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, 403 insertions, 0 deletions

diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
new file mode 100644
index 000000000..7ce361484
--- /dev/null
+++ b/fs/ext4/mmp.c
@@ -0,0 +1,403 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/random.h>
+#include <linux/buffer_head.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+
+#include "ext4.h"
+
+/* Checksumming functions */
+static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int offset = offsetof(struct mmp_struct, mmp_checksum);
+	__u32 csum;
+
+	csum = ext4_chksum(sbi->s_csum_seed, (char *)mmp, offset);
+
+	return cpu_to_le32(csum);
+}
+
+static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
+{
+	if (!ext4_has_feature_metadata_csum(sb))
+		return 1;
+
+	return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
+}
+
+static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
+{
+	if (!ext4_has_feature_metadata_csum(sb))
+		return;
+
+	mmp->mmp_checksum = ext4_mmp_csum(sb, mmp);
+}
+
+/*
+ * Write the MMP block using REQ_SYNC to try to get the block on-disk
+ * faster.
+ */
+static int write_mmp_block_thawed(struct super_block *sb,
+				  struct buffer_head *bh)
+{
+	struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data);
+
+	ext4_mmp_csum_set(sb, mmp);
+	lock_buffer(bh);
+	bh_submit(bh, REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO,
+			bh_end_write);
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh)))
+		return -EIO;
+	return 0;
+}
+
+static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
+{
+	/*
+	 * We protect against freezing so that we don't create dirty buffers
+	 * on frozen filesystem.
+	 */
+	scoped_guard(super_write, sb)
+		return write_mmp_block_thawed(sb, bh);
+}
+
+/*
+ * Read the MMP block. It _must_ be read from disk and hence we clear the
+ * uptodate flag on the buffer.
+ */
+static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
+			  ext4_fsblk_t mmp_block)
+{
+	struct mmp_struct *mmp;
+	int ret;
+
+	if (*bh)
+		clear_buffer_uptodate(*bh);
+
+	/* This would be sb_bread(sb, mmp_block), except we need to be sure
+	 * that the MD RAID device cache has been bypassed, and that the read
+	 * is not blocked in the elevator. */
+	if (!*bh) {
+		*bh = sb_getblk(sb, mmp_block);
+		if (!*bh) {
+			ret = -ENOMEM;
+			goto warn_exit;
+		}
+	}
+
+	lock_buffer(*bh);
+	ret = ext4_read_bh(*bh, REQ_META | REQ_PRIO, NULL, false);
+	if (ret)
+		goto warn_exit;
+
+	mmp = (struct mmp_struct *)((*bh)->b_data);
+	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) {
+		ret = -EFSCORRUPTED;
+		goto warn_exit;
+	}
+	if (!ext4_mmp_csum_verify(sb, mmp)) {
+		ret = -EFSBADCRC;
+		goto warn_exit;
+	}
+	return 0;
+warn_exit:
+	brelse(*bh);
+	*bh = NULL;
+	ext4_warning(sb, "Error %d while reading MMP block %llu",
+		     ret, mmp_block);
+	return ret;
+}
+
+/*
+ * Dump as much information as possible to help the admin.
+ */
+void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
+		    const char *function, unsigned int line, const char *msg)
+{
+	__ext4_warning(sb, function, line, "%s", msg);
+	__ext4_warning(sb, function, line,
+		       "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s",
+		       (unsigned long long)le64_to_cpu(mmp->mmp_time),
+		       (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename,
+		       (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname);
+}
+
+/*
+ * kmmpd will update the MMP sequence every s_mmp_update_interval seconds
+ */
+static int kmmpd(void *data)
+{
+	struct super_block *sb = data;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh;
+	struct mmp_struct *mmp;
+	ext4_fsblk_t mmp_block;
+	u32 seq = 0;
+	unsigned long failed_writes = 0;
+	int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned mmp_check_interval;
+	unsigned long last_update_time;
+	unsigned long diff;
+	int retval = 0;
+
+	mmp_block = le64_to_cpu(es->s_mmp_block);
+	mmp = (struct mmp_struct *)(bh->b_data);
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
+	/*
+	 * Start with the higher mmp_check_interval and reduce it if
+	 * the MMP block is being updated on time.
+	 */
+	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
+				 EXT4_MMP_MIN_CHECK_INTERVAL);
+	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+
+	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
+	       sizeof(mmp->mmp_nodename));
+
+	while (!kthread_should_stop() && !ext4_emergency_state(sb)) {
+		if (!ext4_has_feature_mmp(sb)) {
+			ext4_warning(sb, "kmmpd being stopped since MMP feature"
+				     " has been disabled.");
+			goto wait_to_exit;
+		}
+		if (++seq > EXT4_MMP_SEQ_MAX)
+			seq = 1;
+
+		mmp->mmp_seq = cpu_to_le32(seq);
+		mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
+		last_update_time = jiffies;
+
+		retval = write_mmp_block(sb, bh);
+		/*
+		 * Don't spew too many error messages. Print one every
+		 * (s_mmp_update_interval * 60) seconds.
+		 */
+		if (retval) {
+			if ((failed_writes % 60) == 0) {
+				ext4_error_err(sb, -retval,
+					       "Error writing to MMP block");
+			}
+			failed_writes++;
+		}
+
+		diff = jiffies - last_update_time;
+		if (diff < mmp_update_interval * HZ)
+			schedule_timeout_interruptible(mmp_update_interval *
+						       HZ - diff);
+
+		/*
+		 * We need to make sure that more than mmp_check_interval
+		 * seconds have not passed since writing. If that has happened
+		 * we need to check if the MMP block is as we left it.
+		 */
+		diff = jiffies - last_update_time;
+		if (diff > mmp_check_interval * HZ) {
+			struct buffer_head *bh_check = NULL;
+			struct mmp_struct *mmp_check;
+
+			retval = read_mmp_block(sb, &bh_check, mmp_block);
+			if (retval) {
+				ext4_error_err(sb, -retval,
+					       "error reading MMP data: %d",
+					       retval);
+				goto wait_to_exit;
+			}
+
+			mmp_check = (struct mmp_struct *)(bh_check->b_data);
+			if (mmp->mmp_seq != mmp_check->mmp_seq ||
+			    memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
+				   sizeof(mmp->mmp_nodename))) {
+				dump_mmp_msg(sb, mmp_check,
+					     "Error while updating MMP info. "
+					     "The filesystem seems to have been"
+					     " multiply mounted.");
+				ext4_error_err(sb, EBUSY, "abort");
+				put_bh(bh_check);
+				retval = -EBUSY;
+				goto wait_to_exit;
+			}
+			put_bh(bh_check);
+		}
+
+		 /*
+		 * Adjust the mmp_check_interval depending on how much time
+		 * it took for the MMP block to be written.
+		 */
+		mmp_check_interval = clamp(EXT4_MMP_CHECK_MULT * diff / HZ,
+					   EXT4_MMP_MIN_CHECK_INTERVAL,
+					   EXT4_MMP_MAX_CHECK_INTERVAL);
+		mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	}
+
+	/*
+	 * Unmount seems to be clean.
+	 */
+	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
+
+	retval = write_mmp_block(sb, bh);
+
+wait_to_exit:
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!kthread_should_stop())
+			schedule();
+	}
+	set_current_state(TASK_RUNNING);
+	return retval;
+}
+
+void ext4_stop_mmpd(struct ext4_sb_info *sbi)
+{
+	if (sbi->s_mmp_tsk) {
+		kthread_stop(sbi->s_mmp_tsk);
+		brelse(sbi->s_mmp_bh);
+		sbi->s_mmp_tsk = NULL;
+	}
+}
+
+/*
+ * Get a random new sequence number but make sure it is not greater than
+ * EXT4_MMP_SEQ_MAX.
+ */
+static unsigned int mmp_new_seq(void)
+{
+	return get_random_u32_below(EXT4_MMP_SEQ_MAX + 1);
+}
+
+/*
+ * Protect the filesystem from being mounted more than once.
+ */
+int ext4_multi_mount_protect(struct super_block *sb,
+				    ext4_fsblk_t mmp_block)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = NULL;
+	struct mmp_struct *mmp = NULL;
+	u32 seq;
+	unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned int wait_time = 0;
+	int retval;
+
+	if (mmp_block < le32_to_cpu(es->s_first_data_block) ||
+	    mmp_block >= ext4_blocks_count(es)) {
+		ext4_warning(sb, "Invalid MMP block in superblock");
+		retval = -EINVAL;
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+
+	mmp = (struct mmp_struct *)(bh->b_data);
+
+	if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL)
+		mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL;
+
+	/*
+	 * If check_interval in MMP block is larger, use that instead of
+	 * update_interval from the superblock.
+	 */
+	if (le16_to_cpu(mmp->mmp_check_interval) > mmp_check_interval)
+		mmp_check_interval = le16_to_cpu(mmp->mmp_check_interval);
+
+	seq = le32_to_cpu(mmp->mmp_seq);
+	if (seq == EXT4_MMP_SEQ_CLEAN)
+		goto skip;
+
+	if (seq == EXT4_MMP_SEQ_FSCK) {
+		dump_mmp_msg(sb, mmp, "fsck is running on the filesystem");
+		retval = -EBUSY;
+		goto failed;
+	}
+
+	wait_time = min(mmp_check_interval * 2 + 1,
+			mmp_check_interval + 60);
+
+	/* Print MMP interval if more than 20 secs. */
+	if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4)
+		ext4_warning(sb, "MMP interval %u higher than expected, please"
+			     " wait.\n", wait_time * 2);
+
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		retval = -ETIMEDOUT;
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		retval = -EBUSY;
+		goto failed;
+	}
+
+skip:
+	/*
+	 * write a new random sequence number.
+	 */
+	seq = mmp_new_seq();
+	mmp->mmp_seq = cpu_to_le32(seq);
+
+	/*
+	 * On mount / remount we are protected against fs freezing (by s_umount
+	 * semaphore) and grabbing freeze protection upsets lockdep
+	 */
+	retval = write_mmp_block_thawed(sb, bh);
+	if (retval)
+		goto failed;
+
+	/*
+	 * wait for MMP interval and check mmp_seq.
+	 */
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount");
+		retval = -ETIMEDOUT;
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		retval = -EBUSY;
+		goto failed;
+	}
+
+	EXT4_SB(sb)->s_mmp_bh = bh;
+
+	BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
+	snprintf(mmp->mmp_bdevname, sizeof(mmp->mmp_bdevname),
+		 "%pg", bh->b_bdev);
+
+	/*
+	 * Start a kernel thread to update the MMP block periodically.
+	 */
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s",
+					     (int)sizeof(mmp->mmp_bdevname),
+					     mmp->mmp_bdevname);
+	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
+		EXT4_SB(sb)->s_mmp_tsk = NULL;
+		ext4_warning(sb, "Unable to create kmmpd thread for %s.",
+			     sb->s_id);
+		retval = -ENOMEM;
+		goto failed;
+	}
+
+	return 0;
+
+failed:
+	brelse(bh);
+	return retval;
+}