Hi all, 1. Background ============= We used to implement the lockless slab shrink with SRCU [1], but then kernel test robot reported -88.8% regression in stress-ng.ramfs.ops_per_sec test case [2], so we reverted it [3]. This patch series aims to re-implement the lockless slab shrink using the refcount+RCU method proposed by Dave Chinner [4]. [1]. https://lore.kernel.org/lkml/20230313112819.38938-1-zhengqi.arch@xxxxxxxxxxxxx/ [2]. https://lore.kernel.org/lkml/202305230837.db2c233f-yujie.liu@xxxxxxxxx/ [3]. https://lore.kernel.org/all/20230609081518.3039120-1-qi.zheng@xxxxxxxxx/ [4]. https://lore.kernel.org/lkml/ZIJhou1d55d4H1s0@xxxxxxxxxxxxxxxxxxx/ 2. Implementation ================= Currently, the shrinker instances can be divided into the following three types: a) global shrinker instance statically defined in the kernel, such as workingset_shadow_shrinker. b) global shrinker instance statically defined in the kernel modules, such as mmu_shrinker in x86. c) shrinker instance embedded in other structures. For case a, the memory of shrinker instance is never freed. For case b, the memory of shrinker instance will be freed after synchronize_rcu() when the module is unloaded. For case c, the memory of shrinker instance will be freed along with the structure it is embedded in. In preparation for implementing lockless slab shrink, we need to dynamically allocate those shrinker instances in case c, then the memory can be dynamically freed alone by calling kfree_rcu(). This patchset adds the following new APIs for dynamically allocating shrinker, and add a private_data field to struct shrinker to record and get the original embedded structure. 1. shrinker_alloc() 2. shrinker_free_non_registered() 3. shrinker_register() 4. shrinker_unregister() In order to simplify shrinker-related APIs and make shrinker more independent of other kernel mechanisms, this patchset uses the above APIs to convert all shrinkers (including case a and b) to dynamically allocated, and then remove all existing APIs. This will also have another advantage mentioned by Dave Chinner: ``` The other advantage of this is that it will break all the existing out of tree code and third party modules using the old API and will no longer work with a kernel using lockless slab shrinkers. They need to break (both at the source and binary levels) to stop bad things from happening due to using uncoverted shrinkers in the new setup. ``` Then we free the shrinker by calling kfree_rcu(), and use rcu_read_{lock,unlock}() to ensure that the shrinker instance is valid. And the shrinker::refcount mechanism ensures that the shrinker instance will not be run again after unregistration. So the structure that records the pointer of shrinker instance can be safely freed without waiting for the RCU read-side critical section. In this way, while we implement the lockless slab shrink, we don't need to be blocked in unregister_shrinker() to wait RCU read-side critical section. PATCH 1: move shrinker-related code into a separate file PATCH 2: remove redundant shrinker_rwsem in debugfs operations PATCH 3: add infrastructure for dynamically allocating shrinker PATCH 4 ~ 21: dynamically allocate the shrinker instances in case a and b PATCH 22 ~ 40: dynamically allocate the shrinker instances in case c PATCH 41: remove old APIs PATCH 42: introduce pool_shrink_rwsem to implement private synchronize_shrinkers() PATCH 43: add a secondary array for shrinker_info::{map, nr_deferred} PATCH 44 ~ 45: implement the lockless slab shrink PATCH 46 ~ 47: convert shrinker_rwsem to mutex 3. Testing ========== 3.1 slab shrink stress test --------------------------- We can reproduce the down_read_trylock() hotspot through the following script: ``` DIR="/root/shrinker/memcg/mnt" do_create() { mkdir -p /sys/fs/cgroup/memory/test echo 4G > /sys/fs/cgroup/memory/test/memory.limit_in_bytes for i in `seq 0 $1`; do mkdir -p /sys/fs/cgroup/memory/test/$i; echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; mkdir -p $DIR/$i; done } do_mount() { for i in `seq $1 $2`; do mount -t tmpfs $i $DIR/$i; done } do_touch() { for i in `seq $1 $2`; do echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; dd if=/dev/zero of=$DIR/$i/file$i bs=1M count=1 & done } case "$1" in touch) do_touch $2 $3 ;; test) do_create 4000 do_mount 0 4000 do_touch 0 3000 ;; *) exit 1 ;; esac ``` Save the above script, then run test and touch commands. Then we can use the following perf command to view hotspots: perf top -U -F 999 1) Before applying this patchset: 40.44% [kernel] [k] down_read_trylock 17.59% [kernel] [k] up_read 13.64% [kernel] [k] pv_native_safe_halt 11.90% [kernel] [k] shrink_slab 8.21% [kernel] [k] idr_find 2.71% [kernel] [k] _find_next_bit 1.36% [kernel] [k] shrink_node 0.81% [kernel] [k] shrink_lruvec 0.80% [kernel] [k] __radix_tree_lookup 0.50% [kernel] [k] do_shrink_slab 0.21% [kernel] [k] list_lru_count_one 0.16% [kernel] [k] mem_cgroup_iter 2) After applying this patchset: 60.17% [kernel] [k] shrink_slab 20.42% [kernel] [k] pv_native_safe_halt 3.03% [kernel] [k] do_shrink_slab 2.73% [kernel] [k] shrink_node 2.27% [kernel] [k] shrink_lruvec 2.00% [kernel] [k] __rcu_read_unlock 1.92% [kernel] [k] mem_cgroup_iter 0.98% [kernel] [k] __rcu_read_lock 0.91% [kernel] [k] osq_lock 0.63% [kernel] [k] mem_cgroup_calculate_protection 0.55% [kernel] [k] shrinker_put 0.46% [kernel] [k] list_lru_count_one We can see that the first perf hotspot becomes shrink_slab, which is what we expect. 3.2 registeration and unregisteration stress test ------------------------------------------------- Run the command below to test: stress-ng --timeout 60 --times --verify --metrics-brief --ramfs 9 & 1) Before applying this patchset: setting to a 60 second run per stressor dispatching hogs: 9 ramfs stressor bogo ops real time usr time sys time bogo ops/s bogo ops/s (secs) (secs) (secs) (real time) (usr+sys time) ramfs 735238 60.00 12.37 363.70 12253.05 1955.08 for a 60.01s run time: 1440.27s available CPU time 12.36s user time ( 0.86%) 363.70s system time ( 25.25%) 376.06s total time ( 26.11%) load average: 10.79 4.47 1.69 passed: 9: ramfs (9) failed: 0 skipped: 0 successful run completed in 60.01s (1 min, 0.01 secs) 2) After applying this patchset: setting to a 60 second run per stressor dispatching hogs: 9 ramfs stressor bogo ops real time usr time sys time bogo ops/s bogo ops/s (secs) (secs) (secs) (real time) (usr+sys time) ramfs 746677 60.00 12.22 367.75 12443.70 1965.13 for a 60.01s run time: 1440.26s available CPU time 12.21s user time ( 0.85%) 367.75s system time ( 25.53%) 379.96s total time ( 26.38%) load average: 8.37 2.48 0.86 passed: 9: ramfs (9) failed: 0 skipped: 0 successful run completed in 60.01s (1 min, 0.01 secs) We can see that the ops/s has hardly changed. This series is based on next-20230711, and the [PATCH v2 05/49] depends on the patch: https://lore.kernel.org/lkml/20230625154937.64316-1-qi.zheng@xxxxxxxxx/. Comments and suggestions are welcome. Thanks, Qi Changelog in v1 -> v2: - implement the new APIs and convert all shrinkers to use it. (suggested by Dave Chinner) - fix UAF in PATCH [05/29] (pointed by Steven Price) - add a secondary array for shrinker_info::{map, nr_deferred} - re-implement the lockless slab shrink (Since unifying the processing of global and memcg slab shrink needs to modify the startup sequence (As I mentioned in https://lore.kernel.org/lkml/38b14080-4ce5-d300-8a0a-c630bca6806b@xxxxxxxxxxxxx/), I finally choose to process them separately.) - collect Acked-bys Qi Zheng (47): mm: vmscan: move shrinker-related code into a separate file mm: shrinker: remove redundant shrinker_rwsem in debugfs operations mm: shrinker: add infrastructure for dynamically allocating shrinker kvm: mmu: dynamically allocate the x86-mmu shrinker binder: dynamically allocate the android-binder shrinker drm/ttm: dynamically allocate the drm-ttm_pool shrinker xenbus/backend: dynamically allocate the xen-backend shrinker erofs: dynamically allocate the erofs-shrinker f2fs: dynamically allocate the f2fs-shrinker gfs2: dynamically allocate the gfs2-glock shrinker gfs2: dynamically allocate the gfs2-qd shrinker NFSv4.2: dynamically allocate the nfs-xattr shrinkers nfs: dynamically allocate the nfs-acl shrinker nfsd: dynamically allocate the nfsd-filecache shrinker quota: dynamically allocate the dquota-cache shrinker ubifs: dynamically allocate the ubifs-slab shrinker rcu: dynamically allocate the rcu-lazy shrinker rcu: dynamically allocate the rcu-kfree shrinker mm: thp: dynamically allocate the thp-related shrinkers sunrpc: dynamically allocate the sunrpc_cred shrinker mm: workingset: dynamically allocate the mm-shadow shrinker drm/i915: dynamically allocate the i915_gem_mm shrinker drm/msm: dynamically allocate the drm-msm_gem shrinker drm/panfrost: dynamically allocate the drm-panfrost shrinker dm: dynamically allocate the dm-bufio shrinker dm zoned: dynamically allocate the dm-zoned-meta shrinker md/raid5: dynamically allocate the md-raid5 shrinker bcache: dynamically allocate the md-bcache shrinker vmw_balloon: dynamically allocate the vmw-balloon shrinker virtio_balloon: dynamically allocate the virtio-balloon shrinker mbcache: dynamically allocate the mbcache shrinker ext4: dynamically allocate the ext4-es shrinker jbd2,ext4: dynamically allocate the jbd2-journal shrinker nfsd: dynamically allocate the nfsd-client shrinker nfsd: dynamically allocate the nfsd-reply shrinker xfs: dynamically allocate the xfs-buf shrinker xfs: dynamically allocate the xfs-inodegc shrinker xfs: dynamically allocate the xfs-qm shrinker zsmalloc: dynamically allocate the mm-zspool shrinker fs: super: dynamically allocate the s_shrink mm: shrinker: remove old APIs drm/ttm: introduce pool_shrink_rwsem mm: shrinker: add a secondary array for shrinker_info::{map, nr_deferred} mm: shrinker: make global slab shrink lockless mm: shrinker: make memcg slab shrink lockless mm: shrinker: hold write lock to reparent shrinker nr_deferred mm: shrinker: convert shrinker_rwsem to mutex arch/x86/kvm/mmu/mmu.c | 18 +- drivers/android/binder_alloc.c | 31 +- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 30 +- drivers/gpu/drm/i915/i915_drv.h | 2 +- drivers/gpu/drm/msm/msm_drv.c | 4 +- drivers/gpu/drm/msm/msm_drv.h | 4 +- drivers/gpu/drm/msm/msm_gem_shrinker.c | 36 +- drivers/gpu/drm/panfrost/panfrost_device.h | 2 +- drivers/gpu/drm/panfrost/panfrost_drv.c | 6 +- drivers/gpu/drm/panfrost/panfrost_gem.h | 2 +- .../gpu/drm/panfrost/panfrost_gem_shrinker.c | 32 +- drivers/gpu/drm/ttm/ttm_pool.c | 38 +- drivers/md/bcache/bcache.h | 2 +- drivers/md/bcache/btree.c | 27 +- drivers/md/bcache/sysfs.c | 3 +- drivers/md/dm-bufio.c | 26 +- drivers/md/dm-cache-metadata.c | 2 +- drivers/md/dm-zoned-metadata.c | 28 +- drivers/md/raid5.c | 25 +- drivers/md/raid5.h | 2 +- drivers/misc/vmw_balloon.c | 38 +- drivers/virtio/virtio_balloon.c | 25 +- drivers/xen/xenbus/xenbus_probe_backend.c | 17 +- fs/btrfs/super.c | 2 +- fs/erofs/utils.c | 20 +- fs/ext4/ext4.h | 2 +- fs/ext4/extents_status.c | 22 +- fs/f2fs/super.c | 32 +- fs/gfs2/glock.c | 20 +- fs/gfs2/main.c | 6 +- fs/gfs2/quota.c | 26 +- fs/gfs2/quota.h | 3 +- fs/jbd2/journal.c | 27 +- fs/kernfs/mount.c | 2 +- fs/mbcache.c | 23 +- fs/nfs/nfs42xattr.c | 87 +- fs/nfs/super.c | 20 +- fs/nfsd/filecache.c | 22 +- fs/nfsd/netns.h | 4 +- fs/nfsd/nfs4state.c | 20 +- fs/nfsd/nfscache.c | 31 +- fs/proc/root.c | 2 +- fs/quota/dquot.c | 17 +- fs/super.c | 39 +- fs/ubifs/super.c | 22 +- fs/xfs/xfs_buf.c | 25 +- fs/xfs/xfs_buf.h | 2 +- fs/xfs/xfs_icache.c | 26 +- fs/xfs/xfs_mount.c | 4 +- fs/xfs/xfs_mount.h | 2 +- fs/xfs/xfs_qm.c | 26 +- fs/xfs/xfs_qm.h | 2 +- include/linux/fs.h | 2 +- include/linux/jbd2.h | 2 +- include/linux/memcontrol.h | 12 +- include/linux/shrinker.h | 54 +- kernel/rcu/tree.c | 21 +- kernel/rcu/tree_nocb.h | 19 +- mm/Makefile | 4 +- mm/huge_memory.c | 69 +- mm/shrinker.c | 772 ++++++++++++++++++ mm/shrinker_debug.c | 76 +- mm/vmscan.c | 701 ---------------- mm/workingset.c | 26 +- mm/zsmalloc.c | 28 +- net/sunrpc/auth.c | 19 +- 66 files changed, 1516 insertions(+), 1225 deletions(-) create mode 100644 mm/shrinker.c -- 2.30.2
