); + + if (imm12 >= 0) + emit(ARM_MOV_I(rd, imm12), ctx); + else + emit_mov_i_no8m(rd, val, ctx); +} + +#if __LINUX_ARM_ARCH__ < 6 + +static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx) +{ + _emit(cond, ARM_LDRB_I(ARM_R3, r_addr, 1), ctx); + _emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx); + _emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 3), ctx); + _emit(cond, ARM_LSL_I(ARM_R3, ARM_R3, 16), ctx); + _emit(cond, ARM_LDRB_I(ARM_R0, r_addr, 2), ctx); + _emit(cond, ARM_ORR_S(ARM_R3, ARM_R3, ARM_R1, SRTYPE_LSL, 24), ctx); + _emit(cond, ARM_ORR_R(ARM_R3, ARM_R3, ARM_R2), ctx); + _emit(cond, ARM_ORR_S(r_res, ARM_R3, ARM_R0, SRTYPE_LSL, 8), ctx); +} + +static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx) +{ + _emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx); + _emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 1), ctx); + _emit(cond, ARM_ORR_S(r_res, ARM_R2, ARM_R1, SRTYPE_LSL, 8), ctx); +} + +static inline void emit_swap16(u8 r_dst, u8 r_src, struct jit_ctx *ctx) +{ + emit(ARM_LSL_R(ARM_R1, r_src, 8), ctx); + emit(ARM_ORR_S(r_dst, ARM_R1, r_src, SRTYPE_LSL, 8), ctx); + emit(ARM_LSL_I(r_dst, r_dst, 8), ctx); + emit(ARM_LSL_R(r_dst, r_dst, 8), ctx); +} + +#else /* ARMv6+ */ + +static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx) +{ + _emit(cond, ARM_LDR_I(r_res, r_addr, 0), ctx); +#ifdef __LITTLE_ENDIAN + _emit(cond, ARM_REV(r_res, r_res), ctx); +#endif +} + +static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx) +{ + _emit(cond, ARM_LDRH_I(r_res, r_addr, 0), ctx); +#ifdef __LITTLE_ENDIAN + _emit(cond, ARM_REV16(r_res, r_res), ctx); +#endif +} + +static inline void emit_swap16(u8 r_dst __maybe_unused, + u8 r_src __maybe_unused, + struct jit_ctx *ctx __maybe_unused) +{ +#ifdef __LITTLE_ENDIAN + emit(ARM_REV16(r_dst, r_src), ctx); +#endif +} + +#endif /* __LINUX_ARM_ARCH__ < 6 */ + + +/* Compute the immediate value for a PC-relative branch. */ +static inline u32 b_imm(unsigned tgt, struct jit_ctx *ctx) +{ + u32 imm; + + if (ctx->target == NULL) + return 0; + /* + * BPF allows only forward jumps and the offset of the target is + * still the one computed during the first pass. + */ + imm = ctx->offsets[tgt] + ctx->prologue_bytes - (ctx->idx * 4 + 8); + + return imm >> 2; +} + +#define OP_IMM3(op, r1, r2, imm_val, ctx) \ + do { \ + imm12 = imm8m(imm_val); \ + if (imm12 < 0) { \ + emit_mov_i_no8m(r_scratch, imm_val, ctx); \ + emit(op ## _R((r1), (r2), r_scratch), ctx); \ + } else { \ + emit(op ## _I((r1), (r2), imm12), ctx); \ + } \ + } while (0) + +static inline void emit_err_ret(u8 cond, struct jit_ctx *ctx) +{ + if (ctx->ret0_fp_idx >= 0) { + _emit(cond, ARM_B(b_imm(ctx->ret0_fp_idx, ctx)), ctx); + /* NOP to keep the size constant between passes */ + emit(ARM_MOV_R(ARM_R0, ARM_R0), ctx); + } else { + _emit(cond, ARM_MOV_I(ARM_R0, 0), ctx); + _emit(cond, ARM_B(b_imm(ctx->skf->len, ctx)), ctx); + } +} + +static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx) +{ +#if __LINUX_ARM_ARCH__ < 5 + emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx); + + if (elf_hwcap & HWCAP_THUMB) + emit(ARM_BX(tgt_reg), ctx); + else + emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx); +#else + emit(ARM_BLX_R(tgt_reg), ctx); +#endif +} + +static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx) +{ +#if __LINUX_ARM_ARCH__ == 7 + if (elf_hwcap & HWCAP_IDIVA) { + emit(ARM_UDIV(rd, rm, rn), ctx); + return; + } +#endif + if (rm != ARM_R0) + emit(ARM_MOV_R(ARM_R0, rm), ctx); + if (rn != ARM_R1) + emit(ARM_MOV_R(ARM_R1, rn), ctx); + + ctx->seen |= SEEN_CALL; + emit_mov_i(ARM_R3, (u32)jit_udiv, ctx); + emit_blx_r(ARM_R3, ctx); + + if (rd != ARM_R0) + emit(ARM_MOV_R(rd, ARM_R0), ctx); +} + +static inline void update_on_xread(struct jit_ctx *ctx) +{ + if (!(ctx->seen & SEEN_X)) + ctx->flags |= FLAG_NEED_X_RESET; + + ctx->seen |= SEEN_X; +} + +static int build_body(struct jit_ctx *ctx) +{ + void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w}; + const struct sk_filter *prog = ctx->skf; + const struct sock_filter *inst; + unsigned i, load_order, off, condt; + int imm12; + u32 k; + + for (i = 0; i < prog->len; i++) { + inst = &(prog->insns[i]); + /* K as an immediate value operand */ + k = inst->k; + + /* compute offsets only in the fake pass */ + if (ctx->target == NULL) + ctx->offsets[i] = ctx->idx * 4; + + switch (inst->code) { + case BPF_S_LD_IMM: + emit_mov_i(r_A, k, ctx); + break; + case BPF_S_LD_W_LEN: + ctx->seen |= SEEN_SKB; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + emit(ARM_LDR_I(r_A, r_skb, + offsetof(struct sk_buff, len)), ctx); + break; + case BPF_S_LD_MEM: + /* A = scratch[k] */ + ctx->seen |= SEEN_MEM_WORD(k); + emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx); + break; + case BPF_S_LD_W_ABS: + load_order = 2; + goto load; + case BPF_S_LD_H_ABS: + load_order = 1; + goto load; + case BPF_S_LD_B_ABS: + load_order = 0; +load: + /* the interpreter will deal with the negative K */ + if ((int)k < 0) + return -ENOTSUPP; + emit_mov_i(r_off, k, ctx); +load_common: + ctx->seen |= SEEN_DATA | SEEN_CALL; + + if (load_order > 0) { + emit(ARM_SUB_I(r_scratch, r_skb_hl, + 1 << load_order), ctx); + emit(ARM_CMP_R(r_scratch, r_off), ctx); + condt = ARM_COND_HS; + } else { + emit(ARM_CMP_R(r_skb_hl, r_off), ctx); + condt = ARM_COND_HI; + } + + _emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data), + ctx); + + if (load_order == 0) + _emit(condt, ARM_LDRB_I(r_A, r_scratch, 0), + ctx); + else if (load_order == 1) + emit_load_be16(condt, r_A, r_scratch, ctx); + else if (load_order == 2) + emit_load_be32(condt, r_A, r_scratch, ctx); + + _emit(condt, ARM_B(b_imm(i + 1, ctx)), ctx); + + /* the slowpath */ + emit_mov_i(ARM_R3, (u32)load_func[load_order], ctx); + emit(ARM_MOV_R(ARM_R0, r_skb), ctx); + /* the offset is already in R1 */ + emit_blx_r(ARM_R3, ctx); + /* check the result of skb_copy_bits */ + emit(ARM_CMP_I(ARM_R1, 0), ctx); + emit_err_ret(ARM_COND_NE, ctx); + emit(ARM_MOV_R(r_A, ARM_R0), ctx); + break; + case BPF_S_LD_W_IND: + load_order = 2; + goto load_ind; + case BPF_S_LD_H_IND: + load_order = 1; + goto load_ind; + case BPF_S_LD_B_IND: + load_order = 0; +load_ind: + OP_IMM3(ARM_ADD, r_off, r_X, k, ctx); + goto load_common; + case BPF_S_LDX_IMM: + ctx->seen |= SEEN_X; + emit_mov_i(r_X, k, ctx); + break; + case BPF_S_LDX_W_LEN: + ctx->seen |= SEEN_X | SEEN_SKB; + emit(ARM_LDR_I(r_X, r_skb, + offsetof(struct sk_buff, len)), ctx); + break; + case BPF_S_LDX_MEM: + ctx->seen |= SEEN_X | SEEN_MEM_WORD(k); + emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx); + break; + case BPF_S_LDX_B_MSH: + /* x = ((*(frame + k)) & 0xf) << 2; */ + ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL; + /* the interpreter should deal with the negative K */ + if (k < 0) + return -1; + /* offset in r1: we might have to take the slow path */ + emit_mov_i(r_off, k, ctx); + emit(ARM_CMP_R(r_skb_hl, r_off), ctx); + + /* load in r0: common with the slowpath */ + _emit(ARM_COND_HI, ARM_LDRB_R(ARM_R0, r_skb_data, + ARM_R1), ctx); + /* + * emit_mov_i() might generate one or two instructions, + * the same holds for emit_blx_r() + */ + _emit(ARM_COND_HI, ARM_B(b_imm(i + 1, ctx) - 2), ctx); + + emit(ARM_MOV_R(ARM_R0, r_skb), ctx); + /* r_off is r1 */ + emit_mov_i(ARM_R3, (u32)jit_get_skb_b, ctx); + emit_blx_r(ARM_R3, ctx); + /* check the return value of skb_copy_bits */ + emit(ARM_CMP_I(ARM_R1, 0), ctx); + emit_err_ret(ARM_COND_NE, ctx); + + emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx); + emit(ARM_LSL_I(r_X, r_X, 2), ctx); + break; + case BPF_S_ST: + ctx->seen |= SEEN_MEM_WORD(k); + emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx); + break; + case BPF_S_STX: + update_on_xread(ctx); + ctx->seen |= SEEN_MEM_WORD(k); + emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx); + break; + case BPF_S_ALU_ADD_K: + /* A += K */ + OP_IMM3(ARM_ADD, r_A, r_A, k, ctx); + break; + case BPF_S_ALU_ADD_X: + update_on_xread(ctx); + emit(ARM_ADD_R(r_A, r_A, r_X), ctx); + break; + case BPF_S_ALU_SUB_K: + /* A -= K */ + OP_IMM3(ARM_SUB, r_A, r_A, k, ctx); + break; + case BPF_S_ALU_SUB_X: + update_on_xread(ctx); + emit(ARM_SUB_R(r_A, r_A, r_X), ctx); + break; + case BPF_S_ALU_MUL_K: + /* A *= K */ + emit_mov_i(r_scratch, k, ctx); + emit(ARM_MUL(r_A, r_A, r_scratch), ctx); + break; + case BPF_S_ALU_MUL_X: + update_on_xread(ctx); + emit(ARM_MUL(r_A, r_A, r_X), ctx); + break; + case BPF_S_ALU_DIV_K: + /* current k == reciprocal_value(userspace k) */ + emit_mov_i(r_scratch, k, ctx); + /* A = top 32 bits of the product */ + emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx); + break; + case BPF_S_ALU_DIV_X: + update_on_xread(ctx); + emit(ARM_CMP_I(r_X, 0), ctx); + emit_err_ret(ARM_COND_EQ, ctx); + emit_udiv(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_OR_K: + /* A |= K */ + OP_IMM3(ARM_ORR, r_A, r_A, k, ctx); + break; + case BPF_S_ALU_OR_X: + update_on_xread(ctx); + emit(ARM_ORR_R(r_A, r_A, r_X), ctx); + break; + case BPF_S_ALU_AND_K: + /* A &= K */ + OP_IMM3(ARM_AND, r_A, r_A, k, ctx); + break; + case BPF_S_ALU_AND_X: + update_on_xread(ctx); + emit(ARM_AND_R(r_A, r_A, r_X), ctx); + break; + case BPF_S_ALU_LSH_K: + if (unlikely(k > 31)) + return -1; + emit(ARM_LSL_I(r_A, r_A, k), ctx); + break; + case BPF_S_ALU_LSH_X: + update_on_xread(ctx); + emit(ARM_LSL_R(r_A, r_A, r_X), ctx); + break; + case BPF_S_ALU_RSH_K: + if (unlikely(k > 31)) + return -1; + emit(ARM_LSR_I(r_A, r_A, k), ctx); + break; + case BPF_S_ALU_RSH_X: + update_on_xread(ctx); + emit(ARM_LSR_R(r_A, r_A, r_X), ctx); + break; + case BPF_S_ALU_NEG: + /* A = -A */ + emit(ARM_RSB_I(r_A, r_A, 0), ctx); + break; + case BPF_S_JMP_JA: + /* pc += K */ + emit(ARM_B(b_imm(i + k + 1, ctx)), ctx); + break; + case BPF_S_JMP_JEQ_K: + /* pc += (A == K) ? pc->jt : pc->jf */ + condt = ARM_COND_EQ; + goto cmp_imm; + case BPF_S_JMP_JGT_K: + /* pc += (A > K) ? pc->jt : pc->jf */ + condt = ARM_COND_HI; + goto cmp_imm; + case BPF_S_JMP_JGE_K: + /* pc += (A >= K) ? pc->jt : pc->jf */ + condt = ARM_COND_HS; +cmp_imm: + imm12 = imm8m(k); + if (imm12 < 0) { + emit_mov_i_no8m(r_scratch, k, ctx); + emit(ARM_CMP_R(r_A, r_scratch), ctx); + } else { + emit(ARM_CMP_I(r_A, imm12), ctx); + } +cond_jump: + if (inst->jt) + _emit(condt, ARM_B(b_imm(i + inst->jt + 1, + ctx)), ctx); + if (inst->jf) + _emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1, + ctx)), ctx); + break; + case BPF_S_JMP_JEQ_X: + /* pc += (A == X) ? pc->jt : pc->jf */ + condt = ARM_COND_EQ; + goto cmp_x; + case BPF_S_JMP_JGT_X: + /* pc += (A > X) ? pc->jt : pc->jf */ + condt = ARM_COND_HI; + goto cmp_x; + case BPF_S_JMP_JGE_X: + /* pc += (A >= X) ? pc->jt : pc->jf */ + condt = ARM_COND_CS; +cmp_x: + update_on_xread(ctx); + emit(ARM_CMP_R(r_A, r_X), ctx); + goto cond_jump; + case BPF_S_JMP_JSET_K: + /* pc += (A & K) ? pc->jt : pc->jf */ + condt = ARM_COND_NE; + /* not set iff all zeroes iff Z==1 iff EQ */ + + imm12 = imm8m(k); + if (imm12 < 0) { + emit_mov_i_no8m(r_scratch, k, ctx); + emit(ARM_TST_R(r_A, r_scratch), ctx); + } else { + emit(ARM_TST_I(r_A, imm12), ctx); + } + goto cond_jump; + case BPF_S_JMP_JSET_X: + /* pc += (A & X) ? pc->jt : pc->jf */ + update_on_xread(ctx); + condt = ARM_COND_NE; + emit(ARM_TST_R(r_A, r_X), ctx); + goto cond_jump; + case BPF_S_RET_A: + emit(ARM_MOV_R(ARM_R0, r_A), ctx); + goto b_epilogue; + case BPF_S_RET_K: + if ((k == 0) && (ctx->ret0_fp_idx < 0)) + ctx->ret0_fp_idx = i; + emit_mov_i(ARM_R0, k, ctx); +b_epilogue: + if (i != ctx->skf->len - 1) + emit(ARM_B(b_imm(prog->len, ctx)), ctx); + break; + case BPF_S_MISC_TAX: + /* X = A */ + ctx->seen |= SEEN_X; + emit(ARM_MOV_R(r_X, r_A), ctx); + break; + case BPF_S_MISC_TXA: + /* A = X */ + update_on_xread(ctx); + emit(ARM_MOV_R(r_A, r_X), ctx); + break; + case BPF_S_ANC_PROTOCOL: + /* A = ntohs(skb->protocol) */ + ctx->seen |= SEEN_SKB; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + protocol) != 2); + off = offsetof(struct sk_buff, protocol); + emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx); + emit_swap16(r_A, r_scratch, ctx); + break; + case BPF_S_ANC_CPU: + /* r_scratch = current_thread_info() */ + OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx); + /* A = current_thread_info()->cpu */ + BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4); + off = offsetof(struct thread_info, cpu); + emit(ARM_LDR_I(r_A, r_scratch, off), ctx); + break; + case BPF_S_ANC_IFINDEX: + /* A = skb->dev->ifindex */ + ctx->seen |= SEEN_SKB; + off = offsetof(struct sk_buff, dev); + emit(ARM_LDR_I(r_scratch, r_skb, off), ctx); + + emit(ARM_CMP_I(r_scratch, 0), ctx); + emit_err_ret(ARM_COND_EQ, ctx); + + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + ifindex) != 4); + off = offsetof(struct net_device, ifindex); + emit(ARM_LDR_I(r_A, r_scratch, off), ctx); + break; + case BPF_S_ANC_MARK: + ctx->seen |= SEEN_SKB; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + off = offsetof(struct sk_buff, mark); + emit(ARM_LDR_I(r_A, r_skb, off), ctx); + break; + case BPF_S_ANC_RXHASH: + ctx->seen |= SEEN_SKB; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4); + off = offsetof(struct sk_buff, rxhash); + emit(ARM_LDR_I(r_A, r_skb, off), ctx); + break; + case BPF_S_ANC_QUEUE: + ctx->seen |= SEEN_SKB; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + queue_mapping) != 2); + BUILD_BUG_ON(offsetof(struct sk_buff, + queue_mapping) > 0xff); + off = offsetof(struct sk_buff, queue_mapping); + emit(ARM_LDRH_I(r_A, r_skb, off), ctx); + break; + default: + return -1; + } + } + + /* compute offsets only during the first pass */ + if (ctx->target == NULL) + ctx->offsets[i] = ctx->idx * 4; + + return 0; +} + + +void bpf_jit_compile(struct sk_filter *fp) +{ + struct jit_ctx ctx; + unsigned tmp_idx; + unsigned alloc_size; + + if (!bpf_jit_enable) + return; + + memset(&ctx, 0, sizeof(ctx)); + ctx.skf = fp; + ctx.ret0_fp_idx = -1; + + ctx.offsets = kzalloc(GFP_KERNEL, 4 * (ctx.skf->len + 1)); + if (ctx.offsets == NULL) + return; + + /* fake pass to fill in the ctx->seen */ + if (unlikely(build_body(&ctx))) + goto out; + + tmp_idx = ctx.idx; + build_prologue(&ctx); + ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4; + +#if __LINUX_ARM_ARCH__ < 7 + tmp_idx = ctx.idx; + build_epilogue(&ctx); + ctx.epilogue_bytes = (ctx.idx - tmp_idx) * 4; + + ctx.idx += ctx.imm_count; + if (ctx.imm_count) { + ctx.imms = kzalloc(GFP_KERNEL, 4 * ctx.imm_count); + if (ctx.imms == NULL) + goto out; + } +#else + /* there's nothing after the epilogue on ARMv7 */ + build_epilogue(&ctx); +#endif + + alloc_size = 4 * ctx.idx; + ctx.target = module_alloc(max(sizeof(struct work_struct), + alloc_size)); + if (unlikely(ctx.target == NULL)) + goto out; + + ctx.idx = 0; + build_prologue(&ctx); + build_body(&ctx); + build_epilogue(&ctx); + + flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx)); + +#if __LINUX_ARM_ARCH__ < 7 + if (ctx.imm_count) + kfree(ctx.imms); +#endif + + if (bpf_jit_enable > 1) + print_hex_dump(KERN_INFO, "BPF JIT code: ", + DUMP_PREFIX_ADDRESS, 16, 4, ctx.target, + alloc_size, false); + + fp->bpf_func = (void *)ctx.target; +out: + kfree(ctx.offsets); + return; +} + +static void bpf_jit_free_worker(struct work_struct *work) +{ + module_free(NULL, work); +} + +void bpf_jit_free(struct sk_filter *fp) +{ + struct work_struct *work; + + if (fp->bpf_func != sk_run_filter) { + work = (struct work_struct *)fp->bpf_func; + + INIT_WORK(work, bpf_jit_free_worker); + schedule_work(work); + } +} diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h new file mode 100644 index 000000000000..99ae5e3f46d2 --- /dev/null +++ b/arch/arm/net/bpf_jit_32.h @@ -0,0 +1,190 @@ +/* + * Just-In-Time compiler for BPF filters on 32bit ARM + * + * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License. + */ + +#ifndef PFILTER_OPCODES_ARM_H +#define PFILTER_OPCODES_ARM_H + +#define ARM_R0 0 +#define ARM_R1 1 +#define ARM_R2 2 +#define ARM_R3 3 +#define ARM_R4 4 +#define ARM_R5 5 +#define ARM_R6 6 +#define ARM_R7 7 +#define ARM_R8 8 +#define ARM_R9 9 +#define ARM_R10 10 +#define ARM_FP 11 +#define ARM_IP 12 +#define ARM_SP 13 +#define ARM_LR 14 +#define ARM_PC 15 + +#define ARM_COND_EQ 0x0 +#define ARM_COND_NE 0x1 +#define ARM_COND_CS 0x2 +#define ARM_COND_HS ARM_COND_CS +#define ARM_COND_CC 0x3 +#define ARM_COND_LO ARM_COND_CC +#define ARM_COND_MI 0x4 +#define ARM_COND_PL 0x5 +#define ARM_COND_VS 0x6 +#define ARM_COND_VC 0x7 +#define ARM_COND_HI 0x8 +#define ARM_COND_LS 0x9 +#define ARM_COND_GE 0xa +#define ARM_COND_LT 0xb +#define ARM_COND_GT 0xc +#define ARM_COND_LE 0xd +#define ARM_COND_AL 0xe + +/* register shift types */ +#define SRTYPE_LSL 0 +#define SRTYPE_LSR 1 +#define SRTYPE_ASR 2 +#define SRTYPE_ROR 3 + +#define ARM_INST_ADD_R 0x00800000 +#define ARM_INST_ADD_I 0x02800000 + +#define ARM_INST_AND_R 0x00000000 +#define ARM_INST_AND_I 0x02000000 + +#define ARM_INST_BIC_R 0x01c00000 +#define ARM_INST_BIC_I 0x03c00000 + +#define ARM_INST_B 0x0a000000 +#define ARM_INST_BX 0x012FFF10 +#define ARM_INST_BLX_R 0x012fff30 + +#define ARM_INST_CMP_R 0x01500000 +#define ARM_INST_CMP_I 0x03500000 + +#define ARM_INST_LDRB_I 0x05d00000 +#define ARM_INST_LDRB_R 0x07d00000 +#define ARM_INST_LDRH_I 0x01d000b0 +#define ARM_INST_LDR_I 0x05900000 + +#define ARM_INST_LDM 0x08900000 + +#define ARM_INST_LSL_I 0x01a00000 +#define ARM_INST_LSL_R 0x01a00010 + +#define ARM_INST_LSR_I 0x01a00020 +#define ARM_INST_LSR_R 0x01a00030 + +#define ARM_INST_MOV_R 0x01a00000 +#define ARM_INST_MOV_I 0x03a00000 +#define ARM_INST_MOVW 0x03000000 +#define ARM_INST_MOVT 0x03400000 + +#define ARM_INST_MUL 0x00000090 + +#define ARM_INST_POP 0x08bd0000 +#define ARM_INST_PUSH 0x092d0000 + +#define ARM_INST_ORR_R 0x01800000 +#define ARM_INST_ORR_I 0x03800000 + +#define ARM_INST_REV 0x06bf0f30 +#define ARM_INST_REV16 0x06bf0fb0 + +#define ARM_INST_RSB_I 0x02600000 + +#define ARM_INST_SUB_R 0x00400000 +#define ARM_INST_SUB_I 0x02400000 + +#define ARM_INST_STR_I 0x05800000 + +#define ARM_INST_TST_R 0x01100000 +#define ARM_INST_TST_I 0x03100000 + +#define ARM_INST_UDIV 0x0730f010 + +#define ARM_INST_UMULL 0x00800090 + +/* register */ +#define _AL3_R(op, rd, rn, rm) ((op ## _R) | (rd) << 12 | (rn) << 16 | (rm)) +/* immediate */ +#define _AL3_I(op, rd, rn, imm) ((op ## _I) | (rd) << 12 | (rn) << 16 | (imm)) + +#define ARM_ADD_R(rd, rn, rm) _AL3_R(ARM_INST_ADD, rd, rn, rm) +#define ARM_ADD_I(rd, rn, imm) _AL3_I(ARM_INST_ADD, rd, rn, imm) + +#define ARM_AND_R(rd, rn, rm) _AL3_R(ARM_INST_AND, rd, rn, rm) +#define ARM_AND_I(rd, rn, imm) _AL3_I(ARM_INST_AND, rd, rn, imm) + +#define ARM_BIC_R(rd, rn, rm) _AL3_R(ARM_INST_BIC, rd, rn, rm) +#define ARM_BIC_I(rd, rn, imm) _AL3_I(ARM_INST_BIC, rd, rn, imm) + +#define ARM_B(imm24) (ARM_INST_B | ((imm24) & 0xffffff)) +#define ARM_BX(rm) (ARM_INST_BX | (rm)) +#define ARM_BLX_R(rm) (ARM_INST_BLX_R | (rm)) + +#define ARM_CMP_R(rn, rm) _AL3_R(ARM_INST_CMP, 0, rn, rm) +#define ARM_CMP_I(rn, imm) _AL3_I(ARM_INST_CMP, 0, rn, imm) + +#define ARM_LDR_I(rt, rn, off) (ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \ + | (off)) +#define ARM_LDRB_I(rt, rn, off) (ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \ + | (off)) +#define ARM_LDRB_R(rt, rn, rm) (ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \ + | (rm)) +#define ARM_LDRH_I(rt, rn, off) (ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \ + | (((off) & 0xf0) << 4) | ((off) & 0xf)) + +#define ARM_LDM(rn, regs) (ARM_INST_LDM | (rn) << 16 | (regs)) + +#define ARM_LSL_R(rd, rn, rm) (_AL3_R(ARM_INST_LSL, rd, 0, rn) | (rm) << 8) +#define ARM_LSL_I(rd, rn, imm) (_AL3_I(ARM_INST_LSL, rd, 0, rn) | (imm) << 7) + +#define ARM_LSR_R(rd, rn, rm) (_AL3_R(ARM_INST_LSR, rd, 0, rn) | (rm) << 8) +#define ARM_LSR_I(rd, rn, imm) (_AL3_I(ARM_INST_LSR, rd, 0, rn) | (imm) << 7) + +#define ARM_MOV_R(rd, rm) _AL3_R(ARM_INST_MOV, rd, 0, rm) +#define ARM_MOV_I(rd, imm) _AL3_I(ARM_INST_MOV, rd, 0, imm) + +#define ARM_MOVW(rd, imm) \ + (ARM_INST_MOVW | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff)) + +#define ARM_MOVT(rd, imm) \ + (ARM_INST_MOVT | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff)) + +#define ARM_MUL(rd, rm, rn) (ARM_INST_MUL | (rd) << 16 | (rm) << 8 | (rn)) + +#define ARM_POP(regs) (ARM_INST_POP | (regs)) +#define ARM_PUSH(regs) (ARM_INST_PUSH | (regs)) + +#define ARM_ORR_R(rd, rn, rm) _AL3_R(ARM_INST_ORR, rd, rn, rm) +#define ARM_ORR_I(rd, rn, imm) _AL3_I(ARM_INST_ORR, rd, rn, imm) +#define ARM_ORR_S(rd, rn, rm, type, rs) \ + (ARM_ORR_R(rd, rn, rm) | (type) << 5 | (rs) << 7) + +#define ARM_REV(rd, rm) (ARM_INST_REV | (rd) << 12 | (rm)) +#define ARM_REV16(rd, rm) (ARM_INST_REV16 | (rd) << 12 | (rm)) + +#define ARM_RSB_I(rd, rn, imm) _AL3_I(ARM_INST_RSB, rd, rn, imm) + +#define ARM_SUB_R(rd, rn, rm) _AL3_R(ARM_INST_SUB, rd, rn, rm) +#define ARM_SUB_I(rd, rn, imm) _AL3_I(ARM_INST_SUB, rd, rn, imm) + +#define ARM_STR_I(rt, rn, off) (ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \ + | (off)) + +#define ARM_TST_R(rn, rm) _AL3_R(ARM_INST_TST, 0, rn, rm) +#define ARM_TST_I(rn, imm) _AL3_I(ARM_INST_TST, 0, rn, imm) + +#define ARM_UDIV(rd, rn, rm) (ARM_INST_UDIV | (rd) << 16 | (rn) | (rm) << 8) + +#define ARM_UMULL(rd_lo, rd_hi, rn, rm) (ARM_INST_UMULL | (rd_hi) << 16 \ + | (rd_lo) << 12 | (rm) << 8 | rn) + +#endif /* PFILTER_OPCODES_ARM_H */ diff --git a/arch/arm/plat-versatile/Kconfig b/arch/arm/plat-versatile/Kconfig index c6f4b9625e71..043f7b02a9e7 100644 --- a/arch/arm/plat-versatile/Kconfig +++ b/arch/arm/plat-versatile/Kconfig @@ -11,6 +11,6 @@ config PLAT_VERSATILE_LEDS depends on ARCH_REALVIEW || ARCH_VERSATILE config PLAT_VERSATILE_SCHED_CLOCK - def_bool y if !ARCH_INTEGRATOR_AP + def_bool y endif diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 8f3ccddbdafd..d89068f6d6e5 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -18,6 +18,7 @@ #include <linux/smp.h> #include <linux/init.h> +#include <asm/cp15.h> #include <asm/cputype.h> #include <asm/thread_notify.h> #include <asm/vfp.h> diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 999d6a03e436..5138927a416c 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -26,7 +26,6 @@ config CLKSRC_DBX500_PRCMU config CLKSRC_DBX500_PRCMU_SCHED_CLOCK bool "Clocksource PRCMU Timer sched_clock" depends on (CLKSRC_DBX500_PRCMU && !NOMADIK_MTU_SCHED_CLOCK) - select HAVE_SCHED_CLOCK default y help Use the always on PRCMU Timer as sched_clock diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh index 98cffcb941ea..a2af2e88daf3 100644 --- a/scripts/gcc-goto.sh +++ b/scripts/gcc-goto.sh @@ -2,4 +2,20 @@ # Test for gcc 'asm goto' support # Copyright (C) 2010, Jason Baron <jbaron@redhat.com> -echo "int main(void) { entry: asm goto (\"\"::::entry); return 0; }" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y" +cat << "END" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y" +int main(void) +{ +#ifdef __arm__ + /* + * Not related to asm goto, but used by jump label + * and broken on some ARM GCC versions (see GCC Bug 48637). + */ + static struct { int dummy; int state; } tp; + asm (".long %c0" :: "i" (&tp.state)); +#endif + +entry: + asm goto ("" :::: entry); + return 0; +} +END |