The patch titled
Subject: mm: remove PG_reclaim
has been added to the -mm mm-unstable branch. Its filename is
mm-remove-pg_reclaim.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-remove-pg_reclaim.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Subject: mm: remove PG_reclaim
Date: Thu, 30 Jan 2025 12:00:47 +0200
Nobody sets the flag anymore.
Remove the PG_reclaim, making PG_readhead exclusive user of the page flag
bit.
Link: https://lkml.kernel.org/r/20250130100050.1868208-10-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Acked-by: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>
Cc: Chengming Zhou <chengming.zhou@xxxxxxxxx>
Cc: Christian Brauner <brauner@xxxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Cc: Dave Airlie <airlied@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: gehao <gehao@xxxxxxxxxx>
Cc: Jani Nikula <jani.nikula@xxxxxxxxxxxxxxx>
Cc: Jason A. Donenfeld <jason@xxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Jonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Cc: Josef Bacik <josef@xxxxxxxxxxxxxx>
Cc: "Masami Hiramatsu (Google)" <mhiramat@xxxxxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Mattew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Miklos Szeredi <miklos@xxxxxxxxxx>
Cc: Nhat Pham <nphamcs@xxxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Ran Xiaokai <ran.xiaokai@xxxxxxxxxx>
Cc: Rodrigo Vivi <rodrigo.vivi@xxxxxxxxx>
Cc: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
Cc: Tvrtko Ursulin <tursulin@xxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/fuse/dev.c | 2
fs/proc/page.c | 2
include/linux/mm_inline.h | 15 -----
include/linux/page-flags.h | 15 +----
include/trace/events/mmflags.h | 2
include/uapi/linux/kernel-page-flags.h | 2
mm/filemap.c | 12 ----
mm/migrate.c | 10 ---
mm/page-writeback.c | 16 ------
mm/page_io.c | 15 +----
mm/swap.c | 61 +----------------------
mm/vmscan.c | 7 --
tools/mm/page-types.c | 8 ---
13 files changed, 22 insertions(+), 145 deletions(-)
--- a/fs/fuse/dev.c~mm-remove-pg_reclaim
+++ a/fs/fuse/dev.c
@@ -827,7 +827,7 @@ static int fuse_check_folio(struct folio
1 << PG_lru |
1 << PG_active |
1 << PG_workingset |
- 1 << PG_reclaim |
+ 1 << PG_readahead |
1 << PG_waiters |
LRU_GEN_MASK | LRU_REFS_MASK))) {
dump_page(&folio->page, "fuse: trying to steal weird page");
--- a/fs/proc/page.c~mm-remove-pg_reclaim
+++ a/fs/proc/page.c
@@ -189,7 +189,7 @@ u64 stable_page_flags(const struct page
u |= kpf_copy_bit(k, KPF_LRU, PG_lru);
u |= kpf_copy_bit(k, KPF_REFERENCED, PG_referenced);
u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active);
- u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim);
+ u |= kpf_copy_bit(k, KPF_READAHEAD, PG_readahead);
#define SWAPCACHE ((1 << PG_swapbacked) | (1 << PG_swapcache))
if ((k & SWAPCACHE) == SWAPCACHE)
--- a/include/linux/mm_inline.h~mm-remove-pg_reclaim
+++ a/include/linux/mm_inline.h
@@ -270,7 +270,6 @@ static inline bool lru_gen_add_folio(str
set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags);
lru_gen_update_size(lruvec, folio, -1, gen);
- /* for folio_rotate_reclaimable() */
if (reclaiming)
list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
else
@@ -350,20 +349,6 @@ void lruvec_add_folio(struct lruvec *lru
}
static __always_inline
-void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
-{
- enum lru_list lru = folio_lru_list(folio);
-
- if (lru_gen_add_folio(lruvec, folio, true))
- return;
-
- update_lru_size(lruvec, lru, folio_zonenum(folio),
- folio_nr_pages(folio));
- /* This is not expected to be used on LRU_UNEVICTABLE */
- list_add_tail(&folio->lru, &lruvec->lists[lru]);
-}
-
-static __always_inline
void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio)
{
enum lru_list lru = folio_lru_list(folio);
--- a/include/linux/page-flags.h~mm-remove-pg_reclaim
+++ a/include/linux/page-flags.h
@@ -63,8 +63,8 @@
* might lose their PG_swapbacked flag when they simply can be dropped (e.g. as
* a result of MADV_FREE).
*
- * PG_referenced, PG_reclaim are used for page reclaim for anonymous and
- * file-backed pagecache (see mm/vmscan.c).
+ * PG_referenced is used for page reclaim for anonymous and file-backed
+ * pagecache (see mm/vmscan.c).
*
* PG_arch_1 is an architecture specific page state bit. The generic code
* guarantees that this bit is cleared for a page when it first is entered into
@@ -107,7 +107,7 @@ enum pageflags {
PG_reserved,
PG_private, /* If pagecache, has fs-private data */
PG_private_2, /* If pagecache, has fs aux data */
- PG_reclaim, /* To be reclaimed asap */
+ PG_readahead,
PG_swapbacked, /* Page is backed by RAM/swap */
PG_unevictable, /* Page is "unevictable" */
PG_dropbehind, /* drop pages on IO completion */
@@ -129,8 +129,6 @@ enum pageflags {
#endif
__NR_PAGEFLAGS,
- PG_readahead = PG_reclaim,
-
/* Anonymous memory (and shmem) */
PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */
/* Some filesystems */
@@ -168,7 +166,7 @@ enum pageflags {
PG_xen_remapped = PG_owner_priv_1,
/* non-lru isolated movable page */
- PG_isolated = PG_reclaim,
+ PG_isolated = PG_readahead,
/* Only valid for buddy pages. Used to track pages that are reported */
PG_reported = PG_uptodate,
@@ -187,7 +185,7 @@ enum pageflags {
/* At least one page in this folio has the hwpoison flag set */
PG_has_hwpoisoned = PG_active,
PG_large_rmappable = PG_workingset, /* anon or file-backed */
- PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */
+ PG_partially_mapped = PG_readahead, /* was identified to be partially mapped */
};
#define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1)
@@ -594,9 +592,6 @@ TESTPAGEFLAG(Writeback, writeback, PF_NO
TESTSCFLAG(Writeback, writeback, PF_NO_TAIL)
FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE)
-/* PG_readahead is only used for reads; PG_reclaim is only for writes */
-PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL)
- TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL)
FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE)
FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE)
--- a/include/trace/events/mmflags.h~mm-remove-pg_reclaim
+++ a/include/trace/events/mmflags.h
@@ -177,7 +177,7 @@ TRACE_DEFINE_ENUM(___GFP_LAST_BIT);
DEF_PAGEFLAG_NAME(private_2), \
DEF_PAGEFLAG_NAME(writeback), \
DEF_PAGEFLAG_NAME(head), \
- DEF_PAGEFLAG_NAME(reclaim), \
+ DEF_PAGEFLAG_NAME(readahead), \
DEF_PAGEFLAG_NAME(swapbacked), \
DEF_PAGEFLAG_NAME(unevictable), \
DEF_PAGEFLAG_NAME(dropbehind) \
--- a/include/uapi/linux/kernel-page-flags.h~mm-remove-pg_reclaim
+++ a/include/uapi/linux/kernel-page-flags.h
@@ -15,7 +15,7 @@
#define KPF_ACTIVE 6
#define KPF_SLAB 7
#define KPF_WRITEBACK 8
-#define KPF_RECLAIM 9
+#define KPF_READAHEAD 9
#define KPF_BUDDY 10
/* 11-20: new additions in 2.6.31 */
--- a/mm/filemap.c~mm-remove-pg_reclaim
+++ a/mm/filemap.c
@@ -1626,18 +1626,6 @@ void folio_end_writeback(struct folio *f
VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio);
/*
- * folio_test_clear_reclaim() could be used here but it is an
- * atomic operation and overkill in this particular case. Failing
- * to shuffle a folio marked for immediate reclaim is too mild
- * a gain to justify taking an atomic operation penalty at the
- * end of every folio writeback.
- */
- if (folio_test_reclaim(folio)) {
- folio_clear_reclaim(folio);
- folio_rotate_reclaimable(folio);
- }
-
- /*
* Writeback does not hold a folio reference of its own, relying
* on truncation to wait for the clearing of PG_writeback.
* But here we must make sure that the folio is not freed and
--- a/mm/migrate.c~mm-remove-pg_reclaim
+++ a/mm/migrate.c
@@ -690,6 +690,8 @@ void folio_migrate_flags(struct folio *n
folio_set_young(newfolio);
if (folio_test_idle(folio))
folio_set_idle(newfolio);
+ if (folio_test_readahead(folio))
+ folio_set_readahead(newfolio);
folio_migrate_refs(newfolio, folio);
/*
@@ -732,14 +734,6 @@ void folio_migrate_flags(struct folio *n
if (folio_test_writeback(newfolio))
folio_end_writeback(newfolio);
- /*
- * PG_readahead shares the same bit with PG_reclaim. The above
- * end_page_writeback() may clear PG_readahead mistakenly, so set the
- * bit after that.
- */
- if (folio_test_readahead(folio))
- folio_set_readahead(newfolio);
-
folio_copy_owner(newfolio, folio);
pgalloc_tag_swap(newfolio, folio);
--- a/mm/page_io.c~mm-remove-pg_reclaim
+++ a/mm/page_io.c
@@ -37,14 +37,11 @@ static void __end_swap_bio_write(struct
* Re-dirty the page in order to avoid it being reclaimed.
* Also print a dire warning that things will go BAD (tm)
* very quickly.
- *
- * Also clear PG_reclaim to avoid folio_rotate_reclaimable()
*/
folio_mark_dirty(folio);
pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
(unsigned long long)bio->bi_iter.bi_sector);
- folio_clear_reclaim(folio);
}
folio_end_writeback(folio);
}
@@ -350,19 +347,17 @@ static void sio_write_complete(struct ki
if (ret != sio->len) {
/*
- * In the case of swap-over-nfs, this can be a
- * temporary failure if the system has limited
- * memory for allocating transmit buffers.
- * Mark the page dirty and avoid
- * folio_rotate_reclaimable but rate-limit the
- * messages.
+ * In the case of swap-over-nfs, this can be a temporary failure
+ * if the system has limited memory for allocating transmit
+ * buffers.
+ *
+ * Mark the page dirty but rate-limit the messages.
*/
pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
ret, swap_dev_pos(page_swap_entry(page)));
for (p = 0; p < sio->pages; p++) {
page = sio->bvec[p].bv_page;
set_page_dirty(page);
- ClearPageReclaim(page);
}
}
--- a/mm/page-writeback.c~mm-remove-pg_reclaim
+++ a/mm/page-writeback.c
@@ -2888,22 +2888,8 @@ bool folio_mark_dirty(struct folio *foli
{
struct address_space *mapping = folio_mapping(folio);
- if (likely(mapping)) {
- /*
- * readahead/folio_deactivate could remain
- * PG_readahead/PG_reclaim due to race with folio_end_writeback
- * About readahead, if the folio is written, the flags would be
- * reset. So no problem.
- * About folio_deactivate, if the folio is redirtied,
- * the flag will be reset. So no problem. but if the
- * folio is used by readahead it will confuse readahead
- * and make it restart the size rampup process. But it's
- * a trivial problem.
- */
- if (folio_test_reclaim(folio))
- folio_clear_reclaim(folio);
+ if (likely(mapping))
return mapping->a_ops->dirty_folio(mapping, folio);
- }
return noop_dirty_folio(mapping, folio);
}
--- a/mm/swap.c~mm-remove-pg_reclaim
+++ a/mm/swap.c
@@ -59,14 +59,10 @@ struct cpu_fbatches {
#ifdef CONFIG_SMP
struct folio_batch lru_activate;
#endif
- /* Protecting the following batches which require disabling interrupts */
- local_lock_t lock_irq;
- struct folio_batch lru_move_tail;
};
static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = {
.lock = INIT_LOCAL_LOCK(lock),
- .lock_irq = INIT_LOCAL_LOCK(lock_irq),
};
static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp,
@@ -175,29 +171,20 @@ static void folio_batch_move_lru(struct
}
static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
- struct folio *folio, move_fn_t move_fn,
- bool on_lru, bool disable_irq)
+ struct folio *folio, move_fn_t move_fn, bool on_lru)
{
- unsigned long flags;
-
if (on_lru && !folio_test_clear_lru(folio))
return;
folio_get(folio);
- if (disable_irq)
- local_lock_irqsave(&cpu_fbatches.lock_irq, flags);
- else
- local_lock(&cpu_fbatches.lock);
+ local_lock(&cpu_fbatches.lock);
if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) ||
lru_cache_disabled())
folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn);
- if (disable_irq)
- local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags);
- else
- local_unlock(&cpu_fbatches.lock);
+ local_unlock(&cpu_fbatches.lock);
}
#define folio_batch_add_and_move(folio, op, on_lru) \
@@ -205,37 +192,9 @@ static void __folio_batch_add_and_move(s
&cpu_fbatches.op, \
folio, \
op, \
- on_lru, \
- offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq) \
+ on_lru \
)
-static void lru_move_tail(struct lruvec *lruvec, struct folio *folio)
-{
- if (folio_test_unevictable(folio))
- return;
-
- lruvec_del_folio(lruvec, folio);
- folio_clear_active(folio);
- lruvec_add_folio_tail(lruvec, folio);
- __count_vm_events(PGROTATED, folio_nr_pages(folio));
-}
-
-/*
- * Writeback is about to end against a folio which has been marked for
- * immediate reclaim. If it still appears to be reclaimable, move it
- * to the tail of the inactive list.
- *
- * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races.
- */
-void folio_rotate_reclaimable(struct folio *folio)
-{
- if (folio_test_locked(folio) || folio_test_dirty(folio) ||
- folio_test_unevictable(folio))
- return;
-
- folio_batch_add_and_move(folio, lru_move_tail, true);
-}
-
void lru_note_cost(struct lruvec *lruvec, bool file,
unsigned int nr_io, unsigned int nr_rotated)
{
@@ -578,17 +537,6 @@ void lru_add_drain_cpu(int cpu)
if (folio_batch_count(fbatch))
folio_batch_move_lru(fbatch, lru_add);
- fbatch = &fbatches->lru_move_tail;
- /* Disabling interrupts below acts as a compiler barrier. */
- if (data_race(folio_batch_count(fbatch))) {
- unsigned long flags;
-
- /* No harm done if a racing interrupt already did this */
- local_lock_irqsave(&cpu_fbatches.lock_irq, flags);
- folio_batch_move_lru(fbatch, lru_move_tail);
- local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags);
- }
-
fbatch = &fbatches->lru_deactivate;
if (folio_batch_count(fbatch))
folio_batch_move_lru(fbatch, lru_deactivate);
@@ -682,7 +630,6 @@ static bool cpu_needs_drain(unsigned int
/* Check these in order of likelihood that they're not zero */
return folio_batch_count(&fbatches->lru_add) ||
- folio_batch_count(&fbatches->lru_move_tail) ||
folio_batch_count(&fbatches->lru_deactivate) ||
folio_batch_count(&fbatches->lru_lazyfree) ||
folio_batch_count(&fbatches->lru_activate) ||
--- a/mm/vmscan.c~mm-remove-pg_reclaim
+++ a/mm/vmscan.c
@@ -3221,9 +3221,6 @@ static int folio_inc_gen(struct lruvec *
new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS);
new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF;
- /* for folio_end_writeback() */
- if (reclaiming)
- new_flags |= BIT(PG_reclaim);
} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
lru_gen_update_size(lruvec, folio, old_gen, new_gen);
@@ -4465,9 +4462,6 @@ static bool isolate_folio(struct lruvec
if (!folio_test_referenced(folio))
set_mask_bits(&folio->flags, LRU_REFS_MASK, 0);
- /* for shrink_folio_list() */
- folio_clear_reclaim(folio);
-
success = lru_gen_del_folio(lruvec, folio, true);
VM_WARN_ON_ONCE_FOLIO(!success, folio);
@@ -4664,7 +4658,6 @@ retry:
continue;
}
- /* retry folios that may have missed folio_rotate_reclaimable() */
if (!skip_retry && !folio_test_active(folio) && !folio_mapped(folio) &&
!folio_test_dirty(folio) && !folio_test_writeback(folio)) {
list_move(&folio->lru, &clean);
--- a/tools/mm/page-types.c~mm-remove-pg_reclaim
+++ a/tools/mm/page-types.c
@@ -85,7 +85,6 @@
* not part of kernel API
*/
#define KPF_ANON_EXCLUSIVE 47
-#define KPF_READAHEAD 48
#define KPF_SLUB_FROZEN 50
#define KPF_SLUB_DEBUG 51
#define KPF_FILE 61
@@ -108,7 +107,7 @@ static const char * const page_flag_name
[KPF_ACTIVE] = "A:active",
[KPF_SLAB] = "S:slab",
[KPF_WRITEBACK] = "W:writeback",
- [KPF_RECLAIM] = "I:reclaim",
+ [KPF_READAHEAD] = "I:readahead",
[KPF_BUDDY] = "B:buddy",
[KPF_MMAP] = "M:mmap",
@@ -139,7 +138,6 @@ static const char * const page_flag_name
[KPF_ARCH_2] = "H:arch_2",
[KPF_ANON_EXCLUSIVE] = "d:anon_exclusive",
- [KPF_READAHEAD] = "I:readahead",
[KPF_SLUB_FROZEN] = "A:slub_frozen",
[KPF_SLUB_DEBUG] = "E:slub_debug",
@@ -484,10 +482,6 @@ static uint64_t expand_overloaded_flags(
flags ^= BIT(ERROR) | BIT(SLUB_DEBUG);
}
- /* PG_reclaim is overloaded as PG_readahead in the read path */
- if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM))
- flags ^= BIT(RECLAIM) | BIT(READAHEAD);
-
if (pme & PM_SOFT_DIRTY)
flags |= BIT(SOFTDIRTY);
if (pme & PM_FILE)
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
mm-migrate-transfer-pg_dropbehind-to-the-new-folio.patch
drm-i915-gem-convert-__shmem_writeback-to-folios.patch
drm-i915-gem-use-pg_dropbehind-instead-of-pg_reclaim.patch
mm-zswap-use-pg_dropbehind-instead-of-pg_reclaim.patch
mm-truncate-use-folio_set_dropbehind-instead-of-deactivate_file_folio.patch
mm-vmscan-use-pg_dropbehind-instead-of-pg_reclaim.patch
mm-vmscan-use-pg_dropbehind-instead-of-pg_reclaim-in-shrink_folio_list.patch
mm-mglru-check-pg_dropbehind-instead-of-pg_reclaim-in-lru_gen_folio_seq.patch
mm-remove-pg_reclaim.patch
mm-vmscan-do-not-demote-pg_dropbehind-folios.patch
mm-rename-pg_dropbehind-to-pg_reclaim.patch
