/** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags * @vma: user vma this address belongs to * @addr: target address for mempolicy * * Returns the struct page for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen * because it doesn't cost us any seek time. We also make sure to queue * the 'original' request together with the readahead ones... * * This has been extended to use the NUMA policies from the mm triggering * the readahead. * * Caller must hold down_read on the vma->vm_mm if vma is not NULL. */ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { struct page *page; unsigned long offset = swp_offset(entry); unsigned long start_offset, end_offset; unsigned long mask = is_swap_fast(entry) ? 0 : (1UL << page_cluster) - 1; /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; end_offset = offset | mask; if (!start_offset) /* First page is swap header. */ start_offset++; for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = read_swap_cache_async(swp_entry(swp_type(entry), offset), gfp_mask, vma, addr); if (!page) continue; page_cache_release(page); } lru_add_drain(); /* Push any new pages onto the LRU now */ return read_swap_cache_async(entry, gfp_mask, vma, addr); }
/** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags * @vma: user vma this address belongs to * @addr: target address for mempolicy * * Returns the struct page for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen * because it doesn't cost us any seek time. We also make sure to queue * the 'original' request together with the readahead ones... * * This has been extended to use the NUMA policies from the mm triggering * the readahead. * * Caller must hold down_read on the vma->vm_mm if vma is not NULL. */ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { int nr_pages; struct page *page; unsigned long offset; unsigned long end_offset; /* * Get starting offset for readaround, and number of pages to read. * Adjust starting address by readbehind (for NUMA interleave case)? * No, it's very unlikely that swap layout would follow vma layout, * more likely that neighbouring swap pages came from the same node: * so use the same "addr" to choose the same node for each swap read. */ nr_pages = valid_swaphandles(entry, &offset); for (end_offset = offset + nr_pages; offset < end_offset; offset++) { /* Ok, do the async read-ahead now */ page = read_swap_cache_async(swp_entry(swp_type(entry), offset), gfp_mask, vma, addr); if (!page) break; page_cache_release(page); } lru_add_drain(); /* Push any new pages onto the LRU now */ return read_swap_cache_async(entry, gfp_mask, vma, addr); }
struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { struct page *page; unsigned long offset = swp_offset(entry); unsigned long start_offset, end_offset; unsigned long mask = (1UL << page_cluster) - 1; start_offset = offset & ~mask; end_offset = offset | mask; if (!start_offset) start_offset++; for (offset = start_offset; offset <= end_offset ; offset++) { page = read_swap_cache_async(swp_entry(swp_type(entry), offset), gfp_mask, vma, addr); if (!page) continue; page_cache_release(page); } lru_add_drain(); return read_swap_cache_async(entry, gfp_mask, vma, addr); }
/** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags * @vma: user vma this address belongs to * @addr: target address for mempolicy * * Returns the struct page for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen * because it doesn't cost us any seek time. We also make sure to queue * the 'original' request together with the readahead ones... * * This has been extended to use the NUMA policies from the mm triggering * the readahead. * * Caller must hold down_read on the vma->vm_mm if vma is not NULL. */ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { #ifdef CONFIG_SWAP_ENABLE_READAHEAD struct page *page; unsigned long offset = swp_offset(entry); unsigned long start_offset, end_offset; unsigned long mask = (1UL << page_cluster) - 1; struct blk_plug plug; /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; end_offset = offset | mask; if (!start_offset) /* First page is swap header. */ start_offset++; blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = read_swap_cache_async(swp_entry(swp_type(entry), offset), gfp_mask, vma, addr); if (!page) continue; page_cache_release(page); } blk_finish_plug(&plug); lru_add_drain(); /* Push any new pages onto the LRU now */ #endif /* CONFIG_SWAP_ENABLE_READAHEAD */ return read_swap_cache_async(entry, gfp_mask, vma, addr); }
/* * The pages which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those pages may be * cache-warm and we want to give them back to the page allocator as soon as possible * * So __pagevec_release() will drain those queues here. __pagevec_lru_add() * and __pagevec_lru_add_active() call release_pages() directly to avoid * mutual recursion. */ void __pagevec_release(struct pagevec *pvec) { lru_add_drain(); release_pages(pvec->pages, pagevec_count(pvec), pvec->cold); // dyc: set pvec->nr to 0 pagevec_reinit(pvec); }
/* * The pages which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those pages may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __pagevec_release() will drain those queues here. __pagevec_lru_add() * and __pagevec_lru_add_active() call release_pages() directly to avoid * mutual recursion. */ void __pagevec_release(struct pagevec *pvec) { if (!pvec->percpu_pvec_drained) { lru_add_drain(); pvec->percpu_pvec_drained = true; } release_pages(pvec->pages, pagevec_count(pvec)); pagevec_reinit(pvec); }
/* * Passed an array of pages, drop them all from swapcache and then release * them. They are removed from the LRU and freed if this is their last use. */ void free_pages_and_swap_cache(struct page **pages, int nr) { struct page **pagep = pages; int i; lru_add_drain(); for (i = 0; i < nr; i++) free_swap_cache(pagep[i]); release_pages(pagep, nr, false); }
/* * Passed an array of pages, drop them all from swapcache and then release * them. They are removed from the LRU and freed if this is their last use. */ void free_pages_and_swap_cache(struct page **pages, int nr) { struct page **pagep = pages; lru_add_drain(); while (nr) { int todo = min(nr, PAGEVEC_SIZE); int i; for (i = 0; i < todo; i++) free_swap_cache(pagep[i]); release_pages(pagep, todo, 0); pagep += todo; nr -= todo; } }
/** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags * @vma: user vma this address belongs to * @addr: target address for mempolicy * * Returns the struct page for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen * because it doesn't cost us any seek time. We also make sure to queue * the 'original' request together with the readahead ones... * * This has been extended to use the NUMA policies from the mm triggering * the readahead. * * Caller must hold down_read on the vma->vm_mm if vma is not NULL. */ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { struct page *page; unsigned long entry_offset = swp_offset(entry); unsigned long offset = entry_offset; unsigned long start_offset, end_offset; unsigned long mask; struct blk_plug plug; bool do_poll = true; mask = swapin_nr_pages(offset) - 1; if (!mask) goto skip; do_poll = false; /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; end_offset = offset | mask; if (!start_offset) /* First page is swap header. */ start_offset++; blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = read_swap_cache_async(swp_entry(swp_type(entry), offset), gfp_mask, vma, addr, false); if (!page) continue; if (offset != entry_offset && likely(!PageTransCompound(page))) SetPageReadahead(page); put_page(page); } blk_finish_plug(&plug); lru_add_drain(); /* Push any new pages onto the LRU now */ skip: return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll); }
static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); }
/* Do the necessary work of migrate_prep but not if it involves other CPUs */ int migrate_prep_local(void) { lru_add_drain(); return 0; }
/* * Returns 0 for success */ int lru_add_drain_all(void) { lru_add_drain(); return 0; }
static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; struct dev_pagemap *pgmap = NULL; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; retry: if (unlikely(pmd_bad(*pmd))) return no_page_table(vma, flags); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); pte = *ptep; if (!pte_present(pte)) { swp_entry_t entry; /* * KSM's break_ksm() relies upon recognizing a ksm page * even while it is being migrated, so for that case we * need migration_entry_wait(). */ if (likely(!(flags & FOLL_MIGRATION))) goto no_page; if (pte_none(pte)) goto no_page; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry)) goto no_page; pte_unmap_unlock(ptep, ptl); migration_entry_wait(mm, pmd, address); goto retry; } if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { pte_unmap_unlock(ptep, ptl); return NULL; } page = vm_normal_page(vma, address, pte); if (!page && pte_devmap(pte) && (flags & FOLL_GET)) { /* * Only return device mapping pages in the FOLL_GET case since * they are only valid while holding the pgmap reference. */ pgmap = get_dev_pagemap(pte_pfn(pte), NULL); if (pgmap) page = pte_page(pte); else goto no_page; } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); goto out; } if (is_zero_pfn(pte_pfn(pte))) { page = pte_page(pte); } else { int ret; ret = follow_pfn_pte(vma, address, ptep, flags); page = ERR_PTR(ret); goto out; } } if (flags & FOLL_SPLIT && PageTransCompound(page)) { int ret; get_page(page); pte_unmap_unlock(ptep, ptl); lock_page(page); ret = split_huge_page(page); unlock_page(page); put_page(page); if (ret) return ERR_PTR(ret); goto retry; } if (flags & FOLL_GET) { get_page(page); /* drop the pgmap reference now that we hold the page */ if (pgmap) { put_dev_pagemap(pgmap); pgmap = NULL; } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * mark_page_accessed(). */ mark_page_accessed(page); } if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* Do not mlock pte-mapped THP */ if (PageTransCompound(page)) goto out; /* * The preliminary mapping check is mainly to avoid the * pointless overhead of lock_page on the ZERO_PAGE * which might bounce very badly if there is contention. * * If the page is already locked, we don't need to * handle it now - vmscan will handle it later if and * when it attempts to reclaim the page. */ if (page->mapping && trylock_page(page)) { lru_add_drain(); /* push cached pages to LRU */ /* * Because we lock page here, and migration is * blocked by the pte's page reference, and we * know the page is still mapped, we don't even * need to check for file-cache page truncation. */ mlock_vma_page(page); unlock_page(page); } } out: pte_unmap_unlock(ptep, ptl); return page; no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; return no_page_table(vma, flags); }
static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; retry: if (unlikely(pmd_bad(*pmd))) return no_page_table(vma, flags); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); pte = *ptep; if (!pte_present(pte)) { swp_entry_t entry; /* * KSM's break_ksm() relies upon recognizing a ksm page * even while it is being migrated, so for that case we * need migration_entry_wait(). */ if (likely(!(flags & FOLL_MIGRATION))) goto no_page; if (pte_none(pte) || pte_file(pte)) goto no_page; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry)) goto no_page; pte_unmap_unlock(ptep, ptl); migration_entry_wait(mm, pmd, address); goto retry; } if ((flags & FOLL_NUMA) && pte_numa(pte)) goto no_page; if ((flags & FOLL_WRITE) && !pte_write(pte)) { pte_unmap_unlock(ptep, ptl); return NULL; } page = vm_normal_page(vma, address, pte); if (unlikely(!page)) { if ((flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(pte))) goto bad_page; page = pte_page(pte); } if (flags & FOLL_GET) get_page_foll(page); if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * mark_page_accessed(). */ mark_page_accessed(page); } if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* * The preliminary mapping check is mainly to avoid the * pointless overhead of lock_page on the ZERO_PAGE * which might bounce very badly if there is contention. * * If the page is already locked, we don't need to * handle it now - vmscan will handle it later if and * when it attempts to reclaim the page. */ if (page->mapping && trylock_page(page)) { lru_add_drain(); /* push cached pages to LRU */ /* * Because we lock page here, and migration is * blocked by the pte's page reference, and we * know the page is still mapped, we don't even * need to check for file-cache page truncation. */ mlock_vma_page(page); unlock_page(page); } } pte_unmap_unlock(ptep, ptl); return page; bad_page: pte_unmap_unlock(ptep, ptl); return ERR_PTR(-EFAULT); no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; return no_page_table(vma, flags); }
static void lru_add_drain_per_cpu(void *dummy) { lru_add_drain(); }