diff options
Diffstat (limited to 'mm/mlock.c')
| -rw-r--r-- | mm/mlock.c | 935 |
1 files changed, 446 insertions, 489 deletions
diff --git a/mm/mlock.c b/mm/mlock.c index 41cc47e28ad6..2f699c3497a5 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -14,6 +14,7 @@ #include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/pagevec.h> +#include <linux/pagewalk.h> #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> @@ -23,9 +24,19 @@ #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/mm_inline.h> +#include <linux/secretmem.h> #include "internal.h" +struct mlock_fbatch { + local_lock_t lock; + struct folio_batch fbatch; +}; + +static DEFINE_PER_CPU(struct mlock_fbatch, mlock_fbatch) = { + .lock = INIT_LOCAL_LOCK(lock), +}; + bool can_do_mlock(void) { if (rlimit(RLIMIT_MEMLOCK) != 0) @@ -37,473 +48,409 @@ bool can_do_mlock(void) EXPORT_SYMBOL(can_do_mlock); /* - * Mlocked pages are marked with PageMlocked() flag for efficient testing + * Mlocked folios are marked with the PG_mlocked flag for efficient testing * in vmscan and, possibly, the fault path; and to support semi-accurate * statistics. * - * An mlocked page [PageMlocked(page)] is unevictable. As such, it will - * be placed on the LRU "unevictable" list, rather than the [in]active lists. - * The unevictable list is an LRU sibling list to the [in]active lists. - * PageUnevictable is set to indicate the unevictable state. - * - * When lazy mlocking via vmscan, it is important to ensure that the - * vma's VM_LOCKED status is not concurrently being modified, otherwise we - * may have mlocked a page that is being munlocked. So lazy mlock must take - * the mmap_sem for read, and verify that the vma really is locked - * (see mm/rmap.c). + * An mlocked folio [folio_test_mlocked(folio)] is unevictable. As such, it + * will be ostensibly placed on the LRU "unevictable" list (actually no such + * list exists), rather than the [in]active lists. PG_unevictable is set to + * indicate the unevictable state. */ -/* - * LRU accounting for clear_page_mlock() - */ -void clear_page_mlock(struct page *page) +static struct lruvec *__mlock_folio(struct folio *folio, struct lruvec *lruvec) { - if (!TestClearPageMlocked(page)) - return; + /* There is nothing more we can do while it's off LRU */ + if (!folio_test_clear_lru(folio)) + return lruvec; - mod_zone_page_state(page_zone(page), NR_MLOCK, - -hpage_nr_pages(page)); - count_vm_event(UNEVICTABLE_PGCLEARED); - /* - * The previous TestClearPageMlocked() corresponds to the smp_mb() - * in __pagevec_lru_add_fn(). - * - * See __pagevec_lru_add_fn for more explanation. - */ - if (!isolate_lru_page(page)) { - putback_lru_page(page); - } else { + lruvec = folio_lruvec_relock_irq(folio, lruvec); + + if (unlikely(folio_evictable(folio))) { /* - * We lost the race. the page already moved to evictable list. + * This is a little surprising, but quite possible: PG_mlocked + * must have got cleared already by another CPU. Could this + * folio be unevictable? I'm not sure, but move it now if so. */ - if (PageUnevictable(page)) - count_vm_event(UNEVICTABLE_PGSTRANDED); + if (folio_test_unevictable(folio)) { + lruvec_del_folio(lruvec, folio); + folio_clear_unevictable(folio); + lruvec_add_folio(lruvec, folio); + + __count_vm_events(UNEVICTABLE_PGRESCUED, + folio_nr_pages(folio)); + } + goto out; } + + if (folio_test_unevictable(folio)) { + if (folio_test_mlocked(folio)) + folio->mlock_count++; + goto out; + } + + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + folio_set_unevictable(folio); + folio->mlock_count = !!folio_test_mlocked(folio); + lruvec_add_folio(lruvec, folio); + __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); +out: + folio_set_lru(folio); + return lruvec; } -/* - * Mark page as mlocked if not already. - * If page on LRU, isolate and putback to move to unevictable list. - */ -void mlock_vma_page(struct page *page) +static struct lruvec *__mlock_new_folio(struct folio *folio, struct lruvec *lruvec) { - /* Serialize with page migration */ - BUG_ON(!PageLocked(page)); - - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); - - if (!TestSetPageMlocked(page)) { - mod_zone_page_state(page_zone(page), NR_MLOCK, - hpage_nr_pages(page)); - count_vm_event(UNEVICTABLE_PGMLOCKED); - if (!isolate_lru_page(page)) - putback_lru_page(page); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + + lruvec = folio_lruvec_relock_irq(folio, lruvec); + + /* As above, this is a little surprising, but possible */ + if (unlikely(folio_evictable(folio))) + goto out; + + folio_set_unevictable(folio); + folio->mlock_count = !!folio_test_mlocked(folio); + __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); +out: + lruvec_add_folio(lruvec, folio); + folio_set_lru(folio); + return lruvec; +} + +static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec) +{ + int nr_pages = folio_nr_pages(folio); + bool isolated = false; + + if (!folio_test_clear_lru(folio)) + goto munlock; + + isolated = true; + lruvec = folio_lruvec_relock_irq(folio, lruvec); + + if (folio_test_unevictable(folio)) { + /* Then mlock_count is maintained, but might undercount */ + if (folio->mlock_count) + folio->mlock_count--; + if (folio->mlock_count) + goto out; + } + /* else assume that was the last mlock: reclaim will fix it if not */ + +munlock: + if (folio_test_clear_mlocked(folio)) { + __zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); + if (isolated || !folio_test_unevictable(folio)) + __count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages); + else + __count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); + } + + /* folio_evictable() has to be checked *after* clearing Mlocked */ + if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) { + lruvec_del_folio(lruvec, folio); + folio_clear_unevictable(folio); + lruvec_add_folio(lruvec, folio); + __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } +out: + if (isolated) + folio_set_lru(folio); + return lruvec; } /* - * Isolate a page from LRU with optional get_page() pin. - * Assumes lru_lock already held and page already pinned. + * Flags held in the low bits of a struct folio pointer on the mlock_fbatch. */ -static bool __munlock_isolate_lru_page(struct page *page, bool getpage) +#define LRU_FOLIO 0x1 +#define NEW_FOLIO 0x2 +static inline struct folio *mlock_lru(struct folio *folio) { - if (PageLRU(page)) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); - if (getpage) - get_page(page); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_lru(page)); - return true; - } + return (struct folio *)((unsigned long)folio + LRU_FOLIO); +} - return false; +static inline struct folio *mlock_new(struct folio *folio) +{ + return (struct folio *)((unsigned long)folio + NEW_FOLIO); } /* - * Finish munlock after successful page isolation - * - * Page must be locked. This is a wrapper for try_to_munlock() - * and putback_lru_page() with munlock accounting. + * mlock_folio_batch() is derived from folio_batch_move_lru(): perhaps that can + * make use of such folio pointer flags in future, but for now just keep it for + * mlock. We could use three separate folio batches instead, but one feels + * better (munlocking a full folio batch does not need to drain mlocking folio + * batches first). */ -static void __munlock_isolated_page(struct page *page) +static void mlock_folio_batch(struct folio_batch *fbatch) { - /* - * Optimization: if the page was mapped just once, that's our mapping - * and we don't need to check all the other vmas. - */ - if (page_mapcount(page) > 1) - try_to_munlock(page); + struct lruvec *lruvec = NULL; + unsigned long mlock; + struct folio *folio; + int i; - /* Did try_to_unlock() succeed or punt? */ - if (!PageMlocked(page)) - count_vm_event(UNEVICTABLE_PGMUNLOCKED); + for (i = 0; i < folio_batch_count(fbatch); i++) { + folio = fbatch->folios[i]; + mlock = (unsigned long)folio & (LRU_FOLIO | NEW_FOLIO); + folio = (struct folio *)((unsigned long)folio - mlock); + fbatch->folios[i] = folio; + + if (mlock & LRU_FOLIO) + lruvec = __mlock_folio(folio, lruvec); + else if (mlock & NEW_FOLIO) + lruvec = __mlock_new_folio(folio, lruvec); + else + lruvec = __munlock_folio(folio, lruvec); + } - putback_lru_page(page); + if (lruvec) + unlock_page_lruvec_irq(lruvec); + folios_put(fbatch); } -/* - * Accounting for page isolation fail during munlock - * - * Performs accounting when page isolation fails in munlock. There is nothing - * else to do because it means some other task has already removed the page - * from the LRU. putback_lru_page() will take care of removing the page from - * the unevictable list, if necessary. vmscan [page_referenced()] will move - * the page back to the unevictable list if some other vma has it mlocked. - */ -static void __munlock_isolation_failed(struct page *page) +void mlock_drain_local(void) { - if (PageUnevictable(page)) - __count_vm_event(UNEVICTABLE_PGSTRANDED); - else - __count_vm_event(UNEVICTABLE_PGMUNLOCKED); + struct folio_batch *fbatch; + + local_lock(&mlock_fbatch.lock); + fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); + if (folio_batch_count(fbatch)) + mlock_folio_batch(fbatch); + local_unlock(&mlock_fbatch.lock); } -/** - * munlock_vma_page - munlock a vma page - * @page: page to be unlocked, either a normal page or THP page head - * - * returns the size of the page as a page mask (0 for normal page, - * HPAGE_PMD_NR - 1 for THP head page) - * - * called from munlock()/munmap() path with page supposedly on the LRU. - * When we munlock a page, because the vma where we found the page is being - * munlock()ed or munmap()ed, we want to check whether other vmas hold the - * page locked so that we can leave it on the unevictable lru list and not - * bother vmscan with it. However, to walk the page's rmap list in - * try_to_munlock() we must isolate the page from the LRU. If some other - * task has removed the page from the LRU, we won't be able to do that. - * So we clear the PageMlocked as we might not get another chance. If we - * can't isolate the page, we leave it for putback_lru_page() and vmscan - * [page_referenced()/try_to_unmap()] to deal with. - */ -unsigned int munlock_vma_page(struct page *page) +void mlock_drain_remote(int cpu) { - int nr_pages; - struct zone *zone = page_zone(page); + struct folio_batch *fbatch; - /* For try_to_munlock() and to serialize with page migration */ - BUG_ON(!PageLocked(page)); + WARN_ON_ONCE(cpu_online(cpu)); + fbatch = &per_cpu(mlock_fbatch.fbatch, cpu); + if (folio_batch_count(fbatch)) + mlock_folio_batch(fbatch); +} - VM_BUG_ON_PAGE(PageTail(page), page); +bool need_mlock_drain(int cpu) +{ + return folio_batch_count(&per_cpu(mlock_fbatch.fbatch, cpu)); +} - /* - * Serialize with any parallel __split_huge_page_refcount() which - * might otherwise copy PageMlocked to part of the tail pages before - * we clear it in the head page. It also stabilizes hpage_nr_pages(). - */ - spin_lock_irq(zone_lru_lock(zone)); +/** + * mlock_folio - mlock a folio already on (or temporarily off) LRU + * @folio: folio to be mlocked. + */ +void mlock_folio(struct folio *folio) +{ + struct folio_batch *fbatch; - if (!TestClearPageMlocked(page)) { - /* Potentially, PTE-mapped THP: do not skip the rest PTEs */ - nr_pages = 1; - goto unlock_out; - } + local_lock(&mlock_fbatch.lock); + fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); - nr_pages = hpage_nr_pages(page); - __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); + if (!folio_test_set_mlocked(folio)) { + int nr_pages = folio_nr_pages(folio); - if (__munlock_isolate_lru_page(page, true)) { - spin_unlock_irq(zone_lru_lock(zone)); - __munlock_isolated_page(page); - goto out; + zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); + __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } - __munlock_isolation_failed(page); - -unlock_out: - spin_unlock_irq(zone_lru_lock(zone)); -out: - return nr_pages - 1; + folio_get(folio); + if (!folio_batch_add(fbatch, mlock_lru(folio)) || + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) + mlock_folio_batch(fbatch); + local_unlock(&mlock_fbatch.lock); } -/* - * convert get_user_pages() return value to posix mlock() error +/** + * mlock_new_folio - mlock a newly allocated folio not yet on LRU + * @folio: folio to be mlocked, either normal or a THP head. */ -static int __mlock_posix_error_return(long retval) +void mlock_new_folio(struct folio *folio) { - if (retval == -EFAULT) - retval = -ENOMEM; - else if (retval == -ENOMEM) - retval = -EAGAIN; - return retval; -} + struct folio_batch *fbatch; + int nr_pages = folio_nr_pages(folio); -/* - * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec() - * - * The fast path is available only for evictable pages with single mapping. - * Then we can bypass the per-cpu pvec and get better performance. - * when mapcount > 1 we need try_to_munlock() which can fail. - * when !page_evictable(), we need the full redo logic of putback_lru_page to - * avoid leaving evictable page in unevictable list. - * - * In case of success, @page is added to @pvec and @pgrescued is incremented - * in case that the page was previously unevictable. @page is also unlocked. - */ -static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec, - int *pgrescued) -{ - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(!PageLocked(page), page); - - if (page_mapcount(page) <= 1 && page_evictable(page)) { - pagevec_add(pvec, page); - if (TestClearPageUnevictable(page)) - (*pgrescued)++; - unlock_page(page); - return true; - } + local_lock(&mlock_fbatch.lock); + fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); + folio_set_mlocked(folio); - return false; + zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); + __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); + + folio_get(folio); + if (!folio_batch_add(fbatch, mlock_new(folio)) || + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) + mlock_folio_batch(fbatch); + local_unlock(&mlock_fbatch.lock); } -/* - * Putback multiple evictable pages to the LRU - * - * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of - * the pages might have meanwhile become unevictable but that is OK. +/** + * munlock_folio - munlock a folio + * @folio: folio to be munlocked, either normal or a THP head. */ -static void __putback_lru_fast(struct pagevec *pvec, int pgrescued) +void munlock_folio(struct folio *folio) { - count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec)); + struct folio_batch *fbatch; + + local_lock(&mlock_fbatch.lock); + fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); /* - *__pagevec_lru_add() calls release_pages() so we don't call - * put_page() explicitly + * folio_test_clear_mlocked(folio) must be left to __munlock_folio(), + * which will check whether the folio is multiply mlocked. */ - __pagevec_lru_add(pvec); - count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); + folio_get(folio); + if (!folio_batch_add(fbatch, folio) || + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) + mlock_folio_batch(fbatch); + local_unlock(&mlock_fbatch.lock); } -/* - * Munlock a batch of pages from the same zone - * - * The work is split to two main phases. First phase clears the Mlocked flag - * and attempts to isolate the pages, all under a single zone lru lock. - * The second phase finishes the munlock only for pages where isolation - * succeeded. - * - * Note that the pagevec may be modified during the process. - */ -static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) +static inline unsigned int folio_mlock_step(struct folio *folio, + pte_t *pte, unsigned long addr, unsigned long end) { - int i; - int nr = pagevec_count(pvec); - int delta_munlocked = -nr; - struct pagevec pvec_putback; - int pgrescued = 0; - - pagevec_init(&pvec_putback); - - /* Phase 1: page isolation */ - spin_lock_irq(zone_lru_lock(zone)); - for (i = 0; i < nr; i++) { - struct page *page = pvec->pages[i]; - - if (TestClearPageMlocked(page)) { - /* - * We already have pin from follow_page_mask() - * so we can spare the get_page() here. - */ - if (__munlock_isolate_lru_page(page, false)) - continue; - else - __munlock_isolation_failed(page); - } else { - delta_munlocked++; - } + unsigned int count = (end - addr) >> PAGE_SHIFT; + pte_t ptent = ptep_get(pte); - /* - * We won't be munlocking this page in the next phase - * but we still need to release the follow_page_mask() - * pin. We cannot do it under lru_lock however. If it's - * the last pin, __page_cache_release() would deadlock. - */ - pagevec_add(&pvec_putback, pvec->pages[i]); - pvec->pages[i] = NULL; - } - __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); - spin_unlock_irq(zone_lru_lock(zone)); - - /* Now we can release pins of pages that we are not munlocking */ - pagevec_release(&pvec_putback); - - /* Phase 2: page munlock */ - for (i = 0; i < nr; i++) { - struct page *page = pvec->pages[i]; - - if (page) { - lock_page(page); - if (!__putback_lru_fast_prepare(page, &pvec_putback, - &pgrescued)) { - /* - * Slow path. We don't want to lose the last - * pin before unlock_page() - */ - get_page(page); /* for putback_lru_page() */ - __munlock_isolated_page(page); - unlock_page(page); - put_page(page); /* from follow_page_mask() */ - } - } - } + if (!folio_test_large(folio)) + return 1; + + return folio_pte_batch(folio, pte, ptent, count); +} +static inline bool allow_mlock_munlock(struct folio *folio, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned int step) +{ /* - * Phase 3: page putback for pages that qualified for the fast path - * This will also call put_page() to return pin from follow_page_mask() + * For unlock, allow munlock large folio which is partially + * mapped to VMA. As it's possible that large folio is + * mlocked and VMA is split later. + * + * During memory pressure, such kind of large folio can + * be split. And the pages are not in VM_LOCKed VMA + * can be reclaimed. */ - if (pagevec_count(&pvec_putback)) - __putback_lru_fast(&pvec_putback, pgrescued); + if (!(vma->vm_flags & VM_LOCKED)) + return true; + + /* folio_within_range() cannot take KSM, but any small folio is OK */ + if (!folio_test_large(folio)) + return true; + + /* folio not in range [start, end), skip mlock */ + if (!folio_within_range(folio, vma, start, end)) + return false; + + /* folio is not fully mapped, skip mlock */ + if (step != folio_nr_pages(folio)) + return false; + + return true; } -/* - * Fill up pagevec for __munlock_pagevec using pte walk - * - * The function expects that the struct page corresponding to @start address is - * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone. - * - * The rest of @pvec is filled by subsequent pages within the same pmd and same - * zone, as long as the pte's are present and vm_normal_page() succeeds. These - * pages also get pinned. - * - * Returns the address of the next page that should be scanned. This equals - * @start + PAGE_SIZE when no page could be added by the pte walk. - */ -static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, - struct vm_area_struct *vma, struct zone *zone, - unsigned long start, unsigned long end) +static int mlock_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) + { - pte_t *pte; + struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; + pte_t *start_pte, *pte; + pte_t ptent; + struct folio *folio; + unsigned int step = 1; + unsigned long start = addr; + + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { + if (!pmd_present(*pmd)) + goto out; + if (is_huge_zero_pmd(*pmd)) + goto out; + folio = pmd_folio(*pmd); + if (folio_is_zone_device(folio)) + goto out; + if (vma->vm_flags & VM_LOCKED) + mlock_folio(folio); + else + munlock_folio(folio); + goto out; + } - /* - * Initialize pte walk starting at the already pinned page where we - * are sure that there is a pte, as it was pinned under the same - * mmap_sem write op. - */ - pte = get_locked_pte(vma->vm_mm, start, &ptl); - /* Make sure we do not cross the page table boundary */ - end = pgd_addr_end(start, end); - end = p4d_addr_end(start, end); - end = pud_addr_end(start, end); - end = pmd_addr_end(start, end); - - /* The page next to the pinned page is the first we will try to get */ - start += PAGE_SIZE; - while (start < end) { - struct page *page = NULL; - pte++; - if (pte_present(*pte)) - page = vm_normal_page(vma, start, *pte); - /* - * Break if page could not be obtained or the page's node+zone does not - * match - */ - if (!page || page_zone(page) != zone) - break; + start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + if (!start_pte) { + walk->action = ACTION_AGAIN; + return 0; + } - /* - * Do not use pagevec for PTE-mapped THP, - * munlock_vma_pages_range() will handle them. - */ - if (PageTransCompound(page)) - break; + for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { + ptent = ptep_get(pte); + if (!pte_present(ptent)) + continue; + folio = vm_normal_folio(vma, addr, ptent); + if (!folio || folio_is_zone_device(folio)) + continue; - get_page(page); - /* - * Increase the address that will be returned *before* the - * eventual break due to pvec becoming full by adding the page - */ - start += PAGE_SIZE; - if (pagevec_add(pvec, page) == 0) - break; + step = folio_mlock_step(folio, pte, addr, end); + if (!allow_mlock_munlock(folio, vma, start, end, step)) + goto next_entry; + + if (vma->vm_flags & VM_LOCKED) + mlock_folio(folio); + else + munlock_folio(folio); + +next_entry: + pte += step - 1; + addr += (step - 1) << PAGE_SHIFT; } - pte_unmap_unlock(pte, ptl); - return start; + pte_unmap(start_pte); +out: + spin_unlock(ptl); + cond_resched(); + return 0; } /* - * munlock_vma_pages_range() - munlock all pages in the vma range.' - * @vma - vma containing range to be munlock()ed. + * mlock_vma_pages_range() - mlock any pages already in the range, + * or munlock all pages in the range. + * @vma - vma containing range to be mlock()ed or munlock()ed * @start - start address in @vma of the range - * @end - end of range in @vma. - * - * For mremap(), munmap() and exit(). + * @end - end of range in @vma + * @newflags - the new set of flags for @vma. * - * Called with @vma VM_LOCKED. - * - * Returns with VM_LOCKED cleared. Callers must be prepared to - * deal with this. - * - * We don't save and restore VM_LOCKED here because pages are - * still on lru. In unmap path, pages might be scanned by reclaim - * and re-mlocked by try_to_{munlock|unmap} before we unmap and - * free them. This will result in freeing mlocked pages. + * Called for mlock(), mlock2() and mlockall(), to set @vma VM_LOCKED; + * called for munlock() and munlockall(), to clear VM_LOCKED from @vma. */ -void munlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) +static void mlock_vma_pages_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, vm_flags_t newflags) { - vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + static const struct mm_walk_ops mlock_walk_ops = { + .pmd_entry = mlock_pte_range, + .walk_lock = PGWALK_WRLOCK_VERIFY, + }; - while (start < end) { - struct page *page; - unsigned int page_mask = 0; - unsigned long page_increm; - struct pagevec pvec; - struct zone *zone; - - pagevec_init(&pvec); - /* - * Although FOLL_DUMP is intended for get_dump_page(), - * it just so happens that its special treatment of the - * ZERO_PAGE (returning an error instead of doing get_page) - * suits munlock very well (and if somehow an abnormal page - * has sneaked into the range, we won't oops here: great). - */ - page = follow_page(vma, start, FOLL_GET | FOLL_DUMP); - - if (page && !IS_ERR(page)) { - if (PageTransTail(page)) { - VM_BUG_ON_PAGE(PageMlocked(page), page); - put_page(page); /* follow_page_mask() */ - } else if (PageTransHuge(page)) { - lock_page(page); - /* - * Any THP page found by follow_page_mask() may - * have gotten split before reaching - * munlock_vma_page(), so we need to compute - * the page_mask here instead. - */ - page_mask = munlock_vma_page(page); - unlock_page(page); - put_page(page); /* follow_page_mask() */ - } else { - /* - * Non-huge pages are handled in batches via - * pagevec. The pin from follow_page_mask() - * prevents them from collapsing by THP. - */ - pagevec_add(&pvec, page); - zone = page_zone(page); - - /* - * Try to fill the rest of pagevec using fast - * pte walk. This will also update start to - * the next page to process. Then munlock the - * pagevec. - */ - start = __munlock_pagevec_fill(&pvec, vma, - zone, start, end); - __munlock_pagevec(&pvec, zone); - goto next; - } - } - page_increm = 1 + page_mask; - start += page_increm * PAGE_SIZE; -next: - cond_resched(); + /* + * There is a slight chance that concurrent page migration, + * or page reclaim finding a page of this now-VM_LOCKED vma, + * will call mlock_vma_folio() and raise page's mlock_count: + * double counting, leaving the page unevictable indefinitely. + * Communicate this danger to mlock_vma_folio() with VM_IO, + * which is a VM_SPECIAL flag not allowed on VM_LOCKED vmas. + * mmap_lock is held in write mode here, so this weird + * combination should not be visible to other mmap_lock users; + * but WRITE_ONCE so rmap walkers must see VM_IO if VM_LOCKED. + */ + if (newflags & VM_LOCKED) + newflags |= VM_IO; + vma_start_write(vma); + vm_flags_reset_once(vma, newflags); + + lru_add_drain(); + walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL); + lru_add_drain(); + + if (newflags & VM_IO) { + newflags &= ~VM_IO; + vm_flags_reset_once(vma, newflags); } } @@ -516,65 +463,49 @@ next: * * For vmas that pass the filters, merge/split as appropriate. */ -static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, - unsigned long start, unsigned long end, vm_flags_t newflags) +static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, + unsigned long end, vm_flags_t newflags) { struct mm_struct *mm = vma->vm_mm; - pgoff_t pgoff; int nr_pages; int ret = 0; - int lock = !!(newflags & VM_LOCKED); - vm_flags_t old_flags = vma->vm_flags; + vm_flags_t oldflags = vma->vm_flags; - if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) || + if (newflags == oldflags || (oldflags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) || - vma_is_dax(vma)) + vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE)) /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, - vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); - if (*prev) { - vma = *prev; - goto success; - } - - if (start != vma->vm_start) { - ret = split_vma(mm, vma, start, 1); - if (ret) - goto out; - } - - if (end != vma->vm_end) { - ret = split_vma(mm, vma, end, 0); - if (ret) - goto out; + vma = vma_modify_flags(vmi, *prev, vma, start, end, &newflags); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; } -success: /* * Keep track of amount of locked VM. */ nr_pages = (end - start) >> PAGE_SHIFT; - if (!lock) + if (!(newflags & VM_LOCKED)) nr_pages = -nr_pages; - else if (old_flags & VM_LOCKED) + else if (oldflags & VM_LOCKED) nr_pages = 0; mm->locked_vm += nr_pages; /* - * vm_flags is protected by the mmap_sem held in write mode. + * vm_flags is protected by the mmap_lock held in write mode. * It's okay if try_to_unmap_one unmaps a page just after we * set VM_LOCKED, populate_vma_page_range will bring it back. */ - - if (lock) - vma->vm_flags = newflags; - else - munlock_vma_pages_range(vma, start, end); - + if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) { + /* No work to do, and mlocking twice would be wrong */ + vma_start_write(vma); + vm_flags_reset(vma, newflags); + } else { + mlock_vma_pages_range(vma, start, end, newflags); + } out: *prev = vma; return ret; @@ -584,8 +515,8 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, vm_flags_t flags) { unsigned long nstart, end, tmp; - struct vm_area_struct * vma, * prev; - int error; + struct vm_area_struct *vma, *prev; + VMA_ITERATOR(vmi, current->mm, start); VM_BUG_ON(offset_in_page(start)); VM_BUG_ON(len != PAGE_ALIGN(len)); @@ -594,39 +525,40 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, return -EINVAL; if (end == start) return 0; - vma = find_vma(current->mm, start); - if (!vma || vma->vm_start > start) + vma = vma_iter_load(&vmi); + if (!vma) return -ENOMEM; - prev = vma->vm_prev; + prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; - for (nstart = start ; ; ) { - vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; + nstart = start; + tmp = vma->vm_start; + for_each_vma_range(vmi, vma, end) { + int error; + vm_flags_t newflags; + + if (vma->vm_start != tmp) + return -ENOMEM; + newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= flags; - /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ tmp = vma->vm_end; if (tmp > end) tmp = end; - error = mlock_fixup(vma, &prev, nstart, tmp, newflags); + error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags); if (error) - break; + return error; + tmp = vma_iter_end(&vmi); nstart = tmp; - if (nstart < prev->vm_end) - nstart = prev->vm_end; - if (nstart >= end) - break; - - vma = prev->vm_next; - if (!vma || vma->vm_start != nstart) { - error = -ENOMEM; - break; - } } - return error; + + if (tmp < end) + return -ENOMEM; + + return 0; } /* @@ -636,29 +568,26 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, * is also counted. * Return value: previously mlocked page counts */ -static int count_mm_mlocked_page_nr(struct mm_struct *mm, +static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, unsigned long start, size_t len) { struct vm_area_struct *vma; - int count = 0; - - if (mm == NULL) - mm = current->mm; + unsigned long count = 0; + unsigned long end; + VMA_ITERATOR(vmi, mm, start); - vma = find_vma(mm, start); - if (vma == NULL) - vma = mm->mmap; + /* Don't overflow past ULONG_MAX */ + if (unlikely(ULONG_MAX - len < start)) + end = ULONG_MAX; + else + end = start + len; - for (; vma ; vma = vma->vm_next) { - if (start >= vma->vm_end) - continue; - if (start + len <= vma->vm_start) - break; + for_each_vma_range(vmi, vma, end) { if (vma->vm_flags & VM_LOCKED) { if (start > vma->vm_start) count -= (start - vma->vm_start); - if (start + len < vma->vm_end) { - count += start + len - vma->vm_start; + if (end < vma->vm_end) { + count += end - vma->vm_start; break; } count += vma->vm_end - vma->vm_start; @@ -668,12 +597,26 @@ static int count_mm_mlocked_page_nr(struct mm_struct *mm, return count >> PAGE_SHIFT; } +/* + * convert get_user_pages() return value to posix mlock() error + */ +static int __mlock_posix_error_return(long retval) +{ + if (retval == -EFAULT) + retval = -ENOMEM; + else if (retval == -ENOMEM) + retval = -EAGAIN; + return retval; +} + static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; int error = -ENOMEM; + start = untagged_addr(start); + if (!can_do_mlock()) return -EPERM; @@ -684,7 +627,7 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; - if (down_write_killable(¤t->mm->mmap_sem)) + if (mmap_write_lock_killable(current->mm)) return -EINTR; locked += current->mm->locked_vm; @@ -703,7 +646,7 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = apply_vma_lock_flags(start, len, flags); - up_write(¤t->mm->mmap_sem); + mmap_write_unlock(current->mm); if (error) return error; @@ -735,13 +678,15 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; + start = untagged_addr(start); + len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; - if (down_write_killable(¤t->mm->mmap_sem)) + if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_vma_lock_flags(start, len, 0); - up_write(¤t->mm->mmap_sem); + mmap_write_unlock(current->mm); return ret; } @@ -758,10 +703,11 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) */ static int apply_mlockall_flags(int flags) { - struct vm_area_struct * vma, * prev = NULL; + VMA_ITERATOR(vmi, current->mm, 0); + struct vm_area_struct *vma, *prev = NULL; vm_flags_t to_add = 0; - current->mm->def_flags &= VM_LOCKED_CLEAR_MASK; + current->mm->def_flags &= ~VM_LOCKED_MASK; if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; @@ -778,14 +724,18 @@ static int apply_mlockall_flags(int flags) to_add |= VM_LOCKONFAULT; } - for (vma = current->mm->mmap; vma ; vma = prev->vm_next) { + for_each_vma(vmi, vma) { + int error; vm_flags_t newflags; - newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; + newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; - /* Ignore errors */ - mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); + error = mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, + newflags); + /* Ignore errors, but prev needs fixing up. */ + if (error) + prev = vma; cond_resched(); } out: @@ -797,7 +747,8 @@ SYSCALL_DEFINE1(mlockall, int, flags) unsigned long lock_limit; int ret; - if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT))) + if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) || + flags == MCL_ONFAULT) return -EINVAL; if (!can_do_mlock()) @@ -806,14 +757,14 @@ SYSCALL_DEFINE1(mlockall, int, flags) lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; - if (down_write_killable(¤t->mm->mmap_sem)) + if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); - up_write(¤t->mm->mmap_sem); + mmap_write_unlock(current->mm); if (!ret && (flags & MCL_CURRENT)) mm_populate(0, TASK_SIZE); @@ -824,10 +775,10 @@ SYSCALL_DEFINE0(munlockall) { int ret; - if (down_write_killable(¤t->mm->mmap_sem)) + if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_mlockall_flags(0); - up_write(¤t->mm->mmap_sem); + mmap_write_unlock(current->mm); return ret; } @@ -837,32 +788,38 @@ SYSCALL_DEFINE0(munlockall) */ static DEFINE_SPINLOCK(shmlock_user_lock); -int user_shm_lock(size_t size, struct user_struct *user) +int user_shm_lock(size_t size, struct ucounts *ucounts) { unsigned long lock_limit, locked; + long memlock; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; lock_limit = rlimit(RLIMIT_MEMLOCK); - if (lock_limit == RLIM_INFINITY) - allowed = 1; - lock_limit >>= PAGE_SHIFT; + if (lock_limit != RLIM_INFINITY) + lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); - if (!allowed && - locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK)) + memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); + + if ((memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) { + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); goto out; - get_uid(user); - user->locked_shm += locked; + } + if (!get_ucounts(ucounts)) { + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); + allowed = 0; + goto out; + } allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; } -void user_shm_unlock(size_t size, struct user_struct *user) +void user_shm_unlock(size_t size, struct ucounts *ucounts) { spin_lock(&shmlock_user_lock); - user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT); spin_unlock(&shmlock_user_lock); - free_uid(user); + put_ucounts(ucounts); } |