From nobody Fri Jan 2 17:24:06 2026 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3F6FACD6907 for ; Tue, 10 Oct 2023 08:32:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1442864AbjJJIcc (ORCPT ); Tue, 10 Oct 2023 04:32:32 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:58714 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1442876AbjJJIc3 (ORCPT ); Tue, 10 Oct 2023 04:32:29 -0400 Received: from outbound-smtp44.blacknight.com (outbound-smtp44.blacknight.com [46.22.136.52]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 345BAA4 for ; Tue, 10 Oct 2023 01:32:28 -0700 (PDT) Received: from mail.blacknight.com (pemlinmail04.blacknight.ie [81.17.254.17]) by outbound-smtp44.blacknight.com (Postfix) with ESMTPS id A0BB3F846C for ; Tue, 10 Oct 2023 09:32:26 +0100 (IST) Received: (qmail 8011 invoked from network); 10 Oct 2023 08:32:26 -0000 Received: from unknown (HELO morpheus.112glenside.lan) (mgorman@techsingularity.net@[84.203.197.19]) by 81.17.254.9 with ESMTPA; 10 Oct 2023 08:32:26 -0000 From: Mel Gorman To: Peter Zijlstra Cc: Raghavendra K T , K Prateek Nayak , Bharata B Rao , Ingo Molnar , LKML , Linux-MM , Mel Gorman Subject: [PATCH 3/6] sched/numa: Trace decisions related to skipping VMAs Date: Tue, 10 Oct 2023 09:31:40 +0100 Message-Id: <20231010083143.19593-4-mgorman@techsingularity.net> X-Mailer: git-send-email 2.35.3 In-Reply-To: <20231010083143.19593-1-mgorman@techsingularity.net> References: <20231010083143.19593-1-mgorman@techsingularity.net> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" NUMA Balancing skip or scans VMAs for a variety of reasons. In preparation for completing scans of VMAs regardless of PID access, trace the reasons why a VMA was skipped. In a later patch, the tracing will be used to track if a VMA was forcibly scanned. Signed-off-by: Mel Gorman --- include/linux/sched/numa_balancing.h | 8 +++++ include/trace/events/sched.h | 50 ++++++++++++++++++++++++++++ kernel/sched/fair.c | 17 +++++++--- 3 files changed, 71 insertions(+), 4 deletions(-) diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/num= a_balancing.h index 3988762efe15..c127a1509e2f 100644 --- a/include/linux/sched/numa_balancing.h +++ b/include/linux/sched/numa_balancing.h @@ -15,6 +15,14 @@ #define TNF_FAULT_LOCAL 0x08 #define TNF_MIGRATE_FAIL 0x10 =20 +enum numa_vmaskip_reason { + NUMAB_SKIP_UNSUITABLE, + NUMAB_SKIP_SHARED_RO, + NUMAB_SKIP_INACCESSIBLE, + NUMAB_SKIP_SCAN_DELAY, + NUMAB_SKIP_PID_INACTIVE, +}; + #ifdef CONFIG_NUMA_BALANCING extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index fbb99a61f714..b0d0dbf491ea 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -664,6 +664,56 @@ DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa, TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); =20 +#ifdef CONFIG_NUMA_BALANCING +#define NUMAB_SKIP_REASON \ + EM( NUMAB_SKIP_UNSUITABLE, "unsuitable" ) \ + EM( NUMAB_SKIP_SHARED_RO, "shared_ro" ) \ + EM( NUMAB_SKIP_INACCESSIBLE, "inaccessible" ) \ + EM( NUMAB_SKIP_SCAN_DELAY, "scan_delay" ) \ + EMe(NUMAB_SKIP_PID_INACTIVE, "pid_inactive" ) + +/* Redefine for export. */ +#undef EM +#undef EMe +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +NUMAB_SKIP_REASON + +/* Redefine for symbolic printing. */ +#undef EM +#undef EMe +#define EM(a, b) { a, b }, +#define EMe(a, b) { a, b } + +TRACE_EVENT(sched_skip_vma_numa, + + TP_PROTO(struct mm_struct *mm, struct vm_area_struct *vma, + enum numa_vmaskip_reason reason), + + TP_ARGS(mm, vma, reason), + + TP_STRUCT__entry( + __field(unsigned long, numa_scan_offset) + __field(unsigned long, vm_start) + __field(unsigned long, vm_end) + __field(enum numa_vmaskip_reason, reason) + ), + + TP_fast_assign( + __entry->numa_scan_offset =3D mm->numa_scan_offset; + __entry->vm_start =3D vma->vm_start; + __entry->vm_end =3D vma->vm_end; + __entry->reason =3D reason; + ), + + TP_printk("numa_scan_offset=3D%lX vm_start=3D%lX vm_end=3D%lX reason=3D%s= ", + __entry->numa_scan_offset, + __entry->vm_start, + __entry->vm_end, + __print_symbolic(__entry->reason, NUMAB_SKIP_REASON)) +); +#endif /* CONFIG_NUMA_BALANCING */ =20 /* * Tracepoint for waking a polling cpu without an IPI. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 81405627b9ed..0535c57f6a77 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3227,6 +3227,7 @@ static void task_numa_work(struct callback_head *work) do { if (!vma_migratable(vma) || !vma_policy_mof(vma) || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { + trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_UNSUITABLE); continue; } =20 @@ -3237,15 +3238,19 @@ static void task_numa_work(struct callback_head *wo= rk) * as migrating the pages will be of marginal benefit. */ if (!vma->vm_mm || - (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) =3D=3D (VM_REA= D))) + (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) =3D=3D (VM_REA= D))) { + trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_SHARED_RO); continue; + } =20 /* * Skip inaccessible VMAs to avoid any confusion between * PROT_NONE and NUMA hinting ptes */ - if (!vma_is_accessible(vma)) + if (!vma_is_accessible(vma)) { + trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_INACCESSIBLE); continue; + } =20 /* Initialise new per-VMA NUMAB state. */ if (!vma->numab_state) { @@ -3267,12 +3272,16 @@ static void task_numa_work(struct callback_head *wo= rk) * delay the scan for new VMAs. */ if (mm->numa_scan_seq && time_before(jiffies, - vma->numab_state->next_scan)) + vma->numab_state->next_scan)) { + trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_SCAN_DELAY); continue; + } =20 /* Do not scan the VMA if task has not accessed */ - if (!vma_is_accessed(vma)) + if (!vma_is_accessed(vma)) { + trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_PID_INACTIVE); continue; + } =20 /* * RESET access PIDs regularly for old VMAs. Resetting after checking --=20 2.35.3