Merge tag 'vfs-7.1-rc5.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:
 "This contains a fixes for the current development cycle. Note that AI
  related review sometimes delays fixes a bit because we find more fixes
  for the fixes. I might try and send smaller but more fixes PRs if this
  trend keeps up.

   - Fix various netfslib bugs

   - Fix an out-of-bounds write when listing idmappings

   - Fix the return values in jfs_mkdir() and orangefs_mkdir()

   - Fix a writeback writeback array overflow in fuse

   - Fix a forced iversion increment on lazytime timestamp updates

   - Reject a negative timeval component in kern_select()

   - Fix error return when vfs_mkdir() fails in the cachefiles code

   - Fix wrong error code returned for pidns ioctls"

* tag 'vfs-7.1-rc5.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (31 commits)
  cachefiles: Fix error return when vfs_mkdir() fails
  afs: Fix the locking used by afs_get_link()
  netfs, afs: Fix write skipping in dir/link writepages
  netfs: Fix netfs_read_folio() to wait on writeback
  netfs: Fix folio->private handling in netfs_perform_write()
  netfs: Fix partial invalidation of streaming-write folio
  netfs: Fix potential UAF in netfs_unlock_abandoned_read_pages()
  netfs: Fix leak of request in netfs_write_begin() error handling
  netfs: Fix early put of sink folio in netfs_read_gaps()
  netfs: Fix write streaming disablement if fd open O_RDWR
  netfs: Fix read-gaps to remove netfs_folio from filled folio
  netfs: Fix potential deadlock in write-through mode
  netfs: Fix streaming write being overwritten
  netfs: Defer the emission of trace_netfs_folio()
  netfs: Fix netfs_invalidate_folio() to clear dirty bit if all changes gone
  netfs: Fix overrun check in netfs_extract_user_iter()
  netfs: fix error handling in netfs_extract_user_iter()
  netfs: Fix potential uninitialised var in netfs_extract_user_iter()
  netfs: fix VM_BUG_ON_FOLIO() issue in netfs_write_begin() call
  netfs: Fix zeropoint update where i_size > remote_i_size
  ...

Author: torvalds

fs/9p/v9fs_vfs.h

@@ -75,17 +75,4 @@ static inline void v9fs_invalidate_inode_attr(struct inode *inode)
 
 int v9fs_open_to_dotl_flags(int flags);
 
-static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size)
-{
-	/*
-	 * 32-bit need the lock, concurrent updates could break the
-	 * sequences and make i_size_read() loop forever.
-	 * 64-bit updates are atomic and can skip the locking.
-	 */
-	if (sizeof(i_size) > sizeof(long))
-		spin_lock(&inode->i_lock);
-	i_size_write(inode, i_size);
-	if (sizeof(i_size) > sizeof(long))
-		spin_unlock(&inode->i_lock);
-}
 #endif

fs/9p/vfs_inode.c

@@ -1141,11 +1141,13 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 	mode |= inode->i_mode & ~S_IALLUGO;
 	inode->i_mode = mode;
 
-	v9inode->netfs.remote_i_size = stat->length;
+	spin_lock(&inode->i_lock);
+	netfs_write_remote_i_size(inode, stat->length);
 	if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
-		v9fs_i_size_write(inode, stat->length);
+		i_size_write(inode, stat->length);
 	/* not real number of blocks, but 512 byte ones ... */
 	inode->i_blocks = (stat->length + 512 - 1) >> 9;
+	spin_unlock(&inode->i_lock);
 	v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR;
 }
 

fs/9p/vfs_inode_dotl.c

@@ -634,10 +634,12 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
 		mode |= inode->i_mode & ~S_IALLUGO;
 		inode->i_mode = mode;
 
-		v9inode->netfs.remote_i_size = stat->st_size;
+		spin_lock(&inode->i_lock);
+		netfs_write_remote_i_size(inode, stat->st_size);
 		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
-			v9fs_i_size_write(inode, stat->st_size);
+			i_size_write(inode, stat->st_size);
 		inode->i_blocks = stat->st_blocks;
+		spin_unlock(&inode->i_lock);
 	} else {
 		if (stat->st_result_mask & P9_STATS_ATIME) {
 			inode_set_atime(inode, stat->st_atime_sec,
@@ -662,13 +664,15 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
 			mode |= inode->i_mode & ~S_IALLUGO;
 			inode->i_mode = mode;
 		}
+		spin_lock(&inode->i_lock);
 		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) &&
 		    stat->st_result_mask & P9_STATS_SIZE) {
-			v9inode->netfs.remote_i_size = stat->st_size;
-			v9fs_i_size_write(inode, stat->st_size);
+			netfs_write_remote_i_size(inode, stat->st_size);
+			i_size_write(inode, stat->st_size);
 		}
 		if (stat->st_result_mask & P9_STATS_BLOCKS)
 			inode->i_blocks = stat->st_blocks;
+		spin_unlock(&inode->i_lock);
 	}
 	if (stat->st_result_mask & P9_STATS_GEN)
 		inode->i_generation = stat->st_gen;

fs/afs/Makefile

@@ -30,6 +30,7 @@ kafs-y := \
 	server.o \
 	server_list.o \
 	super.o \
+	symlink.o \
 	validation.o \
 	vlclient.o \
 	vl_alias.o \

fs/afs/dir.c

@@ -44,6 +44,8 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 		      struct dentry *old_dentry, struct inode *new_dir,
 		      struct dentry *new_dentry, unsigned int flags);
+static int afs_dir_writepages(struct address_space *mapping,
+			      struct writeback_control *wbc);
 
 const struct file_operations afs_dir_file_operations = {
 	.open		= afs_dir_open,
@@ -68,7 +70,7 @@ const struct inode_operations afs_dir_inode_operations = {
 };
 
 const struct address_space_operations afs_dir_aops = {
-	.writepages	= afs_single_writepages,
+	.writepages	= afs_dir_writepages,
 };
 
 const struct dentry_operations afs_fs_dentry_operations = {
@@ -233,22 +235,13 @@ static ssize_t afs_do_read_single(struct afs_vnode *dvnode, struct file *file)
 	struct iov_iter iter;
 	ssize_t ret;
 	loff_t i_size;
-	bool is_dir = (S_ISDIR(dvnode->netfs.inode.i_mode) &&
-		       !test_bit(AFS_VNODE_MOUNTPOINT, &dvnode->flags));
 
 	i_size = i_size_read(&dvnode->netfs.inode);
-	if (is_dir) {
-		if (i_size < AFS_DIR_BLOCK_SIZE)
-			return afs_bad(dvnode, afs_file_error_dir_small);
-		if (i_size > AFS_DIR_BLOCK_SIZE * 1024) {
-			trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big);
-			return -EFBIG;
-		}
-	} else {
-		if (i_size > AFSPATHMAX) {
-			trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big);
-			return -EFBIG;
-		}
+	if (i_size < AFS_DIR_BLOCK_SIZE)
+		return afs_bad(dvnode, afs_file_error_dir_small);
+	if (i_size > AFS_DIR_BLOCK_SIZE * 1024) {
+		trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big);
+		return -EFBIG;
 	}
 
 	/* Expand the storage.  TODO: Shrink the storage too. */
@@ -277,24 +270,18 @@ static ssize_t afs_do_read_single(struct afs_vnode *dvnode, struct file *file)
 			 * buffer.
 			 */
 			ret = -ESTALE;
-		} else if (is_dir) {
+		} else {
 			int ret2 = afs_dir_check(dvnode);
 
 			if (ret2 < 0)
 				ret = ret2;
-		} else if (i_size < folioq_folio_size(dvnode->directory, 0)) {
-			/* NUL-terminate a symlink. */
-			char *symlink = kmap_local_folio(folioq_folio(dvnode->directory, 0), 0);
-
-			symlink[i_size] = 0;
-			kunmap_local(symlink);
 		}
 	}
 
 	return ret;
 }
 
-ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file)
+static ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file)
 {
 	ssize_t ret;
 
@@ -1763,13 +1750,20 @@ static int afs_link(struct dentry *from, struct inode *dir,
 	return ret;
 }
 
+static void afs_symlink_put(struct afs_operation *op)
+{
+	kfree(op->create.symlink);
+	op->create.symlink = NULL;
+	afs_create_put(op);
+}
+
 static const struct afs_operation_ops afs_symlink_operation = {
 	.issue_afs_rpc	= afs_fs_symlink,
 	.issue_yfs_rpc	= yfs_fs_symlink,
 	.success	= afs_create_success,
 	.aborted	= afs_check_for_remote_deletion,
 	.edit_dir	= afs_create_edit_dir,
-	.put		= afs_create_put,
+	.put		= afs_symlink_put,
 };
 
 /*
@@ -1779,7 +1773,9 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		       struct dentry *dentry, const char *content)
 {
 	struct afs_operation *op;
+	struct afs_symlink *symlink;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
+	size_t clen = strlen(content);
 	int ret;
 
 	_enter("{%llx:%llu},{%pd},%s",
@@ -1791,12 +1787,20 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		goto error;
 
 	ret = -EINVAL;
-	if (strlen(content) >= AFSPATHMAX)
+	if (clen >= AFSPATHMAX)
+		goto error;
+
+	ret = -ENOMEM;
+	symlink = kmalloc_flex(struct afs_symlink, content, clen + 1, GFP_KERNEL);
+	if (!symlink)
 		goto error;
+	refcount_set(&symlink->ref, 1);
+	memcpy(symlink->content, content, clen + 1);
 
 	op = afs_alloc_operation(NULL, dvnode->volume);
 	if (IS_ERR(op)) {
 		ret = PTR_ERR(op);
+		kfree(symlink);
 		goto error;
 	}
 
@@ -1808,7 +1812,7 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	op->dentry		= dentry;
 	op->ops			= &afs_symlink_operation;
 	op->create.reason	= afs_edit_dir_for_symlink;
-	op->create.symlink	= content;
+	op->create.symlink	= symlink;
 	op->mtime		= current_time(dir);
 	ret = afs_do_sync_operation(op);
 	afs_dir_unuse_cookie(dvnode, ret);
@@ -2192,28 +2196,33 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 }
 
 /*
- * Write the file contents to the cache as a single blob.
+ * Write the directory contents to the cache as a single blob.
  */
-int afs_single_writepages(struct address_space *mapping,
-			  struct writeback_control *wbc)
+static int afs_dir_writepages(struct address_space *mapping,
+			      struct writeback_control *wbc)
 {
 	struct afs_vnode *dvnode = AFS_FS_I(mapping->host);
 	struct iov_iter iter;
-	bool is_dir = (S_ISDIR(dvnode->netfs.inode.i_mode) &&
-		       !test_bit(AFS_VNODE_MOUNTPOINT, &dvnode->flags));
 	int ret = 0;
 
 	/* Need to lock to prevent the folio queue and folios from being thrown
 	 * away.
 	 */
-	down_read(&dvnode->validate_lock);
+	if (!down_read_trylock(&dvnode->validate_lock)) {
+		if (wbc->sync_mode == WB_SYNC_NONE) {
+			/* The VFS will have undirtied the inode. */
+			netfs_single_mark_inode_dirty(&dvnode->netfs.inode);
+			return 0;
+		}
+		down_read(&dvnode->validate_lock);
+	}
 
-	if (is_dir ?
-	    test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) :
-	    atomic64_read(&dvnode->cb_expires_at) != AFS_NO_CB_PROMISE) {
+	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
 		iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0,
 				     i_size_read(&dvnode->netfs.inode));
 		ret = netfs_writeback_single(mapping, wbc, &iter);
+		if (ret == 1)
+			ret = 0; /* Skipped write due to lock conflict. */
 	}
 
 	up_read(&dvnode->validate_lock);

fs/afs/file.c

@@ -427,21 +427,35 @@ static void afs_free_request(struct netfs_io_request *rreq)
 	afs_put_wb_key(rreq->netfs_priv2);
 }
 
-static void afs_update_i_size(struct inode *inode, loff_t new_i_size)
+/*
+ * Set the file size and block count, taking ->cb_lock and ->i_lock to maintain
+ * coherency and prevent 64-bit tearing on 32-bit arches.
+ *
+ * Also, estimate the number of 512 bytes blocks used, rounded up to nearest 1K
+ * for consistency with other AFS clients.
+ */
+void afs_set_i_size(struct afs_vnode *vnode, loff_t new_i_size)
 {
-	struct afs_vnode *vnode = AFS_FS_I(inode);
+	struct inode *inode = &vnode->netfs.inode;
 	loff_t i_size;
 
 	write_seqlock(&vnode->cb_lock);
-	i_size = i_size_read(&vnode->netfs.inode);
+	spin_lock(&inode->i_lock);
+	i_size = i_size_read(inode);
 	if (new_i_size > i_size) {
-		i_size_write(&vnode->netfs.inode, new_i_size);
-		inode_set_bytes(&vnode->netfs.inode, new_i_size);
+		i_size_write(inode, new_i_size);
+		inode_set_bytes(inode, round_up(new_i_size, 1024));
 	}
+	spin_unlock(&inode->i_lock);
 	write_sequnlock(&vnode->cb_lock);
 	fscache_update_cookie(afs_vnode_cache(vnode), NULL, &new_i_size);
 }
 
+static void afs_update_i_size(struct inode *inode, loff_t new_i_size)
+{
+	afs_set_i_size(AFS_FS_I(inode), new_i_size);
+}
+
 static void afs_netfs_invalidate_cache(struct netfs_io_request *wreq)
 {
 	struct afs_vnode *vnode = AFS_FS_I(wreq->inode);

fs/afs/fsclient.c

@@ -886,7 +886,7 @@ void afs_fs_symlink(struct afs_operation *op)
 	namesz = name->len;
 	padsz = (4 - (namesz & 3)) & 3;
 
-	c_namesz = strlen(op->create.symlink);
+	c_namesz = strlen(op->create.symlink->content);
 	c_padsz = (4 - (c_namesz & 3)) & 3;
 
 	reqsz = (6 * 4) + namesz + padsz + c_namesz + c_padsz + (6 * 4);
@@ -910,7 +910,7 @@ void afs_fs_symlink(struct afs_operation *op)
 		bp = (void *) bp + padsz;
 	}
 	*bp++ = htonl(c_namesz);
-	memcpy(bp, op->create.symlink, c_namesz);
+	memcpy(bp, op->create.symlink->content, c_namesz);
 	bp = (void *) bp + c_namesz;
 	if (c_padsz > 0) {
 		memset(bp, 0, c_padsz);