diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-11 18:14:31 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-11 18:14:31 -0800 |
commit | 090f8ccba37034cec5a5972a70abeaae7eb0222b (patch) | |
tree | 0b7cf8a4bb94601816399acfb336835fbf309a2a /kernel | |
parent | aefb058b0c27dafb15072406fbfd92d2ac2c8790 (diff) | |
parent | cc1b39dbf9f55a438e8a21a694394c20e6a17129 (diff) |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"Lots of activity:
211 files changed, 8328 insertions(+), 4116 deletions(-)
most of it on the tooling side.
Main changes:
* ftrace enhancements and fixes from Steve Rostedt.
* uprobes fixes, cleanups and preparation for the ARM port from Oleg
Nesterov.
* UAPI fixes, from David Howels - prepares the arch/x86 UAPI
transition
* Separate perf tests into multiple objects, one per test, from Jiri
Olsa.
* Make hardware event translations available in sysfs, from Jiri
Olsa.
* Fixes to /proc/pid/maps parsing, preparatory to supporting data
maps, from Namhyung Kim
* Implement ui_progress for GTK, from Namhyung Kim
* Add framework for automated perf_event_attr tests, where tools with
different command line options will be run from a 'perf test', via
python glue, and the perf syscall will be intercepted to verify
that the perf_event_attr fields set by the tool are those expected,
from Jiri Olsa
* Add a 'link' method for hists, so that we can have the leader with
buckets for all the entries in all the hists. This new method is
now used in the default 'diff' output, making the sum of the
'baseline' column be 100%, eliminating blind spots.
* libtraceevent fixes for compiler warnings trying to make perf it
build on some distros, like fedora 14, 32-bit, some of the warnings
really pointed to real bugs.
* Add a browser for 'perf script' and make it available from the
report and annotate browsers. It does filtering to find the
scripts that handle events found in the perf.data file used. From
Feng Tang
* perf inject changes to allow showing where a task sleeps, from
Andrew Vagin.
* Makefile improvements from Namhyung Kim.
* Add --pre and --post command hooks in 'stat', from Peter Zijlstra.
* Don't stop synthesizing threads when one vanishes, this is for the
existing threads when we start a tool like trace.
* Use sched:sched_stat_runtime to provide a thread summary, this
produces the same output as the 'trace summary' subcommand of
tglx's original "trace" tool.
* Support interrupted syscalls in 'trace'
* Add an event duration column and filter in 'trace'.
* There are references to the man pages in some tools, so try to
build Documentation when installing, warning the user if that is
not possible, from Borislav Petkov.
* Give user better message if precise is not supported, from David
Ahern.
* Try to find cross-built objdump path by using the session
environment information in the perf.data file header, from Irina
Tirdea, original patch and idea by Namhyung Kim.
* Diplays more output on features check for make V=1, so that one can
figure out what is happening by looking at gcc output, etc. From
Jiri Olsa.
* Add on_exit implementation for systems without one, e.g. Android,
from Bernhard Rosenkraenzer.
* Only process events for vcpus of interest, helps handling large
number of events, from David Ahern.
* Cross compilation fixes for Android, from Irina Tirdea.
* Add documentation on compiling for Android, from Irina Tirdea.
* perf diff improvements from Jiri Olsa.
* Target (task/user/cpu/syswide) handling improvements, from Namhyung
Kim.
* Add support in 'trace' for tracing workload given by command line,
from Namhyung Kim.
* ... and much more."
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (194 commits)
uprobes: Use percpu_rw_semaphore to fix register/unregister vs dup_mmap() race
perf evsel: Introduce is_group_member method
perf powerpc: Use uapi/unistd.h to fix build error
tools: Pass the target in descend
tools: Honour the O= flag when tool build called from a higher Makefile
tools: Define a Makefile function to do subdir processing
perf ui: Always compile browser setup code
perf ui: Add ui_progress__finish()
perf ui gtk: Implement ui_progress functions
perf ui: Introduce generic ui_progress helper
perf ui tui: Move progress.c under ui/tui directory
perf tools: Add basic event modifier sanity check
perf tools: Omit group members from perf_evlist__disable/enable
perf tools: Ensure single disable call per event in record comand
perf tools: Fix 'disabled' attribute config for record command
perf tools: Fix attributes for '{}' defined event groups
perf tools: Use sscanf for parsing /proc/pid/maps
perf tools: Add gtk.<command> config option for launching GTK browser
perf tools: Fix compile error on NO_NEWT=1 build
perf hists: Initialize all of he->stat with zeroes
...
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/events/uprobes.c | 43 | ||||
-rw-r--r-- | kernel/fork.c | 2 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 1 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 6 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 51 | ||||
-rw-r--r-- | kernel/trace/trace.c | 411 | ||||
-rw-r--r-- | kernel/trace/trace.h | 18 | ||||
-rw-r--r-- | kernel/trace/trace_branch.c | 4 | ||||
-rw-r--r-- | kernel/trace/trace_events.c | 51 | ||||
-rw-r--r-- | kernel/trace/trace_events_filter.c | 4 | ||||
-rw-r--r-- | kernel/trace/trace_functions.c | 5 | ||||
-rw-r--r-- | kernel/trace/trace_functions_graph.c | 6 | ||||
-rw-r--r-- | kernel/trace/trace_irqsoff.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 10 | ||||
-rw-r--r-- | kernel/trace/trace_output.c | 78 | ||||
-rw-r--r-- | kernel/trace/trace_probe.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_sched_switch.c | 4 | ||||
-rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 10 | ||||
-rw-r--r-- | kernel/trace/trace_selftest.c | 13 | ||||
-rw-r--r-- | kernel/trace/trace_syscalls.c | 61 | ||||
-rw-r--r-- | kernel/trace/trace_uprobe.c | 4 |
21 files changed, 451 insertions, 359 deletions
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 5cc4e7e42e6..dea7acfbb07 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -33,6 +33,7 @@ #include <linux/ptrace.h> /* user_enable_single_step */ #include <linux/kdebug.h> /* notifier mechanism */ #include "../../mm/internal.h" /* munlock_vma_page */ +#include <linux/percpu-rwsem.h> #include <linux/uprobes.h> @@ -71,6 +72,8 @@ static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; #define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) +static struct percpu_rw_semaphore dup_mmap_sem; + /* * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe * events active at this time. Probably a fine grained per inode count is @@ -766,10 +769,13 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) struct map_info *info; int err = 0; + percpu_down_write(&dup_mmap_sem); info = build_map_info(uprobe->inode->i_mapping, uprobe->offset, is_register); - if (IS_ERR(info)) - return PTR_ERR(info); + if (IS_ERR(info)) { + err = PTR_ERR(info); + goto out; + } while (info) { struct mm_struct *mm = info->mm; @@ -799,7 +805,8 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) mmput(mm); info = free_map_info(info); } - + out: + percpu_up_write(&dup_mmap_sem); return err; } @@ -1131,6 +1138,16 @@ void uprobe_clear_state(struct mm_struct *mm) kfree(area); } +void uprobe_start_dup_mmap(void) +{ + percpu_down_read(&dup_mmap_sem); +} + +void uprobe_end_dup_mmap(void) +{ + percpu_up_read(&dup_mmap_sem); +} + void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { newmm->uprobes_state.xol_area = NULL; @@ -1199,6 +1216,11 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe, unsigned long slot vaddr = kmap_atomic(area->page); memcpy(vaddr + offset, uprobe->arch.insn, MAX_UINSN_BYTES); kunmap_atomic(vaddr); + /* + * We probably need flush_icache_user_range() but it needs vma. + * This should work on supported architectures too. + */ + flush_dcache_page(area->page); return current->utask->xol_vaddr; } @@ -1430,16 +1452,6 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) return uprobe; } -void __weak arch_uprobe_enable_step(struct arch_uprobe *arch) -{ - user_enable_single_step(current); -} - -void __weak arch_uprobe_disable_step(struct arch_uprobe *arch) -{ - user_disable_single_step(current); -} - /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. @@ -1493,7 +1505,6 @@ static void handle_swbp(struct pt_regs *regs) goto out; if (!pre_ssout(uprobe, regs, bp_vaddr)) { - arch_uprobe_enable_step(&uprobe->arch); utask->active_uprobe = uprobe; utask->state = UTASK_SSTEP; return; @@ -1525,7 +1536,6 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) else WARN_ON_ONCE(1); - arch_uprobe_disable_step(&uprobe->arch); put_uprobe(uprobe); utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; @@ -1604,6 +1614,9 @@ static int __init init_uprobes(void) mutex_init(&uprobes_mmap_mutex[i]); } + if (percpu_init_rwsem(&dup_mmap_sem)) + return -ENOMEM; + return register_die_notifier(&uprobe_exception_nb); } module_init(init_uprobes); diff --git a/kernel/fork.c b/kernel/fork.c index 8b20ab7d3aa..c497e57aa65 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -352,6 +352,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) unsigned long charge; struct mempolicy *pol; + uprobe_start_dup_mmap(); down_write(&oldmm->mmap_sem); flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); @@ -469,6 +470,7 @@ out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); up_write(&oldmm->mmap_sem); + uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: mpol_put(pol); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 4cea4f41c1d..5d89335a485 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -119,6 +119,7 @@ config TRACING select BINARY_PRINTF select EVENT_TRACING select TRACE_CLOCK + select IRQ_WORK config GENERIC_TRACER bool diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9dcf15d3838..4451aa3a55a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2868,7 +2868,7 @@ static int __init ftrace_mod_cmd_init(void) { return register_ftrace_command(&ftrace_mod_cmd); } -device_initcall(ftrace_mod_cmd_init); +core_initcall(ftrace_mod_cmd_init); static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) @@ -4055,7 +4055,7 @@ static int __init ftrace_nodyn_init(void) ftrace_enabled = 1; return 0; } -device_initcall(ftrace_nodyn_init); +core_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } @@ -4381,7 +4381,7 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf, if (strlen(tmp) == 0) return 1; - ret = strict_strtol(tmp, 10, &val); + ret = kstrtol(tmp, 10, &val); if (ret < 0) return ret; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b979426d16c..3c7834c24e5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -460,9 +460,10 @@ struct ring_buffer_per_cpu { unsigned long lost_events; unsigned long last_overrun; local_t entries_bytes; - local_t commit_overrun; - local_t overrun; local_t entries; + local_t overrun; + local_t commit_overrun; + local_t dropped_events; local_t committing; local_t commits; unsigned long read; @@ -1820,7 +1821,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta) } /** - * ring_buffer_update_event - update event type and data + * rb_update_event - update event type and data * @event: the even to update * @type: the type of event * @length: the size of the event field in the ring buffer @@ -2155,8 +2156,10 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, * If we are not in overwrite mode, * this is easy, just stop here. */ - if (!(buffer->flags & RB_FL_OVERWRITE)) + if (!(buffer->flags & RB_FL_OVERWRITE)) { + local_inc(&cpu_buffer->dropped_events); goto out_reset; + } ret = rb_handle_head_page(cpu_buffer, tail_page, @@ -2720,8 +2723,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_discard_commit); * and not the length of the event which would hold the header. */ int ring_buffer_write(struct ring_buffer *buffer, - unsigned long length, - void *data) + unsigned long length, + void *data) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; @@ -2929,12 +2932,12 @@ rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ -unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) +u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) { unsigned long flags; struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage; - unsigned long ret; + u64 ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; @@ -2995,7 +2998,8 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu); /** - * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer + * ring_buffer_overrun_cpu - get the number of overruns caused by the ring + * buffer wrapping around (only if RB_FL_OVERWRITE is on). * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from */ @@ -3015,7 +3019,9 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu); /** - * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits + * ring_buffer_commit_overrun_cpu - get the number of overruns caused by + * commits failing due to the buffer wrapping around while there are uncommitted + * events, such as during an interrupt storm. * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from */ @@ -3036,6 +3042,28 @@ ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu); /** + * ring_buffer_dropped_events_cpu - get the number of dropped events caused by + * the ring buffer filling up (only if RB_FL_OVERWRITE is off). + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the number of overruns from + */ +unsigned long +ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + ret = local_read(&cpu_buffer->dropped_events); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu); + +/** * ring_buffer_entries - get the number of entries in a buffer * @buffer: The ring buffer * @@ -3864,9 +3892,10 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) local_set(&cpu_buffer->reader_page->page->commit, 0); cpu_buffer->reader_page->read = 0; - local_set(&cpu_buffer->commit_overrun, 0); local_set(&cpu_buffer->entries_bytes, 0); local_set(&cpu_buffer->overrun, 0); + local_set(&cpu_buffer->commit_overrun, 0); + local_set(&cpu_buffer->dropped_events, 0); local_set(&cpu_buffer->entries, 0); local_set(&cpu_buffer->committing, 0); local_set(&cpu_buffer->commits, 0); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 31e4f55773f..b69cc380322 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -19,6 +19,7 @@ #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/irqflags.h> +#include <linux/irq_work.h> #include <linux/debugfs.h> #include <linux/pagemap.h> #include <linux/hardirq.h> @@ -78,6 +79,21 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set) } /* + * To prevent the comm cache from being overwritten when no + * tracing is active, only save the comm when a trace event + * occurred. + */ +static DEFINE_PER_CPU(bool, trace_cmdline_save); + +/* + * When a reader is waiting for data, then this variable is + * set to true. + */ +static bool trace_wakeup_needed; + +static struct irq_work trace_work_wakeup; + +/* * Kill all tracing for good (never come back). * It is initialized to 1 but will turn to zero if the initialization * of the tracer is successful. But that is the only place that sets @@ -139,6 +155,18 @@ static int __init set_ftrace_dump_on_oops(char *str) } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); + +static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; +static char *trace_boot_options __initdata; + +static int __init set_trace_boot_options(char *str) +{ + strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); + trace_boot_options = trace_boot_options_buf; + return 0; +} +__setup("trace_options=", set_trace_boot_options); + unsigned long long ns2usecs(cycle_t nsec) { nsec += 500; @@ -198,20 +226,9 @@ static struct trace_array max_tr; static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data); -/* tracer_enabled is used to toggle activation of a tracer */ -static int tracer_enabled = 1; - -/** - * tracing_is_enabled - return tracer_enabled status - * - * This function is used by other tracers to know the status - * of the tracer_enabled flag. Tracers may use this function - * to know if it should enable their features when starting - * up. See irqsoff tracer for an example (start_irqsoff_tracer). - */ int tracing_is_enabled(void) { - return tracer_enabled; + return tracing_is_on(); } /* @@ -333,12 +350,18 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | static int trace_stop_count; static DEFINE_RAW_SPINLOCK(tracing_start_lock); -static void wakeup_work_handler(struct work_struct *work) +/** + * trace_wake_up - wake up tasks waiting for trace input + * + * Schedules a delayed work to wake up any task that is blocked on the + * trace_wait queue. These is used with trace_poll for tasks polling the + * trace. + */ +static void trace_wake_up(struct irq_work *work) { - wake_up(&trace_wait); -} + wake_up_all(&trace_wait); -static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); +} /** * tracing_on - enable tracing buffers @@ -393,22 +416,6 @@ int tracing_is_on(void) } EXPORT_SYMBOL_GPL(tracing_is_on); -/** - * trace_wake_up - wake up tasks waiting for trace input - * - * Schedules a delayed work to wake up any task that is blocked on the - * trace_wait queue. These is used with trace_poll for tasks polling the - * trace. - */ -void trace_wake_up(void) -{ - const unsigned long delay = msecs_to_jiffies(2); - - if (trace_flags & TRACE_ITER_BLOCK) - return; - schedule_delayed_work(&wakeup_work, delay); -} - static int __init set_buf_size(char *str) { unsigned long buf_size; @@ -431,7 +438,7 @@ static int __init set_tracing_thresh(char *str) if (!str) return 0; - ret = strict_strtoul(str, 0, &threshold); + ret = kstrtoul(str, 0, &threshold); if (ret < 0) return 0; tracing_thresh = threshold * 1000; @@ -477,10 +484,12 @@ static const char *trace_options[] = { static struct { u64 (*func)(void); const char *name; + int in_ns; /* is this clock in nanoseconds? */ } trace_clocks[] = { - { trace_clock_local, "local" }, - { trace_clock_global, "global" }, - { trace_clock_counter, "counter" }, + { trace_clock_local, "local", 1 }, + { trace_clock_global, "global", 1 }, + { trace_clock_counter, "counter", 0 }, + ARCH_TRACE_CLOCKS }; int trace_clock_id; @@ -757,6 +766,40 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) } #endif /* CONFIG_TRACER_MAX_TRACE */ +static void default_wait_pipe(struct trace_iterator *iter) +{ + DEFINE_WAIT(wait); + + prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE); + + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + trace_wakeup_needed = true; + + if (trace_empty(iter)) + schedule(); + + finish_wait(&trace_wait, &wait); +} + /** * register_tracer - register a tracer with the ftrace system. * @type - the plugin for the tracer @@ -875,32 +918,6 @@ int register_tracer(struct tracer *type) return ret; } -void unregister_tracer(struct tracer *type) -{ - struct tracer **t; - - mutex_lock(&trace_types_lock); - for (t = &trace_types; *t; t = &(*t)->next) { - if (*t == type) - goto found; - } - pr_info("Tracer %s not registered\n", type->name); - goto out; - - found: - *t = (*t)->next; - - if (type == current_trace && tracer_enabled) { - tracer_enabled = 0; - tracing_stop(); - if (current_trace->stop) - current_trace->stop(&global_trace); - current_trace = &nop_trace; - } -out: - mutex_unlock(&trace_types_lock); -} - void tracing_reset(struct trace_array *tr, int cpu) { struct ring_buffer *buffer = tr->buffer; @@ -1131,10 +1148,14 @@ void trace_find_cmdline(int pid, char comm[]) void tracing_record_cmdline(struct task_struct *tsk) { - if (atomic_read(&trace_record_cmdline_disabled) || !tracer_enabled || - !tracing_is_on()) + if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on()) return; + if (!__this_cpu_read(trace_cmdline_save)) + return; + + __this_cpu_write(trace_cmdline_save, false); + trace_save_cmdline(tsk); } @@ -1178,27 +1199,36 @@ trace_buffer_lock_reserve(struct ring_buffer *buffer, return event; } +void +__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) +{ + __this_cpu_write(trace_cmdline_save, true); + if (trace_wakeup_needed) { + trace_wakeup_needed = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&trace_work_wakeup); + } + ring_buffer_unlock_commit(buffer, event); +} + static inline void __trace_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, - unsigned long flags, int pc, - int wake) + unsigned long flags, int pc) { - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); ftrace_trace_userstack(buffer, flags, pc); - - if (wake) - trace_wake_up(); } void trace_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { - __trace_buffer_unlock_commit(buffer, event, flags, pc, 1); + __trace_buffer_unlock_commit(buffer, event, flags, pc); } +EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit); struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_rb, @@ -1215,29 +1245,21 @@ void trace_current_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { - __trace_buffer_unlock_commit(buffer, event, flags, pc, 1); + __trace_buffer_unlock_commit(buffer, event, flags, pc); } EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit); -void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags, int pc) +void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc, + struct pt_regs *regs) { - __trace_buffer_unlock_commit(buffer, event, flags, pc, 0); -} -EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit); - -void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags, int pc, - struct pt_regs *regs) -{ - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); ftrace_trace_stack_regs(buffer, flags, 0, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } -EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit_regs); +EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); void trace_current_buffer_discard_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) @@ -1269,7 +1291,7 @@ trace_function(struct trace_array *tr, entry->parent_ip = parent_ip; if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); } void @@ -1362,7 +1384,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, entry->size = trace.nr_entries; if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); out: /* Again, don't let gcc optimize things here */ @@ -1458,7 +1480,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) save_stack_trace_user(&trace); if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); out_drop_count: __this_cpu_dec(user_stack_count); @@ -1559,10 +1581,10 @@ static int alloc_percpu_trace_buffer(void) return -ENOMEM; } +static int buffers_allocated; + void trace_printk_init_buffers(void) { - static int buffers_allocated; - if (buffers_allocated) return; @@ -1571,7 +1593,38 @@ void trace_printk_init_buffers(void) pr_info("ftrace: Allocated trace_printk buffers\n"); + /* Expand the buffers to set size */ + tracing_update_buffers(); + buffers_allocated = 1; + + /* + * trace_printk_init_buffers() can be called by modules. + * If that happens, then we need to start cmdline recording + * directly here. If the global_trace.buffer is already + * allocated here, then this was called by module code. + */ + if (global_trace.buffer) + tracing_start_cmdline_record(); +} + +void trace_printk_start_comm(void) +{ + /* Start tracing comms if trace printk is set */ + if (!buffers_allocated) + return; + tracing_start_cmdline_record(); +} + +static void trace_printk_start_stop_comm(int enabled) +{ + if (!buffers_allocated) + return; + + if (enabled) + tracing_start_cmdline_record(); + else + tracing_stop_cmdline_record(); } /** @@ -1622,7 +1675,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) memcpy(entry->buf, tbuffer, sizeof(u32) * len); if (!filter_check_discard(call, entry, buffer, event)) { - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } @@ -1693,7 +1746,7 @@ int trace_array_vprintk(struct trace_array *tr, memcpy(&entry->buf, tbuffer, len); entry->buf[len] = '\0'; if (!filter_check_discard(call, entry, buffer, event)) { - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } out: @@ -2426,6 +2479,10 @@ __tracing_open(struct inode *inode, struct file *file) if (ring_buffer_overruns(iter->tr->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; + /* Output in nanoseconds only if we are using a clock in nanoseconds. */ + if (trace_clocks[trace_clock_id].in_ns) + iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + /* stop the trace while dumping */ tracing_stop(); @@ -2794,26 +2851,19 @@ static void set_tracer_flags(unsigned int mask, int enabled) if (mask == TRACE_ITER_OVERWRITE) ring_buffer_change_overwrite(global_trace.buffer, enabled); + + if (mask == TRACE_ITER_PRINTK) + trace_printk_start_stop_comm(enabled); } -static ssize_t -tracing_trace_options_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +static int trace_set_options(char *option) { - char buf[64]; char *cmp; int neg = 0; - int ret; + int ret = 0; int i; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - cmp = strstrip(buf); + cmp = strstrip(option); if (strncmp(cmp, "no", 2) == 0) { neg = 1; @@ -2832,10 +2882,25 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, mutex_lock(&trace_types_lock); ret = set_tracer_option(current_trace, cmp, neg); mutex_unlock(&trace_types_lock); - if (ret) - return ret; } + return ret; +} + +static ssize_t +tracing_trace_options_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + trace_set_options(buf); + *ppos += cnt; return cnt; @@ -2940,56 +3005,6 @@ static const struct file_operations tracing_saved_cmdlines_fops = { }; static ssize_t -tracing_ctrl_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - int r; - - r = sprintf(buf, "%u\n", tracer_enabled); - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - -static ssize_t -tracing_ctrl_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - struct trace_array *tr = filp->private_data; - unsigned long val; - int ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - return ret; - - val = !!val; - - mutex_lock(&trace_types_lock); - if (tracer_enabled ^ val) { - - /* Only need to warn if this is used to change the state */ - WARN_ONCE(1, "tracing_enabled is deprecated. Use tracing_on"); - - if (val) { - tracer_enabled = 1; - if (current_trace->start) - current_trace->start(tr); - tracing_start(); - } else { - tracer_enabled = 0; - tracing_stop(); - if (current_trace->stop) - current_trace->stop(tr); - } - } - mutex_unlock(&trace_types_lock); - - *ppos += cnt; - - return cnt; -} - -static ssize_t tracing_set_trace_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -3030,6 +3045,10 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) */ ring_buffer_expanded = 1; + /* May be called before buffers are initialized */ + if (!global_trace.buffer) + return 0; + ret = ring_buffer_resize(global_trace.buffer, size, cpu); if (ret < 0) return ret; @@ -3325,6 +3344,10 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) if (trace_flags & TRACE_ITER_LATENCY_FMT) iter->iter_flags |= TRACE_FILE_LAT_FMT; + /* Output in nanoseconds only if we are using a clock in nanoseconds. */ + if (trace_clocks[trace_clock_id].in_ns) + iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + iter->cpu_file = cpu_file; iter->tr = &global_trace; mutex_init(&iter->mutex); @@ -3385,19 +3408,6 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) } } - -void default_wait_pipe(struct trace_iterator *iter) -{ - DEFINE_WAIT(wait); - - prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE); - - if (trace_empty(iter)) - schedule(); - - finish_wait(&trace_wait, &wait); -} - /* * This is a make-shift waitqueue. * A tracer might use this callback on some rare cases: @@ -3438,7 +3448,7 @@ static int tracing_wait_pipe(struct file *filp) return -EINTR; /* - * We block until we read something and tracing is disabled. + * We block until we read something and tracing is enabled. * We still block if tracing is disabled, but we have never * read anything. This allows a user to cat this file, and * then enable tracing. But after we have read something, @@ -3446,7 +3456,7 @@ static int tracing_wait_pipe(struct file *filp) * * iter->pos will be 0 if we haven't read anything. */ - if (!tracer_enabled && iter->pos) + if (tracing_is_enabled() && iter->pos) break; } @@ -3955,7 +3965,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, } else entry->buf[cnt] = '\0'; - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); written = cnt; @@ -4016,6 +4026,14 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, if (max_tr.buffer) ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func); + /* + * New clock may not be consistent with the previous clock. + * Reset the buffer so that it doesn't have incomparable timestamps. + */ + tracing_reset_online_cpus(&global_trace); + if (max_tr.buffer) + tracing_reset_online_cpus(&max_tr); + mutex_unlock(&trace_types_lock); *fpos += cnt; @@ -4037,13 +4055,6 @@ static const struct file_operations tracing_max_lat_fops = { .llseek = generic_file_llseek, }; -static const struct file_operations tracing_ctrl_fops = { - .open = tracing_open_generic, - .read = tracing_ctrl_read, - .write = tracing_ctrl_write, - .llseek = generic_file_llseek, -}; - static const struct file_operations set_tracer_fops = { .open = tracing_open_generic, .read = tracing_set_trace_read, @@ -4377,13 +4388,27 @@ tracing_stats_read(struct file *filp, char __user *ubuf, cnt = ring_buffer_bytes_cpu(tr->buffer, cpu); trace_seq_printf(s, "bytes: %ld\n", cnt); - t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu)); - usec_rem = do_div(t, USEC_PER_SEC); - trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); + if (trace_clocks[trace_clock_id].in_ns) { + /* local or global for trace_clock */ + t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu)); + usec_rem = do_div(t, USEC_PER_SEC); + trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", + t, usec_rem); + + t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu)); + usec_rem = do_div(t, USEC_PER_SEC); + trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); + } else { + /* counter or tsc mode for trace_clock */ + trace_seq_printf(s, "oldest event ts: %llu\n", + ring_buffer_oldest_event_ts(tr->buffer, cpu)); + + trace_seq_printf(s, "now ts: %llu\n", + ring_buffer_time_stamp(tr->buffer, cpu)); + } - t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu)); - usec_rem = do_div(t, USEC_PER_SEC); - trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); + cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu); + trace_seq_printf(s, "dropped events: %ld\n", cnt); count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); @@ -4815,9 +4840,6 @@ static __init int tracer_init_debugfs(void) d_tracer = tracing_init_dentry(); - trace_create_file("tracing_enabled", 0644, d_tracer, - &global_trace, &tracing_ctrl_fops); - trace_create_file("trace_options", 0644, d_tracer, NULL, &tracing_iter_fops); @@ -5089,6 +5111,7 @@ __init static int tracer_alloc_buffers(void) /* Only allocate trace_printk buffers if a trace_printk exists */ if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + /* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers(); /* To save memory, keep the ring buffer size to its minimum */ @@ -5136,6 +5159,7 @@ __init static int tracer_alloc_buffers(void) #endif trace_init_cmdlines(); + init_irq_work(&trace_work_wakeup, trace_wake_up); register_tracer(&nop_trace); current_trace = &nop_trace; @@ -5147,6 +5171,13 @@ __init static int tracer_alloc_buffers(void) register_die_notifier(&trace_die_notifier); + while (trace_boot_options) { + char *option; + + option = strsep(&trace_boot_options, ","); + trace_set_options(option); + } + return 0; out_free_cpumask: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c15f528c1af..c75d7988902 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -285,8 +285,8 @@ struct tracer { int (*set_flag)(u32 old_flags, u32 bit, int set); struct tracer *next; struct tracer_flags *flags; - int print_max; - int use_max_tr; + bool print_max; + bool use_max_tr; }; @@ -327,7 +327,6 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu) int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); -void trace_wake_up(void); void tracing_reset(struct trace_array *tr, int cpu); void tracing_reset_online_cpus(struct trace_array *tr); void tracing_reset_current(int cpu); @@ -349,9 +348,6 @@ trace_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long len, unsigned long flags, int pc); -void trace_buffer_unlock_commit(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags, int pc); struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data); @@ -359,6 +355,9 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts); +void __buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event); + int trace_empty(struct trace_iterator *iter); void *trace_find_next_entry_inc(struct trace_iterator *iter); @@ -367,7 +366,6 @@ void trace_init_global_iter(struct trace_iterator *iter); void tracing_iter_reset(struct trace_iterator *iter, int cpu); -void default_wait_pipe(struct trace_iterator *iter); void poll_wait_pipe(struct trace_iterator *iter); void ftrace(struct trace_array *tr, @@ -407,12 +405,7 @@ void tracing_sched_switch_assign_trace(struct trace_array *tr); void tracing_stop_sched_switch_record(void); void tracing_start_sched_switch_record(void); int register_tracer(struct tracer *type); -void unregister_tracer(struct tracer *type); int is_tracing_stopped(void); -enum trace_file_type { - TRACE_FILE_LAT_FMT = 1, - TRACE_FILE_ANNOTATE = 2, -}; extern cpumask_var_t __read_mostly tracing_buffer_mask; @@ -841,6 +834,7 @@ extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; void trace_printk_init_buffers(void); +void trace_printk_start_comm(void); #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 8d3538b4ea5..95e96842ed2 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -77,7 +77,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) entry->correct = val == expect; if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); out: atomic_dec(&tr->data[cpu]->disabled); @@ -199,7 +199,7 @@ __init static int init_branch_tracer(void) } return register_tracer(&branch_trace); } -device_initcall(init_branch_tracer); +core_initcall(init_branch_tracer); #else static inline diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index d608d09d08c..880073d0b94 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -491,19 +491,6 @@ static void t_stop(struct seq_file *m, void *p) mutex_unlock(&event_mutex); } -static int -ftrace_event_seq_open(struct inode *inode, struct file *file) -{ - const struct seq_operations *seq_ops; - - if ((file->f_mode & FMODE_WRITE) && - (file->f_flags & O_TRUNC)) - ftrace_clear_events(); - - seq_ops = inode->i_private; - return seq_open(file, seq_ops); -} - static ssize_t event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -980,6 +967,9 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) return r; } +static int ftrace_event_avail_open(struct inode *inode, struct file *file); +static int ftrace_event_set_open(struct inode *inode, struct file *file); + static const struct seq_operations show_event_seq_ops = { .start = t_start, .next = t_next, @@ -995,14 +985,14 @@ static const struct seq_operations show_set_event_seq_ops = { }; static const struct file_operations ftrace_avail_fops = { - .open = ftrace_event_seq_open, + .open = ftrace_event_avail_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations ftrace_set_event_fops = { - .open = ftrace_event_seq_open, + .open = ftrace_event_set_open, .read = seq_read, .write = ftrace_event_write, .llseek = seq_lseek, @@ -1078,6 +1068,26 @@ static struct dentry *event_trace_events_dir(void) return d_events; } +static int +ftrace_event_avail_open(struct inode *inode, struct file *file) +{ + const struct seq_operations *seq_ops = &show_event_seq_ops; + + return seq_open(file, seq_ops); +} + +static int +ftrace_event_set_open(struct inode *inode, struct file *file) +{ + const struct seq_operations *seq_ops = &show_set_event_seq_ops; + + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) + ftrace_clear_events(); + + return seq_open(file, seq_ops); +} + static struct dentry * event_subsystem_dir(const char *name, struct dentry *d_events) { @@ -1489,6 +1499,9 @@ static __init int event_trace_enable(void) if (ret) pr_warn("Failed to enable trace event: %s\n", token); } + + trace_printk_start_comm(); + return 0; } @@ -1505,15 +1518,13 @@ static __init int event_trace_init(void) return 0; entry = debugfs_create_file("available_events", 0444, d_tracer, - (void *)&show_event_seq_ops, - &ftrace_avail_fops); + NULL, &ftrace_avail_fops); if (!entry) pr_warning("Could not create debugfs " "'available_events' entry\n"); entry = debugfs_create_file("set_event", 0644, d_tracer, - (void *)&show_set_event_seq_ops, - &ftrace_set_event_fops); + NULL, &ftrace_set_event_fops); if (!entry) pr_warning("Could not create debugfs " "'set_event' entry\n"); @@ -1749,7 +1760,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip, entry->ip = ip; entry->parent_ip = parent_ip; - trace_nowake_buffer_unlock_commit(buffer, event, flags, pc); + trace_buffer_unlock_commit(buffer, event, flags, pc); out: atomic_dec(&per_cpu(ftrace_test_event_disable, cpu)); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c154797a7ff..e5b0ca8b8d4 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1000,9 +1000,9 @@ static int init_pred(struct filter_parse_state *ps, } } else { if (field->is_signed) - ret = strict_strtoll(pred->regex.pattern, 0, &val); + ret = kstrtoll(pred->regex.pattern, 0, &val); else - ret = strict_strtoull(pred->regex.pattern, 0, &val); + ret = kstrtoull(pred->regex.pattern, 0, &val); if (ret) { parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0); return -EINVAL; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 507a7a9630b..bb227e380cb 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -366,7 +366,7 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash, * We use the callback data field (which is a pointer) * as our counter. */ - ret = strict_strtoul(number, 0, (unsigned long *)&count); + ret = kstrtoul(number, 0, (unsigned long *)&count); if (ret) return ret; @@ -411,5 +411,4 @@ static __init int init_function_trace(void) init_func_cmd_traceon(); return register_tracer(&function_trace); } -device_initcall(init_function_trace); - +core_initcall(init_function_trace); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 99b4378393d..4edb4b74eb7 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -223,7 +223,7 @@ int __trace_graph_entry(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->graph_ent = *trace; if (!filter_current_check_discard(buffer, call, entry, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); return 1; } @@ -327,7 +327,7 @@ void __trace_graph_return(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->ret = *trace; if (!filter_current_check_discard(buffer, call, entry, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); } void trace_graph_return(struct ftrace_graph_ret *trace) @@ -1474,4 +1474,4 @@ static __init int init_graph_trace(void) return register_tracer(&graph_trace); } -device_initcall(init_graph_trace); +core_initcall(init_graph_trace); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index d98ee8283b2..5ffce7b0f33 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -604,7 +604,7 @@ static struct tracer irqsoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .print_max = 1, + .print_max = true, .print_header = irqsoff_print_header, .print_line = irqsoff_print_line, .flags = &tracer_flags, @@ -614,7 +614,7 @@ static struct tracer irqsoff_tracer __read_mostly = #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; # define register_irqsoff(trace) register_tracer(&trace) #else @@ -637,7 +637,7 @@ static struct tracer preemptoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .print_max = 1, + .print_max = true, .print_header = irqsoff_print_header, .print_line = irqsoff_print_line, .flags = &tracer_flags, @@ -647,7 +647,7 @@ static struct tracer preemptoff_tracer __read_mostly = #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; # define register_preemptoff(trace) register_tracer(&trace) #else @@ -672,7 +672,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .print_max = 1, + .print_max = true, .print_header = irqsoff_print_header, .print_line = irqsoff_print_line, .flags = &tracer_flags, @@ -682,7 +682,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly = #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; # define register_preemptirqsoff(trace) register_tracer(&trace) @@ -698,4 +698,4 @@ __init static int init_irqsoff_tracer(void) return 0; } -device_initcall(init_irqsoff_tracer); +core_initcall(init_irqsoff_tracer); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1a2117043bb..1865d5f7653 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -444,7 +444,7 @@ static int create_trace_probe(int argc, char **argv) return -EINVAL; } /* an address specified */ - ret = strict_strtoul(&argv[1][0], 0, (unsigned long *)&addr); + ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); if (ret) { pr_info("Failed to parse address.\n"); return ret; @@ -751,8 +751,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); if (!filter_current_check_discard(buffer, call, entry, event)) - trace_nowake_buffer_unlock_commit_regs(buffer, event, - irq_flags, pc, regs); + trace_buffer_unlock_commit_regs(buffer, event, + irq_flags, pc, regs); } /* Kretprobe handler */ @@ -784,8 +784,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); if (!filter_current_check_discard(buffer, call, entry, event)) - trace_nowake_buffer_unlock_commit_regs(buffer, event, - irq_flags, pc, regs); + trace_buffer_unlock_commit_regs(buffer, event, + irq_flags, pc, regs); } /* Event entry printers */ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 123b189c732..194d79602dc 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -610,24 +610,54 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) return trace_print_lat_fmt(s, entry); } -static unsigned long preempt_mark_thresh = 100; +static unsigned long preempt_mark_thresh_us = 100; static int -lat_print_timestamp(struct trace_seq *s, u64 abs_usecs, - unsigned long rel_usecs) +lat_print_timestamp(struct trace_iterator *iter, u64 next_ts) { - return trace_seq_printf(s, " %4lldus%c: ", abs_usecs, - rel_usecs > preempt_mark_thresh ? '!' : - rel_usecs > 1 ? '+' : ' '); + unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE; + unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS; + unsigned long long abs_ts = iter->ts - iter->tr->time_start; + unsigned long long rel_ts = next_ts - iter->ts; + struct trace_seq *s = &iter->seq; + + if (in_ns) { + abs_ts = ns2usecs(abs_ts); + rel_ts = ns2usecs(rel_ts); + } + + if (verbose && in_ns) { + unsigned long abs_usec = do_div(abs_ts, USEC_PER_MSEC); + unsigned long abs_msec = (unsigned long)abs_ts; + unsigned long rel_usec = do_div(rel_ts, USEC_PER_MSEC); + unsigned long rel_msec = (unsigned long)rel_ts; + + return trace_seq_printf( + s, "[%08llx] %ld.%03ldms (+%ld.%03ldms): ", + ns2usecs(iter->ts), + abs_msec, abs_usec, + rel_msec, rel_usec); + } else if (verbose && !in_ns) { + return trace_seq_printf( + s, "[%016llx] %lld (+%lld): ", + iter->ts, abs_ts, rel_ts); + } else if (!verbose && in_ns) { + return trace_seq_printf( + s, " %4lldus%c: ", + abs_ts, + rel_ts > preempt_mark_thresh_us ? '!' : + rel_ts > 1 ? '+' : ' '); + } else { /* !verbose && !in_ns */ + return trace_seq_printf(s, " %4lld: ", abs_ts); + } } int trace_print_context(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry = iter->ent; - unsigned long long t = ns2usecs(iter->ts); - unsigned long usec_rem = do_div(t, USEC_PER_SEC); - unsigned long secs = (unsigned long)t; + unsigned long long t; + unsigned long secs, usec_rem; char comm[TASK_COMM_LEN]; int ret; @@ -644,8 +674,13 @@ int trace_print_context(struct trace_iterator *iter) return 0; } - return trace_seq_printf(s, " %5lu.%06lu: ", - secs, usec_rem); + if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) { + t = ns2usecs(iter->ts); + usec_rem = do_div(t, USEC_PER_SEC); + secs = (unsigned long)t; + return trace_seq_printf(s, " %5lu.%06lu: ", secs, usec_rem); + } else + return trace_seq_printf(s, " %12llu: ", iter->ts); } int trace_print_lat_context(struct trace_iterator *iter) @@ -659,36 +694,29 @@ int trace_print_lat_context(struct trace_iterator *iter) *next_entry = trace_find_next_entry(iter, NULL, &next_ts); unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); - unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start); - unsigned long rel_usecs; /* Restore the original ent_size */ iter->ent_size = ent_size; if (!next_entry) next_ts = iter->ts; - rel_usecs = ns2usecs(next_ts - iter->ts); if (verbose) { char comm[TASK_COMM_LEN]; trace_find_cmdline(entry->pid, comm); - ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08llx]" - " %ld.%03ldms (+%ld.%03ldms): ", comm, - entry->pid, iter->cpu, entry->flags, - entry->preempt_count, iter->idx, - ns2usecs(iter->ts), - abs_usecs / USEC_PER_MSEC, - abs_usecs % USEC_PER_MSEC, - rel_usecs / USEC_PER_MSEC, - rel_usecs % USEC_PER_MSEC); + ret = trace_seq_printf( + s, "%16s %5d %3d %d %08x %08lx ", + comm, entry->pid, iter->cpu, entry->flags, + entry->preempt_count, iter->idx); } else { ret = lat_print_generic(s, entry, iter->cpu); - if (ret) - ret = lat_print_timestamp(s, abs_usecs, rel_usecs); } + if (ret) + ret = lat_print_timestamp(iter, next_ts); + return ret; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index daa9980153a..412e959709b 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -441,7 +441,7 @@ static const struct fetch_type *find_fetch_type(const char *type) goto fail; type++; - if (strict_strtoul(type, 0, &bs)) + if (kstrtoul(type, 0, &bs)) goto fail; switch (bs) { @@ -501,8 +501,8 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset) tmp = strchr(symbol, '+'); if (tmp) { - /* skip sign because strict_strtol doesn't accept '+' */ - ret = strict_strtoul(tmp + 1, 0, offset); + /* skip sign because kstrtoul doesn't accept '+' */ + ret = kstrtoul(tmp + 1, 0, offset); if (ret) return ret; @@ -533,7 +533,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, else ret = -EINVAL; } else if (isdigit(arg[5])) { - ret = strict_strtoul(arg + 5, 10, ¶m); + ret = kstrtoul(arg + 5, 10, ¶m); if (ret || param > PARAM_MAX_STACK) ret = -EINVAL; else { @@ -579,7 +579,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, case '@': /* memory or symbol */ if (isdigit(arg[1])) { - ret = strict_strtoul(arg + 1, 0, ¶m); + ret = kstrtoul(arg + 1, 0, ¶m); if (ret) break; @@ -597,14 +597,14 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, break; case '+': /* deref memory */ - arg++; /* Skip '+', because strict_strtol() rejects it. */ + arg++; /* Skip '+', because kstrtol() rejects it. */ case '-': tmp = strchr(arg, '('); if (!tmp) break; *tmp = '\0'; - ret = strict_strtol(arg, 0, &offset); + ret = kstrtol(arg, 0, &offset); if (ret) break; diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 7e62c0a1845..3374c792ccd 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -102,9 +102,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_cpu = task_cpu(wakee); if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr->buffer, flags, 6, pc); - ftrace_trace_userstack(tr->buffer, flags, pc); + trace_buffer_unlock_commit(buffer, event, flags, pc); } static void diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 02170c00c41..bc64fc13755 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -589,7 +589,7 @@ static struct tracer wakeup_tracer __read_mostly = .reset = wakeup_tracer_reset, .start = wakeup_tracer_start, .stop = wakeup_tracer_stop, - .print_max = 1, + .print_max = true, .print_header = wakeup_print_header, .print_line = wakeup_print_line, .flags = &tracer_flags, @@ -599,7 +599,7 @@ static struct tracer wakeup_tracer __read_mostly = #endif .open = wakeup_trace_open, .close = wakeup_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; static struct tracer wakeup_rt_tracer __read_mostly = @@ -610,7 +610,7 @@ static struct tracer wakeup_rt_tracer __read_mostly = .start = wakeup_tracer_start, .stop = wakeup_tracer_stop, .wait_pipe = poll_wait_pipe, - .print_max = 1, + .print_max = true, .print_header = wakeup_print_header, .print_line = wakeup_print_line, .flags = &tracer_flags, @@ -620,7 +620,7 @@ static struct tracer wakeup_rt_tracer __read_mostly = #endif .open = wakeup_trace_open, .close = wakeup_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; __init static int init_wakeup_tracer(void) @@ -637,4 +637,4 @@ __init static int init_wakeup_tracer(void) return 0; } -device_initcall(init_wakeup_tracer); +core_initcall(init_wakeup_tracer); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 2c00a691a54..47623169a81 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -320,7 +320,6 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, int (*func)(void)) { int save_ftrace_enabled = ftrace_enabled; - int save_tracer_enabled = tracer_enabled; unsigned long count; char *func_name; int ret; @@ -331,7 +330,6 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, /* enable tracing, and record the filter function */ ftrace_enabled = 1; - tracer_enabled = 1; /* passed in by parameter to fool gcc from optimizing */ func(); @@ -395,7 +393,6 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, out: ftrace_enabled = save_ftrace_enabled; - tracer_enabled = save_tracer_enabled; /* Enable tracing on all functions again */ ftrace_set_global_filter(NULL, 0, 1); @@ -452,7 +449,6 @@ static int trace_selftest_function_recursion(void) { int save_ftrace_enabled = ftrace_enabled; - int save_tracer_enabled = tracer_enabled; char *func_name; int len; int ret; @@ -465,7 +461,6 @@ trace_selftest_function_recursion(void) /* enable tracing, and record the filter function */ ftrace_enabled = 1; - tracer_enabled = 1; /* Handle PPC64 '.' name */ func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); @@ -534,7 +529,6 @@ trace_selftest_function_recursion(void) ret = 0; out: ftrace_enabled = save_ftrace_enabled; - tracer_enabled = save_tracer_enabled; return ret; } @@ -569,7 +563,6 @@ static int trace_selftest_function_regs(void) { int save_ftrace_enabled = ftrace_enabled; - int save_tracer_enabled = tracer_enabled; char *func_name; int len; int ret; @@ -586,7 +579,6 @@ trace_selftest_function_regs(void) /* enable tracing, and record the filter function */ ftrace_enabled = 1; - tracer_enabled = 1; /* Handle PPC64 '.' name */ func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); @@ -648,7 +640,6 @@ trace_selftest_function_regs(void) ret = 0; out: ftrace_enabled = save_ftrace_enabled; - tracer_enabled = save_tracer_enabled; return ret; } @@ -662,7 +653,6 @@ int trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) { int save_ftrace_enabled = ftrace_enabled; - int save_tracer_enabled = tracer_enabled; unsigned long count; int ret; @@ -671,7 +661,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) /* start the tracing */ ftrace_enabled = 1; - tracer_enabled = 1; ret = tracer_init(trace, tr); if (ret) { @@ -708,7 +697,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ret = trace_selftest_function_regs(); out: ftrace_enabled = save_ftrace_enabled; - tracer_enabled = save_tracer_enabled; /* kill ftrace totally if we failed */ if (ret) @@ -1106,6 +1094,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(tr, NULL); + printk("ret = %d\n", ret); if (!ret) ret = trace_test_buffer(&max_tr, &count); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 2485a7d09b1..7609dd6714c 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -21,9 +21,6 @@ static int syscall_enter_register(struct ftrace_event_call *event, static int syscall_exit_register(struct ftrace_event_call *event, enum trace_reg type, void *data); -static int syscall_enter_define_fields(struct ftrace_event_call *call); -static int syscall_exit_define_fields(struct ftrace_event_call *call); - static struct list_head * syscall_get_enter_fields(struct ftrace_event_call *call) { @@ -32,30 +29,6 @@ syscall_get_enter_fields(struct ftrace_event_call *call) return &entry->enter_fields; } -struct trace_event_functions enter_syscall_print_funcs = { - .trace = print_syscall_enter, -}; - -struct trace_event_functions exit_syscall_print_funcs = { - .trace = print_syscall_exit, -}; - -struct ftrace_event_class event_class_syscall_enter = { - .system = "syscalls", - .reg = syscall_enter_register, - .define_fields = syscall_enter_define_fields, - .get_fields = syscall_get_enter_fields, - .raw_init = init_syscall_trace, -}; - -struct ftrace_event_class event_class_syscall_exit = { - .system = "syscalls", - .reg = syscall_exit_register, - .define_fields = syscall_exit_define_fields, - .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), - .raw_init = init_syscall_trace, -}; - extern struct syscall_metadata *__start_syscalls_metadata[]; extern struct syscall_metadata *__stop_syscalls_metadata[]; @@ -432,7 +405,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call) mutex_unlock(&syscall_trace_lock); } -int init_syscall_trace(struct ftrace_event_call *call) +static int init_syscall_trace(struct ftrace_event_call *call) { int id; int num; @@ -457,6 +430,30 @@ int init_syscall_trace(struct ftrace_event_call *call) return id; } +struct trace_event_functions enter_syscall_print_funcs = { + .trace = print_syscall_enter, +}; + +struct trace_event_functions exit_syscall_print_funcs = { + .trace = print_syscall_exit, +}; + +struct ftrace_event_class event_class_syscall_enter = { + .system = "syscalls", + .reg = syscall_enter_register, + .define_fields = syscall_enter_define_fields, + .get_fields = syscall_get_enter_fields, + .raw_init = init_syscall_trace, +}; + +struct ftrace_event_class event_class_syscall_exit = { + .system = "syscalls", + .reg = syscall_exit_register, + .define_fields = syscall_exit_define_fields, + .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), + .raw_init = init_syscall_trace, +}; + unsigned long __init __weak arch_syscall_addr(int nr) { return (unsigned long)sys_call_table[nr]; @@ -537,7 +534,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } -int perf_sysenter_enable(struct ftrace_event_call *call) +static int perf_sysenter_enable(struct ftrace_event_call *call) { int ret = 0; int num; @@ -558,7 +555,7 @@ int perf_sysenter_enable(struct ftrace_event_call *call) return ret; } -void perf_sysenter_disable(struct ftrace_event_call *call) +static void perf_sysenter_disable(struct ftrace_event_call *call) { int num; @@ -615,7 +612,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } -int perf_sysexit_enable(struct ftrace_event_call *call) +static int perf_sysexit_enable(struct ftrace_event_call *call) { int ret = 0; int num; @@ -636,7 +633,7 @@ int perf_sysexit_enable(struct ftrace_event_call *call) return ret; } -void perf_sysexit_disable(struct ftrace_event_call *call) +static void perf_sysexit_disable(struct ftrace_event_call *call) { int num; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 03003cd7dd9..9614db8b0f8 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -189,7 +189,7 @@ static int create_trace_uprobe(int argc, char **argv) if (argv[0][0] == '-') is_delete = true; else if (argv[0][0] != 'p') { - pr_info("Probe definition must be started with 'p', 'r' or" " '-'.\n"); + pr_info("Probe definition must be started with 'p' or '-'.\n"); return -EINVAL; } @@ -252,7 +252,7 @@ static int create_trace_uprobe(int argc, char **argv) if (ret) goto fail_address_parse; - ret = strict_strtoul(arg, 0, &offset); + ret = kstrtoul(arg, 0, &offset); if (ret) goto fail_address_parse; |