* [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg [not found] <cover.1793250194.git.x-professor@outlook.com> @ 2026-10-29 5:03 ` Yingjie Wang 2026-11-16 4:19 ` Shakeel Butt 2026-11-16 16:10 ` Shakeel Butt 2026-10-29 5:03 ` [PATCH v5 2/3] ipc/sem: reject negative SEMOPM values Yingjie Wang 1 sibling, 2 replies; 6+ messages in thread From: Yingjie Wang @ 2026-10-29 5:03 UTC (permalink / raw) To: akpm@linux-foundation.org, Manfred Spraul, Alexey Gladkov, Eric W . Biederman Cc: Yingjie Wang, Vasily Averin, Johannes Weiner, Shakeel Butt, Michal Koutný, Michal Hocko, Alejandro Colomar, linux-kernel@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, linux-api@vger.kernel.org, linux-man@vger.kernel.org, linux-hardening@vger.kernel.org, stable@vger.kernel.org Commit 6a4746ba0619 ("ipc: remove memcg accounting for sops objects in do_semtimedop()") removed accounting based on the assumption that sops arrays would remain small, describing a maximum cost of two pages. SEMOPM is a UAPI default that can be changed at build time and through the per-namespace sysctl. Commit 50ec499b9a43 ("sysctl: allow change system v ipc sysctls inside ipc namespace") made that limit tunable by IPC namespace owners without capabilities in the initial user namespace. do_semtimedop() keeps up to SEMOPM_FAST operations on the stack. Charge every larger, dynamically allocated operation array to the caller's memory cgroup. This avoids a second size threshold and prevents a configured SEMOPM limit from expanding an unaccounted heap-allocation range. In a 4-vCPU KVM guest, with the benchmark pinned to one vCPU in a leaf memory cgroup, accounting raised the median time per successful semop() call by 2.3% to 3.2% for 65, 500 and 1000 operations, compared with unaccounted allocation. An invalid semid, which allocates and copies the array before returning EINVAL, rose by 5.6% to 11.9%. The 64-operation stack path changed by at most 0.9%, and successful calls in the root cgroup by at most 2.3%. Each result used 21 samples from three boots. Suggested-by: Shakeel Butt <shakeel.butt@linux.dev> Link: https://lore.kernel.org/r/20261016152609.2528805-1-x-professor@outlook.com Fixes: 6a4746ba0619 ("ipc: remove memcg accounting for sops objects in do_semtimedop()") Cc: stable@vger.kernel.org Signed-off-by: Yingjie Wang <x-professor@outlook.com> --- ipc/sem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ipc/sem.c b/ipc/sem.c index 5ec41de7e85b2..ea95cca5bb0ec 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2234,7 +2234,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, return -EINVAL; if (nsops > SEMOPM_FAST) { - sops = kvmalloc_objs(*sops, nsops); + sops = kvmalloc_objs(*sops, nsops, GFP_KERNEL_ACCOUNT); if (sops == NULL) return -ENOMEM; } -- 2.43.0 ^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg 2026-10-29 5:03 ` [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg Yingjie Wang @ 2026-11-16 4:19 ` Shakeel Butt 2026-11-16 8:20 ` Yingjie Wang 2026-11-16 16:10 ` Shakeel Butt 1 sibling, 1 reply; 6+ messages in thread From: Shakeel Butt @ 2026-11-16 4:19 UTC (permalink / raw) To: Yingjie Wang Cc: akpm@linux-foundation.org, Manfred Spraul, Alexey Gladkov, Eric W . Biederman, Vasily Averin, Johannes Weiner, Michal Koutný, Michal Hocko, Alejandro Colomar, linux-kernel@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, linux-api@vger.kernel.org, linux-man@vger.kernel.org, linux-hardening@vger.kernel.org, stable@vger.kernel.org On Thu, Oct 29, 2026 at 05:03:25AM +0000, Yingjie Wang wrote: > Commit 6a4746ba0619 ("ipc: remove memcg accounting for sops objects in > do_semtimedop()") removed accounting based on the assumption that sops > arrays would remain small, describing a maximum cost of two pages. > > SEMOPM is a UAPI default that can be changed at build time and through > the per-namespace sysctl. Commit 50ec499b9a43 ("sysctl: allow change > system v ipc sysctls inside ipc namespace") made that limit tunable by > IPC namespace owners without capabilities in the initial user namespace. > > do_semtimedop() keeps up to SEMOPM_FAST operations on the stack. Charge > every larger, dynamically allocated operation array to the caller's memory > cgroup. This avoids a second size threshold and prevents a configured > SEMOPM limit from expanding an unaccounted heap-allocation range. > > In a 4-vCPU KVM guest, with the benchmark pinned to one vCPU in a leaf > memory cgroup, accounting raised the median time per successful semop() > call by 2.3% to 3.2% for 65, 500 and 1000 operations, compared with > unaccounted allocation. An invalid semid, which allocates and copies the > array before returning EINVAL, rose by 5.6% to 11.9%. The 64-operation > stack path changed by at most 0.9%, and successful calls in the root > cgroup by at most 2.3%. Each result used 21 samples from three boots. There is no kmem accounting in root cgroup, do you know why there is an increase of 2.3% there? > > Suggested-by: Shakeel Butt <shakeel.butt@linux.dev> > Link: https://lore.kernel.org/r/20261016152609.2528805-1-x-professor@outlook.com > Fixes: 6a4746ba0619 ("ipc: remove memcg accounting for sops objects in do_semtimedop()") > Cc: stable@vger.kernel.org > Signed-off-by: Yingjie Wang <x-professor@outlook.com> > --- > ipc/sem.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/ipc/sem.c b/ipc/sem.c > index 5ec41de7e85b2..ea95cca5bb0ec 100644 > --- a/ipc/sem.c > +++ b/ipc/sem.c > @@ -2234,7 +2234,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, > return -EINVAL; > > if (nsops > SEMOPM_FAST) { > - sops = kvmalloc_objs(*sops, nsops); > + sops = kvmalloc_objs(*sops, nsops, GFP_KERNEL_ACCOUNT); > if (sops == NULL) > return -ENOMEM; > } > -- > 2.43.0 > ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg 2026-11-16 4:19 ` Shakeel Butt @ 2026-11-16 8:20 ` Yingjie Wang 2026-11-16 16:00 ` Andrew Morton 0 siblings, 1 reply; 6+ messages in thread From: Yingjie Wang @ 2026-11-16 8:20 UTC (permalink / raw) To: shakeel.butt@linux.dev Cc: akpm@linux-foundation.org, manfred@colorfullife.com, legion@kernel.org, ebiederm@xmission.com, vasily.averin@linux.dev, hannes@cmpxchg.org, mkoutny@suse.com, mhocko@suse.com, alx@kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, linux-api@vger.kernel.org, linux-man@vger.kernel.org, linux-hardening@vger.kernel.org, stable@vger.kernel.org > There is no kmem accounting in root cgroup, do you know why there is an increase > of 2.3% there? I think the 2.3% mainly reflects boot-to-boot variation. The unchanged 64-operation stack path also slowed down by 1.9%, even though it does not reach the changed allocation. For successful calls, the per-boot medians were: nops V4 boots (ns) V5 boots (ns) 64 230.5 229.4 230.0 231.2 235.0 235.4 65 546.0 551.2 548.2 551.2 562.6 566.3 The first V5 boot was very close to the upper end of the V4 results at 65 operations, while the later two boots were slower at both sizes. That is why I interpret the increase mainly as boot-to-boot variation, rather than root-cgroup charging. __GFP_ACCOUNT does still change the allocation path, including selecting the kmalloc-cg cache, so a small contribution from that is also possible. Andrew, could we clarify the root-cgroup result in the [1/3] changelog? Please change and successful calls in the root cgroup by at most 2.3%. to and successful calls in the root cgroup by at most 2.3%, which appears to be mainly boot-to-boot variation. Thanks, Yingjie ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg 2026-11-16 8:20 ` Yingjie Wang @ 2026-11-16 16:00 ` Andrew Morton 0 siblings, 0 replies; 6+ messages in thread From: Andrew Morton @ 2026-11-16 16:00 UTC (permalink / raw) To: Yingjie Wang Cc: shakeel.butt@linux.dev, manfred@colorfullife.com, legion@kernel.org, ebiederm@xmission.com, vasily.averin@linux.dev, hannes@cmpxchg.org, mkoutny@suse.com, mhocko@suse.com, alx@kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, linux-api@vger.kernel.org, linux-man@vger.kernel.org, linux-hardening@vger.kernel.org, stable@vger.kernel.org On Mon, 16 Nov 2026 08:20:52 +0000 Yingjie Wang <x-professor@outlook.com> wrote: > > There is no kmem accounting in root cgroup, do you know why there is an increase > > of 2.3% there? > > I think the 2.3% mainly reflects boot-to-boot variation. The unchanged > 64-operation stack path also slowed down by 1.9%, even though it does > not reach the changed allocation. > > For successful calls, the per-boot medians were: > > nops V4 boots (ns) V5 boots (ns) > 64 230.5 229.4 230.0 231.2 235.0 235.4 > 65 546.0 551.2 548.2 551.2 562.6 566.3 > > The first V5 boot was very close to the upper end of the V4 results at > 65 operations, while the later two boots were slower at both sizes. > That is why I interpret the increase mainly as boot-to-boot variation, > rather than root-cgroup charging. > > __GFP_ACCOUNT does still change the allocation path, including selecting > the kmalloc-cg cache, so a small contribution from that is also possible. > > Andrew, could we clarify the root-cgroup result in the [1/3] changelog? > Please change > > and successful calls in the root cgroup by at most 2.3%. > > to > > and successful calls in the root cgroup by at most 2.3%, which > appears to be mainly boot-to-boot variation. Yes, I have made both requested edits. ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg 2026-10-29 5:03 ` [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg Yingjie Wang 2026-11-16 4:19 ` Shakeel Butt @ 2026-11-16 16:10 ` Shakeel Butt 1 sibling, 0 replies; 6+ messages in thread From: Shakeel Butt @ 2026-11-16 16:10 UTC (permalink / raw) To: Yingjie Wang Cc: akpm@linux-foundation.org, Manfred Spraul, Alexey Gladkov, Eric W . Biederman, Vasily Averin, Johannes Weiner, Michal Koutný, Michal Hocko, Alejandro Colomar, linux-kernel@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, linux-api@vger.kernel.org, linux-man@vger.kernel.org, linux-hardening@vger.kernel.org, stable@vger.kernel.org On Thu, Oct 29, 2026 at 05:03:25AM +0000, Yingjie Wang wrote: > Commit 6a4746ba0619 ("ipc: remove memcg accounting for sops objects in > do_semtimedop()") removed accounting based on the assumption that sops > arrays would remain small, describing a maximum cost of two pages. > > SEMOPM is a UAPI default that can be changed at build time and through > the per-namespace sysctl. Commit 50ec499b9a43 ("sysctl: allow change > system v ipc sysctls inside ipc namespace") made that limit tunable by > IPC namespace owners without capabilities in the initial user namespace. > > do_semtimedop() keeps up to SEMOPM_FAST operations on the stack. Charge > every larger, dynamically allocated operation array to the caller's memory > cgroup. This avoids a second size threshold and prevents a configured > SEMOPM limit from expanding an unaccounted heap-allocation range. > > In a 4-vCPU KVM guest, with the benchmark pinned to one vCPU in a leaf > memory cgroup, accounting raised the median time per successful semop() > call by 2.3% to 3.2% for 65, 500 and 1000 operations, compared with > unaccounted allocation. An invalid semid, which allocates and copies the > array before returning EINVAL, rose by 5.6% to 11.9%. The 64-operation > stack path changed by at most 0.9%, and successful calls in the root > cgroup by at most 2.3%. Each result used 21 samples from three boots. > > Suggested-by: Shakeel Butt <shakeel.butt@linux.dev> > Link: https://lore.kernel.org/r/20261016152609.2528805-1-x-professor@outlook.com > Fixes: 6a4746ba0619 ("ipc: remove memcg accounting for sops objects in do_semtimedop()") > Cc: stable@vger.kernel.org > Signed-off-by: Yingjie Wang <x-professor@outlook.com> Acked-by: Shakeel Butt <shakeel.butt@linux.dev> ^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH v5 2/3] ipc/sem: reject negative SEMOPM values [not found] <cover.1793250194.git.x-professor@outlook.com> 2026-10-29 5:03 ` [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg Yingjie Wang @ 2026-10-29 5:03 ` Yingjie Wang 1 sibling, 0 replies; 6+ messages in thread From: Yingjie Wang @ 2026-10-29 5:03 UTC (permalink / raw) To: akpm@linux-foundation.org, Manfred Spraul, Alexey Gladkov, Eric W . Biederman Cc: Yingjie Wang, Vasily Averin, Johannes Weiner, Shakeel Butt, Michal Koutný, Michal Hocko, Alejandro Colomar, linux-kernel@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, linux-api@vger.kernel.org, linux-man@vger.kernel.org, linux-hardening@vger.kernel.org, stable@vger.kernel.org The SEMOPM field has been stored as an int while semop() receives an unsigned operation count since the beginning of Git history. A negative SEMOPM accepted by proc_dointvec() is converted to a large unsigned value in the comparison, defeating the intended operation-count limit. Commit 50ec499b9a43 ("sysctl: allow change system v ipc sysctls inside ipc namespace") made kernel.sem writable by IPC namespace owners without capabilities in the initial user namespace. Parse writes against a temporary copy and validate SEMOPM and SEMMNI before changing the live settings. Hold a per-namespace mutex from the snapshot through publication so concurrent sysctl writers cannot publish stale values for fields they did not supply. Access the live fields with READ_ONCE() and WRITE_ONCE(), preserving the per-field access semantics of proc_dointvec(). Read requests continue to use proc_dointvec() directly. Failed writes leave the live settings unchanged. Successful partial writes change only the supplied fields relative to the latest locked snapshot. The writer mutex retains the existing per-field visibility for readers. Keep zero and positive SEMOPM values valid. Zero continues to reject every non-empty semop() request. Suggested-by: Andrew Morton <akpm@linux-foundation.org> Link: https://lore.kernel.org/r/20261016155905.2a659b7bb7d61f33467a3263@linux-foundation.org Link: https://lore.kernel.org/r/51c93c19-f1dd-455f-8698-6b1ee30eb630@colorfullife.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Reviewed-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Yingjie Wang <x-professor@outlook.com> --- include/linux/ipc_namespace.h | 3 +++ ipc/ipc_sysctl.c | 35 ++++++++++++++++++++++++++--------- ipc/sem.c | 1 + ipc/util.h | 9 --------- 4 files changed, 30 insertions(+), 18 deletions(-) diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 12faca29bbb9c..c06568ccfca88 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -4,6 +4,7 @@ #include <linux/err.h> #include <linux/idr.h> +#include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/notifier.h> #include <linux/nsproxy.h> @@ -31,6 +32,8 @@ struct ipc_ids { struct ipc_namespace { struct ipc_ids ids[3]; + /* Serialize kernel.sem writers. */ + struct mutex sem_ctls_mutex; int sem_ctls[4]; int used_sems; diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index d038d944257f6..0e3608258fe29 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -51,21 +51,38 @@ static int proc_ipc_auto_msgmni(const struct ctl_table *table, int write, static int proc_ipc_sem_dointvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { + struct ctl_table ipc_table; struct ipc_namespace *ns = container_of(table->data, struct ipc_namespace, sem_ctls); - int ret, semmni; + int sem_ctls[ARRAY_SIZE(ns->sem_ctls)]; + size_t i; + int ret; + + if (!write) + return proc_dointvec(table, write, buffer, lenp, ppos); - semmni = ns->sem_ctls[3]; - ret = proc_dointvec(table, write, buffer, lenp, ppos); + mutex_lock(&ns->sem_ctls_mutex); + for (i = 0; i < ARRAY_SIZE(sem_ctls); i++) + sem_ctls[i] = READ_ONCE(ns->sem_ctls[i]); - if (!ret) - ret = sem_check_semmni(ns); + ipc_table = *table; + ipc_table.data = sem_ctls; - /* - * Reset the semmni value if an error happens. - */ + ret = proc_dointvec(&ipc_table, write, buffer, lenp, ppos); if (ret) - ns->sem_ctls[3] = semmni; + goto out_unlock; + + if (sem_ctls[2] < 0 || + sem_ctls[3] < 0 || sem_ctls[3] > ipc_mni) { + ret = -ERANGE; + goto out_unlock; + } + + for (i = 0; i < ARRAY_SIZE(sem_ctls); i++) + WRITE_ONCE(ns->sem_ctls[i], sem_ctls[i]); + +out_unlock: + mutex_unlock(&ns->sem_ctls_mutex); return ret; } diff --git a/ipc/sem.c b/ipc/sem.c index ea95cca5bb0ec..098e483ae8d3c 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -248,6 +248,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); void sem_init_ns(struct ipc_namespace *ns) { + mutex_init(&ns->sem_ctls_mutex); ns->sc_semmsl = SEMMSL; ns->sc_semmns = SEMMNS; ns->sc_semopm = SEMOPM; diff --git a/ipc/util.h b/ipc/util.h index a55d6cebe6d3b..51b4efa3d6db0 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -245,15 +245,6 @@ int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)); -static inline int sem_check_semmni(struct ipc_namespace *ns) { - /* - * Check semmni range [0, ipc_mni] - * semmni is the last element of sem_ctls[4] array - */ - return ((ns->sem_ctls[3] < 0) || (ns->sem_ctls[3] > ipc_mni)) - ? -ERANGE : 0; -} - #ifdef CONFIG_COMPAT #include <linux/compat.h> struct compat_ipc_perm { -- 2.43.0 ^ permalink raw reply related [flat|nested] 6+ messages in thread
end of thread, other threads:[~2026-11-16 16:10 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <cover.1793250194.git.x-professor@outlook.com>
2026-10-29 5:03 ` [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg Yingjie Wang
2026-11-16 4:19 ` Shakeel Butt
2026-11-16 8:20 ` Yingjie Wang
2026-11-16 16:00 ` Andrew Morton
2026-11-16 16:10 ` Shakeel Butt
2026-10-29 5:03 ` [PATCH v5 2/3] ipc/sem: reject negative SEMOPM values Yingjie Wang
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox