1 files changed, 90 insertions, 53 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4509cf51fbfd..a0c54d118c4e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -26,6 +26,7 @@
 #include <linux/linkage.h>
 #include <linux/uaccess.h>
 #include <linux/kprobes.h>
+#include <linux/vmalloc.h>
 #include <linux/ftrace.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
@@ -234,6 +235,10 @@ __setup("trace_clock=", set_trace_boot_clock);
 
 static int __init set_tracepoint_printk(char *str)
 {
+	/* Ignore the "tp_printk_stop_on_boot" param */
+	if (*str == '_')
+		return 0;
+
 	if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0))
 		tracepoint_printk = 1;
 	return 1;
@@ -840,10 +845,12 @@ static int __init set_buf_size(char *str)
 	if (!str)
 		return 0;
 	buf_size = memparse(str, &str);
-	/* nr_entries can not be zero */
-	if (buf_size == 0)
-		return 0;
-	trace_buf_size = buf_size;
+	/*
+	 * nr_entries can not be zero and the startup
+	 * tests require some buffer space. Therefore
+	 * ensure we have at least 4096 bytes of buffer.
+	 */
+	trace_buf_size = max(4096UL, buf_size);
 	return 1;
 }
 __setup("trace_buf_size=", set_buf_size);
@@ -1375,9 +1382,6 @@ struct saved_cmdlines_buffer {
 };
 static struct saved_cmdlines_buffer *savedcmd;
 
-/* temporary disable recording */
-static atomic_t trace_record_cmdline_disabled __read_mostly;
-
 static inline char *get_saved_cmdlines(int idx)
 {
 	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
@@ -1579,10 +1583,13 @@ void trace_stop_cmdline_recording(void);
 
 static int trace_save_cmdline(struct task_struct *tsk)
 {
-	unsigned pid, idx;
+	unsigned tpid, idx;
 
-	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
-		return 0;
+	/* treat recording of idle task as a success */
+	if (!tsk->pid)
+		return 1;
+
+	tpid = tsk->pid & (PID_MAX_DEFAULT - 1);
 
 	preempt_disable();
 	/*
@@ -1596,26 +1603,15 @@ static int trace_save_cmdline(struct task_struct *tsk)
 		return 0;
 	}
 
-	idx = savedcmd->map_pid_to_cmdline[tsk->pid];
+	idx = savedcmd->map_pid_to_cmdline[tpid];
 	if (idx == NO_CMDLINE_MAP) {
 		idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;
 
-		/*
-		 * Check whether the cmdline buffer at idx has a pid
-		 * mapped. We are going to overwrite that entry so we
-		 * need to clear the map_pid_to_cmdline. Otherwise we
-		 * would read the new comm for the old pid.
-		 */
-		pid = savedcmd->map_cmdline_to_pid[idx];
-		if (pid != NO_CMDLINE_MAP)
-			savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
-
-		savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
-		savedcmd->map_pid_to_cmdline[tsk->pid] = idx;
-
+		savedcmd->map_pid_to_cmdline[tpid] = idx;
 		savedcmd->cmdline_idx = idx;
 	}
 
+	savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
 	set_cmdline(idx, tsk->comm);
 	savedcmd->map_cmdline_to_tgid[idx] = tsk->tgid;
 	arch_spin_unlock(&trace_cmdline_lock);
@@ -1627,6 +1623,7 @@ static int trace_save_cmdline(struct task_struct *tsk)
 static void __trace_find_cmdline(int pid, char comm[])
 {
 	unsigned map;
+	int tpid;
 
 	if (!pid) {
 		strcpy(comm, "<idle>");
@@ -1638,16 +1635,16 @@ static void __trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
-	if (pid > PID_MAX_DEFAULT) {
-		strcpy(comm, "<...>");
-		return;
+	tpid = pid & (PID_MAX_DEFAULT - 1);
+	map = savedcmd->map_pid_to_cmdline[tpid];
+	if (map != NO_CMDLINE_MAP) {
+		tpid = savedcmd->map_cmdline_to_pid[map];
+		if (tpid == pid) {
+			strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
+			return;
+		}
 	}
-
-	map = savedcmd->map_pid_to_cmdline[pid];
-	if (map != NO_CMDLINE_MAP)
-		strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN - 1);
-	else
-		strcpy(comm, "<...>");
+	strcpy(comm, "<...>");
 }
 
 void trace_find_cmdline(int pid, char comm[])
@@ -1692,9 +1689,6 @@ int trace_find_tgid(int pid)
 
 void tracing_record_cmdline(struct task_struct *tsk)
 {
-	if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on())
-		return;
-
 	if (!__this_cpu_read(trace_cmdline_save))
 		return;
 
@@ -1757,7 +1751,7 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
 	__buffer_unlock_commit(buffer, event);
 
 	ftrace_trace_stack(tr, buffer, flags, 6, pc, NULL);
-	ftrace_trace_userstack(buffer, flags, pc);
+	ftrace_trace_userstack(tr, buffer, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
@@ -1819,7 +1813,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 	 * two. They are that meaningful.
 	 */
 	ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs);
-	ftrace_trace_userstack(buffer, flags, pc);
+	ftrace_trace_userstack(tr, buffer, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
 
@@ -1918,7 +1912,8 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	size *= sizeof(unsigned long);
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
-					  sizeof(*entry) + size, flags, pc);
+				    (sizeof(*entry) - sizeof(entry->caller)) + size,
+				    flags, pc);
 	if (!event)
 		goto out;
 	entry = ring_buffer_event_data(event);
@@ -1992,14 +1987,15 @@ void trace_dump_stack(int skip)
 static DEFINE_PER_CPU(int, user_stack_count);
 
 void
-ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
+ftrace_trace_userstack(struct trace_array *tr,
+		       struct ring_buffer *buffer, unsigned long flags, int pc)
 {
 	struct trace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
 	struct stack_trace trace;
 
-	if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE))
+	if (!(tr->trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
 
 	/*
@@ -2323,6 +2319,9 @@ int trace_array_printk(struct trace_array *tr,
 	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
+	if (!tr)
+		return -ENOENT;
+
 	va_start(ap, fmt);
 	ret = trace_array_vprintk(tr, ip, fmt, ap);
 	va_end(ap);
@@ -2544,8 +2543,15 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	 * will point to the same string as current_trace->name.
 	 */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name))
+	if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) {
+		/* Close iter->trace before switching to the new current tracer */
+		if (iter->trace->close)
+			iter->trace->close(iter);
 		*iter->trace = *tr->current_trace;
+		/* Reopen the new current tracer */
+		if (iter->trace->open)
+			iter->trace->open(iter);
+	}
 	mutex_unlock(&trace_types_lock);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -2553,9 +2559,6 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		return ERR_PTR(-EBUSY);
 #endif
 
-	if (!iter->snapshot)
-		atomic_inc(&trace_record_cmdline_disabled);
-
 	if (*pos != iter->pos) {
 		iter->ent = NULL;
 		iter->cpu = 0;
@@ -2598,9 +2601,6 @@ static void s_stop(struct seq_file *m, void *p)
 		return;
 #endif
 
-	if (!iter->snapshot)
-		atomic_dec(&trace_record_cmdline_disabled);
-
 	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 }
@@ -4550,12 +4550,18 @@ static void tracing_set_nop(struct trace_array *tr)
 	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);
 }
 
@@ -4972,7 +4978,20 @@ waitagain:
 
 		ret = print_trace_line(iter);
 		if (ret == TRACE_TYPE_PARTIAL_LINE) {
-			/* don't print partial lines */
+			/*
+			 * If one print_trace_line() fills entire trace_seq in one shot,
+			 * trace_seq_to_user() will returns -EBUSY because save_len == 0,
+			 * In this case, we need to consume it, otherwise, loop will peek
+			 * this event next time, resulting in an infinite loop.
+			 */
+			if (save_len == 0) {
+				iter->seq.full = 0;
+				trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n");
+				trace_consume(iter);
+				break;
+			}
+
+			/* In other cases, don't print partial lines */
 			iter->seq.seq.len = save_len;
 			break;
 		}
@@ -5910,12 +5929,16 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
 	buf->private = 0;
 }
 
-static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
+static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 				struct pipe_buffer *buf)
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
+	if (ref->ref > INT_MAX/2)
+		return false;
+
 	ref->ref++;
+	return true;
 }
 
 /* Pipe buffer operations for a buffer. */
@@ -6778,6 +6801,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	 */
 	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;
 }
 
@@ -6823,6 +6859,7 @@ static void __update_tracer_options(struct trace_array *tr)
 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);
 }
@@ -7022,7 +7059,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 
 }
 
-static struct vfsmount *trace_automount(void *ingore)
+static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
 {
 	struct vfsmount *mnt;
 	struct file_system_type *type;
@@ -7035,7 +7072,7 @@ static struct vfsmount *trace_automount(void *ingore)
 	type = get_fs_type("tracefs");
 	if (!type)
 		return NULL;
-	mnt = vfs_kern_mount(type, 0, "tracefs", NULL);
+	mnt = vfs_submount(mntpt, type, "tracefs", NULL);
 	put_filesystem(type);
 	if (IS_ERR(mnt))
 		return NULL;
@@ -7420,7 +7457,7 @@ __init static int tracer_alloc_buffers(void)
 		goto out_free_buffer_mask;
 
 	/* Only allocate trace_printk buffers if a trace_printk exists */
-	if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt)
+	if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt)
 		/* Must be called before global_trace.buffer is allocated */
 		trace_printk_init_buffers();