diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/damon/core.c | 23 | ||||
| -rw-r--r-- | mm/filemap.c | 20 | ||||
| -rw-r--r-- | mm/gup.c | 291 | ||||
| -rw-r--r-- | mm/huge_memory.c | 2 | ||||
| -rw-r--r-- | mm/hugetlb.c | 70 | ||||
| -rw-r--r-- | mm/hugetlb_vmemmap.c | 16 | ||||
| -rw-r--r-- | mm/internal.h | 4 | ||||
| -rw-r--r-- | mm/khugepaged.c | 10 | ||||
| -rw-r--r-- | mm/memcontrol.c | 11 | ||||
| -rw-r--r-- | mm/migrate.c | 13 | ||||
| -rw-r--r-- | mm/page-writeback.c | 32 | ||||
| -rw-r--r-- | mm/readahead.c | 8 | ||||
| -rw-r--r-- | mm/shmem.c | 36 | ||||
| -rw-r--r-- | mm/vmalloc.c | 10 | ||||
| -rw-r--r-- | mm/workingset.c | 14 |
15 files changed, 314 insertions, 246 deletions
diff --git a/mm/damon/core.c b/mm/damon/core.c index 6392f1cc97a3..e66823d6b10b 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1358,14 +1358,31 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, * access frequencies are similar. This is for minimizing the monitoring * overhead under the dynamically changeable access pattern. If a merge was * unnecessarily made, later 'kdamond_split_regions()' will revert it. + * + * The total number of regions could be higher than the user-defined limit, + * max_nr_regions for some cases. For example, the user can update + * max_nr_regions to a number that lower than the current number of regions + * while DAMON is running. For such a case, repeat merging until the limit is + * met while increasing @threshold up to possible maximum level. */ static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold, unsigned long sz_limit) { struct damon_target *t; - - damon_for_each_target(t, c) - damon_merge_regions_of(t, threshold, sz_limit); + unsigned int nr_regions; + unsigned int max_thres; + + max_thres = c->attrs.aggr_interval / + (c->attrs.sample_interval ? c->attrs.sample_interval : 1); + do { + nr_regions = 0; + damon_for_each_target(t, c) { + damon_merge_regions_of(t, threshold, sz_limit); + nr_regions += damon_nr_regions(t); + } + threshold = max(1, threshold * 2); + } while (nr_regions > c->attrs.max_nr_regions && + threshold / 2 < max_thres); } /* diff --git a/mm/filemap.c b/mm/filemap.c index 876cc64aadd7..657bcd887fdb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1847,7 +1847,7 @@ repeat: if (!folio || xa_is_value(folio)) goto out; - if (!folio_try_get_rcu(folio)) + if (!folio_try_get(folio)) goto repeat; if (unlikely(folio != xas_reload(&xas))) { @@ -2001,7 +2001,7 @@ retry: if (!folio || xa_is_value(folio)) return folio; - if (!folio_try_get_rcu(folio)) + if (!folio_try_get(folio)) goto reset; if (unlikely(folio != xas_reload(xas))) { @@ -2181,7 +2181,7 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, if (xa_is_value(folio)) goto update_start; - if (!folio_try_get_rcu(folio)) + if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) @@ -2313,7 +2313,7 @@ static void filemap_get_read_batch(struct address_space *mapping, break; if (xa_is_sibling(folio)) break; - if (!folio_try_get_rcu(folio)) + if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) @@ -3124,7 +3124,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ - if (vm_flags & VM_HUGEPAGE) { + if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); ra->size = HPAGE_PMD_NR; @@ -3231,7 +3231,8 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; - ptep = pte_offset_map(vmf->pmd, vmf->address); + ptep = pte_offset_map_nolock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; @@ -3472,7 +3473,7 @@ static struct folio *next_uptodate_folio(struct xa_state *xas, continue; if (folio_test_locked(folio)) continue; - if (!folio_try_get_rcu(folio)) + if (!folio_try_get(folio)) continue; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) @@ -4248,6 +4249,9 @@ static void filemap_cachestat(struct address_space *mapping, XA_STATE(xas, &mapping->i_pages, first_index); struct folio *folio; + /* Flush stats (and potentially sleep) outside the RCU read section. */ + mem_cgroup_flush_stats_ratelimited(NULL); + rcu_read_lock(); xas_for_each(&xas, folio, last_index) { int order; @@ -4311,7 +4315,7 @@ static void filemap_cachestat(struct address_space *mapping, goto resched; } #endif - if (workingset_test_recent(shadow, true, &workingset)) + if (workingset_test_recent(shadow, true, &workingset, false)) cs->nr_recently_evicted += nr_pages; goto resched; @@ -76,7 +76,7 @@ retry: folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) < 0)) return NULL; - if (unlikely(!folio_ref_try_add_rcu(folio, refs))) + if (unlikely(!folio_ref_try_add(folio, refs))) return NULL; /* @@ -97,95 +97,6 @@ retry: return folio; } -/** - * try_grab_folio() - Attempt to get or pin a folio. - * @page: pointer to page to be grabbed - * @refs: the value to (effectively) add to the folio's refcount - * @flags: gup flags: these are the FOLL_* flag values. - * - * "grab" names in this file mean, "look at flags to decide whether to use - * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. - * - * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the - * same time. (That's true throughout the get_user_pages*() and - * pin_user_pages*() APIs.) Cases: - * - * FOLL_GET: folio's refcount will be incremented by @refs. - * - * FOLL_PIN on large folios: folio's refcount will be incremented by - * @refs, and its pincount will be incremented by @refs. - * - * FOLL_PIN on single-page folios: folio's refcount will be incremented by - * @refs * GUP_PIN_COUNTING_BIAS. - * - * Return: The folio containing @page (with refcount appropriately - * incremented) for success, or NULL upon failure. If neither FOLL_GET - * nor FOLL_PIN was set, that's considered failure, and furthermore, - * a likely bug in the caller, so a warning is also emitted. - */ -struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) -{ - struct folio *folio; - - if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) - return NULL; - - if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) - return NULL; - - if (flags & FOLL_GET) - return try_get_folio(page, refs); - - /* FOLL_PIN is set */ - - /* - * Don't take a pin on the zero page - it's not going anywhere - * and it is used in a *lot* of places. - */ - if (is_zero_page(page)) - return page_folio(page); - - folio = try_get_folio(page, refs); - if (!folio) - return NULL; - - /* - * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a - * right zone, so fail and let the caller fall back to the slow - * path. - */ - if (unlikely((flags & FOLL_LONGTERM) && - !folio_is_longterm_pinnable(folio))) { - if (!put_devmap_managed_folio_refs(folio, refs)) - folio_put_refs(folio, refs); - return NULL; - } - - /* - * When pinning a large folio, use an exact count to track it. - * - * However, be sure to *also* increment the normal folio - * refcount field at least once, so that the folio really - * is pinned. That's why the refcount from the earlier - * try_get_folio() is left intact. - */ - if (folio_test_large(folio)) - atomic_add(refs, &folio->_pincount); - else - folio_ref_add(folio, - refs * (GUP_PIN_COUNTING_BIAS - 1)); - /* - * Adjust the pincount before re-checking the PTE for changes. - * This is essentially a smp_mb() and is paired with a memory - * barrier in folio_try_share_anon_rmap_*(). - */ - smp_mb__after_atomic(); - - node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); - - return folio; -} - static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { @@ -203,58 +114,59 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) } /** - * try_grab_page() - elevate a page's refcount by a flag-dependent amount - * @page: pointer to page to be grabbed - * @flags: gup flags: these are the FOLL_* flag values. + * try_grab_folio() - add a folio's refcount by a flag-dependent amount + * @folio: pointer to folio to be grabbed + * @refs: the value to (effectively) add to the folio's refcount + * @flags: gup flags: these are the FOLL_* flag values * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use - * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount. + * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same - * time. Cases: please see the try_grab_folio() documentation, with - * "refs=1". + * time. * * Return: 0 for success, or if no action was required (if neither FOLL_PIN * nor FOLL_GET was set, nothing is done). A negative error code for failure: * - * -ENOMEM FOLL_GET or FOLL_PIN was set, but the page could not + * -ENOMEM FOLL_GET or FOLL_PIN was set, but the folio could not * be grabbed. + * + * It is called when we have a stable reference for the folio, typically in + * GUP slow path. */ -int __must_check try_grab_page(struct page *page, unsigned int flags) +int __must_check try_grab_folio(struct folio *folio, int refs, + unsigned int flags) { - struct folio *folio = page_folio(page); - if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; - if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) + if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page))) return -EREMOTEIO; if (flags & FOLL_GET) - folio_ref_inc(folio); + folio_ref_add(folio, refs); else if (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ - if (is_zero_page(page)) + if (is_zero_folio(folio)) return 0; /* - * Similar to try_grab_folio(): be sure to *also* - * increment the normal page refcount field at least once, + * Increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { - folio_ref_add(folio, 1); - atomic_add(1, &folio->_pincount); + folio_ref_add(folio, refs); + atomic_add(refs, &folio->_pincount); } else { - folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); + folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS); } - node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1); + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); } return 0; @@ -515,6 +427,102 @@ static int record_subpages(struct page *page, unsigned long sz, return nr; } + +/** + * try_grab_folio_fast() - Attempt to get or pin a folio in fast path. + * @page: pointer to page to be grabbed + * @refs: the value to (effectively) add to the folio's refcount + * @flags: gup flags: these are the FOLL_* flag values. + * + * "grab" names in this file mean, "look at flags to decide whether to use + * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. + * + * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the + * same time. (That's true throughout the get_user_pages*() and + * pin_user_pages*() APIs.) Cases: + * + * FOLL_GET: folio's refcount will be incremented by @refs. + * + * FOLL_PIN on large folios: folio's refcount will be incremented by + * @refs, and its pincount will be incremented by @refs. + * + * FOLL_PIN on single-page folios: folio's refcount will be incremented by + * @refs * GUP_PIN_COUNTING_BIAS. + * + * Return: The folio containing @page (with refcount appropriately + * incremented) for success, or NULL upon failure. If neither FOLL_GET + * nor FOLL_PIN was set, that's considered failure, and furthermore, + * a likely bug in the caller, so a warning is also emitted. + * + * It uses add ref unless zero to elevate the folio refcount and must be called + * in fast path only. + */ +static struct folio *try_grab_folio_fast(struct page *page, int refs, + unsigned int flags) +{ + struct folio *folio; + + /* Raise warn if it is not called in fast GUP */ + VM_WARN_ON_ONCE(!irqs_disabled()); + + if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) + return NULL; + + if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) + return NULL; + + if (flags & FOLL_GET) + return try_get_folio(page, refs); + + /* FOLL_PIN is set */ + + /* + * Don't take a pin on the zero page - it's not going anywhere + * and it is used in a *lot* of places. + */ + if (is_zero_page(page)) + return page_folio(page); + + folio = try_get_folio(page, refs); + if (!folio) + return NULL; + + /* + * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a + * right zone, so fail and let the caller fall back to the slow + * path. + */ + if (unlikely((flags & FOLL_LONGTERM) && + !folio_is_longterm_pinnable(folio))) { + if (!put_devmap_managed_folio_refs(folio, refs)) + folio_put_refs(folio, refs); + return NULL; + } + + /* + * When pinning a large folio, use an exact count to track it. + * + * However, be sure to *also* increment the normal folio + * refcount field at least once, so that the folio really + * is pinned. That's why the refcount from the earlier + * try_get_folio() is left intact. + */ + if (folio_test_large(folio)) + atomic_add(refs, &folio->_pincount); + else + folio_ref_add(folio, + refs * (GUP_PIN_COUNTING_BIAS - 1)); + /* + * Adjust the pincount before re-checking the PTE for changes. + * This is essentially a smp_mb() and is paired with a memory + * barrier in folio_try_share_anon_rmap_*(). + */ + smp_mb__after_atomic(); + + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); + + return folio; +} #endif /* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */ #ifdef CONFIG_ARCH_HAS_HUGEPD @@ -535,7 +543,7 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, */ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz, unsigned long addr, unsigned long end, unsigned int flags, - struct page **pages, int *nr) + struct page **pages, int *nr, bool fast) { unsigned long pte_end; struct page *page; @@ -558,9 +566,15 @@ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz page = pte_page(pte); refs = record_subpages(page, sz, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); - if (!folio) - return 0; + if (fast) { + folio = try_grab_folio_fast(page, refs, flags); + if (!folio) + return 0; + } else { + folio = page_folio(page); + if (try_grab_folio(folio, refs, flags)) + return 0; + } if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, refs, flags); @@ -588,7 +602,7 @@ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, - struct page **pages, int *nr) + struct page **pages, int *nr, bool fast) { pte_t *ptep; unsigned long sz = 1UL << hugepd_shift(hugepd); @@ -598,7 +612,8 @@ static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, ptep = hugepte_offset(hugepd, addr, pdshift); do { next = hugepte_addr_end(addr, end, sz); - ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr); + ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr, + fast); if (ret != 1) return ret; } while (ptep++, addr = next, addr != end); @@ -625,7 +640,7 @@ static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, ptep = hugepte_offset(hugepd, addr, pdshift); ptl = huge_pte_lock(h, vma->vm_mm, ptep); ret = gup_hugepd(vma, hugepd, addr, pdshift, addr + PAGE_SIZE, - flags, &page, &nr); + flags, &page, &nr, false); spin_unlock(ptl); if (ret == 1) { @@ -642,7 +657,7 @@ static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, static inline int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, - struct page **pages, int *nr) + struct page **pages, int *nr, bool fast) { return 0; } @@ -729,7 +744,7 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma, gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); - ret = try_grab_page(page, flags); + ret = try_grab_folio(page_folio(page), 1, flags); if (ret) page = ERR_PTR(ret); else @@ -806,7 +821,7 @@ static struct page *follow_huge_pmd(struct vm_area_struct *vma, VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); - ret = try_grab_page(page, flags); + ret = try_grab_folio(page_folio(page), 1, flags); if (ret) return ERR_PTR(ret); @@ -968,8 +983,8 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); - /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */ - ret = try_grab_page(page, flags); + /* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */ + ret = try_grab_folio(page_folio(page), 1, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; @@ -1233,7 +1248,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, goto unmap; *page = pte_page(entry); } - ret = try_grab_page(*page, gup_flags); + ret = try_grab_folio(page_folio(*page), 1, gup_flags); if (unlikely(ret)) goto unmap; out: @@ -1636,20 +1651,19 @@ next_page: * pages. */ if (page_increm > 1) { - struct folio *folio; + struct folio *folio = page_folio(page); /* * Since we already hold refcount on the * large folio, this should never fail. */ - folio = try_grab_folio(page, page_increm - 1, - foll_flags); - if (WARN_ON_ONCE(!folio)) { + if (try_grab_folio(folio, page_increm - 1, + foll_flags)) { /* * Release the 1st page ref if the * folio is problematic, fail hard. */ - gup_put_folio(page_folio(page), 1, + gup_put_folio(folio, 1, foll_flags); ret = -EFAULT; goto out; @@ -2797,7 +2811,6 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * This code is based heavily on the PowerPC implementation by Nick Piggin. */ #ifdef CONFIG_HAVE_GUP_FAST - /* * Used in the GUP-fast path to determine whether GUP is permitted to work on * a specific folio. @@ -2962,7 +2975,7 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - folio = try_grab_folio(page, 1, flags); + folio = try_grab_folio_fast(page, 1, flags); if (!folio) goto pte_unmap; @@ -3049,7 +3062,7 @@ static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, break; } - folio = try_grab_folio(page, 1, flags); + folio = try_grab_folio_fast(page, 1, flags); if (!folio) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; @@ -3138,7 +3151,7 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, page = pmd_page(orig); refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -3182,7 +3195,7 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, page = pud_page(orig); refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -3222,7 +3235,7 @@ static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, page = pgd_page(orig); refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -3276,7 +3289,8 @@ static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, * pmd format and THP pmd format */ if (gup_hugepd(NULL, __hugepd(pmd_val(pmd)), addr, - PMD_SHIFT, next, flags, pages, nr) != 1) + PMD_SHIFT, next, flags, pages, nr, + true) != 1) return 0; } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) @@ -3306,7 +3320,8 @@ static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, return 0; } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { if (gup_hugepd(NULL, __hugepd(pud_val(pud)), addr, - PUD_SHIFT, next, flags, pages, nr) != 1) + PUD_SHIFT, next, flags, pages, nr, + true) != 1) return 0; } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, pages, nr)) @@ -3333,7 +3348,8 @@ static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, BUILD_BUG_ON(p4d_leaf(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { if (gup_hugepd(NULL, __hugepd(p4d_val(p4d)), addr, - P4D_SHIFT, next, flags, pages, nr) != 1) + P4D_SHIFT, next, flags, pages, nr, + true) != 1) return 0; } else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) @@ -3362,7 +3378,8 @@ static void gup_fast_pgd_range(unsigned long addr, unsigned long end, return; } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { if (gup_hugepd(NULL, __hugepd(pgd_val(pgd)), addr, - PGDIR_SHIFT, next, flags, pages, nr) != 1) + PGDIR_SHIFT, next, flags, pages, nr, + true) != 1) return; } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index db7946a0a28c..2120f7478e55 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1331,7 +1331,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); - ret = try_grab_page(page, flags); + ret = try_grab_folio(page_folio(page), 1, flags); if (ret) page = ERR_PTR(ret); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f35abff8be60..43e1af868cfd 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1625,13 +1625,10 @@ static inline void destroy_compound_gigantic_folio(struct folio *folio, * folio appears as just a compound page. Otherwise, wait until after * allocating vmemmap to clear the flag. * - * A reference is held on the folio, except in the case of demote. - * * Must be called with hugetlb lock held. */ -static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, - bool adjust_surplus, - bool demote) +static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, + bool adjust_surplus) { int nid = folio_nid(folio); @@ -1645,6 +1642,7 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, list_del(&folio->lru); if (folio_test_hugetlb_freed(folio)) { + folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; } @@ -1661,33 +1659,13 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, if (!folio_test_hugetlb_vmemmap_optimized(folio)) __folio_clear_hugetlb(folio); - /* - * In the case of demote we do not ref count the page as it will soon - * be turned into a page of smaller size. - */ - if (!demote) - folio_ref_unfreeze(folio, 1); - h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } -static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, - bool adjust_surplus) -{ - __remove_hugetlb_folio(h, folio, adjust_surplus, false); -} - -static void remove_hugetlb_folio_for_demote(struct hstate *h, struct folio *folio, - bool adjust_surplus) -{ - __remove_hugetlb_folio(h, folio, adjust_surplus, true); -} - static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { - int zeroed; int nid = folio_nid(folio); VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); @@ -1711,21 +1689,6 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, */ folio_set_hugetlb_vmemmap_optimized(folio); - /* - * This folio is about to be managed by the hugetlb allocator and - * should have no users. Drop our reference, and check for others - * just in case. - */ - zeroed = folio_put_testzero(folio); - if (unlikely(!zeroed)) - /* - * It is VERY unlikely soneone else has taken a ref - * on the folio. In this case, we simply return as - * free_huge_folio() will be called when this other ref - * is dropped. - */ - return; - arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } @@ -1763,13 +1726,6 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, } /* - * Move PageHWPoison flag from head page to the raw error pages, - * which makes any healthy subpages reusable. - */ - if (unlikely(folio_test_hwpoison(folio))) - folio_clear_hugetlb_hwpoison(folio); - - /* * If vmemmap pages were allocated above, then we need to clear the * hugetlb flag under the hugetlb lock. */ @@ -1780,6 +1736,15 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, } /* + * Move PageHWPoison flag from head page to the raw error pages, + * which makes any healthy subpages reusable. + */ + if (unlikely(folio_test_hwpoison(folio))) + folio_clear_hugetlb_hwpoison(folio); + + folio_ref_unfreeze(folio, 1); + + /* * Non-gigantic pages demoted from CMA allocated gigantic pages * need to be given back to CMA in free_gigantic_folio. */ @@ -2197,6 +2162,9 @@ static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, nid = numa_mem_id(); retry: folio = __folio_alloc(gfp_mask, order, nid, nmask); + /* Ensure hugetlb folio won't have large_rmappable flag set. */ + if (folio) + folio_clear_large_rmappable(folio); if (folio && !folio_ref_freeze(folio, 1)) { folio_put(folio); @@ -3079,11 +3047,8 @@ retry: free_new: spin_unlock_irq(&hugetlb_lock); - if (new_folio) { - /* Folio has a zero ref count, but needs a ref to be freed */ - folio_ref_unfreeze(new_folio, 1); + if (new_folio) update_and_free_hugetlb_folio(h, new_folio, false); - } return ret; } @@ -3938,7 +3903,7 @@ static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); - remove_hugetlb_folio_for_demote(h, folio, false); + remove_hugetlb_folio(h, folio, false); spin_unlock_irq(&hugetlb_lock); /* @@ -3952,7 +3917,6 @@ static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) if (rc) { /* Allocation of vmemmmap failed, we can not demote folio */ spin_lock_irq(&hugetlb_lock); - folio_ref_unfreeze(folio, 1); add_hugetlb_folio(h, folio, false); return rc; } diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index b9a55322e52c..8193906515c6 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -446,6 +446,8 @@ static int __hugetlb_vmemmap_restore_folio(const struct hstate *h, unsigned long vmemmap_reuse; VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_ref_count(folio), folio); + if (!folio_test_hugetlb_vmemmap_optimized(folio)) return 0; @@ -481,6 +483,9 @@ static int __hugetlb_vmemmap_restore_folio(const struct hstate *h, */ int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio) { + /* avoid writes from page_ref_add_unless() while unfolding vmemmap */ + synchronize_rcu(); + return __hugetlb_vmemmap_restore_folio(h, folio, 0); } @@ -505,6 +510,9 @@ long hugetlb_vmemmap_restore_folios(const struct hstate *h, long restored = 0; long ret = 0; + /* avoid writes from page_ref_add_unless() while unfolding vmemmap */ + synchronize_rcu(); + list_for_each_entry_safe(folio, t_folio, folio_list, lru) { if (folio_test_hugetlb_vmemmap_optimized(folio)) { ret = __hugetlb_vmemmap_restore_folio(h, folio, @@ -550,6 +558,8 @@ static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h, unsigned long vmemmap_reuse; VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_ref_count(folio), folio); + if (!vmemmap_should_optimize_folio(h, folio)) return ret; @@ -601,6 +611,9 @@ void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio) { LIST_HEAD(vmemmap_pages); + /* avoid writes from page_ref_add_unless() while folding vmemmap */ + synchronize_rcu(); + __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, 0); free_vmemmap_page_list(&vmemmap_pages); } @@ -644,6 +657,9 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l flush_tlb_all(); + /* avoid writes from page_ref_add_unless() while folding vmemmap */ + synchronize_rcu(); + list_for_each_entry(folio, folio_list, lru) { int ret; diff --git a/mm/internal.h b/mm/internal.h index 6902b7dd8509..cc2c5e07fad3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1182,8 +1182,8 @@ int migrate_device_coherent_page(struct page *page); /* * mm/gup.c */ -struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); -int __must_check try_grab_page(struct page *page, unsigned int flags); +int __must_check try_grab_folio(struct folio *folio, int refs, + unsigned int flags); /* * mm/huge_memory.c diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 774a97e6e2da..aab471791bd9 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2000,9 +2000,9 @@ out_unlock: if (!is_shmem) { filemap_nr_thps_inc(mapping); /* - * Paired with smp_mb() in do_dentry_open() to ensure - * i_writecount is up to date and the update to nr_thps is - * visible. Ensures the page cache will be truncated if the + * Paired with the fence in do_dentry_open() -> get_write_access() + * to ensure i_writecount is up to date and the update to nr_thps + * is visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); @@ -2190,8 +2190,8 @@ rollback: if (!is_shmem && result == SCAN_COPY_MC) { filemap_nr_thps_dec(mapping); /* - * Paired with smp_mb() in do_dentry_open() to - * ensure the update to nr_thps is visible. + * Paired with the fence in do_dentry_open() -> get_write_access() + * to ensure the update to nr_thps is visible. */ smp_mb(); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 71fe2a95b8bd..8f2f1bb18c9c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7823,17 +7823,6 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new) /* Transfer the charge and the css ref */ commit_charge(new, memcg); - /* - * If the old folio is a large folio and is in the split queue, it needs - * to be removed from the split queue now, in case getting an incorrect - * split queue in destroy_large_folio() after the memcg of the old folio - * is cleared. - * - * In addition, the old folio is about to be freed after migration, so - * removing from the split queue a bit earlier seems reasonable. - */ - if (folio_test_large(old) && folio_test_large_rmappable(old)) - folio_undo_large_rmappable(old); old->memcg_data = 0; } diff --git a/mm/migrate.c b/mm/migrate.c index 20cb9f5f7446..a8c6f466e33a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -415,6 +415,15 @@ int folio_migrate_mapping(struct address_space *mapping, if (folio_ref_count(folio) != expected_count) return -EAGAIN; + /* Take off deferred split queue while frozen and memcg set */ + if (folio_test_large(folio) && + folio_test_large_rmappable(folio)) { + if (!folio_ref_freeze(folio, expected_count)) + return -EAGAIN; + folio_undo_large_rmappable(folio); + folio_ref_unfreeze(folio, expected_count); + } + /* No turning back from here */ newfolio->index = folio->index; newfolio->mapping = folio->mapping; @@ -433,6 +442,10 @@ int folio_migrate_mapping(struct address_space *mapping, return -EAGAIN; } + /* Take off deferred split queue while frozen and memcg set */ + if (folio_test_large(folio) && folio_test_large_rmappable(folio)) + folio_undo_large_rmappable(folio); + /* * Now we know that no one else is looking at the folio: * no turning back from here. diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 12c9297ed4a7..8a1c92090129 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -415,13 +415,20 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc) else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; - if (bg_thresh >= thresh) - bg_thresh = thresh / 2; tsk = current; if (rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } + /* + * Dirty throttling logic assumes the limits in page units fit into + * 32-bits. This gives 16TB dirty limits max which is hopefully enough. + */ + if (thresh > UINT_MAX) + thresh = UINT_MAX; + /* This makes sure bg_thresh is within 32-bits as well */ + if (bg_thresh >= thresh) + bg_thresh = thresh / 2; dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; @@ -471,7 +478,11 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat) if (rt_task(tsk)) dirty += dirty / 4; - return dirty; + /* + * Dirty throttling logic assumes the limits in page units fit into + * 32-bits. This gives 16TB dirty limits max which is hopefully enough. + */ + return min_t(unsigned long, dirty, UINT_MAX); } /** @@ -508,10 +519,17 @@ static int dirty_background_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; + unsigned long old_bytes = dirty_background_bytes; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); - if (ret == 0 && write) + if (ret == 0 && write) { + if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) > + UINT_MAX) { + dirty_background_bytes = old_bytes; + return -ERANGE; + } dirty_background_ratio = 0; + } return ret; } @@ -537,6 +555,10 @@ static int dirty_bytes_handler(struct ctl_table *table, int write, ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { + if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) { + vm_dirty_bytes = old_bytes; + return -ERANGE; + } writeback_set_ratelimit(); vm_dirty_ratio = 0; } @@ -1660,7 +1682,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) */ dtc->wb_thresh = __wb_calc_thresh(dtc, dtc->thresh); dtc->wb_bg_thresh = dtc->thresh ? - div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; + div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need diff --git a/mm/readahead.c b/mm/readahead.c index c1b23989d9ca..817b2a352d78 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -503,11 +503,11 @@ void page_cache_ra_order(struct readahead_control *ractl, limit = min(limit, index + ra->size - 1); - if (new_order < MAX_PAGECACHE_ORDER) { + if (new_order < MAX_PAGECACHE_ORDER) new_order += 2; - new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order); - new_order = min_t(unsigned int, new_order, ilog2(ra->size)); - } + + new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order); + new_order = min_t(unsigned int, new_order, ilog2(ra->size)); /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); diff --git a/mm/shmem.c b/mm/shmem.c index a8b181a63402..831b52dfd56e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -541,8 +541,9 @@ static bool shmem_confirm_swap(struct address_space *mapping, static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; -bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags) +static bool __shmem_is_huge(struct inode *inode, pgoff_t index, + bool shmem_huge_force, struct mm_struct *mm, + unsigned long vm_flags) { loff_t i_size; @@ -573,6 +574,16 @@ bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, } } +bool shmem_is_huge(struct inode *inode, pgoff_t index, + bool shmem_huge_force, struct mm_struct *mm, + unsigned long vm_flags) +{ + if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) + return false; + + return __shmem_is_huge(inode, index, shmem_huge_force, mm, vm_flags); +} + #if defined(CONFIG_SYSFS) static int shmem_parse_huge(const char *str) { @@ -3166,10 +3177,13 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, struct folio *folio; /* - * Good, the fallocate(2) manpage permits EINTR: we may have - * been interrupted because we are using up too much memory. + * Check for fatal signal so that we abort early in OOM + * situations. We don't want to abort in case of non-fatal + * signals as large fallocate can take noticeable time and + * e.g. periodic timers may result in fallocate constantly + * restarting. */ - if (signal_pending(current)) + if (fatal_signal_pending(current)) error = -EINTR; else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced) error = -ENOMEM; @@ -3903,14 +3917,14 @@ static const struct constant_table shmem_param_enums_huge[] = { }; const struct fs_parameter_spec shmem_fs_parameters[] = { - fsparam_u32 ("gid", Opt_gid), + fsparam_gid ("gid", Opt_gid), fsparam_enum ("huge", Opt_huge, shmem_param_enums_huge), fsparam_u32oct("mode", Opt_mode), fsparam_string("mpol", Opt_mpol), fsparam_string("nr_blocks", Opt_nr_blocks), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("size", Opt_size), - fsparam_u32 ("uid", Opt_uid), + fsparam_uid ("uid", Opt_uid), fsparam_flag ("inode32", Opt_inode32), fsparam_flag ("inode64", Opt_inode64), fsparam_flag ("noswap", Opt_noswap), @@ -3970,9 +3984,7 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) ctx->mode = result.uint_32 & 07777; break; case Opt_uid: - kuid = make_kuid(current_user_ns(), result.uint_32); - if (!uid_valid(kuid)) - goto bad_value; + kuid = result.uid; /* * The requested uid must be representable in the @@ -3984,9 +3996,7 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) ctx->uid = kuid; break; case Opt_gid: - kgid = make_kgid(current_user_ns(), result.uint_32); - if (!gid_valid(kgid)) - goto bad_value; + kgid = result.gid; /* * The requested gid must be representable in the diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d0cbdd7c1e5b..e34ea860153f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2543,7 +2543,15 @@ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); static struct xarray * addr_to_vb_xa(unsigned long addr) { - int index = (addr / VMAP_BLOCK_SIZE) % num_possible_cpus(); + int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids; + + /* + * Please note, nr_cpu_ids points on a highest set + * possible bit, i.e. we never invoke cpumask_next() + * if an index points on it which is nr_cpu_ids - 1. + */ + if (!cpu_possible(index)) + index = cpumask_next(index, cpu_possible_mask); return &per_cpu(vmap_block_queue, index).vmap_blocks; } diff --git a/mm/workingset.c b/mm/workingset.c index c22adb93622a..a2b28e356e68 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -412,10 +412,12 @@ void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg) * @file: whether the corresponding folio is from the file lru. * @workingset: where the workingset value unpacked from shadow should * be stored. + * @flush: whether to flush cgroup rstat. * * Return: true if the shadow is for a recently evicted folio; false otherwise. */ -bool workingset_test_recent(void *shadow, bool file, bool *workingset) +bool workingset_test_recent(void *shadow, bool file, bool *workingset, + bool flush) { struct mem_cgroup *eviction_memcg; struct lruvec *eviction_lruvec; @@ -467,10 +469,16 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset) /* * Flush stats (and potentially sleep) outside the RCU read section. + * + * Note that workingset_test_recent() itself might be called in RCU read + * section (for e.g, in cachestat) - these callers need to skip flushing + * stats (via the flush argument). + * * XXX: With per-memcg flushing and thresholding, is ratelimiting * still needed here? */ - mem_cgroup_flush_stats_ratelimited(eviction_memcg); + if (flush) + mem_cgroup_flush_stats_ratelimited(eviction_memcg); eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); refault = atomic_long_read(&eviction_lruvec->nonresident_age); @@ -558,7 +566,7 @@ void workingset_refault(struct folio *folio, void *shadow) mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - if (!workingset_test_recent(shadow, file, &workingset)) + if (!workingset_test_recent(shadow, file, &workingset, true)) return; folio_set_active(folio); |