diff --git a/Makefile b/Makefile index 3133a5772eeb..865126614a33 100644 --- a/Makefile +++ b/Makefile @@ -591,6 +591,11 @@ KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) # conserve stack if available KBUILD_CFLAGS += $(call cc-option,-fconserve-stack) +# check for 'asm goto' +ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y) + KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO +endif + # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments # But warn user when we do so warn-assign = \ diff --git a/arch/Kconfig b/arch/Kconfig index fe48fc7a3eba..53d7f619a1b9 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -158,4 +158,7 @@ config HAVE_PERF_EVENTS_NMI subsystem. Also has support for calculating CPU cycle events to determine how many clock cycles in a given period. +config HAVE_ARCH_JUMP_LABEL + bool + source "kernel/gcov/Kconfig" diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 491e9d6de191..9212cd42a832 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -30,6 +30,7 @@ config SPARC select PERF_USE_VMALLOC select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG + select HAVE_ARCH_JUMP_LABEL config SPARC32 def_bool !64BIT diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h new file mode 100644 index 000000000000..62e66d7b2fb6 --- /dev/null +++ b/arch/sparc/include/asm/jump_label.h @@ -0,0 +1,32 @@ +#ifndef _ASM_SPARC_JUMP_LABEL_H +#define _ASM_SPARC_JUMP_LABEL_H + +#ifdef __KERNEL__ + +#include +#include + +#define JUMP_LABEL_NOP_SIZE 4 + +#define JUMP_LABEL(key, label) \ + do { \ + asm goto("1:\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".pushsection __jump_table, \"a\"\n\t"\ + ".word 1b, %l[" #label "], %c0\n\t" \ + ".popsection \n\t" \ + : : "i" (key) : : label);\ + } while (0) + +#endif /* __KERNEL__ */ + +typedef u32 jump_label_t; + +struct jump_entry { + jump_label_t code; + jump_label_t target; + jump_label_t key; +}; + +#endif diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index 0c2dc1f24a9a..599398fbbc7c 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -119,3 +119,5 @@ obj-$(CONFIG_COMPAT) += $(audit--y) pc--$(CONFIG_PERF_EVENTS) := perf_event.o obj-$(CONFIG_SPARC64) += $(pc--y) + +obj-$(CONFIG_SPARC64) += jump_label.o diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c new file mode 100644 index 000000000000..ea2dafc93d78 --- /dev/null +++ b/arch/sparc/kernel/jump_label.c @@ -0,0 +1,47 @@ +#include +#include +#include +#include + +#include +#include + +#ifdef HAVE_JUMP_LABEL + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + u32 val; + u32 *insn = (u32 *) (unsigned long) entry->code; + + if (type == JUMP_LABEL_ENABLE) { + s32 off = (s32)entry->target - (s32)entry->code; + +#ifdef CONFIG_SPARC64 + /* ba,pt %xcc, . + (off << 2) */ + val = 0x10680000 | ((u32) off >> 2); +#else + /* ba . + (off << 2) */ + val = 0x10800000 | ((u32) off >> 2); +#endif + } else { + val = 0x01000000; + } + + get_online_cpus(); + mutex_lock(&text_mutex); + *insn = val; + flushi(insn); + mutex_unlock(&text_mutex); + put_online_cpus(); +} + +void arch_jump_label_text_poke_early(jump_label_t addr) +{ + u32 *insn_p = (u32 *) (unsigned long) addr; + + *insn_p = 0x01000000; + flushi(insn_p); +} + +#endif diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c index f848aadf54dc..ee3c7dde8d9f 100644 --- a/arch/sparc/kernel/module.c +++ b/arch/sparc/kernel/module.c @@ -18,6 +18,9 @@ #include #ifdef CONFIG_SPARC64 + +#include + static void *module_map(unsigned long size) { struct vm_struct *area; @@ -227,6 +230,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { + /* make jump label nops */ + jump_label_apply_nops(me); + /* Cheetah's I-cache is fully coherent. */ if (tlb_type == spitfire) { unsigned long va; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cea0cd9a316f..b431a0824a93 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -59,6 +59,7 @@ config X86 select ANON_INODES select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER + select HAVE_ARCH_JUMP_LABEL config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index bc6abb7bc7ee..76561d20ea2f 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -4,6 +4,7 @@ #include #include #include +#include #include /* @@ -160,6 +161,8 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, #define __parainstructions_end NULL #endif +extern void *text_poke_early(void *addr, const void *opcode, size_t len); + /* * Clear and restore the kernel write-protection flag on the local CPU. * Allows the kernel to edit read-only pages. @@ -180,4 +183,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, extern void *text_poke(void *addr, const void *opcode, size_t len); extern void *text_poke_smp(void *addr, const void *opcode, size_t len); +#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) +#define IDEAL_NOP_SIZE_5 5 +extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; +extern void arch_init_ideal_nop5(void); +#else +static inline void arch_init_ideal_nop5(void) {} +#endif + #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h new file mode 100644 index 000000000000..f52d42e80585 --- /dev/null +++ b/arch/x86/include/asm/jump_label.h @@ -0,0 +1,37 @@ +#ifndef _ASM_X86_JUMP_LABEL_H +#define _ASM_X86_JUMP_LABEL_H + +#ifdef __KERNEL__ + +#include +#include + +#define JUMP_LABEL_NOP_SIZE 5 + +# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t" + +# define JUMP_LABEL(key, label) \ + do { \ + asm goto("1:" \ + JUMP_LABEL_INITIAL_NOP \ + ".pushsection __jump_table, \"a\" \n\t"\ + _ASM_PTR "1b, %l[" #label "], %c0 \n\t" \ + ".popsection \n\t" \ + : : "i" (key) : : label); \ + } while (0) + +#endif /* __KERNEL__ */ + +#ifdef CONFIG_X86_64 +typedef u64 jump_label_t; +#else +typedef u32 jump_label_t; +#endif + +struct jump_entry { + jump_label_t code; + jump_label_t target; + jump_label_t key; +}; + +#endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0925676266bd..24fa1718ddb9 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -32,7 +32,7 @@ GCOV_PROFILE_paravirt.o := n obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o ldt.o dumpstack.o -obj-y += setup.o x86_init.o i8259.o irqinit.o +obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o obj-$(CONFIG_X86_VISWS) += visws_quirks.o obj-$(CONFIG_X86_32) += probe_roms_32.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index f65ab8b014c4..cb0e6d385f6d 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -195,7 +195,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; -static void *text_poke_early(void *addr, const void *opcode, size_t len); +void *text_poke_early(void *addr, const void *opcode, size_t len); /* Replace instructions with better alternatives for this CPU type. This runs before SMP is initialized to avoid SMP problems with @@ -522,7 +522,7 @@ void __init alternative_instructions(void) * instructions. And on the local CPU you need to be protected again NMI or MCE * handlers seeing an inconsistent instruction while you patch. */ -static void *__init_or_module text_poke_early(void *addr, const void *opcode, +void *__init_or_module text_poke_early(void *addr, const void *opcode, size_t len) { unsigned long flags; @@ -641,3 +641,67 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) return addr; } +#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) + +unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; + +void __init arch_init_ideal_nop5(void) +{ + extern const unsigned char ftrace_test_p6nop[]; + extern const unsigned char ftrace_test_nop5[]; + extern const unsigned char ftrace_test_jmp[]; + int faulted = 0; + + /* + * There is no good nop for all x86 archs. + * We will default to using the P6_NOP5, but first we + * will test to make sure that the nop will actually + * work on this CPU. If it faults, we will then + * go to a lesser efficient 5 byte nop. If that fails + * we then just use a jmp as our nop. This isn't the most + * efficient nop, but we can not use a multi part nop + * since we would then risk being preempted in the middle + * of that nop, and if we enabled tracing then, it might + * cause a system crash. + * + * TODO: check the cpuid to determine the best nop. + */ + asm volatile ( + "ftrace_test_jmp:" + "jmp ftrace_test_p6nop\n" + "nop\n" + "nop\n" + "nop\n" /* 2 byte jmp + 3 bytes */ + "ftrace_test_p6nop:" + P6_NOP5 + "jmp 1f\n" + "ftrace_test_nop5:" + ".byte 0x66,0x66,0x66,0x66,0x90\n" + "1:" + ".section .fixup, \"ax\"\n" + "2: movl $1, %0\n" + " jmp ftrace_test_nop5\n" + "3: movl $2, %0\n" + " jmp 1b\n" + ".previous\n" + _ASM_EXTABLE(ftrace_test_p6nop, 2b) + _ASM_EXTABLE(ftrace_test_nop5, 3b) + : "=r"(faulted) : "0" (faulted)); + + switch (faulted) { + case 0: + pr_info("converting mcount calls to 0f 1f 44 00 00\n"); + memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5); + break; + case 1: + pr_info("converting mcount calls to 66 66 66 66 90\n"); + memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5); + break; + case 2: + pr_info("converting mcount calls to jmp . + 5\n"); + memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5); + break; + } + +} +#endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index cd37469b54ee..3afb33f14d2d 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -257,14 +257,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) return mod_code_status; } - - - -static unsigned char ftrace_nop[MCOUNT_INSN_SIZE]; - static unsigned char *ftrace_nop_replace(void) { - return ftrace_nop; + return ideal_nop5; } static int @@ -338,62 +333,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func) int __init ftrace_dyn_arch_init(void *data) { - extern const unsigned char ftrace_test_p6nop[]; - extern const unsigned char ftrace_test_nop5[]; - extern const unsigned char ftrace_test_jmp[]; - int faulted = 0; - - /* - * There is no good nop for all x86 archs. - * We will default to using the P6_NOP5, but first we - * will test to make sure that the nop will actually - * work on this CPU. If it faults, we will then - * go to a lesser efficient 5 byte nop. If that fails - * we then just use a jmp as our nop. This isn't the most - * efficient nop, but we can not use a multi part nop - * since we would then risk being preempted in the middle - * of that nop, and if we enabled tracing then, it might - * cause a system crash. - * - * TODO: check the cpuid to determine the best nop. - */ - asm volatile ( - "ftrace_test_jmp:" - "jmp ftrace_test_p6nop\n" - "nop\n" - "nop\n" - "nop\n" /* 2 byte jmp + 3 bytes */ - "ftrace_test_p6nop:" - P6_NOP5 - "jmp 1f\n" - "ftrace_test_nop5:" - ".byte 0x66,0x66,0x66,0x66,0x90\n" - "1:" - ".section .fixup, \"ax\"\n" - "2: movl $1, %0\n" - " jmp ftrace_test_nop5\n" - "3: movl $2, %0\n" - " jmp 1b\n" - ".previous\n" - _ASM_EXTABLE(ftrace_test_p6nop, 2b) - _ASM_EXTABLE(ftrace_test_nop5, 3b) - : "=r"(faulted) : "0" (faulted)); - - switch (faulted) { - case 0: - pr_info("converting mcount calls to 0f 1f 44 00 00\n"); - memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE); - break; - case 1: - pr_info("converting mcount calls to 66 66 66 66 90\n"); - memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE); - break; - case 2: - pr_info("converting mcount calls to jmp . + 5\n"); - memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE); - break; - } - /* The return code is retured via data */ *(unsigned long *)data = 0; diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c new file mode 100644 index 000000000000..961b6b30ba90 --- /dev/null +++ b/arch/x86/kernel/jump_label.c @@ -0,0 +1,50 @@ +/* + * jump label x86 support + * + * Copyright (C) 2009 Jason Baron + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef HAVE_JUMP_LABEL + +union jump_code_union { + char code[JUMP_LABEL_NOP_SIZE]; + struct { + char jump; + int offset; + } __attribute__((packed)); +}; + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + union jump_code_union code; + + if (type == JUMP_LABEL_ENABLE) { + code.jump = 0xe9; + code.offset = entry->target - + (entry->code + JUMP_LABEL_NOP_SIZE); + } else + memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE); + get_online_cpus(); + mutex_lock(&text_mutex); + text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + mutex_unlock(&text_mutex); + put_online_cpus(); +} + +void arch_jump_label_text_poke_early(jump_label_t addr) +{ + text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE); +} + +#endif diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e05952af5d26..1cbd54c0df99 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1218,7 +1218,8 @@ static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) } /* Check whether the address range is reserved */ if (ftrace_text_reserved(src, src + len - 1) || - alternatives_text_reserved(src, src + len - 1)) + alternatives_text_reserved(src, src + len - 1) || + jump_label_text_reserved(src, src + len - 1)) return -EBUSY; return len; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index e0bc186d7501..5399f58de7ed 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -239,6 +239,9 @@ int module_finalize(const Elf_Ehdr *hdr, apply_paravirt(pseg, pseg + para->sh_size); } + /* make jump label nops */ + jump_label_apply_nops(me); + return module_bug_finalize(hdr, sechdrs, me); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c3a4fbb2b996..00e167870f71 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -112,6 +112,7 @@ #include #endif #include +#include /* * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. @@ -726,6 +727,7 @@ void __init setup_arch(char **cmdline_p) { int acpi = 0; int k8 = 0; + unsigned long flags; #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); @@ -1071,6 +1073,10 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.banner(); mcheck_init(); + + local_irq_save(flags); + arch_init_ideal_nop5(); + local_irq_restore(flags); } #ifdef CONFIG_X86_32 diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8a92a170fb7d..ef2af9948eac 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -220,6 +220,8 @@ \ BUG_TABLE \ \ + JUMP_TABLE \ + \ /* PCI quirks */ \ .pci_fixup : AT(ADDR(.pci_fixup) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start_pci_fixups_early) = .; \ @@ -563,6 +565,14 @@ #define BUG_TABLE #endif +#define JUMP_TABLE \ + . = ALIGN(8); \ + __jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) { \ + VMLINUX_SYMBOL(__start___jump_table) = .; \ + *(__jump_table) \ + VMLINUX_SYMBOL(__stop___jump_table) = .; \ + } + #ifdef CONFIG_PM_TRACE #define TRACEDATA \ . = ALIGN(4); \ diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 52c0da4bdd18..bef3cda44c4c 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -1,6 +1,8 @@ #ifndef _DYNAMIC_DEBUG_H #define _DYNAMIC_DEBUG_H +#include + /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They * use independent hash functions, to reduce the chance of false positives. @@ -22,8 +24,6 @@ struct _ddebug { const char *function; const char *filename; const char *format; - char primary_hash; - char secondary_hash; unsigned int lineno:24; /* * The flags field controls the behaviour at the callsite. @@ -33,6 +33,7 @@ struct _ddebug { #define _DPRINTK_FLAGS_PRINT (1<<0) /* printk() a message using the format */ #define _DPRINTK_FLAGS_DEFAULT 0 unsigned int flags:8; + char enabled; } __attribute__((aligned(8))); @@ -42,33 +43,35 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n, #if defined(CONFIG_DYNAMIC_DEBUG) extern int ddebug_remove_module(const char *mod_name); -#define __dynamic_dbg_enabled(dd) ({ \ - int __ret = 0; \ - if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) && \ - (dynamic_debug_enabled2 & (1LL << DEBUG_HASH2)))) \ - if (unlikely(dd.flags)) \ - __ret = 1; \ - __ret; }) - #define dynamic_pr_debug(fmt, ...) do { \ + __label__ do_printk; \ + __label__ out; \ static struct _ddebug descriptor \ __used \ __attribute__((section("__verbose"), aligned(8))) = \ - { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ - DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ - if (__dynamic_dbg_enabled(descriptor)) \ - printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ + _DPRINTK_FLAGS_DEFAULT }; \ + JUMP_LABEL(&descriptor.enabled, do_printk); \ + goto out; \ +do_printk: \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ +out: ; \ } while (0) #define dynamic_dev_dbg(dev, fmt, ...) do { \ + __label__ do_printk; \ + __label__ out; \ static struct _ddebug descriptor \ __used \ __attribute__((section("__verbose"), aligned(8))) = \ - { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ - DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ - if (__dynamic_dbg_enabled(descriptor)) \ - dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ + _DPRINTK_FLAGS_DEFAULT }; \ + JUMP_LABEL(&descriptor.enabled, do_printk); \ + goto out; \ +do_printk: \ + dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ +out: ; \ } while (0) #else diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h new file mode 100644 index 000000000000..b72cd9f92c2e --- /dev/null +++ b/include/linux/jump_label.h @@ -0,0 +1,64 @@ +#ifndef _LINUX_JUMP_LABEL_H +#define _LINUX_JUMP_LABEL_H + +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL) +# include +# define HAVE_JUMP_LABEL +#endif + +enum jump_label_type { + JUMP_LABEL_ENABLE, + JUMP_LABEL_DISABLE +}; + +struct module; + +#ifdef HAVE_JUMP_LABEL + +extern struct jump_entry __start___jump_table[]; +extern struct jump_entry __stop___jump_table[]; + +extern void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type); +extern void arch_jump_label_text_poke_early(jump_label_t addr); +extern void jump_label_update(unsigned long key, enum jump_label_type type); +extern void jump_label_apply_nops(struct module *mod); +extern int jump_label_text_reserved(void *start, void *end); + +#define enable_jump_label(key) \ + jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE); + +#define disable_jump_label(key) \ + jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE); + +#else + +#define JUMP_LABEL(key, label) \ +do { \ + if (unlikely(*key)) \ + goto label; \ +} while (0) + +#define enable_jump_label(cond_var) \ +do { \ + *(cond_var) = 1; \ +} while (0) + +#define disable_jump_label(cond_var) \ +do { \ + *(cond_var) = 0; \ +} while (0) + +static inline int jump_label_apply_nops(struct module *mod) +{ + return 0; +} + +static inline int jump_label_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif + +#endif diff --git a/include/linux/module.h b/include/linux/module.h index 8a6b9fdc7ffa..403ac26023ce 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -350,7 +350,10 @@ struct module struct tracepoint *tracepoints; unsigned int num_tracepoints; #endif - +#ifdef HAVE_JUMP_LABEL + struct jump_entry *jump_entries; + unsigned int num_jump_entries; +#endif #ifdef CONFIG_TRACING const char **trace_bprintk_fmt_start; unsigned int num_trace_bprintk_fmt; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 103d1b61aacb..a4a90b6726ce 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -17,6 +17,7 @@ #include #include #include +#include struct module; struct tracepoint; @@ -145,7 +146,9 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ - if (unlikely(__tracepoint_##name.state)) \ + JUMP_LABEL(&__tracepoint_##name.state, do_trace); \ + return; \ +do_trace: \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args)); \ diff --git a/kernel/Makefile b/kernel/Makefile index 0b72d1a74be0..d52b473c99a1 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -10,7 +10,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ - async.o range.o + async.o range.o jump_label.o obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o obj-y += groups.o diff --git a/kernel/jump_label.c b/kernel/jump_label.c new file mode 100644 index 000000000000..7be868bf25c6 --- /dev/null +++ b/kernel/jump_label.c @@ -0,0 +1,429 @@ +/* + * jump label support + * + * Copyright (C) 2009 Jason Baron + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef HAVE_JUMP_LABEL + +#define JUMP_LABEL_HASH_BITS 6 +#define JUMP_LABEL_TABLE_SIZE (1 << JUMP_LABEL_HASH_BITS) +static struct hlist_head jump_label_table[JUMP_LABEL_TABLE_SIZE]; + +/* mutex to protect coming/going of the the jump_label table */ +static DEFINE_MUTEX(jump_label_mutex); + +struct jump_label_entry { + struct hlist_node hlist; + struct jump_entry *table; + int nr_entries; + /* hang modules off here */ + struct hlist_head modules; + unsigned long key; +}; + +struct jump_label_module_entry { + struct hlist_node hlist; + struct jump_entry *table; + int nr_entries; + struct module *mod; +}; + +static int jump_label_cmp(const void *a, const void *b) +{ + const struct jump_entry *jea = a; + const struct jump_entry *jeb = b; + + if (jea->key < jeb->key) + return -1; + + if (jea->key > jeb->key) + return 1; + + return 0; +} + +static void +sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop) +{ + unsigned long size; + + size = (((unsigned long)stop - (unsigned long)start) + / sizeof(struct jump_entry)); + sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL); +} + +static struct jump_label_entry *get_jump_label_entry(jump_label_t key) +{ + struct hlist_head *head; + struct hlist_node *node; + struct jump_label_entry *e; + u32 hash = jhash((void *)&key, sizeof(jump_label_t), 0); + + head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)]; + hlist_for_each_entry(e, node, head, hlist) { + if (key == e->key) + return e; + } + return NULL; +} + +static struct jump_label_entry * +add_jump_label_entry(jump_label_t key, int nr_entries, struct jump_entry *table) +{ + struct hlist_head *head; + struct jump_label_entry *e; + u32 hash; + + e = get_jump_label_entry(key); + if (e) + return ERR_PTR(-EEXIST); + + e = kmalloc(sizeof(struct jump_label_entry), GFP_KERNEL); + if (!e) + return ERR_PTR(-ENOMEM); + + hash = jhash((void *)&key, sizeof(jump_label_t), 0); + head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)]; + e->key = key; + e->table = table; + e->nr_entries = nr_entries; + INIT_HLIST_HEAD(&(e->modules)); + hlist_add_head(&e->hlist, head); + return e; +} + +static int +build_jump_label_hashtable(struct jump_entry *start, struct jump_entry *stop) +{ + struct jump_entry *iter, *iter_begin; + struct jump_label_entry *entry; + int count; + + sort_jump_label_entries(start, stop); + iter = start; + while (iter < stop) { + entry = get_jump_label_entry(iter->key); + if (!entry) { + iter_begin = iter; + count = 0; + while ((iter < stop) && + (iter->key == iter_begin->key)) { + iter++; + count++; + } + entry = add_jump_label_entry(iter_begin->key, + count, iter_begin); + if (IS_ERR(entry)) + return PTR_ERR(entry); + } else { + WARN_ONCE(1, KERN_ERR "build_jump_hashtable: unexpected entry!\n"); + return -1; + } + } + return 0; +} + +/*** + * jump_label_update - update jump label text + * @key - key value associated with a a jump label + * @type - enum set to JUMP_LABEL_ENABLE or JUMP_LABEL_DISABLE + * + * Will enable/disable the jump for jump label @key, depending on the + * value of @type. + * + */ + +void jump_label_update(unsigned long key, enum jump_label_type type) +{ + struct jump_entry *iter; + struct jump_label_entry *entry; + struct hlist_node *module_node; + struct jump_label_module_entry *e_module; + int count; + + mutex_lock(&jump_label_mutex); + entry = get_jump_label_entry((jump_label_t)key); + if (entry) { + count = entry->nr_entries; + iter = entry->table; + while (count--) { + if (kernel_text_address(iter->code)) + arch_jump_label_transform(iter, type); + iter++; + } + /* eanble/disable jump labels in modules */ + hlist_for_each_entry(e_module, module_node, &(entry->modules), + hlist) { + count = e_module->nr_entries; + iter = e_module->table; + while (count--) { + if (kernel_text_address(iter->code)) + arch_jump_label_transform(iter, type); + iter++; + } + } + } + mutex_unlock(&jump_label_mutex); +} + +static int addr_conflict(struct jump_entry *entry, void *start, void *end) +{ + if (entry->code <= (unsigned long)end && + entry->code + JUMP_LABEL_NOP_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +#ifdef CONFIG_MODULES + +static int module_conflict(void *start, void *end) +{ + struct hlist_head *head; + struct hlist_node *node, *node_next, *module_node, *module_node_next; + struct jump_label_entry *e; + struct jump_label_module_entry *e_module; + struct jump_entry *iter; + int i, count; + int conflict = 0; + + for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { + head = &jump_label_table[i]; + hlist_for_each_entry_safe(e, node, node_next, head, hlist) { + hlist_for_each_entry_safe(e_module, module_node, + module_node_next, + &(e->modules), hlist) { + count = e_module->nr_entries; + iter = e_module->table; + while (count--) { + if (addr_conflict(iter, start, end)) { + conflict = 1; + goto out; + } + iter++; + } + } + } + } +out: + return conflict; +} + +#endif + +/*** + * jump_label_text_reserved - check if addr range is reserved + * @start: start text addr + * @end: end text addr + * + * checks if the text addr located between @start and @end + * overlaps with any of the jump label patch addresses. Code + * that wants to modify kernel text should first verify that + * it does not overlap with any of the jump label addresses. + * + * returns 1 if there is an overlap, 0 otherwise + */ +int jump_label_text_reserved(void *start, void *end) +{ + struct jump_entry *iter; + struct jump_entry *iter_start = __start___jump_table; + struct jump_entry *iter_stop = __start___jump_table; + int conflict = 0; + + mutex_lock(&jump_label_mutex); + iter = iter_start; + while (iter < iter_stop) { + if (addr_conflict(iter, start, end)) { + conflict = 1; + goto out; + } + iter++; + } + + /* now check modules */ +#ifdef CONFIG_MODULES + conflict = module_conflict(start, end); +#endif +out: + mutex_unlock(&jump_label_mutex); + return conflict; +} + +static __init int init_jump_label(void) +{ + int ret; + struct jump_entry *iter_start = __start___jump_table; + struct jump_entry *iter_stop = __stop___jump_table; + struct jump_entry *iter; + + mutex_lock(&jump_label_mutex); + ret = build_jump_label_hashtable(__start___jump_table, + __stop___jump_table); + iter = iter_start; + while (iter < iter_stop) { + arch_jump_label_text_poke_early(iter->code); + iter++; + } + mutex_unlock(&jump_label_mutex); + return ret; +} +early_initcall(init_jump_label); + +#ifdef CONFIG_MODULES + +static struct jump_label_module_entry * +add_jump_label_module_entry(struct jump_label_entry *entry, + struct jump_entry *iter_begin, + int count, struct module *mod) +{ + struct jump_label_module_entry *e; + + e = kmalloc(sizeof(struct jump_label_module_entry), GFP_KERNEL); + if (!e) + return ERR_PTR(-ENOMEM); + e->mod = mod; + e->nr_entries = count; + e->table = iter_begin; + hlist_add_head(&e->hlist, &entry->modules); + return e; +} + +static int add_jump_label_module(struct module *mod) +{ + struct jump_entry *iter, *iter_begin; + struct jump_label_entry *entry; + struct jump_label_module_entry *module_entry; + int count; + + /* if the module doesn't have jump label entries, just return */ + if (!mod->num_jump_entries) + return 0; + + sort_jump_label_entries(mod->jump_entries, + mod->jump_entries + mod->num_jump_entries); + iter = mod->jump_entries; + while (iter < mod->jump_entries + mod->num_jump_entries) { + entry = get_jump_label_entry(iter->key); + iter_begin = iter; + count = 0; + while ((iter < mod->jump_entries + mod->num_jump_entries) && + (iter->key == iter_begin->key)) { + iter++; + count++; + } + if (!entry) { + entry = add_jump_label_entry(iter_begin->key, 0, NULL); + if (IS_ERR(entry)) + return PTR_ERR(entry); + } + module_entry = add_jump_label_module_entry(entry, iter_begin, + count, mod); + if (IS_ERR(module_entry)) + return PTR_ERR(module_entry); + } + return 0; +} + +static void remove_jump_label_module(struct module *mod) +{ + struct hlist_head *head; + struct hlist_node *node, *node_next, *module_node, *module_node_next; + struct jump_label_entry *e; + struct jump_label_module_entry *e_module; + int i; + + /* if the module doesn't have jump label entries, just return */ + if (!mod->num_jump_entries) + return; + + for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { + head = &jump_label_table[i]; + hlist_for_each_entry_safe(e, node, node_next, head, hlist) { + hlist_for_each_entry_safe(e_module, module_node, + module_node_next, + &(e->modules), hlist) { + if (e_module->mod == mod) { + hlist_del(&e_module->hlist); + kfree(e_module); + } + } + if (hlist_empty(&e->modules) && (e->nr_entries == 0)) { + hlist_del(&e->hlist); + kfree(e); + } + } + } +} + +static int +jump_label_module_notify(struct notifier_block *self, unsigned long val, + void *data) +{ + struct module *mod = data; + int ret = 0; + + switch (val) { + case MODULE_STATE_COMING: + mutex_lock(&jump_label_mutex); + ret = add_jump_label_module(mod); + if (ret) + remove_jump_label_module(mod); + mutex_unlock(&jump_label_mutex); + break; + case MODULE_STATE_GOING: + mutex_lock(&jump_label_mutex); + remove_jump_label_module(mod); + mutex_unlock(&jump_label_mutex); + break; + } + return ret; +} + +/*** + * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop() + * @mod: module to patch + * + * Allow for run-time selection of the optimal nops. Before the module + * loads patch these with arch_get_jump_label_nop(), which is specified by + * the arch specific jump label code. + */ +void jump_label_apply_nops(struct module *mod) +{ + struct jump_entry *iter; + + /* if the module doesn't have jump label entries, just return */ + if (!mod->num_jump_entries) + return; + + iter = mod->jump_entries; + while (iter < mod->jump_entries + mod->num_jump_entries) { + arch_jump_label_text_poke_early(iter->code); + iter++; + } +} + +struct notifier_block jump_label_module_nb = { + .notifier_call = jump_label_module_notify, + .priority = 0, +}; + +static __init int init_jump_label_module(void) +{ + return register_module_notifier(&jump_label_module_nb); +} +early_initcall(init_jump_label_module); + +#endif /* CONFIG_MODULES */ + +#endif diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 6dd5359e1f0e..ec4210c6501e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -1146,7 +1147,8 @@ int __kprobes register_kprobe(struct kprobe *p) preempt_disable(); if (!kernel_text_address((unsigned long) p->addr) || in_kprobes_functions((unsigned long) p->addr) || - ftrace_text_reserved(p->addr, p->addr)) { + ftrace_text_reserved(p->addr, p->addr) || + jump_label_text_reserved(p->addr, p->addr)) { preempt_enable(); return -EINVAL; } diff --git a/kernel/module.c b/kernel/module.c index d0b5f8db11b4..eba134157ef6 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -55,6 +55,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -2308,6 +2309,11 @@ static void find_module_sections(struct module *mod, struct load_info *info) sizeof(*mod->tracepoints), &mod->num_tracepoints); #endif +#ifdef HAVE_JUMP_LABEL + mod->jump_entries = section_objs(info, "__jump_table", + sizeof(*mod->jump_entries), + &mod->num_jump_entries); +#endif #ifdef CONFIG_EVENT_TRACING mod->trace_events = section_objs(info, "_ftrace_events", sizeof(*mod->trace_events), diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c index a7cc3793baf6..209b379a4721 100644 --- a/kernel/trace/trace_workqueue.c +++ b/kernel/trace/trace_workqueue.c @@ -263,6 +263,11 @@ int __init trace_workqueue_early_init(void) { int ret, cpu; + for_each_possible_cpu(cpu) { + spin_lock_init(&workqueue_cpu_stat(cpu)->lock); + INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list); + } + ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL); if (ret) goto out; @@ -279,11 +284,6 @@ int __init trace_workqueue_early_init(void) if (ret) goto no_creation; - for_each_possible_cpu(cpu) { - spin_lock_init(&workqueue_cpu_stat(cpu)->lock); - INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list); - } - return 0; no_creation: diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index c77f3eceea25..d6073a50a6ca 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -25,6 +25,7 @@ #include #include #include +#include extern struct tracepoint __start___tracepoints[]; extern struct tracepoint __stop___tracepoints[]; @@ -263,7 +264,13 @@ static void set_tracepoint(struct tracepoint_entry **entry, * is used. */ rcu_assign_pointer(elem->funcs, (*entry)->funcs); - elem->state = active; + if (!elem->state && active) { + enable_jump_label(&elem->state); + elem->state = active; + } else if (elem->state && !active) { + disable_jump_label(&elem->state); + elem->state = active; + } } /* @@ -277,7 +284,10 @@ static void disable_tracepoint(struct tracepoint *elem) if (elem->unregfunc && elem->state) elem->unregfunc(); - elem->state = 0; + if (elem->state) { + disable_jump_label(&elem->state); + elem->state = 0; + } rcu_assign_pointer(elem->funcs, NULL); } diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 02afc2533728..e925c7b960f1 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -26,19 +26,11 @@ #include #include #include +#include extern struct _ddebug __start___verbose[]; extern struct _ddebug __stop___verbose[]; -/* dynamic_debug_enabled, and dynamic_debug_enabled2 are bitmasks in which - * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They - * use independent hash functions, to reduce the chance of false positives. - */ -long long dynamic_debug_enabled; -EXPORT_SYMBOL_GPL(dynamic_debug_enabled); -long long dynamic_debug_enabled2; -EXPORT_SYMBOL_GPL(dynamic_debug_enabled2); - struct ddebug_table { struct list_head link; char *mod_name; @@ -87,26 +79,6 @@ static char *ddebug_describe_flags(struct _ddebug *dp, char *buf, return buf; } -/* - * must be called with ddebug_lock held - */ - -static int disabled_hash(char hash, bool first_table) -{ - struct ddebug_table *dt; - char table_hash_value; - - list_for_each_entry(dt, &ddebug_tables, link) { - if (first_table) - table_hash_value = dt->ddebugs->primary_hash; - else - table_hash_value = dt->ddebugs->secondary_hash; - if (dt->num_enabled && (hash == table_hash_value)) - return 0; - } - return 1; -} - /* * Search the tables for _ddebug's which match the given * `query' and apply the `flags' and `mask' to them. Tells @@ -170,17 +142,9 @@ static void ddebug_change(const struct ddebug_query *query, dt->num_enabled++; dp->flags = newflags; if (newflags) { - dynamic_debug_enabled |= - (1LL << dp->primary_hash); - dynamic_debug_enabled2 |= - (1LL << dp->secondary_hash); + enable_jump_label(&dp->enabled); } else { - if (disabled_hash(dp->primary_hash, true)) - dynamic_debug_enabled &= - ~(1LL << dp->primary_hash); - if (disabled_hash(dp->secondary_hash, false)) - dynamic_debug_enabled2 &= - ~(1LL << dp->secondary_hash); + disable_jump_label(&dp->enabled); } if (verbose) printk(KERN_INFO diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 54fd1b700131..7bfcf1a09ac5 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -101,14 +101,6 @@ basename_flags = -D"KBUILD_BASENAME=KBUILD_STR($(call name-fix,$(basetarget)))" modname_flags = $(if $(filter 1,$(words $(modname))),\ -D"KBUILD_MODNAME=KBUILD_STR($(call name-fix,$(modname)))") -#hash values -ifdef CONFIG_DYNAMIC_DEBUG -debug_flags = -D"DEBUG_HASH=$(shell ./scripts/basic/hash djb2 $(@D)$(modname))"\ - -D"DEBUG_HASH2=$(shell ./scripts/basic/hash r5 $(@D)$(modname))" -else -debug_flags = -endif - orig_c_flags = $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(KBUILD_SUBDIR_CCFLAGS) \ $(ccflags-y) $(CFLAGS_$(basetarget).o) _c_flags = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(orig_c_flags)) @@ -152,8 +144,7 @@ endif c_flags = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \ $(__c_flags) $(modkern_cflags) \ - -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags) \ - $(debug_flags) + -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags) a_flags = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \ $(__a_flags) $(modkern_aflags) diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile index 09559951df12..4c324a1f1e0e 100644 --- a/scripts/basic/Makefile +++ b/scripts/basic/Makefile @@ -9,7 +9,7 @@ # fixdep: Used to generate dependency information during build process # docproc: Used in Documentation/DocBook -hostprogs-y := fixdep docproc hash +hostprogs-y := fixdep docproc always := $(hostprogs-y) # fixdep is needed to compile other host programs diff --git a/scripts/basic/hash.c b/scripts/basic/hash.c deleted file mode 100644 index 2ef5d3f666b8..000000000000 --- a/scripts/basic/hash.c +++ /dev/null @@ -1,64 +0,0 @@ -/* - * Copyright (C) 2008 Red Hat, Inc., Jason Baron - * - */ - -#include -#include -#include - -#define DYNAMIC_DEBUG_HASH_BITS 6 - -static const char *program; - -static void usage(void) -{ - printf("Usage: %s \n", program); - exit(1); -} - -/* djb2 hashing algorithm by Dan Bernstein. From: - * http://www.cse.yorku.ca/~oz/hash.html - */ - -static unsigned int djb2_hash(char *str) -{ - unsigned long hash = 5381; - int c; - - c = *str; - while (c) { - hash = ((hash << 5) + hash) + c; - c = *++str; - } - return (unsigned int)(hash & ((1 << DYNAMIC_DEBUG_HASH_BITS) - 1)); -} - -static unsigned int r5_hash(char *str) -{ - unsigned long hash = 0; - int c; - - c = *str; - while (c) { - hash = (hash + (c << 4) + (c >> 4)) * 11; - c = *++str; - } - return (unsigned int)(hash & ((1 << DYNAMIC_DEBUG_HASH_BITS) - 1)); -} - -int main(int argc, char *argv[]) -{ - program = argv[0]; - - if (argc != 3) - usage(); - if (!strcmp(argv[1], "djb2")) - printf("%d\n", djb2_hash(argv[2])); - else if (!strcmp(argv[1], "r5")) - printf("%d\n", r5_hash(argv[2])); - else - usage(); - exit(0); -} - diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh new file mode 100644 index 000000000000..8e82424be7aa --- /dev/null +++ b/scripts/gcc-goto.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# Test for gcc 'asm goto' suport +# Copyright (C) 2010, Jason Baron + +echo "int main(void) { entry: asm goto (\"\"::::entry); return 0; }" | $1 -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"