From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from linux.microsoft.com (linux.microsoft.com [13.77.154.182]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 24C8D330657 for ; Mon, 23 Feb 2026 17:15:51 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=13.77.154.182 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1771866952; cv=none; b=WNGl1LioDty6l5uIGX4wK6dCSR/8slDCAwOkrNQ+WPi1sSPsXKeoq1B/yXL240T0zGctNlwcxzFKGBJiX5UivZAIx9TucRig7+OVkv3sV33Cgi8Q6ABOAbeUll6GqDoxqZNhjsifC4rGNJVB0cjyoG4wzVjlqNrDhmZj5n6xT24= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1771866952; c=relaxed/simple; bh=XlerxhHqMoT7DZCTFijqKQxtr1Sv54TnMNH3sWU9ZIk=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=CVa4cTm5kVeAORDvo4wNFrJZ8gQ76+QY47xlHQEEKqsIKes0d+4HWUPBWIY4z1MKJIMOzmpG2U4DqOeuU7ApdepFCX3gpQHwuXjnPrssUp48Aj/cgf0nInm/3tuccaLlhS9DfY5zHtk9ar6PSSataYtlvXpLLupggwqJ6OrDNPs= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.microsoft.com; spf=pass smtp.mailfrom=linux.microsoft.com; dkim=pass (1024-bit key) header.d=linux.microsoft.com header.i=@linux.microsoft.com header.b=GYafJ4EF; arc=none smtp.client-ip=13.77.154.182 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.microsoft.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.microsoft.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.microsoft.com header.i=@linux.microsoft.com header.b="GYafJ4EF" Received: from LAPTOP-U3CCR7C6.lan (unknown [20.236.11.185]) by linux.microsoft.com (Postfix) with ESMTPSA id 2A67A20B6F03; Mon, 23 Feb 2026 09:15:50 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 2A67A20B6F03 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1771866950; bh=VDyWFdIJtNhC5hDziRtEOk+Pt3OXel3vxA48TpqXHRE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=GYafJ4EF9loYhEjOZGniiOZtqMtIRZFy3wBtor4BFdYy/U2QsOCEiA9GcuzeKuAEb 9Au3PQIeunqhd1R1z92dwG7yWgGV8Zpmvm5I9tRS65RKE3PdiOflZf1xNsGpnUEwhq TSpRj8rIn+fVWPPOJ7PdWp+7eOVcpewivL3UAP48= From: Thomas Ballasi To: tballasi@linux.microsoft.com Cc: akpm@linux-foundation.org, axelrasmussen@google.com, david@kernel.org, hannes@cmpxchg.org, linux-mm@kvack.org, linux-trace-kernel@vger.kernel.org, lorenzo.stoakes@oracle.com, mhiramat@kernel.org, mhocko@kernel.org, rostedt@goodmis.org, shakeel.butt@linux.dev, weixugc@google.com, yuanchu@google.com, zhengqi.arch@bytedance.com Subject: [PATCH v7 2/3] mm: vmscan: add cgroup IDs to vmscan tracepoints Date: Mon, 23 Feb 2026 09:15:43 -0800 Message-Id: <20260223171544.4750-3-tballasi@linux.microsoft.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20260223171544.4750-1-tballasi@linux.microsoft.com> References: <20260213181537.54350-1-tballasi@linux.microsoft.com> <20260223171544.4750-1-tballasi@linux.microsoft.com> Precedence: bulk X-Mailing-List: linux-trace-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Memory reclaim events are currently difficult to attribute to specific cgroups, making debugging memory pressure issues challenging. This patch adds memory cgroup ID (memcg_id) to key vmscan tracepoints to enable better correlation and analysis. For operations not associated with a specific cgroup, the field is defaulted to 0. Signed-off-by: Thomas Ballasi --- include/trace/events/vmscan.h | 83 ++++++++++++++++++++--------------- mm/shrinker.c | 6 ++- mm/vmscan.c | 17 +++---- 3 files changed, 61 insertions(+), 45 deletions(-) diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 490958fa10dee..1212f6a7c223e 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -114,85 +114,92 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd, DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg), - TP_ARGS(order, gfp_flags), + TP_ARGS(gfp_flags, order, memcg), TP_STRUCT__entry( - __field( int, order ) __field( unsigned long, gfp_flags ) + __field( u64, memcg_id ) + __field( int, order ) ), TP_fast_assign( - __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; + __entry->order = order; + __entry->memcg_id = mem_cgroup_id(memcg); ), - TP_printk("order=%d gfp_flags=%s", + TP_printk("order=%d gfp_flags=%s memcg_id=%llu", __entry->order, - show_gfp_flags(__entry->gfp_flags)) + show_gfp_flags(__entry->gfp_flags), + __entry->memcg_id) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg), - TP_ARGS(order, gfp_flags) + TP_ARGS(gfp_flags, order, memcg) ); #ifdef CONFIG_MEMCG DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg), - TP_ARGS(order, gfp_flags) + TP_ARGS(gfp_flags, order, memcg) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg), - TP_ARGS(order, gfp_flags) + TP_ARGS(gfp_flags, order, memcg) ); #endif /* CONFIG_MEMCG */ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg), - TP_ARGS(nr_reclaimed), + TP_ARGS(nr_reclaimed, memcg), TP_STRUCT__entry( __field( unsigned long, nr_reclaimed ) + __field( u64, memcg_id ) ), TP_fast_assign( __entry->nr_reclaimed = nr_reclaimed; + __entry->memcg_id = mem_cgroup_id(memcg); ), - TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed) + TP_printk("nr_reclaimed=%lu memcg_id=%llu", + __entry->nr_reclaimed, + __entry->memcg_id) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg), - TP_ARGS(nr_reclaimed) + TP_ARGS(nr_reclaimed, memcg) ); #ifdef CONFIG_MEMCG DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg), - TP_ARGS(nr_reclaimed) + TP_ARGS(nr_reclaimed, memcg) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg), - TP_ARGS(nr_reclaimed) + TP_ARGS(nr_reclaimed, memcg) ); #endif /* CONFIG_MEMCG */ @@ -200,39 +207,42 @@ TRACE_EVENT(mm_shrink_slab_start, TP_PROTO(struct shrinker *shr, struct shrink_control *sc, long nr_objects_to_shrink, unsigned long cache_items, unsigned long long delta, unsigned long total_scan, - int priority), + int priority, struct mem_cgroup *memcg), TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan, - priority), + priority, memcg), TP_STRUCT__entry( __field(struct shrinker *, shr) __field(void *, shrink) - __field(int, nid) __field(long, nr_objects_to_shrink) __field(unsigned long, gfp_flags) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) __field(int, priority) + __field(int, nid) + __field(u64, memcg_id) ), TP_fast_assign( __entry->shr = shr; __entry->shrink = shr->scan_objects; - __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; __entry->gfp_flags = (__force unsigned long)sc->gfp_mask; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; __entry->priority = priority; + __entry->nid = sc->nid; + __entry->memcg_id = mem_cgroup_id(memcg); ), - TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d", + TP_printk("%pS %p: nid: %d memcg_id: %llu objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d", __entry->shrink, __entry->shr, __entry->nid, + __entry->memcg_id, __entry->nr_objects_to_shrink, show_gfp_flags(__entry->gfp_flags), __entry->cache_items, @@ -243,35 +253,38 @@ TRACE_EVENT(mm_shrink_slab_start, TRACE_EVENT(mm_shrink_slab_end, TP_PROTO(struct shrinker *shr, int nid, int shrinker_retval, - long unused_scan_cnt, long new_scan_cnt, long total_scan), + long unused_scan_cnt, long new_scan_cnt, long total_scan, struct mem_cgroup *memcg), TP_ARGS(shr, nid, shrinker_retval, unused_scan_cnt, new_scan_cnt, - total_scan), + total_scan, memcg), TP_STRUCT__entry( __field(struct shrinker *, shr) - __field(int, nid) __field(void *, shrink) __field(long, unused_scan) __field(long, new_scan) - __field(int, retval) __field(long, total_scan) + __field(int, nid) + __field(int, retval) + __field(u64, memcg_id) ), TP_fast_assign( __entry->shr = shr; - __entry->nid = nid; __entry->shrink = shr->scan_objects; __entry->unused_scan = unused_scan_cnt; __entry->new_scan = new_scan_cnt; - __entry->retval = shrinker_retval; __entry->total_scan = total_scan; + __entry->nid = nid; + __entry->retval = shrinker_retval; + __entry->memcg_id = mem_cgroup_id(memcg); ), - TP_printk("%pS %p: nid: %d unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d", + TP_printk("%pS %p: nid: %d memcg_id: %llu unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d", __entry->shrink, __entry->shr, __entry->nid, + __entry->memcg_id, __entry->unused_scan, __entry->new_scan, __entry->total_scan, @@ -504,9 +517,9 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin, DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg), - TP_ARGS(nr_reclaimed) + TP_ARGS(nr_reclaimed, memcg) ); TRACE_EVENT(mm_vmscan_throttled, diff --git a/mm/shrinker.c b/mm/shrinker.c index 4a93fd433689a..ddf784f996a59 100644 --- a/mm/shrinker.c +++ b/mm/shrinker.c @@ -410,7 +410,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, - freeable, delta, total_scan, priority); + freeable, delta, total_scan, priority, + shrinkctl->memcg); /* * Normally, we should not scan less than batch_size objects in one @@ -461,7 +462,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, */ new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); - trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); + trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan, + shrinkctl->memcg); return freed; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 614ccf39fe3fa..9d512fb354fcd 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -6603,11 +6603,11 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, return 1; set_task_reclaim_state(current, &sc.reclaim_state); - trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); + trace_mm_vmscan_direct_reclaim_begin(sc.gfp_mask, order, 0); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); - trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); + trace_mm_vmscan_direct_reclaim_end(nr_reclaimed, 0); set_task_reclaim_state(current, NULL); return nr_reclaimed; @@ -6636,8 +6636,9 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); - trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, - sc.gfp_mask); + trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.gfp_mask, + sc.order, + memcg); /* * NOTE: Although we can get the priority field, using it @@ -6648,7 +6649,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, */ shrink_lruvec(lruvec, &sc); - trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); + trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed, memcg); *nr_scanned = sc.nr_scanned; @@ -6684,13 +6685,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); - trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); + trace_mm_vmscan_memcg_reclaim_begin(sc.gfp_mask, 0, memcg); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); - trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); + trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed, memcg); set_task_reclaim_state(current, NULL); return nr_reclaimed; @@ -7642,7 +7643,7 @@ static unsigned long __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, delayacct_freepages_end(); psi_memstall_leave(&pflags); - trace_mm_vmscan_node_reclaim_end(sc->nr_reclaimed); + trace_mm_vmscan_node_reclaim_end(sc->nr_reclaimed, 0); return sc->nr_reclaimed; } -- 2.33.8