+++ /dev/null
-From 60accdd3d3a54a9d28d0f2d39ec740df38c167fa Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 22 Mar 2022 14:45:41 -0700
-Subject: mm: __isolate_lru_page_prepare() in isolate_migratepages_block()
-
-From: Hugh Dickins <hughd@google.com>
-
-[ Upstream commit 89f6c88a6ab4a11deb14c270f7f1454cda4f73d6 ]
-
-__isolate_lru_page_prepare() conflates two unrelated functions, with the
-flags to one disjoint from the flags to the other; and hides some of the
-important checks outside of isolate_migratepages_block(), where the
-sequence is better to be visible. It comes from the days of lumpy
-reclaim, before compaction, when the combination made more sense.
-
-Move what's needed by mm/compaction.c isolate_migratepages_block() inline
-there, and what's needed by mm/vmscan.c isolate_lru_pages() inline there.
-
-Shorten "isolate_mode" to "mode", so the sequence of conditions is easier
-to read. Declare a "mapping" variable, to save one call to page_mapping()
-(but not another: calling again after page is locked is necessary).
-Simplify isolate_lru_pages() with a "move_to" list pointer.
-
-Link: https://lkml.kernel.org/r/879d62a8-91cc-d3c6-fb3b-69768236df68@google.com
-Signed-off-by: Hugh Dickins <hughd@google.com>
-Acked-by: David Rientjes <rientjes@google.com>
-Reviewed-by: Alex Shi <alexs@kernel.org>
-Cc: Alexander Duyck <alexander.duyck@gmail.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-Stable-dep-of: 829ae0f81ce0 ("mm: migrate: fix THP's mapcount on isolation")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/swap.h | 1 -
- mm/compaction.c | 51 +++++++++++++++++++---
- mm/vmscan.c | 101 ++++++++-----------------------------------
- 3 files changed, 62 insertions(+), 91 deletions(-)
-
-diff --git a/include/linux/swap.h b/include/linux/swap.h
-index 394d5de5d4b4..a502928c29c5 100644
---- a/include/linux/swap.h
-+++ b/include/linux/swap.h
-@@ -358,7 +358,6 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page,
- extern unsigned long zone_reclaimable_pages(struct zone *zone);
- extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
- gfp_t gfp_mask, nodemask_t *mask);
--extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
- extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
- unsigned long nr_pages,
- gfp_t gfp_mask,
-diff --git a/mm/compaction.c b/mm/compaction.c
-index ea46aadc7c21..57ce6b001b10 100644
---- a/mm/compaction.c
-+++ b/mm/compaction.c
-@@ -784,7 +784,7 @@ static bool too_many_isolated(pg_data_t *pgdat)
- * @cc: Compaction control structure.
- * @low_pfn: The first PFN to isolate
- * @end_pfn: The one-past-the-last PFN to isolate, within same pageblock
-- * @isolate_mode: Isolation mode to be used.
-+ * @mode: Isolation mode to be used.
- *
- * Isolate all pages that can be migrated from the range specified by
- * [low_pfn, end_pfn). The range is expected to be within same pageblock.
-@@ -798,7 +798,7 @@ static bool too_many_isolated(pg_data_t *pgdat)
- */
- static unsigned long
- isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
-- unsigned long end_pfn, isolate_mode_t isolate_mode)
-+ unsigned long end_pfn, isolate_mode_t mode)
- {
- pg_data_t *pgdat = cc->zone->zone_pgdat;
- unsigned long nr_scanned = 0, nr_isolated = 0;
-@@ -806,6 +806,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- unsigned long flags = 0;
- bool locked = false;
- struct page *page = NULL, *valid_page = NULL;
-+ struct address_space *mapping;
- unsigned long start_pfn = low_pfn;
- bool skip_on_failure = false;
- unsigned long next_skip_pfn = 0;
-@@ -949,7 +950,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- locked = false;
- }
-
-- if (!isolate_movable_page(page, isolate_mode))
-+ if (!isolate_movable_page(page, mode))
- goto isolate_success;
- }
-
-@@ -961,15 +962,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- * so avoid taking lru_lock and isolating it unnecessarily in an
- * admittedly racy check.
- */
-- if (!page_mapping(page) &&
-- page_count(page) > page_mapcount(page))
-+ mapping = page_mapping(page);
-+ if (!mapping && page_count(page) > page_mapcount(page))
- goto isolate_fail;
-
- /*
- * Only allow to migrate anonymous pages in GFP_NOFS context
- * because those do not depend on fs locks.
- */
-- if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page))
-+ if (!(cc->gfp_mask & __GFP_FS) && mapping)
- goto isolate_fail;
-
- /*
-@@ -980,9 +981,45 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- if (unlikely(!get_page_unless_zero(page)))
- goto isolate_fail;
-
-- if (!__isolate_lru_page_prepare(page, isolate_mode))
-+ /* Only take pages on LRU: a check now makes later tests safe */
-+ if (!PageLRU(page))
-+ goto isolate_fail_put;
-+
-+ /* Compaction might skip unevictable pages but CMA takes them */
-+ if (!(mode & ISOLATE_UNEVICTABLE) && PageUnevictable(page))
-+ goto isolate_fail_put;
-+
-+ /*
-+ * To minimise LRU disruption, the caller can indicate with
-+ * ISOLATE_ASYNC_MIGRATE that it only wants to isolate pages
-+ * it will be able to migrate without blocking - clean pages
-+ * for the most part. PageWriteback would require blocking.
-+ */
-+ if ((mode & ISOLATE_ASYNC_MIGRATE) && PageWriteback(page))
- goto isolate_fail_put;
-
-+ if ((mode & ISOLATE_ASYNC_MIGRATE) && PageDirty(page)) {
-+ bool migrate_dirty;
-+
-+ /*
-+ * Only pages without mappings or that have a
-+ * ->migratepage callback are possible to migrate
-+ * without blocking. However, we can be racing with
-+ * truncation so it's necessary to lock the page
-+ * to stabilise the mapping as truncation holds
-+ * the page lock until after the page is removed
-+ * from the page cache.
-+ */
-+ if (!trylock_page(page))
-+ goto isolate_fail_put;
-+
-+ mapping = page_mapping(page);
-+ migrate_dirty = !mapping || mapping->a_ops->migratepage;
-+ unlock_page(page);
-+ if (!migrate_dirty)
-+ goto isolate_fail_put;
-+ }
-+
- /* Try isolate the page */
- if (!TestClearPageLRU(page))
- goto isolate_fail_put;
-diff --git a/mm/vmscan.c b/mm/vmscan.c
-index 00a47845a15b..9cba0f890b33 100644
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -1535,69 +1535,6 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
- return nr_reclaimed;
- }
-
--/*
-- * Attempt to remove the specified page from its LRU. Only take this page
-- * if it is of the appropriate PageActive status. Pages which are being
-- * freed elsewhere are also ignored.
-- *
-- * page: page to consider
-- * mode: one of the LRU isolation modes defined above
-- *
-- * returns true on success, false on failure.
-- */
--bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
--{
-- /* Only take pages on the LRU. */
-- if (!PageLRU(page))
-- return false;
--
-- /* Compaction should not handle unevictable pages but CMA can do so */
-- if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
-- return false;
--
-- /*
-- * To minimise LRU disruption, the caller can indicate that it only
-- * wants to isolate pages it will be able to operate on without
-- * blocking - clean pages for the most part.
-- *
-- * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
-- * that it is possible to migrate without blocking
-- */
-- if (mode & ISOLATE_ASYNC_MIGRATE) {
-- /* All the caller can do on PageWriteback is block */
-- if (PageWriteback(page))
-- return false;
--
-- if (PageDirty(page)) {
-- struct address_space *mapping;
-- bool migrate_dirty;
--
-- /*
-- * Only pages without mappings or that have a
-- * ->migratepage callback are possible to migrate
-- * without blocking. However, we can be racing with
-- * truncation so it's necessary to lock the page
-- * to stabilise the mapping as truncation holds
-- * the page lock until after the page is removed
-- * from the page cache.
-- */
-- if (!trylock_page(page))
-- return false;
--
-- mapping = page_mapping(page);
-- migrate_dirty = !mapping || mapping->a_ops->migratepage;
-- unlock_page(page);
-- if (!migrate_dirty)
-- return false;
-- }
-- }
--
-- if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
-- return false;
--
-- return true;
--}
--
- /*
- * Update LRU sizes after isolating pages. The LRU size updates must
- * be complete before mem_cgroup_update_lru_size due to a sanity check.
-@@ -1647,11 +1584,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
- unsigned long skipped = 0;
- unsigned long scan, total_scan, nr_pages;
- LIST_HEAD(pages_skipped);
-- isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED);
-
- total_scan = 0;
- scan = 0;
- while (scan < nr_to_scan && !list_empty(src)) {
-+ struct list_head *move_to = src;
- struct page *page;
-
- page = lru_to_page(src);
-@@ -1661,9 +1598,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
- total_scan += nr_pages;
-
- if (page_zonenum(page) > sc->reclaim_idx) {
-- list_move(&page->lru, &pages_skipped);
- nr_skipped[page_zonenum(page)] += nr_pages;
-- continue;
-+ move_to = &pages_skipped;
-+ goto move;
- }
-
- /*
-@@ -1671,37 +1608,34 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
- * return with no isolated pages if the LRU mostly contains
- * ineligible pages. This causes the VM to not reclaim any
- * pages, triggering a premature OOM.
-- *
-- * Account all tail pages of THP. This would not cause
-- * premature OOM since __isolate_lru_page() returns -EBUSY
-- * only when the page is being freed somewhere else.
-+ * Account all tail pages of THP.
- */
- scan += nr_pages;
-- if (!__isolate_lru_page_prepare(page, mode)) {
-- /* It is being freed elsewhere */
-- list_move(&page->lru, src);
-- continue;
-- }
-+
-+ if (!PageLRU(page))
-+ goto move;
-+ if (!sc->may_unmap && page_mapped(page))
-+ goto move;
-+
- /*
- * Be careful not to clear PageLRU until after we're
- * sure the page is not being freed elsewhere -- the
- * page release code relies on it.
- */
-- if (unlikely(!get_page_unless_zero(page))) {
-- list_move(&page->lru, src);
-- continue;
-- }
-+ if (unlikely(!get_page_unless_zero(page)))
-+ goto move;
-
- if (!TestClearPageLRU(page)) {
- /* Another thread is already isolating this page */
- put_page(page);
-- list_move(&page->lru, src);
-- continue;
-+ goto move;
- }
-
- nr_taken += nr_pages;
- nr_zone_taken[page_zonenum(page)] += nr_pages;
-- list_move(&page->lru, dst);
-+ move_to = dst;
-+move:
-+ list_move(&page->lru, move_to);
- }
-
- /*
-@@ -1725,7 +1659,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
- }
- *nr_scanned = total_scan;
- trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
-- total_scan, skipped, nr_taken, mode, lru);
-+ total_scan, skipped, nr_taken,
-+ sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru);
- update_lru_sizes(lruvec, lru, nr_zone_taken);
- return nr_taken;
- }
---
-2.35.1
-
+++ /dev/null
-From ef33d369381db1a4df5a9f474b014cc4e4664606 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 15 Dec 2020 12:34:20 -0800
-Subject: mm/compaction: do page isolation first in compaction
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-From: Alex Shi <alex.shi@linux.alibaba.com>
-
-[ Upstream commit 9df41314390b81a541ca6e84c8340bad0959e4b5 ]
-
-Currently, compaction would get the lru_lock and then do page isolation
-which works fine with pgdat->lru_lock, since any page isoltion would
-compete for the lru_lock. If we want to change to memcg lru_lock, we have
-to isolate the page before getting lru_lock, thus isoltion would block
-page's memcg change which relay on page isoltion too. Then we could
-safely use per memcg lru_lock later.
-
-The new page isolation use previous introduced TestClearPageLRU() + pgdat
-lru locking which will be changed to memcg lru lock later.
-
-Hugh Dickins <hughd@google.com> fixed following bugs in this patch's early
-version:
-
-Fix lots of crashes under compaction load: isolate_migratepages_block()
-must clean up appropriately when rejecting a page, setting PageLRU again
-if it had been cleared; and a put_page() after get_page_unless_zero()
-cannot safely be done while holding locked_lruvec - it may turn out to be
-the final put_page(), which will take an lruvec lock when PageLRU.
-
-And move __isolate_lru_page_prepare back after get_page_unless_zero to
-make trylock_page() safe: trylock_page() is not safe to use at this time:
-its setting PG_locked can race with the page being freed or allocated
-("Bad page"), and can also erase flags being set by one of those "sole
-owners" of a freshly allocated page who use non-atomic __SetPageFlag().
-
-Link: https://lkml.kernel.org/r/1604566549-62481-16-git-send-email-alex.shi@linux.alibaba.com
-Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
-Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
-Acked-by: Hugh Dickins <hughd@google.com>
-Acked-by: Johannes Weiner <hannes@cmpxchg.org>
-Acked-by: Vlastimil Babka <vbabka@suse.cz>
-Cc: Matthew Wilcox <willy@infradead.org>
-Cc: Alexander Duyck <alexander.duyck@gmail.com>
-Cc: Andrea Arcangeli <aarcange@redhat.com>
-Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
-Cc: "Chen, Rong A" <rong.a.chen@intel.com>
-Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
-Cc: "Huang, Ying" <ying.huang@intel.com>
-Cc: Jann Horn <jannh@google.com>
-Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
-Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
-Cc: Kirill A. Shutemov <kirill@shutemov.name>
-Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
-Cc: Mel Gorman <mgorman@techsingularity.net>
-Cc: Michal Hocko <mhocko@kernel.org>
-Cc: Michal Hocko <mhocko@suse.com>
-Cc: Mika Penttilä <mika.penttila@nextfour.com>
-Cc: Minchan Kim <minchan@kernel.org>
-Cc: Shakeel Butt <shakeelb@google.com>
-Cc: Tejun Heo <tj@kernel.org>
-Cc: Thomas Gleixner <tglx@linutronix.de>
-Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
-Cc: Wei Yang <richard.weiyang@gmail.com>
-Cc: Yang Shi <yang.shi@linux.alibaba.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-Stable-dep-of: 829ae0f81ce0 ("mm: migrate: fix THP's mapcount on isolation")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/swap.h | 2 +-
- mm/compaction.c | 42 +++++++++++++++++++++++++++++++++---------
- mm/vmscan.c | 43 ++++++++++++++++++++++---------------------
- 3 files changed, 56 insertions(+), 31 deletions(-)
-
-diff --git a/include/linux/swap.h b/include/linux/swap.h
-index fbc6805358da..3577d3a6ec37 100644
---- a/include/linux/swap.h
-+++ b/include/linux/swap.h
-@@ -358,7 +358,7 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page,
- extern unsigned long zone_reclaimable_pages(struct zone *zone);
- extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
- gfp_t gfp_mask, nodemask_t *mask);
--extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
-+extern int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
- extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
- unsigned long nr_pages,
- gfp_t gfp_mask,
-diff --git a/mm/compaction.c b/mm/compaction.c
-index 8dfbe86bd74f..ba3e907f03b7 100644
---- a/mm/compaction.c
-+++ b/mm/compaction.c
-@@ -890,6 +890,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) {
- if (!cc->ignore_skip_hint && get_pageblock_skip(page)) {
- low_pfn = end_pfn;
-+ page = NULL;
- goto isolate_abort;
- }
- valid_page = page;
-@@ -971,6 +972,21 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page))
- goto isolate_fail;
-
-+ /*
-+ * Be careful not to clear PageLRU until after we're
-+ * sure the page is not being freed elsewhere -- the
-+ * page release code relies on it.
-+ */
-+ if (unlikely(!get_page_unless_zero(page)))
-+ goto isolate_fail;
-+
-+ if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
-+ goto isolate_fail_put;
-+
-+ /* Try isolate the page */
-+ if (!TestClearPageLRU(page))
-+ goto isolate_fail_put;
-+
- /* If we already hold the lock, we can skip some rechecking */
- if (!locked) {
- locked = compact_lock_irqsave(&pgdat->lru_lock,
-@@ -983,10 +999,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- goto isolate_abort;
- }
-
-- /* Recheck PageLRU and PageCompound under lock */
-- if (!PageLRU(page))
-- goto isolate_fail;
--
- /*
- * Page become compound since the non-locked check,
- * and it's on LRU. It can only be a THP so the order
-@@ -994,16 +1006,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- */
- if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
- low_pfn += compound_nr(page) - 1;
-- goto isolate_fail;
-+ SetPageLRU(page);
-+ goto isolate_fail_put;
- }
- }
-
- lruvec = mem_cgroup_page_lruvec(page, pgdat);
-
-- /* Try isolate the page */
-- if (__isolate_lru_page(page, isolate_mode) != 0)
-- goto isolate_fail;
--
- /* The whole page is taken off the LRU; skip the tail pages. */
- if (PageCompound(page))
- low_pfn += compound_nr(page) - 1;
-@@ -1032,6 +1041,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- }
-
- continue;
-+
-+isolate_fail_put:
-+ /* Avoid potential deadlock in freeing page under lru_lock */
-+ if (locked) {
-+ spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-+ locked = false;
-+ }
-+ put_page(page);
-+
- isolate_fail:
- if (!skip_on_failure)
- continue;
-@@ -1068,9 +1086,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- if (unlikely(low_pfn > end_pfn))
- low_pfn = end_pfn;
-
-+ page = NULL;
-+
- isolate_abort:
- if (locked)
- spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-+ if (page) {
-+ SetPageLRU(page);
-+ put_page(page);
-+ }
-
- /*
- * Updated the cached scanner pfn once the pageblock has been scanned
-diff --git a/mm/vmscan.c b/mm/vmscan.c
-index 8d62eedfc794..5ada402c8d95 100644
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -1545,7 +1545,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
- *
- * returns 0 on success, -ve errno on failure.
- */
--int __isolate_lru_page(struct page *page, isolate_mode_t mode)
-+int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
- {
- int ret = -EBUSY;
-
-@@ -1597,22 +1597,9 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
- if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
- return ret;
-
-- if (likely(get_page_unless_zero(page))) {
-- /*
-- * Be careful not to clear PageLRU until after we're
-- * sure the page is not being freed elsewhere -- the
-- * page release code relies on it.
-- */
-- if (TestClearPageLRU(page))
-- ret = 0;
-- else
-- put_page(page);
-- }
--
-- return ret;
-+ return 0;
- }
-
--
- /*
- * Update LRU sizes after isolating pages. The LRU size updates must
- * be complete before mem_cgroup_update_lru_size due to a sanity check.
-@@ -1692,20 +1679,34 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
- * only when the page is being freed somewhere else.
- */
- scan += nr_pages;
-- switch (__isolate_lru_page(page, mode)) {
-+ switch (__isolate_lru_page_prepare(page, mode)) {
- case 0:
-+ /*
-+ * Be careful not to clear PageLRU until after we're
-+ * sure the page is not being freed elsewhere -- the
-+ * page release code relies on it.
-+ */
-+ if (unlikely(!get_page_unless_zero(page)))
-+ goto busy;
-+
-+ if (!TestClearPageLRU(page)) {
-+ /*
-+ * This page may in other isolation path,
-+ * but we still hold lru_lock.
-+ */
-+ put_page(page);
-+ goto busy;
-+ }
-+
- nr_taken += nr_pages;
- nr_zone_taken[page_zonenum(page)] += nr_pages;
- list_move(&page->lru, dst);
- break;
-
-- case -EBUSY:
-+ default:
-+busy:
- /* else it is being freed elsewhere */
- list_move(&page->lru, src);
-- continue;
--
-- default:
-- BUG();
- }
- }
-
---
-2.35.1
-
+++ /dev/null
-From d84c0415a11eafaa01336ef3fa61f707986b5656 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 15 Dec 2020 12:34:16 -0800
-Subject: mm/lru: introduce TestClearPageLRU()
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-From: Alex Shi <alex.shi@linux.alibaba.com>
-
-[ Upstream commit d25b5bd8a8f420b15517c19c4626c0c009f72a63 ]
-
-Currently lru_lock still guards both lru list and page's lru bit, that's
-ok. but if we want to use specific lruvec lock on the page, we need to
-pin down the page's lruvec/memcg during locking. Just taking lruvec lock
-first may be undermined by the page's memcg charge/migration. To fix this
-problem, we will clear the lru bit out of locking and use it as pin down
-action to block the page isolation in memcg changing.
-
-So now a standard steps of page isolation is following:
- 1, get_page(); #pin the page avoid to be free
- 2, TestClearPageLRU(); #block other isolation like memcg change
- 3, spin_lock on lru_lock; #serialize lru list access
- 4, delete page from lru list;
-
-This patch start with the first part: TestClearPageLRU, which combines
-PageLRU check and ClearPageLRU into a macro func TestClearPageLRU. This
-function will be used as page isolation precondition to prevent other
-isolations some where else. Then there are may !PageLRU page on lru list,
-need to remove BUG() checking accordingly.
-
-There 2 rules for lru bit now:
-1, the lru bit still indicate if a page on lru list, just in some
- temporary moment(isolating), the page may have no lru bit when
- it's on lru list. but the page still must be on lru list when the
- lru bit set.
-2, have to remove lru bit before delete it from lru list.
-
-As Andrew Morton mentioned this change would dirty cacheline for a page
-which isn't on the LRU. But the loss would be acceptable in Rong Chen
-<rong.a.chen@intel.com> report:
-https://lore.kernel.org/lkml/20200304090301.GB5972@shao2-debian/
-
-Link: https://lkml.kernel.org/r/1604566549-62481-15-git-send-email-alex.shi@linux.alibaba.com
-Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
-Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
-Acked-by: Hugh Dickins <hughd@google.com>
-Acked-by: Johannes Weiner <hannes@cmpxchg.org>
-Acked-by: Vlastimil Babka <vbabka@suse.cz>
-Cc: Michal Hocko <mhocko@kernel.org>
-Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
-Cc: Alexander Duyck <alexander.duyck@gmail.com>
-Cc: Andrea Arcangeli <aarcange@redhat.com>
-Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
-Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
-Cc: "Huang, Ying" <ying.huang@intel.com>
-Cc: Jann Horn <jannh@google.com>
-Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
-Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
-Cc: Kirill A. Shutemov <kirill@shutemov.name>
-Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
-Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
-Cc: Mel Gorman <mgorman@techsingularity.net>
-Cc: Michal Hocko <mhocko@suse.com>
-Cc: Mika Penttilä <mika.penttila@nextfour.com>
-Cc: Minchan Kim <minchan@kernel.org>
-Cc: Shakeel Butt <shakeelb@google.com>
-Cc: Tejun Heo <tj@kernel.org>
-Cc: Thomas Gleixner <tglx@linutronix.de>
-Cc: Wei Yang <richard.weiyang@gmail.com>
-Cc: Yang Shi <yang.shi@linux.alibaba.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-Stable-dep-of: 829ae0f81ce0 ("mm: migrate: fix THP's mapcount on isolation")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/page-flags.h | 1 +
- mm/mlock.c | 3 +--
- mm/vmscan.c | 39 +++++++++++++++++++-------------------
- 3 files changed, 21 insertions(+), 22 deletions(-)
-
-diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
-index 4f6ba9379112..14a0cac9e099 100644
---- a/include/linux/page-flags.h
-+++ b/include/linux/page-flags.h
-@@ -335,6 +335,7 @@ PAGEFLAG(Referenced, referenced, PF_HEAD)
- PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
- __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
- PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
-+ TESTCLEARFLAG(LRU, lru, PF_HEAD)
- PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
- TESTCLEARFLAG(Active, active, PF_HEAD)
- PAGEFLAG(Workingset, workingset, PF_HEAD)
-diff --git a/mm/mlock.c b/mm/mlock.c
-index d487aa864e86..7b0e6334be6f 100644
---- a/mm/mlock.c
-+++ b/mm/mlock.c
-@@ -276,10 +276,9 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
- * We already have pin from follow_page_mask()
- * so we can spare the get_page() here.
- */
-- if (PageLRU(page)) {
-+ if (TestClearPageLRU(page)) {
- struct lruvec *lruvec;
-
-- ClearPageLRU(page);
- lruvec = mem_cgroup_page_lruvec(page,
- page_pgdat(page));
- del_page_from_lru_list(page, lruvec,
-diff --git a/mm/vmscan.c b/mm/vmscan.c
-index 51ccd80e70b6..8d62eedfc794 100644
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -1547,7 +1547,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
- */
- int __isolate_lru_page(struct page *page, isolate_mode_t mode)
- {
-- int ret = -EINVAL;
-+ int ret = -EBUSY;
-
- /* Only take pages on the LRU. */
- if (!PageLRU(page))
-@@ -1557,8 +1557,6 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
- if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
- return ret;
-
-- ret = -EBUSY;
--
- /*
- * To minimise LRU disruption, the caller can indicate that it only
- * wants to isolate pages it will be able to operate on without
-@@ -1605,8 +1603,10 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
- * sure the page is not being freed elsewhere -- the
- * page release code relies on it.
- */
-- ClearPageLRU(page);
-- ret = 0;
-+ if (TestClearPageLRU(page))
-+ ret = 0;
-+ else
-+ put_page(page);
- }
-
- return ret;
-@@ -1672,8 +1672,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
- page = lru_to_page(src);
- prefetchw_prev_lru_page(page, src, flags);
-
-- VM_BUG_ON_PAGE(!PageLRU(page), page);
--
- nr_pages = compound_nr(page);
- total_scan += nr_pages;
-
-@@ -1770,21 +1768,18 @@ int isolate_lru_page(struct page *page)
- VM_BUG_ON_PAGE(!page_count(page), page);
- WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
-
-- if (PageLRU(page)) {
-+ if (TestClearPageLRU(page)) {
- pg_data_t *pgdat = page_pgdat(page);
- struct lruvec *lruvec;
-
-- spin_lock_irq(&pgdat->lru_lock);
-+ get_page(page);
- lruvec = mem_cgroup_page_lruvec(page, pgdat);
-- if (PageLRU(page)) {
-- int lru = page_lru(page);
-- get_page(page);
-- ClearPageLRU(page);
-- del_page_from_lru_list(page, lruvec, lru);
-- ret = 0;
-- }
-+ spin_lock_irq(&pgdat->lru_lock);
-+ del_page_from_lru_list(page, lruvec, page_lru(page));
- spin_unlock_irq(&pgdat->lru_lock);
-+ ret = 0;
- }
-+
- return ret;
- }
-
-@@ -4291,6 +4286,10 @@ void check_move_unevictable_pages(struct pagevec *pvec)
- nr_pages = thp_nr_pages(page);
- pgscanned += nr_pages;
-
-+ /* block memcg migration during page moving between lru */
-+ if (!TestClearPageLRU(page))
-+ continue;
-+
- if (pagepgdat != pgdat) {
- if (pgdat)
- spin_unlock_irq(&pgdat->lru_lock);
-@@ -4299,10 +4298,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
- }
- lruvec = mem_cgroup_page_lruvec(page, pgdat);
-
-- if (!PageLRU(page) || !PageUnevictable(page))
-- continue;
--
-- if (page_evictable(page)) {
-+ if (page_evictable(page) && PageUnevictable(page)) {
- enum lru_list lru = page_lru_base_type(page);
-
- VM_BUG_ON_PAGE(PageActive(page), page);
-@@ -4311,12 +4307,15 @@ void check_move_unevictable_pages(struct pagevec *pvec)
- add_page_to_lru_list(page, lruvec, lru);
- pgrescued += nr_pages;
- }
-+ SetPageLRU(page);
- }
-
- if (pgdat) {
- __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
- __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
- spin_unlock_irq(&pgdat->lru_lock);
-+ } else if (pgscanned) {
-+ count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
- }
- }
- EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
---
-2.35.1
-
+++ /dev/null
-From 91f25a9aa0bb126c81ed361cef0f8608ac4c3f15 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 24 Nov 2022 17:55:23 +0800
-Subject: mm: migrate: fix THP's mapcount on isolation
-
-From: Gavin Shan <gshan@redhat.com>
-
-[ Upstream commit 829ae0f81ce093d674ff2256f66a714753e9ce32 ]
-
-The issue is reported when removing memory through virtio_mem device. The
-transparent huge page, experienced copy-on-write fault, is wrongly
-regarded as pinned. The transparent huge page is escaped from being
-isolated in isolate_migratepages_block(). The transparent huge page can't
-be migrated and the corresponding memory block can't be put into offline
-state.
-
-Fix it by replacing page_mapcount() with total_mapcount(). With this, the
-transparent huge page can be isolated and migrated, and the memory block
-can be put into offline state. Besides, The page's refcount is increased
-a bit earlier to avoid the page is released when the check is executed.
-
-Link: https://lkml.kernel.org/r/20221124095523.31061-1-gshan@redhat.com
-Fixes: 1da2f328fa64 ("mm,thp,compaction,cma: allow THP migration for CMA allocations")
-Signed-off-by: Gavin Shan <gshan@redhat.com>
-Reported-by: Zhenyu Zhang <zhenyzha@redhat.com>
-Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
-Suggested-by: David Hildenbrand <david@redhat.com>
-Acked-by: David Hildenbrand <david@redhat.com>
-Cc: Alistair Popple <apopple@nvidia.com>
-Cc: Hugh Dickins <hughd@google.com>
-Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
-Cc: Matthew Wilcox <willy@infradead.org>
-Cc: William Kucharski <william.kucharski@oracle.com>
-Cc: Zi Yan <ziy@nvidia.com>
-Cc: <stable@vger.kernel.org> [5.7+]
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- mm/compaction.c | 22 +++++++++++-----------
- 1 file changed, 11 insertions(+), 11 deletions(-)
-
-diff --git a/mm/compaction.c b/mm/compaction.c
-index 57ce6b001b10..54d1041560c7 100644
---- a/mm/compaction.c
-+++ b/mm/compaction.c
-@@ -957,29 +957,29 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- goto isolate_fail;
- }
-
-+ /*
-+ * Be careful not to clear PageLRU until after we're
-+ * sure the page is not being freed elsewhere -- the
-+ * page release code relies on it.
-+ */
-+ if (unlikely(!get_page_unless_zero(page)))
-+ goto isolate_fail;
-+
- /*
- * Migration will fail if an anonymous page is pinned in memory,
- * so avoid taking lru_lock and isolating it unnecessarily in an
- * admittedly racy check.
- */
- mapping = page_mapping(page);
-- if (!mapping && page_count(page) > page_mapcount(page))
-- goto isolate_fail;
-+ if (!mapping && (page_count(page) - 1) > total_mapcount(page))
-+ goto isolate_fail_put;
-
- /*
- * Only allow to migrate anonymous pages in GFP_NOFS context
- * because those do not depend on fs locks.
- */
- if (!(cc->gfp_mask & __GFP_FS) && mapping)
-- goto isolate_fail;
--
-- /*
-- * Be careful not to clear PageLRU until after we're
-- * sure the page is not being freed elsewhere -- the
-- * page release code relies on it.
-- */
-- if (unlikely(!get_page_unless_zero(page)))
-- goto isolate_fail;
-+ goto isolate_fail_put;
-
- /* Only take pages on LRU: a check now makes later tests safe */
- if (!PageLRU(page))
---
-2.35.1
-
+++ /dev/null
-From 6649227e330b37c9583146cd7446b41771b3a7f1 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 15 Dec 2020 12:34:11 -0800
-Subject: mm/mlock: remove __munlock_isolate_lru_page()
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-From: Alex Shi <alex.shi@linux.alibaba.com>
-
-[ Upstream commit 13805a88a9bd3fb37f33dd8972d904de62796f3d ]
-
-__munlock_isolate_lru_page() only has one caller, remove it to clean up
-and simplify code.
-
-Link: https://lkml.kernel.org/r/1604566549-62481-14-git-send-email-alex.shi@linux.alibaba.com
-Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
-Acked-by: Hugh Dickins <hughd@google.com>
-Acked-by: Johannes Weiner <hannes@cmpxchg.org>
-Acked-by: Vlastimil Babka <vbabka@suse.cz>
-Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
-Cc: Alexander Duyck <alexander.duyck@gmail.com>
-Cc: Andrea Arcangeli <aarcange@redhat.com>
-Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
-Cc: "Chen, Rong A" <rong.a.chen@intel.com>
-Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
-Cc: "Huang, Ying" <ying.huang@intel.com>
-Cc: Jann Horn <jannh@google.com>
-Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
-Cc: Kirill A. Shutemov <kirill@shutemov.name>
-Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
-Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
-Cc: Mel Gorman <mgorman@techsingularity.net>
-Cc: Michal Hocko <mhocko@kernel.org>
-Cc: Michal Hocko <mhocko@suse.com>
-Cc: Mika Penttilä <mika.penttila@nextfour.com>
-Cc: Minchan Kim <minchan@kernel.org>
-Cc: Shakeel Butt <shakeelb@google.com>
-Cc: Tejun Heo <tj@kernel.org>
-Cc: Thomas Gleixner <tglx@linutronix.de>
-Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
-Cc: Wei Yang <richard.weiyang@gmail.com>
-Cc: Yang Shi <yang.shi@linux.alibaba.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-Stable-dep-of: 829ae0f81ce0 ("mm: migrate: fix THP's mapcount on isolation")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- mm/mlock.c | 31 +++++++++----------------------
- 1 file changed, 9 insertions(+), 22 deletions(-)
-
-diff --git a/mm/mlock.c b/mm/mlock.c
-index 796c726a0407..d487aa864e86 100644
---- a/mm/mlock.c
-+++ b/mm/mlock.c
-@@ -105,26 +105,6 @@ void mlock_vma_page(struct page *page)
- }
- }
-
--/*
-- * Isolate a page from LRU with optional get_page() pin.
-- * Assumes lru_lock already held and page already pinned.
-- */
--static bool __munlock_isolate_lru_page(struct page *page, bool getpage)
--{
-- if (PageLRU(page)) {
-- struct lruvec *lruvec;
--
-- lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
-- if (getpage)
-- get_page(page);
-- ClearPageLRU(page);
-- del_page_from_lru_list(page, lruvec, page_lru(page));
-- return true;
-- }
--
-- return false;
--}
--
- /*
- * Finish munlock after successful page isolation
- *
-@@ -296,9 +276,16 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
- * We already have pin from follow_page_mask()
- * so we can spare the get_page() here.
- */
-- if (__munlock_isolate_lru_page(page, false))
-+ if (PageLRU(page)) {
-+ struct lruvec *lruvec;
-+
-+ ClearPageLRU(page);
-+ lruvec = mem_cgroup_page_lruvec(page,
-+ page_pgdat(page));
-+ del_page_from_lru_list(page, lruvec,
-+ page_lru(page));
- continue;
-- else
-+ } else
- __munlock_isolation_failed(page);
- } else {
- delta_munlocked++;
---
-2.35.1
-
+++ /dev/null
-From b824ddafd0a14e7a943171ce5903b83057e0c587 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 15 Dec 2020 12:34:07 -0800
-Subject: mm/mlock: remove lru_lock on TestClearPageMlocked
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-From: Alex Shi <alex.shi@linux.alibaba.com>
-
-[ Upstream commit 3db19aa39bac33f2e850fa1ddd67be29b192e51f ]
-
-In the func munlock_vma_page, comments mentained lru_lock needed for
-serialization with split_huge_pages. But the page must be PageLocked as
-well as pages in split_huge_page series funcs. Thus the PageLocked is
-enough to serialize both funcs.
-
-Further more, Hugh Dickins pointed: before splitting in
-split_huge_page_to_list, the page was unmap_page() to remove pmd/ptes
-which protect the page from munlock. Thus, no needs to guard
-__split_huge_page_tail for mlock clean, just keep the lru_lock there for
-isolation purpose.
-
-LKP found a preempt issue on __mod_zone_page_state which need change to
-mod_zone_page_state. Thanks!
-
-Link: https://lkml.kernel.org/r/1604566549-62481-13-git-send-email-alex.shi@linux.alibaba.com
-Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
-Acked-by: Hugh Dickins <hughd@google.com>
-Acked-by: Johannes Weiner <hannes@cmpxchg.org>
-Acked-by: Vlastimil Babka <vbabka@suse.cz>
-Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
-Cc: Alexander Duyck <alexander.duyck@gmail.com>
-Cc: Andrea Arcangeli <aarcange@redhat.com>
-Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
-Cc: "Chen, Rong A" <rong.a.chen@intel.com>
-Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
-Cc: "Huang, Ying" <ying.huang@intel.com>
-Cc: Jann Horn <jannh@google.com>
-Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
-Cc: Kirill A. Shutemov <kirill@shutemov.name>
-Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
-Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
-Cc: Mel Gorman <mgorman@techsingularity.net>
-Cc: Michal Hocko <mhocko@kernel.org>
-Cc: Michal Hocko <mhocko@suse.com>
-Cc: Mika Penttilä <mika.penttila@nextfour.com>
-Cc: Minchan Kim <minchan@kernel.org>
-Cc: Shakeel Butt <shakeelb@google.com>
-Cc: Tejun Heo <tj@kernel.org>
-Cc: Thomas Gleixner <tglx@linutronix.de>
-Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
-Cc: Wei Yang <richard.weiyang@gmail.com>
-Cc: Yang Shi <yang.shi@linux.alibaba.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-Stable-dep-of: 829ae0f81ce0 ("mm: migrate: fix THP's mapcount on isolation")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- mm/mlock.c | 26 +++++---------------------
- 1 file changed, 5 insertions(+), 21 deletions(-)
-
-diff --git a/mm/mlock.c b/mm/mlock.c
-index 884b1216da6a..796c726a0407 100644
---- a/mm/mlock.c
-+++ b/mm/mlock.c
-@@ -187,40 +187,24 @@ static void __munlock_isolation_failed(struct page *page)
- unsigned int munlock_vma_page(struct page *page)
- {
- int nr_pages;
-- pg_data_t *pgdat = page_pgdat(page);
-
- /* For try_to_munlock() and to serialize with page migration */
- BUG_ON(!PageLocked(page));
--
- VM_BUG_ON_PAGE(PageTail(page), page);
-
-- /*
-- * Serialize with any parallel __split_huge_page_refcount() which
-- * might otherwise copy PageMlocked to part of the tail pages before
-- * we clear it in the head page. It also stabilizes thp_nr_pages().
-- */
-- spin_lock_irq(&pgdat->lru_lock);
--
- if (!TestClearPageMlocked(page)) {
- /* Potentially, PTE-mapped THP: do not skip the rest PTEs */
-- nr_pages = 1;
-- goto unlock_out;
-+ return 0;
- }
-
- nr_pages = thp_nr_pages(page);
-- __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
-+ mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
-
-- if (__munlock_isolate_lru_page(page, true)) {
-- spin_unlock_irq(&pgdat->lru_lock);
-+ if (!isolate_lru_page(page))
- __munlock_isolated_page(page);
-- goto out;
-- }
-- __munlock_isolation_failed(page);
--
--unlock_out:
-- spin_unlock_irq(&pgdat->lru_lock);
-+ else
-+ __munlock_isolation_failed(page);
-
--out:
- return nr_pages - 1;
- }
-
---
-2.35.1
-
+++ /dev/null
-From af78db2daeeeec6283747a8d591daf6df57e1961 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Wed, 24 Feb 2021 12:08:01 -0800
-Subject: mm/vmscan: __isolate_lru_page_prepare() cleanup
-
-From: Alex Shi <alex.shi@linux.alibaba.com>
-
-[ Upstream commit c2135f7c570bc274035834848d9bf46ea89ba763 ]
-
-The function just returns 2 results, so using a 'switch' to deal with its
-result is unnecessary. Also simplify it to a bool func as Vlastimil
-suggested.
-
-Also remove 'goto' by reusing list_move(), and take Matthew Wilcox's
-suggestion to update comments in function.
-
-Link: https://lkml.kernel.org/r/728874d7-2d93-4049-68c1-dcc3b2d52ccd@linux.alibaba.com
-Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
-Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
-Acked-by: Vlastimil Babka <vbabka@suse.cz>
-Cc: Matthew Wilcox <willy@infradead.org>
-Cc: Hugh Dickins <hughd@google.com>
-Cc: Yu Zhao <yuzhao@google.com>
-Cc: Michal Hocko <mhocko@suse.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-Stable-dep-of: 829ae0f81ce0 ("mm: migrate: fix THP's mapcount on isolation")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/swap.h | 2 +-
- mm/compaction.c | 2 +-
- mm/vmscan.c | 68 ++++++++++++++++++++------------------------
- 3 files changed, 33 insertions(+), 39 deletions(-)
-
-diff --git a/include/linux/swap.h b/include/linux/swap.h
-index 3577d3a6ec37..394d5de5d4b4 100644
---- a/include/linux/swap.h
-+++ b/include/linux/swap.h
-@@ -358,7 +358,7 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page,
- extern unsigned long zone_reclaimable_pages(struct zone *zone);
- extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
- gfp_t gfp_mask, nodemask_t *mask);
--extern int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
-+extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
- extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
- unsigned long nr_pages,
- gfp_t gfp_mask,
-diff --git a/mm/compaction.c b/mm/compaction.c
-index ba3e907f03b7..ea46aadc7c21 100644
---- a/mm/compaction.c
-+++ b/mm/compaction.c
-@@ -980,7 +980,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
- if (unlikely(!get_page_unless_zero(page)))
- goto isolate_fail;
-
-- if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
-+ if (!__isolate_lru_page_prepare(page, isolate_mode))
- goto isolate_fail_put;
-
- /* Try isolate the page */
-diff --git a/mm/vmscan.c b/mm/vmscan.c
-index 5ada402c8d95..00a47845a15b 100644
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -1543,19 +1543,17 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
- * page: page to consider
- * mode: one of the LRU isolation modes defined above
- *
-- * returns 0 on success, -ve errno on failure.
-+ * returns true on success, false on failure.
- */
--int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
-+bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
- {
-- int ret = -EBUSY;
--
- /* Only take pages on the LRU. */
- if (!PageLRU(page))
-- return ret;
-+ return false;
-
- /* Compaction should not handle unevictable pages but CMA can do so */
- if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
-- return ret;
-+ return false;
-
- /*
- * To minimise LRU disruption, the caller can indicate that it only
-@@ -1568,7 +1566,7 @@ int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
- if (mode & ISOLATE_ASYNC_MIGRATE) {
- /* All the caller can do on PageWriteback is block */
- if (PageWriteback(page))
-- return ret;
-+ return false;
-
- if (PageDirty(page)) {
- struct address_space *mapping;
-@@ -1584,20 +1582,20 @@ int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
- * from the page cache.
- */
- if (!trylock_page(page))
-- return ret;
-+ return false;
-
- mapping = page_mapping(page);
- migrate_dirty = !mapping || mapping->a_ops->migratepage;
- unlock_page(page);
- if (!migrate_dirty)
-- return ret;
-+ return false;
- }
- }
-
- if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
-- return ret;
-+ return false;
-
-- return 0;
-+ return true;
- }
-
- /*
-@@ -1679,35 +1677,31 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
- * only when the page is being freed somewhere else.
- */
- scan += nr_pages;
-- switch (__isolate_lru_page_prepare(page, mode)) {
-- case 0:
-- /*
-- * Be careful not to clear PageLRU until after we're
-- * sure the page is not being freed elsewhere -- the
-- * page release code relies on it.
-- */
-- if (unlikely(!get_page_unless_zero(page)))
-- goto busy;
--
-- if (!TestClearPageLRU(page)) {
-- /*
-- * This page may in other isolation path,
-- * but we still hold lru_lock.
-- */
-- put_page(page);
-- goto busy;
-- }
--
-- nr_taken += nr_pages;
-- nr_zone_taken[page_zonenum(page)] += nr_pages;
-- list_move(&page->lru, dst);
-- break;
-+ if (!__isolate_lru_page_prepare(page, mode)) {
-+ /* It is being freed elsewhere */
-+ list_move(&page->lru, src);
-+ continue;
-+ }
-+ /*
-+ * Be careful not to clear PageLRU until after we're
-+ * sure the page is not being freed elsewhere -- the
-+ * page release code relies on it.
-+ */
-+ if (unlikely(!get_page_unless_zero(page))) {
-+ list_move(&page->lru, src);
-+ continue;
-+ }
-
-- default:
--busy:
-- /* else it is being freed elsewhere */
-+ if (!TestClearPageLRU(page)) {
-+ /* Another thread is already isolating this page */
-+ put_page(page);
- list_move(&page->lru, src);
-+ continue;
- }
-+
-+ nr_taken += nr_pages;
-+ nr_zone_taken[page_zonenum(page)] += nr_pages;
-+ list_move(&page->lru, dst);
- }
-
- /*
---
-2.35.1
-
+++ /dev/null
-From 876f244f4ef1d9bd6121dee4e3066f26e179c573 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Fri, 25 Nov 2022 19:50:03 +0800
-Subject: net: broadcom: Add PTP_1588_CLOCK_OPTIONAL dependency for BCMGENET
- under ARCH_BCM2835
-
-From: YueHaibing <yuehaibing@huawei.com>
-
-[ Upstream commit 421f8663b3a775c32f724f793264097c60028f2e ]
-
-commit 8d820bc9d12b ("net: broadcom: Fix BCMGENET Kconfig") fixes the build
-that contain 99addbe31f55 ("net: broadcom: Select BROADCOM_PHY for BCMGENET")
-and enable BCMGENET=y but PTP_1588_CLOCK_OPTIONAL=m, which otherwise
-leads to a link failure. However this may trigger a runtime failure.
-
-Fix the original issue by propagating the PTP_1588_CLOCK_OPTIONAL dependency
-of BROADCOM_PHY down to BCMGENET.
-
-Fixes: 8d820bc9d12b ("net: broadcom: Fix BCMGENET Kconfig")
-Fixes: 99addbe31f55 ("net: broadcom: Select BROADCOM_PHY for BCMGENET")
-Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
-Suggested-by: Arnd Bergmann <arnd@arndb.de>
-Signed-off-by: YueHaibing <yuehaibing@huawei.com>
-Acked-by: Arnd Bergmann <arnd@arndb.de>
-Link: https://lore.kernel.org/r/20221125115003.30308-1-yuehaibing@huawei.com
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- drivers/net/ethernet/broadcom/Kconfig | 1 +
- 1 file changed, 1 insertion(+)
-
-diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
-index 7b79528d6eed..06aaeaadf2e9 100644
---- a/drivers/net/ethernet/broadcom/Kconfig
-+++ b/drivers/net/ethernet/broadcom/Kconfig
-@@ -63,6 +63,7 @@ config BCM63XX_ENET
- config BCMGENET
- tristate "Broadcom GENET internal MAC support"
- depends on HAS_IOMEM
-+ depends on PTP_1588_CLOCK_OPTIONAL || !ARCH_BCM2835
- select MII
- select PHYLIB
- select FIXED_PHY
---
-2.35.1
-
-mm-mlock-remove-lru_lock-on-testclearpagemlocked.patch
-mm-mlock-remove-__munlock_isolate_lru_page.patch
-mm-lru-introduce-testclearpagelru.patch
-mm-compaction-do-page-isolation-first-in-compaction.patch
-mm-vmscan-__isolate_lru_page_prepare-cleanup.patch
-mm-__isolate_lru_page_prepare-in-isolate_migratepage.patch
-mm-migrate-fix-thp-s-mapcount-on-isolation.patch
arm64-dts-rockchip-keep-i2s1-disabled-for-gpio-funct.patch
arm-dts-rockchip-fix-node-name-for-hym8563-rtc.patch
arm-dts-rockchip-fix-ir-receiver-node-names.patch
gpio-amd8111-fix-pci-device-reference-count-leak.patch
e1000e-fix-tx-dispatch-condition.patch
igb-allocate-msi-x-vector-when-testing.patch
-net-broadcom-add-ptp_1588_clock_optional-dependency-.patch
drm-bridge-dw_hdmi-fix-preference-of-rgb-modes-over-.patch
af_unix-get-user_ns-from-in_skb-in-unix_diag_get_exa.patch
vmxnet3-correctly-report-encapsulated-lro-packet.patch
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
- io_uring/io_uring.c | 4 +++-
+ io_uring/io_uring.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
-diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
-index 1279b5c5c959..eebbe8a6da0c 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
-@@ -9467,8 +9467,10 @@ static void io_tctx_exit_cb(struct callback_head *cb)
+@@ -9467,8 +9467,10 @@ static void io_tctx_exit_cb(struct callb
/*
* When @in_idle, we're in cancellation and it's racy to remove the
* node. It'll be removed by the end of cancellation, just ignore it.
io_uring_del_tctx_node((unsigned long)work->ctx);
complete(&work->completion);
}
---
-2.35.1
-
projects / thirdparty / kernel / stable-queue.git / commitdiff
