diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/Kconfig | 5 | ||||
-rw-r--r-- | arch/x86/include/asm/alternative.h | 14 | ||||
-rw-r--r-- | arch/x86/include/asm/tsc.h | 1 | ||||
-rw-r--r-- | arch/x86/kernel/alternative.c | 155 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/jump_label.c | 16 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/common.h | 5 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/core.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/opt.c | 110 | ||||
-rw-r--r-- | arch/x86/kernel/traps.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/tsc.c | 6 |
11 files changed, 133 insertions, 191 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b32ebf9..3106e0e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -81,7 +81,6 @@ config X86 select HAVE_USER_RETURN_NOTIFIER select ARCH_BINFMT_ELF_RANDOMIZE_PIE select HAVE_ARCH_JUMP_LABEL - select HAVE_TEXT_POKE_SMP select HAVE_GENERIC_HARDIRQS select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select SPARSE_IRQ @@ -2332,10 +2331,6 @@ config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 -config HAVE_TEXT_POKE_SMP - bool - select STOP_MACHINE if SMP - config X86_DEV_DMA_OPS bool depends on X86_64 || STA2X11 diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 58ed6d9..0a3f9c9 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -5,6 +5,7 @@ #include <linux/stddef.h> #include <linux/stringify.h> #include <asm/asm.h> +#include <asm/ptrace.h> /* * Alternative inline assembly for SMP. @@ -220,20 +221,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len); * no thread can be preempted in the instructions being modified (no iret to an * invalid instruction possible) or if the instructions are changed from a * consistent state to another consistent state atomically. - * More care must be taken when modifying code in the SMP case because of - * Intel's errata. text_poke_smp() takes care that errata, but still - * doesn't support NMI/MCE handler code modifying. * On the local CPU you need to be protected again NMI or MCE handlers seeing an * inconsistent instruction while you patch. */ -struct text_poke_param { - void *addr; - const void *opcode; - size_t len; -}; - 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); -extern void text_poke_smp_batch(struct text_poke_param *params, int n); +extern int poke_int3_handler(struct pt_regs *regs); +extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index c91e8b9..235be70 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -49,6 +49,7 @@ extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); +extern int check_tsc_disabled(void); extern unsigned long native_calibrate_tsc(void); extern int tsc_clocksource_reliable; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c15cf9a..15e8563 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -11,6 +11,7 @@ #include <linux/memory.h> #include <linux/stop_machine.h> #include <linux/slab.h> +#include <linux/kdebug.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> @@ -596,97 +597,93 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) return addr; } -/* - * Cross-modifying kernel text with stop_machine(). - * This code originally comes from immediate value. - */ -static atomic_t stop_machine_first; -static int wrote_text; +static void do_sync_core(void *info) +{ + sync_core(); +} -struct text_poke_params { - struct text_poke_param *params; - int nparams; -}; +static bool bp_patching_in_progress; +static void *bp_int3_handler, *bp_int3_addr; -static int __kprobes stop_machine_text_poke(void *data) +int poke_int3_handler(struct pt_regs *regs) { - struct text_poke_params *tpp = data; - struct text_poke_param *p; - int i; + /* bp_patching_in_progress */ + smp_rmb(); - if (atomic_xchg(&stop_machine_first, 0)) { - for (i = 0; i < tpp->nparams; i++) { - p = &tpp->params[i]; - text_poke(p->addr, p->opcode, p->len); - } - smp_wmb(); /* Make sure other cpus see that this has run */ - wrote_text = 1; - } else { - while (!wrote_text) - cpu_relax(); - smp_mb(); /* Load wrote_text before following execution */ - } + if (likely(!bp_patching_in_progress)) + return 0; - for (i = 0; i < tpp->nparams; i++) { - p = &tpp->params[i]; - flush_icache_range((unsigned long)p->addr, - (unsigned long)p->addr + p->len); - } - /* - * Intel Archiecture Software Developer's Manual section 7.1.3 specifies - * that a core serializing instruction such as "cpuid" should be - * executed on _each_ core before the new instruction is made visible. - */ - sync_core(); - return 0; -} + if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr) + return 0; + + /* set up the specified breakpoint handler */ + regs->ip = (unsigned long) bp_int3_handler; + + return 1; -/** - * text_poke_smp - Update instructions on a live kernel on SMP - * @addr: address to modify - * @opcode: source of the copy - * @len: length to copy - * - * Modify multi-byte instruction by using stop_machine() on SMP. This allows - * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying - * should be allowed, since stop_machine() does _not_ protect code against - * NMI and MCE. - * - * Note: Must be called under get_online_cpus() and text_mutex. - */ -void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) -{ - struct text_poke_params tpp; - struct text_poke_param p; - - p.addr = addr; - p.opcode = opcode; - p.len = len; - tpp.params = &p; - tpp.nparams = 1; - atomic_set(&stop_machine_first, 1); - wrote_text = 0; - /* Use __stop_machine() because the caller already got online_cpus. */ - __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); - return addr; } /** - * text_poke_smp_batch - Update instructions on a live kernel on SMP - * @params: an array of text_poke parameters - * @n: the number of elements in params. + * text_poke_bp() -- update instructions on live kernel on SMP + * @addr: address to patch + * @opcode: opcode of new instruction + * @len: length to copy + * @handler: address to jump to when the temporary breakpoint is hit * - * Modify multi-byte instruction by using stop_machine() on SMP. Since the - * stop_machine() is heavy task, it is better to aggregate text_poke requests - * and do it once if possible. + * Modify multi-byte instruction by using int3 breakpoint on SMP. + * We completely avoid stop_machine() here, and achieve the + * synchronization using int3 breakpoint. * - * Note: Must be called under get_online_cpus() and text_mutex. + * The way it is done: + * - add a int3 trap to the address that will be patched + * - sync cores + * - update all but the first byte of the patched range + * - sync cores + * - replace the first byte (int3) by the first byte of + * replacing opcode + * - sync cores + * + * Note: must be called under text_mutex. */ -void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) +void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) { - struct text_poke_params tpp = {.params = params, .nparams = n}; + unsigned char int3 = 0xcc; + + bp_int3_handler = handler; + bp_int3_addr = (u8 *)addr + sizeof(int3); + bp_patching_in_progress = true; + /* + * Corresponding read barrier in int3 notifier for + * making sure the in_progress flags is correctly ordered wrt. + * patching + */ + smp_wmb(); + + text_poke(addr, &int3, sizeof(int3)); - atomic_set(&stop_machine_first, 1); - wrote_text = 0; - __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); + on_each_cpu(do_sync_core, NULL, 1); + + if (len - sizeof(int3) > 0) { + /* patch all but the first byte */ + text_poke((char *)addr + sizeof(int3), + (const char *) opcode + sizeof(int3), + len - sizeof(int3)); + /* + * According to Intel, this core syncing is very likely + * not necessary and we'd be safe even without it. But + * better safe than sorry (plus there's not only Intel). + */ + on_each_cpu(do_sync_core, NULL, 1); + } + + /* patch the first byte */ + text_poke(addr, opcode, sizeof(int3)); + + on_each_cpu(do_sync_core, NULL, 1); + + bp_patching_in_progress = false; + smp_wmb(); + + return addr; } + diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index a7c7305..8355c84 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1884,6 +1884,7 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { userpg->cap_usr_time = 0; + userpg->cap_usr_time_zero = 0; userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; @@ -1897,6 +1898,11 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) userpg->time_mult = this_cpu_read(cyc2ns); userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; + + if (sched_clock_stable && !check_tsc_disabled()) { + userpg->cap_usr_time_zero = 1; + userpg->time_zero = this_cpu_read(cyc2ns_offset); + } } /* diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 2889b3d..460f5d9 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -37,7 +37,19 @@ static void __jump_label_transform(struct jump_entry *entry, } else memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE); - (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + /* + * Make text_poke_bp() a default fallback poker. + * + * At the time the change is being done, just ignore whether we + * are doing nop -> jump or jump -> nop transition, and assume + * always nop being the 'currently valid' instruction + * + */ + if (poker) + (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + else + text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE, + (void *)entry->code + JUMP_LABEL_NOP_SIZE); } void arch_jump_label_transform(struct jump_entry *entry, @@ -45,7 +57,7 @@ void arch_jump_label_transform(struct jump_entry *entry, { get_online_cpus(); mutex_lock(&text_mutex); - __jump_label_transform(entry, type, text_poke_smp); + __jump_label_transform(entry, type, NULL); mutex_unlock(&text_mutex); put_online_cpus(); } diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index 2e9d4b5..c6ee63f 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -82,14 +82,9 @@ extern void synthesize_reljump(void *from, void *to); extern void synthesize_relcall(void *from, void *to); #ifdef CONFIG_OPTPROBES -extern int arch_init_optprobes(void); extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); #else /* !CONFIG_OPTPROBES */ -static inline int arch_init_optprobes(void) -{ - return 0; -} static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) { return 0; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 211bce4..cd49b2c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1068,7 +1068,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) int __init arch_init_kprobes(void) { - return arch_init_optprobes(); + return 0; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 76dc6f0..d71e994 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -371,31 +371,6 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) return 0; } -#define MAX_OPTIMIZE_PROBES 256 -static struct text_poke_param *jump_poke_params; -static struct jump_poke_buffer { - u8 buf[RELATIVEJUMP_SIZE]; -} *jump_poke_bufs; - -static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); - - insn_buf[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&insn_buf[1]) = rel; - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - /* * Replace breakpoints (int3) with relative jumps. * Caller must call with locking kprobe_mutex and text_mutex. @@ -403,37 +378,38 @@ static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, void __kprobes arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; - int c = 0; + u8 insn_buf[RELATIVEJUMP_SIZE]; list_for_each_entry_safe(op, tmp, oplist, list) { + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + WARN_ON(kprobe_disabled(&op->kp)); - /* Setup param */ - setup_optimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, + RELATIVE_ADDR_SIZE); + + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, + op->optinsn.insn); + list_del_init(&op->list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); } -static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) +/* Replace a relative jump with a breakpoint (int3). */ +void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) { + u8 insn_buf[RELATIVEJUMP_SIZE]; + /* Set int3 to first byte for kprobes */ insn_buf[0] = BREAKPOINT_INSTRUCTION; memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; + text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, + op->optinsn.insn); } /* @@ -444,34 +420,11 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list) { struct optimized_kprobe *op, *tmp; - int c = 0; list_for_each_entry_safe(op, tmp, oplist, list) { - /* Setup param */ - setup_unoptimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); + arch_unoptimize_kprobe(op); list_move(&op->list, done_list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -/* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) -{ - u8 buf[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); } int __kprobes @@ -491,22 +444,3 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) } return 0; } - -int __kprobes arch_init_optprobes(void) -{ - /* Allocate code buffer and parameter array */ - jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_bufs) - return -ENOMEM; - - jump_poke_params = kmalloc(sizeof(struct text_poke_param) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_params) { - kfree(jump_poke_bufs); - jump_poke_bufs = NULL; - return -ENOMEM; - } - - return 0; -} diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1b23a1c..8c8093b 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -58,6 +58,7 @@ #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> +#include <asm/alternative.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -327,6 +328,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + if (poke_int3_handler(regs)) + return; + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6ff4924..930e5d4 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -89,6 +89,12 @@ int check_tsc_unstable(void) } EXPORT_SYMBOL_GPL(check_tsc_unstable); +int check_tsc_disabled(void) +{ + return tsc_disabled; +} +EXPORT_SYMBOL_GPL(check_tsc_disabled); + #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { |