diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index e2ae608e7043..453084c67327 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -256,7 +256,7 @@ static int msr_update_perf(struct cpufreq_policy *policy, u8 min_perf, if (trace_amd_pstate_epp_perf_enabled()) { union perf_cached perf = READ_ONCE(cpudata->perf); - trace_amd_pstate_epp_perf(cpudata->cpu, + trace_call__amd_pstate_epp_perf(cpudata->cpu, perf.highest_perf, epp, min_perf, @@ -306,7 +306,7 @@ static int msr_set_epp(struct cpufreq_policy *policy, u8 epp) if (trace_amd_pstate_epp_perf_enabled()) { union perf_cached perf = cpudata->perf; - trace_amd_pstate_epp_perf(cpudata->cpu, perf.highest_perf, + trace_call__amd_pstate_epp_perf(cpudata->cpu, perf.highest_perf, epp, FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cpudata->cppc_req_cached), @@ -420,7 +420,7 @@ static int shmem_set_epp(struct cpufreq_policy *policy, u8 epp) if (trace_amd_pstate_epp_perf_enabled()) { union perf_cached perf = cpudata->perf; - trace_amd_pstate_epp_perf(cpudata->cpu, perf.highest_perf, + trace_call__amd_pstate_epp_perf(cpudata->cpu, perf.highest_perf, epp, FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cpudata->cppc_req_cached), @@ -585,7 +585,7 @@ static int shmem_update_perf(struct cpufreq_policy *policy, u8 min_perf, if (trace_amd_pstate_epp_perf_enabled()) { union perf_cached perf = READ_ONCE(cpudata->perf); - trace_amd_pstate_epp_perf(cpudata->cpu, + trace_call__amd_pstate_epp_perf(cpudata->cpu, perf.highest_perf, epp, min_perf, @@ -663,7 +663,7 @@ static void amd_pstate_update(struct cpufreq_policy *policy, u8 min_perf, } if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) { - trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq, + trace_call__amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq, cpudata->cur.mperf, cpudata->cur.aperf, cpudata->cur.tsc, cpudata->cpu, fast_switch); } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 3c5b7fe52cd7..44eb1b7e7fc1 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2212,7 +2212,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, if (trace_cpu_frequency_enabled()) { for_each_cpu(cpu, policy->cpus) - trace_cpu_frequency(freq, cpu); + trace_call__cpu_frequency(freq, cpu); } return freq; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1552b2d32a34..1292da53e5fc 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -3132,7 +3132,7 @@ static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, in return; sample = &cpu->sample; - trace_pstate_sample(trace_type, + trace_call__pstate_sample(trace_type, 0, old_pstate, cpu->pstate.current_pstate, diff --git a/drivers/i2c/i2c-core-slave.c b/drivers/i2c/i2c-core-slave.c index 02ca55c2246b..bebb7ba67e30 100644 --- a/drivers/i2c/i2c-core-slave.c +++ b/drivers/i2c/i2c-core-slave.c @@ -89,7 +89,7 @@ int i2c_slave_event(struct i2c_client *client, int ret = client->slave_cb(client, event, val); if (trace_i2c_slave_enabled()) - trace_i2c_slave(client, event, val, ret); + trace_call__i2c_slave(client, event, val, ret); return ret; } diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c index 48ee5bf48173..02bbc5d0cfc5 100644 --- a/drivers/spi/spi-axi-spi-engine.c +++ b/drivers/spi/spi-axi-spi-engine.c @@ -953,7 +953,7 @@ static int spi_engine_transfer_one_message(struct spi_controller *host, struct spi_transfer *xfer; list_for_each_entry(xfer, &msg->transfers, transfer_list) - trace_spi_transfer_start(msg, xfer); + trace_call__spi_transfer_start(msg, xfer); } spin_lock_irqsave(&spi_engine->lock, flags); @@ -987,7 +987,7 @@ static int spi_engine_transfer_one_message(struct spi_controller *host, struct spi_transfer *xfer; list_for_each_entry(xfer, &msg->transfers, transfer_list) - trace_spi_transfer_stop(msg, xfer); + trace_call__spi_transfer_stop(msg, xfer); } out: diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 095a561d733f..9284c0a81bef 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -1318,7 +1318,7 @@ static void btrfs_extent_map_shrinker_worker(struct work_struct *work) if (trace_btrfs_extent_map_shrinker_scan_enter_enabled()) { s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps); - trace_btrfs_extent_map_shrinker_scan_enter(fs_info, nr); + trace_call__btrfs_extent_map_shrinker_scan_enter(fs_info, nr); } while (ctx.scanned < ctx.nr_to_scan && !btrfs_fs_closing(fs_info)) { @@ -1358,7 +1358,7 @@ static void btrfs_extent_map_shrinker_worker(struct work_struct *work) if (trace_btrfs_extent_map_shrinker_scan_exit_enabled()) { s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps); - trace_btrfs_extent_map_shrinker_scan_exit(fs_info, nr_dropped, nr); + trace_call__btrfs_extent_map_shrinker_scan_exit(fs_info, nr_dropped, nr); } atomic64_set(&fs_info->em_shrinker_nr_to_scan, 0); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index baebd9f733e9..08ee8f316d96 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1719,7 +1719,7 @@ static void submit_read_wait_bio_list(struct btrfs_raid_bio *rbio, struct raid56_bio_trace_info trace_info = { 0 }; bio_get_trace_info(rbio, bio, &trace_info); - trace_raid56_read(rbio, bio, &trace_info); + trace_call__raid56_read(rbio, bio, &trace_info); } submit_bio(bio); } @@ -2404,7 +2404,7 @@ static void submit_write_bios(struct btrfs_raid_bio *rbio, struct raid56_bio_trace_info trace_info = { 0 }; bio_get_trace_info(rbio, bio, &trace_info); - trace_raid56_write(rbio, bio, &trace_info); + trace_call__raid56_write(rbio, bio, &trace_info); } submit_bio(bio); } diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index c242fe49af4c..28b30c6f1031 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -31,7 +31,7 @@ #define ARCH_SUPPORTS_FTRACE_OPS 0 #endif -#ifdef CONFIG_TRACING +#ifdef CONFIG_TRACER_SNAPSHOT extern void ftrace_boot_snapshot(void); #else static inline void ftrace_boot_snapshot(void) { } diff --git a/include/linux/trace_printk.h b/include/linux/trace_printk.h index bb5874097f24..2670ec7f4262 100644 --- a/include/linux/trace_printk.h +++ b/include/linux/trace_printk.h @@ -107,7 +107,6 @@ do { \ __trace_printk(_THIS_IP_, fmt, ##args); \ } while (0) -extern __printf(2, 3) int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 1d7f29f5e901..578e520b6ee6 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -314,6 +314,10 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) WARN_ONCE(!rcu_is_watching(), \ "RCU not watching for tracepoint"); \ } \ + } \ + static inline void trace_call__##name(proto) \ + { \ + __do_trace_##name(args); \ } #define __DECLARE_TRACE_SYSCALL(name, proto, args, data_proto) \ @@ -333,6 +337,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) WARN_ONCE(!rcu_is_watching(), \ "RCU not watching for tracepoint"); \ } \ + } \ + static inline void trace_call__##name(proto) \ + { \ + might_fault(); \ + __do_trace_##name(args); \ } /* @@ -418,6 +427,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define __DECLARE_TRACE_COMMON(name, proto, args, data_proto) \ static inline void trace_##name(proto) \ { } \ + static inline void trace_call__##name(proto) \ + { } \ static inline int \ register_trace_##name(void (*probe)(data_proto), \ void *data) \ diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h index 9912f0ded81d..fae4f8eac411 100644 --- a/include/trace/events/ipi.h +++ b/include/trace/events/ipi.h @@ -68,16 +68,16 @@ TRACE_EVENT(ipi_raise, TP_ARGS(mask, reason), TP_STRUCT__entry( - __bitmask(target_cpus, nr_cpumask_bits) + __cpumask(target_cpus) __field(const char *, reason) ), TP_fast_assign( - __assign_bitmask(target_cpus, cpumask_bits(mask), nr_cpumask_bits); + __assign_cpumask(target_cpus, cpumask_bits(mask)); __entry->reason = reason; ), - TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) + TP_printk("target_mask=%s (%s)", __get_cpumask(target_cpus), __entry->reason) ); DECLARE_EVENT_CLASS(ipi_handler, diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h index e8185889a1c8..7e5e3900d39f 100644 --- a/include/uapi/linux/trace_mmap.h +++ b/include/uapi/linux/trace_mmap.h @@ -10,6 +10,7 @@ * @meta_struct_len: Size of this structure. * @subbuf_size: Size of each sub-buffer. * @nr_subbufs: Number of subbfs in the ring-buffer, including the reader. + * @reader: The reader composite info structure * @reader.lost_events: Number of events lost at the time of the reader swap. * @reader.id: subbuf ID of the current reader. ID range [0 : @nr_subbufs - 1] * @reader.read: Number of bytes read on the reader subbuf. diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 73f7e1fd4ab4..120fd7365fbe 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -79,7 +79,7 @@ void __weak arch_irq_work_raise(void) static __always_inline void irq_work_raise(struct irq_work *work) { if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) - trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); + trace_call__ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); arch_irq_work_raise(); } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 012ca8bd70fb..e426e27b6794 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -5943,7 +5943,7 @@ static __printf(2, 3) void dump_line(struct seq_buf *s, const char *fmt, ...) vscnprintf(line_buf, sizeof(line_buf), fmt, args); va_end(args); - trace_sched_ext_dump(line_buf); + trace_call__sched_ext_dump(line_buf); } #endif /* @s may be zero sized and seq_buf triggers WARN if so */ diff --git a/kernel/smp.c b/kernel/smp.c index 6c77848d91f3..a0bb56bd8dda 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -408,7 +408,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; - trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); + trace_call__csd_queue_cpu(cpu, _RET_IP_, func, csd); } /* diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index d662c1a64cd5..4d4229e5eec4 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_TRACING) += trace_seq.o obj-$(CONFIG_TRACING) += trace_stat.o obj-$(CONFIG_TRACING) += trace_printk.o obj-$(CONFIG_TRACING) += trace_pid.o +obj-$(CONFIG_TRACER_SNAPSHOT) += trace_snapshot.o obj-$(CONFIG_TRACING) += pid_list.o obj-$(CONFIG_TRACING_MAP) += tracing_map.o obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7eac1472cc57..b2611de3f594 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6841,7 +6841,8 @@ bool ftrace_filter_param __initdata; static int __init set_ftrace_notrace(char *str) { ftrace_filter_param = true; - strscpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); + trace_append_boot_param(ftrace_notrace_buf, str, ',', + FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_notrace=", set_ftrace_notrace); @@ -6849,7 +6850,8 @@ __setup("ftrace_notrace=", set_ftrace_notrace); static int __init set_ftrace_filter(char *str) { ftrace_filter_param = true; - strscpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); + trace_append_boot_param(ftrace_filter_buf, str, ',', + FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_filter=", set_ftrace_filter); @@ -6861,14 +6863,16 @@ static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer); static int __init set_graph_function(char *str) { - strscpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); + trace_append_boot_param(ftrace_graph_buf, str, ',', + FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_graph_filter=", set_graph_function); static int __init set_graph_notrace_function(char *str) { - strscpy(ftrace_graph_notrace_buf, str, FTRACE_FILTER_SIZE); + trace_append_boot_param(ftrace_graph_notrace_buf, str, ',', + FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_graph_notrace=", set_graph_notrace_function); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e9455d46ec16..6eb4d3097a4d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -47,7 +47,6 @@ #include #include #include -#include #include #include #include @@ -219,14 +218,36 @@ static void ftrace_trace_userstack(struct trace_array *tr, static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; -static bool allocate_snapshot; -static bool snapshot_at_boot; - static char boot_instance_info[COMMAND_LINE_SIZE] __initdata; static int boot_instance_index; -static char boot_snapshot_info[COMMAND_LINE_SIZE] __initdata; -static int boot_snapshot_index; +/* + * Repeated boot parameters, including Bootconfig array expansions, need + * to stay in the delimiter form that the existing parser consumes. + */ +void __init trace_append_boot_param(char *buf, const char *str, char sep, + int size) +{ + int len, needed, str_len; + + if (!*str) + return; + + len = strlen(buf); + str_len = strlen(str); + needed = len + str_len + 1; + + /* For continuation, account for the separator. */ + if (len) + needed++; + if (needed > size) + return; + + if (len) + buf[len++] = sep; + + strscpy(buf + len, str, size - len); +} static int __init set_cmdline_ftrace(char *str) { @@ -276,38 +297,6 @@ static int __init stop_trace_on_warning(char *str) } __setup("traceoff_on_warning", stop_trace_on_warning); -static int __init boot_alloc_snapshot(char *str) -{ - char *slot = boot_snapshot_info + boot_snapshot_index; - int left = sizeof(boot_snapshot_info) - boot_snapshot_index; - int ret; - - if (str[0] == '=') { - str++; - if (strlen(str) >= left) - return -1; - - ret = snprintf(slot, left, "%s\t", str); - boot_snapshot_index += ret; - } else { - allocate_snapshot = true; - /* We also need the main ring buffer expanded */ - trace_set_ring_buffer_expanded(NULL); - } - return 1; -} -__setup("alloc_snapshot", boot_alloc_snapshot); - - -static int __init boot_snapshot(char *str) -{ - snapshot_at_boot = true; - boot_alloc_snapshot(str); - return 1; -} -__setup("ftrace_boot_snapshot", boot_snapshot); - - static int __init boot_instance(char *str) { char *slot = boot_instance_info + boot_instance_index; @@ -329,7 +318,8 @@ static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) { - strscpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); + trace_append_boot_param(trace_boot_options_buf, str, ',', + MAX_TRACER_SIZE); return 1; } __setup("trace_options=", set_trace_boot_options); @@ -863,47 +853,6 @@ void tracing_on(void) EXPORT_SYMBOL_GPL(tracing_on); #ifdef CONFIG_TRACER_SNAPSHOT -static void tracing_snapshot_instance_cond(struct trace_array *tr, - void *cond_data) -{ - unsigned long flags; - - if (in_nmi()) { - trace_array_puts(tr, "*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); - trace_array_puts(tr, "*** snapshot is being ignored ***\n"); - return; - } - - if (!tr->allocated_snapshot) { - trace_array_puts(tr, "*** SNAPSHOT NOT ALLOCATED ***\n"); - trace_array_puts(tr, "*** stopping trace here! ***\n"); - tracer_tracing_off(tr); - return; - } - - if (tr->mapped) { - trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); - trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); - return; - } - - /* Note, snapshot can not be used when the tracer uses it */ - if (tracer_uses_snapshot(tr->current_trace)) { - trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); - trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); - return; - } - - local_irq_save(flags); - update_max_tr(tr, current, smp_processor_id(), cond_data); - local_irq_restore(flags); -} - -void tracing_snapshot_instance(struct trace_array *tr) -{ - tracing_snapshot_instance_cond(tr, NULL); -} - /** * tracing_snapshot - take a snapshot of the current buffer. * @@ -926,138 +875,6 @@ void tracing_snapshot(void) } EXPORT_SYMBOL_GPL(tracing_snapshot); -/** - * tracing_snapshot_cond - conditionally take a snapshot of the current buffer. - * @tr: The tracing instance to snapshot - * @cond_data: The data to be tested conditionally, and possibly saved - * - * This is the same as tracing_snapshot() except that the snapshot is - * conditional - the snapshot will only happen if the - * cond_snapshot.update() implementation receiving the cond_data - * returns true, which means that the trace array's cond_snapshot - * update() operation used the cond_data to determine whether the - * snapshot should be taken, and if it was, presumably saved it along - * with the snapshot. - */ -void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) -{ - tracing_snapshot_instance_cond(tr, cond_data); -} -EXPORT_SYMBOL_GPL(tracing_snapshot_cond); - -/** - * tracing_cond_snapshot_data - get the user data associated with a snapshot - * @tr: The tracing instance - * - * When the user enables a conditional snapshot using - * tracing_snapshot_cond_enable(), the user-defined cond_data is saved - * with the snapshot. This accessor is used to retrieve it. - * - * Should not be called from cond_snapshot.update(), since it takes - * the tr->max_lock lock, which the code calling - * cond_snapshot.update() has already done. - * - * Returns the cond_data associated with the trace array's snapshot. - */ -void *tracing_cond_snapshot_data(struct trace_array *tr) -{ - void *cond_data = NULL; - - local_irq_disable(); - arch_spin_lock(&tr->max_lock); - - if (tr->cond_snapshot) - cond_data = tr->cond_snapshot->cond_data; - - arch_spin_unlock(&tr->max_lock); - local_irq_enable(); - - return cond_data; -} -EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data); - -static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, - struct array_buffer *size_buf, int cpu_id); -static void set_buffer_entries(struct array_buffer *buf, unsigned long val); - -int tracing_alloc_snapshot_instance(struct trace_array *tr) -{ - int order; - int ret; - - if (!tr->allocated_snapshot) { - - /* Make the snapshot buffer have the same order as main buffer */ - order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); - ret = ring_buffer_subbuf_order_set(tr->snapshot_buffer.buffer, order); - if (ret < 0) - return ret; - - /* allocate spare buffer */ - ret = resize_buffer_duplicate_size(&tr->snapshot_buffer, - &tr->array_buffer, RING_BUFFER_ALL_CPUS); - if (ret < 0) - return ret; - - tr->allocated_snapshot = true; - } - - return 0; -} - -static void free_snapshot(struct trace_array *tr) -{ - /* - * We don't free the ring buffer. instead, resize it because - * The max_tr ring buffer has some state (e.g. ring->clock) and - * we want preserve it. - */ - ring_buffer_subbuf_order_set(tr->snapshot_buffer.buffer, 0); - ring_buffer_resize(tr->snapshot_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); - set_buffer_entries(&tr->snapshot_buffer, 1); - tracing_reset_online_cpus(&tr->snapshot_buffer); - tr->allocated_snapshot = false; -} - -static int tracing_arm_snapshot_locked(struct trace_array *tr) -{ - int ret; - - lockdep_assert_held(&trace_types_lock); - - spin_lock(&tr->snapshot_trigger_lock); - if (tr->snapshot == UINT_MAX || tr->mapped) { - spin_unlock(&tr->snapshot_trigger_lock); - return -EBUSY; - } - - tr->snapshot++; - spin_unlock(&tr->snapshot_trigger_lock); - - ret = tracing_alloc_snapshot_instance(tr); - if (ret) { - spin_lock(&tr->snapshot_trigger_lock); - tr->snapshot--; - spin_unlock(&tr->snapshot_trigger_lock); - } - - return ret; -} - -int tracing_arm_snapshot(struct trace_array *tr) -{ - guard(mutex)(&trace_types_lock); - return tracing_arm_snapshot_locked(tr); -} - -void tracing_disarm_snapshot(struct trace_array *tr) -{ - spin_lock(&tr->snapshot_trigger_lock); - if (!WARN_ON(!tr->snapshot)) - tr->snapshot--; - spin_unlock(&tr->snapshot_trigger_lock); -} - /** * tracing_alloc_snapshot - allocate snapshot buffer. * @@ -1078,159 +895,18 @@ int tracing_alloc_snapshot(void) return ret; } -EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); - -/** - * tracing_snapshot_alloc - allocate and take a snapshot of the current buffer. - * - * This is similar to tracing_snapshot(), but it will allocate the - * snapshot buffer if it isn't already allocated. Use this only - * where it is safe to sleep, as the allocation may sleep. - * - * This causes a swap between the snapshot buffer and the current live - * tracing buffer. You can use this to take snapshots of the live - * trace when some condition is triggered, but continue to trace. - */ -void tracing_snapshot_alloc(void) -{ - int ret; - - ret = tracing_alloc_snapshot(); - if (ret < 0) - return; - - tracing_snapshot(); -} -EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); - -/** - * tracing_snapshot_cond_enable - enable conditional snapshot for an instance - * @tr: The tracing instance - * @cond_data: User data to associate with the snapshot - * @update: Implementation of the cond_snapshot update function - * - * Check whether the conditional snapshot for the given instance has - * already been enabled, or if the current tracer is already using a - * snapshot; if so, return -EBUSY, else create a cond_snapshot and - * save the cond_data and update function inside. - * - * Returns 0 if successful, error otherwise. - */ -int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, - cond_update_fn_t update) -{ - struct cond_snapshot *cond_snapshot __free(kfree) = - kzalloc_obj(*cond_snapshot); - int ret; - - if (!cond_snapshot) - return -ENOMEM; - - cond_snapshot->cond_data = cond_data; - cond_snapshot->update = update; - - guard(mutex)(&trace_types_lock); - - if (tracer_uses_snapshot(tr->current_trace)) - return -EBUSY; - - /* - * The cond_snapshot can only change to NULL without the - * trace_types_lock. We don't care if we race with it going - * to NULL, but we want to make sure that it's not set to - * something other than NULL when we get here, which we can - * do safely with only holding the trace_types_lock and not - * having to take the max_lock. - */ - if (tr->cond_snapshot) - return -EBUSY; - - ret = tracing_arm_snapshot_locked(tr); - if (ret) - return ret; - - local_irq_disable(); - arch_spin_lock(&tr->max_lock); - tr->cond_snapshot = no_free_ptr(cond_snapshot); - arch_spin_unlock(&tr->max_lock); - local_irq_enable(); - - return 0; -} -EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); - -/** - * tracing_snapshot_cond_disable - disable conditional snapshot for an instance - * @tr: The tracing instance - * - * Check whether the conditional snapshot for the given instance is - * enabled; if so, free the cond_snapshot associated with it, - * otherwise return -EINVAL. - * - * Returns 0 if successful, error otherwise. - */ -int tracing_snapshot_cond_disable(struct trace_array *tr) -{ - int ret = 0; - - local_irq_disable(); - arch_spin_lock(&tr->max_lock); - - if (!tr->cond_snapshot) - ret = -EINVAL; - else { - kfree(tr->cond_snapshot); - tr->cond_snapshot = NULL; - } - - arch_spin_unlock(&tr->max_lock); - local_irq_enable(); - - tracing_disarm_snapshot(tr); - - return ret; -} -EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); #else void tracing_snapshot(void) { WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used"); } EXPORT_SYMBOL_GPL(tracing_snapshot); -void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) -{ - WARN_ONCE(1, "Snapshot feature not enabled, but internal conditional snapshot used"); -} -EXPORT_SYMBOL_GPL(tracing_snapshot_cond); -int tracing_alloc_snapshot(void) -{ - WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used"); - return -ENODEV; -} -EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); void tracing_snapshot_alloc(void) { /* Give warning */ tracing_snapshot(); } EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); -void *tracing_cond_snapshot_data(struct trace_array *tr) -{ - return NULL; -} -EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data); -int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update) -{ - return -ENODEV; -} -EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); -int tracing_snapshot_cond_disable(struct trace_array *tr) -{ - return false; -} -EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); -#define free_snapshot(tr) do { } while (0) -#define tracing_arm_snapshot_locked(tr) ({ -EBUSY; }) #endif /* CONFIG_TRACER_SNAPSHOT */ void tracer_tracing_off(struct trace_array *tr) @@ -1543,206 +1219,6 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) unsigned long __read_mostly tracing_thresh; -#ifdef CONFIG_TRACER_MAX_TRACE -#ifdef LATENCY_FS_NOTIFY -static struct workqueue_struct *fsnotify_wq; - -static void latency_fsnotify_workfn(struct work_struct *work) -{ - struct trace_array *tr = container_of(work, struct trace_array, - fsnotify_work); - fsnotify_inode(tr->d_max_latency->d_inode, FS_MODIFY); -} - -static void latency_fsnotify_workfn_irq(struct irq_work *iwork) -{ - struct trace_array *tr = container_of(iwork, struct trace_array, - fsnotify_irqwork); - queue_work(fsnotify_wq, &tr->fsnotify_work); -} - -__init static int latency_fsnotify_init(void) -{ - fsnotify_wq = alloc_workqueue("tr_max_lat_wq", - WQ_UNBOUND | WQ_HIGHPRI, 0); - if (!fsnotify_wq) { - pr_err("Unable to allocate tr_max_lat_wq\n"); - return -ENOMEM; - } - return 0; -} - -late_initcall_sync(latency_fsnotify_init); - -void latency_fsnotify(struct trace_array *tr) -{ - if (!fsnotify_wq) - return; - /* - * We cannot call queue_work(&tr->fsnotify_work) from here because it's - * possible that we are called from __schedule() or do_idle(), which - * could cause a deadlock. - */ - irq_work_queue(&tr->fsnotify_irqwork); -} -#endif /* !LATENCY_FS_NOTIFY */ - -static const struct file_operations tracing_max_lat_fops; - -static void trace_create_maxlat_file(struct trace_array *tr, - struct dentry *d_tracer) -{ -#ifdef LATENCY_FS_NOTIFY - INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn); - init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); -#endif - tr->d_max_latency = trace_create_file("tracing_max_latency", - TRACE_MODE_WRITE, - d_tracer, tr, - &tracing_max_lat_fops); -} - -/* - * Copy the new maximum trace into the separate maximum-trace - * structure. (this way the maximum trace is permanently saved, - * for later retrieval via /sys/kernel/tracing/tracing_max_latency) - */ -static void -__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) -{ - struct array_buffer *trace_buf = &tr->array_buffer; - struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); - struct array_buffer *max_buf = &tr->snapshot_buffer; - struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); - - max_buf->cpu = cpu; - max_buf->time_start = data->preempt_timestamp; - - max_data->saved_latency = tr->max_latency; - max_data->critical_start = data->critical_start; - max_data->critical_end = data->critical_end; - - strscpy(max_data->comm, tsk->comm); - max_data->pid = tsk->pid; - /* - * If tsk == current, then use current_uid(), as that does not use - * RCU. The irq tracer can be called out of RCU scope. - */ - if (tsk == current) - max_data->uid = current_uid(); - else - max_data->uid = task_uid(tsk); - - max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; - max_data->policy = tsk->policy; - max_data->rt_priority = tsk->rt_priority; - - /* record this tasks comm */ - tracing_record_cmdline(tsk); - latency_fsnotify(tr); -} -#else -static inline void trace_create_maxlat_file(struct trace_array *tr, - struct dentry *d_tracer) { } -static inline void __update_max_tr(struct trace_array *tr, - struct task_struct *tsk, int cpu) { } -#endif /* CONFIG_TRACER_MAX_TRACE */ - -#ifdef CONFIG_TRACER_SNAPSHOT -/** - * update_max_tr - snapshot all trace buffers from global_trace to max_tr - * @tr: tracer - * @tsk: the task with the latency - * @cpu: The cpu that initiated the trace. - * @cond_data: User data associated with a conditional snapshot - * - * Flip the buffers between the @tr and the max_tr and record information - * about which task was the cause of this latency. - */ -void -update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, - void *cond_data) -{ - if (tr->stop_count) - return; - - WARN_ON_ONCE(!irqs_disabled()); - - if (!tr->allocated_snapshot) { - /* Only the nop tracer should hit this when disabling */ - WARN_ON_ONCE(tr->current_trace != &nop_trace); - return; - } - - arch_spin_lock(&tr->max_lock); - - /* Inherit the recordable setting from array_buffer */ - if (ring_buffer_record_is_set_on(tr->array_buffer.buffer)) - ring_buffer_record_on(tr->snapshot_buffer.buffer); - else - ring_buffer_record_off(tr->snapshot_buffer.buffer); - - if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) { - arch_spin_unlock(&tr->max_lock); - return; - } - - swap(tr->array_buffer.buffer, tr->snapshot_buffer.buffer); - - __update_max_tr(tr, tsk, cpu); - - arch_spin_unlock(&tr->max_lock); - - /* Any waiters on the old snapshot buffer need to wake up */ - ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS); -} - -/** - * update_max_tr_single - only copy one trace over, and reset the rest - * @tr: tracer - * @tsk: task with the latency - * @cpu: the cpu of the buffer to copy. - * - * Flip the trace of a single CPU buffer between the @tr and the max_tr. - */ -void -update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) -{ - int ret; - - if (tr->stop_count) - return; - - WARN_ON_ONCE(!irqs_disabled()); - if (!tr->allocated_snapshot) { - /* Only the nop tracer should hit this when disabling */ - WARN_ON_ONCE(tr->current_trace != &nop_trace); - return; - } - - arch_spin_lock(&tr->max_lock); - - ret = ring_buffer_swap_cpu(tr->snapshot_buffer.buffer, tr->array_buffer.buffer, cpu); - - if (ret == -EBUSY) { - /* - * We failed to swap the buffer due to a commit taking - * place on this CPU. We fail to record, but we reset - * the max trace buffer (no one writes directly to it) - * and flag that it failed. - * Another reason is resize is in progress. - */ - trace_array_printk_buf(tr->snapshot_buffer.buffer, _THIS_IP_, - "Failed to swap buffers due to commit or resize in progress\n"); - } - - WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); - - __update_max_tr(tr, tsk, cpu); - arch_spin_unlock(&tr->max_lock); -} -#endif /* CONFIG_TRACER_SNAPSHOT */ - struct pipe_wait { struct trace_iterator *iter; int wait_index; @@ -2051,7 +1527,7 @@ int __init register_tracer(struct tracer *type) return 0; } -static void tracing_reset_cpu(struct array_buffer *buf, int cpu) +void tracing_reset_cpu(struct array_buffer *buf, int cpu) { struct trace_buffer *buffer = buf->buffer; @@ -3816,50 +3292,6 @@ static void test_ftrace_alive(struct seq_file *m) "# MAY BE MISSING FUNCTION EVENTS\n"); } -#ifdef CONFIG_TRACER_SNAPSHOT -static void show_snapshot_main_help(struct seq_file *m) -{ - seq_puts(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n" - "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" - "# Takes a snapshot of the main buffer.\n" - "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free)\n" - "# (Doesn't have to be '2' works with any number that\n" - "# is not a '0' or '1')\n"); -} - -static void show_snapshot_percpu_help(struct seq_file *m) -{ - seq_puts(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n"); -#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP - seq_puts(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" - "# Takes a snapshot of the main buffer for this cpu.\n"); -#else - seq_puts(m, "# echo 1 > snapshot : Not supported with this kernel.\n" - "# Must use main snapshot file to allocate.\n"); -#endif - seq_puts(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n" - "# (Doesn't have to be '2' works with any number that\n" - "# is not a '0' or '1')\n"); -} - -static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) -{ - if (iter->tr->allocated_snapshot) - seq_puts(m, "#\n# * Snapshot is allocated *\n#\n"); - else - seq_puts(m, "#\n# * Snapshot is freed *\n#\n"); - - seq_puts(m, "# Snapshot commands:\n"); - if (iter->cpu_file == RING_BUFFER_ALL_CPUS) - show_snapshot_main_help(m); - else - show_snapshot_percpu_help(m); -} -#else -/* Should never be called */ -static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { } -#endif - static int s_show(struct seq_file *m, void *v) { struct trace_iterator *iter = v; @@ -3908,17 +3340,6 @@ static int s_show(struct seq_file *m, void *v) return 0; } -/* - * Should be used after trace_array_get(), trace_types_lock - * ensures that i_cdev was already initialized. - */ -int tracing_get_cpu(struct inode *inode) -{ - if (inode->i_cdev) /* See trace_create_cpu_file() */ - return (long)inode->i_cdev - 1; - return RING_BUFFER_ALL_CPUS; -} - static const struct seq_operations tracer_seq_ops = { .start = s_start, .next = s_next, @@ -3945,7 +3366,7 @@ static void free_trace_iter_content(struct trace_iterator *iter) free_cpumask_var(iter->started); } -static struct trace_iterator * +struct trace_iterator * __tracing_open(struct inode *inode, struct file *file, bool snapshot) { struct trace_array *tr = inode->i_private; @@ -4111,8 +3532,6 @@ int tracing_open_file_tr(struct inode *inode, struct file *filp) event_file_get(file); } - filp->private_data = inode->i_private; - return 0; } @@ -4132,7 +3551,7 @@ int tracing_single_release_file_tr(struct inode *inode, struct file *filp) return single_release(inode, filp); } -static int tracing_release(struct inode *inode, struct file *file) +int tracing_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct seq_file *m = file->private_data; @@ -5283,7 +4702,7 @@ int tracer_init(struct tracer *t, struct trace_array *tr) return t->init(tr); } -static void set_buffer_entries(struct array_buffer *buf, unsigned long val) +void trace_set_buffer_entries(struct array_buffer *buf, unsigned long val) { int cpu; @@ -5294,40 +4713,12 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val) static void update_buffer_entries(struct array_buffer *buf, int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { - set_buffer_entries(buf, ring_buffer_size(buf->buffer, 0)); + trace_set_buffer_entries(buf, ring_buffer_size(buf->buffer, 0)); } else { per_cpu_ptr(buf->data, cpu)->entries = ring_buffer_size(buf->buffer, cpu); } } -#ifdef CONFIG_TRACER_SNAPSHOT -/* resize @tr's buffer to the size of @size_tr's entries */ -static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, - struct array_buffer *size_buf, int cpu_id) -{ - int cpu, ret = 0; - - if (cpu_id == RING_BUFFER_ALL_CPUS) { - for_each_tracing_cpu(cpu) { - ret = ring_buffer_resize(trace_buf->buffer, - per_cpu_ptr(size_buf->data, cpu)->entries, cpu); - if (ret < 0) - break; - per_cpu_ptr(trace_buf->data, cpu)->entries = - per_cpu_ptr(size_buf->data, cpu)->entries; - } - } else { - ret = ring_buffer_resize(trace_buf->buffer, - per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id); - if (ret == 0) - per_cpu_ptr(trace_buf->data, cpu_id)->entries = - per_cpu_ptr(size_buf->data, cpu_id)->entries; - } - - return ret; -} -#endif /* CONFIG_TRACER_SNAPSHOT */ - static int __tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu) { @@ -5750,9 +5141,8 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, return ret; } -static ssize_t -tracing_nsecs_read(unsigned long *ptr, char __user *ubuf, - size_t cnt, loff_t *ppos) +ssize_t tracing_nsecs_read(unsigned long *ptr, char __user *ubuf, + size_t cnt, loff_t *ppos) { char buf[64]; int r; @@ -5764,9 +5154,8 @@ tracing_nsecs_read(unsigned long *ptr, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static ssize_t -tracing_nsecs_write(unsigned long *ptr, const char __user *ubuf, - size_t cnt, loff_t *ppos) +ssize_t tracing_nsecs_write(unsigned long *ptr, const char __user *ubuf, + size_t cnt, loff_t *ppos) { unsigned long val; int ret; @@ -5808,28 +5197,6 @@ tracing_thresh_write(struct file *filp, const char __user *ubuf, return cnt; } -#ifdef CONFIG_TRACER_MAX_TRACE - -static ssize_t -tracing_max_lat_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - struct trace_array *tr = filp->private_data; - - return tracing_nsecs_read(&tr->max_latency, ubuf, cnt, ppos); -} - -static ssize_t -tracing_max_lat_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - struct trace_array *tr = filp->private_data; - - return tracing_nsecs_write(&tr->max_latency, ubuf, cnt, ppos); -} - -#endif - static int open_pipe_on_cpu(struct trace_array *tr, int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { @@ -7212,194 +6579,6 @@ u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_eve return ring_buffer_event_time_stamp(buffer, rbe); } -struct ftrace_buffer_info { - struct trace_iterator iter; - void *spare; - unsigned int spare_cpu; - unsigned int spare_size; - unsigned int read; -}; - -#ifdef CONFIG_TRACER_SNAPSHOT -static int tracing_snapshot_open(struct inode *inode, struct file *file) -{ - struct trace_array *tr = inode->i_private; - struct trace_iterator *iter; - struct seq_file *m; - int ret; - - ret = tracing_check_open_get_tr(tr); - if (ret) - return ret; - - if (file->f_mode & FMODE_READ) { - iter = __tracing_open(inode, file, true); - if (IS_ERR(iter)) - ret = PTR_ERR(iter); - } else { - /* Writes still need the seq_file to hold the private data */ - ret = -ENOMEM; - m = kzalloc_obj(*m); - if (!m) - goto out; - iter = kzalloc_obj(*iter); - if (!iter) { - kfree(m); - goto out; - } - ret = 0; - - iter->tr = tr; - iter->array_buffer = &tr->snapshot_buffer; - iter->cpu_file = tracing_get_cpu(inode); - m->private = iter; - file->private_data = m; - } -out: - if (ret < 0) - trace_array_put(tr); - - return ret; -} - -static void tracing_swap_cpu_buffer(void *tr) -{ - update_max_tr_single((struct trace_array *)tr, current, smp_processor_id()); -} - -static ssize_t -tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, - loff_t *ppos) -{ - struct seq_file *m = filp->private_data; - struct trace_iterator *iter = m->private; - struct trace_array *tr = iter->tr; - unsigned long val; - int ret; - - ret = tracing_update_buffers(tr); - if (ret < 0) - return ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - return ret; - - guard(mutex)(&trace_types_lock); - - if (tracer_uses_snapshot(tr->current_trace)) - return -EBUSY; - - local_irq_disable(); - arch_spin_lock(&tr->max_lock); - if (tr->cond_snapshot) - ret = -EBUSY; - arch_spin_unlock(&tr->max_lock); - local_irq_enable(); - if (ret) - return ret; - - switch (val) { - case 0: - if (iter->cpu_file != RING_BUFFER_ALL_CPUS) - return -EINVAL; - if (tr->allocated_snapshot) - free_snapshot(tr); - break; - case 1: -/* Only allow per-cpu swap if the ring buffer supports it */ -#ifndef CONFIG_RING_BUFFER_ALLOW_SWAP - if (iter->cpu_file != RING_BUFFER_ALL_CPUS) - return -EINVAL; -#endif - if (tr->allocated_snapshot) - ret = resize_buffer_duplicate_size(&tr->snapshot_buffer, - &tr->array_buffer, iter->cpu_file); - - ret = tracing_arm_snapshot_locked(tr); - if (ret) - return ret; - - /* Now, we're going to swap */ - if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { - local_irq_disable(); - update_max_tr(tr, current, smp_processor_id(), NULL); - local_irq_enable(); - } else { - smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer, - (void *)tr, 1); - } - tracing_disarm_snapshot(tr); - break; - default: - if (tr->allocated_snapshot) { - if (iter->cpu_file == RING_BUFFER_ALL_CPUS) - tracing_reset_online_cpus(&tr->snapshot_buffer); - else - tracing_reset_cpu(&tr->snapshot_buffer, iter->cpu_file); - } - break; - } - - if (ret >= 0) { - *ppos += cnt; - ret = cnt; - } - - return ret; -} - -static int tracing_snapshot_release(struct inode *inode, struct file *file) -{ - struct seq_file *m = file->private_data; - int ret; - - ret = tracing_release(inode, file); - - if (file->f_mode & FMODE_READ) - return ret; - - /* If write only, the seq_file is just a stub */ - if (m) - kfree(m->private); - kfree(m); - - return 0; -} - -static int tracing_buffers_open(struct inode *inode, struct file *filp); -static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, - size_t count, loff_t *ppos); -static int tracing_buffers_release(struct inode *inode, struct file *file); -static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, unsigned int flags); - -static int snapshot_raw_open(struct inode *inode, struct file *filp) -{ - struct ftrace_buffer_info *info; - int ret; - - /* The following checks for tracefs lockdown */ - ret = tracing_buffers_open(inode, filp); - if (ret < 0) - return ret; - - info = filp->private_data; - - if (tracer_uses_snapshot(info->iter.trace)) { - tracing_buffers_release(inode, filp); - return -EBUSY; - } - - info->iter.snapshot = true; - info->iter.array_buffer = &info->iter.tr->snapshot_buffer; - - return ret; -} - -#endif /* CONFIG_TRACER_SNAPSHOT */ - - static const struct file_operations tracing_thresh_fops = { .open = tracing_open_generic, .read = tracing_thresh_read, @@ -7407,16 +6586,6 @@ static const struct file_operations tracing_thresh_fops = { .llseek = generic_file_llseek, }; -#ifdef CONFIG_TRACER_MAX_TRACE -static const struct file_operations tracing_max_lat_fops = { - .open = tracing_open_generic_tr, - .read = tracing_max_lat_read, - .write = tracing_max_lat_write, - .llseek = generic_file_llseek, - .release = tracing_release_generic_tr, -}; -#endif - static const struct file_operations set_tracer_fops = { .open = tracing_open_generic_tr, .read = tracing_set_trace_read, @@ -7503,24 +6672,6 @@ static const struct file_operations last_boot_fops = { .release = tracing_seq_release, }; -#ifdef CONFIG_TRACER_SNAPSHOT -static const struct file_operations snapshot_fops = { - .open = tracing_snapshot_open, - .read = seq_read, - .write = tracing_snapshot_write, - .llseek = tracing_lseek, - .release = tracing_snapshot_release, -}; - -static const struct file_operations snapshot_raw_fops = { - .open = snapshot_raw_open, - .read = tracing_buffers_read, - .release = tracing_buffers_release, - .splice_read = tracing_buffers_splice_read, -}; - -#endif /* CONFIG_TRACER_SNAPSHOT */ - /* * trace_min_max_write - Write a u64 value to a trace_min_max_param struct * @filp: The active open file structure @@ -7880,7 +7031,7 @@ static const struct file_operations tracing_err_log_fops = { .release = tracing_err_log_release, }; -static int tracing_buffers_open(struct inode *inode, struct file *filp) +int tracing_buffers_open(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct ftrace_buffer_info *info; @@ -7928,9 +7079,8 @@ tracing_buffers_poll(struct file *filp, poll_table *poll_table) return trace_poll(iter, filp, poll_table); } -static ssize_t -tracing_buffers_read(struct file *filp, char __user *ubuf, - size_t count, loff_t *ppos) +ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; @@ -8031,7 +7181,7 @@ static int tracing_buffers_flush(struct file *file, fl_owner_t id) return 0; } -static int tracing_buffers_release(struct inode *inode, struct file *file) +int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; @@ -8105,10 +7255,9 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) spd->partial[i].private = 0; } -static ssize_t -tracing_buffers_splice_read(struct file *file, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; @@ -8262,44 +7411,6 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned return 0; } -#ifdef CONFIG_TRACER_SNAPSHOT -static int get_snapshot_map(struct trace_array *tr) -{ - int err = 0; - - /* - * Called with mmap_lock held. lockdep would be unhappy if we would now - * take trace_types_lock. Instead use the specific - * snapshot_trigger_lock. - */ - spin_lock(&tr->snapshot_trigger_lock); - - if (tr->snapshot || tr->mapped == UINT_MAX) - err = -EBUSY; - else - tr->mapped++; - - spin_unlock(&tr->snapshot_trigger_lock); - - /* Wait for update_max_tr() to observe iter->tr->mapped */ - if (tr->mapped == 1) - synchronize_rcu(); - - return err; - -} -static void put_snapshot_map(struct trace_array *tr) -{ - spin_lock(&tr->snapshot_trigger_lock); - if (!WARN_ON(!tr->mapped)) - tr->mapped--; - spin_unlock(&tr->snapshot_trigger_lock); -} -#else -static inline int get_snapshot_map(struct trace_array *tr) { return 0; } -static inline void put_snapshot_map(struct trace_array *tr) { } -#endif - /* * This is called when a VMA is duplicated (e.g., on fork()) to increment * the user_mapped counter without remapping pages. @@ -8480,170 +7591,6 @@ static const struct file_operations tracing_dyn_info_fops = { }; #endif /* CONFIG_DYNAMIC_FTRACE */ -#if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) -static void -ftrace_snapshot(unsigned long ip, unsigned long parent_ip, - struct trace_array *tr, struct ftrace_probe_ops *ops, - void *data) -{ - tracing_snapshot_instance(tr); -} - -static void -ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, - struct trace_array *tr, struct ftrace_probe_ops *ops, - void *data) -{ - struct ftrace_func_mapper *mapper = data; - long *count = NULL; - - if (mapper) - count = (long *)ftrace_func_mapper_find_ip(mapper, ip); - - if (count) { - - if (*count <= 0) - return; - - (*count)--; - } - - tracing_snapshot_instance(tr); -} - -static int -ftrace_snapshot_print(struct seq_file *m, unsigned long ip, - struct ftrace_probe_ops *ops, void *data) -{ - struct ftrace_func_mapper *mapper = data; - long *count = NULL; - - seq_printf(m, "%ps:", (void *)ip); - - seq_puts(m, "snapshot"); - - if (mapper) - count = (long *)ftrace_func_mapper_find_ip(mapper, ip); - - if (count) - seq_printf(m, ":count=%ld\n", *count); - else - seq_puts(m, ":unlimited\n"); - - return 0; -} - -static int -ftrace_snapshot_init(struct ftrace_probe_ops *ops, struct trace_array *tr, - unsigned long ip, void *init_data, void **data) -{ - struct ftrace_func_mapper *mapper = *data; - - if (!mapper) { - mapper = allocate_ftrace_func_mapper(); - if (!mapper) - return -ENOMEM; - *data = mapper; - } - - return ftrace_func_mapper_add_ip(mapper, ip, init_data); -} - -static void -ftrace_snapshot_free(struct ftrace_probe_ops *ops, struct trace_array *tr, - unsigned long ip, void *data) -{ - struct ftrace_func_mapper *mapper = data; - - if (!ip) { - if (!mapper) - return; - free_ftrace_func_mapper(mapper, NULL); - return; - } - - ftrace_func_mapper_remove_ip(mapper, ip); -} - -static struct ftrace_probe_ops snapshot_probe_ops = { - .func = ftrace_snapshot, - .print = ftrace_snapshot_print, -}; - -static struct ftrace_probe_ops snapshot_count_probe_ops = { - .func = ftrace_count_snapshot, - .print = ftrace_snapshot_print, - .init = ftrace_snapshot_init, - .free = ftrace_snapshot_free, -}; - -static int -ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, - char *glob, char *cmd, char *param, int enable) -{ - struct ftrace_probe_ops *ops; - void *count = (void *)-1; - char *number; - int ret; - - if (!tr) - return -ENODEV; - - /* hash funcs only work with set_ftrace_filter */ - if (!enable) - return -EINVAL; - - ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; - - if (glob[0] == '!') { - ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); - if (!ret) - tracing_disarm_snapshot(tr); - - return ret; - } - - if (!param) - goto out_reg; - - number = strsep(¶m, ":"); - - if (!strlen(number)) - goto out_reg; - - /* - * We use the callback data field (which is a pointer) - * as our counter. - */ - ret = kstrtoul(number, 0, (unsigned long *)&count); - if (ret) - return ret; - - out_reg: - ret = tracing_arm_snapshot(tr); - if (ret < 0) - return ret; - - ret = register_ftrace_function_probe(glob, tr, ops, count); - if (ret < 0) - tracing_disarm_snapshot(tr); - - return ret < 0 ? ret : 0; -} - -static struct ftrace_func_command ftrace_snapshot_cmd = { - .name = "snapshot", - .func = ftrace_trace_snapshot_callback, -}; - -static __init int register_snapshot_cmd(void) -{ - return register_ftrace_command(&ftrace_snapshot_cmd); -} -#else -static inline __init int register_snapshot_cmd(void) { return 0; } -#endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */ - static struct dentry *tracing_get_dentry(struct trace_array *tr) { /* Top directory uses NULL as the parent */ @@ -9436,8 +8383,7 @@ static void setup_trace_scratch(struct trace_array *tr, memset(tscratch, 0, size); } -static int -allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned long size) +int allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size) { enum ring_buffer_flags rb_flags; struct trace_scratch *tscratch; @@ -9476,8 +8422,8 @@ allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned } /* Allocate the first page for all buffers */ - set_buffer_entries(&tr->array_buffer, - ring_buffer_size(tr->array_buffer.buffer, 0)); + trace_set_buffer_entries(&tr->array_buffer, + ring_buffer_size(tr->array_buffer.buffer, 0)); return 0; } @@ -9500,23 +8446,11 @@ static int allocate_trace_buffers(struct trace_array *tr, unsigned long size) if (ret) return ret; -#ifdef CONFIG_TRACER_SNAPSHOT - /* Fix mapped buffer trace arrays do not have snapshot buffers */ - if (tr->range_addr_start) - return 0; - - ret = allocate_trace_buffer(tr, &tr->snapshot_buffer, - allocate_snapshot ? size : 1); - if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) { + ret = trace_allocate_snapshot(tr, size); + if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) free_trace_buffer(&tr->array_buffer); - return -ENOMEM; - } - tr->allocated_snapshot = allocate_snapshot; - allocate_snapshot = false; -#endif - - return 0; + return ret; } static void free_trace_buffers(struct trace_array *tr) @@ -10638,47 +9572,6 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer, return done; } -#ifdef CONFIG_TRACER_SNAPSHOT -__init static bool tr_needs_alloc_snapshot(const char *name) -{ - char *test; - int len = strlen(name); - bool ret; - - if (!boot_snapshot_index) - return false; - - if (strncmp(name, boot_snapshot_info, len) == 0 && - boot_snapshot_info[len] == '\t') - return true; - - test = kmalloc(strlen(name) + 3, GFP_KERNEL); - if (!test) - return false; - - sprintf(test, "\t%s\t", name); - ret = strstr(boot_snapshot_info, test) == NULL; - kfree(test); - return ret; -} - -__init static void do_allocate_snapshot(const char *name) -{ - if (!tr_needs_alloc_snapshot(name)) - return; - - /* - * When allocate_snapshot is set, the next call to - * allocate_trace_buffers() (called by trace_array_get_by_name()) - * will allocate the snapshot buffer. That will also clear - * this flag. - */ - allocate_snapshot = true; -} -#else -static inline void do_allocate_snapshot(const char *name) { } -#endif - __init static int backup_instance_area(const char *backup, unsigned long *addr, phys_addr_t *size) { @@ -10828,8 +9721,7 @@ __init static void enable_instances(void) } } else { /* Only non mapped buffers have snapshot buffers */ - if (IS_ENABLED(CONFIG_TRACER_SNAPSHOT)) - do_allocate_snapshot(name); + do_allocate_snapshot(name); } tr = trace_array_create_systems(name, NULL, addr, size); @@ -11045,24 +9937,6 @@ struct trace_array *trace_get_global_array(void) } #endif -void __init ftrace_boot_snapshot(void) -{ -#ifdef CONFIG_TRACER_SNAPSHOT - struct trace_array *tr; - - if (!snapshot_at_boot) - return; - - list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (!tr->allocated_snapshot) - continue; - - tracing_snapshot_instance(tr); - trace_array_puts(tr, "** Boot snapshot taken **\n"); - } -#endif -} - void __init early_trace_init(void) { if (tracepoint_printk) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e68f9c2027eb..80fe152af1dd 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -264,6 +264,7 @@ static inline bool still_need_pid_events(int type, struct trace_pid_list *pid_li typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data); +#ifdef CONFIG_TRACER_SNAPSHOT /** * struct cond_snapshot - conditional snapshot data and callback * @@ -306,6 +307,7 @@ struct cond_snapshot { void *cond_data; cond_update_fn_t update; }; +#endif /* CONFIG_TRACER_SNAPSHOT */ /* * struct trace_func_repeats - used to keep track of the consecutive @@ -691,6 +693,7 @@ void tracing_reset_all_online_cpus(void); void tracing_reset_all_online_cpus_unlocked(void); int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); +int tracing_release(struct inode *inode, struct file *file); int tracing_release_generic_tr(struct inode *inode, struct file *file); int tracing_open_file_tr(struct inode *inode, struct file *filp); int tracing_release_file_tr(struct inode *inode, struct file *filp); @@ -700,6 +703,7 @@ void tracer_tracing_on(struct trace_array *tr); void tracer_tracing_off(struct trace_array *tr); void tracer_tracing_disable(struct trace_array *tr); void tracer_tracing_enable(struct trace_array *tr); +int allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size); struct dentry *trace_create_file(const char *name, umode_t mode, struct dentry *parent, @@ -711,8 +715,42 @@ struct dentry *trace_create_cpu_file(const char *name, void *data, long cpu, const struct file_operations *fops); -int tracing_get_cpu(struct inode *inode); +struct trace_iterator *__tracing_open(struct inode *inode, struct file *file, + bool snapshot); +int tracing_buffers_open(struct inode *inode, struct file *filp); +ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos); +int tracing_buffers_release(struct inode *inode, struct file *file); +ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, unsigned int flags); + +ssize_t tracing_nsecs_read(unsigned long *ptr, char __user *ubuf, + size_t cnt, loff_t *ppos); +ssize_t tracing_nsecs_write(unsigned long *ptr, const char __user *ubuf, + size_t cnt, loff_t *ppos); + +void trace_set_buffer_entries(struct array_buffer *buf, unsigned long val); + +/* + * Should be used after trace_array_get(), trace_types_lock + * ensures that i_cdev was already initialized. + */ +static inline int tracing_get_cpu(struct inode *inode) +{ + if (inode->i_cdev) /* See trace_create_cpu_file() */ + return (long)inode->i_cdev - 1; + return RING_BUFFER_ALL_CPUS; +} +void tracing_reset_cpu(struct array_buffer *buf, int cpu); + +struct ftrace_buffer_info { + struct trace_iterator iter; + void *spare; + unsigned int spare_cpu; + unsigned int spare_size; + unsigned int read; +}; /** * tracer_tracing_is_on_cpu - show real state of ring buffer enabled on for a cpu @@ -829,13 +867,13 @@ void update_max_tr_single(struct trace_array *tr, #if defined(CONFIG_TRACER_MAX_TRACE) && defined(CONFIG_FSNOTIFY) # define LATENCY_FS_NOTIFY #endif +#endif /* CONFIG_TRACER_SNAPSHOT */ #ifdef LATENCY_FS_NOTIFY void latency_fsnotify(struct trace_array *tr); #else static inline void latency_fsnotify(struct trace_array *tr) { } #endif -#endif /* CONFIG_TRACER_SNAPSHOT */ #ifdef CONFIG_STACKTRACE void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip); @@ -851,11 +889,15 @@ static inline bool tracer_uses_snapshot(struct tracer *tracer) { return tracer->use_max_tr; } +void trace_create_maxlat_file(struct trace_array *tr, + struct dentry *d_tracer); #else static inline bool tracer_uses_snapshot(struct tracer *tracer) { return false; } +static inline void trace_create_maxlat_file(struct trace_array *tr, + struct dentry *d_tracer) { } #endif void trace_last_func_repeats(struct trace_array *tr, @@ -885,6 +927,8 @@ extern int DYN_FTRACE_TEST_NAME(void); #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 extern int DYN_FTRACE_TEST_NAME2(void); +void __init trace_append_boot_param(char *buf, const char *str, + char sep, int size); extern void trace_set_ring_buffer_expanded(struct trace_array *tr); extern bool tracing_selftest_disabled; @@ -1825,11 +1869,6 @@ extern struct trace_event_file *find_event_file(struct trace_array *tr, const char *system, const char *event); -static inline void *event_file_data(struct file *filp) -{ - return READ_ONCE(file_inode(filp)->i_private); -} - extern struct mutex event_mutex; extern struct list_head ftrace_events; @@ -1850,12 +1889,22 @@ static inline struct trace_event_file *event_file_file(struct file *filp) struct trace_event_file *file; lockdep_assert_held(&event_mutex); - file = READ_ONCE(file_inode(filp)->i_private); + file = file_inode(filp)->i_private; if (!file || file->flags & EVENT_FILE_FL_FREED) return NULL; return file; } +static inline void *event_file_data(struct file *filp) +{ + struct trace_event_file *file; + + lockdep_assert_held(&event_mutex); + file = file_inode(filp)->i_private; + WARN_ON(!file || file->flags & EVENT_FILE_FL_FREED); + return file; +} + extern const struct file_operations event_trigger_fops; extern const struct file_operations event_hist_fops; extern const struct file_operations event_hist_debug_fops; @@ -2158,12 +2207,6 @@ static inline bool event_command_needs_rec(struct event_command *cmd_ops) extern int trace_event_enable_disable(struct trace_event_file *file, int enable, int soft_disable); -extern int tracing_alloc_snapshot(void); -extern void tracing_snapshot_cond(struct trace_array *tr, void *cond_data); -extern int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update); - -extern int tracing_snapshot_cond_disable(struct trace_array *tr); -extern void *tracing_cond_snapshot_data(struct trace_array *tr); extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; @@ -2251,19 +2294,71 @@ static inline void trace_event_update_all(struct trace_eval_map **map, int len) #endif #ifdef CONFIG_TRACER_SNAPSHOT +extern const struct file_operations snapshot_fops; +extern const struct file_operations snapshot_raw_fops; + +/* Used when creating instances */ +int trace_allocate_snapshot(struct trace_array *tr, int size); + +int tracing_alloc_snapshot(void); +void tracing_snapshot_cond(struct trace_array *tr, void *cond_data); +int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update); +int tracing_snapshot_cond_disable(struct trace_array *tr); +void *tracing_cond_snapshot_data(struct trace_array *tr); void tracing_snapshot_instance(struct trace_array *tr); int tracing_alloc_snapshot_instance(struct trace_array *tr); +int tracing_arm_snapshot_locked(struct trace_array *tr); int tracing_arm_snapshot(struct trace_array *tr); void tracing_disarm_snapshot(struct trace_array *tr); -#else +void free_snapshot(struct trace_array *tr); +void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter); +int get_snapshot_map(struct trace_array *tr); +void put_snapshot_map(struct trace_array *tr); +int resize_buffer_duplicate_size(struct array_buffer *trace_buf, + struct array_buffer *size_buf, int cpu_id); +__init void do_allocate_snapshot(const char *name); +# ifdef CONFIG_DYNAMIC_FTRACE +__init int register_snapshot_cmd(void); +# else +static inline int register_snapshot_cmd(void) { return 0; } +# endif +#else /* !CONFIG_TRACER_SNAPSHOT */ +static inline int trace_allocate_snapshot(struct trace_array *tr, int size) { return 0; } static inline void tracing_snapshot_instance(struct trace_array *tr) { } static inline int tracing_alloc_snapshot_instance(struct trace_array *tr) { return 0; } +static inline int tracing_arm_snapshot_locked(struct trace_array *tr) { return -EBUSY; } static inline int tracing_arm_snapshot(struct trace_array *tr) { return 0; } static inline void tracing_disarm_snapshot(struct trace_array *tr) { } -#endif +static inline void free_snapshot(struct trace_array *tr) {} +static inline void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) +{ + WARN_ONCE(1, "Snapshot feature not enabled, but internal conditional snapshot used"); +} +static inline void *tracing_cond_snapshot_data(struct trace_array *tr) +{ + return NULL; +} +static inline int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update) +{ + return -ENODEV; +} +static inline int tracing_snapshot_cond_disable(struct trace_array *tr) +{ + return false; +} +static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) +{ + /* Should never be called */ + WARN_ONCE(1, "Snapshot print function called without snapshot configured"); +} +static inline int get_snapshot_map(struct trace_array *tr) { return 0; } +static inline void put_snapshot_map(struct trace_array *tr) { } +static inline void do_allocate_snapshot(const char *name) { } +static inline int register_snapshot_cmd(void) { return 0; } +#endif /* CONFIG_TRACER_SNAPSHOT */ #ifdef CONFIG_PREEMPT_TRACER void tracer_preempt_on(unsigned long a0, unsigned long a1); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index aa422dc80ae8..c46e623e7e0d 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1721,7 +1721,7 @@ static int t_show_filters(struct seq_file *m, void *v) len = get_call_len(call); - seq_printf(m, "%s:%s%*.s%s\n", call->class->system, + seq_printf(m, "%s:%s%*s%s\n", call->class->system, trace_event_name(call), len, "", filter->filter_string); return 0; @@ -1753,7 +1753,7 @@ static int t_show_triggers(struct seq_file *m, void *v) len = get_call_len(call); list_for_each_entry_rcu(data, &file->triggers, list) { - seq_printf(m, "%s:%s%*.s", call->class->system, + seq_printf(m, "%s:%s%*s", call->class->system, trace_event_name(call), len, ""); data->cmd_ops->print(m, data); @@ -2187,12 +2187,12 @@ static int trace_format_open(struct inode *inode, struct file *file) static ssize_t event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - int id = (long)event_file_data(filp); + /* id is directly in i_private and available for inode's lifetime. */ + int id = (long)file_inode(filp)->i_private; char buf[32]; int len; - if (unlikely(!id)) - return -ENODEV; + WARN_ON(!id); len = sprintf(buf, "%d\n", id); @@ -2250,12 +2250,8 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); file = event_file_file(filp); - if (file) { - if (file->flags & EVENT_FILE_FL_FREED) - err = -ENODEV; - else - err = apply_event_filter(file, buf); - } + if (file) + err = apply_event_filter(file, buf); mutex_unlock(&event_mutex); kfree(buf); @@ -3687,20 +3683,27 @@ static struct boot_triggers { } bootup_triggers[MAX_BOOT_TRIGGERS]; static char bootup_trigger_buf[COMMAND_LINE_SIZE]; +static int boot_trigger_buf_len; static int nr_boot_triggers; static __init int setup_trace_triggers(char *str) { char *trigger; char *buf; + int len = boot_trigger_buf_len; int i; - strscpy(bootup_trigger_buf, str, COMMAND_LINE_SIZE); + if (len >= COMMAND_LINE_SIZE) + return 1; + + strscpy(bootup_trigger_buf + len, str, COMMAND_LINE_SIZE - len); trace_set_ring_buffer_expanded(NULL); disable_tracing_selftest("running event triggers"); - buf = bootup_trigger_buf; - for (i = 0; i < MAX_BOOT_TRIGGERS; i++) { + buf = bootup_trigger_buf + len; + boot_trigger_buf_len += strlen(buf) + 1; + + for (i = nr_boot_triggers; i < MAX_BOOT_TRIGGERS; i++) { trigger = strsep(&buf, ","); if (!trigger) break; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 73ea180cad55..0dbbf6cca9bc 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1361,12 +1361,17 @@ static const char *hist_field_name(struct hist_field *field, field->flags & HIST_FIELD_FL_VAR_REF) { if (field->system) { static char full_name[MAX_FILTER_STR_VAL]; + static char *fmt; + int len; + + fmt = field->flags & HIST_FIELD_FL_VAR_REF ? "%s.%s.$%s" : "%s.%s.%s"; + + len = snprintf(full_name, sizeof(full_name), fmt, + field->system, field->event_name, + field->name); + if (len >= sizeof(full_name)) + return NULL; - strcat(full_name, field->system); - strcat(full_name, "."); - strcat(full_name, field->event_name); - strcat(full_name, "."); - strcat(full_name, field->name); field_name = full_name; } else field_name = field->name; @@ -1740,9 +1745,10 @@ static const char *get_hist_field_flags(struct hist_field *hist_field) static void expr_field_str(struct hist_field *field, char *expr) { - if (field->flags & HIST_FIELD_FL_VAR_REF) - strcat(expr, "$"); - else if (field->flags & HIST_FIELD_FL_CONST) { + if (field->flags & HIST_FIELD_FL_VAR_REF) { + if (!field->system) + strcat(expr, "$"); + } else if (field->flags & HIST_FIELD_FL_CONST) { char str[HIST_CONST_DIGITS_MAX]; snprintf(str, HIST_CONST_DIGITS_MAX, "%llu", field->constant); @@ -5836,8 +5842,6 @@ static int event_hist_open(struct inode *inode, struct file *file) hist_file->file = file; hist_file->last_act = get_hist_hit_count(event_file); - /* Clear private_data to avoid warning in single_open() */ - file->private_data = NULL; ret = single_open(file, hist_show, hist_file); if (ret) { kfree(hist_file); @@ -6126,8 +6130,6 @@ static int event_hist_debug_open(struct inode *inode, struct file *file) if (ret) return ret; - /* Clear private_data to avoid warning in single_open() */ - file->private_data = NULL; ret = single_open(file, hist_debug_show, file); if (ret) tracing_release_file_tr(inode, file); @@ -6158,7 +6160,8 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field) else if (field_name) { if (hist_field->flags & HIST_FIELD_FL_VAR_REF || hist_field->flags & HIST_FIELD_FL_ALIAS) - seq_putc(m, '$'); + if (!hist_field->system) + seq_putc(m, '$'); seq_printf(m, "%s", field_name); } else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP) seq_puts(m, "common_timestamp"); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 058724c41c46..a8420e6abb56 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -31,7 +31,8 @@ static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata; static int __init set_kprobe_boot_events(char *str) { - strscpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE); + trace_append_boot_param(kprobe_boot_events_buf, str, ';', + COMMAND_LINE_SIZE); disable_tracing_selftest("running kprobe events"); return 1; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 96e2d22b4364..a5ad76175d10 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -723,12 +723,13 @@ void print_function_args(struct trace_seq *s, unsigned long *args, { const struct btf_param *param; const struct btf_type *t; + const struct btf_enum *enums; const char *param_name; char name[KSYM_NAME_LEN]; unsigned long arg; struct btf *btf; s32 tid, nr = 0; - int a, p, x; + int a, p, x, i; u16 encode; trace_seq_printf(s, "("); @@ -782,6 +783,15 @@ void print_function_args(struct trace_seq *s, unsigned long *args, break; case BTF_KIND_ENUM: trace_seq_printf(s, "%ld", arg); + enums = btf_enum(t); + for (i = 0; i < btf_vlen(t); i++) { + if (arg == enums[i].val) { + trace_seq_printf(s, " [%s]", + btf_name_by_offset(btf, + enums[i].name_off)); + break; + } + } break; default: /* This does not handle complex arguments */ diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 5ea5e0d76f00..3ea17af60169 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -197,6 +197,7 @@ struct notifier_block module_trace_bprintk_format_nb = { .notifier_call = module_trace_bprintk_format_notify, }; +__printf(2, 3) int __trace_bprintk(unsigned long ip, const char *fmt, ...) { int ret; diff --git a/kernel/trace/trace_snapshot.c b/kernel/trace/trace_snapshot.c new file mode 100644 index 000000000000..07b43c9863a2 --- /dev/null +++ b/kernel/trace/trace_snapshot.c @@ -0,0 +1,1066 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +#include /* COMMAND_LINE_SIZE */ + +#include "trace.h" + +/* Used if snapshot allocated at boot */ +static bool allocate_snapshot; +static bool snapshot_at_boot; + +static char boot_snapshot_info[COMMAND_LINE_SIZE] __initdata; +static int boot_snapshot_index; + +static int __init boot_alloc_snapshot(char *str) +{ + char *slot = boot_snapshot_info + boot_snapshot_index; + int left = sizeof(boot_snapshot_info) - boot_snapshot_index; + int ret; + + if (str[0] == '=') { + str++; + if (strlen(str) >= left) + return -1; + + ret = snprintf(slot, left, "%s\t", str); + boot_snapshot_index += ret; + } else { + allocate_snapshot = true; + /* We also need the main ring buffer expanded */ + trace_set_ring_buffer_expanded(NULL); + } + return 1; +} +__setup("alloc_snapshot", boot_alloc_snapshot); + + +static int __init boot_snapshot(char *str) +{ + snapshot_at_boot = true; + boot_alloc_snapshot(str); + return 1; +} +__setup("ftrace_boot_snapshot", boot_snapshot); +static void tracing_snapshot_instance_cond(struct trace_array *tr, + void *cond_data) +{ + unsigned long flags; + + if (in_nmi()) { + trace_array_puts(tr, "*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); + trace_array_puts(tr, "*** snapshot is being ignored ***\n"); + return; + } + + if (!tr->allocated_snapshot) { + trace_array_puts(tr, "*** SNAPSHOT NOT ALLOCATED ***\n"); + trace_array_puts(tr, "*** stopping trace here! ***\n"); + tracer_tracing_off(tr); + return; + } + + if (tr->mapped) { + trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); + return; + } + + /* Note, snapshot can not be used when the tracer uses it */ + if (tracer_uses_snapshot(tr->current_trace)) { + trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); + return; + } + + local_irq_save(flags); + update_max_tr(tr, current, smp_processor_id(), cond_data); + local_irq_restore(flags); +} + +void tracing_snapshot_instance(struct trace_array *tr) +{ + tracing_snapshot_instance_cond(tr, NULL); +} + +/** + * tracing_snapshot_cond - conditionally take a snapshot of the current buffer. + * @tr: The tracing instance to snapshot + * @cond_data: The data to be tested conditionally, and possibly saved + * + * This is the same as tracing_snapshot() except that the snapshot is + * conditional - the snapshot will only happen if the + * cond_snapshot.update() implementation receiving the cond_data + * returns true, which means that the trace array's cond_snapshot + * update() operation used the cond_data to determine whether the + * snapshot should be taken, and if it was, presumably saved it along + * with the snapshot. + */ +void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) +{ + tracing_snapshot_instance_cond(tr, cond_data); +} +EXPORT_SYMBOL_GPL(tracing_snapshot_cond); + +/** + * tracing_cond_snapshot_data - get the user data associated with a snapshot + * @tr: The tracing instance + * + * When the user enables a conditional snapshot using + * tracing_snapshot_cond_enable(), the user-defined cond_data is saved + * with the snapshot. This accessor is used to retrieve it. + * + * Should not be called from cond_snapshot.update(), since it takes + * the tr->max_lock lock, which the code calling + * cond_snapshot.update() has already done. + * + * Returns the cond_data associated with the trace array's snapshot. + */ +void *tracing_cond_snapshot_data(struct trace_array *tr) +{ + void *cond_data = NULL; + + local_irq_disable(); + arch_spin_lock(&tr->max_lock); + + if (tr->cond_snapshot) + cond_data = tr->cond_snapshot->cond_data; + + arch_spin_unlock(&tr->max_lock); + local_irq_enable(); + + return cond_data; +} +EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data); + +/* resize @tr's buffer to the size of @size_tr's entries */ +int resize_buffer_duplicate_size(struct array_buffer *trace_buf, + struct array_buffer *size_buf, int cpu_id) +{ + int cpu, ret = 0; + + if (cpu_id == RING_BUFFER_ALL_CPUS) { + for_each_tracing_cpu(cpu) { + ret = ring_buffer_resize(trace_buf->buffer, + per_cpu_ptr(size_buf->data, cpu)->entries, cpu); + if (ret < 0) + break; + per_cpu_ptr(trace_buf->data, cpu)->entries = + per_cpu_ptr(size_buf->data, cpu)->entries; + } + } else { + ret = ring_buffer_resize(trace_buf->buffer, + per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id); + if (ret == 0) + per_cpu_ptr(trace_buf->data, cpu_id)->entries = + per_cpu_ptr(size_buf->data, cpu_id)->entries; + } + + return ret; +} + +int tracing_alloc_snapshot_instance(struct trace_array *tr) +{ + int order; + int ret; + + if (!tr->allocated_snapshot) { + + /* Make the snapshot buffer have the same order as main buffer */ + order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + ret = ring_buffer_subbuf_order_set(tr->snapshot_buffer.buffer, order); + if (ret < 0) + return ret; + + /* allocate spare buffer */ + ret = resize_buffer_duplicate_size(&tr->snapshot_buffer, + &tr->array_buffer, RING_BUFFER_ALL_CPUS); + if (ret < 0) + return ret; + + tr->allocated_snapshot = true; + } + + return 0; +} + +void free_snapshot(struct trace_array *tr) +{ + /* + * We don't free the ring buffer. instead, resize it because + * The max_tr ring buffer has some state (e.g. ring->clock) and + * we want preserve it. + */ + ring_buffer_subbuf_order_set(tr->snapshot_buffer.buffer, 0); + ring_buffer_resize(tr->snapshot_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); + trace_set_buffer_entries(&tr->snapshot_buffer, 1); + tracing_reset_online_cpus(&tr->snapshot_buffer); + tr->allocated_snapshot = false; +} + +int tracing_arm_snapshot_locked(struct trace_array *tr) +{ + int ret; + + lockdep_assert_held(&trace_types_lock); + + spin_lock(&tr->snapshot_trigger_lock); + if (tr->snapshot == UINT_MAX || tr->mapped) { + spin_unlock(&tr->snapshot_trigger_lock); + return -EBUSY; + } + + tr->snapshot++; + spin_unlock(&tr->snapshot_trigger_lock); + + ret = tracing_alloc_snapshot_instance(tr); + if (ret) { + spin_lock(&tr->snapshot_trigger_lock); + tr->snapshot--; + spin_unlock(&tr->snapshot_trigger_lock); + } + + return ret; +} + +int tracing_arm_snapshot(struct trace_array *tr) +{ + guard(mutex)(&trace_types_lock); + return tracing_arm_snapshot_locked(tr); +} + +void tracing_disarm_snapshot(struct trace_array *tr) +{ + spin_lock(&tr->snapshot_trigger_lock); + if (!WARN_ON(!tr->snapshot)) + tr->snapshot--; + spin_unlock(&tr->snapshot_trigger_lock); +} + +/** + * tracing_snapshot_alloc - allocate and take a snapshot of the current buffer. + * + * This is similar to tracing_snapshot(), but it will allocate the + * snapshot buffer if it isn't already allocated. Use this only + * where it is safe to sleep, as the allocation may sleep. + * + * This causes a swap between the snapshot buffer and the current live + * tracing buffer. You can use this to take snapshots of the live + * trace when some condition is triggered, but continue to trace. + */ +void tracing_snapshot_alloc(void) +{ + int ret; + + ret = tracing_alloc_snapshot(); + if (ret < 0) + return; + + tracing_snapshot(); +} +EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); + +/** + * tracing_snapshot_cond_enable - enable conditional snapshot for an instance + * @tr: The tracing instance + * @cond_data: User data to associate with the snapshot + * @update: Implementation of the cond_snapshot update function + * + * Check whether the conditional snapshot for the given instance has + * already been enabled, or if the current tracer is already using a + * snapshot; if so, return -EBUSY, else create a cond_snapshot and + * save the cond_data and update function inside. + * + * Returns 0 if successful, error otherwise. + */ +int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, + cond_update_fn_t update) +{ + struct cond_snapshot *cond_snapshot __free(kfree) = + kzalloc_obj(*cond_snapshot); + int ret; + + if (!cond_snapshot) + return -ENOMEM; + + cond_snapshot->cond_data = cond_data; + cond_snapshot->update = update; + + guard(mutex)(&trace_types_lock); + + if (tracer_uses_snapshot(tr->current_trace)) + return -EBUSY; + + /* + * The cond_snapshot can only change to NULL without the + * trace_types_lock. We don't care if we race with it going + * to NULL, but we want to make sure that it's not set to + * something other than NULL when we get here, which we can + * do safely with only holding the trace_types_lock and not + * having to take the max_lock. + */ + if (tr->cond_snapshot) + return -EBUSY; + + ret = tracing_arm_snapshot_locked(tr); + if (ret) + return ret; + + local_irq_disable(); + arch_spin_lock(&tr->max_lock); + tr->cond_snapshot = no_free_ptr(cond_snapshot); + arch_spin_unlock(&tr->max_lock); + local_irq_enable(); + + return 0; +} +EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); + +/** + * tracing_snapshot_cond_disable - disable conditional snapshot for an instance + * @tr: The tracing instance + * + * Check whether the conditional snapshot for the given instance is + * enabled; if so, free the cond_snapshot associated with it, + * otherwise return -EINVAL. + * + * Returns 0 if successful, error otherwise. + */ +int tracing_snapshot_cond_disable(struct trace_array *tr) +{ + int ret = 0; + + local_irq_disable(); + arch_spin_lock(&tr->max_lock); + + if (!tr->cond_snapshot) + ret = -EINVAL; + else { + kfree(tr->cond_snapshot); + tr->cond_snapshot = NULL; + } + + arch_spin_unlock(&tr->max_lock); + local_irq_enable(); + + tracing_disarm_snapshot(tr); + + return ret; +} +EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); + +#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef LATENCY_FS_NOTIFY +static struct workqueue_struct *fsnotify_wq; + +static void latency_fsnotify_workfn(struct work_struct *work) +{ + struct trace_array *tr = container_of(work, struct trace_array, + fsnotify_work); + fsnotify_inode(tr->d_max_latency->d_inode, FS_MODIFY); +} + +static void latency_fsnotify_workfn_irq(struct irq_work *iwork) +{ + struct trace_array *tr = container_of(iwork, struct trace_array, + fsnotify_irqwork); + queue_work(fsnotify_wq, &tr->fsnotify_work); +} + +__init static int latency_fsnotify_init(void) +{ + fsnotify_wq = alloc_workqueue("tr_max_lat_wq", + WQ_UNBOUND | WQ_HIGHPRI, 0); + if (!fsnotify_wq) { + pr_err("Unable to allocate tr_max_lat_wq\n"); + return -ENOMEM; + } + return 0; +} + +late_initcall_sync(latency_fsnotify_init); + +void latency_fsnotify(struct trace_array *tr) +{ + if (!fsnotify_wq) + return; + /* + * We cannot call queue_work(&tr->fsnotify_work) from here because it's + * possible that we are called from __schedule() or do_idle(), which + * could cause a deadlock. + */ + irq_work_queue(&tr->fsnotify_irqwork); +} +#endif /* LATENCY_FS_NOTIFY */ + +static const struct file_operations tracing_max_lat_fops; + +void trace_create_maxlat_file(struct trace_array *tr, + struct dentry *d_tracer) +{ +#ifdef LATENCY_FS_NOTIFY + INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn); + init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); +#endif + tr->d_max_latency = trace_create_file("tracing_max_latency", + TRACE_MODE_WRITE, + d_tracer, tr, + &tracing_max_lat_fops); +} + +/* + * Copy the new maximum trace into the separate maximum-trace + * structure. (this way the maximum trace is permanently saved, + * for later retrieval via /sys/kernel/tracing/tracing_max_latency) + */ +static void +__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct array_buffer *trace_buf = &tr->array_buffer; + struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); + struct array_buffer *max_buf = &tr->snapshot_buffer; + struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); + + max_buf->cpu = cpu; + max_buf->time_start = data->preempt_timestamp; + + max_data->saved_latency = tr->max_latency; + max_data->critical_start = data->critical_start; + max_data->critical_end = data->critical_end; + + strscpy(max_data->comm, tsk->comm); + max_data->pid = tsk->pid; + /* + * If tsk == current, then use current_uid(), as that does not use + * RCU. The irq tracer can be called out of RCU scope. + */ + if (tsk == current) + max_data->uid = current_uid(); + else + max_data->uid = task_uid(tsk); + + max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; + max_data->policy = tsk->policy; + max_data->rt_priority = tsk->rt_priority; + + /* record this tasks comm */ + tracing_record_cmdline(tsk); + latency_fsnotify(tr); +} +#else +static inline void __update_max_tr(struct trace_array *tr, + struct task_struct *tsk, int cpu) { } +#endif /* CONFIG_TRACER_MAX_TRACE */ + +/** + * update_max_tr - snapshot all trace buffers from global_trace to max_tr + * @tr: tracer + * @tsk: the task with the latency + * @cpu: The cpu that initiated the trace. + * @cond_data: User data associated with a conditional snapshot + * + * Flip the buffers between the @tr and the max_tr and record information + * about which task was the cause of this latency. + */ +void +update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, + void *cond_data) +{ + if (tr->stop_count) + return; + + WARN_ON_ONCE(!irqs_disabled()); + + if (!tr->allocated_snapshot) { + /* Only the nop tracer should hit this when disabling */ + WARN_ON_ONCE(tr->current_trace != &nop_trace); + return; + } + + arch_spin_lock(&tr->max_lock); + + /* Inherit the recordable setting from array_buffer */ + if (ring_buffer_record_is_set_on(tr->array_buffer.buffer)) + ring_buffer_record_on(tr->snapshot_buffer.buffer); + else + ring_buffer_record_off(tr->snapshot_buffer.buffer); + + if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) { + arch_spin_unlock(&tr->max_lock); + return; + } + + swap(tr->array_buffer.buffer, tr->snapshot_buffer.buffer); + + __update_max_tr(tr, tsk, cpu); + + arch_spin_unlock(&tr->max_lock); + + /* Any waiters on the old snapshot buffer need to wake up */ + ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS); +} + +/** + * update_max_tr_single - only copy one trace over, and reset the rest + * @tr: tracer + * @tsk: task with the latency + * @cpu: the cpu of the buffer to copy. + * + * Flip the trace of a single CPU buffer between the @tr and the max_tr. + */ +void +update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + int ret; + + if (tr->stop_count) + return; + + WARN_ON_ONCE(!irqs_disabled()); + if (!tr->allocated_snapshot) { + /* Only the nop tracer should hit this when disabling */ + WARN_ON_ONCE(tr->current_trace != &nop_trace); + return; + } + + arch_spin_lock(&tr->max_lock); + + ret = ring_buffer_swap_cpu(tr->snapshot_buffer.buffer, tr->array_buffer.buffer, cpu); + + if (ret == -EBUSY) { + /* + * We failed to swap the buffer due to a commit taking + * place on this CPU. We fail to record, but we reset + * the max trace buffer (no one writes directly to it) + * and flag that it failed. + * Another reason is resize is in progress. + */ + trace_array_printk_buf(tr->snapshot_buffer.buffer, _THIS_IP_, + "Failed to swap buffers due to commit or resize in progress\n"); + } + + WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); + + __update_max_tr(tr, tsk, cpu); + arch_spin_unlock(&tr->max_lock); +} + +static void show_snapshot_main_help(struct seq_file *m) +{ + seq_puts(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n" + "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" + "# Takes a snapshot of the main buffer.\n" + "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free)\n" + "# (Doesn't have to be '2' works with any number that\n" + "# is not a '0' or '1')\n"); +} + +static void show_snapshot_percpu_help(struct seq_file *m) +{ + seq_puts(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n"); +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP + seq_puts(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" + "# Takes a snapshot of the main buffer for this cpu.\n"); +#else + seq_puts(m, "# echo 1 > snapshot : Not supported with this kernel.\n" + "# Must use main snapshot file to allocate.\n"); +#endif + seq_puts(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n" + "# (Doesn't have to be '2' works with any number that\n" + "# is not a '0' or '1')\n"); +} + +void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) +{ + if (iter->tr->allocated_snapshot) + seq_puts(m, "#\n# * Snapshot is allocated *\n#\n"); + else + seq_puts(m, "#\n# * Snapshot is freed *\n#\n"); + + seq_puts(m, "# Snapshot commands:\n"); + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + show_snapshot_main_help(m); + else + show_snapshot_percpu_help(m); +} + +static int tracing_snapshot_open(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + struct trace_iterator *iter; + struct seq_file *m; + int ret; + + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; + + if (file->f_mode & FMODE_READ) { + iter = __tracing_open(inode, file, true); + if (IS_ERR(iter)) + ret = PTR_ERR(iter); + } else { + /* Writes still need the seq_file to hold the private data */ + ret = -ENOMEM; + m = kzalloc_obj(*m); + if (!m) + goto out; + iter = kzalloc_obj(*iter); + if (!iter) { + kfree(m); + goto out; + } + ret = 0; + + iter->tr = tr; + iter->array_buffer = &tr->snapshot_buffer; + iter->cpu_file = tracing_get_cpu(inode); + m->private = iter; + file->private_data = m; + } +out: + if (ret < 0) + trace_array_put(tr); + + return ret; +} + +static void tracing_swap_cpu_buffer(void *tr) +{ + update_max_tr_single((struct trace_array *)tr, current, smp_processor_id()); +} + +static ssize_t +tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct seq_file *m = filp->private_data; + struct trace_iterator *iter = m->private; + struct trace_array *tr = iter->tr; + unsigned long val; + int ret; + + ret = tracing_update_buffers(tr); + if (ret < 0) + return ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + guard(mutex)(&trace_types_lock); + + if (tracer_uses_snapshot(tr->current_trace)) + return -EBUSY; + + local_irq_disable(); + arch_spin_lock(&tr->max_lock); + if (tr->cond_snapshot) + ret = -EBUSY; + arch_spin_unlock(&tr->max_lock); + local_irq_enable(); + if (ret) + return ret; + + switch (val) { + case 0: + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) + return -EINVAL; + if (tr->allocated_snapshot) + free_snapshot(tr); + break; + case 1: +/* Only allow per-cpu swap if the ring buffer supports it */ +#ifndef CONFIG_RING_BUFFER_ALLOW_SWAP + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) + return -EINVAL; +#endif + if (tr->allocated_snapshot) + ret = resize_buffer_duplicate_size(&tr->snapshot_buffer, + &tr->array_buffer, iter->cpu_file); + + ret = tracing_arm_snapshot_locked(tr); + if (ret) + return ret; + + /* Now, we're going to swap */ + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { + local_irq_disable(); + update_max_tr(tr, current, smp_processor_id(), NULL); + local_irq_enable(); + } else { + smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer, + (void *)tr, 1); + } + tracing_disarm_snapshot(tr); + break; + default: + if (tr->allocated_snapshot) { + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + tracing_reset_online_cpus(&tr->snapshot_buffer); + else + tracing_reset_cpu(&tr->snapshot_buffer, iter->cpu_file); + } + break; + } + + if (ret >= 0) { + *ppos += cnt; + ret = cnt; + } + + return ret; +} + +static int tracing_snapshot_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + int ret; + + ret = tracing_release(inode, file); + + if (file->f_mode & FMODE_READ) + return ret; + + /* If write only, the seq_file is just a stub */ + if (m) + kfree(m->private); + kfree(m); + + return 0; +} + +static int snapshot_raw_open(struct inode *inode, struct file *filp) +{ + struct ftrace_buffer_info *info; + int ret; + + /* The following checks for tracefs lockdown */ + ret = tracing_buffers_open(inode, filp); + if (ret < 0) + return ret; + + info = filp->private_data; + + if (tracer_uses_snapshot(info->iter.trace)) { + tracing_buffers_release(inode, filp); + return -EBUSY; + } + + info->iter.snapshot = true; + info->iter.array_buffer = &info->iter.tr->snapshot_buffer; + + return ret; +} + +const struct file_operations snapshot_fops = { + .open = tracing_snapshot_open, + .read = seq_read, + .write = tracing_snapshot_write, + .llseek = tracing_lseek, + .release = tracing_snapshot_release, +}; + +const struct file_operations snapshot_raw_fops = { + .open = snapshot_raw_open, + .read = tracing_buffers_read, + .release = tracing_buffers_release, + .splice_read = tracing_buffers_splice_read, +}; + +#ifdef CONFIG_TRACER_MAX_TRACE +static ssize_t +tracing_max_lat_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + + return tracing_nsecs_read(&tr->max_latency, ubuf, cnt, ppos); +} + +static ssize_t +tracing_max_lat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + + return tracing_nsecs_write(&tr->max_latency, ubuf, cnt, ppos); +} + +static const struct file_operations tracing_max_lat_fops = { + .open = tracing_open_generic_tr, + .read = tracing_max_lat_read, + .write = tracing_max_lat_write, + .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, +}; +#endif /* CONFIG_TRACER_MAX_TRACE */ + +int get_snapshot_map(struct trace_array *tr) +{ + int err = 0; + + /* + * Called with mmap_lock held. lockdep would be unhappy if we would now + * take trace_types_lock. Instead use the specific + * snapshot_trigger_lock. + */ + spin_lock(&tr->snapshot_trigger_lock); + + if (tr->snapshot || tr->mapped == UINT_MAX) + err = -EBUSY; + else + tr->mapped++; + + spin_unlock(&tr->snapshot_trigger_lock); + + /* Wait for update_max_tr() to observe iter->tr->mapped */ + if (tr->mapped == 1) + synchronize_rcu(); + + return err; + +} + +void put_snapshot_map(struct trace_array *tr) +{ + spin_lock(&tr->snapshot_trigger_lock); + if (!WARN_ON(!tr->mapped)) + tr->mapped--; + spin_unlock(&tr->snapshot_trigger_lock); +} + +#ifdef CONFIG_DYNAMIC_FTRACE +static void +ftrace_snapshot(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) +{ + tracing_snapshot_instance(tr); +} + +static void +ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) +{ + struct ftrace_func_mapper *mapper = data; + long *count = NULL; + + if (mapper) + count = (long *)ftrace_func_mapper_find_ip(mapper, ip); + + if (count) { + + if (*count <= 0) + return; + + (*count)--; + } + + tracing_snapshot_instance(tr); +} + +static int +ftrace_snapshot_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + struct ftrace_func_mapper *mapper = data; + long *count = NULL; + + seq_printf(m, "%ps:", (void *)ip); + + seq_puts(m, "snapshot"); + + if (mapper) + count = (long *)ftrace_func_mapper_find_ip(mapper, ip); + + if (count) + seq_printf(m, ":count=%ld\n", *count); + else + seq_puts(m, ":unlimited\n"); + + return 0; +} + +static int +ftrace_snapshot_init(struct ftrace_probe_ops *ops, struct trace_array *tr, + unsigned long ip, void *init_data, void **data) +{ + struct ftrace_func_mapper *mapper = *data; + + if (!mapper) { + mapper = allocate_ftrace_func_mapper(); + if (!mapper) + return -ENOMEM; + *data = mapper; + } + + return ftrace_func_mapper_add_ip(mapper, ip, init_data); +} + +static void +ftrace_snapshot_free(struct ftrace_probe_ops *ops, struct trace_array *tr, + unsigned long ip, void *data) +{ + struct ftrace_func_mapper *mapper = data; + + if (!ip) { + if (!mapper) + return; + free_ftrace_func_mapper(mapper, NULL); + return; + } + + ftrace_func_mapper_remove_ip(mapper, ip); +} + +static struct ftrace_probe_ops snapshot_probe_ops = { + .func = ftrace_snapshot, + .print = ftrace_snapshot_print, +}; + +static struct ftrace_probe_ops snapshot_count_probe_ops = { + .func = ftrace_count_snapshot, + .print = ftrace_snapshot_print, + .init = ftrace_snapshot_init, + .free = ftrace_snapshot_free, +}; + +static int +ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + void *count = (void *)-1; + char *number; + int ret; + + if (!tr) + return -ENODEV; + + /* hash funcs only work with set_ftrace_filter */ + if (!enable) + return -EINVAL; + + ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; + + if (glob[0] == '!') { + ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); + if (!ret) + tracing_disarm_snapshot(tr); + + return ret; + } + + if (!param) + goto out_reg; + + number = strsep(¶m, ":"); + + if (!strlen(number)) + goto out_reg; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, (unsigned long *)&count); + if (ret) + return ret; + + out_reg: + ret = tracing_arm_snapshot(tr); + if (ret < 0) + return ret; + + ret = register_ftrace_function_probe(glob, tr, ops, count); + if (ret < 0) + tracing_disarm_snapshot(tr); + + return ret < 0 ? ret : 0; +} + +static struct ftrace_func_command ftrace_snapshot_cmd = { + .name = "snapshot", + .func = ftrace_trace_snapshot_callback, +}; + +__init int register_snapshot_cmd(void) +{ + return register_ftrace_command(&ftrace_snapshot_cmd); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +int trace_allocate_snapshot(struct trace_array *tr, int size) +{ + int ret; + + /* Fix mapped buffer trace arrays do not have snapshot buffers */ + if (tr->range_addr_start) + return 0; + + /* allocate_snapshot can only be true during system boot */ + ret = allocate_trace_buffer(tr, &tr->snapshot_buffer, + allocate_snapshot ? size : 1); + if (ret < 0) + return -ENOMEM; + + tr->allocated_snapshot = allocate_snapshot; + + allocate_snapshot = false; + return 0; +} + +__init static bool tr_needs_alloc_snapshot(const char *name) +{ + char *test; + int len = strlen(name); + bool ret; + + if (!boot_snapshot_index) + return false; + + if (strncmp(name, boot_snapshot_info, len) == 0 && + boot_snapshot_info[len] == '\t') + return true; + + test = kmalloc(strlen(name) + 3, GFP_KERNEL); + if (!test) + return false; + + sprintf(test, "\t%s\t", name); + ret = strstr(boot_snapshot_info, test) == NULL; + kfree(test); + return ret; +} + +__init void do_allocate_snapshot(const char *name) +{ + if (!tr_needs_alloc_snapshot(name)) + return; + + /* + * When allocate_snapshot is set, the next call to + * allocate_trace_buffers() (called by trace_array_get_by_name()) + * will allocate the snapshot buffer. That will also clear + * this flag. + */ + allocate_snapshot = true; +} + +void __init ftrace_boot_snapshot(void) +{ + struct trace_array *tr; + + if (!snapshot_at_boot) + return; + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (!tr->allocated_snapshot) + continue; + + tracing_snapshot_instance(tr); + trace_array_puts(tr, "** Boot snapshot taken **\n"); + } +} diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 91905aa19294..dffef52a807b 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -300,6 +300,8 @@ static int tracepoint_add_func(struct tracepoint *tp, lockdep_is_held(&tracepoints_mutex)); old = func_add(&tp_funcs, func, prio); if (IS_ERR(old)) { + if (tp->ext && tp->ext->unregfunc && !static_key_enabled(&tp->key)) + tp->ext->unregfunc(); WARN_ON_ONCE(warn && PTR_ERR(old) != -ENOMEM); return PTR_ERR(old); } diff --git a/mm/damon/core.c b/mm/damon/core.c index db6c67e52d2b..7f04fc3f8c8c 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -2510,7 +2510,7 @@ static void damos_trace_stat(struct damon_ctx *c, struct damos *s) break; sidx++; } - trace_damos_stat_after_apply_interval(cidx, sidx, &s->stat); + trace_call__damos_stat_after_apply_interval(cidx, sidx, &s->stat); } static void kdamond_apply_schemes(struct damon_ctx *c) diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-fully-qualified-var-ref.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-fully-qualified-var-ref.tc new file mode 100644 index 000000000000..8d12cdd06f1d --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-fully-qualified-var-ref.tc @@ -0,0 +1,34 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test fully-qualified variable reference support +# requires: set_event synthetic_events events/sched/sched_process_fork/hist ping:program + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test fully-qualified variable reference support" + +echo 'wakeup_latency u64 lat; pid_t pid; int prio; char comm[16]' > synthetic_events +echo 'hist:keys=comm:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_waking/trigger +echo 'hist:keys=comm:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger +echo 'hist:keys=next_comm:wakeup_lat=common_timestamp.usecs-sched.sched_wakeup.$ts0:onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,next_pid,sched.sched_waking.prio,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger +echo 'hist:keys=pid,prio,comm:vals=lat:sort=pid,prio' > events/synthetic/wakeup_latency/trigger + +ping $LOCALHOST -c 3 +if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then + fail "Failed to create inter-event histogram" +fi + +if ! grep -q "synthetic_prio=prio" events/sched/sched_waking/hist; then + fail "Failed to create histogram with fully-qualified variable reference" +fi + +echo '!hist:keys=next_comm:wakeup_lat=common_timestamp.usecs-sched.sched_wakeup.$ts0:onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,next_pid,sched.sched_waking.prio,next_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger + +if grep -q "synthetic_prio=prio" events/sched/sched_waking/hist; then + fail "Failed to remove histogram with fully-qualified variable reference" +fi + +exit 0