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
...
Sphinx complains that ep_get_upwards_depth_proc() has a kerneldoc-style
comment without documenting its parameters.
This is an internal function that was not meant to show up in kernel
documentation, so fix the warning by changing the comment to a
non-kerneldoc one.
Fixes: 22bacca48a17 ("epoll: prevent creating circular epoll structures")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/r/20250717173655.10ecdce6@canb.auug.org.au
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202507171958.aMcW08Cn-lkp@intel.com/
Signed-off-by: Jann Horn <jannh@google.com>
Link: https://lore.kernel.org/20250721-epoll-sphinx-fix-v1-1-b695c92bf009@google.com
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Ensure that epoll instances can never form a graph deeper than
EP_MAX_NESTS+1 links.
Currently, ep_loop_check_proc() ensures that the graph is loop-free and
does some recursion depth checks, but those recursion depth checks don't
limit the depth of the resulting tree for two reasons:
- They don't look upwards in the tree.
- If there are multiple downwards paths of different lengths, only one of
the paths is actually considered for the depth check since commit
28d82dc1c4ed ("epoll: limit paths").
Essentially, the current recursion depth check in ep_loop_check_proc() just
serves to prevent it from recursing too deeply while checking for loops.
A more thorough check is done in reverse_path_check() after the new graph
edge has already been created; this checks, among other things, that no
paths going upwards from any non-epoll file with a length of more than 5
edges exist. However, this check does not apply to non-epoll files.
As a result, it is possible to recurse to a depth of at least roughly 500,
tested on v6.15. (I am unsure if deeper recursion is possible; and this may
have changed with commit 8c44dac8add7 ("eventpoll: Fix priority inversion
problem").)
To fix it:
1. In ep_loop_check_proc(), note the subtree depth of each visited node,
and use subtree depths for the total depth calculation even when a subtree
has already been visited.
2. Add ep_get_upwards_depth_proc() for similarly determining the maximum
depth of an upwards walk.
3. In ep_loop_check(), use these values to limit the total path length
between epoll nodes to EP_MAX_NESTS edges.
Fixes: 22bacca48a17 ("epoll: prevent creating circular epoll structures")
Cc: stable@vger.kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Link: https://lore.kernel.org/20250711-epoll-recursion-fix-v1-1-fb2457c33292@google.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
This reverts commit 8c44dac8add7503c345c0f6c7962e4863b88ba42. I haven't figured out what the actual bug in this commit is, but I did spend a lot of time chasing it down and eventually succeeded in bisecting it down to this. For some reason, this eventpoll commit ends up causing delays and stuck user space processes, but it only happens on one of my machines, and only during early boot or during the flurry of initial activity when logging in. I must be triggering some very subtle timing issue, but once I figured out the behavior pattern that made it reasonably reliable to trigger, it did bisect right to this, and reverting the commit fixes the problem. Of course, that was only after I had failed at bisecting it several times, and had flailed around blaming both the drm people and the netlink people for the odd problems. The most obvious of which happened at the time of the first graphical login (the most common symptom being that some gnome app aborted due to a 30s timeout, often leading to the whole session then failing if it was some critical component like gnome-shell or similar). Acked-by: Nam Cao <namcao@linutronix.de> Cc: Frederic Weisbecker <frederic@kernel.org> Cc: Valentin Schneider <vschneid@redhat.com> Cc: Christian Brauner <brauner@kernel.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jann Horn points out that epoll is decrementing the ep refcount and then
doing a
mutex_unlock(&ep->mtx);
afterwards. That's very wrong, because it can lead to a use-after-free.
That pattern is actually fine for the very last reference, because the
code in question will delay the actual call to "ep_free(ep)" until after
it has unlocked the mutex.
But it's wrong for the much subtler "next to last" case when somebody
*else* may also be dropping their reference and free the ep while we're
still using the mutex.
Note that this is true even if that other user is also using the same ep
mutex: mutexes, unlike spinlocks, can not be used for object ownership,
even if they guarantee mutual exclusion.
A mutex "unlock" operation is not atomic, and as one user is still
accessing the mutex as part of unlocking it, another user can come in
and get the now released mutex and free the data structure while the
first user is still cleaning up.
See our mutex documentation in Documentation/locking/mutex-design.rst,
in particular the section [1] about semantics:
"mutex_unlock() may access the mutex structure even after it has
internally released the lock already - so it's not safe for
another context to acquire the mutex and assume that the
mutex_unlock() context is not using the structure anymore"
So if we drop our ep ref before the mutex unlock, but we weren't the
last one, we may then unlock the mutex, another user comes in, drops
_their_ reference and releases the 'ep' as it now has no users - all
while the mutex_unlock() is still accessing it.
Fix this by simply moving the ep refcount dropping to outside the mutex:
the refcount itself is atomic, and doesn't need mutex protection (that's
the whole _point_ of refcounts: unlike mutexes, they are inherently
about object lifetimes).
Reported-by: Jann Horn <jannh@google.com>
Link: https://docs.kernel.org/locking/mutex-design.html#semantics [1]
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The ready event list of an epoll object is protected by read-write
semaphore:
- The consumer (waiter) acquires the write lock and takes items.
- the producer (waker) takes the read lock and adds items.
The point of this design is enabling epoll to scale well with large number
of producers, as multiple producers can hold the read lock at the same
time.
Unfortunately, this implementation may cause scheduling priority inversion
problem. Suppose the consumer has higher scheduling priority than the
producer. The consumer needs to acquire the write lock, but may be blocked
by the producer holding the read lock. Since read-write semaphore does not
support priority-boosting for the readers (even with CONFIG_PREEMPT_RT=y),
we have a case of priority inversion: a higher priority consumer is blocked
by a lower priority producer. This problem was reported in [1].
Furthermore, this could also cause stall problem, as described in [2].
To fix this problem, make the event list half-lockless:
- The consumer acquires a mutex (ep->mtx) and takes items.
- The producer locklessly adds items to the list.
Performance is not the main goal of this patch, but as the producer now can
add items without waiting for consumer to release the lock, performance
improvement is observed using the stress test from
https://github.com/rouming/test-tools/blob/master/stress-epoll.c. This is
the same test that justified using read-write semaphore in the past.
Testing using 12 x86_64 CPUs:
Before After Diff
threads events/ms events/ms
8 6932 19753 +185%
16 7820 27923 +257%
32 7648 35164 +360%
64 9677 37780 +290%
128 11166 38174 +242%
Testing using 1 riscv64 CPU (averaged over 10 runs, as the numbers are
noisy):
Before After Diff
threads events/ms events/ms
1 73 129 +77%
2 151 216 +43%
4 216 364 +69%
8 234 382 +63%
16 251 392 +56%
Reported-by: Frederic Weisbecker <frederic@kernel.org>
Closes: https://lore.kernel.org/linux-rt-users/20210825132754.GA895675@lothringen/ [1]
Reported-by: Valentin Schneider <vschneid@redhat.com>
Closes: https://lore.kernel.org/linux-rt-users/xhsmhttqvnall.mognet@vschneid.remote.csb/ [2]
Signed-off-by: Nam Cao <namcao@linutronix.de>
Link: https://lore.kernel.org/20250527090836.1290532-1-namcao@linutronix.de
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
After commit 0a65bc27bd64 ("eventpoll: Set epoll timeout if it's in
the future"), the following program would immediately enter a busy
loop in the kernel:
```
int main() {
int e = epoll_create1(0);
struct epoll_event event = {.events = EPOLLIN};
epoll_ctl(e, EPOLL_CTL_ADD, 0, &event);
const struct timespec timeout = {.tv_nsec = 1};
epoll_pwait2(e, &event, 1, &timeout, 0);
}
```
This happens because the given (non-zero) timeout of 1 nanosecond
usually expires before ep_poll() is entered and then
ep_schedule_timeout() returns false, but `timed_out` is never set
because the code line that sets it is skipped. This quickly turns
into a soft lockup, RCU stalls and deadlocks, inflicting severe
headaches to the whole system.
When the timeout has expired, we don't need to schedule a hrtimer, but
we should set the `timed_out` variable. Therefore, I suggest moving
the ep_schedule_timeout() check into the `timed_out` expression
instead of skipping it.
brauner: Note that there was an earlier fix by Joe Damato in response to
my bug report in [1].
Fixes: 0a65bc27bd64 ("eventpoll: Set epoll timeout if it's in the future")
Cc: Joe Damato <jdamato@fastly.com>
Cc: stable@vger.kernel.org
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Link: https://lore.kernel.org/20250429153419.94723-1-jdamato@fastly.com [1]
Link: https://lore.kernel.org/20250429185827.3564438-1-max.kellermann@ionos.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Avoid an edge case where epoll_wait arms a timer and calls schedule()
even if the timer will expire immediately.
For example: if the user has specified an epoll busy poll usecs which is
equal or larger than the epoll_wait/epoll_pwait2 timeout, it is
unnecessary to call schedule_hrtimeout_range; the busy poll usecs have
consumed the entire timeout duration so it is unnecessary to induce
scheduling latency by calling schedule() (via schedule_hrtimeout_range).
This can be measured using a simple bpftrace script:
tracepoint:sched:sched_switch
/ args->prev_pid == $1 /
{
print(kstack());
print(ustack());
}
Before this patch is applied:
Testing an epoll_wait app with busy poll usecs set to 1000, and
epoll_wait timeout set to 1ms using the script above shows:
__traceiter_sched_switch+69
__schedule+1495
schedule+32
schedule_hrtimeout_range+159
do_epoll_wait+1424
__x64_sys_epoll_wait+97
do_syscall_64+95
entry_SYSCALL_64_after_hwframe+118
epoll_wait+82
Which is unexpected; the busy poll usecs should have consumed the
entire timeout and there should be no reason to arm a timer.
After this patch is applied: the same test scenario does not generate a
call to schedule() in the above edge case. If the busy poll usecs are
reduced (for example usecs: 100, epoll_wait timeout 1ms) the timer is
armed as expected.
Fixes: bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.")
Signed-off-by: Joe Damato <jdamato@fastly.com>
Link: https://lore.kernel.org/20250416185826.26375-1-jdamato@fastly.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Pull networking updates from Jakub Kicinski:
"Core & protocols:
- Continue Netlink conversions to per-namespace RTNL lock
(IPv4 routing, routing rules, routing next hops, ARP ioctls)
- Continue extending the use of netdev instance locks. As a driver
opt-in protect queue operations and (in due course) ethtool
operations with the instance lock and not RTNL lock.
- Support collecting TCP timestamps (data submitted, sent, acked) in
BPF, allowing for transparent (to the application) and lower
overhead tracking of TCP RPC performance.
- Tweak existing networking Rx zero-copy infra to support zero-copy
Rx via io_uring.
- Optimize MPTCP performance in single subflow mode by 29%.
- Enable GRO on packets which went thru XDP CPU redirect (were queued
for processing on a different CPU). Improving TCP stream
performance up to 2x.
- Improve performance of contended connect() by 200% by searching for
an available 4-tuple under RCU rather than a spin lock. Bring an
additional 229% improvement by tweaking hash distribution.
- Avoid unconditionally touching sk_tsflags on RX, improving
performance under UDP flood by as much as 10%.
- Avoid skb_clone() dance in ping_rcv() to improve performance under
ping flood.
- Avoid FIB lookup in netfilter if socket is available, 20% perf win.
- Rework network device creation (in-kernel) API to more clearly
identify network namespaces and their roles. There are up to 4
namespace roles but we used to have just 2 netns pointer arguments,
interpreted differently based on context.
- Use sysfs_break_active_protection() instead of trylock to avoid
deadlocks between unregistering objects and sysfs access.
- Add a new sysctl and sockopt for capping max retransmit timeout in
TCP.
- Support masking port and DSCP in routing rule matches.
- Support dumping IPv4 multicast addresses with RTM_GETMULTICAST.
- Support specifying at what time packet should be sent on AF_XDP
sockets.
- Expose TCP ULP diagnostic info (for TLS and MPTCP) to non-admin
users.
- Add Netlink YAML spec for WiFi (nl80211) and conntrack.
- Introduce EXPORT_IPV6_MOD() and EXPORT_IPV6_MOD_GPL() for symbols
which only need to be exported when IPv6 support is built as a
module.
- Age FDB entries based on Rx not Tx traffic in VxLAN, similar to
normal bridging.
- Allow users to specify source port range for GENEVE tunnels.
- netconsole: allow attaching kernel release, CPU ID and task name to
messages as metadata
Driver API:
- Continue rework / fixing of Energy Efficient Ethernet (EEE) across
the SW layers. Delegate the responsibilities to phylink where
possible. Improve its handling in phylib.
- Support symmetric OR-XOR RSS hashing algorithm.
- Support tracking and preserving IRQ affinity by NAPI itself.
- Support loopback mode speed selection for interface selftests.
Device drivers:
- Remove the IBM LCS driver for s390
- Remove the sb1000 cable modem driver
- Add support for SFP module access over SMBus
- Add MCTP transport driver for MCTP-over-USB
- Enable XDP metadata support in multiple drivers
- Ethernet high-speed NICs:
- Broadcom (bnxt):
- add PCIe TLP Processing Hints (TPH) support for new AMD
platforms
- support dumping RoCE queue state for debug
- opt into instance locking
- Intel (100G, ice, idpf):
- ice: rework MSI-X IRQ management and distribution
- ice: support for E830 devices
- iavf: add support for Rx timestamping
- iavf: opt into instance locking
- nVidia/Mellanox:
- mlx4: use page pool memory allocator for Rx
- mlx5: support for one PTP device per hardware clock
- mlx5: support for 200Gbps per-lane link modes
- mlx5: move IPSec policy check after decryption
- AMD/Solarflare:
- support FW flashing via devlink
- Cisco (enic):
- use page pool memory allocator for Rx
- enable 32, 64 byte CQEs
- get max rx/tx ring size from the device
- Meta (fbnic):
- support flow steering and RSS configuration
- report queue stats
- support TCP segmentation
- support IRQ coalescing
- support ring size configuration
- Marvell/Cavium:
- support AF_XDP
- Wangxun:
- support for PTP clock and timestamping
- Huawei (hibmcge):
- checksum offload
- add more statistics
- Ethernet virtual:
- VirtIO net:
- aggressively suppress Tx completions, improve perf by 96%
with 1 CPU and 55% with 2 CPUs
- expose NAPI to IRQ mapping and persist NAPI settings
- Google (gve):
- support XDP in DQO RDA Queue Format
- opt into instance locking
- Microsoft vNIC:
- support BIG TCP
- Ethernet NICs consumer, and embedded:
- Synopsys (stmmac):
- cleanup Tx and Tx clock setting and other link-focused
cleanups
- enable SGMII and 2500BASEX mode switching for Intel platforms
- support Sophgo SG2044
- Broadcom switches (b53):
- support for BCM53101
- TI:
- iep: add perout configuration support
- icssg: support XDP
- Cadence (macb):
- implement BQL
- Xilinx (axinet):
- support dynamic IRQ moderation and changing coalescing at
runtime
- implement BQL
- report standard stats
- MediaTek:
- support phylink managed EEE
- Intel:
- igc: don't restart the interface on every XDP program change
- RealTek (r8169):
- support reading registers of internal PHYs directly
- increase max jumbo packet size on RTL8125/RTL8126
- Airoha:
- support for RISC-V NPU packet processing unit
- enable scatter-gather and support MTU up to 9kB
- Tehuti (tn40xx):
- support cards with TN4010 MAC and an Aquantia AQR105 PHY
- Ethernet PHYs:
- support for TJA1102S, TJA1121
- dp83tg720: add randomized polling intervals for link detection
- dp83822: support changing the transmit amplitude voltage
- support for LEDs on 88q2xxx
- CAN:
- canxl: support Remote Request Substitution bit access
- flexcan: add S32G2/S32G3 SoC
- WiFi:
- remove cooked monitor support
- strict mode for better AP testing
- basic EPCS support
- OMI RX bandwidth reduction support
- batman-adv: add support for jumbo frames
- WiFi drivers:
- RealTek (rtw88):
- support RTL8814AE and RTL8814AU
- RealTek (rtw89):
- switch using wiphy_lock and wiphy_work
- add BB context to manipulate two PHY as preparation of MLO
- improve BT-coexistence mechanism to play A2DP smoothly
- Intel (iwlwifi):
- add new iwlmld sub-driver for latest HW/FW combinations
- MediaTek (mt76):
- preparation for mt7996 Multi-Link Operation (MLO) support
- Qualcomm/Atheros (ath12k):
- continued work on MLO
- Silabs (wfx):
- Wake-on-WLAN support
- Bluetooth:
- add support for skb TX SND/COMPLETION timestamping
- hci_core: enable buffer flow control for SCO/eSCO
- coredump: log devcd dumps into the monitor
- Bluetooth drivers:
- intel: add support to configure TX power
- nxp: handle bootloader error during cmd5 and cmd7"
* tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1681 commits)
unix: fix up for "apparmor: add fine grained af_unix mediation"
mctp: Fix incorrect tx flow invalidation condition in mctp-i2c
net: usb: asix: ax88772: Increase phy_name size
net: phy: Introduce PHY_ID_SIZE — minimum size for PHY ID string
net: libwx: fix Tx L4 checksum
net: libwx: fix Tx descriptor content for some tunnel packets
atm: Fix NULL pointer dereference
net: tn40xx: add pci-id of the aqr105-based Tehuti TN4010 cards
net: tn40xx: prepare tn40xx driver to find phy of the TN9510 card
net: tn40xx: create swnode for mdio and aqr105 phy and add to mdiobus
net: phy: aquantia: add essential functions to aqr105 driver
net: phy: aquantia: search for firmware-name in fwnode
net: phy: aquantia: add probe function to aqr105 for firmware loading
net: phy: Add swnode support to mdiobus_scan
gve: add XDP DROP and PASS support for DQ
gve: update XDP allocation path support RX buffer posting
gve: merge packet buffer size fields
gve: update GQ RX to use buf_size
gve: introduce config-based allocation for XDP
gve: remove xdp_xsk_done and xdp_xsk_wakeup statistics
...
Pull vfs eventpoll updates from Christian Brauner: "This contains a few preparatory changes to eventpoll to allow io_uring to support epoll" * tag 'vfs-6.15-rc1.eventpoll' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: eventpoll: add epoll_sendevents() helper eventpoll: abstract out ep_try_send_events() helper eventpoll: abstract out parameter sanity checking