diff options
author | Kirill A. Shutemov <kirill.shutemov@linux.intel.com> | 2016-07-27 00:26:18 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-07-27 01:19:19 +0200 |
commit | 800d8c63b2e989c2e349632d1648119bf5862f01 (patch) | |
tree | 8f72ce10bcdc01f17a5e8f2197ae4858fbab6bd4 /mm/shmem.c | |
parent | shmem: get_unmapped_area align huge page (diff) | |
download | linux-800d8c63b2e989c2e349632d1648119bf5862f01.tar.xz linux-800d8c63b2e989c2e349632d1648119bf5862f01.zip |
shmem: add huge pages support
Here's basic implementation of huge pages support for shmem/tmpfs.
It's all pretty streight-forward:
- shmem_getpage() allcoates huge page if it can and try to inserd into
radix tree with shmem_add_to_page_cache();
- shmem_add_to_page_cache() puts the page onto radix-tree if there's
space for it;
- shmem_undo_range() removes huge pages, if it fully within range.
Partial truncate of huge pages zero out this part of THP.
This have visible effect on fallocate(FALLOC_FL_PUNCH_HOLE)
behaviour. As we don't really create hole in this case,
lseek(SEEK_HOLE) may have inconsistent results depending what
pages happened to be allocated.
- no need to change shmem_fault: core-mm will map an compound page as
huge if VMA is suitable;
Link: http://lkml.kernel.org/r/1466021202-61880-30-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/shmem.c')
-rw-r--r-- | mm/shmem.c | 380 |
1 files changed, 313 insertions, 67 deletions
diff --git a/mm/shmem.c b/mm/shmem.c index ab02b5bb5553..302ae4a0af3d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -173,10 +173,13 @@ static inline int shmem_reacct_size(unsigned long flags, * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ -static inline int shmem_acct_block(unsigned long flags) +static inline int shmem_acct_block(unsigned long flags, long pages) { - return (flags & VM_NORESERVE) ? - security_vm_enough_memory_mm(current->mm, VM_ACCT(PAGE_SIZE)) : 0; + if (!(flags & VM_NORESERVE)) + return 0; + + return security_vm_enough_memory_mm(current->mm, + pages * VM_ACCT(PAGE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) @@ -249,6 +252,51 @@ static void shmem_recalc_inode(struct inode *inode) } } +bool shmem_charge(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + + if (shmem_acct_block(info->flags, pages)) + return false; + spin_lock(&info->lock); + info->alloced += pages; + inode->i_blocks += pages * BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + inode->i_mapping->nrpages += pages; + + if (!sbinfo->max_blocks) + return true; + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks - pages) > 0) { + inode->i_mapping->nrpages -= pages; + spin_lock(&info->lock); + info->alloced -= pages; + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + + return false; + } + percpu_counter_add(&sbinfo->used_blocks, pages); + return true; +} + +void shmem_uncharge(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + + spin_lock(&info->lock); + info->alloced -= pages; + inode->i_blocks -= pages * BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + + if (sbinfo->max_blocks) + percpu_counter_sub(&sbinfo->used_blocks, pages); +} + /* * Replace item expected in radix tree by a new item, while holding tree lock. */ @@ -376,30 +424,57 @@ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t index, void *expected) { - int error; + int error, nr = hpage_nr_pages(page); + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(index != round_down(index, nr), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + VM_BUG_ON(expected && PageTransHuge(page)); - get_page(page); + page_ref_add(page, nr); page->mapping = mapping; page->index = index; spin_lock_irq(&mapping->tree_lock); - if (!expected) + if (PageTransHuge(page)) { + void __rcu **results; + pgoff_t idx; + int i; + + error = 0; + if (radix_tree_gang_lookup_slot(&mapping->page_tree, + &results, &idx, index, 1) && + idx < index + HPAGE_PMD_NR) { + error = -EEXIST; + } + + if (!error) { + for (i = 0; i < HPAGE_PMD_NR; i++) { + error = radix_tree_insert(&mapping->page_tree, + index + i, page + i); + VM_BUG_ON(error); + } + count_vm_event(THP_FILE_ALLOC); + } + } else if (!expected) { error = radix_tree_insert(&mapping->page_tree, index, page); - else + } else { error = shmem_radix_tree_replace(mapping, index, expected, page); + } + if (!error) { - mapping->nrpages++; - __inc_zone_page_state(page, NR_FILE_PAGES); - __inc_zone_page_state(page, NR_SHMEM); + mapping->nrpages += nr; + if (PageTransHuge(page)) + __inc_zone_page_state(page, NR_SHMEM_THPS); + __mod_zone_page_state(page_zone(page), NR_FILE_PAGES, nr); + __mod_zone_page_state(page_zone(page), NR_SHMEM, nr); spin_unlock_irq(&mapping->tree_lock); } else { page->mapping = NULL; spin_unlock_irq(&mapping->tree_lock); - put_page(page); + page_ref_sub(page, nr); } return error; } @@ -412,6 +487,8 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) struct address_space *mapping = page->mapping; int error; + VM_BUG_ON_PAGE(PageCompound(page), page); + spin_lock_irq(&mapping->tree_lock); error = shmem_radix_tree_replace(mapping, page->index, page, radswap); page->mapping = NULL; @@ -591,10 +668,33 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, continue; } + VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page); + if (!trylock_page(page)) continue; + + if (PageTransTail(page)) { + /* Middle of THP: zero out the page */ + clear_highpage(page); + unlock_page(page); + continue; + } else if (PageTransHuge(page)) { + if (index == round_down(end, HPAGE_PMD_NR)) { + /* + * Range ends in the middle of THP: + * zero out the page + */ + clear_highpage(page); + unlock_page(page); + continue; + } + index += HPAGE_PMD_NR - 1; + i += HPAGE_PMD_NR - 1; + } + if (!unfalloc || !PageUptodate(page)) { - if (page->mapping == mapping) { + VM_BUG_ON_PAGE(PageTail(page), page); + if (page_mapping(page) == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } @@ -670,8 +770,36 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } lock_page(page); + + if (PageTransTail(page)) { + /* Middle of THP: zero out the page */ + clear_highpage(page); + unlock_page(page); + /* + * Partial thp truncate due 'start' in middle + * of THP: don't need to look on these pages + * again on !pvec.nr restart. + */ + if (index != round_down(end, HPAGE_PMD_NR)) + start++; + continue; + } else if (PageTransHuge(page)) { + if (index == round_down(end, HPAGE_PMD_NR)) { + /* + * Range ends in the middle of THP: + * zero out the page + */ + clear_highpage(page); + unlock_page(page); + continue; + } + index += HPAGE_PMD_NR - 1; + i += HPAGE_PMD_NR - 1; + } + if (!unfalloc || !PageUptodate(page)) { - if (page->mapping == mapping) { + VM_BUG_ON_PAGE(PageTail(page), page); + if (page_mapping(page) == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } else { @@ -929,6 +1057,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) swp_entry_t swap; pgoff_t index; + VM_BUG_ON_PAGE(PageCompound(page), page); BUG_ON(!PageLocked(page)); mapping = page->mapping; index = page->index; @@ -1065,24 +1194,63 @@ static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) #define vm_policy vm_private_data #endif +static void shmem_pseudo_vma_init(struct vm_area_struct *vma, + struct shmem_inode_info *info, pgoff_t index) +{ + /* Create a pseudo vma that just contains the policy */ + vma->vm_start = 0; + /* Bias interleave by inode number to distribute better across nodes */ + vma->vm_pgoff = index + info->vfs_inode.i_ino; + vma->vm_ops = NULL; + vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); +} + +static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) +{ + /* Drop reference taken by mpol_shared_policy_lookup() */ + mpol_cond_put(vma->vm_policy); +} + static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; - /* Create a pseudo vma that just contains the policy */ - pvma.vm_start = 0; - /* Bias interleave by inode number to distribute better across nodes */ - pvma.vm_pgoff = index + info->vfs_inode.i_ino; - pvma.vm_ops = NULL; - pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); - + shmem_pseudo_vma_init(&pvma, info, index); page = swapin_readahead(swap, gfp, &pvma, 0); + shmem_pseudo_vma_destroy(&pvma); - /* Drop reference taken by mpol_shared_policy_lookup() */ - mpol_cond_put(pvma.vm_policy); + return page; +} + +static struct page *shmem_alloc_hugepage(gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + struct vm_area_struct pvma; + struct inode *inode = &info->vfs_inode; + struct address_space *mapping = inode->i_mapping; + pgoff_t idx, hindex = round_down(index, HPAGE_PMD_NR); + void __rcu **results; + struct page *page; + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return NULL; + + rcu_read_lock(); + if (radix_tree_gang_lookup_slot(&mapping->page_tree, &results, &idx, + hindex, 1) && idx < hindex + HPAGE_PMD_NR) { + rcu_read_unlock(); + return NULL; + } + rcu_read_unlock(); + + shmem_pseudo_vma_init(&pvma, info, hindex); + page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + shmem_pseudo_vma_destroy(&pvma); + if (page) + prep_transhuge_page(page); return page; } @@ -1092,23 +1260,51 @@ static struct page *shmem_alloc_page(gfp_t gfp, struct vm_area_struct pvma; struct page *page; - /* Create a pseudo vma that just contains the policy */ - pvma.vm_start = 0; - /* Bias interleave by inode number to distribute better across nodes */ - pvma.vm_pgoff = index + info->vfs_inode.i_ino; - pvma.vm_ops = NULL; - pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); + shmem_pseudo_vma_init(&pvma, info, index); + page = alloc_page_vma(gfp, &pvma, 0); + shmem_pseudo_vma_destroy(&pvma); + + return page; +} + +static struct page *shmem_alloc_and_acct_page(gfp_t gfp, + struct shmem_inode_info *info, struct shmem_sb_info *sbinfo, + pgoff_t index, bool huge) +{ + struct page *page; + int nr; + int err = -ENOSPC; + + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + huge = false; + nr = huge ? HPAGE_PMD_NR : 1; + + if (shmem_acct_block(info->flags, nr)) + goto failed; + if (sbinfo->max_blocks) { + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks - nr) > 0) + goto unacct; + percpu_counter_add(&sbinfo->used_blocks, nr); + } - page = alloc_pages_vma(gfp, 0, &pvma, 0, numa_node_id(), false); + if (huge) + page = shmem_alloc_hugepage(gfp, info, index); + else + page = shmem_alloc_page(gfp, info, index); if (page) { __SetPageLocked(page); __SetPageSwapBacked(page); + return page; } - /* Drop reference taken by mpol_shared_policy_lookup() */ - mpol_cond_put(pvma.vm_policy); - - return page; + err = -ENOMEM; + if (sbinfo->max_blocks) + percpu_counter_add(&sbinfo->used_blocks, -nr); +unacct: + shmem_unacct_blocks(info->flags, nr); +failed: + return ERR_PTR(err); } /* @@ -1213,6 +1409,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct mem_cgroup *memcg; struct page *page; swp_entry_t swap; + pgoff_t hindex = index; int error; int once = 0; int alloced = 0; @@ -1334,47 +1531,74 @@ repeat: swap_free(swap); } else { - if (shmem_acct_block(info->flags)) { - error = -ENOSPC; - goto failed; - } - if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks) >= 0) { - error = -ENOSPC; - goto unacct; - } - percpu_counter_inc(&sbinfo->used_blocks); + /* shmem_symlink() */ + if (mapping->a_ops != &shmem_aops) + goto alloc_nohuge; + if (shmem_huge == SHMEM_HUGE_DENY) + goto alloc_nohuge; + if (shmem_huge == SHMEM_HUGE_FORCE) + goto alloc_huge; + switch (sbinfo->huge) { + loff_t i_size; + pgoff_t off; + case SHMEM_HUGE_NEVER: + goto alloc_nohuge; + case SHMEM_HUGE_WITHIN_SIZE: + off = round_up(index, HPAGE_PMD_NR); + i_size = round_up(i_size_read(inode), PAGE_SIZE); + if (i_size >= HPAGE_PMD_SIZE && + i_size >> PAGE_SHIFT >= off) + goto alloc_huge; + /* fallthrough */ + case SHMEM_HUGE_ADVISE: + /* TODO: wire up fadvise()/madvise() */ + goto alloc_nohuge; } - page = shmem_alloc_page(gfp, info, index); - if (!page) { - error = -ENOMEM; - goto decused; +alloc_huge: + page = shmem_alloc_and_acct_page(gfp, info, sbinfo, + index, true); + if (IS_ERR(page)) { +alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, info, sbinfo, + index, false); + } + if (IS_ERR(page)) { + error = PTR_ERR(page); + page = NULL; + goto failed; } + + if (PageTransHuge(page)) + hindex = round_down(index, HPAGE_PMD_NR); + else + hindex = index; + if (sgp == SGP_WRITE) __SetPageReferenced(page); error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg, - false); + PageTransHuge(page)); if (error) - goto decused; - error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); + goto unacct; + error = radix_tree_maybe_preload_order(gfp & GFP_RECLAIM_MASK, + compound_order(page)); if (!error) { - error = shmem_add_to_page_cache(page, mapping, index, + error = shmem_add_to_page_cache(page, mapping, hindex, NULL); radix_tree_preload_end(); } if (error) { - mem_cgroup_cancel_charge(page, memcg, false); - goto decused; + mem_cgroup_cancel_charge(page, memcg, + PageTransHuge(page)); + goto unacct; } - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false, + PageTransHuge(page)); lru_cache_add_anon(page); spin_lock(&info->lock); - info->alloced++; - inode->i_blocks += BLOCKS_PER_PAGE; + info->alloced += 1 << compound_order(page); + inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page); shmem_recalc_inode(inode); spin_unlock(&info->lock); alloced = true; @@ -1390,10 +1614,15 @@ clear: * but SGP_FALLOC on a page fallocated earlier must initialize * it now, lest undo on failure cancel our earlier guarantee. */ - if (sgp != SGP_WRITE) { - clear_highpage(page); - flush_dcache_page(page); - SetPageUptodate(page); + if (sgp != SGP_WRITE && !PageUptodate(page)) { + struct page *head = compound_head(page); + int i; + + for (i = 0; i < (1 << compound_order(head)); i++) { + clear_highpage(head + i); + flush_dcache_page(head + i); + } + SetPageUptodate(head); } } @@ -1410,17 +1639,23 @@ clear: error = -EINVAL; goto unlock; } - *pagep = page; + *pagep = page + index - hindex; return 0; /* * Error recovery. */ -decused: - if (sbinfo->max_blocks) - percpu_counter_add(&sbinfo->used_blocks, -1); unacct: - shmem_unacct_blocks(info->flags, 1); + if (sbinfo->max_blocks) + percpu_counter_sub(&sbinfo->used_blocks, + 1 << compound_order(page)); + shmem_unacct_blocks(info->flags, 1 << compound_order(page)); + + if (PageTransHuge(page)) { + unlock_page(page); + put_page(page); + goto alloc_nohuge; + } failed: if (swap.val && !shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; @@ -1758,12 +1993,23 @@ shmem_write_end(struct file *file, struct address_space *mapping, i_size_write(inode, pos + copied); if (!PageUptodate(page)) { + struct page *head = compound_head(page); + if (PageTransCompound(page)) { + int i; + + for (i = 0; i < HPAGE_PMD_NR; i++) { + if (head + i == page) + continue; + clear_highpage(head + i); + flush_dcache_page(head + i); + } + } if (copied < PAGE_SIZE) { unsigned from = pos & (PAGE_SIZE - 1); zero_user_segments(page, 0, from, from + copied, PAGE_SIZE); } - SetPageUptodate(page); + SetPageUptodate(head); } set_page_dirty(page); unlock_page(page); |