From: Alexander Zhu <alexlzhu@xxxxxx> Currently, when /sys/kernel/mm/transparent_hugepage/enabled=always is set there are a large number of transparent hugepages that are almost entirely zero filled. This is mentioned in a number of previous patchsets including: https://lore.kernel.org/all/20210731063938.1391602-1-yuzhao@xxxxxxxxxx/ https://lore.kernel.org/all/ 1635422215-99394-1-git-send-email-ningzhang@xxxxxxxxxxxxxxxxx/ Currently, split_huge_page() does not have a way to identify zero filled pages within the THP. Thus these zero pages get remapped and continue to create memory waste. In this patch, we identify and free tail pages that are zero filled in split_huge_page(). In this way, we avoid mapping these pages back into page table entries and can free up unused memory within THPs. This is based off the previously mentioned patchset by Yu Zhao. However, we chose to free anonymous zero tail pages whenever they are encountered instead of only on reclaim or migration. We also add self tests to verify the RssAnon value to make sure zero pages are not remapped except in the case of userfaultfd. In the case of userfaultfd we remap to the shared zero page, similar to what is done by KSM. Signed-off-by: Alexander Zhu <alexlzhu@xxxxxx> --- v1 to v2 -Modified split_huge_page self test based off more recent changes. RFC to v1 -Added support to map to the read only zero page when splitting a THP registered with userfaultfd. Also added a self test to verify that this is working. -Only trigger the unmap_clean/zap in split_huge_page on anonymous THPs. We cannot zap zero pages for file THPs. include/linux/rmap.h | 2 +- include/linux/vm_event_item.h | 3 + mm/huge_memory.c | 45 ++++++- mm/migrate.c | 73 +++++++++-- mm/migrate_device.c | 4 +- mm/vmstat.c | 3 + .../selftests/vm/split_huge_page_test.c | 115 +++++++++++++++++- tools/testing/selftests/vm/vm_util.c | 23 ++++ tools/testing/selftests/vm/vm_util.h | 3 + 9 files changed, 256 insertions(+), 15 deletions(-) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index bd3504d11b15..3f83bbcf1333 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -428,7 +428,7 @@ int folio_mkclean(struct folio *); int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma); -void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); +void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked, bool unmap_clean); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 3518dba1e02f..3618b10ddec9 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -111,6 +111,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD THP_SPLIT_PUD, #endif + THP_SPLIT_FREE, + THP_SPLIT_UNMAP, + THP_SPLIT_REMAP_READONLY_ZERO_PAGE, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, THP_SWPOUT, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1cc4a5f4791e..f68a353e0adf 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2373,7 +2373,7 @@ static void unmap_folio(struct folio *folio) try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); } -static void remap_page(struct folio *folio, unsigned long nr) +static void remap_page(struct folio *folio, unsigned long nr, bool unmap_clean) { int i = 0; @@ -2381,7 +2381,7 @@ static void remap_page(struct folio *folio, unsigned long nr) if (!folio_test_anon(folio)) return; for (;;) { - remove_migration_ptes(folio, folio, true); + remove_migration_ptes(folio, folio, true, unmap_clean); i += folio_nr_pages(folio); if (i >= nr) break; @@ -2496,6 +2496,8 @@ static void __split_huge_page(struct page *page, struct list_head *list, struct address_space *swap_cache = NULL; unsigned long offset = 0; unsigned int nr = thp_nr_pages(head); + LIST_HEAD(pages_to_free); + int nr_pages_to_free = 0; int i; /* complete memcg works before add pages to LRU */ @@ -2558,7 +2560,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, } local_irq_enable(); - remap_page(folio, nr); + remap_page(folio, nr, PageAnon(head)); if (PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; @@ -2572,6 +2574,34 @@ static void __split_huge_page(struct page *page, struct list_head *list, continue; unlock_page(subpage); + /* + * If a tail page has only two references left, one inherited + * from the isolation of its head and the other from + * lru_add_page_tail() which we are about to drop, it means this + * tail page was concurrently zapped. Then we can safely free it + * and save page reclaim or migration the trouble of trying it. + */ + if (list && page_ref_freeze(subpage, 2)) { + VM_BUG_ON_PAGE(PageLRU(subpage), subpage); + VM_BUG_ON_PAGE(PageCompound(subpage), subpage); + VM_BUG_ON_PAGE(page_mapped(subpage), subpage); + + ClearPageActive(subpage); + ClearPageUnevictable(subpage); + list_move(&subpage->lru, &pages_to_free); + nr_pages_to_free++; + continue; + } + + /* + * If a tail page has only one reference left, it will be freed + * by the call to free_page_and_swap_cache below. Since zero + * subpages are no longer remapped, there will only be one + * reference left in cases outside of reclaim or migration. + */ + if (page_ref_count(subpage) == 1) + nr_pages_to_free++; + /* * Subpages may be freed if there wasn't any mapping * like if add_to_swap() is running on a lru page that @@ -2581,6 +2611,13 @@ static void __split_huge_page(struct page *page, struct list_head *list, */ free_page_and_swap_cache(subpage); } + + if (!nr_pages_to_free) + return; + + mem_cgroup_uncharge_list(&pages_to_free); + free_unref_page_list(&pages_to_free); + count_vm_events(THP_SPLIT_FREE, nr_pages_to_free); } /* Racy check whether the huge page can be split */ @@ -2752,7 +2789,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (mapping) xas_unlock(&xas); local_irq_enable(); - remap_page(folio, folio_nr_pages(folio)); + remap_page(folio, folio_nr_pages(folio), false); ret = -EBUSY; } diff --git a/mm/migrate.c b/mm/migrate.c index 1379e1912772..bc96a084d925 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -30,6 +30,7 @@ #include <linux/writeback.h> #include <linux/mempolicy.h> #include <linux/vmalloc.h> +#include <linux/vm_event_item.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/compaction.h> @@ -168,13 +169,62 @@ void putback_movable_pages(struct list_head *l) } } +static bool try_to_unmap_clean(struct page_vma_mapped_walk *pvmw, struct page *page) +{ + void *addr; + bool dirty; + pte_t newpte; + + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(pte_present(*pvmw->pte), page); + + if (PageMlocked(page) || (pvmw->vma->vm_flags & VM_LOCKED)) + return false; + + /* + * The pmd entry mapping the old thp was flushed and the pte mapping + * this subpage has been non present. Therefore, this subpage is + * inaccessible. We don't need to remap it if it contains only zeros. + */ + addr = kmap_local_page(page); + dirty = memchr_inv(addr, 0, PAGE_SIZE); + kunmap_local(addr); + + if (dirty) + return false; + + pte_clear_not_present_full(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, false); + + if (userfaultfd_armed(pvmw->vma)) { + newpte = pte_mkspecial(pfn_pte(page_to_pfn(ZERO_PAGE(pvmw->address)), + pvmw->vma->vm_page_prot)); + ptep_clear_flush(pvmw->vma, pvmw->address, pvmw->pte); + set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte); + dec_mm_counter(pvmw->vma->vm_mm, MM_ANONPAGES); + count_vm_event(THP_SPLIT_REMAP_READONLY_ZERO_PAGE); + return true; + } + + dec_mm_counter(pvmw->vma->vm_mm, mm_counter(page)); + count_vm_event(THP_SPLIT_UNMAP); + return true; +} + +struct rmap_walk_arg { + struct folio *folio; + bool unmap_clean; +}; + /* * Restore a potential migration pte to a working pte entry */ static bool remove_migration_pte(struct folio *folio, - struct vm_area_struct *vma, unsigned long addr, void *old) + struct vm_area_struct *vma, unsigned long addr, void *arg) { - DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); + struct rmap_walk_arg *rmap_walk_arg = arg; + DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { rmap_t rmap_flags = RMAP_NONE; @@ -197,6 +247,8 @@ static bool remove_migration_pte(struct folio *folio, continue; } #endif + if (rmap_walk_arg->unmap_clean && try_to_unmap_clean(&pvmw, new)) + continue; folio_get(folio); pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); @@ -272,13 +324,20 @@ static bool remove_migration_pte(struct folio *folio, * Get rid of all migration entries and replace them by * references to the indicated page. */ -void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked) +void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked, bool unmap_clean) { + struct rmap_walk_arg rmap_walk_arg = { + .folio = src, + .unmap_clean = unmap_clean, + }; + struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, - .arg = src, + .arg = &rmap_walk_arg, }; + VM_BUG_ON_FOLIO(unmap_clean && src != dst, src); + if (locked) rmap_walk_locked(dst, &rwc); else @@ -872,7 +931,7 @@ static int writeout(struct address_space *mapping, struct folio *folio) * At this point we know that the migration attempt cannot * be successful. */ - remove_migration_ptes(folio, folio, false); + remove_migration_ptes(folio, folio, false, false); rc = mapping->a_ops->writepage(&folio->page, &wbc); @@ -1128,7 +1187,7 @@ static int __unmap_and_move(struct folio *src, struct folio *dst, if (page_was_mapped) remove_migration_ptes(src, - rc == MIGRATEPAGE_SUCCESS ? dst : src, false); + rc == MIGRATEPAGE_SUCCESS ? dst : src, false, false); out_unlock_both: folio_unlock(dst); @@ -1338,7 +1397,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (page_was_mapped) remove_migration_ptes(src, - rc == MIGRATEPAGE_SUCCESS ? dst : src, false); + rc == MIGRATEPAGE_SUCCESS ? dst : src, false, false); unlock_put_anon: folio_unlock(dst); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 6fa682eef7a0..6508a083d7fd 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -421,7 +421,7 @@ static unsigned long migrate_device_unmap(unsigned long *src_pfns, continue; folio = page_folio(page); - remove_migration_ptes(folio, folio, false); + remove_migration_ptes(folio, folio, false, false); src_pfns[i] = 0; folio_unlock(folio); @@ -847,7 +847,7 @@ void migrate_device_finalize(unsigned long *src_pfns, src = page_folio(page); dst = page_folio(newpage); - remove_migration_ptes(src, dst, false); + remove_migration_ptes(src, dst, false, false); folio_unlock(src); if (is_zone_device_page(page)) diff --git a/mm/vmstat.c b/mm/vmstat.c index b2371d745e00..3d802eb6754d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1359,6 +1359,9 @@ const char * const vmstat_text[] = { #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD "thp_split_pud", #endif + "thp_split_free", + "thp_split_unmap", + "thp_split_remap_readonly_zero_page", "thp_zero_page_alloc", "thp_zero_page_alloc_failed", "thp_swpout", diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c index 76e1c36dd9e5..42f0e79a4508 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -16,6 +16,9 @@ #include <sys/mount.h> #include <malloc.h> #include <stdbool.h> +#include <sys/syscall.h> /* Definition of SYS_* constants */ +#include <linux/userfaultfd.h> +#include <sys/ioctl.h> #include "vm_util.h" uint64_t pagesize; @@ -88,6 +91,115 @@ static void write_debugfs(const char *fmt, ...) } } +static char *allocate_zero_filled_hugepage(size_t len) +{ + char *result; + size_t i; + + result = memalign(pmd_pagesize, len); + if (!result) { + printf("Fail to allocate memory\n"); + exit(EXIT_FAILURE); + } + + madvise(result, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + result[i] = (char)0; + + return result; +} + +static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hpages, size_t len) +{ + uint64_t rss_anon_before, rss_anon_after; + size_t i; + + if (!check_huge_anon(one_page, 4, pmd_pagesize)) { + printf("No THP is allocated\n"); + exit(EXIT_FAILURE); + } + + rss_anon_before = rss_anon(); + if (!rss_anon_before) { + printf("No RssAnon is allocated before split\n"); + exit(EXIT_FAILURE); + } + + /* split all THPs */ + write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, + (uint64_t)one_page + len); + + for (i = 0; i < len; i++) + if (one_page[i] != (char)0) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + + if (!check_huge_anon(one_page, 0, pmd_pagesize)) { + printf("Still AnonHugePages not split\n"); + exit(EXIT_FAILURE); + } + + rss_anon_after = rss_anon(); + if (rss_anon_after >= rss_anon_before) { + printf("Incorrect RssAnon value. Before: %ld After: %ld\n", + rss_anon_before, rss_anon_after); + exit(EXIT_FAILURE); + } +} + +void split_pmd_zero_pages(void) +{ + char *one_page; + int nr_hpages = 4; + size_t len = nr_hpages * pmd_pagesize; + + one_page = allocate_zero_filled_hugepage(len); + verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len); + printf("Split zero filled huge pages successful\n"); + free(one_page); +} + +void split_pmd_zero_pages_uffd(void) +{ + char *one_page; + int nr_hpages = 4; + size_t len = nr_hpages * pmd_pagesize; + long uffd; /* userfaultfd file descriptor */ + struct uffdio_api uffdio_api; + struct uffdio_register uffdio_register; + + /* Create and enable userfaultfd object. */ + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd == -1) { + perror("userfaultfd"); + exit(1); + } + + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { + perror("ioctl-UFFDIO_API"); + exit(1); + } + + one_page = allocate_zero_filled_hugepage(len); + + uffdio_register.range.start = (unsigned long)one_page; + uffdio_register.range.len = len; + uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { + perror("ioctl-UFFDIO_REGISTER"); + exit(1); + } + + verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len); + printf("Split zero filled huge pages with uffd successful\n"); + free(one_page); +} + void split_pmd_thp(void) { char *one_page; @@ -121,7 +233,6 @@ void split_pmd_thp(void) exit(EXIT_FAILURE); } - if (check_huge_anon(one_page, 0, pmd_pagesize)) { printf("Still AnonHugePages not split\n"); exit(EXIT_FAILURE); @@ -301,6 +412,8 @@ int main(int argc, char **argv) pageshift = ffs(pagesize) - 1; pmd_pagesize = read_pmd_pagesize(); + split_pmd_zero_pages(); + split_pmd_zero_pages_uffd(); split_pmd_thp(); split_pte_mapped_thp(); split_file_backed_thp(); diff --git a/tools/testing/selftests/vm/vm_util.c b/tools/testing/selftests/vm/vm_util.c index f11f8adda521..72f3edc64aaf 100644 --- a/tools/testing/selftests/vm/vm_util.c +++ b/tools/testing/selftests/vm/vm_util.c @@ -6,6 +6,7 @@ #define PMD_SIZE_FILE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" #define SMAP_FILE_PATH "/proc/self/smaps" +#define STATUS_FILE_PATH "/proc/self/status" #define MAX_LINE_LENGTH 500 uint64_t pagemap_get_entry(int fd, char *start) @@ -72,6 +73,28 @@ uint64_t read_pmd_pagesize(void) return strtoul(buf, NULL, 10); } +uint64_t rss_anon(void) +{ + uint64_t rss_anon = 0; + int ret; + FILE *fp; + char buffer[MAX_LINE_LENGTH]; + + fp = fopen(STATUS_FILE_PATH, "r"); + if (!fp) + ksft_exit_fail_msg("%s: Failed to open file %s\n", __func__, STATUS_FILE_PATH); + + if (!check_for_pattern(fp, "RssAnon:", buffer, sizeof(buffer))) + goto err_out; + + if (sscanf(buffer, "RssAnon:%10ld kB", &rss_anon) != 1) + ksft_exit_fail_msg("Reading status error\n"); + +err_out: + fclose(fp); + return rss_anon; +} + bool __check_huge(void *addr, char *pattern, int nr_hpages, uint64_t hpage_size) { diff --git a/tools/testing/selftests/vm/vm_util.h b/tools/testing/selftests/vm/vm_util.h index 5c35de454e08..dd1885f66097 100644 --- a/tools/testing/selftests/vm/vm_util.h +++ b/tools/testing/selftests/vm/vm_util.h @@ -1,12 +1,15 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <stdint.h> #include <stdbool.h> +#include <stddef.h> +#include <stdio.h> uint64_t pagemap_get_entry(int fd, char *start); bool pagemap_is_softdirty(int fd, char *start); void clear_softdirty(void); bool check_for_pattern(FILE *fp, const char *pattern, char *buf, size_t len); uint64_t read_pmd_pagesize(void); +uint64_t rss_anon(void); bool check_huge_anon(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); -- 2.30.2
