Merge tag 'linux-cpupower-6.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux

Merge cpupower utility updates for 6.18-rc1 from Shuah Khan:

"Fixes incorrect return vale in cpupower_write_sysfs() error path
 and passing incorrect size to cpuidle_state_write_file() while
 writing status to disable file in cpuidle_state_disable()."

* tag 'linux-cpupower-6.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux: (1125 commits)
  tools/cpupower: Fix incorrect size in cpuidle_state_disable()
  tools/cpupower: fix error return value in cpupower_write_sysfs()
  Linux 6.17-rc6
  MAINTAINERS: Input: Drop melfas-mip4 section
  USB: core: remove the move buf action
  MAINTAINERS: Update the DMA Rust entry
  erofs: fix long xattr name prefix placement
  Revert "net: usb: asix: ax88772: drop phylink use in PM to avoid MDIO runtime PM wakeups"
  hsr: hold rcu and dev lock for hsr_get_port_ndev
  hsr: use hsr_for_each_port_rtnl in hsr_port_get_hsr
  hsr: use rtnl lock when iterating over ports
  wifi: nl80211: completely disable per-link stats for now
  net: usb: asix: ax88772: drop phylink use in PM to avoid MDIO runtime PM wakeups
  net: ethtool: fix wrong type used in struct kernel_ethtool_ts_info
  selftests/bpf: Skip timer cases when bpf_timer is not supported
  bpf: Reject bpf_timer for PREEMPT_RT
  libceph: fix invalid accesses to ceph_connection_v1_info
  PM: hibernate: Restrict GFP mask in hibernation_snapshot()
  MAINTAINERS: add Phil as netfilter reviewer
  netfilter: nf_tables: restart set lookup on base_seq change
  ...

1 files changed, 53 insertions, 25 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 69e11557fd13..7d5d90845ca9 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3340,6 +3340,31 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static bool mark_inode_as_not_logged(const struct btrfs_trans_handle *trans,
+				     struct btrfs_inode *inode)
+{
+	bool ret = false;
+
+	/*
+	 * Do this only if ->logged_trans is still 0 to prevent races with
+	 * concurrent logging as we may see the inode not logged when
+	 * inode_logged() is called but it gets logged after inode_logged() did
+	 * not find it in the log tree and we end up setting ->logged_trans to a
+	 * value less than trans->transid after the concurrent logging task has
+	 * set it to trans->transid. As a consequence, subsequent rename, unlink
+	 * and link operations may end up not logging new names and removing old
+	 * names from the log.
+	 */
+	spin_lock(&inode->lock);
+	if (inode->logged_trans == 0)
+		inode->logged_trans = trans->transid - 1;
+	else if (inode->logged_trans == trans->transid)
+		ret = true;
+	spin_unlock(&inode->lock);
+
+	return ret;
+}
+
 /*
  * Check if an inode was logged in the current transaction. This correctly deals
  * with the case where the inode was logged but has a logged_trans of 0, which
@@ -3357,15 +3382,32 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	int ret;
 
-	if (inode->logged_trans == trans->transid)
+	/*
+	 * Quick lockless call, since once ->logged_trans is set to the current
+	 * transaction, we never set it to a lower value anywhere else.
+	 */
+	if (data_race(inode->logged_trans) == trans->transid)
 		return 1;
 
 	/*
-	 * If logged_trans is not 0, then we know the inode logged was not logged
-	 * in this transaction, so we can return false right away.
+	 * If logged_trans is not 0 and not trans->transid, then we know the
+	 * inode was not logged in this transaction, so we can return false
+	 * right away. We take the lock to avoid a race caused by load/store
+	 * tearing with a concurrent btrfs_log_inode() call or a concurrent task
+	 * in this function further below - an update to trans->transid can be
+	 * teared into two 32 bits updates for example, in which case we could
+	 * see a positive value that is not trans->transid and assume the inode
+	 * was not logged when it was.
 	 */
-	if (inode->logged_trans > 0)
+	spin_lock(&inode->lock);
+	if (inode->logged_trans == trans->transid) {
+		spin_unlock(&inode->lock);
+		return 1;
+	} else if (inode->logged_trans > 0) {
+		spin_unlock(&inode->lock);
 		return 0;
+	}
+	spin_unlock(&inode->lock);
 
 	/*
 	 * If no log tree was created for this root in this transaction, then
@@ -3374,10 +3416,8 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	 * transaction's ID, to avoid the search below in a future call in case
 	 * a log tree gets created after this.
 	 */
-	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state)) {
-		inode->logged_trans = trans->transid - 1;
-		return 0;
-	}
+	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state))
+		return mark_inode_as_not_logged(trans, inode);
 
 	/*
 	 * We have a log tree and the inode's logged_trans is 0. We can't tell
@@ -3431,8 +3471,7 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 		 * Set logged_trans to a value greater than 0 and less then the
 		 * current transaction to avoid doing the search in future calls.
 		 */
-		inode->logged_trans = trans->transid - 1;
-		return 0;
+		return mark_inode_as_not_logged(trans, inode);
 	}
 
 	/*
@@ -3440,20 +3479,9 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	 * the current transacion's ID, to avoid future tree searches as long as
 	 * the inode is not evicted again.
 	 */
+	spin_lock(&inode->lock);
 	inode->logged_trans = trans->transid;
-
-	/*
-	 * If it's a directory, then we must set last_dir_index_offset to the
-	 * maximum possible value, so that the next attempt to log the inode does
-	 * not skip checking if dir index keys found in modified subvolume tree
-	 * leaves have been logged before, otherwise it would result in attempts
-	 * to insert duplicate dir index keys in the log tree. This must be done
-	 * because last_dir_index_offset is an in-memory only field, not persisted
-	 * in the inode item or any other on-disk structure, so its value is lost
-	 * once the inode is evicted.
-	 */
-	if (S_ISDIR(inode->vfs_inode.i_mode))
-		inode->last_dir_index_offset = (u64)-1;
+	spin_unlock(&inode->lock);
 
 	return 1;
 }
@@ -4045,7 +4073,7 @@ done:
 
 /*
  * If the inode was logged before and it was evicted, then its
- * last_dir_index_offset is (u64)-1, so we don't the value of the last index
+ * last_dir_index_offset is 0, so we don't know the value of the last index
  * key offset. If that's the case, search for it and update the inode. This
  * is to avoid lookups in the log tree every time we try to insert a dir index
  * key from a leaf changed in the current transaction, and to allow us to always
@@ -4061,7 +4089,7 @@ static int update_last_dir_index_offset(struct btrfs_inode *inode,
 
 	lockdep_assert_held(&inode->log_mutex);
 
-	if (inode->last_dir_index_offset != (u64)-1)
+	if (inode->last_dir_index_offset != 0)
 		return 0;
 
 	if (!ctx->logged_before) {