diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-10 19:53:40 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-10 19:53:40 -0700 |
commit | 862366118026a358882eefc70238dbcc3db37aac (patch) | |
tree | 4eb62bc10327a5afac064a95a091ea05ecd2acc1 /kernel | |
parent | 57eee9ae7bbcfb692dc96c739a5184adb6349733 (diff) | |
parent | 511b01bdf64ad8a38414096eab283c7784aebfc4 (diff) |
Merge branch 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (244 commits)
Revert "x86, bts: reenable ptrace branch trace support"
tracing: do not translate event helper macros in print format
ftrace/documentation: fix typo in function grapher name
tracing/events: convert block trace points to TRACE_EVENT(), fix !CONFIG_BLOCK
tracing: add protection around module events unload
tracing: add trace_seq_vprint interface
tracing: fix the block trace points print size
tracing/events: convert block trace points to TRACE_EVENT()
ring-buffer: fix ret in rb_add_time_stamp
ring-buffer: pass in lockdep class key for reader_lock
tracing: add annotation to what type of stack trace is recorded
tracing: fix multiple use of __print_flags and __print_symbolic
tracing/events: fix output format of user stack
tracing/events: fix output format of kernel stack
tracing/trace_stack: fix the number of entries in the header
ring-buffer: discard timestamps that are at the start of the buffer
ring-buffer: try to discard unneeded timestamps
ring-buffer: fix bug in ring_buffer_discard_commit
ftrace: do not profile functions when disabled
tracing: make trace pipe recognize latency format flag
...
Diffstat (limited to 'kernel')
47 files changed, 4782 insertions, 1977 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 42423665660..a35eee3436d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -93,6 +93,7 @@ obj-$(CONFIG_LATENCYTOP) += latencytop.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ +obj-$(CONFIG_X86_DS) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o obj-$(CONFIG_SLOW_WORK) += slow-work.o diff --git a/kernel/exit.c b/kernel/exit.c index abf9cf3b95c..cab535c427b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -48,7 +48,7 @@ #include <linux/tracehook.h> #include <linux/fs_struct.h> #include <linux/init_task.h> -#include <trace/sched.h> +#include <trace/events/sched.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -56,10 +56,6 @@ #include <asm/mmu_context.h> #include "cred-internals.h" -DEFINE_TRACE(sched_process_free); -DEFINE_TRACE(sched_process_exit); -DEFINE_TRACE(sched_process_wait); - static void exit_mm(struct task_struct * tsk); static void __unhash_process(struct task_struct *p) diff --git a/kernel/fork.c b/kernel/fork.c index 875ffbdd96d..5449efbc642 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -61,7 +61,6 @@ #include <linux/proc_fs.h> #include <linux/blkdev.h> #include <linux/fs_struct.h> -#include <trace/sched.h> #include <linux/magic.h> #include <asm/pgtable.h> @@ -71,6 +70,8 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> +#include <trace/events/sched.h> + /* * Protected counters by write_lock_irq(&tasklist_lock) */ @@ -83,8 +84,6 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ -DEFINE_TRACE(sched_process_fork); - int nr_processes(void) { int cpu; @@ -1089,8 +1088,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif - if (unlikely(current->ptrace)) - ptrace_fork(p, clone_flags); + + p->bts = NULL; /* Perform scheduler related setup. Assign this task to a CPU. */ sched_fork(p, clone_flags); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 18041a254d3..a60018402f4 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -18,8 +18,8 @@ #include <linux/kernel_stat.h> #include <linux/rculist.h> #include <linux/hash.h> -#include <trace/irq.h> #include <linux/bootmem.h> +#include <trace/events/irq.h> #include "internals.h" @@ -355,9 +355,6 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action) "but no thread function available.", irq, action->name); } -DEFINE_TRACE(irq_handler_entry); -DEFINE_TRACE(irq_handler_exit); - /** * handle_IRQ_event - irq action chain handler * @irq: the interrupt number diff --git a/kernel/kthread.c b/kernel/kthread.c index 4ebaf8519ab..41c88fe4050 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -13,7 +13,7 @@ #include <linux/file.h> #include <linux/module.h> #include <linux/mutex.h> -#include <trace/sched.h> +#include <trace/events/sched.h> #define KTHREAD_NICE_LEVEL (-5) @@ -21,9 +21,6 @@ static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; -DEFINE_TRACE(sched_kthread_stop); -DEFINE_TRACE(sched_kthread_stop_ret); - struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ diff --git a/kernel/lockdep.c b/kernel/lockdep.c index accb40cdb12..8bbeef996c7 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -42,12 +42,14 @@ #include <linux/hash.h> #include <linux/ftrace.h> #include <linux/stringify.h> -#include <trace/lockdep.h> #include <asm/sections.h> #include "lockdep_internals.h" +#define CREATE_TRACE_POINTS +#include <trace/events/lockdep.h> + #ifdef CONFIG_PROVE_LOCKING int prove_locking = 1; module_param(prove_locking, int, 0644); @@ -2935,8 +2937,6 @@ void lock_set_class(struct lockdep_map *lock, const char *name, } EXPORT_SYMBOL_GPL(lock_set_class); -DEFINE_TRACE(lock_acquire); - /* * We are not always called with irqs disabled - do that here, * and also avoid lockdep recursion: @@ -2963,8 +2963,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, } EXPORT_SYMBOL_GPL(lock_acquire); -DEFINE_TRACE(lock_release); - void lock_release(struct lockdep_map *lock, int nested, unsigned long ip) { @@ -3105,6 +3103,8 @@ found_it: hlock->holdtime_stamp = now; } + trace_lock_acquired(lock, ip, waittime); + stats = get_lock_stats(hlock_class(hlock)); if (waittime) { if (hlock->read) @@ -3120,8 +3120,6 @@ found_it: lock->ip = ip; } -DEFINE_TRACE(lock_contended); - void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; @@ -3143,14 +3141,10 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) } EXPORT_SYMBOL_GPL(lock_contended); -DEFINE_TRACE(lock_acquired); - void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - trace_lock_acquired(lock, ip); - if (unlikely(!lock_stat)) return; diff --git a/kernel/module.c b/kernel/module.c index e797812a4d9..2383e60fcf3 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -18,6 +18,7 @@ */ #include <linux/module.h> #include <linux/moduleloader.h> +#include <linux/ftrace_event.h> #include <linux/init.h> #include <linux/kallsyms.h> #include <linux/fs.h> @@ -1489,9 +1490,6 @@ static void free_module(struct module *mod) /* Free any allocated parameters. */ destroy_params(mod->kp, mod->num_kp); - /* 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); @@ -1892,11 +1890,9 @@ static noinline struct module *load_module(void __user *umod, unsigned int symindex = 0; unsigned int strindex = 0; unsigned int modindex, versindex, infoindex, pcpuindex; - unsigned int num_mcount; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ - unsigned long *mseg; mm_segment_t old_fs; DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -2172,7 +2168,19 @@ static noinline struct module *load_module(void __user *umod, sizeof(*mod->tracepoints), &mod->num_tracepoints); #endif - +#ifdef CONFIG_EVENT_TRACING + mod->trace_events = section_objs(hdr, sechdrs, secstrings, + "_ftrace_events", + sizeof(*mod->trace_events), + &mod->num_trace_events); +#endif +#ifdef CONFIG_FTRACE_MCOUNT_RECORD + /* sechdrs[0].sh_size is always zero */ + mod->ftrace_callsites = section_objs(hdr, sechdrs, secstrings, + "__mcount_loc", + sizeof(*mod->ftrace_callsites), + &mod->num_ftrace_callsites); +#endif #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs) @@ -2237,11 +2245,6 @@ static noinline struct module *load_module(void __user *umod, dynamic_debug_setup(debug, num_debug); } - /* sechdrs[0].sh_size is always zero */ - mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc", - sizeof(*mseg), &num_mcount); - ftrace_init_module(mod, mseg, mseg + num_mcount); - err = module_finalize(hdr, sechdrs, mod); if (err < 0) goto cleanup; @@ -2302,7 +2305,6 @@ 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); #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 42c317874cf..2442d140bd9 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -25,16 +25,6 @@ /* - * Initialize a new task whose father had been ptraced. - * - * Called from copy_process(). - */ -void ptrace_fork(struct task_struct *child, unsigned long clone_flags) -{ - arch_ptrace_fork(child, clone_flags); -} - -/* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * diff --git a/kernel/sched.c b/kernel/sched.c index 076e403b9c8..14c447ae5d5 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -72,13 +72,15 @@ #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> #include "sched_cpupri.h" +#define CREATE_TRACE_POINTS +#include <trace/events/sched.h> + /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], @@ -118,12 +120,6 @@ */ #define RUNTIME_INF ((u64)~0ULL) -DEFINE_TRACE(sched_wait_task); -DEFINE_TRACE(sched_wakeup); -DEFINE_TRACE(sched_wakeup_new); -DEFINE_TRACE(sched_switch); -DEFINE_TRACE(sched_migrate_task); - #ifdef CONFIG_SMP static void double_rq_lock(struct rq *rq1, struct rq *rq2); @@ -1964,7 +1960,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) clock_offset = old_rq->clock - new_rq->clock; - trace_sched_migrate_task(p, task_cpu(p), new_cpu); + trace_sched_migrate_task(p, new_cpu); #ifdef CONFIG_SCHEDSTATS if (p->se.wait_start) @@ -2021,6 +2017,49 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) } /* + * wait_task_context_switch - wait for a thread to complete at least one + * context switch. + * + * @p must not be current. + */ +void wait_task_context_switch(struct task_struct *p) +{ + unsigned long nvcsw, nivcsw, flags; + int running; + struct rq *rq; + + nvcsw = p->nvcsw; + nivcsw = p->nivcsw; + for (;;) { + /* + * The runqueue is assigned before the actual context + * switch. We need to take the runqueue lock. + * + * We could check initially without the lock but it is + * very likely that we need to take the lock in every + * iteration. + */ + rq = task_rq_lock(p, &flags); + running = task_running(rq, p); + task_rq_unlock(rq, &flags); + + if (likely(!running)) + break; + /* + * The switch count is incremented before the actual + * context switch. We thus wait for two switches to be + * sure at least one completed. + */ + if ((p->nvcsw - nvcsw) > 1) + break; + if ((p->nivcsw - nivcsw) > 1) + break; + + cpu_relax(); + } +} + +/* * wait_task_inactive - wait for a thread to unschedule. * * If @match_state is nonzero, it's the @p->state value just checked and diff --git a/kernel/signal.c b/kernel/signal.c index f79b3b9f837..dba6ae99978 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -27,7 +27,7 @@ #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <linux/nsproxy.h> -#include <trace/sched.h> +#include <trace/events/sched.h> #include <asm/param.h> #include <asm/uaccess.h> @@ -41,8 +41,6 @@ static struct kmem_cache *sigqueue_cachep; -DEFINE_TRACE(sched_signal_send); - static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; diff --git a/kernel/softirq.c b/kernel/softirq.c index f674f332a02..258885a543d 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -24,7 +24,9 @@ #include <linux/ftrace.h> #include <linux/smp.h> #include <linux/tick.h> -#include <trace/irq.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/irq.h> #include <asm/irq.h> /* @@ -186,9 +188,6 @@ EXPORT_SYMBOL(local_bh_enable_ip); */ #define MAX_SOFTIRQ_RESTART 10 -DEFINE_TRACE(softirq_entry); -DEFINE_TRACE(softirq_exit); - asmlinkage void __do_softirq(void) { struct softirq_action *h; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 417d1985e29..4a13e5a01ce 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -48,6 +48,21 @@ config FTRACE_NMI_ENTER depends on HAVE_FTRACE_NMI_ENTER default y +config EVENT_TRACING + select CONTEXT_SWITCH_TRACER + bool + +config CONTEXT_SWITCH_TRACER + select MARKERS + bool + +# All tracer options should select GENERIC_TRACER. For those options that are +# enabled by all tracers (context switch and event tracer) they select TRACING. +# This allows those options to appear when no other tracer is selected. But the +# options do not appear when something else selects it. We need the two options +# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the +# hidding of the automatic options options. + config TRACING bool select DEBUG_FS @@ -56,6 +71,11 @@ config TRACING select TRACEPOINTS select NOP_TRACER select BINARY_PRINTF + select EVENT_TRACING + +config GENERIC_TRACER + bool + select TRACING # # Minimum requirements an architecture has to meet for us to @@ -73,14 +93,20 @@ config TRACING_SUPPORT if TRACING_SUPPORT -menu "Tracers" +menuconfig FTRACE + bool "Tracers" + default y if DEBUG_KERNEL + help + Enable the kernel tracing infrastructure. + +if FTRACE config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER select FRAME_POINTER select KALLSYMS - select TRACING + select GENERIC_TRACER select CONTEXT_SWITCH_TRACER help Enable the kernel to trace every kernel function. This is done @@ -104,13 +130,14 @@ config FUNCTION_GRAPH_TRACER the return value. This is done by setting the current return address on the current task structure into a stack of calls. + config IRQSOFF_TRACER bool "Interrupts-off Latency Tracer" default n depends on TRACE_IRQFLAGS_SUPPORT depends on GENERIC_TIME select TRACE_IRQFLAGS - select TRACING + select GENERIC_TRACER select TRACER_MAX_TRACE help This option measures the time spent in irqs-off critical @@ -131,7 +158,7 @@ config PREEMPT_TRACER default n depends on GENERIC_TIME depends on PREEMPT - select TRACING + select GENERIC_TRACER select TRACER_MAX_TRACE help This option measures the time spent in preemption off critical @@ -150,7 +177,7 @@ config PREEMPT_TRACER config SYSPROF_TRACER bool "Sysprof Tracer" depends on X86 - select TRACING + select GENERIC_TRACER select CONTEXT_SWITCH_TRACER help This tracer provides the trace needed by the 'Sysprof' userspace @@ -158,40 +185,33 @@ config SYSPROF_TRACER config SCHED_TRACER bool "Scheduling Latency Tracer" - select TRACING + select GENERIC_TRACER select CONTEXT_SWITCH_TRACER select TRACER_MAX_TRACE help This tracer tracks the latency of the highest priority task to be scheduled in, starting from the point it has woken up. -config CONTEXT_SWITCH_TRACER - bool "Trace process context switches" - select TRACING - select MARKERS - help - This tracer gets called from the context switch and records - all switching of tasks. - -config EVENT_TRACER - bool "Trace various events in the kernel" +config ENABLE_DEFAULT_TRACERS + bool "Trace process context switches and events" + depends on !GENERIC_TRACER select TRACING help This tracer hooks to various trace points in the kernel allowing the user to pick and choose which trace point they - want to trace. + want to trace. It also includes the sched_switch tracer plugin. config FTRACE_SYSCALLS bool "Trace syscalls" depends on HAVE_FTRACE_SYSCALLS - select TRACING + select GENERIC_TRACER select KALLSYMS help Basic tracer to catch the syscall entry and exit events. config BOOT_TRACER bool "Trace boot initcalls" - select TRACING + select GENERIC_TRACER select CONTEXT_SWITCH_TRACER help This tracer helps developers to optimize boot times: it records @@ -207,8 +227,36 @@ config BOOT_TRACER to enable this on bootup. config TRACE_BRANCH_PROFILING + bool + select GENERIC_TRACER + +choice + prompt "Branch Profiling" + default BRANCH_PROFILE_NONE + help + The branch profiling is a software profiler. It will add hooks + into the C conditionals to test which path a branch takes. + + The likely/unlikely profiler only looks at the conditions that + are annotated with a likely or unlikely macro. + + The "all branch" profiler will profile every if statement in the + kernel. This profiler will also enable the likely/unlikely + profiler as well. + + Either of the above profilers add a bit of overhead to the system. + If unsure choose "No branch profiling". + +config BRANCH_PROFILE_NONE + bool "No branch profiling" + help + No branch profiling. Branch profiling adds a bit of overhead. + Only enable it if you want to analyse the branching behavior. + Otherwise keep it disabled. + +config PROFILE_ANNOTATED_BRANCHES bool "Trace likely/unlikely profiler" - select TRACING + select TRACE_BRANCH_PROFILING help This tracer profiles all the the likely and unlikely macros in the kernel. It will display the results in: @@ -218,11 +266,9 @@ config TRACE_BRANCH_PROFILING Note: this will add a significant overhead, only turn this on if you need to profile the system's use of these macros. - Say N if unsure. - config PROFILE_ALL_BRANCHES bool "Profile all if conditionals" - depends on TRACE_BRANCH_PROFILING + select TRACE_BRANCH_PROFILING help This tracer profiles all branch conditions. Every if () taken in the kernel is recorded whether it hit or miss. @@ -230,11 +276,12 @@ config PROFILE_ALL_BRANCHES /debugfs/tracing/profile_branch + This option also enables the likely/unlikely profiler. + This configuration, when enabled, will impose a great overhead on the system. This should only be enabled when the system is to be analyzed - - Say N if unsure. +endchoice config TRACING_BRANCHES bool @@ -261,7 +308,7 @@ config BRANCH_TRACER config POWER_TRACER bool "Trace power consumption behavior" depends on X86 - select TRACING + select GENERIC_TRACER help This tracer helps developers to analyze and optimize the kernels power management decisions, specifically the C-state and P-state @@ -295,14 +342,14 @@ config STACK_TRACER config HW_BRANCH_TRACER depends on HAVE_HW_BRANCH_TRACER bool "Trace hw branches" - select TRACING + select GENERIC_TRACER help This tracer records all branches on the system in a circular buffer giving access to the last N branches for each cpu. config KMEMTRACE bool "Trace SLAB allocations" - select TRACING + select GENERIC_TRACER help kmemtrace provides tracing for slab allocator functions, such as kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected @@ -322,7 +369,7 @@ config KMEMTRACE config WORKQUEUE_TRACER bool "Trace workqueues" - select TRACING + select GENERIC_TRACER help The workqueue tracer provides some statistical informations about each cpu workqueue thread such as the number of the @@ -338,7 +385,7 @@ config BLK_DEV_IO_TRACE select RELAY select DEBUG_FS select TRACEPOINTS - select TRACING + select GENERIC_TRACER select STACKTRACE help Say Y here if you want to be able to trace the block layer actions @@ -375,6 +422,20 @@ 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 FUNCTION_PROFILER + bool "Kernel function profiler" + depends on FUNCTION_TRACER + default n + help + This option enables the kernel function profiler. A file is created + in debugfs called function_profile_enabled which defaults to zero. + When a 1 is echoed into this file profiling begins, and when a + zero is entered, profiling stops. A file in the trace_stats + directory called functions, that show the list of functions that + have been hit and their counters. + + If in doubt, say N + config FTRACE_MCOUNT_RECORD def_bool y depends on DYNAMIC_FTRACE @@ -385,7 +446,7 @@ config FTRACE_SELFTEST config FTRACE_STARTUP_TEST bool "Perform a startup test on ftrace" - depends on TRACING + depends on GENERIC_TRACER select FTRACE_SELFTEST help This option performs a series of startup tests on ftrace. On bootup @@ -396,7 +457,7 @@ config FTRACE_STARTUP_TEST |