- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10 0/3] bpf: unify array->elem_size usage in arraymap.c and add inner_array_lookup.c selftest
by Xiaomeng Zhang 26 Mar '25

26 Mar '25

Andrii Nakryiko (1): bpf: make uniform use of array->elem_size everywhere in arraymap.c Rhys Rustad-Elliott (2): bpf: Fix elem_size not being set for inner maps selftests/bpf: Add access_inner_map selftest kernel/bpf/arraymap.c | 14 +++--- kernel/bpf/map_in_map.c | 8 +++- .../bpf/prog_tests/inner_array_lookup.c | 31 +++++++++++++ .../selftests/bpf/progs/inner_array_lookup.c | 45 +++++++++++++++++++ 4 files changed, 90 insertions(+), 8 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c create mode 100644 tools/testing/selftests/bpf/progs/inner_array_lookup.c -- 2.34.1

2 4

[PATCH] arm64_mpam: Add prefetch option
by Zeng Heng 26 Mar '25

26 Mar '25

Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- arch/arm64/include/asm/mpam.h | 15 +++++ arch/arm64/include/asm/thread_info.h | 4 ++ fs/resctrl/internal.h | 1 + fs/resctrl/rdtgroup.c | 84 ++++++++++++++++++++++++++++ 4 files changed, 104 insertions(+) diff --git a/arch/arm64/include/asm/mpam.h b/arch/arm64/include/asm/mpam.h index 9abe1fe58c34..ac7b6250250c 100644 --- a/arch/arm64/include/asm/mpam.h +++ b/arch/arm64/include/asm/mpam.h @@ -143,16 +143,31 @@ static inline void resctrl_arch_set_rmid(struct task_struct *tsk, u32 rmid) #endif } +#define setbit(x, y) (x |= (1<<y)) +#define clrbit(x, y) (x &= ~(1<<y)) + static inline void mpam_thread_switch(struct task_struct *tsk) { u64 oldregval; int cpu = smp_processor_id(); u64 regval = mpam_get_regval(tsk); + u64 val, val1; if (!IS_ENABLED(CONFIG_ARM64_MPAM) || !static_branch_likely(&mpam_enabled)) return; + asm volatile("mrs %0, S3_1_c15_c6_4" : "=r" (val)); + val1 = val; + + if (task_thread_info(tsk)->prefetch_dis) + setbit(val1, 0); + else + clrbit(val1, 0); + + if (val1 != val) + asm volatile("msr S3_1_c15_c6_4, %0" : : "r"(val1)); + if (regval == READ_ONCE(mpam_resctrl_default_group)) regval = READ_ONCE(per_cpu(arm64_mpam_default, cpu)); diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 379d24059f5b..a996caebb08e 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -48,7 +48,11 @@ struct thread_info { #endif u32 cpu; +#ifdef CONFIG_ARM64_MPAM + KABI_USE(1, u32 prefetch_dis) +#else KABI_RESERVE(1) +#endif KABI_RESERVE(2) }; diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index fb620beba958..fbc76efa06d9 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -173,6 +173,7 @@ struct rdtgroup { struct mongroup mon; enum rdtgrp_mode mode; struct pseudo_lock_region *plr; + u32 prefetch_dis; }; /* List of all resource groups */ diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 9776b4e2834c..bdf75b75b695 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -822,6 +822,80 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } +#ifdef CONFIG_ARM64_MPAM +static void update_prefetch_tasks(struct rdtgroup *r, u32 prefetch_dis) +{ + struct task_struct *p, *t; + + rcu_read_lock(); + + for_each_process_thread(p, t) { + if (is_closid_match(t, r) || is_rmid_match(t, r)) { + WRITE_ONCE(task_thread_info(t)->prefetch_dis, prefetch_dis); + /* Update task_struct and will send IPI to target cpu */ + smp_mb(); + update_task_closid_rmid(t); + } + } + + rcu_read_unlock(); +} + +static ssize_t rdtgroup_prefetch_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + u32 prefetch_dis; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + rdt_last_cmd_clear(); + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("Pseudo-locking in progress\n"); + goto unlock; + } + + if (kstrtou32(buf, 0, &prefetch_dis)) { + rdt_last_cmd_printf("Task list parsing error prefetch %s\n", buf); + ret = -EINVAL; + goto unlock; + } + + if (rdtgrp->prefetch_dis != prefetch_dis) { + rdtgrp->prefetch_dis = prefetch_dis; + update_prefetch_tasks(rdtgrp, prefetch_dis); + } + +unlock: + rdtgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +static int rdtgroup_prefetch_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) + seq_printf(s, "%u\n", rdtgrp->prefetch_dis); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} +#endif + static int rdtgroup_closid_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { @@ -1891,6 +1965,16 @@ static struct rftype res_common_files[] = { .seq_show = rdtgroup_tasks_show, .fflags = RFTYPE_BASE, }, +#ifdef CONFIG_ARM64_MPAM + { + .name = "prefetch_dis", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_prefetch_write, + .seq_show = rdtgroup_prefetch_show, + .fflags = RFTYPE_BASE, + }, +#endif { .name = "mon_hw_id", .mode = 0444, -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] media: uvcvideo: Remove dangling pointers
by Zhao Yipeng 26 Mar '25

26 Mar '25

From: Ricardo Ribalda <ribalda(a)chromium.org> mainline inclusion from mainline-v6.14-rc1 commit 221cd51efe4565501a3dbf04cc011b537dcce7fb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBPC8W CVE: CVE-2024-58002 Reference: https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/comm… -------------------------------- When an async control is written, we copy a pointer to the file handle that started the operation. That pointer will be used when the device is done. Which could be anytime in the future. If the user closes that file descriptor, its structure will be freed, and there will be one dangling pointer per pending async control, that the driver will try to use. Clean all the dangling pointers during release(). To avoid adding a performance penalty in the most common case (no async operation), a counter has been introduced with some logic to make sure that it is properly handled. Cc: stable(a)vger.kernel.org Fixes: e5225c820c05 ("media: uvcvideo: Send a control event when a Control Change interrupt arrives") Reviewed-by: Hans de Goede <hdegoede(a)redhat.com> Signed-off-by: Ricardo Ribalda <ribalda(a)chromium.org> Reviewed-by: Laurent Pinchart <laurent.pinchart(a)ideasonboard.com> Link: https://lore.kernel.org/r/20241203-uvc-fix-async-v6-3-26c867231118@chromium… Signed-off-by: Laurent Pinchart <laurent.pinchart(a)ideasonboard.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei(a)kernel.org> Conflicts: drivers/media/usb/uvc/uvc_ctrl.c drivers/media/usb/uvc/uvc_v4l2.c drivers/media/usb/uvc/uvcvideo.h [The guard() function is not introduced. 'for' loop initial declaration are only allowed in C99 or C11 mode. And other conflicts are contextual due to the commits d9fecd096f67, 9e56380ae625 and d9c8763e6129 not being merged.] Signed-off-by: Zhao Yipeng <zhaoyipeng5(a)huawei.com> --- drivers/media/usb/uvc/uvc_ctrl.c | 64 +++++++++++++++++++++++++++++++- drivers/media/usb/uvc/uvc_v4l2.c | 2 + drivers/media/usb/uvc/uvcvideo.h | 9 ++++- 3 files changed, 72 insertions(+), 3 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index f2854337cdca..fc02bbcd6245 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -1276,6 +1276,40 @@ static void uvc_ctrl_send_slave_event(struct uvc_video_chain *chain, uvc_ctrl_send_event(chain, handle, ctrl, mapping, val, changes); } +static void uvc_ctrl_set_handle(struct uvc_fh *handle, struct uvc_control *ctrl, + struct uvc_fh *new_handle) +{ + lockdep_assert_held(&handle->chain->ctrl_mutex); + + if (new_handle) { + if (ctrl->handle) + dev_warn_ratelimited(&handle->stream->dev->udev->dev, + "UVC non compliance: Setting an async control with a pending operation."); + + if (new_handle == ctrl->handle) + return; + + if (ctrl->handle) { + WARN_ON(!ctrl->handle->pending_async_ctrls); + if (ctrl->handle->pending_async_ctrls) + ctrl->handle->pending_async_ctrls--; + } + + ctrl->handle = new_handle; + handle->pending_async_ctrls++; + return; + } + + /* Cannot clear the handle for a control not owned by us.*/ + if (WARN_ON(ctrl->handle != handle)) + return; + + ctrl->handle = NULL; + if (WARN_ON(!handle->pending_async_ctrls)) + return; + handle->pending_async_ctrls--; +} + static void uvc_ctrl_status_event_work(struct work_struct *work) { struct uvc_device *dev = container_of(work, struct uvc_device, @@ -1291,7 +1325,8 @@ static void uvc_ctrl_status_event_work(struct work_struct *work) mutex_lock(&chain->ctrl_mutex); handle = ctrl->handle; - ctrl->handle = NULL; + if (handle) + uvc_ctrl_set_handle(handle, ctrl, NULL); list_for_each_entry(mapping, &ctrl->info.mappings, list) { s32 value = __uvc_ctrl_get_value(mapping, w->data); @@ -1684,7 +1719,7 @@ int uvc_ctrl_set(struct uvc_fh *handle, uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT)); if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS) - ctrl->handle = handle; + uvc_ctrl_set_handle(handle, ctrl, handle); ctrl->dirty = 1; ctrl->modified = 1; @@ -2330,6 +2365,31 @@ int uvc_ctrl_init_device(struct uvc_device *dev) return 0; } +void uvc_ctrl_cleanup_fh(struct uvc_fh *handle) +{ + struct uvc_entity *entity; + + mutex_lock(&handle->chain->ctrl_mutex); + + if (!handle->pending_async_ctrls) { + mutex_unlock(&handle->chain->ctrl_mutex); + return; + } + + list_for_each_entry(entity, &handle->chain->dev->entities, list) { + unsigned int i; + + for (i = 0; i < entity->ncontrols; ++i) { + if (entity->controls[i].handle != handle) + continue; + uvc_ctrl_set_handle(handle, &entity->controls[i], NULL); + } + } + + WARN_ON(handle->pending_async_ctrls); + mutex_unlock(&handle->chain->ctrl_mutex); +} + /* * Cleanup device controls. */ diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c index 18a7384b50ee..34b9843cec3a 100644 --- a/drivers/media/usb/uvc/uvc_v4l2.c +++ b/drivers/media/usb/uvc/uvc_v4l2.c @@ -563,6 +563,8 @@ static int uvc_v4l2_release(struct file *file) uvc_trace(UVC_TRACE_CALLS, "uvc_v4l2_release\n"); + uvc_ctrl_cleanup_fh(handle); + /* Only free resources if this is a privileged handle. */ if (uvc_has_privileges(handle)) uvc_queue_release(&stream->queue); diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index a738486fd9d6..243caeb4a6d7 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -434,7 +434,11 @@ struct uvc_video_chain { struct uvc_entity *processing; /* Processing unit */ struct uvc_entity *selector; /* Selector unit */ - struct mutex ctrl_mutex; /* Protects ctrl.info */ + struct mutex ctrl_mutex; /* + * Protects ctrl.info, + * ctrl.handle and + * uvc_fh.pending_async_ctrls + */ struct v4l2_prio_state prio; /* V4L2 priority state */ u32 caps; /* V4L2 chain-wide caps */ @@ -626,6 +630,7 @@ struct uvc_fh { struct uvc_video_chain *chain; struct uvc_streaming *stream; enum uvc_handle_state state; + unsigned int pending_async_ctrls; }; struct uvc_driver { @@ -792,6 +797,8 @@ int uvc_ctrl_set(struct uvc_fh *handle, struct v4l2_ext_control *xctrl); int uvc_xu_ctrl_query(struct uvc_video_chain *chain, struct uvc_xu_control_query *xqry); +void uvc_ctrl_cleanup_fh(struct uvc_fh *handle); + /* Utility functions */ void uvc_simplify_fraction(u32 *numerator, u32 *denominator, unsigned int n_terms, unsigned int threshold); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] nilfs2: do not force clear folio if buffer is referenced
by Liu Chuang 26 Mar '25

26 Mar '25

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> mainline inclusion from mainline-v6.14-rc1 commit ca76bb226bf47ff04c782cacbd299f12ddee1ec1 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBPBK0 CVE: CVE-2025-21722 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------- Patch series "nilfs2: protect busy buffer heads from being force-cleared". This series fixes the buffer head state inconsistency issues reported by syzbot that occurs when the filesystem is corrupted and falls back to read-only, and the associated buffer head use-after-free issue. This patch (of 2): Syzbot has reported that after nilfs2 detects filesystem corruption and falls back to read-only, inconsistencies in the buffer state may occur. One of the inconsistencies is that when nilfs2 calls mark_buffer_dirty() to set a data or metadata buffer as dirty, but it detects that the buffer is not in the uptodate state: WARNING: CPU: 0 PID: 6049 at fs/buffer.c:1177 mark_buffer_dirty+0x2e5/0x520 fs/buffer.c:1177 ... Call Trace: <TASK> nilfs_palloc_commit_alloc_entry+0x4b/0x160 fs/nilfs2/alloc.c:598 nilfs_ifile_create_inode+0x1dd/0x3a0 fs/nilfs2/ifile.c:73 nilfs_new_inode+0x254/0x830 fs/nilfs2/inode.c:344 nilfs_mkdir+0x10d/0x340 fs/nilfs2/namei.c:218 vfs_mkdir+0x2f9/0x4f0 fs/namei.c:4257 do_mkdirat+0x264/0x3a0 fs/namei.c:4280 __do_sys_mkdirat fs/namei.c:4295 [inline] __se_sys_mkdirat fs/namei.c:4293 [inline] __x64_sys_mkdirat+0x87/0xa0 fs/namei.c:4293 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f The other is when nilfs_btree_propagate(), which propagates the dirty state to the ancestor nodes of a b-tree that point to a dirty buffer, detects that the origin buffer is not dirty, even though it should be: WARNING: CPU: 0 PID: 5245 at fs/nilfs2/btree.c:2089 nilfs_btree_propagate+0xc79/0xdf0 fs/nilfs2/btree.c:2089 ... Call Trace: <TASK> nilfs_bmap_propagate+0x75/0x120 fs/nilfs2/bmap.c:345 nilfs_collect_file_data+0x4d/0xd0 fs/nilfs2/segment.c:587 nilfs_segctor_apply_buffers+0x184/0x340 fs/nilfs2/segment.c:1006 nilfs_segctor_scan_file+0x28c/0xa50 fs/nilfs2/segment.c:1045 nilfs_segctor_collect_blocks fs/nilfs2/segment.c:1216 [inline] nilfs_segctor_collect fs/nilfs2/segment.c:1540 [inline] nilfs_segctor_do_construct+0x1c28/0x6b90 fs/nilfs2/segment.c:2115 nilfs_segctor_construct+0x181/0x6b0 fs/nilfs2/segment.c:2479 nilfs_segctor_thread_construct fs/nilfs2/segment.c:2587 [inline] nilfs_segctor_thread+0x69e/0xe80 fs/nilfs2/segment.c:2701 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Both of these issues are caused by the callbacks that handle the page/folio write requests, forcibly clear various states, including the working state of the buffers they hold, at unexpected times when they detect read-only fallback. Fix these issues by checking if the buffer is referenced before clearing the page/folio state, and skipping the clear if it is. Link: https://lkml.kernel.org/r/20250107200202.6432-1-konishi.ryusuke@gmail.com Link: https://lkml.kernel.org/r/20250107200202.6432-2-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+b2b14916b77acf8626d7(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b2b14916b77acf8626d7 Reported-by: syzbot+d98fd19acd08b36ff422(a)syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=d98fd19acd08b36ff422 Fixes: 8c26c4e2694a ("nilfs2: fix issue with flush kernel thread after remount in RO mode because of driver's internal error or metadata corruption") Tested-by: syzbot+b2b14916b77acf8626d7(a)syzkaller.appspotmail.com Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Conflicts: fs/nilfs2/page.c [Due to previous commits not merged.] Signed-off-by: Liu Chuang <liuchuang40(a)huawei.com> --- fs/nilfs2/page.c | 36 +++++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index cc3308d1c61d..78661186c360 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -383,6 +383,11 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) * nilfs_clear_dirty_page - discard dirty page * @page: dirty page that will be discarded * @silent: suppress [true] or print [false] warning messages + * + * nilfs_clear_dirty_page() clears working states including dirty state for + * the page and its buffers. If the page has buffers, clear only if it is + * confirmed that none of the buffer heads are busy (none have valid + * references and none are locked). */ void nilfs_clear_dirty_page(struct page *page, bool silent) { @@ -396,18 +401,35 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) "discard dirty page: offset=%lld, ino=%lu", page_offset(page), inode->i_ino); - ClearPageUptodate(page); - ClearPageMappedToDisk(page); - ClearPageChecked(page); - if (page_has_buffers(page)) { struct buffer_head *bh, *head; const unsigned long clear_bits = (BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) | BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected)); + bool busy, invalidated = false; - bh = head = page_buffers(page); + head = page_buffers(page); + +recheck_buffers: + busy = false; + bh = head; + do { + if (atomic_read(&bh->b_count) | buffer_locked(bh)) { + busy = true; + break; + } + } while (bh = bh->b_this_page, bh != head); + + if (busy) { + if (invalidated) + return; + invalidate_bh_lrus(); + invalidated = true; + goto recheck_buffers; + } + + bh = head; do { lock_buffer(bh); if (!silent) @@ -420,6 +442,10 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) } while (bh = bh->b_this_page, bh != head); } + ClearPageUptodate(page); + ClearPageMappedToDisk(page); + ClearPageChecked(page); + __nilfs_clear_page_dirty(page); } -- 2.34.1

2 1

[PATCH OLK-5.10] nilfs2: do not force clear folio if buffer is referenced
by Liu Chuang 26 Mar '25

26 Mar '25

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> mainline inclusion from mainline-v6.14-rc1 commit ca76bb226bf47ff04c782cacbd299f12ddee1ec1 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBPBK0 CVE: CVE-2025-21722 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------- Patch series "nilfs2: protect busy buffer heads from being force-cleared". This series fixes the buffer head state inconsistency issues reported by syzbot that occurs when the filesystem is corrupted and falls back to read-only, and the associated buffer head use-after-free issue. This patch (of 2): Syzbot has reported that after nilfs2 detects filesystem corruption and falls back to read-only, inconsistencies in the buffer state may occur. One of the inconsistencies is that when nilfs2 calls mark_buffer_dirty() to set a data or metadata buffer as dirty, but it detects that the buffer is not in the uptodate state: WARNING: CPU: 0 PID: 6049 at fs/buffer.c:1177 mark_buffer_dirty+0x2e5/0x520 fs/buffer.c:1177 ... Call Trace: <TASK> nilfs_palloc_commit_alloc_entry+0x4b/0x160 fs/nilfs2/alloc.c:598 nilfs_ifile_create_inode+0x1dd/0x3a0 fs/nilfs2/ifile.c:73 nilfs_new_inode+0x254/0x830 fs/nilfs2/inode.c:344 nilfs_mkdir+0x10d/0x340 fs/nilfs2/namei.c:218 vfs_mkdir+0x2f9/0x4f0 fs/namei.c:4257 do_mkdirat+0x264/0x3a0 fs/namei.c:4280 __do_sys_mkdirat fs/namei.c:4295 [inline] __se_sys_mkdirat fs/namei.c:4293 [inline] __x64_sys_mkdirat+0x87/0xa0 fs/namei.c:4293 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f The other is when nilfs_btree_propagate(), which propagates the dirty state to the ancestor nodes of a b-tree that point to a dirty buffer, detects that the origin buffer is not dirty, even though it should be: WARNING: CPU: 0 PID: 5245 at fs/nilfs2/btree.c:2089 nilfs_btree_propagate+0xc79/0xdf0 fs/nilfs2/btree.c:2089 ... Call Trace: <TASK> nilfs_bmap_propagate+0x75/0x120 fs/nilfs2/bmap.c:345 nilfs_collect_file_data+0x4d/0xd0 fs/nilfs2/segment.c:587 nilfs_segctor_apply_buffers+0x184/0x340 fs/nilfs2/segment.c:1006 nilfs_segctor_scan_file+0x28c/0xa50 fs/nilfs2/segment.c:1045 nilfs_segctor_collect_blocks fs/nilfs2/segment.c:1216 [inline] nilfs_segctor_collect fs/nilfs2/segment.c:1540 [inline] nilfs_segctor_do_construct+0x1c28/0x6b90 fs/nilfs2/segment.c:2115 nilfs_segctor_construct+0x181/0x6b0 fs/nilfs2/segment.c:2479 nilfs_segctor_thread_construct fs/nilfs2/segment.c:2587 [inline] nilfs_segctor_thread+0x69e/0xe80 fs/nilfs2/segment.c:2701 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Both of these issues are caused by the callbacks that handle the page/folio write requests, forcibly clear various states, including the working state of the buffers they hold, at unexpected times when they detect read-only fallback. Fix these issues by checking if the buffer is referenced before clearing the page/folio state, and skipping the clear if it is. Link: https://lkml.kernel.org/r/20250107200202.6432-1-konishi.ryusuke@gmail.com Link: https://lkml.kernel.org/r/20250107200202.6432-2-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+b2b14916b77acf8626d7(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b2b14916b77acf8626d7 Reported-by: syzbot+d98fd19acd08b36ff422(a)syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=d98fd19acd08b36ff422 Fixes: 8c26c4e2694a ("nilfs2: fix issue with flush kernel thread after remount in RO mode because of driver's internal error or metadata corruption") Tested-by: syzbot+b2b14916b77acf8626d7(a)syzkaller.appspotmail.com Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Conflicts: fs/nilfs2/page.c [Conflicts due to previous commits not merged.] Signed-off-by: Liu Chuang <liuchuang40(a)huawei.com> --- fs/nilfs2/page.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index d2d6d5c761e8..3b97d2f51ec9 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -390,6 +390,11 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) * nilfs_clear_dirty_page - discard dirty page * @page: dirty page that will be discarded * @silent: suppress [true] or print [false] warning messages + * + * nilfs_clear_dirty_page() clears working states including dirty state for + * the page and its buffers. If the page has buffers, clear only if it is + * confirmed that none of the buffer heads are busy (none have valid + * references and none are locked). */ void nilfs_clear_dirty_page(struct page *page, bool silent) { @@ -402,10 +407,6 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) nilfs_warn(sb, "discard dirty page: offset=%lld, ino=%lu", page_offset(page), inode->i_ino); - ClearPageUptodate(page); - ClearPageMappedToDisk(page); - ClearPageChecked(page); - if (page_has_buffers(page)) { struct buffer_head *bh, *head; const unsigned long clear_bits = @@ -413,8 +414,28 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) | BIT(BH_Delay)); + bool busy, invalidated = false; - bh = head = page_buffers(page); + head = page_buffers(page); +recheck_buffers: + busy = false; + bh = head; + do { + if (atomic_read(&bh->b_count) | buffer_locked(bh)) { + busy = true; + break; + } + } while (bh = bh->b_this_page, bh != head); + + if (busy) { + if (invalidated) + return; + invalidate_bh_lrus(); + invalidated = true; + goto recheck_buffers; + } + + bh = head; do { lock_buffer(bh); if (!silent) @@ -427,6 +448,9 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) } while (bh = bh->b_this_page, bh != head); } + ClearPageUptodate(page); + ClearPageMappedToDisk(page); + ClearPageChecked(page); __nilfs_clear_page_dirty(page); } -- 2.34.1

2 1

[PATCH OLK-6.6] nilfs2: do not force clear folio if buffer is referenced
by Liu Chuang 26 Mar '25

26 Mar '25

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> mainline inclusion from mainline-v6.14-rc1 commit ca76bb226bf47ff04c782cacbd299f12ddee1ec1 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBPBK0 CVE: CVE-2025-21722 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------- Patch series "nilfs2: protect busy buffer heads from being force-cleared". This series fixes the buffer head state inconsistency issues reported by syzbot that occurs when the filesystem is corrupted and falls back to read-only, and the associated buffer head use-after-free issue. This patch (of 2): Syzbot has reported that after nilfs2 detects filesystem corruption and falls back to read-only, inconsistencies in the buffer state may occur. One of the inconsistencies is that when nilfs2 calls mark_buffer_dirty() to set a data or metadata buffer as dirty, but it detects that the buffer is not in the uptodate state: WARNING: CPU: 0 PID: 6049 at fs/buffer.c:1177 mark_buffer_dirty+0x2e5/0x520 fs/buffer.c:1177 ... Call Trace: <TASK> nilfs_palloc_commit_alloc_entry+0x4b/0x160 fs/nilfs2/alloc.c:598 nilfs_ifile_create_inode+0x1dd/0x3a0 fs/nilfs2/ifile.c:73 nilfs_new_inode+0x254/0x830 fs/nilfs2/inode.c:344 nilfs_mkdir+0x10d/0x340 fs/nilfs2/namei.c:218 vfs_mkdir+0x2f9/0x4f0 fs/namei.c:4257 do_mkdirat+0x264/0x3a0 fs/namei.c:4280 __do_sys_mkdirat fs/namei.c:4295 [inline] __se_sys_mkdirat fs/namei.c:4293 [inline] __x64_sys_mkdirat+0x87/0xa0 fs/namei.c:4293 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f The other is when nilfs_btree_propagate(), which propagates the dirty state to the ancestor nodes of a b-tree that point to a dirty buffer, detects that the origin buffer is not dirty, even though it should be: WARNING: CPU: 0 PID: 5245 at fs/nilfs2/btree.c:2089 nilfs_btree_propagate+0xc79/0xdf0 fs/nilfs2/btree.c:2089 ... Call Trace: <TASK> nilfs_bmap_propagate+0x75/0x120 fs/nilfs2/bmap.c:345 nilfs_collect_file_data+0x4d/0xd0 fs/nilfs2/segment.c:587 nilfs_segctor_apply_buffers+0x184/0x340 fs/nilfs2/segment.c:1006 nilfs_segctor_scan_file+0x28c/0xa50 fs/nilfs2/segment.c:1045 nilfs_segctor_collect_blocks fs/nilfs2/segment.c:1216 [inline] nilfs_segctor_collect fs/nilfs2/segment.c:1540 [inline] nilfs_segctor_do_construct+0x1c28/0x6b90 fs/nilfs2/segment.c:2115 nilfs_segctor_construct+0x181/0x6b0 fs/nilfs2/segment.c:2479 nilfs_segctor_thread_construct fs/nilfs2/segment.c:2587 [inline] nilfs_segctor_thread+0x69e/0xe80 fs/nilfs2/segment.c:2701 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Both of these issues are caused by the callbacks that handle the page/folio write requests, forcibly clear various states, including the working state of the buffers they hold, at unexpected times when they detect read-only fallback. Fix these issues by checking if the buffer is referenced before clearing the page/folio state, and skipping the clear if it is. Link: https://lkml.kernel.org/r/20250107200202.6432-1-konishi.ryusuke@gmail.com Link: https://lkml.kernel.org/r/20250107200202.6432-2-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+b2b14916b77acf8626d7(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b2b14916b77acf8626d7 Reported-by: syzbot+d98fd19acd08b36ff422(a)syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=d98fd19acd08b36ff422 Fixes: 8c26c4e2694a ("nilfs2: fix issue with flush kernel thread after remount in RO mode because of driver's internal error or metadata corruption") Tested-by: syzbot+b2b14916b77acf8626d7(a)syzkaller.appspotmail.com Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Conflicts: fs/nilfs2/page.c [Conflicts due to previous commits not merged.] Signed-off-by: Liu Chuang <liuchuang40(a)huawei.com> --- fs/nilfs2/page.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index d2d6d5c761e8..3b97d2f51ec9 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -390,6 +390,11 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) * nilfs_clear_dirty_page - discard dirty page * @page: dirty page that will be discarded * @silent: suppress [true] or print [false] warning messages + * + * nilfs_clear_dirty_page() clears working states including dirty state for + * the page and its buffers. If the page has buffers, clear only if it is + * confirmed that none of the buffer heads are busy (none have valid + * references and none are locked). */ void nilfs_clear_dirty_page(struct page *page, bool silent) { @@ -402,10 +407,6 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) nilfs_warn(sb, "discard dirty page: offset=%lld, ino=%lu", page_offset(page), inode->i_ino); - ClearPageUptodate(page); - ClearPageMappedToDisk(page); - ClearPageChecked(page); - if (page_has_buffers(page)) { struct buffer_head *bh, *head; const unsigned long clear_bits = @@ -413,8 +414,28 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) | BIT(BH_Delay)); + bool busy, invalidated = false; - bh = head = page_buffers(page); + head = page_buffers(page); +recheck_buffers: + busy = false; + bh = head; + do { + if (atomic_read(&bh->b_count) | buffer_locked(bh)) { + busy = true; + break; + } + } while (bh = bh->b_this_page, bh != head); + + if (busy) { + if (invalidated) + return; + invalidate_bh_lrus(); + invalidated = true; + goto recheck_buffers; + } + + bh = head; do { lock_buffer(bh); if (!silent) @@ -427,6 +448,9 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) } while (bh = bh->b_this_page, bh != head); } + ClearPageUptodate(page); + ClearPageMappedToDisk(page); + ClearPageChecked(page); __nilfs_clear_page_dirty(page); } -- 2.34.1

2 1

[PATCH OLK-6.6] ata: libata-sff: Ensure that we cannot write outside the allocated buffer
by Zheng Qixing 26 Mar '25

26 Mar '25

From: Niklas Cassel <cassel(a)kernel.org> stable inclusion from stable-v6.6.78 commit d5e6e3000309359eae2a17117aa6e3c44897bf6c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBPC5G CVE: CVE-2025-21738 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------ commit 6e74e53b34b6dec5a50e1404e2680852ec6768d2 upstream. reveliofuzzing reported that a SCSI_IOCTL_SEND_COMMAND ioctl with out_len set to 0xd42, SCSI command set to ATA_16 PASS-THROUGH, ATA command set to ATA_NOP, and protocol set to ATA_PROT_PIO, can cause ata_pio_sector() to write outside the allocated buffer, overwriting random memory. While a ATA device is supposed to abort a ATA_NOP command, there does seem to be a bug either in libata-sff or QEMU, where either this status is not set, or the status is cleared before read by ata_sff_hsm_move(). Anyway, that is most likely a separate bug. Looking at __atapi_pio_bytes(), it already has a safety check to ensure that __atapi_pio_bytes() cannot write outside the allocated buffer. Add a similar check to ata_pio_sector(), such that also ata_pio_sector() cannot write outside the allocated buffer. Cc: stable(a)vger.kernel.org Reported-by: reveliofuzzing <reveliofuzzing(a)gmail.com> Closes: https://lore.kernel.org/linux-ide/CA+-ZZ_jTgxh3bS7m+KX07_EWckSnW3N2adX3KV63… Link: https://lore.kernel.org/r/20250127154303.15567-2-cassel@kernel.org Signed-off-by: Niklas Cassel <cassel(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/ata/libata-sff.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 8fcc622fcb3d..9b6529f2dfcb 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -602,7 +602,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct page *page; - unsigned int offset; + unsigned int offset, count; if (!qc->cursg) { qc->curbytes = qc->nbytes; @@ -618,25 +618,27 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) page = nth_page(page, (offset >> PAGE_SHIFT)); offset %= PAGE_SIZE; - trace_ata_sff_pio_transfer_data(qc, offset, qc->sect_size); + /* don't overrun current sg */ + count = min(qc->cursg->length - qc->cursg_ofs, qc->sect_size); + + trace_ata_sff_pio_transfer_data(qc, offset, count); /* * Split the transfer when it splits a page boundary. Note that the * split still has to be dword aligned like all ATA data transfers. */ WARN_ON_ONCE(offset % 4); - if (offset + qc->sect_size > PAGE_SIZE) { + if (offset + count > PAGE_SIZE) { unsigned int split_len = PAGE_SIZE - offset; ata_pio_xfer(qc, page, offset, split_len); - ata_pio_xfer(qc, nth_page(page, 1), 0, - qc->sect_size - split_len); + ata_pio_xfer(qc, nth_page(page, 1), 0, count - split_len); } else { - ata_pio_xfer(qc, page, offset, qc->sect_size); + ata_pio_xfer(qc, page, offset, count); } - qc->curbytes += qc->sect_size; - qc->cursg_ofs += qc->sect_size; + qc->curbytes += count; + qc->cursg_ofs += count; if (qc->cursg_ofs == qc->cursg->length) { qc->cursg = sg_next(qc->cursg); -- 2.39.2

2 1

[PATCH OLK-5.10 0/3] Sidecarless
by Xiaomeng Zhang 26 Mar '25

26 Mar '25

Andrii Nakryiko (1): bpf: make uniform use of array->elem_size everywhere in arraymap.c Rhys Rustad-Elliott (2): bpf: Fix elem_size not being set for inner maps selftests/bpf: Add access_inner_map selftest kernel/bpf/arraymap.c | 14 +++--- kernel/bpf/map_in_map.c | 8 +++- .../bpf/prog_tests/inner_array_lookup.c | 31 +++++++++++++ .../selftests/bpf/progs/inner_array_lookup.c | 45 +++++++++++++++++++ 4 files changed, 90 insertions(+), 8 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c create mode 100644 tools/testing/selftests/bpf/progs/inner_array_lookup.c -- 2.34.1

2 4

[PATCH OLK-6.6] block: don't revert iter for -EIOCBQUEUED
by Zheng Qixing 26 Mar '25

26 Mar '25

From: Jens Axboe <axboe(a)kernel.dk> stable inclusion from stable-v6.6.78 commit 84671b0630ccb46ae9f1f99a45c7d63ffcd6a474 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBRECT CVE: CVE-2025-21832 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------ commit b13ee668e8280ca5b07f8ce2846b9957a8a10853 upstream. blkdev_read_iter() has a few odd checks, like gating the position and count adjustment on whether or not the result is bigger-than-or-equal to zero (where bigger than makes more sense), and not checking the return value of blkdev_direct_IO() before doing an iov_iter_revert(). The latter can lead to attempting to revert with a negative value, which when passed to iov_iter_revert() as an unsigned value will lead to throwing a WARN_ON() because unroll is bigger than MAX_RW_COUNT. Be sane and don't revert for -EIOCBQUEUED, like what is done in other spots. Cc: stable(a)vger.kernel.org Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- block/fops.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/block/fops.c b/block/fops.c index 33b724b1d963..cda9978ebf67 100644 --- a/block/fops.c +++ b/block/fops.c @@ -730,11 +730,12 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) file_accessed(iocb->ki_filp); ret = blkdev_direct_IO(iocb, to); - if (ret >= 0) { + if (ret > 0) { iocb->ki_pos += ret; count -= ret; } - iov_iter_revert(to, count - iov_iter_count(to)); + if (ret != -EIOCBQUEUED) + iov_iter_revert(to, count - iov_iter_count(to)); if (ret < 0 || !count) goto reexpand; } -- 2.39.2

2 1

[PATCH OLK-5.10 0/3] Sidecarless
by Xiaomeng Zhang 26 Mar '25

26 Mar '25

Andrii Nakryiko (1): bpf: make uniform use of array->elem_size everywhere in arraymap.c Rhys Rustad-Elliott (2): bpf: Fix elem_size not being set for inner maps selftests/bpf: Add access_inner_map selftest kernel/bpf/arraymap.c | 14 +++--- kernel/bpf/map_in_map.c | 8 +++- .../bpf/prog_tests/inner_array_lookup.c | 31 +++++++++++++ .../selftests/bpf/progs/inner_array_lookup.c | 45 +++++++++++++++++++ 4 files changed, 90 insertions(+), 8 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c create mode 100644 tools/testing/selftests/bpf/progs/inner_array_lookup.c -- 2.34.1

2 4