Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 421 insertions, 0 deletions

diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c
new file mode 100644
index 000000000..d68bf20b4
--- /dev/null
+++ b/fs/xfs/scrub/readdir.c
@@ -0,0 +1,421 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs_platform.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_trace.h"
+#include "xfs_bmap.h"
+#include "xfs_trans.h"
+#include "xfs_error.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/readdir.h"
+
+/* Call a function for every entry in a shortform directory. */
+STATIC int
+xchk_dir_walk_sf(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*dp,
+	xchk_dirent_fn		dirent_fn,
+	void			*priv)
+{
+	struct xfs_name		name = {
+		.name		= ".",
+		.len		= 1,
+		.type		= XFS_DIR3_FT_DIR,
+	};
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_geometry	*geo = mp->m_dir_geo;
+	struct xfs_dir2_sf_entry *sfep;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
+	xfs_ino_t		ino;
+	xfs_dir2_dataptr_t	dapos;
+	unsigned int		i;
+	int			error;
+
+	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
+	ASSERT(sfp != NULL);
+
+	/* dot entry */
+	dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
+			geo->data_entry_offset);
+
+	error = dirent_fn(sc, dp, dapos, &name, I_INO(dp), priv);
+	if (error)
+		return error;
+
+	/* dotdot entry */
+	dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
+			geo->data_entry_offset +
+			xfs_dir2_data_entsize(mp, sizeof(".") - 1));
+	ino = xfs_dir2_sf_get_parent_ino(sfp);
+	name.name = "..";
+	name.len = 2;
+
+	error = dirent_fn(sc, dp, dapos, &name, ino, priv);
+	if (error)
+		return error;
+
+	/* iterate everything else */
+	sfep = xfs_dir2_sf_firstentry(sfp);
+	for (i = 0; i < sfp->count; i++) {
+		dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
+				xfs_dir2_sf_get_offset(sfep));
+		ino = xfs_dir2_sf_get_ino(mp, sfp, sfep);
+		name.name = sfep->name;
+		name.len = sfep->namelen;
+		name.type = xfs_dir2_sf_get_ftype(mp, sfep);
+
+		error = dirent_fn(sc, dp, dapos, &name, ino, priv);
+		if (error)
+			return error;
+
+		sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep);
+	}
+
+	return 0;
+}
+
+/* Call a function for every entry in a block directory. */
+STATIC int
+xchk_dir_walk_block(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*dp,
+	xchk_dirent_fn		dirent_fn,
+	void			*priv)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_geometry	*geo = mp->m_dir_geo;
+	struct xfs_buf		*bp;
+	unsigned int		off, next_off, end;
+	int			error;
+
+	error = xfs_dir3_block_read(sc->tp, dp, I_INO(dp), &bp);
+	if (error)
+		return error;
+
+	/* Walk each directory entry. */
+	end = xfs_dir3_data_end_offset(geo, bp->b_addr);
+	for (off = geo->data_entry_offset; off < end; off = next_off) {
+		struct xfs_name			name = { };
+		struct xfs_dir2_data_unused	*dup = bp->b_addr + off;
+		struct xfs_dir2_data_entry	*dep = bp->b_addr + off;
+		xfs_ino_t			ino;
+		xfs_dir2_dataptr_t		dapos;
+
+		/* Skip an empty entry. */
+		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
+			next_off = off + be16_to_cpu(dup->length);
+			continue;
+		}
+
+		/* Otherwise, find the next entry and report it. */
+		next_off = off + xfs_dir2_data_entsize(mp, dep->namelen);
+		if (next_off > end)
+			break;
+
+		dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk, off);
+		ino = be64_to_cpu(dep->inumber);
+		name.name = dep->name;
+		name.len = dep->namelen;
+		name.type = xfs_dir2_data_get_ftype(mp, dep);
+
+		error = dirent_fn(sc, dp, dapos, &name, ino, priv);
+		if (error)
+			break;
+	}
+
+	xfs_trans_brelse(sc->tp, bp);
+	return error;
+}
+
+/* Read a leaf-format directory buffer. */
+STATIC int
+xchk_read_leaf_dir_buf(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_da_geometry	*geo,
+	xfs_dir2_off_t		*curoff,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	map;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK);
+	xfs_dablk_t		last_da;
+	xfs_dablk_t		map_off;
+	xfs_dir2_off_t		new_off;
+
+	*bpp = NULL;
+
+	/*
+	 * Look for mapped directory blocks at or above the current offset.
+	 * Truncate down to the nearest directory block to start the scanning
+	 * operation.
+	 */
+	last_da = xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET);
+	map_off = xfs_dir2_db_to_da(geo, xfs_dir2_byte_to_db(geo, *curoff));
+
+	if (!xfs_iext_lookup_extent(dp, ifp, map_off, &icur, &map))
+		return 0;
+	if (map.br_startoff >= last_da)
+		return 0;
+	xfs_trim_extent(&map, map_off, last_da - map_off);
+
+	/* Read the directory block of that first mapping. */
+	new_off = xfs_dir2_da_to_byte(geo, map.br_startoff);
+	if (new_off > *curoff)
+		*curoff = new_off;
+
+	return xfs_dir3_data_read(tp, dp, I_INO(dp), map.br_startoff, 0, bpp);
+}
+
+/* Call a function for every entry in a leaf directory. */
+STATIC int
+xchk_dir_walk_leaf(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*dp,
+	xchk_dirent_fn		dirent_fn,
+	void			*priv)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_geometry	*geo = mp->m_dir_geo;
+	struct xfs_buf		*bp = NULL;
+	xfs_dir2_off_t		curoff = 0;
+	unsigned int		offset = 0;
+	int			error;
+
+	/* Iterate every directory offset in this directory. */
+	while (curoff < XFS_DIR2_LEAF_OFFSET) {
+		struct xfs_name			name = { };
+		struct xfs_dir2_data_unused	*dup;
+		struct xfs_dir2_data_entry	*dep;
+		xfs_ino_t			ino;
+		unsigned int			length;
+		xfs_dir2_dataptr_t		dapos;
+
+		/*
+		 * If we have no buffer, or we're off the end of the
+		 * current buffer, need to get another one.
+		 */
+		if (!bp || offset >= geo->blksize) {
+			if (bp) {
+				xfs_trans_brelse(sc->tp, bp);
+				bp = NULL;
+			}
+
+			error = xchk_read_leaf_dir_buf(sc->tp, dp, geo, &curoff,
+					&bp);
+			if (error || !bp)
+				break;
+
+			/*
+			 * Find our position in the block.
+			 */
+			offset = geo->data_entry_offset;
+			curoff += geo->data_entry_offset;
+		}
+
+		/* Skip an empty entry. */
+		dup = bp->b_addr + offset;
+		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
+			length = be16_to_cpu(dup->length);
+			offset += length;
+			curoff += length;
+			continue;
+		}
+
+		/* Otherwise, find the next entry and report it. */
+		dep = bp->b_addr + offset;
+		length = xfs_dir2_data_entsize(mp, dep->namelen);
+
+		dapos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
+		ino = be64_to_cpu(dep->inumber);
+		name.name = dep->name;
+		name.len = dep->namelen;
+		name.type = xfs_dir2_data_get_ftype(mp, dep);
+
+		error = dirent_fn(sc, dp, dapos, &name, ino, priv);
+		if (error)
+			break;
+
+		/* Advance to the next entry. */
+		offset += length;
+		curoff += length;
+	}
+
+	if (bp)
+		xfs_trans_brelse(sc->tp, bp);
+	return error;
+}
+
+/*
+ * Call a function for every entry in a directory.
+ *
+ * Callers must hold the ILOCK.  File types are XFS_DIR3_FT_*.
+ */
+int
+xchk_dir_walk(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*dp,
+	xchk_dirent_fn		dirent_fn,
+	void			*priv)
+{
+	struct xfs_da_args	args = {
+		.dp		= dp,
+		.geo		= dp->i_mount->m_dir_geo,
+		.trans		= sc->tp,
+		.owner		= I_INO(dp),
+	};
+	int			error;
+
+	if (xfs_is_shutdown(dp->i_mount))
+		return -EIO;
+
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	xfs_assert_ilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
+
+	switch (xfs_dir2_format(&args, &error)) {
+	case XFS_DIR2_FMT_SF:
+		return xchk_dir_walk_sf(sc, dp, dirent_fn, priv);
+	case XFS_DIR2_FMT_BLOCK:
+		return xchk_dir_walk_block(sc, dp, dirent_fn, priv);
+	case XFS_DIR2_FMT_LEAF:
+	case XFS_DIR2_FMT_NODE:
+		return xchk_dir_walk_leaf(sc, dp, dirent_fn, priv);
+	default:
+		return error;
+	}
+}
+
+/*
+ * Look up the inode number for an exact name in a directory.
+ *
+ * Callers must hold the ILOCK.  File types are XFS_DIR3_FT_*.  Names are not
+ * checked for correctness.
+ */
+int
+xchk_dir_lookup(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*dp,
+	const struct xfs_name	*name,
+	xfs_ino_t		*ino)
+{
+	struct xfs_da_args	args = {
+		.dp		= dp,
+		.geo		= dp->i_mount->m_dir_geo,
+		.trans		= sc->tp,
+		.name		= name->name,
+		.namelen	= name->len,
+		.filetype	= name->type,
+		.hashval	= xfs_dir2_hashname(dp->i_mount, name),
+		.whichfork	= XFS_DATA_FORK,
+		.op_flags	= XFS_DA_OP_OKNOENT,
+		.owner		= I_INO(dp),
+	};
+	int			error;
+
+	if (xfs_is_shutdown(dp->i_mount))
+		return -EIO;
+
+	/*
+	 * A temporary directory's block headers are written with the owner
+	 * set to sc->ip, so we must switch the owner here for the lookup.
+	 */
+	if (dp == sc->tempip)
+		args.owner = I_INO(sc->ip);
+
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	xfs_assert_ilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
+
+	error = xfs_dir_lookup_args(&args);
+	if (!error)
+		*ino = args.inumber;
+	return error;
+}
+
+/*
+ * Try to grab the IOLOCK and ILOCK of sc->ip and ip, returning @ip's lock
+ * state.  The caller may have a transaction, so we must use trylock for both
+ * IOLOCKs.
+ */
+static inline unsigned int
+xchk_dir_trylock_both(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
+{
+	if (!xchk_ilock_nowait(sc, XFS_IOLOCK_EXCL))
+		return 0;
+
+	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
+		goto parent_iolock;
+
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
+	if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+		goto parent_ilock;
+
+	return XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL;
+
+parent_ilock:
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+parent_iolock:
+	xchk_iunlock(sc, XFS_IOLOCK_EXCL);
+	return 0;
+}
+
+/*
+ * Try for a limited time to grab the IOLOCK and ILOCK of both the scrub target
+ * (@sc->ip) and the inode at the other end (@ip) of a directory or parent
+ * pointer link so that we can check that link.
+ *
+ * We do not know ahead of time that the directory tree is /not/ corrupt, so we
+ * cannot use the "lock two inode" functions because we do not know that there
+ * is not a racing thread trying to take the locks in opposite order.  First
+ * take IOLOCK_EXCL of the scrub target, and then try to take IOLOCK_SHARED
+ * of @ip to synchronize with the VFS.  Next, take ILOCK_EXCL of the scrub
+ * target and @ip to synchronize with XFS.
+ *
+ * If the trylocks succeed, *lockmode will be set to the locks held for @ip;
+ * @sc->ilock_flags will be set for the locks held for @sc->ip; and zero will
+ * be returned.  If not, returns -EDEADLOCK to try again; or -ETIMEDOUT if
+ * XCHK_TRY_HARDER was set.  Returns -EINTR if the process has been killed.
+ */
+int
+xchk_dir_trylock_for_pptrs(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	unsigned int		*lockmode)
+{
+	unsigned int		nr;
+	int			error = 0;
+
+	ASSERT(sc->ilock_flags == 0);
+
+	for (nr = 0; nr < HZ; nr++) {
+		*lockmode = xchk_dir_trylock_both(sc, ip);
+		if (*lockmode)
+			return 0;
+
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		delay(1);
+	}
+
+	if (sc->flags & XCHK_TRY_HARDER) {
+		xchk_set_incomplete(sc);
+		return -ETIMEDOUT;
+	}
+
+	return -EDEADLOCK;
+}