diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Makefile | 1 | ||||
-rw-r--r-- | kernel/exit.c | 10 | ||||
-rw-r--r-- | kernel/fork.c | 3 | ||||
-rw-r--r-- | kernel/kthread.c | 5 | ||||
-rw-r--r-- | kernel/marker.c | 36 | ||||
-rw-r--r-- | kernel/module.c | 81 | ||||
-rw-r--r-- | kernel/notifier.c | 2 | ||||
-rw-r--r-- | kernel/sched.c | 17 | ||||
-rw-r--r-- | kernel/signal.c | 3 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 64 | ||||
-rw-r--r-- | kernel/trace/Makefile | 4 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 275 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 2014 | ||||
-rw-r--r-- | kernel/trace/trace.c | 1845 | ||||
-rw-r--r-- | kernel/trace/trace.h | 211 | ||||
-rw-r--r-- | kernel/trace/trace_boot.c | 126 | ||||
-rw-r--r-- | kernel/trace/trace_functions.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace_irqsoff.c | 19 | ||||
-rw-r--r-- | kernel/trace/trace_mmiotrace.c | 116 | ||||
-rw-r--r-- | kernel/trace/trace_nop.c | 64 | ||||
-rw-r--r-- | kernel/trace/trace_sched_switch.c | 137 | ||||
-rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 148 | ||||
-rw-r--r-- | kernel/trace/trace_selftest.c | 83 | ||||
-rw-r--r-- | kernel/trace/trace_stack.c | 310 | ||||
-rw-r--r-- | kernel/trace/trace_sysprof.c | 2 | ||||
-rw-r--r-- | kernel/tracepoint.c | 477 |
26 files changed, 4711 insertions, 1344 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 066550aa61c5..305f11dbef21 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -85,6 +85,7 @@ obj-$(CONFIG_SYSCTL) += utsname_sysctl.o obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_MARKERS) += marker.o +obj-$(CONFIG_TRACEPOINTS) += tracepoint.o obj-$(CONFIG_LATENCYTOP) += latencytop.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o obj-$(CONFIG_FTRACE) += trace/ diff --git a/kernel/exit.c b/kernel/exit.c index 059b38cae384..80137a5d9467 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -47,6 +47,7 @@ #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> #include <linux/tracehook.h> +#include <trace/sched.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -146,7 +147,10 @@ static void __exit_signal(struct task_struct *tsk) static void delayed_put_task_struct(struct rcu_head *rhp) { - put_task_struct(container_of(rhp, struct task_struct, rcu)); + struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); + + trace_sched_process_free(tsk); + put_task_struct(tsk); } @@ -1070,6 +1074,8 @@ NORET_TYPE void do_exit(long code) if (group_dead) acct_process(); + trace_sched_process_exit(tsk); + exit_sem(tsk); exit_files(tsk); exit_fs(tsk); @@ -1675,6 +1681,8 @@ static long do_wait(enum pid_type type, struct pid *pid, int options, struct task_struct *tsk; int retval; + trace_sched_process_wait(pid); + add_wait_queue(¤t->signal->wait_chldexit,&wait); repeat: /* diff --git a/kernel/fork.c b/kernel/fork.c index 44e64d7ba29b..4d093552dd6e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -58,6 +58,7 @@ #include <linux/tty.h> #include <linux/proc_fs.h> #include <linux/blkdev.h> +#include <trace/sched.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -1372,6 +1373,8 @@ long do_fork(unsigned long clone_flags, if (!IS_ERR(p)) { struct completion vfork; + trace_sched_process_fork(current, p); + nr = task_pid_vnr(p); if (clone_flags & CLONE_PARENT_SETTID) diff --git a/kernel/kthread.c b/kernel/kthread.c index 14ec64fe175a..8e7a7ce3ed0a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -13,6 +13,7 @@ #include <linux/file.h> #include <linux/module.h> #include <linux/mutex.h> +#include <trace/sched.h> #define KTHREAD_NICE_LEVEL (-5) @@ -205,6 +206,8 @@ int kthread_stop(struct task_struct *k) /* It could exit after stop_info.k set, but before wake_up_process. */ get_task_struct(k); + trace_sched_kthread_stop(k); + /* Must init completion *before* thread sees kthread_stop_info.k */ init_completion(&kthread_stop_info.done); smp_wmb(); @@ -220,6 +223,8 @@ int kthread_stop(struct task_struct *k) ret = kthread_stop_info.err; mutex_unlock(&kthread_stop_lock); + trace_sched_kthread_stop_ret(ret); + return ret; } EXPORT_SYMBOL(kthread_stop); diff --git a/kernel/marker.c b/kernel/marker.c index 7d1faecd7a51..e9c6b2bc9400 100644 --- a/kernel/marker.c +++ b/kernel/marker.c @@ -62,7 +62,7 @@ struct marker_entry { int refcount; /* Number of times armed. 0 if disarmed. */ struct rcu_head rcu; void *oldptr; - unsigned char rcu_pending:1; + int rcu_pending; unsigned char ptype:1; char name[0]; /* Contains name'\0'format'\0' */ }; @@ -103,11 +103,11 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) char ptype; /* - * preempt_disable does two things : disabling preemption to make sure - * the teardown of the callbacks can be done correctly when they are in - * modules and they insure RCU read coherency. + * rcu_read_lock_sched does two things : disabling preemption to make + * sure the teardown of the callbacks can be done correctly when they + * are in modules and they insure RCU read coherency. */ - preempt_disable(); + rcu_read_lock_sched(); ptype = mdata->ptype; if (likely(!ptype)) { marker_probe_func *func; @@ -145,7 +145,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) va_end(args); } } - preempt_enable(); + rcu_read_unlock_sched(); } EXPORT_SYMBOL_GPL(marker_probe_cb); @@ -162,7 +162,7 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) va_list args; /* not initialized */ char ptype; - preempt_disable(); + rcu_read_lock_sched(); ptype = mdata->ptype; if (likely(!ptype)) { marker_probe_func *func; @@ -195,7 +195,7 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) multi[i].func(multi[i].probe_private, call_private, mdata->format, &args); } - preempt_enable(); + rcu_read_unlock_sched(); } EXPORT_SYMBOL_GPL(marker_probe_cb_noarg); @@ -560,7 +560,7 @@ static int set_marker(struct marker_entry **entry, struct marker *elem, * Disable a marker and its probe callback. * Note: only waiting an RCU period after setting elem->call to the empty * function insures that the original callback is not used anymore. This insured - * by preempt_disable around the call site. + * by rcu_read_lock_sched around the call site. */ static void disable_marker(struct marker *elem) { @@ -653,11 +653,17 @@ int marker_probe_register(const char *name, const char *format, entry = get_marker(name); if (!entry) { entry = add_marker(name, format); - if (IS_ERR(entry)) { + if (IS_ERR(entry)) ret = PTR_ERR(entry); - goto end; - } + } else if (format) { + if (!entry->format) + ret = marker_set_format(&entry, format); + else if (strcmp(entry->format, format)) + ret = -EPERM; } + if (ret) + goto end; + /* * If we detect that a call_rcu is pending for this marker, * make sure it's executed now. @@ -674,6 +680,8 @@ int marker_probe_register(const char *name, const char *format, mutex_lock(&markers_mutex); entry = get_marker(name); WARN_ON(!entry); + if (entry->rcu_pending) + rcu_barrier_sched(); entry->oldptr = old; entry->rcu_pending = 1; /* write rcu_pending before calling the RCU callback */ @@ -717,6 +725,8 @@ int marker_probe_unregister(const char *name, entry = get_marker(name); if (!entry) goto end; + if (entry->rcu_pending) + rcu_barrier_sched(); entry->oldptr = old; entry->rcu_pending = 1; /* write rcu_pending before calling the RCU callback */ @@ -795,6 +805,8 @@ int marker_probe_unregister_private_data(marker_probe_func *probe, mutex_lock(&markers_mutex); entry = get_marker_from_private_data(probe, probe_private); WARN_ON(!entry); + if (entry->rcu_pending) + rcu_barrier_sched(); entry->oldptr = old; entry->rcu_pending = 1; /* write rcu_pending before calling the RCU callback */ diff --git a/kernel/module.c b/kernel/module.c index 25bc9ac9e226..0d8d21ee792c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -46,6 +46,8 @@ #include <asm/cacheflush.h> #include <linux/license.h> #include <asm/sections.h> +#include <linux/tracepoint.h> +#include <linux/ftrace.h> #if 0 #define DEBUGP printk @@ -1430,6 +1432,9 @@ static void free_module(struct module *mod) /* Module unload stuff */ module_unload_free(mod); + /* release any pointers to mcount in this module */ + ftrace_release(mod->module_core, mod->core_size); + /* This may be NULL, but that's OK */ module_free(mod, mod->module_init); kfree(mod->args); @@ -1861,9 +1866,13 @@ static noinline struct module *load_module(void __user *umod, unsigned int markersindex; unsigned int markersstringsindex; unsigned int verboseindex; + unsigned int tracepointsindex; + unsigned int tracepointsstringsindex; + unsigned int mcountindex; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ + void *mseg; struct exception_table_entry *extable; mm_segment_t old_fs; @@ -2156,6 +2165,12 @@ static noinline struct module *load_module(void __user *umod, markersstringsindex = find_sec(hdr, sechdrs, secstrings, "__markers_strings"); verboseindex = find_sec(hdr, sechdrs, secstrings, "__verbose"); + tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints"); + tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings, + "__tracepoints_strings"); + + mcountindex = find_sec(hdr, sechdrs, secstrings, + "__mcount_loc"); /* Now do relocations. */ for (i = 1; i < hdr->e_shnum; i++) { @@ -2183,6 +2198,12 @@ static noinline struct module *load_module(void __user *umod, mod->num_markers = sechdrs[markersindex].sh_size / sizeof(*mod->markers); #endif +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints = (void *)sechdrs[tracepointsindex].sh_addr; + mod->num_tracepoints = + sechdrs[tracepointsindex].sh_size / sizeof(*mod->tracepoints); +#endif + /* Find duplicate symbols */ err = verify_export_symbols(mod); @@ -2201,12 +2222,22 @@ static noinline struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); + if (!mod->taints) { #ifdef CONFIG_MARKERS - if (!mod->taints) marker_update_probe_range(mod->markers, mod->markers + mod->num_markers); #endif dynamic_printk_setup(sechdrs, verboseindex); +#ifdef CONFIG_TRACEPOINTS + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); +#endif + } + + /* sechdrs[0].sh_size is always zero */ + mseg = (void *)sechdrs[mcountindex].sh_addr; + ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size); + err = module_finalize(hdr, sechdrs, mod); if (err < 0) goto cleanup; @@ -2276,6 +2307,7 @@ static noinline struct module *load_module(void __user *umod, cleanup: kobject_del(&mod->mkobj.kobj); kobject_put(&mod->mkobj.kobj); + ftrace_release(mod->module_core, mod->core_size); free_unload: module_unload_free(mod); module_free(mod, mod->module_init); @@ -2759,3 +2791,50 @@ void module_update_markers(void) mutex_unlock(&module_mutex); } #endif + +#ifdef CONFIG_TRACEPOINTS +void module_update_tracepoints(void) +{ + struct module *mod; + + mutex_lock(&module_mutex); + list_for_each_entry(mod, &modules, list) + if (!mod->taints) + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + mutex_unlock(&module_mutex); +} + +/* + * Returns 0 if current not found. + * Returns 1 if current found. + */ +int module_get_iter_tracepoints(struct tracepoint_iter *iter) +{ + struct module *iter_mod; + int found = 0; + + mutex_lock(&module_mutex); + list_for_each_entry(iter_mod, &modules, list) { + if (!iter_mod->taints) { + /* + * Sorted module list + */ + if (iter_mod < iter->module) + continue; + else if (iter_mod > iter->module) + iter->tracepoint = NULL; + found = tracepoint_get_iter_range(&iter->tracepoint, + iter_mod->tracepoints, + iter_mod->tracepoints + + iter_mod->num_tracepoints); + if (found) { + iter->module = iter_mod; + break; + } + } + } + mutex_unlock(&module_mutex); + return found; +} +#endif diff --git a/kernel/notifier.c b/kernel/notifier.c index 823be11584ef..4282c0a40a57 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -550,7 +550,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier); static ATOMIC_NOTIFIER_HEAD(die_chain); -int notify_die(enum die_val val, const char *str, +int notrace notify_die(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) { struct die_args args = { diff --git a/kernel/sched.c b/kernel/sched.c index 09a8c15748f1..d906f72b42d2 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -71,6 +71,7 @@ #include <linux/debugfs.h> #include <linux/ctype.h> #include <linux/ftrace.h> +#include <trace/sched.h> #include <asm/tlb.h> #include <asm/irq_regs.h> @@ -1936,6 +1937,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * just go back and repeat. */ rq = task_rq_lock(p, &flags); + trace_sched_wait_task(rq, p); running = task_running(rq, p); on_rq = p->se.on_rq; ncsw = 0; @@ -2297,9 +2299,7 @@ out_activate: success = 1; out_running: - trace_mark(kernel_sched_wakeup, - "pid %d state %ld ## rq %p task %p rq->curr %p", - p->pid, p->state, rq, p, rq->curr); + trace_sched_wakeup(rq, p); check_preempt_curr(rq, p, sync); p->state = TASK_RUNNING; @@ -2432,9 +2432,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) p->sched_class->task_new(rq, p); inc_nr_running(rq); } - trace_mark(kernel_sched_wakeup_new, - "pid %d state %ld ## rq %p task %p rq->curr %p", - p->pid, p->state, rq, p, rq->curr); + trace_sched_wakeup_new(rq, p); check_preempt_curr(rq, p, 0); #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) @@ -2607,11 +2605,7 @@ context_switch(struct rq *rq, struct task_struct *prev, struct mm_struct *mm, *oldmm; prepare_task_switch(rq, prev, next); - trace_mark(kernel_sched_schedule, - "prev_pid %d next_pid %d prev_state %ld " - "## rq %p prev %p next %p", - prev->pid, next->pid, prev->state, - rq, prev, next); + trace_sched_switch(rq, prev, next); mm = next->mm; oldmm = prev->active_mm; /* @@ -2851,6 +2845,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu) || unlikely(!cpu_active(dest_cpu))) goto out; + trace_sched_migrate_task(rq, p, dest_cpu); /* force the process onto the specified CPU */ if (migrate_task(p, dest_cpu, &req)) { /* Need to wait for migration thread (might exit: take ref). */ diff --git a/kernel/signal.c b/kernel/signal.c index 6eea5826d618..105217da5c82 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -27,6 +27,7 @@ #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <linux/nsproxy.h> +#include <trace/sched.h> #include <asm/param.h> #include <asm/uaccess.h> @@ -803,6 +804,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, struct sigpending *pending; struct sigqueue *q; + trace_sched_signal_send(sig, t); + assert_spin_locked(&t->sighand->siglock); if (!prepare_signal(sig, t)) return 0; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 263e9e6bbd60..1cb3e1f616af 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -1,23 +1,37 @@ # # Architectures that offer an FTRACE implementation should select HAVE_FTRACE: # + +config NOP_TRACER + bool + config HAVE_FTRACE bool + select NOP_TRACER config HAVE_DYNAMIC_FTRACE bool +config HAVE_FTRACE_MCOUNT_RECORD + bool + config TRACER_MAX_TRACE bool +config RING_BUFFER + bool + config TRACING bool select DEBUG_FS + select RING_BUFFER select STACKTRACE + select TRACEPOINTS config FTRACE bool "Kernel Function Tracer" depends on HAVE_FTRACE + depends on DEBUG_KERNEL select FRAME_POINTER select TRACING select CONTEXT_SWITCH_TRACER @@ -36,6 +50,7 @@ config IRQSOFF_TRACER depends on TRACE_IRQFLAGS_SUPPORT depends on GENERIC_TIME depends on HAVE_FTRACE + depends on DEBUG_KERNEL select TRACE_IRQFLAGS select TRACING select TRACER_MAX_TRACE @@ -59,6 +74,7 @@ config PREEMPT_TRACER depends on GENERIC_TIME depends on PREEMPT depends on HAVE_FTRACE + depends on DEBUG_KERNEL select TRACING select TRACER_MAX_TRACE help @@ -86,6 +102,7 @@ config SYSPROF_TRACER config SCHED_TRACER bool "Scheduling Latency Tracer" depends on HAVE_FTRACE + depends on DEBUG_KERNEL select TRACING select CONTEXT_SWITCH_TRACER select TRACER_MAX_TRACE @@ -96,16 +113,56 @@ config SCHED_TRACER config CONTEXT_SWITCH_TRACER bool "Trace process context switches" depends on HAVE_FTRACE + depends on DEBUG_KERNEL select TRACING select MARKERS help This tracer gets called from the context switch and records all switching of tasks. +config BOOT_TRACER + bool "Trace boot initcalls" + depends on HAVE_FTRACE + depends on DEBUG_KERNEL + select TRACING + help + This tracer helps developers to optimize boot times: it records + the timings of the initcalls and traces key events and the identity + of tasks that can cause boot delays, such as context-switches. + + Its aim is to be parsed by the /scripts/bootgraph.pl tool to + produce pretty graphics about boot inefficiencies, giving a visual + representation of the delays during initcalls - but the raw + /debug/tracing/trace text output is readable too. + + ( Note that tracing self tests can't be enabled if this tracer is + selected, because the self-tests are an initcall as well and that + would invalidate the boot trace. ) + +config STACK_TRACER + bool "Trace max stack" + depends on HAVE_FTRACE + depends on DEBUG_KERNEL + select FTRACE + select STACKTRACE + help + This special tracer records the maximum stack footprint of the + kernel and displays it in debugfs/tracing/stack_trace. + + This tracer works by hooking into every function call that the + kernel executes, and keeping a maximum stack depth value and + stack-trace saved. Because this logic has to execute in every + kernel function, all the time, this option can slow down the + kernel measurably and is generally intended for kernel + developers only. + + Say N if unsure. + config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" depends on FTRACE depends on HAVE_DYNAMIC_FTRACE + depends on DEBUG_KERNEL default y help This option will modify all the calls to ftrace dynamically @@ -121,12 +178,17 @@ config DYNAMIC_FTRACE were made. If so, it runs stop_machine (stops all CPUS) and modifies the code to jump over the call to ftrace. +config FTRACE_MCOUNT_RECORD + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_FTRACE_MCOUNT_RECORD + config FTRACE_SELFTEST bool config FTRACE_STARTUP_TEST bool "Perform a startup test on ftrace" - depends on TRACING + depends on TRACING && DEBUG_KERNEL && !BOOT_TRACER select FTRACE_SELFTEST help This option performs a series of startup tests on ftrace. On bootup diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 71d17de17288..a85dfba88ba0 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -11,6 +11,7 @@ obj-y += trace_selftest_dynamic.o endif obj-$(CONFIG_FTRACE) += libftrace.o +obj-$(CONFIG_RING_BUFFER) += ring_buffer.o obj-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o @@ -19,6 +20,9 @@ obj-$(CONFIG_FTRACE) += trace_functions.o obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o +obj-$(CONFIG_NOP_TRACER) += trace_nop.o +obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o +obj-$(CONFIG_BOOT_TRACER) += trace_boot.o libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f6e3af31b403..4dda4f60a2a9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -81,7 +81,7 @@ void clear_ftrace_function(void) static int __register_ftrace_function(struct ftrace_ops *ops) { - /* Should never be called by interrupts */ + /* should not be called from interrupt context */ spin_lock(&ftrace_lock); ops->next = ftrace_list; @@ -115,6 +115,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) struct ftrace_ops **p; int ret = 0; + /* should not be called from interrupt context */ spin_lock(&ftrace_lock); /* @@ -153,6 +154,30 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) #ifdef CONFIG_DYNAMIC_FTRACE +#ifndef CONFIG_FTRACE_MCOUNT_RECORD +/* + * The hash lock is only needed when the recording of the mcount + * callers are dynamic. That is, by the caller themselves and + * not recorded via the compilation. + */ +static DEFINE_SPINLOCK(ftrace_hash_lock); +#define ftrace_hash_lock(flags) spin_lock_irqsave(&ftrace_hash_lock, flags) +#define ftrace_hash_unlock(flags) \ + spin_unlock_irqrestore(&ftrace_hash_lock, flags) +#else +/* This is protected via the ftrace_lock with MCOUNT_RECORD. */ +#define ftrace_hash_lock(flags) do { (void)(flags); } while (0) +#define ftrace_hash_unlock(flags) do { } while(0) +#endif + +/* + * Since MCOUNT_ADDR may point to mcount itself, we do not want + * to get it confused by reading a reference in the code as we + * are parsing on objcopy output of text. Use a variable for + * it instead. + */ +static unsigned long mcount_addr = MCOUNT_ADDR; + static struct task_struct *ftraced_task; enum { @@ -171,7 +196,6 @@ static struct hlist_head ftrace_hash[FTRACE_HASHSIZE]; static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu); -static DEFINE_SPINLOCK(ftrace_shutdown_lock); static DEFINE_MUTEX(ftraced_lock); static DEFINE_MUTEX(ftrace_regex_lock); @@ -294,13 +318,37 @@ static inline void ftrace_del_hash(struct dyn_ftrace *node) static void ftrace_free_rec(struct dyn_ftrace *rec) { - /* no locking, only called from kstop_machine */ - rec->ip = (unsigned long)ftrace_free_records; ftrace_free_records = rec; rec->flags |= FTRACE_FL_FREE; } +void ftrace_release(void *start, unsigned long size) +{ + struct dyn_ftrace *rec; + struct ftrace_page *pg; + unsigned long s = (unsigned long)start; + unsigned long e = s + size; + int i; + + if (ftrace_disabled || !start) + return; + + /* should not be called from interrupt context */ + spin_lock(&ftrace_lock); + + for (pg = ftrace_pages_start; pg; pg = pg->next) { + for (i = 0; i < pg->index; i++) { + rec = &pg->records[i]; + + if ((rec->ip >= s) && (rec->ip < e)) + ftrace_free_rec(rec); + } + } + spin_unlock(&ftrace_lock); + +} + static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) { struct dyn_ftrace *rec; @@ -338,7 +386,6 @@ ftrace_record_ip(unsigned long ip) unsigned long flags; unsigned long key; int resched; - int atomic; int cpu; if (!ftrace_enabled || ftrace_disabled) @@ -368,9 +415,7 @@ ftrace_record_ip(unsigned long ip) if (ftrace_ip_in_hash(ip, key)) goto out; - atomic = irqs_disabled(); - - spin_lock_irqsave(&ftrace_shutdown_lock, flags); + ftrace_hash_lock(flags); /* This ip may have hit the hash before the lock */ if (ftrace_ip_in_hash(ip, key)) @@ -387,7 +432,7 @@ ftrace_record_ip(unsigned long ip) ftraced_trigger = 1; out_unlock: - spin_unlock_irqrestore(&ftrace_shutdown_lock, flags); + ftrace_hash_unlock(flags); out: per_cpu(ftrace_shutdown_disable_cpu, cpu)--; @@ -531,6 +576,16 @@ static void ftrace_shutdown_replenish(void) ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL); } +static void print_ip_ins(const char *fmt, unsigned char *p) +{ + int i; + + printk(KERN_CONT "%s", fmt); + + for (i = 0; i < MCOUNT_INSN_SIZE; i++) + printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); +} + static int ftrace_code_disable(struct dyn_ftrace *rec) { @@ -541,10 +596,27 @@ ftrace_code_disable(struct dyn_ftrace *rec) ip = rec->ip; nop = ftrace_nop_replace(); - call = ftrace_call_replace(ip, MCOUNT_ADDR); + call = ftrace_call_replace(ip, mcount_addr); failed = ftrace_modify_code(ip, call, nop); if (failed) { + switch (failed) { + case 1: + WARN_ON_ONCE(1); + pr_info("ftrace faulted on modifying "); + print_ip_sym(ip); + break; + case 2: + WARN_ON_ONCE(1); + pr_info("ftrace failed to modify "); + print_ip_sym(ip); + print_ip_ins(" expected: ", call); + print_ip_ins(" actual: ", (unsigned char *)ip); + print_ip_ins(" replace: ", nop); + printk(KERN_CONT "\n"); + break; + } + rec->flags |= FTRACE_FL_FAILED; return 0; } @@ -792,47 +864,7 @@ static int ftrace_update_code(void) return 1; } -static int ftraced(void *ignore) -{ - unsigned long usecs; - - while (!kthread_should_stop()) { - - set_current_state(TASK_INTERRUPTIBLE); - - /* check once a second */ - schedule_timeout(HZ); - - if (unlikely(ftrace_disabled)) - continue; - - mutex_lock(&ftrace_sysctl_lock); - mutex_lock(&ftraced_lock); - if (!ftraced_suspend && !ftraced_stop && - ftrace_update_code()) { - usecs = nsecs_to_usecs(ftrace_update_time); - if (ftrace_update_tot_cnt > 100000) { - ftrace_update_tot_cnt = 0; - pr_info("hm, dftrace overflow: %lu change%s" - " (%lu total) in %lu usec%s\n", - ftrace_update_cnt, - ftrace_update_cnt != 1 ? "s" : "", - ftrace_update_tot_cnt, - usecs, usecs != 1 ? "s" : ""); - ftrace_disabled = 1; - WARN_ON_ONCE(1); - } - } - mutex_unlock(&ftraced_lock); - mutex_unlock(&ftrace_sysctl_lock); - - ftrace_shutdown_replenish(); - } - __set_current_state(TASK_RUNNING); - return 0; -} - -static int __init ftrace_dyn_table_alloc(void) +static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) { struct ftrace_page *pg; int cnt; @@ -859,7 +891,9 @@ static int __init ftrace_dyn_table_alloc(void) pg = ftrace_pages = ftrace_pages_start; - cnt = NR_TO_INIT / ENTRIES_PER_PAGE; + cnt = num_to_init / ENTRIES_PER_PAGE; + pr_info("ftrace: allocating %ld hash entries in %d pages\n", + num_to_init, cnt); for (i = 0; i < cnt; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); @@ -901,6 +935,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) (*pos)++; + /* should not be called from interrupt context */ + spin_lock(&ftrace_lock); retry: if (iter->idx >= iter->pg->index) { if (iter->pg->next) { @@ -910,15 +946,13 @@ t_next(struct seq_file *m, void *v, loff_t *pos) } } else { rec = &iter->pg->records[iter->idx++]; - if ((!(iter->flags & FTRACE_ITER_FAILURES) && + if ((rec->flags & FTRACE_FL_FREE) || + + (!(iter->flags & FTRACE_ITER_FAILURES) && (rec->flags & FTRACE_FL_FAILED)) || ((iter->flags & FTRACE_ITER_FAILURES) && - (!(rec->flags & FTRACE_FL_FAILED) || - (rec->flags & FTRACE_FL_FREE))) || - - ((iter->flags & FTRACE_ITER_FILTER) && - !(rec->flags & FTRACE_FL_FILTER)) || + !(rec->flags & FTRACE_FL_FAILED)) || ((iter->flags & FTRACE_ITER_NOTRACE) && !(rec->flags & FTRACE_FL_NOTRACE))) { @@ -926,6 +960,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) goto retry; } } + spin_unlock(&ftrace_lock); iter->pos = *pos; @@ -1039,8 +1074,8 @@ static void ftrace_filter_reset(int enable) unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; unsigned i; - /* keep kstop machine from running */ - preempt_disable(); + /* should not be called from interrupt context */ + spin_lock(&ftrace_lock); if (enable) ftrace_filtered = 0; pg = ftrace_pages_start; @@ -1053,7 +1088,7 @@ static void ftrace_filter_reset(int enable) } pg = pg->next; } - preempt_enable(); + spin_unlock(&ftrace_lock); } static int @@ -1165,8 +1200,8 @@ ftrace_match(unsigned char *buff, int len, int enable) } } - /* keep kstop machine from running */ - preempt_disable(); + /* should not be called from interrupt context */ + spin_lock(&ftrace_lock); if (enable) ftrace_filtered = 1; pg = ftrace_pages_start; @@ -1203,7 +1238,7 @@ ftrace_match(unsigned char *buff, int len, int enable) } pg = pg->next; } - preempt_enable(); + spin_unlock(&ftrace_lock); } static ssize_t @@ -1556,6 +1591,114 @@ static __init int ftrace_init_debugfs(void) fs_initcall(ftrace_init_debugfs); +#ifdef CONFIG_FTRACE_MCOUNT_RECORD +static int ftrace_convert_nops(unsigned long *start, + unsigned long *end) +{ + unsigned long *p; + unsigned long addr; + unsigned long flags; + |