From: Ridong Chen <ridong.chen@linux.dev>
To: Steven Rostedt <rostedt@goodmis.org>,
Masami Hiramatsu <mhiramat@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Michal Hocko <mhocko@kernel.org>,
Roman Gushchin <roman.gushchin@linux.dev>,
Shakeel Butt <shakeel.butt@linux.dev>,
Dave Chinner <david@fromorbit.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Muchun Song <muchun.song@linux.dev>,
Qi Zheng <qi.zheng@linux.dev>, Kairui Song <kasong@tencent.com>,
Barry Song <baohua@kernel.org>,
Axel Rasmussen <axelrasmussen@google.com>,
Yuanchu Xie <yuanchu@google.com>, Wei Xu <weixugc@google.com>,
Baoquan He <baoquan.he@linux.dev>,
Baolin Wang <baolin.wang@linux.alibaba.com>,
David Hildenbrand <david@kernel.org>,
Lorenzo Stoakes <ljs@kernel.org>,
linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
linux-mm@kvack.org,
cgroups@vger.kernel.org (open list:CONTROL GROUP - MEMORY
RESOURCE CONTROLLER (MEMCG)),
bpf@vger.kernel.org (open list:BPF
[MISC]:Keyword:(?:\b|_)bpf(?:\b|_)),
Ridong Chen <ridong.chen@linux.dev>,
Ridong Chen <chenridong@xiaomi.com>
Subject: [PATCH v5 4/6] mm/vmscan: pass scan_control to the vmscan tracepoints
Date: Sat, 31 Oct 2026 17:00:39 +0800 [thread overview]
Message-ID: <20261031090041.58574-5-ridong.chen@linux.dev> (raw)
In-Reply-To: <20261031090041.58574-1-ridong.chen@linux.dev>
From: Ridong Chen <chenridong@xiaomi.com>
Several vmscan tracepoints spell out reclaim state as individual
arguments, all of which the caller already holds in struct scan_control.
Now that the struct is visible from the trace header, pass sc directly
and pick the fields out in TP_fast_assign instead of spelling them out
at every callsite:
- mm_vmscan_direct_reclaim_begin, mm_vmscan_memcg_reclaim_begin and
mm_vmscan_node_reclaim_begin: gfp_mask and order.
- mm_vmscan_lru_isolate, mm_vmscan_lru_shrink_inactive and
mm_vmscan_lru_shrink_active: reclaim_idx, order and priority.
- mm_vmscan_reclaim_pages: nr_scanned. nr_reclaimed stays a separate
argument: it is the return value of shrink_folio_list(), which does
not update sc->nr_reclaimed.
- mm_vmscan_balance_pgdat_end: order and nr_reclaimed. highest_zoneidx
stays a separate argument: it is a balance_pgdat() parameter, and
sc.reclaim_idx may differ from it by the time the end event fires.
No functional change. The tracefs event format (TP_STRUCT__entry and
TP_printk) is unchanged, so tracefs-based consumers are unaffected.
BPF programs attached via raw_tp/tp_btf see the new TP_PROTO and need
to be adjusted; tracepoints are not a stable ABI (see
Documentation/bpf/bpf_design_QA.rst).
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
mm/trace_vmscan.h | 74 +++++++++++++++++++++++------------------------
mm/vmscan.c | 26 ++++++++---------
2 files changed, 48 insertions(+), 52 deletions(-)
diff --git a/mm/trace_vmscan.h b/mm/trace_vmscan.h
index 3917e1b62dfa..b2ad83e5f25e 100644
--- a/mm/trace_vmscan.h
+++ b/mm/trace_vmscan.h
@@ -124,10 +124,9 @@ TRACE_EVENT(mm_vmscan_balance_pgdat_begin,
TRACE_EVENT(mm_vmscan_balance_pgdat_end,
- TP_PROTO(int nid, int order, int highest_zoneidx,
- unsigned long nr_reclaimed),
+ TP_PROTO(int nid, struct scan_control *sc, int highest_zoneidx),
- TP_ARGS(nid, order, highest_zoneidx, nr_reclaimed),
+ TP_ARGS(nid, sc, highest_zoneidx),
TP_STRUCT__entry(
__field(int, nid)
@@ -138,9 +137,9 @@ TRACE_EVENT(mm_vmscan_balance_pgdat_end,
TP_fast_assign(
__entry->nid = nid;
- __entry->order = order;
+ __entry->order = sc->order;
__entry->highest_zoneidx = highest_zoneidx;
- __entry->nr_reclaimed = nr_reclaimed;
+ __entry->nr_reclaimed = sc->nr_reclaimed;
),
TP_printk("nid=%d order=%d highest_zoneidx=%-8s nr_reclaimed=%lu",
@@ -178,9 +177,9 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
- TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
+ TP_PROTO(struct scan_control *sc, struct mem_cgroup *memcg),
- TP_ARGS(gfp_flags, order, memcg),
+ TP_ARGS(sc, memcg),
TP_STRUCT__entry(
__field( unsigned long, gfp_flags )
@@ -189,8 +188,8 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
),
TP_fast_assign(
- __entry->gfp_flags = (__force unsigned long)gfp_flags;
- __entry->order = order;
+ __entry->gfp_flags = (__force unsigned long)sc->gfp_mask;
+ __entry->order = sc->order;
__entry->memcg_id = mem_cgroup_id(memcg);
),
@@ -204,17 +203,17 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
- TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
+ TP_PROTO(struct scan_control *sc, struct mem_cgroup *memcg),
- TP_ARGS(gfp_flags, order, memcg)
+ TP_ARGS(sc, memcg)
);
#ifdef CONFIG_MEMCG
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
- TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
+ TP_PROTO(struct scan_control *sc, struct mem_cgroup *memcg),
- TP_ARGS(gfp_flags, order, memcg)
+ TP_ARGS(sc, memcg)
);
#endif /* CONFIG_MEMCG */
@@ -350,15 +349,14 @@ TRACE_EVENT(mm_shrink_slab_end,
);
TRACE_EVENT(mm_vmscan_lru_isolate,
- TP_PROTO(int highest_zoneidx,
- int order,
- unsigned long nr_requested,
- unsigned long nr_scanned,
- unsigned long nr_skipped,
- unsigned long nr_taken,
- int lru),
+ TP_PROTO(struct scan_control *sc,
+ unsigned long nr_requested,
+ unsigned long nr_scanned,
+ unsigned long nr_skipped,
+ unsigned long nr_taken,
+ int lru),
- TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, lru),
+ TP_ARGS(sc, nr_requested, nr_scanned, nr_skipped, nr_taken, lru),
TP_STRUCT__entry(
__field(int, highest_zoneidx)
@@ -371,8 +369,8 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
),
TP_fast_assign(
- __entry->highest_zoneidx = highest_zoneidx;
- __entry->order = order;
+ __entry->highest_zoneidx = sc->reclaim_idx;
+ __entry->order = sc->order;
__entry->nr_requested = nr_requested;
__entry->nr_scanned = nr_scanned;
__entry->nr_skipped = nr_skipped;
@@ -419,11 +417,11 @@ TRACE_EVENT(mm_vmscan_write_folio,
TRACE_EVENT(mm_vmscan_reclaim_pages,
- TP_PROTO(int nid,
- unsigned long nr_scanned, unsigned long nr_reclaimed,
- struct reclaim_stat *stat),
+ TP_PROTO(int nid, struct scan_control *sc,
+ unsigned long nr_reclaimed,
+ struct reclaim_stat *stat),
- TP_ARGS(nid, nr_scanned, nr_reclaimed, stat),
+ TP_ARGS(nid, sc, nr_reclaimed, stat),
TP_STRUCT__entry(
__field(int, nid)
@@ -441,7 +439,7 @@ TRACE_EVENT(mm_vmscan_reclaim_pages,
TP_fast_assign(
__entry->nid = nid;
- __entry->nr_scanned = nr_scanned;
+ __entry->nr_scanned = sc->nr_scanned;
__entry->nr_reclaimed = nr_reclaimed;
__entry->nr_dirty = stat->nr_dirty;
__entry->nr_writeback = stat->nr_writeback;
@@ -466,9 +464,9 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
TP_PROTO(int nid,
unsigned long nr_scanned, unsigned long nr_reclaimed,
- struct reclaim_stat *stat, int priority, int file),
+ struct reclaim_stat *stat, struct scan_control *sc, int file),
- TP_ARGS(nid, nr_scanned, nr_reclaimed, stat, priority, file),
+ TP_ARGS(nid, nr_scanned, nr_reclaimed, stat, sc, file),
TP_STRUCT__entry(
__field(int, nid)
@@ -498,7 +496,7 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
__entry->nr_activate1 = stat->nr_activate[1];
__entry->nr_ref_keep = stat->nr_ref_keep;
__entry->nr_unmap_fail = stat->nr_unmap_fail;
- __entry->priority = priority;
+ __entry->priority = sc->priority;
__entry->reclaim_flags = trace_reclaim_flags(file);
),
@@ -517,9 +515,9 @@ TRACE_EVENT(mm_vmscan_lru_shrink_active,
TP_PROTO(int nid, unsigned long nr_taken,
unsigned long nr_active, unsigned long nr_deactivated,
- unsigned long nr_referenced, int priority, int file),
+ unsigned long nr_referenced, struct scan_control *sc, int file),
- TP_ARGS(nid, nr_taken, nr_active, nr_deactivated, nr_referenced, priority, file),
+ TP_ARGS(nid, nr_taken, nr_active, nr_deactivated, nr_referenced, sc, file),
TP_STRUCT__entry(
__field(int, nid)
@@ -537,7 +535,7 @@ TRACE_EVENT(mm_vmscan_lru_shrink_active,
__entry->nr_active = nr_active;
__entry->nr_deactivated = nr_deactivated;
__entry->nr_referenced = nr_referenced;
- __entry->priority = priority;
+ __entry->priority = sc->priority;
__entry->reclaim_flags = trace_reclaim_flags(file);
),
@@ -551,9 +549,9 @@ TRACE_EVENT(mm_vmscan_lru_shrink_active,
TRACE_EVENT(mm_vmscan_node_reclaim_begin,
- TP_PROTO(int nid, int order, gfp_t gfp_flags),
+ TP_PROTO(int nid, struct scan_control *sc),
- TP_ARGS(nid, order, gfp_flags),
+ TP_ARGS(nid, sc),
TP_STRUCT__entry(
__field(int, nid)
@@ -563,8 +561,8 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin,
TP_fast_assign(
__entry->nid = nid;
- __entry->order = order;
- __entry->gfp_flags = (__force unsigned long)gfp_flags;
+ __entry->order = sc->order;
+ __entry->gfp_flags = (__force unsigned long)sc->gfp_mask;
),
TP_printk("nid=%d order=%d gfp_flags=%s",
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 49677464fc9a..15e9184a580a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1764,7 +1764,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
}
}
*nr_scanned = total_scan;
- trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
+ trace_mm_vmscan_lru_isolate(sc, nr_to_scan,
total_scan, skipped, nr_taken, lru);
update_lru_sizes(lruvec, lru, nr_zone_taken);
return nr_taken;
@@ -2053,7 +2053,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
handle_reclaim_writeback(nr_taken, pgdat, sc, &stat);
trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
- nr_scanned, nr_reclaimed, &stat, sc->priority, file);
+ nr_scanned, nr_reclaimed, &stat, sc, file);
return nr_reclaimed;
}
@@ -2160,7 +2160,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
mod_lruvec_state(lruvec, PGROTATE_ANON + file, nr_rotated);
trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
- nr_deactivate, nr_rotated, sc->priority, file);
+ nr_deactivate, nr_rotated, sc, file);
}
static unsigned int reclaim_folio_list(struct list_head *folio_list,
@@ -2183,7 +2183,7 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
list_del(&folio->lru);
folio_putback_lru(folio);
}
- trace_mm_vmscan_reclaim_pages(pgdat->node_id, sc.nr_scanned, nr_reclaimed, &stat);
+ trace_mm_vmscan_reclaim_pages(pgdat->node_id, &sc, nr_reclaimed, &stat);
return nr_reclaimed;
}
@@ -4849,9 +4849,9 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
mod_lruvec_state(lruvec, item, isolated);
mod_lruvec_state(lruvec, PGREFILL, sorted);
mod_lruvec_state(lruvec, PGSCAN_ANON + type, isolated);
- trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
- scanned, skipped, isolated,
- type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
+ trace_mm_vmscan_lru_isolate(sc, nr_to_scan,
+ scanned, skipped, isolated,
+ type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
*isolatedp = isolated;
return scanned;
@@ -4993,7 +4993,7 @@ static int evict_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
if (isolated)
handle_reclaim_writeback(isolated, pgdat, sc, &stat);
trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
- type_scanned, reclaimed, &stat, sc->priority,
+ type_scanned, reclaimed, &stat, sc,
type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
list_for_each_entry_safe_reverse(folio, next, &list, lru) {
@@ -6889,7 +6889,7 @@ 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(sc.gfp_mask, order, NULL);
+ trace_mm_vmscan_direct_reclaim_begin(&sc, NULL);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
@@ -6930,7 +6930,7 @@ 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(sc.gfp_mask, 0, memcg);
+ trace_mm_vmscan_memcg_reclaim_begin(&sc, memcg);
noreclaim_flag = memalloc_noreclaim_save();
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
@@ -7407,8 +7407,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
psi_memstall_leave(&pflags);
set_task_reclaim_state(current, NULL);
- trace_mm_vmscan_balance_pgdat_end(pgdat->node_id, sc.order,
- highest_zoneidx, sc.nr_reclaimed);
+ trace_mm_vmscan_balance_pgdat_end(pgdat->node_id, &sc, highest_zoneidx);
/*
* Return the order kswapd stopped reclaiming at as
@@ -7886,8 +7885,7 @@ static unsigned long __node_reclaim(struct pglist_data *pgdat,
unsigned int noreclaim_flag;
unsigned long pflags;
- trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, sc->order,
- sc->gfp_mask);
+ trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, sc);
cond_resched();
if (!sc->proactive)
--
2.43.0
next prev parent reply other threads:[~2026-10-31 9:01 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-31 9:00 [PATCH v5 0/6] mm/vmscan: move tracepoints to mm/ and add MGLRU tracepoints Ridong Chen
2026-10-31 9:00 ` [PATCH v5 1/6] mm/memcontrol: drop unused vmscan tracepoint include Ridong Chen
2026-10-31 9:00 ` [PATCH v5 2/6] mm/vmscan: move vmscan tracepoints to a local header Ridong Chen
2026-10-31 9:27 ` Muchun Song
2026-10-31 9:00 ` [PATCH v5 3/6] mm/vmscan: move struct scan_control to a dedicated header Ridong Chen
2026-10-31 9:29 ` Muchun Song
2026-10-31 9:00 ` Ridong Chen [this message]
2026-10-31 10:12 ` [PATCH v5 4/6] mm/vmscan: pass scan_control to the vmscan tracepoints Muchun Song
2026-10-31 9:00 ` [PATCH v5 5/6] mm/mglru: add tracepoint for scan_folios() Ridong Chen
2026-10-31 9:00 ` [PATCH v5 6/6] mm/mglru: add tracepoint for inc_max_seq() Ridong Chen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261031090041.58574-5-ridong.chen@linux.dev \
--to=ridong.chen@linux.dev \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=baoquan.he@linux.dev \
--cc=bpf@vger.kernel.org \
--cc=cgroups@vger.kernel.org \
--cc=chenridong@xiaomi.com \
--cc=david@fromorbit.com \
--cc=david@kernel.org \
--cc=hannes@cmpxchg.org \
--cc=kasong@tencent.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=ljs@kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=mhocko@kernel.org \
--cc=muchun.song@linux.dev \
--cc=qi.zheng@linux.dev \
--cc=roman.gushchin@linux.dev \
--cc=rostedt@goodmis.org \
--cc=shakeel.butt@linux.dev \
--cc=weixugc@google.com \
--cc=yuanchu@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®