Commit 7879d7af authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'vfs-6.17-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs 

Pull misc VFS updates from Christian Brauner:
 "This contains the usual selections of misc updates for this cycle.

  Features:

   - Add ext4 IOCB_DONTCACHE support

     This refactors the address_space_operations write_begin() and
     write_end() callbacks to take const struct kiocb * as their first
     argument, allowing IOCB flags such as IOCB_DONTCACHE to propagate
     to the filesystem's buffered I/O path.

     Ext4 is updated to implement handling of the IOCB_DONTCACHE flag
     and advertises support via the FOP_DONTCACHE file operation flag.

     Additionally, the i915 driver's shmem write paths are updated to
     bypass the legacy write_begin/write_end interface in favor of
     directly calling write_iter() with a constructed synchronous kiocb.
     Another i915 change replaces a manual write loop with
     kernel_write() during GEM shmem object creation.

  Cleanups:

   - don't duplicate vfs_open() in kernel_file_open()

   - proc_fd_getattr(): don't bother with S_ISDIR() check

   - fs/ecryptfs: replace snprintf with sysfs_emit in show function

   - vfs: Remove unnecessary list_for_each_entry_safe() from
     evict_inodes()

   - filelock: add new locks_wake_up_waiter() helper

   - fs: Remove three arguments from block_write_end()

   - VFS: change old_dir and new_dir in struct renamedata to dentrys

   - netfs: Remove unused declaration netfs_queue_write_request()

  Fixes:

   - eventpoll: Fix semi-unbounded recursion

   - eventpoll: fix sphinx documentation build warning

   - fs/read_write: Fix spelling typo

   - fs: annotate data race between poll_schedule_timeout() and
     pollwake()

   - fs/pipe: set FMODE_NOWAIT in create_pipe_files()

   - docs/vfs: update references to i_mutex to i_rwsem

   - fs/buffer: remove comment about hard sectorsize

   - fs/buffer: remove the min and max limit checks in __getblk_slow()

   - fs/libfs: don't assume blocksize <= PAGE_SIZE in
     generic_check_addressable

   - fs_context: fix parameter name in infofc() macro

   - fs: Prevent file descriptor table allocations exceeding INT_MAX"

* tag 'vfs-6.17-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (24 commits)
  netfs: Remove unused declaration netfs_queue_write_request()
  eventpoll: fix sphinx documentation build warning
  ext4: support uncached buffered I/O
  mm/pagemap: add write_begin_get_folio() helper function
  fs: change write_begin/write_end interface to take struct kiocb *
  drm/i915: Refactor shmem_pwrite() to use kiocb and write_iter
  drm/i915: Use kernel_write() in shmem object create
  eventpoll: Fix semi-unbounded recursion
  vfs: Remove unnecessary list_for_each_entry_safe() from evict_inodes()
  fs/libfs: don't assume blocksize <= PAGE_SIZE in generic_check_addressable
  fs/buffer: remove the min and max limit checks in __getblk_slow()
  fs: Prevent file descriptor table allocations exceeding INT_MAX
  fs: Remove three arguments from block_write_end()
  fs/ecryptfs: replace snprintf with sysfs_emit in show function
  fs: annotate suspected data race between poll_schedule_timeout() and pollwake()
  docs/vfs: update references to i_mutex to i_rwsem
  fs/buffer: remove comment about hard sectorsize
  fs_context: fix parameter name in infofc() macro
  VFS: change old_dir and new_dir in struct renamedata to dentrys
  proc_fd_getattr(): don't bother with S_ISDIR() check
  ...
parents 794cbac9 4e8fc4f7

Documentation/filesystems/locking.rst

+2 −2
Original line number Diff line number Diff line
@@ -253,10 +253,10 @@ prototypes:: 
	int (*writepages)(struct address_space *, struct writeback_control *);

	bool (*dirty_folio)(struct address_space *, struct folio *folio);

	void (*readahead)(struct readahead_control *);

	int (*write_begin)(struct file *, struct address_space *mapping,

	int (*write_begin)(const struct kiocb *, struct address_space *mapping,

				loff_t pos, unsigned len,

				struct folio **foliop, void **fsdata);

	int (*write_end)(struct file *, struct address_space *mapping,

	int (*write_end)(const struct kiocb *, struct address_space *mapping,

				loff_t pos, unsigned len, unsigned copied,

				struct folio *folio, void *fsdata);

	sector_t (*bmap)(struct address_space *, sector_t);

Documentation/filesystems/vfs.rst

+6 −5
Original line number Diff line number Diff line
@@ -758,8 +758,9 @@ process is more complicated and uses write_begin/write_end or 
dirty_folio to write data into the address_space, and

writepages to writeback data to storage.



Adding and removing pages to/from an address_space is protected by the

inode's i_mutex.

Removing pages from an address_space requires holding the inode's i_rwsem

exclusively, while adding pages to the address_space requires holding the

inode's i_mapping->invalidate_lock exclusively.



When data is written to a page, the PG_Dirty flag should be set.  It

typically remains set until writepages asks for it to be written.  This
@@ -822,10 +823,10 @@ cache in your filesystem. The following members are defined: 
		int (*writepages)(struct address_space *, struct writeback_control *);

		bool (*dirty_folio)(struct address_space *, struct folio *);

		void (*readahead)(struct readahead_control *);

		int (*write_begin)(struct file *, struct address_space *mapping,

		int (*write_begin)(const struct kiocb *, struct address_space *mapping,

				   loff_t pos, unsigned len,

				   struct page **pagep, void **fsdata);

		int (*write_end)(struct file *, struct address_space *mapping,

		int (*write_end)(const struct kiocb *, struct address_space *mapping,

				 loff_t pos, unsigned len, unsigned copied,

				 struct folio *folio, void *fsdata);

		sector_t (*bmap)(struct address_space *, sector_t);

block/fops.c

+9 −6
Original line number Diff line number Diff line
@@ -496,18 +496,21 @@ static void blkdev_readahead(struct readahead_control *rac) 
	mpage_readahead(rac, blkdev_get_block);

}



static int blkdev_write_begin(struct file *file, struct address_space *mapping,

		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)

static int blkdev_write_begin(const struct kiocb *iocb,

			      struct address_space *mapping, loff_t pos,

			      unsigned len, struct folio **foliop,

			      void **fsdata)

{

	return block_write_begin(mapping, pos, len, foliop, blkdev_get_block);

}



static int blkdev_write_end(struct file *file, struct address_space *mapping,

		loff_t pos, unsigned len, unsigned copied, struct folio *folio,

		void *fsdata)

static int blkdev_write_end(const struct kiocb *iocb,

			    struct address_space *mapping,

			    loff_t pos, unsigned len, unsigned copied,

			    struct folio *folio, void *fsdata)

{

	int ret;

	ret = block_write_end(file, mapping, pos, len, copied, folio, fsdata);

	ret = block_write_end(pos, len, copied, folio);



	folio_unlock(folio);

	folio_put(folio);

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

+31 −84
Original line number Diff line number Diff line
@@ -6,6 +6,7 @@ 
#include <linux/pagevec.h>

#include <linux/shmem_fs.h>

#include <linux/swap.h>

#include <linux/uio.h>



#include <drm/drm_cache.h>
@@ -400,12 +401,12 @@ static int 
shmem_pwrite(struct drm_i915_gem_object *obj,

	     const struct drm_i915_gem_pwrite *arg)

{

	struct address_space *mapping = obj->base.filp->f_mapping;

	const struct address_space_operations *aops = mapping->a_ops;

	char __user *user_data = u64_to_user_ptr(arg->data_ptr);

	u64 remain;

	loff_t pos;

	unsigned int pg;

	struct file *file = obj->base.filp;

	struct kiocb kiocb;

	struct iov_iter iter;

	ssize_t written;

	u64 size = arg->size;



	/* Caller already validated user args */

	GEM_BUG_ON(!access_ok(user_data, arg->size));
@@ -428,63 +429,24 @@ shmem_pwrite(struct drm_i915_gem_object *obj, 
	if (obj->mm.madv != I915_MADV_WILLNEED)

		return -EFAULT;



	/*

	 * Before the pages are instantiated the object is treated as being

	 * in the CPU domain. The pages will be clflushed as required before

	 * use, and we can freely write into the pages directly. If userspace

	 * races pwrite with any other operation; corruption will ensue -

	 * that is userspace's prerogative!

	 */



	remain = arg->size;

	pos = arg->offset;

	pg = offset_in_page(pos);



	do {

		unsigned int len, unwritten;

		struct folio *folio;

		void *data, *vaddr;

		int err;

		char __maybe_unused c;

	if (size > MAX_RW_COUNT)

		return -EFBIG;



		len = PAGE_SIZE - pg;

		if (len > remain)

			len = remain;

	if (!file->f_op->write_iter)

		return -EINVAL;



		/* Prefault the user page to reduce potential recursion */

		err = __get_user(c, user_data);

		if (err)

			return err;

	init_sync_kiocb(&kiocb, file);

	kiocb.ki_pos = arg->offset;

	iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)user_data, size);



		err = __get_user(c, user_data + len - 1);

		if (err)

			return err;

	written = file->f_op->write_iter(&kiocb, &iter);

	BUG_ON(written == -EIOCBQUEUED);



		err = aops->write_begin(obj->base.filp, mapping, pos, len,

					&folio, &data);

		if (err < 0)

			return err;

	if (written != size)

		return -EIO;



		vaddr = kmap_local_folio(folio, offset_in_folio(folio, pos));

		pagefault_disable();

		unwritten = __copy_from_user_inatomic(vaddr, user_data, len);

		pagefault_enable();

		kunmap_local(vaddr);



		err = aops->write_end(obj->base.filp, mapping, pos, len,

				      len - unwritten, folio, data);

		if (err < 0)

			return err;



		/* We don't handle -EFAULT, leave it to the caller to check */

		if (unwritten)

			return -ENODEV;



		remain -= len;

		user_data += len;

		pos += len;

		pg = 0;

	} while (remain);

	if (written < 0)

		return written;



	return 0;

}
@@ -637,9 +599,8 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, 
{

	struct drm_i915_gem_object *obj;

	struct file *file;

	const struct address_space_operations *aops;

	loff_t pos;

	int err;

	loff_t pos = 0;

	ssize_t err;



	GEM_WARN_ON(IS_DGFX(i915));

	obj = i915_gem_object_create_shmem(i915, round_up(size, PAGE_SIZE));
@@ -649,29 +610,15 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, 
	GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU);



	file = obj->base.filp;

	aops = file->f_mapping->a_ops;

	pos = 0;

	do {

		unsigned int len = min_t(typeof(size), size, PAGE_SIZE);

		struct folio *folio;

		void *fsdata;

	err = kernel_write(file, data, size, &pos);



		err = aops->write_begin(file, file->f_mapping, pos, len,

					&folio, &fsdata);

	if (err < 0)

		goto fail;



		memcpy_to_folio(folio, offset_in_folio(folio, pos), data, len);



		err = aops->write_end(file, file->f_mapping, pos, len, len,

				      folio, fsdata);

		if (err < 0)

	if (err != size) {

		err = -EIO;

		goto fail;



		size -= len;

		data += len;

		pos += len;

	} while (size);

	}



	return obj;

fs/adfs/inode.c

+5 −4
Original line number Diff line number Diff line
@@ -53,13 +53,14 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to) 
		truncate_pagecache(inode, inode->i_size);

}



static int adfs_write_begin(struct file *file, struct address_space *mapping,

static int adfs_write_begin(const struct kiocb *iocb,

			    struct address_space *mapping,

			    loff_t pos, unsigned len,

			    struct folio **foliop, void **fsdata)

{

	int ret;



	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,

	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,

				adfs_get_block,

				&ADFS_I(mapping->host)->mmu_private);

	if (unlikely(ret))