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, 433 insertions, 0 deletions

diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
new file mode 100644
index 000000000..53ddedb52
--- /dev/null
+++ b/fs/ext4/ext4_jbd2.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Interface between ext4 and JBD
+ */
+
+#include "ext4_jbd2.h"
+
+#include <trace/events/ext4.h>
+
+int ext4_inode_journal_mode(struct inode *inode)
+{
+	if (EXT4_JOURNAL(inode) == NULL)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	/* We do not support data journalling with delayed allocation */
+	if (!S_ISREG(inode->i_mode) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))) {
+		/* We do not support data journalling for encrypted data */
+		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
+			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	}
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	BUG();
+}
+
+/* Just increment the non-pointer handle value */
+static handle_t *ext4_get_nojournal(void)
+{
+	handle_t *handle = current->journal_info;
+
+	BUG_ON(handle && !handle->h_invalid);
+
+	if (!handle) {
+		handle = jbd2_alloc_handle(GFP_NOFS);
+		if (!handle)
+			return ERR_PTR(-ENOMEM);
+		handle->h_invalid = 1;
+		/*
+		 * This is done by start_this_handle() if journalling
+		 * is enabled.
+		 */
+		handle->saved_alloc_context = memalloc_nofs_save();
+		current->journal_info = handle;
+	}
+	handle->h_ref++;
+	return handle;
+}
+
+
+/* Decrement the non-pointer handle value */
+static void ext4_put_nojournal(handle_t *handle)
+{
+	BUG_ON(handle->h_ref == 0);
+
+	handle->h_ref--;
+	if (handle->h_ref == 0) {
+		memalloc_nofs_restore(handle->saved_alloc_context);
+		jbd2_free_handle(handle);
+		current->journal_info = NULL;
+	}
+}
+
+/*
+ * Wrappers for jbd2_journal_start/end.
+ */
+static int ext4_journal_check_start(struct super_block *sb)
+{
+	int ret;
+	journal_t *journal;
+
+	might_sleep();
+
+	ret = ext4_emergency_state(sb);
+	if (unlikely(ret))
+		return ret;
+
+	if (WARN_ON_ONCE(sb_rdonly(sb)))
+		return -EROFS;
+
+	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
+	journal = EXT4_SB(sb)->s_journal;
+	/*
+	 * Special case here: if the journal has aborted behind our
+	 * backs (eg. EIO in the commit thread), then we still need to
+	 * take the FS itself readonly cleanly.
+	 */
+	if (journal && is_journal_aborted(journal)) {
+		ext4_abort(sb, -journal->j_errno, "Detected aborted journal");
+		return -EROFS;
+	}
+	return 0;
+}
+
+handle_t *__ext4_journal_start_sb(struct inode *inode,
+				  struct super_block *sb, unsigned int line,
+				  int type, int blocks, int rsv_blocks,
+				  int revoke_creds)
+{
+	journal_t *journal;
+	int err;
+	if (inode)
+		trace_ext4_journal_start_inode(inode, blocks, rsv_blocks,
+					revoke_creds, type,
+					_RET_IP_);
+	else
+		trace_ext4_journal_start_sb(sb, blocks, rsv_blocks,
+					revoke_creds, type,
+					_RET_IP_);
+	err = ext4_journal_check_start(sb);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	journal = EXT4_SB(sb)->s_journal;
+	if (!journal || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+		return ext4_get_nojournal();
+	return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds,
+				   GFP_NOFS, type, line);
+}
+
+int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
+{
+	struct super_block *sb;
+	int err;
+	int rc;
+
+	if (!ext4_handle_valid(handle)) {
+		ext4_put_nojournal(handle);
+		return 0;
+	}
+
+	err = handle->h_err;
+	if (!handle->h_transaction) {
+		rc = jbd2_journal_stop(handle);
+		return err ? err : rc;
+	}
+
+	sb = handle->h_transaction->t_journal->j_private;
+	rc = jbd2_journal_stop(handle);
+
+	if (!err)
+		err = rc;
+	if (err)
+		__ext4_std_error(sb, where, line, err);
+	return err;
+}
+
+handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
+					int type)
+{
+	struct super_block *sb;
+	int err;
+
+	if (!ext4_handle_valid(handle))
+		return ext4_get_nojournal();
+
+	sb = handle->h_journal->j_private;
+	trace_ext4_journal_start_reserved(sb,
+				jbd2_handle_buffer_credits(handle), _RET_IP_);
+	err = ext4_journal_check_start(sb);
+	if (err < 0) {
+		jbd2_journal_free_reserved(handle);
+		return ERR_PTR(err);
+	}
+
+	err = jbd2_journal_start_reserved(handle, type, line);
+	if (err < 0)
+		return ERR_PTR(err);
+	return handle;
+}
+
+int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
+				  int extend_cred, int revoke_cred)
+{
+	if (!ext4_handle_valid(handle))
+		return 0;
+	if (is_handle_aborted(handle))
+		return -EROFS;
+	if (jbd2_handle_buffer_credits(handle) >= check_cred &&
+	    handle->h_revoke_credits >= revoke_cred)
+		return 0;
+	extend_cred = max(0, extend_cred - jbd2_handle_buffer_credits(handle));
+	revoke_cred = max(0, revoke_cred - handle->h_revoke_credits);
+	return ext4_journal_extend(handle, extend_cred, revoke_cred);
+}
+
+static void ext4_journal_abort_handle(const char *caller, unsigned int line,
+				      const char *err_fn,
+				      struct buffer_head *bh,
+				      handle_t *handle, int err)
+{
+	char nbuf[16];
+	const char *errstr = ext4_decode_error(NULL, err, nbuf);
+
+	BUG_ON(!ext4_handle_valid(handle));
+
+	if (bh)
+		BUFFER_TRACE(bh, "abort");
+
+	if (!handle->h_err)
+		handle->h_err = err;
+
+	if (is_handle_aborted(handle))
+		return;
+
+	printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n",
+	       caller, line, errstr, err_fn);
+
+	jbd2_journal_abort_handle(handle);
+}
+
+static void ext4_check_bdev_write_error(struct super_block *sb)
+{
+	struct address_space *mapping = sb->s_bdev->bd_mapping;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err;
+
+	/*
+	 * If the block device has write error flag, it may have failed to
+	 * async write out metadata buffers in the background. In this case,
+	 * we could read old data from disk and write it out again, which
+	 * may lead to on-disk filesystem inconsistency.
+	 */
+	if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) {
+		spin_lock(&sbi->s_bdev_wb_lock);
+		err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err);
+		spin_unlock(&sbi->s_bdev_wb_lock);
+		if (err)
+			ext4_error_err(sb, -err,
+				       "Error while async write back metadata");
+	}
+}
+
+int __ext4_journal_get_write_access(const char *where, unsigned int line,
+				    handle_t *handle, struct super_block *sb,
+				    struct buffer_head *bh,
+				    enum ext4_journal_trigger_type trigger_type)
+{
+	int err;
+
+	might_sleep();
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_write_access(handle, bh);
+		if (err) {
+			ext4_journal_abort_handle(where, line, __func__, bh,
+						  handle, err);
+			return err;
+		}
+	} else
+		ext4_check_bdev_write_error(sb);
+	if (trigger_type == EXT4_JTR_NONE ||
+	    !ext4_has_feature_metadata_csum(sb))
+		return 0;
+	BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
+	jbd2_journal_set_triggers(bh,
+		&EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers);
+	return 0;
+}
+
+/*
+ * The ext4 forget function must perform a revoke if we are freeing data
+ * which has been journaled.  Metadata (eg. indirect blocks) must be
+ * revoked in all cases.
+ *
+ * "bh" may be NULL: a metadata block may have been freed from memory
+ * but there may still be a record of it in the journal, and that record
+ * still needs to be revoked.
+ */
+int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
+		  int is_metadata, struct inode *inode,
+		  struct buffer_head *bh, ext4_fsblk_t blocknr)
+{
+	int err;
+
+	might_sleep();
+
+	trace_ext4_forget(inode, is_metadata, blocknr);
+	BUFFER_TRACE(bh, "enter");
+
+	ext4_debug("forgetting bh %p: is_metadata=%d, mode %o, data mode %x\n",
+		  bh, is_metadata, inode->i_mode,
+		  test_opt(inode->i_sb, DATA_FLAGS));
+
+	/*
+	 * In the no journal case, we should wait for the ongoing buffer
+	 * to complete and do a forget.
+	 */
+	if (!ext4_handle_valid(handle)) {
+		if (bh) {
+			clear_buffer_dirty(bh);
+			wait_on_buffer(bh);
+			__bforget(bh);
+		}
+		return 0;
+	}
+
+	/* Never use the revoke function if we are doing full data
+	 * journaling: there is no need to, and a V1 superblock won't
+	 * support it.  Otherwise, only skip the revoke on un-journaled
+	 * data blocks. */
+
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (!is_metadata && !ext4_should_journal_data(inode))) {
+		if (bh) {
+			BUFFER_TRACE(bh, "call jbd2_journal_forget");
+			err = jbd2_journal_forget(handle, bh);
+			if (err)
+				ext4_journal_abort_handle(where, line, __func__,
+							  bh, handle, err);
+			return err;
+		}
+		return 0;
+	}
+
+	/*
+	 * data!=journal && (is_metadata || should_journal_data(inode))
+	 */
+	BUFFER_TRACE(bh, "call jbd2_journal_revoke");
+	err = jbd2_journal_revoke(handle, blocknr, bh);
+	if (err) {
+		ext4_journal_abort_handle(where, line, __func__,
+					  bh, handle, err);
+		__ext4_error(inode->i_sb, where, line, true, -err, 0,
+			     "error %d when attempting revoke", err);
+	}
+	BUFFER_TRACE(bh, "exit");
+	return err;
+}
+
+int __ext4_journal_get_create_access(const char *where, unsigned int line,
+				handle_t *handle, struct super_block *sb,
+				struct buffer_head *bh,
+				enum ext4_journal_trigger_type trigger_type)
+{
+	int err;
+
+	if (!ext4_handle_valid(handle))
+		return 0;
+
+	err = jbd2_journal_get_create_access(handle, bh);
+	if (err) {
+		ext4_journal_abort_handle(where, line, __func__, bh, handle,
+					  err);
+		return err;
+	}
+	if (trigger_type == EXT4_JTR_NONE ||
+	    !ext4_has_feature_metadata_csum(sb))
+		return 0;
+	BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
+	jbd2_journal_set_triggers(bh,
+		&EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers);
+	return 0;
+}
+
+static void ext4_inode_attach_mmb(struct inode *inode)
+{
+	struct mapping_metadata_bhs *mmb;
+
+	/*
+	 * It's difficult to handle failure when marking buffer dirty without
+	 * leaving filesystem corrupted
+	 */
+	mmb = kmalloc_obj(*mmb, GFP_NOFS | __GFP_NOFAIL | __GFP_ACCOUNT);
+	mmb_init(mmb, &inode->i_data);
+	/* Someone swapped another mmb before us? */
+	if (cmpxchg(&EXT4_I(inode)->i_metadata_bhs, NULL, mmb))
+		kfree(mmb);
+}
+
+int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
+				 handle_t *handle, struct inode *inode,
+				 struct buffer_head *bh)
+{
+	int err = 0;
+
+	might_sleep();
+
+	set_buffer_meta(bh);
+	set_buffer_prio(bh);
+	set_buffer_uptodate(bh);
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_dirty_metadata(handle, bh);
+		/* Errors can only happen due to aborted journal or a nasty bug */
+		if (!is_handle_aborted(handle) && WARN_ON_ONCE(err)) {
+			ext4_journal_abort_handle(where, line, __func__, bh,
+						  handle, err);
+			if (inode == NULL) {
+				pr_err("EXT4: jbd2_journal_dirty_metadata "
+				       "failed: handle type %u started at "
+				       "line %u, credits %u/%u, errcode %d",
+				       handle->h_type,
+				       handle->h_line_no,
+				       handle->h_requested_credits,
+				       jbd2_handle_buffer_credits(handle), err);
+				return err;
+			}
+			ext4_error_inode(inode, where, line,
+					 bh->b_blocknr,
+					 "journal_dirty_metadata failed: "
+					 "handle type %u started at line %u, "
+					 "credits %u/%u, errcode %d",
+					 handle->h_type,
+					 handle->h_line_no,
+					 handle->h_requested_credits,
+					 jbd2_handle_buffer_credits(handle),
+					 err);
+		}
+	} else {
+		if (inode) {
+			if (!ext4_i_metadata_bhs(inode))
+				ext4_inode_attach_mmb(inode);
+			mmb_mark_buffer_dirty(bh, ext4_i_metadata_bhs(inode));
+		} else {
+			mark_buffer_dirty(bh);
+		}
+		if (inode && inode_needs_sync(inode)) {
+			sync_dirty_buffer(bh);
+			if (buffer_req(bh) && !buffer_uptodate(bh)) {
+				ext4_error_inode_err(inode, where, line,
+						     bh->b_blocknr, EIO,
+					"IO error syncing itable block");
+				err = -EIO;
+			}
+		}
+	}
+	return err;
+}