Linux-stable-mirror

linux-stable-mirror@lists.linaro.org

99 participants
123919 discussions

FAILED: patch "[PATCH] xfs: fix a memory leak in xfs_buf_item_init()" 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 fc40459de82543b565ebc839dca8f7987f16f62e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025122919-balancing-colony-41ee@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From fc40459de82543b565ebc839dca8f7987f16f62e Mon Sep 17 00:00:00 2001 From: Haoxiang Li <lihaoxiang(a)isrc.iscas.ac.cn> Date: Wed, 10 Dec 2025 17:06:01 +0800 Subject: [PATCH] xfs: fix a memory leak in xfs_buf_item_init() xfs_buf_item_get_format() may allocate memory for bip->bli_formats, free the memory in the error path. Fixes: c3d5f0c2fb85 ("xfs: complain if anyone tries to create a too-large buffer log item") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <lihaoxiang(a)isrc.iscas.ac.cn> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Carlos Maiolino <cmaiolino(a)redhat.com> Signed-off-by: Carlos Maiolino <cem(a)kernel.org> diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 8d85b5eee444..f4c5be67826e 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -896,6 +896,7 @@ xfs_buf_item_init( map_size = DIV_ROUND_UP(chunks, NBWORD); if (map_size > XFS_BLF_DATAMAP_SIZE) { + xfs_buf_item_free_format(bip); kmem_cache_free(xfs_buf_item_cache, bip); xfs_err(mp, "buffer item dirty bitmap (%u uints) too small to reflect %u bytes!",

5 days, 9 hours

[PATCH 5/5] ceph: Fix write storm on fscrypted files

by Sam Edwards

CephFS stores file data across multiple RADOS objects. An object is the atomic unit of storage, so the writeback code must clean only folios that belong to the same object with each OSD request. CephFS also supports RAID0-style striping of file contents: if enabled, each object stores multiple unbroken "stripe units" covering different portions of the file; if disabled, a "stripe unit" is simply the whole object. The stripe unit is (usually) reported as the inode's block size. Though the writeback logic could, in principle, lock all dirty folios belonging to the same object, its current design is to lock only a single stripe unit at a time. Ever since this code was first written, it has determined this size by checking the inode's block size. However, the relatively-new fscrypt support needed to reduce the block size for encrypted inodes to the crypto block size (see 'fixes' commit), which causes an unnecessarily high number of write operations (~1024x as many, with 4MiB objects) and grossly degraded performance. Fix this (and clarify intent) by using i_layout.stripe_unit directly in ceph_define_write_size() so that encrypted inodes are written back with the same number of operations as if they were unencrypted. Fixes: 94af0470924c ("ceph: add some fscrypt guardrails") Cc: stable(a)vger.kernel.org Signed-off-by: Sam Edwards <CFSworks(a)gmail.com> --- fs/ceph/addr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b3569d44d510..cb1da8e27c2b 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1000,7 +1000,8 @@ unsigned int ceph_define_write_size(struct address_space *mapping) { struct inode *inode = mapping->host; struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode); - unsigned int wsize = i_blocksize(inode); + struct ceph_inode_info *ci = ceph_inode(inode); + unsigned int wsize = ci->i_layout.stripe_unit; if (fsc->mount_options->wsize < wsize) wsize = fsc->mount_options->wsize; -- 2.51.2

5 days, 9 hours

[PATCH 3/5] ceph: Free page array when ceph_submit_write fails

by Sam Edwards

If `locked_pages` is zero, the page array must not be allocated: ceph_process_folio_batch() uses `locked_pages` to decide when to allocate `pages`, and redundant allocations trigger ceph_allocate_page_array()'s BUG_ON(), resulting in a worker oops (and writeback stall) or even a kernel panic. Consequently, the main loop in ceph_writepages_start() assumes that the lifetime of `pages` is confined to a single iteration. The ceph_submit_write() function claims ownership of the page array on success. But failures only redirty/unlock the pages and fail to free the array, making the failure case in ceph_submit_write() fatal. Free the page array in ceph_submit_write()'s error-handling 'if' block so that the caller's invariant (that the array does not outlive the iteration) is maintained unconditionally, allowing failures in ceph_submit_write() to be recoverable as originally intended. Fixes: 1551ec61dc55 ("ceph: introduce ceph_submit_write() method") Cc: stable(a)vger.kernel.org Signed-off-by: Sam Edwards <CFSworks(a)gmail.com> --- fs/ceph/addr.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 2b722916fb9b..91cc43950162 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1466,6 +1466,13 @@ int ceph_submit_write(struct address_space *mapping, unlock_page(page); } + if (ceph_wbc->from_pool) { + mempool_free(ceph_wbc->pages, ceph_wb_pagevec_pool); + ceph_wbc->from_pool = false; + } else + kfree(ceph_wbc->pages); + ceph_wbc->pages = NULL; + ceph_osdc_put_request(req); return -EIO; } -- 2.51.2

5 days, 9 hours

[PATCH 1/5] ceph: Do not propagate page array emplacement errors as batch errors

by Sam Edwards

When fscrypt is enabled, move_dirty_folio_in_page_array() may fail because it needs to allocate bounce buffers to store the encrypted versions of each folio. Each folio beyond the first allocates its bounce buffer with GFP_NOWAIT. Failures are common (and expected) under this allocation mode; they should flush (not abort) the batch. However, ceph_process_folio_batch() uses the same `rc` variable for its own return code and for capturing the return codes of its routine calls; failing to reset `rc` back to 0 results in the error being propagated out to the main writeback loop, which cannot actually tolerate any errors here: once `ceph_wbc.pages` is allocated, it must be passed to ceph_submit_write() to be freed. If it survives until the next iteration (e.g. due to the goto being followed), ceph_allocate_page_array()'s BUG_ON() will oops the worker. (Subsequent patches in this series make the loop more robust.) Note that this failure mode is currently masked due to another bug (addressed later in this series) that prevents multiple encrypted folios from being selected for the same write. For now, just reset `rc` when redirtying the folio and prevent the error from propagating. After this change, ceph_process_folio_batch() no longer returns errors; its only remaining failure indicator is `locked_pages == 0`, which the caller already handles correctly. The next patch in this series addresses this. Fixes: ce80b76dd327 ("ceph: introduce ceph_process_folio_batch() method") Cc: stable(a)vger.kernel.org Signed-off-by: Sam Edwards <CFSworks(a)gmail.com> --- fs/ceph/addr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 63b75d214210..3462df35d245 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1369,6 +1369,7 @@ int ceph_process_folio_batch(struct address_space *mapping, rc = move_dirty_folio_in_page_array(mapping, wbc, ceph_wbc, folio); if (rc) { + rc = 0; folio_redirty_for_writepage(wbc, folio); folio_unlock(folio); break; -- 2.51.2

5 days, 9 hours

[PATCH v2] mm/damon/core: remove call_control in inactive contexts

by SeongJae Park

If damon_call() is executed against a DAMON context that is not running, the function returns error while keeping the damon_call_control object linked to the context's call_controls list. Let's suppose the object is deallocated after the damon_call(), and yet another damon_call() is executed against the same context. The function tries to add the new damon_call_control object to the call_controls list, which still has the pointer to the previous damon_call_control object, which is deallocated. As a result, use-after-free happens. This can actually be triggered using the DAMON sysfs interface. It is not easily exploitable since it requires the sysfs write permission and making a definitely weird file writes, though. Please refer to the report for more details about the issue reproduction steps. Fix the issue by making two changes. Firstly, move the final kdamond_call() for cancelling all existing damon_call() requests from terminating DAMON context to be done before the ctx->kdamond reset. This makes any code that sees NULL ctx->kdamond can safely assume the context may not access damon_call() requests anymore. Secondly, let damon_call() to cleanup the damon_call_control objects that were added to the already-terminated DAMON context, before returning the error. Fixes: 004ded6bee11 ("mm/damon: accept parallel damon_call() requests") Reported-by: JaeJoon Jung <rgbi3307(a)gmail.com> Closes: https://lore.kernel.org/20251224094401.20384-1-rgbi3307@gmail.com Cc: <stable(a)vger.kernel.org> # 6.17.x Signed-off-by: SeongJae Park <sj(a)kernel.org> --- Changes from v1 (https://lkml.kernel.org/r/20251228183105.289441-1-sj@kernel.org): - Do final kdamond_call() before ctx->kdamond reset. - Fix Fixes: tag. mm/damon/core.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 2d3e8006db50..199529dd7c66 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1442,6 +1442,35 @@ bool damon_is_running(struct damon_ctx *ctx) return running; } +/* + * damon_call_handle_inactive_ctx() - handle DAMON call request that added to + * an inactive context. + * @ctx: The inactive DAMON context. + * @control: Control variable of the call request. + * + * This function is called in a case that @control is added to @ctx but @ctx is + * not running (inactive). See if @ctx handled @control or not, and cleanup + * @control if it was not handled. + * + * Returns 0 if @control was handled by @ctx, negative error code otherwise. + */ +static int damon_call_handle_inactive_ctx( + struct damon_ctx *ctx, struct damon_call_control *control) +{ + struct damon_call_control *c; + + mutex_lock(&ctx->call_controls_lock); + list_for_each_entry(c, &ctx->call_controls, list) { + if (c == control) { + list_del(&control->list); + mutex_unlock(&ctx->call_controls_lock); + return -EINVAL; + } + } + mutex_unlock(&ctx->call_controls_lock); + return 0; +} + /** * damon_call() - Invoke a given function on DAMON worker thread (kdamond). * @ctx: DAMON context to call the function for. @@ -1472,7 +1501,7 @@ int damon_call(struct damon_ctx *ctx, struct damon_call_control *control) list_add_tail(&control->list, &ctx->call_controls); mutex_unlock(&ctx->call_controls_lock); if (!damon_is_running(ctx)) - return -EINVAL; + return damon_call_handle_inactive_ctx(ctx, control); if (control->repeat) return 0; wait_for_completion(&control->completion); @@ -2797,13 +2826,13 @@ static int kdamond_fn(void *data) if (ctx->ops.cleanup) ctx->ops.cleanup(ctx); kfree(ctx->regions_score_histogram); + kdamond_call(ctx, true); pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); ctx->kdamond = NULL; mutex_unlock(&ctx->kdamond_lock); - kdamond_call(ctx, true); damos_walk_cancel(ctx); mutex_lock(&damon_lock); base-commit: 40fd05d807b3a7678e3284b8a9a6cb89a32fa8ce -- 2.47.3

5 days, 11 hours

[PATCH V3 0/2] LoongArch: KVM: fix "unreliable stack" issue

by Xianglai Li

When starting multi-core loongarch virtualization on loongarch physical machine, loading livepatch on the physical machine will cause an error similar to the following: [ 411.686289] livepatch: klp_try_switch_task: CPU 31/KVM:3116 has an unreliable stack The specific test steps are as follows: 1.Start a multi-core virtual machine on a physical machine 2.Enter the following command on the physical machine to turn on the debug switch: echo "file kernel/livepatch/transition.c +p" > /sys/kernel/debug/\ dynamic_debug/control 3.Load livepatch: modprobe livepatch-sample Through the above steps, similar prints can be viewed in dmesg. The reason for this issue is that the code of the kvm_exc_entry function was copied in the function kvm_loongarch_env_init. When the cpu needs to execute kvm_exc_entry, it will switch to the copied address for execution. The new address of the kvm_exc_entry function cannot be recognized in ORC, which eventually leads to the arch_stack_walk_reliable function returning an error and printing an exception message. To solve the above problems, we directly compile the switch.S file into the kernel instead of the module. In this way, the function kvm_exc_entry will no longer need to be copied. changlog: V3<-V2: 1.Replace the EXPORT_SYMBOL macro declaration symbol with the EXPORT_SYMBOL_FOR_KVM macro 2.Add some comments in kvm_enter_guest 3.Place the correct pc address in era 4.Move .p2align after .text V2<-V1: 1.Rollback the modification of function parameter types such as kvm_save_fpu. In the asm-prototypes.h header file, only the parameter types it depends on are included Cc: Huacai Chen <chenhuacai(a)kernel.org> Cc: WANG Xuerui <kernel(a)xen0n.name> Cc: Tianrui Zhao <zhaotianrui(a)loongson.cn> Cc: Bibo Mao <maobibo(a)loongson.cn> Cc: Charlie Jenkins <charlie(a)rivosinc.com> Cc: Xianglai Li <lixianglai(a)loongson.cn> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Cc: Tiezhu Yang <yangtiezhu(a)loongson.cn> Xianglai Li (2): LoongArch: KVM: Compile the switch.S file directly into the kernel LoongArch: KVM: fix "unreliable stack" issue arch/loongarch/Kbuild | 2 +- arch/loongarch/include/asm/asm-prototypes.h | 21 +++++++++++++ arch/loongarch/include/asm/kvm_host.h | 3 -- arch/loongarch/kvm/Makefile | 2 +- arch/loongarch/kvm/main.c | 35 ++------------------- arch/loongarch/kvm/switch.S | 32 ++++++++++++++++--- 6 files changed, 53 insertions(+), 42 deletions(-) base-commit: 8f0b4cce4481fb22653697cced8d0d04027cb1e8 -- 2.39.1

5 days, 11 hours

[PATCH] riscv: boot: Always make Image from vmlinux, not vmlinux.unstripped

by Vivian Wang

Since commit 4b47a3aefb29 ("kbuild: Restore pattern to avoid stripping .rela.dyn from vmlinux") vmlinux has .rel*.dyn preserved. Therefore, use vmlinux to produce Image, not vmlinux.unstripped. Doing so fixes booting a RELOCATABLE=y Image with kexec. The problem is caused by this chain of events: - Since commit 3e86e4d74c04 ("kbuild: keep .modinfo section in vmlinux.unstripped"), vmlinux.unstripped gets a .modinfo section. - The .modinfo section has SHF_ALLOC, so it ends up in Image, at the end of it. - The Image header's image_size field does not expect to include .modinfo and does not account for it, since it should not be in Image. - If .modinfo is large enough, the file size of Image ends up larger than image_size, which eventually leads to it failing sanity_check_segment_list(). Using vmlinux instead of vmlinux.unstripped means that the unexpected .modinfo section is gone from Image, fixing the file size problem. Cc: stable(a)vger.kernel.org Fixes: 3e86e4d74c04 ("kbuild: keep .modinfo section in vmlinux.unstripped") Signed-off-by: Vivian Wang <wangruikang(a)iscas.ac.cn> --- arch/riscv/boot/Makefile | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile index bfc3d0b75b9b..5301adf5f3f5 100644 --- a/arch/riscv/boot/Makefile +++ b/arch/riscv/boot/Makefile @@ -31,11 +31,7 @@ $(obj)/xipImage: vmlinux FORCE endif -ifdef CONFIG_RELOCATABLE -$(obj)/Image: vmlinux.unstripped FORCE -else $(obj)/Image: vmlinux FORCE -endif $(call if_changed,objcopy) $(obj)/Image.gz: $(obj)/Image FORCE --- base-commit: 8f0b4cce4481fb22653697cced8d0d04027cb1e8 change-id: 20251230-riscv-vmlinux-not-unstripped-30ec0c930fd2 Best regards, -- Vivian "dramforever" Wang

5 days, 11 hours

FAILED: patch "[PATCH] f2fs: use global inline_xattr_slab instead of per-sb slab" 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 1f27ef42bb0b7c0740c5616ec577ec188b8a1d05 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025122924-placidly-rehire-4364@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1f27ef42bb0b7c0740c5616ec577ec188b8a1d05 Mon Sep 17 00:00:00 2001 From: Chao Yu <chao(a)kernel.org> Date: Tue, 21 Oct 2025 11:48:56 +0800 Subject: [PATCH] f2fs: use global inline_xattr_slab instead of per-sb slab cache MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As Hong Yun reported in mailing list: loop7: detected capacity change from 0 to 131072 ------------[ cut here ]------------ kmem_cache of name 'f2fs_xattr_entry-7:7' already exists WARNING: CPU: 0 PID: 24426 at mm/slab_common.c:110 kmem_cache_sanity_check mm/slab_common.c:109 [inline] WARNING: CPU: 0 PID: 24426 at mm/slab_common.c:110 __kmem_cache_create_args+0xa6/0x320 mm/slab_common.c:307 CPU: 0 UID: 0 PID: 24426 Comm: syz.7.1370 Not tainted 6.17.0-rc4 #1 PREEMPT(full) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:kmem_cache_sanity_check mm/slab_common.c:109 [inline] RIP: 0010:__kmem_cache_create_args+0xa6/0x320 mm/slab_common.c:307 Call Trace: __kmem_cache_create include/linux/slab.h:353 [inline] f2fs_kmem_cache_create fs/f2fs/f2fs.h:2943 [inline] f2fs_init_xattr_caches+0xa5/0xe0 fs/f2fs/xattr.c:843 f2fs_fill_super+0x1645/0x2620 fs/f2fs/super.c:4918 get_tree_bdev_flags+0x1fb/0x260 fs/super.c:1692 vfs_get_tree+0x43/0x140 fs/super.c:1815 do_new_mount+0x201/0x550 fs/namespace.c:3808 do_mount fs/namespace.c:4136 [inline] __do_sys_mount fs/namespace.c:4347 [inline] __se_sys_mount+0x298/0x2f0 fs/namespace.c:4324 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x8e/0x3a0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e The bug can be reproduced w/ below scripts: - mount /dev/vdb /mnt1 - mount /dev/vdc /mnt2 - umount /mnt1 - mounnt /dev/vdb /mnt1 The reason is if we created two slab caches, named f2fs_xattr_entry-7:3 and f2fs_xattr_entry-7:7, and they have the same slab size. Actually, slab system will only create one slab cache core structure which has slab name of "f2fs_xattr_entry-7:3", and two slab caches share the same structure and cache address. So, if we destroy f2fs_xattr_entry-7:3 cache w/ cache address, it will decrease reference count of slab cache, rather than release slab cache entirely, since there is one more user has referenced the cache. Then, if we try to create slab cache w/ name "f2fs_xattr_entry-7:3" again, slab system will find that there is existed cache which has the same name and trigger the warning. Let's changes to use global inline_xattr_slab instead of per-sb slab cache for fixing. Fixes: a999150f4fe3 ("f2fs: use kmem_cache pool during inline xattr lookups") Cc: stable(a)kernel.org Reported-by: Hong Yun <yhong(a)link.cuhk.edu.hk> Tested-by: Hong Yun <yhong(a)link.cuhk.edu.hk> Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index e69b01c1173a..9ca2124aac84 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1885,9 +1885,6 @@ struct f2fs_sb_info { spinlock_t error_lock; /* protect errors/stop_reason array */ bool error_dirty; /* errors of sb is dirty */ - struct kmem_cache *inline_xattr_slab; /* inline xattr entry */ - unsigned int inline_xattr_slab_size; /* default inline xattr slab size */ - /* For reclaimed segs statistics per each GC mode */ unsigned int gc_segment_mode; /* GC state for reclaimed segments */ unsigned int gc_reclaimed_segs[MAX_GC_MODE]; /* Reclaimed segs for each mode */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d0b5791a1f8c..f76ba2b08be0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2027,7 +2027,6 @@ static void f2fs_put_super(struct super_block *sb) kfree(sbi->raw_super); f2fs_destroy_page_array_cache(sbi); - f2fs_destroy_xattr_caches(sbi); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) kfree(F2FS_OPTION(sbi).s_qf_names[i]); @@ -4975,13 +4974,9 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) goto free_iostat; - /* init per sbi slab cache */ - err = f2fs_init_xattr_caches(sbi); - if (err) - goto free_percpu; err = f2fs_init_page_array_cache(sbi); if (err) - goto free_xattr_cache; + goto free_percpu; /* get an inode for meta space */ sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi)); @@ -5310,8 +5305,6 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) sbi->meta_inode = NULL; free_page_array_cache: f2fs_destroy_page_array_cache(sbi); -free_xattr_cache: - f2fs_destroy_xattr_caches(sbi); free_percpu: destroy_percpu_info(sbi); free_iostat: @@ -5514,10 +5507,15 @@ static int __init init_f2fs_fs(void) err = f2fs_create_casefold_cache(); if (err) goto free_compress_cache; - err = register_filesystem(&f2fs_fs_type); + err = f2fs_init_xattr_cache(); if (err) goto free_casefold_cache; + err = register_filesystem(&f2fs_fs_type); + if (err) + goto free_xattr_cache; return 0; +free_xattr_cache: + f2fs_destroy_xattr_cache(); free_casefold_cache: f2fs_destroy_casefold_cache(); free_compress_cache: @@ -5558,6 +5556,7 @@ static int __init init_f2fs_fs(void) static void __exit exit_f2fs_fs(void) { unregister_filesystem(&f2fs_fs_type); + f2fs_destroy_xattr_cache(); f2fs_destroy_casefold_cache(); f2fs_destroy_compress_cache(); f2fs_destroy_compress_mempool(); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 58632a2b6613..b4e5c406632f 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -23,11 +23,12 @@ #include "xattr.h" #include "segment.h" +static struct kmem_cache *inline_xattr_slab; static void *xattr_alloc(struct f2fs_sb_info *sbi, int size, bool *is_inline) { - if (likely(size == sbi->inline_xattr_slab_size)) { + if (likely(size == DEFAULT_XATTR_SLAB_SIZE)) { *is_inline = true; - return f2fs_kmem_cache_alloc(sbi->inline_xattr_slab, + return f2fs_kmem_cache_alloc(inline_xattr_slab, GFP_F2FS_ZERO, false, sbi); } *is_inline = false; @@ -38,7 +39,7 @@ static void xattr_free(struct f2fs_sb_info *sbi, void *xattr_addr, bool is_inline) { if (is_inline) - kmem_cache_free(sbi->inline_xattr_slab, xattr_addr); + kmem_cache_free(inline_xattr_slab, xattr_addr); else kfree(xattr_addr); } @@ -830,25 +831,14 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, return err; } -int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) +int __init f2fs_init_xattr_cache(void) { - dev_t dev = sbi->sb->s_bdev->bd_dev; - char slab_name[32]; - - sprintf(slab_name, "f2fs_xattr_entry-%u:%u", MAJOR(dev), MINOR(dev)); - - sbi->inline_xattr_slab_size = F2FS_OPTION(sbi).inline_xattr_size * - sizeof(__le32) + XATTR_PADDING_SIZE; - - sbi->inline_xattr_slab = f2fs_kmem_cache_create(slab_name, - sbi->inline_xattr_slab_size); - if (!sbi->inline_xattr_slab) - return -ENOMEM; - - return 0; + inline_xattr_slab = f2fs_kmem_cache_create("f2fs_xattr_entry", + DEFAULT_XATTR_SLAB_SIZE); + return inline_xattr_slab ? 0 : -ENOMEM; } -void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) +void f2fs_destroy_xattr_cache(void) { - kmem_cache_destroy(sbi->inline_xattr_slab); -} + kmem_cache_destroy(inline_xattr_slab); +} \ No newline at end of file diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 4fc0b2305fbd..bce3d93e4755 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -89,6 +89,8 @@ struct f2fs_xattr_entry { F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \ DEF_INLINE_RESERVED_SIZE - \ MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) +#define DEFAULT_XATTR_SLAB_SIZE (DEFAULT_INLINE_XATTR_ADDRS * \ + sizeof(__le32) + XATTR_PADDING_SIZE) /* * On-disk structure of f2fs_xattr @@ -132,8 +134,8 @@ int f2fs_setxattr(struct inode *, int, const char *, const void *, int f2fs_getxattr(struct inode *, int, const char *, void *, size_t, struct folio *); ssize_t f2fs_listxattr(struct dentry *, char *, size_t); -int f2fs_init_xattr_caches(struct f2fs_sb_info *); -void f2fs_destroy_xattr_caches(struct f2fs_sb_info *); +int __init f2fs_init_xattr_cache(void); +void f2fs_destroy_xattr_cache(void); #else #define f2fs_xattr_handlers NULL @@ -150,8 +152,8 @@ static inline int f2fs_getxattr(struct inode *inode, int index, { return -EOPNOTSUPP; } -static inline int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) { return 0; } -static inline void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) { } +static inline int __init f2fs_init_xattr_cache(void) { return 0; } +static inline void f2fs_destroy_xattr_cache(void) { } #endif #ifdef CONFIG_F2FS_FS_SECURITY

5 days, 14 hours

FAILED: patch "[PATCH] pinctrl: renesas: rzg2l: Fix ISEL restore on resume" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-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-6.12.y git checkout FETCH_HEAD git cherry-pick -x 44bf66122c12ef6d3382a9b84b9be1802e5f0e95 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025122907-jujitsu-boneless-55a8@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 44bf66122c12ef6d3382a9b84b9be1802e5f0e95 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Date: Fri, 12 Sep 2025 12:53:08 +0300 Subject: [PATCH] pinctrl: renesas: rzg2l: Fix ISEL restore on resume Commit 1d2da79708cb ("pinctrl: renesas: rzg2l: Avoid configuring ISEL in gpio_irq_{en,dis}able*()") dropped the configuration of ISEL from struct irq_chip::{irq_enable, irq_disable} APIs and moved it to struct gpio_chip::irq::{child_to_parent_hwirq, child_irq_domain_ops::free} APIs to fix spurious IRQs. After commit 1d2da79708cb ("pinctrl: renesas: rzg2l: Avoid configuring ISEL in gpio_irq_{en,dis}able*()"), ISEL was no longer configured properly on resume. This is because the pinctrl resume code used struct irq_chip::irq_enable (called from rzg2l_gpio_irq_restore()) to reconfigure the wakeup interrupts. Some drivers (e.g. Ethernet) may also reconfigure non-wakeup interrupts on resume through their own code, eventually calling struct irq_chip::irq_enable. Fix this by adding ISEL configuration back into the struct irq_chip::irq_enable API and on resume path for wakeup interrupts. As struct irq_chip::irq_enable needs now to lock to update the ISEL, convert the struct rzg2l_pinctrl::lock to a raw spinlock and replace the locking API calls with the raw variants. Otherwise the lockdep reports invalid wait context when probing the adv7511 module on RZ/G2L: [ BUG: Invalid wait context ] 6.17.0-rc5-next-20250911-00001-gfcfac22533c9 #18 Not tainted ----------------------------- (udev-worker)/165 is trying to lock: ffff00000e3664a8 (&pctrl->lock){....}-{3:3}, at: rzg2l_gpio_irq_enable+0x38/0x78 other info that might help us debug this: context-{5:5} 3 locks held by (udev-worker)/165: #0: ffff00000e890108 (&dev->mutex){....}-{4:4}, at: __driver_attach+0x90/0x1ac #1: ffff000011c07240 (request_class){+.+.}-{4:4}, at: __setup_irq+0xb4/0x6dc #2: ffff000011c070c8 (lock_class){....}-{2:2}, at: __setup_irq+0xdc/0x6dc stack backtrace: CPU: 1 UID: 0 PID: 165 Comm: (udev-worker) Not tainted 6.17.0-rc5-next-20250911-00001-gfcfac22533c9 #18 PREEMPT Hardware name: Renesas SMARC EVK based on r9a07g044l2 (DT) Call trace: show_stack+0x18/0x24 (C) dump_stack_lvl+0x90/0xd0 dump_stack+0x18/0x24 __lock_acquire+0xa14/0x20b4 lock_acquire+0x1c8/0x354 _raw_spin_lock_irqsave+0x60/0x88 rzg2l_gpio_irq_enable+0x38/0x78 irq_enable+0x40/0x8c __irq_startup+0x78/0xa4 irq_startup+0x108/0x16c __setup_irq+0x3c0/0x6dc request_threaded_irq+0xec/0x1ac devm_request_threaded_irq+0x80/0x134 adv7511_probe+0x928/0x9a4 [adv7511] i2c_device_probe+0x22c/0x3dc really_probe+0xbc/0x2a0 __driver_probe_device+0x78/0x12c driver_probe_device+0x40/0x164 __driver_attach+0x9c/0x1ac bus_for_each_dev+0x74/0xd0 driver_attach+0x24/0x30 bus_add_driver+0xe4/0x208 driver_register+0x60/0x128 i2c_register_driver+0x48/0xd0 adv7511_init+0x5c/0x1000 [adv7511] do_one_initcall+0x64/0x30c do_init_module+0x58/0x23c load_module+0x1bcc/0x1d40 init_module_from_file+0x88/0xc4 idempotent_init_module+0x188/0x27c __arm64_sys_finit_module+0x68/0xac invoke_syscall+0x48/0x110 el0_svc_common.constprop.0+0xc0/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x4c/0x160 el0t_64_sync_handler+0xa0/0xe4 el0t_64_sync+0x198/0x19c Having ISEL configuration back into the struct irq_chip::irq_enable API should be safe with respect to spurious IRQs, as in the probe case IRQs are enabled anyway in struct gpio_chip::irq::child_to_parent_hwirq. No spurious IRQs were detected on suspend/resume, boot, ethernet link insert/remove tests (executed on RZ/G3S). Boot, ethernet link insert/remove tests were also executed successfully on RZ/G2L. Fixes: 1d2da79708cb ("pinctrl: renesas: rzg2l: Avoid configuring ISEL in gpio_irq_{en,dis}able*(") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Reviewed-by: Geert Uytterhoeven <geert+renesas(a)glider.be> Link: https://patch.msgid.link/20250912095308.3603704-1-claudiu.beznea.uj@bp.rene… Signed-off-by: Geert Uytterhoeven <geert+renesas(a)glider.be> diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index f524af6f586f..c360e473488c 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -359,7 +359,7 @@ struct rzg2l_pinctrl { spinlock_t bitmap_lock; /* protect tint_slot bitmap */ unsigned int hwirq[RZG2L_TINT_MAX_INTERRUPT]; - spinlock_t lock; /* lock read/write registers */ + raw_spinlock_t lock; /* lock read/write registers */ struct mutex mutex; /* serialize adding groups and functions */ struct rzg2l_pinctrl_pin_settings *settings; @@ -543,7 +543,7 @@ static void rzg2l_pinctrl_set_pfc_mode(struct rzg2l_pinctrl *pctrl, unsigned long flags; u32 reg; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); /* Set pin to 'Non-use (Hi-Z input protection)' */ reg = readw(pctrl->base + PM(off)); @@ -567,7 +567,7 @@ static void rzg2l_pinctrl_set_pfc_mode(struct rzg2l_pinctrl *pctrl, pctrl->data->pwpr_pfc_lock_unlock(pctrl, true); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); }; static int rzg2l_pinctrl_set_mux(struct pinctrl_dev *pctldev, @@ -882,10 +882,10 @@ static void rzg2l_rmw_pin_config(struct rzg2l_pinctrl *pctrl, u32 offset, addr += 4; } - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg = readl(addr) & ~(mask << (bit * 8)); writel(reg | (val << (bit * 8)), addr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_caps_to_pwr_reg(const struct rzg2l_register_offsets *regs, u32 caps) @@ -1121,7 +1121,7 @@ static int rzg2l_write_oen(struct rzg2l_pinctrl *pctrl, unsigned int _pin, u8 oe if (bit < 0) return -EINVAL; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); val = readb(pctrl->base + oen_offset); if (oen) val &= ~BIT(bit); @@ -1134,7 +1134,7 @@ static int rzg2l_write_oen(struct rzg2l_pinctrl *pctrl, unsigned int _pin, u8 oe writeb(val, pctrl->base + oen_offset); if (pctrl->data->hwcfg->oen_pwpr_lock) writeb(pwpr & ~PWPR_REGWE_B, pctrl->base + regs->pwpr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -1687,14 +1687,14 @@ static int rzg2l_gpio_request(struct gpio_chip *chip, unsigned int offset) if (ret) return ret; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); /* Select GPIO mode in PMC Register */ reg8 = readb(pctrl->base + PMC(off)); reg8 &= ~BIT(bit); pctrl->data->pmc_writeb(pctrl, reg8, PMC(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -1709,7 +1709,7 @@ static void rzg2l_gpio_set_direction(struct rzg2l_pinctrl *pctrl, u32 offset, unsigned long flags; u16 reg16; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg16 = readw(pctrl->base + PM(off)); reg16 &= ~(PM_MASK << (bit * 2)); @@ -1717,7 +1717,7 @@ static void rzg2l_gpio_set_direction(struct rzg2l_pinctrl *pctrl, u32 offset, reg16 |= (output ? PM_OUTPUT : PM_INPUT) << (bit * 2); writew(reg16, pctrl->base + PM(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) @@ -1761,7 +1761,7 @@ static int rzg2l_gpio_set(struct gpio_chip *chip, unsigned int offset, unsigned long flags; u8 reg8; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg8 = readb(pctrl->base + P(off)); @@ -1770,7 +1770,7 @@ static int rzg2l_gpio_set(struct gpio_chip *chip, unsigned int offset, else writeb(reg8 & ~BIT(bit), pctrl->base + P(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -2429,14 +2429,13 @@ static int rzg2l_gpio_get_gpioint(unsigned int virq, struct rzg2l_pinctrl *pctrl return gpioint; } -static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, - unsigned int hwirq, bool enable) +static void __rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, + unsigned int hwirq, bool enable) { const struct pinctrl_pin_desc *pin_desc = &pctrl->desc.pins[hwirq]; u64 *pin_data = pin_desc->drv_data; u32 off = RZG2L_PIN_CFG_TO_PORT_OFFSET(*pin_data); u8 bit = RZG2L_PIN_ID_TO_PIN(hwirq); - unsigned long flags; void __iomem *addr; addr = pctrl->base + ISEL(off); @@ -2445,12 +2444,20 @@ static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, addr += 4; } - spin_lock_irqsave(&pctrl->lock, flags); if (enable) writel(readl(addr) | BIT(bit * 8), addr); else writel(readl(addr) & ~BIT(bit * 8), addr); - spin_unlock_irqrestore(&pctrl->lock, flags); +} + +static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, + unsigned int hwirq, bool enable) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&pctrl->lock, flags); + __rzg2l_gpio_irq_endisable(pctrl, hwirq, enable); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static void rzg2l_gpio_irq_disable(struct irq_data *d) @@ -2462,15 +2469,25 @@ static void rzg2l_gpio_irq_disable(struct irq_data *d) gpiochip_disable_irq(gc, hwirq); } -static void rzg2l_gpio_irq_enable(struct irq_data *d) +static void __rzg2l_gpio_irq_enable(struct irq_data *d, bool lock) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct rzg2l_pinctrl *pctrl = container_of(gc, struct rzg2l_pinctrl, gpio_chip); unsigned int hwirq = irqd_to_hwirq(d); gpiochip_enable_irq(gc, hwirq); + if (lock) + rzg2l_gpio_irq_endisable(pctrl, hwirq, true); + else + __rzg2l_gpio_irq_endisable(pctrl, hwirq, true); irq_chip_enable_parent(d); } +static void rzg2l_gpio_irq_enable(struct irq_data *d) +{ + __rzg2l_gpio_irq_enable(d, true); +} + static int rzg2l_gpio_irq_set_type(struct irq_data *d, unsigned int type) { return irq_chip_set_type_parent(d, type); @@ -2616,11 +2633,11 @@ static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl) * This has to be atomically executed to protect against a concurrent * interrupt. */ - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); ret = rzg2l_gpio_irq_set_type(data, irqd_get_trigger_type(data)); if (!ret && !irqd_irq_disabled(data)) - rzg2l_gpio_irq_enable(data); - spin_unlock_irqrestore(&pctrl->lock, flags); + __rzg2l_gpio_irq_enable(data, false); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); if (ret) dev_crit(pctrl->dev, "Failed to set IRQ type for virq=%u\n", virq); @@ -2950,7 +2967,7 @@ static int rzg2l_pinctrl_probe(struct platform_device *pdev) "failed to enable GPIO clk\n"); } - spin_lock_init(&pctrl->lock); + raw_spin_lock_init(&pctrl->lock); spin_lock_init(&pctrl->bitmap_lock); mutex_init(&pctrl->mutex); atomic_set(&pctrl->wakeup_path, 0); @@ -3093,7 +3110,7 @@ static void rzg2l_pinctrl_pm_setup_pfc(struct rzg2l_pinctrl *pctrl) u32 nports = pctrl->data->n_port_pins / RZG2L_PINS_PER_PORT; unsigned long flags; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); pctrl->data->pwpr_pfc_lock_unlock(pctrl, false); /* Restore port registers. */ @@ -3138,7 +3155,7 @@ static void rzg2l_pinctrl_pm_setup_pfc(struct rzg2l_pinctrl *pctrl) } pctrl->data->pwpr_pfc_lock_unlock(pctrl, true); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_pinctrl_suspend_noirq(struct device *dev) @@ -3187,14 +3204,14 @@ static int rzg2l_pinctrl_resume_noirq(struct device *dev) writeb(cache->qspi, pctrl->base + QSPI); if (pctrl->data->hwcfg->oen_pwpr_lock) { - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); pwpr = readb(pctrl->base + regs->pwpr); writeb(pwpr | PWPR_REGWE_B, pctrl->base + regs->pwpr); } writeb(cache->oen, pctrl->base + pctrl->data->hwcfg->regs.oen); if (pctrl->data->hwcfg->oen_pwpr_lock) { writeb(pwpr & ~PWPR_REGWE_B, pctrl->base + regs->pwpr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } for (u8 i = 0; i < 2; i++) { if (regs->sd_ch)

5 days, 14 hours

[PATCH RESEND v3 4/4] mm/hugetlb: fix excessive IPI broadcasts when unsharing PMD tables using mmu_gather

by David Hildenbrand (Red Hat)

As reported, ever since commit 1013af4f585f ("mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race") we can end up in some situations where we perform so many IPI broadcasts when unsharing hugetlb PMD page tables that it severely regresses some workloads. In particular, when we fork()+exit(), or when we munmap() a large area backed by many shared PMD tables, we perform one IPI broadcast per unshared PMD table. There are two optimizations to be had: (1) When we process (unshare) multiple such PMD tables, such as during exit(), it is sufficient to send a single IPI broadcast (as long as we respect locking rules) instead of one per PMD table. Locking prevents that any of these PMD tables could get reused before we drop the lock. (2) When we are not the last sharer (> 2 users including us), there is no need to send the IPI broadcast. The shared PMD tables cannot become exclusive (fully unshared) before an IPI will be broadcasted by the last sharer. Concurrent GUP-fast could walk into a PMD table just before we unshared it. It could then succeed in grabbing a page from the shared page table even after munmap() etc succeeded (and supressed an IPI). But there is not difference compared to GUP-fast just sleeping for a while after grabbing the page and re-enabling IRQs. Most importantly, GUP-fast will never walk into page tables that are no-longer shared, because the last sharer will issue an IPI broadcast. (if ever required, checking whether the PUD changed in GUP-fast after grabbing the page like we do in the PTE case could handle this) So let's rework PMD sharing TLB flushing + IPI sync to use the mmu_gather infrastructure so we can implement these optimizations and demystify the code at least a bit. Extend the mmu_gather infrastructure to be able to deal with our special hugetlb PMD table sharing implementation. To make initialization of the mmu_gather easier when working on a single VMA (in particular, when dealing with hugetlb), provide tlb_gather_mmu_vma(). We'll consolidate the handling for (full) unsharing of PMD tables in tlb_unshare_pmd_ptdesc() and tlb_flush_unshared_tables(), and track in "struct mmu_gather" whether we had (full) unsharing of PMD tables. Because locking is very special (concurrent unsharing+reuse must be prevented), we disallow deferring flushing to tlb_finish_mmu() and instead require an explicit earlier call to tlb_flush_unshared_tables(). From hugetlb code, we call huge_pmd_unshare_flush() where we make sure that the expected lock protecting us from concurrent unsharing+reuse is still held. Check with a VM_WARN_ON_ONCE() in tlb_finish_mmu() that tlb_flush_unshared_tables() was properly called earlier. Document it all properly. Notes about tlb_remove_table_sync_one() interaction with unsharing: There are two fairly tricky things: (1) tlb_remove_table_sync_one() is a NOP on architectures without CONFIG_MMU_GATHER_RCU_TABLE_FREE. Here, the assumption is that the previous TLB flush would send an IPI to all relevant CPUs. Careful: some architectures like x86 only send IPIs to all relevant CPUs when tlb->freed_tables is set. The relevant architectures should be selecting MMU_GATHER_RCU_TABLE_FREE, but x86 might not do that in stable kernels and it might have been problematic before this patch. Also, the arch flushing behavior (independent of IPIs) is different when tlb->freed_tables is set. Do we have to enlighten them to also take care of tlb->unshared_tables? So far we didn't care, so hopefully we are fine. Of course, we could be setting tlb->freed_tables as well, but that might then unnecessarily flush too much, because the semantics of tlb->freed_tables are a bit fuzzy. This patch changes nothing in this regard. (2) tlb_remove_table_sync_one() is not a NOP on architectures with CONFIG_MMU_GATHER_RCU_TABLE_FREE that actually don't need a sync. Take x86 as an example: in the common case (!pv, !X86_FEATURE_INVLPGB) we still issue IPIs during TLB flushes and don't actually need the second tlb_remove_table_sync_one(). This optimized can be implemented on top of this, by checking e.g., in tlb_remove_table_sync_one() whether we really need IPIs. But as described in (1), it really must honor tlb->freed_tables then to send IPIs to all relevant CPUs. Notes on TLB flushing changes: (1) Flushing for non-shared PMD tables We're converting from flush_hugetlb_tlb_range() to tlb_remove_huge_tlb_entry(). Given that we properly initialize the MMU gather in tlb_gather_mmu_vma() to be hugetlb aware, similar to __unmap_hugepage_range(), that should be fine. (2) Flushing for shared PMD tables We're converting from various things (flush_hugetlb_tlb_range(), tlb_flush_pmd_range(), flush_tlb_range()) to tlb_flush_pmd_range(). tlb_flush_pmd_range() achieves the same that tlb_remove_huge_tlb_entry() would achieve in these scenarios. Note that tlb_remove_huge_tlb_entry() also calls __tlb_remove_tlb_entry(), however that is only implemented on powerpc, which does not support PMD table sharing. Similar to (1), tlb_gather_mmu_vma() should make sure that TLB flushing keeps on working as expected. Further, note that the ptdesc_pmd_pts_dec() in huge_pmd_share() is not a concern, as we are holding the i_mmap_lock the whole time, preventing concurrent unsharing. That ptdesc_pmd_pts_dec() usage will be removed separately as a cleanup later. There are plenty more cleanups to be had, but they have to wait until this is fixed. Fixes: 1013af4f585f ("mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race") Reported-by: Uschakow, Stanislav" <suschako(a)amazon.de> Closes: https://lore.kernel.org/all/4d3878531c76479d9f8ca9789dc6485d@amazon.de/ Tested-by: Laurence Oberman <loberman(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: David Hildenbrand (Red Hat) <david(a)kernel.org> --- include/asm-generic/tlb.h | 77 +++++++++++++++++++++++- include/linux/hugetlb.h | 15 +++-- include/linux/mm_types.h | 1 + mm/hugetlb.c | 123 ++++++++++++++++++++++---------------- mm/mmu_gather.c | 33 ++++++++++ mm/rmap.c | 25 +++++--- 6 files changed, 208 insertions(+), 66 deletions(-) diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 1fff717cae510..4d679d2a206b4 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -46,7 +46,8 @@ * * The mmu_gather API consists of: * - * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu() + * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / + * tlb_finish_mmu() * * start and finish a mmu_gather * @@ -364,6 +365,20 @@ struct mmu_gather { unsigned int vma_huge : 1; unsigned int vma_pfn : 1; + /* + * Did we unshare (unmap) any shared page tables? For now only + * used for hugetlb PMD table sharing. + */ + unsigned int unshared_tables : 1; + + /* + * Did we unshare any page tables such that they are now exclusive + * and could get reused+modified by the new owner? When setting this + * flag, "unshared_tables" will be set as well. For now only used + * for hugetlb PMD table sharing. + */ + unsigned int fully_unshared_tables : 1; + unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER @@ -400,6 +415,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; + tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an @@ -484,7 +500,7 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || - tlb->cleared_puds || tlb->cleared_p4ds)) + tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); @@ -773,6 +789,63 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) } #endif +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, + unsigned long addr) +{ + /* + * The caller must make sure that concurrent unsharing + exclusive + * reuse is impossible until tlb_flush_unshared_tables() was called. + */ + VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); + ptdesc_pmd_pts_dec(pt); + + /* Clearing a PUD pointing at a PMD table with PMD leaves. */ + tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); + + /* + * If the page table is now exclusively owned, we fully unshared + * a page table. + */ + if (!ptdesc_pmd_is_shared(pt)) + tlb->fully_unshared_tables = true; + tlb->unshared_tables = true; +} + +static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) +{ + /* + * As soon as the caller drops locks to allow for reuse of + * previously-shared tables, these tables could get modified and + * even reused outside of hugetlb context, so we have to make sure that + * any page table walkers (incl. TLB, GUP-fast) are aware of that + * change. + * + * Even if we are not fully unsharing a PMD table, we must + * flush the TLB for the unsharer now. + */ + if (tlb->unshared_tables) + tlb_flush_mmu_tlbonly(tlb); + + /* + * Similarly, we must make sure that concurrent GUP-fast will not + * walk previously-shared page tables that are getting modified+reused + * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. + * + * We only perform this when we are the last sharer of a page table, + * as the IPI will reach all CPUs: any GUP-fast. + * + * Note that on configs where tlb_remove_table_sync_one() is a NOP, + * the expectation is that the tlb_flush_mmu_tlbonly() would have issued + * required IPIs already for us. + */ + if (tlb->fully_unshared_tables) { + tlb_remove_table_sync_one(); + tlb->fully_unshared_tables = false; + } +} +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 03c8725efa289..e51b8ef0cebd9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -240,8 +240,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); @@ -300,13 +301,17 @@ static inline struct address_space *hugetlb_folio_mapping_lock_write( return NULL; } -static inline int huge_pmd_unshare(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline int huge_pmd_unshare(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } +static inline void huge_pmd_unshare_flush(struct mmu_gather *tlb, + struct vm_area_struct *vma) +{ +} + static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 42af2292951d4..d1053b2c1f800 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1522,6 +1522,7 @@ static inline unsigned int mm_cid_size(void) struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma); extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3c77cdef12a32..2609b6d58f99e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5096,7 +5096,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; - bool shared_pmd = false; + struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); @@ -5106,6 +5106,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, * range. */ flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); @@ -5122,8 +5123,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; - if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { - shared_pmd = true; + if (huge_pmd_unshare(&tlb, vma, old_addr, src_pte)) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; @@ -5134,15 +5134,16 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); + tlb_remove_huge_tlb_entry(h, &tlb, src_pte, old_addr); } - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, old_end - len, old_end); + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); + mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); return len + old_addr - old_end; } @@ -5161,7 +5162,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); bool adjust_reservation; unsigned long last_addr_mask; - bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -5184,10 +5184,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(tlb, vma, address, ptep)) { spin_unlock(ptl); - tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); - force_flush = true; address |= last_addr_mask; continue; } @@ -5303,14 +5301,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } tlb_end_vma(tlb, vma); - /* - * There is nothing protecting a previously-shared page table that we - * unshared through huge_pmd_unshare() from getting freed after we - * release i_mmap_rwsem, so flush the TLB now. If huge_pmd_unshare() - * succeeded, flush the range corresponding to the pud. - */ - if (force_flush) - tlb_flush_mmu_tlbonly(tlb); + huge_pmd_unshare_flush(tlb, vma); } void __hugetlb_zap_begin(struct vm_area_struct *vma, @@ -6409,11 +6400,11 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); - bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + struct mmu_gather tlb; /* * In the case of shared PMDs, the area to flush could be beyond @@ -6426,6 +6417,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); @@ -6452,7 +6444,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, } } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(&tlb, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it @@ -6461,7 +6453,6 @@ long hugetlb_change_protection(struct vm_area_struct *vma, WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); - shared_pmd = true; address |= last_addr_mask; continue; } @@ -6522,22 +6513,16 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + tlb_remove_huge_tlb_entry(h, &tlb, ptep, address); } next: spin_unlock(ptl); cond_resched(); } - /* - * There is nothing protecting a previously-shared page table that we - * unshared through huge_pmd_unshare() from getting freed after we - * release i_mmap_rwsem, so flush the TLB now. If huge_pmd_unshare() - * succeeded, flush the range corresponding to the pud. - */ - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, start, end); + + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new @@ -6548,6 +6533,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); return pages > 0 ? (pages << h->order) : pages; } @@ -6904,18 +6890,27 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return pte; } -/* - * unmap huge page backed by shared pte. +/** + * huge_pmd_unshare - Unmap a pmd table if it is shared by multiple users + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * @addr: the address we are trying to unshare. + * @ptep: pointer into the (pmd) page table. + * + * Called with the page table lock held, the i_mmap_rwsem held in write mode + * and the hugetlb vma lock held in write mode. * - * Called with page table lock held. + * Note: The caller must call huge_pmd_unshare_flush() before dropping the + * i_mmap_rwsem. * - * returns: 1 successfully unmapped a shared pte page - * 0 the underlying pte page is not shared, or it is the last user + * Returns: 1 if it was a shared PMD table and it got unmapped, or 0 if it + * was not a shared PMD table. */ -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); + struct mm_struct *mm = vma->vm_mm; pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); @@ -6927,18 +6922,36 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); pud_clear(pud); - /* - * Once our caller drops the rmap lock, some other process might be - * using this page table as a normal, non-hugetlb page table. - * Wait for pending gup_fast() in other threads to finish before letting - * that happen. - */ - tlb_remove_table_sync_one(); - ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); + + tlb_unshare_pmd_ptdesc(tlb, virt_to_ptdesc(ptep), addr); + mm_dec_nr_pmds(mm); return 1; } +/* + * huge_pmd_unshare_flush - Complete a sequence of huge_pmd_unshare() calls + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * + * Perform necessary TLB flushes or IPI broadcasts to synchronize PMD table + * unsharing with concurrent page table walkers. + * + * This function must be called after a sequence of huge_pmd_unshare() + * calls while still holding the i_mmap_rwsem. + */ +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + /* + * We must synchronize page table unsharing such that nobody will + * try reusing a previously-shared page table while it might still + * be in use by previous sharers (TLB, GUP_fast). + */ + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + + tlb_flush_unshared_tables(tlb); +} + #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, @@ -6947,12 +6960,16 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; } -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { return 0; } +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ +} + void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { @@ -7219,6 +7236,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; + struct mmu_gather tlb; unsigned long address; spinlock_t *ptl; pte_t *ptep; @@ -7230,6 +7248,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, return; flush_cache_range(vma, start, end); + tlb_gather_mmu_vma(&tlb, vma); + /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. @@ -7248,10 +7268,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - huge_pmd_unshare(mm, vma, address, ptep); + huge_pmd_unshare(&tlb, vma, address, ptep); spin_unlock(ptl); } - flush_hugetlb_tlb_range(vma, start, end); + huge_pmd_unshare_flush(&tlb, vma); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); @@ -7261,6 +7281,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); } /* diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 247e3f9db6c7a..cd32c2dbf501b 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -10,6 +10,7 @@ #include <linux/swap.h> #include <linux/rmap.h> #include <linux/pgalloc.h> +#include <linux/hugetlb.h> #include <asm/tlb.h> @@ -426,6 +427,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, #endif tlb->vma_pfn = 0; + tlb->fully_unshared_tables = 0; __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } @@ -459,6 +461,31 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) __tlb_gather_mmu(tlb, mm, true); } +/** + * tlb_gather_mmu - initialize an mmu_gather structure for operating on a single + * VMA + * @tlb: the mmu_gather structure to initialize + * @vma: the vm_area_struct + * + * Called to initialize an (on-stack) mmu_gather structure for operating on + * a single VMA. In contrast to tlb_gather_mmu(), calling this function will + * not require another call to tlb_start_vma(). In contrast to tlb_start_vma(), + * this function will *not* call flush_cache_range(). + * + * For hugetlb VMAs, this function will also initialize the mmu_gather + * page_size accordingly, not requiring a separate call to + * tlb_change_page_size(). + * + */ +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + tlb_gather_mmu(tlb, vma->vm_mm); + tlb_update_vma_flags(tlb, vma); + if (is_vm_hugetlb_page(vma)) + /* All entries have the same size. */ + tlb_change_page_size(tlb, huge_page_size(hstate_vma(vma))); +} + /** * tlb_finish_mmu - finish an mmu_gather structure * @tlb: the mmu_gather structure to finish @@ -468,6 +495,12 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) */ void tlb_finish_mmu(struct mmu_gather *tlb) { + /* + * We expect an earlier huge_pmd_unshare_flush() call to sort this out, + * due to complicated locking requirements with page table unsharing. + */ + VM_WARN_ON_ONCE(tlb->fully_unshared_tables); + /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB diff --git a/mm/rmap.c b/mm/rmap.c index 748f48727a162..7b9879ef442d9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -76,7 +76,7 @@ #include <linux/mm_inline.h> #include <linux/oom.h> -#include <asm/tlbflush.h> +#include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> @@ -2008,13 +2008,17 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { + + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. @@ -2022,6 +2026,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, goto walk_done; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) @@ -2398,17 +2403,20 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, * fail if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { - hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { + hugetlb_vma_unlock_write(vma); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. @@ -2417,6 +2425,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, break; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); -- 2.52.0

5 days, 14 hours

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror