linux/fs
David Howells 219d92056b splice, net: Fix SPLICE_F_MORE signalling in splice_direct_to_actor()
splice_direct_to_actor() doesn't manage SPLICE_F_MORE correctly[1] - and,
as a result, it incorrectly signals/fails to signal MSG_MORE when splicing
to a socket.  The problem I'm seeing happens when a short splice occurs
because we got a short read due to hitting the EOF on a file: as the length
read (read_len) is less than the remaining size to be spliced (len),
SPLICE_F_MORE (and thus MSG_MORE) is set.

The issue is that, for the moment, we have no way to know *why* the short
read occurred and so can't make a good decision on whether we *should* keep
MSG_MORE set.

MSG_SENDPAGE_NOTLAST was added to work around this, but that is also set
incorrectly under some circumstances - for example if a short read fills a
single pipe_buffer, but the next read would return more (seqfile can do
this).

This was observed with the multi_chunk_sendfile tests in the tls kselftest
program.  Some of those tests would hang and time out when the last chunk
of file was less than the sendfile request size:

	build/kselftest/net/tls -r tls.12_aes_gcm.multi_chunk_sendfile

This has been observed before[2] and worked around in AF_TLS[3].

Fix this by making splice_direct_to_actor() always signal SPLICE_F_MORE if
we haven't yet hit the requested operation size.  SPLICE_F_MORE remains
signalled if the user passed it in to splice() but otherwise gets cleared
when we've read sufficient data to fulfill the request.

If, however, we get a premature EOF from ->splice_read(), have sent at
least one byte and SPLICE_F_MORE was not set by the caller, ->splice_eof()
will be invoked.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Linus Torvalds <torvalds@linux-foundation.org>
cc: Jens Axboe <axboe@kernel.dk>
cc: Christoph Hellwig <hch@lst.de>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: Matthew Wilcox <willy@infradead.org>
cc: Jan Kara <jack@suse.cz>
cc: Jeff Layton <jlayton@kernel.org>
cc: David Hildenbrand <david@redhat.com>
cc: Christian Brauner <brauner@kernel.org>
cc: Chuck Lever <chuck.lever@oracle.com>
cc: Boris Pismenny <borisp@nvidia.com>
cc: John Fastabend <john.fastabend@gmail.com>
cc: linux-mm@kvack.org

Link: https://lore.kernel.org/r/499791.1685485603@warthog.procyon.org.uk/ [1]
Link: https://lore.kernel.org/r/1591392508-14592-1-git-send-email-pooja.trivedi@stackpath.com/ [2]
Link: https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?id=d452d48b9f8b1a7f8152d33ef52cfd7fe1735b0a [3]
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-06-08 19:40:31 -07:00
..
9p Including fixes from netfilter. 2023-05-05 19:12:01 -07:00
adfs fs: port ->setattr() to pass mnt_idmap 2023-01-19 09:24:02 +01:00
affs for-6.3/dio-2023-02-16 2023-02-20 14:10:36 -08:00
afs afs: Fix setting of mtime when creating a file/dir/symlink 2023-06-07 09:03:12 -07:00
autofs fs: port ->permission() to pass mnt_idmap 2023-01-19 09:24:28 +01:00
befs befs: Convert befs_symlink_read_folio() to use a folio 2022-08-02 12:34:03 -04:00
bfs fs: port inode_init_owner() to mnt_idmap 2023-01-19 09:24:28 +01:00
btrfs for-6.4-rc4-tag 2023-06-02 17:16:19 -04:00
cachefiles fs/cachefiles: simplify one-level sysctl registration for cachefiles_sysctls 2023-04-13 11:49:35 -07:00
ceph ceph: force updating the msg pointer in non-split case 2023-05-18 11:15:28 +02:00
coda sysctl-6.4-rc1 2023-04-27 16:52:33 -07:00
configfs fs: consolidate duplicate dt_type helpers 2023-04-03 09:23:54 +02:00
cramfs fs/cramfs/inode.c: initialize file_ra_state 2023-03-02 21:54:23 -08:00
crypto fscrypt: optimize fscrypt_initialize() 2023-04-06 11:16:39 -07:00
debugfs ARM: SoC drivers for 6.3 2023-02-27 10:04:49 -08:00
devpts devpts: simplify two-level sysctl registration for pty_kern_table 2023-03-13 12:36:34 +01:00
dlm Networking changes for 6.4. 2023-04-26 16:07:23 -07:00
ecryptfs fs: drop unused posix acl handlers 2023-03-06 09:57:12 +01:00
efivarfs A healthy mix of EFI contributions this time: 2023-02-23 14:41:48 -08:00
efs
erofs erofs: use HIPRI by default if per-cpu kthreads are enabled 2023-05-23 16:57:08 +08:00
exfat Description for this pull request: 2023-03-01 08:42:27 -08:00
exportfs fs: port ->permission() to pass mnt_idmap 2023-01-19 09:24:28 +01:00
ext2 \n 2023-04-26 09:07:46 -07:00
ext4 Revert "ext4: remove ac->ac_found > sbi->s_mb_min_to_scan dead check in ext4_mb_check_limits" 2023-06-02 14:47:29 -04:00
f2fs f2fs update for 6.4-rc1 2023-04-26 09:42:10 -07:00
fat There is no particular theme here - mainly quick hits all over the tree. 2023-02-23 17:55:40 -08:00
freevxfs There is no particular theme here - mainly quick hits all over the tree. 2023-02-23 17:55:40 -08:00
fscache fscache: Use clear_and_wake_up_bit() in fscache_create_volume_work() 2023-01-30 12:51:54 +00:00
fuse Driver core changes for 6.4-rc1 2023-04-27 11:53:57 -07:00
gfs2 gfs2: Don't get stuck writing page onto itself under direct I/O 2023-06-01 14:55:43 +02:00
hfs There is no particular theme here - mainly quick hits all over the tree. 2023-02-23 17:55:40 -08:00
hfsplus fs: hfsplus: remove WARN_ON() from hfsplus_cat_{read,write}_inode() 2023-04-12 11:29:32 +02:00
hostfs um: hostfs: define our own API boundary 2023-04-20 23:04:40 +02:00
hpfs fs: port ->rename() to pass mnt_idmap 2023-01-19 09:24:26 +01:00
hugetlbfs mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area() 2023-04-21 14:52:05 -07:00
iomap New code for 6.4: 2023-04-29 10:35:48 -07:00
isofs - hfs and hfsplus kmap API modernization from Fabio Francesco 2022-10-12 11:00:22 -07:00
jbd2 jdb2: Don't refuse invalidation of already invalidated buffers 2023-04-14 19:38:50 -04:00
jffs2 fs: rename generic posix acl handlers 2023-03-06 09:57:13 +01:00
jfs write_one_page series 2023-04-24 19:20:27 -07:00
kernfs Driver core changes for 6.4-rc1 2023-04-27 11:53:57 -07:00
lockd nfsd-6.4 fixes: 2023-05-17 09:56:01 -07:00
minix Merge branch 'work.minix' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2023-02-24 19:01:15 -08:00
netfs Move netfs_extract_iter_to_sg() to lib/scatterlist.c 2023-06-08 13:42:33 +02:00
nfs NFSv4.2: Fix a potential double free with READ_PLUS 2023-05-19 17:11:59 -04:00
nfs_common NFSv4.2: remove MODULE_LICENSE in non-modules 2023-04-13 13:13:52 -07:00
nfsd nfsd-6.4 fixes: 2023-06-02 13:38:55 -04:00
nilfs2 nilfs2: fix use-after-free bug of nilfs_root in nilfs_evict_inode() 2023-05-17 15:24:34 -07:00
nls
notify inotify: Avoid reporting event with invalid wd 2023-04-25 12:36:55 +02:00
ntfs ntfs: simplfy one-level sysctl registration for ntfs_sysctls 2023-04-13 11:49:35 -07:00
ntfs3 driver ntfs3 for linux 6.4 2023-04-29 10:52:37 -07:00
ocfs2 Mainly singleton patches all over the place. Series of note are: 2023-04-27 19:57:00 -07:00
omfs fs: port inode_init_owner() to mnt_idmap 2023-01-19 09:24:28 +01:00
openpromfs
orangefs - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of 2023-04-27 19:42:02 -07:00
overlayfs ovl: check for ->listxattr() support 2023-03-06 09:57:13 +01:00
proc sysctl: remove register_sysctl_paths() 2023-05-02 19:24:16 -07:00
pstore pstore update for v6.4-rc1 2023-04-27 17:03:40 -07:00
qnx4 qnx4: credit contributors in CREDITS 2023-03-14 12:56:30 -06:00
qnx6 qnx6: credit contributor and mark filesystem orphan 2023-03-14 12:56:30 -06:00
quota quota: mark PRINT_QUOTA_WARNING as BROKEN 2023-04-14 13:06:50 +02:00
ramfs mm, treewide: redefine MAX_ORDER sanely 2023-04-05 19:42:46 -07:00
reiserfs \n 2023-04-26 09:07:46 -07:00
romfs mm/nommu: factor out check for NOMMU shared mappings into is_nommu_shared_mapping() 2023-01-18 17:12:56 -08:00
smb Drop the netfs_ prefix from netfs_extract_iter_to_sg() 2023-06-08 13:42:33 +02:00
squashfs revert "squashfs: harden sanity check in squashfs_read_xattr_id_table" 2023-02-03 17:52:25 -08:00
sysfs
sysv sysv: switch to put_and_unmap_page() 2023-03-12 20:03:41 -04:00
tracefs fs: port ->mkdir() to pass mnt_idmap 2023-01-19 09:24:26 +01:00
ubifs ubifs: Fix memleak when insert_old_idx() failed 2023-04-23 23:36:38 +02:00
udf udf: use wrapper i_blocksize() in udf_discard_prealloc() 2023-03-13 11:16:16 +01:00
ufs ufs: don't flush page immediately for DIRSYNC directories 2023-03-28 16:20:14 -07:00
unicode unicode: remove MODULE_LICENSE in non-modules 2023-04-13 13:13:54 -07:00
vboxsf fs: port ->rename() to pass mnt_idmap 2023-01-19 09:24:26 +01:00
verity fsverity: reject FS_IOC_ENABLE_VERITY on mode 3 fds 2023-04-11 19:23:23 -07:00
xfs xfs: collect errors from inodegc for unlinked inode recovery 2023-06-05 14:48:15 +10:00
zonefs zonefs: Do not propagate iomap_dio_rw() ENOTBLK error to user space 2023-03-30 20:56:02 +09:00
aio.c Merge branch 'mm-hotfixes-stable' into mm-stable 2023-02-10 15:34:48 -08:00
anon_inodes.c dynamic_dname(): drop unused dentry argument 2022-08-20 11:34:04 -04:00
attr.c nfs: use vfs setgid helper 2023-03-30 08:51:48 +02:00
bad_inode.c fs: port ->permission() to pass mnt_idmap 2023-01-19 09:24:28 +01:00
binfmt_elf_fdpic.c ELF: fix all "Elf" typos 2023-04-08 13:45:37 -07:00
binfmt_elf_test.c
binfmt_elf.c Mainly singleton patches all over the place. Series of note are: 2023-04-27 19:57:00 -07:00
binfmt_flat.c
binfmt_misc.c binfmt_misc: fix shift-out-of-bounds in check_special_flags 2022-12-02 13:57:04 -08:00
binfmt_script.c
buffer.c - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of 2023-04-27 19:42:02 -07:00
char_dev.c chardev: fix error handling in cdev_device_add() 2022-12-02 17:48:59 +01:00
compat_binfmt_elf.c
coredump.c fork, vhost: Use CLONE_THREAD to fix freezer/ps regression 2023-06-01 17:15:33 -04:00
d_path.c d_path.c: typo fix... 2022-08-20 11:34:33 -04:00
dax.c fsdax: force clear dirty mark if CoW 2023-04-05 18:06:23 -07:00
dcache.c tmpfile API change 2022-10-10 19:45:17 -07:00
direct-io.c __blockdev_direct_IO(): get rid of submit_io callback 2023-03-05 20:27:41 -05:00
drop_caches.c
eventfd.c eventfd: use wait_event_interruptible_locked_irq() helper 2023-04-06 10:01:50 +02:00
eventpoll.c Mainly singleton patches all over the place. Series of note are: 2023-04-27 19:57:00 -07:00
exec.c tracing updates for 6.4: 2023-04-28 15:57:53 -07:00
fcntl.c fs.idmapped.v6.3 2023-02-20 11:53:11 -08:00
fhandle.c do_sys_name_to_handle(): constify path 2022-09-01 17:36:39 -04:00
file_table.c filelock: move file locking definitions to separate header file 2023-01-11 06:52:32 -05:00
file.c fs: prevent out-of-bounds array speculation when closing a file descriptor 2023-03-09 22:46:21 -05:00
filesystems.c
fs_context.c
fs_parser.c ext4: journal_path mount options should follow links 2022-12-01 10:46:54 -05:00
fs_pin.c
fs_struct.c
fs_types.c
fs-writeback.c for-6.4/block-2023-05-06 2023-05-06 08:28:58 -07:00
fsopen.c
init.c fs: port ->permission() to pass mnt_idmap 2023-01-19 09:24:28 +01:00
inode.c - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of 2023-04-27 19:42:02 -07:00
internal.h five ksmbd server fixes, and new lock_rename_child VFS helper routine 2023-04-29 11:10:39 -07:00
ioctl.c fs: port inode_owner_or_capable() to mnt_idmap 2023-01-19 09:24:29 +01:00
Kconfig smb: move client and server files to common directory fs/smb 2023-05-24 16:29:21 -05:00
Kconfig.binfmt Xtensa updates for v6.1 2022-10-10 14:21:11 -07:00
kernel_read_file.c
libfs.c fs: consolidate duplicate dt_type helpers 2023-04-03 09:23:54 +02:00
locks.c filelocks: use mount idmapping for setlease permission check 2023-03-09 22:36:12 +01:00
Makefile smb: move client and server files to common directory fs/smb 2023-05-24 16:29:21 -05:00
mbcache.c ext4: fix deadlock due to mbcache entry corruption 2022-12-08 21:49:25 -05:00
mnt_idmapping.c fs: move mnt_idmap 2023-01-19 09:24:30 +01:00
mount.h
mpage.c mpage: use folios in bio end_io handler 2023-04-18 16:30:02 -07:00
namei.c five ksmbd server fixes, and new lock_rename_child VFS helper routine 2023-04-29 11:10:39 -07:00
namespace.c fget() to fdget() conversions 2023-04-24 19:14:20 -07:00
no-block.c
nsfs.c kill the last remaining user of proc_ns_fget() 2023-04-20 22:55:35 -04:00
open.c open: return EINVAL for O_DIRECTORY | O_CREAT 2023-03-22 11:06:55 +01:00
pipe.c pipe: check for IOCB_NOWAIT alongside O_NONBLOCK 2023-05-12 17:17:27 +02:00
pnode.c pnode: pass mountpoint directly 2023-04-06 14:53:38 +02:00
pnode.h
posix_acl.c acl: don't depend on IOP_XATTR 2023-03-06 09:59:20 +01:00
proc_namespace.c
read_write.c iov_iter: add iter_iov_addr() and iter_iov_len() helpers 2023-03-30 08:12:29 -06:00
readdir.c Change calling conventions for filldir_t 2022-08-17 17:25:04 -04:00
remap_range.c fs: port i_{g,u}id_into_vfs{g,u}id() to mnt_idmap 2023-01-19 09:24:29 +01:00
select.c
seq_file.c use less confusing names for iov_iter direction initializers 2022-11-25 13:01:55 -05:00
signalfd.c
splice.c splice, net: Fix SPLICE_F_MORE signalling in splice_direct_to_actor() 2023-06-08 19:40:31 -07:00
stack.c
stat.c fs.idmapped.v6.3 2023-02-20 11:53:11 -08:00
statfs.c statfs: enforce statfs[64] structure initialization 2023-05-17 15:20:17 +02:00
super.c mm: shrinkers: convert shrinker_rwsem to mutex 2023-03-28 16:20:17 -07:00
sync.c
sysctls.c
timerfd.c
userfaultfd.c - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of 2023-04-27 19:42:02 -07:00
utimes.c fs.idmapped.v6.3 2023-02-20 11:53:11 -08:00
xattr.c fs: don't call posix_acl_listxattr in generic_listxattr 2023-05-17 15:25:20 +02:00