- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] mm: proc: use per_vma mmap_lock for vma traversal.
by Qi Xi 19 Nov '25

19 Nov '25

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ID6KMQ -------------------------------- The current method of reading /proc/pid/numa_maps uses a global mmap_lock, which can block high-priority writers and therefore lead to low performance. The mmap_lock is held during vma traversal, acquired in m_start() and released in m_stop(). Now introduces a more fine-grained mmap_lock that next() releases and reacquires the lock between vma iterations. The fine-grained lock avoids priority inversion and improves concurrency. However, the output is non-atomic for the entire address space. Signed-off-by: Qi Xi <xiqi2(a)huawei.com> --- fs/proc/task_mmu.c | 113 +++++++++++++++++++++++++++++++++++++-- include/linux/pagewalk.h | 2 + mm/pagewalk.c | 27 ++++++++++ 3 files changed, 138 insertions(+), 4 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 7b41f7c290ce..4370eb895e76 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -182,6 +182,102 @@ static void *m_next(struct seq_file *m, void *v, loff_t *ppos) return next; } +static void *numa_maps_next(struct seq_file *m, void *v, loff_t *ppos) +{ + struct proc_maps_private *priv = m->private; + struct vm_area_struct *next = NULL; + struct vm_area_struct *vma = v; + struct mm_struct *mm = priv->mm; + unsigned long last_vma_end; + unsigned long last_vma_start; + int ret; + + if (!mm) + goto out; + + if (vma == priv->tail_vma) + goto out; + + if (vma->vm_next) + next = vma->vm_next; + else + next = priv->tail_vma; + + last_vma_end = vma->vm_end; + last_vma_start = vma->vm_start; + if (mmap_lock_is_contended(mm)) { + mmap_read_unlock(mm); + ret = mmap_read_lock_killable(mm); + if (ret) { + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; + return ERR_PTR(ret); + } + + /* + * After dropping the lock, there are four cases to + * consider. See the following example for explanation. + * + * +------+------+-----------+ + * | VMA1 | VMA2 | VMA3 | + * +------+------+-----------+ + * | | | | + * 4k 8k 16k 400k + * + * Suppose we drop the lock after reading VMA2 due to + * contention, then we get: + * + * last_vma_end = 16k + * + * 1) VMA2 is freed, but VMA3 exists: + * + * find_vma(mm, 16k - 1) will return VMA3. + * In this case, just continue from VMA3. + * + * 2) VMA2 still exists: + * + * find_vma(mm, 16k - 1) will return VMA2. + * Iterate the loop like the original one. + * + * 3) No more VMAs can be found: + * + * find_vma(mm, 16k - 1) will return NULL. + * No more things to do, just break. + * + * 4) (last_vma_end - 1) is the middle of a vma (VMA'): + * + * find_vma(mm, 16k - 1) will return VMA' whose range + * contains last_vma_end. + * Iterate VMA' from last_vma_end. + */ + next = find_vma(mm, last_vma_end - 1); + + /* Case 3 above */ + if (!next) + goto out; + + /* Case 1 above */ + if (next->vm_start >= last_vma_end) + goto out; + + /* Case 4 above */ + if (next->vm_end > last_vma_end) { + *ppos = last_vma_end; + return next; + } + + /* Case 2 above */ + if (next->vm_next) + next = next->vm_next; + else + next = priv->tail_vma; + } +out: + *ppos = next ? next->vm_start : -1UL; + return next; +} + static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; @@ -2260,6 +2356,7 @@ static int show_numa_map(struct seq_file *m, void *v) struct mempolicy *pol; char buffer[64]; int nid; + unsigned long start_addr; if (!mm) return 0; @@ -2267,7 +2364,15 @@ static int show_numa_map(struct seq_file *m, void *v) /* Ensure we start with an empty set of numa_maps statistics. */ memset(md, 0, sizeof(*md)); - pol = __get_vma_policy(vma, vma->vm_start); + start_addr = max_t(unsigned long, vma->vm_start, m->index); + if (start_addr >= vma->vm_end) { + VM_WARN_ONCE(1, + "invalid range: start_addr=%p vma=[%p-%p]\n", + (void *)start_addr, (void *)vma->vm_start, (void *)vma->vm_end); + return 0; + } + + pol = __get_vma_policy(vma, start_addr); if (pol) { mpol_to_str(buffer, sizeof(buffer), pol); mpol_cond_put(pol); @@ -2275,7 +2380,7 @@ static int show_numa_map(struct seq_file *m, void *v) mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy); } - seq_printf(m, "%08lx %s", vma->vm_start, buffer); + seq_printf(m, "%08lx %s", start_addr, buffer); if (file) { seq_puts(m, " file="); @@ -2290,7 +2395,7 @@ static int show_numa_map(struct seq_file *m, void *v) seq_puts(m, " huge"); /* mmap_lock is held by m_start */ - walk_page_vma(vma, &show_numa_ops, md); + walk_page_vma_range(vma, start_addr, &show_numa_ops, md); if (!md->pages) goto out; @@ -2328,7 +2433,7 @@ static int show_numa_map(struct seq_file *m, void *v) static const struct seq_operations proc_pid_numa_maps_op = { .start = m_start, - .next = m_next, + .next = numa_maps_next, .stop = m_stop, .show = show_numa_map, }; diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index b1cb6b753abb..9b8e2586cfc2 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -101,6 +101,8 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, void *private); int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private); +int walk_page_vma_range(struct vm_area_struct *vma, unsigned long start_addr, + const struct mm_walk_ops *ops, void *private); int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, const struct mm_walk_ops *ops, void *private); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 6a4212cf00ba..12032258d1ec 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -485,6 +485,33 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, return __walk_page_range(vma->vm_start, vma->vm_end, &walk); } +int walk_page_vma_range(struct vm_area_struct *vma, unsigned long start_addr, + const struct mm_walk_ops *ops, void *private) +{ + struct mm_walk walk = { + .ops = ops, + .mm = vma->vm_mm, + .vma = vma, + .private = private, + }; + int err; + + if (!walk.mm) + return -EINVAL; + + if (start_addr < vma->vm_start || start_addr >= vma->vm_end) + return -EINVAL; + + mmap_assert_locked(walk.mm); + + err = walk_page_test(start_addr, vma->vm_end, &walk); + if (err > 0) + return 0; + if (err < 0) + return err; + return __walk_page_range(start_addr, vma->vm_end, &walk); +} + /** * walk_page_mapping - walk all memory areas mapped into a struct address_space. * @mapping: Pointer to the struct address_space -- 2.33.0

2 1

[PATCH OLK-5.10] mm: proc: use per_vma mmap_lock for vma traversal.
by Qi Xi 19 Nov '25

19 Nov '25

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ID6KMQ -------------------------------- The current method of reading /proc/pid/numa_maps uses a global mmap_lock, which can block high-priority writers and therefore lead to low performance. The mmap_lock is held during vma traversal, acquired in m_start() and released in m_stop(). Now introduces a more fine-grained mmap_lock that next() releases and reacquires the lock between vma iterations. The fine-grained lock avoids priority inversion and improves concurrency. However, the output is non-atomic for the entire address space. Signed-off-by: Qi Xi <xiqi2(a)huawei.com> --- fs/proc/task_mmu.c | 113 +++++++++++++++++++++++++++++++++++++-- include/linux/pagewalk.h | 2 + mm/pagewalk.c | 27 ++++++++++ 3 files changed, 138 insertions(+), 4 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 7b41f7c290ce..4370eb895e76 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -182,6 +182,102 @@ static void *m_next(struct seq_file *m, void *v, loff_t *ppos) return next; } +static void *numa_maps_next(struct seq_file *m, void *v, loff_t *ppos) +{ + struct proc_maps_private *priv = m->private; + struct vm_area_struct *next = NULL; + struct vm_area_struct *vma = v; + struct mm_struct *mm = priv->mm; + unsigned long last_vma_end; + unsigned long last_vma_start; + int ret; + + if (!mm) + goto out; + + if (vma == priv->tail_vma) + goto out; + + if (vma->vm_next) + next = vma->vm_next; + else + next = priv->tail_vma; + + last_vma_end = vma->vm_end; + last_vma_start = vma->vm_start; + if (mmap_lock_is_contended(mm)) { + mmap_read_unlock(mm); + ret = mmap_read_lock_killable(mm); + if (ret) { + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; + return ERR_PTR(ret); + } + + /* + * After dropping the lock, there are four cases to + * consider. See the following example for explanation. + * + * +------+------+-----------+ + * | VMA1 | VMA2 | VMA3 | + * +------+------+-----------+ + * | | | | + * 4k 8k 16k 400k + * + * Suppose we drop the lock after reading VMA2 due to + * contention, then we get: + * + * last_vma_end = 16k + * + * 1) VMA2 is freed, but VMA3 exists: + * + * find_vma(mm, 16k - 1) will return VMA3. + * In this case, just continue from VMA3. + * + * 2) VMA2 still exists: + * + * find_vma(mm, 16k - 1) will return VMA2. + * Iterate the loop like the original one. + * + * 3) No more VMAs can be found: + * + * find_vma(mm, 16k - 1) will return NULL. + * No more things to do, just break. + * + * 4) (last_vma_end - 1) is the middle of a vma (VMA'): + * + * find_vma(mm, 16k - 1) will return VMA' whose range + * contains last_vma_end. + * Iterate VMA' from last_vma_end. + */ + next = find_vma(mm, last_vma_end - 1); + + /* Case 3 above */ + if (!next) + goto out; + + /* Case 1 above */ + if (next->vm_start >= last_vma_end) + goto out; + + /* Case 4 above */ + if (next->vm_end > last_vma_end) { + *ppos = last_vma_end; + return next; + } + + /* Case 2 above */ + if (next->vm_next) + next = next->vm_next; + else + next = priv->tail_vma; + } +out: + *ppos = next ? next->vm_start : -1UL; + return next; +} + static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; @@ -2260,6 +2356,7 @@ static int show_numa_map(struct seq_file *m, void *v) struct mempolicy *pol; char buffer[64]; int nid; + unsigned long start_addr; if (!mm) return 0; @@ -2267,7 +2364,15 @@ static int show_numa_map(struct seq_file *m, void *v) /* Ensure we start with an empty set of numa_maps statistics. */ memset(md, 0, sizeof(*md)); - pol = __get_vma_policy(vma, vma->vm_start); + start_addr = max_t(unsigned long, vma->vm_start, m->index); + if (start_addr >= vma->vm_end) { + VM_WARN_ONCE(1, + "invalid range: start_addr=%p vma=[%p-%p]\n", + (void *)start_addr, (void *)vma->vm_start, (void *)vma->vm_end); + return 0; + } + + pol = __get_vma_policy(vma, start_addr); if (pol) { mpol_to_str(buffer, sizeof(buffer), pol); mpol_cond_put(pol); @@ -2275,7 +2380,7 @@ static int show_numa_map(struct seq_file *m, void *v) mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy); } - seq_printf(m, "%08lx %s", vma->vm_start, buffer); + seq_printf(m, "%08lx %s", start_addr, buffer); if (file) { seq_puts(m, " file="); @@ -2290,7 +2395,7 @@ static int show_numa_map(struct seq_file *m, void *v) seq_puts(m, " huge"); /* mmap_lock is held by m_start */ - walk_page_vma(vma, &show_numa_ops, md); + walk_page_vma_range(vma, start_addr, &show_numa_ops, md); if (!md->pages) goto out; @@ -2328,7 +2433,7 @@ static int show_numa_map(struct seq_file *m, void *v) static const struct seq_operations proc_pid_numa_maps_op = { .start = m_start, - .next = m_next, + .next = numa_maps_next, .stop = m_stop, .show = show_numa_map, }; diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index b1cb6b753abb..9b8e2586cfc2 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -101,6 +101,8 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, void *private); int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private); +int walk_page_vma_range(struct vm_area_struct *vma, unsigned long start_addr, + const struct mm_walk_ops *ops, void *private); int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, const struct mm_walk_ops *ops, void *private); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 6a4212cf00ba..12032258d1ec 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -485,6 +485,33 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, return __walk_page_range(vma->vm_start, vma->vm_end, &walk); } +int walk_page_vma_range(struct vm_area_struct *vma, unsigned long start_addr, + const struct mm_walk_ops *ops, void *private) +{ + struct mm_walk walk = { + .ops = ops, + .mm = vma->vm_mm, + .vma = vma, + .private = private, + }; + int err; + + if (!walk.mm) + return -EINVAL; + + if (start_addr < vma->vm_start || start_addr >= vma->vm_end) + return -EINVAL; + + mmap_assert_locked(walk.mm); + + err = walk_page_test(start_addr, vma->vm_end, &walk); + if (err > 0) + return 0; + if (err < 0) + return err; + return __walk_page_range(start_addr, vma->vm_end, &walk); +} + /** * walk_page_mapping - walk all memory areas mapped into a struct address_space. * @mapping: Pointer to the struct address_space -- 2.33.0

2 1

[PATCH OLK-6.6 0/8] xsched: XCU Partition
by Zicheng Qu 19 Nov '25

19 Nov '25

Alekseev Dmitry (2): xsched: Add XCU control group implementation and its backend in xsched CFS xsched: Add support for CFS quota for cgroups Konstantin Meskhidze (6): xsched: Add base vstream support xcu: Add base NPU driver support xsched: Introduce vstream management xsched: Add basic scheduler core support xsched: Add xsched RT class xsched: Add xsched CFS class arch/arm/tools/syscall.tbl | 2 +- arch/arm64/configs/openeuler_defconfig | 2 + arch/powerpc/kernel/syscalls/syscall.tbl | 2 +- arch/x86/configs/openeuler_defconfig | 2 + arch/x86/entry/syscalls/syscall_32.tbl | 2 +- arch/x86/entry/syscalls/syscall_64.tbl | 2 +- drivers/Makefile | 1 + drivers/xcu/Makefile | 2 + drivers/xcu/xcu_group.c | 380 +++++++++ include/linux/cgroup_subsys.h | 4 + include/linux/syscalls.h | 2 + include/linux/vstream.h | 91 ++ include/linux/xcu_group.h | 96 +++ include/linux/xsched.h | 514 ++++++++++++ include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/xcu_vstream.h | 77 ++ init/Kconfig | 1 + kernel/Makefile | 1 + kernel/cgroup/cgroup.c | 2 +- kernel/xsched/Kconfig | 85 ++ kernel/xsched/Makefile | 9 + kernel/xsched/cfs.c | 237 ++++++ kernel/xsched/cfs_quota.c | 98 +++ kernel/xsched/cgroup.c | 775 ++++++++++++++++++ kernel/xsched/core.c | 526 ++++++++++++ kernel/xsched/rt.c | 281 +++++++ kernel/xsched/vstream.c | 674 +++++++++++++++ .../arch/powerpc/entry/syscalls/syscall.tbl | 2 +- .../arch/x86/entry/syscalls/syscall_64.tbl | 2 +- 29 files changed, 3868 insertions(+), 9 deletions(-) create mode 100644 drivers/xcu/Makefile create mode 100644 drivers/xcu/xcu_group.c create mode 100644 include/linux/vstream.h create mode 100644 include/linux/xcu_group.h create mode 100644 include/linux/xsched.h create mode 100644 include/uapi/linux/xcu_vstream.h create mode 100644 kernel/xsched/Kconfig create mode 100644 kernel/xsched/Makefile create mode 100644 kernel/xsched/cfs.c create mode 100644 kernel/xsched/cfs_quota.c create mode 100644 kernel/xsched/cgroup.c create mode 100644 kernel/xsched/core.c create mode 100644 kernel/xsched/rt.c create mode 100644 kernel/xsched/vstream.c -- 2.34.1

2 9

[PATCH OLK-6.6] blk-mq: check kobject state_in_sysfs before deleting in blk_mq_unregister_hctx
by Zheng Qixing 19 Nov '25

19 Nov '25

From: Li Nan <linan122(a)huawei.com> mainline inclusion from mainline-v6.18-rc1 commit 4c7ef92f6d4d08a27d676e4c348f4e2922cab3ed category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ID6B4D CVE: CVE-2025-40125 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------ In __blk_mq_update_nr_hw_queues() the return value of blk_mq_sysfs_register_hctxs() is not checked. If sysfs creation for hctx fails, later changing the number of hw_queues or removing disk will trigger the following warning: kernfs: can not remove 'nr_tags', no directory WARNING: CPU: 2 PID: 637 at fs/kernfs/dir.c:1707 kernfs_remove_by_name_ns+0x13f/0x160 Call Trace: remove_files.isra.1+0x38/0xb0 sysfs_remove_group+0x4d/0x100 sysfs_remove_groups+0x31/0x60 __kobject_del+0x23/0xf0 kobject_del+0x17/0x40 blk_mq_unregister_hctx+0x5d/0x80 blk_mq_sysfs_unregister_hctxs+0x94/0xd0 blk_mq_update_nr_hw_queues+0x124/0x760 nullb_update_nr_hw_queues+0x71/0xf0 [null_blk] nullb_device_submit_queues_store+0x92/0x120 [null_blk] kobjct_del() was called unconditionally even if sysfs creation failed. Fix it by checkig the kobject creation statusbefore deleting it. Fixes: 477e19dedc9d ("blk-mq: adjust debugfs and sysfs register when updating nr_hw_queues") Signed-off-by: Li Nan <linan122(a)huawei.com> Reviewed-by: Yu Kuai <yukuai3(a)huawei.com> Link: https://lore.kernel.org/r/20250826084854.1030545-1-linan666@huaweicloud.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- block/blk-mq-sysfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 156e9bb07abf..2fb234ab467b 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -150,9 +150,11 @@ static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx) return; hctx_for_each_ctx(hctx, ctx, i) - kobject_del(&ctx->kobj); + if (ctx->kobj.state_in_sysfs) + kobject_del(&ctx->kobj); - kobject_del(&hctx->kobj); + if (hctx->kobj.state_in_sysfs) + kobject_del(&hctx->kobj); } static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] scsi: ses: Fix possible addl_desc_ptr out-of-bounds accesses
by Zheng Qixing 19 Nov '25

19 Nov '25

From: Tomas Henzl <thenzl(a)redhat.com> stable inclusion from stable-v4.19.276 commit a156a262c543fa5ff30bcb2fc6ad1a95cb4ab57a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ID43SW CVE: CVE-2023-7324 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------ commit db95d4df71cb55506425b6e4a5f8d68e3a765b63 upstream. Sanitize possible addl_desc_ptr out-of-bounds accesses in ses_enclosure_data_process(). Link: https://lore.kernel.org/r/20230202162451.15346-3-thenzl@redhat.com Cc: stable(a)vger.kernel.org Signed-off-by: Tomas Henzl <thenzl(a)redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/scsi/ses.c [Context conflicts.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/scsi/ses.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 6ef1e12a2fce..b42c0bb8caa9 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -435,8 +435,8 @@ int ses_match_host(struct enclosure_device *edev, void *data) } #endif /* 0 */ -static void ses_process_descriptor(struct enclosure_component *ecomp, - unsigned char *desc) +static int ses_process_descriptor(struct enclosure_component *ecomp, + unsigned char *desc, int max_desc_len) { int eip = desc[0] & 0x10; int invalid = desc[0] & 0x80; @@ -447,22 +447,32 @@ static void ses_process_descriptor(struct enclosure_component *ecomp, unsigned char *d; if (invalid) - return; + return 0; switch (proto) { case SCSI_PROTOCOL_FCP: if (eip) { + if (max_desc_len <= 7) + return 1; d = desc + 4; slot = d[3]; } break; case SCSI_PROTOCOL_SAS: + if (eip) { + if (max_desc_len <= 27) + return 1; d = desc + 4; slot = d[3]; d = desc + 8; - } else + } else { + if (max_desc_len <= 23) + return 1; d = desc + 4; + } + + /* only take the phy0 addr */ addr = (u64)d[12] << 56 | (u64)d[13] << 48 | @@ -479,6 +489,8 @@ static void ses_process_descriptor(struct enclosure_component *ecomp, } ecomp->slot = slot; scomp->addr = addr; + + return 0; } struct efd { @@ -548,7 +560,7 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, /* skip past overall descriptor */ desc_ptr += len + 4; } - if (ses_dev->page10) + if (ses_dev->page10 && ses_dev->page10_len > 9) addl_desc_ptr = ses_dev->page10 + 8; type_ptr = ses_dev->page1_types; components = 0; @@ -556,6 +568,7 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, for (j = 0; j < type_ptr[1]; j++) { char *name = NULL; struct enclosure_component *ecomp; + int max_desc_len; if (desc_ptr) { if (desc_ptr + 3 >= buf + page7_len) { @@ -588,10 +601,14 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, ecomp = ERR_PTR(-EINVAL); if (!IS_ERR(ecomp)) { - if (addl_desc_ptr) - ses_process_descriptor( - ecomp, - addl_desc_ptr); + if (addl_desc_ptr) { + max_desc_len = ses_dev->page10_len - + (addl_desc_ptr - ses_dev->page10); + if (ses_process_descriptor(ecomp, + addl_desc_ptr, + max_desc_len)) + addl_desc_ptr = NULL; + } if (create) enclosure_component_register( ecomp); -- 2.39.2

2 1

[PATCH OLK-6.6 0/8] xsched: XCU Partition
by Zicheng Qu 19 Nov '25

19 Nov '25

Alekseev Dmitry (2): xsched: Add XCU control group implementation and its backend in xsched CFS xsched: Add support for CFS quota for cgroups Konstantin Meskhidze (6): xsched: Add base vstream support xcu: Add base NPU driver support xsched: Introduce vstream management xsched: Add basic scheduler core support xsched: Add xsched RT class xsched: Add xsched CFS class arch/arm/tools/syscall.tbl | 2 +- arch/arm64/configs/openeuler_defconfig | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 2 +- arch/x86/configs/openeuler_defconfig | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 2 +- arch/x86/entry/syscalls/syscall_64.tbl | 2 +- drivers/Makefile | 1 + drivers/xcu/Makefile | 2 + drivers/xcu/xcu_group.c | 380 +++++++++ include/linux/cgroup_subsys.h | 4 + include/linux/syscalls.h | 2 + include/linux/vstream.h | 91 ++ include/linux/xcu_group.h | 96 +++ include/linux/xsched.h | 514 ++++++++++++ include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/xcu_vstream.h | 77 ++ init/Kconfig | 1 + kernel/Makefile | 1 + kernel/cgroup/cgroup.c | 2 +- kernel/xsched/Kconfig | 85 ++ kernel/xsched/Makefile | 9 + kernel/xsched/cfs.c | 237 ++++++ kernel/xsched/cfs_quota.c | 98 +++ kernel/xsched/cgroup.c | 775 ++++++++++++++++++ kernel/xsched/core.c | 526 ++++++++++++ kernel/xsched/rt.c | 281 +++++++ kernel/xsched/vstream.c | 674 +++++++++++++++ .../arch/powerpc/entry/syscalls/syscall.tbl | 2 +- .../arch/x86/entry/syscalls/syscall_64.tbl | 2 +- 29 files changed, 3866 insertions(+), 9 deletions(-) create mode 100644 drivers/xcu/Makefile create mode 100644 drivers/xcu/xcu_group.c create mode 100644 include/linux/vstream.h create mode 100644 include/linux/xcu_group.h create mode 100644 include/linux/xsched.h create mode 100644 include/uapi/linux/xcu_vstream.h create mode 100644 kernel/xsched/Kconfig create mode 100644 kernel/xsched/Makefile create mode 100644 kernel/xsched/cfs.c create mode 100644 kernel/xsched/cfs_quota.c create mode 100644 kernel/xsched/cgroup.c create mode 100644 kernel/xsched/core.c create mode 100644 kernel/xsched/rt.c create mode 100644 kernel/xsched/vstream.c -- 2.34.1

2 9

[PATCH OLK-6.6] blk-ioinf: fix default weight being reset to 0 for non-root cgroups
by Baokun Li 19 Nov '25

19 Nov '25

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ID0C1D -------------------------------- The legacy blkio cgroup treats both `/sys/fs/cgroup/blkio` (the true root) and `/sys/fs/cgroup/blkio/1` (often the first user-created cgroup) as root when initializing the per-device (pd) structure. Consequently, if a default weight is set for the non-root cgroup (`/sys/fs/cgroup/blkio/1`), it is incorrectly overwritten and reset to 0 inside `ioinf_pd_init()`. This patch resolves the issue by increasing the priority of the `IOINFG_WEIGHT_UNINIT` check, ensuring that an explicitly set default weight is honored and is not reset when the `pd` is initialized. Fixes: a63e78514d11 ("blk-ioinf: introduce inflight-based IO QoS controller") Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- block/blk-ioinf.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/block/blk-ioinf.c b/block/blk-ioinf.c index 7432d88bf1f0..623c2715802b 100644 --- a/block/blk-ioinf.c +++ b/block/blk-ioinf.c @@ -1289,18 +1289,16 @@ static void ioinf_pd_init(struct blkg_policy_data *pd) struct blkcg_gq *parent = blkg->parent; infg->inf = q_to_inf(blkg->q); - if (!parent || parent->blkcg->css.cgroup->level == 0) { - infcg->dfl_user_weight = 0; - return; - } - - infg->user_weight = blkg_to_infg(parent)->user_weight; + if (parent) + infg->user_weight = blkg_to_infg(parent)->user_weight; /* Inherit the parent cgroup's dfl_user_weight if it was not set. */ if (infcg->dfl_user_weight == IOINFG_WEIGHT_UNINIT) { - struct ioinf_cgrp *parent_cgrp = blkcg_to_infcg(parent->blkcg); - - infcg->dfl_user_weight = parent_cgrp->dfl_user_weight; + if (!parent || parent->blkcg->css.cgroup->level == 0) + infcg->dfl_user_weight = 0; + else + infcg->dfl_user_weight = + blkcg_to_infcg(parent->blkcg)->dfl_user_weight; } infg->dfl_user_weight = infcg->dfl_user_weight; -- 2.46.1

2 1

[PATCH OLK-6.6] arm64/mpam: Add build dependencies for CONFIG_RESCTRL_IOMMU
by Zeng Heng 19 Nov '25

19 Nov '25

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IC03L1 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/morse/linux.git/commit/?h=m… -------------------------------- On the ARM64 architecture, the CONFIG_RESCTRL_IOMMU actually depends on the CONFIG_ARM_SMMU_V3, which allows to bind SMMU iommu_groups with resctrl groups. Therefore, add this build dependency in Kconfig. Additionally, to avoid compilation errors due to re-definitions in the include/linux/resctrl.h header file when the CONFIG_RESCTRL_IOMMU is disabled, add the build switch for resctrl_arch_*_iommu_closid_rmid(). Fixes: 7e3f95a1a861 ("fs/resctrl: Add support for assigning iommu_groups to resctrl groups") Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- drivers/platform/mpam/Kconfig | 2 +- drivers/platform/mpam/mpam_resctrl.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/platform/mpam/Kconfig b/drivers/platform/mpam/Kconfig index a6e937b8f91d..96dd7c091a9f 100644 --- a/drivers/platform/mpam/Kconfig +++ b/drivers/platform/mpam/Kconfig @@ -6,4 +6,4 @@ config ARM_CPU_RESCTRL depends on ARM64 && ARCH_HAS_CPU_RESCTRL depends on MISC_FILESYSTEMS select RESCTRL_RMID_DEPENDS_ON_CLOSID - select RESCTRL_IOMMU + select RESCTRL_IOMMU if ARM_SMMU_V3 diff --git a/drivers/platform/mpam/mpam_resctrl.c b/drivers/platform/mpam/mpam_resctrl.c index 2d3a1827a48c..7c386ce7b80f 100644 --- a/drivers/platform/mpam/mpam_resctrl.c +++ b/drivers/platform/mpam/mpam_resctrl.c @@ -260,6 +260,7 @@ bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 closid, u32 rmid) return (tsk_closid == closid) && (tsk_rmid == rmid); } +#ifdef CONFIG_RESCTRL_IOMMU int resctrl_arch_set_iommu_closid_rmid(struct iommu_group *group, u32 closid, u32 rmid) { @@ -302,6 +303,7 @@ bool resctrl_arch_match_iommu_closid_rmid(struct iommu_group *group, return (partid == closid) && (rmid == pmg); } +#endif struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l) { -- 2.25.1

2 1

openEuler Kernel SIG双周例会
by openEuler conference 19 Nov '25

19 Nov '25

您好！ Kernel 邀请您参加 2025-11-21 14:00 召开的WeLink会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1. 进展update 2. 议题征集中（新增议题可回复本邮件申请，或填报至会议纪要看板）会议链接：https://meeting.huaweicloud.com:36443/#/j/987186410 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 更多资讯尽在：https://www.openeuler.org/zh/ Hello! Kernel invites you to attend the WeLink conference(auto recording) will be held at 2025-11-21 14:00, The subject of the conference is openEuler Kernel SIG双周例会 Summary: 1. 进展update 2. 议题征集中（新增议题可回复本邮件申请，或填报至会议纪要看板） You can join the meeting at https://meeting.huaweicloud.com:36443/#/j/987186410 Add topics at https://etherpad.openeuler.org/p/Kernel-meetings More information: https://www.openeuler.org/en/

1 0

[PATCH OLK-6.6 0/8] xsched: XCU Partition
by Zicheng Qu 19 Nov '25

19 Nov '25

Alekseev Dmitry (2): xsched: Add XCU control group implementation and its backend in xsched CFS xsched: Add support for CFS quota for cgroups Konstantin Meskhidze (6): xsched: Add base vstream support xcu: Add base NPU driver support xsched: Introduce vstream management xsched: Add basic scheduler core support xsched: Add xsched RT class xsched: Add xsched CFS class arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 2 +- drivers/Makefile | 1 + drivers/xcu/Makefile | 2 + drivers/xcu/xcu_group.c | 380 +++++++++ include/linux/cgroup_subsys.h | 4 + include/linux/syscalls.h | 2 + include/linux/vstream.h | 91 ++ include/linux/xcu_group.h | 96 +++ include/linux/xsched.h | 514 ++++++++++++ include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/xcu_vstream.h | 77 ++ init/Kconfig | 1 + kernel/Makefile | 1 + kernel/cgroup/cgroup.c | 2 +- kernel/xsched/Kconfig | 85 ++ kernel/xsched/Makefile | 9 + kernel/xsched/cfs.c | 237 ++++++ kernel/xsched/cfs_quota.c | 98 +++ kernel/xsched/cgroup.c | 775 ++++++++++++++++++ kernel/xsched/core.c | 526 ++++++++++++ kernel/xsched/rt.c | 281 +++++++ kernel/xsched/vstream.c | 674 +++++++++++++++ .../arch/x86/entry/syscalls/syscall_64.tbl | 2 +- 25 files changed, 3862 insertions(+), 5 deletions(-) create mode 100644 drivers/xcu/Makefile create mode 100644 drivers/xcu/xcu_group.c create mode 100644 include/linux/vstream.h create mode 100644 include/linux/xcu_group.h create mode 100644 include/linux/xsched.h create mode 100644 include/uapi/linux/xcu_vstream.h create mode 100644 kernel/xsched/Kconfig create mode 100644 kernel/xsched/Makefile create mode 100644 kernel/xsched/cfs.c create mode 100644 kernel/xsched/cfs_quota.c create mode 100644 kernel/xsched/cgroup.c create mode 100644 kernel/xsched/core.c create mode 100644 kernel/xsched/rt.c create mode 100644 kernel/xsched/vstream.c -- 2.34.1

2 9