From 01573e231f18eb2d99162747186f59511f56b64d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 08 Dec 2023 10:40:48 +0000
Subject: [PATCH] 移去rt
---
kernel/kernel/trace/trace.c | 2615 +++++++++++++++++++++++++++++++++++++++++-----------------
1 files changed, 1,834 insertions(+), 781 deletions(-)
diff --git a/kernel/kernel/trace/trace.c b/kernel/kernel/trace/trace.c
index ead2e09..c4cce26 100644
--- a/kernel/kernel/trace/trace.c
+++ b/kernel/kernel/trace/trace.c
@@ -17,6 +17,7 @@
#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>
@@ -44,6 +45,10 @@
#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 <trace/hooks/ftrace_dump.h>
#include "trace.h"
#include "trace_output.h"
@@ -64,9 +69,20 @@
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;
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+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);
+ }
+}
+#endif
/* Pipe tracepoints to printk */
struct trace_iterator *tracepoint_print_iter;
@@ -158,7 +174,10 @@
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;
@@ -215,7 +234,7 @@
static int __init set_trace_boot_options(char *str)
{
strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
- return 0;
+ return 1;
}
__setup("trace_options=", set_trace_boot_options);
@@ -226,7 +245,7 @@
{
strlcpy(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);
@@ -248,6 +267,145 @@
do_div(nsec, 1000);
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;
+
+ preempt_disable_notrace();
+
+ export = rcu_dereference_raw_check(ftrace_exports_list);
+ while (export) {
+ trace_process_export(export, event, flag);
+ export = rcu_dereference_raw_check(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)
+{
+ 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;
+
+ 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);
/* trace_flags holds trace_options default values */
#define TRACE_DEFAULT_FLAGS \
@@ -299,15 +457,44 @@
this_tr->ref--;
}
+/**
+ * trace_array_put - Decrement the reference counter for this 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)
{
+ if (!this_tr)
+ return;
+
mutex_lock(&trace_types_lock);
__trace_array_put(this_tr);
mutex_unlock(&trace_types_lock);
}
+EXPORT_SYMBOL_GPL(trace_array_put);
+
+int tracing_check_open_get_tr(struct trace_array *tr)
+{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
+ if (tracing_disabled)
+ return -ENODEV;
+
+ if (tr && trace_array_get(tr) < 0)
+ return -ENODEV;
+
+ return 0;
+}
int call_filter_check_discard(struct trace_event_call *call, void *rec,
- struct ring_buffer *buffer,
+ struct trace_buffer *buffer,
struct ring_buffer_event *event)
{
if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
@@ -355,20 +542,26 @@
* 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 filterd_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
@@ -572,7 +765,7 @@
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;
@@ -588,7 +781,7 @@
u64 ftrace_now(int cpu)
{
- return buffer_ftrace_now(&global_trace.trace_buffer, cpu);
+ return buffer_ftrace_now(&global_trace.array_buffer, cpu);
}
/**
@@ -716,24 +909,24 @@
#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_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_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)
{
}
@@ -741,33 +934,32 @@
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
@@ -795,7 +987,7 @@
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);
@@ -818,28 +1010,28 @@
int __trace_puts(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))
return 0;
-
- pc = preempt_count();
if (unlikely(tracing_selftest_running || 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);
- if (!event)
- return 0;
+ trace_ctx = tracing_gen_ctx();
+ buffer = global_trace.array_buffer.buffer;
+ ring_buffer_nest_start(buffer);
+ event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
+ trace_ctx);
+ if (!event) {
+ size = 0;
+ goto out;
+ }
entry = ring_buffer_event_data(event);
entry->ip = ip;
@@ -854,8 +1046,9 @@
entry->buf[size] = '\0';
__buffer_unlock_commit(buffer, event);
- ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL);
-
+ ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL);
+ out:
+ ring_buffer_nest_end(buffer);
return size;
}
EXPORT_SYMBOL_GPL(__trace_puts);
@@ -868,40 +1061,44 @@
int __trace_bputs(unsigned long ip, const char *str)
{
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;
+ int ret = 0;
if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
return 0;
- pc = preempt_count();
-
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 = global_trace.array_buffer.buffer;
+
+ ring_buffer_nest_start(buffer);
event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
- irq_flags, pc);
+ trace_ctx);
if (!event)
- return 0;
+ goto out;
entry = ring_buffer_event_data(event);
entry->ip = ip;
entry->str = str;
__buffer_unlock_commit(buffer, event);
- ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL);
+ ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL);
- return 1;
+ ret = 1;
+ out:
+ ring_buffer_nest_end(buffer);
+ return ret;
}
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;
@@ -927,8 +1124,13 @@
}
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);
}
/**
@@ -953,9 +1155,59 @@
}
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_snapshot_cond_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)
{
@@ -965,7 +1217,7 @@
/* 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;
@@ -1032,12 +1284,115 @@
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;
+ int ret = 0;
+
+ cond_snapshot = kzalloc(sizeof(*cond_snapshot), GFP_KERNEL);
+ if (!cond_snapshot)
+ return -ENOMEM;
+
+ cond_snapshot->cond_data = cond_data;
+ cond_snapshot->update = update;
+
+ mutex_lock(&trace_types_lock);
+
+ ret = tracing_alloc_snapshot_instance(tr);
+ if (ret)
+ goto fail_unlock;
+
+ if (tr->current_trace->use_max_tr) {
+ ret = -EBUSY;
+ goto fail_unlock;
+ }
+
+ /*
+ * 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) {
+ ret = -EBUSY;
+ goto fail_unlock;
+ }
+
+ local_irq_disable();
+ arch_spin_lock(&tr->max_lock);
+ tr->cond_snapshot = cond_snapshot;
+ arch_spin_unlock(&tr->max_lock);
+ local_irq_enable();
+
+ mutex_unlock(&trace_types_lock);
+
+ return ret;
+
+ fail_unlock:
+ mutex_unlock(&trace_types_lock);
+ kfree(cond_snapshot);
+ return ret;
+}
+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();
+
+ 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");
@@ -1050,12 +1405,27 @@
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);
#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
@@ -1085,8 +1455,11 @@
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();
+ }
}
/**
@@ -1097,8 +1470,8 @@
*/
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_on(tr->array_buffer.buffer);
return !tr->buffer_disabled;
}
@@ -1118,10 +1491,12 @@
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);
@@ -1315,6 +1690,73 @@
}
unsigned long __read_mostly tracing_thresh;
+static const struct file_operations tracing_max_lat_fops;
+
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+ defined(CONFIG_FSNOTIFY)
+
+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", 0644,
+ d_tracer, &tr->max_latency,
+ &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);
+}
+
+/*
+ * (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+ * defined(CONFIG_FSNOTIFY)
+ */
+#else
+
+#define trace_create_maxlat_file(tr, d_tracer) \
+ trace_create_file("tracing_max_latency", 0644, d_tracer, \
+ &tr->max_latency, &tracing_max_lat_fops)
+
+#endif
#ifdef CONFIG_TRACER_MAX_TRACE
/*
@@ -1325,8 +1767,8 @@
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);
@@ -1337,7 +1779,7 @@
max_data->critical_start = data->critical_start;
max_data->critical_end = data->critical_end;
- memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
+ strncpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
max_data->pid = tsk->pid;
/*
* If tsk == current, then use current_uid(), as that does not use
@@ -1354,6 +1796,7 @@
/* record this tasks comm */
tracing_record_cmdline(tsk);
+ latency_fsnotify(tr);
}
/**
@@ -1361,12 +1804,14 @@
* @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;
@@ -1381,23 +1826,29 @@
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))
+ goto out_unlock;
+#endif
+ swap(tr->array_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
+
+ out_unlock:
arch_spin_unlock(&tr->max_lock);
}
/**
* 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.
*/
@@ -1418,7 +1869,7 @@
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) {
/*
@@ -1438,13 +1889,13 @@
}
#endif /* CONFIG_TRACER_MAX_TRACE */
-static int wait_on_pipe(struct trace_iterator *iter, bool full)
+static int wait_on_pipe(struct trace_iterator *iter, int full)
{
/* 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,
+ return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file,
full);
}
@@ -1495,7 +1946,7 @@
* 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;
@@ -1521,7 +1972,7 @@
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) {
@@ -1555,6 +2006,10 @@
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) {
@@ -1593,7 +2048,7 @@
/**
* 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.
*/
@@ -1610,6 +2065,12 @@
if (strlen(type->name) >= MAX_TRACER_SIZE) {
pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE);
return -1;
+ }
+
+ if (security_locked_down(LOCKDOWN_TRACEFS)) {
+ pr_warn("Can not register tracer %s due to lockdown\n",
+ type->name);
+ return -EPERM;
}
mutex_lock(&trace_types_lock);
@@ -1670,19 +2131,15 @@
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;
}
-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;
@@ -1690,16 +2147,15 @@
ring_buffer_record_disable(buffer);
/* Make sure all commits have finished */
- synchronize_sched();
+ synchronize_rcu();
ring_buffer_reset_cpu(buffer, 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;
@@ -1707,12 +2163,11 @@
ring_buffer_record_disable(buffer);
/* Make sure all commits have finished */
- synchronize_sched();
+ synchronize_rcu();
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);
}
@@ -1726,7 +2181,7 @@
if (!tr->clear_trace)
continue;
tr->clear_trace = false;
- tracing_reset_online_cpus(&tr->trace_buffer);
+ tracing_reset_online_cpus(&tr->array_buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
tracing_reset_online_cpus(&tr->max_buffer);
#endif
@@ -1744,6 +2199,11 @@
#define SAVED_CMDLINES_DEFAULT 128
#define NO_CMDLINE_MAP UINT_MAX
+/*
+ * Preemption must be disabled before acquiring trace_cmdline_lock.
+ * The various trace_arrays' max_lock must be acquired in a context
+ * where interrupt is disabled.
+ */
static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
struct saved_cmdlines_buffer {
unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -1761,7 +2221,7 @@
static inline void set_cmdline(int idx, const char *cmdline)
{
- memcpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
+ strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
}
static int allocate_cmdlines_buffer(unsigned int val,
@@ -1820,7 +2280,7 @@
*/
void tracing_start(void)
{
- struct ring_buffer *buffer;
+ struct trace_buffer *buffer;
unsigned long flags;
if (tracing_disabled)
@@ -1839,7 +2299,7 @@
/* Prevent the buffers from switching */
arch_spin_lock(&global_trace.max_lock);
- buffer = global_trace.trace_buffer.buffer;
+ buffer = global_trace.array_buffer.buffer;
if (buffer)
ring_buffer_record_enable(buffer);
@@ -1857,7 +2317,7 @@
static void tracing_start_tr(struct trace_array *tr)
{
- struct ring_buffer *buffer;
+ struct trace_buffer *buffer;
unsigned long flags;
if (tracing_disabled)
@@ -1878,7 +2338,7 @@
goto out;
}
- buffer = tr->trace_buffer.buffer;
+ buffer = tr->array_buffer.buffer;
if (buffer)
ring_buffer_record_enable(buffer);
@@ -1894,7 +2354,7 @@
*/
void tracing_stop(void)
{
- struct ring_buffer *buffer;
+ struct trace_buffer *buffer;
unsigned long flags;
raw_spin_lock_irqsave(&global_trace.start_lock, flags);
@@ -1904,7 +2364,7 @@
/* Prevent the buffers from switching */
arch_spin_lock(&global_trace.max_lock);
- buffer = global_trace.trace_buffer.buffer;
+ buffer = global_trace.array_buffer.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
@@ -1922,7 +2382,7 @@
static void tracing_stop_tr(struct trace_array *tr)
{
- struct ring_buffer *buffer;
+ struct trace_buffer *buffer;
unsigned long flags;
/* If global, we need to also stop the max tracer */
@@ -1933,7 +2393,7 @@
if (tr->stop_count++)
goto out;
- buffer = tr->trace_buffer.buffer;
+ buffer = tr->array_buffer.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
@@ -1956,7 +2416,11 @@
* 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.
+ *
+ * This is called within the scheduler and wake up, so interrupts
+ * had better been disabled and run queue lock been held.
*/
+ lockdep_assert_preemption_disabled();
if (!arch_spin_trylock(&trace_cmdline_lock))
return 0;
@@ -2064,9 +2528,9 @@
/**
* 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
+ * @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)
{
@@ -2092,10 +2556,10 @@
/**
* tracing_record_taskinfo_sched_switch - record task info for sched_switch
*
- * @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
+ * @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
*/
void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
struct task_struct *next, int flags)
@@ -2144,39 +2608,52 @@
}
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->preempt_lazy_count = preempt_lazy_count();
- 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) && defined(CONFIG_PREEMPT_RT)
+ 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_now() ? TRACE_FLAG_NEED_RESCHED : 0) |
- (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) |
- (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
-
- entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 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 (tif_need_resched())
+ trace_flags |= TRACE_FLAG_NEED_RESCHED;
+ if (test_preempt_need_resched())
+ trace_flags |= TRACE_FLAG_PREEMPT_RESCHED;
+
+#ifdef CONFIG_PREEMPT_LAZY
+ if (need_resched_lazy())
+ trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY;
+#endif
+
+ return (pc & 0xff) |
+ (migration_disable_value() & 0xff) << 8 |
+ (preempt_lazy_count() & 0xff) << 16 |
+ (trace_flags << 24);
+}
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);
@@ -2221,7 +2698,7 @@
preempt_disable();
if (cpu == smp_processor_id() &&
- this_cpu_read(trace_buffered_event) !=
+ __this_cpu_read(trace_buffered_event) !=
per_cpu(trace_buffered_event, cpu))
WARN_ON_ONCE(1);
preempt_enable();
@@ -2271,7 +2748,7 @@
preempt_enable();
/* Wait for all current users to finish */
- synchronize_sched();
+ synchronize_rcu();
for_each_tracing_cpu(cpu) {
free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
@@ -2290,18 +2767,18 @@
preempt_enable();
}
-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;
int val;
- *current_rb = trace_file->tr->trace_buffer.buffer;
+ *current_rb = trace_file->tr->array_buffer.buffer;
if (!ring_buffer_time_stamp_abs(*current_rb) && (trace_file->flags &
(EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
@@ -2309,7 +2786,7 @@
/* Try to use the per cpu buffer first */
val = this_cpu_inc_return(trace_buffered_event_cnt);
if ((len < (PAGE_SIZE - sizeof(*entry) - sizeof(entry->array[0]))) && val == 1) {
- trace_event_setup(entry, type, flags, pc);
+ trace_event_setup(entry, type, trace_ctx);
entry->array[0] = len;
return entry;
}
@@ -2317,28 +2794,29 @@
}
entry = __trace_buffer_lock_reserve(*current_rb,
- type, len, flags, pc);
+ 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;
@@ -2352,20 +2830,26 @@
!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,
+ void *buffer, size_t *lenp,
loff_t *ppos)
{
int save_tracepoint_printk;
@@ -2402,9 +2886,11 @@
if (static_key_false(&tracepoint_printk_key.key))
output_printk(fbuffer);
- event_trigger_unlock_commit(fbuffer->trace_file, fbuffer->buffer,
+ if (static_branch_unlikely(&trace_event_exports_enabled))
+ ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT);
+ event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer,
fbuffer->event, fbuffer->entry,
- fbuffer->flags, fbuffer->pc);
+ fbuffer->trace_ctx, fbuffer->regs);
}
EXPORT_SYMBOL_GPL(trace_event_buffer_commit);
@@ -2418,9 +2904,9 @@
# 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);
@@ -2431,155 +2917,31 @@
* 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(tr, 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);
-}
-
-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 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;
event = __trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
- flags, pc);
+ trace_ctx);
if (!event)
return;
entry = ring_buffer_event_data(event);
@@ -2587,35 +2949,41 @@
entry->parent_ip = parent_ip;
if (!call_filter_check_discard(call, entry, buffer, event)) {
- if (static_branch_unlikely(&ftrace_exports_enabled))
- ftrace_exports(event);
+ 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 (PAGE_SIZE / FTRACE_KSTACK_NESTING)
+
struct ftrace_stack {
- unsigned long calls[FTRACE_STACK_MAX_ENTRIES];
+ unsigned long calls[FTRACE_KSTACK_ENTRIES];
};
-static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+
+struct ftrace_stacks {
+ struct ftrace_stack stacks[FTRACE_KSTACK_NESTING];
+};
+
+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_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()
@@ -2623,65 +2991,46 @@
*/
#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();
- use_stack = __this_cpu_inc_return(ftrace_stack_reserve);
+ 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;
+
/*
- * 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);
-
+ size = nr_entries * sizeof(unsigned long);
event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
(sizeof(*entry) - sizeof(entry->caller)) + size,
- flags, pc);
+ 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;
+ memcpy(&entry->caller, fstack->calls, size);
+ entry->size = nr_entries;
if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
@@ -2695,23 +3044,23 @@
}
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))
return;
- __ftrace_trace_stack(buffer, flags, skip, pc, regs);
+ __ftrace_trace_stack(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(buffer, trace_ctx, skip, NULL);
return;
}
@@ -2725,7 +3074,7 @@
return;
rcu_irq_enter_irqson();
- __ftrace_trace_stack(buffer, flags, skip, pc, NULL);
+ __ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
rcu_irq_exit_irqson();
}
@@ -2735,31 +3084,28 @@
*/
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(global_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
+static void
ftrace_trace_userstack(struct trace_array *tr,
- struct ring_buffer *buffer, unsigned long flags, int pc)
+ 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 (!(tr->trace_flags & TRACE_ITER_USERSTACKTRACE))
return;
@@ -2782,7 +3128,7 @@
__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);
@@ -2790,12 +3136,7 @@
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);
+ stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES);
if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
@@ -2804,13 +3145,13 @@
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 */
@@ -2851,8 +3192,11 @@
{
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;
@@ -2897,9 +3241,10 @@
* 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)
{
@@ -2922,18 +3267,20 @@
/**
* 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_buffer *buffer;
struct trace_array *tr = &global_trace;
struct bprint_entry *entry;
- unsigned long flags;
+ unsigned int trace_ctx;
char *tbuffer;
- int len = 0, size, pc;
+ int len = 0, size;
if (unlikely(tracing_selftest_running || tracing_disabled))
return 0;
@@ -2941,7 +3288,7 @@
/* Don't pollute graph traces with trace_vprintk internals */
pause_graph_tracing();
- pc = preempt_count();
+ trace_ctx = tracing_gen_ctx();
preempt_disable_notrace();
tbuffer = get_trace_buf();
@@ -2953,13 +3300,13 @@
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;
+ buffer = tr->array_buffer.buffer;
+ ring_buffer_nest_start(buffer);
event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
- flags, pc);
+ trace_ctx);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
@@ -2969,10 +3316,12 @@
memcpy(entry->buf, tbuffer, sizeof(u32) * len);
if (!call_filter_check_discard(call, entry, buffer, event)) {
__buffer_unlock_commit(buffer, event);
- ftrace_trace_stack(tr, buffer, flags, 6, pc, NULL);
+ ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
}
out:
+ ring_buffer_nest_end(buffer);
+out_put:
put_trace_buf();
out_nobuffer:
@@ -2985,14 +3334,14 @@
__printf(3, 0)
static int
-__trace_array_vprintk(struct ring_buffer *buffer,
+__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)
@@ -3001,7 +3350,7 @@
/* Don't pollute graph traces with trace_vprintk internals */
pause_graph_tracing();
- pc = preempt_count();
+ trace_ctx = tracing_gen_ctx();
preempt_disable_notrace();
@@ -3013,10 +3362,10 @@
len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);
- local_save_flags(flags);
size = sizeof(*entry) + len + 1;
+ ring_buffer_nest_start(buffer);
event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
- flags, pc);
+ trace_ctx);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
@@ -3025,10 +3374,11 @@
memcpy(&entry->buf, tbuffer, len + 1);
if (!call_filter_check_discard(call, entry, buffer, event)) {
__buffer_unlock_commit(buffer, event);
- ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL);
+ ftrace_trace_stack(&global_trace, buffer, trace_ctx, 6, NULL);
}
out:
+ ring_buffer_nest_end(buffer);
put_trace_buf();
out_nobuffer:
@@ -3042,9 +3392,29 @@
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);
+ return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args);
}
+/**
+ * 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 encorporated 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.
+ */
__printf(3, 0)
int trace_array_printk(struct trace_array *tr,
unsigned long ip, const char *fmt, ...)
@@ -3052,20 +3422,46 @@
int ret;
va_list ap;
- if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
- return 0;
-
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);
ret = trace_array_vprintk(tr, ip, fmt, ap);
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;
@@ -3093,7 +3489,7 @@
iter->idx++;
if (buf_iter)
- ring_buffer_read(buf_iter, NULL);
+ ring_buffer_iter_advance(buf_iter);
}
static struct trace_entry *
@@ -3103,11 +3499,15 @@
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);
@@ -3121,7 +3521,7 @@
__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;
@@ -3177,11 +3577,53 @@
return next;
}
+#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 */
@@ -3198,7 +3640,7 @@
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);
}
@@ -3231,12 +3673,11 @@
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)
@@ -3249,14 +3690,14 @@
* 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);
}
- per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries;
+ per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries;
}
/*
@@ -3335,49 +3776,84 @@
}
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"
- "# || / _-----=> need-resched_lazy \n"
- "# ||| / _----=> hardirq/softirq \n"
- "# |||| / _---=> preempt-depth \n"
- "# ||||| / _--=> preempt-lazy-depth\n"
- "# |||||| / _-=> migrate-disable \n"
- "# ||||||| / delay \n"
- "# cmd pid |||||||| time | caller \n"
- "# \\ / |||||||| \\ | / \n");
+ seq_puts(m, "# _--------=> CPU# \n"
+ "# / _-------=> irqs-off \n"
+ "# | / _------=> need-resched \n"
+ "# || / _-----=> need-resched-lazy\n"
+ "# ||| / _----=> hardirq/softirq \n"
+ "# |||| / _---=> preempt-depth \n"
+ "# ||||| / _--=> preempt-lazy-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;
@@ -3388,49 +3864,43 @@
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;
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[] = " ";
+ const char *space = " ";
+ int prec = tgid ? 12 : 2;
print_event_info(buf, m);
- 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| / _---=> need-resched_lazy\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);
+ seq_printf(m, "# %.*s _-------=> irqs-off\n", prec, space);
+ seq_printf(m, "# %.*s / _------=> need-resched\n", prec, space);
+ seq_printf(m, "# %.*s| / _-----=> need-resched-lazy\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|||| / _--=> preempt-lazy-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;
@@ -3457,6 +3927,8 @@
"desktop",
#elif defined(CONFIG_PREEMPT)
"preempt",
+#elif defined(CONFIG_PREEMPT_RT)
+ "preempt_rt",
#else
"unknown",
#endif
@@ -3503,7 +3975,7 @@
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))
@@ -3637,7 +4109,7 @@
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;
@@ -3649,7 +4121,7 @@
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;
}
}
@@ -3665,8 +4137,12 @@
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;
}
@@ -3739,10 +4215,10 @@
} else {
if (!(trace_flags & TRACE_ITER_VERBOSE)) {
if (trace_flags & TRACE_ITER_IRQ_INFO)
- print_func_help_header_irq(iter->trace_buffer,
+ 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);
}
}
@@ -3882,6 +4358,18 @@
goto release;
/*
+ * 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.
+ */
+ iter->temp = kmalloc(128, GFP_KERNEL);
+ if (iter->temp)
+ iter->temp_size = 128;
+
+ /*
* We make a copy of the current tracer to avoid concurrent
* changes on it while we are reading.
*/
@@ -3900,35 +4388,38 @@
#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))
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,
+ ring_buffer_read_prepare(iter->array_buffer->buffer,
cpu, GFP_KERNEL);
}
ring_buffer_read_prepare_sync();
@@ -3939,7 +4430,7 @@
} else {
cpu = iter->cpu_file;
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->trace_buffer->buffer,
+ ring_buffer_read_prepare(iter->array_buffer->buffer,
cpu, GFP_KERNEL);
ring_buffer_read_prepare_sync();
ring_buffer_read_start(iter->buffer_iter[cpu]);
@@ -3953,6 +4444,7 @@
fail:
mutex_unlock(&trace_types_lock);
kfree(iter->trace);
+ kfree(iter->temp);
kfree(iter->buffer_iter);
release:
seq_release_private(inode, file);
@@ -3961,8 +4453,11 @@
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;
@@ -3977,15 +4472,14 @@
* 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;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
filp->private_data = inode->i_private;
@@ -4016,7 +4510,7 @@
if (iter->trace && iter->trace->close)
iter->trace->close(iter);
- if (!iter->snapshot)
+ if (!iter->snapshot && tr->stop_count)
/* reenable tracing if it was previously enabled */
tracing_start_tr(tr);
@@ -4026,6 +4520,7 @@
mutex_destroy(&iter->mutex);
free_cpumask_var(iter->started);
+ kfree(iter->temp);
kfree(iter->trace);
kfree(iter->buffer_iter);
seq_release_private(inode, file);
@@ -4054,15 +4549,16 @@
{
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)
@@ -4072,7 +4568,7 @@
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) {
@@ -4173,11 +4669,9 @@
struct seq_file *m;
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 = seq_open(file, &show_traces_seq_ops);
if (ret) {
@@ -4261,20 +4755,13 @@
return count;
}
-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;
+ int cpu;
- if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
- return -ENOMEM;
-
- 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);
@@ -4285,24 +4772,47 @@
*/
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);
+ atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled);
+ ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu);
}
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);
+ atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled);
+ ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu);
}
}
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 (!alloc_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;
@@ -4444,7 +4954,7 @@
ftrace_pid_follow_fork(tr, enabled);
if (mask == TRACE_ITER_OVERWRITE) {
- ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled);
+ ring_buffer_change_overwrite(tr->array_buffer.buffer, enabled);
#ifdef CONFIG_TRACER_MAX_TRACE
ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled);
#endif
@@ -4458,19 +4968,21 @@
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;
int ret;
size_t orig_len = strlen(option);
+ int len;
cmp = strstrip(option);
- if (strncmp(cmp, "no", 2) == 0) {
+ len = str_has_prefix(cmp, "no");
+ if (len)
neg = 1;
- cmp += 2;
- }
+
+ cmp += len;
mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
@@ -4546,11 +5058,9 @@
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)
@@ -4577,6 +5087,7 @@
" 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"
@@ -4597,7 +5108,7 @@
" 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
@@ -4641,6 +5152,8 @@
#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"
@@ -4662,31 +5175,49 @@
"\t\t\t traces\n"
#endif
#endif /* CONFIG_STACK_TRACER */
+#ifdef CONFIG_DYNAMIC_EVENTS
+ " 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)
"\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"
+#ifdef CONFIG_HIST_TRIGGERS
+ "\t s:[synthetic/]<event> <field> [<field>]\n"
+#endif
"\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
- "\t place: <path>:<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 $stack<index>, $stack, $retval, $comm\n"
- "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string,\n"
- "\t b<bit-width>@<bit-offset>/<container-size>\n"
+#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
+ "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
+#else
+ "\t $stack<index>, $stack, $retval, $comm,\n"
+#endif
+ "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n"
+ "\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>, ustring,\n"
+ "\t <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
#endif
" events/\t\t- Directory containing all trace event subsystems:\n"
" enable\t\t- Write 0/1 to enable/disable tracing of all events\n"
@@ -4739,6 +5270,7 @@
"\t [:size=#entries]\n"
"\t [:pause][:continue][:clear]\n"
"\t [:name=histname1]\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"
@@ -4783,8 +5315,26 @@
"\t unchanged.\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[]' >> synthetic_events\n"
+#endif
#endif
;
@@ -4842,8 +5392,11 @@
static int tracing_saved_tgids_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_saved_tgids_seq_ops);
}
@@ -4919,8 +5472,11 @@
static int tracing_saved_cmdlines_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_saved_cmdlines_seq_ops);
}
@@ -4939,9 +5495,11 @@
char buf[64];
int r;
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@@ -4966,10 +5524,12 @@
return -ENOMEM;
}
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
savedcmd_temp = savedcmd;
savedcmd = s;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
free_saved_cmdlines_buffer(savedcmd_temp);
return 0;
@@ -5028,14 +5588,12 @@
* 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;
@@ -5084,8 +5642,11 @@
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);
}
@@ -5198,11 +5759,11 @@
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;
@@ -5212,8 +5773,8 @@
#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;
@@ -5251,10 +5812,10 @@
ring_buffer_expanded = true;
/* 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);
+ ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu);
if (ret < 0)
return ret;
@@ -5265,8 +5826,8 @@
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
@@ -5297,15 +5858,15 @@
#endif /* CONFIG_TRACER_MAX_TRACE */
if (cpu == RING_BUFFER_ALL_CPUS)
- set_buffer_entries(&tr->trace_buffer, size);
+ set_buffer_entries(&tr->array_buffer, size);
else
- per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size;
+ per_cpu_ptr(tr->array_buffer.data, cpu)->entries = size;
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;
@@ -5375,16 +5936,22 @@
tr->current_trace = &nop_trace;
}
+static bool tracer_options_updated;
+
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;
+ /* Only create trace option files after update_tracer_options finish */
+ if (!tracer_options_updated)
+ return;
+
create_trace_option_files(tr, t);
}
-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;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -5413,6 +5980,18 @@
if (t == tr->current_trace)
goto out;
+#ifdef CONFIG_TRACER_SNAPSHOT
+ if (t->use_max_tr) {
+ local_irq_disable();
+ arch_spin_lock(&tr->max_lock);
+ if (tr->cond_snapshot)
+ ret = -EBUSY;
+ arch_spin_unlock(&tr->max_lock);
+ local_irq_enable();
+ if (ret)
+ goto out;
+ }
+#endif
/* Some tracers won't work on kernel command line */
if (system_state < SYSTEM_RUNNING && t->noboot) {
pr_warn("Tracer '%s' is not allowed on command line, ignored\n",
@@ -5427,7 +6006,7 @@
}
/* If trace pipe files are being read, we can't change the tracer */
- if (tr->current_trace->ref) {
+ if (tr->trace_ref) {
ret = -EBUSY;
goto out;
}
@@ -5439,11 +6018,11 @@
if (tr->current_trace->reset)
tr->current_trace->reset(tr);
- /* Current trace needs to be nop_trace before synchronize_sched */
- tr->current_trace = &nop_trace;
-
#ifdef CONFIG_TRACER_MAX_TRACE
- had_max_tr = tr->allocated_snapshot;
+ had_max_tr = tr->current_trace->use_max_tr;
+
+ /* Current trace needs to be nop_trace before synchronize_rcu */
+ tr->current_trace = &nop_trace;
if (had_max_tr && !t->use_max_tr) {
/*
@@ -5453,17 +6032,17 @@
* The update_max_tr is called from interrupts disabled
* so a synchronized_sched() is sufficient.
*/
- synchronize_sched();
+ synchronize_rcu();
free_snapshot(tr);
}
-#endif
-#ifdef CONFIG_TRACER_MAX_TRACE
- if (t->use_max_tr && !had_max_tr) {
+ if (t->use_max_tr && !tr->allocated_snapshot) {
ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
goto out;
}
+#else
+ tr->current_trace = &nop_trace;
#endif
if (t->init) {
@@ -5598,13 +6177,11 @@
{
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
- int ret = 0;
+ 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;
mutex_lock(&trace_types_lock);
@@ -5635,7 +6212,7 @@
iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
iter->tr = tr;
- iter->trace_buffer = &tr->trace_buffer;
+ iter->array_buffer = &tr->array_buffer;
iter->cpu_file = tracing_get_cpu(inode);
mutex_init(&iter->mutex);
filp->private_data = iter;
@@ -5645,7 +6222,7 @@
nonseekable_open(inode, filp);
- tr->current_trace->ref++;
+ tr->trace_ref++;
out:
mutex_unlock(&trace_types_lock);
return ret;
@@ -5664,7 +6241,7 @@
mutex_lock(&trace_types_lock);
- tr->current_trace->ref--;
+ tr->trace_ref--;
if (iter->trace->pipe_close)
iter->trace->pipe_close(iter);
@@ -5695,8 +6272,8 @@
*/
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
@@ -5733,7 +6310,7 @@
mutex_unlock(&iter->mutex);
- ret = wait_on_pipe(iter, false);
+ ret = wait_on_pipe(iter, 0);
mutex_lock(&iter->mutex);
@@ -5849,14 +6426,6 @@
__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)
{
@@ -5918,7 +6487,7 @@
.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;
@@ -6013,8 +6582,8 @@
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;
}
@@ -6030,7 +6599,7 @@
} 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);
@@ -6077,7 +6646,7 @@
mutex_lock(&trace_types_lock);
for_each_tracing_cpu(cpu) {
- size += per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10;
+ size += per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10;
if (!ring_buffer_expanded)
expanded_size += trace_buf_size >> 10;
}
@@ -6127,16 +6696,15 @@
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>";
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 */
+#define FAULTED_STR "<faulted>"
+#define FAULTED_SIZE (sizeof(FAULTED_STR) - 1) /* '\0' is already accounted for */
if (tracing_disabled)
return -EINVAL;
@@ -6149,16 +6717,15 @@
BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
- local_save_flags(irq_flags);
size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */
/* If less than "<faulted>", then make sure we can still add that */
if (cnt < FAULTED_SIZE)
size += FAULTED_SIZE - cnt;
- buffer = tr->trace_buffer.buffer;
+ buffer = tr->array_buffer.buffer;
event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
- irq_flags, preempt_count());
+ tracing_gen_ctx());
if (unlikely(!event))
/* Ring buffer disabled, return as if not open for write */
return -EBADF;
@@ -6168,12 +6735,11 @@
len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt);
if (len) {
- memcpy(&entry->buf, faulted, FAULTED_SIZE);
+ memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
cnt = FAULTED_SIZE;
written = -EFAULT;
} else
written = cnt;
- len = cnt;
if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) {
/* do not add \n before testing triggers, but add \0 */
@@ -6187,6 +6753,8 @@
} 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)
@@ -6207,10 +6775,8 @@
{
struct trace_array *tr = filp->private_data;
struct ring_buffer_event *event;
- struct ring_buffer *buffer;
+ struct trace_buffer *buffer;
struct raw_data_entry *entry;
- const char faulted[] = "<faulted>";
- unsigned long irq_flags;
ssize_t written;
int size;
int len;
@@ -6232,14 +6798,13 @@
BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
- local_save_flags(irq_flags);
size = sizeof(*entry) + cnt;
if (cnt < FAULT_SIZE_ID)
size += FAULT_SIZE_ID - cnt;
- buffer = tr->trace_buffer.buffer;
+ buffer = tr->array_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;
@@ -6249,7 +6814,7 @@
len = __copy_from_user_inatomic(&entry->id, ubuf, cnt);
if (len) {
entry->id = -1;
- memcpy(&entry->buf, faulted, FAULTED_SIZE);
+ memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
written = -EFAULT;
} else
written = cnt;
@@ -6292,13 +6857,13 @@
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)
@@ -6344,11 +6909,9 @@
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)
@@ -6363,7 +6926,7 @@
mutex_lock(&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");
@@ -6378,11 +6941,9 @@
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)
@@ -6410,7 +6971,7 @@
goto out;
}
- ring_buffer_set_time_stamp_abs(tr->trace_buffer.buffer, abs);
+ ring_buffer_set_time_stamp_abs(tr->array_buffer.buffer, abs);
#ifdef CONFIG_TRACER_MAX_TRACE
if (tr->max_buffer.buffer)
@@ -6435,10 +6996,11 @@
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);
@@ -6458,7 +7020,7 @@
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;
@@ -6495,6 +7057,15 @@
goto out;
}
+ local_irq_disable();
+ arch_spin_lock(&tr->max_lock);
+ if (tr->cond_snapshot)
+ ret = -EBUSY;
+ arch_spin_unlock(&tr->max_lock);
+ local_irq_enable();
+ if (ret)
+ goto out;
+
switch (val) {
case 0:
if (iter->cpu_file != RING_BUFFER_ALL_CPUS) {
@@ -6514,7 +7085,7 @@
#endif
if (tr->allocated_snapshot)
ret = resize_buffer_duplicate_size(&tr->max_buffer,
- &tr->trace_buffer, iter->cpu_file);
+ &tr->array_buffer, iter->cpu_file);
else
ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
@@ -6522,7 +7093,7 @@
local_irq_disable();
/* Now, we're going to swap */
if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
- update_max_tr(tr, current, smp_processor_id());
+ update_max_tr(tr, current, smp_processor_id(), NULL);
else
update_max_tr_single(tr, current, iter->cpu_file);
local_irq_enable();
@@ -6532,7 +7103,7 @@
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;
}
@@ -6576,6 +7147,7 @@
struct ftrace_buffer_info *info;
int ret;
+ /* The following checks for tracefs lockdown */
ret = tracing_buffers_open(inode, filp);
if (ret < 0)
return ret;
@@ -6588,7 +7160,7 @@
}
info->iter.snapshot = true;
- info->iter.trace_buffer = &info->iter.tr->max_buffer;
+ info->iter.array_buffer = &info->iter.tr->max_buffer;
return ret;
}
@@ -6697,19 +7269,263 @@
#endif /* CONFIG_TRACER_SNAPSHOT */
+#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 */
+ u8 pos; /* MAX_FILTER_STR_VAL = 256 */
+ u64 ts;
+};
+
+struct tracing_log_err {
+ struct list_head list;
+ struct err_info info;
+ char loc[TRACING_LOG_LOC_MAX]; /* err location */
+ char cmd[MAX_FILTER_STR_VAL]; /* what caused err */
+};
+
+static DEFINE_MUTEX(tracing_err_log_lock);
+
+static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
+{
+ struct tracing_log_err *err;
+
+ if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) {
+ err = kzalloc(sizeof(*err), GFP_KERNEL);
+ if (!err)
+ err = ERR_PTR(-ENOMEM);
+ else
+ tr->n_err_log_entries++;
+
+ return err;
+ }
+
+ err = list_first_entry(&tr->err_log, struct tracing_log_err, list);
+ 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 occurence 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 occurence 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, u8 pos)
+{
+ struct tracing_log_err *err;
+
+ if (!tr)
+ tr = &global_trace;
+
+ mutex_lock(&tracing_err_log_lock);
+ err = get_tracing_log_err(tr);
+ if (PTR_ERR(err) == -ENOMEM) {
+ mutex_unlock(&tracing_err_log_lock);
+ return;
+ }
+
+ snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc);
+ snprintf(err->cmd, MAX_FILTER_STR_VAL,"\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);
+ mutex_unlock(&tracing_err_log_lock);
+}
+
+static void clear_tracing_err_log(struct trace_array *tr)
+{
+ struct tracing_log_err *err, *next;
+
+ mutex_lock(&tracing_err_log_lock);
+ list_for_each_entry_safe(err, next, &tr->err_log, list) {
+ list_del(&err->list);
+ kfree(err);
+ }
+
+ tr->n_err_log_entries = 0;
+ mutex_unlock(&tracing_err_log_lock);
+}
+
+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, u8 pos)
+{
+ u8 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 = seq_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;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
-
- info = kzalloc(sizeof(*info), GFP_KERNEL);
+ info = kvzalloc(sizeof(*info), GFP_KERNEL);
if (!info) {
trace_array_put(tr);
return -ENOMEM;
@@ -6720,14 +7536,14 @@
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);
@@ -6765,7 +7581,7 @@
#endif
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);
@@ -6783,7 +7599,7 @@
again:
trace_access_lock(iter->cpu_file);
- ret = ring_buffer_read_page(iter->trace_buffer->buffer,
+ ret = ring_buffer_read_page(iter->array_buffer->buffer,
&info->spare,
count,
iter->cpu_file, 0);
@@ -6794,7 +7610,7 @@
if ((filp->f_flags & O_NONBLOCK))
return -EAGAIN;
- ret = wait_on_pipe(iter, false);
+ ret = wait_on_pipe(iter, 0);
if (ret)
return ret;
@@ -6828,14 +7644,14 @@
mutex_lock(&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);
+ kvfree(info);
mutex_unlock(&trace_types_lock);
@@ -6843,7 +7659,7 @@
}
struct buffer_ref {
- struct ring_buffer *buffer;
+ struct trace_buffer *buffer;
void *page;
int cpu;
refcount_t refcount;
@@ -6880,10 +7696,7 @@
/* 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_nosteal,
.get = buffer_pipe_buf_get,
};
@@ -6939,7 +7752,7 @@
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) {
struct page *page;
@@ -6952,7 +7765,7 @@
}
refcount_set(&ref->refcount, 1);
- ref->buffer = iter->trace_buffer->buffer;
+ 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);
@@ -6980,7 +7793,7 @@
spd.nr_pages++;
*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);
@@ -6995,7 +7808,7 @@
if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
goto out;
- ret = wait_on_pipe(iter, true);
+ ret = wait_on_pipe(iter, iter->tr->buffer_percent);
if (ret)
goto out;
@@ -7024,7 +7837,7 @@
{
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;
@@ -7095,14 +7908,23 @@
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';
+ /* 256 should be plenty to hold the amount needed */
+ buf = kmalloc(256, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
- return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+ r = scnprintf(buf, 256, "%ld pages:%ld groups: %ld\n",
+ ftrace_update_tot_cnt,
+ ftrace_number_of_pages,
+ ftrace_number_of_groups);
+
+ ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+ kfree(buf);
+ return ret;
}
static const struct file_operations tracing_dyn_info_fops = {
@@ -7296,7 +8118,7 @@
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;
@@ -7617,7 +8439,7 @@
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);
}
@@ -7674,7 +8496,7 @@
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;
@@ -7711,13 +8533,60 @@
.llseek = default_llseek,
};
-struct dentry *trace_instance_dir;
+static ssize_t
+buffer_percent_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct trace_array *tr = filp->private_data;
+ char buf[64];
+ int r;
+
+ r = tr->buffer_percent;
+ r = sprintf(buf, "%d\n", r);
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+buffer_percent_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct trace_array *tr = filp->private_data;
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+ if (ret)
+ return ret;
+
+ if (val > 100)
+ return -EINVAL;
+
+ if (!val)
+ val = 1;
+
+ tr->buffer_percent = val;
+
+ (*ppos)++;
+
+ return cnt;
+}
+
+static const struct file_operations buffer_percent_fops = {
+ .open = tracing_open_generic_tr,
+ .read = buffer_percent_read,
+ .write = buffer_percent_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);
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;
@@ -7737,8 +8606,8 @@
}
/* 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;
}
@@ -7747,18 +8616,18 @@
{
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
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")) {
+ ring_buffer_free(tr->array_buffer.buffer);
+ tr->array_buffer.buffer = NULL;
+ free_percpu(tr->array_buffer.data);
+ tr->array_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
@@ -7770,22 +8639,10 @@
allocate_snapshot = false;
#endif
- /*
- * Because of some magic with the way alloc_percpu() works on
- * x86_64, we need to synchronize the pgd of all the tables,
- * otherwise the trace events that happen in x86_64 page fault
- * handlers can't cope with accessing the chance that a
- * alloc_percpu()'d memory might be touched in the page fault trace
- * event. Oh, and we need to audit all other alloc_percpu() and vmalloc()
- * calls in tracing, because something might get triggered within a
- * page fault trace event!
- */
- vmalloc_sync_mappings();
-
return 0;
}
-static void free_trace_buffer(struct trace_buffer *buf)
+static void free_trace_buffer(struct array_buffer *buf)
{
if (buf->buffer) {
ring_buffer_free(buf->buffer);
@@ -7800,7 +8657,7 @@
if (!tr)
return;
- free_trace_buffer(&tr->trace_buffer);
+ free_trace_buffer(&tr->array_buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
free_trace_buffer(&tr->max_buffer);
@@ -7827,28 +8684,68 @@
static void update_tracer_options(struct trace_array *tr)
{
mutex_lock(&trace_types_lock);
+ tracer_options_updated = true;
__update_tracer_options(tr);
mutex_unlock(&trace_types_lock);
}
-static int instance_mkdir(const char *name)
+/* Must have trace_types_lock held */
+struct trace_array *trace_array_find(const char *instance)
+{
+ struct trace_array *tr, *found = NULL;
+
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ 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;
+
+ mutex_lock(&trace_types_lock);
+ tr = trace_array_find(instance);
+ if (tr)
+ tr->ref++;
+ mutex_unlock(&trace_types_lock);
+
+ 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);
+ __update_tracer_options(tr);
+
+ return ret;
+}
+
+static struct trace_array *trace_array_create(const char *name)
{
struct trace_array *tr;
int ret;
- mutex_lock(&event_mutex);
- mutex_lock(&trace_types_lock);
-
- ret = -EEXIST;
- list_for_each_entry(tr, &ftrace_trace_arrays, list) {
- if (tr->name && strcmp(tr->name, name) == 0)
- goto out_unlock;
- }
-
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)
@@ -7870,70 +8767,112 @@
INIT_LIST_HEAD(&tr->systems);
INIT_LIST_HEAD(&tr->events);
INIT_LIST_HEAD(&tr->hist_vars);
+ INIT_LIST_HEAD(&tr->err_log);
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)
+ if (ftrace_allocate_ftrace_ops(tr) < 0)
goto out_free_tr;
-
- ret = event_trace_add_tracer(tr->dir, tr);
- if (ret) {
- tracefs_remove_recursive(tr->dir);
- 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->tracing_cpumask);
kfree(tr->name);
kfree(tr);
- out_unlock:
- mutex_unlock(&trace_types_lock);
- mutex_unlock(&event_mutex);
-
- return ret;
-
+ return ERR_PTR(ret);
}
-static int instance_rmdir(const char *name)
+static int instance_mkdir(const char *name)
{
struct trace_array *tr;
- int found = 0;
int ret;
- int i;
mutex_lock(&event_mutex);
mutex_lock(&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;
- }
- }
- if (!found)
+ ret = -EEXIST;
+ if (trace_array_find(name))
goto out_unlock;
- ret = -EBUSY;
- if (tr->ref || (tr->current_trace && tr->current_trace->ref))
- goto out_unlock;
+ tr = trace_array_create(name);
+
+ ret = PTR_ERR_OR_ZERO(tr);
+
+out_unlock:
+ mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
+ return ret;
+}
+
+/**
+ * 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.
+ *
+ * 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)
+{
+ struct trace_array *tr;
+
+ mutex_lock(&event_mutex);
+ mutex_lock(&trace_types_lock);
+
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (tr->name && strcmp(tr->name, name) == 0)
+ goto out_unlock;
+ }
+
+ tr = trace_array_create(name);
+
+ if (IS_ERR(tr))
+ tr = NULL;
+out_unlock:
+ if (tr)
+ tr->ref++;
+
+ mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
+ 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);
@@ -7948,7 +8887,7 @@
event_trace_del_tracer(tr);
ftrace_clear_pids(tr);
ftrace_destroy_function_files(tr);
- tracefs_remove_recursive(tr->dir);
+ tracefs_remove(tr->dir);
free_trace_buffers(tr);
for (i = 0; i < tr->nr_topts; i++) {
@@ -7960,9 +8899,50 @@
kfree(tr->name);
kfree(tr);
- ret = 0;
+ return 0;
+}
- out_unlock:
+int trace_array_destroy(struct trace_array *this_tr)
+{
+ struct trace_array *tr;
+ int ret;
+
+ if (!this_tr)
+ return -EINVAL;
+
+ mutex_lock(&event_mutex);
+ mutex_lock(&trace_types_lock);
+
+ ret = -ENODEV;
+
+ /* Making sure trace array exists before destroying it. */
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (tr == this_tr) {
+ ret = __remove_instance(tr);
+ break;
+ }
+ }
+
+ mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(trace_array_destroy);
+
+static int instance_rmdir(const char *name)
+{
+ struct trace_array *tr;
+ int ret;
+
+ mutex_lock(&event_mutex);
+ mutex_lock(&trace_types_lock);
+
+ ret = -ENODEV;
+ tr = trace_array_find(name);
+ if (tr)
+ ret = __remove_instance(tr);
+
mutex_unlock(&trace_types_lock);
mutex_unlock(&event_mutex);
@@ -7971,11 +8951,27 @@
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;
+
+ mutex_lock(&event_mutex);
+ mutex_lock(&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"))
+ break;
+ }
+
+ mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
}
static void
@@ -8032,20 +9028,27 @@
trace_create_file("timestamp_mode", 0444, d_tracer, tr,
&trace_time_stamp_mode_fops);
+ tr->buffer_percent = 50;
+
+ trace_create_file("buffer_percent", 0444, d_tracer,
+ tr, &buffer_percent_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);
+ 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");
#ifdef CONFIG_TRACER_SNAPSHOT
trace_create_file("snapshot", 0644, d_tracer,
tr, &snapshot_fops);
#endif
+
+ trace_create_file("error_log", 0644, d_tracer,
+ tr, &tracing_err_log_fops);
for_each_tracing_cpu(cpu)
tracing_init_tracefs_percpu(tr, cpu);
@@ -8053,6 +9056,7 @@
ftrace_init_tracefs(tr, d_tracer);
}
+#ifndef CONFIG_TRACEFS_DISABLE_AUTOMOUNT
static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
{
struct vfsmount *mnt;
@@ -8074,6 +9078,7 @@
return mnt;
}
+#endif
/**
* tracing_init_dentry - initialize top level trace array
@@ -8082,19 +9087,23 @@
* 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;
+#ifndef CONFIG_TRACEFS_DISABLE_AUTOMOUNT
/*
* As there may still be users that expect the tracing
* files to exist in debugfs/tracing, we must automount
@@ -8103,12 +9112,11 @@
*/
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);
- }
+#else
+ tr->dir = ERR_PTR(-ENODEV);
+#endif
- return NULL;
+ return 0;
}
extern struct trace_eval_map *__start_ftrace_eval_maps[];
@@ -8184,7 +9192,7 @@
break;
}
- return 0;
+ return NOTIFY_OK;
}
static struct notifier_block trace_module_nb = {
@@ -8195,48 +9203,48 @@
static __init int tracer_init_tracefs(void)
{
- struct dentry *d_tracer;
+ int ret;
trace_access_lock_init();
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
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", 0644, NULL,
&global_trace, &tracing_thresh_fops);
- trace_create_file("README", 0444, d_tracer,
+ trace_create_file("README", 0444, NULL,
NULL, &tracing_readme_fops);
- trace_create_file("saved_cmdlines", 0444, d_tracer,
+ trace_create_file("saved_cmdlines", 0444, NULL,
NULL, &tracing_saved_cmdlines_fops);
- trace_create_file("saved_cmdlines_size", 0644, d_tracer,
+ trace_create_file("saved_cmdlines_size", 0644, NULL,
NULL, &tracing_saved_cmdlines_size_fops);
- trace_create_file("saved_tgids", 0444, d_tracer,
+ trace_create_file("saved_tgids", 0444, 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", 0444, NULL,
+ NULL, &tracing_dyn_info_fops);
#endif
- create_trace_instances(d_tracer);
+ create_trace_instances(NULL);
update_tracer_options(&global_trace);
@@ -8246,8 +9254,17 @@
static int trace_panic_handler(struct notifier_block *this,
unsigned long event, void *unused)
{
+ bool ftrace_check = false;
+
+ trace_android_vh_ftrace_oops_enter(&ftrace_check);
+
+ if (ftrace_check)
+ return NOTIFY_OK;
+
if (ftrace_dump_on_oops)
ftrace_dump(ftrace_dump_on_oops);
+
+ trace_android_vh_ftrace_oops_exit(&ftrace_check);
return NOTIFY_OK;
}
@@ -8261,6 +9278,13 @@
unsigned long val,
void *data)
{
+ bool ftrace_check = false;
+
+ trace_android_vh_ftrace_oops_enter(&ftrace_check);
+
+ if (ftrace_check)
+ return NOTIFY_OK;
+
switch (val) {
case DIE_OOPS:
if (ftrace_dump_on_oops)
@@ -8269,6 +9293,8 @@
default:
break;
}
+
+ trace_android_vh_ftrace_oops_exit(&ftrace_check);
return NOTIFY_OK;
}
@@ -8293,6 +9319,8 @@
void
trace_printk_seq(struct trace_seq *s)
{
+ bool dump_printk = true;
+
/* Probably should print a warning here. */
if (s->seq.len >= TRACE_MAX_PRINT)
s->seq.len = TRACE_MAX_PRINT;
@@ -8308,7 +9336,9 @@
/* should be zero ended, but we are paranoid. */
s->buffer[s->seq.len] = 0;
- printk(KERN_TRACE "%s", s->buffer);
+ trace_android_vh_ftrace_dump_buffer(s, &dump_printk);
+ if (dump_printk)
+ printk(KERN_TRACE "%s", s->buffer);
trace_seq_init(s);
}
@@ -8318,13 +9348,13 @@
iter->tr = &global_trace;
iter->trace = iter->tr->current_trace;
iter->cpu_file = RING_BUFFER_ALL_CPUS;
- iter->trace_buffer = &global_trace.trace_buffer;
+ iter->array_buffer = &global_trace.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. */
@@ -8341,6 +9371,8 @@
unsigned int old_userobj;
unsigned long flags;
int cnt = 0, cpu;
+ bool ftrace_check = false;
+ unsigned long size;
/* Only allow one dump user at a time. */
if (atomic_inc_return(&dump_running) != 1) {
@@ -8359,19 +9391,26 @@
tracing_off();
local_irq_save(flags);
- printk_nmi_direct_enter();
/* Simulate the iterator */
trace_init_global_iter(&iter);
+ /* Can not use kmalloc for iter.temp */
+ iter.temp = static_temp_buf;
+ iter.temp_size = STATIC_TEMP_BUF_SIZE;
for_each_tracing_cpu(cpu) {
- atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
+ atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
+ size = ring_buffer_size(iter.array_buffer->buffer, cpu);
+ trace_android_vh_ftrace_size_check(size, &ftrace_check);
}
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;
+
+ if (ftrace_check)
+ goto out_enable;
switch (oops_dump_mode) {
case DUMP_ALL:
@@ -8396,13 +9435,14 @@
}
/*
- * 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.
*/
while (!trace_empty(&iter)) {
+ ftrace_check = true;
if (!cnt)
printk(KERN_TRACE "---------------------------------\n");
@@ -8410,7 +9450,9 @@
cnt++;
trace_iterator_reset(&iter);
- iter.iter_flags |= TRACE_FILE_LAT_FMT;
+ trace_android_vh_ftrace_format_check(&ftrace_check);
+ if (ftrace_check)
+ iter.iter_flags |= TRACE_FILE_LAT_FMT;
if (trace_find_next_entry_inc(&iter) != NULL) {
int ret;
@@ -8433,10 +9475,9 @@
tr->trace_flags |= old_userobj;
for_each_tracing_cpu(cpu) {
- atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
+ atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
}
atomic_dec(&dump_running);
- printk_nmi_direct_exit();
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(ftrace_dump);
@@ -8532,8 +9573,14 @@
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);
@@ -8562,7 +9609,7 @@
/*
* 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.
*/
@@ -8582,8 +9629,7 @@
/* 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);
+ MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n");
goto out_free_savedcmd;
}
@@ -8628,6 +9674,7 @@
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.list, &ftrace_trace_arrays);
apply_trace_boot_options();
@@ -8655,7 +9702,8 @@
if (tracepoint_printk) {
tracepoint_print_iter =
kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
- if (WARN_ON(!tracepoint_print_iter))
+ if (MEM_FAIL(!tracepoint_print_iter,
+ "Failed to allocate trace iterator\n"))
tracepoint_printk = 0;
else
static_key_enable(&tracepoint_printk_key.key);
@@ -8695,6 +9743,11 @@
{
/* 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 -EPERM;
+ }
+
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"
--
Gitblit v1.6.2