From cd7ebe2298ff1c3112232878678ce5fe6be8a15b Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 3 Dec 2010 18:54:28 +0900 Subject: kprobes: Use text_poke_smp_batch for optimizing Use text_poke_smp_batch() in optimization path for reducing the number of stop_machine() issues. If the number of optimizing probes is more than MAX_OPTIMIZE_PROBES(=256), kprobes optimizes first MAX_OPTIMIZE_PROBES probes and kicks optimizer for remaining probes. Changes in v5: - Use kick_kprobe_optimizer() instead of directly calling schedule_delayed_work(). - Rescheduling optimizer outside of kprobe mutex lock. Changes in v2: - Allocate code buffer and parameters in arch_init_kprobes() instead of using static arraies. - Merge previous max optimization limit patch into this patch. So, this patch introduces upper limit of optimization at once. Signed-off-by: Masami Hiramatsu Cc: Rusty Russell Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli Cc: Jason Baron Cc: Mathieu Desnoyers Cc: 2nddept-manager@sdl.hitachi.co.jp Cc: Peter Zijlstra Cc: Steven Rostedt LKML-Reference: <20101203095428.2961.8994.stgit@ltc236.sdl.hitachi.co.jp> Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/kprobes.h') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e7d1b2e0070d..fe157ba6aa0e 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -275,7 +275,7 @@ 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_optimize_kprobes(struct list_head *oplist); 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); -- cgit v1.2.3 From f984ba4eb575e4a27ed28a76d4126d2aa9233c32 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 3 Dec 2010 18:54:34 +0900 Subject: kprobes: Use text_poke_smp_batch for unoptimizing Use text_poke_smp_batch() on unoptimization path for reducing the number of stop_machine() issues. If the number of unoptimizing probes is more than MAX_OPTIMIZE_PROBES(=256), kprobes unoptimizes first MAX_OPTIMIZE_PROBES probes and kicks optimizer for remaining probes. Signed-off-by: Masami Hiramatsu Cc: Rusty Russell Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli Cc: Jason Baron Cc: Mathieu Desnoyers Cc: 2nddept-manager@sdl.hitachi.co.jp Cc: Peter Zijlstra Cc: Steven Rostedt LKML-Reference: <20101203095434.2961.22657.stgit@ltc236.sdl.hitachi.co.jp> Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/kprobes.h | 2 ++ kernel/kprobes.c | 10 ++++------ 3 files changed, 46 insertions(+), 6 deletions(-) (limited to 'include/linux/kprobes.h') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 25a8af76feb5..5940282bd2f9 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1457,6 +1457,46 @@ void __kprobes arch_optimize_kprobes(struct list_head *oplist) 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) +{ + /* 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; +} + +/* + * Recover original instructions and breakpoints from relative jumps. + * Caller must call with locking kprobe_mutex. + */ +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); + 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) { diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index fe157ba6aa0e..b78edb58ee66 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -276,6 +276,8 @@ 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 void arch_optimize_kprobes(struct list_head *oplist); +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list); 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); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 531e10164836..7663e5df0e6f 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -517,9 +517,9 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list) /* Ditto to do_optimize_kprobes */ get_online_cpus(); mutex_lock(&text_mutex); - list_for_each_entry_safe(op, tmp, &unoptimizing_list, list) { - /* Unoptimize kprobes */ - arch_unoptimize_kprobe(op); + arch_unoptimize_kprobes(&unoptimizing_list, free_list); + /* Loop free_list for disarming */ + list_for_each_entry_safe(op, tmp, free_list, list) { /* Disarm probes if marked disabled */ if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); @@ -530,8 +530,6 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list) * (reclaiming is done by do_free_cleaned_kprobes.) */ hlist_del_rcu(&op->kp.hlist); - /* Move only unused probes on free_list */ - list_move(&op->list, free_list); } else list_del_init(&op->list); } @@ -592,7 +590,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) mutex_unlock(&module_mutex); /* Step 5: Kick optimizer again if needed */ - if (!list_empty(&optimizing_list)) + if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); else /* Wake up all waiters */ -- cgit v1.2.3 From b76834bc1b6db0a0923eed85c81b1113021b0612 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 6 Dec 2010 11:16:25 -0600 Subject: kprobes: Use this_cpu_ops Use this_cpu ops in various places to optimize per cpu data access. Cc: Jason Baron Cc: Namhyung Kim Acked-by: H. Peter Anvin Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- arch/x86/kernel/kprobes.c | 14 +++++++------- include/linux/kprobes.h | 4 ++-- kernel/kprobes.c | 8 ++++---- 3 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux/kprobes.h') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 1cbd54c0df99..572ecc88ca40 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -403,7 +403,7 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags; kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags; @@ -412,7 +412,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); kcb->kprobe_saved_flags = kcb->kprobe_old_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); if (is_IF_modifier(p->ainsn.insn)) @@ -586,7 +586,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_enable_no_resched(); return 1; } else if (kprobe_running()) { - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { setup_singlestep(p, regs, kcb, 0); return 1; @@ -759,11 +759,11 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { - __get_cpu_var(current_kprobe) = &ri->rp->kp; + __this_cpu_write(current_kprobe, &ri->rp->kp); get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __get_cpu_var(current_kprobe) = NULL; + __this_cpu_write(current_kprobe, NULL); } recycle_rp_inst(ri, &empty_rp); @@ -1198,10 +1198,10 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; regs->orig_ax = ~0UL; - __get_cpu_var(current_kprobe) = &op->kp; + __this_cpu_write(current_kprobe, &op->kp); kcb->kprobe_status = KPROBE_HIT_ACTIVE; opt_pre_handler(&op->kp, regs); - __get_cpu_var(current_kprobe) = NULL; + __this_cpu_write(current_kprobe, NULL); } preempt_enable_no_resched(); } diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e7d1b2e0070d..0c251e9f0507 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -303,12 +303,12 @@ struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk); /* kprobe_running() will just return the current_kprobe on this CPU */ static inline struct kprobe *kprobe_running(void) { - return (__get_cpu_var(current_kprobe)); + return (__this_cpu_read(current_kprobe)); } static inline void reset_current_kprobe(void) { - __get_cpu_var(current_kprobe) = NULL; + __this_cpu_write(current_kprobe, NULL); } static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9737a76e106f..732f1e9b65ee 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -317,12 +317,12 @@ void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty) /* We have preemption disabled.. so it is safe to use __ versions */ static inline void set_kprobe_instance(struct kprobe *kp) { - __get_cpu_var(kprobe_instance) = kp; + __this_cpu_write(kprobe_instance, kp); } static inline void reset_kprobe_instance(void) { - __get_cpu_var(kprobe_instance) = NULL; + __this_cpu_write(kprobe_instance, NULL); } /* @@ -775,7 +775,7 @@ static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs, static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr) { - struct kprobe *cur = __get_cpu_var(kprobe_instance); + struct kprobe *cur = __this_cpu_read(kprobe_instance); /* * if we faulted "during" the execution of a user specified @@ -790,7 +790,7 @@ static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs) { - struct kprobe *cur = __get_cpu_var(kprobe_instance); + struct kprobe *cur = __this_cpu_read(kprobe_instance); int ret = 0; if (cur && cur->break_handler) { -- cgit v1.2.3