From 3f4a2670deea53e3765e24a7f46aafe6f077cb68 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 22 Jan 2016 15:10:37 -0800 Subject: pmem: add wb_cache_pmem() to the PMEM API __arch_wb_cache_pmem() was already an internal implementation detail of the x86 PMEM API, but this functionality needs to be exported as part of the general PMEM API to handle the fsync/msync case for DAX mmaps. One thing worth noting is that we really do want this to be part of the PMEM API as opposed to a stand-alone function like clflush_cache_range() because of ordering restrictions. By having wb_cache_pmem() as part of the PMEM API we can leave it unordered, call it multiple times to write back large amounts of memory, and then order the multiple calls with a single wmb_pmem(). Signed-off-by: Ross Zwisler Cc: "H. Peter Anvin" Cc: "J. Bruce Fields" Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Dave Chinner Cc: Ingo Molnar Cc: Jan Kara Cc: Jeff Layton Cc: Matthew Wilcox Cc: Thomas Gleixner Cc: Dan Williams Cc: Matthew Wilcox Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pmem.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pmem.h b/include/linux/pmem.h index acfea8ce4a07..7c3d11a6b4ad 100644 --- a/include/linux/pmem.h +++ b/include/linux/pmem.h @@ -53,12 +53,18 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size) { BUG(); } + +static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size) +{ + BUG(); +} #endif /* * Architectures that define ARCH_HAS_PMEM_API must provide * implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(), - * arch_copy_from_iter_pmem(), arch_clear_pmem() and arch_has_wmb_pmem(). + * arch_copy_from_iter_pmem(), arch_clear_pmem(), arch_wb_cache_pmem() + * and arch_has_wmb_pmem(). */ static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size) { @@ -178,4 +184,18 @@ static inline void clear_pmem(void __pmem *addr, size_t size) else default_clear_pmem(addr, size); } + +/** + * wb_cache_pmem - write back processor cache for PMEM memory range + * @addr: virtual start address + * @size: number of bytes to write back + * + * Write back the processor cache range starting at 'addr' for 'size' bytes. + * This function requires explicit ordering with a wmb_pmem() call. + */ +static inline void wb_cache_pmem(void __pmem *addr, size_t size) +{ + if (arch_has_pmem_api()) + arch_wb_cache_pmem(addr, size); +} #endif /* __PMEM_H__ */ -- cgit v1.2.3 From f9fe48bece3af2d60e1bad65db4825f5a025dd36 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 22 Jan 2016 15:10:40 -0800 Subject: dax: support dirty DAX entries in radix tree Add support for tracking dirty DAX entries in the struct address_space radix tree. This tree is already used for dirty page writeback, and it already supports the use of exceptional (non struct page*) entries. In order to properly track dirty DAX pages we will insert new exceptional entries into the radix tree that represent dirty DAX PTE or PMD pages. These exceptional entries will also contain the writeback addresses for the PTE or PMD faults that we can use at fsync/msync time. There are currently two types of exceptional entries (shmem and shadow) that can be placed into the radix tree, and this adds a third. We rely on the fact that only one type of exceptional entry can be found in a given radix tree based on its usage. This happens for free with DAX vs shmem but we explicitly prevent shadow entries from being added to radix trees for DAX mappings. The only shadow entries that would be generated for DAX radix trees would be to track zero page mappings that were created for holes. These pages would receive minimal benefit from having shadow entries, and the choice to have only one type of exceptional entry in a given radix tree makes the logic simpler both in clear_exceptional_entry() and in the rest of DAX. Signed-off-by: Ross Zwisler Cc: "H. Peter Anvin" Cc: "J. Bruce Fields" Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Dave Chinner Cc: Ingo Molnar Cc: Jan Kara Cc: Jeff Layton Cc: Matthew Wilcox Cc: Thomas Gleixner Cc: Dan Williams Cc: Matthew Wilcox Cc: Dave Hansen Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 2 +- fs/inode.c | 2 +- include/linux/dax.h | 5 ++++ include/linux/fs.h | 3 +- include/linux/radix-tree.h | 9 ++++++ mm/filemap.c | 17 ++++++++---- mm/truncate.c | 69 ++++++++++++++++++++++++++-------------------- mm/vmscan.c | 9 +++++- mm/workingset.c | 4 +-- 9 files changed, 78 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/fs/block_dev.c b/fs/block_dev.c index ba762ea07f67..60895e500e15 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -75,7 +75,7 @@ void kill_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_inode->i_mapping; - if (mapping->nrpages == 0 && mapping->nrshadows == 0) + if (mapping->nrpages == 0 && mapping->nrexceptional == 0) return; invalidate_bh_lrus(); diff --git a/fs/inode.c b/fs/inode.c index e491e54d2430..1e6dd388ba7f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -495,7 +495,7 @@ void clear_inode(struct inode *inode) */ spin_lock_irq(&inode->i_data.tree_lock); BUG_ON(inode->i_data.nrpages); - BUG_ON(inode->i_data.nrshadows); + BUG_ON(inode->i_data.nrexceptional); spin_unlock_irq(&inode->i_data.tree_lock); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); diff --git a/include/linux/dax.h b/include/linux/dax.h index b415e521528d..e9d57f680f50 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -36,4 +36,9 @@ static inline bool vma_is_dax(struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } + +static inline bool dax_mapping(struct address_space *mapping) +{ + return mapping->host && IS_DAX(mapping->host); +} #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index eb73d74ed992..0d7570320d63 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -433,7 +433,8 @@ struct address_space { struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ - unsigned long nrshadows; /* number of shadow entries */ + /* number of shadow or DAX exceptional entries */ + unsigned long nrexceptional; pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ unsigned long flags; /* error bits/gfp mask */ diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 57e7d87d2d4c..7c88ad156a29 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -51,6 +51,15 @@ #define RADIX_TREE_EXCEPTIONAL_ENTRY 2 #define RADIX_TREE_EXCEPTIONAL_SHIFT 2 +#define RADIX_DAX_MASK 0xf +#define RADIX_DAX_SHIFT 4 +#define RADIX_DAX_PTE (0x4 | RADIX_TREE_EXCEPTIONAL_ENTRY) +#define RADIX_DAX_PMD (0x8 | RADIX_TREE_EXCEPTIONAL_ENTRY) +#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_MASK) +#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT)) +#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \ + RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE))) + static inline int radix_tree_is_indirect_ptr(void *ptr) { return (int)((unsigned long)ptr & RADIX_TREE_INDIRECT_PTR); diff --git a/mm/filemap.c b/mm/filemap.c index 847ee43c2806..7b8be78cfd9e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -11,6 +11,7 @@ */ #include #include +#include #include #include #include @@ -123,9 +124,9 @@ static void page_cache_tree_delete(struct address_space *mapping, __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); if (shadow) { - mapping->nrshadows++; + mapping->nrexceptional++; /* - * Make sure the nrshadows update is committed before + * Make sure the nrexceptional update is committed before * the nrpages update so that final truncate racing * with reclaim does not see both counters 0 at the * same time and miss a shadow entry. @@ -579,9 +580,13 @@ static int page_cache_tree_insert(struct address_space *mapping, p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); if (!radix_tree_exceptional_entry(p)) return -EEXIST; + + if (WARN_ON(dax_mapping(mapping))) + return -EINVAL; + if (shadowp) *shadowp = p; - mapping->nrshadows--; + mapping->nrexceptional--; if (node) workingset_node_shadows_dec(node); } @@ -1245,9 +1250,9 @@ repeat: if (radix_tree_deref_retry(page)) goto restart; /* - * A shadow entry of a recently evicted page, - * or a swap entry from shmem/tmpfs. Return - * it without attempting to raise page count. + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. */ goto export; } diff --git a/mm/truncate.c b/mm/truncate.c index 76e35ad97102..e3ee0e27cd17 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -34,31 +35,39 @@ static void clear_exceptional_entry(struct address_space *mapping, return; spin_lock_irq(&mapping->tree_lock); - /* - * Regular page slots are stabilized by the page lock even - * without the tree itself locked. These unlocked entries - * need verification under the tree lock. - */ - if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot)) - goto unlock; - if (*slot != entry) - goto unlock; - radix_tree_replace_slot(slot, NULL); - mapping->nrshadows--; - if (!node) - goto unlock; - workingset_node_shadows_dec(node); - /* - * Don't track node without shadow entries. - * - * Avoid acquiring the list_lru lock if already untracked. - * The list_empty() test is safe as node->private_list is - * protected by mapping->tree_lock. - */ - if (!workingset_node_shadows(node) && - !list_empty(&node->private_list)) - list_lru_del(&workingset_shadow_nodes, &node->private_list); - __radix_tree_delete_node(&mapping->page_tree, node); + + if (dax_mapping(mapping)) { + if (radix_tree_delete_item(&mapping->page_tree, index, entry)) + mapping->nrexceptional--; + } else { + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + if (!__radix_tree_lookup(&mapping->page_tree, index, &node, + &slot)) + goto unlock; + if (*slot != entry) + goto unlock; + radix_tree_replace_slot(slot, NULL); + mapping->nrexceptional--; + if (!node) + goto unlock; + workingset_node_shadows_dec(node); + /* + * Don't track node without shadow entries. + * + * Avoid acquiring the list_lru lock if already untracked. + * The list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && + !list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, + &node->private_list); + __radix_tree_delete_node(&mapping->page_tree, node); + } unlock: spin_unlock_irq(&mapping->tree_lock); } @@ -228,7 +237,7 @@ void truncate_inode_pages_range(struct address_space *mapping, int i; cleancache_invalidate_inode(mapping); - if (mapping->nrpages == 0 && mapping->nrshadows == 0) + if (mapping->nrpages == 0 && mapping->nrexceptional == 0) return; /* Offsets within partial pages */ @@ -402,7 +411,7 @@ EXPORT_SYMBOL(truncate_inode_pages); */ void truncate_inode_pages_final(struct address_space *mapping) { - unsigned long nrshadows; + unsigned long nrexceptional; unsigned long nrpages; /* @@ -416,14 +425,14 @@ void truncate_inode_pages_final(struct address_space *mapping) /* * When reclaim installs eviction entries, it increases - * nrshadows first, then decreases nrpages. Make sure we see + * nrexceptional first, then decreases nrpages. Make sure we see * this in the right order or we might miss an entry. */ nrpages = mapping->nrpages; smp_rmb(); - nrshadows = mapping->nrshadows; + nrexceptional = mapping->nrexceptional; - if (nrpages || nrshadows) { + if (nrpages || nrexceptional) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree diff --git a/mm/vmscan.c b/mm/vmscan.c index bd620b65db52..eb3dd37ccd7c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include @@ -671,9 +672,15 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. + * + * We also don't store shadows for DAX mappings because the + * only page cache pages found in these are zero pages + * covering holes, and because we don't want to mix DAX + * exceptional entries and shadow exceptional entries in the + * same page_tree. */ if (reclaimed && page_is_file_cache(page) && - !mapping_exiting(mapping)) + !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(mapping, page); __delete_from_page_cache(page, shadow, memcg); spin_unlock_irqrestore(&mapping->tree_lock, flags); diff --git a/mm/workingset.c b/mm/workingset.c index aa017133744b..61ead9e5549d 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -351,8 +351,8 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, node->slots[i] = NULL; BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT)); node->count -= 1U << RADIX_TREE_COUNT_SHIFT; - BUG_ON(!mapping->nrshadows); - mapping->nrshadows--; + BUG_ON(!mapping->nrexceptional); + mapping->nrexceptional--; } } BUG_ON(node->count); -- cgit v1.2.3 From 7e7f774984cd88c45c18e7ffaf0256c3e9118043 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 22 Jan 2016 15:10:44 -0800 Subject: mm: add find_get_entries_tag() Add find_get_entries_tag() to the family of functions that include find_get_entries(), find_get_pages() and find_get_pages_tag(). This is needed for DAX dirty page handling because we need a list of both page offsets and radix tree entries ('indices' and 'entries' in this function) that are marked with the PAGECACHE_TAG_TOWRITE tag. Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Cc: "H. Peter Anvin" Cc: "J. Bruce Fields" Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Dave Chinner Cc: Ingo Molnar Cc: Jeff Layton Cc: Matthew Wilcox Cc: Thomas Gleixner Cc: Dan Williams Cc: Matthew Wilcox Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 +++ mm/filemap.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4d08b6c33557..92395a0a7dc5 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -361,6 +361,9 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, int tag, unsigned int nr_pages, struct page **pages); +unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, + int tag, unsigned int nr_entries, + struct page **entries, pgoff_t *indices); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags); diff --git a/mm/filemap.c b/mm/filemap.c index 7b8be78cfd9e..1e215fc36c83 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1499,6 +1499,74 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); +/** + * find_get_entries_tag - find and return entries that match @tag + * @mapping: the address_space to search + * @start: the starting page cache index + * @tag: the tag index + * @nr_entries: the maximum number of entries + * @entries: where the resulting entries are placed + * @indices: the cache indices corresponding to the entries in @entries + * + * Like find_get_entries, except we only return entries which are tagged with + * @tag. + */ +unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, + int tag, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_entries) + return 0; + + rcu_read_lock(); +restart: + radix_tree_for_each_tagged(slot, &mapping->page_tree, + &iter, start, tag) { + struct page *page; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) { + /* + * Transient condition which can only trigger + * when entry at index 0 moves out of or back + * to root: none yet gotten, safe to restart. + */ + goto restart; + } + + /* + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. + */ + goto export; + } + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } +export: + indices[ret] = iter.index; + entries[ret] = page; + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL(find_get_entries_tag); + /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: -- cgit v1.2.3 From 9973c98ecfda3a1dfcab981665b5f1e39bcde64a Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 22 Jan 2016 15:10:47 -0800 Subject: dax: add support for fsync/sync To properly handle fsync/msync in an efficient way DAX needs to track dirty pages so it is able to flush them durably to media on demand. The tracking of dirty pages is done via the radix tree in struct address_space. This radix tree is already used by the page writeback infrastructure for tracking dirty pages associated with an open file, and it already has support for exceptional (non struct page*) entries. We build upon these features to add exceptional entries to the radix tree for DAX dirty PMD or PTE pages at fault time. [dan.j.williams@intel.com: fix dax_pmd_dbg build warning] Signed-off-by: Ross Zwisler Cc: "H. Peter Anvin" Cc: "J. Bruce Fields" Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Dave Chinner Cc: Ingo Molnar Cc: Jan Kara Cc: Jeff Layton Cc: Matthew Wilcox Cc: Thomas Gleixner Cc: Matthew Wilcox Cc: Dave Hansen Signed-off-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dax.c | 274 +++++++++++++++++++++++++++++++++++++++++++++++++--- include/linux/dax.h | 2 + mm/filemap.c | 6 ++ 3 files changed, 266 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/fs/dax.c b/fs/dax.c index 5b84a46201c2..d5f6aca5a4d7 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -324,6 +325,199 @@ static int copy_user_bh(struct page *to, struct inode *inode, return 0; } +#define NO_SECTOR -1 +#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_CACHE_SHIFT)) + +static int dax_radix_entry(struct address_space *mapping, pgoff_t index, + sector_t sector, bool pmd_entry, bool dirty) +{ + struct radix_tree_root *page_tree = &mapping->page_tree; + pgoff_t pmd_index = DAX_PMD_INDEX(index); + int type, error = 0; + void *entry; + + WARN_ON_ONCE(pmd_entry && !dirty); + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + + spin_lock_irq(&mapping->tree_lock); + + entry = radix_tree_lookup(page_tree, pmd_index); + if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) { + index = pmd_index; + goto dirty; + } + + entry = radix_tree_lookup(page_tree, index); + if (entry) { + type = RADIX_DAX_TYPE(entry); + if (WARN_ON_ONCE(type != RADIX_DAX_PTE && + type != RADIX_DAX_PMD)) { + error = -EIO; + goto unlock; + } + + if (!pmd_entry || type == RADIX_DAX_PMD) + goto dirty; + + /* + * We only insert dirty PMD entries into the radix tree. This + * means we don't need to worry about removing a dirty PTE + * entry and inserting a clean PMD entry, thus reducing the + * range we would flush with a follow-up fsync/msync call. + */ + radix_tree_delete(&mapping->page_tree, index); + mapping->nrexceptional--; + } + + if (sector == NO_SECTOR) { + /* + * This can happen during correct operation if our pfn_mkwrite + * fault raced against a hole punch operation. If this + * happens the pte that was hole punched will have been + * unmapped and the radix tree entry will have been removed by + * the time we are called, but the call will still happen. We + * will return all the way up to wp_pfn_shared(), where the + * pte_same() check will fail, eventually causing page fault + * to be retried by the CPU. + */ + goto unlock; + } + + error = radix_tree_insert(page_tree, index, + RADIX_DAX_ENTRY(sector, pmd_entry)); + if (error) + goto unlock; + + mapping->nrexceptional++; + dirty: + if (dirty) + radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY); + unlock: + spin_unlock_irq(&mapping->tree_lock); + return error; +} + +static int dax_writeback_one(struct block_device *bdev, + struct address_space *mapping, pgoff_t index, void *entry) +{ + struct radix_tree_root *page_tree = &mapping->page_tree; + int type = RADIX_DAX_TYPE(entry); + struct radix_tree_node *node; + struct blk_dax_ctl dax; + void **slot; + int ret = 0; + + spin_lock_irq(&mapping->tree_lock); + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + if (!__radix_tree_lookup(page_tree, index, &node, &slot)) + goto unlock; + if (*slot != entry) + goto unlock; + + /* another fsync thread may have already written back this entry */ + if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)) + goto unlock; + + if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) { + ret = -EIO; + goto unlock; + } + + dax.sector = RADIX_DAX_SECTOR(entry); + dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE); + spin_unlock_irq(&mapping->tree_lock); + + /* + * We cannot hold tree_lock while calling dax_map_atomic() because it + * eventually calls cond_resched(). + */ + ret = dax_map_atomic(bdev, &dax); + if (ret < 0) + return ret; + + if (WARN_ON_ONCE(ret < dax.size)) { + ret = -EIO; + goto unmap; + } + + wb_cache_pmem(dax.addr, dax.size); + + spin_lock_irq(&mapping->tree_lock); + radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE); + spin_unlock_irq(&mapping->tree_lock); + unmap: + dax_unmap_atomic(bdev, &dax); + return ret; + + unlock: + spin_unlock_irq(&mapping->tree_lock); + return ret; +} + +/* + * Flush the mapping to the persistent domain within the byte range of [start, + * end]. This is required by data integrity operations to ensure file data is + * on persistent storage prior to completion of the operation. + */ +int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, + loff_t end) +{ + struct inode *inode = mapping->host; + struct block_device *bdev = inode->i_sb->s_bdev; + pgoff_t start_index, end_index, pmd_index; + pgoff_t indices[PAGEVEC_SIZE]; + struct pagevec pvec; + bool done = false; + int i, ret = 0; + void *entry; + + if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT)) + return -EIO; + + start_index = start >> PAGE_CACHE_SHIFT; + end_index = end >> PAGE_CACHE_SHIFT; + pmd_index = DAX_PMD_INDEX(start_index); + + rcu_read_lock(); + entry = radix_tree_lookup(&mapping->page_tree, pmd_index); + rcu_read_unlock(); + + /* see if the start of our range is covered by a PMD entry */ + if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) + start_index = pmd_index; + + tag_pages_for_writeback(mapping, start_index, end_index); + + pagevec_init(&pvec, 0); + while (!done) { + pvec.nr = find_get_entries_tag(mapping, start_index, + PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE, + pvec.pages, indices); + + if (pvec.nr == 0) + break; + + for (i = 0; i < pvec.nr; i++) { + if (indices[i] > end_index) { + done = true; + break; + } + + ret = dax_writeback_one(bdev, mapping, indices[i], + pvec.pages[i]); + if (ret < 0) + return ret; + } + } + wmb_pmem(); + return 0; +} +EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); + static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, struct vm_area_struct *vma, struct vm_fault *vmf) { @@ -363,6 +557,11 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, } dax_unmap_atomic(bdev, &dax); + error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false, + vmf->flags & FAULT_FLAG_WRITE); + if (error) + goto out; + error = vm_insert_mixed(vma, vaddr, dax.pfn); out: @@ -487,6 +686,7 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, delete_from_page_cache(page); unlock_page(page); page_cache_release(page); + page = NULL; } /* @@ -589,9 +789,9 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, bool write = flags & FAULT_FLAG_WRITE; struct block_device *bdev; pgoff_t size, pgoff; - loff_t lstart, lend; sector_t block; - int result = 0; + int error, result = 0; + bool alloc = false; /* dax pmd mappings require pfn_t_devmap() */ if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) @@ -629,10 +829,17 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; - if (get_block(inode, block, &bh, write) != 0) + + if (get_block(inode, block, &bh, 0) != 0) return VM_FAULT_SIGBUS; + + if (!buffer_mapped(&bh) && write) { + if (get_block(inode, block, &bh, 1) != 0) + return VM_FAULT_SIGBUS; + alloc = true; + } + bdev = bh.b_bdev; - i_mmap_lock_read(mapping); /* * If the filesystem isn't willing to tell us the length of a hole, @@ -641,15 +848,20 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, */ if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) { dax_pmd_dbg(&bh, address, "allocated block too small"); - goto fallback; + return VM_FAULT_FALLBACK; + } + + /* + * If we allocated new storage, make sure no process has any + * zero pages covering this hole + */ + if (alloc) { + loff_t lstart = pgoff << PAGE_SHIFT; + loff_t lend = lstart + PMD_SIZE - 1; /* inclusive */ + + truncate_pagecache_range(inode, lstart, lend); } - /* make sure no process has any zero pages covering this hole */ - lstart = pgoff << PAGE_SHIFT; - lend = lstart + PMD_SIZE - 1; /* inclusive */ - i_mmap_unlock_read(mapping); - unmap_mapping_range(mapping, lstart, PMD_SIZE, 0); - truncate_inode_pages_range(mapping, lstart, lend); i_mmap_lock_read(mapping); /* @@ -733,6 +945,31 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, } dax_unmap_atomic(bdev, &dax); + /* + * For PTE faults we insert a radix tree entry for reads, and + * leave it clean. Then on the first write we dirty the radix + * tree entry via the dax_pfn_mkwrite() path. This sequence + * allows the dax_pfn_mkwrite() call to be simpler and avoid a + * call into get_block() to translate the pgoff to a sector in + * order to be able to create a new radix tree entry. + * + * The PMD path doesn't have an equivalent to + * dax_pfn_mkwrite(), though, so for a read followed by a + * write we traverse all the way through __dax_pmd_fault() + * twice. This means we can just skip inserting a radix tree + * entry completely on the initial read and just wait until + * the write to insert a dirty entry. + */ + if (write) { + error = dax_radix_entry(mapping, pgoff, dax.sector, + true, true); + if (error) { + dax_pmd_dbg(&bh, address, + "PMD radix insertion failed"); + goto fallback; + } + } + dev_dbg(part_to_dev(bdev->bd_part), "%s: %s addr: %lx pfn: %lx sect: %llx\n", __func__, current->comm, address, @@ -791,15 +1028,20 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault); * dax_pfn_mkwrite - handle first write to DAX page * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault - * */ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { - struct super_block *sb = file_inode(vma->vm_file)->i_sb; + struct file *file = vma->vm_file; - sb_start_pagefault(sb); - file_update_time(vma->vm_file); - sb_end_pagefault(sb); + /* + * We pass NO_SECTOR to dax_radix_entry() because we expect that a + * RADIX_DAX_PTE entry already exists in the radix tree from a + * previous call to __dax_fault(). We just want to look up that PTE + * entry using vmf->pgoff and make sure the dirty tag is set. This + * saves us from having to make a call to get_block() here to look + * up the sector. + */ + dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false, true); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(dax_pfn_mkwrite); diff --git a/include/linux/dax.h b/include/linux/dax.h index e9d57f680f50..8204c3dc3800 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -41,4 +41,6 @@ static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } +int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, + loff_t end); #endif diff --git a/mm/filemap.c b/mm/filemap.c index 1e215fc36c83..2e7c8d980d5e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -482,6 +482,12 @@ int filemap_write_and_wait_range(struct address_space *mapping, { int err = 0; + if (dax_mapping(mapping) && mapping->nrexceptional) { + err = dax_writeback_mapping_range(mapping, lstart, lend); + if (err) + return err; + } + if (mapping->nrpages) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); -- cgit v1.2.3