From 545994197ad8ab96eb709b870b44d94bcca66692 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 4 Aug 2025 14:13:52 +0200 Subject: [PATCH 1/5] mm: rename huge_zero_page to huge_zero_folio As we already moved from exposing huge_zero_page to huge_zero_folio, change the name of the shrinker and the other helper function to reflect that. No functional changes. Reviewed-by: Lorenzo Stoakes Suggested-by: David Hildenbrand Acked-by: David Hildenbrand Signed-off-by: Pankaj Raghav --- mm/huge_memory.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9c38a95e9f091..46df57b2c0775 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -207,7 +207,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, return orders; } -static bool get_huge_zero_page(void) +static bool get_huge_zero_folio(void) { struct folio *zero_folio; retry: @@ -237,7 +237,7 @@ static bool get_huge_zero_page(void) return true; } -static void put_huge_zero_page(void) +static void put_huge_zero_folio(void) { /* * Counter should never go to zero here. Only shrinker can put @@ -251,11 +251,11 @@ struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) return READ_ONCE(huge_zero_folio); - if (!get_huge_zero_page()) + if (!get_huge_zero_folio()) return NULL; if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) - put_huge_zero_page(); + put_huge_zero_folio(); return READ_ONCE(huge_zero_folio); } @@ -263,18 +263,18 @@ struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) void mm_put_huge_zero_folio(struct mm_struct *mm) { if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) - put_huge_zero_page(); + put_huge_zero_folio(); } -static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long shrink_huge_zero_folio_count(struct shrinker *shrink, + struct shrink_control *sc) { /* we can free zero page only if last reference remains */ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; } -static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long shrink_huge_zero_folio_scan(struct shrinker *shrink, + struct shrink_control *sc) { if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct folio *zero_folio = xchg(&huge_zero_folio, NULL); @@ -287,7 +287,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, return 0; } -static struct shrinker *huge_zero_page_shrinker; +static struct shrinker *huge_zero_folio_shrinker; #ifdef CONFIG_SYSFS static ssize_t enabled_show(struct kobject *kobj, @@ -849,8 +849,8 @@ static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj) static int __init thp_shrinker_init(void) { - huge_zero_page_shrinker = shrinker_alloc(0, "thp-zero"); - if (!huge_zero_page_shrinker) + huge_zero_folio_shrinker = shrinker_alloc(0, "thp-zero"); + if (!huge_zero_folio_shrinker) return -ENOMEM; deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | @@ -858,13 +858,13 @@ static int __init thp_shrinker_init(void) SHRINKER_NONSLAB, "thp-deferred_split"); if (!deferred_split_shrinker) { - shrinker_free(huge_zero_page_shrinker); + shrinker_free(huge_zero_folio_shrinker); return -ENOMEM; } - huge_zero_page_shrinker->count_objects = shrink_huge_zero_page_count; - huge_zero_page_shrinker->scan_objects = shrink_huge_zero_page_scan; - shrinker_register(huge_zero_page_shrinker); + huge_zero_folio_shrinker->count_objects = shrink_huge_zero_folio_count; + huge_zero_folio_shrinker->scan_objects = shrink_huge_zero_folio_scan; + shrinker_register(huge_zero_folio_shrinker); deferred_split_shrinker->count_objects = deferred_split_count; deferred_split_shrinker->scan_objects = deferred_split_scan; @@ -875,7 +875,7 @@ static int __init thp_shrinker_init(void) static void __init thp_shrinker_exit(void) { - shrinker_free(huge_zero_page_shrinker); + shrinker_free(huge_zero_folio_shrinker); shrinker_free(deferred_split_shrinker); } From 78689ae389b427d86c33f72d6b20799809ca839e Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 4 Aug 2025 14:13:53 +0200 Subject: [PATCH 2/5] mm: rename MMF_HUGE_ZERO_PAGE to MMF_HUGE_ZERO_FOLIO As all the helper functions has been renamed from *_page to *_folio, rename the MM flag from MMF_HUGE_ZERO_PAGE to MMF_HUGE_ZERO_FOLIO. No functional changes. Suggested-by: David Hildenbrand Signed-off-by: Pankaj Raghav Reviewed-by: Lorenzo Stoakes Acked-by: David Hildenbrand Reviewed-by: Zi Yan --- include/linux/mm_types.h | 2 +- mm/huge_memory.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 08bc2442db934..a87b40610ab9e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1758,7 +1758,7 @@ enum { #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ #define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ -#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ +#define MMF_HUGE_ZERO_FOLIO 23 /* mm has ever used the global huge zero folio */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 46df57b2c0775..f3492605bb21f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -248,13 +248,13 @@ static void put_huge_zero_folio(void) struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) { - if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + if (test_bit(MMF_HUGE_ZERO_FOLIO, &mm->flags)) return READ_ONCE(huge_zero_folio); if (!get_huge_zero_folio()) return NULL; - if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + if (test_and_set_bit(MMF_HUGE_ZERO_FOLIO, &mm->flags)) put_huge_zero_folio(); return READ_ONCE(huge_zero_folio); @@ -262,7 +262,7 @@ struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) void mm_put_huge_zero_folio(struct mm_struct *mm) { - if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + if (test_bit(MMF_HUGE_ZERO_FOLIO, &mm->flags)) put_huge_zero_folio(); } From 43732bd9f915f1b000e9f8ff9eb3bd9f04ebd4fe Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 4 Aug 2025 14:13:54 +0200 Subject: [PATCH 3/5] mm: add static huge zero folio There are many places in the kernel where we need to zeroout larger chunks but the maximum segment we can zeroout at a time by ZERO_PAGE is limited by PAGE_SIZE. This is especially annoying in block devices and filesystems where we attach multiple ZERO_PAGEs to the bio in different bvecs. With multipage bvec support in block layer, it is much more efficient to send out larger zero pages as a part of single bvec. This concern was raised during the review of adding LBS support to XFS[1][2]. Usually huge_zero_folio is allocated on demand, and it will be deallocated by the shrinker if there are no users of it left. At moment, huge_zero_folio infrastructure refcount is tied to the process lifetime that created it. This might not work for bio layer as the completions can be async and the process that created the huge_zero_folio might no longer be alive. And, one of the main point that came during discussion is to have something bigger than zero page as a drop-in replacement. Add a config option STATIC_HUGE_ZERO_FOLIO that will result in allocating the huge zero folio on first request, if not already allocated, and turn it static such that it can never get freed. This makes using the huge_zero_folio without having to pass any mm struct and does not tie the lifetime of the zero folio to anything, making it a drop-in replacement for ZERO_PAGE. If STATIC_HUGE_ZERO_FOLIO config option is enabled, then mm_get_huge_zero_folio() will simply return this page instead of dynamically allocating a new PMD page. This option can waste memory in small systems or systems with 64k base page size. So make it an opt-in and also add an option from individual architecture so that we don't enable this feature for larger base page size systems. Only x86 is enabled as a part of this series. Other architectures shall be enabled as a follow-up to this series. [1] https://lore.kernel.org/linux-xfs/20231027051847.GA7885@lst.de/ [2] https://lore.kernel.org/linux-xfs/ZitIK5OnR7ZNY0IG@infradead.org/ Co-developed-by: David Hildenbrand Signed-off-by: David Hildenbrand Signed-off-by: Pankaj Raghav --- arch/x86/Kconfig | 1 + include/linux/huge_mm.h | 18 ++++++++++++++++ mm/Kconfig | 21 +++++++++++++++++++ mm/huge_memory.c | 46 ++++++++++++++++++++++++++++++++++++++++- 4 files changed, 85 insertions(+), 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 58d890fe2100e..a20a58b8c29b7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -151,6 +151,7 @@ config X86 select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64 select ARCH_WANT_HUGETLB_VMEMMAP_PREINIT if X86_64 select ARCH_WANTS_THP_SWAP if X86_64 + select ARCH_WANTS_STATIC_HUGE_ZERO_FOLIO if X86_64 select ARCH_HAS_PARANOID_L1D_FLUSH select ARCH_WANT_IRQS_OFF_ACTIVATE_MM select BUILDTIME_TABLE_SORT diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 7748489fde1b7..78ebceb61d0e4 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -476,6 +476,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); extern struct folio *huge_zero_folio; extern unsigned long huge_zero_pfn; +extern atomic_t huge_zero_folio_is_static; static inline bool is_huge_zero_folio(const struct folio *folio) { @@ -494,6 +495,18 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); void mm_put_huge_zero_folio(struct mm_struct *mm); +struct folio *__get_static_huge_zero_folio(void); + +static inline struct folio *get_static_huge_zero_folio(void) +{ + if (!IS_ENABLED(CONFIG_STATIC_HUGE_ZERO_FOLIO)) + return NULL; + + if (likely(atomic_read(&huge_zero_folio_is_static))) + return huge_zero_folio; + + return __get_static_huge_zero_folio(); +} static inline bool thp_migration_supported(void) { @@ -685,6 +698,11 @@ static inline int change_huge_pud(struct mmu_gather *tlb, { return 0; } + +static inline struct folio *get_static_huge_zero_folio(void) +{ + return NULL; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline int split_folio_to_list_to_order(struct folio *folio, diff --git a/mm/Kconfig b/mm/Kconfig index e443fe8cd6cf2..366a6d2d771e3 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -823,6 +823,27 @@ config ARCH_WANT_GENERAL_HUGETLB config ARCH_WANTS_THP_SWAP def_bool n +config ARCH_WANTS_STATIC_HUGE_ZERO_FOLIO + def_bool n + +config STATIC_HUGE_ZERO_FOLIO + bool "Allocate a PMD sized folio for zeroing" + depends on ARCH_WANTS_STATIC_HUGE_ZERO_FOLIO && TRANSPARENT_HUGEPAGE + help + Without this config enabled, the huge zero folio is allocated on + demand and freed under memory pressure once no longer in use. + To detect remaining users reliably, references to the huge zero folio + must be tracked precisely, so it is commonly only available for mapping + it into user page tables. + + With this config enabled, the huge zero folio can also be used + for other purposes that do not implement precise reference counting: + it is still allocated on demand, but never freed, allowing for more + wide-spread use, for example, when performing I/O similar to the + traditional shared zeropage. + + Not suitable for memory constrained systems. + config MM_ID def_bool n diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f3492605bb21f..db4fb108ffd90 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -75,6 +75,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, static bool split_underused_thp = true; static atomic_t huge_zero_refcount; +atomic_t huge_zero_folio_is_static __read_mostly; struct folio *huge_zero_folio __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; unsigned long huge_anon_orders_always __read_mostly; @@ -266,6 +267,45 @@ void mm_put_huge_zero_folio(struct mm_struct *mm) put_huge_zero_folio(); } +#ifdef CONFIG_STATIC_HUGE_ZERO_FOLIO + +struct folio *__get_static_huge_zero_folio(void) +{ + static unsigned long fail_count_clear_timer; + static atomic_t huge_zero_static_fail_count __read_mostly; + + if (unlikely(!slab_is_available())) + return NULL; + + /* + * If we failed to allocate a huge zero folio, just refrain from + * trying for one minute before retrying to get a reference again. + */ + if (atomic_read(&huge_zero_static_fail_count) > 1) { + if (time_before(jiffies, fail_count_clear_timer)) + return NULL; + atomic_set(&huge_zero_static_fail_count, 0); + } + /* + * Our raised reference will prevent the shrinker from ever having + * success. + */ + if (!get_huge_zero_folio()) { + int count = atomic_inc_return(&huge_zero_static_fail_count); + + if (count > 1) + fail_count_clear_timer = get_jiffies_64() + 60 * HZ; + + return NULL; + } + + if (atomic_cmpxchg(&huge_zero_folio_is_static, 0, 1) != 0) + put_huge_zero_folio(); + + return huge_zero_folio; +} +#endif /* CONFIG_STATIC_HUGE_ZERO_FOLIO */ + static unsigned long shrink_huge_zero_folio_count(struct shrinker *shrink, struct shrink_control *sc) { @@ -277,7 +317,11 @@ static unsigned long shrink_huge_zero_folio_scan(struct shrinker *shrink, struct shrink_control *sc) { if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { - struct folio *zero_folio = xchg(&huge_zero_folio, NULL); + struct folio *zero_folio; + + if (WARN_ON_ONCE(atomic_read(&huge_zero_folio_is_static))) + return 0; + zero_folio = xchg(&huge_zero_folio, NULL); BUG_ON(zero_folio == NULL); WRITE_ONCE(huge_zero_pfn, ~0UL); folio_put(zero_folio); From 2c1761bd0040b4524e69b5e82e9893a73bf70497 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 4 Aug 2025 14:13:55 +0200 Subject: [PATCH 4/5] mm: add largest_zero_folio() routine Add largest_zero_folio() routine so that huge_zero_folio can be used directly when CONFIG_STATIC_HUGE_ZERO_FOLIO is enabled. This will return ZERO_PAGE folio if CONFIG_STATIC_HUGE_ZERO_FOLIO is disabled or if we failed to allocate a huge_zero_folio. Co-developed-by: David Hildenbrand Signed-off-by: David Hildenbrand Signed-off-by: Pankaj Raghav Reviewed-by: Lorenzo Stoakes Reviewed-by: Zi Yan --- include/linux/huge_mm.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 78ebceb61d0e4..c44a6736704bb 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -716,4 +716,21 @@ static inline int split_folio_to_order(struct folio *folio, int new_order) return split_folio_to_list_to_order(folio, NULL, new_order); } +/* + * largest_zero_folio - Get the largest zero size folio available + * + * This function will return huge_zero_folio if CONFIG_STATIC_HUGE_ZERO_FOLIO + * is enabled. Otherwise, a ZERO_PAGE folio is returned. + * + * Deduce the size of the folio with folio_size instead of assuming the + * folio size. + */ +static inline struct folio *largest_zero_folio(void) +{ + struct folio *folio = get_static_huge_zero_folio(); + + if (folio) + return folio; + return page_folio(ZERO_PAGE(0)); +} #endif /* _LINUX_HUGE_MM_H */ From 0f29ef69d5bc0912b15467a9f48f6eccfac15cd6 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 4 Aug 2025 14:13:56 +0200 Subject: [PATCH 5/5] block: use largest_zero_folio in __blkdev_issue_zero_pages() Use largest_zero_folio() in __blkdev_issue_zero_pages(). On systems with CONFIG_STATIC_HUGE_ZERO_FOLIO enabled, we will end up sending larger bvecs instead of multiple small ones. Noticed a 4% increase in performance on a commercial NVMe SSD which does not support OP_WRITE_ZEROES. The device's MDTS was 128K. The performance gains might be bigger if the device supports bigger MDTS. Signed-off-by: Pankaj Raghav Acked-by: Lorenzo Stoakes --- block/blk-lib.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/block/blk-lib.c b/block/blk-lib.c index 4c9f20a689f7b..3030a772d3aa0 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -196,6 +196,8 @@ static void __blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned int flags) { + struct folio *zero_folio = largest_zero_folio(); + while (nr_sects) { unsigned int nr_vecs = __blkdev_sectors_to_bio_pages(nr_sects); struct bio *bio; @@ -208,15 +210,14 @@ static void __blkdev_issue_zero_pages(struct block_device *bdev, break; do { - unsigned int len, added; + unsigned int len; - len = min_t(sector_t, - PAGE_SIZE, nr_sects << SECTOR_SHIFT); - added = bio_add_page(bio, ZERO_PAGE(0), len, 0); - if (added < len) + len = min_t(sector_t, folio_size(zero_folio), + nr_sects << SECTOR_SHIFT); + if (!bio_add_folio(bio, zero_folio, len, 0)) break; - nr_sects -= added >> SECTOR_SHIFT; - sector += added >> SECTOR_SHIFT; + nr_sects -= len >> SECTOR_SHIFT; + sector += len >> SECTOR_SHIFT; } while (nr_sects); *biop = bio_chain_and_submit(*biop, bio);