From 02d954c0fdf91845169cdacc7405b120f90afe01 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 10 Feb 2025 16:32:50 +0100 Subject: [PATCH 1/2] sched: Compact RSEQ concurrency IDs with reduced threads and affinity When a process reduces its number of threads or clears bits in its CPU affinity mask, the mm_cid allocation should eventually converge towards smaller values. However, the change introduced by: commit 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads") adds a per-mm/CPU recent_cid which is never unset unless a thread migrates. This is a tradeoff between: A) Preserving cache locality after a transition from many threads to few threads, or after reducing the hamming weight of the allowed CPU mask. B) Making the mm_cid upper bounds wrt nr threads and allowed CPU mask easy to document and understand. C) Allowing applications to eventually react to mm_cid compaction after reduction of the nr threads or allowed CPU mask, making the tracking of mm_cid compaction easier by shrinking it back towards 0 or not. D) Making sure applications that periodically reduce and then increase again the nr threads or allowed CPU mask still benefit from good cache locality with mm_cid. Introduce the following changes: * After shrinking the number of threads or reducing the number of allowed CPUs, reduce the value of max_nr_cid so expansion of CID allocation will preserve cache locality if the number of threads or allowed CPUs increase again. * Only re-use a recent_cid if it is within the max_nr_cid upper bound, else find the first available CID. Fixes: 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads") Signed-off-by: Mathieu Desnoyers Signed-off-by: Gabriele Monaco Signed-off-by: Peter Zijlstra (Intel) Tested-by: Gabriele Monaco Link: https://lkml.kernel.org/r/20250210153253.460471-2-gmonaco@redhat.com --- include/linux/mm_types.h | 7 ++++--- kernel/sched/sched.h | 25 ++++++++++++++++++++++--- 2 files changed, 26 insertions(+), 6 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6b27db7f9496..0234f14f2aa6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -875,10 +875,11 @@ struct mm_struct { */ unsigned int nr_cpus_allowed; /** - * @max_nr_cid: Maximum number of concurrency IDs allocated. + * @max_nr_cid: Maximum number of allowed concurrency + * IDs allocated. * - * Track the highest number of concurrency IDs allocated for the - * mm. + * Track the highest number of allowed concurrency IDs + * allocated for the mm. */ atomic_t max_nr_cid; /** diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b93c8c3dc05a..c8512a9fb022 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3698,10 +3698,28 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm) { struct cpumask *cidmask = mm_cidmask(mm); struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid; - int cid = __this_cpu_read(pcpu_cid->recent_cid); + int cid, max_nr_cid, allowed_max_nr_cid; + /* + * After shrinking the number of threads or reducing the number + * of allowed cpus, reduce the value of max_nr_cid so expansion + * of cid allocation will preserve cache locality if the number + * of threads or allowed cpus increase again. + */ + max_nr_cid = atomic_read(&mm->max_nr_cid); + while ((allowed_max_nr_cid = min_t(int, READ_ONCE(mm->nr_cpus_allowed), + atomic_read(&mm->mm_users))), + max_nr_cid > allowed_max_nr_cid) { + /* atomic_try_cmpxchg loads previous mm->max_nr_cid into max_nr_cid. */ + if (atomic_try_cmpxchg(&mm->max_nr_cid, &max_nr_cid, allowed_max_nr_cid)) { + max_nr_cid = allowed_max_nr_cid; + break; + } + } /* Try to re-use recent cid. This improves cache locality. */ - if (!mm_cid_is_unset(cid) && !cpumask_test_and_set_cpu(cid, cidmask)) + cid = __this_cpu_read(pcpu_cid->recent_cid); + if (!mm_cid_is_unset(cid) && cid < max_nr_cid && + !cpumask_test_and_set_cpu(cid, cidmask)) return cid; /* * Expand cid allocation if the maximum number of concurrency @@ -3709,8 +3727,9 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm) * and number of threads. Expanding cid allocation as much as * possible improves cache locality. */ - cid = atomic_read(&mm->max_nr_cid); + cid = max_nr_cid; while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) { + /* atomic_try_cmpxchg loads previous mm->max_nr_cid into cid. */ if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1)) continue; if (!cpumask_test_and_set_cpu(cid, cidmask)) From dc0a241ceaf3b7df6f1a7658b020c92682b75bfc Mon Sep 17 00:00:00 2001 From: Michael Jeanson Date: Wed, 19 Feb 2025 15:53:26 -0500 Subject: [PATCH 2/2] rseq: Fix rseq registration with CONFIG_DEBUG_RSEQ With CONFIG_DEBUG_RSEQ=y, at rseq registration the read-only fields are copied from user-space, if this copy fails the syscall returns -EFAULT and the registration should not be activated - but it erroneously is. Move the activation of the registration after the copy of the fields to fix this bug. Fixes: 7d5265ffcd8b ("rseq: Validate read-only fields under DEBUG_RSEQ config") Signed-off-by: Michael Jeanson Signed-off-by: Ingo Molnar Reviewed-by: Mathieu Desnoyers Link: https://lore.kernel.org/r/20250219205330.324770-1-mjeanson@efficios.com --- kernel/rseq.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/kernel/rseq.c b/kernel/rseq.c index 442aba29bc4c..2cb16091ec0a 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -507,9 +507,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; - current->rseq = rseq; - current->rseq_len = rseq_len; - current->rseq_sig = sig; #ifdef CONFIG_DEBUG_RSEQ /* * Initialize the in-kernel rseq fields copy for validation of @@ -521,6 +518,14 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, get_user(rseq_kernel_fields(current)->mm_cid, &rseq->mm_cid)) return -EFAULT; #endif + /* + * Activate the registration by setting the rseq area address, length + * and signature in the task struct. + */ + current->rseq = rseq; + current->rseq_len = rseq_len; + current->rseq_sig = sig; + /* * If rseq was previously inactive, and has just been * registered, ensure the cpu_id_start and cpu_id fields