| Age | Commit message (Collapse) | Author |
|---|
|
Under a high NFSv3 load with lots of different files being accessed,
the LRU list of garbage-collectable files can become quite long.
Asking list_lru_scan_node() to scan the whole list can result in a long
period during which a spinlock is held, blocking the addition of new LRU
items.
So ask list_lru_scan_node() to scan only a few entries at a time, and
repeat until the scan is complete.
If the shrinker runs between two consecutive calls of
list_lru_scan_node() it could invalidate the "remaining" counter which
could lead to premature freeing. So add a spinlock to avoid that.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
There is no need to remove a file from the lru every time we access it,
and then add it back. It is sufficient to set the REFERENCED flag every
time we put the file. The order in the lru of REFERENCED files is
largely irrelevant as they will all be moved to the end.
With this patch, files are added only when they are allocated (if
want_gc) and they are removed only by the list_lru_(shrink_)walk
callback or when forcibly removing a file.
This should reduce contention on the list_lru spinlock(s) and reduce
memory traffic a little.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
The filecache lru is walked in 2 circumstances for 2 different reasons.
1/ When called from the shrinker we want to discard the first few
entries on the list, ignoring any with NFSD_FILE_REFERENCED set
because they should really be at the end of the LRU as they have been
referenced recently. So those ones are ROTATED.
2/ When called from the nfsd_file_gc() timer function we want to discard
anything that hasn't been used since before the previous call, and
mark everything else as unused at this point in time.
Using the same flag for both of these can result in some unexpected
outcomes. If the shrinker callback clears NFSD_FILE_REFERENCED then
nfsd_file_gc() will think the file hasn't been used in a while, while
really it has.
I think it is easier to reason about the behaviour if we instead have
two flags.
NFSD_FILE_REFERENCED means "this should be at the end of the LRU, please
put it there when convenient"
NFSD_FILE_RECENT means "this has been used recently - since the last
run of nfsd_file_gc()
When either caller finds an NFSD_FILE_REFERENCED entry, that entry
should be moved to the end of the LRU and the flag cleared. This can
safely happen at any time. The actual order on the lru might not be
strictly least-recently-used, but that is normal for linux lrus.
The shrinker callback can ignore the "recent" flag. If it ends up
freeing something that is "recent" that simply means that memory
pressure is sufficient to limit the acceptable cache age to less than
the nfsd_file_gc frequency.
The gc callback should primarily focus on NFSD_FILE_RECENT. It should
free everything that doesn't have this flag set, and should clear the
flag on everything else. When it clears the flag it is convenient to
clear the "REFERENCED" flag and move to the end of the LRU too.
With this, calls from the shrinker do not prematurely age files. It
will focus only on freeing those that are least recently used.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
list_lru_walk() is only useful when the aim is to remove all elements
from the list_lru. It will repeatedly visit rotated elements of the
first per-node sublist before proceeding to subsequent sublists.
This patch changes nfsd_file_gc() to use list_lru_walk_node() and
list_lru_count_node() on each NUMA node.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
nfsd_file_close_inode_sync() contains an exact copy of
nfsd_file_dispose_list().
This patch removes that copy and calls nfsd_file_dispose_list()
instead.
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Dave opines:
IMO, there is no need to do this unnecessary work on every object
that is added to the LRU. Changing the gc worker to always run
every 2s and check if it has work to do like so:
static void
nfsd_file_gc_worker(struct work_struct *work)
{
- nfsd_file_gc();
- if (list_lru_count(&nfsd_file_lru))
- nfsd_file_schedule_laundrette();
+ if (list_lru_count(&nfsd_file_lru))
+ nfsd_file_gc();
+ nfsd_file_schedule_laundrette();
}
means that nfsd_file_gc() will be run the same way and have the same
behaviour as the current code. When the system it idle, it does a
list_lru_count() check every 2 seconds and goes back to sleep.
That's going to be pretty much unnoticable on most machines that run
NFS servers.
Suggested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
The race that this code tries to protect against is not interesting.
The code is problematic as we access the "nf" after we have given our
reference to the lru system. While that takes 2+ seconds to free
things, it is still poor form.
The only interesting race I can find would be with
nfsd_file_close_inode_sync();
This is the only place that really doesn't want the file to stay on the
LRU when unhashed (which is the direct consequence of the race).
However for the race to happen, some other thread must own a reference
to a file and be putting it while nfsd_file_close_inode_sync() is trying
to close all files for an inode. If this is possible, that other thread
could simply call nfsd_file_put() a little bit later and the result
would be the same: not all files are closed when
nfsd_file_close_inode_sync() completes.
If this was really a problem, we would need to wait in close_inode_sync
for the other references to be dropped. We probably don't want to do
that.
So it is best to simply remove this code.
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux
Pull nfsd fixes from Chuck Lever:
"Fixes for new bugs:
- A fix for CB_GETATTR reply decoding was not quite correct
- Fix the NFSD connection limiting logic
- Fix a bug in the new session table resizing logic
Bugs that pre-date v6.14:
- Support for courteous clients (5.19) introduced a shutdown hang
- Fix a crash in the filecache laundrette (6.9)
- Fix a zero-day crash in NFSD's NFSv3 ACL implementation"
* tag 'nfsd-6.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux:
NFSD: Fix CB_GETATTR status fix
NFSD: fix hang in nfsd4_shutdown_callback
nfsd: fix __fh_verify for localio
nfsd: fix uninitialised slot info when a request is retried
nfsd: validate the nfsd_serv pointer before calling svc_wake_up
nfsd: clear acl_access/acl_default after releasing them
|
|
nfsd_file_dispose_list_delayed can be called from the filecache
laundrette, which is shut down after the nfsd threads are shut down and
the nfsd_serv pointer is cleared. If nn->nfsd_serv is NULL then there
are no threads to wake.
Ensure that the nn->nfsd_serv pointer is non-NULL before calling
svc_wake_up in nfsd_file_dispose_list_delayed. This is safe since the
svc_serv is not freed until after the filecache laundrette is cancelled.
Reported-by: Salvatore Bonaccorso <carnil@debian.org>
Closes: https://bugs.debian.org/1093734
Fixes: ffb402596147 ("nfsd: Don't leave work of closing files to a work queue")
Cc: stable@vger.kernel.org
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Pull NFS client updates from Anna Schumaker:
"New Features:
- Enable using direct IO with localio
- Added localio related tracepoints
Bugfixes:
- Sunrpc fixes for working with a very large cl_tasks list
- Fix a possible buffer overflow in nfs_sysfs_link_rpc_client()
- Fixes for handling reconnections with localio
- Fix how the NFS_FSCACHE kconfig option interacts with NETFS_SUPPORT
- Fix COPY_NOTIFY xdr_buf size calculations
- pNFS/Flexfiles fix for retrying requesting a layout segment for
reads
- Sunrpc fix for retrying on EKEYEXPIRED error when the TGT is
expired
Cleanups:
- Various other nfs & nfsd localio cleanups
- Prepratory patches for async copy improvements that are under
development
- Make OFFLOAD_CANCEL, LAYOUTSTATS, and LAYOUTERR moveable to other
xprts
- Add netns inum and srcaddr to debugfs rpc_xprt info"
* tag 'nfs-for-6.14-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (28 commits)
SUNRPC: do not retry on EKEYEXPIRED when user TGT ticket expired
sunrpc: add netns inum and srcaddr to debugfs rpc_xprt info
pnfs/flexfiles: retry getting layout segment for reads
NFSv4.2: make LAYOUTSTATS and LAYOUTERROR MOVEABLE
NFSv4.2: mark OFFLOAD_CANCEL MOVEABLE
NFSv4.2: fix COPY_NOTIFY xdr buf size calculation
NFS: Rename struct nfs4_offloadcancel_data
NFS: Fix typo in OFFLOAD_CANCEL comment
NFS: CB_OFFLOAD can return NFS4ERR_DELAY
nfs: Make NFS_FSCACHE select NETFS_SUPPORT instead of depending on it
nfs: fix incorrect error handling in LOCALIO
nfs: probe for LOCALIO when v3 client reconnects to server
nfs: probe for LOCALIO when v4 client reconnects to server
nfs/localio: remove redundant code and simplify LOCALIO enablement
nfs_common: add nfs_localio trace events
nfs_common: track all open nfsd_files per LOCALIO nfs_client
nfs_common: rename nfslocalio nfs_uuid_lock to nfs_uuids_lock
nfsd: nfsd_file_acquire_local no longer returns GC'd nfsd_file
nfsd: rename nfsd_serv_ prefixed methods and variables with nfsd_net_
nfsd: update percpu_ref to manage references on nfsd_net
...
|
|
This tracking enables __nfsd_file_cache_purge() to call
nfs_localio_invalidate_clients(), upon shutdown or export change, to
nfs_close_local_fh() all open nfsd_files that are still cached by the
LOCALIO nfs clients associated with nfsd_net that is being shutdown.
Now that the client must track all open nfsd_files there was more work
than necessary being done with the global nfs_uuids_lock contended.
This manifested in various RCU issues, e.g.:
hrtimer: interrupt took 47969440 ns
rcu: INFO: rcu_sched detected stalls on CPUs/tasks:
Use nfs_uuid->lock to protect all nfs_uuid_t members, instead of
nfs_uuids_lock, once nfs_uuid_is_local() adds the client to
nn->local_clients.
Also add 'local_clients_lock' to 'struct nfsd_net' to protect
nn->local_clients. And store a pointer to spinlock in the 'list_lock'
member of nfs_uuid_t so nfs_localio_disable_client() can use it to
avoid taking the global nfs_uuids_lock.
In combination, these split out locks eliminate the use of the single
nfslocalio.c global nfs_uuids_lock in the IO paths (open and close).
Also refactored associated fs/nfs_common/nfslocalio.c methods' locking
to reduce work performed with spinlocks held in general.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
|
|
Now that LOCALIO no longer leans on NFSD's filecache for caching open
files (and instead uses NFS client-side open nfsd_file caching) there
is no need to use NFSD filecache's GC feature. Avoiding GC will speed
up nfsd_file initial opens.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
|
|
Also update Documentation/filesystems/nfs/localio.rst accordingly
and reduce the technical documentation debt that was previously
captured in that document.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
|
|
Rename all calls to revert_creds_light() back to revert_creds().
Link: https://lore.kernel.org/r/20241125-work-cred-v2-6-68b9d38bb5b2@kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
|
|
Convert all calls to revert_creds() over to explicitly dropping
reference counts in preparation for converting revert_creds() to
revert_creds_light() semantics.
Link: https://lore.kernel.org/r/20241125-work-cred-v2-3-68b9d38bb5b2@kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
|
|
Pull nfsd updates from Chuck Lever:
"Jeff Layton contributed a scalability improvement to NFSD's NFSv4
backchannel session implementation. This improvement is intended to
increase the rate at which NFSD can safely recall NFSv4 delegations
from clients, to avoid the need to revoke them. Revoking requires a
slow state recovery process.
A wide variety of bug fixes and other incremental improvements make up
the bulk of commits in this series. As always I am grateful to the
NFSD contributors, reviewers, testers, and bug reporters who
participated during this cycle"
* tag 'nfsd-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (72 commits)
nfsd: allow for up to 32 callback session slots
nfs_common: must not hold RCU while calling nfsd_file_put_local
nfsd: get rid of include ../internal.h
nfsd: fix nfs4_openowner leak when concurrent nfsd4_open occur
NFSD: Add nfsd4_copy time-to-live
NFSD: Add a laundromat reaper for async copy state
NFSD: Block DESTROY_CLIENTID only when there are ongoing async COPY operations
NFSD: Handle an NFS4ERR_DELAY response to CB_OFFLOAD
NFSD: Free async copy information in nfsd4_cb_offload_release()
NFSD: Fix nfsd4_shutdown_copy()
NFSD: Add a tracepoint to record canceled async COPY operations
nfsd: make nfsd4_session->se_flags a bool
nfsd: remove nfsd4_session->se_bchannel
nfsd: make use of warning provided by refcount_t
nfsd: Don't fail OP_SETCLIENTID when there are too many clients.
svcrdma: fix miss destroy percpu_counter in svc_rdma_proc_init()
xdrgen: Remove program_stat_to_errno() call sites
xdrgen: Update the files included in client-side source code
xdrgen: Remove check for "nfs_ok" in C templates
xdrgen: Remove tracepoint call site
...
|
|
Move holding the RCU from nfs_to_nfsd_file_put_local to
nfs_to_nfsd_net_put. It is the call to nfs_to->nfsd_serv_put that
requires the RCU anyway (the puts for nfsd_file and netns were
combined to avoid an extra indirect reference but that
micro-optimization isn't possible now).
This fixes xfstests generic/013 and it triggering:
"Voluntary context switch within RCU read-side critical section!"
[ 143.545738] Call Trace:
[ 143.546206] <TASK>
[ 143.546625] ? show_regs+0x6d/0x80
[ 143.547267] ? __warn+0x91/0x140
[ 143.547951] ? rcu_note_context_switch+0x496/0x5d0
[ 143.548856] ? report_bug+0x193/0x1a0
[ 143.549557] ? handle_bug+0x63/0xa0
[ 143.550214] ? exc_invalid_op+0x1d/0x80
[ 143.550938] ? asm_exc_invalid_op+0x1f/0x30
[ 143.551736] ? rcu_note_context_switch+0x496/0x5d0
[ 143.552634] ? wakeup_preempt+0x62/0x70
[ 143.553358] __schedule+0xaa/0x1380
[ 143.554025] ? _raw_spin_unlock_irqrestore+0x12/0x40
[ 143.554958] ? try_to_wake_up+0x1fe/0x6b0
[ 143.555715] ? wake_up_process+0x19/0x20
[ 143.556452] schedule+0x2e/0x120
[ 143.557066] schedule_preempt_disabled+0x19/0x30
[ 143.557933] rwsem_down_read_slowpath+0x24d/0x4a0
[ 143.558818] ? xfs_efi_item_format+0x50/0xc0 [xfs]
[ 143.559894] down_read+0x4e/0xb0
[ 143.560519] xlog_cil_commit+0x1b2/0xbc0 [xfs]
[ 143.561460] ? _raw_spin_unlock+0x12/0x30
[ 143.562212] ? xfs_inode_item_precommit+0xc7/0x220 [xfs]
[ 143.563309] ? xfs_trans_run_precommits+0x69/0xd0 [xfs]
[ 143.564394] __xfs_trans_commit+0xb5/0x330 [xfs]
[ 143.565367] xfs_trans_roll+0x48/0xc0 [xfs]
[ 143.566262] xfs_defer_trans_roll+0x57/0x100 [xfs]
[ 143.567278] xfs_defer_finish_noroll+0x27a/0x490 [xfs]
[ 143.568342] xfs_defer_finish+0x1a/0x80 [xfs]
[ 143.569267] xfs_bunmapi_range+0x4d/0xb0 [xfs]
[ 143.570208] xfs_itruncate_extents_flags+0x13d/0x230 [xfs]
[ 143.571353] xfs_free_eofblocks+0x12e/0x190 [xfs]
[ 143.572359] xfs_file_release+0x12d/0x140 [xfs]
[ 143.573324] __fput+0xe8/0x2d0
[ 143.573922] __fput_sync+0x1d/0x30
[ 143.574574] nfsd_filp_close+0x33/0x60 [nfsd]
[ 143.575430] nfsd_file_free+0x96/0x150 [nfsd]
[ 143.576274] nfsd_file_put+0xf7/0x1a0 [nfsd]
[ 143.577104] nfsd_file_put_local+0x18/0x30 [nfsd]
[ 143.578070] nfs_close_local_fh+0x101/0x110 [nfs_localio]
[ 143.579079] __put_nfs_open_context+0xc9/0x180 [nfs]
[ 143.580031] nfs_file_clear_open_context+0x4a/0x60 [nfs]
[ 143.581038] nfs_file_release+0x3e/0x60 [nfs]
[ 143.581879] __fput+0xe8/0x2d0
[ 143.582464] __fput_sync+0x1d/0x30
[ 143.583108] __x64_sys_close+0x41/0x80
[ 143.583823] x64_sys_call+0x189a/0x20d0
[ 143.584552] do_syscall_64+0x64/0x170
[ 143.585240] entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 143.586185] RIP: 0033:0x7f3c5153efd7
Fixes: 65f2a5c36635 ("nfs_common: fix race in NFS calls to nfsd_file_put_local() and nfsd_serv_put()")
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
refcount_t, by design, checks for unwanted situations and provides
warnings. It is rarely useful to have explicit warnings with refcount
usage.
In this case we have an explicit warning if a refcount_t reaches zero
when decremented. Simply using refcount_dec() will provide a similar
warning and also mark the refcount_t as saturated to avoid any possible
use-after-free.
This patch drops the warning and uses refcount_dec() instead of
refcount_dec_and_test().
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Now isolation no longer takes the list_lru global node lock, only use the
per-cgroup lock instead. And this lock is inside the list_lru_one being
walked, no longer needed to pass the lock explicitly.
Link: https://lkml.kernel.org/r/20241104175257.60853-7-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
|
Clean up: Commit 65294c1f2c5e ("nfsd: add a new struct file caching
facility to nfsd") moved the fh_verify() call site out of
nfsd_open(). That was the only user of nfsd_open's @rqstp parameter,
so that parameter can be removed.
Reviewed-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Pull NFS client fixes from Anna Schumaker:
"Localio Bugfixes:
- remove duplicated include in localio.c
- fix race in NFS calls to nfsd_file_put_local() and nfsd_serv_put()
- fix Kconfig for NFS_COMMON_LOCALIO_SUPPORT
- fix nfsd_file tracepoints to handle NULL rqstp pointers
Other Bugfixes:
- fix program selection loop in svc_process_common
- fix integer overflow in decode_rc_list()
- prevent NULL-pointer dereference in nfs42_complete_copies()
- fix CB_RECALL performance issues when using a large number of
delegations"
* tag 'nfs-for-6.12-2' of git://git.linux-nfs.org/projects/anna/linux-nfs:
NFS: remove revoked delegation from server's delegation list
nfsd/localio: fix nfsd_file tracepoints to handle NULL rqstp
nfs_common: fix Kconfig for NFS_COMMON_LOCALIO_SUPPORT
nfs_common: fix race in NFS calls to nfsd_file_put_local() and nfsd_serv_put()
NFSv4: Prevent NULL-pointer dereference in nfs42_complete_copies()
SUNRPC: Fix integer overflow in decode_rc_list()
sunrpc: fix prog selection loop in svc_process_common
nfs: Remove duplicated include in localio.c
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux
Pull nfsd fixes from Chuck Lever:
- Fix NFSD bring-up / shutdown
- Fix a UAF when releasing a stateid
* tag 'nfsd-6.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux:
nfsd: fix possible badness in FREE_STATEID
nfsd: nfsd_destroy_serv() must call svc_destroy() even if nfsd_startup_net() failed
NFSD: Mark filecache "down" if init fails
|
|
Add nfs_to_nfsd_file_put_local() interface to fix race with nfsd
module unload. Similarly, use RCU around nfs_open_local_fh()'s error
path call to nfs_to->nfsd_serv_put(). Holding RCU ensures that NFS
will safely _call and return_ from its nfs_to calls into the NFSD
functions nfsd_file_put_local() and nfsd_serv_put().
Otherwise, if RCU isn't used then there is a narrow window when NFS's
reference for the nfsd_file and nfsd_serv are dropped and the NFSD
module could be unloaded, which could result in a crash from the
return instruction for either nfs_to->nfsd_file_put_local() or
nfs_to->nfsd_serv_put().
Reported-by: NeilBrown <neilb@suse.de>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
|
|
[Syzbot reported]
WARNING: possible circular locking dependency detected
6.11.0-rc4-syzkaller-00019-gb311c1b497e5 #0 Not tainted
------------------------------------------------------
kswapd0/78 is trying to acquire lock:
ffff88801b8d8930 (&group->mark_mutex){+.+.}-{3:3}, at: fsnotify_group_lock include/linux/fsnotify_backend.h:270 [inline]
ffff88801b8d8930 (&group->mark_mutex){+.+.}-{3:3}, at: fsnotify_destroy_mark+0x38/0x3c0 fs/notify/mark.c:578
but task is already holding lock:
ffffffff8ea2fd60 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat mm/vmscan.c:6841 [inline]
ffffffff8ea2fd60 (fs_reclaim){+.+.}-{0:0}, at: kswapd+0xbb4/0x35a0 mm/vmscan.c:7223
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (fs_reclaim){+.+.}-{0:0}:
...
kmem_cache_alloc_noprof+0x3d/0x2a0 mm/slub.c:4044
inotify_new_watch fs/notify/inotify/inotify_user.c:599 [inline]
inotify_update_watch fs/notify/inotify/inotify_user.c:647 [inline]
__do_sys_inotify_add_watch fs/notify/inotify/inotify_user.c:786 [inline]
__se_sys_inotify_add_watch+0x72e/0x1070 fs/notify/inotify/inotify_user.c:729
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x77/0x7f
-> #0 (&group->mark_mutex){+.+.}-{3:3}:
...
__mutex_lock+0x136/0xd70 kernel/locking/mutex.c:752
fsnotify_group_lock include/linux/fsnotify_backend.h:270 [inline]
fsnotify_destroy_mark+0x38/0x3c0 fs/notify/mark.c:578
fsnotify_destroy_marks+0x14a/0x660 fs/notify/mark.c:934
fsnotify_inoderemove include/linux/fsnotify.h:264 [inline]
dentry_unlink_inode+0x2e0/0x430 fs/dcache.c:403
__dentry_kill+0x20d/0x630 fs/dcache.c:610
shrink_kill+0xa9/0x2c0 fs/dcache.c:1055
shrink_dentry_list+0x2c0/0x5b0 fs/dcache.c:1082
prune_dcache_sb+0x10f/0x180 fs/dcache.c:1163
super_cache_scan+0x34f/0x4b0 fs/super.c:221
do_shrink_slab+0x701/0x1160 mm/shrinker.c:435
shrink_slab+0x1093/0x14d0 mm/shrinker.c:662
shrink_one+0x43b/0x850 mm/vmscan.c:4815
shrink_many mm/vmscan.c:4876 [inline]
lru_gen_shrink_node mm/vmscan.c:4954 [inline]
shrink_node+0x3799/0x3de0 mm/vmscan.c:5934
kswapd_shrink_node mm/vmscan.c:6762 [inline]
balance_pgdat mm/vmscan.c:6954 [inline]
kswapd+0x1bcd/0x35a0 mm/vmscan.c:7223
[Analysis]
The problem is that inotify_new_watch() is using GFP_KERNEL to allocate
new watches under group->mark_mutex, however if dentry reclaim races
with unlinking of an inode, it can end up dropping the last dentry reference
for an unlinked inode resulting in removal of fsnotify mark from reclaim
context which wants to acquire group->mark_mutex as well.
This scenario shows that all notification groups are in principle prone
to this kind of a deadlock (previously, we considered only fanotify and
dnotify to be problematic for other reasons) so make sure all
allocations under group->mark_mutex happen with GFP_NOFS.
Reported-and-tested-by: syzbot+c679f13773f295d2da53@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=c679f13773f295d2da53
Signed-off-by: Lizhi Xu <lizhi.xu@windriver.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20240927143642.2369508-1-lizhi.xu@windriver.com
|
|
Add server support for bypassing NFS for localhost reads, writes, and
commits. This is only useful when both the client and server are
running on the same host.
If nfsd_open_local_fh() fails then the NFS client will both retry and
fallback to normal network-based read, write and commit operations if
localio is no longer supported.
Care is taken to ensure the same NFS security mechanisms are used
(authentication, etc) regardless of whether localio or regular NFS
access is used. The auth_domain established as part of the traditional
NFS client access to the NFS server is also used for localio. Store
auth_domain for localio in nfsd_uuid_t and transfer it to the client
if it is local to the server.
Relative to containers, localio gives the client access to the network
namespace the server has. This is required to allow the client to
access the server's per-namespace nfsd_net struct.
This commit also introduces the use of NFSD's percpu_ref to interlock
nfsd_destroy_serv and nfsd_open_local_fh, to ensure nn->nfsd_serv is
not destroyed while in use by nfsd_open_local_fh and other LOCALIO
client code.
CONFIG_NFS_LOCALIO enables NFS server support for LOCALIO.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Co-developed-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Co-developed-by: NeilBrown <neilb@suse.de>
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
|
|
The next commit will introduce nfsd_open_local_fh() which returns an
nfsd_file structure. This commit exposes LOCALIO's required NFSD
symbols to the NFS client:
- Make nfsd_open_local_fh() symbol and other required NFSD symbols
available to NFS in a global 'nfs_to' nfsd_localio_operations
struct (global access suggested by Trond, nfsd_localio_operations
suggested by NeilBrown). The next commit will also introduce
nfsd_localio_ops_init() that init_nfsd() will call to initialize
'nfs_to'.
- Introduce nfsd_file_file() that provides access to nfsd_file's
backing file. Keeps nfsd_file structure opaque to NFS client (as
suggested by Jeff Layton).
- Introduce nfsd_file_put_local() that will put the reference to the
nfsd_file's associated nn->nfsd_serv and then put the reference to
the nfsd_file (as suggested by NeilBrown).
Suggested-by: Trond Myklebust <trond.myklebust@hammerspace.com> # nfs_to
Suggested-by: NeilBrown <neilb@suse.de> # nfsd_localio_operations
Suggested-by: Jeff Layton <jlayton@kernel.org> # nfsd_file_file
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
|
|
nfsd_file_acquire_local() can be used to look up a file by filehandle
without having a struct svc_rqst. This can be used by NFS LOCALIO to
allow the NFS client to bypass the NFS protocol to directly access a
file provided by the NFS server which is running in the same kernel.
In nfsd_file_do_acquire() care is taken to always use fh_verify() if
rqstp is not NULL (as is the case for non-LOCALIO callers). Otherwise
the non-LOCALIO callers will not supply the correct and required
arguments to __fh_verify (e.g. gssclient isn't passed).
Introduce fh_verify_local() wrapper around __fh_verify to make it
clear that LOCALIO is intended caller.
Also, use GC for nfsd_file returned by nfsd_file_acquire_local. GC
offers performance improvements if/when a file is reopened before
launderette cleans it from the filecache's LRU.
Suggested-by: Jeff Layton <jlayton@kernel.org> # use filecache's GC
Signed-off-by: NeilBrown <neilb@suse.de>
Co-developed-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
|
|
NeilBrown says:
> The handling of NFSD_FILE_CACHE_UP is strange. nfsd_file_cache_init()
> sets it, but doesn't clear it on failure. So if nfsd_file_cache_init()
> fails for some reason, nfsd_file_cache_shutdown() would still try to
> clean up if it was called.
Reported-by: NeilBrown <neilb@suse.de>
Fixes: c7b824c3d06c ("NFSD: Replace the "init once" mechanism")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Commit 427f5f83a319 ("NFSD: Ensure nf_inode is never dereferenced") passes
inode directly to nfsd_file_mark_find_or_create instead of getting it from
nf, so there is no need to pass nf.
Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
After many rounds of changes in filecache.c, the fix by commit
ce7df055(NFSD: Make the file_delayed_close workqueue UNBOUND)
is gone, now we are getting syslog messages like these:
[ 1618.186688] workqueue: nfsd_file_gc_worker [nfsd] hogged CPU for >13333us 4 times, consider switching to WQ_UNBOUND
[ 1638.661616] workqueue: nfsd_file_gc_worker [nfsd] hogged CPU for >13333us 8 times, consider switching to WQ_UNBOUND
[ 1665.284542] workqueue: nfsd_file_gc_worker [nfsd] hogged CPU for >13333us 16 times, consider switching to WQ_UNBOUND
[ 1759.491342] workqueue: nfsd_file_gc_worker [nfsd] hogged CPU for >13333us 32 times, consider switching to WQ_UNBOUND
[ 3013.012308] workqueue: nfsd_file_gc_worker [nfsd] hogged CPU for >13333us 64 times, consider switching to WQ_UNBOUND
[ 3154.172827] workqueue: nfsd_file_gc_worker [nfsd] hogged CPU for >13333us 128 times, consider switching to WQ_UNBOUND
[ 3422.461924] workqueue: nfsd_file_gc_worker [nfsd] hogged CPU for >13333us 256 times, consider switching to WQ_UNBOUND
[ 3963.152054] workqueue: nfsd_file_gc_worker [nfsd] hogged CPU for >13333us 512 times, consider switching to WQ_UNBOUND
Consider use system_unbound_wq instead of system_wq for
nfsd_file_gc_worker().
Signed-off-by: Youzhong Yang <youzhong@gmail.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
We already count the frees (via nfsd_file_releases). Count the
allocations as well. Also switch the direct call to nfsd_file_slab_free
in nfsd_file_do_acquire to nfsd_file_free, so that the allocs and
releases match up.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
If we wait_for_construction and find that the file is no longer hashed,
and we're going to retry the open, the old nfsd_file reference is
currently leaked. Put the reference before retrying.
Fixes: c6593366c0bf ("nfsd: don't kill nfsd_files because of lease break error")
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Youzhong Yang <youzhong@gmail.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Given that we do the search and insertion while holding the i_lock, I
don't think it's possible for us to get EEXIST here. Remove this case.
Fixes: c6593366c0bf ("nfsd: don't kill nfsd_files because of lease break error")
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Youzhong Yang <youzhong@gmail.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
nfsd_file_put() in one thread can race with another thread doing
garbage collection (running nfsd_file_gc() -> list_lru_walk() ->
nfsd_file_lru_cb()):
* In nfsd_file_put(), nf->nf_ref is 1, so it tries to do nfsd_file_lru_add().
* nfsd_file_lru_add() returns true (with NFSD_FILE_REFERENCED bit set)
* garbage collector kicks in, nfsd_file_lru_cb() clears REFERENCED bit and
returns LRU_ROTATE.
* garbage collector kicks in again, nfsd_file_lru_cb() now decrements nf->nf_ref
to 0, runs nfsd_file_unhash(), removes it from the LRU and adds to the dispose
list [list_lru_isolate_move(lru, &nf->nf_lru, head)]
* nfsd_file_put() detects NFSD_FILE_HASHED bit is cleared, so it tries to remove
the 'nf' from the LRU [if (!nfsd_file_lru_remove(nf))]. The 'nf' has been added
to the 'dispose' list by nfsd_file_lru_cb(), so nfsd_file_lru_remove(nf) simply
treats it as part of the LRU and removes it, which leads to its removal from
the 'dispose' list.
* At this moment, 'nf' is unhashed with its nf_ref being 0, and not on the LRU.
nfsd_file_put() continues its execution [if (refcount_dec_and_test(&nf->nf_ref))],
as nf->nf_ref is already 0, nf->nf_ref is set to REFCOUNT_SATURATED, and the 'nf'
gets no chance of being freed.
nfsd_file_put() can also race with nfsd_file_cond_queue():
* In nfsd_file_put(), nf->nf_ref is 1, so it tries to do nfsd_file_lru_add().
* nfsd_file_lru_add() sets REFERENCED bit and returns true.
* Some userland application runs 'exportfs -f' or something like that, which triggers
__nfsd_file_cache_purge() -> nfsd_file_cond_queue().
* In nfsd_file_cond_queue(), it runs [if (!nfsd_file_unhash(nf))], unhash is done
successfully.
* nfsd_file_cond_queue() runs [if (!nfsd_file_get(nf))], now nf->nf_ref goes to 2.
* nfsd_file_cond_queue() runs [if (nfsd_file_lru_remove(nf))], it succeeds.
* nfsd_file_cond_queue() runs [if (refcount_sub_and_test(decrement, &nf->nf_ref))]
(with "decrement" being 2), so the nf->nf_ref goes to 0, the 'nf' is added to the
dispose list [list_add(&nf->nf_lru, dispose)]
* nfsd_file_put() detects NFSD_FILE_HASHED bit is cleared, so it tries to remove
the 'nf' from the LRU [if (!nfsd_file_lru_remove(nf))], although the 'nf' is not
in the LRU, but it is linked in the 'dispose' list, nfsd_file_lru_remove() simply
treats it as part of the LRU and removes it. This leads to its removal from
the 'dispose' list!
* Now nf->ref is 0, unhashed. nfsd_file_put() continues its execution and set
nf->nf_ref to REFCOUNT_SATURATED.
As shown in the above analysis, using nf_lru for both the LRU list and dispose list
can cause the leaks. This patch adds a new list_head nf_gc in struct nfsd_file, and uses
it for the dispose list. This does not fix the nfsd_file leaking issue completely.
Signed-off-by: Youzhong Yang <youzhong@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
"data" actually refers to a file_lease and not a file_lock. Both structs
have their file_lock_core as the first field though, so this bug should
be harmless without struct randomization in play.
Reported-by: Florian Evers <florian-evers@gmx.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219008
Fixes: 05580bbfc6bc ("nfsd: adapt to breakup of struct file_lock")
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Florian Evers <florian-evers@gmx.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
In preparation to passing an object pointer to fsnotify_find_mark(), add
a wrapper fsnotify_find_inode_mark() and use it where possible.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Message-Id: <20240317184154.1200192-4-amir73il@gmail.com>
|
|
Pull nfsd updates from Chuck Lever:
"The bulk of the patches for this release are optimizations, code
clean-ups, and minor bug fixes.
One new feature to mention is that NFSD administrators now have the
ability to revoke NFSv4 open and lock state. NFSD's NFSv3 support has
had this capability for some time.
As always I am grateful to NFSD contributors, reviewers, and testers"
* tag 'nfsd-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (75 commits)
NFSD: Clean up nfsd4_encode_replay()
NFSD: send OP_CB_RECALL_ANY to clients when number of delegations reaches its limit
NFSD: Document nfsd_setattr() fill-attributes behavior
nfsd: Fix NFSv3 atomicity bugs in nfsd_setattr()
nfsd: Fix a regression in nfsd_setattr()
NFSD: OP_CB_RECALL_ANY should recall both read and write delegations
NFSD: handle GETATTR conflict with write delegation
NFSD: add support for CB_GETATTR callback
NFSD: Document the phases of CREATE_SESSION
NFSD: Fix the NFSv4.1 CREATE_SESSION operation
nfsd: clean up comments over nfs4_client definition
svcrdma: Add Write chunk WRs to the RPC's Send WR chain
svcrdma: Post WRs for Write chunks in svc_rdma_sendto()
svcrdma: Post the Reply chunk and Send WR together
svcrdma: Move write_info for Reply chunks into struct svc_rdma_send_ctxt
svcrdma: Post Send WR chain
svcrdma: Fix retry loop in svc_rdma_send()
svcrdma: Prevent a UAF in svc_rdma_send()
svcrdma: Fix SQ wake-ups
svcrdma: Increase the per-transport rw_ctx count
...
|
|
Use the new KMEM_CACHE() macro instead of direct kmem_cache_create
to simplify the creation of SLAB caches.
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Acked-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Calling fput() directly or though filp_close() from a kernel thread like
nfsd causes the final __fput() (if necessary) to be called from a
workqueue. This means that nfsd is not forced to wait for any work to
complete. If the ->release or ->destroy_inode function is slow for any
reason, this can result in nfsd closing files more quickly than the
workqueue can complete the close and the queue of pending closes can
grow without bounces (30 million has been seen at one customer site,
though this was in part due to a slowness in xfs which has since been
fixed).
nfsd does not need this. It is quite appropriate and safe for nfsd to
do its own close work. There is no reason that close should ever wait
for nfsd, so no deadlock can occur.
It should be safe and sensible to change all fput() calls to
__fput_sync(). However in the interests of caution this patch only
changes two - the two that can be most directly affected by client
behaviour and could occur at high frequency.
- the fput() implicitly in flip_close() is changed to __fput_sync()
by calling get_file() first to ensure filp_close() doesn't do
the final fput() itself. If is where files opened for IO are closed.
- the fput() in nfsd_read() is also changed. This is where directories
opened for readdir are closed.
This ensure that minimal fput work is queued to the workqueue.
This removes the need for the flush_delayed_fput() call in
nfsd_file_close_inode_sync()
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
The work of closing a file can have non-trivial cost. Doing it in a
separate work queue thread means that cost isn't imposed on the nfsd
threads and an imbalance can be created. This can result in files being
queued for the work queue more quickly that the work queue can process
them, resulting in unbounded growth of the queue and memory exhaustion.
To avoid this work imbalance that exhausts memory, this patch moves all
closing of files into the nfsd threads. This means that when the work
imposes a cost, that cost appears where it would be expected - in the
work of the nfsd thread. A subsequent patch will ensure the final
__fput() is called in the same (nfsd) thread which calls filp_close().
Files opened for NFSv3 are never explicitly closed by the client and are
kept open by the server in the "filecache", which responds to memory
pressure, is garbage collected even when there is no pressure, and
sometimes closes files when there is particular need such as for rename.
These files currently have filp_close() called in a dedicated work
queue, so their __fput() can have no effect on nfsd threads.
This patch discards the work queue and instead has each nfsd thread call
flip_close() on as many as 8 files from the filecache each time it acts
on a client request (or finds there are no pending client requests). If
there are more to be closed, more threads are woken. This spreads the
work of __fput() over multiple threads and imposes any cost on those
threads.
The number 8 is somewhat arbitrary. It needs to be greater than 1 to
ensure that files are closed more quickly than they can be added to the
cache. It needs to be small enough to limit the per-request delays that
will be imposed on clients when all threads are busy closing files.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Most of the existing APIs have remained the same, but subsystems that
access file_lock fields directly need to reach into struct
file_lock_core now.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20240131-flsplit-v3-42-c6129007ee8d@kernel.org
Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
|
|
Pull nfsd updates from Chuck Lever:
"The bulk of the patches for this release are clean-ups and minor bug
fixes.
There is one significant revert to mention: support for RDMA Read
operations in the server's RPC-over-RDMA transport implementation has
been fixed so it waits for Read completion in a way that avoids tying
up an nfsd thread. This prevents a possible DoS vector if an
RPC-over-RDMA client should become unresponsive during RDMA Read
operations.
As always I am grateful to NFSD contributors, reviewers, and testers"
* tag 'nfsd-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (56 commits)
nfsd: rename nfsd_last_thread() to nfsd_destroy_serv()
SUNRPC: discard sv_refcnt, and svc_get/svc_put
svc: don't hold reference for poolstats, only mutex.
SUNRPC: remove printk when back channel request not found
svcrdma: Implement multi-stage Read completion again
svcrdma: Copy construction of svc_rqst::rq_arg to rdma_read_complete()
svcrdma: Add back svcxprt_rdma::sc_read_complete_q
svcrdma: Add back svc_rdma_recv_ctxt::rc_pages
svcrdma: Clean up comment in svc_rdma_accept()
svcrdma: Remove queue-shortening warnings
svcrdma: Remove pointer addresses shown in dprintk()
svcrdma: Optimize svc_rdma_cc_init()
svcrdma: De-duplicate completion ID initialization helpers
svcrdma: Move the svc_rdma_cc_init() call
svcrdma: Remove struct svc_rdma_read_info
svcrdma: Update the synopsis of svc_rdma_read_special()
svcrdma: Update the synopsis of svc_rdma_read_call_chunk()
svcrdma: Update synopsis of svc_rdma_read_multiple_chunks()
svcrdma: Update synopsis of svc_rdma_copy_inline_range()
svcrdma: Update the synopsis of svc_rdma_read_data_item()
...
|
|
workqueue: nfsd_file_delayed_close [nfsd] hogged CPU for >13333us 8
times, consider switching to WQ_UNBOUND
There's no harm in closing a cached file descriptor on another core.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Patch series "workload-specific and memory pressure-driven zswap
writeback", v8.
There are currently several issues with zswap writeback:
1. There is only a single global LRU for zswap, making it impossible to
perform worload-specific shrinking - an memcg under memory pressure
cannot determine which pages in the pool it owns, and often ends up
writing pages from other memcgs. This issue has been previously
observed in practice and mitigated by simply disabling
memcg-initiated shrinking:
https://lore.kernel.org/all/20230530232435.3097106-1-nphamcs@gmail.com/T/#u
But this solution leaves a lot to be desired, as we still do not
have an avenue for an memcg to free up its own memory locked up in
the zswap pool.
2. We only shrink the zswap pool when the user-defined limit is hit.
This means that if we set the limit too high, cold data that are
unlikely to be used again will reside in the pool, wasting precious
memory. It is hard to predict how much zswap space will be needed
ahead of time, as this depends on the workload (specifically, on
factors such as memory access patterns and compressibility of the
memory pages).
This patch series solves these issues by separating the global zswap LRU
into per-memcg and per-NUMA LRUs, and performs workload-specific (i.e
memcg- and NUMA-aware) zswap writeback under memory pressure. The new
shrinker does not have any parameter that must be tuned by the user, and
can be opted in or out on a per-memcg basis.
As a proof of concept, we ran the following synthetic benchmark: build the
linux kernel in a memory-limited cgroup, and allocate some cold data in
tmpfs to see if the shrinker could write them out and improved the overall
performance. Depending on the amount of cold data generated, we observe
from 14% to 35% reduction in kernel CPU time used in the kernel builds.
This patch (of 6):
The interface of list_lru is based on the assumption that the list node
and the data it represents belong to the same allocated on the correct
node/memcg. While this assumption is valid for existing slab objects LRU
such as dentries and inodes, it is undocumented, and rather inflexible for
certain potential list_lru users (such as the upcoming zswap shrinker and
the THP shrinker). It has caused us a lot of issues during our
development.
This patch changes list_lru interface so that the caller must explicitly
specify numa node and memcg when adding and removing objects. The old
list_lru_add() and list_lru_del() are renamed to list_lru_add_obj() and
list_lru_del_obj(), respectively.
It also extends the list_lru API with a new function, list_lru_putback,
which undoes a previous list_lru_isolate call. Unlike list_lru_add, it
does not increment the LRU node count (as list_lru_isolate does not
decrement the node count). list_lru_putback also allows for explicit
memcg and NUMA node selection.
Link: https://lkml.kernel.org/r/20231130194023.4102148-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20231130194023.4102148-2-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
"Many singleton patches against the MM code. The patch series which are
included in this merge do the following:
- Kemeng Shi has contributed some compation maintenance work in the
series 'Fixes and cleanups to compaction'
- Joel Fernandes has a patchset ('Optimize mremap during mutual
alignment within PMD') which fixes an obscure issue with mremap()'s
pagetable handling during a subsequent exec(), based upon an
implementation which Linus suggested
- More DAMON/DAMOS maintenance and feature work from SeongJae Park i
the following patch series:
mm/damon: misc fixups for documents, comments and its tracepoint
mm/damon: add a tracepoint for damos apply target regions
mm/damon: provide pseudo-moving sum based access rate
mm/damon: implement DAMOS apply intervals
mm/damon/core-test: Fix memory leaks in core-test
mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval
- In the series 'Do not try to access unaccepted memory' Adrian
Hunter provides some fixups for the recently-added 'unaccepted
memory' feature. To increase the feature's checking coverage. 'Plug
a few gaps where RAM is exposed without checking if it is
unaccepted memory'
- In the series 'cleanups for lockless slab shrink' Qi Zheng has done
some maintenance work which is preparation for the lockless slab
shrinking code
- Qi Zheng has redone the earlier (and reverted) attempt to make slab
shrinking lockless in the series 'use refcount+RCU method to
implement lockless slab shrink'
- David Hildenbrand contributes some maintenance work for the rmap
code in the series 'Anon rmap cleanups'
- Kefeng Wang does more folio conversions and some maintenance work
in the migration code. Series 'mm: migrate: more folio conversion
and unification'
- Matthew Wilcox has fixed an issue in the buffer_head code which was
causing long stalls under some heavy memory/IO loads. Some cleanups
were added on the way. Series 'Add and use bdev_getblk()'
- In the series 'Use nth_page() in place of direct struct page
manipulation' Zi Yan has fixed a potential issue with the direct
manipulation of hugetlb page frames
- In the series 'mm: hugetlb: Skip initialization of gigantic tail
struct pages if freed by HVO' has improved our handling of gigantic
pages in the hugetlb vmmemmep optimizaton code. This provides
significant boot time improvements when significant amounts of
gigantic pages are in use
- Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code
rationalization and folio conversions in the hugetlb code
- Yin Fengwei has improved mlock()'s handling of large folios in the
series 'support large folio for mlock'
- In the series 'Expose swapcache stat for memcg v1' Liu Shixin has
added statistics for memcg v1 users which are available (and
useful) under memcg v2
- Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable)
prctl so that userspace may direct the kernel to not automatically
propagate the denial to child processes. The series is named 'MDWE
without inheritance'
- Kefeng Wang has provided the series 'mm: convert numa balancing
functions to use a folio' which does what it says
- In the series 'mm/ksm: add fork-exec support for prctl' Stefan
Roesch makes is possible for a process to propagate KSM treatment
across exec()
- Huang Ying has enhanced memory tiering's calculation of memory
distances. This is used to permit the dax/kmem driver to use 'high
bandwidth memory' in addition to Optane Data Center Persistent
Memory Modules (DCPMM). The series is named 'memory tiering:
calculate abstract distance based on ACPI HMAT'
- In the series 'Smart scanning mode for KSM' Stefan Roesch has
optimized KSM by teaching it to retain and use some historical
information from previous scans
- Yosry Ahmed has fixed some inconsistencies in memcg statistics in
the series 'mm: memcg: fix tracking of pending stats updates
values'
- In the series 'Implement IOCTL to get and optionally clear info
about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap
which permits us to atomically read-then-clear page softdirty
state. This is mainly used by CRIU
- Hugh Dickins contributed the series 'shmem,tmpfs: general
maintenance', a bunch of relatively minor maintenance tweaks to
this code
- Matthew Wilcox has increased the use of the VMA lock over
file-backed page faults in the series 'Handle more faults under the
VMA lock'. Some rationalizations of the fault path became possible
as a result
- In the series 'mm/rmap: convert page_move_anon_rmap() to
folio_move_anon_rmap()' David Hildenbrand has implemented some
cleanups and folio conversions
- In the series 'various improvements to the GUP interface' Lorenzo
Stoakes has simplified and improved the GUP interface with an eye
to providing groundwork for future improvements
- Andrey Konovalov has sent along the series 'kasan: assorted fixes
and improvements' which does those things
- Some page allocator maintenance work from Kemeng Shi in the series
'Two minor cleanups to break_down_buddy_pages'
- In thes series 'New selftest for mm' Breno Leitao has developed
another MM self test which tickles a race we had between madvise()
and page faults
- In the series 'Add folio_end_read' Matthew Wilcox provides cleanups
and an optimization to the core pagecache code
- Nhat Pham has added memcg accounting for hugetlb memory in the
series 'hugetlb memcg accounting'
- Cleanups and rationalizations to the pagemap code from Lorenzo
Stoakes, in the series 'Abstract vma_merge() and split_vma()'
- Audra Mitchell has fixed issues in the procfs page_owner code's new
timestamping feature which was causing some misbehaviours. In the
series 'Fix page_owner's use of free timestamps'
- Lorenzo Stoakes has fixed the handling of new mappings of sealed
files in the series 'permit write-sealed memfd read-only shared
mappings'
- Mike Kravetz has optimized the hugetlb vmemmap optimization in the
series 'Batch hugetlb vmemmap modification operations'
- Some buffer_head folio conversions and cleanups from Matthew Wilcox
in the series 'Finish the create_empty_buffers() transition'
- As a page allocator performance optimization Huang Ying has added
automatic tuning to the allocator's per-cpu-pages feature, in the
series 'mm: PCP high auto-tuning'
- Roman Gushchin has contributed the patchset 'mm: improve
performance of accounted kernel memory allocations' which improves
their performance by ~30% as measured by a micro-benchmark
- folio conversions from Kefeng Wang in the series 'mm: convert page
cpupid functions to folios'
- Some kmemleak fixups in Liu Shixin's series 'Some bugfix about
kmemleak'
- Qi Zheng has improved our handling of memoryless nodes by keeping
them off the allocation fallback list. This is done in the series
'handle memoryless nodes more appropriately'
- khugepaged conversions from Vishal Moola in the series 'Some
khugepaged folio conversions'"
[ bcachefs conflicts with the dynamically allocated shrinkers have been
resolved as per Stephen Rothwell in
https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/
with help from Qi Zheng.
The clone3 test filtering conflict was half-arsed by yours truly ]
* tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits)
mm/damon/sysfs: update monitoring target regions for online input commit
mm/damon/sysfs: remove requested targets when online-commit inputs
selftests: add a sanity check for zswap
Documentation: maple_tree: fix word spelling error
mm/vmalloc: fix the unchecked dereference warning in vread_iter()
zswap: export compression failure stats
Documentation: ubsan: drop "the" from article title
mempolicy: migration attempt to match interleave nodes
mempolicy: mmap_lock is not needed while migrating folios
mempolicy: alloc_pages_mpol() for NUMA policy without vma
mm: add page_rmappable_folio() wrapper
mempolicy: remove confusing MPOL_MF_LAZY dead code
mempolicy: mpol_shared_policy_init() without pseudo-vma
mempolicy trivia: use pgoff_t in shared mempolicy tree
mempolicy trivia: slightly more consistent naming
mempolicy trivia: delete those ancient pr_debug()s
mempolicy: fix migrate_pages(2) syscall return nr_failed
kernfs: drop shared NUMA mempolicy hooks
hugetlbfs: drop shared NUMA mempolicy pretence
mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets()
...
|
|
The nfsd_open code handles EOPENSTALE correctly, by retrying the call to
fh_verify() and __nfsd_open(). However the filecache just drops the
error on the floor, and immediately returns nfserr_stale to the caller.
This patch ensures that we propagate the EOPENSTALE code back to
nfsd_file_do_acquire, and that we handle it correctly.
Fixes: 65294c1f2c5e ("nfsd: add a new struct file caching facility to nfsd")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Message-Id: <20230911183027.11372-1-trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Use new APIs to dynamically allocate the nfsd-filecache shrinker.
Link: https://lkml.kernel.org/r/20230911094444.68966-13-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Neil Brown <neilb@suse.de>
Cc: Olga Kornievskaia <kolga@netapp.com>
Cc: Dai Ngo <Dai.Ngo@oracle.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: Abhinav Kumar <quic_abhinavk@quicinc.com>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Bob Peterson <rpeterso@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Carlos Llamas <cmllamas@google.com>
Cc: Chandan Babu R <chandan.babu@oracle.com>
Cc: Chao Yu <chao@kernel.org>
Cc: Chris Mason <clm@fb.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Chuck Lever <cel@kernel.org>
Cc: Coly Li <colyli@suse.de>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: "Darrick J. Wong" <djwong@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Airlie <airlied@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Gao Xiang <hsiangkao@linux.alibaba.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Huang Rui <ray.huang@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jeffle Xu <jefflexu@linux.alibaba.com>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Kirill Tkhai <tkhai@ya.ru>
Cc: Marijn Suijten <marijn.suijten@somainline.org>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Mike Snitzer <snitzer@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Sean Paul <sean@poorly.run>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Song Liu <song@kernel.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Steven Price <steven.price@arm.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: Yue Hu <huyue2@coolpad.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
|
The following request sequence to the same file causes the NFS client and
server getting into an infinite loop with COMMIT and NFS4ERR_DELAY:
OPEN
REMOVE
WRITE
COMMIT
Problem reported by recall11, recall12, recall14, recall20, recall22,
recall40, recall42, recall48, recall50 of nfstest suite.
This patch restores the handling of race condition in nfsd_file_do_acquire
with unlink to that prior of the regression.
Fixes: ac3a2585f018 ("nfsd: rework refcounting in filecache")
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
When queueing a dispose list to the appropriate "freeme" lists, it
pointlessly queues the objects one at a time to an intermediate list.
Remove a few helpers and just open code a list_move to make it more
clear and efficient. Better document the resulting functions with
kerneldoc comments.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
While we were converting the nfs4_file hashtable to use the kernel's
resizable hashtable data structure, Neil Brown observed that the
list variant (rhltable) would be better for managing nfsd_file items
as well. The nfsd_file hash table will contain multiple entries for
the same inode -- these should be kept together on a list. And, it
could be possible for exotic or malicious client behavior to cause
the hash table to resize itself on every insertion.
A nice simplification is that rhltable_lookup() can return a list
that contains only nfsd_file items that match a given inode, which
enables us to eliminate specialized hash table helper functions and
use the default functions provided by the rhashtable implementation).
Since we are now storing nfsd_file items for the same inode on a
single list, that effectively reduces the number of hash entries
that have to be tracked in the hash table. The mininum bucket count
is therefore lowered.
Light testing with fstests generic/531 show no regressions.
Suggested-by: Neil Brown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
