vfs-6.11-rc6.fixes

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCZsxg5QAKCRCRxhvAZXjc
 olSiAQDvFvim4YtMmUDagC3yWTBsf+o3lYdAIuzNE0NtSn4vpAEAl/HVhQCaEDjv
 mcE3jokEsbvyXLnzs78PrY0Heua2mQg=
 =AHAd
 -----END PGP SIGNATURE-----

Merge tag 'vfs-6.11-rc6.fixes' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:
 "VFS:

   - Ensure that backing files uses file->f_ops->splice_write() for
     splice

  netfs:

   - Revert the removal of PG_private_2 from netfs_release_folio() as
     cephfs still relies on this

   - When AS_RELEASE_ALWAYS is set on a mapping the folio needs to
     always be invalidated during truncation

   - Fix losing untruncated data in a folio by making letting
     netfs_release_folio() return false if the folio is dirty

   - Fix trimming of streaming-write folios in netfs_inval_folio()

   - Reset iterator before retrying a short read

   - Fix interaction of streaming writes with zero-point tracker

  afs:

   - During truncation afs currently calls truncate_setsize() which sets
     i_size, expands the pagecache and truncates it. The first two
     operations aren't needed because they will have already been done.
     So call truncate_pagecache() instead and skip the redundant parts

  overlayfs:

   - Fix checking of the number of allowed lower layers so 500 layers
     can actually be used instead of just 499

   - Add missing '\n' to pr_err() output

   - Pass string to ovl_parse_layer() and thus allow it to be used for
     Opt_lowerdir as well

  pidfd:

   - Revert blocking the creation of pidfds for kthread as apparently
     userspace relies on this. Specifically, it breaks systemd during
     shutdown

  romfs:

   - Fix romfs_read_folio() to use the correct offset with
     folio_zero_tail()"

* tag 'vfs-6.11-rc6.fixes' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs:
  netfs: Fix interaction of streaming writes with zero-point tracker
  netfs: Fix missing iterator reset on retry of short read
  netfs: Fix trimming of streaming-write folios in netfs_inval_folio()
  netfs: Fix netfs_release_folio() to say no if folio dirty
  afs: Fix post-setattr file edit to do truncation correctly
  mm: Fix missing folio invalidation calls during truncation
  ovl: ovl_parse_param_lowerdir: Add missed '\n' for pr_err
  ovl: fix wrong lowerdir number check for parameter Opt_lowerdir
  ovl: pass string to ovl_parse_layer()
  backing-file: convert to using fops->splice_write
  Revert "pidfd: prevent creation of pidfds for kthreads"
  romfs: fix romfs_read_folio()
  netfs, ceph: Partially revert "netfs: Replace PG_fscache by setting folio->private and marking dirty"

fs/afs/inode.c

@@ -695,13 +695,18 @@ static void afs_setattr_edit_file(struct afs_operation *op)
 {
 	struct afs_vnode_param *vp = &op->file[0];
 	struct afs_vnode *vnode = vp->vnode;
+	struct inode *inode = &vnode->netfs.inode;
 
 	if (op->setattr.attr->ia_valid & ATTR_SIZE) {
 		loff_t size = op->setattr.attr->ia_size;
-		loff_t i_size = op->setattr.old_i_size;
+		loff_t old = op->setattr.old_i_size;
 
-		if (size != i_size) {
-			truncate_setsize(&vnode->netfs.inode, size);
+		/* Note: inode->i_size was updated by afs_apply_status() inside
+		 * the I/O and callback locks.
+		 */
+
+		if (size != old) {
+			truncate_pagecache(inode, size);
 			netfs_resize_file(&vnode->netfs, size, true);
 			fscache_resize_cookie(afs_vnode_cache(vnode), size);
 		}

fs/backing-file.c

@@ -303,13 +303,16 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
 	if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING)))
 		return -EIO;
 
+	if (!out->f_op->splice_write)
+		return -EINVAL;
+
 	ret = file_remove_privs(ctx->user_file);
 	if (ret)
 		return ret;
 
 	old_cred = override_creds(ctx->cred);
 	file_start_write(out);
-	ret = iter_file_splice_write(pipe, out, ppos, len, flags);
+	ret = out->f_op->splice_write(pipe, out, ppos, len, flags);
 	file_end_write(out);
 	revert_creds(old_cred);
 

fs/ceph/inode.c

@@ -695,6 +695,7 @@ void ceph_evict_inode(struct inode *inode)
 
 	percpu_counter_dec(&mdsc->metric.total_inodes);
 
+	netfs_wait_for_outstanding_io(inode);
 	truncate_inode_pages_final(&inode->i_data);
 	if (inode->i_state & I_PINNING_NETFS_WB)
 		ceph_fscache_unuse_cookie(inode, true);

fs/netfs/io.c

@@ -313,6 +313,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
 			netfs_reset_subreq_iter(rreq, subreq);
 			netfs_read_from_server(rreq, subreq);
 		} else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) {
+			netfs_reset_subreq_iter(rreq, subreq);
 			netfs_rreq_short_read(rreq, subreq);
 		}
 	}

fs/netfs/misc.c

@@ -97,10 +97,22 @@ EXPORT_SYMBOL(netfs_clear_inode_writeback);
 void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 {
 	struct netfs_folio *finfo;
+	struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
 	size_t flen = folio_size(folio);
 
 	_enter("{%lx},%zx,%zx", folio->index, offset, length);
 
+	if (offset == 0 && length == flen) {
+		unsigned long long i_size = i_size_read(&ctx->inode);
+		unsigned long long fpos = folio_pos(folio), end;
+
+		end = umin(fpos + flen, i_size);
+		if (fpos < i_size && end > ctx->zero_point)
+			ctx->zero_point = end;
+	}
+
+	folio_wait_private_2(folio); /* [DEPRECATED] */
+
 	if (!folio_test_private(folio))
 		return;
 
@@ -113,18 +125,34 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 		/* We have a partially uptodate page from a streaming write. */
 		unsigned int fstart = finfo->dirty_offset;
 		unsigned int fend = fstart + finfo->dirty_len;
-		unsigned int end = offset + length;
+		unsigned int iend = offset + length;
 
 		if (offset >= fend)
 			return;
-		if (end <= fstart)
+		if (iend <= fstart)
 			return;
-		if (offset <= fstart && end >= fend)
+
+		/* The invalidation region overlaps the data.  If the region
+		 * covers the start of the data, we either move along the start
+		 * or just erase the data entirely.
+		 */
+		if (offset <= fstart) {
+			if (iend >= fend)
 				goto erase_completely;
-		if (offset <= fstart && end > fstart)
-			goto reduce_len;
-		if (offset > fstart && end >= fend)
-			goto move_start;
+			/* Move the start of the data. */
+			finfo->dirty_len = fend - iend;
+			finfo->dirty_offset = offset;
+			return;
+		}
+
+		/* Reduce the length of the data if the invalidation region
+		 * covers the tail part.
+		 */
+		if (iend >= fend) {
+			finfo->dirty_len = offset - fstart;
+			return;
+		}
+
 		/* A partial write was split.  The caller has already zeroed
 		 * it, so just absorb the hole.
 		 */
@@ -137,12 +165,6 @@ erase_completely:
 	folio_clear_uptodate(folio);
 	kfree(finfo);
 	return;
-reduce_len:
-	finfo->dirty_len = offset + length - finfo->dirty_offset;
-	return;
-move_start:
-	finfo->dirty_len -= offset - finfo->dirty_offset;
-	finfo->dirty_offset = offset;
 }
 EXPORT_SYMBOL(netfs_invalidate_folio);
 
@@ -159,12 +181,20 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp)
 	struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
 	unsigned long long end;
 
-	end = folio_pos(folio) + folio_size(folio);
+	if (folio_test_dirty(folio))
+		return false;
+
+	end = umin(folio_pos(folio) + folio_size(folio), i_size_read(&ctx->inode));
 	if (end > ctx->zero_point)
 		ctx->zero_point = end;
 
 	if (folio_test_private(folio))
 		return false;
+	if (unlikely(folio_test_private_2(folio))) { /* [DEPRECATED] */
+		if (current_is_kswapd() || !(gfp & __GFP_FS))
+			return false;
+		folio_wait_private_2(folio);
+	}
 	fscache_note_page_release(netfs_i_cookie(ctx));
 	return true;
 }

fs/netfs/write_collect.c

@@ -33,6 +33,7 @@
 int netfs_folio_written_back(struct folio *folio)
 {
 	enum netfs_folio_trace why = netfs_folio_trace_clear;
+	struct netfs_inode *ictx = netfs_inode(folio->mapping->host);
 	struct netfs_folio *finfo;
 	struct netfs_group *group = NULL;
 	int gcount = 0;
@@ -41,6 +42,12 @@ int netfs_folio_written_back(struct folio *folio)
 		/* Streaming writes cannot be redirtied whilst under writeback,
 		 * so discard the streaming record.
 		 */
+		unsigned long long fend;
+
+		fend = folio_pos(folio) + finfo->dirty_offset + finfo->dirty_len;
+		if (fend > ictx->zero_point)
+			ictx->zero_point = fend;
+
 		folio_detach_private(folio);
 		group = finfo->netfs_group;
 		gcount++;

fs/overlayfs/params.c

@@ -353,6 +353,8 @@ static void ovl_add_layer(struct fs_context *fc, enum ovl_opt layer,
 	case Opt_datadir_add:
 		ctx->nr_data++;
 		fallthrough;
+	case Opt_lowerdir:
+		fallthrough;
 	case Opt_lowerdir_add:
 		WARN_ON(ctx->nr >= ctx->capacity);
 		l = &ctx->lower[ctx->nr++];
@@ -365,10 +367,9 @@ static void ovl_add_layer(struct fs_context *fc, enum ovl_opt layer,
 	}
 }
 
-static int ovl_parse_layer(struct fs_context *fc, struct fs_parameter *param,
-			   enum ovl_opt layer)
+static int ovl_parse_layer(struct fs_context *fc, const char *layer_name, enum ovl_opt layer)
 {
-	char *name = kstrdup(param->string, GFP_KERNEL);
+	char *name = kstrdup(layer_name, GFP_KERNEL);
 	bool upper = (layer == Opt_upperdir || layer == Opt_workdir);
 	struct path path;
 	int err;
@@ -376,7 +377,7 @@ static int ovl_parse_layer(struct fs_context *fc, struct fs_parameter *param,
 	if (!name)
 		return -ENOMEM;
 
-	if (upper)
+	if (upper || layer == Opt_lowerdir)
 		err = ovl_mount_dir(name, &path);
 	else
 		err = ovl_mount_dir_noesc(name, &path);
@@ -432,7 +433,6 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 {
 	int err;
 	struct ovl_fs_context *ctx = fc->fs_private;
-	struct ovl_fs_context_layer *l;
 	char *dup = NULL, *iter;
 	ssize_t nr_lower, nr;
 	bool data_layer = false;
@@ -449,7 +449,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 		return 0;
 
 	if (*name == ':') {
-		pr_err("cannot append lower layer");
+		pr_err("cannot append lower layer\n");
 		return -EINVAL;
 	}
 
@@ -472,35 +472,11 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 		goto out_err;
 	}
 
-	if (nr_lower > ctx->capacity) {
-		err = -ENOMEM;
-		l = krealloc_array(ctx->lower, nr_lower, sizeof(*ctx->lower),
-				   GFP_KERNEL_ACCOUNT);
-		if (!l)
-			goto out_err;
-
-		ctx->lower = l;
-		ctx->capacity = nr_lower;
-	}
-
 	iter = dup;
-	l = ctx->lower;
-	for (nr = 0; nr < nr_lower; nr++, l++) {
-		ctx->nr++;
-		memset(l, 0, sizeof(*l));
-
-		err = ovl_mount_dir(iter, &l->path);
+	for (nr = 0; nr < nr_lower; nr++) {
+		err = ovl_parse_layer(fc, iter, Opt_lowerdir);
 		if (err)
-			goto out_put;
-
-		err = ovl_mount_dir_check(fc, &l->path, Opt_lowerdir, iter, false);
-		if (err)
-			goto out_put;
-
-		err = -ENOMEM;
-		l->name = kstrdup(iter, GFP_KERNEL_ACCOUNT);
-		if (!l->name)
-			goto out_put;
+			goto out_err;
 
 		if (data_layer)
 			ctx->nr_data++;
@@ -517,8 +493,8 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 			 * there are no data layers.
 			 */
 			if (ctx->nr_data > 0) {
-				pr_err("regular lower layers cannot follow data lower layers");
-				goto out_put;
+				pr_err("regular lower layers cannot follow data lower layers\n");
+				goto out_err;
 			}
 
 			data_layer = false;
@@ -532,9 +508,6 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 	kfree(dup);
 	return 0;
 
-out_put:
-	ovl_reset_lowerdirs(ctx);
-
 out_err:
 	kfree(dup);
 
@@ -582,7 +555,7 @@ static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	case Opt_datadir_add:
 	case Opt_upperdir:
 	case Opt_workdir:
-		err = ovl_parse_layer(fc, param, opt);
+		err = ovl_parse_layer(fc, param->string, opt);
 		break;
 	case Opt_default_permissions:
 		config->default_permissions = true;

fs/romfs/super.c

@@ -126,7 +126,7 @@ static int romfs_read_folio(struct file *file, struct folio *folio)
 		}
 	}
 
-	buf = folio_zero_tail(folio, fillsize, buf);
+	buf = folio_zero_tail(folio, fillsize, buf + fillsize);
 	kunmap_local(buf);
 	folio_end_read(folio, ret == 0);
 	return ret;

kernel/fork.c

@@ -2053,24 +2053,11 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  */
 int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
 {
-	if (!pid)
-		return -EINVAL;
+	bool thread = flags & PIDFD_THREAD;
 
-	scoped_guard(rcu) {
-		struct task_struct *tsk;
-
-		if (flags & PIDFD_THREAD)
-			tsk = pid_task(pid, PIDTYPE_PID);
-		else
-			tsk = pid_task(pid, PIDTYPE_TGID);
-		if (!tsk)
+	if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID))
 		return -EINVAL;
 
-		/* Don't create pidfds for kernel threads for now. */
-		if (tsk->flags & PF_KTHREAD)
-			return -EINVAL;
-	}
-
 	return __pidfd_prepare(pid, flags, ret);
 }
 
@@ -2416,12 +2403,6 @@ __latent_entropy struct task_struct *copy_process(
 	if (clone_flags & CLONE_PIDFD) {
 		int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0;
 
-		/* Don't create pidfds for kernel threads for now. */
-		if (args->kthread) {
-			retval = -EINVAL;
-			goto bad_fork_free_pid;
-		}
-
 		/* Note that no task has been attached to @pid yet. */
 		retval = __pidfd_prepare(pid, flags, &pidfile);
 		if (retval < 0)

mm/truncate.c

@@ -157,7 +157,7 @@ static void truncate_cleanup_folio(struct folio *folio)
 	if (folio_mapped(folio))
 		unmap_mapping_folio(folio);
 
-	if (folio_has_private(folio))
+	if (folio_needs_release(folio))
 		folio_invalidate(folio, 0, folio_size(folio));
 
 	/*
@@ -219,7 +219,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 	if (!mapping_inaccessible(folio->mapping))
 		folio_zero_range(folio, offset, length);
 
-	if (folio_has_private(folio))
+	if (folio_needs_release(folio))
 		folio_invalidate(folio, offset, length);
 	if (!folio_test_large(folio))
 		return true;