From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit 99fbb6bfc16f202adc411ad5d353db214750d121 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Patch series "Rearrange batched folio freeing", v3. Other than the obvious "remove calls to compound_head" changes, the fundamental belief here is that iterating a linked list is much slower than iterating an array (5-15x slower in my testing). There's also an associated belief that since we iterate the batch of folios three times, we do better when the array is small (ie 15 entries) than we do with a batch that is hundreds of entries long, which only gives us the opportunity for the first pages to fall out of cache by the time we get to the end. It is possible we should increase the size of folio_batch. Hopefully the bots let us know if this introduces any performance regressions. This patch (of 3): By making release_pages() call folios_put(), we can get rid of the calls to compound_head() for the callers that already know they have folios. We can also get rid of the lock_batch tracking as we know the size of the batch is limited by folio_batch. This does reduce the maximum number of pages for which the lruvec lock is held, from SWAP_CLUSTER_MAX (32) to PAGEVEC_SIZE (15). I do not expect this to make a significant difference, but if it does, we can increase PAGEVEC_SIZE to 31. Link: https://lkml.kernel.org/r/20240227174254.710559-1-willy@infradead.org Link: https://lkml.kernel.org/r/20240227174254.710559-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- include/linux/mm.h | 16 +++++--- mm/mlock.c | 3 +- mm/swap.c | 100 ++++++++++++++++++++++++++------------------- 3 files changed, 70 insertions(+), 49 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 49f4fac2dcf7..ca70fe2405c7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -37,6 +37,7 @@ struct anon_vma; struct anon_vma_chain; struct user_struct; struct pt_regs; +struct folio_batch; extern int sysctl_page_lock_unfairness; @@ -1532,6 +1533,8 @@ static inline void folio_put_refs(struct folio *folio, int refs) __folio_put(folio); } +void folios_put_refs(struct folio_batch *folios, unsigned int *refs); + /* * union release_pages_arg - an array of pages or folios * @@ -1554,18 +1557,19 @@ void release_pages(release_pages_arg, int nr); /** * folios_put - Decrement the reference count on an array of folios. * @folios: The folios. - * @nr: How many folios there are. * - * Like folio_put(), but for an array of folios. This is more efficient - * than writing the loop yourself as it will optimise the locks which - * need to be taken if the folios are freed. + * Like folio_put(), but for a batch of folios. This is more efficient + * than writing the loop yourself as it will optimise the locks which need + * to be taken if the folios are freed. The folios batch is returned + * empty and ready to be reused for another batch; there is no need to + * reinitialise it. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ -static inline void folios_put(struct folio **folios, unsigned int nr) +static inline void folios_put(struct folio_batch *folios) { - release_pages(folios, nr); + folios_put_refs(folios, NULL); } static inline void put_page(struct page *page) diff --git a/mm/mlock.c b/mm/mlock.c index f79d8262c1a0..d0b06ea3b721 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -206,8 +206,7 @@ static void mlock_folio_batch(struct folio_batch *fbatch) if (lruvec) unlock_page_lruvec_irq(lruvec); - folios_put(fbatch->folios, folio_batch_count(fbatch)); - folio_batch_reinit(fbatch); + folios_put(fbatch); } void mlock_drain_local(void) diff --git a/mm/swap.c b/mm/swap.c index e5380d732c0d..3d51f8c72017 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -89,7 +89,7 @@ static void __page_cache_release(struct folio *folio) __folio_clear_lru_flags(folio); unlock_page_lruvec_irqrestore(lruvec, flags); } - /* See comment on folio_test_mlocked in release_pages() */ + /* See comment on folio_test_mlocked in folios_put() */ if (unlikely(folio_test_mlocked(folio))) { long nr_pages = folio_nr_pages(folio); @@ -175,7 +175,7 @@ static void lru_add_fn(struct lruvec *lruvec, struct folio *folio) * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily - * true of release_pages(): but those only clear the mlocked flag after + * true of folios_put(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { @@ -221,8 +221,7 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); - folios_put(fbatch->folios, folio_batch_count(fbatch)); - folio_batch_reinit(fbatch); + folios_put(fbatch); } static void folio_batch_add_and_move(struct folio_batch *fbatch, @@ -946,47 +945,30 @@ void lru_cache_disable(void) } /** - * release_pages - batched put_page() - * @arg: array of pages to release - * @nr: number of pages + * folios_put_refs - Reduce the reference count on a batch of folios. + * @folios: The folios. + * @refs: The number of refs to subtract from each folio. * - * Decrement the reference count on all the pages in @arg. If it - * fell to zero, remove the page from the LRU and free it. + * Like folio_put(), but for a batch of folios. This is more efficient + * than writing the loop yourself as it will optimise the locks which need + * to be taken if the folios are freed. The folios batch is returned + * empty and ready to be reused for another batch; there is no need + * to reinitialise it. If @refs is NULL, we subtract one from each + * folio refcount. * - * Note that the argument can be an array of pages, encoded pages, - * or folio pointers. We ignore any encoded bits, and turn any of - * them into just a folio that gets free'd. + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. */ -void release_pages(release_pages_arg arg, int nr) +void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { int i; - struct encoded_page **encoded = arg.encoded_pages; LIST_HEAD(pages_to_free); struct lruvec *lruvec = NULL; unsigned long flags = 0; - unsigned int lock_batch; - for (i = 0; i < nr; i++) { - unsigned int nr_refs = 1; - struct folio *folio; - - /* Turn any of the argument types into a folio */ - folio = page_folio(encoded_page_ptr(encoded[i])); - - /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ - if (unlikely(encoded_page_flags(encoded[i]) & - ENCODED_PAGE_BIT_NR_PAGES_NEXT)) - nr_refs = encoded_nr_pages(encoded[++i]); - - /* - * Make sure the IRQ-safe lock-holding time does not get - * excessive with a continuous string of pages from the - * same lruvec. The lock is held only if lruvec != NULL. - */ - if (lruvec && ++lock_batch == SWAP_CLUSTER_MAX) { - unlock_page_lruvec_irqrestore(lruvec, flags); - lruvec = NULL; - } + for (i = 0; i < folios->nr; i++) { + struct folio *folio = folios->folios[i]; + unsigned int nr_refs = refs ? refs[i] : 1; if (is_huge_zero_page(&folio->page)) continue; @@ -1016,13 +998,8 @@ void release_pages(release_pages_arg arg, int nr) } if (folio_test_lru(folio)) { - struct lruvec *prev_lruvec = lruvec; - lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); - if (prev_lruvec != lruvec) - lock_batch = 0; - lruvec_del_folio(lruvec, folio); __folio_clear_lru_flags(folio); } @@ -1046,6 +1023,47 @@ void release_pages(release_pages_arg arg, int nr) mem_cgroup_uncharge_list(&pages_to_free); free_unref_page_list(&pages_to_free); + folio_batch_reinit(folios); +} +EXPORT_SYMBOL(folios_put_refs); + +/** + * release_pages - batched put_page() + * @arg: array of pages to release + * @nr: number of pages + * + * Decrement the reference count on all the pages in @arg. If it + * fell to zero, remove the page from the LRU and free it. + * + * Note that the argument can be an array of pages, encoded pages, + * or folio pointers. We ignore any encoded bits, and turn any of + * them into just a folio that gets free'd. + */ +void release_pages(release_pages_arg arg, int nr) +{ + struct folio_batch fbatch; + int refs[PAGEVEC_SIZE]; + struct encoded_page **encoded = arg.encoded_pages; + int i; + + folio_batch_init(&fbatch); + for (i = 0; i < nr; i++) { + /* Turn any of the argument types into a folio */ + struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); + + /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ + refs[fbatch.nr] = 1; + if (unlikely(encoded_page_flags(encoded[i]) & + ENCODED_PAGE_BIT_NR_PAGES_NEXT)) + refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); + + if (folio_batch_add(&fbatch, folio) > 0) + continue; + folios_put_refs(&fbatch, refs); + } + + if (fbatch.nr) + folios_put_refs(&fbatch, refs); } EXPORT_SYMBOL(release_pages); -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit 90491d87dd46a4c843dae775b9e72c91624c5a7b category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Iterate over a folio_batch rather than a linked list. This is easier for the CPU to prefetch and has a batch count naturally built in so we don't need to track it. Again, this lowers the maximum lock hold time from 32 folios to 15, but I do not expect this to have a significant effect. Link: https://lkml.kernel.org/r/20240227174254.710559-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Conflicts: mm/page_alloc.c [ Conflicts with dynamic pool, fix the code in free_unref_page_list(). ] Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/internal.h | 5 +++-- mm/page_alloc.c | 60 +++++++++++++++++++++++++++++-------------------- 2 files changed, 39 insertions(+), 26 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 6451747b7160..9d02b5a630e4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -635,8 +635,9 @@ extern void dpool_prep_new_page(struct page *page, unsigned int order, #endif extern int user_min_free_kbytes; -extern void free_unref_page(struct page *page, unsigned int order); -extern void free_unref_page_list(struct list_head *list); +void free_unref_page(struct page *page, unsigned int order); +void free_unref_folios(struct folio_batch *fbatch); +void free_unref_page_list(struct list_head *list); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 27f13b34760a..4e0a11a0b62a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -32,6 +32,7 @@ #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/cpuset.h> +#include <linux/pagevec.h> #include <linux/memory_hotplug.h> #include <linux/nodemask.h> #include <linux/vmstat.h> @@ -2554,64 +2555,57 @@ void free_unref_page(struct page *page, unsigned int order) } /* - * Free a list of 0-order pages + * Free a batch of 0-order pages */ -void free_unref_page_list(struct list_head *list) +void free_unref_folios(struct folio_batch *folios) { unsigned long __maybe_unused UP_flags; - struct folio *folio, *next; struct per_cpu_pages *pcp = NULL; struct zone *locked_zone = NULL; - int batch_count = 0; - int migratetype; + int i, j, migratetype; - /* Prepare pages for freeing */ - list_for_each_entry_safe(folio, next, list, lru) { + /* Prepare folios for freeing */ + for (i = 0, j = 0; i < folios->nr; i++) { + struct folio *folio = folios->folios[i]; unsigned long pfn = folio_pfn(folio); if (page_from_dynamic_pool(&folio->page)) { - list_del(&folio->lru); dynamic_pool_free_page(&folio->page); continue; } - if (!free_unref_page_prepare(&folio->page, pfn, 0)) { - list_del(&folio->lru); + if (!free_unref_page_prepare(&folio->page, pfn, 0)) continue; - } /* - * Free isolated pages directly to the allocator, see + * Free isolated folios directly to the allocator, see * comment in free_unref_page. */ migratetype = get_pcppage_migratetype(&folio->page); if (unlikely(is_migrate_isolate(migratetype))) { - list_del(&folio->lru); free_one_page(folio_zone(folio), &folio->page, pfn, 0, migratetype, FPI_NONE); continue; } + if (j != i) + folios->folios[j] = folio; + j++; } + folios->nr = j; - list_for_each_entry_safe(folio, next, list, lru) { + for (i = 0; i < folios->nr; i++) { + struct folio *folio = folios->folios[i]; struct zone *zone = folio_zone(folio); - list_del(&folio->lru); migratetype = get_pcppage_migratetype(&folio->page); - /* - * Either different zone requiring a different pcp lock or - * excessive lock hold times when freeing a large list of - * folios. - */ - if (zone != locked_zone || batch_count == SWAP_CLUSTER_MAX) { + /* Different zone requires a different pcp lock */ + if (zone != locked_zone) { if (pcp) { pcp_spin_unlock(pcp); pcp_trylock_finish(UP_flags); } - batch_count = 0; - /* * trylock is necessary as folios may be getting freed * from IRQ or SoftIRQ context after an IO completion. @@ -2638,13 +2632,31 @@ void free_unref_page_list(struct list_head *list) trace_mm_page_free_batched(&folio->page); free_unref_page_commit(zone, pcp, &folio->page, migratetype, 0); - batch_count++; } if (pcp) { pcp_spin_unlock(pcp); pcp_trylock_finish(UP_flags); } + folio_batch_reinit(folios); +} + +void free_unref_page_list(struct list_head *list) +{ + struct folio_batch fbatch; + + folio_batch_init(&fbatch); + while (!list_empty(list)) { + struct folio *folio = list_first_entry(list, struct folio, lru); + + list_del(&folio->lru); + if (folio_batch_add(&fbatch, folio) > 0) + continue; + free_unref_folios(&fbatch); + } + + if (fbatch.nr) + free_unref_folios(&fbatch); } /* -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit 4882c80975e2bf7241a5b043eb1dbe8df2726a29 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Almost identical to mem_cgroup_uncharge_list(), except it takes a folio_batch instead of a list_head. Link: https://lkml.kernel.org/r/20240227174254.710559-6-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- include/linux/memcontrol.h | 14 ++++++++++++-- mm/memcontrol.c | 13 +++++++++++++ 2 files changed, 25 insertions(+), 2 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8c199fe368c2..d137a1286777 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -837,10 +837,16 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) __mem_cgroup_uncharge_list(page_list); } -void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages); +void __mem_cgroup_uncharge_folios(struct folio_batch *folios); +static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_uncharge_folios(folios); +} +void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_replace_folio(struct folio *old, struct folio *new); - void mem_cgroup_migrate(struct folio *old, struct folio *new); /** @@ -1425,6 +1431,10 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } +static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) +{ +} + static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fff8b9322521..a3824f608254 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -33,6 +33,7 @@ #include <linux/shmem_fs.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> +#include <linux/pagevec.h> #include <linux/vm_event_item.h> #include <linux/smp.h> #include <linux/page-flags.h> @@ -8601,6 +8602,18 @@ void __mem_cgroup_uncharge_list(struct list_head *page_list) uncharge_batch(&ug); } +void __mem_cgroup_uncharge_folios(struct folio_batch *folios) +{ + struct uncharge_gather ug; + unsigned int i; + + uncharge_gather_clear(&ug); + for (i = 0; i < folios->nr; i++) + uncharge_folio(folios->folios[i], &ug); + if (ug.memcg) + uncharge_batch(&ug); +} + /** * mem_cgroup_replace_folio - Charge a folio's replacement. * @old: Currently circulating folio. -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit 24835f899c0129a4733e899e4da20e2e72f40bd9 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Break up the list of folios into batches here so that the folios are more likely to be cache hot when doing the rest of the processing. Link: https://lkml.kernel.org/r/20240227174254.710559-8-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/swap.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/mm/swap.c b/mm/swap.c index ee8b131bf32c..ad3f2e9448a4 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -138,22 +138,25 @@ EXPORT_SYMBOL(__folio_put); */ void put_pages_list(struct list_head *pages) { - struct folio *folio, *next; + struct folio_batch fbatch; + struct folio *folio; - list_for_each_entry_safe(folio, next, pages, lru) { - if (!folio_put_testzero(folio)) { - list_del(&folio->lru); + folio_batch_init(&fbatch); + list_for_each_entry(folio, pages, lru) { + if (!folio_put_testzero(folio)) continue; - } if (folio_test_large(folio)) { - list_del(&folio->lru); __folio_put_large(folio); continue; } /* LRU flag must be clear because it's passed using the lru */ + if (folio_batch_add(&fbatch, folio) > 0) + continue; + free_unref_folios(&fbatch); } - free_unref_page_list(pages); + if (fbatch.nr) + free_unref_folios(&fbatch); INIT_LIST_HEAD(pages); } EXPORT_SYMBOL(put_pages_list); -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit 31b2ff82aefb33ce92496a1becddd6ce51060db2 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Call folio_undo_large_rmappable() if needed. free_unref_page_prepare() destroys the ability to call folio_order(), so stash the order in folio->private for the benefit of the second loop. Link: https://lkml.kernel.org/r/20240227174254.710559-10-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Conflicts: mm/page_alloc.c [ Conflicts with dynamic pool, fix the code in free_unref_folios(). ] Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/page_alloc.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4e0a11a0b62a..b09e69f14925 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2555,7 +2555,7 @@ void free_unref_page(struct page *page, unsigned int order) } /* - * Free a batch of 0-order pages + * Free a batch of folios */ void free_unref_folios(struct folio_batch *folios) { @@ -2568,25 +2568,30 @@ void free_unref_folios(struct folio_batch *folios) for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsigned long pfn = folio_pfn(folio); + unsigned int order = folio_order(folio); if (page_from_dynamic_pool(&folio->page)) { dynamic_pool_free_page(&folio->page); continue; } - if (!free_unref_page_prepare(&folio->page, pfn, 0)) + if (order > 0 && folio_test_large_rmappable(folio)) + folio_undo_large_rmappable(folio); + if (!free_unref_page_prepare(&folio->page, pfn, order)) continue; /* - * Free isolated folios directly to the allocator, see - * comment in free_unref_page. + * Free isolated folios and orders not handled on the PCP + * directly to the allocator, see comment in free_unref_page. */ migratetype = get_pcppage_migratetype(&folio->page); - if (unlikely(is_migrate_isolate(migratetype))) { + if (!pcp_allowed_order(order) || + is_migrate_isolate(migratetype)) { free_one_page(folio_zone(folio), &folio->page, pfn, - 0, migratetype, FPI_NONE); + order, migratetype, FPI_NONE); continue; } + folio->private = (void *)(unsigned long)order; if (j != i) folios->folios[j] = folio; j++; @@ -2596,7 +2601,9 @@ void free_unref_folios(struct folio_batch *folios) for (i = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; struct zone *zone = folio_zone(folio); + unsigned int order = (unsigned long)folio->private; + folio->private = NULL; migratetype = get_pcppage_migratetype(&folio->page); /* Different zone requires a different pcp lock */ @@ -2615,7 +2622,7 @@ void free_unref_folios(struct folio_batch *folios) if (unlikely(!pcp)) { pcp_trylock_finish(UP_flags); free_one_page(zone, &folio->page, - folio_pfn(folio), 0, + folio_pfn(folio), order, migratetype, FPI_NONE); locked_zone = NULL; continue; @@ -2631,7 +2638,8 @@ void free_unref_folios(struct folio_batch *folios) migratetype = MIGRATE_MOVABLE; trace_mm_page_free_batched(&folio->page); - free_unref_page_commit(zone, pcp, &folio->page, migratetype, 0); + free_unref_page_commit(zone, pcp, &folio->page, migratetype, + order); } if (pcp) { -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit bc2ff4cbc3294c01f29449405c42ee26ee0e1f59 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Use free_unref_page_batch() to free the folios. This may increase the number of IPIs from calling try_to_unmap_flush() more often, but that's going to be very workload-dependent. It may even reduce the number of IPIs as we now batch-free large folios instead of freeing them one at a time. Link: https://lkml.kernel.org/r/20240227174254.710559-12-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: David Hildenbrand <david@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/vmscan.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 34614bb7062d..f3ed46d5c7d7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1711,14 +1711,15 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { + struct folio_batch free_folios; LIST_HEAD(ret_folios); - LIST_HEAD(free_folios); LIST_HEAD(demote_folios); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; + folio_batch_init(&free_folios); memset(stat, 0, sizeof(*stat)); cond_resched(); do_demote_pass = can_demote(pgdat->node_id, sc); @@ -2134,14 +2135,11 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, */ nr_reclaimed += nr_pages; - /* - * Is there need to periodically free_folio_list? It would - * appear not as the counts should be low - */ - if (unlikely(folio_test_large(folio))) - destroy_large_folio(folio); - else - list_add(&folio->lru, &free_folios); + if (folio_batch_add(&free_folios, folio) == 0) { + mem_cgroup_uncharge_folios(&free_folios); + try_to_unmap_flush(); + free_unref_folios(&free_folios); + } continue; activate_locked_split: @@ -2205,9 +2203,9 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; - mem_cgroup_uncharge_list(&free_folios); + mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); - free_unref_page_list(&free_folios); + free_unref_folios(&free_folios); list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit be5a9e17a2ccbecfb7020aa1938e2c62d8a9189c category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- All users have been converted to mem_cgroup_uncharge_folios() so we can remove this API. Link: https://lkml.kernel.org/r/20240227174254.710559-14-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- include/linux/memcontrol.h | 12 ------------ mm/memcontrol.c | 19 ------------------- 2 files changed, 31 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7381a34d9c17..b2a80e089a0a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -829,14 +829,6 @@ static inline void mem_cgroup_uncharge(struct folio *folio) __mem_cgroup_uncharge(folio); } -void __mem_cgroup_uncharge_list(struct list_head *page_list); -static inline void mem_cgroup_uncharge_list(struct list_head *page_list) -{ - if (mem_cgroup_disabled()) - return; - __mem_cgroup_uncharge_list(page_list); -} - void __mem_cgroup_uncharge_folios(struct folio_batch *folios); static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { @@ -1427,10 +1419,6 @@ static inline void mem_cgroup_uncharge(struct folio *folio) { } -static inline void mem_cgroup_uncharge_list(struct list_head *page_list) -{ -} - static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a3824f608254..9951efb06d7b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -8583,25 +8583,6 @@ void __mem_cgroup_uncharge(struct folio *folio) uncharge_batch(&ug); } -/** - * __mem_cgroup_uncharge_list - uncharge a list of page - * @page_list: list of pages to uncharge - * - * Uncharge a list of pages previously charged with - * __mem_cgroup_charge(). - */ -void __mem_cgroup_uncharge_list(struct list_head *page_list) -{ - struct uncharge_gather ug; - struct folio *folio; - - uncharge_gather_clear(&ug); - list_for_each_entry(folio, page_list, lru) - uncharge_folio(folio, &ug); - if (ug.memcg) - uncharge_batch(&ug); -} - void __mem_cgroup_uncharge_folios(struct folio_batch *folios) { struct uncharge_gather ug; -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit f39ec4dcb9e9b03b2a280829b8c15e3ae607398c category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The last user was removed over a year ago; remove the definition. Link: https://lkml.kernel.org/r/20240227174254.710559-16-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index ca70fe2405c7..0d570b3eb301 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -228,7 +228,6 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) -#define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit d4111eecdc3c2a5eabafcc467dbfce0e216fa485 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- These pages are all chained together through the lru list, so we know they're folios. Use the folio APIs to save three hidden calls to compound_head(). Link: https://lkml.kernel.org/r/20240227174254.710559-18-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Conflicts: mm/khugepaged.c [ Context conflicts with memory reliable. ] Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/khugepaged.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 7d329e9eeec8..75dcd160735b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -695,9 +695,7 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte, spinlock_t *ptl, struct list_head *compound_pagelist) { - struct folio *src_folio; - struct page *src_page; - struct page *tmp; + struct folio *src, *tmp; pte_t *_pte; pte_t pteval; @@ -716,10 +714,11 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte, ksm_might_unmap_zero_page(vma->vm_mm, pteval); } } else { - src_page = pte_page(pteval); - src_folio = page_folio(src_page); - if (!folio_test_large(src_folio)) - release_pte_folio(src_folio); + struct page *src_page = pte_page(pteval); + + src = page_folio(src_page); + if (!folio_test_large(src)) + release_pte_folio(src); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats @@ -728,20 +727,19 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte, spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); add_reliable_page_counter(src_page, vma->vm_mm, 1); - folio_remove_rmap_pte(src_folio, src_page, vma); + folio_remove_rmap_pte(src, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } - list_for_each_entry_safe(src_page, tmp, compound_pagelist, lru) { - list_del(&src_page->lru); - mod_node_page_state(page_pgdat(src_page), - NR_ISOLATED_ANON + page_is_file_lru(src_page), - -compound_nr(src_page)); - unlock_page(src_page); - free_swap_cache(src_page); - putback_lru_page(src_page); + list_for_each_entry_safe(src, tmp, compound_pagelist, lru) { + list_del(&src->lru); + node_stat_sub_folio(src, NR_ISOLATED_ANON + + folio_is_file_lru(src)); + folio_unlock(src); + free_swap_cache(&src->page); + folio_putback_lru(src); } } -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc1 commit 47932e7048df9156e96133ee90fb3e9df68dbd15 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- When freeing a large folio, we must remove it from the deferred split list before we uncharge it as each memcg has its own deferred split list (with associated lock) and removing a folio from the deferred split list while holding the wrong lock will corrupt that list and cause various related problems. Link: https://lore.kernel.org/linux-mm/367a14f7-340e-4b29-90ae-bc3fcefdd5f4@arm.co... Link: https://lkml.kernel.org/r/20240311191835.312162-1-willy@infradead.org Fixes: f77171d241e3 (mm: allow non-hugetlb large folios to be batch processed) Fixes: 29f3843026cf (mm: free folios directly in move_folios_to_lru()) Fixes: bc2ff4cbc329 (mm: free folios in a batch in shrink_folio_list()) Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Debugged-by: Ryan Roberts <ryan.roberts@arm.com> Tested-by: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/swap.c | 3 +++ mm/vmscan.c | 6 ++++++ 2 files changed, 9 insertions(+) diff --git a/mm/swap.c b/mm/swap.c index 6b697d33fa5b..e43a5911b170 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1012,6 +1012,9 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) free_huge_folio(folio); continue; } + if (folio_test_large(folio) && + folio_test_large_rmappable(folio)) + folio_undo_large_rmappable(folio); __page_cache_release(folio, &lruvec, &flags); diff --git a/mm/vmscan.c b/mm/vmscan.c index d88f9b8fd5d3..44154c63ec6c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2135,6 +2135,9 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, */ nr_reclaimed += nr_pages; + if (folio_test_large(folio) && + folio_test_large_rmappable(folio)) + folio_undo_large_rmappable(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); @@ -2542,6 +2545,9 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec, if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); + if (folio_test_large(folio) && + folio_test_large_rmappable(folio)) + folio_undo_large_rmappable(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.9-rc2 commit 9cecde80aae0fb0aa44425575d5aca71bc646d89 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- On a 104 thread, 2 socket Skylake system, Intel report a 4.7% performance reduction with will-it-scale page_fault2. This was due to reducing the size of the batch from 32 to 15. Increasing the folio batch size from 15 to 31 gives a performance increase of 12.5% relative to the original, or 17.2% relative to the reduced performance commit. The penalty of this commit is an additional 128 bytes of stack usage. Six folio_batches are also allocated from percpu memory in cpu_fbatches so that will be an additional 768 bytes of percpu memory (per CPU). Tim Chen originally submitted a patch like this in 2020: https://lore.kernel.org/linux-mm/d1cc9f12a8ad6c2a52cb600d93b06b064f2bbc57.15... Link: https://lkml.kernel.org/r/20240315140823.2478146-1-willy@infradead.org Fixes: 99fbb6bfc16f ("mm: make folios_put() the basis of release_pages()") Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Yujie Liu <yujie.liu@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202403151058.7048f6a8-oliver.sang@intel.com Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- include/linux/pagevec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 87cc678adc85..67f10b8810a8 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -11,8 +11,8 @@ #include <linux/types.h> -/* 15 pointers + header align the folio_batch structure to a power of two */ -#define PAGEVEC_SIZE 15 +/* 31 pointers + header align the folio_batch structure to a power of two */ +#define PAGEVEC_SIZE 31 struct folio; -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.10-rc1 commit 5b8d75913a0ed9deb16140c0aa880c4d6db2dc62 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The pcp_allowed_order() check in free_the_page() was only being skipped by __folio_put_small() which is about to be rearranged. Link: https://lkml.kernel.org/r/20240405153228.2563754-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Conflicts: mm/page_alloc.c [ Context conflicts with commit 17edeb5d3f76 and cc92eba1c88b. ] Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/page_alloc.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 315c3fdaa62b..19ba7cf4e80d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -567,14 +567,6 @@ static inline bool pcp_allowed_order(unsigned int order) return false; } -static inline void free_the_page(struct page *page, unsigned int order) -{ - if (pcp_allowed_order(order)) /* Via pcp? */ - free_unref_page(page, order); - else - __free_pages_ok(page, order, FPI_NONE); -} - /* * Higher-order pages are called "compound pages". They are structured thusly: * @@ -610,7 +602,7 @@ void destroy_large_folio(struct folio *folio) folio_undo_large_rmappable(folio); mem_cgroup_uncharge(folio); - free_the_page(&folio->page, folio_order(folio)); + free_unref_page(&folio->page, folio_order(folio)); } static inline void set_buddy_order(struct page *page, unsigned int order) @@ -2523,6 +2515,11 @@ void free_unref_page(struct page *page, unsigned int order) return; } + if (!pcp_allowed_order(order)) { + __free_pages_ok(page, order, FPI_NONE); + return; + } + if (!free_unref_page_prepare(page, pfn, order)) return; @@ -4909,10 +4906,10 @@ void __free_pages(struct page *page, unsigned int order) int head = PageHead(page); if (put_page_testzero(page)) - free_the_page(page, order); + free_unref_page(page, order); else if (!head) while (order-- > 0) - free_the_page(page + (1 << order), order); + free_unref_page(page + (1 << order), order); } EXPORT_SYMBOL(__free_pages); @@ -4963,7 +4960,7 @@ void __page_frag_cache_drain(struct page *page, unsigned int count) VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); if (page_ref_sub_and_test(page, count)) - free_the_page(page, compound_order(page)); + free_unref_page(page, compound_order(page)); } EXPORT_SYMBOL(__page_frag_cache_drain); @@ -5004,7 +5001,7 @@ void *page_frag_alloc_align(struct page_frag_cache *nc, goto refill; if (unlikely(nc->pfmemalloc)) { - free_the_page(page, compound_order(page)); + free_unref_page(page, compound_order(page)); goto refill; } @@ -5048,7 +5045,7 @@ void page_frag_free(void *addr) struct page *page = virt_to_head_page(addr); if (unlikely(put_page_testzero(page))) - free_the_page(page, compound_order(page)); + free_unref_page(page, compound_order(page)); } EXPORT_SYMBOL(page_frag_free); -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.10-rc1 commit 79a48287515848c18a49d75c1fdf176c82bb13cf category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- It's now obvious that __folio_put_small() and __folio_put_large() do almost exactly the same thing. Inline them both into __folio_put(). Link: https://lkml.kernel.org/r/20240405153228.2563754-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/swap.c | 32 ++++++-------------------------- 1 file changed, 6 insertions(+), 26 deletions(-) diff --git a/mm/swap.c b/mm/swap.c index 862a8e69def6..f6921d3b4862 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -112,42 +112,22 @@ static void page_cache_release(struct folio *folio) unlock_page_lruvec_irqrestore(lruvec, flags); } -static void __folio_put_small(struct folio *folio) -{ - page_cache_release(folio); - mem_cgroup_uncharge(folio); - free_unref_page(&folio->page, 0); -} - -static void __folio_put_large(struct folio *folio) +void __folio_put(struct folio *folio) { - /* - * __page_cache_release() is supposed to be called for thp, not for - * hugetlb. This is because hugetlb page does never have PageLRU set - * (it's never listed to any LRU lists) and no memcg routines should - * be called for hugetlb (it has a separate hugetlb_cgroup.) - */ - if (folio_test_hugetlb(folio)) { + if (unlikely(folio_is_zone_device(folio))) { + free_zone_device_page(&folio->page); + return; + } else if (folio_test_hugetlb(folio)) { free_huge_folio(folio); return; } page_cache_release(folio); - if (folio_test_large_rmappable(folio)) + if (folio_test_large(folio) && folio_test_large_rmappable(folio)) folio_undo_large_rmappable(folio); mem_cgroup_uncharge(folio); free_unref_page(&folio->page, folio_order(folio)); } - -void __folio_put(struct folio *folio) -{ - if (unlikely(folio_is_zone_device(folio))) - free_zone_device_page(&folio->page); - else if (unlikely(folio_test_large(folio))) - __folio_put_large(folio); - else - __folio_put_small(folio); -} EXPORT_SYMBOL(__folio_put); /** -- 2.25.1

From: Richard Chang <richardycc@google.com> mainline inclusion from mainline-v6.9-rc1 commit c8b36003121834cb77fcaf8a1ce0a454d7a97891 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- alloc_contig_migrate_range has every information to be able to understand big contiguous allocation latency. For example, how many pages are migrated, how many times they were needed to unmap from page tables. This patch adds the trace event to collect the allocation statistics. In the field, it was quite useful to understand CMA allocation latency. [akpm@linux-foundation.org: a/trace_mm_alloc_config_migrate_range_info_enabled/trace_mm_alloc_contig_migrate_range_info_enabled] Link: https://lkml.kernel.org/r/20240228051127.2859472-1-richardycc@google.com Signed-off-by: Richard Chang <richardycc@google.com> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org. Cc: Martin Liu <liumartin@google.com> Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- include/trace/events/kmem.h | 38 +++++++++++++++++++++++++++++++++++++ mm/internal.h | 3 ++- mm/page_alloc.c | 32 ++++++++++++++++++++++++++----- mm/page_isolation.c | 2 +- 4 files changed, 68 insertions(+), 7 deletions(-) diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index be39ca5af0ba..a4e40ae6a8c8 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -304,6 +304,44 @@ TRACE_EVENT(mm_page_alloc_extfrag, __entry->change_ownership) ); +TRACE_EVENT(mm_alloc_contig_migrate_range_info, + + TP_PROTO(unsigned long start, + unsigned long end, + unsigned long nr_migrated, + unsigned long nr_reclaimed, + unsigned long nr_mapped, + int migratetype), + + TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, migratetype), + + TP_STRUCT__entry( + __field(unsigned long, start) + __field(unsigned long, end) + __field(unsigned long, nr_migrated) + __field(unsigned long, nr_reclaimed) + __field(unsigned long, nr_mapped) + __field(int, migratetype) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + __entry->nr_migrated = nr_migrated; + __entry->nr_reclaimed = nr_reclaimed; + __entry->nr_mapped = nr_mapped; + __entry->migratetype = migratetype; + ), + + TP_printk("start=0x%lx end=0x%lx migratetype=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu", + __entry->start, + __entry->end, + __entry->migratetype, + __entry->nr_migrated, + __entry->nr_reclaimed, + __entry->nr_mapped) +); + /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ diff --git a/mm/internal.h b/mm/internal.h index fad7d8bf2e32..6983493b997e 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -725,7 +725,8 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int __alloc_contig_migrate_range(struct compact_control *cc, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + int migratetype); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9780cc3c8365..f450bc4a4637 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6458,9 +6458,14 @@ static void alloc_contig_dump_pages(struct list_head *page_list) } } -/* [start, end) must belong to a single zone. */ +/* + * [start, end) must belong to a single zone. + * @migratetype: using migratetype to filter the type of migration in + * trace_mm_alloc_contig_migrate_range_info. + */ int __alloc_contig_migrate_range(struct compact_control *cc, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, + int migratetype) { /* This function is based on compact_zone() from compaction.c. */ unsigned int nr_reclaimed; @@ -6471,6 +6476,10 @@ int __alloc_contig_migrate_range(struct compact_control *cc, .nid = zone_to_nid(cc->zone), .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, }; + struct page *page; + unsigned long total_mapped = 0; + unsigned long total_migrated = 0; + unsigned long total_reclaimed = 0; lru_cache_disable(); @@ -6496,9 +6505,18 @@ int __alloc_contig_migrate_range(struct compact_control *cc, &cc->migratepages); cc->nr_migratepages -= nr_reclaimed; + if (trace_mm_alloc_contig_migrate_range_info_enabled()) { + total_reclaimed += nr_reclaimed; + list_for_each_entry(page, &cc->migratepages, lru) + total_mapped += page_mapcount(page); + } + ret = migrate_pages(&cc->migratepages, alloc_migration_target, NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE, NULL); + if (trace_mm_alloc_contig_migrate_range_info_enabled() && !ret) + total_migrated += cc->nr_migratepages; + /* * On -ENOMEM, migrate_pages() bails out right away. It is pointless * to retry again over this error, so do the same here. @@ -6512,9 +6530,13 @@ int __alloc_contig_migrate_range(struct compact_control *cc, if (!(cc->gfp_mask & __GFP_NOWARN) && ret == -EBUSY) alloc_contig_dump_pages(&cc->migratepages); putback_movable_pages(&cc->migratepages); - return ret; } - return 0; + + trace_mm_alloc_contig_migrate_range_info(start, end, migratetype, + total_migrated, + total_reclaimed, + total_mapped); + return (ret < 0) ? ret : 0; } /** @@ -6594,7 +6616,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, * allocated. So, if we fall through be sure to clear ret so that * -EBUSY is not accidentally used or returned to caller. */ - ret = __alloc_contig_migrate_range(&cc, start, end); + ret = __alloc_contig_migrate_range(&cc, start, end, migratetype); if (ret && ret != -EBUSY) goto done; ret = 0; diff --git a/mm/page_isolation.c b/mm/page_isolation.c index fefc8a926944..09eb445cfde9 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -437,7 +437,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, } ret = __alloc_contig_migrate_range(&cc, head_pfn, - head_pfn + nr_pages); + head_pfn + nr_pages, page_mt); /* * restore the page's migratetype so that it can -- 2.25.1

From: Mike Kravetz <mike.kravetz@oracle.com> mainline inclusion from mainline-v6.7-rc1 commit 30a89adf872d2e46323840964c95dc0ae3bb5843 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- In commit d8f5f7e445f0 ("hugetlb: set hugetlb page flag before optimizing vmemmap") checks were added to print a warning if hugetlb_vmemmap_restore was called on a non-hugetlb page. This was mostly due to ordering issues in the hugetlb page set up and tear down sequencees. One place missed was the routine dissolve_free_huge_page. Naoya Horiguchi noted: "I saw that VM_WARN_ON_ONCE() in hugetlb_vmemmap_restore is triggered when memory_failure() is called on a free hugetlb page with vmemmap optimization disabled (the warning is not triggered if vmemmap optimization is enabled). I think that we need check folio_test_hugetlb() before dissolve_free_huge_page() calls hugetlb_vmemmap_restore_folio()." Perform the check as suggested by Naoya. Link: https://lkml.kernel.org/r/20231017032140.GA3680@monkey Fixes: d8f5f7e445f0 ("hugetlb: set hugetlb page flag before optimizing vmemmap") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Suggested-by: Naoya Horiguchi <naoya.horiguchi@linux.dev> Tested-by: Naoya Horiguchi <naoya.horiguchi@linux.dev> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Barry Song <song.bao.hua@hisilicon.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Xiongchun Duan <duanxiongchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/hugetlb.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 270ee50a9b5a..4c48bbe39407 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2411,17 +2411,23 @@ int dissolve_free_huge_page(struct page *page) * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. + * + * The folio_test_hugetlb check here is because + * remove_hugetlb_folio will clear hugetlb folio flag for + * non-vmemmap optimized hugetlb folios. */ - rc = hugetlb_vmemmap_restore(h, &folio->page); - if (!rc) { - update_and_free_hugetlb_folio(h, folio, false); - } else { - spin_lock_irq(&hugetlb_lock); - add_hugetlb_folio(h, folio, false); - h->max_huge_pages++; - spin_unlock_irq(&hugetlb_lock); - } + if (folio_test_hugetlb(folio)) { + rc = hugetlb_vmemmap_restore(h, &folio->page); + if (rc) { + spin_lock_irq(&hugetlb_lock); + add_hugetlb_folio(h, folio, false); + h->max_huge_pages++; + goto out; + } + } else + rc = 0; + update_and_free_hugetlb_folio(h, folio, false); return rc; } out: -- 2.25.1

From: Lucas Stach <l.stach@pengutronix.de> mainline inclusion from mainline-v6.10-rc1 commit 55f77df7d715110299f12c27f4365bd6332d1adb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Patch series "mm/treewide: Remove pXd_huge() API", v2. In previous work [1], we removed the pXd_large() API, which is arch specific. This patchset further removes the hugetlb pXd_huge() API. Hugetlb was never special on creating huge mappings when compared with other huge mappings. Having a standalone API just to detect such pgtable entries is more or less redundant, especially after the pXd_leaf() API set is introduced with/without CONFIG_HUGETLB_PAGE. When looking at this problem, a few issues are also exposed that we don't have a clear definition of the *_huge() variance API. This patchset started by cleaning these issues first, then replace all *_huge() users to use *_leaf(), then drop all *_huge() code. On x86/sparc, swap entries will be reported "true" in pXd_huge(), while for all the rest archs they're reported "false" instead. This part is done in patch 1-5, in which I suspect patch 1 can be seen as a bug fix, but I'll leave that to hmm experts to decide. Besides, there are three archs (arm, arm64, powerpc) that have slightly different definitions between the *_huge() v.s. *_leaf() variances. I tackled them separately so that it'll be easier for arch experts to chim in when necessary. This part is done in patch 6-9. The final patches 10-14 do the rest on the final removal, since *_leaf() will be the ultimate API in the future, and we seem to have quite some confusions on how *_huge() APIs can be defined, provide a rich comment for *_leaf() API set to define them properly to avoid future misuse, and hopefully that'll also help new archs to start support huge mappings and avoid traps (like either swap entries, or PROT_NONE entry checks). [1] https://lore.kernel.org/r/20240305043750.93762-1-peterx@redhat.com This patch (of 14): When the complete PCP is drained a much larger number of pages than the usual batch size might be freed at once, causing large IRQ and preemption latency spikes, as they are all freed while holding the pcp and zone spinlocks. To avoid those latency spikes, limit the number of pages freed in a single bulk operation to common batch limits. Link: https://lkml.kernel.org/r/20240318200404.448346-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20240318200736.2835502-1-l.stach@pengutronix.de Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Signed-off-by: Peter Xu <peterx@redhat.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andreas Larsson <andreas@gaisler.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bjorn Andersson <andersson@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Fabio Estevam <festevam@denx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konrad Dybcio <konrad.dybcio@linaro.org> Cc: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Cc: Mark Salter <msalter@redhat.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Naoya Horiguchi <nao.horiguchi@gmail.com> Cc: "Naveen N. Rao" <naveen.n.rao@linux.ibm.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Shawn Guo <shawnguo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/page_alloc.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f450bc4a4637..2225e08d1c8e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2228,12 +2228,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) */ static void drain_pages_zone(unsigned int cpu, struct zone *zone) { - struct per_cpu_pages *pcp; + struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + int count = READ_ONCE(pcp->count); + + while (count) { + int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX); + count -= to_drain; - pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - if (pcp->count) { spin_lock(&pcp->lock); - free_pcppages_bulk(zone, pcp->count, pcp, 0); + free_pcppages_bulk(zone, to_drain, pcp, 0); spin_unlock(&pcp->lock); } } -- 2.25.1

From: "Vishal Moola (Oracle)" <vishal.moola@gmail.com> mainline inclusion from mainline-v6.9-rc1 commit 997f0ecb11da15602a3d34e10f9ca8418db794d0 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Patch series "Handle hugetlb faults under the VMA lock", v2. It is generally safe to handle hugetlb faults under the VMA lock. The only time this is unsafe is when no anon_vma has been allocated to this vma yet, so we can use vmf_anon_prepare() instead of anon_vma_prepare() to bailout if necessary. This should only happen for the first hugetlb page in the vma. Additionally, this patchset begins to use struct vm_fault within hugetlb_fault(). This works towards cleaning up hugetlb code, and should significantly reduce the number of arguments passed to functions. The last patch in this series may cause ltp hugemmap10 to "fail". This is because vmf_anon_prepare() may bailout with no anon_vma under the VMA lock after allocating a folio for the hugepage. In free_huge_folio(), this folio is completely freed on bailout iff there is a surplus of hugetlb pages. This will remove a folio off the freelist and decrement the number of hugepages while ltp expects these counters to remain unchanged on failure. The rest of the ltp testcases pass. This patch (of 2): In order to handle hugetlb faults under the VMA lock, hugetlb can use vmf_anon_prepare() to ensure we can safely prepare an anon_vma. Change it to be a non-static function so it can be used within hugetlb as well. Link: https://lkml.kernel.org/r/20240221234732.187629-6-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20240221234732.187629-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Muchun Song <muchun.song@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/internal.h | 1 + mm/memory.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/internal.h b/mm/internal.h index 65e06f06d26b..0ecbaa392054 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -282,6 +282,7 @@ static inline void wake_throttle_isolated(pg_data_t *pgdat) wake_up(wqh); } +vm_fault_t vmf_anon_prepare(struct vm_fault *vmf); vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); diff --git a/mm/memory.c b/mm/memory.c index ed275401e695..776f59299900 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3215,7 +3215,7 @@ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf) return VM_FAULT_RETRY; } -static vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) +vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; -- 2.25.1

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v6.10-rc1 commit a373baed5a9dca65a4d9fa55e61800a18c9936f1 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9R3AY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Instead of checking the anon_vma early in the fault path where all page faults pay the cost, delay it until we know we're going to need the anon_vma to be filled in. This will have a slight negative effect on the first fault in an anonymous VMA, but it shortens every other page fault. It also makes the code slightly cleaner as the anon and file backed fault handling look more similar. The Intel kernel test bot reports a 3x improvement in vm-scalability throughput with the small-allocs-mt test. This is clearly an extreme situation that won't be replicated in any real-world workload, but it's a nice win. https://lore.kernel.org/all/202404261055.c5e24608-oliver.sang@intel.com/ Link: https://lkml.kernel.org/r/20240426144506.1290619-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Jann Horn <jannh@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/huge_memory.c | 6 ++++-- mm/memory.c | 29 ++++++++++++++++++----------- 2 files changed, 22 insertions(+), 13 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 04ca43ce7a36..18ec0e138b03 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1225,11 +1225,13 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) gfp_t gfp; struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + vm_fault_t ret; if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return VM_FAULT_FALLBACK; - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; + ret = vmf_anon_prepare(vmf); + if (ret) + return ret; khugepaged_enter_vma(vma, vma->vm_flags); if (!(vmf->flags & FAULT_FLAG_WRITE) && diff --git a/mm/memory.c b/mm/memory.c index 776f59299900..0a3e0f680f90 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3215,6 +3215,21 @@ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf) return VM_FAULT_RETRY; } +/** + * vmf_anon_prepare - Prepare to handle an anonymous fault. + * @vmf: The vm_fault descriptor passed from the fault handler. + * + * When preparing to insert an anonymous page into a VMA from a + * fault handler, call this function rather than anon_vma_prepare(). + * If this vma does not already have an associated anon_vma and we are + * only protected by the per-VMA lock, the caller must retry with the + * mmap_lock held. __anon_vma_prepare() will look at adjacent VMAs to + * determine if this VMA can share its anon_vma, and that's not safe to + * do with only the per-VMA lock held for this VMA. + * + * Return: 0 if fault handling can proceed. Any other value should be + * returned to the caller. + */ vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; @@ -4418,8 +4433,9 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } /* Allocate our own private page. */ - if (unlikely(anon_vma_prepare(vma))) - goto oom; + ret = vmf_anon_prepare(vmf); + if (ret) + return ret; /* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */ folio = alloc_anon_folio(vmf); if (IS_ERR(folio)) @@ -5803,15 +5819,6 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, if (!vma_start_read(vma)) goto inval; - /* - * find_mergeable_anon_vma uses adjacent vmas which are not locked. - * This check must happen after vma_start_read(); otherwise, a - * concurrent mremap() with MREMAP_DONTUNMAP could dissociate the VMA - * from its anon_vma. - */ - if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) - goto inval_end_read; - /* Check since vm_start/vm_end might change before we lock the VMA */ if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto inval_end_read; -- 2.25.1