From d498f763950703c724c650db1d34a1c8679f9ca8 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:33:49 -0500 Subject: kprobes/x86: Cleanup RELATIVEJUMP_INSTRUCTION to RELATIVEJUMP_OPCODE Change RELATIVEJUMP_INSTRUCTION macro to RELATIVEJUMP_OPCODE since it represents just the opcode byte. Signed-off-by: Masami Hiramatsu Acked-by: Mathieu Desnoyers Cc: systemtap Cc: DLE Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133349.6725.99302.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/kprobes.h | 2 +- arch/x86/kernel/kprobes.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 4fe681de1e76..eaec8ea7bf18 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -32,7 +32,7 @@ struct kprobe; typedef u8 kprobe_opcode_t; #define BREAKPOINT_INSTRUCTION 0xcc -#define RELATIVEJUMP_INSTRUCTION 0xe9 +#define RELATIVEJUMP_OPCODE 0xe9 #define MAX_INSN_SIZE 16 #define MAX_STACK_SIZE 64 #define MIN_STACK_SIZE(ADDR) \ diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 5de9f4a9c3fd..15177cdfdd00 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -115,7 +115,7 @@ static void __kprobes set_jmp_op(void *from, void *to) } __attribute__((packed)) * jop; jop = (struct __arch_jmp_op *)from; jop->raddr = (s32)((long)(to) - ((long)(from) + 5)); - jop->op = RELATIVEJUMP_INSTRUCTION; + jop->op = RELATIVEJUMP_OPCODE; } /* -- cgit v1.2.3 From afd66255b9a48f5851326ddae50e2203fbf71dc9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:34:07 -0500 Subject: kprobes: Introduce kprobes jump optimization Introduce kprobes jump optimization arch-independent parts. Kprobes uses breakpoint instruction for interrupting execution flow, on some architectures, it can be replaced by a jump instruction and interruption emulation code. This gains kprobs' performance drastically. To enable this feature, set CONFIG_OPTPROBES=y (default y if the arch supports OPTPROBE). Changes in v9: - Fix a bug to optimize probe when enabling. - Check nearby probes can be optimize/unoptimize when disarming/arming kprobes, instead of registering/unregistering. This will help kprobe-tracer because most of probes on it are usually disabled. Changes in v6: - Cleanup coding style for readability. - Add comments around get/put_online_cpus(). Changes in v5: - Use get_online_cpus()/put_online_cpus() for avoiding text_mutex deadlock. Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133407.6725.81992.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- arch/Kconfig | 13 ++ include/linux/kprobes.h | 36 ++++ kernel/kprobes.c | 461 ++++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 459 insertions(+), 51 deletions(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 9d055b4f0585..e0ad3caf16d9 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -57,6 +57,17 @@ config KPROBES for kernel debugging, non-intrusive instrumentation and testing. If in doubt, say "N". +config OPTPROBES + bool "Kprobes jump optimization support (EXPERIMENTAL)" + default y + depends on KPROBES + depends on !PREEMPT + depends on HAVE_OPTPROBES + select KALLSYMS_ALL + help + This option will allow kprobes to optimize breakpoint to + a jump for reducing its overhead. + config HAVE_EFFICIENT_UNALIGNED_ACCESS bool help @@ -99,6 +110,8 @@ config HAVE_KPROBES config HAVE_KRETPROBES bool +config HAVE_OPTPROBES + bool # # An arch should select this if it provides all these things: # diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 1b672f74a32f..aed1f95c582f 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -122,6 +122,11 @@ struct kprobe { /* Kprobe status flags */ #define KPROBE_FLAG_GONE 1 /* breakpoint has already gone */ #define KPROBE_FLAG_DISABLED 2 /* probe is temporarily disabled */ +#define KPROBE_FLAG_OPTIMIZED 4 /* + * probe is really optimized. + * NOTE: + * this flag is only for optimized_kprobe. + */ /* Has this kprobe gone ? */ static inline int kprobe_gone(struct kprobe *p) @@ -134,6 +139,12 @@ static inline int kprobe_disabled(struct kprobe *p) { return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE); } + +/* Is this kprobe really running optimized path ? */ +static inline int kprobe_optimized(struct kprobe *p) +{ + return p->flags & KPROBE_FLAG_OPTIMIZED; +} /* * Special probe type that uses setjmp-longjmp type tricks to resume * execution at a specified entry with a matching prototype corresponding @@ -249,6 +260,31 @@ extern kprobe_opcode_t *get_insn_slot(void); extern void free_insn_slot(kprobe_opcode_t *slot, int dirty); extern void kprobes_inc_nmissed_count(struct kprobe *p); +#ifdef CONFIG_OPTPROBES +/* + * Internal structure for direct jump optimized probe + */ +struct optimized_kprobe { + struct kprobe kp; + struct list_head list; /* list for optimizing queue */ + struct arch_optimized_insn optinsn; +}; + +/* Architecture dependent functions for direct jump optimization */ +extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn); +extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); +extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op); +extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); +extern int arch_optimize_kprobe(struct optimized_kprobe *op); +extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); +extern kprobe_opcode_t *get_optinsn_slot(void); +extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty); +extern int arch_within_optimized_kprobe(struct optimized_kprobe *op, + unsigned long addr); + +extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); +#endif /* CONFIG_OPTPROBES */ + /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); void kretprobe_hash_lock(struct task_struct *tsk, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 78105623d739..612af2d61614 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -280,6 +281,33 @@ void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) __free_insn_slot(&kprobe_insn_slots, slot, dirty); mutex_unlock(&kprobe_insn_mutex); } +#ifdef CONFIG_OPTPROBES +/* For optimized_kprobe buffer */ +static DEFINE_MUTEX(kprobe_optinsn_mutex); /* Protects kprobe_optinsn_slots */ +static struct kprobe_insn_cache kprobe_optinsn_slots = { + .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages), + /* .insn_size is initialized later */ + .nr_garbage = 0, +}; +/* Get a slot for optimized_kprobe buffer */ +kprobe_opcode_t __kprobes *get_optinsn_slot(void) +{ + kprobe_opcode_t *ret = NULL; + + mutex_lock(&kprobe_optinsn_mutex); + ret = __get_insn_slot(&kprobe_optinsn_slots); + mutex_unlock(&kprobe_optinsn_mutex); + + return ret; +} + +void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty) +{ + mutex_lock(&kprobe_optinsn_mutex); + __free_insn_slot(&kprobe_optinsn_slots, slot, dirty); + mutex_unlock(&kprobe_optinsn_mutex); +} +#endif #endif /* We have preemption disabled.. so it is safe to use __ versions */ @@ -310,23 +338,324 @@ struct kprobe __kprobes *get_kprobe(void *addr) if (p->addr == addr) return p; } + return NULL; } +static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); + +/* Return true if the kprobe is an aggregator */ +static inline int kprobe_aggrprobe(struct kprobe *p) +{ + return p->pre_handler == aggr_pre_handler; +} + +/* + * Keep all fields in the kprobe consistent + */ +static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) +{ + memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t)); + memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn)); +} + +#ifdef CONFIG_OPTPROBES +/* + * Call all pre_handler on the list, but ignores its return value. + * This must be called from arch-dep optimized caller. + */ +void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe *kp; + + list_for_each_entry_rcu(kp, &p->list, list) { + if (kp->pre_handler && likely(!kprobe_disabled(kp))) { + set_kprobe_instance(kp); + kp->pre_handler(kp, regs); + } + reset_kprobe_instance(); + } +} + +/* Return true(!0) if the kprobe is ready for optimization. */ +static inline int kprobe_optready(struct kprobe *p) +{ + struct optimized_kprobe *op; + + if (kprobe_aggrprobe(p)) { + op = container_of(p, struct optimized_kprobe, kp); + return arch_prepared_optinsn(&op->optinsn); + } + + return 0; +} + +/* + * Return an optimized kprobe whose optimizing code replaces + * instructions including addr (exclude breakpoint). + */ +struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr) +{ + int i; + struct kprobe *p = NULL; + struct optimized_kprobe *op; + + /* Don't check i == 0, since that is a breakpoint case. */ + for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) + p = get_kprobe((void *)(addr - i)); + + if (p && kprobe_optready(p)) { + op = container_of(p, struct optimized_kprobe, kp); + if (arch_within_optimized_kprobe(op, addr)) + return p; + } + + return NULL; +} + +/* Optimization staging list, protected by kprobe_mutex */ +static LIST_HEAD(optimizing_list); + +static void kprobe_optimizer(struct work_struct *work); +static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); +#define OPTIMIZE_DELAY 5 + +/* Kprobe jump optimizer */ +static __kprobes void kprobe_optimizer(struct work_struct *work) +{ + struct optimized_kprobe *op, *tmp; + + /* Lock modules while optimizing kprobes */ + mutex_lock(&module_mutex); + mutex_lock(&kprobe_mutex); + if (kprobes_all_disarmed) + goto end; + + /* + * Wait for quiesence period to ensure all running interrupts + * are done. Because optprobe may modify multiple instructions + * there is a chance that Nth instruction is interrupted. In that + * case, running interrupt can return to 2nd-Nth byte of jump + * instruction. This wait is for avoiding it. + */ + synchronize_sched(); + + /* + * The optimization/unoptimization refers online_cpus via + * stop_machine() and cpu-hotplug modifies online_cpus. + * And same time, text_mutex will be held in cpu-hotplug and here. + * This combination can cause a deadlock (cpu-hotplug try to lock + * text_mutex but stop_machine can not be done because online_cpus + * has been changed) + * To avoid this deadlock, we need to call get_online_cpus() + * for preventing cpu-hotplug outside of text_mutex locking. + */ + get_online_cpus(); + mutex_lock(&text_mutex); + list_for_each_entry_safe(op, tmp, &optimizing_list, list) { + WARN_ON(kprobe_disabled(&op->kp)); + if (arch_optimize_kprobe(op) < 0) + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + list_del_init(&op->list); + } + mutex_unlock(&text_mutex); + put_online_cpus(); +end: + mutex_unlock(&kprobe_mutex); + mutex_unlock(&module_mutex); +} + +/* Optimize kprobe if p is ready to be optimized */ +static __kprobes void optimize_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + /* Check if the kprobe is disabled or not ready for optimization. */ + if (!kprobe_optready(p) || + (kprobe_disabled(p) || kprobes_all_disarmed)) + return; + + /* Both of break_handler and post_handler are not supported. */ + if (p->break_handler || p->post_handler) + return; + + op = container_of(p, struct optimized_kprobe, kp); + + /* Check there is no other kprobes at the optimized instructions */ + if (arch_check_optimized_kprobe(op) < 0) + return; + + /* Check if it is already optimized. */ + if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) + return; + + op->kp.flags |= KPROBE_FLAG_OPTIMIZED; + list_add(&op->list, &optimizing_list); + if (!delayed_work_pending(&optimizing_work)) + schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); +} + +/* Unoptimize a kprobe if p is optimized */ +static __kprobes void unoptimize_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) { + op = container_of(p, struct optimized_kprobe, kp); + if (!list_empty(&op->list)) + /* Dequeue from the optimization queue */ + list_del_init(&op->list); + else + /* Replace jump with break */ + arch_unoptimize_kprobe(op); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } +} + +/* Remove optimized instructions */ +static void __kprobes kill_optimized_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + if (!list_empty(&op->list)) { + /* Dequeue from the optimization queue */ + list_del_init(&op->list); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } + /* Don't unoptimize, because the target code will be freed. */ + arch_remove_optimized_kprobe(op); +} + +/* Try to prepare optimized instructions */ +static __kprobes void prepare_optimized_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + arch_prepare_optimized_kprobe(op); +} + +/* Free optimized instructions and optimized_kprobe */ +static __kprobes void free_aggr_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + arch_remove_optimized_kprobe(op); + kfree(op); +} + +/* Allocate new optimized_kprobe and try to prepare optimized instructions */ +static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL); + if (!op) + return NULL; + + INIT_LIST_HEAD(&op->list); + op->kp.addr = p->addr; + arch_prepare_optimized_kprobe(op); + + return &op->kp; +} + +static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); + +/* + * Prepare an optimized_kprobe and optimize it + * NOTE: p must be a normal registered kprobe + */ +static __kprobes void try_to_optimize_kprobe(struct kprobe *p) +{ + struct kprobe *ap; + struct optimized_kprobe *op; + + ap = alloc_aggr_kprobe(p); + if (!ap) + return; + + op = container_of(ap, struct optimized_kprobe, kp); + if (!arch_prepared_optinsn(&op->optinsn)) { + /* If failed to setup optimizing, fallback to kprobe */ + free_aggr_kprobe(ap); + return; + } + + init_aggr_kprobe(ap, p); + optimize_kprobe(ap); +} + +static void __kprobes __arm_kprobe(struct kprobe *p) +{ + struct kprobe *old_p; + + /* Check collision with other optimized kprobes */ + old_p = get_optimized_kprobe((unsigned long)p->addr); + if (unlikely(old_p)) + unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */ + + arch_arm_kprobe(p); + optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ +} + +static void __kprobes __disarm_kprobe(struct kprobe *p) +{ + struct kprobe *old_p; + + unoptimize_kprobe(p); /* Try to unoptimize */ + arch_disarm_kprobe(p); + + /* If another kprobe was blocked, optimize it. */ + old_p = get_optimized_kprobe((unsigned long)p->addr); + if (unlikely(old_p)) + optimize_kprobe(old_p); +} + +#else /* !CONFIG_OPTPROBES */ + +#define optimize_kprobe(p) do {} while (0) +#define unoptimize_kprobe(p) do {} while (0) +#define kill_optimized_kprobe(p) do {} while (0) +#define prepare_optimized_kprobe(p) do {} while (0) +#define try_to_optimize_kprobe(p) do {} while (0) +#define __arm_kprobe(p) arch_arm_kprobe(p) +#define __disarm_kprobe(p) arch_disarm_kprobe(p) + +static __kprobes void free_aggr_kprobe(struct kprobe *p) +{ + kfree(p); +} + +static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +{ + return kzalloc(sizeof(struct kprobe), GFP_KERNEL); +} +#endif /* CONFIG_OPTPROBES */ + /* Arm a kprobe with text_mutex */ static void __kprobes arm_kprobe(struct kprobe *kp) { + /* + * Here, since __arm_kprobe() doesn't use stop_machine(), + * this doesn't cause deadlock on text_mutex. So, we don't + * need get_online_cpus(). + */ mutex_lock(&text_mutex); - arch_arm_kprobe(kp); + __arm_kprobe(kp); mutex_unlock(&text_mutex); } /* Disarm a kprobe with text_mutex */ static void __kprobes disarm_kprobe(struct kprobe *kp) { + get_online_cpus(); /* For avoiding text_mutex deadlock */ mutex_lock(&text_mutex); - arch_disarm_kprobe(kp); + __disarm_kprobe(kp); mutex_unlock(&text_mutex); + put_online_cpus(); } /* @@ -395,7 +724,7 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs) void __kprobes kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; - if (p->pre_handler != aggr_pre_handler) { + if (!kprobe_aggrprobe(p)) { p->nmissed++; } else { list_for_each_entry_rcu(kp, &p->list, list) @@ -518,15 +847,6 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp) free_rp_inst(rp); } -/* - * Keep all fields in the kprobe consistent - */ -static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) -{ - memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t)); - memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn)); -} - /* * Add the new probe to ap->list. Fail if this is the * second jprobe at the address - two jprobes can't coexist @@ -534,6 +854,10 @@ static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) { BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); + + if (p->break_handler || p->post_handler) + unoptimize_kprobe(ap); /* Fall back to normal kprobe */ + if (p->break_handler) { if (ap->break_handler) return -EEXIST; @@ -548,7 +872,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) ap->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed) /* Arm the breakpoint again. */ - arm_kprobe(ap); + __arm_kprobe(ap); } return 0; } @@ -557,12 +881,13 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) * Fill in the required fields of the "manager kprobe". Replace the * earlier kprobe in the hlist with the manager kprobe */ -static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) +static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { + /* Copy p's insn slot to ap */ copy_kprobe(p, ap); flush_insn_slot(ap); ap->addr = p->addr; - ap->flags = p->flags; + ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED; ap->pre_handler = aggr_pre_handler; ap->fault_handler = aggr_fault_handler; /* We don't care the kprobe which has gone. */ @@ -572,8 +897,9 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) ap->break_handler = aggr_break_handler; INIT_LIST_HEAD(&ap->list); - list_add_rcu(&p->list, &ap->list); + INIT_HLIST_NODE(&ap->hlist); + list_add_rcu(&p->list, &ap->list); hlist_replace_rcu(&p->hlist, &ap->hlist); } @@ -587,12 +913,12 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, int ret = 0; struct kprobe *ap = old_p; - if (old_p->pre_handler != aggr_pre_handler) { - /* If old_p is not an aggr_probe, create new aggr_kprobe. */ - ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL); + if (!kprobe_aggrprobe(old_p)) { + /* If old_p is not an aggr_kprobe, create new aggr_kprobe. */ + ap = alloc_aggr_kprobe(old_p); if (!ap) return -ENOMEM; - add_aggr_kprobe(ap, old_p); + init_aggr_kprobe(ap, old_p); } if (kprobe_gone(ap)) { @@ -611,6 +937,9 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, */ return ret; + /* Prepare optimized instructions if possible. */ + prepare_optimized_kprobe(ap); + /* * Clear gone flag to prevent allocating new slot again, and * set disabled flag because it is not armed yet. @@ -619,6 +948,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, | KPROBE_FLAG_DISABLED; } + /* Copy ap's insn slot to p */ copy_kprobe(ap, p); return add_new_kprobe(ap, p); } @@ -769,27 +1099,34 @@ int __kprobes register_kprobe(struct kprobe *p) p->nmissed = 0; INIT_LIST_HEAD(&p->list); mutex_lock(&kprobe_mutex); + + get_online_cpus(); /* For avoiding text_mutex deadlock. */ + mutex_lock(&text_mutex); + old_p = get_kprobe(p->addr); if (old_p) { + /* Since this may unoptimize old_p, locking text_mutex. */ ret = register_aggr_kprobe(old_p, p); goto out; } - mutex_lock(&text_mutex); ret = arch_prepare_kprobe(p); if (ret) - goto out_unlock_text; + goto out; INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) - arch_arm_kprobe(p); + __arm_kprobe(p); + + /* Try to optimize kprobe */ + try_to_optimize_kprobe(p); -out_unlock_text: - mutex_unlock(&text_mutex); out: + mutex_unlock(&text_mutex); + put_online_cpus(); mutex_unlock(&kprobe_mutex); if (probed_mod) @@ -811,7 +1148,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p) return -EINVAL; if (old_p == p || - (old_p->pre_handler == aggr_pre_handler && + (kprobe_aggrprobe(old_p) && list_is_singular(&old_p->list))) { /* * Only probe on the hash list. Disarm only if kprobes are @@ -819,7 +1156,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p) * already have been removed. We save on flushing icache. */ if (!kprobes_all_disarmed && !kprobe_disabled(old_p)) - disarm_kprobe(p); + disarm_kprobe(old_p); hlist_del_rcu(&old_p->hlist); } else { if (p->break_handler && !kprobe_gone(p)) @@ -835,8 +1172,13 @@ noclean: list_del_rcu(&p->list); if (!kprobe_disabled(old_p)) { try_to_disable_aggr_kprobe(old_p); - if (!kprobes_all_disarmed && kprobe_disabled(old_p)) - disarm_kprobe(old_p); + if (!kprobes_all_disarmed) { + if (kprobe_disabled(old_p)) + disarm_kprobe(old_p); + else + /* Try to optimize this probe again */ + optimize_kprobe(old_p); + } } } return 0; @@ -853,7 +1195,7 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) old_p = list_entry(p->list.next, struct kprobe, list); list_del(&p->list); arch_remove_kprobe(old_p); - kfree(old_p); + free_aggr_kprobe(old_p); } } @@ -1149,7 +1491,7 @@ static void __kprobes kill_kprobe(struct kprobe *p) struct kprobe *kp; p->flags |= KPROBE_FLAG_GONE; - if (p->pre_handler == aggr_pre_handler) { + if (kprobe_aggrprobe(p)) { /* * If this is an aggr_kprobe, we have to list all the * chained probes and mark them GONE. @@ -1158,6 +1500,7 @@ static void __kprobes kill_kprobe(struct kprobe *p) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; p->break_handler = NULL; + kill_optimized_kprobe(p); } /* * Here, we can remove insn_slot safely, because no thread calls @@ -1267,6 +1610,11 @@ static int __init init_kprobes(void) } } +#if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT) + /* Init kprobe_optinsn_slots */ + kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; +#endif + /* By default, kprobes are armed */ kprobes_all_disarmed = false; @@ -1285,7 +1633,7 @@ static int __init init_kprobes(void) #ifdef CONFIG_DEBUG_FS static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, - const char *sym, int offset,char *modname) + const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; @@ -1295,19 +1643,21 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, kprobe_type = "j"; else kprobe_type = "k"; + if (sym) - seq_printf(pi, "%p %s %s+0x%x %s %s%s\n", + seq_printf(pi, "%p %s %s+0x%x %s ", p->addr, kprobe_type, sym, offset, - (modname ? modname : " "), - (kprobe_gone(p) ? "[GONE]" : ""), - ((kprobe_disabled(p) && !kprobe_gone(p)) ? - "[DISABLED]" : "")); + (modname ? modname : " ")); else - seq_printf(pi, "%p %s %p %s%s\n", - p->addr, kprobe_type, p->addr, - (kprobe_gone(p) ? "[GONE]" : ""), - ((kprobe_disabled(p) && !kprobe_gone(p)) ? - "[DISABLED]" : "")); + seq_printf(pi, "%p %s %p ", + p->addr, kprobe_type, p->addr); + + if (!pp) + pp = p; + seq_printf(pi, "%s%s%s\n", + (kprobe_gone(p) ? "[GONE]" : ""), + ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), + (kprobe_optimized(pp) ? "[OPTIMIZED]" : "")); } static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) @@ -1343,11 +1693,11 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v) hlist_for_each_entry_rcu(p, node, head, hlist) { sym = kallsyms_lookup((unsigned long)p->addr, NULL, &offset, &modname, namebuf); - if (p->pre_handler == aggr_pre_handler) { + if (kprobe_aggrprobe(p)) { list_for_each_entry_rcu(kp, &p->list, list) - report_probe(pi, kp, sym, offset, modname); + report_probe(pi, kp, sym, offset, modname, p); } else - report_probe(pi, p, sym, offset, modname); + report_probe(pi, p, sym, offset, modname, NULL); } preempt_enable(); return 0; @@ -1425,12 +1775,13 @@ int __kprobes enable_kprobe(struct kprobe *kp) goto out; } - if (!kprobes_all_disarmed && kprobe_disabled(p)) - arm_kprobe(p); - - p->flags &= ~KPROBE_FLAG_DISABLED; if (p != kp) kp->flags &= ~KPROBE_FLAG_DISABLED; + + if (!kprobes_all_disarmed && kprobe_disabled(p)) { + p->flags &= ~KPROBE_FLAG_DISABLED; + arm_kprobe(p); + } out: mutex_unlock(&kprobe_mutex); return ret; @@ -1450,12 +1801,13 @@ static void __kprobes arm_all_kprobes(void) if (!kprobes_all_disarmed) goto already_enabled; + /* Arming kprobes doesn't optimize kprobe itself */ mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) if (!kprobe_disabled(p)) - arch_arm_kprobe(p); + __arm_kprobe(p); } mutex_unlock(&text_mutex); @@ -1482,16 +1834,23 @@ static void __kprobes disarm_all_kprobes(void) kprobes_all_disarmed = true; printk(KERN_INFO "Kprobes globally disabled\n"); + + /* + * Here we call get_online_cpus() for avoiding text_mutex deadlock, + * because disarming may also unoptimize kprobes. + */ + get_online_cpus(); mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - arch_disarm_kprobe(p); + __disarm_kprobe(p); } } mutex_unlock(&text_mutex); + put_online_cpus(); mutex_unlock(&kprobe_mutex); /* Allow all currently running kprobes to complete */ synchronize_sched(); -- cgit v1.2.3 From 0f94eb634ef7af736dee5639aac1c2fe9635d089 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:34:23 -0500 Subject: kprobes/x86: Boost probes when reentering Integrate prepare_singlestep() into setup_singlestep() to boost up reenter probes, if possible. Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133423.6725.12071.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes.c | 48 +++++++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 22 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 15177cdfdd00..c69bb65006f3 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -406,18 +406,6 @@ static void __kprobes restore_btf(void) update_debugctlmsr(current->thread.debugctlmsr); } -static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) -{ - clear_btf(); - regs->flags |= X86_EFLAGS_TF; - regs->flags &= ~X86_EFLAGS_IF; - /* single step inline if the instruction is an int3 */ - if (p->opcode == BREAKPOINT_INSTRUCTION) - regs->ip = (unsigned long)p->addr; - else - regs->ip = (unsigned long)p->ainsn.insn; -} - void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -430,19 +418,38 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, } static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) + struct kprobe_ctlblk *kcb, int reenter) { #if !defined(CONFIG_PREEMPT) if (p->ainsn.boostable == 1 && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ - reset_current_kprobe(); + if (!reenter) + reset_current_kprobe(); + /* + * Reentering boosted probe doesn't reset current_kprobe, + * nor set current_kprobe, because it doesn't use single + * stepping. + */ regs->ip = (unsigned long)p->ainsn.insn; preempt_enable_no_resched(); return; } #endif - prepare_singlestep(p, regs); - kcb->kprobe_status = KPROBE_HIT_SS; + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p, regs, kcb); + kcb->kprobe_status = KPROBE_REENTER; + } else + kcb->kprobe_status = KPROBE_HIT_SS; + /* Prepare real single stepping */ + clear_btf(); + regs->flags |= X86_EFLAGS_TF; + regs->flags &= ~X86_EFLAGS_IF; + /* single step inline if the instruction is an int3 */ + if (p->opcode == BREAKPOINT_INSTRUCTION) + regs->ip = (unsigned long)p->addr; + else + regs->ip = (unsigned long)p->ainsn.insn; } /* @@ -456,11 +463,8 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: case KPROBE_HIT_ACTIVE: - save_previous_kprobe(kcb); - set_current_kprobe(p, regs, kcb); kprobes_inc_nmissed_count(p); - prepare_singlestep(p, regs); - kcb->kprobe_status = KPROBE_REENTER; + setup_singlestep(p, regs, kcb, 1); break; case KPROBE_HIT_SS: /* A probe has been hit in the codepath leading up to, or just @@ -535,13 +539,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) * more here. */ if (!p->pre_handler || !p->pre_handler(p, regs)) - setup_singlestep(p, regs, kcb); + setup_singlestep(p, regs, kcb, 0); return 1; } } else if (kprobe_running()) { p = __get_cpu_var(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { - setup_singlestep(p, regs, kcb); + setup_singlestep(p, regs, kcb, 0); return 1; } } /* else: not a kprobe fault; let the kernel handle it */ -- cgit v1.2.3 From f007ea2685692bafb386820144cf73a14016fc7c Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:34:30 -0500 Subject: kprobes/x86: Cleanup save/restore registers Introduce SAVE/RESOTRE_REGS_STRING for cleanup kretprobe-trampoline asm code. These macros will be used for emulating interruption. Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133430.6725.83342.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes.c | 128 ++++++++++++++++++++++++---------------------- 1 file changed, 67 insertions(+), 61 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index c69bb65006f3..4ae95befd0eb 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -554,6 +554,69 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) return 0; } +#ifdef CONFIG_X86_64 +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax. */ \ + " subq $24, %rsp\n" \ + " pushq %rdi\n" \ + " pushq %rsi\n" \ + " pushq %rdx\n" \ + " pushq %rcx\n" \ + " pushq %rax\n" \ + " pushq %r8\n" \ + " pushq %r9\n" \ + " pushq %r10\n" \ + " pushq %r11\n" \ + " pushq %rbx\n" \ + " pushq %rbp\n" \ + " pushq %r12\n" \ + " pushq %r13\n" \ + " pushq %r14\n" \ + " pushq %r15\n" +#define RESTORE_REGS_STRING \ + " popq %r15\n" \ + " popq %r14\n" \ + " popq %r13\n" \ + " popq %r12\n" \ + " popq %rbp\n" \ + " popq %rbx\n" \ + " popq %r11\n" \ + " popq %r10\n" \ + " popq %r9\n" \ + " popq %r8\n" \ + " popq %rax\n" \ + " popq %rcx\n" \ + " popq %rdx\n" \ + " popq %rsi\n" \ + " popq %rdi\n" \ + /* Skip orig_ax, ip, cs */ \ + " addq $24, %rsp\n" +#else +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax and gs. */ \ + " subl $16, %esp\n" \ + " pushl %fs\n" \ + " pushl %ds\n" \ + " pushl %es\n" \ + " pushl %eax\n" \ + " pushl %ebp\n" \ + " pushl %edi\n" \ + " pushl %esi\n" \ + " pushl %edx\n" \ + " pushl %ecx\n" \ + " pushl %ebx\n" +#define RESTORE_REGS_STRING \ + " popl %ebx\n" \ + " popl %ecx\n" \ + " popl %edx\n" \ + " popl %esi\n" \ + " popl %edi\n" \ + " popl %ebp\n" \ + " popl %eax\n" \ + /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ + " addl $24, %esp\n" +#endif + /* * When a retprobed function returns, this code saves registers and * calls trampoline_handler() runs, which calls the kretprobe's handler. @@ -567,65 +630,16 @@ static void __used __kprobes kretprobe_trampoline_holder(void) /* We don't bother saving the ss register */ " pushq %rsp\n" " pushfq\n" - /* - * Skip cs, ip, orig_ax. - * trampoline_handler() will plug in these values - */ - " subq $24, %rsp\n" - " pushq %rdi\n" - " pushq %rsi\n" - " pushq %rdx\n" - " pushq %rcx\n" - " pushq %rax\n" - " pushq %r8\n" - " pushq %r9\n" - " pushq %r10\n" - " pushq %r11\n" - " pushq %rbx\n" - " pushq %rbp\n" - " pushq %r12\n" - " pushq %r13\n" - " pushq %r14\n" - " pushq %r15\n" + SAVE_REGS_STRING " movq %rsp, %rdi\n" " call trampoline_handler\n" /* Replace saved sp with true return address. */ " movq %rax, 152(%rsp)\n" - " popq %r15\n" - " popq %r14\n" - " popq %r13\n" - " popq %r12\n" - " popq %rbp\n" - " popq %rbx\n" - " popq %r11\n" - " popq %r10\n" - " popq %r9\n" - " popq %r8\n" - " popq %rax\n" - " popq %rcx\n" - " popq %rdx\n" - " popq %rsi\n" - " popq %rdi\n" - /* Skip orig_ax, ip, cs */ - " addq $24, %rsp\n" + RESTORE_REGS_STRING " popfq\n" #else " pushf\n" - /* - * Skip cs, ip, orig_ax and gs. - * trampoline_handler() will plug in these values - */ - " subl $16, %esp\n" - " pushl %fs\n" - " pushl %es\n" - " pushl %ds\n" - " pushl %eax\n" - " pushl %ebp\n" - " pushl %edi\n" - " pushl %esi\n" - " pushl %edx\n" - " pushl %ecx\n" - " pushl %ebx\n" + SAVE_REGS_STRING " movl %esp, %eax\n" " call trampoline_handler\n" /* Move flags to cs */ @@ -633,15 +647,7 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " movl %edx, 52(%esp)\n" /* Replace saved flags with true return address. */ " movl %eax, 56(%esp)\n" - " popl %ebx\n" - " popl %ecx\n" - " popl %edx\n" - " popl %esi\n" - " popl %edi\n" - " popl %ebp\n" - " popl %eax\n" - /* Skip ds, es, fs, gs, orig_ax and ip */ - " addl $24, %esp\n" + RESTORE_REGS_STRING " popf\n" #endif " ret\n"); -- cgit v1.2.3 From 3d55cc8a058ee96291d6d45b1e35121b9920eca3 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:34:38 -0500 Subject: x86: Add text_poke_smp for SMP cross modifying code Add generic text_poke_smp for SMP which uses stop_machine() to synchronize modifying code. This stop_machine() method is officially described at "7.1.3 Handling Self- and Cross-Modifying Code" on the intel's software developer's manual 3A. Since stop_machine() can't protect code against NMI/MCE, this function can not modify those handlers. And also, this function is basically for modifying multibyte-single-instruction. For modifying multibyte-multi-instructions, we need another special trap & detour code. This code originaly comes from immediate values with stop_machine() version. Thanks Jason and Mathieu! Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE Cc: Mathieu Desnoyers Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133438.6725.80273.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/alternative.h | 4 ++- arch/x86/kernel/alternative.c | 60 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index ac80b7d70014..643d6ab3588b 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -160,10 +160,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, * 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. + * 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. */ 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); #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e63b80e5861c..c41f13c15e8f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -570,3 +571,62 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) local_irq_restore(flags); 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; + +struct text_poke_params { + void *addr; + const void *opcode; + size_t len; +}; + +static int __kprobes stop_machine_text_poke(void *data) +{ + struct text_poke_params *tpp = data; + + if (atomic_dec_and_test(&stop_machine_first)) { + text_poke(tpp->addr, tpp->opcode, tpp->len); + smp_wmb(); /* Make sure other cpus see that this has run */ + wrote_text = 1; + } else { + while (!wrote_text) + smp_rmb(); + sync_core(); + } + + flush_icache_range((unsigned long)tpp->addr, + (unsigned long)tpp->addr + tpp->len); + return 0; +} + +/** + * 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; + + tpp.addr = addr; + tpp.opcode = opcode; + tpp.len = len; + atomic_set(&stop_machine_first, 1); + wrote_text = 0; + stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); + return addr; +} + -- cgit v1.2.3 From c0f7ac3a9edde786bc129d37627953a8b8abefdf Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:34:46 -0500 Subject: kprobes/x86: Support kprobes jump optimization on x86 Introduce x86 arch-specific optimization code, which supports both of x86-32 and x86-64. This code also supports safety checking, which decodes whole of a function in which probe is inserted, and checks following conditions before optimization: - The optimized instructions which will be replaced by a jump instruction don't straddle the function boundary. - There is no indirect jump instruction, because it will jumps into the address range which is replaced by jump operand. - There is no jump/loop instruction which jumps into the address range which is replaced by jump operand. - Don't optimize kprobes if it is in functions into which fixup code will jumps. This uses text_poke_multibyte() which doesn't support modifying code on NMI/MCE handler. However, since kprobes itself doesn't support NMI/MCE code probing, it's not a problem. Changes in v9: - Use *_text_reserved() for checking the probe can be optimized. - Verify jump address range is in 2G range when preparing slot. - Backup original code when switching optimized buffer, instead of preparing buffer, because there can be int3 of other probes in preparing phase. - Check kprobe is disabled in arch_check_optimized_kprobe(). - Strictly check indirect jump opcodes (ff /4, ff /5). Changes in v6: - Split stop_machine-based jump patching code. - Update comments and coding style. Changes in v5: - Introduce stop_machine-based jump replacing. Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133446.6725.78994.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 1 + arch/x86/include/asm/kprobes.h | 29 +++ arch/x86/kernel/kprobes.c | 433 ++++++++++++++++++++++++++++++++++++++--- 3 files changed, 441 insertions(+), 22 deletions(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cbcbfdee3ee0..e6f5a98d5157 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -31,6 +31,7 @@ config X86 select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS select HAVE_KRETPROBES + select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index eaec8ea7bf18..4ffa345a8ccb 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -33,6 +33,9 @@ struct kprobe; typedef u8 kprobe_opcode_t; #define BREAKPOINT_INSTRUCTION 0xcc #define RELATIVEJUMP_OPCODE 0xe9 +#define RELATIVEJUMP_SIZE 5 +#define RELATIVECALL_OPCODE 0xe8 +#define RELATIVE_ADDR_SIZE 4 #define MAX_INSN_SIZE 16 #define MAX_STACK_SIZE 64 #define MIN_STACK_SIZE(ADDR) \ @@ -44,6 +47,17 @@ typedef u8 kprobe_opcode_t; #define flush_insn_slot(p) do { } while (0) +/* optinsn template addresses */ +extern kprobe_opcode_t optprobe_template_entry; +extern kprobe_opcode_t optprobe_template_val; +extern kprobe_opcode_t optprobe_template_call; +extern kprobe_opcode_t optprobe_template_end; +#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) +#define MAX_OPTINSN_SIZE \ + (((unsigned long)&optprobe_template_end - \ + (unsigned long)&optprobe_template_entry) + \ + MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE) + extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); @@ -64,6 +78,21 @@ struct arch_specific_insn { int boostable; }; +struct arch_optimized_insn { + /* copy of the original instructions */ + kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE]; + /* detour code buffer */ + kprobe_opcode_t *insn; + /* the size of instructions copied to detour code buffer */ + size_t size; +}; + +/* Return true (!0) if optinsn is prepared for optimization. */ +static inline int arch_prepared_optinsn(struct arch_optimized_insn *optinsn) +{ + return optinsn->size; +} + struct prev_kprobe { struct kprobe *kp; unsigned long status; diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 4ae95befd0eb..b43bbaebe2c0 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -106,16 +107,22 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { }; const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); -/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -static void __kprobes set_jmp_op(void *from, void *to) +static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) { - struct __arch_jmp_op { - char op; + struct __arch_relative_insn { + u8 op; s32 raddr; - } __attribute__((packed)) * jop; - jop = (struct __arch_jmp_op *)from; - jop->raddr = (s32)((long)(to) - ((long)(from) + 5)); - jop->op = RELATIVEJUMP_OPCODE; + } __attribute__((packed)) *insn; + + insn = (struct __arch_relative_insn *)from; + insn->raddr = (s32)((long)(to) - ((long)(from) + 5)); + insn->op = op; +} + +/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ +static void __kprobes synthesize_reljump(void *from, void *to) +{ + __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); } /* @@ -202,7 +209,7 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) /* * Basically, kp->ainsn.insn has an original instruction. * However, RIP-relative instruction can not do single-stepping - * at different place, fix_riprel() tweaks the displacement of + * at different place, __copy_instruction() tweaks the displacement of * that instruction. In that case, we can't recover the instruction * from the kp->ainsn.insn. * @@ -284,21 +291,37 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) } /* - * Adjust the displacement if the instruction uses the %rip-relative - * addressing mode. + * Copy an instruction and adjust the displacement if the instruction + * uses the %rip-relative addressing mode. * If it does, Return the address of the 32-bit displacement word. * If not, return null. * Only applicable to 64-bit x86. */ -static void __kprobes fix_riprel(struct kprobe *p) +static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover) { -#ifdef CONFIG_X86_64 struct insn insn; - kernel_insn_init(&insn, p->ainsn.insn); + int ret; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + kernel_insn_init(&insn, src); + if (recover) { + insn_get_opcode(&insn); + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { + ret = recover_probed_instruction(buf, + (unsigned long)src); + if (ret) + return 0; + kernel_insn_init(&insn, buf); + } + } + insn_get_length(&insn); + memcpy(dest, insn.kaddr, insn.length); + +#ifdef CONFIG_X86_64 if (insn_rip_relative(&insn)) { s64 newdisp; u8 *disp; + kernel_insn_init(&insn, dest); insn_get_displacement(&insn); /* * The copied instruction uses the %rip-relative addressing @@ -312,20 +335,23 @@ static void __kprobes fix_riprel(struct kprobe *p) * extension of the original signed 32-bit displacement would * have given. */ - newdisp = (u8 *) p->addr + (s64) insn.displacement.value - - (u8 *) p->ainsn.insn; + newdisp = (u8 *) src + (s64) insn.displacement.value - + (u8 *) dest; BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ - disp = (u8 *) p->ainsn.insn + insn_offset_displacement(&insn); + disp = (u8 *) dest + insn_offset_displacement(&insn); *(s32 *) disp = (s32) newdisp; } #endif + return insn.length; } static void __kprobes arch_copy_kprobe(struct kprobe *p) { - memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); - - fix_riprel(p); + /* + * Copy an instruction without recovering int3, because it will be + * put by another subsystem. + */ + __copy_instruction(p->ainsn.insn, p->addr, 0); if (can_boost(p->addr)) p->ainsn.boostable = 0; @@ -417,9 +443,20 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, *sara = (unsigned long) &kretprobe_trampoline; } +#ifdef CONFIG_OPTPROBES +static int __kprobes setup_detour_execution(struct kprobe *p, + struct pt_regs *regs, + int reenter); +#else +#define setup_detour_execution(p, regs, reenter) (0) +#endif + static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter) { + if (setup_detour_execution(p, regs, reenter)) + return; + #if !defined(CONFIG_PREEMPT) if (p->ainsn.boostable == 1 && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ @@ -815,8 +852,8 @@ static void __kprobes resume_execution(struct kprobe *p, * These instructions can be executed directly if it * jumps back to correct address. */ - set_jmp_op((void *)regs->ip, - (void *)orig_ip + (regs->ip - copy_ip)); + synthesize_reljump((void *)regs->ip, + (void *)orig_ip + (regs->ip - copy_ip)); p->ainsn.boostable = 1; } else { p->ainsn.boostable = -1; @@ -1043,6 +1080,358 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } + +#ifdef CONFIG_OPTPROBES + +/* Insert a call instruction at address 'from', which calls address 'to'.*/ +static void __kprobes synthesize_relcall(void *from, void *to) +{ + __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); +} + +/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ +static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, + unsigned long val) +{ +#ifdef CONFIG_X86_64 + *addr++ = 0x48; + *addr++ = 0xbf; +#else + *addr++ = 0xb8; +#endif + *(unsigned long *)addr = val; +} + +void __kprobes kprobes_optinsn_template_holder(void) +{ + asm volatile ( + ".global optprobe_template_entry\n" + "optprobe_template_entry: \n" +#ifdef CONFIG_X86_64 + /* We don't bother saving the ss register */ + " pushq %rsp\n" + " pushfq\n" + SAVE_REGS_STRING + " movq %rsp, %rsi\n" + ".global optprobe_template_val\n" + "optprobe_template_val: \n" + ASM_NOP5 + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call: \n" + ASM_NOP5 + /* Move flags to rsp */ + " movq 144(%rsp), %rdx\n" + " movq %rdx, 152(%rsp)\n" + RESTORE_REGS_STRING + /* Skip flags entry */ + " addq $8, %rsp\n" + " popfq\n" +#else /* CONFIG_X86_32 */ + " pushf\n" + SAVE_REGS_STRING + " movl %esp, %edx\n" + ".global optprobe_template_val\n" + "optprobe_template_val: \n" + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call: \n" + ASM_NOP5 + RESTORE_REGS_STRING + " addl $4, %esp\n" /* skip cs */ + " popf\n" +#endif + ".global optprobe_template_end\n" + "optprobe_template_end: \n"); +} + +#define TMPL_MOVE_IDX \ + ((long)&optprobe_template_val - (long)&optprobe_template_entry) +#define TMPL_CALL_IDX \ + ((long)&optprobe_template_call - (long)&optprobe_template_entry) +#define TMPL_END_IDX \ + ((long)&optprobe_template_end - (long)&optprobe_template_entry) + +#define INT3_SIZE sizeof(kprobe_opcode_t) + +/* Optimized kprobe call back function: called from optinsn */ +static void __kprobes optimized_callback(struct optimized_kprobe *op, + struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + preempt_disable(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(&op->kp); + } else { + /* Save skipped registers */ +#ifdef CONFIG_X86_64 + regs->cs = __KERNEL_CS; +#else + regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; +#endif + regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->orig_ax = ~0UL; + + __get_cpu_var(current_kprobe) = &op->kp; + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + opt_pre_handler(&op->kp, regs); + __get_cpu_var(current_kprobe) = NULL; + } + preempt_enable_no_resched(); +} + +static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) +{ + int len = 0, ret; + + while (len < RELATIVEJUMP_SIZE) { + ret = __copy_instruction(dest + len, src + len, 1); + if (!ret || !can_boost(dest + len)) + return -EINVAL; + len += ret; + } + /* Check whether the address range is reserved */ + if (ftrace_text_reserved(src, src + len - 1) || + alternatives_text_reserved(src, src + len - 1)) + return -EBUSY; + + return len; +} + +/* Check whether insn is indirect jump */ +static int __kprobes insn_is_indirect_jump(struct insn *insn) +{ + return ((insn->opcode.bytes[0] == 0xff && + (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ + insn->opcode.bytes[0] == 0xea); /* Segment based jump */ +} + +/* Check whether insn jumps into specified address range */ +static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) +{ + unsigned long target = 0; + + switch (insn->opcode.bytes[0]) { + case 0xe0: /* loopne */ + case 0xe1: /* loope */ + case 0xe2: /* loop */ + case 0xe3: /* jcxz */ + case 0xe9: /* near relative jump */ + case 0xeb: /* short relative jump */ + break; + case 0x0f: + if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ + break; + return 0; + default: + if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ + break; + return 0; + } + target = (unsigned long)insn->next_byte + insn->immediate.value; + + return (start <= target && target <= start + len); +} + +/* Decode whole function to ensure any instructions don't jump into target */ +static int __kprobes can_optimize(unsigned long paddr) +{ + int ret; + unsigned long addr, size = 0, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + /* Dummy buffers for lookup_symbol_attrs */ + static char __dummy_buf[KSYM_NAME_LEN]; + + /* Lookup symbol including addr */ + if (!kallsyms_lookup(paddr, &size, &offset, NULL, __dummy_buf)) + return 0; + + /* Check there is enough space for a relative jump. */ + if (size - offset < RELATIVEJUMP_SIZE) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr - offset + size) { /* Decode until function end */ + if (search_exception_tables(addr)) + /* + * Since some fixup code will jumps into this function, + * we can't optimize kprobe in this function. + */ + return 0; + kernel_insn_init(&insn, (void *)addr); + insn_get_opcode(&insn); + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { + ret = recover_probed_instruction(buf, addr); + if (ret) + return 0; + kernel_insn_init(&insn, buf); + } + insn_get_length(&insn); + /* Recover address */ + insn.kaddr = (void *)addr; + insn.next_byte = (void *)(addr + insn.length); + /* Check any instructions don't jump into target */ + if (insn_is_indirect_jump(&insn) || + insn_jump_into_range(&insn, paddr + INT3_SIZE, + RELATIVE_ADDR_SIZE)) + return 0; + addr += insn.length; + } + + return 1; +} + +/* Check optimized_kprobe can actually be optimized. */ +int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) +{ + int i; + struct kprobe *p; + + for (i = 1; i < op->optinsn.size; i++) { + p = get_kprobe(op->kp.addr + i); + if (p && !kprobe_disabled(p)) + return -EEXIST; + } + + return 0; +} + +/* Check the addr is within the optimized instructions. */ +int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op, + unsigned long addr) +{ + return ((unsigned long)op->kp.addr <= addr && + (unsigned long)op->kp.addr + op->optinsn.size > addr); +} + +/* Free optimized instruction slot */ +static __kprobes +void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) +{ + if (op->optinsn.insn) { + free_optinsn_slot(op->optinsn.insn, dirty); + op->optinsn.insn = NULL; + op->optinsn.size = 0; + } +} + +void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) +{ + __arch_remove_optimized_kprobe(op, 1); +} + +/* + * Copy replacing target instructions + * Target instructions MUST be relocatable (checked inside) + */ +int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) +{ + u8 *buf; + int ret; + long rel; + + if (!can_optimize((unsigned long)op->kp.addr)) + return -EILSEQ; + + op->optinsn.insn = get_optinsn_slot(); + if (!op->optinsn.insn) + return -ENOMEM; + + /* + * Verify if the address gap is in 2GB range, because this uses + * a relative jump. + */ + rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; + if (abs(rel) > 0x7fffffff) + return -ERANGE; + + buf = (u8 *)op->optinsn.insn; + + /* Copy instructions into the out-of-line buffer */ + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); + if (ret < 0) { + __arch_remove_optimized_kprobe(op, 0); + return ret; + } + op->optinsn.size = ret; + + /* Copy arch-dep-instance from template */ + memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); + + /* Set probe information */ + synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); + + /* Set probe function call */ + synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); + + /* Set returning jmp instruction at the tail of out-of-line buffer */ + synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, + (u8 *)op->kp.addr + op->optinsn.size); + + flush_icache_range((unsigned long) buf, + (unsigned long) buf + TMPL_END_IDX + + op->optinsn.size + RELATIVEJUMP_SIZE); + return 0; +} + +/* Replace a breakpoint (int3) with a relative jump. */ +int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op) +{ + unsigned char jmp_code[RELATIVEJUMP_SIZE]; + 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); + + jmp_code[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&jmp_code[1]) = rel; + + /* + * 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(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE); + return 0; +} + +/* 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); +} + +static int __kprobes setup_detour_execution(struct kprobe *p, + struct pt_regs *regs, + int reenter) +{ + struct optimized_kprobe *op; + + if (p->flags & KPROBE_FLAG_OPTIMIZED) { + /* This kprobe is really able to run optimized path. */ + op = container_of(p, struct optimized_kprobe, kp); + /* Detour through copied instructions */ + regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; + if (!reenter) + reset_current_kprobe(); + preempt_enable_no_resched(); + return 1; + } + return 0; +} +#endif + int __init arch_init_kprobes(void) { return 0; -- cgit v1.2.3 From e5a11016643d1ab7172193591506d33a844734cc Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 3 Mar 2010 22:38:50 -0500 Subject: x86: Issue at least one memory barrier in stop_machine_text_poke() Fix stop_machine_text_poke() to issue smp_mb() before exiting waiting loop, and use cpu_relax() for waiting. Changes in v2: - Don't use ACCESS_ONCE(). Signed-off-by: Masami Hiramatsu Acked-by: Mathieu Desnoyers Cc: systemtap Cc: DLE Cc: Jason Baron LKML-Reference: <20100304033850.3819.74590.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- arch/x86/kernel/alternative.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c41f13c15e8f..e0b877099470 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -595,8 +595,8 @@ static int __kprobes stop_machine_text_poke(void *data) wrote_text = 1; } else { while (!wrote_text) - smp_rmb(); - sync_core(); + cpu_relax(); + smp_mb(); /* Load wrote_text before following execution */ } flush_icache_range((unsigned long)tpp->addr, -- cgit v1.2.3