[v6.6][PATCH 39/57] eventfs: Do ctx->pos update for all iterations in eventfs_iterate()

[Steven Rostedt]

From: "Steven Rostedt (Google)" <rostedt@xxxxxxxxxxx>

The ctx->pos was only updated when it added an entry, but the "skip to
current pos" check (c--) happened for every loop regardless of if the
entry was added or not. This inconsistency caused readdir to be incorrect.

It was due to:

	for (i = 0; i < ei->nr_entries; i++) {

		if (c > 0) {
			c--;
			continue;
		}

		mutex_lock(&eventfs_mutex);
		/* If ei->is_freed then just bail here, nothing more to do */
		if (ei->is_freed) {
			mutex_unlock(&eventfs_mutex);
			goto out;
		}
		r = entry->callback(name, &mode, &cdata, &fops);
		mutex_unlock(&eventfs_mutex);

		[..]
		ctx->pos++;
	}

But this can cause the iterator to return a file that was already read.
That's because of the way the callback() works. Some events may not have
all files, and the callback can return 0 to tell eventfs to skip the file
for this directory.

for instance, we have:

 # ls /sys/kernel/tracing/events/ftrace/function
format  hist  hist_debug  id  inject

and

 # ls /sys/kernel/tracing/events/sched/sched_switch/
enable  filter  format  hist  hist_debug  id  inject  trigger

Where the function directory is missing "enable", "filter" and
"trigger". That's because the callback() for events has:

static int event_callback(const char *name, umode_t *mode, void **data,
			  const struct file_operations **fops)
{
	struct trace_event_file *file = *data;
	struct trace_event_call *call = file->event_call;

[..]

	/*
	 * Only event directories that can be enabled should have
	 * triggers or filters, with the exception of the "print"
	 * event that can have a "trigger" file.
	 */
	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
		if (call->class->reg && strcmp(name, "enable") == 0) {
			*mode = TRACE_MODE_WRITE;
			*fops = &ftrace_enable_fops;
			return 1;
		}

		if (strcmp(name, "filter") == 0) {
			*mode = TRACE_MODE_WRITE;
			*fops = &ftrace_event_filter_fops;
			return 1;
		}
	}

	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) ||
	    strcmp(trace_event_name(call), "print") == 0) {
		if (strcmp(name, "trigger") == 0) {
			*mode = TRACE_MODE_WRITE;
			*fops = &event_trigger_fops;
			return 1;
		}
	}
[..]
	return 0;
}

Where the function event has the TRACE_EVENT_FL_IGNORE_ENABLE set.

This means that the entries array elements for "enable", "filter" and
"trigger" when called on the function event will have the callback return
0 and not 1, to tell eventfs to skip these files for it.

Because the "skip to current ctx->pos" check happened for all entries, but
the ctx->pos++ only happened to entries that exist, it would confuse the
reading of a directory. Which would cause:

 # ls /sys/kernel/tracing/events/ftrace/function/
format  hist  hist  hist_debug  hist_debug  id  inject  inject

The missing "enable", "filter" and "trigger" caused ls to show "hist",
"hist_debug" and "inject" twice.

Update the ctx->pos for every iteration to keep its update and the "skip"
update consistent. This also means that on error, the ctx->pos needs to be
decremented if it was incremented without adding something.

Link: https://lore.kernel.org/all/20240104150500.38b15a62@xxxxxxxxxxxxxxxxxx/
Link: https://lore.kernel.org/linux-trace-kernel/20240104220048.172295263@xxxxxxxxxxx

Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Christian Brauner <brauner@xxxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Fixes: 493ec81a8fb8e ("eventfs: Stop using dcache_readdir() for getdents()")
Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
(cherry picked from commit 1e4624eb5a0ecaae0d2c4e3019bece119725bb98)
---
 fs/tracefs/event_inode.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 0aca6910efb3..c73fb1f7ddbc 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -760,6 +760,8 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 			continue;
 		}
 
+		ctx->pos++;
+
 		if (ei_child->is_freed)
 			continue;
 
@@ -767,13 +769,12 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		dentry = create_dir_dentry(ei, ei_child, ei_dentry);
 		if (!dentry)
-			goto out;
+			goto out_dec;
 		ino = dentry->d_inode->i_ino;
 		dput(dentry);
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
-			goto out;
-		ctx->pos++;
+			goto out_dec;
 	}
 
 	for (i = 0; i < ei->nr_entries; i++) {
@@ -784,6 +785,8 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 			continue;
 		}
 
+		ctx->pos++;
+
 		entry = &ei->entries[i];
 		name = entry->name;
 
@@ -791,7 +794,7 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 		/* If ei->is_freed then just bail here, nothing more to do */
 		if (ei->is_freed) {
 			mutex_unlock(&eventfs_mutex);
-			goto out;
+			goto out_dec;
 		}
 		r = entry->callback(name, &mode, &cdata, &fops);
 		mutex_unlock(&eventfs_mutex);
@@ -800,19 +803,23 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		dentry = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
 		if (!dentry)
-			goto out;
+			goto out_dec;
 		ino = dentry->d_inode->i_ino;
 		dput(dentry);
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
-			goto out;
-		ctx->pos++;
+			goto out_dec;
 	}
 	ret = 1;
  out:
 	srcu_read_unlock(&eventfs_srcu, idx);
 
 	return ret;
+
+ out_dec:
+	/* Incremented ctx->pos without adding something, reset it */
+	ctx->pos--;
+	goto out;
 }
 
 /**
-- 
2.43.0