- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] md: fix mssing blktrace bio split events" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 22f166218f7313e8fe2d19213b5f4b3265f8c39e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101607-musket-agile-64f4@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 22f166218f7313e8fe2d19213b5f4b3265f8c39e Mon Sep 17 00:00:00 2001 From: Yu Kuai <yukuai3(a)huawei.com> Date: Wed, 10 Sep 2025 14:30:44 +0800 Subject: [PATCH] md: fix mssing blktrace bio split events If bio is split by internal handling like chunksize or badblocks, the corresponding trace_block_split() is missing, resulting in blktrace inability to catch BIO split events and making it harder to analyze the BIO sequence. Cc: stable(a)vger.kernel.org Fixes: 4b1faf931650 ("block: Kill bio_pair_split()") Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Damien Le Moal <dlemoal(a)kernel.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 5d9b08115375..59d7963c7843 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -266,6 +266,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) } bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); submit_bio_noacct(bio); bio = split; } diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f1d8811a542a..1ba7d0c090f7 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -472,7 +472,9 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) bio_endio(bio); return; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); submit_bio_noacct(bio); bio = split; end = zone->zone_end; @@ -620,7 +622,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); return true; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); raid0_map_submit_bio(mddev, bio); bio = split; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index f096f4d0fca7..64a1e0b47e87 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1384,7 +1384,9 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, error = PTR_ERR(split); goto err_handle; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); submit_bio_noacct(bio); bio = split; r1_bio->master_bio = bio; @@ -1616,7 +1618,9 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, error = PTR_ERR(split); goto err_handle; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); submit_bio_noacct(bio); bio = split; r1_bio->master_bio = bio; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 312e8a0e93e7..3d7b24d6b4eb 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1209,7 +1209,9 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, error = PTR_ERR(split); goto err_handle; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); submit_bio_noacct(bio); wait_barrier(conf, false); @@ -1495,7 +1497,9 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, error = PTR_ERR(split); goto err_handle; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); submit_bio_noacct(bio); wait_barrier(conf, false); @@ -1679,7 +1683,9 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) bio_endio(bio); return 0; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); /* Resend the fist split part */ submit_bio_noacct(split); @@ -1694,7 +1700,9 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) bio_endio(bio); return 0; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); /* Resend the second split part */ submit_bio_noacct(bio); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5112658ef5f6..96a6d63b3d62 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5493,8 +5493,10 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) if (sectors < bio_sectors(raid_bio)) { struct r5conf *conf = mddev->private; + split = bio_split(raid_bio, sectors, GFP_NOIO, &conf->bio_split); bio_chain(split, raid_bio); + trace_block_split(split, raid_bio->bi_iter.bi_sector); submit_bio_noacct(raid_bio); raid_bio = split; }

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] md: fix mssing blktrace bio split events" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 22f166218f7313e8fe2d19213b5f4b3265f8c39e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101607-sizable-dreamlike-52a7@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 22f166218f7313e8fe2d19213b5f4b3265f8c39e Mon Sep 17 00:00:00 2001 From: Yu Kuai <yukuai3(a)huawei.com> Date: Wed, 10 Sep 2025 14:30:44 +0800 Subject: [PATCH] md: fix mssing blktrace bio split events If bio is split by internal handling like chunksize or badblocks, the corresponding trace_block_split() is missing, resulting in blktrace inability to catch BIO split events and making it harder to analyze the BIO sequence. Cc: stable(a)vger.kernel.org Fixes: 4b1faf931650 ("block: Kill bio_pair_split()") Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Damien Le Moal <dlemoal(a)kernel.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 5d9b08115375..59d7963c7843 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -266,6 +266,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) } bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); submit_bio_noacct(bio); bio = split; } diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f1d8811a542a..1ba7d0c090f7 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -472,7 +472,9 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) bio_endio(bio); return; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); submit_bio_noacct(bio); bio = split; end = zone->zone_end; @@ -620,7 +622,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); return true; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); raid0_map_submit_bio(mddev, bio); bio = split; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index f096f4d0fca7..64a1e0b47e87 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1384,7 +1384,9 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, error = PTR_ERR(split); goto err_handle; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); submit_bio_noacct(bio); bio = split; r1_bio->master_bio = bio; @@ -1616,7 +1618,9 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, error = PTR_ERR(split); goto err_handle; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); submit_bio_noacct(bio); bio = split; r1_bio->master_bio = bio; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 312e8a0e93e7..3d7b24d6b4eb 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1209,7 +1209,9 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, error = PTR_ERR(split); goto err_handle; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); submit_bio_noacct(bio); wait_barrier(conf, false); @@ -1495,7 +1497,9 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, error = PTR_ERR(split); goto err_handle; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); submit_bio_noacct(bio); wait_barrier(conf, false); @@ -1679,7 +1683,9 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) bio_endio(bio); return 0; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); /* Resend the fist split part */ submit_bio_noacct(split); @@ -1694,7 +1700,9 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) bio_endio(bio); return 0; } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); /* Resend the second split part */ submit_bio_noacct(bio); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5112658ef5f6..96a6d63b3d62 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5493,8 +5493,10 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) if (sectors < bio_sectors(raid_bio)) { struct r5conf *conf = mddev->private; + split = bio_split(raid_bio, sectors, GFP_NOIO, &conf->bio_split); bio_chain(split, raid_bio); + trace_block_split(split, raid_bio->bi_iter.bi_sector); submit_bio_noacct(raid_bio); raid_bio = split; }

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] iommu/vt-d: PRS isn't usable if PDS isn't supported" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 5ef7e24c742038a5d8c626fdc0e3a21834358341 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101631-encrust-snagged-88c4@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 5ef7e24c742038a5d8c626fdc0e3a21834358341 Mon Sep 17 00:00:00 2001 From: Lu Baolu <baolu.lu(a)linux.intel.com> Date: Thu, 18 Sep 2025 13:02:02 +0800 Subject: [PATCH] iommu/vt-d: PRS isn't usable if PDS isn't supported The specification, Section 7.10, "Software Steps to Drain Page Requests & Responses," requires software to submit an Invalidation Wait Descriptor (inv_wait_dsc) with the Page-request Drain (PD=1) flag set, along with the Invalidation Wait Completion Status Write flag (SW=1). It then waits for the Invalidation Wait Descriptor's completion. However, the PD field in the Invalidation Wait Descriptor is optional, as stated in Section 6.5.2.9, "Invalidation Wait Descriptor": "Page-request Drain (PD): Remapping hardware implementations reporting Page-request draining as not supported (PDS = 0 in ECAP_REG) treat this field as reserved." This implies that if the IOMMU doesn't support the PDS capability, software can't drain page requests and group responses as expected. Do not enable PCI/PRI if the IOMMU doesn't support PDS. Reported-by: Joel Granados <joel.granados(a)kernel.org> Closes: https://lore.kernel.org/r/20250909-jag-pds-v1-1-ad8cba0e494e@kernel.org Fixes: 66ac4db36f4c ("iommu/vt-d: Add page request draining support") Cc: stable(a)vger.kernel.org Signed-off-by: Lu Baolu <baolu.lu(a)linux.intel.com> Link: https://lore.kernel.org/r/20250915062946.120196-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel <joerg.roedel(a)amd.com> diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 9c3ab9d9f69a..92759a8f8330 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3812,7 +3812,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) } if (info->ats_supported && ecap_prs(iommu->ecap) && - pci_pri_supported(pdev)) + ecap_pds(iommu->ecap) && pci_pri_supported(pdev)) info->pri_supported = 1; } }

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] fuse: fix livelock in synchronous file put from fuseblk" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 26e5c67deb2e1f42a951f022fdf5b9f7eb747b01 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101631-recount-smashing-e39c@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 26e5c67deb2e1f42a951f022fdf5b9f7eb747b01 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" <djwong(a)kernel.org> Date: Mon, 15 Sep 2025 17:24:17 -0700 Subject: [PATCH] fuse: fix livelock in synchronous file put from fuseblk workers I observed a hang when running generic/323 against a fuseblk server. This test opens a file, initiates a lot of AIO writes to that file descriptor, and closes the file descriptor before the writes complete. Unsurprisingly, the AIO exerciser threads are mostly stuck waiting for responses from the fuseblk server: # cat /proc/372265/task/372313/stack [<0>] request_wait_answer+0x1fe/0x2a0 [fuse] [<0>] __fuse_simple_request+0xd3/0x2b0 [fuse] [<0>] fuse_do_getattr+0xfc/0x1f0 [fuse] [<0>] fuse_file_read_iter+0xbe/0x1c0 [fuse] [<0>] aio_read+0x130/0x1e0 [<0>] io_submit_one+0x542/0x860 [<0>] __x64_sys_io_submit+0x98/0x1a0 [<0>] do_syscall_64+0x37/0xf0 [<0>] entry_SYSCALL_64_after_hwframe+0x4b/0x53 But the /weird/ part is that the fuseblk server threads are waiting for responses from itself: # cat /proc/372210/task/372232/stack [<0>] request_wait_answer+0x1fe/0x2a0 [fuse] [<0>] __fuse_simple_request+0xd3/0x2b0 [fuse] [<0>] fuse_file_put+0x9a/0xd0 [fuse] [<0>] fuse_release+0x36/0x50 [fuse] [<0>] __fput+0xec/0x2b0 [<0>] task_work_run+0x55/0x90 [<0>] syscall_exit_to_user_mode+0xe9/0x100 [<0>] do_syscall_64+0x43/0xf0 [<0>] entry_SYSCALL_64_after_hwframe+0x4b/0x53 The fuseblk server is fuse2fs so there's nothing all that exciting in the server itself. So why is the fuse server calling fuse_file_put? The commit message for the fstest sheds some light on that: "By closing the file descriptor before calling io_destroy, you pretty much guarantee that the last put on the ioctx will be done in interrupt context (during I/O completion). Aha. AIO fgets a new struct file from the fd when it queues the ioctx. The completion of the FUSE_WRITE command from userspace causes the fuse server to call the AIO completion function. The completion puts the struct file, queuing a delayed fput to the fuse server task. When the fuse server task returns to userspace, it has to run the delayed fput, which in the case of a fuseblk server, it does synchronously. Sending the FUSE_RELEASE command sychronously from fuse server threads is a bad idea because a client program can initiate enough simultaneous AIOs such that all the fuse server threads end up in delayed_fput, and now there aren't any threads left to handle the queued fuse commands. Fix this by only using asynchronous fputs when closing files, and leave a comment explaining why. Cc: stable(a)vger.kernel.org # v2.6.38 Fixes: 5a18ec176c934c ("fuse: fix hang of single threaded fuseblk filesystem") Signed-off-by: Darrick J. Wong <djwong(a)kernel.org> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 54786f62a9d8..f1ef77a0be05 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -356,8 +356,14 @@ void fuse_file_release(struct inode *inode, struct fuse_file *ff, * Make the release synchronous if this is a fuseblk mount, * synchronous RELEASE is allowed (and desirable) in this case * because the server can be trusted not to screw up. + * + * Always use the asynchronous file put because the current thread + * might be the fuse server. This can happen if a process starts some + * aio and closes the fd before the aio completes. Since aio takes its + * own ref to the file, the IO completion has to drop the ref, which is + * how the fuse server can end up closing its clients' files. */ - fuse_file_put(ff, ff->fm->fc->destroy); + fuse_file_put(ff, false); } void fuse_release_common(struct file *file, bool isdir)

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] fs: quota: create dedicated workqueue for quota_release_work" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 72b7ceca857f38a8ca7c5629feffc63769638974 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101653-unloved-prodigal-b5e0@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 72b7ceca857f38a8ca7c5629feffc63769638974 Mon Sep 17 00:00:00 2001 From: Shashank A P <shashank.ap(a)samsung.com> Date: Mon, 1 Sep 2025 14:59:00 +0530 Subject: [PATCH] fs: quota: create dedicated workqueue for quota_release_work There is a kernel panic due to WARN_ONCE when panic_on_warn is set. This issue occurs when writeback is triggered due to sync call for an opened file(ie, writeback reason is WB_REASON_SYNC). When f2fs balance is needed at sync path, flush for quota_release_work is triggered. By default quota_release_work is queued to "events_unbound" queue which does not have WQ_MEM_RECLAIM flag. During f2fs balance "writeback" workqueue tries to flush quota_release_work causing kernel panic due to MEM_RECLAIM flag mismatch errors. This patch creates dedicated workqueue with WQ_MEM_RECLAIM flag for work quota_release_work. ------------[ cut here ]------------ WARNING: CPU: 4 PID: 14867 at kernel/workqueue.c:3721 check_flush_dependency+0x13c/0x148 Call trace: check_flush_dependency+0x13c/0x148 __flush_work+0xd0/0x398 flush_delayed_work+0x44/0x5c dquot_writeback_dquots+0x54/0x318 f2fs_do_quota_sync+0xb8/0x1a8 f2fs_write_checkpoint+0x3cc/0x99c f2fs_gc+0x190/0x750 f2fs_balance_fs+0x110/0x168 f2fs_write_single_data_page+0x474/0x7dc f2fs_write_data_pages+0x7d0/0xd0c do_writepages+0xe0/0x2f4 __writeback_single_inode+0x44/0x4ac writeback_sb_inodes+0x30c/0x538 wb_writeback+0xf4/0x440 wb_workfn+0x128/0x5d4 process_scheduled_works+0x1c4/0x45c worker_thread+0x32c/0x3e8 kthread+0x11c/0x1b0 ret_from_fork+0x10/0x20 Kernel panic - not syncing: kernel: panic_on_warn set ... Fixes: ac6f420291b3 ("quota: flush quota_release_work upon quota writeback") CC: stable(a)vger.kernel.org Signed-off-by: Shashank A P <shashank.ap(a)samsung.com> Link: https://patch.msgid.link/20250901092905.2115-1-shashank.ap@samsung.com Signed-off-by: Jan Kara <jack(a)suse.cz> diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index df4a9b348769..6c4a6ee1fa2b 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -162,6 +162,9 @@ static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES; /* SLAB cache for dquot structures */ static struct kmem_cache *dquot_cachep; +/* workqueue for work quota_release_work*/ +static struct workqueue_struct *quota_unbound_wq; + void register_quota_format(struct quota_format_type *fmt) { spin_lock(&dq_list_lock); @@ -881,7 +884,7 @@ void dqput(struct dquot *dquot) put_releasing_dquots(dquot); atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); - queue_delayed_work(system_unbound_wq, &quota_release_work, 1); + queue_delayed_work(quota_unbound_wq, &quota_release_work, 1); } EXPORT_SYMBOL(dqput); @@ -3041,6 +3044,11 @@ static int __init dquot_init(void) shrinker_register(dqcache_shrinker); + quota_unbound_wq = alloc_workqueue("quota_events_unbound", + WQ_UNBOUND | WQ_MEM_RECLAIM, WQ_MAX_ACTIVE); + if (!quota_unbound_wq) + panic("Cannot create quota_unbound_wq\n"); + return 0; } fs_initcall(dquot_init);

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] fs: quota: create dedicated workqueue for quota_release_work" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 72b7ceca857f38a8ca7c5629feffc63769638974 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101652-coziness-jailer-d369@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 72b7ceca857f38a8ca7c5629feffc63769638974 Mon Sep 17 00:00:00 2001 From: Shashank A P <shashank.ap(a)samsung.com> Date: Mon, 1 Sep 2025 14:59:00 +0530 Subject: [PATCH] fs: quota: create dedicated workqueue for quota_release_work There is a kernel panic due to WARN_ONCE when panic_on_warn is set. This issue occurs when writeback is triggered due to sync call for an opened file(ie, writeback reason is WB_REASON_SYNC). When f2fs balance is needed at sync path, flush for quota_release_work is triggered. By default quota_release_work is queued to "events_unbound" queue which does not have WQ_MEM_RECLAIM flag. During f2fs balance "writeback" workqueue tries to flush quota_release_work causing kernel panic due to MEM_RECLAIM flag mismatch errors. This patch creates dedicated workqueue with WQ_MEM_RECLAIM flag for work quota_release_work. ------------[ cut here ]------------ WARNING: CPU: 4 PID: 14867 at kernel/workqueue.c:3721 check_flush_dependency+0x13c/0x148 Call trace: check_flush_dependency+0x13c/0x148 __flush_work+0xd0/0x398 flush_delayed_work+0x44/0x5c dquot_writeback_dquots+0x54/0x318 f2fs_do_quota_sync+0xb8/0x1a8 f2fs_write_checkpoint+0x3cc/0x99c f2fs_gc+0x190/0x750 f2fs_balance_fs+0x110/0x168 f2fs_write_single_data_page+0x474/0x7dc f2fs_write_data_pages+0x7d0/0xd0c do_writepages+0xe0/0x2f4 __writeback_single_inode+0x44/0x4ac writeback_sb_inodes+0x30c/0x538 wb_writeback+0xf4/0x440 wb_workfn+0x128/0x5d4 process_scheduled_works+0x1c4/0x45c worker_thread+0x32c/0x3e8 kthread+0x11c/0x1b0 ret_from_fork+0x10/0x20 Kernel panic - not syncing: kernel: panic_on_warn set ... Fixes: ac6f420291b3 ("quota: flush quota_release_work upon quota writeback") CC: stable(a)vger.kernel.org Signed-off-by: Shashank A P <shashank.ap(a)samsung.com> Link: https://patch.msgid.link/20250901092905.2115-1-shashank.ap@samsung.com Signed-off-by: Jan Kara <jack(a)suse.cz> diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index df4a9b348769..6c4a6ee1fa2b 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -162,6 +162,9 @@ static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES; /* SLAB cache for dquot structures */ static struct kmem_cache *dquot_cachep; +/* workqueue for work quota_release_work*/ +static struct workqueue_struct *quota_unbound_wq; + void register_quota_format(struct quota_format_type *fmt) { spin_lock(&dq_list_lock); @@ -881,7 +884,7 @@ void dqput(struct dquot *dquot) put_releasing_dquots(dquot); atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); - queue_delayed_work(system_unbound_wq, &quota_release_work, 1); + queue_delayed_work(quota_unbound_wq, &quota_release_work, 1); } EXPORT_SYMBOL(dqput); @@ -3041,6 +3044,11 @@ static int __init dquot_init(void) shrinker_register(dqcache_shrinker); + quota_unbound_wq = alloc_workqueue("quota_events_unbound", + WQ_UNBOUND | WQ_MEM_RECLAIM, WQ_MAX_ACTIVE); + if (!quota_unbound_wq) + panic("Cannot create quota_unbound_wq\n"); + return 0; } fs_initcall(dquot_init);

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] fs: quota: create dedicated workqueue for quota_release_work" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 72b7ceca857f38a8ca7c5629feffc63769638974 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101651-arrive-frail-3c0f@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 72b7ceca857f38a8ca7c5629feffc63769638974 Mon Sep 17 00:00:00 2001 From: Shashank A P <shashank.ap(a)samsung.com> Date: Mon, 1 Sep 2025 14:59:00 +0530 Subject: [PATCH] fs: quota: create dedicated workqueue for quota_release_work There is a kernel panic due to WARN_ONCE when panic_on_warn is set. This issue occurs when writeback is triggered due to sync call for an opened file(ie, writeback reason is WB_REASON_SYNC). When f2fs balance is needed at sync path, flush for quota_release_work is triggered. By default quota_release_work is queued to "events_unbound" queue which does not have WQ_MEM_RECLAIM flag. During f2fs balance "writeback" workqueue tries to flush quota_release_work causing kernel panic due to MEM_RECLAIM flag mismatch errors. This patch creates dedicated workqueue with WQ_MEM_RECLAIM flag for work quota_release_work. ------------[ cut here ]------------ WARNING: CPU: 4 PID: 14867 at kernel/workqueue.c:3721 check_flush_dependency+0x13c/0x148 Call trace: check_flush_dependency+0x13c/0x148 __flush_work+0xd0/0x398 flush_delayed_work+0x44/0x5c dquot_writeback_dquots+0x54/0x318 f2fs_do_quota_sync+0xb8/0x1a8 f2fs_write_checkpoint+0x3cc/0x99c f2fs_gc+0x190/0x750 f2fs_balance_fs+0x110/0x168 f2fs_write_single_data_page+0x474/0x7dc f2fs_write_data_pages+0x7d0/0xd0c do_writepages+0xe0/0x2f4 __writeback_single_inode+0x44/0x4ac writeback_sb_inodes+0x30c/0x538 wb_writeback+0xf4/0x440 wb_workfn+0x128/0x5d4 process_scheduled_works+0x1c4/0x45c worker_thread+0x32c/0x3e8 kthread+0x11c/0x1b0 ret_from_fork+0x10/0x20 Kernel panic - not syncing: kernel: panic_on_warn set ... Fixes: ac6f420291b3 ("quota: flush quota_release_work upon quota writeback") CC: stable(a)vger.kernel.org Signed-off-by: Shashank A P <shashank.ap(a)samsung.com> Link: https://patch.msgid.link/20250901092905.2115-1-shashank.ap@samsung.com Signed-off-by: Jan Kara <jack(a)suse.cz> diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index df4a9b348769..6c4a6ee1fa2b 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -162,6 +162,9 @@ static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES; /* SLAB cache for dquot structures */ static struct kmem_cache *dquot_cachep; +/* workqueue for work quota_release_work*/ +static struct workqueue_struct *quota_unbound_wq; + void register_quota_format(struct quota_format_type *fmt) { spin_lock(&dq_list_lock); @@ -881,7 +884,7 @@ void dqput(struct dquot *dquot) put_releasing_dquots(dquot); atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); - queue_delayed_work(system_unbound_wq, &quota_release_work, 1); + queue_delayed_work(quota_unbound_wq, &quota_release_work, 1); } EXPORT_SYMBOL(dqput); @@ -3041,6 +3044,11 @@ static int __init dquot_init(void) shrinker_register(dqcache_shrinker); + quota_unbound_wq = alloc_workqueue("quota_events_unbound", + WQ_UNBOUND | WQ_MEM_RECLAIM, WQ_MAX_ACTIVE); + if (!quota_unbound_wq) + panic("Cannot create quota_unbound_wq\n"); + return 0; } fs_initcall(dquot_init);

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] fs: quota: create dedicated workqueue for quota_release_work" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 72b7ceca857f38a8ca7c5629feffc63769638974 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101651-whiny-creme-9639@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 72b7ceca857f38a8ca7c5629feffc63769638974 Mon Sep 17 00:00:00 2001 From: Shashank A P <shashank.ap(a)samsung.com> Date: Mon, 1 Sep 2025 14:59:00 +0530 Subject: [PATCH] fs: quota: create dedicated workqueue for quota_release_work There is a kernel panic due to WARN_ONCE when panic_on_warn is set. This issue occurs when writeback is triggered due to sync call for an opened file(ie, writeback reason is WB_REASON_SYNC). When f2fs balance is needed at sync path, flush for quota_release_work is triggered. By default quota_release_work is queued to "events_unbound" queue which does not have WQ_MEM_RECLAIM flag. During f2fs balance "writeback" workqueue tries to flush quota_release_work causing kernel panic due to MEM_RECLAIM flag mismatch errors. This patch creates dedicated workqueue with WQ_MEM_RECLAIM flag for work quota_release_work. ------------[ cut here ]------------ WARNING: CPU: 4 PID: 14867 at kernel/workqueue.c:3721 check_flush_dependency+0x13c/0x148 Call trace: check_flush_dependency+0x13c/0x148 __flush_work+0xd0/0x398 flush_delayed_work+0x44/0x5c dquot_writeback_dquots+0x54/0x318 f2fs_do_quota_sync+0xb8/0x1a8 f2fs_write_checkpoint+0x3cc/0x99c f2fs_gc+0x190/0x750 f2fs_balance_fs+0x110/0x168 f2fs_write_single_data_page+0x474/0x7dc f2fs_write_data_pages+0x7d0/0xd0c do_writepages+0xe0/0x2f4 __writeback_single_inode+0x44/0x4ac writeback_sb_inodes+0x30c/0x538 wb_writeback+0xf4/0x440 wb_workfn+0x128/0x5d4 process_scheduled_works+0x1c4/0x45c worker_thread+0x32c/0x3e8 kthread+0x11c/0x1b0 ret_from_fork+0x10/0x20 Kernel panic - not syncing: kernel: panic_on_warn set ... Fixes: ac6f420291b3 ("quota: flush quota_release_work upon quota writeback") CC: stable(a)vger.kernel.org Signed-off-by: Shashank A P <shashank.ap(a)samsung.com> Link: https://patch.msgid.link/20250901092905.2115-1-shashank.ap@samsung.com Signed-off-by: Jan Kara <jack(a)suse.cz> diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index df4a9b348769..6c4a6ee1fa2b 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -162,6 +162,9 @@ static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES; /* SLAB cache for dquot structures */ static struct kmem_cache *dquot_cachep; +/* workqueue for work quota_release_work*/ +static struct workqueue_struct *quota_unbound_wq; + void register_quota_format(struct quota_format_type *fmt) { spin_lock(&dq_list_lock); @@ -881,7 +884,7 @@ void dqput(struct dquot *dquot) put_releasing_dquots(dquot); atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); - queue_delayed_work(system_unbound_wq, &quota_release_work, 1); + queue_delayed_work(quota_unbound_wq, &quota_release_work, 1); } EXPORT_SYMBOL(dqput); @@ -3041,6 +3044,11 @@ static int __init dquot_init(void) shrinker_register(dqcache_shrinker); + quota_unbound_wq = alloc_workqueue("quota_events_unbound", + WQ_UNBOUND | WQ_MEM_RECLAIM, WQ_MAX_ACTIVE); + if (!quota_unbound_wq) + panic("Cannot create quota_unbound_wq\n"); + return 0; } fs_initcall(dquot_init);

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] eventpoll: Replace rwlock with spinlock" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 0c43094f8cc9d3d99d835c0ac9c4fe1ccc62babd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101620-overcook-path-9b00@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0c43094f8cc9d3d99d835c0ac9c4fe1ccc62babd Mon Sep 17 00:00:00 2001 From: Nam Cao <namcao(a)linutronix.de> Date: Tue, 15 Jul 2025 14:46:34 +0200 Subject: [PATCH] eventpoll: Replace rwlock with spinlock 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]. Fix this problem by replacing rwlock with spinlock. This reduces the event bandwidth, as the producers now have to contend with each other for the spinlock. According to the benchmark from https://github.com/rouming/test-tools/blob/master/stress-epoll.c: On 12 x86 CPUs: Before After Diff threads events/ms events/ms 8 7162 4956 -31% 16 8733 5383 -38% 32 7968 5572 -30% 64 10652 5739 -46% 128 11236 5931 -47% On 4 riscv CPUs: Before After Diff threads events/ms events/ms 8 2958 2833 -4% 16 3323 3097 -7% 32 3451 3240 -6% 64 3554 3178 -11% 128 3601 3235 -10% Although the numbers look bad, it should be noted that this benchmark creates multiple threads who do nothing except constantly generating new epoll events, thus contention on the spinlock is high. For real workload, the event rate is likely much lower, and the performance drop is not as bad. Using another benchmark (perf bench epoll wait) where spinlock contention is lower, improvement is even observed on x86: On 12 x86 CPUs: Before: Averaged 110279 operations/sec (+- 1.09%), total secs = 8 After: Averaged 114577 operations/sec (+- 2.25%), total secs = 8 On 4 riscv CPUs: Before: Averaged 175767 operations/sec (+- 0.62%), total secs = 8 After: Averaged 167396 operations/sec (+- 0.23%), total secs = 8 In conclusion, no one is likely to be upset over this change. After all, spinlock was used originally for years, and the commit which converted to rwlock didn't mention a real workload, just that the benchmark numbers are nice. This patch is not exactly the revert of commit a218cc491420 ("epoll: use rwlock in order to reduce ep_poll_callback() contention"), because git revert conflicts in some places which are not obvious on the resolution. This patch is intended to be backported, therefore go with the obvious approach: - Replace rwlock_t with spinlock_t one to one - Delete list_add_tail_lockless() and chain_epi_lockless(). These were introduced to allow producers to concurrently add items to the list. But now that spinlock no longer allows producers to touch the event list concurrently, these two functions are not necessary anymore. Fixes: a218cc491420 ("epoll: use rwlock in order to reduce ep_poll_callback() contention") Signed-off-by: Nam Cao <namcao(a)linutronix.de> Link: https://lore.kernel.org/ec92458ea357ec503c737ead0f10b2c6e4c37d47.1752581388… Tested-by: K Prateek Nayak <kprateek.nayak(a)amd.com> Cc: stable(a)vger.kernel.org Reported-by: Frederic Weisbecker <frederic(a)kernel.org> Closes: https://lore.kernel.org/linux-rt-users/20210825132754.GA895675@lothringen/ [1] Reported-by: Valentin Schneider <vschneid(a)redhat.com> Closes: https://lore.kernel.org/linux-rt-users/xhsmhttqvnall.mognet@vschneid.remote… [2] Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/eventpoll.c b/fs/eventpoll.c index b22d6f819f78..ee7c4b683ec3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -46,10 +46,10 @@ * * 1) epnested_mutex (mutex) * 2) ep->mtx (mutex) - * 3) ep->lock (rwlock) + * 3) ep->lock (spinlock) * * The acquire order is the one listed above, from 1 to 3. - * We need a rwlock (ep->lock) because we manipulate objects + * We need a spinlock (ep->lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need @@ -195,7 +195,7 @@ struct eventpoll { struct list_head rdllist; /* Lock which protects rdllist and ovflist */ - rwlock_t lock; + spinlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; @@ -741,10 +741,10 @@ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) * in a lockless way. */ lockdep_assert_irqs_enabled(); - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); list_splice_init(&ep->rdllist, txlist); WRITE_ONCE(ep->ovflist, NULL); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, @@ -752,7 +752,7 @@ static void ep_done_scan(struct eventpoll *ep, { struct epitem *epi, *nepi; - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. @@ -793,7 +793,7 @@ static void ep_done_scan(struct eventpoll *ep, wake_up(&ep->wq); } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) @@ -868,10 +868,10 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) rb_erase_cached(&epi->rbn, &ep->rbr); - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* @@ -1152,7 +1152,7 @@ static int ep_alloc(struct eventpoll **pep) return -ENOMEM; mutex_init(&ep->mtx); - rwlock_init(&ep->lock); + spin_lock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); @@ -1239,100 +1239,10 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, } #endif /* CONFIG_KCMP */ -/* - * Adds a new entry to the tail of the list in a lockless way, i.e. - * multiple CPUs are allowed to call this function concurrently. - * - * Beware: it is necessary to prevent any other modifications of the - * existing list until all changes are completed, in other words - * concurrent list_add_tail_lockless() calls should be protected - * with a read lock, where write lock acts as a barrier which - * makes sure all list_add_tail_lockless() calls are fully - * completed. - * - * Also an element can be locklessly added to the list only in one - * direction i.e. either to the tail or to the head, otherwise - * concurrent access will corrupt the list. - * - * Return: %false if element has been already added to the list, %true - * otherwise. - */ -static inline bool list_add_tail_lockless(struct list_head *new, - struct list_head *head) -{ - struct list_head *prev; - - /* - * This is simple 'new->next = head' operation, but cmpxchg() - * is used in order to detect that same element has been just - * added to the list from another CPU: the winner observes - * new->next == new. - */ - if (!try_cmpxchg(&new->next, &new, head)) - return false; - - /* - * Initially ->next of a new element must be updated with the head - * (we are inserting to the tail) and only then pointers are atomically - * exchanged. XCHG guarantees memory ordering, thus ->next should be - * updated before pointers are actually swapped and pointers are - * swapped before prev->next is updated. - */ - - prev = xchg(&head->prev, new); - - /* - * It is safe to modify prev->next and new->prev, because a new element - * is added only to the tail and new->next is updated before XCHG. - */ - - prev->next = new; - new->prev = prev; - - return true; -} - -/* - * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, - * i.e. multiple CPUs are allowed to call this function concurrently. - * - * Return: %false if epi element has been already chained, %true otherwise. - */ -static inline bool chain_epi_lockless(struct epitem *epi) -{ - struct eventpoll *ep = epi->ep; - - /* Fast preliminary check */ - if (epi->next != EP_UNACTIVE_PTR) - return false; - - /* Check that the same epi has not been just chained from another CPU */ - if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) - return false; - - /* Atomically exchange tail */ - epi->next = xchg(&ep->ovflist, epi); - - return true; -} - /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. - * - * This callback takes a read lock in order not to contend with concurrent - * events from another file descriptor, thus all modifications to ->rdllist - * or ->ovflist are lockless. Read lock is paired with the write lock from - * ep_start/done_scan(), which stops all list modifications and guarantees - * that lists state is seen correctly. - * - * Another thing worth to mention is that ep_poll_callback() can be called - * concurrently for the same @epi from different CPUs if poll table was inited - * with several wait queues entries. Plural wakeup from different CPUs of a - * single wait queue is serialized by wq.lock, but the case when multiple wait - * queues are used should be detected accordingly. This is detected using - * cmpxchg() operation. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { @@ -1343,7 +1253,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v unsigned long flags; int ewake = 0; - read_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); @@ -1372,12 +1282,15 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { - if (chain_epi_lockless(epi)) + if (epi->next == EP_UNACTIVE_PTR) { + epi->next = READ_ONCE(ep->ovflist); + WRITE_ONCE(ep->ovflist, epi); ep_pm_stay_awake_rcu(epi); + } } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ - if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) - ep_pm_stay_awake_rcu(epi); + list_add_tail(&epi->rdllink, &ep->rdllist); + ep_pm_stay_awake_rcu(epi); } /* @@ -1410,7 +1323,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v pwake++; out_unlock: - read_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) @@ -1745,7 +1658,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, } /* We have to drop the new item inside our item list to keep track of it */ - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); @@ -1762,7 +1675,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, pwake++; } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) @@ -1826,7 +1739,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); @@ -1837,7 +1750,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, if (waitqueue_active(&ep->poll_wait)) pwake++; } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ @@ -2089,7 +2002,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, init_wait(&wait); wait.func = ep_autoremove_wake_function; - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it @@ -2108,7 +2021,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, if (!eavail) __add_wait_queue_exclusive(&ep->wq, &wait); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); if (!eavail) timed_out = !ep_schedule_timeout(to) || @@ -2124,7 +2037,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, eavail = 1; if (!list_empty_careful(&wait.entry)) { - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, * it means that the thread was woken up after its @@ -2135,7 +2048,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } } }

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] eventpoll: Replace rwlock with spinlock" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 0c43094f8cc9d3d99d835c0ac9c4fe1ccc62babd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025101619-cesarean-cresting-01cb@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0c43094f8cc9d3d99d835c0ac9c4fe1ccc62babd Mon Sep 17 00:00:00 2001 From: Nam Cao <namcao(a)linutronix.de> Date: Tue, 15 Jul 2025 14:46:34 +0200 Subject: [PATCH] eventpoll: Replace rwlock with spinlock 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]. Fix this problem by replacing rwlock with spinlock. This reduces the event bandwidth, as the producers now have to contend with each other for the spinlock. According to the benchmark from https://github.com/rouming/test-tools/blob/master/stress-epoll.c: On 12 x86 CPUs: Before After Diff threads events/ms events/ms 8 7162 4956 -31% 16 8733 5383 -38% 32 7968 5572 -30% 64 10652 5739 -46% 128 11236 5931 -47% On 4 riscv CPUs: Before After Diff threads events/ms events/ms 8 2958 2833 -4% 16 3323 3097 -7% 32 3451 3240 -6% 64 3554 3178 -11% 128 3601 3235 -10% Although the numbers look bad, it should be noted that this benchmark creates multiple threads who do nothing except constantly generating new epoll events, thus contention on the spinlock is high. For real workload, the event rate is likely much lower, and the performance drop is not as bad. Using another benchmark (perf bench epoll wait) where spinlock contention is lower, improvement is even observed on x86: On 12 x86 CPUs: Before: Averaged 110279 operations/sec (+- 1.09%), total secs = 8 After: Averaged 114577 operations/sec (+- 2.25%), total secs = 8 On 4 riscv CPUs: Before: Averaged 175767 operations/sec (+- 0.62%), total secs = 8 After: Averaged 167396 operations/sec (+- 0.23%), total secs = 8 In conclusion, no one is likely to be upset over this change. After all, spinlock was used originally for years, and the commit which converted to rwlock didn't mention a real workload, just that the benchmark numbers are nice. This patch is not exactly the revert of commit a218cc491420 ("epoll: use rwlock in order to reduce ep_poll_callback() contention"), because git revert conflicts in some places which are not obvious on the resolution. This patch is intended to be backported, therefore go with the obvious approach: - Replace rwlock_t with spinlock_t one to one - Delete list_add_tail_lockless() and chain_epi_lockless(). These were introduced to allow producers to concurrently add items to the list. But now that spinlock no longer allows producers to touch the event list concurrently, these two functions are not necessary anymore. Fixes: a218cc491420 ("epoll: use rwlock in order to reduce ep_poll_callback() contention") Signed-off-by: Nam Cao <namcao(a)linutronix.de> Link: https://lore.kernel.org/ec92458ea357ec503c737ead0f10b2c6e4c37d47.1752581388… Tested-by: K Prateek Nayak <kprateek.nayak(a)amd.com> Cc: stable(a)vger.kernel.org Reported-by: Frederic Weisbecker <frederic(a)kernel.org> Closes: https://lore.kernel.org/linux-rt-users/20210825132754.GA895675@lothringen/ [1] Reported-by: Valentin Schneider <vschneid(a)redhat.com> Closes: https://lore.kernel.org/linux-rt-users/xhsmhttqvnall.mognet@vschneid.remote… [2] Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/eventpoll.c b/fs/eventpoll.c index b22d6f819f78..ee7c4b683ec3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -46,10 +46,10 @@ * * 1) epnested_mutex (mutex) * 2) ep->mtx (mutex) - * 3) ep->lock (rwlock) + * 3) ep->lock (spinlock) * * The acquire order is the one listed above, from 1 to 3. - * We need a rwlock (ep->lock) because we manipulate objects + * We need a spinlock (ep->lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need @@ -195,7 +195,7 @@ struct eventpoll { struct list_head rdllist; /* Lock which protects rdllist and ovflist */ - rwlock_t lock; + spinlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; @@ -741,10 +741,10 @@ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) * in a lockless way. */ lockdep_assert_irqs_enabled(); - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); list_splice_init(&ep->rdllist, txlist); WRITE_ONCE(ep->ovflist, NULL); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, @@ -752,7 +752,7 @@ static void ep_done_scan(struct eventpoll *ep, { struct epitem *epi, *nepi; - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. @@ -793,7 +793,7 @@ static void ep_done_scan(struct eventpoll *ep, wake_up(&ep->wq); } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) @@ -868,10 +868,10 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) rb_erase_cached(&epi->rbn, &ep->rbr); - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* @@ -1152,7 +1152,7 @@ static int ep_alloc(struct eventpoll **pep) return -ENOMEM; mutex_init(&ep->mtx); - rwlock_init(&ep->lock); + spin_lock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); @@ -1239,100 +1239,10 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, } #endif /* CONFIG_KCMP */ -/* - * Adds a new entry to the tail of the list in a lockless way, i.e. - * multiple CPUs are allowed to call this function concurrently. - * - * Beware: it is necessary to prevent any other modifications of the - * existing list until all changes are completed, in other words - * concurrent list_add_tail_lockless() calls should be protected - * with a read lock, where write lock acts as a barrier which - * makes sure all list_add_tail_lockless() calls are fully - * completed. - * - * Also an element can be locklessly added to the list only in one - * direction i.e. either to the tail or to the head, otherwise - * concurrent access will corrupt the list. - * - * Return: %false if element has been already added to the list, %true - * otherwise. - */ -static inline bool list_add_tail_lockless(struct list_head *new, - struct list_head *head) -{ - struct list_head *prev; - - /* - * This is simple 'new->next = head' operation, but cmpxchg() - * is used in order to detect that same element has been just - * added to the list from another CPU: the winner observes - * new->next == new. - */ - if (!try_cmpxchg(&new->next, &new, head)) - return false; - - /* - * Initially ->next of a new element must be updated with the head - * (we are inserting to the tail) and only then pointers are atomically - * exchanged. XCHG guarantees memory ordering, thus ->next should be - * updated before pointers are actually swapped and pointers are - * swapped before prev->next is updated. - */ - - prev = xchg(&head->prev, new); - - /* - * It is safe to modify prev->next and new->prev, because a new element - * is added only to the tail and new->next is updated before XCHG. - */ - - prev->next = new; - new->prev = prev; - - return true; -} - -/* - * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, - * i.e. multiple CPUs are allowed to call this function concurrently. - * - * Return: %false if epi element has been already chained, %true otherwise. - */ -static inline bool chain_epi_lockless(struct epitem *epi) -{ - struct eventpoll *ep = epi->ep; - - /* Fast preliminary check */ - if (epi->next != EP_UNACTIVE_PTR) - return false; - - /* Check that the same epi has not been just chained from another CPU */ - if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) - return false; - - /* Atomically exchange tail */ - epi->next = xchg(&ep->ovflist, epi); - - return true; -} - /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. - * - * This callback takes a read lock in order not to contend with concurrent - * events from another file descriptor, thus all modifications to ->rdllist - * or ->ovflist are lockless. Read lock is paired with the write lock from - * ep_start/done_scan(), which stops all list modifications and guarantees - * that lists state is seen correctly. - * - * Another thing worth to mention is that ep_poll_callback() can be called - * concurrently for the same @epi from different CPUs if poll table was inited - * with several wait queues entries. Plural wakeup from different CPUs of a - * single wait queue is serialized by wq.lock, but the case when multiple wait - * queues are used should be detected accordingly. This is detected using - * cmpxchg() operation. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { @@ -1343,7 +1253,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v unsigned long flags; int ewake = 0; - read_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); @@ -1372,12 +1282,15 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { - if (chain_epi_lockless(epi)) + if (epi->next == EP_UNACTIVE_PTR) { + epi->next = READ_ONCE(ep->ovflist); + WRITE_ONCE(ep->ovflist, epi); ep_pm_stay_awake_rcu(epi); + } } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ - if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) - ep_pm_stay_awake_rcu(epi); + list_add_tail(&epi->rdllink, &ep->rdllist); + ep_pm_stay_awake_rcu(epi); } /* @@ -1410,7 +1323,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v pwake++; out_unlock: - read_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) @@ -1745,7 +1658,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, } /* We have to drop the new item inside our item list to keep track of it */ - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); @@ -1762,7 +1675,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, pwake++; } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) @@ -1826,7 +1739,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); @@ -1837,7 +1750,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, if (waitqueue_active(&ep->poll_wait)) pwake++; } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ @@ -2089,7 +2002,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, init_wait(&wait); wait.func = ep_autoremove_wake_function; - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it @@ -2108,7 +2021,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, if (!eavail) __add_wait_queue_exclusive(&ep->wq, &wait); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); if (!eavail) timed_out = !ep_schedule_timeout(to) || @@ -2124,7 +2037,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, eavail = 1; if (!list_empty_careful(&wait.entry)) { - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, * it means that the thread was woken up after its @@ -2135,7 +2048,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } } }

1 week, 5 days

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror