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

Pull vfs inode updates from Christian Brauner:
 "This contains a series I originally wrote and that Eric brought over
  the finish line. It moves out the i_crypt_info and i_verity_info
  pointers out of 'struct inode' and into the fs-specific part of the
  inode.

  So now the few filesytems that actually make use of this pay the price
  in their own private inode storage instead of forcing it upon every
  user of struct inode.

  The pointer for the crypt and verity info is simply found by storing
  an offset to its address in struct fsverity_operations and struct
  fscrypt_operations. This shrinks struct inode by 16 bytes.

  I hope to move a lot more out of it in the future so that struct inode
  becomes really just about very core stuff that we need, much like
  struct dentry and struct file, instead of the dumping ground it has
  become over the years.

  On top of this are a various changes associated with the ongoing inode
  lifetime handling rework that multiple people are pushing forward:

   - Stop accessing inode->i_count directly in f2fs and gfs2. They
     simply should use the __iget() and iput() helpers

   - Make the i_state flags an enum

   - Rework the iput() logic

     Currently, if we are the last iput, and we have the I_DIRTY_TIME
     bit set, we will grab a reference on the inode again and then mark
     it dirty and then redo the put. This is to make sure we delay the
     time update for as long as possible

     We can rework this logic to simply dec i_count if it is not 1, and
     if it is do the time update while still holding the i_count
     reference

     Then we can replace the atomic_dec_and_lock with locking the
     ->i_lock and doing atomic_dec_and_test, since we did the
     atomic_add_unless above

   - Add an icount_read() helper and convert everyone that accesses
     inode->i_count directly for this purpose to use the helper

   - Expand dump_inode() to dump more information about an inode helping
     in debugging

   - Add some might_sleep() annotations to iput() and associated
     helpers"

* tag 'vfs-6.18-rc1.inode' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: add might_sleep() annotation to iput() and more
  fs: expand dump_inode()
  inode: fix whitespace issues
  fs: add an icount_read helper
  fs: rework iput logic
  fs: make the i_state flags an enum
  fs: stop accessing ->i_count directly in f2fs and gfs2
  fsverity: check IS_VERITY() in fsverity_cleanup_inode()
  fs: remove inode::i_verity_info
  btrfs: move verity info pointer to fs-specific part of inode
  f2fs: move verity info pointer to fs-specific part of inode
  ext4: move verity info pointer to fs-specific part of inode
  fsverity: add support for info in fs-specific part of inode
  fs: remove inode::i_crypt_info
  ceph: move crypt info pointer to fs-specific part of inode
  ubifs: move crypt info pointer to fs-specific part of inode
  f2fs: move crypt info pointer to fs-specific part of inode
  ext4: move crypt info pointer to fs-specific part of inode
  fscrypt: add support for info in fs-specific part of inode
  fscrypt: replace raw loads of info pointer with helper function

1 files changed, 70 insertions, 20 deletions

diff --git a/fs/inode.c b/fs/inode.c
index a66c02123bca..ec9339024ac3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -534,7 +534,7 @@ static void __inode_add_lru(struct inode *inode, bool rotate)
 {
 	if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE))
 		return;
-	if (atomic_read(&inode->i_count))
+	if (icount_read(inode))
 		return;
 	if (!(inode->i_sb->s_flags & SB_ACTIVE))
 		return;
@@ -550,11 +550,11 @@ static void __inode_add_lru(struct inode *inode, bool rotate)
 struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe,
 					    struct inode *inode, u32 bit)
 {
-        void *bit_address;
+	void *bit_address;
 
-        bit_address = inode_state_wait_address(inode, bit);
-        init_wait_var_entry(wqe, bit_address, 0);
-        return __var_waitqueue(bit_address);
+	bit_address = inode_state_wait_address(inode, bit);
+	init_wait_var_entry(wqe, bit_address, 0);
+	return __var_waitqueue(bit_address);
 }
 EXPORT_SYMBOL(inode_bit_waitqueue);
 
@@ -871,11 +871,11 @@ void evict_inodes(struct super_block *sb)
 again:
 	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (atomic_read(&inode->i_count))
+		if (icount_read(inode))
 			continue;
 
 		spin_lock(&inode->i_lock);
-		if (atomic_read(&inode->i_count)) {
+		if (icount_read(inode)) {
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
@@ -937,7 +937,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
 	 * unreclaimable for a while. Remove them lazily here; iput,
 	 * sync, or the last page cache deletion will requeue them.
 	 */
-	if (atomic_read(&inode->i_count) ||
+	if (icount_read(inode) ||
 	    (inode->i_state & ~I_REFERENCED) ||
 	    !mapping_shrinkable(&inode->i_data)) {
 		list_lru_isolate(lru, &inode->i_lru);
@@ -1279,6 +1279,8 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
 	struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
 	struct inode *old;
 
+	might_sleep();
+
 again:
 	spin_lock(&inode_hash_lock);
 	old = find_inode(inode->i_sb, head, test, data, true);
@@ -1382,6 +1384,8 @@ struct inode *iget5_locked_rcu(struct super_block *sb, unsigned long hashval,
 	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
 	struct inode *inode, *new;
 
+	might_sleep();
+
 again:
 	inode = find_inode(sb, head, test, data, false);
 	if (inode) {
@@ -1422,6 +1426,9 @@ struct inode *iget_locked(struct super_block *sb, unsigned long ino)
 {
 	struct hlist_head *head = inode_hashtable + hash(sb, ino);
 	struct inode *inode;
+
+	might_sleep();
+
 again:
 	inode = find_inode_fast(sb, head, ino, false);
 	if (inode) {
@@ -1605,6 +1612,9 @@ struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
 		int (*test)(struct inode *, void *), void *data)
 {
 	struct inode *inode;
+
+	might_sleep();
+
 again:
 	inode = ilookup5_nowait(sb, hashval, test, data);
 	if (inode) {
@@ -1630,6 +1640,9 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino)
 {
 	struct hlist_head *head = inode_hashtable + hash(sb, ino);
 	struct inode *inode;
+
+	might_sleep();
+
 again:
 	inode = find_inode_fast(sb, head, ino, false);
 
@@ -1780,6 +1793,8 @@ int insert_inode_locked(struct inode *inode)
 	ino_t ino = inode->i_ino;
 	struct hlist_head *head = inode_hashtable + hash(sb, ino);
 
+	might_sleep();
+
 	while (1) {
 		struct inode *old = NULL;
 		spin_lock(&inode_hash_lock);
@@ -1826,6 +1841,8 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 {
 	struct inode *old;
 
+	might_sleep();
+
 	inode->i_state |= I_CREATING;
 	old = inode_insert5(inode, hashval, test, NULL, data);
 
@@ -1908,20 +1925,45 @@ static void iput_final(struct inode *inode)
  */
 void iput(struct inode *inode)
 {
-	if (!inode)
+	might_sleep();
+	if (unlikely(!inode))
 		return;
-	BUG_ON(inode->i_state & I_CLEAR);
+
 retry:
-	if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) {
-		if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) {
-			atomic_inc(&inode->i_count);
-			spin_unlock(&inode->i_lock);
-			trace_writeback_lazytime_iput(inode);
-			mark_inode_dirty_sync(inode);
-			goto retry;
-		}
-		iput_final(inode);
+	lockdep_assert_not_held(&inode->i_lock);
+	VFS_BUG_ON_INODE(inode->i_state & I_CLEAR, inode);
+	/*
+	 * Note this assert is technically racy as if the count is bogusly
+	 * equal to one, then two CPUs racing to further drop it can both
+	 * conclude it's fine.
+	 */
+	VFS_BUG_ON_INODE(atomic_read(&inode->i_count) < 1, inode);
+
+	if (atomic_add_unless(&inode->i_count, -1, 1))
+		return;
+
+	if ((inode->i_state & I_DIRTY_TIME) && inode->i_nlink) {
+		trace_writeback_lazytime_iput(inode);
+		mark_inode_dirty_sync(inode);
+		goto retry;
+	}
+
+	spin_lock(&inode->i_lock);
+	if (unlikely((inode->i_state & I_DIRTY_TIME) && inode->i_nlink)) {
+		spin_unlock(&inode->i_lock);
+		goto retry;
+	}
+
+	if (!atomic_dec_and_test(&inode->i_count)) {
+		spin_unlock(&inode->i_lock);
+		return;
 	}
+
+	/*
+	 * iput_final() drops ->i_lock, we can't assert on it as the inode may
+	 * be deallocated by the time the call returns.
+	 */
+	iput_final(inode);
 }
 EXPORT_SYMBOL(iput);
 
@@ -2917,10 +2959,18 @@ EXPORT_SYMBOL(mode_strip_sgid);
  *
  * TODO: add a proper inode dumping routine, this is a stub to get debug off the
  * ground.
+ *
+ * TODO: handle getting to fs type with get_kernel_nofault()?
+ * See dump_mapping() above.
  */
 void dump_inode(struct inode *inode, const char *reason)
 {
-	pr_warn("%s encountered for inode %px (%s)\n", reason, inode, inode->i_sb->s_type->name);
+	struct super_block *sb = inode->i_sb;
+
+	pr_warn("%s encountered for inode %px\n"
+		"fs %s mode %ho opflags 0x%hx flags 0x%x state 0x%x count %d\n",
+		reason, inode, sb->s_type->name, inode->i_mode, inode->i_opflags,
+		inode->i_flags, inode->i_state, atomic_read(&inode->i_count));
 }
 
 EXPORT_SYMBOL(dump_inode);