From 804c26b961da295bd70c86a3c9dc4bea0b09de88 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 16 Dec 2025 00:01:25 -0800 Subject: mm/damon/core: add trace point for damos stat per apply interval DAMON users can read DAMOS stats via DAMON sysfs interface. It enables efficient, simple and flexible usages of the stats. Especially for systems not having advanced tools like perf or bpftrace, that can be useful. But if the advanced tools are available, exposing the stats via tracepoint can reduce unnecessary reimplementation of the wheels. Add a new tracepoint for DAMOS stats, namely damos_stat_after_apply_interval. The tracepoint is triggered for each scheme's apply interval and exposes the whole stat values. If the user needs sub-apply interval information for any chance, damos_before_apply tracepoint could be used. Link: https://lkml.kernel.org/r/20251216080128.42991-13-sj@kernel.org Signed-off-by: SeongJae Park Reviewed-by: Steven Rostedt (Google) Cc: Jonathan Corbet Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: "Masami Hiramatsu (Google)" Cc: Mathieu Desnoyers Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/trace/events/damon.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/damon.h b/include/trace/events/damon.h index 852d725afea2..24fc402ab3c8 100644 --- a/include/trace/events/damon.h +++ b/include/trace/events/damon.h @@ -9,6 +9,47 @@ #include #include +TRACE_EVENT(damos_stat_after_apply_interval, + + TP_PROTO(unsigned int context_idx, unsigned int scheme_idx, + struct damos_stat *stat), + + TP_ARGS(context_idx, scheme_idx, stat), + + TP_STRUCT__entry( + __field(unsigned int, context_idx) + __field(unsigned int, scheme_idx) + __field(unsigned long, nr_tried) + __field(unsigned long, sz_tried) + __field(unsigned long, nr_applied) + __field(unsigned long, sz_applied) + __field(unsigned long, sz_ops_filter_passed) + __field(unsigned long, qt_exceeds) + __field(unsigned long, nr_snapshots) + ), + + TP_fast_assign( + __entry->context_idx = context_idx; + __entry->scheme_idx = scheme_idx; + __entry->nr_tried = stat->nr_tried; + __entry->sz_tried = stat->sz_tried; + __entry->nr_applied = stat->nr_applied; + __entry->sz_applied = stat->sz_applied; + __entry->sz_ops_filter_passed = stat->sz_ops_filter_passed; + __entry->qt_exceeds = stat->qt_exceeds; + __entry->nr_snapshots = stat->nr_snapshots; + ), + + TP_printk("ctx_idx=%u scheme_idx=%u nr_tried=%lu sz_tried=%lu " + "nr_applied=%lu sz_tried=%lu sz_ops_filter_passed=%lu " + "qt_exceeds=%lu nr_snapshots=%lu", + __entry->context_idx, __entry->scheme_idx, + __entry->nr_tried, __entry->sz_tried, + __entry->nr_applied, __entry->sz_applied, + __entry->sz_ops_filter_passed, __entry->qt_exceeds, + __entry->nr_snapshots) +); + TRACE_EVENT(damos_esz, TP_PROTO(unsigned int context_idx, unsigned int scheme_idx, -- cgit v1.2.3 From 64dd89ae01f2708a508e028c28b7906e4702a9a7 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 15 Dec 2025 12:57:53 -0500 Subject: mm/block/fs: remove laptop_mode Laptop mode was introduced to save battery, by delaying and consolidating writes and thereby maximize the time rotating hard drives wouldn't have to spin. Luckily, rotating hard drives, with their high spin-up times and power draw, are a thing of the past for battery-powered devices. Reclaim has also since changed to not write single filesystem pages anymore, and regular filesystem writeback is lumpy by design. The juice doesn't appear worth the squeeze anymore. The footprint of the feature is small, but nevertheless it's a complicating factor in mm, block, filesystems. Developers don't think about it, and it likely hasn't been tested with new reclaim and writeback changes in years. Let's sunset it. Keep the sysctl with a deprecation warning around for a few more cycles, but remove all functionality behind it. [akpm@linux-foundation.org: fix Documentation/admin-guide/laptops/index.rst] Link: https://lkml.kernel.org/r/20251216185201.GH905277@cmpxchg.org Signed-off-by: Johannes Weiner Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Acked-by: Jens Axboe Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Deepanshu Kartikey Signed-off-by: Andrew Morton --- include/trace/events/writeback.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 311a341e6fe4..b6f94e97788a 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -42,7 +42,6 @@ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ - EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EM( WB_REASON_FORKER_THREAD, "forker_thread") \ EMe(WB_REASON_FOREIGN_FLUSH, "foreign_flush") -- cgit v1.2.3 From 5173ae0a068d64643ccf4915b7cbedf82810a592 Mon Sep 17 00:00:00 2001 From: Shivank Garg Date: Sun, 18 Jan 2026 19:09:40 +0000 Subject: mm/khugepaged: map dirty/writeback pages failures to EAGAIN Patch series "mm/khugepaged: fix dirty page handling for MADV_COLLAPSE", v5. MADV_COLLAPSE on file-backed mappings fails with -EINVAL when TEXT pages are dirty. This affects scenarios like package/container updates or executing binaries immediately after writing them, etc. The issue is that collapse_file() triggers async writeback and returns SCAN_FAIL (maps to -EINVAL), expecting khugepaged to revisit later. But MADV_COLLAPSE is synchronous and userspace expects immediate success or a clear retry signal. Reproduction: - Compile or copy 2MB-aligned executable to XFS/ext4 FS - Call MADV_COLLAPSE on .text section - First call fails with -EINVAL (text pages dirty from copy) - Second call succeeds (async writeback completed) Issue Report: https://lore.kernel.org/all/4e26fe5e-7374-467c-a333-9dd48f85d7cc@amd.com This patch (of 2): When collapse_file encounters dirty or writeback pages in file-backed mappings, it currently returns SCAN_FAIL which maps to -EINVAL. This is misleading as EINVAL suggests invalid arguments, whereas dirty/writeback pages represent transient conditions that may resolve on retry. Introduce SCAN_PAGE_DIRTY_OR_WRITEBACK to cover both dirty and writeback states, mapping it to -EAGAIN. For MADV_COLLAPSE, this provides userspace with a clear signal that retry may succeed after writeback completes. For khugepaged, this is harmless as it will naturally revisit the range during periodic scans after async writeback completes. Link: https://lkml.kernel.org/r/20260118190939.8986-2-shivankg@amd.com Link: https://lkml.kernel.org/r/20260118190939.8986-4-shivankg@amd.com Fixes: 34488399fa08 ("mm/madvise: add file and shmem support to MADV_COLLAPSE") Signed-off-by: Shivank Garg Reported-by: Branden Moore Closes: https://lore.kernel.org/all/4e26fe5e-7374-467c-a333-9dd48f85d7cc@amd.com Reviewed-by: Dev Jain Reviewed-by: Lance Yang Reviewed-by: Baolin Wang Reviewed-by: wang lian Acked-by: David Hildenbrand (Red Hat) Cc: Barry Song Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Nico Pache Cc: Ryan Roberts Cc: Zach O'Keefe Cc: Zi Yan Signed-off-by: Andrew Morton --- include/trace/events/huge_memory.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 4cde53b45a85..4e41bff31888 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -37,7 +37,8 @@ EM( SCAN_PAGE_HAS_PRIVATE, "page_has_private") \ EM( SCAN_STORE_FAILED, "store_failed") \ EM( SCAN_COPY_MC, "copy_poisoned_page") \ - EMe(SCAN_PAGE_FILLED, "page_filled") + EM( SCAN_PAGE_FILLED, "page_filled") \ + EMe(SCAN_PAGE_DIRTY_OR_WRITEBACK, "page_dirty_or_writeback") #undef EM #undef EMe -- cgit v1.2.3 From a45088376d8a847a5e3b1982fcfceb41644e3b1d Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 20 Jan 2026 10:43:49 +0800 Subject: mm/vmscan: add tracepoint and reason for kswapd_failures reset Currently, kswapd_failures is reset in multiple places (kswapd, direct reclaim, PCP freeing, memory-tiers), but there's no way to trace when and why it was reset, making it difficult to debug memory reclaim issues. This patch: 1. Introduce kswapd_clear_hopeless() as a wrapper function to centralize kswapd_failures reset logic. 2. Introduce kswapd_test_hopeless() to encapsulate hopeless node checks, replacing all open-coded kswapd_failures comparisons. 3. Add kswapd_clear_hopeless_reason enum to distinguish reset sources: - KSWAPD_CLEAR_HOPELESS_KSWAPD: reset from kswapd context - KSWAPD_CLEAR_HOPELESS_DIRECT: reset from direct reclaim - KSWAPD_CLEAR_HOPELESS_PCP: reset from PCP page freeing - KSWAPD_CLEAR_HOPELESS_OTHER: reset from other paths 4. Add tracepoints for better observability: - mm_vmscan_kswapd_clear_hopeless: traces each reset with reason - mm_vmscan_kswapd_reclaim_fail: traces each kswapd reclaim failure Test results: $ trace-cmd record -e vmscan:mm_vmscan_kswapd_clear_hopeless -e vmscan:mm_vmscan_kswapd_reclaim_fail $ # generate memory pressure $ trace-cmd report cpus=4 kswapd0-71 [000] 27.216563: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=1 kswapd0-71 [000] 27.217169: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=2 kswapd0-71 [000] 27.217764: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=3 kswapd0-71 [000] 27.218353: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=4 kswapd0-71 [000] 27.218993: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=5 kswapd0-71 [000] 27.219744: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=6 kswapd0-71 [000] 27.220488: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=7 kswapd0-71 [000] 27.221206: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=8 kswapd0-71 [000] 27.221806: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=9 kswapd0-71 [000] 27.222634: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=10 kswapd0-71 [000] 27.223286: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=11 kswapd0-71 [000] 27.223894: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=12 kswapd0-71 [000] 27.224712: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=13 kswapd0-71 [000] 27.225424: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=14 kswapd0-71 [000] 27.226082: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=15 kswapd0-71 [000] 27.226810: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=16 kswapd1-72 [002] 27.386869: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=1 kswapd1-72 [002] 27.387435: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=2 kswapd1-72 [002] 27.388016: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=3 kswapd1-72 [002] 27.388586: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=4 kswapd1-72 [002] 27.389155: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=5 kswapd1-72 [002] 27.389723: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=6 kswapd1-72 [002] 27.390292: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=7 kswapd1-72 [002] 27.392364: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=8 kswapd1-72 [002] 27.392934: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=9 kswapd1-72 [002] 27.393504: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=10 kswapd1-72 [002] 27.394073: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=11 kswapd1-72 [002] 27.394899: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=12 kswapd1-72 [002] 27.395472: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=13 kswapd1-72 [002] 27.396055: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=14 kswapd1-72 [002] 27.396628: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=15 kswapd1-72 [002] 27.397199: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=16 kworker/u18:0-40 [002] 27.410151: mm_vmscan_kswapd_clear_hopeless: nid=0 reason=DIRECT kswapd0-71 [000] 27.439454: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=1 kswapd0-71 [000] 27.440048: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=2 kswapd0-71 [000] 27.440634: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=3 kswapd0-71 [000] 27.441211: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=4 kswapd0-71 [000] 27.441787: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=5 kswapd0-71 [000] 27.442363: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=6 kswapd0-71 [000] 27.443030: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=7 kswapd0-71 [000] 27.443725: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=8 kswapd0-71 [000] 27.444315: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=9 kswapd0-71 [000] 27.444898: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=10 kswapd0-71 [000] 27.445476: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=11 kswapd0-71 [000] 27.446053: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=12 kswapd0-71 [000] 27.446646: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=13 kswapd0-71 [000] 27.447230: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=14 kswapd0-71 [000] 27.447812: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=15 kswapd0-71 [000] 27.448391: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=16 ann-423 [003] 28.028285: mm_vmscan_kswapd_clear_hopeless: nid=0 reason=PCP Link: https://lkml.kernel.org/r/20260120024402.387576-3-jiayuan.chen@linux.dev Signed-off-by: Jiayuan Chen Signed-off-by: Jiayuan Chen Acked-by: Shakeel Butt Suggested-by: Johannes Weiner Reviewed-by: Steven Rostedt (Google) [tracing] Cc: Axel Rasmussen Cc: Brendan Jackman Cc: David Hildenbrand Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: "Masami Hiramatsu (Google)" Cc: Mathieu Desnoyers Cc: Michal Hocko Cc: Mike Rapoport Cc: Qi Zheng Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Wei Xu Cc: Yuanchu Xie Cc: Zi Yan Signed-off-by: Andrew Morton --- include/trace/events/vmscan.h | 51 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 490958fa10de..ea58e4656abf 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -40,6 +40,16 @@ {_VMSCAN_THROTTLE_CONGESTED, "VMSCAN_THROTTLE_CONGESTED"} \ ) : "VMSCAN_THROTTLE_NONE" +TRACE_DEFINE_ENUM(KSWAPD_CLEAR_HOPELESS_OTHER); +TRACE_DEFINE_ENUM(KSWAPD_CLEAR_HOPELESS_KSWAPD); +TRACE_DEFINE_ENUM(KSWAPD_CLEAR_HOPELESS_DIRECT); +TRACE_DEFINE_ENUM(KSWAPD_CLEAR_HOPELESS_PCP); + +#define kswapd_clear_hopeless_reason_ops \ + {KSWAPD_CLEAR_HOPELESS_KSWAPD, "KSWAPD"}, \ + {KSWAPD_CLEAR_HOPELESS_DIRECT, "DIRECT"}, \ + {KSWAPD_CLEAR_HOPELESS_PCP, "PCP"}, \ + {KSWAPD_CLEAR_HOPELESS_OTHER, "OTHER"} #define trace_reclaim_flags(file) ( \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ @@ -535,6 +545,47 @@ TRACE_EVENT(mm_vmscan_throttled, __entry->usec_delayed, show_throttle_flags(__entry->reason)) ); + +TRACE_EVENT(mm_vmscan_kswapd_reclaim_fail, + + TP_PROTO(int nid, int failures), + + TP_ARGS(nid, failures), + + TP_STRUCT__entry( + __field(int, nid) + __field(int, failures) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->failures = failures; + ), + + TP_printk("nid=%d failures=%d", + __entry->nid, __entry->failures) +); + +TRACE_EVENT(mm_vmscan_kswapd_clear_hopeless, + + TP_PROTO(int nid, int reason), + + TP_ARGS(nid, reason), + + TP_STRUCT__entry( + __field(int, nid) + __field(int, reason) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->reason = reason; + ), + + TP_printk("nid=%d reason=%s", + __entry->nid, + __print_symbolic(__entry->reason, kswapd_clear_hopeless_reason_ops)) +); #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ -- cgit v1.2.3