diff options
Diffstat (limited to 'kernel/trace/trace.c')
| -rw-r--r-- | kernel/trace/trace.c | 7562 |
1 files changed, 5313 insertions, 2249 deletions
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c521b7347482..e575956ef9b5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -13,19 +13,21 @@ * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/ring_buffer.h> -#include <generated/utsrelease.h> +#include <linux/utsname.h> #include <linux/stacktrace.h> #include <linux/writeback.h> #include <linux/kallsyms.h> +#include <linux/security.h> #include <linux/seq_file.h> -#include <linux/notifier.h> #include <linux/irqflags.h> +#include <linux/syscalls.h> #include <linux/debugfs.h> #include <linux/tracefs.h> #include <linux/pagemap.h> #include <linux/hardirq.h> #include <linux/linkage.h> #include <linux/uaccess.h> +#include <linux/cleanup.h> #include <linux/vmalloc.h> #include <linux/ftrace.h> #include <linux/module.h> @@ -38,22 +40,26 @@ #include <linux/slab.h> #include <linux/ctype.h> #include <linux/init.h> +#include <linux/panic_notifier.h> #include <linux/poll.h> #include <linux/nmi.h> #include <linux/fs.h> #include <linux/trace.h> #include <linux/sched/clock.h> #include <linux/sched/rt.h> +#include <linux/fsnotify.h> +#include <linux/irq_work.h> +#include <linux/workqueue.h> +#include <linux/sort.h> +#include <linux/io.h> /* vmap_page_range() */ +#include <linux/fs_context.h> + +#include <asm/setup.h> /* COMMAND_LINE_SIZE */ #include "trace.h" #include "trace_output.h" -/* - * On boot up, the ring buffer is set to the minimum size, so that - * we do not waste memory on systems that are not using tracing. - */ -bool ring_buffer_expanded; - +#ifdef CONFIG_FTRACE_STARTUP_TEST /* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the @@ -64,32 +70,43 @@ bool ring_buffer_expanded; static bool __read_mostly tracing_selftest_running; /* - * If a tracer is running, we do not want to run SELFTEST. + * If boot-time tracing including tracers/events via kernel cmdline + * is running, we do not want to run SELFTEST. */ bool __read_mostly tracing_selftest_disabled; +void __init disable_tracing_selftest(const char *reason) +{ + if (!tracing_selftest_disabled) { + tracing_selftest_disabled = true; + pr_info("Ftrace startup test is disabled due to %s\n", reason); + } +} +#else +#define tracing_selftest_running 0 +#define tracing_selftest_disabled 0 +#endif + /* Pipe tracepoints to printk */ -struct trace_iterator *tracepoint_print_iter; +static struct trace_iterator *tracepoint_print_iter; int tracepoint_printk; +static bool tracepoint_printk_stop_on_boot __initdata; +static bool traceoff_after_boot __initdata; static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key); -/* For tracers that don't implement custom flags */ -static struct tracer_opt dummy_tracer_opt[] = { - { } +/* Store tracers and their flags per instance */ +struct tracers { + struct list_head list; + struct tracer *tracer; + struct tracer_flags *flags; }; -static int -dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) -{ - return 0; -} - /* * To prevent the comm cache from being overwritten when no * tracing is active, only save the comm when a trace event * occurred. */ -static DEFINE_PER_CPU(bool, trace_taskinfo_save); +DEFINE_PER_CPU(bool, trace_taskinfo_save); /* * Kill all tracing for good (never come back). @@ -101,13 +118,14 @@ static int tracing_disabled = 1; cpumask_var_t __read_mostly tracing_buffer_mask; +#define MAX_TRACER_SIZE 100 /* * ftrace_dump_on_oops - variable to dump ftrace buffer on oops * * If there is an oops (or kernel panic) and the ftrace_dump_on_oops * is set, then ftrace_dump is called. This will output the contents * of the ftrace buffers to the console. This is very useful for - * capturing traces that lead to crashes and outputing it to a + * capturing traces that lead to crashes and outputting it to a * serial console. * * It is default off, but you can enable it with either specifying @@ -115,12 +133,48 @@ cpumask_var_t __read_mostly tracing_buffer_mask; * /proc/sys/kernel/ftrace_dump_on_oops * Set 1 if you want to dump buffers of all CPUs * Set 2 if you want to dump the buffer of the CPU that triggered oops + * Set instance name if you want to dump the specific trace instance + * Multiple instance dump is also supported, and instances are separated + * by commas. */ - -enum ftrace_dump_mode ftrace_dump_on_oops; +/* Set to string format zero to disable by default */ +char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0"; /* When set, tracing will stop when a WARN*() is hit */ -int __disable_trace_on_warning; +static int __disable_trace_on_warning; + +int tracepoint_printk_sysctl(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +static const struct ctl_table trace_sysctl_table[] = { + { + .procname = "ftrace_dump_on_oops", + .data = &ftrace_dump_on_oops, + .maxlen = MAX_TRACER_SIZE, + .mode = 0644, + .proc_handler = proc_dostring, + }, + { + .procname = "traceoff_on_warning", + .data = &__disable_trace_on_warning, + .maxlen = sizeof(__disable_trace_on_warning), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tracepoint_printk", + .data = &tracepoint_printk, + .maxlen = sizeof(tracepoint_printk), + .mode = 0644, + .proc_handler = tracepoint_printk_sysctl, + }, +}; + +static int __init init_trace_sysctls(void) +{ + register_sysctl_init("kernel", trace_sysctl_table); + return 0; +} +subsys_initcall(init_trace_sysctls); #ifdef CONFIG_TRACE_EVAL_MAP_FILE /* Map of enums to their values, for "eval_map" file */ @@ -158,37 +212,60 @@ union trace_eval_map_item { static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ -static int tracing_set_tracer(struct trace_array *tr, const char *buf); +int tracing_set_tracer(struct trace_array *tr, const char *buf); +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx); -#define MAX_TRACER_SIZE 100 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; static int __init set_cmdline_ftrace(char *str) { - strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); + strscpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ - ring_buffer_expanded = true; + trace_set_ring_buffer_expanded(NULL); return 1; } __setup("ftrace=", set_cmdline_ftrace); +int ftrace_dump_on_oops_enabled(void) +{ + if (!strcmp("0", ftrace_dump_on_oops)) + return 0; + else + return 1; +} + static int __init set_ftrace_dump_on_oops(char *str) { - if (*str++ != '=' || !*str) { - ftrace_dump_on_oops = DUMP_ALL; + if (!*str) { + strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE); return 1; } - if (!strcmp("orig_cpu", str)) { - ftrace_dump_on_oops = DUMP_ORIG; - return 1; - } + if (*str == ',') { + strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE); + strscpy(ftrace_dump_on_oops + 1, str, MAX_TRACER_SIZE - 1); + return 1; + } + + if (*str++ == '=') { + strscpy(ftrace_dump_on_oops, str, MAX_TRACER_SIZE); + return 1; + } - return 0; + return 0; } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); @@ -202,20 +279,59 @@ __setup("traceoff_on_warning", stop_trace_on_warning); static int __init boot_alloc_snapshot(char *str) { - allocate_snapshot = true; - /* We also need the main ring buffer expanded */ - ring_buffer_expanded = true; + 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; + int left = sizeof(boot_instance_info) - boot_instance_index; + int ret; + + if (strlen(str) >= left) + return -1; + + ret = snprintf(slot, left, "%s\t", str); + boot_instance_index += ret; + + return 1; +} +__setup("trace_instance=", boot_instance); + + static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) { - strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); - return 0; + strscpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); + return 1; } __setup("trace_options=", set_trace_boot_options); @@ -224,20 +340,38 @@ static char *trace_boot_clock __initdata; static int __init set_trace_boot_clock(char *str) { - strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); + strscpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); trace_boot_clock = trace_boot_clock_buf; - return 0; + return 1; } __setup("trace_clock=", set_trace_boot_clock); static int __init set_tracepoint_printk(char *str) { + /* Ignore the "tp_printk_stop_on_boot" param */ + if (*str == '_') + return 0; + if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) tracepoint_printk = 1; return 1; } __setup("tp_printk", set_tracepoint_printk); +static int __init set_tracepoint_printk_stop(char *str) +{ + tracepoint_printk_stop_on_boot = true; + return 1; +} +__setup("tp_printk_stop_on_boot", set_tracepoint_printk_stop); + +static int __init set_traceoff_after_boot(char *str) +{ + traceoff_after_boot = true; + return 1; +} +__setup("traceoff_after_boot", set_traceoff_after_boot); + unsigned long long ns2usecs(u64 nsec) { nsec += 500; @@ -245,21 +379,153 @@ unsigned long long ns2usecs(u64 nsec) return nsec; } +static void +trace_process_export(struct trace_export *export, + struct ring_buffer_event *event, int flag) +{ + struct trace_entry *entry; + unsigned int size = 0; + + if (export->flags & flag) { + entry = ring_buffer_event_data(event); + size = ring_buffer_event_length(event); + export->write(export, entry, size); + } +} + +static DEFINE_MUTEX(ftrace_export_lock); + +static struct trace_export __rcu *ftrace_exports_list __read_mostly; + +static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled); +static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled); +static DEFINE_STATIC_KEY_FALSE(trace_marker_exports_enabled); + +static inline void ftrace_exports_enable(struct trace_export *export) +{ + if (export->flags & TRACE_EXPORT_FUNCTION) + static_branch_inc(&trace_function_exports_enabled); + + if (export->flags & TRACE_EXPORT_EVENT) + static_branch_inc(&trace_event_exports_enabled); + + if (export->flags & TRACE_EXPORT_MARKER) + static_branch_inc(&trace_marker_exports_enabled); +} + +static inline void ftrace_exports_disable(struct trace_export *export) +{ + if (export->flags & TRACE_EXPORT_FUNCTION) + static_branch_dec(&trace_function_exports_enabled); + + if (export->flags & TRACE_EXPORT_EVENT) + static_branch_dec(&trace_event_exports_enabled); + + if (export->flags & TRACE_EXPORT_MARKER) + static_branch_dec(&trace_marker_exports_enabled); +} + +static void ftrace_exports(struct ring_buffer_event *event, int flag) +{ + struct trace_export *export; + + guard(preempt_notrace)(); + + export = rcu_dereference_raw_check(ftrace_exports_list); + while (export) { + trace_process_export(export, event, flag); + export = rcu_dereference_raw_check(export->next); + } +} + +static inline void +add_trace_export(struct trace_export **list, struct trace_export *export) +{ + rcu_assign_pointer(export->next, *list); + /* + * We are entering export into the list but another + * CPU might be walking that list. We need to make sure + * the export->next pointer is valid before another CPU sees + * the export pointer included into the list. + */ + rcu_assign_pointer(*list, export); +} + +static inline int +rm_trace_export(struct trace_export **list, struct trace_export *export) +{ + struct trace_export **p; + + for (p = list; *p != NULL; p = &(*p)->next) + if (*p == export) + break; + + if (*p != export) + return -1; + + rcu_assign_pointer(*p, (*p)->next); + + return 0; +} + +static inline void +add_ftrace_export(struct trace_export **list, struct trace_export *export) +{ + ftrace_exports_enable(export); + + add_trace_export(list, export); +} + +static inline int +rm_ftrace_export(struct trace_export **list, struct trace_export *export) +{ + int ret; + + ret = rm_trace_export(list, export); + ftrace_exports_disable(export); + + return ret; +} + +int register_ftrace_export(struct trace_export *export) +{ + if (WARN_ON_ONCE(!export->write)) + return -1; + + guard(mutex)(&ftrace_export_lock); + + add_ftrace_export(&ftrace_exports_list, export); + + return 0; +} +EXPORT_SYMBOL_GPL(register_ftrace_export); + +int unregister_ftrace_export(struct trace_export *export) +{ + guard(mutex)(&ftrace_export_lock); + return rm_ftrace_export(&ftrace_exports_list, export); +} +EXPORT_SYMBOL_GPL(unregister_ftrace_export); + /* trace_flags holds trace_options default values */ #define TRACE_DEFAULT_FLAGS \ - (FUNCTION_DEFAULT_FLAGS | \ - TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | \ - TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | \ - TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | \ - TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS) + (FUNCTION_DEFAULT_FLAGS | FPROFILE_DEFAULT_FLAGS | \ + TRACE_ITER(PRINT_PARENT) | TRACE_ITER(PRINTK) | \ + TRACE_ITER(ANNOTATE) | TRACE_ITER(CONTEXT_INFO) | \ + TRACE_ITER(RECORD_CMD) | TRACE_ITER(OVERWRITE) | \ + TRACE_ITER(IRQ_INFO) | TRACE_ITER(MARKERS) | \ + TRACE_ITER(HASH_PTR) | TRACE_ITER(TRACE_PRINTK) | \ + TRACE_ITER(COPY_MARKER)) /* trace_options that are only supported by global_trace */ -#define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER_PRINTK | \ - TRACE_ITER_PRINTK_MSGONLY | TRACE_ITER_RECORD_CMD) +#define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER(PRINTK) | \ + TRACE_ITER(PRINTK_MSGONLY) | TRACE_ITER(RECORD_CMD) | \ + TRACE_ITER(PROF_TEXT_OFFSET) | FPROFILE_DEFAULT_FLAGS) /* trace_flags that are default zero for instances */ #define ZEROED_TRACE_FLAGS \ - (TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK) + (TRACE_ITER(EVENT_FORK) | TRACE_ITER(FUNC_FORK) | TRACE_ITER(TRACE_PRINTK) | \ + TRACE_ITER(COPY_MARKER)) /* * The global_trace is the descriptor that holds the top-level tracing @@ -269,24 +535,76 @@ static struct trace_array global_trace = { .trace_flags = TRACE_DEFAULT_FLAGS, }; +static struct trace_array *printk_trace = &global_trace; + +/* List of trace_arrays interested in the top level trace_marker */ +static LIST_HEAD(marker_copies); + +static __always_inline bool printk_binsafe(struct trace_array *tr) +{ + /* + * The binary format of traceprintk can cause a crash if used + * by a buffer from another boot. Force the use of the + * non binary version of trace_printk if the trace_printk + * buffer is a boot mapped ring buffer. + */ + return !(tr->flags & TRACE_ARRAY_FL_BOOT); +} + +static void update_printk_trace(struct trace_array *tr) +{ + if (printk_trace == tr) + return; + + printk_trace->trace_flags &= ~TRACE_ITER(TRACE_PRINTK); + printk_trace = tr; + tr->trace_flags |= TRACE_ITER(TRACE_PRINTK); +} + +/* Returns true if the status of tr changed */ +static bool update_marker_trace(struct trace_array *tr, int enabled) +{ + lockdep_assert_held(&event_mutex); + + if (enabled) { + if (!list_empty(&tr->marker_list)) + return false; + + list_add_rcu(&tr->marker_list, &marker_copies); + tr->trace_flags |= TRACE_ITER(COPY_MARKER); + return true; + } + + if (list_empty(&tr->marker_list)) + return false; + + list_del_init(&tr->marker_list); + tr->trace_flags &= ~TRACE_ITER(COPY_MARKER); + return true; +} + +void trace_set_ring_buffer_expanded(struct trace_array *tr) +{ + if (!tr) + tr = &global_trace; + tr->ring_buffer_expanded = true; +} + LIST_HEAD(ftrace_trace_arrays); int trace_array_get(struct trace_array *this_tr) { struct trace_array *tr; - int ret = -ENODEV; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr == this_tr) { tr->ref++; - ret = 0; - break; + return 0; } } - mutex_unlock(&trace_types_lock); - return ret; + return -ENODEV; } static void __trace_array_put(struct trace_array *this_tr) @@ -295,30 +613,40 @@ static void __trace_array_put(struct trace_array *this_tr) this_tr->ref--; } +/** + * trace_array_put - Decrement the reference counter for this trace array. + * @this_tr : pointer to the trace array + * + * NOTE: Use this when we no longer need the trace array returned by + * trace_array_get_by_name(). This ensures the trace array can be later + * destroyed. + * + */ void trace_array_put(struct trace_array *this_tr) { - mutex_lock(&trace_types_lock); + if (!this_tr) + return; + + guard(mutex)(&trace_types_lock); __trace_array_put(this_tr); - mutex_unlock(&trace_types_lock); } +EXPORT_SYMBOL_GPL(trace_array_put); -int call_filter_check_discard(struct trace_event_call *call, void *rec, - struct ring_buffer *buffer, - struct ring_buffer_event *event) +int tracing_check_open_get_tr(struct trace_array *tr) { - if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) && - !filter_match_preds(call->filter, rec)) { - __trace_event_discard_commit(buffer, event); - return 1; - } + int ret; - return 0; -} + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; -void trace_free_pid_list(struct trace_pid_list *pid_list) -{ - vfree(pid_list->pids); - kfree(pid_list); + if (tracing_disabled) + return -ENODEV; + + if (tr && trace_array_get(tr) < 0) + return -ENODEV; + + return 0; } /** @@ -326,24 +654,18 @@ void trace_free_pid_list(struct trace_pid_list *pid_list) * @filtered_pids: The list of pids to check * @search_pid: The PID to find in @filtered_pids * - * Returns true if @search_pid is fonud in @filtered_pids, and false otherwis. + * Returns true if @search_pid is found in @filtered_pids, and false otherwise. */ bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) { - /* - * If pid_max changed after filtered_pids was created, we - * by default ignore all pids greater than the previous pid_max. - */ - if (search_pid >= filtered_pids->pid_max) - return false; - - return test_bit(search_pid, filtered_pids->pids); + return trace_pid_list_is_set(filtered_pids, search_pid); } /** * trace_ignore_this_task - should a task be ignored for tracing * @filtered_pids: The list of pids to check + * @filtered_no_pids: The list of pids not to be traced * @task: The task that should be ignored if not filtered * * Checks if @task should be traced or not from @filtered_pids. @@ -351,20 +673,26 @@ trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) * Returns false if @task should be traced. */ bool -trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task) +trace_ignore_this_task(struct trace_pid_list *filtered_pids, + struct trace_pid_list *filtered_no_pids, + struct task_struct *task) { /* - * Return false, because if filtered_pids does not exist, - * all pids are good to trace. + * If filtered_no_pids is not empty, and the task's pid is listed + * in filtered_no_pids, then return true. + * Otherwise, if filtered_pids is empty, that means we can + * trace all tasks. If it has content, then only trace pids + * within filtered_pids. */ - if (!filtered_pids) - return false; - return !trace_find_filtered_pid(filtered_pids, task->pid); + return (filtered_pids && + !trace_find_filtered_pid(filtered_pids, task->pid)) || + (filtered_no_pids && + trace_find_filtered_pid(filtered_no_pids, task->pid)); } /** - * trace_pid_filter_add_remove_task - Add or remove a task from a pid_list + * trace_filter_add_remove_task - Add or remove a task from a pid_list * @pid_list: The list to modify * @self: The current task for fork or NULL for exit * @task: The task to add or remove @@ -388,15 +716,11 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list, return; } - /* Sorry, but we don't support pid_max changing after setting */ - if (task->pid >= pid_list->pid_max) - return; - /* "self" is set for forks, and NULL for exits */ if (self) - set_bit(task->pid, pid_list->pids); + trace_pid_list_set(pid_list, task->pid); else - clear_bit(task->pid, pid_list->pids); + trace_pid_list_clear(pid_list, task->pid); } /** @@ -413,18 +737,19 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list, */ void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos) { - unsigned long pid = (unsigned long)v; + long pid = (unsigned long)v; + unsigned int next; (*pos)++; - /* pid already is +1 of the actual prevous bit */ - pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid); + /* pid already is +1 of the actual previous bit */ + if (trace_pid_list_next(pid_list, pid, &next) < 0) + return NULL; - /* Return pid + 1 to allow zero to be represented */ - if (pid < pid_list->pid_max) - return (void *)(pid + 1); + pid = next; - return NULL; + /* Return pid + 1 to allow zero to be represented */ + return (void *)(pid + 1); } /** @@ -441,12 +766,14 @@ void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos) void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos) { unsigned long pid; + unsigned int first; loff_t l = 0; - pid = find_first_bit(pid_list->pids, pid_list->pid_max); - if (pid >= pid_list->pid_max) + if (trace_pid_list_first(pid_list, &first) < 0) return NULL; + pid = first; + /* Return pid + 1 so that zero can be the exit value */ for (pid++; pid && l < *pos; pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l)) @@ -482,7 +809,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, unsigned long val; int nr_pids = 0; ssize_t read = 0; - ssize_t ret = 0; + ssize_t ret; loff_t pos; pid_t pid; @@ -495,68 +822,67 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, * the user. If the operation fails, then the current list is * not modified. */ - pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); - if (!pid_list) - return -ENOMEM; - - pid_list->pid_max = READ_ONCE(pid_max); - - /* Only truncating will shrink pid_max */ - if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max) - pid_list->pid_max = filtered_pids->pid_max; - - pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); - if (!pid_list->pids) { - kfree(pid_list); + pid_list = trace_pid_list_alloc(); + if (!pid_list) { + trace_parser_put(&parser); return -ENOMEM; } if (filtered_pids) { /* copy the current bits to the new max */ - for_each_set_bit(pid, filtered_pids->pids, - filtered_pids->pid_max) { - set_bit(pid, pid_list->pids); + ret = trace_pid_list_first(filtered_pids, &pid); + while (!ret) { + ret = trace_pid_list_set(pid_list, pid); + if (ret < 0) + goto out; + + ret = trace_pid_list_next(filtered_pids, pid + 1, &pid); nr_pids++; } } + ret = 0; while (cnt > 0) { pos = 0; ret = trace_get_user(&parser, ubuf, cnt, &pos); - if (ret < 0 || !trace_parser_loaded(&parser)) + if (ret < 0) break; read += ret; ubuf += ret; cnt -= ret; + if (!trace_parser_loaded(&parser)) + break; + ret = -EINVAL; if (kstrtoul(parser.buffer, 0, &val)) break; - if (val >= pid_list->pid_max) - break; pid = (pid_t)val; - set_bit(pid, pid_list->pids); + if (trace_pid_list_set(pid_list, pid) < 0) { + ret = -1; + break; + } nr_pids++; trace_parser_clear(&parser); ret = 0; } + out: trace_parser_put(&parser); if (ret < 0) { - trace_free_pid_list(pid_list); + trace_pid_list_free(pid_list); return ret; } if (!nr_pids) { /* Cleared the list of pids */ - trace_free_pid_list(pid_list); - read = ret; + trace_pid_list_free(pid_list); pid_list = NULL; } @@ -565,7 +891,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, return read; } -static u64 buffer_ftrace_now(struct trace_buffer *buf, int cpu) +static u64 buffer_ftrace_now(struct array_buffer *buf, int cpu) { u64 ts; @@ -573,7 +899,7 @@ static u64 buffer_ftrace_now(struct trace_buffer *buf, int cpu) if (!buf->buffer) return trace_clock_local(); - ts = ring_buffer_time_stamp(buf->buffer, cpu); + ts = ring_buffer_time_stamp(buf->buffer); ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts); return ts; @@ -581,11 +907,11 @@ static u64 buffer_ftrace_now(struct trace_buffer *buf, int cpu) u64 ftrace_now(int cpu) { - return buffer_ftrace_now(&global_trace.trace_buffer, cpu); + return buffer_ftrace_now(&global_trace.array_buffer, cpu); } /** - * tracing_is_enabled - Show if global_trace has been disabled + * tracing_is_enabled - Show if global_trace has been enabled * * Shows if the global trace has been enabled or not. It uses the * mirror flag "buffer_disabled" to be used in fast paths such as for @@ -600,7 +926,6 @@ int tracing_is_enabled(void) * return the mirror variable of the state of the ring buffer. * It's a little racy, but we don't really care. */ - smp_rmb(); return !global_trace.buffer_disabled; } @@ -636,7 +961,7 @@ DEFINE_MUTEX(trace_types_lock); * The content of events may become garbage if we allow other process consumes * these events concurrently: * A) the page of the consumed events may become a normal page - * (not reader page) in ring buffer, and this page will be rewrited + * (not reader page) in ring buffer, and this page will be rewritten * by events producer. * B) The page of the consumed events may become a page for splice_read, * and this page will be returned to system. @@ -709,24 +1034,26 @@ static inline void trace_access_lock_init(void) #endif #ifdef CONFIG_STACKTRACE -static void __ftrace_trace_stack(struct ring_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs); +static void __ftrace_trace_stack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs); static inline void ftrace_trace_stack(struct trace_array *tr, - struct ring_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs); + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs); #else -static inline void __ftrace_trace_stack(struct ring_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs) +static inline void __ftrace_trace_stack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs) { } static inline void ftrace_trace_stack(struct trace_array *tr, - struct ring_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs) + struct trace_buffer *buffer, + unsigned long trace_ctx, + int skip, struct pt_regs *regs) { } @@ -734,33 +1061,32 @@ static inline void ftrace_trace_stack(struct trace_array *tr, static __always_inline void trace_event_setup(struct ring_buffer_event *event, - int type, unsigned long flags, int pc) + int type, unsigned int trace_ctx) { struct trace_entry *ent = ring_buffer_event_data(event); - tracing_generic_entry_update(ent, flags, pc); - ent->type = type; + tracing_generic_entry_update(ent, type, trace_ctx); } static __always_inline struct ring_buffer_event * -__trace_buffer_lock_reserve(struct ring_buffer *buffer, +__trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, - unsigned long flags, int pc) + unsigned int trace_ctx) { struct ring_buffer_event *event; event = ring_buffer_lock_reserve(buffer, len); if (event != NULL) - trace_event_setup(event, type, flags, pc); + trace_event_setup(event, type, trace_ctx); return event; } void tracer_tracing_on(struct trace_array *tr) { - if (tr->trace_buffer.buffer) - ring_buffer_record_on(tr->trace_buffer.buffer); + if (tr->array_buffer.buffer) + ring_buffer_record_on(tr->array_buffer.buffer); /* * This flag is looked at when buffers haven't been allocated * yet, or by some tracers (like irqsoff), that just want to @@ -770,8 +1096,6 @@ void tracer_tracing_on(struct trace_array *tr) * important to be fast than accurate. */ tr->buffer_disabled = 0; - /* Make the flag seen by readers */ - smp_wmb(); } /** @@ -788,7 +1112,7 @@ EXPORT_SYMBOL_GPL(tracing_on); static __always_inline void -__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) +__buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { __this_cpu_write(trace_taskinfo_save, true); @@ -798,39 +1122,37 @@ __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *eve ring_buffer_write(buffer, event->array[0], &event->array[1]); /* Release the temp buffer */ this_cpu_dec(trace_buffered_event_cnt); + /* ring_buffer_unlock_commit() enables preemption */ + preempt_enable_notrace(); } else - ring_buffer_unlock_commit(buffer, event); + ring_buffer_unlock_commit(buffer); } -/** - * __trace_puts - write a constant string into the trace buffer. - * @ip: The address of the caller - * @str: The constant string to write - * @size: The size of the string. - */ -int __trace_puts(unsigned long ip, const char *str, int size) +int __trace_array_puts(struct trace_array *tr, unsigned long ip, + const char *str, int size) { struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct print_entry *entry; - unsigned long irq_flags; + unsigned int trace_ctx; int alloc; - int pc; - if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) + if (!(tr->trace_flags & TRACE_ITER(PRINTK))) return 0; - pc = preempt_count(); + if (unlikely(tracing_selftest_running && tr == &global_trace)) + return 0; - if (unlikely(tracing_selftest_running || tracing_disabled)) + if (unlikely(tracing_disabled)) return 0; alloc = sizeof(*entry) + size + 2; /* possible \n added */ - local_save_flags(irq_flags); - buffer = global_trace.trace_buffer.buffer; - event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, - irq_flags, pc); + trace_ctx = tracing_gen_ctx(); + buffer = tr->array_buffer.buffer; + guard(ring_buffer_nest)(buffer); + event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, + trace_ctx); if (!event) return 0; @@ -847,10 +1169,21 @@ int __trace_puts(unsigned long ip, const char *str, int size) entry->buf[size] = '\0'; __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL); - + ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); return size; } +EXPORT_SYMBOL_GPL(__trace_array_puts); + +/** + * __trace_puts - write a constant string into the trace buffer. + * @ip: The address of the caller + * @str: The constant string to write + * @size: The size of the string. + */ +int __trace_puts(unsigned long ip, const char *str, int size) +{ + return __trace_array_puts(printk_trace, ip, str, size); +} EXPORT_SYMBOL_GPL(__trace_puts); /** @@ -860,25 +1193,28 @@ EXPORT_SYMBOL_GPL(__trace_puts); */ int __trace_bputs(unsigned long ip, const char *str) { + struct trace_array *tr = READ_ONCE(printk_trace); struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct bputs_entry *entry; - unsigned long irq_flags; + unsigned int trace_ctx; int size = sizeof(struct bputs_entry); - int pc; - if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) - return 0; + if (!printk_binsafe(tr)) + return __trace_puts(ip, str, strlen(str)); - pc = preempt_count(); + if (!(tr->trace_flags & TRACE_ITER(PRINTK))) + return 0; if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; - local_save_flags(irq_flags); - buffer = global_trace.trace_buffer.buffer; + trace_ctx = tracing_gen_ctx(); + buffer = tr->array_buffer.buffer; + + guard(ring_buffer_nest)(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, - irq_flags, pc); + trace_ctx); if (!event) return 0; @@ -887,43 +1223,55 @@ int __trace_bputs(unsigned long ip, const char *str) entry->str = str; __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL); + ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); return 1; } EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -void tracing_snapshot_instance(struct trace_array *tr) +static void tracing_snapshot_instance_cond(struct trace_array *tr, + void *cond_data) { struct tracer *tracer = tr->current_trace; unsigned long flags; if (in_nmi()) { - internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); - internal_trace_puts("*** snapshot is being ignored ***\n"); + trace_array_puts(tr, "*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); + trace_array_puts(tr, "*** snapshot is being ignored ***\n"); return; } if (!tr->allocated_snapshot) { - internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n"); - internal_trace_puts("*** stopping trace here! ***\n"); - tracing_off(); + trace_array_puts(tr, "*** SNAPSHOT NOT ALLOCATED ***\n"); + trace_array_puts(tr, "*** stopping trace here! ***\n"); + tracer_tracing_off(tr); return; } /* Note, snapshot can not be used when the tracer uses it */ if (tracer->use_max_tr) { - internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n"); - internal_trace_puts("*** Can not use snapshot (sorry) ***\n"); + trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); + return; + } + + if (tr->mapped) { + trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; } local_irq_save(flags); - update_max_tr(tr, current, smp_processor_id()); + 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. * @@ -933,7 +1281,7 @@ void tracing_snapshot_instance(struct trace_array *tr) * * Note, make sure to allocate the snapshot with either * a tracing_snapshot_alloc(), or by doing it manually - * with: echo 1 > /sys/kernel/debug/tracing/snapshot + * with: echo 1 > /sys/kernel/tracing/snapshot * * If the snapshot buffer is not allocated, it will stop tracing. * Basically making a permanent snapshot. @@ -946,19 +1294,76 @@ void tracing_snapshot(void) } EXPORT_SYMBOL_GPL(tracing_snapshot); -static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, - struct trace_buffer *size_buf, int cpu_id); -static void set_buffer_entries(struct trace_buffer *buf, unsigned long val); +/** + * 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->max_buffer.buffer, order); + if (ret < 0) + return ret; + /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&tr->max_buffer, - &tr->trace_buffer, RING_BUFFER_ALL_CPUS); + &tr->array_buffer, RING_BUFFER_ALL_CPUS); if (ret < 0) return ret; @@ -975,12 +1380,52 @@ static void free_snapshot(struct trace_array *tr) * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ + ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0); ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&tr->max_buffer, 1); tracing_reset_online_cpus(&tr->max_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. * @@ -1025,12 +1470,106 @@ void tracing_snapshot_alloc(void) 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(sizeof(*cond_snapshot), GFP_KERNEL); + int ret; + + if (!cond_snapshot) + return -ENOMEM; + + cond_snapshot->cond_data = cond_data; + cond_snapshot->update = update; + + guard(mutex)(&trace_types_lock); + + if (tr->current_trace->use_max_tr) + 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"); @@ -1043,12 +1582,29 @@ void tracing_snapshot_alloc(void) 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) { - if (tr->trace_buffer.buffer) - ring_buffer_record_off(tr->trace_buffer.buffer); + if (tr->array_buffer.buffer) + ring_buffer_record_off(tr->array_buffer.buffer); /* * This flag is looked at when buffers haven't been allocated * yet, or by some tracers (like irqsoff), that just want to @@ -1058,8 +1614,39 @@ void tracer_tracing_off(struct trace_array *tr) * important to be fast than accurate. */ tr->buffer_disabled = 1; - /* Make the flag seen by readers */ - smp_wmb(); +} + +/** + * tracer_tracing_disable() - temporary disable the buffer from write + * @tr: The trace array to disable its buffer for + * + * Expects trace_tracing_enable() to re-enable tracing. + * The difference between this and tracer_tracing_off() is that this + * is a counter and can nest, whereas, tracer_tracing_off() can + * be called multiple times and a single trace_tracing_on() will + * enable it. + */ +void tracer_tracing_disable(struct trace_array *tr) +{ + if (WARN_ON_ONCE(!tr->array_buffer.buffer)) + return; + + ring_buffer_record_disable(tr->array_buffer.buffer); +} + +/** + * tracer_tracing_enable() - counter part of tracer_tracing_disable() + * @tr: The trace array that had tracer_tracincg_disable() called on it + * + * This is called after tracer_tracing_disable() has been called on @tr, + * when it's safe to re-enable tracing. + */ +void tracer_tracing_enable(struct trace_array *tr) +{ + if (WARN_ON_ONCE(!tr->array_buffer.buffer)) + return; + + ring_buffer_record_enable(tr->array_buffer.buffer); } /** @@ -1078,8 +1665,11 @@ EXPORT_SYMBOL_GPL(tracing_off); void disable_trace_on_warning(void) { - if (__disable_trace_on_warning) + if (__disable_trace_on_warning) { + trace_array_printk_buf(global_trace.array_buffer.buffer, _THIS_IP_, + "Disabling tracing due to warning\n"); tracing_off(); + } } /** @@ -1090,8 +1680,8 @@ void disable_trace_on_warning(void) */ bool tracer_tracing_is_on(struct trace_array *tr) { - if (tr->trace_buffer.buffer) - return ring_buffer_record_is_on(tr->trace_buffer.buffer); + if (tr->array_buffer.buffer) + return ring_buffer_record_is_set_on(tr->array_buffer.buffer); return !tr->buffer_disabled; } @@ -1111,10 +1701,12 @@ static int __init set_buf_size(char *str) if (!str) return 0; buf_size = memparse(str, &str); - /* nr_entries can not be zero */ - if (buf_size == 0) - return 0; - trace_buf_size = buf_size; + /* + * nr_entries can not be zero and the startup + * tests require some buffer space. Therefore + * ensure we have at least 4096 bytes of buffer. + */ + trace_buf_size = max(4096UL, buf_size); return 1; } __setup("trace_buf_size=", set_buf_size); @@ -1148,7 +1740,7 @@ unsigned long nsecs_to_usecs(unsigned long nsecs) #undef C #define C(a, b) b -/* These must match the bit postions in trace_iterator_flags */ +/* These must match the bit positions in trace_iterator_flags */ static const char *trace_options[] = { TRACE_FLAGS NULL @@ -1167,6 +1759,7 @@ static struct { { ktime_get_mono_fast_ns, "mono", 1 }, { ktime_get_raw_fast_ns, "mono_raw", 1 }, { ktime_get_boot_fast_ns, "boot", 1 }, + { ktime_get_tai_fast_ns, "tai", 1 }, ARCH_TRACE_CLOCKS }; @@ -1225,7 +1818,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, ret = get_user(ch, ubuf++); if (ret) - goto out; + goto fail; read++; cnt--; @@ -1239,7 +1832,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, while (cnt && isspace(ch)) { ret = get_user(ch, ubuf++); if (ret) - goto out; + goto fail; read++; cnt--; } @@ -1249,8 +1842,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, /* only spaces were written */ if (isspace(ch) || !ch) { *ppos += read; - ret = read; - goto out; + return read; } } @@ -1260,11 +1852,12 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, parser->buffer[parser->idx++] = ch; else { ret = -EINVAL; - goto out; + goto fail; } + ret = get_user(ch, ubuf++); if (ret) - goto out; + goto fail; read++; cnt--; } @@ -1280,13 +1873,13 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, parser->buffer[parser->idx] = 0; } else { ret = -EINVAL; - goto out; + goto fail; } *ppos += read; - ret = read; - -out: + return read; +fail: + trace_parser_fail(parser); return ret; } @@ -1295,21 +1888,85 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) { int len; - if (trace_seq_used(s) <= s->seq.readpos) + if (trace_seq_used(s) <= s->readpos) return -EBUSY; - len = trace_seq_used(s) - s->seq.readpos; + len = trace_seq_used(s) - s->readpos; if (cnt > len) cnt = len; - memcpy(buf, s->buffer + s->seq.readpos, cnt); + memcpy(buf, s->buffer + s->readpos, cnt); - s->seq.readpos += cnt; + s->readpos += cnt; return cnt; } unsigned long __read_mostly tracing_thresh; #ifdef CONFIG_TRACER_MAX_TRACE +static const struct file_operations tracing_max_lat_fops; + +#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); +} + +static void trace_create_maxlat_file(struct trace_array *tr, + struct dentry *d_tracer) +{ + INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn); + init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); + tr->d_max_latency = trace_create_file("tracing_max_latency", + TRACE_MODE_WRITE, + d_tracer, tr, + &tracing_max_lat_fops); +} + +__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); +} + +#else /* !LATENCY_FS_NOTIFY */ + +#define trace_create_maxlat_file(tr, d_tracer) \ + trace_create_file("tracing_max_latency", TRACE_MODE_WRITE, \ + d_tracer, tr, &tracing_max_lat_fops) + +#endif + /* * Copy the new maximum trace into the separate maximum-trace * structure. (this way the maximum trace is permanently saved, @@ -1318,8 +1975,8 @@ unsigned long __read_mostly tracing_thresh; static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct trace_buffer *trace_buf = &tr->trace_buffer; - struct trace_buffer *max_buf = &tr->max_buffer; + struct array_buffer *trace_buf = &tr->array_buffer; + struct array_buffer *max_buf = &tr->max_buffer; struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); @@ -1330,7 +1987,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) max_data->critical_start = data->critical_start; max_data->critical_end = data->critical_end; - memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN); + strscpy(max_data->comm, tsk->comm); max_data->pid = tsk->pid; /* * If tsk == current, then use current_uid(), as that does not use @@ -1347,6 +2004,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) /* record this tasks comm */ tracing_record_cmdline(tsk); + latency_fsnotify(tr); } /** @@ -1354,12 +2012,14 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) * @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) +update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, + void *cond_data) { if (tr->stop_count) return; @@ -1374,23 +2034,33 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); - /* Inherit the recordable setting from trace_buffer */ - if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer)) + /* Inherit the recordable setting from array_buffer */ + if (ring_buffer_record_is_set_on(tr->array_buffer.buffer)) ring_buffer_record_on(tr->max_buffer.buffer); else ring_buffer_record_off(tr->max_buffer.buffer); - swap(tr->trace_buffer.buffer, tr->max_buffer.buffer); +#ifdef CONFIG_TRACER_SNAPSHOT + if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) { + arch_spin_unlock(&tr->max_lock); + return; + } +#endif + swap(tr->array_buffer.buffer, tr->max_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. + * @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. */ @@ -1411,7 +2081,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); - ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu); + ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->array_buffer.buffer, cpu); if (ret == -EBUSY) { /* @@ -1419,9 +2089,10 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * 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->max_buffer.buffer, _THIS_IP_, - "Failed to swap buffers due to commit in progress\n"); + "Failed to swap buffers due to commit or resize in progress\n"); } WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); @@ -1429,16 +2100,49 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); } + #endif /* CONFIG_TRACER_MAX_TRACE */ +struct pipe_wait { + struct trace_iterator *iter; + int wait_index; +}; + +static bool wait_pipe_cond(void *data) +{ + struct pipe_wait *pwait = data; + struct trace_iterator *iter = pwait->iter; + + if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index) + return true; + + return iter->closed; +} + static int wait_on_pipe(struct trace_iterator *iter, int full) { + struct pipe_wait pwait; + int ret; + /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file, - full); + pwait.wait_index = atomic_read_acquire(&iter->wait_index); + pwait.iter = iter; + + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, + wait_pipe_cond, &pwait); + +#ifdef CONFIG_TRACER_MAX_TRACE + /* + * Make sure this is still the snapshot buffer, as if a snapshot were + * to happen, this would now be the main buffer. + */ + if (iter->snapshot) + iter->array_buffer = &iter->tr->max_buffer; +#endif + return ret; } #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -1467,6 +2171,7 @@ static int save_selftest(struct tracer *type) static int run_tracer_selftest(struct tracer *type) { struct trace_array *tr = &global_trace; + struct tracer_flags *saved_flags = tr->current_trace_flags; struct tracer *saved_tracer = tr->current_trace; int ret; @@ -1481,6 +2186,12 @@ static int run_tracer_selftest(struct tracer *type) if (!selftests_can_run) return save_selftest(type); + if (!tracing_is_on()) { + pr_warn("Selftest for tracer %s skipped due to tracing disabled\n", + type->name); + return 0; + } + /* * Run a selftest on this tracer. * Here we reset the trace buffer, and set the current @@ -1488,14 +2199,15 @@ static int run_tracer_selftest(struct tracer *type) * internal tracing to verify that everything is in order. * If we fail, we do not register this tracer. */ - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); tr->current_trace = type; + tr->current_trace_flags = type->flags ? : type->default_flags; #ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { /* If we expanded the buffers, make sure the max is expanded too */ - if (ring_buffer_expanded) + if (tr->ring_buffer_expanded) ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, RING_BUFFER_ALL_CPUS); tr->allocated_snapshot = true; @@ -1507,6 +2219,7 @@ static int run_tracer_selftest(struct tracer *type) ret = type->selftest(type, tr); /* the test is responsible for resetting too */ tr->current_trace = saved_tracer; + tr->current_trace_flags = saved_flags; if (ret) { printk(KERN_CONT "FAILED!\n"); /* Add the warning after printing 'FAILED' */ @@ -1514,14 +2227,14 @@ static int run_tracer_selftest(struct tracer *type) return -1; } /* Only reset on passing, to avoid touching corrupted buffers */ - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { tr->allocated_snapshot = false; /* Shrink the max buffer again */ - if (ring_buffer_expanded) + if (tr->ring_buffer_expanded) ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); } @@ -1531,6 +2244,24 @@ static int run_tracer_selftest(struct tracer *type) return 0; } +static int do_run_tracer_selftest(struct tracer *type) +{ + int ret; + + /* + * Tests can take a long time, especially if they are run one after the + * other, as does happen during bootup when all the tracers are + * registered. This could cause the soft lockup watchdog to trigger. + */ + cond_resched(); + + tracing_selftest_running = true; + ret = run_tracer_selftest(type); + tracing_selftest_running = false; + + return ret; +} + static __init int init_trace_selftests(void) { struct trace_selftests *p, *n; @@ -1539,14 +2270,19 @@ static __init int init_trace_selftests(void) selftests_can_run = true; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (list_empty(&postponed_selftests)) - goto out; + return 0; pr_info("Running postponed tracer tests:\n"); + tracing_selftest_running = true; list_for_each_entry_safe(p, n, &postponed_selftests, list) { + /* This loop can take minutes when sanitizers are enabled, so + * lets make sure we allow RCU processing. + */ + cond_resched(); ret = run_tracer_selftest(p->type); /* If the test fails, then warn and remove from available_tracers */ if (ret < 0) { @@ -1564,32 +2300,44 @@ static __init int init_trace_selftests(void) list_del(&p->list); kfree(p); } - - out: - mutex_unlock(&trace_types_lock); + tracing_selftest_running = false; return 0; } core_initcall(init_trace_selftests); #else -static inline int run_tracer_selftest(struct tracer *type) +static inline int do_run_tracer_selftest(struct tracer *type) { return 0; } #endif /* CONFIG_FTRACE_STARTUP_TEST */ -static void add_tracer_options(struct trace_array *tr, struct tracer *t); +static int add_tracer(struct trace_array *tr, struct tracer *t); static void __init apply_trace_boot_options(void); +static void free_tracers(struct trace_array *tr) +{ + struct tracers *t, *n; + + lockdep_assert_held(&trace_types_lock); + + list_for_each_entry_safe(t, n, &tr->tracers, list) { + list_del(&t->list); + kfree(t->flags); + kfree(t); + } +} + /** * register_tracer - register a tracer with the ftrace system. - * @type - the plugin for the tracer + * @type: the plugin for the tracer * * Register a new plugin tracer. */ int __init register_tracer(struct tracer *type) { + struct trace_array *tr; struct tracer *t; int ret = 0; @@ -1603,9 +2351,13 @@ int __init register_tracer(struct tracer *type) return -1; } - mutex_lock(&trace_types_lock); + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not register tracer %s due to lockdown\n", + type->name); + return -EPERM; + } - tracing_selftest_running = true; + mutex_lock(&trace_types_lock); for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { @@ -1617,63 +2369,51 @@ int __init register_tracer(struct tracer *type) } } - if (!type->set_flag) - type->set_flag = &dummy_set_flag; - if (!type->flags) { - /*allocate a dummy tracer_flags*/ - type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL); - if (!type->flags) { - ret = -ENOMEM; - goto out; - } - type->flags->val = 0; - type->flags->opts = dummy_tracer_opt; - } else - if (!type->flags->opts) - type->flags->opts = dummy_tracer_opt; - /* store the tracer for __set_tracer_option */ - type->flags->trace = type; + if (type->flags) + type->flags->trace = type; - ret = run_tracer_selftest(type); + ret = do_run_tracer_selftest(type); if (ret < 0) goto out; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + ret = add_tracer(tr, type); + if (ret < 0) { + /* The tracer will still exist but without options */ + pr_warn("Failed to create tracer options for %s\n", type->name); + break; + } + } + type->next = trace_types; trace_types = type; - add_tracer_options(&global_trace, type); out: - tracing_selftest_running = false; mutex_unlock(&trace_types_lock); if (ret || !default_bootup_tracer) - goto out_unlock; + return ret; if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE)) - goto out_unlock; + return 0; printk(KERN_INFO "Starting tracer '%s'\n", type->name); /* Do we want this tracer to start on bootup? */ - tracing_set_tracer(&global_trace, type->name); + WARN_ON(tracing_set_tracer(&global_trace, type->name) < 0); default_bootup_tracer = NULL; apply_trace_boot_options(); /* disable other selftests, since this will break it. */ - tracing_selftest_disabled = true; -#ifdef CONFIG_FTRACE_STARTUP_TEST - printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n", - type->name); -#endif + disable_tracing_selftest("running a tracer"); - out_unlock: - return ret; + return 0; } -void tracing_reset(struct trace_buffer *buf, int cpu) +static void tracing_reset_cpu(struct array_buffer *buf, int cpu) { - struct ring_buffer *buffer = buf->buffer; + struct trace_buffer *buffer = buf->buffer; if (!buffer) return; @@ -1687,10 +2427,9 @@ void tracing_reset(struct trace_buffer *buf, int cpu) ring_buffer_record_enable(buffer); } -void tracing_reset_online_cpus(struct trace_buffer *buf) +void tracing_reset_online_cpus(struct array_buffer *buf) { - struct ring_buffer *buffer = buf->buffer; - int cpu; + struct trace_buffer *buffer = buf->buffer; if (!buffer) return; @@ -1702,96 +2441,52 @@ void tracing_reset_online_cpus(struct trace_buffer *buf) buf->time_start = buffer_ftrace_now(buf, buf->cpu); - for_each_online_cpu(cpu) - ring_buffer_reset_cpu(buffer, cpu); + ring_buffer_reset_online_cpus(buffer); ring_buffer_record_enable(buffer); } -/* Must have trace_types_lock held */ -void tracing_reset_all_online_cpus(void) +static void tracing_reset_all_cpus(struct array_buffer *buf) { - struct trace_array *tr; + struct trace_buffer *buffer = buf->buffer; - list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (!tr->clear_trace) - continue; - tr->clear_trace = false; - tracing_reset_online_cpus(&tr->trace_buffer); -#ifdef CONFIG_TRACER_MAX_TRACE - tracing_reset_online_cpus(&tr->max_buffer); -#endif - } -} + if (!buffer) + return; -static int *tgid_map; + ring_buffer_record_disable(buffer); -#define SAVED_CMDLINES_DEFAULT 128 -#define NO_CMDLINE_MAP UINT_MAX -static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; -struct saved_cmdlines_buffer { - unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; - unsigned *map_cmdline_to_pid; - unsigned cmdline_num; - int cmdline_idx; - char *saved_cmdlines; -}; -static struct saved_cmdlines_buffer *savedcmd; + /* Make sure all commits have finished */ + synchronize_rcu(); -/* temporary disable recording */ -static atomic_t trace_record_taskinfo_disabled __read_mostly; + buf->time_start = buffer_ftrace_now(buf, buf->cpu); -static inline char *get_saved_cmdlines(int idx) -{ - return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; -} + ring_buffer_reset(buffer); -static inline void set_cmdline(int idx, const char *cmdline) -{ - memcpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); + ring_buffer_record_enable(buffer); } -static int allocate_cmdlines_buffer(unsigned int val, - struct saved_cmdlines_buffer *s) +/* Must have trace_types_lock held */ +void tracing_reset_all_online_cpus_unlocked(void) { - s->map_cmdline_to_pid = kmalloc_array(val, - sizeof(*s->map_cmdline_to_pid), - GFP_KERNEL); - if (!s->map_cmdline_to_pid) - return -ENOMEM; - - s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL); - if (!s->saved_cmdlines) { - kfree(s->map_cmdline_to_pid); - return -ENOMEM; - } + struct trace_array *tr; - s->cmdline_idx = 0; - s->cmdline_num = val; - memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, - sizeof(s->map_pid_to_cmdline)); - memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, - val * sizeof(*s->map_cmdline_to_pid)); + lockdep_assert_held(&trace_types_lock); - return 0; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (!tr->clear_trace) + continue; + tr->clear_trace = false; + tracing_reset_online_cpus(&tr->array_buffer); +#ifdef CONFIG_TRACER_MAX_TRACE + tracing_reset_online_cpus(&tr->max_buffer); +#endif + } } -static int trace_create_savedcmd(void) +void tracing_reset_all_online_cpus(void) { - int ret; - - savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); - if (!savedcmd) - return -ENOMEM; - - ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd); - if (ret < 0) { - kfree(savedcmd); - savedcmd = NULL; - return -ENOMEM; - } - - return 0; + guard(mutex)(&trace_types_lock); + tracing_reset_all_online_cpus_unlocked(); } int is_tracing_stopped(void) @@ -1799,320 +2494,83 @@ int is_tracing_stopped(void) return global_trace.stop_count; } -/** - * tracing_start - quick start of the tracer - * - * If tracing is enabled but was stopped by tracing_stop, - * this will start the tracer back up. - */ -void tracing_start(void) +static void tracing_start_tr(struct trace_array *tr) { - struct ring_buffer *buffer; - unsigned long flags; + struct trace_buffer *buffer; if (tracing_disabled) return; - raw_spin_lock_irqsave(&global_trace.start_lock, flags); - if (--global_trace.stop_count) { - if (global_trace.stop_count < 0) { + guard(raw_spinlock_irqsave)(&tr->start_lock); + if (--tr->stop_count) { + if (WARN_ON_ONCE(tr->stop_count < 0)) { /* Someone screwed up their debugging */ - WARN_ON_ONCE(1); - global_trace.stop_count = 0; + tr->stop_count = 0; } - goto out; + return; } /* Prevent the buffers from switching */ - arch_spin_lock(&global_trace.max_lock); + arch_spin_lock(&tr->max_lock); - buffer = global_trace.trace_buffer.buffer; + buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE - buffer = global_trace.max_buffer.buffer; + buffer = tr->max_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #endif - arch_spin_unlock(&global_trace.max_lock); - - out: - raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); -} - -static void tracing_start_tr(struct trace_array *tr) -{ - struct ring_buffer *buffer; - unsigned long flags; - - if (tracing_disabled) - return; - - /* If global, we need to also start the max tracer */ - if (tr->flags & TRACE_ARRAY_FL_GLOBAL) - return tracing_start(); - - raw_spin_lock_irqsave(&tr->start_lock, flags); - - if (--tr->stop_count) { - if (tr->stop_count < 0) { - /* Someone screwed up their debugging */ - WARN_ON_ONCE(1); - tr->stop_count = 0; - } - goto out; - } - - buffer = tr->trace_buffer.buffer; - if (buffer) - ring_buffer_record_enable(buffer); - - out: - raw_spin_unlock_irqrestore(&tr->start_lock, flags); + arch_spin_unlock(&tr->max_lock); } /** - * tracing_stop - quick stop of the tracer + * tracing_start - quick start of the tracer * - * Light weight way to stop tracing. Use in conjunction with - * tracing_start. + * If tracing is enabled but was stopped by tracing_stop, + * this will start the tracer back up. */ -void tracing_stop(void) +void tracing_start(void) + { - struct ring_buffer *buffer; - unsigned long flags; + return tracing_start_tr(&global_trace); +} - raw_spin_lock_irqsave(&global_trace.start_lock, flags); - if (global_trace.stop_count++) - goto out; +static void tracing_stop_tr(struct trace_array *tr) +{ + struct trace_buffer *buffer; + + guard(raw_spinlock_irqsave)(&tr->start_lock); + if (tr->stop_count++) + return; /* Prevent the buffers from switching */ - arch_spin_lock(&global_trace.max_lock); + arch_spin_lock(&tr->max_lock); - buffer = global_trace.trace_buffer.buffer; + buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE - buffer = global_trace.max_buffer.buffer; + buffer = tr->max_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #endif - arch_spin_unlock(&global_trace.max_lock); - - out: - raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); -} - -static void tracing_stop_tr(struct trace_array *tr) -{ - struct ring_buffer *buffer; - unsigned long flags; - - /* If global, we need to also stop the max tracer */ - if (tr->flags & TRACE_ARRAY_FL_GLOBAL) - return tracing_stop(); - - raw_spin_lock_irqsave(&tr->start_lock, flags); - if (tr->stop_count++) - goto out; - - buffer = tr->trace_buffer.buffer; - if (buffer) - ring_buffer_record_disable(buffer); - - out: - raw_spin_unlock_irqrestore(&tr->start_lock, flags); -} - -static int trace_save_cmdline(struct task_struct *tsk) -{ - unsigned pid, idx; - - /* treat recording of idle task as a success */ - if (!tsk->pid) - return 1; - - if (unlikely(tsk->pid > PID_MAX_DEFAULT)) - return 0; - - /* - * It's not the end of the world if we don't get - * the lock, but we also don't want to spin - * nor do we want to disable interrupts, - * so if we miss here, then better luck next time. - */ - if (!arch_spin_trylock(&trace_cmdline_lock)) - return 0; - - idx = savedcmd->map_pid_to_cmdline[tsk->pid]; - if (idx == NO_CMDLINE_MAP) { - idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num; - - /* - * Check whether the cmdline buffer at idx has a pid - * mapped. We are going to overwrite that entry so we - * need to clear the map_pid_to_cmdline. Otherwise we - * would read the new comm for the old pid. - */ - pid = savedcmd->map_cmdline_to_pid[idx]; - if (pid != NO_CMDLINE_MAP) - savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP; - - savedcmd->map_cmdline_to_pid[idx] = tsk->pid; - savedcmd->map_pid_to_cmdline[tsk->pid] = idx; - - savedcmd->cmdline_idx = idx; - } - - set_cmdline(idx, tsk->comm); - - arch_spin_unlock(&trace_cmdline_lock); - - return 1; -} - -static void __trace_find_cmdline(int pid, char comm[]) -{ - unsigned map; - - if (!pid) { - strcpy(comm, "<idle>"); - return; - } - - if (WARN_ON_ONCE(pid < 0)) { - strcpy(comm, "<XXX>"); - return; - } - - if (pid > PID_MAX_DEFAULT) { - strcpy(comm, "<...>"); - return; - } - - map = savedcmd->map_pid_to_cmdline[pid]; - if (map != NO_CMDLINE_MAP) - strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN); - else - strcpy(comm, "<...>"); -} - -void trace_find_cmdline(int pid, char comm[]) -{ - preempt_disable(); - arch_spin_lock(&trace_cmdline_lock); - - __trace_find_cmdline(pid, comm); - - arch_spin_unlock(&trace_cmdline_lock); - preempt_enable(); -} - -int trace_find_tgid(int pid) -{ - if (unlikely(!tgid_map || !pid || pid > PID_MAX_DEFAULT)) - return 0; - - return tgid_map[pid]; -} - -static int trace_save_tgid(struct task_struct *tsk) -{ - /* treat recording of idle task as a success */ - if (!tsk->pid) - return 1; - - if (unlikely(!tgid_map || tsk->pid > PID_MAX_DEFAULT)) - return 0; - - tgid_map[tsk->pid] = tsk->tgid; - return 1; -} - -static bool tracing_record_taskinfo_skip(int flags) -{ - if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) - return true; - if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on()) - return true; - if (!__this_cpu_read(trace_taskinfo_save)) - return true; - return false; -} - -/** - * tracing_record_taskinfo - record the task info of a task - * - * @task - task to record - * @flags - TRACE_RECORD_CMDLINE for recording comm - * - TRACE_RECORD_TGID for recording tgid - */ -void tracing_record_taskinfo(struct task_struct *task, int flags) -{ - bool done; - - if (tracing_record_taskinfo_skip(flags)) - return; - - /* - * Record as much task information as possible. If some fail, continue - * to try to record the others. - */ - done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(task); - done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(task); - - /* If recording any information failed, retry again soon. */ - if (!done) - return; - - __this_cpu_write(trace_taskinfo_save, false); + arch_spin_unlock(&tr->max_lock); } /** - * tracing_record_taskinfo_sched_switch - record task info for sched_switch + * tracing_stop - quick stop of the tracer * - * @prev - previous task during sched_switch - * @next - next task during sched_switch - * @flags - TRACE_RECORD_CMDLINE for recording comm - * TRACE_RECORD_TGID for recording tgid + * Light weight way to stop tracing. Use in conjunction with + * tracing_start. */ -void tracing_record_taskinfo_sched_switch(struct task_struct *prev, - struct task_struct *next, int flags) -{ - bool done; - - if (tracing_record_taskinfo_skip(flags)) - return; - - /* - * Record as much task information as possible. If some fail, continue - * to try to record the others. - */ - done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(prev); - done &= !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(next); - done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(prev); - done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(next); - - /* If recording any information failed, retry again soon. */ - if (!done) - return; - - __this_cpu_write(trace_taskinfo_save, false); -} - -/* Helpers to record a specific task information */ -void tracing_record_cmdline(struct task_struct *task) -{ - tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE); -} - -void tracing_record_tgid(struct task_struct *task) +void tracing_stop(void) { - tracing_record_taskinfo(task, TRACE_RECORD_TGID); + return tracing_stop_tr(&global_trace); } /* @@ -2127,35 +2585,48 @@ enum print_line_t trace_handle_return(struct trace_seq *s) } EXPORT_SYMBOL_GPL(trace_handle_return); -void -tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, - int pc) +static unsigned short migration_disable_value(void) { - struct task_struct *tsk = current; - - entry->preempt_count = pc & 0xff; - entry->pid = (tsk) ? tsk->pid : 0; - entry->flags = -#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT - (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | +#if defined(CONFIG_SMP) + return current->migration_disabled; #else - TRACE_FLAG_IRQS_NOSUPPORT | + return 0; #endif - ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | - ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | - ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | - (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | - (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); } -EXPORT_SYMBOL_GPL(tracing_generic_entry_update); + +unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) +{ + unsigned int trace_flags = irqs_status; + unsigned int pc; + + pc = preempt_count(); + + if (pc & NMI_MASK) + trace_flags |= TRACE_FLAG_NMI; + if (pc & HARDIRQ_MASK) + trace_flags |= TRACE_FLAG_HARDIRQ; + if (in_serving_softirq()) + trace_flags |= TRACE_FLAG_SOFTIRQ; + if (softirq_count() >> (SOFTIRQ_SHIFT + 1)) + trace_flags |= TRACE_FLAG_BH_OFF; + + if (tif_need_resched()) + trace_flags |= TRACE_FLAG_NEED_RESCHED; + if (test_preempt_need_resched()) + trace_flags |= TRACE_FLAG_PREEMPT_RESCHED; + if (IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY) && tif_test_bit(TIF_NEED_RESCHED_LAZY)) + trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY; + return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) | + (min_t(unsigned int, migration_disable_value(), 0xf)) << 4; +} struct ring_buffer_event * -trace_buffer_lock_reserve(struct ring_buffer *buffer, +trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, - unsigned long flags, int pc) + unsigned int trace_ctx) { - return __trace_buffer_lock_reserve(buffer, type, len, flags, pc); + return __trace_buffer_lock_reserve(buffer, type, len, trace_ctx); } DEFINE_PER_CPU(struct ring_buffer_event *, trace_buffered_event); @@ -2190,31 +2661,28 @@ void trace_buffered_event_enable(void) for_each_tracing_cpu(cpu) { page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); - if (!page) - goto failed; + /* This is just an optimization and can handle failures */ + if (!page) { + pr_err("Failed to allocate event buffer\n"); + break; + } event = page_address(page); memset(event, 0, sizeof(*event)); per_cpu(trace_buffered_event, cpu) = event; - preempt_disable(); - if (cpu == smp_processor_id() && - this_cpu_read(trace_buffered_event) != - per_cpu(trace_buffered_event, cpu)) - WARN_ON_ONCE(1); - preempt_enable(); + scoped_guard(preempt,) { + if (cpu == smp_processor_id() && + __this_cpu_read(trace_buffered_event) != + per_cpu(trace_buffered_event, cpu)) + WARN_ON_ONCE(1); + } } - - return; - failed: - trace_buffered_event_disable(); } static void enable_trace_buffered_event(void *data) { - /* Probably not needed, but do it anyway */ - smp_rmb(); this_cpu_dec(trace_buffered_event_cnt); } @@ -2243,11 +2711,9 @@ void trace_buffered_event_disable(void) if (--trace_buffered_event_ref) return; - preempt_disable(); /* For each CPU, set the buffer as used. */ - smp_call_function_many(tracing_buffer_mask, - disable_trace_buffered_event, NULL, 1); - preempt_enable(); + on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event, + NULL, true); /* Wait for all current users to finish */ synchronize_rcu(); @@ -2256,68 +2722,113 @@ void trace_buffered_event_disable(void) free_page((unsigned long)per_cpu(trace_buffered_event, cpu)); per_cpu(trace_buffered_event, cpu) = NULL; } + /* - * Make sure trace_buffered_event is NULL before clearing - * trace_buffered_event_cnt. + * Wait for all CPUs that potentially started checking if they can use + * their event buffer only after the previous synchronize_rcu() call and + * they still read a valid pointer from trace_buffered_event. It must be + * ensured they don't see cleared trace_buffered_event_cnt else they + * could wrongly decide to use the pointed-to buffer which is now freed. */ - smp_wmb(); + synchronize_rcu(); - preempt_disable(); - /* Do the work on each cpu */ - smp_call_function_many(tracing_buffer_mask, - enable_trace_buffered_event, NULL, 1); - preempt_enable(); + /* For each CPU, relinquish the buffer */ + on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL, + true); } -static struct ring_buffer *temp_buffer; +static struct trace_buffer *temp_buffer; struct ring_buffer_event * -trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, +trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, struct trace_event_file *trace_file, int type, unsigned long len, - unsigned long flags, int pc) + unsigned int trace_ctx) { struct ring_buffer_event *entry; + struct trace_array *tr = trace_file->tr; int val; - *current_rb = trace_file->tr->trace_buffer.buffer; - - if (!ring_buffer_time_stamp_abs(*current_rb) && (trace_file->flags & - (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) && - (entry = this_cpu_read(trace_buffered_event))) { - /* Try to use the per cpu buffer first */ - val = this_cpu_inc_return(trace_buffered_event_cnt); - if (val == 1) { - trace_event_setup(entry, type, flags, pc); - entry->array[0] = len; - return entry; + *current_rb = tr->array_buffer.buffer; + + if (!tr->no_filter_buffering_ref && + (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED))) { + preempt_disable_notrace(); + /* + * Filtering is on, so try to use the per cpu buffer first. + * This buffer will simulate a ring_buffer_event, + * where the type_len is zero and the array[0] will + * hold the full length. + * (see include/linux/ring-buffer.h for details on + * how the ring_buffer_event is structured). + * + * Using a temp buffer during filtering and copying it + * on a matched filter is quicker than writing directly + * into the ring buffer and then discarding it when + * it doesn't match. That is because the discard + * requires several atomic operations to get right. + * Copying on match and doing nothing on a failed match + * is still quicker than no copy on match, but having + * to discard out of the ring buffer on a failed match. + */ + if ((entry = __this_cpu_read(trace_buffered_event))) { + int max_len = PAGE_SIZE - struct_size(entry, array, 1); + + val = this_cpu_inc_return(trace_buffered_event_cnt); + + /* + * Preemption is disabled, but interrupts and NMIs + * can still come in now. If that happens after + * the above increment, then it will have to go + * back to the old method of allocating the event + * on the ring buffer, and if the filter fails, it + * will have to call ring_buffer_discard_commit() + * to remove it. + * + * Need to also check the unlikely case that the + * length is bigger than the temp buffer size. + * If that happens, then the reserve is pretty much + * guaranteed to fail, as the ring buffer currently + * only allows events less than a page. But that may + * change in the future, so let the ring buffer reserve + * handle the failure in that case. + */ + if (val == 1 && likely(len <= max_len)) { + trace_event_setup(entry, type, trace_ctx); + entry->array[0] = len; + /* Return with preemption disabled */ + return entry; + } + this_cpu_dec(trace_buffered_event_cnt); } - this_cpu_dec(trace_buffered_event_cnt); + /* __trace_buffer_lock_reserve() disables preemption */ + preempt_enable_notrace(); } - entry = __trace_buffer_lock_reserve(*current_rb, - type, len, flags, pc); + entry = __trace_buffer_lock_reserve(*current_rb, type, len, + trace_ctx); /* * If tracing is off, but we have triggers enabled * we still need to look at the event data. Use the temp_buffer - * to store the trace event for the tigger to use. It's recusive + * to store the trace event for the trigger to use. It's recursive * safe and will not be recorded anywhere. */ if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) { *current_rb = temp_buffer; - entry = __trace_buffer_lock_reserve(*current_rb, - type, len, flags, pc); + entry = __trace_buffer_lock_reserve(*current_rb, type, len, + trace_ctx); } return entry; } EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); -static DEFINE_SPINLOCK(tracepoint_iter_lock); +static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock); static DEFINE_MUTEX(tracepoint_printk_mutex); static void output_printk(struct trace_event_buffer *fbuffer) { struct trace_event_call *event_call; + struct trace_event_file *file; struct trace_event *event; unsigned long flags; struct trace_iterator *iter = tracepoint_print_iter; @@ -2331,26 +2842,32 @@ static void output_printk(struct trace_event_buffer *fbuffer) !event_call->event.funcs->trace) return; + file = fbuffer->trace_file; + if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || + (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && + !filter_match_preds(file->filter, fbuffer->entry))) + return; + event = &fbuffer->trace_file->event_call->event; - spin_lock_irqsave(&tracepoint_iter_lock, flags); + raw_spin_lock_irqsave(&tracepoint_iter_lock, flags); trace_seq_init(&iter->seq); iter->ent = fbuffer->entry; event_call->event.funcs->trace(iter, 0, event); trace_seq_putc(&iter->seq, 0); printk("%s", iter->seq.buffer); - spin_unlock_irqrestore(&tracepoint_iter_lock, flags); + raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags); } -int tracepoint_printk_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, +int tracepoint_printk_sysctl(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int save_tracepoint_printk; int ret; - mutex_lock(&tracepoint_printk_mutex); + guard(mutex)(&tracepoint_printk_mutex); save_tracepoint_printk = tracepoint_printk; ret = proc_dointvec(table, write, buffer, lenp, ppos); @@ -2363,27 +2880,38 @@ int tracepoint_printk_sysctl(struct ctl_table *table, int write, tracepoint_printk = 0; if (save_tracepoint_printk == tracepoint_printk) - goto out; + return ret; if (tracepoint_printk) static_key_enable(&tracepoint_printk_key.key); else static_key_disable(&tracepoint_printk_key.key); - out: - mutex_unlock(&tracepoint_printk_mutex); - return ret; } void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) { + enum event_trigger_type tt = ETT_NONE; + struct trace_event_file *file = fbuffer->trace_file; + + if (__event_trigger_test_discard(file, fbuffer->buffer, fbuffer->event, + fbuffer->entry, &tt)) + goto discard; + if (static_key_false(&tracepoint_printk_key.key)) output_printk(fbuffer); - event_trigger_unlock_commit(fbuffer->trace_file, fbuffer->buffer, - fbuffer->event, fbuffer->entry, - fbuffer->flags, fbuffer->pc); + if (static_branch_unlikely(&trace_event_exports_enabled)) + ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT); + + trace_buffer_unlock_commit_regs(file->tr, fbuffer->buffer, + fbuffer->event, fbuffer->trace_ctx, fbuffer->regs); + +discard: + if (tt) + event_triggers_post_call(file, tt); + } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); @@ -2397,9 +2925,9 @@ EXPORT_SYMBOL_GPL(trace_event_buffer_commit); # define STACK_SKIP 3 void trace_buffer_unlock_commit_regs(struct trace_array *tr, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event, - unsigned long flags, int pc, + unsigned int trace_ctx, struct pt_regs *regs) { __buffer_unlock_commit(buffer, event); @@ -2410,191 +2938,80 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, * and mmiotrace, but that's ok if they lose a function or * two. They are not that meaningful. */ - ftrace_trace_stack(tr, buffer, flags, regs ? 0 : STACK_SKIP, pc, regs); - ftrace_trace_userstack(buffer, flags, pc); + ftrace_trace_stack(tr, buffer, trace_ctx, regs ? 0 : STACK_SKIP, regs); + ftrace_trace_userstack(tr, buffer, trace_ctx); } /* * Similar to trace_buffer_unlock_commit_regs() but do not dump stack. */ void -trace_buffer_unlock_commit_nostack(struct ring_buffer *buffer, +trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, struct ring_buffer_event *event) { __buffer_unlock_commit(buffer, event); } -static void -trace_process_export(struct trace_export *export, - struct ring_buffer_event *event) -{ - struct trace_entry *entry; - unsigned int size = 0; - - entry = ring_buffer_event_data(event); - size = ring_buffer_event_length(event); - export->write(export, entry, size); -} - -static DEFINE_MUTEX(ftrace_export_lock); - -static struct trace_export __rcu *ftrace_exports_list __read_mostly; - -static DEFINE_STATIC_KEY_FALSE(ftrace_exports_enabled); - -static inline void ftrace_exports_enable(void) -{ - static_branch_enable(&ftrace_exports_enabled); -} - -static inline void ftrace_exports_disable(void) -{ - static_branch_disable(&ftrace_exports_enabled); -} - -static void ftrace_exports(struct ring_buffer_event *event) -{ - struct trace_export *export; - - preempt_disable_notrace(); - - export = rcu_dereference_raw_notrace(ftrace_exports_list); - while (export) { - trace_process_export(export, event); - export = rcu_dereference_raw_notrace(export->next); - } - - preempt_enable_notrace(); -} - -static inline void -add_trace_export(struct trace_export **list, struct trace_export *export) -{ - rcu_assign_pointer(export->next, *list); - /* - * We are entering export into the list but another - * CPU might be walking that list. We need to make sure - * the export->next pointer is valid before another CPU sees - * the export pointer included into the list. - */ - rcu_assign_pointer(*list, export); -} - -static inline int -rm_trace_export(struct trace_export **list, struct trace_export *export) -{ - struct trace_export **p; - - for (p = list; *p != NULL; p = &(*p)->next) - if (*p == export) - break; - - if (*p != export) - return -1; - - rcu_assign_pointer(*p, (*p)->next); - - return 0; -} - -static inline void -add_ftrace_export(struct trace_export **list, struct trace_export *export) -{ - if (*list == NULL) - ftrace_exports_enable(); - - add_trace_export(list, export); -} - -static inline int -rm_ftrace_export(struct trace_export **list, struct trace_export *export) -{ - int ret; - - ret = rm_trace_export(list, export); - if (*list == NULL) - ftrace_exports_disable(); - - return ret; -} - -int register_ftrace_export(struct trace_export *export) -{ - if (WARN_ON_ONCE(!export->write)) - return -1; - - mutex_lock(&ftrace_export_lock); - - add_ftrace_export(&ftrace_exports_list, export); - - mutex_unlock(&ftrace_export_lock); - - return 0; -} -EXPORT_SYMBOL_GPL(register_ftrace_export); - -int unregister_ftrace_export(struct trace_export *export) -{ - int ret; - - mutex_lock(&ftrace_export_lock); - - ret = rm_ftrace_export(&ftrace_exports_list, export); - - mutex_unlock(&ftrace_export_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(unregister_ftrace_export); - void -trace_function(struct trace_array *tr, - unsigned long ip, unsigned long parent_ip, unsigned long flags, - int pc) +trace_function(struct trace_array *tr, unsigned long ip, unsigned long + parent_ip, unsigned int trace_ctx, struct ftrace_regs *fregs) { - struct trace_event_call *call = &event_function; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; + int size = sizeof(*entry); + + size += FTRACE_REGS_MAX_ARGS * !!fregs * sizeof(long); - event = __trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), - flags, pc); + event = __trace_buffer_lock_reserve(buffer, TRACE_FN, size, + trace_ctx); if (!event) return; entry = ring_buffer_event_data(event); entry->ip = ip; entry->parent_ip = parent_ip; - if (!call_filter_check_discard(call, entry, buffer, event)) { - if (static_branch_unlikely(&ftrace_exports_enabled)) - ftrace_exports(event); - __buffer_unlock_commit(buffer, event); +#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API + if (fregs) { + for (int i = 0; i < FTRACE_REGS_MAX_ARGS; i++) + entry->args[i] = ftrace_regs_get_argument(fregs, i); } +#endif + + if (static_branch_unlikely(&trace_function_exports_enabled)) + ftrace_exports(event, TRACE_EXPORT_FUNCTION); + __buffer_unlock_commit(buffer, event); } #ifdef CONFIG_STACKTRACE -#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long)) +/* Allow 4 levels of nesting: normal, softirq, irq, NMI */ +#define FTRACE_KSTACK_NESTING 4 + +#define FTRACE_KSTACK_ENTRIES (SZ_4K / FTRACE_KSTACK_NESTING) + struct ftrace_stack { - unsigned long calls[FTRACE_STACK_MAX_ENTRIES]; + unsigned long calls[FTRACE_KSTACK_ENTRIES]; +}; + + +struct ftrace_stacks { + struct ftrace_stack stacks[FTRACE_KSTACK_NESTING]; }; -static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack); +static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks); static DEFINE_PER_CPU(int, ftrace_stack_reserve); -static void __ftrace_trace_stack(struct ring_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs) +static void __ftrace_trace_stack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs) { - struct trace_event_call *call = &event_kernel_stack; struct ring_buffer_event *event; + unsigned int size, nr_entries; + struct ftrace_stack *fstack; struct stack_entry *entry; - struct stack_trace trace; - int use_stack; - int size = FTRACE_STACK_ENTRIES; - - trace.nr_entries = 0; - trace.skip = skip; + int stackidx; /* * Add one, for this function and the call to save_stack_trace() @@ -2602,109 +3019,105 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, */ #ifndef CONFIG_UNWINDER_ORC if (!regs) - trace.skip++; + skip++; #endif - /* - * Since events can happen in NMIs there's no safe way to - * use the per cpu ftrace_stacks. We reserve it and if an interrupt - * or NMI comes in, it will just have to use the default - * FTRACE_STACK_SIZE. - */ - preempt_disable_notrace(); + guard(preempt_notrace)(); + + stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1; + + /* This should never happen. If it does, yell once and skip */ + if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING)) + goto out; - use_stack = __this_cpu_inc_return(ftrace_stack_reserve); /* - * We don't need any atomic variables, just a barrier. - * If an interrupt comes in, we don't care, because it would - * have exited and put the counter back to what we want. - * We just need a barrier to keep gcc from moving things - * around. + * The above __this_cpu_inc_return() is 'atomic' cpu local. An + * interrupt will either see the value pre increment or post + * increment. If the interrupt happens pre increment it will have + * restored the counter when it returns. We just need a barrier to + * keep gcc from moving things around. */ barrier(); - if (use_stack == 1) { - trace.entries = this_cpu_ptr(ftrace_stack.calls); - trace.max_entries = FTRACE_STACK_MAX_ENTRIES; - if (regs) - save_stack_trace_regs(regs, &trace); - else - save_stack_trace(&trace); + fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx; + size = ARRAY_SIZE(fstack->calls); - if (trace.nr_entries > size) - size = trace.nr_entries; - } else - /* From now on, use_stack is a boolean */ - use_stack = 0; + if (regs) { + nr_entries = stack_trace_save_regs(regs, fstack->calls, + size, skip); + } else { + nr_entries = stack_trace_save(fstack->calls, size, skip); + } - size *= sizeof(unsigned long); +#ifdef CONFIG_DYNAMIC_FTRACE + /* Mark entry of stack trace as trampoline code */ + if (tr->ops && tr->ops->trampoline) { + unsigned long tramp_start = tr->ops->trampoline; + unsigned long tramp_end = tramp_start + tr->ops->trampoline_size; + unsigned long *calls = fstack->calls; + + for (int i = 0; i < nr_entries; i++) { + if (calls[i] >= tramp_start && calls[i] < tramp_end) + calls[i] = FTRACE_TRAMPOLINE_MARKER; + } + } +#endif event = __trace_buffer_lock_reserve(buffer, TRACE_STACK, - sizeof(*entry) + size, flags, pc); + struct_size(entry, caller, nr_entries), + trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); - memset(&entry->caller, 0, size); - - if (use_stack) - memcpy(&entry->caller, trace.entries, - trace.nr_entries * sizeof(unsigned long)); - else { - trace.max_entries = FTRACE_STACK_ENTRIES; - trace.entries = entry->caller; - if (regs) - save_stack_trace_regs(regs, &trace); - else - save_stack_trace(&trace); - } - - entry->size = trace.nr_entries; + entry->size = nr_entries; + memcpy(&entry->caller, fstack->calls, + flex_array_size(entry, caller, nr_entries)); - if (!call_filter_check_discard(call, entry, buffer, event)) - __buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); out: /* Again, don't let gcc optimize things here */ barrier(); __this_cpu_dec(ftrace_stack_reserve); - preempt_enable_notrace(); - } static inline void ftrace_trace_stack(struct trace_array *tr, - struct ring_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs) + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs) { - if (!(tr->trace_flags & TRACE_ITER_STACKTRACE)) + if (!(tr->trace_flags & TRACE_ITER(STACKTRACE))) return; - __ftrace_trace_stack(buffer, flags, skip, pc, regs); + __ftrace_trace_stack(tr, buffer, trace_ctx, skip, regs); } -void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, - int pc) +void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, + int skip) { - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; if (rcu_is_watching()) { - __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + __ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL); return; } + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_GENERIC_ENTRY))) + return; + /* - * When an NMI triggers, RCU is enabled via rcu_nmi_enter(), + * When an NMI triggers, RCU is enabled via ct_nmi_enter(), * but if the above rcu_is_watching() failed, then the NMI - * triggered someplace critical, and rcu_irq_enter() should + * triggered someplace critical, and ct_irq_enter() should * not be called from NMI. */ if (unlikely(in_nmi())) return; - rcu_irq_enter_irqson(); - __ftrace_trace_stack(buffer, flags, skip, pc, NULL); - rcu_irq_exit_irqson(); + ct_irq_enter_irqson(); + __ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL); + ct_irq_exit_irqson(); } /** @@ -2713,33 +3126,29 @@ void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, */ void trace_dump_stack(int skip) { - unsigned long flags; - if (tracing_disabled || tracing_selftest_running) return; - local_save_flags(flags); - #ifndef CONFIG_UNWINDER_ORC /* Skip 1 to skip this function. */ skip++; #endif - __ftrace_trace_stack(global_trace.trace_buffer.buffer, - flags, skip, preempt_count(), NULL); + __ftrace_trace_stack(printk_trace, printk_trace->array_buffer.buffer, + tracing_gen_ctx(), skip, NULL); } EXPORT_SYMBOL_GPL(trace_dump_stack); +#ifdef CONFIG_USER_STACKTRACE_SUPPORT static DEFINE_PER_CPU(int, user_stack_count); -void -ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) +static void +ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned int trace_ctx) { - struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; - struct stack_trace trace; - if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE)) + if (!(tr->trace_flags & TRACE_ITER(USERSTACKTRACE))) return; /* @@ -2753,14 +3162,14 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) * prevent recursion, since the user stack tracing may * trigger other kernel events. */ - preempt_disable(); + guard(preempt)(); if (__this_cpu_read(user_stack_count)) - goto out; + return; __this_cpu_inc(user_stack_count); event = __trace_buffer_lock_reserve(buffer, TRACE_USER_STACK, - sizeof(*entry), flags, pc); + sizeof(*entry), trace_ctx); if (!event) goto out_drop_count; entry = ring_buffer_event_data(event); @@ -2768,54 +3177,80 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) entry->tgid = current->tgid; memset(&entry->caller, 0, sizeof(entry->caller)); - trace.nr_entries = 0; - trace.max_entries = FTRACE_STACK_ENTRIES; - trace.skip = 0; - trace.entries = entry->caller; - - save_stack_trace_user(&trace); - if (!call_filter_check_discard(call, entry, buffer, event)) - __buffer_unlock_commit(buffer, event); + stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES); + __buffer_unlock_commit(buffer, event); out_drop_count: __this_cpu_dec(user_stack_count); - out: - preempt_enable(); } - -#ifdef UNUSED -static void __trace_userstack(struct trace_array *tr, unsigned long flags) +#else /* CONFIG_USER_STACKTRACE_SUPPORT */ +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx) { - ftrace_trace_userstack(tr, flags, preempt_count()); } -#endif /* UNUSED */ +#endif /* !CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* CONFIG_STACKTRACE */ +static inline void +func_repeats_set_delta_ts(struct func_repeats_entry *entry, + unsigned long long delta) +{ + entry->bottom_delta_ts = delta & U32_MAX; + entry->top_delta_ts = (delta >> 32); +} + +void trace_last_func_repeats(struct trace_array *tr, + struct trace_func_repeats *last_info, + unsigned int trace_ctx) +{ + struct trace_buffer *buffer = tr->array_buffer.buffer; + struct func_repeats_entry *entry; + struct ring_buffer_event *event; + u64 delta; + + event = __trace_buffer_lock_reserve(buffer, TRACE_FUNC_REPEATS, + sizeof(*entry), trace_ctx); + if (!event) + return; + + delta = ring_buffer_event_time_stamp(buffer, event) - + last_info->ts_last_call; + + entry = ring_buffer_event_data(event); + entry->ip = last_info->ip; + entry->parent_ip = last_info->parent_ip; + entry->count = last_info->count; + func_repeats_set_delta_ts(entry, delta); + + __buffer_unlock_commit(buffer, event); +} + /* created for use with alloc_percpu */ struct trace_buffer_struct { int nesting; char buffer[4][TRACE_BUF_SIZE]; }; -static struct trace_buffer_struct *trace_percpu_buffer; +static struct trace_buffer_struct __percpu *trace_percpu_buffer; /* - * Thise allows for lockless recording. If we're nested too deeply, then + * This allows for lockless recording. If we're nested too deeply, then * this returns NULL. */ static char *get_trace_buf(void) { struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); - if (!buffer || buffer->nesting >= 4) + if (!trace_percpu_buffer || buffer->nesting >= 4) return NULL; buffer->nesting++; /* Interrupts must see nesting incremented before we use the buffer */ barrier(); - return &buffer->buffer[buffer->nesting][0]; + return &buffer->buffer[buffer->nesting - 1][0]; } static void put_trace_buf(void) @@ -2827,10 +3262,13 @@ static void put_trace_buf(void) static int alloc_percpu_trace_buffer(void) { - struct trace_buffer_struct *buffers; + struct trace_buffer_struct __percpu *buffers; + + if (trace_percpu_buffer) + return 0; buffers = alloc_percpu(struct trace_buffer_struct); - if (WARN(!buffers, "Could not allocate percpu trace_printk buffer")) + if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer")) return -ENOMEM; trace_percpu_buffer = buffers; @@ -2865,7 +3303,7 @@ void trace_printk_init_buffers(void) pr_warn("**********************************************************\n"); /* Expand the buffers to set size */ - tracing_update_buffers(); + tracing_update_buffers(&global_trace); buffers_allocated = 1; @@ -2875,9 +3313,10 @@ void trace_printk_init_buffers(void) * directly here. If the global_trace.buffer is already * allocated here, then this was called by module code. */ - if (global_trace.trace_buffer.buffer) + if (global_trace.array_buffer.buffer) tracing_start_cmdline_record(); } +EXPORT_SYMBOL_GPL(trace_printk_init_buffers); void trace_printk_start_comm(void) { @@ -2900,18 +3339,22 @@ static void trace_printk_start_stop_comm(int enabled) /** * trace_vbprintk - write binary msg to tracing buffer - * + * @ip: The address of the caller + * @fmt: The string format to write to the buffer + * @args: Arguments for @fmt */ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) { - struct trace_event_call *call = &event_bprint; struct ring_buffer_event *event; - struct ring_buffer *buffer; - struct trace_array *tr = &global_trace; + struct trace_buffer *buffer; + struct trace_array *tr = READ_ONCE(printk_trace); struct bprint_entry *entry; - unsigned long flags; + unsigned int trace_ctx; char *tbuffer; - int len = 0, size, pc; + int len = 0, size; + + if (!printk_binsafe(tr)) + return trace_vprintk(ip, fmt, args); if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; @@ -2919,8 +3362,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); - pc = preempt_count(); - preempt_disable_notrace(); + trace_ctx = tracing_gen_ctx(); + guard(preempt_notrace)(); tbuffer = get_trace_buf(); if (!tbuffer) { @@ -2931,56 +3374,51 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) - goto out; + goto out_put; - local_save_flags(flags); size = sizeof(*entry) + sizeof(u32) * len; - buffer = tr->trace_buffer.buffer; - event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, - flags, pc); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->ip = ip; - entry->fmt = fmt; - - memcpy(entry->buf, tbuffer, sizeof(u32) * len); - if (!call_filter_check_discard(call, entry, buffer, event)) { + buffer = tr->array_buffer.buffer; + scoped_guard(ring_buffer_nest, buffer) { + event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, + trace_ctx); + if (!event) + goto out_put; + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->fmt = fmt; + + memcpy(entry->buf, tbuffer, sizeof(u32) * len); __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 6, pc, NULL); + ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL); } - -out: +out_put: put_trace_buf(); out_nobuffer: - preempt_enable_notrace(); unpause_graph_tracing(); return len; } EXPORT_SYMBOL_GPL(trace_vbprintk); -__printf(3, 0) -static int -__trace_array_vprintk(struct ring_buffer *buffer, - unsigned long ip, const char *fmt, va_list args) +static __printf(3, 0) +int __trace_array_vprintk(struct trace_buffer *buffer, + unsigned long ip, const char *fmt, va_list args) { - struct trace_event_call *call = &event_print; struct ring_buffer_event *event; - int len = 0, size, pc; + int len = 0, size; struct print_entry *entry; - unsigned long flags; + unsigned int trace_ctx; char *tbuffer; - if (tracing_disabled || tracing_selftest_running) + if (tracing_disabled) return 0; /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); - pc = preempt_count(); - preempt_disable_notrace(); + trace_ctx = tracing_gen_ctx(); + guard(preempt_notrace)(); tbuffer = get_trace_buf(); @@ -2991,46 +3429,71 @@ __trace_array_vprintk(struct ring_buffer *buffer, len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); - local_save_flags(flags); size = sizeof(*entry) + len + 1; - event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, - flags, pc); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->ip = ip; + scoped_guard(ring_buffer_nest, buffer) { + event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, + trace_ctx); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + entry->ip = ip; - memcpy(&entry->buf, tbuffer, len + 1); - if (!call_filter_check_discard(call, entry, buffer, event)) { + memcpy(&entry->buf, tbuffer, len + 1); __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL); + ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL); } - out: put_trace_buf(); out_nobuffer: - preempt_enable_notrace(); unpause_graph_tracing(); return len; } -__printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { - return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args); + if (tracing_selftest_running && tr == &global_trace) + return 0; + + return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); } -__printf(3, 0) +/** + * trace_array_printk - Print a message to a specific instance + * @tr: The instance trace_array descriptor + * @ip: The instruction pointer that this is called from. + * @fmt: The format to print (printf format) + * + * If a subsystem sets up its own instance, they have the right to + * printk strings into their tracing instance buffer using this + * function. Note, this function will not write into the top level + * buffer (use trace_printk() for that), as writing into the top level + * buffer should only have events that can be individually disabled. + * trace_printk() is only used for debugging a kernel, and should not + * be ever incorporated in normal use. + * + * trace_array_printk() can be used, as it will not add noise to the + * top level tracing buffer. + * + * Note, trace_array_init_printk() must be called on @tr before this + * can be used. + */ int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { int ret; va_list ap; - if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) + if (!tr) + return -ENOENT; + + /* This is only allowed for created instances */ + if (tr == &global_trace) + return 0; + + if (!(tr->trace_flags & TRACE_ITER(PRINTK))) return 0; va_start(ap, fmt); @@ -3038,15 +3501,36 @@ int trace_array_printk(struct trace_array *tr, va_end(ap); return ret; } +EXPORT_SYMBOL_GPL(trace_array_printk); + +/** + * trace_array_init_printk - Initialize buffers for trace_array_printk() + * @tr: The trace array to initialize the buffers for + * + * As trace_array_printk() only writes into instances, they are OK to + * have in the kernel (unlike trace_printk()). This needs to be called + * before trace_array_printk() can be used on a trace_array. + */ +int trace_array_init_printk(struct trace_array *tr) +{ + if (!tr) + return -ENOENT; + + /* This is only allowed for created instances */ + if (tr == &global_trace) + return -EINVAL; + + return alloc_percpu_trace_buffer(); +} +EXPORT_SYMBOL_GPL(trace_array_init_printk); -__printf(3, 4) -int trace_array_printk_buf(struct ring_buffer *buffer, +int trace_array_printk_buf(struct trace_buffer *buffer, unsigned long ip, const char *fmt, ...) { int ret; va_list ap; - if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) + if (!(printk_trace->trace_flags & TRACE_ITER(PRINTK))) return 0; va_start(ap, fmt); @@ -3055,10 +3539,9 @@ int trace_array_printk_buf(struct ring_buffer *buffer, return ret; } -__printf(2, 0) int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { - return trace_array_vprintk(&global_trace, ip, fmt, args); + return trace_array_vprintk(printk_trace, ip, fmt, args); } EXPORT_SYMBOL_GPL(trace_vprintk); @@ -3068,7 +3551,7 @@ static void trace_iterator_increment(struct trace_iterator *iter) iter->idx++; if (buf_iter) - ring_buffer_read(buf_iter, NULL); + ring_buffer_iter_advance(buf_iter); } static struct trace_entry * @@ -3078,11 +3561,15 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); - if (buf_iter) + if (buf_iter) { event = ring_buffer_iter_peek(buf_iter, ts); - else - event = ring_buffer_peek(iter->trace_buffer->buffer, cpu, ts, + if (lost_events) + *lost_events = ring_buffer_iter_dropped(buf_iter) ? + (unsigned long)-1 : 0; + } else { + event = ring_buffer_peek(iter->array_buffer->buffer, cpu, ts, lost_events); + } if (event) { iter->ent_size = ring_buffer_event_length(event); @@ -3096,7 +3583,7 @@ static struct trace_entry * __find_next_entry(struct trace_iterator *iter, int *ent_cpu, unsigned long *missing_events, u64 *ent_ts) { - struct ring_buffer *buffer = iter->trace_buffer->buffer; + struct trace_buffer *buffer = iter->array_buffer->buffer; struct trace_entry *ent, *next = NULL; unsigned long lost_events = 0, next_lost = 0; int cpu_file = iter->cpu_file; @@ -3152,11 +3639,245 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, return next; } +#define STATIC_FMT_BUF_SIZE 128 +static char static_fmt_buf[STATIC_FMT_BUF_SIZE]; + +char *trace_iter_expand_format(struct trace_iterator *iter) +{ + char *tmp; + + /* + * iter->tr is NULL when used with tp_printk, which makes + * this get called where it is not safe to call krealloc(). + */ + if (!iter->tr || iter->fmt == static_fmt_buf) + return NULL; + + tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE, + GFP_KERNEL); + if (tmp) { + iter->fmt_size += STATIC_FMT_BUF_SIZE; + iter->fmt = tmp; + } + + return tmp; +} + +/* Returns true if the string is safe to dereference from an event */ +static bool trace_safe_str(struct trace_iterator *iter, const char *str) +{ + unsigned long addr = (unsigned long)str; + struct trace_event *trace_event; + struct trace_event_call *event; + + /* OK if part of the event data */ + if ((addr >= (unsigned long)iter->ent) && + (addr < (unsigned long)iter->ent + iter->ent_size)) + return true; + + /* OK if part of the temp seq buffer */ + if ((addr >= (unsigned long)iter->tmp_seq.buffer) && + (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE)) + return true; + + /* Core rodata can not be freed */ + if (is_kernel_rodata(addr)) + return true; + + if (trace_is_tracepoint_string(str)) + return true; + + /* + * Now this could be a module event, referencing core module + * data, which is OK. + */ + if (!iter->ent) + return false; + + trace_event = ftrace_find_event(iter->ent->type); + if (!trace_event) + return false; + + event = container_of(trace_event, struct trace_event_call, event); + if ((event->flags & TRACE_EVENT_FL_DYNAMIC) || !event->module) + return false; + + /* Would rather have rodata, but this will suffice */ + if (within_module_core(addr, event->module)) + return true; + + return false; +} + +/** + * ignore_event - Check dereferenced fields while writing to the seq buffer + * @iter: The iterator that holds the seq buffer and the event being printed + * + * At boot up, test_event_printk() will flag any event that dereferences + * a string with "%s" that does exist in the ring buffer. It may still + * be valid, as the string may point to a static string in the kernel + * rodata that never gets freed. But if the string pointer is pointing + * to something that was allocated, there's a chance that it can be freed + * by the time the user reads the trace. This would cause a bad memory + * access by the kernel and possibly crash the system. + * + * This function will check if the event has any fields flagged as needing + * to be checked at runtime and perform those checks. + * + * If it is found that a field is unsafe, it will write into the @iter->seq + * a message stating what was found to be unsafe. + * + * @return: true if the event is unsafe and should be ignored, + * false otherwise. + */ +bool ignore_event(struct trace_iterator *iter) +{ + struct ftrace_event_field *field; + struct trace_event *trace_event; + struct trace_event_call *event; + struct list_head *head; + struct trace_seq *seq; + const void *ptr; + + trace_event = ftrace_find_event(iter->ent->type); + + seq = &iter->seq; + + if (!trace_event) { + trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); + return true; + } + + event = container_of(trace_event, struct trace_event_call, event); + if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) + return false; + + head = trace_get_fields(event); + if (!head) { + trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", + trace_event_name(event)); + return true; + } + + /* Offsets are from the iter->ent that points to the raw event */ + ptr = iter->ent; + + list_for_each_entry(field, head, link) { + const char *str; + bool good; + + if (!field->needs_test) + continue; + + str = *(const char **)(ptr + field->offset); + + good = trace_safe_str(iter, str); + + /* + * If you hit this warning, it is likely that the + * trace event in question used %s on a string that + * was saved at the time of the event, but may not be + * around when the trace is read. Use __string(), + * __assign_str() and __get_str() helpers in the TRACE_EVENT() + * instead. See samples/trace_events/trace-events-sample.h + * for reference. + */ + if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", + trace_event_name(event), field->name)) { + trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", + trace_event_name(event), field->name); + return true; + } + } + return false; +} + +const char *trace_event_format(struct trace_iterator *iter, const char *fmt) +{ + const char *p, *new_fmt; + char *q; + + if (WARN_ON_ONCE(!fmt)) + return fmt; + + if (!iter->tr || iter->tr->trace_flags & TRACE_ITER(HASH_PTR)) + return fmt; + + p = fmt; + new_fmt = q = iter->fmt; + while (*p) { + if (unlikely(q - new_fmt + 3 > iter->fmt_size)) { + if (!trace_iter_expand_format(iter)) + return fmt; + + q += iter->fmt - new_fmt; + new_fmt = iter->fmt; + } + + *q++ = *p++; + + /* Replace %p with %px */ + if (p[-1] == '%') { + if (p[0] == '%') { + *q++ = *p++; + } else if (p[0] == 'p' && !isalnum(p[1])) { + *q++ = *p++; + *q++ = 'x'; + } + } + } + *q = '\0'; + + return new_fmt; +} + +#define STATIC_TEMP_BUF_SIZE 128 +static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4); + /* Find the next real entry, without updating the iterator itself */ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) { - return __find_next_entry(iter, ent_cpu, NULL, ent_ts); + /* __find_next_entry will reset ent_size */ + int ent_size = iter->ent_size; + struct trace_entry *entry; + + /* + * If called from ftrace_dump(), then the iter->temp buffer + * will be the static_temp_buf and not created from kmalloc. + * If the entry size is greater than the buffer, we can + * not save it. Just return NULL in that case. This is only + * used to add markers when two consecutive events' time + * stamps have a large delta. See trace_print_lat_context() + */ + if (iter->temp == static_temp_buf && + STATIC_TEMP_BUF_SIZE < ent_size) + return NULL; + + /* + * The __find_next_entry() may call peek_next_entry(), which may + * call ring_buffer_peek() that may make the contents of iter->ent + * undefined. Need to copy iter->ent now. + */ + if (iter->ent && iter->ent != iter->temp) { + if ((!iter->temp || iter->temp_size < iter->ent_size) && + !WARN_ON_ONCE(iter->temp == static_temp_buf)) { + void *temp; + temp = kmalloc(iter->ent_size, GFP_KERNEL); + if (!temp) + return NULL; + kfree(iter->temp); + iter->temp = temp; + iter->temp_size = iter->ent_size; + } + memcpy(iter->temp, iter->ent, iter->ent_size); + iter->ent = iter->temp; + } + entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts); + /* Put back the original ent_size */ + iter->ent_size = ent_size; + + return entry; } /* Find the next real entry, and increment the iterator to the next entry */ @@ -3173,7 +3894,7 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter) static void trace_consume(struct trace_iterator *iter) { - ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, &iter->ts, + ring_buffer_consume(iter->array_buffer->buffer, iter->cpu, &iter->ts, &iter->lost_events); } @@ -3206,12 +3927,11 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) void tracing_iter_reset(struct trace_iterator *iter, int cpu) { - struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter; unsigned long entries = 0; u64 ts; - per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = 0; + per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = 0; buf_iter = trace_buffer_iter(iter, cpu); if (!buf_iter) @@ -3224,14 +3944,16 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) * that a reset never took place on a cpu. This is evident * by the timestamp being before the start of the buffer. */ - while ((event = ring_buffer_iter_peek(buf_iter, &ts))) { - if (ts >= iter->trace_buffer->time_start) + while (ring_buffer_iter_peek(buf_iter, &ts)) { + if (ts >= iter->array_buffer->time_start) break; entries++; - ring_buffer_read(buf_iter, NULL); + ring_buffer_iter_advance(buf_iter); + /* This could be a big loop */ + cond_resched(); } - per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries; + per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries; } /* @@ -3247,15 +3969,16 @@ static void *s_start(struct seq_file *m, loff_t *pos) loff_t l = 0; int cpu; - /* - * copy the tracer to avoid using a global lock all around. - * iter->trace is a copy of current_trace, the pointer to the - * name may be used instead of a strcmp(), as iter->trace->name - * will point to the same string as current_trace->name. - */ mutex_lock(&trace_types_lock); - if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) - *iter->trace = *tr->current_trace; + if (unlikely(tr->current_trace != iter->trace)) { + /* Close iter->trace before switching to the new current tracer */ + if (iter->trace->close) + iter->trace->close(iter); + iter->trace = tr->current_trace; + /* Reopen the new current tracer */ + if (iter->trace->open) + iter->trace->open(iter); + } mutex_unlock(&trace_types_lock); #ifdef CONFIG_TRACER_MAX_TRACE @@ -3263,9 +3986,6 @@ static void *s_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-EBUSY); #endif - if (!iter->snapshot) - atomic_inc(&trace_record_taskinfo_disabled); - if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; @@ -3308,54 +4028,87 @@ static void s_stop(struct seq_file *m, void *p) return; #endif - if (!iter->snapshot) - atomic_dec(&trace_record_taskinfo_disabled); - trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } static void -get_total_entries(struct trace_buffer *buf, - unsigned long *total, unsigned long *entries) +get_total_entries_cpu(struct array_buffer *buf, unsigned long *total, + unsigned long *entries, int cpu) { unsigned long count; + + count = ring_buffer_entries_cpu(buf->buffer, cpu); + /* + * If this buffer has skipped entries, then we hold all + * entries for the trace and we need to ignore the + * ones before the time stamp. + */ + if (per_cpu_ptr(buf->data, cpu)->skipped_entries) { + count -= per_cpu_ptr(buf->data, cpu)->skipped_entries; + /* total is the same as the entries */ + *total = count; + } else + *total = count + + ring_buffer_overrun_cpu(buf->buffer, cpu); + *entries = count; +} + +static void +get_total_entries(struct array_buffer *buf, + unsigned long *total, unsigned long *entries) +{ + unsigned long t, e; int cpu; *total = 0; *entries = 0; for_each_tracing_cpu(cpu) { - count = ring_buffer_entries_cpu(buf->buffer, cpu); - /* - * If this buffer has skipped entries, then we hold all - * entries for the trace and we need to ignore the - * ones before the time stamp. - */ - if (per_cpu_ptr(buf->data, cpu)->skipped_entries) { - count -= per_cpu_ptr(buf->data, cpu)->skipped_entries; - /* total is the same as the entries */ - *total += count; - } else - *total += count + - ring_buffer_overrun_cpu(buf->buffer, cpu); - *entries += count; + get_total_entries_cpu(buf, &t, &e, cpu); + *total += t; + *entries += e; } } +unsigned long trace_total_entries_cpu(struct trace_array *tr, int cpu) +{ + unsigned long total, entries; + + if (!tr) + tr = &global_trace; + + get_total_entries_cpu(&tr->array_buffer, &total, &entries, cpu); + + return entries; +} + +unsigned long trace_total_entries(struct trace_array *tr) +{ + unsigned long total, entries; + + if (!tr) + tr = &global_trace; + + get_total_entries(&tr->array_buffer, &total, &entries); + + return entries; +} + static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n" - "# / _-----=> irqs-off \n" - "# | / _----=> need-resched \n" - "# || / _---=> hardirq/softirq \n" - "# ||| / _--=> preempt-depth \n" - "# |||| / delay \n" - "# cmd pid ||||| time | caller \n" - "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _------=> CPU# \n" + "# / _-----=> irqs-off/BH-disabled\n" + "# | / _----=> need-resched \n" + "# || / _---=> hardirq/softirq \n" + "# ||| / _--=> preempt-depth \n" + "# |||| / _-=> migrate-disable \n" + "# ||||| / delay \n" + "# cmd pid |||||| time | caller \n" + "# \\ / |||||| \\ | / \n"); } -static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +static void print_event_info(struct array_buffer *buf, struct seq_file *m) { unsigned long total; unsigned long entries; @@ -3366,57 +4119,51 @@ static void print_event_info(struct trace_buffer *buf, struct seq_file *m) seq_puts(m, "#\n"); } -static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m, +static void print_func_help_header(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { - bool tgid = flags & TRACE_ITER_RECORD_TGID; + bool tgid = flags & TRACE_ITER(RECORD_TGID); print_event_info(buf, m); - seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); - seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); + seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? " TGID " : ""); + seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } -static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m, +static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { - bool tgid = flags & TRACE_ITER_RECORD_TGID; - const char tgid_space[] = " "; - const char space[] = " "; - - seq_printf(m, "# %s _-----=> irqs-off\n", - tgid ? tgid_space : space); - seq_printf(m, "# %s / _----=> need-resched\n", - tgid ? tgid_space : space); - seq_printf(m, "# %s| / _---=> hardirq/softirq\n", - tgid ? tgid_space : space); - seq_printf(m, "# %s|| / _--=> preempt-depth\n", - tgid ? tgid_space : space); - seq_printf(m, "# %s||| / delay\n", - tgid ? tgid_space : space); - seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n", - tgid ? " TGID " : space); - seq_printf(m, "# | | %s | |||| | |\n", - tgid ? " | " : space); + bool tgid = flags & TRACE_ITER(RECORD_TGID); + static const char space[] = " "; + int prec = tgid ? 12 : 2; + + print_event_info(buf, m); + + seq_printf(m, "# %.*s _-----=> irqs-off/BH-disabled\n", prec, space); + seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); + seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); + seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); + seq_printf(m, "# %.*s||| / _-=> migrate-disable\n", prec, space); + seq_printf(m, "# %.*s|||| / delay\n", prec, space); + seq_printf(m, "# TASK-PID %.*s CPU# ||||| TIMESTAMP FUNCTION\n", prec, " TGID "); + seq_printf(m, "# | | %.*s | ||||| | |\n", prec, " | "); } void print_trace_header(struct seq_file *m, struct trace_iterator *iter) { unsigned long sym_flags = (global_trace.trace_flags & TRACE_ITER_SYM_MASK); - struct trace_buffer *buf = iter->trace_buffer; + struct array_buffer *buf = iter->array_buffer; struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu); struct tracer *type = iter->trace; unsigned long entries; unsigned long total; - const char *name = "preemption"; - - name = type->name; + const char *name = type->name; get_total_entries(buf, &total, &entries); seq_printf(m, "# %s latency trace v1.1.5 on %s\n", - name, UTS_RELEASE); + name, init_utsname()->release); seq_puts(m, "# -----------------------------------" "---------------------------------\n"); seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |" @@ -3425,15 +4172,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) entries, total, buf->cpu, -#if defined(CONFIG_PREEMPT_NONE) - "server", -#elif defined(CONFIG_PREEMPT_VOLUNTARY) - "desktop", -#elif defined(CONFIG_PREEMPT) - "preempt", -#else - "unknown", -#endif + preempt_model_str(), /* These are reserved for later use */ 0, 0, 0, 0); #ifdef CONFIG_SMP @@ -3467,7 +4206,7 @@ static void test_cpu_buff_start(struct trace_iterator *iter) struct trace_seq *s = &iter->seq; struct trace_array *tr = iter->tr; - if (!(tr->trace_flags & TRACE_ITER_ANNOTATE)) + if (!(tr->trace_flags & TRACE_ITER(ANNOTATE))) return; if (!(iter->iter_flags & TRACE_FILE_ANNOTATE)) @@ -3477,7 +4216,7 @@ static void test_cpu_buff_start(struct trace_iterator *iter) cpumask_test_cpu(iter->cpu, iter->started)) return; - if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries) + if (per_cpu_ptr(iter->array_buffer->data, iter->cpu)->skipped_entries) return; if (cpumask_available(iter->started)) @@ -3489,6 +4228,22 @@ static void test_cpu_buff_start(struct trace_iterator *iter) iter->cpu); } +#ifdef CONFIG_FTRACE_SYSCALLS +static bool is_syscall_event(struct trace_event *event) +{ + return (event->funcs == &enter_syscall_print_funcs) || + (event->funcs == &exit_syscall_print_funcs); + +} +#define syscall_buf_size CONFIG_TRACE_SYSCALL_BUF_SIZE_DEFAULT +#else +static inline bool is_syscall_event(struct trace_event *event) +{ + return false; +} +#define syscall_buf_size 0 +#endif /* CONFIG_FTRACE_SYSCALLS */ + static enum print_line_t print_trace_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; @@ -3503,7 +4258,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) event = ftrace_find_event(entry->type); - if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { + if (tr->trace_flags & TRACE_ITER(CONTEXT_INFO)) { if (iter->iter_flags & TRACE_FILE_LAT_FMT) trace_print_lat_context(iter); else @@ -3513,8 +4268,22 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; - if (event) + if (event) { + if (tr->trace_flags & TRACE_ITER(FIELDS)) + return print_event_fields(iter, event); + /* + * For TRACE_EVENT() events, the print_fmt is not + * safe to use if the array has delta offsets + * Force printing via the fields. + */ + if ((tr->text_delta)) { + /* ftrace and system call events are still OK */ + if ((event->type > __TRACE_LAST_TYPE) && + !is_syscall_event(event)) + return print_event_fields(iter, event); + } return event->funcs->trace(iter, sym_flags, event); + } trace_seq_printf(s, "Unknown type %d\n", entry->type); @@ -3530,7 +4299,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter) entry = iter->ent; - if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) + if (tr->trace_flags & TRACE_ITER(CONTEXT_INFO)) trace_seq_printf(s, "%d %d %llu ", entry->pid, iter->cpu, iter->ts); @@ -3556,7 +4325,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter) entry = iter->ent; - if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { + if (tr->trace_flags & TRACE_ITER(CONTEXT_INFO)) { SEQ_PUT_HEX_FIELD(s, entry->pid); SEQ_PUT_HEX_FIELD(s, iter->cpu); SEQ_PUT_HEX_FIELD(s, iter->ts); @@ -3585,7 +4354,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) entry = iter->ent; - if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { + if (tr->trace_flags & TRACE_ITER(CONTEXT_INFO)) { SEQ_PUT_FIELD(s, entry->pid); SEQ_PUT_FIELD(s, iter->cpu); SEQ_PUT_FIELD(s, iter->ts); @@ -3611,7 +4380,7 @@ int trace_empty(struct trace_iterator *iter) if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { - if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) + if (!ring_buffer_empty_cpu(iter->array_buffer->buffer, cpu)) return 0; } return 1; @@ -3623,7 +4392,7 @@ int trace_empty(struct trace_iterator *iter) if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { - if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) + if (!ring_buffer_empty_cpu(iter->array_buffer->buffer, cpu)) return 0; } } @@ -3639,8 +4408,12 @@ enum print_line_t print_trace_line(struct trace_iterator *iter) enum print_line_t ret; if (iter->lost_events) { - trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", - iter->cpu, iter->lost_events); + if (iter->lost_events == (unsigned long)-1) + trace_seq_printf(&iter->seq, "CPU:%d [LOST EVENTS]\n", + iter->cpu); + else + trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", + iter->cpu, iter->lost_events); if (trace_seq_has_overflowed(&iter->seq)) return TRACE_TYPE_PARTIAL_LINE; } @@ -3652,27 +4425,27 @@ enum print_line_t print_trace_line(struct trace_iterator *iter) } if (iter->ent->type == TRACE_BPUTS && - trace_flags & TRACE_ITER_PRINTK && - trace_flags & TRACE_ITER_PRINTK_MSGONLY) + trace_flags & TRACE_ITER(PRINTK) && + trace_flags & TRACE_ITER(PRINTK_MSGONLY)) return trace_print_bputs_msg_only(iter); if (iter->ent->type == TRACE_BPRINT && - trace_flags & TRACE_ITER_PRINTK && - trace_flags & TRACE_ITER_PRINTK_MSGONLY) + trace_flags & TRACE_ITER(PRINTK) && + trace_flags & TRACE_ITER(PRINTK_MSGONLY)) return trace_print_bprintk_msg_only(iter); if (iter->ent->type == TRACE_PRINT && - trace_flags & TRACE_ITER_PRINTK && - trace_flags & TRACE_ITER_PRINTK_MSGONLY) + trace_flags & TRACE_ITER(PRINTK) && + trace_flags & TRACE_ITER(PRINTK_MSGONLY)) return trace_print_printk_msg_only(iter); - if (trace_flags & TRACE_ITER_BIN) + if (trace_flags & TRACE_ITER(BIN)) return print_bin_fmt(iter); - if (trace_flags & TRACE_ITER_HEX) + if (trace_flags & TRACE_ITER(HEX)) return print_hex_fmt(iter); - if (trace_flags & TRACE_ITER_RAW) + if (trace_flags & TRACE_ITER(RAW)) return print_raw_fmt(iter); return print_trace_fmt(iter); @@ -3690,7 +4463,7 @@ void trace_latency_header(struct seq_file *m) if (iter->iter_flags & TRACE_FILE_LAT_FMT) print_trace_header(m, iter); - if (!(tr->trace_flags & TRACE_ITER_VERBOSE)) + if (!(tr->trace_flags & TRACE_ITER(VERBOSE))) print_lat_help_header(m); } @@ -3700,7 +4473,7 @@ void trace_default_header(struct seq_file *m) struct trace_array *tr = iter->tr; unsigned long trace_flags = tr->trace_flags; - if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) + if (!(trace_flags & TRACE_ITER(CONTEXT_INFO))) return; if (iter->iter_flags & TRACE_FILE_LAT_FMT) { @@ -3708,15 +4481,15 @@ void trace_default_header(struct seq_file *m) if (trace_empty(iter)) return; print_trace_header(m, iter); - if (!(trace_flags & TRACE_ITER_VERBOSE)) + if (!(trace_flags & TRACE_ITER(VERBOSE))) print_lat_help_header(m); } else { - if (!(trace_flags & TRACE_ITER_VERBOSE)) { - if (trace_flags & TRACE_ITER_IRQ_INFO) - print_func_help_header_irq(iter->trace_buffer, + if (!(trace_flags & TRACE_ITER(VERBOSE))) { + if (trace_flags & TRACE_ITER(IRQ_INFO)) + print_func_help_header_irq(iter->array_buffer, m, trace_flags); else - print_func_help_header(iter->trace_buffer, m, + print_func_help_header(iter->array_buffer, m, trace_flags); } } @@ -3803,7 +4576,11 @@ static int s_show(struct seq_file *m, void *v) iter->leftover = ret; } else { - print_trace_line(iter); + ret = print_trace_line(iter); + if (ret == TRACE_TYPE_PARTIAL_LINE) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + } ret = trace_print_seq(m, &iter->seq); /* * If we overflow the seq_file buffer, then it will @@ -3836,6 +4613,25 @@ static const struct seq_operations tracer_seq_ops = { .show = s_show, }; +/* + * Note, as iter itself can be allocated and freed in different + * ways, this function is only used to free its content, and not + * the iterator itself. The only requirement to all the allocations + * is that it must zero all fields (kzalloc), as freeing works with + * ethier allocated content or NULL. + */ +static void free_trace_iter_content(struct trace_iterator *iter) +{ + /* The fmt is either NULL, allocated or points to static_fmt_buf */ + if (iter->fmt != static_fmt_buf) + kfree(iter->fmt); + + kfree(iter->temp); + kfree(iter->buffer_iter); + mutex_destroy(&iter->mutex); + free_cpumask_var(iter->started); +} + static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file, bool snapshot) { @@ -3856,15 +4652,29 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) goto release; /* - * We make a copy of the current tracer to avoid concurrent - * changes on it while we are reading. + * trace_find_next_entry() may need to save off iter->ent. + * It will place it into the iter->temp buffer. As most + * events are less than 128, allocate a buffer of that size. + * If one is greater, then trace_find_next_entry() will + * allocate a new buffer to adjust for the bigger iter->ent. + * It's not critical if it fails to get allocated here. */ - mutex_lock(&trace_types_lock); - iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL); - if (!iter->trace) - goto fail; + iter->temp = kmalloc(128, GFP_KERNEL); + if (iter->temp) + iter->temp_size = 128; - *iter->trace = *tr->current_trace; + /* + * trace_event_printf() may need to modify given format + * string to replace %p with %px so that it shows real address + * instead of hash value. However, that is only for the event + * tracing, other tracer may not need. Defer the allocation + * until it is needed. + */ + iter->fmt = NULL; + iter->fmt_size = 0; + + mutex_lock(&trace_types_lock); + iter->trace = tr->current_trace; if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; @@ -3874,47 +4684,48 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) #ifdef CONFIG_TRACER_MAX_TRACE /* Currently only the top directory has a snapshot */ if (tr->current_trace->print_max || snapshot) - iter->trace_buffer = &tr->max_buffer; + iter->array_buffer = &tr->max_buffer; else #endif - iter->trace_buffer = &tr->trace_buffer; + iter->array_buffer = &tr->array_buffer; iter->snapshot = snapshot; iter->pos = -1; iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); /* Notify the tracer early; before we stop tracing. */ - if (iter->trace && iter->trace->open) + if (iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ - if (ring_buffer_overruns(iter->trace_buffer->buffer)) + if (ring_buffer_overruns(iter->array_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; - /* stop the trace while dumping if we are not opening "snapshot" */ - if (!iter->snapshot) + /* + * If pause-on-trace is enabled, then stop the trace while + * dumping, unless this is the "snapshot" file + */ + if (!iter->snapshot && (tr->trace_flags & TRACE_ITER(PAUSE_ON_TRACE))) { + iter->iter_flags |= TRACE_FILE_PAUSE; tracing_stop_tr(tr); + } if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); - } - ring_buffer_read_prepare_sync(); - for_each_tracing_cpu(cpu) { - ring_buffer_read_start(iter->buffer_iter[cpu]); + ring_buffer_read_start(iter->array_buffer->buffer, + cpu, GFP_KERNEL); tracing_iter_reset(iter, cpu); } } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); - ring_buffer_read_prepare_sync(); - ring_buffer_read_start(iter->buffer_iter[cpu]); + ring_buffer_read_start(iter->array_buffer->buffer, + cpu, GFP_KERNEL); tracing_iter_reset(iter, cpu); } @@ -3924,8 +4735,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) fail: mutex_unlock(&trace_types_lock); - kfree(iter->trace); - kfree(iter->buffer_iter); + free_trace_iter_content(iter); release: seq_release_private(inode, file); return ERR_PTR(-ENOMEM); @@ -3933,8 +4743,11 @@ release: int tracing_open_generic(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; filp->private_data = inode->i_private; return 0; @@ -3949,21 +4762,64 @@ bool tracing_is_disabled(void) * Open and update trace_array ref count. * Must have the current trace_array passed to it. */ -static int tracing_open_generic_tr(struct inode *inode, struct file *filp) +int tracing_open_generic_tr(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; + int ret; - if (tracing_disabled) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; + + filp->private_data = inode->i_private; + + return 0; +} + +/* + * The private pointer of the inode is the trace_event_file. + * Update the tr ref count associated to it. + */ +int tracing_open_file_tr(struct inode *inode, struct file *filp) +{ + struct trace_event_file *file = inode->i_private; + int ret; + + ret = tracing_check_open_get_tr(file->tr); + if (ret) + return ret; + + guard(mutex)(&event_mutex); - if (trace_array_get(tr) < 0) + /* Fail if the file is marked for removal */ + if (file->flags & EVENT_FILE_FL_FREED) { + trace_array_put(file->tr); return -ENODEV; + } else { + event_file_get(file); + } filp->private_data = inode->i_private; return 0; } +int tracing_release_file_tr(struct inode *inode, struct file *filp) +{ + struct trace_event_file *file = inode->i_private; + + trace_array_put(file->tr); + event_file_put(file); + + return 0; +} + +int tracing_single_release_file_tr(struct inode *inode, struct file *filp) +{ + tracing_release_file_tr(inode, filp); + return single_release(inode, filp); +} + static int tracing_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; @@ -3988,7 +4844,7 @@ static int tracing_release(struct inode *inode, struct file *file) if (iter->trace && iter->trace->close) iter->trace->close(iter); - if (!iter->snapshot) + if (iter->iter_flags & TRACE_FILE_PAUSE) /* reenable tracing if it was previously enabled */ tracing_start_tr(tr); @@ -3996,16 +4852,13 @@ static int tracing_release(struct inode *inode, struct file *file) mutex_unlock(&trace_types_lock); - mutex_destroy(&iter->mutex); - free_cpumask_var(iter->started); - kfree(iter->trace); - kfree(iter->buffer_iter); + free_trace_iter_content(iter); seq_release_private(inode, file); return 0; } -static int tracing_release_generic_tr(struct inode *inode, struct file *file) +int tracing_release_generic_tr(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; @@ -4026,15 +4879,16 @@ static int tracing_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; - int ret = 0; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { int cpu = tracing_get_cpu(inode); - struct trace_buffer *trace_buf = &tr->trace_buffer; + struct array_buffer *trace_buf = &tr->array_buffer; #ifdef CONFIG_TRACER_MAX_TRACE if (tr->current_trace->print_max) @@ -4044,14 +4898,14 @@ static int tracing_open(struct inode *inode, struct file *file) if (cpu == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(trace_buf); else - tracing_reset(trace_buf, cpu); + tracing_reset_cpu(trace_buf, cpu); } if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, false); if (IS_ERR(iter)) ret = PTR_ERR(iter); - else if (tr->trace_flags & TRACE_ITER_LATENCY_FMT) + else if (tr->trace_flags & TRACE_ITER(LATENCY_FMT)) iter->iter_flags |= TRACE_FILE_LAT_FMT; } @@ -4069,6 +4923,11 @@ static int tracing_open(struct inode *inode, struct file *file) static bool trace_ok_for_array(struct tracer *t, struct trace_array *tr) { +#ifdef CONFIG_TRACER_SNAPSHOT + /* arrays with mapped buffer range do not have snapshots */ + if (tr->range_addr_start && t->use_max_tr) + return false; +#endif return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances; } @@ -4145,12 +5004,15 @@ static int show_traces_open(struct inode *inode, struct file *file) struct seq_file *m; int ret; - if (tracing_disabled) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = seq_open(file, &show_traces_seq_ops); - if (ret) + if (ret) { + trace_array_put(tr); return ret; + } m = file->private_data; m->private = tr; @@ -4158,6 +5020,14 @@ static int show_traces_open(struct inode *inode, struct file *file) return 0; } +static int tracing_seq_release(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + return seq_release(inode, file); +} + static ssize_t tracing_write_stub(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) @@ -4180,6 +5050,8 @@ loff_t tracing_lseek(struct file *file, loff_t offset, int whence) static const struct file_operations tracing_fops = { .open = tracing_open, .read = seq_read, + .read_iter = seq_read_iter, + .splice_read = copy_splice_read, .write = tracing_write_stub, .llseek = tracing_lseek, .release = tracing_release, @@ -4188,8 +5060,8 @@ static const struct file_operations tracing_fops = { static const struct file_operations show_traces_fops = { .open = show_traces_open, .read = seq_read, - .release = seq_release, .llseek = seq_lseek, + .release = tracing_seq_release, }; static ssize_t @@ -4197,7 +5069,7 @@ tracing_cpumask_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct trace_array *tr = file_inode(filp)->i_private; - char *mask_str; + char *mask_str __free(kfree) = NULL; int len; len = snprintf(NULL, 0, "%*pb\n", @@ -4208,32 +5080,19 @@ tracing_cpumask_read(struct file *filp, char __user *ubuf, len = snprintf(mask_str, len, "%*pb\n", cpumask_pr_args(tr->tracing_cpumask)); - if (len >= count) { - count = -EINVAL; - goto out_err; - } - count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len); - -out_err: - kfree(mask_str); + if (len >= count) + return -EINVAL; - return count; + return simple_read_from_buffer(ubuf, count, ppos, mask_str, len); } -static ssize_t -tracing_cpumask_write(struct file *filp, const char __user *ubuf, - size_t count, loff_t *ppos) +int tracing_set_cpumask(struct trace_array *tr, + cpumask_var_t tracing_cpumask_new) { - struct trace_array *tr = file_inode(filp)->i_private; - cpumask_var_t tracing_cpumask_new; - int err, cpu; - - if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) - return -ENOMEM; + int cpu; - err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); - if (err) - goto err_unlock; + if (!tr) + return -EINVAL; local_irq_disable(); arch_spin_lock(&tr->max_lock); @@ -4244,24 +5103,54 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, */ if (cpumask_test_cpu(cpu, tr->tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); - ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu); + ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu); +#endif } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); - ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu); + ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu); +#endif } } arch_spin_unlock(&tr->max_lock); local_irq_enable(); cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new); + + return 0; +} + +static ssize_t +tracing_cpumask_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct trace_array *tr = file_inode(filp)->i_private; + cpumask_var_t tracing_cpumask_new; + int err; + + if (count == 0 || count > KMALLOC_MAX_SIZE) + return -EINVAL; + + if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) + return -ENOMEM; + + err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); + if (err) + goto err_free; + + err = tracing_set_cpumask(tr, tracing_cpumask_new); + if (err) + goto err_free; + free_cpumask_var(tracing_cpumask_new); return count; -err_unlock: +err_free: free_cpumask_var(tracing_cpumask_new); return err; @@ -4279,27 +5168,32 @@ static int tracing_trace_options_show(struct seq_file *m, void *v) { struct tracer_opt *trace_opts; struct trace_array *tr = m->private; + struct tracer_flags *flags; u32 tracer_flags; int i; - mutex_lock(&trace_types_lock); - tracer_flags = tr->current_trace->flags->val; - trace_opts = tr->current_trace->flags->opts; + guard(mutex)(&trace_types_lock); for (i = 0; trace_options[i]; i++) { - if (tr->trace_flags & (1 << i)) + if (tr->trace_flags & (1ULL << i)) seq_printf(m, "%s\n", trace_options[i]); else seq_printf(m, "no%s\n", trace_options[i]); } + flags = tr->current_trace_flags; + if (!flags || !flags->opts) + return 0; + + tracer_flags = flags->val; + trace_opts = flags->opts; + for (i = 0; trace_opts[i].name; i++) { if (tracer_flags & trace_opts[i].bit) seq_printf(m, "%s\n", trace_opts[i].name); else seq_printf(m, "no%s\n", trace_opts[i].name); } - mutex_unlock(&trace_types_lock); return 0; } @@ -4309,9 +5203,10 @@ static int __set_tracer_option(struct trace_array *tr, struct tracer_opt *opts, int neg) { struct tracer *trace = tracer_flags->trace; - int ret; + int ret = 0; - ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); + if (trace->set_flag) + ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); if (ret) return ret; @@ -4325,32 +5220,42 @@ static int __set_tracer_option(struct trace_array *tr, /* Try to assign a tracer specific option */ static int set_tracer_option(struct trace_array *tr, char *cmp, int neg) { - struct tracer *trace = tr->current_trace; - struct tracer_flags *tracer_flags = trace->flags; + struct tracer_flags *tracer_flags = tr->current_trace_flags; struct tracer_opt *opts = NULL; int i; + if (!tracer_flags || !tracer_flags->opts) + return 0; + for (i = 0; tracer_flags->opts[i].name; i++) { opts = &tracer_flags->opts[i]; if (strcmp(cmp, opts->name) == 0) - return __set_tracer_option(tr, trace->flags, opts, neg); + return __set_tracer_option(tr, tracer_flags, opts, neg); } return -EINVAL; } /* Some tracers require overwrite to stay enabled */ -int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) +int trace_keep_overwrite(struct tracer *tracer, u64 mask, int set) { - if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set) + if (tracer->enabled && (mask & TRACE_ITER(OVERWRITE)) && !set) return -1; return 0; } -int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) +int set_tracer_flag(struct trace_array *tr, u64 mask, int enabled) { + switch (mask) { + case TRACE_ITER(RECORD_TGID): + case TRACE_ITER(RECORD_CMD): + case TRACE_ITER(TRACE_PRINTK): + case TRACE_ITER(COPY_MARKER): + lockdep_assert_held(&event_mutex); + } + /* do nothing if flag is already set */ if (!!(tr->trace_flags & mask) == !!enabled) return 0; @@ -4360,49 +5265,83 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) if (tr->current_trace->flag_changed(tr, mask, !!enabled)) return -EINVAL; + switch (mask) { + case TRACE_ITER(TRACE_PRINTK): + if (enabled) { + update_printk_trace(tr); + } else { + /* + * The global_trace cannot clear this. + * It's flag only gets cleared if another instance sets it. + */ + if (printk_trace == &global_trace) + return -EINVAL; + /* + * An instance must always have it set. + * by default, that's the global_trace instance. + */ + if (printk_trace == tr) + update_printk_trace(&global_trace); + } + break; + + case TRACE_ITER(COPY_MARKER): + update_marker_trace(tr, enabled); + /* update_marker_trace updates the tr->trace_flags */ + return 0; + } + if (enabled) tr->trace_flags |= mask; else tr->trace_flags &= ~mask; - if (mask == TRACE_ITER_RECORD_CMD) + switch (mask) { + case TRACE_ITER(RECORD_CMD): trace_event_enable_cmd_record(enabled); + break; - if (mask == TRACE_ITER_RECORD_TGID) { - if (!tgid_map) - tgid_map = kcalloc(PID_MAX_DEFAULT + 1, - sizeof(*tgid_map), - GFP_KERNEL); - if (!tgid_map) { - tr->trace_flags &= ~TRACE_ITER_RECORD_TGID; + case TRACE_ITER(RECORD_TGID): + + if (trace_alloc_tgid_map() < 0) { + tr->trace_flags &= ~TRACE_ITER(RECORD_TGID); return -ENOMEM; } trace_event_enable_tgid_record(enabled); - } + break; - if (mask == TRACE_ITER_EVENT_FORK) + case TRACE_ITER(EVENT_FORK): trace_event_follow_fork(tr, enabled); + break; - if (mask == TRACE_ITER_FUNC_FORK) + case TRACE_ITER(FUNC_FORK): ftrace_pid_follow_fork(tr, enabled); + break; - if (mask == TRACE_ITER_OVERWRITE) { - ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled); + case TRACE_ITER(OVERWRITE): + ring_buffer_change_overwrite(tr->array_buffer.buffer, enabled); #ifdef CONFIG_TRACER_MAX_TRACE ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled); #endif - } + break; - if (mask == TRACE_ITER_PRINTK) { + case TRACE_ITER(PRINTK): trace_printk_start_stop_comm(enabled); trace_printk_control(enabled); + break; + +#if defined(CONFIG_FUNCTION_PROFILER) && defined(CONFIG_FUNCTION_GRAPH_TRACER) + case TRACE_GRAPH_GRAPH_TIME: + ftrace_graph_graph_time_control(enabled); + break; +#endif } return 0; } -static int trace_set_options(struct trace_array *tr, char *option) +int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; @@ -4418,6 +5357,7 @@ static int trace_set_options(struct trace_array *tr, char *option) cmp += len; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = match_string(trace_options, -1, cmp); @@ -4425,9 +5365,10 @@ static int trace_set_options(struct trace_array *tr, char *option) if (ret < 0) ret = set_tracer_option(tr, cmp, neg); else - ret = set_tracer_flag(tr, 1 << ret, !neg); + ret = set_tracer_flag(tr, 1ULL << ret, !neg); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); /* * If the first trailing whitespace is replaced with '\0' by strstrip, @@ -4490,11 +5431,9 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_trace_options_show, inode->i_private); if (ret < 0) @@ -4513,6 +5452,10 @@ static const struct file_operations tracing_iter_fops = { static const char readme_msg[] = "tracing mini-HOWTO:\n\n" + "By default tracefs removes all OTH file permission bits.\n" + "When mounting tracefs an optional group id can be specified\n" + "which adds the group to every directory and file in tracefs:\n\n" + "\t e.g. mount -t tracefs [-o [gid=<gid>]] nodev /sys/kernel/tracing\n\n" "# echo 0 > tracing_on : quick way to disable tracing\n" "# echo 1 > tracing_on : quick way to re-enable tracing\n\n" " Important files:\n" @@ -4521,9 +5464,10 @@ static const char readme_msg[] = " trace_pipe\t\t- A consuming read to see the contents of the buffer\n" " current_tracer\t- function and latency tracers\n" " available_tracers\t- list of configured tracers for current_tracer\n" + " error_log\t- error log for failed commands (that support it)\n" " buffer_size_kb\t- view and modify size of per cpu buffer\n" " buffer_total_size_kb - view total size of all cpu buffers\n\n" - " trace_clock\t\t-change the clock used to order events\n" + " trace_clock\t\t- change the clock used to order events\n" " local: Per cpu clock but may not be synced across CPUs\n" " global: Synced across CPUs but slows tracing down.\n" " counter: Not a clock, but just an increment\n" @@ -4532,7 +5476,7 @@ static const char readme_msg[] = #ifdef CONFIG_X86_64 " x86-tsc: TSC cycle counter\n" #endif - "\n timestamp_mode\t-view the mode used to timestamp events\n" + "\n timestamp_mode\t- view the mode used to timestamp events\n" " delta: Delta difference against a buffer-wide timestamp\n" " absolute: Absolute (standalone) timestamp\n" "\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n" @@ -4541,7 +5485,7 @@ static const char readme_msg[] = " instances\t\t- Make sub-buffers with: mkdir instances/foo\n" "\t\t\t Remove sub-buffer with rmdir\n" " trace_options\t\t- Set format or modify how tracing happens\n" - "\t\t\t Disable an option by adding a suffix 'no' to the\n" + "\t\t\t Disable an option by prefixing 'no' to the\n" "\t\t\t option name\n" " saved_cmdlines_size\t- echo command number in here to store comm-pid list\n" #ifdef CONFIG_DYNAMIC_FTRACE @@ -4585,6 +5529,8 @@ static const char readme_msg[] = #ifdef CONFIG_FUNCTION_TRACER " set_ftrace_pid\t- Write pid(s) to only function trace those pids\n" "\t\t (function)\n" + " set_ftrace_notrace_pid\t- Write pid(s) to not function trace those pids\n" + "\t\t (function)\n" #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER " set_graph_function\t- Trace the nested calls of a function (function_graph)\n" @@ -4607,48 +5553,65 @@ static const char readme_msg[] = #endif #endif /* CONFIG_STACK_TRACER */ #ifdef CONFIG_DYNAMIC_EVENTS - " dynamic_events\t\t- Add/remove/show the generic dynamic events\n" + " dynamic_events\t\t- Create/append/remove/show the generic dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #ifdef CONFIG_KPROBE_EVENTS - " kprobe_events\t\t- Add/remove/show the kernel dynamic events\n" + " kprobe_events\t\t- Create/append/remove/show the kernel dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #ifdef CONFIG_UPROBE_EVENTS - " uprobe_events\t\t- Add/remove/show the userspace dynamic events\n" + " uprobe_events\t\t- Create/append/remove/show the userspace dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif -#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) +#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) || \ + defined(CONFIG_FPROBE_EVENTS) "\t accepts: event-definitions (one definition per line)\n" - "\t Format: p[:[<group>/]<event>] <place> [<args>]\n" - "\t r[maxactive][:[<group>/]<event>] <place> [<args>]\n" +#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) + "\t Format: p[:[<group>/][<event>]] <place> [<args>]\n" + "\t r[maxactive][:[<group>/][<event>]] <place> [<args>]\n" +#endif +#ifdef CONFIG_FPROBE_EVENTS + "\t f[:[<group>/][<event>]] <func-name>[%return] [<args>]\n" + "\t t[:[<group>/][<event>]] <tracepoint> [<args>]\n" +#endif #ifdef CONFIG_HIST_TRIGGERS "\t s:[synthetic/]<event> <field> [<field>]\n" #endif - "\t -:[<group>/]<event>\n" + "\t e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>] [if <filter>]\n" + "\t -:[<group>/][<event>]\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" - "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n" + "place (kretprobe): [<module>:]<symbol>[+<offset>]%return|<memaddr>\n" #endif #ifdef CONFIG_UPROBE_EVENTS - " place (uprobe): <path>:<offset>[(ref_ctr_offset)]\n" + " place (uprobe): <path>:<offset>[%return][(ref_ctr_offset)]\n" #endif "\t args: <name>=fetcharg[:type]\n" - "\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n" + "\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n" #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API - "\t $stack<index>, $stack, $retval, $comm, $arg<N>\n" + "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n" +#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS + "\t <argname>[->field[->field|.field...]],\n" +#endif #else - "\t $stack<index>, $stack, $retval, $comm\n" + "\t $stack<index>, $stack, $retval, $comm,\n" #endif - "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n" - "\t b<bit-width>@<bit-offset>/<container-size>,\n" - "\t <type>\\[<array-size>\\]\n" + "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n" + "\t kernel return probes support: $retval, $arg<N>, $comm\n" + "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n" + "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" + "\t symstr, %pd/%pD, <type>\\[<array-size>\\]\n" #ifdef CONFIG_HIST_TRIGGERS "\t field: <stype> <name>;\n" "\t stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n" "\t [unsigned] char/int/long\n" #endif + "\t efield: For event probes ('e' types), the field is on of the fields\n" + "\t of the <attached-group>/<attached-event>.\n" #endif + " set_event\t\t- Enables events by name written into it\n" + "\t\t\t Can enable module events via: :mod:<module>\n" " events/\t\t- Directory containing all trace event subsystems:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all events\n" " events/<system>/\t- Directory containing all trace events for <system>:\n" @@ -4695,17 +5658,34 @@ static const char readme_msg[] = #ifdef CONFIG_HIST_TRIGGERS " hist trigger\t- If set, event hits are aggregated into a hash table\n" "\t Format: hist:keys=<field1[,field2,...]>\n" + "\t [:<var1>=<field|var_ref|numeric_literal>[,<var2>=...]]\n" "\t [:values=<field1[,field2,...]>]\n" "\t [:sort=<field1[,field2,...]>]\n" "\t [:size=#entries]\n" "\t [:pause][:continue][:clear]\n" "\t [:name=histname1]\n" + "\t [:nohitcount]\n" + "\t [:<handler>.<action>]\n" "\t [if <filter>]\n\n" + "\t Note, special fields can be used as well:\n" + "\t common_timestamp - to record current timestamp\n" + "\t common_cpu - to record the CPU the event happened on\n" + "\n" + "\t A hist trigger variable can be:\n" + "\t - a reference to a field e.g. x=current_timestamp,\n" + "\t - a reference to another variable e.g. y=$x,\n" + "\t - a numeric literal: e.g. ms_per_sec=1000,\n" + "\t - an arithmetic expression: e.g. time_secs=current_timestamp/1000\n" + "\n" + "\t hist trigger arithmetic expressions support addition(+), subtraction(-),\n" + "\t multiplication(*) and division(/) operators. An operand can be either a\n" + "\t variable reference, field or numeric literal.\n" + "\n" "\t When a matching event is hit, an entry is added to a hash\n" "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" - "\t can be any field, or the special string 'stacktrace'.\n" + "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" @@ -4730,7 +5710,10 @@ static const char readme_msg[] = "\t .execname display a common_pid as a program name\n" "\t .syscall display a syscall id as a syscall name\n" "\t .log2 display log2 value rather than raw number\n" - "\t .usecs display a common_timestamp in microseconds\n\n" + "\t .buckets=size display values in groups of size rather than raw number\n" + "\t .usecs display a common_timestamp in microseconds\n" + "\t .percent display a number of percentage value\n" + "\t .graph display a bar-graph of a value\n\n" "\t The 'pause' parameter can be used to pause an existing hist\n" "\t trigger or to start a hist trigger but not log any events\n" "\t until told to do so. 'continue' can be used to start or\n" @@ -4738,10 +5721,30 @@ static const char readme_msg[] = "\t The 'clear' parameter will clear the contents of a running\n" "\t hist trigger and leave its current paused/active state\n" "\t unchanged.\n\n" + "\t The 'nohitcount' (or NOHC) parameter will suppress display of\n" + "\t raw hitcount in the histogram.\n\n" "\t The enable_hist and disable_hist triggers can be used to\n" "\t have one event conditionally start and stop another event's\n" - "\t already-attached hist trigger. The syntax is analagous to\n" - "\t the enable_event and disable_event triggers.\n" + "\t already-attached hist trigger. The syntax is analogous to\n" + "\t the enable_event and disable_event triggers.\n\n" + "\t Hist trigger handlers and actions are executed whenever a\n" + "\t a histogram entry is added or updated. They take the form:\n\n" + "\t <handler>.<action>\n\n" + "\t The available handlers are:\n\n" + "\t onmatch(matching.event) - invoke on addition or update\n" + "\t onmax(var) - invoke if var exceeds current max\n" + "\t onchange(var) - invoke action if var changes\n\n" + "\t The available actions are:\n\n" + "\t trace(<synthetic_event>,param list) - generate synthetic event\n" + "\t save(field,...) - save current event fields\n" +#ifdef CONFIG_TRACER_SNAPSHOT + "\t snapshot() - snapshot the trace buffer\n\n" +#endif +#ifdef CONFIG_SYNTH_EVENTS + " events/synthetic_events\t- Create/append/remove/show synthetic events\n" + "\t Write into this file to define/undefine new synthetic events.\n" + "\t example: echo 'myevent u64 lat; char name[]; long[] stack' >> synthetic_events\n" +#endif #endif ; @@ -4759,225 +5762,6 @@ static const struct file_operations tracing_readme_fops = { .llseek = generic_file_llseek, }; -static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos) -{ - int *ptr = v; - - if (*pos || m->count) - ptr++; - - (*pos)++; - - for (; ptr <= &tgid_map[PID_MAX_DEFAULT]; ptr++) { - if (trace_find_tgid(*ptr)) - return ptr; - } - - return NULL; -} - -static void *saved_tgids_start(struct seq_file *m, loff_t *pos) -{ - void *v; - loff_t l = 0; - - if (!tgid_map) - return NULL; - - v = &tgid_map[0]; - while (l <= *pos) { - v = saved_tgids_next(m, v, &l); - if (!v) - return NULL; - } - - return v; -} - -static void saved_tgids_stop(struct seq_file *m, void *v) -{ -} - -static int saved_tgids_show(struct seq_file *m, void *v) -{ - int pid = (int *)v - tgid_map; - - seq_printf(m, "%d %d\n", pid, trace_find_tgid(pid)); - return 0; -} - -static const struct seq_operations tracing_saved_tgids_seq_ops = { - .start = saved_tgids_start, - .stop = saved_tgids_stop, - .next = saved_tgids_next, - .show = saved_tgids_show, -}; - -static int tracing_saved_tgids_open(struct inode *inode, struct file *filp) -{ - if (tracing_disabled) - return -ENODEV; - - return seq_open(filp, &tracing_saved_tgids_seq_ops); -} - - -static const struct file_operations tracing_saved_tgids_fops = { - .open = tracing_saved_tgids_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos) -{ - unsigned int *ptr = v; - - if (*pos || m->count) - ptr++; - - (*pos)++; - - for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num]; - ptr++) { - if (*ptr == -1 || *ptr == NO_CMDLINE_MAP) - continue; - - return ptr; - } - - return NULL; -} - -static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos) -{ - void *v; - loff_t l = 0; - - preempt_disable(); - arch_spin_lock(&trace_cmdline_lock); - - v = &savedcmd->map_cmdline_to_pid[0]; - while (l <= *pos) { - v = saved_cmdlines_next(m, v, &l); - if (!v) - return NULL; - } - - return v; -} - -static void saved_cmdlines_stop(struct seq_file *m, void *v) -{ - arch_spin_unlock(&trace_cmdline_lock); - preempt_enable(); -} - -static int saved_cmdlines_show(struct seq_file *m, void *v) -{ - char buf[TASK_COMM_LEN]; - unsigned int *pid = v; - - __trace_find_cmdline(*pid, buf); - seq_printf(m, "%d %s\n", *pid, buf); - return 0; -} - -static const struct seq_operations tracing_saved_cmdlines_seq_ops = { - .start = saved_cmdlines_start, - .next = saved_cmdlines_next, - .stop = saved_cmdlines_stop, - .show = saved_cmdlines_show, -}; - -static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp) -{ - if (tracing_disabled) - return -ENODEV; - - return seq_open(filp, &tracing_saved_cmdlines_seq_ops); -} - -static const struct file_operations tracing_saved_cmdlines_fops = { - .open = tracing_saved_cmdlines_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static ssize_t -tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - int r; - - arch_spin_lock(&trace_cmdline_lock); - r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num); - arch_spin_unlock(&trace_cmdline_lock); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - -static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) -{ - kfree(s->saved_cmdlines); - kfree(s->map_cmdline_to_pid); - kfree(s); -} - -static int tracing_resize_saved_cmdlines(unsigned int val) -{ - struct saved_cmdlines_buffer *s, *savedcmd_temp; - - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; - - if (allocate_cmdlines_buffer(val, s) < 0) { - kfree(s); - return -ENOMEM; - } - - arch_spin_lock(&trace_cmdline_lock); - savedcmd_temp = savedcmd; - savedcmd = s; - arch_spin_unlock(&trace_cmdline_lock); - free_saved_cmdlines_buffer(savedcmd_temp); - - return 0; -} - -static ssize_t -tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - unsigned long val; - int ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - return ret; - - /* must have at least 1 entry or less than PID_MAX_DEFAULT */ - if (!val || val > PID_MAX_DEFAULT) - return -EINVAL; - - ret = tracing_resize_saved_cmdlines((unsigned int)val); - if (ret < 0) - return ret; - - *ppos += cnt; - - return cnt; -} - -static const struct file_operations tracing_saved_cmdlines_size_fops = { - .open = tracing_open_generic, - .read = tracing_saved_cmdlines_size_read, - .write = tracing_saved_cmdlines_size_write, -}; - #ifdef CONFIG_TRACE_EVAL_MAP_FILE static union trace_eval_map_item * update_eval_map(union trace_eval_map_item *ptr) @@ -5001,14 +5785,12 @@ static void *eval_map_next(struct seq_file *m, void *v, loff_t *pos) * Paranoid! If ptr points to end, we don't want to increment past it. * This really should never happen. */ + (*pos)++; ptr = update_eval_map(ptr); if (WARN_ON_ONCE(!ptr)) return NULL; ptr++; - - (*pos)++; - ptr = update_eval_map(ptr); return ptr; @@ -5057,8 +5839,11 @@ static const struct seq_operations tracing_eval_map_seq_ops = { static int tracing_eval_map_open(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; return seq_open(filp, &tracing_eval_map_seq_ops); } @@ -5099,7 +5884,7 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, return; } - mutex_lock(&trace_eval_mutex); + guard(mutex)(&trace_eval_mutex); if (!trace_eval_maps) trace_eval_maps = map_array; @@ -5123,13 +5908,11 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, map_array++; } memset(map_array, 0, sizeof(*map_array)); - - mutex_unlock(&trace_eval_mutex); } static void trace_create_eval_file(struct dentry *d_tracer) { - trace_create_file("eval_map", 0444, d_tracer, + trace_create_file("eval_map", TRACE_MODE_READ, d_tracer, NULL, &tracing_eval_map_fops); } @@ -5139,17 +5922,27 @@ static inline void trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, int len) { } #endif /* !CONFIG_TRACE_EVAL_MAP_FILE */ -static void trace_insert_eval_map(struct module *mod, - struct trace_eval_map **start, int len) +static void +trace_event_update_with_eval_map(struct module *mod, + struct trace_eval_map **start, + int len) { struct trace_eval_map **map; - if (len <= 0) - return; + /* Always run sanitizer only if btf_type_tag attr exists. */ + if (len <= 0) { + if (!(IS_ENABLED(CONFIG_DEBUG_INFO_BTF) && + IS_ENABLED(CONFIG_PAHOLE_HAS_BTF_TAG) && + __has_attribute(btf_type_tag))) + return; + } map = start; - trace_event_eval_update(map, len); + trace_event_update_all(map, len); + + if (len <= 0) + return; trace_insert_eval_map_file(mod, start, len); } @@ -5162,20 +5955,20 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf, char buf[MAX_TRACER_SIZE+2]; int r; - mutex_lock(&trace_types_lock); - r = sprintf(buf, "%s\n", tr->current_trace->name); - mutex_unlock(&trace_types_lock); + scoped_guard(mutex, &trace_types_lock) { + r = sprintf(buf, "%s\n", tr->current_trace->name); + } return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } int tracer_init(struct tracer *t, struct trace_array *tr) { - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); return t->init(tr); } -static void set_buffer_entries(struct trace_buffer *buf, unsigned long val) +static void set_buffer_entries(struct array_buffer *buf, unsigned long val) { int cpu; @@ -5183,10 +5976,19 @@ static void set_buffer_entries(struct trace_buffer *buf, unsigned long val) per_cpu_ptr(buf->data, cpu)->entries = 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)); + } else { + per_cpu_ptr(buf->data, cpu)->entries = ring_buffer_size(buf->buffer, cpu); + } +} + #ifdef CONFIG_TRACER_MAX_TRACE /* resize @tr's buffer to the size of @size_tr's entries */ -static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, - struct trace_buffer *size_buf, int cpu_id) +static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, + struct array_buffer *size_buf, int cpu_id) { int cpu, ret = 0; @@ -5221,25 +6023,27 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, * we use the size that was given, and we can forget about * expanding it later. */ - ring_buffer_expanded = true; + trace_set_ring_buffer_expanded(tr); /* May be called before buffers are initialized */ - if (!tr->trace_buffer.buffer) + if (!tr->array_buffer.buffer) return 0; - ret = ring_buffer_resize(tr->trace_buffer.buffer, size, cpu); + /* Do not allow tracing while resizing ring buffer */ + tracing_stop_tr(tr); + + ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu); if (ret < 0) - return ret; + goto out_start; #ifdef CONFIG_TRACER_MAX_TRACE - if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) || - !tr->current_trace->use_max_tr) + if (!tr->allocated_snapshot) goto out; ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); if (ret < 0) { - int r = resize_buffer_duplicate_size(&tr->trace_buffer, - &tr->trace_buffer, cpu); + int r = resize_buffer_duplicate_size(&tr->array_buffer, + &tr->array_buffer, cpu); if (r < 0) { /* * AARGH! We are left with different @@ -5258,53 +6062,191 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, WARN_ON(1); tracing_disabled = 1; } - return ret; + goto out_start; } - if (cpu == RING_BUFFER_ALL_CPUS) - set_buffer_entries(&tr->max_buffer, size); - else - per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size; + update_buffer_entries(&tr->max_buffer, cpu); out: #endif /* CONFIG_TRACER_MAX_TRACE */ - if (cpu == RING_BUFFER_ALL_CPUS) - set_buffer_entries(&tr->trace_buffer, size); - else - per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size; - + update_buffer_entries(&tr->array_buffer, cpu); + out_start: + tracing_start_tr(tr); return ret; } -static ssize_t tracing_resize_ring_buffer(struct trace_array *tr, - unsigned long size, int cpu_id) +ssize_t tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu_id) { - int ret = size; - - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { /* make sure, this cpu is enabled in the mask */ - if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) { - ret = -EINVAL; - goto out; - } + if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) + return -EINVAL; } - ret = __tracing_resize_ring_buffer(tr, size, cpu_id); - if (ret < 0) - ret = -ENOMEM; + return __tracing_resize_ring_buffer(tr, size, cpu_id); +} -out: - mutex_unlock(&trace_types_lock); +struct trace_mod_entry { + unsigned long mod_addr; + char mod_name[MODULE_NAME_LEN]; +}; - return ret; +struct trace_scratch { + unsigned int clock_id; + unsigned long text_addr; + unsigned long nr_entries; + struct trace_mod_entry entries[]; +}; + +static DEFINE_MUTEX(scratch_mutex); + +static int cmp_mod_entry(const void *key, const void *pivot) +{ + unsigned long addr = (unsigned long)key; + const struct trace_mod_entry *ent = pivot; + + if (addr >= ent[0].mod_addr && addr < ent[1].mod_addr) + return 0; + else + return addr - ent->mod_addr; +} + +/** + * trace_adjust_address() - Adjust prev boot address to current address. + * @tr: Persistent ring buffer's trace_array. + * @addr: Address in @tr which is adjusted. + */ +unsigned long trace_adjust_address(struct trace_array *tr, unsigned long addr) +{ + struct trace_module_delta *module_delta; + struct trace_scratch *tscratch; + struct trace_mod_entry *entry; + unsigned long raddr; + int idx = 0, nr_entries; + + /* If we don't have last boot delta, return the address */ + if (!(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) + return addr; + + /* tr->module_delta must be protected by rcu. */ + guard(rcu)(); + tscratch = tr->scratch; + /* if there is no tscrach, module_delta must be NULL. */ + module_delta = READ_ONCE(tr->module_delta); + if (!module_delta || !tscratch->nr_entries || + tscratch->entries[0].mod_addr > addr) { + raddr = addr + tr->text_delta; + return __is_kernel(raddr) || is_kernel_core_data(raddr) || + is_kernel_rodata(raddr) ? raddr : addr; + } + + /* Note that entries must be sorted. */ + nr_entries = tscratch->nr_entries; + if (nr_entries == 1 || + tscratch->entries[nr_entries - 1].mod_addr < addr) + idx = nr_entries - 1; + else { + entry = __inline_bsearch((void *)addr, + tscratch->entries, + nr_entries - 1, + sizeof(tscratch->entries[0]), + cmp_mod_entry); + if (entry) + idx = entry - tscratch->entries; + } + + return addr + module_delta->delta[idx]; } +#ifdef CONFIG_MODULES +static int save_mod(struct module *mod, void *data) +{ + struct trace_array *tr = data; + struct trace_scratch *tscratch; + struct trace_mod_entry *entry; + unsigned int size; + + tscratch = tr->scratch; + if (!tscratch) + return -1; + size = tr->scratch_size; + + if (struct_size(tscratch, entries, tscratch->nr_entries + 1) > size) + return -1; + + entry = &tscratch->entries[tscratch->nr_entries]; + + tscratch->nr_entries++; + + entry->mod_addr = (unsigned long)mod->mem[MOD_TEXT].base; + strscpy(entry->mod_name, mod->name); + + return 0; +} +#else +static int save_mod(struct module *mod, void *data) +{ + return 0; +} +#endif + +static void update_last_data(struct trace_array *tr) +{ + struct trace_module_delta *module_delta; + struct trace_scratch *tscratch; + + if (!(tr->flags & TRACE_ARRAY_FL_BOOT)) + return; + + if (!(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) + return; + + /* Only if the buffer has previous boot data clear and update it. */ + tr->flags &= ~TRACE_ARRAY_FL_LAST_BOOT; + + /* Reset the module list and reload them */ + if (tr->scratch) { + struct trace_scratch *tscratch = tr->scratch; + + tscratch->clock_id = tr->clock_id; + memset(tscratch->entries, 0, + flex_array_size(tscratch, entries, tscratch->nr_entries)); + tscratch->nr_entries = 0; + + guard(mutex)(&scratch_mutex); + module_for_each_mod(save_mod, tr); + } + + /* + * Need to clear all CPU buffers as there cannot be events + * from the previous boot mixed with events with this boot + * as that will cause a confusing trace. Need to clear all + * CPU buffers, even for those that may currently be offline. + */ + tracing_reset_all_cpus(&tr->array_buffer); + + /* Using current data now */ + tr->text_delta = 0; + + if (!tr->scratch) + return; + + tscratch = tr->scratch; + module_delta = READ_ONCE(tr->module_delta); + WRITE_ONCE(tr->module_delta, NULL); + kfree_rcu(module_delta, rcu); + + /* Set the persistent ring buffer meta data to this address */ + tscratch->text_addr = (unsigned long)_text; +} /** * tracing_update_buffers - used by tracing facility to expand ring buffers + * @tr: The tracing instance * * To save on memory when the tracing is never used on a system with it * configured in. The ring buffers are set to a minimum size. But once @@ -5313,24 +6255,20 @@ out: * * This function is to be called when a tracer is about to be used. */ -int tracing_update_buffers(void) +int tracing_update_buffers(struct trace_array *tr) { int ret = 0; - mutex_lock(&trace_types_lock); - if (!ring_buffer_expanded) - ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size, - RING_BUFFER_ALL_CPUS); - mutex_unlock(&trace_types_lock); + guard(mutex)(&trace_types_lock); + update_last_data(tr); + + if (!tr->ring_buffer_expanded) + ret = __tracing_resize_ring_buffer(tr, trace_buf_size, + RING_BUFFER_ALL_CPUS); return ret; } -struct trace_option_dentry; - -static void -create_trace_option_files(struct trace_array *tr, struct tracer *tracer); - /* * Used to clear out the tracer before deletion of an instance. * Must have trace_types_lock held. @@ -5339,71 +6277,76 @@ static void tracing_set_nop(struct trace_array *tr) { if (tr->current_trace == &nop_trace) return; - + tr->current_trace->enabled--; if (tr->current_trace->reset) tr->current_trace->reset(tr); tr->current_trace = &nop_trace; + tr->current_trace_flags = nop_trace.flags; } -static void add_tracer_options(struct trace_array *tr, struct tracer *t) -{ - /* Only enable if the directory has been created already. */ - if (!tr->dir) - return; - - create_trace_option_files(tr, t); -} +static bool tracer_options_updated; -static int tracing_set_tracer(struct trace_array *tr, const char *buf) +int tracing_set_tracer(struct trace_array *tr, const char *buf) { - struct tracer *t; + struct tracer *trace = NULL; + struct tracers *t; #ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; #endif - int ret = 0; + int ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); + + update_last_data(tr); - if (!ring_buffer_expanded) { + if (!tr->ring_buffer_expanded) { ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); if (ret < 0) - goto out; + return ret; ret = 0; } - for (t = trace_types; t; t = t->next) { - if (strcmp(t->name, buf) == 0) + list_for_each_entry(t, &tr->tracers, list) { + if (strcmp(t->tracer->name, buf) == 0) { + trace = t->tracer; break; + } } - if (!t) { - ret = -EINVAL; - goto out; - } - if (t == tr->current_trace) - goto out; + if (!trace) + return -EINVAL; + + if (trace == tr->current_trace) + return 0; +#ifdef CONFIG_TRACER_SNAPSHOT + if (trace->use_max_tr) { + local_irq_disable(); + arch_spin_lock(&tr->max_lock); + ret = tr->cond_snapshot ? -EBUSY : 0; + arch_spin_unlock(&tr->max_lock); + local_irq_enable(); + if (ret) + return ret; + } +#endif /* Some tracers won't work on kernel command line */ - if (system_state < SYSTEM_RUNNING && t->noboot) { + if (system_state < SYSTEM_RUNNING && trace->noboot) { pr_warn("Tracer '%s' is not allowed on command line, ignored\n", - t->name); - goto out; + trace->name); + return -EINVAL; } /* Some tracers are only allowed for the top level buffer */ - if (!trace_ok_for_array(t, tr)) { - ret = -EINVAL; - goto out; - } + if (!trace_ok_for_array(trace, tr)) + return -EINVAL; /* If trace pipe files are being read, we can't change the tracer */ - if (tr->current_trace->ref) { - ret = -EBUSY; - goto out; - } + if (tr->trace_ref) + return -EBUSY; trace_branch_disable(); @@ -5412,13 +6355,14 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); +#ifdef CONFIG_TRACER_MAX_TRACE + had_max_tr = tr->current_trace->use_max_tr; + /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; + tr->current_trace_flags = nop_trace.flags; -#ifdef CONFIG_TRACER_MAX_TRACE - had_max_tr = tr->allocated_snapshot; - - if (had_max_tr && !t->use_max_tr) { + if (had_max_tr && !trace->use_max_tr) { /* * We need to make sure that the update_max_tr sees that * current_trace changed to nop_trace to keep it from @@ -5428,30 +6372,37 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) */ synchronize_rcu(); free_snapshot(tr); + tracing_disarm_snapshot(tr); } -#endif -#ifdef CONFIG_TRACER_MAX_TRACE - if (t->use_max_tr && !had_max_tr) { - ret = tracing_alloc_snapshot_instance(tr); - if (ret < 0) - goto out; + if (!had_max_tr && trace->use_max_tr) { + ret = tracing_arm_snapshot_locked(tr); + if (ret) + return ret; } +#else + tr->current_trace = &nop_trace; #endif - if (t->init) { - ret = tracer_init(t, tr); - if (ret) - goto out; + tr->current_trace_flags = t->flags ? : t->tracer->flags; + + if (trace->init) { + ret = tracer_init(trace, tr); + if (ret) { +#ifdef CONFIG_TRACER_MAX_TRACE + if (trace->use_max_tr) + tracing_disarm_snapshot(tr); +#endif + tr->current_trace_flags = nop_trace.flags; + return ret; + } } - tr->current_trace = t; + tr->current_trace = trace; tr->current_trace->enabled++; trace_branch_enable(tr); - out: - mutex_unlock(&trace_types_lock); - return ret; + return 0; } static ssize_t @@ -5460,7 +6411,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, { struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+1]; - int i; + char *name; size_t ret; int err; @@ -5474,11 +6425,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, buf[cnt] = 0; - /* strip ending whitespace. */ - for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) - buf[i] = 0; + name = strim(buf); - err = tracing_set_tracer(tr, buf); + err = tracing_set_tracer(tr, name); if (err) return err; @@ -5531,62 +6480,89 @@ tracing_thresh_write(struct file *filp, const char __user *ubuf, struct trace_array *tr = filp->private_data; int ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); ret = tracing_nsecs_write(&tracing_thresh, ubuf, cnt, ppos); if (ret < 0) - goto out; + return ret; if (tr->current_trace->update_thresh) { ret = tr->current_trace->update_thresh(tr); if (ret < 0) - goto out; + return ret; } - ret = cnt; -out: - mutex_unlock(&trace_types_lock); - - return ret; + return cnt; } -#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) +#ifdef CONFIG_TRACER_MAX_TRACE static ssize_t tracing_max_lat_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - return tracing_nsecs_read(filp->private_data, ubuf, cnt, 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) { - return tracing_nsecs_write(filp->private_data, ubuf, cnt, 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) { + if (cpumask_empty(tr->pipe_cpumask)) { + cpumask_setall(tr->pipe_cpumask); + return 0; + } + } else if (!cpumask_test_cpu(cpu, tr->pipe_cpumask)) { + cpumask_set_cpu(cpu, tr->pipe_cpumask); + return 0; + } + return -EBUSY; +} + +static void close_pipe_on_cpu(struct trace_array *tr, int cpu) +{ + if (cpu == RING_BUFFER_ALL_CPUS) { + WARN_ON(!cpumask_full(tr->pipe_cpumask)); + cpumask_clear(tr->pipe_cpumask); + } else { + WARN_ON(!cpumask_test_cpu(cpu, tr->pipe_cpumask)); + cpumask_clear_cpu(cpu, tr->pipe_cpumask); + } +} + static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; - int ret = 0; - - if (tracing_disabled) - return -ENODEV; + int cpu; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); + cpu = tracing_get_cpu(inode); + ret = open_pipe_on_cpu(tr, cpu); + if (ret) + goto fail_pipe_on_cpu; /* create a buffer to store the information to pass to userspace */ iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { ret = -ENOMEM; - __trace_array_put(tr); - goto out; + goto fail_alloc_iter; } trace_seq_init(&iter->seq); @@ -5600,7 +6576,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) /* trace pipe does not show start of buffer */ cpumask_setall(iter->started); - if (tr->trace_flags & TRACE_ITER_LATENCY_FMT) + if (tr->trace_flags & TRACE_ITER(LATENCY_FMT)) iter->iter_flags |= TRACE_FILE_LAT_FMT; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ @@ -5608,8 +6584,8 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; iter->tr = tr; - iter->trace_buffer = &tr->trace_buffer; - iter->cpu_file = tracing_get_cpu(inode); + iter->array_buffer = &tr->array_buffer; + iter->cpu_file = cpu; mutex_init(&iter->mutex); filp->private_data = iter; @@ -5618,16 +6594,16 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) nonseekable_open(inode, filp); - tr->current_trace->ref++; -out: - mutex_unlock(&trace_types_lock); + tr->trace_ref++; + return ret; fail: - kfree(iter->trace); kfree(iter); +fail_alloc_iter: + close_pipe_on_cpu(tr, cpu); +fail_pipe_on_cpu: __trace_array_put(tr); - mutex_unlock(&trace_types_lock); return ret; } @@ -5636,17 +6612,15 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) struct trace_iterator *iter = file->private_data; struct trace_array *tr = inode->i_private; - mutex_lock(&trace_types_lock); - - tr->current_trace->ref--; - - if (iter->trace->pipe_close) - iter->trace->pipe_close(iter); + scoped_guard(mutex, &trace_types_lock) { + tr->trace_ref--; - mutex_unlock(&trace_types_lock); + if (iter->trace->pipe_close) + iter->trace->pipe_close(iter); + close_pipe_on_cpu(tr, iter->cpu_file); + } - free_cpumask_var(iter->started); - mutex_destroy(&iter->mutex); + free_trace_iter_content(iter); kfree(iter); trace_array_put(tr); @@ -5663,14 +6637,14 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl if (trace_buffer_iter(iter, iter->cpu_file)) return EPOLLIN | EPOLLRDNORM; - if (tr->trace_flags & TRACE_ITER_BLOCK) + if (tr->trace_flags & TRACE_ITER(BLOCK)) /* * Always select as readable when in blocking mode */ return EPOLLIN | EPOLLRDNORM; else - return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file, - filp, poll_table); + return ring_buffer_poll_wait(iter->array_buffer->buffer, iter->cpu_file, + filp, poll_table, iter->tr->buffer_percent); } static __poll_t @@ -5718,6 +6692,22 @@ static int tracing_wait_pipe(struct file *filp) return 1; } +static bool update_last_data_if_empty(struct trace_array *tr) +{ + if (!(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) + return false; + + if (!ring_buffer_empty(tr->array_buffer.buffer)) + return false; + + /* + * If the buffer contains the last boot data and all per-cpu + * buffers are empty, reset it from the kernel side. + */ + update_last_data(tr); + return true; +} + /* * Consumer reader. */ @@ -5733,41 +6723,40 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, * This is just a matter of traces coherency, the ring buffer itself * is protected. */ - mutex_lock(&iter->mutex); + guard(mutex)(&iter->mutex); /* return any leftover data */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (sret != -EBUSY) - goto out; + return sret; trace_seq_init(&iter->seq); if (iter->trace->read) { sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); if (sret) - goto out; + return sret; } waitagain: + if (update_last_data_if_empty(iter->tr)) + return 0; + sret = tracing_wait_pipe(filp); if (sret <= 0) - goto out; + return sret; /* stop when tracing is finished */ - if (trace_empty(iter)) { - sret = 0; - goto out; - } + if (trace_empty(iter)) + return 0; - if (cnt >= PAGE_SIZE) - cnt = PAGE_SIZE - 1; + if (cnt >= TRACE_SEQ_BUFFER_SIZE) + cnt = TRACE_SEQ_BUFFER_SIZE - 1; /* reset all but tr, trace, and overruns */ - memset(&iter->seq, 0, - sizeof(struct trace_iterator) - - offsetof(struct trace_iterator, seq)); + trace_iterator_reset(iter); cpumask_clear(iter->started); - iter->pos = -1; + trace_seq_init(&iter->seq); trace_event_read_lock(); trace_access_lock(iter->cpu_file); @@ -5777,7 +6766,20 @@ waitagain: ret = print_trace_line(iter); if (ret == TRACE_TYPE_PARTIAL_LINE) { - /* don't print partial lines */ + /* + * If one print_trace_line() fills entire trace_seq in one shot, + * trace_seq_to_user() will returns -EBUSY because save_len == 0, + * In this case, we need to consume it, otherwise, loop will peek + * this event next time, resulting in an infinite loop. + */ + if (save_len == 0) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + trace_consume(iter); + break; + } + + /* In other cases, don't print partial lines */ iter->seq.seq.len = save_len; break; } @@ -5800,7 +6802,7 @@ waitagain: /* Now copy what we have to the user */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); - if (iter->seq.seq.readpos >= trace_seq_used(&iter->seq)) + if (iter->seq.readpos >= trace_seq_used(&iter->seq)) trace_seq_init(&iter->seq); /* @@ -5810,9 +6812,6 @@ waitagain: if (sret == -EBUSY) goto waitagain; -out: - mutex_unlock(&iter->mutex); - return sret; } @@ -5822,14 +6821,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd, __free_page(spd->pages[idx]); } -static const struct pipe_buf_operations tracing_pipe_buf_ops = { - .can_merge = 0, - .confirm = generic_pipe_buf_confirm, - .release = generic_pipe_buf_release, - .steal = generic_pipe_buf_steal, - .get = generic_pipe_buf_get, -}; - static size_t tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) { @@ -5891,7 +6882,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .partial = partial_def, .nr_pages = 0, /* This gets updated below. */ .nr_pages_max = PIPE_DEF_BUFFERS, - .ops = &tracing_pipe_buf_ops, + .ops = &default_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; ssize_t ret; @@ -5933,13 +6924,14 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, /* Copy the data into the page, so we can start over. */ ret = trace_seq_to_buffer(&iter->seq, page_address(spd.pages[i]), - trace_seq_used(&iter->seq)); + min((size_t)trace_seq_used(&iter->seq), + (size_t)PAGE_SIZE)); if (ret < 0) { __free_page(spd.pages[i]); break; } spd.partial[i].offset = 0; - spd.partial[i].len = trace_seq_used(&iter->seq); + spd.partial[i].len = ret; trace_seq_init(&iter->seq); } @@ -5964,6 +6956,43 @@ out_err: } static ssize_t +tracing_syscall_buf_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; + char buf[64]; + int r; + + r = snprintf(buf, 64, "%d\n", tr->syscall_buf_sz); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_syscall_buf_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (val > SYSCALL_FAULT_USER_MAX) + val = SYSCALL_FAULT_USER_MAX; + + tr->syscall_buf_sz = val; + + *ppos += cnt; + + return cnt; +} + +static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -5986,15 +7015,15 @@ tracing_entries_read(struct file *filp, char __user *ubuf, for_each_tracing_cpu(cpu) { /* fill in the size from first enabled cpu */ if (size == 0) - size = per_cpu_ptr(tr->trace_buffer.data, cpu)->entries; - if (size != per_cpu_ptr(tr->trace_buffer.data, cpu)->entries) { + size = per_cpu_ptr(tr->array_buffer.data, cpu)->entries; + if (size != per_cpu_ptr(tr->array_buffer.data, cpu)->entries) { buf_size_same = 0; break; } } if (buf_size_same) { - if (!ring_buffer_expanded) + if (!tr->ring_buffer_expanded) r = sprintf(buf, "%lu (expanded: %lu)\n", size >> 10, trace_buf_size >> 10); @@ -6003,7 +7032,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, } else r = sprintf(buf, "X\n"); } else - r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10); + r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10); mutex_unlock(&trace_types_lock); @@ -6050,11 +7079,11 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { - size += per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10; - if (!ring_buffer_expanded) + size += per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10; + if (!tr->ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } - if (ring_buffer_expanded) + if (tr->ring_buffer_expanded) r = sprintf(buf, "%lu\n", size); else r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size); @@ -6063,6 +7092,120 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } +#define LAST_BOOT_HEADER ((void *)1) + +static void *l_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct trace_array *tr = m->private; + struct trace_scratch *tscratch = tr->scratch; + unsigned int index = *pos; + + (*pos)++; + + if (*pos == 1) + return LAST_BOOT_HEADER; + + /* Only show offsets of the last boot data */ + if (!tscratch || !(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) + return NULL; + + /* *pos 0 is for the header, 1 is for the first module */ + index--; + + if (index >= tscratch->nr_entries) + return NULL; + + return &tscratch->entries[index]; +} + +static void *l_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&scratch_mutex); + + return l_next(m, NULL, pos); +} + +static void l_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&scratch_mutex); +} + +static void show_last_boot_header(struct seq_file *m, struct trace_array *tr) +{ + struct trace_scratch *tscratch = tr->scratch; + + /* + * Do not leak KASLR address. This only shows the KASLR address of + * the last boot. When the ring buffer is started, the LAST_BOOT + * flag gets cleared, and this should only report "current". + * Otherwise it shows the KASLR address from the previous boot which + * should not be the same as the current boot. + */ + if (tscratch && (tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) + seq_printf(m, "%lx\t[kernel]\n", tscratch->text_addr); + else + seq_puts(m, "# Current\n"); +} + +static int l_show(struct seq_file *m, void *v) +{ + struct trace_array *tr = m->private; + struct trace_mod_entry *entry = v; + + if (v == LAST_BOOT_HEADER) { + show_last_boot_header(m, tr); + return 0; + } + + seq_printf(m, "%lx\t%s\n", entry->mod_addr, entry->mod_name); + return 0; +} + +static const struct seq_operations last_boot_seq_ops = { + .start = l_start, + .next = l_next, + .stop = l_stop, + .show = l_show, +}; + +static int tracing_last_boot_open(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + struct seq_file *m; + int ret; + + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; + + ret = seq_open(file, &last_boot_seq_ops); + if (ret) { + trace_array_put(tr); + return ret; + } + + m = file->private_data; + m->private = tr; + + return 0; +} + +static int tracing_buffer_meta_open(struct inode *inode, struct file *filp) +{ + struct trace_array *tr = inode->i_private; + int cpu = tracing_get_cpu(inode); + int ret; + + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; + + ret = ring_buffer_meta_seq_init(filp, tr->array_buffer.buffer, cpu); + if (ret < 0) + __trace_array_put(tr); + return ret; +} + static ssize_t tracing_free_buffer_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) @@ -6083,7 +7226,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) struct trace_array *tr = inode->i_private; /* disable tracing ? */ - if (tr->trace_flags & TRACE_ITER_STOP_ON_FREE) + if (tr->trace_flags & TRACE_ITER(STOP_ON_FREE)) tracer_tracing_off(tr); /* resize the ring buffer to 0 */ tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS); @@ -6093,65 +7236,52 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) return 0; } -static ssize_t -tracing_mark_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *fpos) +#define TRACE_MARKER_MAX_SIZE 4096 + +static ssize_t write_marker_to_buffer(struct trace_array *tr, const char *buf, + size_t cnt, unsigned long ip) { - struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; enum event_trigger_type tt = ETT_NONE; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct print_entry *entry; - unsigned long irq_flags; - const char faulted[] = "<faulted>"; + int meta_size; ssize_t written; - int size; - int len; - -/* Used in tracing_mark_raw_write() as well */ -#define FAULTED_SIZE (sizeof(faulted) - 1) /* '\0' is already accounted for */ - - if (tracing_disabled) - return -EINVAL; - - if (!(tr->trace_flags & TRACE_ITER_MARKERS)) - return -EINVAL; - - if (cnt > TRACE_BUF_SIZE) - cnt = TRACE_BUF_SIZE; - - BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); - - local_save_flags(irq_flags); - size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */ + size_t size; - /* If less than "<faulted>", then make sure we can still add that */ - if (cnt < FAULTED_SIZE) - size += FAULTED_SIZE - cnt; + meta_size = sizeof(*entry) + 2; /* add '\0' and possible '\n' */ + again: + size = cnt + meta_size; - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, - irq_flags, preempt_count()); - if (unlikely(!event)) + tracing_gen_ctx()); + if (unlikely(!event)) { + /* + * If the size was greater than what was allowed, then + * make it smaller and try again. + */ + if (size > ring_buffer_max_event_size(buffer)) { + cnt = ring_buffer_max_event_size(buffer) - meta_size; + /* The above should only happen once */ + if (WARN_ON_ONCE(cnt + meta_size == size)) + return -EBADF; + goto again; + } + /* Ring buffer disabled, return as if not open for write */ return -EBADF; + } entry = ring_buffer_event_data(event); - entry->ip = _THIS_IP_; - - len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt); - if (len) { - memcpy(&entry->buf, faulted, FAULTED_SIZE); - cnt = FAULTED_SIZE; - written = -EFAULT; - } else - written = cnt; - len = cnt; + entry->ip = ip; + memcpy(&entry->buf, buf, cnt); + written = cnt; if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { /* do not add \n before testing triggers, but add \0 */ entry->buf[cnt] = '\0'; - tt = event_triggers_call(tr->trace_marker_file, entry, event); + tt = event_triggers_call(tr->trace_marker_file, buffer, entry, event); } if (entry->buf[cnt - 1] != '\n') { @@ -6160,81 +7290,456 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, } else entry->buf[cnt] = '\0'; + if (static_branch_unlikely(&trace_marker_exports_enabled)) + ftrace_exports(event, TRACE_EXPORT_MARKER); __buffer_unlock_commit(buffer, event); if (tt) event_triggers_post_call(tr->trace_marker_file, tt); - if (written > 0) - *fpos += written; - return written; } -/* Limit it for now to 3K (including tag) */ -#define RAW_DATA_MAX_SIZE (1024*3) +struct trace_user_buf { + char *buf; +}; + +static DEFINE_MUTEX(trace_user_buffer_mutex); +static struct trace_user_buf_info *trace_user_buffer; + +/** + * trace_user_fault_destroy - free up allocated memory of a trace user buffer + * @tinfo: The descriptor to free up + * + * Frees any data allocated in the trace info dsecriptor. + */ +void trace_user_fault_destroy(struct trace_user_buf_info *tinfo) +{ + char *buf; + int cpu; + + if (!tinfo || !tinfo->tbuf) + return; + + for_each_possible_cpu(cpu) { + buf = per_cpu_ptr(tinfo->tbuf, cpu)->buf; + kfree(buf); + } + free_percpu(tinfo->tbuf); +} + +static int user_fault_buffer_enable(struct trace_user_buf_info *tinfo, size_t size) +{ + char *buf; + int cpu; + + lockdep_assert_held(&trace_user_buffer_mutex); + + tinfo->tbuf = alloc_percpu(struct trace_user_buf); + if (!tinfo->tbuf) + return -ENOMEM; + + tinfo->ref = 1; + tinfo->size = size; + + /* Clear each buffer in case of error */ + for_each_possible_cpu(cpu) { + per_cpu_ptr(tinfo->tbuf, cpu)->buf = NULL; + } + + for_each_possible_cpu(cpu) { + buf = kmalloc_node(size, GFP_KERNEL, + cpu_to_node(cpu)); + if (!buf) + return -ENOMEM; + per_cpu_ptr(tinfo->tbuf, cpu)->buf = buf; + } + + return 0; +} + +/* For internal use. Free and reinitialize */ +static void user_buffer_free(struct trace_user_buf_info **tinfo) +{ + lockdep_assert_held(&trace_user_buffer_mutex); + + trace_user_fault_destroy(*tinfo); + kfree(*tinfo); + *tinfo = NULL; +} + +/* For internal use. Initialize and allocate */ +static int user_buffer_init(struct trace_user_buf_info **tinfo, size_t size) +{ + bool alloc = false; + int ret; + + lockdep_assert_held(&trace_user_buffer_mutex); + + if (!*tinfo) { + alloc = true; + *tinfo = kzalloc(sizeof(**tinfo), GFP_KERNEL); + if (!*tinfo) + return -ENOMEM; + } + + ret = user_fault_buffer_enable(*tinfo, size); + if (ret < 0 && alloc) + user_buffer_free(tinfo); + + return ret; +} + +/* For internal use, derefrence and free if necessary */ +static void user_buffer_put(struct trace_user_buf_info **tinfo) +{ + guard(mutex)(&trace_user_buffer_mutex); + + if (WARN_ON_ONCE(!*tinfo || !(*tinfo)->ref)) + return; + + if (--(*tinfo)->ref) + return; + + user_buffer_free(tinfo); +} + +/** + * trace_user_fault_init - Allocated or reference a per CPU buffer + * @tinfo: A pointer to the trace buffer descriptor + * @size: The size to allocate each per CPU buffer + * + * Create a per CPU buffer that can be used to copy from user space + * in a task context. When calling trace_user_fault_read(), preemption + * must be disabled, and it will enable preemption and copy user + * space data to the buffer. If any schedule switches occur, it will + * retry until it succeeds without a schedule switch knowing the buffer + * is still valid. + * + * Returns 0 on success, negative on failure. + */ +int trace_user_fault_init(struct trace_user_buf_info *tinfo, size_t size) +{ + int ret; + + if (!tinfo) + return -EINVAL; + + guard(mutex)(&trace_user_buffer_mutex); + + ret = user_buffer_init(&tinfo, size); + if (ret < 0) + trace_user_fault_destroy(tinfo); + + return ret; +} + +/** + * trace_user_fault_get - up the ref count for the user buffer + * @tinfo: A pointer to a pointer to the trace buffer descriptor + * + * Ups the ref count of the trace buffer. + * + * Returns the new ref count. + */ +int trace_user_fault_get(struct trace_user_buf_info *tinfo) +{ + if (!tinfo) + return -1; + + guard(mutex)(&trace_user_buffer_mutex); + + tinfo->ref++; + return tinfo->ref; +} + +/** + * trace_user_fault_put - dereference a per cpu trace buffer + * @tinfo: The @tinfo that was passed to trace_user_fault_get() + * + * Decrement the ref count of @tinfo. + * + * Returns the new refcount (negative on error). + */ +int trace_user_fault_put(struct trace_user_buf_info *tinfo) +{ + guard(mutex)(&trace_user_buffer_mutex); + + if (WARN_ON_ONCE(!tinfo || !tinfo->ref)) + return -1; + + --tinfo->ref; + return tinfo->ref; +} + +/** + * trace_user_fault_read - Read user space into a per CPU buffer + * @tinfo: The @tinfo allocated by trace_user_fault_get() + * @ptr: The user space pointer to read + * @size: The size of user space to read. + * @copy_func: Optional function to use to copy from user space + * @data: Data to pass to copy_func if it was supplied + * + * Preemption must be disabled when this is called, and must not + * be enabled while using the returned buffer. + * This does the copying from user space into a per CPU buffer. + * + * The @size must not be greater than the size passed in to + * trace_user_fault_init(). + * + * If @copy_func is NULL, trace_user_fault_read() will use copy_from_user(), + * otherwise it will call @copy_func. It will call @copy_func with: + * + * buffer: the per CPU buffer of the @tinfo. + * ptr: The pointer @ptr to user space to read + * size: The @size of the ptr to read + * data: The @data parameter + * + * It is expected that @copy_func will return 0 on success and non zero + * if there was a fault. + * + * Returns a pointer to the buffer with the content read from @ptr. + * Preemption must remain disabled while the caller accesses the + * buffer returned by this function. + * Returns NULL if there was a fault, or the size passed in is + * greater than the size passed to trace_user_fault_init(). + */ +char *trace_user_fault_read(struct trace_user_buf_info *tinfo, + const char __user *ptr, size_t size, + trace_user_buf_copy copy_func, void *data) +{ + int cpu = smp_processor_id(); + char *buffer = per_cpu_ptr(tinfo->tbuf, cpu)->buf; + unsigned int cnt; + int trys = 0; + int ret; + + lockdep_assert_preemption_disabled(); + + /* + * It's up to the caller to not try to copy more than it said + * it would. + */ + if (size > tinfo->size) + return NULL; + + /* + * This acts similar to a seqcount. The per CPU context switches are + * recorded, migration is disabled and preemption is enabled. The + * read of the user space memory is copied into the per CPU buffer. + * Preemption is disabled again, and if the per CPU context switches count + * is still the same, it means the buffer has not been corrupted. + * If the count is different, it is assumed the buffer is corrupted + * and reading must be tried again. + */ + + do { + /* + * If for some reason, copy_from_user() always causes a context + * switch, this would then cause an infinite loop. + * If this task is preempted by another user space task, it + * will cause this task to try again. But just in case something + * changes where the copying from user space causes another task + * to run, prevent this from going into an infinite loop. + * 100 tries should be plenty. + */ + if (WARN_ONCE(trys++ > 100, "Error: Too many tries to read user space")) + return NULL; + + /* Read the current CPU context switch counter */ + cnt = nr_context_switches_cpu(cpu); + + /* + * Preemption is going to be enabled, but this task must + * remain on this CPU. + */ + migrate_disable(); + + /* + * Now preemption is being enabled and another task can come in + * and use the same buffer and corrupt our data. + */ + preempt_enable_notrace(); + + /* Make sure preemption is enabled here */ + lockdep_assert_preemption_enabled(); + + if (copy_func) { + ret = copy_func(buffer, ptr, size, data); + } else { + ret = __copy_from_user(buffer, ptr, size); + } + + preempt_disable_notrace(); + migrate_enable(); + + /* if it faulted, no need to test if the buffer was corrupted */ + if (ret) + return NULL; + + /* + * Preemption is disabled again, now check the per CPU context + * switch counter. If it doesn't match, then another user space + * process may have schedule in and corrupted our buffer. In that + * case the copying must be retried. + */ + } while (nr_context_switches_cpu(cpu) != cnt); + + return buffer; +} static ssize_t -tracing_mark_raw_write(struct file *filp, const char __user *ubuf, +tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { struct trace_array *tr = filp->private_data; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - struct raw_data_entry *entry; - const char faulted[] = "<faulted>"; - unsigned long irq_flags; - ssize_t written; - int size; - int len; - -#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int)) + ssize_t written = -ENODEV; + unsigned long ip; + char *buf; if (tracing_disabled) return -EINVAL; - if (!(tr->trace_flags & TRACE_ITER_MARKERS)) + if (!(tr->trace_flags & TRACE_ITER(MARKERS))) return -EINVAL; - /* The marker must at least have a tag id */ - if (cnt < sizeof(unsigned int) || cnt > RAW_DATA_MAX_SIZE) + if ((ssize_t)cnt < 0) return -EINVAL; - if (cnt > TRACE_BUF_SIZE) - cnt = TRACE_BUF_SIZE; + if (cnt > TRACE_MARKER_MAX_SIZE) + cnt = TRACE_MARKER_MAX_SIZE; + + /* Must have preemption disabled while having access to the buffer */ + guard(preempt_notrace)(); + + buf = trace_user_fault_read(trace_user_buffer, ubuf, cnt, NULL, NULL); + if (!buf) + return -EFAULT; + + /* The selftests expect this function to be the IP address */ + ip = _THIS_IP_; + + /* The global trace_marker can go to multiple instances */ + if (tr == &global_trace) { + guard(rcu)(); + list_for_each_entry_rcu(tr, &marker_copies, marker_list) { + written = write_marker_to_buffer(tr, buf, cnt, ip); + if (written < 0) + break; + } + } else { + written = write_marker_to_buffer(tr, buf, cnt, ip); + } + + return written; +} + +static ssize_t write_raw_marker_to_buffer(struct trace_array *tr, + const char *buf, size_t cnt) +{ + struct ring_buffer_event *event; + struct trace_buffer *buffer; + struct raw_data_entry *entry; + ssize_t written; + size_t size; - BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); + /* cnt includes both the entry->id and the data behind it. */ + size = struct_offset(entry, id) + cnt; - local_save_flags(irq_flags); - size = sizeof(*entry) + cnt; - if (cnt < FAULT_SIZE_ID) - size += FAULT_SIZE_ID - cnt; + buffer = tr->array_buffer.buffer; + + if (size > ring_buffer_max_event_size(buffer)) + return -EINVAL; - buffer = tr->trace_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size, - irq_flags, preempt_count()); + tracing_gen_ctx()); if (!event) /* Ring buffer disabled, return as if not open for write */ return -EBADF; entry = ring_buffer_event_data(event); - - len = __copy_from_user_inatomic(&entry->id, ubuf, cnt); - if (len) { - entry->id = -1; - memcpy(&entry->buf, faulted, FAULTED_SIZE); - written = -EFAULT; - } else - written = cnt; + unsafe_memcpy(&entry->id, buf, cnt, + "id and content already reserved on ring buffer" + "'buf' includes the 'id' and the data." + "'entry' was allocated with cnt from 'id'."); + written = cnt; __buffer_unlock_commit(buffer, event); - if (written > 0) - *fpos += written; + return written; +} + +static ssize_t +tracing_mark_raw_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *fpos) +{ + struct trace_array *tr = filp->private_data; + ssize_t written = -ENODEV; + char *buf; + + if (tracing_disabled) + return -EINVAL; + + if (!(tr->trace_flags & TRACE_ITER(MARKERS))) + return -EINVAL; + + /* The marker must at least have a tag id */ + if (cnt < sizeof(unsigned int)) + return -EINVAL; + + /* raw write is all or nothing */ + if (cnt > TRACE_MARKER_MAX_SIZE) + return -EINVAL; + + /* Must have preemption disabled while having access to the buffer */ + guard(preempt_notrace)(); + + buf = trace_user_fault_read(trace_user_buffer, ubuf, cnt, NULL, NULL); + if (!buf) + return -EFAULT; + + /* The global trace_marker_raw can go to multiple instances */ + if (tr == &global_trace) { + guard(rcu)(); + list_for_each_entry_rcu(tr, &marker_copies, marker_list) { + written = write_raw_marker_to_buffer(tr, buf, cnt); + if (written < 0) + break; + } + } else { + written = write_raw_marker_to_buffer(tr, buf, cnt); + } return written; } +static int tracing_mark_open(struct inode *inode, struct file *filp) +{ + int ret; + + scoped_guard(mutex, &trace_user_buffer_mutex) { + if (!trace_user_buffer) { + ret = user_buffer_init(&trace_user_buffer, TRACE_MARKER_MAX_SIZE); + if (ret < 0) + return ret; + } else { + trace_user_buffer->ref++; + } + } + + stream_open(inode, filp); + ret = tracing_open_generic_tr(inode, filp); + if (ret < 0) + user_buffer_put(&trace_user_buffer); + return ret; +} + +static int tracing_mark_release(struct inode *inode, struct file *file) +{ + user_buffer_put(&trace_user_buffer); + return tracing_release_generic_tr(inode, file); +} + static int tracing_clock_show(struct seq_file *m, void *v) { struct trace_array *tr = m->private; @@ -6261,17 +7766,17 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr) if (i == ARRAY_SIZE(trace_clocks)) return -EINVAL; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); tr->clock_id = i; - ring_buffer_set_clock(tr->trace_buffer.buffer, trace_clocks[i].func); + ring_buffer_set_clock(tr->array_buffer.buffer, trace_clocks[i].func); /* * New clock may not be consistent with the previous clock. * Reset the buffer so that it doesn't have incomparable timestamps. */ - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (tr->max_buffer.buffer) @@ -6279,7 +7784,11 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr) tracing_reset_online_cpus(&tr->max_buffer); #endif - mutex_unlock(&trace_types_lock); + if (tr->scratch && !(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) { + struct trace_scratch *tscratch = tr->scratch; + + tscratch->clock_id = i; + } return 0; } @@ -6317,11 +7826,9 @@ static int tracing_clock_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr)) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_clock_show, inode->i_private); if (ret < 0) @@ -6334,15 +7841,13 @@ static int tracing_time_stamp_mode_show(struct seq_file *m, void *v) { struct trace_array *tr = m->private; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); - if (ring_buffer_time_stamp_abs(tr->trace_buffer.buffer)) + if (ring_buffer_time_stamp_abs(tr->array_buffer.buffer)) seq_puts(m, "delta [absolute]\n"); else seq_puts(m, "[delta] absolute\n"); - mutex_unlock(&trace_types_lock); - return 0; } @@ -6351,11 +7856,9 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr)) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private); if (ret < 0) @@ -6364,41 +7867,39 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) return ret; } -int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs) +u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe) { - int ret = 0; - - mutex_lock(&trace_types_lock); + if (rbe == this_cpu_read(trace_buffered_event)) + return ring_buffer_time_stamp(buffer); - if (abs && tr->time_stamp_abs_ref++) - goto out; + return ring_buffer_event_time_stamp(buffer, rbe); +} - if (!abs) { - if (WARN_ON_ONCE(!tr->time_stamp_abs_ref)) { - ret = -EINVAL; - goto out; - } +/* + * Set or disable using the per CPU trace_buffer_event when possible. + */ +int tracing_set_filter_buffering(struct trace_array *tr, bool set) +{ + guard(mutex)(&trace_types_lock); - if (--tr->time_stamp_abs_ref) - goto out; - } + if (set && tr->no_filter_buffering_ref++) + return 0; - ring_buffer_set_time_stamp_abs(tr->trace_buffer.buffer, abs); + if (!set) { + if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) + return -EINVAL; -#ifdef CONFIG_TRACER_MAX_TRACE - if (tr->max_buffer.buffer) - ring_buffer_set_time_stamp_abs(tr->max_buffer.buffer, abs); -#endif - out: - mutex_unlock(&trace_types_lock); + --tr->no_filter_buffering_ref; + } - return ret; + return 0; } struct ftrace_buffer_info { struct trace_iterator iter; void *spare; unsigned int spare_cpu; + unsigned int spare_size; unsigned int read; }; @@ -6408,10 +7909,11 @@ 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 = 0; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, true); @@ -6431,7 +7933,7 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) ret = 0; iter->tr = tr; - iter->trace_buffer = &tr->max_buffer; + iter->array_buffer = &tr->max_buffer; iter->cpu_file = tracing_get_cpu(inode); m->private = iter; file->private_data = m; @@ -6443,6 +7945,11 @@ out: 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) @@ -6453,7 +7960,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, unsigned long val; int ret; - ret = tracing_update_buffers(); + ret = tracing_update_buffers(tr); if (ret < 0) return ret; @@ -6461,49 +7968,58 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, if (ret) return ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); - if (tr->current_trace->use_max_tr) { + if (tr->current_trace->use_max_tr) + return -EBUSY; + + local_irq_disable(); + arch_spin_lock(&tr->max_lock); + if (tr->cond_snapshot) ret = -EBUSY; - goto out; - } + 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) { - ret = -EINVAL; - break; - } + 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) { - ret = -EINVAL; - break; - } + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) + return -EINVAL; #endif - if (!tr->allocated_snapshot) { - ret = tracing_alloc_snapshot_instance(tr); - if (ret < 0) - break; - } - local_irq_disable(); + if (tr->allocated_snapshot) + ret = resize_buffer_duplicate_size(&tr->max_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) - update_max_tr(tr, current, smp_processor_id()); - else - update_max_tr_single(tr, current, iter->cpu_file); - local_irq_enable(); + 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->max_buffer); else - tracing_reset(&tr->max_buffer, iter->cpu_file); + tracing_reset_cpu(&tr->max_buffer, iter->cpu_file); } break; } @@ -6512,8 +8028,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, *ppos += cnt; ret = cnt; } -out: - mutex_unlock(&trace_types_lock); + return ret; } @@ -6547,6 +8062,7 @@ 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; @@ -6559,7 +8075,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp) } info->iter.snapshot = true; - info->iter.trace_buffer = &info->iter.tr->max_buffer; + info->iter.array_buffer = &info->iter.tr->max_buffer; return ret; } @@ -6574,20 +8090,22 @@ static const struct file_operations tracing_thresh_fops = { .llseek = generic_file_llseek, }; -#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) +#ifdef CONFIG_TRACER_MAX_TRACE static const struct file_operations tracing_max_lat_fops = { - .open = tracing_open_generic, + .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, + .open = tracing_open_generic_tr, .read = tracing_set_trace_read, .write = tracing_set_trace_write, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, }; static const struct file_operations tracing_pipe_fops = { @@ -6596,7 +8114,6 @@ static const struct file_operations tracing_pipe_fops = { .read = tracing_read_pipe, .splice_read = tracing_splice_read_pipe, .release = tracing_release_pipe, - .llseek = no_llseek, }; static const struct file_operations tracing_entries_fops = { @@ -6607,6 +8124,21 @@ static const struct file_operations tracing_entries_fops = { .release = tracing_release_generic_tr, }; +static const struct file_operations tracing_syscall_buf_fops = { + .open = tracing_open_generic_tr, + .read = tracing_syscall_buf_read, + .write = tracing_syscall_buf_write, + .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, +}; + +static const struct file_operations tracing_buffer_meta_fops = { + .open = tracing_buffer_meta_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_seq_release, +}; + static const struct file_operations tracing_total_entries_fops = { .open = tracing_open_generic_tr, .read = tracing_total_entries_read, @@ -6621,17 +8153,15 @@ static const struct file_operations tracing_free_buffer_fops = { }; static const struct file_operations tracing_mark_fops = { - .open = tracing_open_generic_tr, + .open = tracing_mark_open, .write = tracing_mark_write, - .llseek = generic_file_llseek, - .release = tracing_release_generic_tr, + .release = tracing_mark_release, }; static const struct file_operations tracing_mark_raw_fops = { - .open = tracing_open_generic_tr, + .open = tracing_mark_open, .write = tracing_mark_raw_write, - .llseek = generic_file_llseek, - .release = tracing_release_generic_tr, + .release = tracing_mark_release, }; static const struct file_operations trace_clock_fops = { @@ -6649,6 +8179,13 @@ static const struct file_operations trace_time_stamp_mode_fops = { .release = tracing_single_release_tr, }; +static const struct file_operations last_boot_fops = { + .open = tracing_last_boot_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_seq_release, +}; + #ifdef CONFIG_TRACER_SNAPSHOT static const struct file_operations snapshot_fops = { .open = tracing_snapshot_open, @@ -6663,24 +8200,380 @@ static const struct file_operations snapshot_raw_fops = { .read = tracing_buffers_read, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, - .llseek = no_llseek, }; #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 + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * + * This function implements the write interface for a struct trace_min_max_param. + * The filp->private_data must point to a trace_min_max_param structure that + * defines where to write the value, the min and the max acceptable values, + * and a lock to protect the write. + */ +static ssize_t +trace_min_max_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct trace_min_max_param *param = filp->private_data; + u64 val; + int err; + + if (!param) + return -EFAULT; + + err = kstrtoull_from_user(ubuf, cnt, 10, &val); + if (err) + return err; + + if (param->lock) + mutex_lock(param->lock); + + if (param->min && val < *param->min) + err = -EINVAL; + + if (param->max && val > *param->max) + err = -EINVAL; + + if (!err) + *param->val = val; + + if (param->lock) + mutex_unlock(param->lock); + + if (err) + return err; + + return cnt; +} + +/* + * trace_min_max_read - Read a u64 value from a trace_min_max_param struct + * @filp: The active open file structure + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * + * This function implements the read interface for a struct trace_min_max_param. + * The filp->private_data must point to a trace_min_max_param struct with valid + * data. + */ +static ssize_t +trace_min_max_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct trace_min_max_param *param = filp->private_data; + char buf[U64_STR_SIZE]; + int len; + u64 val; + + if (!param) + return -EFAULT; + + val = *param->val; + + if (cnt > sizeof(buf)) + cnt = sizeof(buf); + + len = snprintf(buf, sizeof(buf), "%llu\n", val); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); +} + +const struct file_operations trace_min_max_fops = { + .open = tracing_open_generic, + .read = trace_min_max_read, + .write = trace_min_max_write, +}; + +#define TRACING_LOG_ERRS_MAX 8 +#define TRACING_LOG_LOC_MAX 128 + +#define CMD_PREFIX " Command: " + +struct err_info { + const char **errs; /* ptr to loc-specific array of err strings */ + u8 type; /* index into errs -> specific err string */ + u16 pos; /* caret position */ + u64 ts; +}; + +struct tracing_log_err { + struct list_head list; + struct err_info info; + char loc[TRACING_LOG_LOC_MAX]; /* err location */ + char *cmd; /* what caused err */ +}; + +static DEFINE_MUTEX(tracing_err_log_lock); + +static struct tracing_log_err *alloc_tracing_log_err(int len) +{ + struct tracing_log_err *err; + + err = kzalloc(sizeof(*err), GFP_KERNEL); + if (!err) + return ERR_PTR(-ENOMEM); + + err->cmd = kzalloc(len, GFP_KERNEL); + if (!err->cmd) { + kfree(err); + return ERR_PTR(-ENOMEM); + } + + return err; +} + +static void free_tracing_log_err(struct tracing_log_err *err) +{ + kfree(err->cmd); + kfree(err); +} + +static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr, + int len) +{ + struct tracing_log_err *err; + char *cmd; + + if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) { + err = alloc_tracing_log_err(len); + if (PTR_ERR(err) != -ENOMEM) + tr->n_err_log_entries++; + + return err; + } + cmd = kzalloc(len, GFP_KERNEL); + if (!cmd) + return ERR_PTR(-ENOMEM); + err = list_first_entry(&tr->err_log, struct tracing_log_err, list); + kfree(err->cmd); + err->cmd = cmd; + list_del(&err->list); + + return err; +} + +/** + * err_pos - find the position of a string within a command for error careting + * @cmd: The tracing command that caused the error + * @str: The string to position the caret at within @cmd + * + * Finds the position of the first occurrence of @str within @cmd. The + * return value can be passed to tracing_log_err() for caret placement + * within @cmd. + * + * Returns the index within @cmd of the first occurrence of @str or 0 + * if @str was not found. + */ +unsigned int err_pos(char *cmd, const char *str) +{ + char *found; + + if (WARN_ON(!strlen(cmd))) + return 0; + + found = strstr(cmd, str); + if (found) + return found - cmd; + + return 0; +} + +/** + * tracing_log_err - write an error to the tracing error log + * @tr: The associated trace array for the error (NULL for top level array) + * @loc: A string describing where the error occurred + * @cmd: The tracing command that caused the error + * @errs: The array of loc-specific static error strings + * @type: The index into errs[], which produces the specific static err string + * @pos: The position the caret should be placed in the cmd + * + * Writes an error into tracing/error_log of the form: + * + * <loc>: error: <text> + * Command: <cmd> + * ^ + * + * tracing/error_log is a small log file containing the last + * TRACING_LOG_ERRS_MAX errors (8). Memory for errors isn't allocated + * unless there has been a tracing error, and the error log can be + * cleared and have its memory freed by writing the empty string in + * truncation mode to it i.e. echo > tracing/error_log. + * + * NOTE: the @errs array along with the @type param are used to + * produce a static error string - this string is not copied and saved + * when the error is logged - only a pointer to it is saved. See + * existing callers for examples of how static strings are typically + * defined for use with tracing_log_err(). + */ +void tracing_log_err(struct trace_array *tr, + const char *loc, const char *cmd, + const char **errs, u8 type, u16 pos) +{ + struct tracing_log_err *err; + int len = 0; + + if (!tr) + tr = &global_trace; + + len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1; + + guard(mutex)(&tracing_err_log_lock); + + err = get_tracing_log_err(tr, len); + if (PTR_ERR(err) == -ENOMEM) + return; + + snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc); + snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd); + + err->info.errs = errs; + err->info.type = type; + err->info.pos = pos; + err->info.ts = local_clock(); + + list_add_tail(&err->list, &tr->err_log); +} + +static void clear_tracing_err_log(struct trace_array *tr) +{ + struct tracing_log_err *err, *next; + + guard(mutex)(&tracing_err_log_lock); + + list_for_each_entry_safe(err, next, &tr->err_log, list) { + list_del(&err->list); + free_tracing_log_err(err); + } + + tr->n_err_log_entries = 0; +} + +static void *tracing_err_log_seq_start(struct seq_file *m, loff_t *pos) +{ + struct trace_array *tr = m->private; + + mutex_lock(&tracing_err_log_lock); + + return seq_list_start(&tr->err_log, *pos); +} + +static void *tracing_err_log_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct trace_array *tr = m->private; + + return seq_list_next(v, &tr->err_log, pos); +} + +static void tracing_err_log_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&tracing_err_log_lock); +} + +static void tracing_err_log_show_pos(struct seq_file *m, u16 pos) +{ + u16 i; + + for (i = 0; i < sizeof(CMD_PREFIX) - 1; i++) + seq_putc(m, ' '); + for (i = 0; i < pos; i++) + seq_putc(m, ' '); + seq_puts(m, "^\n"); +} + +static int tracing_err_log_seq_show(struct seq_file *m, void *v) +{ + struct tracing_log_err *err = v; + + if (err) { + const char *err_text = err->info.errs[err->info.type]; + u64 sec = err->info.ts; + u32 nsec; + + nsec = do_div(sec, NSEC_PER_SEC); + seq_printf(m, "[%5llu.%06u] %s%s", sec, nsec / 1000, + err->loc, err_text); + seq_printf(m, "%s", err->cmd); + tracing_err_log_show_pos(m, err->info.pos); + } + + return 0; +} + +static const struct seq_operations tracing_err_log_seq_ops = { + .start = tracing_err_log_seq_start, + .next = tracing_err_log_seq_next, + .stop = tracing_err_log_seq_stop, + .show = tracing_err_log_seq_show +}; + +static int tracing_err_log_open(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + int ret = 0; + + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; + + /* If this file was opened for write, then erase contents */ + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) + clear_tracing_err_log(tr); + + if (file->f_mode & FMODE_READ) { + ret = seq_open(file, &tracing_err_log_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = tr; + } else { + trace_array_put(tr); + } + } + return ret; +} + +static ssize_t tracing_err_log_write(struct file *file, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + return count; +} + +static int tracing_err_log_release(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + + if (file->f_mode & FMODE_READ) + seq_release(inode, file); + + return 0; +} + +static const struct file_operations tracing_err_log_fops = { + .open = tracing_err_log_open, + .write = tracing_err_log_write, + .read = seq_read, + .llseek = tracing_lseek, + .release = tracing_err_log_release, +}; + static int tracing_buffers_open(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct ftrace_buffer_info *info; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = kvzalloc(sizeof(*info), GFP_KERNEL); if (!info) { trace_array_put(tr); return -ENOMEM; @@ -6691,14 +8584,14 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) info->iter.tr = tr; info->iter.cpu_file = tracing_get_cpu(inode); info->iter.trace = tr->current_trace; - info->iter.trace_buffer = &tr->trace_buffer; + info->iter.array_buffer = &tr->array_buffer; info->spare = NULL; /* Force reading ring buffer for first read */ info->read = (unsigned int)-1; filp->private_data = info; - tr->current_trace->ref++; + tr->trace_ref++; mutex_unlock(&trace_types_lock); @@ -6724,6 +8617,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; + void *trace_data; + int page_size; ssize_t ret = 0; ssize_t size; @@ -6735,33 +8630,48 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return -EBUSY; #endif + page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); + + /* Make sure the spare matches the current sub buffer size */ + if (info->spare) { + if (page_size != info->spare_size) { + ring_buffer_free_read_page(iter->array_buffer->buffer, + info->spare_cpu, info->spare); + info->spare = NULL; + } + } + if (!info->spare) { - info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, + info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer, iter->cpu_file); if (IS_ERR(info->spare)) { ret = PTR_ERR(info->spare); info->spare = NULL; } else { info->spare_cpu = iter->cpu_file; + info->spare_size = page_size; } } if (!info->spare) return ret; /* Do we have previous read data to read? */ - if (info->read < PAGE_SIZE) + if (info->read < page_size) goto read; again: trace_access_lock(iter->cpu_file); - ret = ring_buffer_read_page(iter->trace_buffer->buffer, - &info->spare, + ret = ring_buffer_read_page(iter->array_buffer->buffer, + info->spare, count, iter->cpu_file, 0); trace_access_unlock(iter->cpu_file); if (ret < 0) { - if (trace_empty(iter)) { + if (trace_empty(iter) && !iter->closed) { + if (update_last_data_if_empty(iter->tr)) + return 0; + if ((filp->f_flags & O_NONBLOCK)) return -EAGAIN; @@ -6776,11 +8686,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, info->read = 0; read: - size = PAGE_SIZE - info->read; + size = page_size - info->read; if (size > count) size = count; - - ret = copy_to_user(ubuf, info->spare + info->read, size); + trace_data = ring_buffer_read_page_data(info->spare); + ret = copy_to_user(ubuf, trace_data + info->read, size); if (ret == size) return -EFAULT; @@ -6792,61 +8702,78 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return size; } +static int tracing_buffers_flush(struct file *file, fl_owner_t id) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + + iter->closed = true; + /* Make sure the waiters see the new wait_index */ + (void)atomic_fetch_inc_release(&iter->wait_index); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + + return 0; +} + static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); - iter->tr->current_trace->ref--; + iter->tr->trace_ref--; __trace_array_put(iter->tr); if (info->spare) - ring_buffer_free_read_page(iter->trace_buffer->buffer, + ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); - kfree(info); - - mutex_unlock(&trace_types_lock); + kvfree(info); return 0; } struct buffer_ref { - struct ring_buffer *buffer; + struct trace_buffer *buffer; void *page; int cpu; - int ref; + refcount_t refcount; }; +static void buffer_ref_release(struct buffer_ref *ref) +{ + if (!refcount_dec_and_test(&ref->refcount)) + return; + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); + kfree(ref); +} + static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); buf->private = 0; } -static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, +static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - ref->ref++; + if (refcount_read(&ref->refcount) > INT_MAX/2) + return false; + + refcount_inc(&ref->refcount); + return true; } /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { - .can_merge = 0, - .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, - .steal = generic_pipe_buf_steal, .get = buffer_pipe_buf_get, }; @@ -6859,11 +8786,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) struct buffer_ref *ref = (struct buffer_ref *)spd->partial[i].private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); spd->partial[i].private = 0; } @@ -6884,6 +8807,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; + bool woken = false; + int page_size; int entries, i; ssize_t ret = 0; @@ -6892,13 +8817,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return -EBUSY; #endif - if (*ppos & (PAGE_SIZE - 1)) + page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); + if (*ppos & (page_size - 1)) return -EINVAL; - if (len & (PAGE_SIZE - 1)) { - if (len < PAGE_SIZE) + if (len & (page_size - 1)) { + if (len < page_size) return -EINVAL; - len &= PAGE_MASK; + len &= (~(page_size - 1)); } if (splice_grow_spd(pipe, &spd)) @@ -6906,9 +8832,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, again: trace_access_lock(iter->cpu_file); - entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); - for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) { + for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) { struct page *page; int r; @@ -6918,8 +8844,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - ref->ref = 1; - ref->buffer = iter->trace_buffer->buffer; + refcount_set(&ref->refcount, 1); + ref->buffer = iter->array_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (IS_ERR(ref->page)) { ret = PTR_ERR(ref->page); @@ -6929,7 +8855,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, } ref->cpu = iter->cpu_file; - r = ring_buffer_read_page(ref->buffer, &ref->page, + r = ring_buffer_read_page(ref->buffer, ref->page, len, iter->cpu_file, 1); if (r < 0) { ring_buffer_free_read_page(ref->buffer, ref->cpu, @@ -6938,16 +8864,16 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - page = virt_to_page(ref->page); + page = virt_to_page(ring_buffer_read_page_data(ref->page)); spd.pages[i] = page; - spd.partial[i].len = PAGE_SIZE; + spd.partial[i].len = page_size; spd.partial[i].offset = 0; spd.partial[i].private = (unsigned long)ref; spd.nr_pages++; - *ppos += PAGE_SIZE; + *ppos += page_size; - entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); } trace_access_unlock(iter->cpu_file); @@ -6955,17 +8881,28 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { + if (ret) goto out; + if (woken) + goto out; + ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; - ret = wait_on_pipe(iter, iter->tr->buffer_percent); + ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; + /* No need to wait after waking up when tracing is off */ + if (!tracer_tracing_is_on(iter->tr)) + goto out; + + /* Iterate one more time to collect any new data then exit */ + woken = true; + goto again; } @@ -6976,13 +8913,135 @@ out: return ret; } +static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + int err; + + if (cmd == TRACE_MMAP_IOCTL_GET_READER) { + if (!(file->f_flags & O_NONBLOCK)) { + err = ring_buffer_wait(iter->array_buffer->buffer, + iter->cpu_file, + iter->tr->buffer_percent, + NULL, NULL); + if (err) + return err; + } + + return ring_buffer_map_get_reader(iter->array_buffer->buffer, + iter->cpu_file); + } else if (cmd) { + return -ENOTTY; + } + + /* + * An ioctl call with cmd 0 to the ring buffer file will wake up all + * waiters + */ + guard(mutex)(&trace_types_lock); + + /* Make sure the waiters see the new wait_index */ + (void)atomic_fetch_inc_release(&iter->wait_index); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + + return 0; +} + +#ifdef CONFIG_TRACER_MAX_TRACE +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 + +static void tracing_buffers_mmap_close(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + WARN_ON(ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file)); + put_snapshot_map(iter->tr); +} + +static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long addr) +{ + /* + * Trace buffer mappings require the complete buffer including + * the meta page. Partial mappings are not supported. + */ + return -EINVAL; +} + +static const struct vm_operations_struct tracing_buffers_vmops = { + .close = tracing_buffers_mmap_close, + .may_split = tracing_buffers_may_split, +}; + +static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + int ret = 0; + + /* A memmap'ed and backup buffers are not supported for user space mmap */ + if (iter->tr->flags & (TRACE_ARRAY_FL_MEMMAP | TRACE_ARRAY_FL_VMALLOC)) + return -ENODEV; + + ret = get_snapshot_map(iter->tr); + if (ret) + return ret; + + ret = ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file, vma); + if (ret) + put_snapshot_map(iter->tr); + + vma->vm_ops = &tracing_buffers_vmops; + + return ret; +} + static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, .poll = tracing_buffers_poll, .release = tracing_buffers_release, + .flush = tracing_buffers_flush, .splice_read = tracing_buffers_splice_read, - .llseek = no_llseek, + .unlocked_ioctl = tracing_buffers_ioctl, + .mmap = tracing_buffers_mmap, }; static ssize_t @@ -6991,7 +9050,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, { struct inode *inode = file_inode(filp); struct trace_array *tr = inode->i_private; - struct trace_buffer *trace_buf = &tr->trace_buffer; + struct array_buffer *trace_buf = &tr->array_buffer; int cpu = tracing_get_cpu(inode); struct trace_seq *s; unsigned long cnt; @@ -7023,7 +9082,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); - t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer, cpu)); + t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); } else { @@ -7032,7 +9091,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); trace_seq_printf(s, "now ts: %llu\n", - ring_buffer_time_stamp(trace_buf->buffer, cpu)); + ring_buffer_time_stamp(trace_buf->buffer)); } cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu); @@ -7062,14 +9121,30 @@ static ssize_t tracing_read_dyn_info(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - unsigned long *p = filp->private_data; - char buf[64]; /* Not too big for a shallow stack */ + ssize_t ret; + char *buf; int r; - r = scnprintf(buf, 63, "%ld", *p); - buf[r++] = '\n'; + /* 512 should be plenty to hold the amount needed */ +#define DYN_INFO_BUF_SIZE 512 - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + buf = kmalloc(DYN_INFO_BUF_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + r = scnprintf(buf, DYN_INFO_BUF_SIZE, + "%ld pages:%ld groups: %ld\n" + "ftrace boot update time = %llu (ns)\n" + "ftrace module total update time = %llu (ns)\n", + ftrace_update_tot_cnt, + ftrace_number_of_pages, + ftrace_number_of_groups, + ftrace_update_time, + ftrace_total_mod_time); + + ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + kfree(buf); + return ret; } static const struct file_operations tracing_dyn_info_fops = { @@ -7194,8 +9269,13 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; - if (glob[0] == '!') - return unregister_ftrace_function_probe_func(glob+1, tr, 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; @@ -7214,13 +9294,14 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, return ret; out_reg: - ret = tracing_alloc_snapshot_instance(tr); + ret = tracing_arm_snapshot(tr); if (ret < 0) - goto out; + return ret; ret = register_ftrace_function_probe(glob, tr, ops, count); + if (ret < 0) + tracing_disarm_snapshot(tr); - out: return ret < 0 ? ret : 0; } @@ -7239,13 +9320,13 @@ static inline __init int register_snapshot_cmd(void) { return 0; } static struct dentry *tracing_get_dentry(struct trace_array *tr) { - if (WARN_ON(!tr->dir)) - return ERR_PTR(-ENODEV); - /* Top directory uses NULL as the parent */ if (tr->flags & TRACE_ARRAY_FL_GLOBAL) return NULL; + if (WARN_ON(!tr->dir)) + return ERR_PTR(-ENODEV); + /* All sub buffers have a descriptor */ return tr->dir; } @@ -7263,7 +9344,7 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) tr->percpu_dir = tracefs_create_dir("per_cpu", d_tracer); - WARN_ONCE(!tr->percpu_dir, + MEM_FAIL(!tr->percpu_dir, "Could not create tracefs directory 'per_cpu/%d'\n", cpu); return tr->percpu_dir; @@ -7298,28 +9379,33 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu) } /* per cpu trace_pipe */ - trace_create_cpu_file("trace_pipe", 0444, d_cpu, + trace_create_cpu_file("trace_pipe", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_pipe_fops); /* per cpu trace */ - trace_create_cpu_file("trace", 0644, d_cpu, + trace_create_cpu_file("trace", TRACE_MODE_WRITE, d_cpu, tr, cpu, &tracing_fops); - trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu, + trace_create_cpu_file("trace_pipe_raw", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_buffers_fops); - trace_create_cpu_file("stats", 0444, d_cpu, + trace_create_cpu_file("stats", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_stats_fops); - trace_create_cpu_file("buffer_size_kb", 0444, d_cpu, + trace_create_cpu_file("buffer_size_kb", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_entries_fops); + if (tr->range_addr_start) + trace_create_cpu_file("buffer_meta", TRACE_MODE_READ, d_cpu, + tr, cpu, &tracing_buffer_meta_fops); #ifdef CONFIG_TRACER_SNAPSHOT - trace_create_cpu_file("snapshot", 0644, d_cpu, - tr, cpu, &snapshot_fops); + if (!tr->range_addr_start) { + trace_create_cpu_file("snapshot", TRACE_MODE_WRITE, d_cpu, + tr, cpu, &snapshot_fops); - trace_create_cpu_file("snapshot_raw", 0444, d_cpu, - tr, cpu, &snapshot_raw_fops); + trace_create_cpu_file("snapshot_raw", TRACE_MODE_READ, d_cpu, + tr, cpu, &snapshot_raw_fops); + } #endif } @@ -7359,10 +9445,9 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, return -EINVAL; if (!!(topt->flags->val & topt->opt->bit) != val) { - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); ret = __set_tracer_option(topt->tr, topt->flags, topt->opt, !val); - mutex_unlock(&trace_types_lock); if (ret) return ret; } @@ -7372,12 +9457,33 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } +static int tracing_open_options(struct inode *inode, struct file *filp) +{ + struct trace_option_dentry *topt = inode->i_private; + int ret; + + ret = tracing_check_open_get_tr(topt->tr); + if (ret) + return ret; + + filp->private_data = inode->i_private; + return 0; +} + +static int tracing_release_options(struct inode *inode, struct file *file) +{ + struct trace_option_dentry *topt = file->private_data; + + trace_array_put(topt->tr); + return 0; +} static const struct file_operations trace_options_fops = { - .open = tracing_open_generic, + .open = tracing_open_options, .read = trace_options_read, .write = trace_options_write, .llseek = generic_file_llseek, + .release = tracing_release_options, }; /* @@ -7424,7 +9530,7 @@ trace_options_core_read(struct file *filp, char __user *ubuf, size_t cnt, get_tr_index(tr_index, &tr, &index); - if (tr->trace_flags & (1 << index)) + if (tr->trace_flags & (1ULL << index)) buf = "1\n"; else buf = "0\n"; @@ -7451,9 +9557,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); - ret = set_tracer_flag(tr, 1 << index, val); + ret = set_tracer_flag(tr, 1ULL << index, val); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); if (ret < 0) return ret; @@ -7522,41 +9630,21 @@ create_trace_option_file(struct trace_array *tr, topt->opt = opt; topt->tr = tr; - topt->entry = trace_create_file(opt->name, 0644, t_options, topt, - &trace_options_fops); - + topt->entry = trace_create_file(opt->name, TRACE_MODE_WRITE, + t_options, topt, &trace_options_fops); } -static void -create_trace_option_files(struct trace_array *tr, struct tracer *tracer) +static int +create_trace_option_files(struct trace_array *tr, struct tracer *tracer, + struct tracer_flags *flags) { struct trace_option_dentry *topts; struct trace_options *tr_topts; - struct tracer_flags *flags; struct tracer_opt *opts; int cnt; - int i; - - if (!tracer) - return; - - flags = tracer->flags; if (!flags || !flags->opts) - return; - - /* - * If this is an instance, only create flags for tracers - * the instance may have. - */ - if (!trace_ok_for_array(tracer, tr)) - return; - - for (i = 0; i < tr->nr_topts; i++) { - /* Make sure there's no duplicate flags. */ - if (WARN_ON_ONCE(tr->topts[i].tracer->flags == tracer->flags)) - return; - } + return 0; opts = flags->opts; @@ -7565,13 +9653,13 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer) topts = kcalloc(cnt + 1, sizeof(*topts), GFP_KERNEL); if (!topts) - return; + return 0; tr_topts = krealloc(tr->topts, sizeof(*tr->topts) * (tr->nr_topts + 1), GFP_KERNEL); if (!tr_topts) { kfree(topts); - return; + return -ENOMEM; } tr->topts = tr_topts; @@ -7582,10 +9670,101 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer) for (cnt = 0; opts[cnt].name; cnt++) { create_trace_option_file(tr, &topts[cnt], flags, &opts[cnt]); - WARN_ONCE(topts[cnt].entry == NULL, + MEM_FAIL(topts[cnt].entry == NULL, "Failed to create trace option: %s", opts[cnt].name); } + return 0; +} + +static int get_global_flags_val(struct tracer *tracer) +{ + struct tracers *t; + + list_for_each_entry(t, &global_trace.tracers, list) { + if (t->tracer != tracer) + continue; + if (!t->flags) + return -1; + return t->flags->val; + } + return -1; +} + +static int add_tracer_options(struct trace_array *tr, struct tracers *t) +{ + struct tracer *tracer = t->tracer; + struct tracer_flags *flags = t->flags ?: tracer->flags; + + if (!flags) + return 0; + + /* Only add tracer options after update_tracer_options finish */ + if (!tracer_options_updated) + return 0; + + return create_trace_option_files(tr, tracer, flags); +} + +static int add_tracer(struct trace_array *tr, struct tracer *tracer) +{ + struct tracer_flags *flags; + struct tracers *t; + int ret; + + /* Only enable if the directory has been created already. */ + if (!tr->dir && !(tr->flags & TRACE_ARRAY_FL_GLOBAL)) + return 0; + + /* + * If this is an instance, only create flags for tracers + * the instance may have. + */ + if (!trace_ok_for_array(tracer, tr)) + return 0; + + t = kmalloc(sizeof(*t), GFP_KERNEL); + if (!t) + return -ENOMEM; + + t->tracer = tracer; + t->flags = NULL; + list_add(&t->list, &tr->tracers); + + flags = tracer->flags; + if (!flags) { + if (!tracer->default_flags) + return 0; + + /* + * If the tracer defines default flags, it means the flags are + * per trace instance. + */ + flags = kmalloc(sizeof(*flags), GFP_KERNEL); + if (!flags) + return -ENOMEM; + + *flags = *tracer->default_flags; + flags->trace = tracer; + + t->flags = flags; + + /* If this is an instance, inherit the global_trace flags */ + if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL)) { + int val = get_global_flags_val(tracer); + if (!WARN_ON_ONCE(val < 0)) + flags->val = val; + } + } + + ret = add_tracer_options(tr, t); + if (ret < 0) { + list_del(&t->list); + kfree(t->flags); + kfree(t); + } + + return ret; } static struct dentry * @@ -7598,7 +9777,7 @@ create_trace_option_core_file(struct trace_array *tr, if (!t_options) return NULL; - return trace_create_file(option, 0644, t_options, + return trace_create_file(option, TRACE_MODE_WRITE, t_options, (void *)&tr->trace_flags_index[index], &trace_options_core_fops); } @@ -7615,8 +9794,9 @@ static void create_trace_options_dir(struct trace_array *tr) for (i = 0; trace_options[i]; i++) { if (top_level || - !((1 << i) & TOP_LEVEL_TRACE_FLAGS)) + !((1ULL << i) & TOP_LEVEL_TRACE_FLAGS)) { create_trace_option_core_file(tr, trace_options[i], i); + } } } @@ -7639,7 +9819,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; unsigned long val; int ret; @@ -7648,7 +9828,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf, return ret; if (buffer) { - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (!!val == tracer_tracing_is_on(tr)) { val = 0; /* do nothing */ } else if (val) { @@ -7659,8 +9839,9 @@ rb_simple_write(struct file *filp, const char __user *ubuf, tracer_tracing_off(tr); if (tr->current_trace->stop) tr->current_trace->stop(tr); + /* Wake up any waiters */ + ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS); } - mutex_unlock(&trace_types_lock); } (*ppos)++; @@ -7705,9 +9886,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf, if (val > 100) return -EINVAL; - if (!val) - val = 1; - tr->buffer_percent = val; (*ppos)++; @@ -7723,21 +9901,244 @@ static const struct file_operations buffer_percent_fops = { .llseek = default_llseek, }; -struct dentry *trace_instance_dir; +static ssize_t +buffer_subbuf_size_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + size_t size; + char buf[64]; + int order; + int r; + + order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + size = (PAGE_SIZE << order) / 1024; + + r = sprintf(buf, "%zd\n", size); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + unsigned long val; + int old_order; + int order; + int pages; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + val *= 1024; /* value passed in is in KB */ + + pages = DIV_ROUND_UP(val, PAGE_SIZE); + order = fls(pages - 1); + + /* limit between 1 and 128 system pages */ + if (order < 0 || order > 7) + return -EINVAL; + + /* Do not allow tracing while changing the order of the ring buffer */ + tracing_stop_tr(tr); + + old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + if (old_order == order) + goto out; + + ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, order); + if (ret) + goto out; + +#ifdef CONFIG_TRACER_MAX_TRACE + + if (!tr->allocated_snapshot) + goto out_max; + + ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); + if (ret) { + /* Put back the old order */ + cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order); + if (WARN_ON_ONCE(cnt)) { + /* + * AARGH! We are left with different orders! + * The max buffer is our "snapshot" buffer. + * When a tracer needs a snapshot (one of the + * latency tracers), it swaps the max buffer + * with the saved snap shot. We succeeded to + * update the order of the main buffer, but failed to + * update the order of the max buffer. But when we tried + * to reset the main buffer to the original size, we + * failed there too. This is very unlikely to + * happen, but if it does, warn and kill all + * tracing. + */ + tracing_disabled = 1; + } + goto out; + } + out_max: +#endif + (*ppos)++; + out: + if (ret) + cnt = ret; + tracing_start_tr(tr); + return cnt; +} + +static const struct file_operations buffer_subbuf_size_fops = { + .open = tracing_open_generic_tr, + .read = buffer_subbuf_size_read, + .write = buffer_subbuf_size_write, + .release = tracing_release_generic_tr, + .llseek = default_llseek, +}; + +static struct dentry *trace_instance_dir; static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer); +#ifdef CONFIG_MODULES +static int make_mod_delta(struct module *mod, void *data) +{ + struct trace_module_delta *module_delta; + struct trace_scratch *tscratch; + struct trace_mod_entry *entry; + struct trace_array *tr = data; + int i; + + tscratch = tr->scratch; + module_delta = READ_ONCE(tr->module_delta); + for (i = 0; i < tscratch->nr_entries; i++) { + entry = &tscratch->entries[i]; + if (strcmp(mod->name, entry->mod_name)) + continue; + if (mod->state == MODULE_STATE_GOING) + module_delta->delta[i] = 0; + else + module_delta->delta[i] = (unsigned long)mod->mem[MOD_TEXT].base + - entry->mod_addr; + break; + } + return 0; +} +#else +static int make_mod_delta(struct module *mod, void *data) +{ + return 0; +} +#endif + +static int mod_addr_comp(const void *a, const void *b, const void *data) +{ + const struct trace_mod_entry *e1 = a; + const struct trace_mod_entry *e2 = b; + + return e1->mod_addr > e2->mod_addr ? 1 : -1; +} + +static void setup_trace_scratch(struct trace_array *tr, + struct trace_scratch *tscratch, unsigned int size) +{ + struct trace_module_delta *module_delta; + struct trace_mod_entry *entry; + int i, nr_entries; + + if (!tscratch) + return; + + tr->scratch = tscratch; + tr->scratch_size = size; + + if (tscratch->text_addr) + tr->text_delta = (unsigned long)_text - tscratch->text_addr; + + if (struct_size(tscratch, entries, tscratch->nr_entries) > size) + goto reset; + + /* Check if each module name is a valid string */ + for (i = 0; i < tscratch->nr_entries; i++) { + int n; + + entry = &tscratch->entries[i]; + + for (n = 0; n < MODULE_NAME_LEN; n++) { + if (entry->mod_name[n] == '\0') + break; + if (!isprint(entry->mod_name[n])) + goto reset; + } + if (n == MODULE_NAME_LEN) + goto reset; + } + + /* Sort the entries so that we can find appropriate module from address. */ + nr_entries = tscratch->nr_entries; + sort_r(tscratch->entries, nr_entries, sizeof(struct trace_mod_entry), + mod_addr_comp, NULL, NULL); + + if (IS_ENABLED(CONFIG_MODULES)) { + module_delta = kzalloc(struct_size(module_delta, delta, nr_entries), GFP_KERNEL); + if (!module_delta) { + pr_info("module_delta allocation failed. Not able to decode module address."); + goto reset; + } + init_rcu_head(&module_delta->rcu); + } else + module_delta = NULL; + WRITE_ONCE(tr->module_delta, module_delta); + + /* Scan modules to make text delta for modules. */ + module_for_each_mod(make_mod_delta, tr); + + /* Set trace_clock as the same of the previous boot. */ + if (tscratch->clock_id != tr->clock_id) { + if (tscratch->clock_id >= ARRAY_SIZE(trace_clocks) || + tracing_set_clock(tr, trace_clocks[tscratch->clock_id].name) < 0) { + pr_info("the previous trace_clock info is not valid."); + goto reset; + } + } + return; + reset: + /* Invalid trace modules */ + memset(tscratch, 0, size); +} + static int -allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size) +allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size) { enum ring_buffer_flags rb_flags; + struct trace_scratch *tscratch; + unsigned int scratch_size = 0; - rb_flags = tr->trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; + rb_flags = tr->trace_flags & TRACE_ITER(OVERWRITE) ? RB_FL_OVERWRITE : 0; buf->tr = tr; - buf->buffer = ring_buffer_alloc(size, rb_flags); + if (tr->range_addr_start && tr->range_addr_size) { + /* Add scratch buffer to handle 128 modules */ + buf->buffer = ring_buffer_alloc_range(size, rb_flags, 0, + tr->range_addr_start, + tr->range_addr_size, + struct_size(tscratch, entries, 128)); + + tscratch = ring_buffer_meta_scratch(buf->buffer, &scratch_size); + setup_trace_scratch(tr, tscratch, scratch_size); + + /* + * This is basically the same as a mapped buffer, + * with the same restrictions. + */ + tr->mapped++; + } else { + buf->buffer = ring_buffer_alloc(size, rb_flags); + } if (!buf->buffer) return -ENOMEM; @@ -7749,49 +10150,47 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size } /* Allocate the first page for all buffers */ - set_buffer_entries(&tr->trace_buffer, - ring_buffer_size(tr->trace_buffer.buffer, 0)); + set_buffer_entries(&tr->array_buffer, + ring_buffer_size(tr->array_buffer.buffer, 0)); return 0; } +static void free_trace_buffer(struct array_buffer *buf) +{ + if (buf->buffer) { + ring_buffer_free(buf->buffer); + buf->buffer = NULL; + free_percpu(buf->data); + buf->data = NULL; + } +} + static int allocate_trace_buffers(struct trace_array *tr, int size) { int ret; - ret = allocate_trace_buffer(tr, &tr->trace_buffer, size); + ret = allocate_trace_buffer(tr, &tr->array_buffer, size); if (ret) return ret; #ifdef CONFIG_TRACER_MAX_TRACE + /* Fix mapped buffer trace arrays do not have snapshot buffers */ + if (tr->range_addr_start) + return 0; + ret = allocate_trace_buffer(tr, &tr->max_buffer, allocate_snapshot ? size : 1); - if (WARN_ON(ret)) { - ring_buffer_free(tr->trace_buffer.buffer); - tr->trace_buffer.buffer = NULL; - free_percpu(tr->trace_buffer.data); - tr->trace_buffer.data = NULL; + if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) { + free_trace_buffer(&tr->array_buffer); return -ENOMEM; } tr->allocated_snapshot = allocate_snapshot; - /* - * Only the top level trace array gets its snapshot allocated - * from the kernel command line. - */ allocate_snapshot = false; #endif - return 0; -} -static void free_trace_buffer(struct trace_buffer *buf) -{ - if (buf->buffer) { - ring_buffer_free(buf->buffer); - buf->buffer = NULL; - free_percpu(buf->data); - buf->data = NULL; - } + return 0; } static void free_trace_buffers(struct trace_array *tr) @@ -7799,7 +10198,8 @@ static void free_trace_buffers(struct trace_array *tr) if (!tr) return; - free_trace_buffer(&tr->trace_buffer); + free_trace_buffer(&tr->array_buffer); + kfree(tr->module_delta); #ifdef CONFIG_TRACER_MAX_TRACE free_trace_buffer(&tr->max_buffer); @@ -7815,39 +10215,104 @@ static void init_trace_flags_index(struct trace_array *tr) tr->trace_flags_index[i] = i; } -static void __update_tracer_options(struct trace_array *tr) +static int __update_tracer(struct trace_array *tr) { struct tracer *t; + int ret = 0; + + for (t = trace_types; t && !ret; t = t->next) + ret = add_tracer(tr, t); - for (t = trace_types; t; t = t->next) - add_tracer_options(tr, t); + return ret; } -static void update_tracer_options(struct trace_array *tr) +static __init int __update_tracer_options(struct trace_array *tr) { - mutex_lock(&trace_types_lock); - __update_tracer_options(tr); - mutex_unlock(&trace_types_lock); + struct tracers *t; + int ret = 0; + + list_for_each_entry(t, &tr->tracers, list) { + ret = add_tracer_options(tr, t); + if (ret < 0) + break; + } + + return ret; } -static int instance_mkdir(const char *name) +static __init void update_tracer_options(void) { struct trace_array *tr; - int ret; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); + tracer_options_updated = true; + list_for_each_entry(tr, &ftrace_trace_arrays, list) + __update_tracer_options(tr); +} + +/* Must have trace_types_lock held */ +struct trace_array *trace_array_find(const char *instance) +{ + struct trace_array *tr, *found = NULL; - ret = -EEXIST; list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (tr->name && strcmp(tr->name, name) == 0) - goto out_unlock; + if (tr->name && strcmp(tr->name, instance) == 0) { + found = tr; + break; + } + } + + return found; +} + +struct trace_array *trace_array_find_get(const char *instance) +{ + struct trace_array *tr; + + guard(mutex)(&trace_types_lock); + tr = trace_array_find(instance); + if (tr) + tr->ref++; + + return tr; +} + +static int trace_array_create_dir(struct trace_array *tr) +{ + int ret; + + tr->dir = tracefs_create_dir(tr->name, trace_instance_dir); + if (!tr->dir) + return -EINVAL; + + ret = event_trace_add_tracer(tr->dir, tr); + if (ret) { + tracefs_remove(tr->dir); + return ret; } + init_tracer_tracefs(tr, tr->dir); + ret = __update_tracer(tr); + if (ret) { + event_trace_del_tracer(tr); + tracefs_remove(tr->dir); + return ret; + } + return 0; +} + +static struct trace_array * +trace_array_create_systems(const char *name, const char *systems, + unsigned long range_addr_start, + unsigned long range_addr_size) +{ + struct trace_array *tr; + int ret; + ret = -ENOMEM; tr = kzalloc(sizeof(*tr), GFP_KERNEL); if (!tr) - goto out_unlock; + return ERR_PTR(ret); tr->name = kstrdup(name, GFP_KERNEL); if (!tr->name) @@ -7856,155 +10321,318 @@ static int instance_mkdir(const char *name) if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL)) goto out_free_tr; + if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) + goto out_free_tr; + + if (systems) { + tr->system_names = kstrdup_const(systems, GFP_KERNEL); + if (!tr->system_names) + goto out_free_tr; + } + + /* Only for boot up memory mapped ring buffers */ + tr->range_addr_start = range_addr_start; + tr->range_addr_size = range_addr_size; + tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; cpumask_copy(tr->tracing_cpumask, cpu_all_mask); raw_spin_lock_init(&tr->start_lock); - tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + tr->syscall_buf_sz = global_trace.syscall_buf_sz; + tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; +#ifdef CONFIG_TRACER_MAX_TRACE + spin_lock_init(&tr->snapshot_trigger_lock); +#endif tr->current_trace = &nop_trace; + tr->current_trace_flags = nop_trace.flags; INIT_LIST_HEAD(&tr->systems); INIT_LIST_HEAD(&tr->events); INIT_LIST_HEAD(&tr->hist_vars); + INIT_LIST_HEAD(&tr->err_log); + INIT_LIST_HEAD(&tr->tracers); + INIT_LIST_HEAD(&tr->marker_list); + +#ifdef CONFIG_MODULES + INIT_LIST_HEAD(&tr->mod_events); +#endif if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; - tr->dir = tracefs_create_dir(name, trace_instance_dir); - if (!tr->dir) - goto out_free_tr; + /* The ring buffer is defaultly expanded */ + trace_set_ring_buffer_expanded(tr); - ret = event_trace_add_tracer(tr->dir, tr); - if (ret) { - tracefs_remove_recursive(tr->dir); + if (ftrace_allocate_ftrace_ops(tr) < 0) goto out_free_tr; - } ftrace_init_trace_array(tr); - init_tracer_tracefs(tr, tr->dir); init_trace_flags_index(tr); - __update_tracer_options(tr); + + if (trace_instance_dir) { + ret = trace_array_create_dir(tr); + if (ret) + goto out_free_tr; + } else + __trace_early_add_events(tr); list_add(&tr->list, &ftrace_trace_arrays); - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); + tr->ref++; - return 0; + return tr; out_free_tr: + ftrace_free_ftrace_ops(tr); free_trace_buffers(tr); + free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); + kfree_const(tr->system_names); + kfree(tr->range_name); kfree(tr->name); kfree(tr); - out_unlock: - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); + return ERR_PTR(ret); +} + +static struct trace_array *trace_array_create(const char *name) +{ + return trace_array_create_systems(name, NULL, 0, 0); +} + +static int instance_mkdir(const char *name) +{ + struct trace_array *tr; + int ret; + + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); + + ret = -EEXIST; + if (trace_array_find(name)) + return -EEXIST; + + tr = trace_array_create(name); + + ret = PTR_ERR_OR_ZERO(tr); return ret; +} + +#ifdef CONFIG_MMU +static u64 map_pages(unsigned long start, unsigned long size) +{ + unsigned long vmap_start, vmap_end; + struct vm_struct *area; + int ret; + + area = get_vm_area(size, VM_IOREMAP); + if (!area) + return 0; + vmap_start = (unsigned long) area->addr; + vmap_end = vmap_start + size; + + ret = vmap_page_range(vmap_start, vmap_end, + start, pgprot_nx(PAGE_KERNEL)); + if (ret < 0) { + free_vm_area(area); + return 0; + } + + return (u64)vmap_start; } +#else +static inline u64 map_pages(unsigned long start, unsigned long size) +{ + return 0; +} +#endif -static int instance_rmdir(const char *name) +/** + * trace_array_get_by_name - Create/Lookup a trace array, given its name. + * @name: The name of the trace array to be looked up/created. + * @systems: A list of systems to create event directories for (NULL for all) + * + * Returns pointer to trace array with given name. + * NULL, if it cannot be created. + * + * NOTE: This function increments the reference counter associated with the + * trace array returned. This makes sure it cannot be freed while in use. + * Use trace_array_put() once the trace array is no longer needed. + * If the trace_array is to be freed, trace_array_destroy() needs to + * be called after the trace_array_put(), or simply let user space delete + * it from the tracefs instances directory. But until the + * trace_array_put() is called, user space can not delete it. + * + */ +struct trace_array *trace_array_get_by_name(const char *name, const char *systems) { struct trace_array *tr; - int found = 0; - int ret; - int i; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); - ret = -ENODEV; list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr->name && strcmp(tr->name, name) == 0) { - found = 1; - break; + tr->ref++; + return tr; } } - if (!found) - goto out_unlock; - ret = -EBUSY; - if (tr->ref || (tr->current_trace && tr->current_trace->ref)) - goto out_unlock; + tr = trace_array_create_systems(name, systems, 0, 0); + + if (IS_ERR(tr)) + tr = NULL; + else + tr->ref++; + + return tr; +} +EXPORT_SYMBOL_GPL(trace_array_get_by_name); + +static int __remove_instance(struct trace_array *tr) +{ + int i; + + /* Reference counter for a newly created trace array = 1. */ + if (tr->ref > 1 || (tr->current_trace && tr->trace_ref)) + return -EBUSY; list_del(&tr->list); /* Disable all the flags that were enabled coming in */ for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) { if ((1 << i) & ZEROED_TRACE_FLAGS) - set_tracer_flag(tr, 1 << i, 0); + set_tracer_flag(tr, 1ULL << i, 0); } + if (printk_trace == tr) + update_printk_trace(&global_trace); + + if (update_marker_trace(tr, 0)) + synchronize_rcu(); + tracing_set_nop(tr); clear_ftrace_function_probes(tr); event_trace_del_tracer(tr); ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); - tracefs_remove_recursive(tr->dir); + tracefs_remove(tr->dir); + free_percpu(tr->last_func_repeats); free_trace_buffers(tr); + clear_tracing_err_log(tr); + free_tracers(tr); + + if (tr->range_name) { + reserve_mem_release_by_name(tr->range_name); + kfree(tr->range_name); + } + if (tr->flags & TRACE_ARRAY_FL_VMALLOC) + vfree((void *)tr->range_addr_start); for (i = 0; i < tr->nr_topts; i++) { kfree(tr->topts[i].topts); } kfree(tr->topts); + free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); + kfree_const(tr->system_names); kfree(tr->name); kfree(tr); - ret = 0; + return 0; +} - out_unlock: - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); +int trace_array_destroy(struct trace_array *this_tr) +{ + struct trace_array *tr; - return ret; + if (!this_tr) + return -EINVAL; + + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); + + + /* Making sure trace array exists before destroying it. */ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr == this_tr) + return __remove_instance(tr); + } + + return -ENODEV; +} +EXPORT_SYMBOL_GPL(trace_array_destroy); + +static int instance_rmdir(const char *name) +{ + struct trace_array *tr; + + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); + + tr = trace_array_find(name); + if (!tr) + return -ENODEV; + + return __remove_instance(tr); } static __init void create_trace_instances(struct dentry *d_tracer) { + struct trace_array *tr; + trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer, instance_mkdir, instance_rmdir); - if (WARN_ON(!trace_instance_dir)) + if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n")) return; + + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (!tr->name) + continue; + if (MEM_FAIL(trace_array_create_dir(tr) < 0, + "Failed to create instance directory\n")) + return; + } } static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) { - struct trace_event_file *file; int cpu; - trace_create_file("available_tracers", 0444, d_tracer, + trace_create_file("available_tracers", TRACE_MODE_READ, d_tracer, tr, &show_traces_fops); - trace_create_file("current_tracer", 0644, d_tracer, + trace_create_file("current_tracer", TRACE_MODE_WRITE, d_tracer, tr, &set_tracer_fops); - trace_create_file("tracing_cpumask", 0644, d_tracer, + trace_create_file("tracing_cpumask", TRACE_MODE_WRITE, d_tracer, tr, &tracing_cpumask_fops); - trace_create_file("trace_options", 0644, d_tracer, + trace_create_file("trace_options", TRACE_MODE_WRITE, d_tracer, tr, &tracing_iter_fops); - trace_create_file("trace", 0644, d_tracer, + trace_create_file("trace", TRACE_MODE_WRITE, d_tracer, tr, &tracing_fops); - trace_create_file("trace_pipe", 0444, d_tracer, + trace_create_file("trace_pipe", TRACE_MODE_READ, d_tracer, tr, &tracing_pipe_fops); - trace_create_file("buffer_size_kb", 0644, d_tracer, + trace_create_file("buffer_size_kb", TRACE_MODE_WRITE, d_tracer, tr, &tracing_entries_fops); - trace_create_file("buffer_total_size_kb", 0444, d_tracer, + trace_create_file("buffer_total_size_kb", TRACE_MODE_READ, d_tracer, tr, &tracing_total_entries_fops); trace_create_file("free_buffer", 0200, d_tracer, @@ -8013,43 +10641,52 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("trace_marker", 0220, d_tracer, tr, &tracing_mark_fops); - file = __find_event_file(tr, "ftrace", "print"); - if (file && file->dir) - trace_create_file("trigger", 0644, file->dir, file, - &event_trigger_fops); - tr->trace_marker_file = file; + tr->trace_marker_file = __find_event_file(tr, "ftrace", "print"); trace_create_file("trace_marker_raw", 0220, d_tracer, tr, &tracing_mark_raw_fops); - trace_create_file("trace_clock", 0644, d_tracer, tr, + trace_create_file("trace_clock", TRACE_MODE_WRITE, d_tracer, tr, &trace_clock_fops); - trace_create_file("tracing_on", 0644, d_tracer, + trace_create_file("tracing_on", TRACE_MODE_WRITE, d_tracer, tr, &rb_simple_fops); - trace_create_file("timestamp_mode", 0444, d_tracer, tr, + trace_create_file("timestamp_mode", TRACE_MODE_READ, d_tracer, tr, &trace_time_stamp_mode_fops); tr->buffer_percent = 50; - trace_create_file("buffer_percent", 0444, d_tracer, + trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer, tr, &buffer_percent_fops); + trace_create_file("buffer_subbuf_size_kb", TRACE_MODE_WRITE, d_tracer, + tr, &buffer_subbuf_size_fops); + + trace_create_file("syscall_user_buf_size", TRACE_MODE_WRITE, d_tracer, + tr, &tracing_syscall_buf_fops); + create_trace_options_dir(tr); -#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) - trace_create_file("tracing_max_latency", 0644, d_tracer, - &tr->max_latency, &tracing_max_lat_fops); +#ifdef CONFIG_TRACER_MAX_TRACE + trace_create_maxlat_file(tr, d_tracer); #endif if (ftrace_create_function_files(tr, d_tracer)) - WARN(1, "Could not allocate function filter files"); + MEM_FAIL(1, "Could not allocate function filter files"); + if (tr->range_addr_start) { + trace_create_file("last_boot_info", TRACE_MODE_READ, d_tracer, + tr, &last_boot_fops); #ifdef CONFIG_TRACER_SNAPSHOT - trace_create_file("snapshot", 0644, d_tracer, - tr, &snapshot_fops); + } else { + trace_create_file("snapshot", TRACE_MODE_WRITE, d_tracer, + tr, &snapshot_fops); #endif + } + + trace_create_file("error_log", TRACE_MODE_WRITE, d_tracer, + tr, &tracing_err_log_fops); for_each_tracing_cpu(cpu) tracing_init_tracefs_percpu(tr, cpu); @@ -8057,10 +10694,13 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) ftrace_init_tracefs(tr, d_tracer); } +#ifdef CONFIG_TRACEFS_AUTOMOUNT_DEPRECATED static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore) { struct vfsmount *mnt; struct file_system_type *type; + struct fs_context *fc; + int ret; /* * To maintain backward compatibility for tools that mount @@ -8070,14 +10710,24 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore) type = get_fs_type("tracefs"); if (!type) return NULL; - mnt = vfs_submount(mntpt, type, "tracefs", NULL); + + fc = fs_context_for_submount(type, mntpt); put_filesystem(type); - if (IS_ERR(mnt)) - return NULL; - mntget(mnt); + if (IS_ERR(fc)) + return ERR_CAST(fc); + + pr_warn("NOTICE: Automounting of tracing to debugfs is deprecated and will be removed in 2030\n"); + + ret = vfs_parse_fs_string(fc, "source", "tracefs"); + if (!ret) + mnt = fc_mount(fc); + else + mnt = ERR_PTR(ret); + put_fs_context(fc); return mnt; } +#endif /** * tracing_init_dentry - initialize top level trace array @@ -8086,52 +10736,101 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore) * directory. It is called via fs_initcall() by any of the boot up code * and expects to return the dentry of the top level tracing directory. */ -struct dentry *tracing_init_dentry(void) +int tracing_init_dentry(void) { struct trace_array *tr = &global_trace; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Tracing disabled due to lockdown\n"); + return -EPERM; + } + /* The top level trace array uses NULL as parent */ if (tr->dir) - return NULL; + return 0; - if (WARN_ON(!tracefs_initialized()) || - (IS_ENABLED(CONFIG_DEBUG_FS) && - WARN_ON(!debugfs_initialized()))) - return ERR_PTR(-ENODEV); + if (WARN_ON(!tracefs_initialized())) + return -ENODEV; +#ifdef CONFIG_TRACEFS_AUTOMOUNT_DEPRECATED /* * As there may still be users that expect the tracing * files to exist in debugfs/tracing, we must automount * the tracefs file system there, so older tools still - * work with the newer kerenl. + * work with the newer kernel. */ tr->dir = debugfs_create_automount("tracing", NULL, trace_automount, NULL); - if (!tr->dir) { - pr_warn_once("Could not create debugfs directory 'tracing'\n"); - return ERR_PTR(-ENOMEM); - } +#endif - return NULL; + return 0; } extern struct trace_eval_map *__start_ftrace_eval_maps[]; extern struct trace_eval_map *__stop_ftrace_eval_maps[]; -static void __init trace_eval_init(void) +static struct workqueue_struct *eval_map_wq __initdata; +static struct work_struct eval_map_work __initdata; +static struct work_struct tracerfs_init_work __initdata; + +static void __init eval_map_work_func(struct work_struct *work) { int len; len = __stop_ftrace_eval_maps - __start_ftrace_eval_maps; - trace_insert_eval_map(NULL, __start_ftrace_eval_maps, len); + trace_event_update_with_eval_map(NULL, __start_ftrace_eval_maps, len); +} + +static int __init trace_eval_init(void) +{ + INIT_WORK(&eval_map_work, eval_map_work_func); + + eval_map_wq = alloc_workqueue("eval_map_wq", WQ_UNBOUND, 0); + if (!eval_map_wq) { + pr_err("Unable to allocate eval_map_wq\n"); + /* Do work here */ + eval_map_work_func(&eval_map_work); + return -ENOMEM; + } + + queue_work(eval_map_wq, &eval_map_work); + return 0; } +subsys_initcall(trace_eval_init); + +static int __init trace_eval_sync(void) +{ + /* Make sure the eval map updates are finished */ + if (eval_map_wq) + destroy_workqueue(eval_map_wq); + return 0; +} + +late_initcall_sync(trace_eval_sync); + + #ifdef CONFIG_MODULES -static void trace_module_add_evals(struct module *mod) + +bool module_exists(const char *module) { - if (!mod->num_trace_evals) - return; + /* All modules have the symbol __this_module */ + static const char this_mod[] = "__this_module"; + char modname[MODULE_NAME_LEN + sizeof(this_mod) + 2]; + unsigned long val; + int n; + + n = snprintf(modname, sizeof(modname), "%s:%s", module, this_mod); + + if (n > sizeof(modname) - 1) + return false; + val = module_kallsyms_lookup_name(modname); + return val != 0; +} + +static void trace_module_add_evals(struct module *mod) +{ /* * Modules with bad taint do not have events created, do * not bother with enums either. @@ -8139,7 +10838,8 @@ static void trace_module_add_evals(struct module *mod) if (trace_module_has_bad_taint(mod)) return; - trace_insert_eval_map(mod, mod->trace_evals, mod->num_trace_evals); + /* Even if no trace_evals, this need to sanitize field types. */ + trace_event_update_with_eval_map(mod, mod->trace_evals, mod->num_trace_evals); } #ifdef CONFIG_TRACE_EVAL_MAP_FILE @@ -8151,7 +10851,7 @@ static void trace_module_remove_evals(struct module *mod) if (!mod->num_trace_evals) return; - mutex_lock(&trace_eval_mutex); + guard(mutex)(&trace_eval_mutex); map = trace_eval_maps; @@ -8163,17 +10863,33 @@ static void trace_module_remove_evals(struct module *mod) map = map->tail.next; } if (!map) - goto out; + return; *last = trace_eval_jmp_to_tail(map)->tail.next; kfree(map); - out: - mutex_unlock(&trace_eval_mutex); } #else static inline void trace_module_remove_evals(struct module *mod) { } #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ +static void trace_module_record(struct module *mod, bool add) +{ + struct trace_array *tr; + unsigned long flags; + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + flags = tr->flags & (TRACE_ARRAY_FL_BOOT | TRACE_ARRAY_FL_LAST_BOOT); + /* Update any persistent trace array that has already been started */ + if (flags == TRACE_ARRAY_FL_BOOT && add) { + guard(mutex)(&scratch_mutex); + save_mod(mod, tr); + } else if (flags & TRACE_ARRAY_FL_LAST_BOOT) { + /* Update delta if the module loaded in previous boot */ + make_mod_delta(mod, tr); + } + } +} + static int trace_module_notify(struct notifier_block *self, unsigned long val, void *data) { @@ -8182,13 +10898,15 @@ static int trace_module_notify(struct notifier_block *self, switch (val) { case MODULE_STATE_COMING: trace_module_add_evals(mod); + trace_module_record(mod, true); break; case MODULE_STATE_GOING: trace_module_remove_evals(mod); + trace_module_record(mod, false); break; } - return 0; + return NOTIFY_OK; } static struct notifier_block trace_module_nb = { @@ -8197,91 +10915,105 @@ static struct notifier_block trace_module_nb = { }; #endif /* CONFIG_MODULES */ -static __init int tracer_init_tracefs(void) +static __init void tracer_init_tracefs_work_func(struct work_struct *work) { - struct dentry *d_tracer; - - trace_access_lock_init(); - - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) - return 0; event_trace_init(); - init_tracer_tracefs(&global_trace, d_tracer); - ftrace_init_tracefs_toplevel(&global_trace, d_tracer); + init_tracer_tracefs(&global_trace, NULL); + ftrace_init_tracefs_toplevel(&global_trace, NULL); - trace_create_file("tracing_thresh", 0644, d_tracer, + trace_create_file("tracing_thresh", TRACE_MODE_WRITE, NULL, &global_trace, &tracing_thresh_fops); - trace_create_file("README", 0444, d_tracer, + trace_create_file("README", TRACE_MODE_READ, NULL, NULL, &tracing_readme_fops); - trace_create_file("saved_cmdlines", 0444, d_tracer, + trace_create_file("saved_cmdlines", TRACE_MODE_READ, NULL, NULL, &tracing_saved_cmdlines_fops); - trace_create_file("saved_cmdlines_size", 0644, d_tracer, + trace_create_file("saved_cmdlines_size", TRACE_MODE_WRITE, NULL, NULL, &tracing_saved_cmdlines_size_fops); - trace_create_file("saved_tgids", 0444, d_tracer, + trace_create_file("saved_tgids", TRACE_MODE_READ, NULL, NULL, &tracing_saved_tgids_fops); - trace_eval_init(); - - trace_create_eval_file(d_tracer); + trace_create_eval_file(NULL); #ifdef CONFIG_MODULES register_module_notifier(&trace_module_nb); #endif #ifdef CONFIG_DYNAMIC_FTRACE - trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, - &ftrace_update_tot_cnt, &tracing_dyn_info_fops); + trace_create_file("dyn_ftrace_total_info", TRACE_MODE_READ, NULL, + NULL, &tracing_dyn_info_fops); #endif - create_trace_instances(d_tracer); + create_trace_instances(NULL); - update_tracer_options(&global_trace); - - return 0; + update_tracer_options(); } -static int trace_panic_handler(struct notifier_block *this, - unsigned long event, void *unused) +static __init int tracer_init_tracefs(void) { - if (ftrace_dump_on_oops) - ftrace_dump(ftrace_dump_on_oops); - return NOTIFY_OK; -} + int ret; -static struct notifier_block trace_panic_notifier = { - .notifier_call = trace_panic_handler, - .next = NULL, - .priority = 150 /* priority: INT_MAX >= x >= 0 */ -}; + trace_access_lock_init(); -static int trace_die_handler(struct notifier_block *self, - unsigned long val, - void *data) -{ - switch (val) { - case DIE_OOPS: - if (ftrace_dump_on_oops) - ftrace_dump(ftrace_dump_on_oops); - break; - default: - break; + ret = tracing_init_dentry(); + if (ret) + return 0; + + if (eval_map_wq) { + INIT_WORK(&tracerfs_init_work, tracer_init_tracefs_work_func); + queue_work(eval_map_wq, &tracerfs_init_work); + } else { + tracer_init_tracefs_work_func(NULL); } - return NOTIFY_OK; + + if (rv_init_interface()) + pr_err("RV: Error while creating the RV interface\n"); + + return 0; } +fs_initcall(tracer_init_tracefs); + +static int trace_die_panic_handler(struct notifier_block *self, + unsigned long ev, void *unused); + +static struct notifier_block trace_panic_notifier = { + .notifier_call = trace_die_panic_handler, + .priority = INT_MAX - 1, +}; + static struct notifier_block trace_die_notifier = { - .notifier_call = trace_die_handler, - .priority = 200 + .notifier_call = trace_die_panic_handler, + .priority = INT_MAX - 1, }; /* + * The idea is to execute the following die/panic callback early, in order + * to avoid showing irrelevant information in the trace (like other panic + * notifier functions); we are the 2nd to run, after hung_task/rcu_stall + * warnings get disabled (to prevent potential log flooding). + */ +static int trace_die_panic_handler(struct notifier_block *self, + unsigned long ev, void *unused) +{ + if (!ftrace_dump_on_oops_enabled()) + return NOTIFY_DONE; + + /* The die notifier requires DIE_OOPS to trigger */ + if (self == &trace_die_notifier && ev != DIE_OOPS) + return NOTIFY_DONE; + + ftrace_dump(DUMP_PARAM); + + return NOTIFY_DONE; +} + +/* * printk is set to max of 1024, we really don't need it that big. * Nothing should be printing 1000 characters anyway. */ @@ -8317,40 +11049,43 @@ trace_printk_seq(struct trace_seq *s) trace_seq_init(s); } -void trace_init_global_iter(struct trace_iterator *iter) +static void trace_init_iter(struct trace_iterator *iter, struct trace_array *tr) { - iter->tr = &global_trace; + iter->tr = tr; iter->trace = iter->tr->current_trace; iter->cpu_file = RING_BUFFER_ALL_CPUS; - iter->trace_buffer = &global_trace.trace_buffer; + iter->array_buffer = &tr->array_buffer; if (iter->trace && iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ - if (ring_buffer_overruns(iter->trace_buffer->buffer)) + if (ring_buffer_overruns(iter->array_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[iter->tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + + /* Can not use kmalloc for iter.temp and iter.fmt */ + iter->temp = static_temp_buf; + iter->temp_size = STATIC_TEMP_BUF_SIZE; + iter->fmt = static_fmt_buf; + iter->fmt_size = STATIC_FMT_BUF_SIZE; } -void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) +void trace_init_global_iter(struct trace_iterator *iter) +{ + trace_init_iter(iter, &global_trace); +} + +static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_mode) { /* use static because iter can be a bit big for the stack */ static struct trace_iterator iter; - static atomic_t dump_running; - struct trace_array *tr = &global_trace; unsigned int old_userobj; unsigned long flags; - int cnt = 0, cpu; - - /* Only allow one dump user at a time. */ - if (atomic_inc_return(&dump_running) != 1) { - atomic_dec(&dump_running); - return; - } + int cnt = 0; /* * Always turn off tracing when we dump. @@ -8360,38 +11095,30 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) * If the user does a sysrq-z, then they can re-enable * tracing with echo 1 > tracing_on. */ - tracing_off(); + tracer_tracing_off(tr); local_irq_save(flags); - printk_nmi_direct_enter(); /* Simulate the iterator */ - trace_init_global_iter(&iter); + trace_init_iter(&iter, tr); - for_each_tracing_cpu(cpu) { - atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); - } + /* While dumping, do not allow the buffer to be enable */ + tracer_tracing_disable(tr); - old_userobj = tr->trace_flags & TRACE_ITER_SYM_USEROBJ; + old_userobj = tr->trace_flags & TRACE_ITER(SYM_USEROBJ); /* don't look at user memory in panic mode */ - tr->trace_flags &= ~TRACE_ITER_SYM_USEROBJ; + tr->trace_flags &= ~TRACE_ITER(SYM_USEROBJ); - switch (oops_dump_mode) { - case DUMP_ALL: - iter.cpu_file = RING_BUFFER_ALL_CPUS; - break; - case DUMP_ORIG: + if (dump_mode == DUMP_ORIG) iter.cpu_file = raw_smp_processor_id(); - break; - case DUMP_NONE: - goto out_enable; - default: - printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n"); + else iter.cpu_file = RING_BUFFER_ALL_CPUS; - } - printk(KERN_TRACE "Dumping ftrace buffer:\n"); + if (tr == &global_trace) + printk(KERN_TRACE "Dumping ftrace buffer:\n"); + else + printk(KERN_TRACE "Dumping ftrace instance %s buffer:\n", tr->name); /* Did function tracer already get disabled? */ if (ftrace_is_dead()) { @@ -8400,7 +11127,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) } /* - * We need to stop all tracing on all CPUS to read the + * We need to stop all tracing on all CPUS to read * the next buffer. This is a bit expensive, but is * not done often. We fill all what we can read, * and then release the locks again. @@ -8413,12 +11140,8 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) cnt++; - /* reset all but tr, trace, and overruns */ - memset(&iter.seq, 0, - sizeof(struct trace_iterator) - - offsetof(struct trace_iterator, seq)); + trace_iterator_reset(&iter); iter.iter_flags |= TRACE_FILE_LAT_FMT; - iter.pos = -1; if (trace_find_next_entry_inc(&iter) != NULL) { int ret; @@ -8426,10 +11149,10 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) ret = print_trace_line(&iter); if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(&iter); + + trace_printk_seq(&iter.seq); } touch_nmi_watchdog(); - - trace_printk_seq(&iter.seq); } if (!cnt) @@ -8437,44 +11160,92 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) else printk(KERN_TRACE "---------------------------------\n"); - out_enable: tr->trace_flags |= old_userobj; - for_each_tracing_cpu(cpu) { - atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); - } - atomic_dec(&dump_running); - printk_nmi_direct_exit(); + tracer_tracing_enable(tr); local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(ftrace_dump); -int trace_run_command(const char *buf, int (*createfn)(int, char **)) +static void ftrace_dump_by_param(void) { - char **argv; - int argc, ret; + bool first_param = true; + char dump_param[MAX_TRACER_SIZE]; + char *buf, *token, *inst_name; + struct trace_array *tr; - argc = 0; - ret = 0; - argv = argv_split(GFP_KERNEL, buf, &argc); - if (!argv) - return -ENOMEM; + strscpy(dump_param, ftrace_dump_on_oops, MAX_TRACER_SIZE); + buf = dump_param; + + while ((token = strsep(&buf, ",")) != NULL) { + if (first_param) { + first_param = false; + if (!strcmp("0", token)) + continue; + else if (!strcmp("1", token)) { + ftrace_dump_one(&global_trace, DUMP_ALL); + continue; + } + else if (!strcmp("2", token) || + !strcmp("orig_cpu", token)) { + ftrace_dump_one(&global_trace, DUMP_ORIG); + continue; + } + } - if (argc) - ret = createfn(argc, argv); + inst_name = strsep(&token, "="); + tr = trace_array_find(inst_name); + if (!tr) { + printk(KERN_TRACE "Instance %s not found\n", inst_name); + continue; + } - argv_free(argv); + if (token && (!strcmp("2", token) || + !strcmp("orig_cpu", token))) + ftrace_dump_one(tr, DUMP_ORIG); + else + ftrace_dump_one(tr, DUMP_ALL); + } +} - return ret; +void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) +{ + static atomic_t dump_running; + + /* Only allow one dump user at a time. */ + if (atomic_inc_return(&dump_running) != 1) { + atomic_dec(&dump_running); + return; + } + + switch (oops_dump_mode) { + case DUMP_ALL: + ftrace_dump_one(&global_trace, DUMP_ALL); + break; + case DUMP_ORIG: + ftrace_dump_one(&global_trace, DUMP_ORIG); + break; + case DUMP_PARAM: + ftrace_dump_by_param(); + break; + case DUMP_NONE: + break; + default: + printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n"); + ftrace_dump_one(&global_trace, DUMP_ALL); + } + + atomic_dec(&dump_running); } +EXPORT_SYMBOL_GPL(ftrace_dump); #define WRITE_BUFSIZE 4096 ssize_t trace_parse_run_command(struct file *file, const char __user *buffer, size_t count, loff_t *ppos, - int (*createfn)(int, char **)) + int (*createfn)(const char *)) { - char *kbuf, *buf, *tmp; + char *kbuf __free(kfree) = NULL; + char *buf, *tmp; int ret = 0; size_t done = 0; size_t size; @@ -8489,10 +11260,9 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer, if (size >= WRITE_BUFSIZE) size = WRITE_BUFSIZE - 1; - if (copy_from_user(kbuf, buffer + done, size)) { - ret = -EFAULT; - goto out; - } + if (copy_from_user(kbuf, buffer + done, size)) + return -EFAULT; + kbuf[size] = '\0'; buf = kbuf; do { @@ -8508,8 +11278,7 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer, /* This can accept WRITE_BUFSIZE - 2 ('\n' + '\0') */ pr_warn("Line length is too long: Should be less than %d\n", WRITE_BUFSIZE - 2); - ret = -EINVAL; - goto out; + return -EINVAL; } } done += size; @@ -8520,45 +11289,277 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer, if (tmp) *tmp = '\0'; - ret = trace_run_command(buf, createfn); + ret = createfn(buf); if (ret) - goto out; + return ret; buf += size; } while (done < count); } - ret = done; + return done; +} -out: - kfree(kbuf); +#ifdef CONFIG_TRACER_MAX_TRACE +__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) +{ + struct trace_array *backup_tr; + void *allocated_vaddr = NULL; + + backup_tr = trace_array_get_by_name(backup, NULL); + if (!backup_tr) { + pr_warn("Tracing: Instance %s is not found.\n", backup); + return -ENOENT; + } + + if (!(backup_tr->flags & TRACE_ARRAY_FL_BOOT)) { + pr_warn("Tracing: Instance %s is not boot mapped.\n", backup); + trace_array_put(backup_tr); + return -EINVAL; + } + + *size = backup_tr->range_addr_size; + + allocated_vaddr = vzalloc(*size); + if (!allocated_vaddr) { + pr_warn("Tracing: Failed to allocate memory for copying instance %s (size 0x%lx)\n", + backup, (unsigned long)*size); + trace_array_put(backup_tr); + return -ENOMEM; + } + + memcpy(allocated_vaddr, + (void *)backup_tr->range_addr_start, (size_t)*size); + *addr = (unsigned long)allocated_vaddr; + + trace_array_put(backup_tr); + return 0; +} + +__init static void enable_instances(void) +{ + struct trace_array *tr; + bool memmap_area = false; + char *curr_str; + char *name; + char *str; + char *tok; + + /* A tab is always appended */ + boot_instance_info[boot_instance_index - 1] = '\0'; + str = boot_instance_info; + + while ((curr_str = strsep(&str, "\t"))) { + phys_addr_t start = 0; + phys_addr_t size = 0; + unsigned long addr = 0; + bool traceprintk = false; + bool traceoff = false; + char *flag_delim; + char *addr_delim; + char *rname __free(kfree) = NULL; + char *backup; + + tok = strsep(&curr_str, ","); + + name = strsep(&tok, "="); + backup = tok; + + flag_delim = strchr(name, '^'); + addr_delim = strchr(name, '@'); + + if (addr_delim) + *addr_delim++ = '\0'; + + if (flag_delim) + *flag_delim++ = '\0'; + + if (backup) { + if (backup_instance_area(backup, &addr, &size) < 0) + continue; + } + + if (flag_delim) { + char *flag; + + while ((flag = strsep(&flag_delim, "^"))) { + if (strcmp(flag, "traceoff") == 0) { + traceoff = true; + } else if ((strcmp(flag, "printk") == 0) || + (strcmp(flag, "traceprintk") == 0) || + (strcmp(flag, "trace_printk") == 0)) { + traceprintk = true; + } else { + pr_info("Tracing: Invalid instance flag '%s' for %s\n", + flag, name); + } + } + } + + tok = addr_delim; + if (tok && isdigit(*tok)) { + start = memparse(tok, &tok); + if (!start) { + pr_warn("Tracing: Invalid boot instance address for %s\n", + name); + continue; + } + if (*tok != ':') { + pr_warn("Tracing: No size specified for instance %s\n", name); + continue; + } + tok++; + size = memparse(tok, &tok); + if (!size) { + pr_warn("Tracing: Invalid boot instance size for %s\n", + name); + continue; + } + memmap_area = true; + } else if (tok) { + if (!reserve_mem_find_by_name(tok, &start, &size)) { + start = 0; + pr_warn("Failed to map boot instance %s to %s\n", name, tok); + continue; + } + rname = kstrdup(tok, GFP_KERNEL); + } + + if (start) { + /* Start and size must be page aligned */ + if (start & ~PAGE_MASK) { + pr_warn("Tracing: mapping start addr %pa is not page aligned\n", &start); + continue; + } + if (size & ~PAGE_MASK) { + pr_warn("Tracing: mapping size %pa is not page aligned\n", &size); + continue; + } + + if (memmap_area) + addr = map_pages(start, size); + else + addr = (unsigned long)phys_to_virt(start); + if (addr) { + pr_info("Tracing: mapped boot instance %s at physical memory %pa of size 0x%lx\n", + name, &start, (unsigned long)size); + } else { + pr_warn("Tracing: Failed to map boot instance %s\n", name); + continue; + } + } else { + /* Only non mapped buffers have snapshot buffers */ + if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE)) + do_allocate_snapshot(name); + } + + tr = trace_array_create_systems(name, NULL, addr, size); + if (IS_ERR(tr)) { + pr_warn("Tracing: Failed to create instance buffer %s\n", curr_str); + continue; + } + + if (traceoff) + tracer_tracing_off(tr); + + if (traceprintk) + update_printk_trace(tr); + + /* + * memmap'd buffers can not be freed. + */ + if (memmap_area) { + tr->flags |= TRACE_ARRAY_FL_MEMMAP; + tr->ref++; + } + + /* + * Backup buffers can be freed but need vfree(). + */ + if (backup) + tr->flags |= TRACE_ARRAY_FL_VMALLOC; + + if (start || backup) { + tr->flags |= TRACE_ARRAY_FL_BOOT | TRACE_ARRAY_FL_LAST_BOOT; + tr->range_name = no_free_ptr(rname); + } + + while ((tok = strsep(&curr_str, ","))) { + early_enable_events(tr, tok, true); + } + } +} + __init static int tracer_alloc_buffers(void) { int ring_buf_size; int ret = -ENOMEM; + + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Tracing disabled due to lockdown\n"); + return -EPERM; + } + /* - * Make sure we don't accidently add more trace options + * Make sure we don't accidentally add more trace options * than we have bits for. */ BUILD_BUG_ON(TRACE_ITER_LAST_BIT > TRACE_FLAGS_MAX_SIZE); if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL)) - goto out; + return -ENOMEM; if (!alloc_cpumask_var(&global_trace.tracing_cpumask, GFP_KERNEL)) goto out_free_buffer_mask; /* Only allocate trace_printk buffers if a trace_printk exists */ - if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt) /* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers(); /* To save memory, keep the ring buffer size to its minimum */ - if (ring_buffer_expanded) + if (global_trace.ring_buffer_expanded) ring_buf_size = trace_buf_size; else ring_buf_size = 1; @@ -8570,12 +11571,12 @@ __init static int tracer_alloc_buffers(void) /* * The prepare callbacks allocates some memory for the ring buffer. We - * don't free the buffer if the if the CPU goes down. If we were to free + * don't free the buffer if the CPU goes down. If we were to free * the buffer, then the user would lose any trace that was in the * buffer. The memory will be removed once the "instance" is removed. */ ret = cpuhp_setup_state_multi(CPUHP_TRACE_RB_PREPARE, - "trace/RB:preapre", trace_rb_cpu_prepare, + "trace/RB:prepare", trace_rb_cpu_prepare, NULL); if (ret < 0) goto out_free_cpumask; @@ -8588,13 +11589,14 @@ __init static int tracer_alloc_buffers(void) if (trace_create_savedcmd() < 0) goto out_free_temp_buffer; + if (!zalloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL)) + goto out_free_savedcmd; + /* TODO: make the number of buffers hot pluggable with CPUS */ if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { - printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); - WARN_ON(1); - goto out_free_savedcmd; + MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n"); + goto out_free_pipe_cpumask; } - if (global_trace.buffer_disabled) tracing_off(); @@ -8611,17 +11613,21 @@ __init static int tracer_alloc_buffers(void) * just a bootstrap of current_trace anyway. */ global_trace.current_trace = &nop_trace; + global_trace.current_trace_flags = nop_trace.flags; global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; - +#ifdef CONFIG_TRACER_MAX_TRACE + spin_lock_init(&global_trace.snapshot_trigger_lock); +#endif ftrace_init_global_array_ops(&global_trace); - init_trace_flags_index(&global_trace); +#ifdef CONFIG_MODULES + INIT_LIST_HEAD(&global_trace.mod_events); +#endif - register_tracer(&nop_trace); + init_trace_flags_index(&global_trace); - /* Function tracing may start here (via kernel command line) */ - init_function_trace(); + INIT_LIST_HEAD(&global_trace.tracers); /* All seems OK, enable tracing */ tracing_disabled = 0; @@ -8633,19 +11639,30 @@ __init static int tracer_alloc_buffers(void) global_trace.flags = TRACE_ARRAY_FL_GLOBAL; + global_trace.syscall_buf_sz = syscall_buf_size; + INIT_LIST_HEAD(&global_trace.systems); INIT_LIST_HEAD(&global_trace.events); INIT_LIST_HEAD(&global_trace.hist_vars); + INIT_LIST_HEAD(&global_trace.err_log); + list_add(&global_trace.marker_list, &marker_copies); list_add(&global_trace.list, &ftrace_trace_arrays); + register_tracer(&nop_trace); + + /* Function tracing may start here (via kernel command line) */ + init_function_trace(); + apply_trace_boot_options(); register_snapshot_cmd(); return 0; +out_free_pipe_cpumask: + free_cpumask_var(global_trace.pipe_cpumask); out_free_savedcmd: - free_saved_cmdlines_buffer(savedcmd); + trace_free_saved_cmdlines_buffer(); out_free_temp_buffer: ring_buffer_free(temp_buffer); out_rm_hp_state: @@ -8654,29 +11671,60 @@ out_free_cpumask: free_cpumask_var(global_trace.tracing_cpumask); out_free_buffer_mask: free_cpumask_var(tracing_buffer_mask); -out: return ret; } +#ifdef CONFIG_FUNCTION_TRACER +/* Used to set module cached ftrace filtering at boot up */ +struct trace_array *trace_get_global_array(void) +{ + return &global_trace; +} +#endif + +void __init ftrace_boot_snapshot(void) +{ +#ifdef CONFIG_TRACER_MAX_TRACE + 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) { tracepoint_print_iter = - kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL); - if (WARN_ON(!tracepoint_print_iter)) + kzalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL); + if (MEM_FAIL(!tracepoint_print_iter, + "Failed to allocate trace iterator\n")) tracepoint_printk = 0; else static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); + + init_events(); } void __init trace_init(void) { trace_event_init(); + + if (boot_instance_index) + enable_instances(); } -__init static int clear_boot_tracer(void) +__init static void clear_boot_tracer(void) { /* * The default tracer at boot buffer is an init section. @@ -8686,23 +11734,23 @@ __init static int clear_boot_tracer(void) * about to be freed. */ if (!default_bootup_tracer) - return 0; + return; printk(KERN_INFO "ftrace bootup tracer '%s' not registered.\n", default_bootup_tracer); default_bootup_tracer = NULL; - - return 0; } -fs_initcall(tracer_init_tracefs); -late_initcall_sync(clear_boot_tracer); - #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -__init static int tracing_set_default_clock(void) +__init static void tracing_set_default_clock(void) { /* sched_clock_stable() is determined in late_initcall */ if (!trace_boot_clock && !sched_clock_stable()) { + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not set tracing clock due to lockdown\n"); + return; + } + printk(KERN_WARNING "Unstable clock detected, switching default tracing clock to \"global\"\n" "If you want to keep using the local clock, then add:\n" @@ -8710,8 +11758,24 @@ __init static int tracing_set_default_clock(void) "on the kernel command line\n"); tracing_set_clock(&global_trace, "global"); } +} +#else +static inline void tracing_set_default_clock(void) { } +#endif + +__init static int late_trace_init(void) +{ + if (tracepoint_printk && tracepoint_printk_stop_on_boot) { + static_key_disable(&tracepoint_printk_key.key); + tracepoint_printk = 0; + } + + if (traceoff_after_boot) + tracing_off(); + tracing_set_default_clock(); + clear_boot_tracer(); return 0; } -late_initcall_sync(tracing_set_default_clock); -#endif + +late_initcall_sync(late_trace_init); |