Saving the comm of tasks for each trace is very expensive. This patch includes in the context switch hook, a way to store the last 100 command lines of tasks. This table is examined when a trace is to be printed. Note: The comm may be destroyed if other traces are performed. Later (TBD) patches may simply store this information in the trace itself. Signed-off-by: Steven Rostedt --- lib/tracing/Kconfig | 1 lib/tracing/trace_function.c | 2 lib/tracing/trace_sched_switch.c | 5 + lib/tracing/tracer.c | 108 ++++++++++++++++++++++++++++++++++++--- lib/tracing/tracer.h | 3 - 5 files changed, 111 insertions(+), 8 deletions(-) Index: linux-mcount.git/lib/tracing/Kconfig =================================================================== --- linux-mcount.git.orig/lib/tracing/Kconfig 2008-01-29 18:08:06.000000000 -0500 +++ linux-mcount.git/lib/tracing/Kconfig 2008-01-29 18:09:01.000000000 -0500 @@ -18,6 +18,7 @@ config FUNCTION_TRACER depends on DEBUG_KERNEL && HAVE_MCOUNT select MCOUNT select TRACING + select CONTEXT_SWITCH_TRACER help Use profiler instrumentation, adding -pg to CFLAGS. This will insert a call to an architecture specific __mcount routine, Index: linux-mcount.git/lib/tracing/trace_function.c =================================================================== --- linux-mcount.git.orig/lib/tracing/trace_function.c 2008-01-29 18:06:24.000000000 -0500 +++ linux-mcount.git/lib/tracing/trace_function.c 2008-01-29 18:08:10.000000000 -0500 @@ -29,10 +29,12 @@ static notrace void start_function_trace { function_reset(tr); tracing_start_function_trace(); + tracing_start_sched_switch(); } static notrace void stop_function_trace(struct tracing_trace *tr) { + tracing_stop_sched_switch(); tracing_stop_function_trace(); } Index: linux-mcount.git/lib/tracing/trace_sched_switch.c =================================================================== --- linux-mcount.git.orig/lib/tracing/trace_sched_switch.c 2008-01-29 18:08:06.000000000 -0500 +++ linux-mcount.git/lib/tracing/trace_sched_switch.c 2008-01-29 18:09:03.000000000 -0500 @@ -32,6 +32,11 @@ static notrace void sched_switch_callbac va_list ap; int cpu; + if (!atomic_read(&sched_ref)) + return; + + tracing_record_cmdline(current); + if (!trace_enabled) return; Index: linux-mcount.git/lib/tracing/tracer.c =================================================================== --- linux-mcount.git.orig/lib/tracing/tracer.c 2008-01-29 18:08:06.000000000 -0500 +++ linux-mcount.git/lib/tracing/tracer.c 2008-01-29 18:10:04.000000000 -0500 @@ -171,6 +171,87 @@ void tracing_stop_function_trace(void) unregister_mcount_function(&trace_ops); } +#define SAVED_CMDLINES 128 +static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; +static unsigned map_cmdline_to_pid[SAVED_CMDLINES]; +static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN]; +static int cmdline_idx; +static DEFINE_SPINLOCK(trace_cmdline_lock); +atomic_t trace_record_cmdline_disabled; + +static void trace_init_cmdlines(void) +{ + memset(&map_pid_to_cmdline, -1, sizeof(map_pid_to_cmdline)); + memset(&map_cmdline_to_pid, -1, sizeof(map_cmdline_to_pid)); + cmdline_idx = 0; +} + +notrace void trace_stop_cmdline_recording(void); + +static void notrace trace_save_cmdline(struct task_struct *tsk) +{ + unsigned map; + unsigned idx; + + if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) + return; + + /* + * It's not the end of the world if we don't get + * the lock, but we also don't want to spin + * nor do we want to disable interrupts, + * so if we miss here, then better luck next time. + */ + if (!spin_trylock(&trace_cmdline_lock)) + return; + + idx = map_pid_to_cmdline[tsk->pid]; + if (idx >= SAVED_CMDLINES) { + idx = (cmdline_idx + 1) % SAVED_CMDLINES; + + map = map_cmdline_to_pid[idx]; + if (map <= PID_MAX_DEFAULT) + map_pid_to_cmdline[map] = (unsigned)-1; + + map_pid_to_cmdline[tsk->pid] = idx; + + cmdline_idx = idx; + } + + memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN); + + spin_unlock(&trace_cmdline_lock); +} + +static notrace char *trace_find_cmdline(int pid) +{ + char *cmdline = "<...>"; + unsigned map; + + if (!pid) + return ""; + + if (pid > PID_MAX_DEFAULT) + goto out; + + map = map_pid_to_cmdline[pid]; + if (map >= SAVED_CMDLINES) + goto out; + + cmdline = saved_cmdlines[map]; + + out: + return cmdline; +} + +void tracing_record_cmdline(struct task_struct *tsk) +{ + if (atomic_read(&trace_record_cmdline_disabled)) + return; + + trace_save_cmdline(tsk); +} + static inline notrace struct tracing_entry * tracing_get_trace_entry(struct tracing_trace *tr, struct tracing_trace_cpu *data) @@ -212,7 +293,6 @@ tracing_generic_entry_update(struct trac ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); - memcpy(entry->comm, tsk->comm, TASK_COMM_LEN); } notrace void tracing_function_trace(struct tracing_trace *tr, @@ -368,6 +448,8 @@ static void *s_start(struct seq_file *m, if (!current_trace || current_trace != iter->trace) return NULL; + atomic_inc(&trace_record_cmdline_disabled); + /* let the tracer grab locks here if needed */ if (current_trace->start) current_trace->start(iter); @@ -395,6 +477,8 @@ static void s_stop(struct seq_file *m, v { struct tracing_iterator *iter = m->private; + atomic_dec(&trace_record_cmdline_disabled); + /* let the tracer release locks here if needed */ if (current_trace && current_trace == iter->trace && iter->trace->stop) iter->trace->stop(iter); @@ -523,8 +607,11 @@ static void notrace lat_print_generic(struct seq_file *m, struct tracing_entry *entry, int cpu) { int hardirq, softirq; + char *comm; + + comm = trace_find_cmdline(entry->pid); - seq_printf(m, "%8.8s-%-5d ", entry->comm, entry->pid); + seq_printf(m, "%8.8s-%-5d ", comm, entry->pid); seq_printf(m, "%d", cpu); seq_printf(m, "%c%c", (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : '.', @@ -576,6 +663,7 @@ print_lat_fmt(struct seq_file *m, struct struct tracing_entry *next_entry = find_next_entry(iter, NULL); unsigned long abs_usecs; unsigned long rel_usecs; + char *comm; int sym_only = !!(trace_flags & TRACE_ITER_SYM_ONLY); int verbose = !!(trace_flags & TRACE_ITER_VERBOSE); int S; @@ -586,9 +674,10 @@ print_lat_fmt(struct seq_file *m, struct abs_usecs = cycles_to_usecs(entry->t - iter->tr->time_start); if (verbose) { + comm = trace_find_cmdline(entry->pid); seq_printf(m, "%16s %5d %d %d %08x %08x [%08lx]" " %ld.%03ldms (+%ld.%03ldms): ", - entry->comm, + comm, entry->pid, cpu, entry->flags, entry->preempt_count, trace_idx, cycles_to_usecs(entry->t), @@ -608,12 +697,14 @@ print_lat_fmt(struct seq_file *m, struct case TRACE_CTX: S = entry->ctx.prev_state < sizeof(state_to_char) ? state_to_char[entry->ctx.prev_state] : 'X'; - seq_printf(m, " %d:%d:%c --> %d:%d\n", + comm = trace_find_cmdline(entry->ctx.next_pid); + seq_printf(m, " %d:%d:%c --> %d:%d %s\n", entry->ctx.prev_pid, entry->ctx.prev_prio, S, entry->ctx.next_pid, - entry->ctx.next_prio); + entry->ctx.next_prio, + comm); break; } } @@ -626,15 +717,18 @@ static void notrace print_trace_fmt(stru unsigned long secs; int sym_only = !!(trace_flags & TRACE_ITER_SYM_ONLY); unsigned long long t; + char *comm; int S; + comm = trace_find_cmdline(iter->ent->pid); + t = cycles_to_usecs(entry->t); usec_rem = do_div(t, 1000000ULL); secs = (unsigned long)t; seq_printf(m, "[%5lu.%06lu] ", secs, usec_rem); seq_printf(m, "CPU %d: ", iter->cpu); - seq_printf(m, "%s:%d ", entry->comm, + seq_printf(m, "%s:%d ", comm, entry->pid); switch (entry->type) { case TRACE_FN: @@ -1184,6 +1278,8 @@ __init static int tracer_alloc_buffers(v tracer_init_debugfs(); + trace_init_cmdlines(); + register_trace(&disable_trace); return 0; Index: linux-mcount.git/lib/tracing/tracer.h =================================================================== --- linux-mcount.git.orig/lib/tracing/tracer.h 2008-01-29 18:08:06.000000000 -0500 +++ linux-mcount.git/lib/tracing/tracer.h 2008-01-29 18:09:03.000000000 -0500 @@ -25,7 +25,6 @@ struct tracing_entry { char preempt_count; /* assumes PREEMPT_MASK is 8 bits or less */ int pid; cycle_t t; - char comm[TASK_COMM_LEN]; union { struct tracing_function fn; struct tracing_sched_switch ctx; @@ -98,7 +97,7 @@ void tracing_sched_switch_trace(struct t struct task_struct *prev, struct task_struct *next, unsigned long flags); - +void tracing_record_cmdline(struct task_struct *tsk); void tracing_start_function_trace(void); void tracing_stop_function_trace(void); -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/