From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 3494 invoked by alias); 22 Jun 2009 21:47:03 -0000 Received: (qmail 3476 invoked by uid 22791); 22 Jun 2009 21:47:00 -0000 X-SWARE-Spam-Status: No, hits=-1.2 required=5.0 tests=AWL,BAYES_00,J_CHICKENPOX_64,J_CHICKENPOX_66,SPF_HELO_PASS,SPF_PASS X-Spam-Check-By: sourceware.org Received: from mx1.redhat.com (HELO mx1.redhat.com) (66.187.233.31) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Mon, 22 Jun 2009 21:46:53 +0000 Received: from int-mx1.corp.redhat.com (int-mx1.corp.redhat.com [172.16.52.254]) by mx1.redhat.com (8.13.8/8.13.8) with ESMTP id n5MLknoH003383 for ; Mon, 22 Jun 2009 17:46:50 -0400 Received: from ns3.rdu.redhat.com (ns3.rdu.redhat.com [10.11.255.199]) by int-mx1.corp.redhat.com (8.13.1/8.13.1) with ESMTP id n5MLKA4B002206 for ; Mon, 22 Jun 2009 17:20:10 -0400 Received: from localhost.localdomain (dhcp-100-3-156.bos.redhat.com [10.16.3.156]) by ns3.rdu.redhat.com (8.13.8/8.13.8) with ESMTP id n5MLK9Fo029811; Mon, 22 Jun 2009 17:20:09 -0400 From: Masami Hiramatsu Subject: [RFC][ PATCH -tip v2 4/7] kprobes: kprobes jump optimization core To: Ingo Molnar , Ananth N Mavinakayanahalli , lkml Cc: systemtap, DLE, Masami Hiramatsu , Ananth N Mavinakayanahalli , Ingo Molnar , Jim Keniston , Srikar Dronamraju , Christoph Hellwig , Steven Rostedt , Frederic Weisbecker , "H. Peter Anvin" , Anders Kaseorg , Tim Abbott Date: Mon, 22 Jun 2009 21:47:00 -0000 Message-ID: <20090622212319.5384.56039.stgit@localhost.localdomain> In-Reply-To: <20090622212255.5384.53732.stgit@localhost.localdomain> References: <20090622212255.5384.53732.stgit@localhost.localdomain> User-Agent: StGIT/0.14.3 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit X-IsSubscribed: yes Mailing-List: contact systemtap-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Post: List-Help: , Sender: systemtap-owner@sourceware.org X-SW-Source: 2009-q2/txt/msg01001.txt.bz2 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. Changes from v1: - Try to optimize kprobes again when unregistering aggregated kprobe. - Check the probe has been optimized when optimizing kprobe. - Select CONFIG_KALLSYMS_ALL when CONFIG_OPTPROBES=y. - Select CONFIG_DISABLE_CROSSJUMP when CONFIG_OPTPROBES=y. Signed-off-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Ingo Molnar Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Anders Kaseorg Cc: Tim Abbott --- arch/Kconfig | 13 ++ include/linux/kprobes.h | 38 ++++ kernel/kprobes.c | 407 ++++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 411 insertions(+), 47 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index c72f18f..b4d7785 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -44,6 +44,17 @@ config KPROBES for kernel debugging, non-intrusive instrumentation and testing. If in doubt, say "N". +config OPTPROBES + bool "Kprobes jump optimization support (EXPERIMENTAL)" + depends on KPROBES + depends on !PREEMPT + depends on HAVE_OPTPROBES + select KALLSYMS_ALL + select DISABLE_CROSSJUMP + help + This option will allow kprobes to optimize breakpoint to + a jump for reducing its overhead. + config HAVE_EFFICIENT_UNALIGNED_ACCESS bool help @@ -79,6 +90,8 @@ 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 bcd9c07..0adf7af 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 +260,33 @@ 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 int arch_detour_optimized_kprobe(struct optimized_kprobe *op, + struct pt_regs *regs); +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 bc9cfd0..13aea6d 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -298,6 +298,31 @@ 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 */ @@ -331,11 +356,271 @@ struct kprobe __kprobes *get_kprobe(void *addr) 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(); + } +} + +/* Change IP to optimized path. */ +static int __kprobes detour_optimized_kprobe(struct kprobe *p, + struct pt_regs *regs) +{ + struct optimized_kprobe *op; + if (p->flags & KPROBE_FLAG_OPTIMIZED) { + op = container_of(p, struct optimized_kprobe, kp); + /* This kprobe is really able to run optimized path. */ + return arch_detour_optimized_kprobe(op, regs); + } else + /* This kprobe is not optimized. */ + return 0; +} + +/* 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 which replaces instructions including addr. */ +struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr) +{ + int i; + struct kprobe *p = NULL; + struct optimized_kprobe *op; + for (i = 0; !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 quiesence period for ensuring all interrupts are done */ + synchronize_sched(); + + 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); +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); + return; +} +#else /* !CONFIG_OPTPROBES */ +#define get_optimized_kprobe(addr) (NULL) +#define detour_optimized_kprobe(p, regs) (0) +#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) + +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 */ + +static void __kprobes __arm_kprobe(struct kprobe *kp) +{ + arch_arm_kprobe(kp); + optimize_kprobe(kp); /* Try to re-optimize */ +} + +static void __kprobes __disarm_kprobe(struct kprobe *kp) +{ + unoptimize_kprobe(kp); /* Try to unoptimize */ + arch_disarm_kprobe(kp); +} + /* Arm a kprobe with text_mutex */ static void __kprobes arm_kprobe(struct kprobe *kp) { mutex_lock(&text_mutex); - arch_arm_kprobe(kp); + __arm_kprobe(kp); mutex_unlock(&text_mutex); } @@ -343,7 +628,7 @@ static void __kprobes arm_kprobe(struct kprobe *kp) static void __kprobes disarm_kprobe(struct kprobe *kp) { mutex_lock(&text_mutex); - arch_disarm_kprobe(kp); + __disarm_kprobe(kp); mutex_unlock(&text_mutex); } @@ -363,7 +648,7 @@ static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) } reset_kprobe_instance(); } - return 0; + return detour_optimized_kprobe(p, regs); } static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs, @@ -413,7 +698,7 @@ 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) @@ -537,21 +822,16 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *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 */ 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; @@ -566,7 +846,7 @@ 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; } @@ -575,12 +855,13 @@ 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. */ @@ -590,8 +871,9 @@ 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); } @@ -605,12 +887,12 @@ 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)) { @@ -629,6 +911,9 @@ 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. @@ -637,6 +922,7 @@ 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); } @@ -748,16 +1034,23 @@ int __kprobes register_kprobe(struct kprobe *p) p->nmissed = 0; INIT_LIST_HEAD(&p->list); mutex_lock(&kprobe_mutex); + 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); + /* 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 */ + ret = arch_prepare_kprobe(p); if (ret) - goto out_unlock_text; + goto out; INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, @@ -766,9 +1059,11 @@ int __kprobes register_kprobe(struct kprobe *p) if (!kprobes_all_disarmed && !kprobe_disabled(p)) arch_arm_kprobe(p); -out_unlock_text: - mutex_unlock(&text_mutex); + /* Try to optimize kprobe */ + try_to_optimize_kprobe(p); + out: + mutex_unlock(&text_mutex); mutex_unlock(&kprobe_mutex); if (probed_mod) @@ -810,7 +1105,7 @@ 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 @@ -818,8 +1113,13 @@ 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); + + /* 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 { if (p->break_handler && !kprobe_gone(p)) old_p->break_handler = NULL; @@ -834,8 +1134,13 @@ 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; @@ -852,7 +1157,7 @@ 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); } } @@ -1148,7 +1453,7 @@ 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. @@ -1157,6 +1462,7 @@ 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 @@ -1259,6 +1565,11 @@ 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; @@ -1277,7 +1588,7 @@ 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; @@ -1287,19 +1598,21 @@ 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) @@ -1335,11 +1648,11 @@ 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; @@ -1447,7 +1760,7 @@ static void __kprobes arm_all_kprobes(void) 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); @@ -1479,7 +1792,7 @@ static void __kprobes disarm_all_kprobes(void) 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); } } -- Masami Hiramatsu Software Engineer Hitachi Computer Products (America), Inc. Software Solutions Division e-mail: mhiramat@redhat.com