diff options
44 files changed, 1259 insertions, 1008 deletions
diff --git a/block/bio.c b/block/bio.c index db85c5753a76..2cf6ebabc68c 100644 --- a/block/bio.c +++ b/block/bio.c @@ -847,6 +847,55 @@ done: } EXPORT_SYMBOL(bio_add_page); +/** + * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * @bio: bio to add pages to + * @iter: iov iterator describing the region to be mapped + * + * Pins as many pages from *iter and appends them to @bio's bvec array. The + * pages will have to be released using put_page() when done. + */ +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +{ + unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; + struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; + struct page **pages = (struct page **)bv; + size_t offset, diff; + ssize_t size; + + size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); + if (unlikely(size <= 0)) + return size ? size : -EFAULT; + nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; + + /* + * Deep magic below: We need to walk the pinned pages backwards + * because we are abusing the space allocated for the bio_vecs + * for the page array. Because the bio_vecs are larger than the + * page pointers by definition this will always work. But it also + * means we can't use bio_add_page, so any changes to it's semantics + * need to be reflected here as well. + */ + bio->bi_iter.bi_size += size; + bio->bi_vcnt += nr_pages; + + diff = (nr_pages * PAGE_SIZE - offset) - size; + while (nr_pages--) { + bv[nr_pages].bv_page = pages[nr_pages]; + bv[nr_pages].bv_len = PAGE_SIZE; + bv[nr_pages].bv_offset = 0; + } + + bv[0].bv_offset += offset; + bv[0].bv_len -= offset; + if (diff) + bv[bio->bi_vcnt - 1].bv_len -= diff; + + iov_iter_advance(iter, size); + return 0; +} +EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); + struct submit_bio_ret { struct completion event; int error; diff --git a/fs/Kconfig b/fs/Kconfig index 4bd03a2b0518..8e9e5f4104f4 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -55,7 +55,6 @@ config FS_DAX_PMD depends on FS_DAX depends on ZONE_DEVICE depends on TRANSPARENT_HUGEPAGE - depends on BROKEN endif # BLOCK @@ -34,25 +34,11 @@ #include <linux/iomap.h> #include "internal.h" -/* - * We use lowest available bit in exceptional entry for locking, other two - * bits to determine entry type. In total 3 special bits. - */ -#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 3) -#define RADIX_DAX_PTE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) -#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) -#define RADIX_DAX_TYPE_MASK (RADIX_DAX_PTE | RADIX_DAX_PMD) -#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_TYPE_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) | \ - RADIX_TREE_EXCEPTIONAL_ENTRY)) - /* We choose 4096 entries - same as per-zone page wait tables */ #define DAX_WAIT_TABLE_BITS 12 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS) -wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES]; +static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES]; static int __init init_dax_wait_table(void) { @@ -64,14 +50,6 @@ static int __init init_dax_wait_table(void) } fs_initcall(init_dax_wait_table); -static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping, - pgoff_t index) -{ - unsigned long hash = hash_long((unsigned long)mapping ^ index, - DAX_WAIT_TABLE_BITS); - return wait_table + hash; -} - static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax) { struct request_queue *q = bdev->bd_queue; @@ -98,6 +76,26 @@ static void dax_unmap_atomic(struct block_device *bdev, blk_queue_exit(bdev->bd_queue); } +static int dax_is_pmd_entry(void *entry) +{ + return (unsigned long)entry & RADIX_DAX_PMD; +} + +static int dax_is_pte_entry(void *entry) +{ + return !((unsigned long)entry & RADIX_DAX_PMD); +} + +static int dax_is_zero_entry(void *entry) +{ + return (unsigned long)entry & RADIX_DAX_HZP; +} + +static int dax_is_empty_entry(void *entry) +{ + return (unsigned long)entry & RADIX_DAX_EMPTY; +} + struct page *read_dax_sector(struct block_device *bdev, sector_t n) { struct page *page = alloc_pages(GFP_KERNEL, 0); @@ -123,19 +121,6 @@ static bool buffer_written(struct buffer_head *bh) return buffer_mapped(bh) && !buffer_unwritten(bh); } -/* - * When ext4 encounters a hole, it returns without modifying the buffer_head - * which means that we can't trust b_size. To cope with this, we set b_state - * to 0 before calling get_block and, if any bit is set, we know we can trust - * b_size. Unfortunate, really, since ext4 knows precisely how long a hole is - * and would save us time calling get_block repeatedly. - */ -static bool buffer_size_valid(struct buffer_head *bh) -{ - return bh->b_state != 0; -} - - static sector_t to_sector(const struct buffer_head *bh, const struct inode *inode) { @@ -177,8 +162,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, rc = get_block(inode, block, bh, rw == WRITE); if (rc) break; - if (!buffer_size_valid(bh)) - bh->b_size = 1 << blkbits; bh_max = pos - first + bh->b_size; bdev = bh->b_bdev; /* @@ -300,7 +283,7 @@ EXPORT_SYMBOL_GPL(dax_do_io); */ struct exceptional_entry_key { struct address_space *mapping; - unsigned long index; + pgoff_t entry_start; }; struct wait_exceptional_entry_queue { @@ -308,6 +291,26 @@ struct wait_exceptional_entry_queue { struct exceptional_entry_key key; }; +static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping, + pgoff_t index, void *entry, struct exceptional_entry_key *key) +{ + unsigned long hash; + + /* + * If 'entry' is a PMD, align the 'index' that we use for the wait + * queue to the start of that PMD. This ensures that all offsets in + * the range covered by the PMD map to the same bit lock. + */ + if (dax_is_pmd_entry(entry)) + index &= ~((1UL << (PMD_SHIFT - PAGE_SHIFT)) - 1); + + key->mapping = mapping; + key->entry_start = index; + + hash = hash_long((unsigned long)mapping ^ index, DAX_WAIT_TABLE_BITS); + return wait_table + hash; +} + static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode, int sync, void *keyp) { @@ -316,7 +319,7 @@ static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode, container_of(wait, struct wait_exceptional_entry_queue, wait); if (key->mapping != ewait->key.mapping || - key->index != ewait->key.index) + key->entry_start != ewait->key.entry_start) return 0; return autoremove_wake_function(wait, mode, sync, NULL); } @@ -372,24 +375,24 @@ static inline void *unlock_slot(struct address_space *mapping, void **slot) static void *get_unlocked_mapping_entry(struct address_space *mapping, pgoff_t index, void ***slotp) { - void *ret, **slot; + void *entry, **slot; struct wait_exceptional_entry_queue ewait; - wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index); + wait_queue_head_t *wq; init_wait(&ewait.wait); ewait.wait.func = wake_exceptional_entry_func; - ewait.key.mapping = mapping; - ewait.key.index = index; for (;;) { - ret = __radix_tree_lookup(&mapping->page_tree, index, NULL, + entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot); - if (!ret || !radix_tree_exceptional_entry(ret) || + if (!entry || !radix_tree_exceptional_entry(entry) || !slot_locked(mapping, slot)) { if (slotp) *slotp = slot; - return ret; + return entry; } + + wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key); prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE); spin_unlock_irq(&mapping->tree_lock); @@ -399,52 +402,157 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping, } } +static void put_locked_mapping_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + if (!radix_tree_exceptional_entry(entry)) { + unlock_page(entry); + put_page(entry); + } else { + dax_unlock_mapping_entry(mapping, index); + } +} + +/* + * Called when we are done with radix tree entry we looked up via + * get_unlocked_mapping_entry() and which we didn't lock in the end. + */ +static void put_unlocked_mapping_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + if (!radix_tree_exceptional_entry(entry)) + return; + + /* We have to wake up next waiter for the radix tree entry lock */ + dax_wake_mapping_entry_waiter(mapping, index, entry, false); +} + /* * Find radix tree entry at given index. If it points to a page, return with * the page locked. If it points to the exceptional entry, return with the * radix tree entry locked. If the radix tree doesn't contain given index, * create empty exceptional entry for the index and return with it locked. * + * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will + * either return that locked entry or will return an error. This error will + * happen if there are any 4k entries (either zero pages or DAX entries) + * within the 2MiB range that we are requesting. + * + * We always favor 4k entries over 2MiB entries. There isn't a flow where we + * evict 4k entries in order to 'upgrade' them to a 2MiB entry. A 2MiB + * insertion will fail if it finds any 4k entries already in the tree, and a + * 4k insertion will cause an existing 2MiB entry to be unmapped and + * downgraded to 4k entries. This happens for both 2MiB huge zero pages as + * well as 2MiB empty entries. + * + * The exception to this downgrade path is for 2MiB DAX PMD entries that have + * real storage backing them. We will leave these real 2MiB DAX entries in + * the tree, and PTE writes will simply dirty the entire 2MiB DAX entry. + * * Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For * persistent memory the benefit is doubtful. We can add that later if we can * show it helps. */ -static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index) +static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index, + unsigned long size_flag) { - void *ret, **slot; + bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */ + void *entry, **slot; restart: spin_lock_irq(&mapping->tree_lock); - ret = get_unlocked_mapping_entry(mapping, index, &slot); + entry = get_unlocked_mapping_entry(mapping, index, &slot); + + if (entry) { + if (size_flag & RADIX_DAX_PMD) { + if (!radix_tree_exceptional_entry(entry) || + dax_is_pte_entry(entry)) { + put_unlocked_mapping_entry(mapping, index, + entry); + entry = ERR_PTR(-EEXIST); + goto out_unlock; + } + } else { /* trying to grab a PTE entry */ + if (radix_tree_exceptional_entry(entry) && + dax_is_pmd_entry(entry) && + (dax_is_zero_entry(entry) || + dax_is_empty_entry(entry))) { + pmd_downgrade = true; + } + } + } + /* No entry for given index? Make sure radix tree is big enough. */ - if (!ret) { + if (!entry || pmd_downgrade) { int err; + if (pmd_downgrade) { + /* + * Make sure 'entry' remains valid while we drop + * mapping->tree_lock. + */ + entry = lock_slot(mapping, slot); + } + spin_unlock_irq(&mapping->tree_lock); err = radix_tree_preload( mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM); - if (err) + if (err) { + if (pmd_downgrade) + put_locked_mapping_entry(mapping, index, entry); return ERR_PTR(err); - ret = (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | - RADIX_DAX_ENTRY_LOCK); + } + + /* + * Besides huge zero pages the only other thing that gets + * downgraded are empty entries which don't need to be + * unmapped. + */ + if (pmd_downgrade && dax_is_zero_entry(entry)) + unmap_mapping_range(mapping, + (index << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0); + spin_lock_irq(&mapping->tree_lock); - err = radix_tree_insert(&mapping->page_tree, index, ret); + + if (pmd_downgrade) { + radix_tree_delete(&mapping->page_tree, index); + mapping->nrexceptional--; + dax_wake_mapping_entry_waiter(mapping, index, entry, + true); + } + + entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY); + + err = __radix_tree_insert(&mapping->page_tree, index, + dax_radix_order(entry), entry); radix_tree_preload_end(); if (err) { spin_unlock_irq(&mapping->tree_lock); - /* Someone already created the entry? */ - if (err == -EEXIST) + /* + * Someone already created the entry? This is a + * normal failure when inserting PMDs in a range + * that already contains PTEs. In that case we want + * to return -EEXIST immediately. + */ + if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD)) goto restart; + /* + * Our insertion of a DAX PMD entry failed, most + * likely because it collided with a PTE sized entry + * at a different index in the PMD range. We haven't + * inserted anything into the radix tree and have no + * waiters to wake. + */ return ERR_PTR(err); } /* Good, we have inserted empty locked entry into the tree. */ mapping->nrexceptional++; spin_unlock_irq(&mapping->tree_lock); - return ret; + return entry; } /* Normal page in radix tree? */ - if (!radix_tree_exceptional_entry(ret)) { - struct page *page = ret; + if (!radix_tree_exceptional_entry(entry)) { + struct page *page = entry; get_page(page); spin_unlock_irq(&mapping->tree_lock); @@ -457,15 +565,26 @@ restart: } return page; } - ret = lock_slot(mapping, slot); + entry = lock_slot(mapping, slot); + out_unlock: spin_unlock_irq(&mapping->tree_lock); - return ret; + return entry; } +/* + * We do not necessarily hold the mapping->tree_lock when we call this + * function so it is possible that 'entry' is no longer a valid item in the + * radix tree. This is okay because all we really need to do is to find the + * correct waitqueue where tasks might be waiting for that old 'entry' and + * wake them. + */ void dax_wake_mapping_entry_waiter(struct address_space *mapping, - pgoff_t index, bool wake_all) + pgoff_t index, void *entry, bool wake_all) { - wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index); + struct exceptional_entry_key key; + wait_queue_head_t *wq; + + wq = dax_entry_waitqueue(mapping, index, entry, &key); /* * Checking for locked entry and prepare_to_wait_exclusive() happens @@ -473,54 +592,24 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping, * So at this point all tasks that could have seen our entry locked * must be in the waitqueue and the following check will see them. */ - if (waitqueue_active(wq)) { - struct exceptional_entry_key key; - - key.mapping = mapping; - key.index = index; + if (waitqueue_active(wq)) __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); - } } void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index) { - void *ret, **slot; + void *entry, **slot; spin_lock_irq(&mapping->tree_lock); - ret = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot); - if (WARN_ON_ONCE(!ret || !radix_tree_exceptional_entry(ret) || + entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot); + if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) || !slot_locked(mapping, slot))) { spin_unlock_irq(&mapping->tree_lock); return; } unlock_slot(mapping, slot); spin_unlock_irq(&mapping->tree_lock); - dax_wake_mapping_entry_waiter(mapping, index, false); -} - -static void put_locked_mapping_entry(struct address_space *mapping, - pgoff_t index, void *entry) -{ - if (!radix_tree_exceptional_entry(entry)) { - unlock_page(entry); - put_page(entry); - } else { - dax_unlock_mapping_entry(mapping, index); - } -} - -/* - * Called when we are done with radix tree entry we looked up via - * get_unlocked_mapping_entry() and which we didn't lock in the end. - */ -static void put_unlocked_mapping_entry(struct address_space *mapping, - pgoff_t index, void *entry) -{ - if (!radix_tree_exceptional_entry(entry)) - return; - - /* We have to wake up next waiter for the radix tree entry lock */ - dax_wake_mapping_entry_waiter(mapping, index, false); + dax_wake_mapping_entry_waiter(mapping, index, entry, false); } /* @@ -547,7 +636,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) radix_tree_delete(&mapping->page_tree, index); mapping->nrexceptional--; spin_unlock_irq(&mapping->tree_lock); - dax_wake_mapping_entry_waiter(mapping, index, true); + dax_wake_mapping_entry_waiter(mapping, index, entry, true); return 1; } @@ -600,11 +689,17 @@ static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size return 0; } -#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT)) - +/* + * By this point grab_mapping_entry() has ensured that we have a locked entry + * of the appropriate size so we don't have to worry about downgrading PMDs to + * PTEs. If we happen to be trying to insert a PTE and there is a PMD + * already in the tree, we will skip the insertion and just dirty the PMD as + * appropriate. + */ static void *dax_insert_mapping_entry(struct address_space *mapping, struct vm_fault *vmf, - void *entry, sector_t sector) + void *entry, sector_t sector, + unsigned long flags) { struct radix_tree_root *page_tree = &mapping->page_tree; int error = 0; @@ -627,22 +722,35 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM); if (error) return ERR_PTR(error); + } else if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_HZP)) { + /* replacing huge zero page with PMD block mapping */ + unmap_mapping_range(mapping, + (vmf->pgoff << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0); } spin_lock_irq(&mapping->tree_lock); - new_entry = (void *)((unsigned long)RADIX_DAX_ENTRY(sector, false) | - RADIX_DAX_ENTRY_LOCK); + new_entry = dax_radix_locked_entry(sector, flags); + if (hole_fill) { __delete_from_page_cache(entry, NULL); /* Drop pagecache reference */ put_page(entry); - error = radix_tree_insert(page_tree, index, new_entry); + error = __radix_tree_insert(page_tree, index, + dax_radix_order(new_entry), new_entry); if (error) { new_entry = ERR_PTR(error); goto unlock; } mapping->nrexceptional++; - } else { + } else if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + /* + * Only swap our new entry into the radix tree if the current + * entry is a zero page or an empty entry. If a normal PTE or + * PMD entry is already in the tree, we leave it alone. This + * means that if we are trying to insert a PTE and the + * existing entry is a PMD, we will just leave the PMD in the + * tree and dirty it if necessary. + */ void **slot; void *ret; @@ -672,7 +780,6 @@ 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; @@ -693,13 +800,21 @@ static int dax_writeback_one(struct block_device *bdev, 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)) { + if (WARN_ON_ONCE(dax_is_empty_entry(entry) || + dax_is_zero_entry(entry))) { ret = -EIO; goto unlock; } - dax.sector = RADIX_DAX_SECTOR(entry); - dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE); + /* + * Even if dax_writeback_mapping_range() was given a wbc->range_start + * in the middle of a PMD, the 'index' we are given will be aligned to + * the start index of the PMD, as will the sector we pull from + * 'entry'. This allows us to flush for PMD_SIZE and not have to + * worry about partial PMD writebacks. + */ + dax.sector = dax_radix_sector(entry); + dax.size = PAGE_SIZE << dax_radix_order(entry); spin_unlock_irq(&mapping->tree_lock); /* @@ -738,12 +853,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc) { struct inode *inode = mapping->host; - pgoff_t start_index, end_index, pmd_index; + pgoff_t start_index, end_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; @@ -753,15 +867,6 @@ int dax_writeback_mapping_range(struct address_space *mapping, start_index = wbc->range_start >> PAGE_SHIFT; end_index = wbc->range_end >> PAGE_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); @@ -806,7 +911,7 @@ static int dax_insert_mapping(struct address_space *mapping, return PTR_ERR(dax.addr); dax_unmap_atomic(bdev, &dax); - ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector); + ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector, 0); if (IS_ERR(ret)) return PTR_ERR(ret); *entryp = ret; @@ -853,7 +958,7 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, bh.b_bdev = inode->i_sb->s_bdev; bh.b_size = PAGE_SIZE; - entry = grab_mapping_entry(mapping, vmf->pgoff); + entry = grab_mapping_entry(mapping, vmf->pgoff, 0); if (IS_ERR(entry)) { error = PTR_ERR(entry); goto out; @@ -913,224 +1018,6 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, } EXPORT_SYMBOL_GPL(dax_fault); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) -/* - * The 'colour' (ie low bits) within a PMD of a page offset. This comes up - * more often than one might expect in the below function. - */ -#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) - -static void __dax_dbg(struct buffer_head *bh, unsigned long address, - const char *reason, const char *fn) -{ - if (bh) { - char bname[BDEVNAME_SIZE]; - bdevname(bh->b_bdev, bname); - pr_debug("%s: %s addr: %lx dev %s state %lx start %lld " - "length %zd fallback: %s\n", fn, current->comm, - address, bname, bh->b_state, (u64)bh->b_blocknr, - bh->b_size, reason); - } else { - pr_debug("%s: %s addr: %lx fallback: %s\n", fn, - current->comm, address, reason); - } -} - -#define dax_pmd_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pmd") - -/** - * dax_pmd_fault - handle a PMD fault on a DAX file - * @vma: The virtual memory area where the fault occurred - * @vmf: The description of the fault - * @get_block: The filesystem method used to translate file offsets to blocks - * - * When a page fault occurs, filesystems may call this helper in their - * pmd_fault handler for DAX files. - */ -int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd, unsigned int flags, get_block_t get_block) -{ - struct file *file = vma->vm_file; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - struct buffer_head bh; - unsigned blkbits = inode->i_blkbits; - unsigned long pmd_addr = address & PMD_MASK; - bool write = flags & FAULT_FLAG_WRITE; - struct block_device *bdev; - pgoff_t size, pgoff; - sector_t block; - int result = 0; - bool alloc = false; - - /* dax pmd mappings require pfn_t_devmap() */ - if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) - return VM_FAULT_FALLBACK; - - /* Fall back to PTEs if we're going to COW */ - if (write && !(vma->vm_flags & VM_SHARED)) { - split_huge_pmd(vma, pmd, address); - dax_pmd_dbg(NULL, address, "cow write"); - return VM_FAULT_FALLBACK; - } - /* If the PMD would extend outside the VMA */ - if (pmd_addr < vma->vm_start) { - dax_pmd_dbg(NULL, address, "vma start unaligned"); - return VM_FAULT_FALLBACK; - } - if ((pmd_addr + PMD_SIZE) > vma->vm_end) { - dax_pmd_dbg(NULL, address, "vma end unaligned"); - return VM_FAULT_FALLBACK; - } - - pgoff = linear_page_index(vma, pmd_addr); - size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (pgoff >= size) - return VM_FAULT_SIGBUS; - /* If the PMD would cover blocks out of the file */ - if ((pgoff | PG_PMD_COLOUR) >= size) { - dax_pmd_dbg(NULL, address, - "offset + huge page size > file size"); - return VM_FAULT_FALLBACK; - } - - memset(&bh, 0, sizeof(bh)); - bh.b_bdev = inode->i_sb->s_bdev; - block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); - - bh.b_size = PMD_SIZE; - - 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; - WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh)); - } - - bdev = bh.b_bdev; - - /* - * If the filesystem isn't willing to tell us the length of a hole, - * just fall back to PTEs. Calling get_block 512 times in a loop - * would be silly. - */ - if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) { - dax_pmd_dbg(&bh, address, "allocated block too small"); - 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); - } - - if (!write && !buffer_mapped(&bh)) { - spinlock_t *ptl; - pmd_t entry; - struct page *zero_page = mm_get_huge_zero_page(vma->vm_mm); - - if (unlikely(!zero_page)) { - dax_pmd_dbg(&bh, address, "no zero page"); - goto fallback; - } - - ptl = pmd_lock(vma->vm_mm, pmd); - if (!pmd_none(*pmd)) { - spin_unlock(ptl); - dax_pmd_dbg(&bh, address, "pmd already present"); - goto fallback; - } - - dev_dbg(part_to_dev(bdev->bd_part), - "%s: %s addr: %lx pfn: <zero> sect: %llx\n", - __func__, current->comm, address, - (unsigned long long) to_sector(&bh, inode)); - - entry = mk_pmd(zero_page, vma->vm_page_prot); - entry = pmd_mkhuge(entry); - set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry); - result = VM_FAULT_NOPAGE; - spin_unlock(ptl); - } else { - struct blk_dax_ctl dax = { - .sector = to_sector(&bh, inode), - .size = PMD_SIZE, - }; - long length = dax_map_atomic(bdev, &dax); - - if (length < 0) { - dax_pmd_dbg(&bh, address, "dax-error fallback"); - goto fallback; - } - if (length < PMD_SIZE) { - dax_pmd_dbg(&bh, address, "dax-length too small"); - dax_unmap_atomic(bdev, &dax); - goto fallback; - } - if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) { - dax_pmd_dbg(&bh, address, "pfn unaligned"); - dax_unmap_atomic(bdev, &dax); - goto fallback; - } - - if (!pfn_t_devmap(dax.pfn)) { - dax_unmap_atomic(bdev, &dax); - dax_pmd_dbg(&bh, address, "pfn not in memmap"); - goto fallback; - } - 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) { - /* - * We should insert radix-tree entry and dirty it here. - * For now this is broken... - */ - } - - dev_dbg(part_to_dev(bdev->bd_part), - "%s: %s addr: %lx pfn: %lx sect: %llx\n", - __func__, current->comm, address, - pfn_t_to_pfn(dax.pfn), - (unsigned long long) dax.sector); - result |= vmf_insert_pfn_pmd(vma, address, pmd, - dax.pfn, write); - } - - out: - return result; - - fallback: - count_vm_event(THP_FAULT_FALLBACK); - result = VM_FAULT_FALLBACK; - goto out; -} -EXPORT_SYMBOL_GPL(dax_pmd_fault); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - /** * dax_pfn_mkwrite - handle first write to DAX page * @vma: The virtual memory area where the fault occurred @@ -1214,7 +1101,8 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length, /* Block boundary? Nothing to do */ if (!length) return 0; - BUG_ON((offset + length) > PAGE_SIZE); + if (WARN_ON_ONCE((offset + length) > PAGE_SIZE)) + return -EINVAL; memset(&bh, 0, sizeof(bh)); bh.b_bdev = inode->i_sb->s_bdev; @@ -1245,8 +1133,13 @@ int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block) EXPORT_SYMBOL_GPL(dax_truncate_page); #ifdef CONFIG_FS_IOMAP +static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos) +{ + return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9); +} + static loff_t -iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data, +dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap) { struct iov_iter *iter = data; @@ -1270,8 +1163,7 @@ iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct blk_dax_ctl dax = { 0 }; ssize_t map_len; - dax.sector = iomap->blkno + - (((pos & PAGE_MASK) - iomap->offset) >> 9); + dax.sector = dax_iomap_sector(iomap, pos); dax.size = (length + offset + PAGE_SIZE - 1) & PAGE_MASK; map_len = dax_map_atomic(iomap->bdev, &dax); if (map_len < 0) { @@ -1303,7 +1195,7 @@ iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data, } /** - * iomap_dax_rw - Perform I/O to a DAX file + * dax_iomap_rw - Perform I/O to a DAX file * @iocb: The control block for this I/O * @iter: The addresses to do I/O from or to * @ops: iomap ops passed from the file system @@ -1313,7 +1205,7 @@ iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data, * and evicting any page cache pages in the region under I/O. */ ssize_t -iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter, +dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops) { struct address_space *mapping = iocb->ki_filp->f_mapping; @@ -1343,7 +1235,7 @@ iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter, while (iov_iter_count(iter)) { ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops, - iter, iomap_dax_actor); + iter, dax_iomap_actor); if (ret <= 0) break; pos += ret; @@ -1353,10 +1245,10 @@ iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter, iocb->ki_pos += done; return done ? done : ret; } -EXPORT_SYMBOL_GPL(iomap_dax_rw); +EXPORT_SYMBOL_GPL(dax_iomap_rw); /** - * iomap_dax_fault - handle a page fault on a DAX file + * dax_iomap_fault - handle a page fault on a DAX file * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault * @ops: iomap ops passed from the file system @@ -1365,7 +1257,7 @@ EXPORT_SYMBOL_GPL(iomap_dax_rw); * or mkwrite handler for DAX files. Assumes the caller has done all the * necessary locking for the page fault to proceed successfully. */ -int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, +int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, struct iomap_ops *ops) { struct address_space *mapping = vma->vm_file->f_mapping; @@ -1374,8 +1266,9 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT; sector_t sector; struct iomap iomap = { 0 }; - unsigned flags = 0; + unsigned flags = IOMAP_FAULT; int error, major = 0; + int locked_status = 0; void *entry; /* @@ -1386,7 +1279,7 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (pos >= i_size_read(inode)) return VM_FAULT_SIGBUS; - entry = grab_mapping_entry(mapping, vmf->pgoff); + entry = grab_mapping_entry(mapping, vmf->pgoff, 0); if (IS_ERR(entry)) { error = PTR_ERR(entry); goto out; @@ -1405,10 +1298,10 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, goto unlock_entry; if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) { error = -EIO; /* fs corruption? */ - goto unlock_entry; + goto finish_iomap; } - sector = iomap.blkno + (((pos & PAGE_MASK) - iomap.offset) >> 9); + sector = dax_iomap_sector(&iomap, pos); if (vmf->cow_page) { switch (iomap.type) { @@ -1427,13 +1320,15 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, } if (error) - goto unlock_entry; + goto finish_iomap; if (!radix_tree_exceptional_entry(entry)) { vmf->page = entry; - return VM_FAULT_LOCKED; + locked_status = VM_FAULT_LOCKED; + } else { + vmf->entry = entry; + locked_status = VM_FAULT_DAX_LOCKED; } - vmf->entry = entry; - return VM_FAULT_DAX_LOCKED; + goto finish_iomap; } switch (iomap.type) { @@ -1448,8 +1343,10 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, break; case IOMAP_UNWRITTEN: case IOMAP_HOLE: - if (!(vmf->flags & FAULT_FLAG_WRITE)) - return dax_load_hole(mapping, entry, vmf); + if (!(vmf->flags & FAULT_FLAG_WRITE)) { + locked_status = dax_load_hole(mapping, entry, vmf); + break; + } /*FALLTHRU*/ default: WARN_ON_ONCE(1); @@ -1457,15 +1354,218 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, break; } + finish_iomap: + if (ops->iomap_end) { + if (error) { + /* keep previous error */ + ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags, + &iomap); + } else { + error = ops->iomap_end(inode, pos, PAGE_SIZE, + PAGE_SIZE, flags, &iomap); + } + } unlock_entry: - put_locked_mapping_entry(mapping, vmf->pgoff, entry); + if (!locked_status || error) + put_locked_mapping_entry(mapping, vmf->pgoff, entry); out: if (error == -ENOMEM) return VM_FAULT_OOM | major; /* -EBUSY is fine, somebody else faulted on the same PTE */ if (error < 0 && error != -EBUSY) return VM_FAULT_SIGBUS | major; + if (locked_status) { + WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */ + return locked_status; + } return VM_FAULT_NOPAGE | major; } -EXPORT_SYMBOL_GPL(iomap_dax_fault); +EXPORT_SYMBOL_GPL(dax_iomap_fault); + +#ifdef CONFIG_FS_DAX_PMD +/* + * The 'colour' (ie low bits) within a PMD of a page offset. This comes up + * more often than one might expect in the below functions. + */ +#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) + +static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd, + struct vm_fault *vmf, unsigned long address, + struct iomap *iomap, loff_t pos, bool write, void **entryp) +{ + struct address_space *mapping = vma->vm_file->f_mapping; + struct block_device *bdev = iomap->bdev; + struct blk_dax_ctl dax = { + .sector = dax_iomap_sector(iomap, pos), + .size = PMD_SIZE, + }; + long length = dax_map_atomic(bdev, &dax); + void *ret; + + if (length < 0) /* dax_map_atomic() failed */ + return VM_FAULT_FALLBACK; + if (length < PMD_SIZE) + goto unmap_fallback; + if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) + goto unmap_fallback; + if (!pfn_t_devmap(dax.pfn)) + goto unmap_fallback; + + dax_unmap_atomic(bdev, &dax); + + ret = dax_insert_mapping_entry(mapping, vmf, *entryp, dax.sector, + RADIX_DAX_PMD); + if (IS_ERR(ret)) + return VM_FAULT_FALLBACK; + *entryp = ret; + + return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write); + + unmap_fallback: + dax_unmap_atomic(bdev, &dax); + return VM_FAULT_FALLBACK; +} + +static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd, + struct vm_fault *vmf, unsigned long address, + struct iomap *iomap, void **entryp) +{ + struct address_space *mapping = vma->vm_file->f_mapping; + unsigned long pmd_addr = address & PMD_MASK; + struct page *zero_page; + spinlock_t *ptl; + pmd_t pmd_entry; + void *ret; + + zero_page = mm_get_huge_zero_page(vma->vm_mm); + + if (unlikely(!zero_page)) + return VM_FAULT_FALLBACK; + + ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0, + RADIX_DAX_PMD | RADIX_DAX_HZP); + if (IS_ERR(ret)) + return VM_FAULT_FALLBACK; + *entryp = ret; + + ptl = pmd_lock(vma->vm_mm, pmd); + if (!pmd_none(*pmd)) { + spin_unlock(ptl); + return VM_FAULT_FALLBACK; + } + + pmd_entry = mk_pmd(zero_page, vma->vm_page_prot); + pmd_entry = pmd_mkhuge(pmd_entry); + set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry); + spin_unlock(ptl); + return VM_FAULT_NOPAGE; +} + +int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, unsigned int flags, struct iomap_ops *ops) +{ + struct address_space *mapping = vma->vm_file->f_mapping; + unsigned long pmd_addr = address & PMD_MASK; + bool write = flags & FAULT_FLAG_WRITE; + unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT; + struct inode *inode = mapping->host; + int result = VM_FAULT_FALLBACK; + struct iomap iomap = { 0 }; + pgoff_t max_pgoff, pgoff; + struct vm_fault vmf; + void *entry; + loff_t pos; + int error; + + /* Fall back to PTEs if we're going to COW */ + if (write && !(vma->vm_flags & VM_SHARED)) + goto fallback; + + /* If the PMD would extend outside the VMA */ + if (pmd_addr < vma->vm_start) + goto fallback; + if ((pmd_addr + PMD_SIZE) > vma->vm_end) + goto fallback; + + /* + * Check whether offset isn't beyond end of file now. Caller is + * supposed to hold locks serializing us with truncate / punch hole so + * this is a reliable test. + */ + pgoff = linear_page_index(vma, pmd_addr); + max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT; + + if (pgoff > max_pgoff) + return VM_FAULT_SIGBUS; + + /* If the PMD would extend beyond the file size */ + if ((pgoff | PG_PMD_COLOUR) > max_pgoff) + goto fallback; + + /* + * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX + * PMD or a HZP entry. If it can't (because a 4k page is already in + * the tree, for instance), it will return -EEXIST and we just fall + * back to 4k entries. + */ + entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD); + if (IS_ERR(entry)) + goto fallback; + + /* + * Note that we don't use iomap_apply here. We aren't doing I/O, only + * setting up a mapping, so really we're using iomap_begin() as a way + * to look up our filesystem block. + */ + pos = (loff_t)pgoff << PAGE_SHIFT; + error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap); + if (error) + goto unlock_entry; + if (iomap.offset + iomap.length < pos + PMD_SIZE) + goto finish_iomap; + + vmf.pgoff = pgoff; + vmf.flags = flags; + vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO; + + switch (iomap.type) { + case IOMAP_MAPPED: + result = dax_pmd_insert_mapping(vma, pmd, &vmf, address, + &iomap, pos, write, &entry); + break; + case IOMAP_UNWRITTEN: + case IOMAP_HOLE: + if (WARN_ON_ONCE(write)) + goto finish_iomap; + result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap, + &entry); + break; + default: + WARN_ON_ONCE(1); + break; + } + + finish_iomap: + if (ops->iomap_end) { + if (result == VM_FAULT_FALLBACK) { + ops->iomap_end(inode, pos, PMD_SIZE, 0, iomap_flags, + &iomap); + } else { + error = ops->iomap_end(inode, pos, PMD_SIZE, PMD_SIZE, + iomap_flags, &iomap); + if (error) + result = VM_FAULT_FALLBACK; + } + } + unlock_entry: + put_locked_mapping_entry(mapping, pgoff, entry); + fallback: + if (result == VM_FAULT_FALLBACK) { + split_huge_pmd(vma, pmd, address); + count_vm_event(THP_FAULT_FALLBACK); + } + return result; +} +EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault); +#endif /* CONFIG_FS_DAX_PMD */ #endif /* CONFIG_FS_IOMAP */ diff --git a/fs/direct-io.c b/fs/direct-io.c index fb9aa16a7727..19aa448fde6a 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -554,7 +554,7 @@ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio) * filesystems that don't need it and also allows us to create the workqueue * late enough so the we can include s_id in the name of the workqueue. */ -static int sb_init_dio_done_wq(struct super_block *sb) +int sb_init_dio_done_wq(struct super_block *sb) { struct workqueue_struct *old; struct workqueue_struct *wq = alloc_workqueue("dio/%s", diff --git a/fs/ext2/file.c b/fs/ext2/file.c index a0e1478dfd04..b0f241528a30 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -38,7 +38,7 @@ static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) return 0; /* skip atime */ inode_lock_shared(inode); - ret = iomap_dax_rw(iocb, to, &ext2_iomap_ops); + ret = dax_iomap_rw(iocb, to, &ext2_iomap_ops); inode_unlock_shared(inode); file_accessed(iocb->ki_filp); @@ -62,7 +62,7 @@ static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ret) goto out_unlock; - ret = iomap_dax_rw(iocb, from, &ext2_iomap_ops); + ret = dax_iomap_rw(iocb, from, &ext2_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); mark_inode_dirty(inode); @@ -99,7 +99,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } down_read(&ei->dax_sem); - ret = iomap_dax_fault(vma, vmf, &ext2_iomap_ops); + ret = dax_iomap_fault(vma, vmf, &ext2_iomap_ops); up_read(&ei->dax_sem); if (vmf->flags & FAULT_FLAG_WRITE) @@ -107,27 +107,6 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return ret; } -static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned int flags) -{ - struct inode *inode = file_inode(vma->vm_file); - struct ext2_inode_info *ei = EXT2_I(inode); - int ret; - - if (flags & FAULT_FLAG_WRITE) { - sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); - } - down_read(&ei->dax_sem); - - ret = dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block); - - up_read(&ei->dax_sem); - if (flags & FAULT_FLAG_WRITE) - sb_end_pagefault(inode->i_sb); - return ret; -} - static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { @@ -154,7 +133,11 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, - .pmd_fault = ext2_dax_pmd_fault, + /* + * .pmd_fault is not supported for DAX because allocation in ext2 + * cannot be reliably aligned to huge page sizes and so pmd faults + * will always fail and fail back to regular faults. + */ .page_mkwrite = ext2_dax_fault, .pfn_mkwrite = ext2_dax_pfn_mkwrite, }; @@ -166,7 +149,7 @@ static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); vma->vm_ops = &ext2_dax_vm_ops; - vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; + vma->vm_flags |= VM_MIXEDMAP; return 0; } #else diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9c064727ed62..3d58b2b477e8 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -767,6 +767,9 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, ext4_update_bh_state(bh, map.m_flags); bh->b_size = inode->i_sb->s_blocksize * map.m_len; ret = 0; + } else if (ret == 0) { + /* hole case, need to fill in bh->b_size */ + bh->b_size = inode->i_sb->s_blocksize * map.m_len; } return ret; } diff --git a/fs/internal.h b/fs/internal.h index f4da3341b4a3..4fcf51766d4a 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -184,3 +184,6 @@ typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len, loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, struct iomap_ops *ops, void *data, iomap_actor_t actor); + +/* direct-io.c: */ +int sb_init_dio_done_wq(struct super_block *sb); diff --git a/fs/iomap.c b/fs/iomap.c index a8ee8c33ca78..fc2446242935 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -24,6 +24,7 @@ #include <linux/uio.h> #include <linux/backing-dev.h> #include <linux/buffer_head.h> +#include <linux/task_io_accounting_ops.h> #include <linux/dax.h> #include "internal.h" @@ -467,8 +468,9 @@ int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, offset = page_offset(page); while (length > 0) { - ret = iomap_apply(inode, offset, length, IOMAP_WRITE, - ops, page, iomap_page_mkwrite_actor); + ret = iomap_apply(inode, offset, length, + IOMAP_WRITE | IOMAP_FAULT, ops, page, + iomap_page_mkwrite_actor); if (unlikely(ret <= 0)) goto out_unlock; offset += ret; @@ -583,3 +585,375 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, return 0; } EXPORT_SYMBOL_GPL(iomap_fiemap); + +/* + * Private flags for iomap_dio, must not overlap with the public ones in + * iomap.h: + */ +#define IOMAP_DIO_WRITE (1 << 30) +#define IOMAP_DIO_DIRTY (1 << 31) + +struct iomap_dio { + struct kiocb *iocb; + iomap_dio_end_io_t *end_io; + loff_t i_size; + loff_t size; + atomic_t ref; + unsigned flags; + int error; + + union { + /* used during submission and for synchronous completion: */ + struct { + struct iov_iter *iter; + struct task_struct *waiter; + struct request_queue *last_queue; + blk_qc_t cookie; + } submit; + + /* used for aio completion: */ + struct { + struct work_struct work; + } aio; + }; +}; + +static ssize_t iomap_dio_complete(struct iomap_dio *dio) +{ + struct kiocb *iocb = dio->iocb; + ssize_t ret; + + if (dio->end_io) { + ret = dio->end_io(iocb, + dio->error ? dio->error : dio->size, + dio->flags); + } else { + ret = dio->error; + } + + if (likely(!ret)) { + ret = dio->size; + /* check for short read */ + if (iocb->ki_pos + ret > dio->i_size && + !(dio->flags & IOMAP_DIO_WRITE)) + ret = dio->i_size - iocb->ki_pos; + iocb->ki_pos += ret; + } + + inode_dio_end(file_inode(iocb->ki_filp)); + kfree(dio); + + return ret; +} + +static void iomap_dio_complete_work(struct work_struct *work) +{ + struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work); + struct kiocb *iocb = dio->iocb; + bool is_write = (dio->flags & IOMAP_DIO_WRITE); + ssize_t ret; + + ret = iomap_dio_complete(dio); + if (is_write && ret > 0) + ret = generic_write_sync(iocb, ret); + iocb->ki_complete(iocb, ret, 0); +} + +/* + * Set an error in the dio if none is set yet. We have to use cmpxchg + * as the submission context and the completion context(s) can race to + * update the error. + */ +static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret) +{ + cmpxchg(&dio->error, 0, ret); +} + +static void iomap_dio_bio_end_io(struct bio *bio) +{ + struct iomap_dio *dio = bio->bi_private; + bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); + + if (bio->bi_error) + iomap_dio_set_error(dio, bio->bi_error); + + if (atomic_dec_and_test(&dio->ref)) { + if (is_sync_kiocb(dio->iocb)) { + struct task_struct *waiter = dio->submit.waiter; + + WRITE_ONCE(dio->submit.waiter, NULL); + wake_up_process(waiter); + } else if (dio->flags & IOMAP_DIO_WRITE) { + struct inode *inode = file_inode(dio->iocb->ki_filp); + + INIT_WORK(&dio->aio.work, iomap_dio_complete_work); + queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work); + } else { + iomap_dio_complete_work(&dio->aio.work); + } + } + + if (should_dirty) { + bio_check_pages_dirty(bio); + } else { + struct bio_vec *bvec; + int i; + + bio_for_each_segment_all(bvec, bio, i) + put_page(bvec->bv_page); + bio_put(bio); + } +} + +static blk_qc_t +iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, + unsigned len) +{ + struct page *page = ZERO_PAGE(0); + struct bio *bio; + + bio = bio_alloc(GFP_KERNEL, 1); + bio->bi_bdev = iomap->bdev; + bio->bi_iter.bi_sector = + iomap->blkno + ((pos - iomap->offset) >> 9); + bio->bi_private = dio; + bio->bi_end_io = iomap_dio_bio_end_io; + + get_page(page); + if (bio_add_page(bio, page, len, 0) != len) + BUG(); + bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_ODIRECT); + + atomic_inc(&dio->ref); + return submit_bio(bio); +} + +static loff_t +iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, + void *data, struct iomap *iomap) +{ + struct iomap_dio *dio = data; + unsigned blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); + unsigned fs_block_size = (1 << inode->i_blkbits), pad; + unsigned align = iov_iter_alignment(dio->submit.iter); + struct iov_iter iter; + struct bio *bio; + bool need_zeroout = false; + int nr_pages, ret; + + if ((pos | length | align) & ((1 << blkbits) - 1)) + return -EINVAL; + + switch (iomap->type) { + case IOMAP_HOLE: + if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE)) + return -EIO; + /*FALLTHRU*/ + case IOMAP_UNWRITTEN: + if (!(dio->flags & IOMAP_DIO_WRITE)) { + iov_iter_zero(length, dio->submit.iter); + dio->size += length; + return length; + } + dio->flags |= IOMAP_DIO_UNWRITTEN; + need_zeroout = true; + break; + case IOMAP_MAPPED: + if (iomap->flags & IOMAP_F_SHARED) + dio->flags |= IOMAP_DIO_COW; + if (iomap->flags & IOMAP_F_NEW) + need_zeroout = true; + break; + default: + WARN_ON_ONCE(1); + return -EIO; + } + + /* + * Operate on a partial iter trimmed to the extent we were called for. + * We'll update the iter in the dio once we're done with this extent. + */ + iter = *dio->submit.iter; + iov_iter_truncate(&iter, length); + + nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES); + if (nr_pages <= 0) + return nr_pages; + + if (need_zeroout) { + /* zero out from the start of the block to the write offset */ + pad = pos & (fs_block_size - 1); + if (pad) + iomap_dio_zero(dio, iomap, pos - pad, pad); + } + + do { + if (dio->error) + return 0; + + bio = bio_alloc(GFP_KERNEL, nr_pages); + bio->bi_bdev = iomap->bdev; + bio->bi_iter.bi_sector = + iomap->blkno + ((pos - iomap->offset) >> 9); + bio->bi_private = dio; + bio->bi_end_io = iomap_dio_bio_end_io; + + ret = bio_iov_iter_get_pages(bio, &iter); + if (unlikely(ret)) { + bio_put(bio); + return ret; + } + + if (dio->flags & IOMAP_DIO_WRITE) { + bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_ODIRECT); + task_io_account_write(bio->bi_iter.bi_size); + } else { + bio_set_op_attrs(bio, REQ_OP_READ, 0); + if (dio->flags & IOMAP_DIO_DIRTY) + bio_set_pages_dirty(bio); + } + + dio->size += bio->bi_iter.bi_size; + pos += bio->bi_iter.bi_size; + + nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES); + + atomic_inc(&dio->ref); + + dio->submit.last_queue = bdev_get_queue(iomap->bdev); + dio->submit.cookie = submit_bio(bio); + } while (nr_pages); + + if (need_zeroout) { + /* zero out from the end of the write to the end of the block */ + pad = pos & (fs_block_size - 1); + if (pad) + iomap_dio_zero(dio, iomap, pos, fs_block_size - pad); + } + + iov_iter_advance(dio->submit.iter, length); + return length; +} + +ssize_t +iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops, + iomap_dio_end_io_t end_io) +{ + struct address_space *mapping = iocb->ki_filp->f_mapping; + struct inode *inode = file_inode(iocb->ki_filp); + size_t count = iov_iter_count(iter); + loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0; + unsigned int flags = IOMAP_DIRECT; + struct blk_plug plug; + struct iomap_dio *dio; + + lockdep_assert_held(&inode->i_rwsem); + + if (!count) + return 0; + + dio = kmalloc(sizeof(*dio), GFP_KERNEL); + if (!dio) + return -ENOMEM; + + dio->iocb = iocb; + atomic_set(&dio->ref, 1); + dio->size = 0; + dio->i_size = i_size_read(inode); + dio->end_io = end_io; + dio->error = 0; + dio->flags = 0; + + dio->submit.iter = iter; + if (is_sync_kiocb(iocb)) { + dio->submit.waiter = current; + dio->submit.cookie = BLK_QC_T_NONE; + dio->submit.last_queue = NULL; + } + + if (iov_iter_rw(iter) == READ) { + if (pos >= dio->i_size) + goto out_free_dio; + + if (iter->type == ITER_IOVEC) + dio->flags |= IOMAP_DIO_DIRTY; + } else { + dio->flags |= IOMAP_DIO_WRITE; + flags |= IOMAP_WRITE; + } + + if (mapping->nrpages) { + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); + if (ret) + goto out_free_dio; + + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + ret = 0; + } + + inode_dio_begin(inode); + + blk_start_plug(&plug); + do { + ret = iomap_apply(inode, pos, count, flags, ops, dio, + iomap_dio_actor); + if (ret <= 0) { + /* magic error code to fall back to buffered I/O */ + if (ret == -ENOTBLK) + ret = 0; + break; + } + pos += ret; + } while ((count = iov_iter_count(iter)) > 0); + blk_finish_plug(&plug); + + if (ret < 0) + iomap_dio_set_error(dio, ret); + + if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && + !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + iomap_dio_set_error(dio, ret); + } + + if (!atomic_dec_and_test(&dio->ref)) { + if (!is_sync_kiocb(iocb)) + return -EIOCBQUEUED; + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (!READ_ONCE(dio->submit.waiter)) + break; + + if (!(iocb->ki_flags & IOCB_HIPRI) || + !dio->submit.last_queue || + !blk_poll(dio->submit.last_queue, + dio->submit.cookie)) + io_schedule(); + } + __set_current_state(TASK_RUNNING); + } + + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (iov_iter_rw(iter) == WRITE && mapping->nrpages) { + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + } + + return iomap_dio_complete(dio); + +out_free_dio: + kfree(dio); + return ret; +} +EXPORT_SYMBOL_GPL(iomap_dio_rw); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index 91f51637f8af..f7dda0c237b0 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -51,7 +51,7 @@ int xfs_attr_shortform_getvalue(struct xfs_da_args *args); int xfs_attr_shortform_to_leaf(struct xfs_da_args *args); int xfs_attr_shortform_remove(struct xfs_da_args *args); int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); -int xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes); +int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes); void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp); /* diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 29ffc0569ce1..2760bc3b2536 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4850,8 +4850,11 @@ xfs_bmap_del_extent_delay( * sb counters as we might have to borrow some blocks for the * indirect block accounting. */ - xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del->br_blockcount), 0, + error = xfs_trans_reserve_quota_nblks(NULL, ip, + -((long)del->br_blockcount), 0, isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); + if (error) + return error; ip->i_delayed_blks -= del->br_blockcount; if (whichfork == XFS_COW_FORK) diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index becc926c3e3d..0197590fa7d7 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -157,6 +157,9 @@ extern int xfs_dir2_isleaf(struct xfs_da_args *args, int *r); extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db, struct xfs_buf *bp); +extern void xfs_dir2_data_freescan_int(struct xfs_da_geometry *geo, + const struct xfs_dir_ops *ops, + struct xfs_dir2_data_hdr *hdr, int *loghead); extern void xfs_dir2_data_freescan(struct xfs_inode *dp, struct xfs_dir2_data_hdr *hdr, int *loghead); extern void xfs_dir2_data_log_entry(struct xfs_da_args *args, @@ -177,6 +180,8 @@ extern struct xfs_dir2_data_free *xfs_dir2_data_freefind( struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_data_free *bf, struct xfs_dir2_data_unused *dup); +extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino); + extern const struct xfs_buf_ops xfs_dir3_block_buf_ops; extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops; extern const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops; diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index e526f5a5f0be..d478065b9544 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -505,8 +505,9 @@ xfs_dir2_data_freeremove( * Given a data block, reconstruct its bestfree map. */ void -xfs_dir2_data_freescan( - struct xfs_inode *dp, +xfs_dir2_data_freescan_int( + struct xfs_da_geometry *geo, + const struct xfs_dir_ops *ops, struct xfs_dir2_data_hdr *hdr, int *loghead) { @@ -516,7 +517,6 @@ xfs_dir2_data_freescan( struct xfs_dir2_data_free *bf; char *endp; /* end of block's data */ char *p; /* current entry pointer */ - struct xfs_da_geometry *geo = dp->i_mount->m_dir_geo; ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) || @@ -526,13 +526,13 @@ xfs_dir2_data_freescan( /* * Start by clearing the table. */ - bf = dp->d_ops->data_bestfree_p(hdr); + bf = ops->data_bestfree_p(hdr); memset(bf, 0, sizeof(*bf) * XFS_DIR2_DATA_FD_COUNT); *loghead = 1; /* * Set up pointers. */ - p = (char *)dp->d_ops->data_entry_p(hdr); + p = (char *)ops->data_entry_p(hdr); if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) || hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) { btp = xfs_dir2_block_tail_p(geo, hdr); @@ -559,12 +559,22 @@ xfs_dir2_data_freescan( else { dep = (xfs_dir2_data_entry_t *)p; ASSERT((char *)dep - (char *)hdr == - be16_to_cpu(*dp->d_ops->data_entry_tag_p(dep))); - p += dp->d_ops->data_entsize(dep->namelen); + be16_to_cpu(*ops->data_entry_tag_p(dep))); + p += ops->data_entsize(dep->namelen); } } } +void +xfs_dir2_data_freescan( + struct xfs_inode *dp, + struct xfs_dir2_data_hdr *hdr, + int *loghead) +{ + return xfs_dir2_data_freescan_int(dp->i_mount->m_dir_geo, dp->d_ops, + hdr, loghead); +} + /* * Initialize a data block at the given block number in the directory. * Give back the buffer for the created block. diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h index ef9f6ead96a4..d04547fcf274 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -21,7 +21,6 @@ struct dir_context; /* xfs_dir2.c */ -extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino); extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space, xfs_dir2_db_t *dbp); extern int xfs_dir_cilookup_result(struct xfs_da_args *args, diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d45c03779dae..f272abff11e1 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -2344,7 +2344,8 @@ xfs_imap( imap->im_blkno = XFS_AGB_TO_DADDR(mp, agno, agbno); imap->im_len = XFS_FSB_TO_BB(mp, 1); - imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog); + imap->im_boffset = (unsigned short)(offset << + mp->m_sb.sb_inodelog); return 0; } @@ -2372,7 +2373,7 @@ out_map: imap->im_blkno = XFS_AGB_TO_DADDR(mp, agno, cluster_agbno); imap->im_len = XFS_FSB_TO_BB(mp, blks_per_cluster); - imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog); + imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog); /* * If the inode number maps to a block outside the bounds diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 9004665d679a..dd483e2767f7 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -383,7 +383,7 @@ xfs_log_dinode_to_disk( static bool xfs_dinode_verify( struct xfs_mount *mp, - struct xfs_inode *ip, + xfs_ino_t ino, struct xfs_dinode *dip) { uint16_t flags; @@ -409,7 +409,7 @@ xfs_dinode_verify( if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize, XFS_DINODE_CRC_OFF)) return false; - if (be64_to_cpu(dip->di_ino) != ip->i_ino) + if (be64_to_cpu(dip->di_ino) != ino) return false; if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_meta_uuid)) return false; @@ -501,7 +501,7 @@ xfs_iread( return error; /* even unallocated inodes are verified */ - if (!xfs_dinode_verify(mp, ip, dip)) { + if (!xfs_dinode_verify(mp, ip->i_ino, dip)) { xfs_alert(mp, "%s: validation failed for inode %lld failed", __func__, ip->i_ino); diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 3cfe12a4f58a..6848a0afbce7 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -58,8 +58,8 @@ struct xfs_icdinode { */ struct xfs_imap { xfs_daddr_t im_blkno; /* starting BB of inode chunk */ - ushort im_len; /* length in BBs of inode chunk */ - ushort im_boffset; /* inode offset in block in bytes */ + unsigned short im_len; /* length in BBs of inode chunk */ + unsigned short im_boffset; /* inode offset in block in bytes */ }; int xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *, diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 083cdd6d6c28..7ae571f8e34a 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -481,8 +481,8 @@ static inline uint xfs_log_dinode_size(int version) typedef struct xfs_buf_log_format { unsigned short blf_type; /* buf log item type indicator */ unsigned short blf_size; /* size of this item */ - ushort blf_flags; /* misc state */ - ushort blf_len; /* number of blocks in this buf */ + unsigned short blf_flags; /* misc state */ + unsigned short blf_len; /* number of blocks in this buf */ __int64_t blf_blkno; /* starting blkno of this buf */ unsigned int blf_map_size; /* used size of data bitmap in words */ unsigned int blf_data_map[XFS_BLF_DATAMAP_SIZE]; /* dirty bitmap */ diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 8e385f91d660..d9f65e2d5cc8 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -52,7 +52,7 @@ typedef struct xlog_recover { struct list_head r_itemq; /* q for items */ } xlog_recover_t; -#define ITEM_TYPE(i) (*(ushort *)(i)->ri_buf[0].i_addr) +#define ITEM_TYPE(i) (*(unsigned short *)(i)->ri_buf[0].i_addr) /* * This is the number of entries in the l_buf_cancel_table used during diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index e2e1106c9fad..ea45584a9913 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -1016,4 +1016,3 @@ xfs_rtfree_extent( } return 0; } - diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index a70aec910626..2580262e4ea0 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -262,6 +262,12 @@ xfs_mount_validate_sb( return -EFSCORRUPTED; } + if (xfs_sb_version_hascrc(&mp->m_sb) && + sbp->sb_blocksize < XFS_MIN_CRC_BLOCKSIZE) { + xfs_notice(mp, "v5 SB sanity check failed"); + return -EFSCORRUPTED; + } + /* * Until this is fixed only page-sized or smaller data blocks work. */ @@ -338,13 +344,16 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp) XFS_PQUOTA_CHKD : XFS_GQUOTA_CHKD; sbp->sb_qflags &= ~(XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD); - if (sbp->sb_qflags & XFS_PQUOTA_ACCT) { + if (sbp->sb_qflags & XFS_PQUOTA_ACCT && + sbp->sb_gquotino != NULLFSINO) { /* * In older version of superblock, on-disk superblock only * has sb_gquotino, and in-core superblock has both sb_gquotino * and sb_pquotino. But, only one of them is supported at any * point of time. So, if PQUOTA is set in disk superblock, - * copy over sb_gquotino to sb_pquotino. + * copy over sb_gquotino to sb_pquotino. The NULLFSINO test + * above is to make sure we don't do this twice and wipe them + * both out! */ sbp->sb_pquotino = sbp->sb_gquotino; sbp->sb_gquotino = NULLFSINO; diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index f9a1076de911..717909f2f7b7 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -74,11 +74,14 @@ typedef __int64_t xfs_sfiloff_t; /* signed block number in a file */ * Minimum and maximum blocksize and sectorsize. * The blocksize upper limit is pretty much arbitrary. * The sectorsize upper limit is due to sizeof(sb_sectsize). + * CRC enable filesystems use 512 byte inodes, meaning 512 byte block sizes + * cannot be used. */ #define XFS_MIN_BLOCKSIZE_LOG 9 /* i.e. 512 bytes */ #define XFS_MAX_BLOCKSIZE_LOG 16 /* i.e. 65536 bytes */ #define XFS_MIN_BLOCKSIZE (1 << XFS_MIN_BLOCKSIZE_LOG) #define XFS_MAX_BLOCKSIZE (1 << XFS_MAX_BLOCKSIZE_LOG) +#define XFS_MIN_CRC_BLOCKSIZE (1 << (XFS_MIN_BLOCKSIZE_LOG + 1)) #define XFS_MIN_SECTORSIZE_LOG 9 /* i.e. 512 bytes */ #define XFS_MAX_SECTORSIZE_LOG 15 /* i.e. 32768 bytes */ #define XFS_MIN_SECTORSIZE (1 << XFS_MIN_SECTORSIZE_LOG) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 4923b54da556..265000a09327 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -37,11 +37,6 @@ #include <linux/pagevec.h> #include <linux/writeback.h> -/* flags for direct write completions */ -#define XFS_DIO_FLAG_UNWRITTEN (1 << 0) -#define XFS_DIO_FLAG_APPEND (1 << 1) -#define XFS_DIO_FLAG_COW (1 << 2) - /* * structure owned by writepages passed to individual writepage calls */ @@ -1176,45 +1171,6 @@ xfs_vm_releasepage( } /* - * When we map a DIO buffer, we may need to pass flags to - * xfs_end_io_direct_write to tell it what kind of write IO we are doing. - * - * Note that for DIO, an IO to the highest supported file block offset (i.e. - * 2^63 - 1FSB bytes) will result in the offset + count overflowing a signed 64 - * bit variable. Hence if we see this overflow, we have to assume that the IO is - * extending the file size. We won't know for sure until IO completion is run - * and the actual max write offset is communicated to the IO completion - * routine. - */ -static void -xfs_map_direct( - struct inode *inode, - struct buffer_head *bh_result, - struct xfs_bmbt_irec *imap, - xfs_off_t offset, - bool is_cow) -{ - uintptr_t *flags = (uintptr_t *)&bh_result->b_private; - xfs_off_t size = bh_result->b_size; - - trace_xfs_get_blocks_map_direct(XFS_I(inode), offset, size, - ISUNWRITTEN(imap) ? XFS_IO_UNWRITTEN : is_cow ? XFS_IO_COW : - XFS_IO_OVERWRITE, imap); - - if (ISUNWRITTEN(imap)) { - *flags |= XFS_DIO_FLAG_UNWRITTEN; - set_buffer_defer_completion(bh_result); - } else if (is_cow) { - *flags |= XFS_DIO_FLAG_COW; - set_buffer_defer_completion(bh_result); - } - if (offset + size > i_size_read(inode) || offset + size < 0) { - *flags |= XFS_DIO_FLAG_APPEND; - set_buffer_defer_completion(bh_result); - } -} - -/* * If this is O_DIRECT or the mpage code calling tell them how large the mapping * is, so that we can avoid repeated get_blocks calls. * @@ -1254,52 +1210,12 @@ xfs_map_trim_size( bh_result->b_size = mapping_size; } -/* Bounce unaligned directio writes to the page cache. */ static int -xfs_bounce_unaligned_dio_write( - struct xfs_inode *ip, - xfs_fileoff_t offset_fsb, - struct xfs_bmbt_irec *imap) -{ - struct xfs_bmbt_irec irec; - xfs_fileoff_t delta; - bool shared; - bool x; - int error; - - irec = *imap; - if (offset_fsb > irec.br_startoff) { - delta = offset_fsb - irec.br_startoff; - irec.br_blockcount -= delta; - irec.br_startblock += delta; - irec.br_startoff = offset_fsb; - } - error = xfs_reflink_trim_around_shared(ip, &irec, &shared, &x); - if (error) - return error; - - /* - * We're here because we're trying to do a directio write to a - * region that isn't aligned to a filesystem block. If any part - * of the extent is shared, fall back to buffered mode to handle - * the RMW. This is done by returning -EREMCHG ("remote addr - * changed"), which is caught further up the call stack. - */ - if (shared) { - trace_xfs_reflink_bounce_dio_write(ip, imap); - return -EREMCHG; - } - return 0; -} - -STATIC int -__xfs_get_blocks( +xfs_get_blocks( struct inode *inode, sector_t iblock, struct buffer_head *bh_result, - int create, - bool direct, - bool dax_fault) + int create) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -1310,10 +1226,8 @@ __xfs_get_blocks( int nimaps = 1; xfs_off_t offset; ssize_t size; - int new = 0; - bool is_cow = false; - BUG_ON(create && !direct); + BUG_ON(create); if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; @@ -1322,7 +1236,7 @@ __xfs_get_blocks( ASSERT(bh_result->b_size >= (1 << inode->i_blkbits)); size = bh_result->b_size; - if (!create && offset >= i_size_read(inode)) + if (offset >= i_size_read(inode)) return 0; /* @@ -1337,73 +1251,12 @@ __xfs_get_blocks( end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size); offset_fsb = XFS_B_TO_FSBT(mp, offset); - if (create && direct && xfs_is_reflink_inode(ip)) { - is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap); - ASSERT(!is_cow || !isnullstartblock(imap.br_startblock)); - } - - if (!is_cow) { - error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, - &imap, &nimaps, XFS_BMAPI_ENTIRE); - /* - * Truncate an overwrite extent if there's a pending CoW - * reservation before the end of this extent. This - * forces us to come back to get_blocks to take care of - * the CoW. - */ - if (create && direct && nimaps && - imap.br_startblock != HOLESTARTBLOCK && - imap.br_startblock != DELAYSTARTBLOCK && - !ISUNWRITTEN(&imap)) - xfs_reflink_trim_irec_to_next_cow(ip, offset_fsb, - &imap); - } + error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, + &imap, &nimaps, XFS_BMAPI_ENTIRE); if (error) goto out_unlock; - /* - * The only time we can ever safely find delalloc blocks on direct I/O - * is a dio write to post-eof speculative preallocation. All other - * scenarios are indicative of a problem or misuse (such as mixing - * direct and mapped I/O). - * - * The file may be unmapped by the time we get here so we cannot - * reliably fail the I/O based on mapping. Instead, fail the I/O if this - * is a read or a write within eof. Otherwise, carry on but warn as a - * precuation if the file happens to be mapped. - */ - if (direct && imap.br_startblock == DELAYSTARTBLOCK) { - if (!create || offset < i_size_read(VFS_I(ip))) { - WARN_ON_ONCE(1); - error = -EIO; - goto out_unlock; - } - WARN_ON_ONCE(mapping_mapped(VFS_I(ip)->i_mapping)); - } - - /* for DAX, we convert unwritten extents directly */ - if (create && - (!nimaps || - (imap.br_startblock == HOLESTARTBLOCK || - imap.br_startblock == DELAYSTARTBLOCK) || - (IS_DAX(inode) && ISUNWRITTEN(&imap)))) { - /* - * xfs_iomap_write_direct() expects the shared lock. It - * is unlocked on return. - */ - if (lockmode == XFS_ILOCK_EXCL) - xfs_ilock_demote(ip, lockmode); - - error = xfs_iomap_write_direct(ip, offset, size, - &imap, nimaps); - if (error) - return error; - new = 1; - - trace_xfs_get_blocks_alloc(ip, offset, size, - ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN - : XFS_IO_DELALLOC, &imap); - } else if (nimaps) { + if (nimaps) { trace_xfs_get_blocks_found(ip, offset, size, ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, &imap); @@ -1413,12 +1266,6 @@ __xfs_get_blocks( goto out_unlock; } - if (IS_DAX(inode) && create) { - ASSERT(!ISUNWRITTEN(&imap)); - /* zeroing is not needed at a higher layer */ - new = 0; - } - /* trim mapping down to size requested */ xfs_map_trim_size(inode, iblock, bh_result, &imap, offset, size); @@ -1428,48 +1275,14 @@ __xfs_get_blocks( */ if (imap.br_startblock != HOLESTARTBLOCK && imap.br_startblock != DELAYSTARTBLOCK && - (create || !ISUNWRITTEN(&imap))) { - if (create && direct && !is_cow) { - error = xfs_bounce_unaligned_dio_write(ip, offset_fsb, - &imap); - if (error) - return error; - } - + !ISUNWRITTEN(&imap)) xfs_map_buffer(inode, bh_result, &imap, offset); - if (ISUNWRITTEN(&imap)) - set_buffer_unwritten(bh_result); - /* direct IO needs special help */ - if (create) { - if (dax_fault) - ASSERT(!ISUNWRITTEN(&imap)); - else - xfs_map_direct(inode, bh_result, &imap, offset, - is_cow); - } - } /* * If this is a realtime file, data may be on a different device. * to that pointed to from the buffer_head b_bdev currently. */ bh_result->b_bdev = xfs_find_bdev_for_inode(inode); - - /* - * If we previously allocated a block out beyond eof and we are now - * coming back to use it then we will need to flag it as new even if it - * has a disk address. - * - * With sub-block writes into unwritten extents we also need to mark - * the buffer as new so that the unwritten parts of the buffer gets - * correctly zeroed. - */ - if (create && - ((!buffer_mapped(bh_result) && !buffer_uptodate(bh_result)) || - (offset >= i_size_read(inode)) || - (new || ISUNWRITTEN(&imap)))) - set_buffer_new(bh_result); - return 0; out_unlock: @@ -1477,110 +1290,6 @@ out_unlock: return error; } -int -xfs_get_blocks( - struct inode *inode, - sector_t iblock, - struct buffer_head *bh_result, - int create) -{ - return __xfs_get_blocks(inode, iblock, bh_result, create, false, false); -} - -int -xfs_get_blocks_direct( - struct inode *inode, - sector_t iblock, - struct buffer_head *bh_result, - int create) -{ - return __xfs_get_blocks(inode, iblock, bh_result, create, true, false); -} - -int -xfs_get_blocks_dax_fault( - struct inode *inode, - sector_t iblock, - struct buffer_head *bh_result, - int create) -{ - return __xfs_get_blocks(inode, iblock, bh_result, create, true, true); -} - -/* - * Complete a direct I/O write request. - * - * xfs_map_direct passes us some flags in the private data to tell us what to - * do. If no flags are set, then the write IO is an overwrite wholly within - * the existing allocated file size and so there is nothing for us to do. - * - * Note that in this case the completion can be called in interrupt context, - * whereas if we have flags set we will always be called in task context - * (i.e. from a workqueue). - */ -int -xfs_end_io_direct_write( - struct kiocb *iocb, - loff_t offset, - ssize_t size, - void *private) -{ - struct inode *inode = file_inode(iocb->ki_filp); - struct xfs_inode *ip = XFS_I(inode); - uintptr_t flags = (uintptr_t)private; - int error = 0; - - trace_xfs_end_io_direct_write(ip, offset, size); - - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) - return -EIO; - - if (size <= 0) - return size; - - /* - * The flags tell us whether we are doing unwritten extent conversions - * or an append transaction that updates the on-disk file size. These - * cases are the only cases where we should *potentially* be needing - * to update the VFS inode size. - */ - if (flags == 0) { - ASSERT(offset + size <= i_size_read(inode)); - return 0; - } - - /* - * We need to update the in-core inode size here so that we don't end up - * with the on-disk inode size being outside the in-core inode size. We - * have no other method of updating EOF for AIO, so always do it here - * if necessary. - * - * We need to lock the test/set EOF update as we can be racing with - * other IO completions here to update the EOF. Failing to serialise - * here can result in EOF moving backwards and Bad Things Happen when - * that occurs. - */ - spin_lock(&ip->i_flags_lock); - if (offset + size > i_size_read(inode)) - i_size_write(inode, offset + size); - spin_unlock(&ip->i_flags_lock); - - if (flags & XFS_DIO_FLAG_COW) - error = xfs_reflink_end_cow(ip, offset, size); - if (flags & XFS_DIO_FLAG_UNWRITTEN) { - trace_xfs_end_io_direct_write_unwritten(ip, offset, size); - - error = xfs_iomap_write_unwritten(ip, offset, size); - } - if (flags & XFS_DIO_FLAG_APPEND) { - trace_xfs_end_io_direct_write_append(ip, offset, size); - - error = xfs_setfilesize(ip, offset, size); - } - - return error; -} - STATIC ssize_t xfs_vm_direct_IO( struct kiocb *iocb, @@ -1601,7 +1310,6 @@ xfs_vm_bmap( struct xfs_inode *ip = XFS_I(inode); trace_xfs_vm_bmap(XFS_I(inode)); - xfs_ilock(ip, XFS_IOLOCK_SHARED); /* * The swap code (ab-)uses ->bmap to get a block mapping and then @@ -1609,12 +1317,10 @@ xfs_vm_bmap( * that on reflinks inodes, so we have to skip out here. And yes, * 0 is the magic code for a bmap error.. */ - if (xfs_is_reflink_inode(ip)) { - xfs_iunlock(ip, XFS_IOLOCK_SHARED); + if (xfs_is_reflink_inode(ip)) return 0; - } + filemap_write_and_wait(mapping); - xfs_iunlock(ip, XFS_IOLOCK_SHARED); return generic_block_bmap(mapping, block, xfs_get_blocks); } diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index b3c6634f9518..cc174ec6c2fd 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -55,15 +55,6 @@ struct xfs_ioend { extern const struct address_space_operations xfs_address_space_operations; -int xfs_get_blocks(struct inode *inode, sector_t offset, - struct buffer_head *map_bh, int create); -int xfs_get_blocks_direct(struct inode *inode, sector_t offset, - struct buffer_head *map_bh, int create); -int xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset, - struct buffer_head *map_bh, int create); - -int xfs_end_io_direct_write(struct kiocb *iocb, loff_t offset, - ssize_t size, void *private); int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); extern void xfs_count_page_state(struct page *, int *, int *); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 0670a8bd5818..b9abce524c33 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1935,8 +1935,8 @@ xfs_swap_extents( * page cache safely. Once we have done this we can take the ilocks and * do the rest of the checks. */ - lock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; - xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL); + lock_two_nondirectories(VFS_I(ip), VFS_I(tip)); + lock_flags = XFS_MMAPLOCK_EXCL; xfs_lock_two_inodes(ip, tip, XFS_MMAPLOCK_EXCL); /* Verify that both files have the same format */ @@ -2076,15 +2076,13 @@ xfs_swap_extents( trace_xfs_swap_extent_after(ip, 0); trace_xfs_swap_extent_after(tip, 1); +out_unlock: xfs_iunlock(ip, lock_flags); xfs_iunlock(tip, lock_flags); + unlock_two_nondirectories(VFS_I(ip), VFS_I(tip)); return error; out_trans_cancel: xfs_trans_cancel(tp); - -out_unlock: - xfs_iunlock(ip, lock_flags); - xfs_iunlock(tip, lock_flags); - return error; + goto out_unlock; } diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 29816981b50a..003a99b83bd8 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -677,7 +677,6 @@ xfs_readdir( args.dp = dp; args.geo = dp->i_mount->m_dir_geo; - xfs_ilock(dp, XFS_IOLOCK_SHARED); if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) rval = xfs_dir2_sf_getdents(&args, ctx); else if ((rval = xfs_dir2_isblock(&args, &v))) @@ -686,7 +685,6 @@ xfs_readdir( rval = xfs_dir2_block_getdents(&args, ctx); else rval = xfs_dir2_leaf_getdents(&args, ctx, bufsize); - xfs_iunlock(dp, XFS_IOLOCK_SHARED); return rval; } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 9a5d64b5f35a..b837ad8a63e4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -48,40 +48,6 @@ static const struct vm_operations_struct xfs_file_vm_ops; /* - * Locking primitives for read and write IO paths to ensure we consistently use - * and order the inode->i_mutex, ip->i_lock and ip->i_iolock. - */ -static inline void -xfs_rw_ilock( - struct xfs_inode *ip, - int type) -{ - if (type & XFS_IOLOCK_EXCL) - inode_lock(VFS_I(ip)); - xfs_ilock(ip, type); -} - -static inline void -xfs_rw_iunlock( - struct xfs_inode *ip, - int type) -{ - xfs_iunlock(ip, type); - if (type & XFS_IOLOCK_EXCL) - inode_unlock(VFS_I(ip)); -} - -static inline void -xfs_rw_ilock_demote( - struct xfs_inode *ip, - int type) -{ - xfs_ilock_demote(ip, type); - if (type & XFS_IOLOCK_EXCL) - inode_unlock(VFS_I(ip)); -} - -/* * Clear the specified ranges to zero through either the pagecache or DAX. * Holes and unwritten extents will be left as-is as they already are zeroed. */ @@ -244,62 +210,21 @@ xfs_file_dio_aio_read( struct kiocb *iocb, struct iov_iter *to) { - struct address_space *mapping = iocb->ki_filp->f_mapping; - struct inode *inode = mapping->host; - struct xfs_inode *ip = XFS_I(inode); - loff_t isize = i_size_read(inode); + struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); size_t count = iov_iter_count(to); - loff_t end = iocb->ki_pos + count - 1; - struct iov_iter data; - struct xfs_buftarg *target; - ssize_t ret = 0; + ssize_t ret; trace_xfs_file_direct_read(ip, count, iocb->ki_pos); if (!count) return 0; /* skip atime */ - if (XFS_IS_REALTIME_INODE(ip)) - target = ip->i_mount->m_rtdev_targp; - else - target = ip->i_mount->m_ddev_targp; - - /* DIO must be aligned to device logical sector size */ - if ((iocb->ki_pos | count) & target->bt_logical_sectormask) { - if (iocb->ki_pos == isize) - return 0; - return -EINVAL; - } - file_accessed(iocb->ki_filp); - xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); - if (mapping->nrpages) { - ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); - if (ret) - goto out_unlock; - - /* - * Invalidate whole pages. This can return an error if we fail - * to invalidate a page, but this should never happen on XFS. - * Warn if it does fail. - */ - ret = invalidate_inode_pages2_range(mapping, - iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(ret); - ret = 0; - } - - data = *to; - ret = __blockdev_direct_IO(iocb, inode, target->bt_bdev, &data, - xfs_get_blocks_direct, NULL, NULL, 0); - if (ret >= 0) { - iocb->ki_pos += ret; - iov_iter_advance(to, ret); - } + xfs_ilock(ip, XFS_IOLOCK_SHARED); + ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL); + xfs_iunlock(ip, XFS_IOLOCK_SHARED); -out_unlock: - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); return ret; } @@ -317,9 +242,9 @@ xfs_file_dax_read( if (!count) return 0; /* skip atime */ - xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); - ret = iomap_dax_rw(iocb, to, &xfs_iomap_ops); - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); + xfs_ilock(ip, XFS_IOLOCK_SHARED); + ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops); + xfs_iunlock(ip, XFS_IOLOCK_SHARED); file_accessed(iocb->ki_filp); return ret; @@ -335,9 +260,9 @@ xfs_file_buffered_aio_read( trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos); - xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); + xfs_ilock(ip, XFS_IOLOCK_SHARED); ret = generic_file_read_iter(iocb, to); - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); + xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; } @@ -418,15 +343,18 @@ restart: if (error <= 0) return error; - error = xfs_break_layouts(inode, iolock, true); + error = xfs_break_layouts(inode, iolock); if (error) return error; - /* For changing security info in file_remove_privs() we need i_mutex */ + /* + * For changing security info in file_remove_privs() we need i_rwsem + * exclusively. + */ if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) { - xfs_rw_iunlock(ip, *iolock); + xfs_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, *iolock); + xfs_ilock(ip, *iolock); goto restart; } /* @@ -451,9 +379,9 @@ restart: spin_unlock(&ip->i_flags_lock); if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { - xfs_rw_iunlock(ip, *iolock); + xfs_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, *iolock); + xfs_ilock(ip, *iolock); iov_iter_reexpand(from, count); } /* @@ -496,6 +424,58 @@ restart: return 0; } +static int +xfs_dio_write_end_io( + struct kiocb *iocb, + ssize_t size, + unsigned flags) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct xfs_inode *ip = XFS_I(inode); + loff_t offset = iocb->ki_pos; + bool update_size = false; + int error = 0; + + trace_xfs_end_io_direct_write(ip, offset, size); + + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + return -EIO; + + if (size <= 0) + return size; + + /* + * We need to update the in-core inode size here so that we don't end up + * with the on-disk inode size being outside the in-core inode size. We + * have no other method of updating EOF for AIO, so always do it here + * if necessary. + * + * We need to lock the test/set EOF update as we can be racing with + * other IO completions here to update the EOF. Failing to serialise + * here can result in EOF moving backwards and Bad Things Happen when + * that occurs. + */ + spin_lock(&ip->i_flags_lock); + if (offset + size > i_size_read(inode)) { + i_size_write(inode, offset + size); + update_size = true; + } + spin_unlock(&ip->i_flags_lock); + + if (flags & IOMAP_DIO_COW) { + error = xfs_reflink_end_cow(ip, offset, size); + if (error) + return error; + } + + if (flags & IOMAP_DIO_UNWRITTEN) + error = xfs_iomap_write_unwritten(ip, offset, size); + else if (update_size) + error = xfs_setfilesize(ip, offset, size); + + return error; +} + /* * xfs_file_dio_aio_write - handle direct IO writes * @@ -535,9 +515,7 @@ xfs_file_dio_aio_write( int unaligned_io = 0; int iolock; size_t count = iov_iter_count(from); - loff_t end; - struct iov_iter data; - struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? + struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; /* DIO must be aligned to device logical sector size */ @@ -559,29 +537,12 @@ xfs_file_dio_aio_write( iolock = XFS_IOLOCK_SHARED; } - xfs_rw_ilock(ip, iolock); + xfs_ilock(ip, iolock); ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; count = iov_iter_count(from); - end = iocb->ki_pos + count - 1; - - if (mapping->nrpages) { - ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); - if (ret) - goto out; - - /* - * Invalidate whole pages. This can return an error if we fail - * to invalidate a page, but this should never happen on XFS. - * Warn if it does fail. - */ - ret = invalidate_inode_pages2_range(mapping, - iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(ret); - ret = 0; - } /* * If we are doing unaligned IO, wait for all other IO to drain, @@ -591,7 +552,7 @@ xfs_file_dio_aio_write( if (unaligned_io) inode_dio_wait(inode); else if (iolock == XFS_IOLOCK_EXCL) { - xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); + xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; } @@ -604,24 +565,9 @@ xfs_file_dio_aio_write( goto out; } - data = *from; - ret = __blockdev_direct_IO(iocb, inode, target->bt_bdev, &data, - xfs_get_blocks_direct, xfs_end_io_direct_write, - NULL, DIO_ASYNC_EXTEND); - - /* see generic_file_direct_write() for why this is necessary */ - if (mapping->nrpages) { - invalidate_inode_pages2_range(mapping, - iocb->ki_pos >> PAGE_SHIFT, - end >> PAGE_SHIFT); - } - - if (ret > 0) { - iocb->ki_pos += ret; - iov_iter_advance(from, ret); - } + ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io); out: - xfs_rw_iunlock(ip, iolock); + xfs_iunlock(ip, iolock); /* * No fallback to buffered IO on errors for XFS, direct IO will either @@ -643,7 +589,7 @@ xfs_file_dax_write( size_t count; loff_t pos; - xfs_rw_ilock(ip, iolock); + xfs_ilock(ip, iolock); ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; @@ -652,15 +598,13 @@ xfs_file_dax_write( count = iov_iter_count(from); trace_xfs_file_dax_write(ip, count, pos); - - ret = iomap_dax_rw(iocb, from, &xfs_iomap_ops); + ret = dax_iomap_rw(iocb, from, &xfs_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); error = xfs_setfilesize(ip, pos, ret); } - out: - xfs_rw_iunlock(ip, iolock); + xfs_iunlock(ip, iolock); return error ? error : ret; } @@ -677,7 +621,7 @@ xfs_file_buffered_aio_write( int enospc = 0; int iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, iolock); + xfs_ilock(ip, iolock); ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) @@ -721,7 +665,7 @@ write_retry: current->backing_dev_info = NULL; out: - xfs_rw_iunlock(ip, iolock); + xfs_iunlock(ip, iolock); return ret; } @@ -797,7 +741,7 @@ xfs_file_fallocate( return -EOPNOTSUPP; xfs_ilock(ip, iolock); - error = xfs_break_layouts(inode, &iolock, false); + error = xfs_break_layouts(inode, &iolock); if (error) goto out_unlock; @@ -1465,7 +1409,7 @@ xfs_filemap_page_mkwrite( xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); if (IS_DAX(inode)) { - ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops); + ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops); } else { ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops); ret = block_page_mkwrite_return(ret); @@ -1492,15 +1436,9 @@ xfs_filemap_fault( return xfs_filemap_page_mkwrite(vma, vmf); xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - if (IS_DAX(inode)) { - /* - * we do not want to trigger unwritten extent conversion on read - * faults - that is unnecessary overhead and would also require - * changes to xfs_get_blocks_direct() to map unwritten extent - * ioend for conversion on read-only mappings. - */ - ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops); - } else + if (IS_DAX(inode)) + ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops); + else ret = filemap_fault(vma, vmf); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); @@ -1536,7 +1474,7 @@ xfs_filemap_pmd_fault( } xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault); + ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); if (flags & FAULT_FLAG_WRITE) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 9c3e5c6ddf20..ff4d6311c7f4 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -70,8 +70,6 @@ xfs_inode_alloc( ASSERT(!xfs_isiflocked(ip)); ASSERT(ip->i_ino == 0); - mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino); - /* initialise the xfs inode */ ip->i_ino = ino; ip->i_mount = mp; @@ -394,8 +392,8 @@ xfs_iget_cache_hit( xfs_inode_clear_reclaim_tag(pag, ip->i_ino); inode->i_state = I_NEW; - ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock)); - mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino); + ASSERT(!rwsem_is_locked(&inode->i_rwsem)); + init_rwsem(&inode->i_rwsem); spin_unlock(&ip->i_flags_lock); spin_unlock(&pag->pag_ici_lock); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 512ff13ed66a..b9557795eb74 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -142,31 +142,31 @@ xfs_ilock_attr_map_shared( } /* - * The xfs inode contains 3 multi-reader locks: the i_iolock the i_mmap_lock and - * the i_lock. This routine allows various combinations of the locks to be - * obtained. + * In addition to i_rwsem in the VFS inode, the xfs inode contains 2 + * multi-reader locks: i_mmap_lock and the i_lock. This routine allows + * various combinations of the locks to be obtained. * * The 3 locks should always be ordered so that the IO lock is obtained first, * the mmap lock second and the ilock last in order to prevent deadlock. * * Basic locking order: * - * i_iolock -> i_mmap_lock -> page_lock -> i_ilock + * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock * * mmap_sem locking order: * - * i_iolock -> page lock -> mmap_sem + * i_rwsem -> page lock -> mmap_sem * mmap_sem -> i_mmap_lock -> page_lock * * The difference in mmap_sem locking order mean that we cannot hold the * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can * fault in pages during copy in/out (for buffered IO) or require the mmap_sem * in get_user_pages() to map the user pages into the kernel address space for - * direct IO. Similarly the i_iolock cannot be taken inside a page fault because + * direct IO. Similarly the i_rwsem cannot be taken inside a page fault because * page faults already hold the mmap_sem. * * Hence to serialise fully against both syscall and mmap based IO, we need to - * take both the i_iolock and the i_mmap_lock. These locks should *only* be both + * take both the i_rwsem and the i_mmap_lock. These locks should *only* be both * taken in places where we need to invalidate the page cache in a race * free manner (e.g. truncate, hole punch and other extent manipulation * functions). @@ -191,10 +191,13 @@ xfs_ilock( (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); - if (lock_flags & XFS_IOLOCK_EXCL) - mrupdate_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags)); - else if (lock_flags & XFS_IOLOCK_SHARED) - mraccess_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags)); + if (lock_flags & XFS_IOLOCK_EXCL) { + down_write_nested(&VFS_I(ip)->i_rwsem, + XFS_IOLOCK_DEP(lock_flags)); + } else if (lock_flags & XFS_IOLOCK_SHARED) { + down_read_nested(&VFS_I(ip)->i_rwsem, + XFS_IOLOCK_DEP(lock_flags)); + } if (lock_flags & XFS_MMAPLOCK_EXCL) mrupdate_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags)); @@ -240,10 +243,10 @@ xfs_ilock_nowait( ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); if (lock_flags & XFS_IOLOCK_EXCL) { - if (!mrtryupdate(&ip->i_iolock)) + if (!down_write_trylock(&VFS_I(ip)->i_rwsem)) goto out; } else if (lock_flags & XFS_IOLOCK_SHARED) { - if (!mrtryaccess(&ip->i_iolock)) + if (!down_read_trylock(&VFS_I(ip)->i_rwsem)) goto out; } @@ -271,9 +274,9 @@ out_undo_mmaplock: mrunlock_shared(&ip->i_mmaplock); out_undo_iolock: if (lock_flags & XFS_IOLOCK_EXCL) - mrunlock_excl(&ip->i_iolock); + up_write(&VFS_I(ip)->i_rwsem); else if (lock_flags & XFS_IOLOCK_SHARED) - mrunlock_shared(&ip->i_iolock); + up_read(&VFS_I(ip)->i_rwsem); out: return 0; } @@ -310,9 +313,9 @@ xfs_iunlock( ASSERT(lock_flags != 0); if (lock_flags & XFS_IOLOCK_EXCL) - mrunlock_excl(&ip->i_iolock); + up_write(&VFS_I(ip)->i_rwsem); else if (lock_flags & XFS_IOLOCK_SHARED) - mrunlock_shared(&ip->i_iolock); + up_read(&VFS_I(ip)->i_rwsem); if (lock_flags & XFS_MMAPLOCK_EXCL) mrunlock_excl(&ip->i_mmaplock); @@ -345,7 +348,7 @@ xfs_ilock_demote( if (lock_flags & XFS_MMAPLOCK_EXCL) mrdemote(&ip->i_mmaplock); if (lock_flags & XFS_IOLOCK_EXCL) - mrdemote(&ip->i_iolock); + downgrade_write(&VFS_I(ip)->i_rwsem); trace_xfs_ilock_demote(ip, lock_flags, _RET_IP_); } @@ -370,8 +373,9 @@ xfs_isilocked( if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) { if (!(lock_flags & XFS_IOLOCK_SHARED)) - return !!ip->i_iolock.mr_writer; - return rwsem_is_locked(&ip->i_iolock.mr_lock); + return !debug_locks || + lockdep_is_held_type(&VFS_I(ip)->i_rwsem, 0); + return rwsem_is_locked(&VFS_I(ip)->i_rwsem); } ASSERT(0); @@ -421,11 +425,7 @@ xfs_lock_inumorder(int lock_mode, int subclass) if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) { ASSERT(subclass <= XFS_IOLOCK_MAX_SUBCLASS); - ASSERT(xfs_lockdep_subclass_ok(subclass + - XFS_IOLOCK_PARENT_VAL)); class += subclass << XFS_IOLOCK_SHIFT; - if (lock_mode & XFS_IOLOCK_PARENT) - class += XFS_IOLOCK_PARENT_VAL << XFS_IOLOCK_SHIFT; } if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) { @@ -477,8 +477,6 @@ xfs_lock_inodes( XFS_ILOCK_EXCL)); ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED | XFS_MMAPLOCK_SHARED | XFS_ILOCK_SHARED))); - ASSERT(!(lock_mode & XFS_IOLOCK_EXCL) || - inodes <= XFS_IOLOCK_MAX_SUBCLASS + 1); ASSERT(!(lock_mode & XFS_MMAPLOCK_EXCL) || inodes <= XFS_MMAPLOCK_MAX_SUBCLASS + 1); ASSERT(!(lock_mode & XFS_ILOCK_EXCL) || @@ -581,10 +579,8 @@ xfs_lock_two_inodes( int attempts = 0; xfs_log_item_t *lp; - if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) { - ASSERT(!(lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL))); - ASSERT(!(lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))); - } else if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) + ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))); + if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ASSERT(!(lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))); ASSERT(ip0->i_ino != ip1->i_ino); @@ -715,7 +711,6 @@ xfs_lookup( if (XFS_FORCED_SHUTDOWN(dp->i_mount)) return -EIO; - xfs_ilock(dp, XFS_IOLOCK_SHARED); error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name); if (error) goto out_unlock; @@ -724,14 +719,12 @@ xfs_lookup( if (error) goto out_free_name; - xfs_iunlock(dp, XFS_IOLOCK_SHARED); return 0; out_free_name: if (ci_name) kmem_free(ci_name->name); out_unlock: - xfs_iunlock(dp, XFS_IOLOCK_SHARED); *ipp = NULL; return error; } @@ -1215,8 +1208,7 @@ xfs_create( if (error) goto out_release_inode; - xfs_ilock(dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL | - XFS_IOLOCK_PARENT | XFS_ILOCK_PARENT); + xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = true; xfs_defer_init(&dfops, &first_block); @@ -1252,7 +1244,7 @@ xfs_create( * the transaction cancel unlocking dp so don't do it explicitly in the * error path. */ - xfs_trans_ijoin(tp, dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL); unlock_dp_on_error = false; error = xfs_dir_createname(tp, dp, name, ip->i_ino, @@ -1325,7 +1317,7 @@ xfs_create( xfs_qm_dqrele(pdqp); if (unlock_dp_on_error) - xfs_iunlock(dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + xfs_iunlock(dp, XFS_ILOCK_EXCL); return error; } @@ -1466,11 +1458,10 @@ xfs_link( if (error) goto std_return; - xfs_ilock(tdp, XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT); xfs_lock_two_inodes(sip, tdp, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, tdp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL); /* * If we are using project inheritance, we only allow hard link @@ -2577,10 +2568,9 @@ xfs_remove( goto std_return; } - xfs_ilock(dp, XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT); xfs_lock_two_inodes(dp, ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); /* @@ -2961,12 +2951,6 @@ xfs_rename( * whether the target directory is the same as the source * directory, we can lock from 2 to 4 inodes. */ - if (!new_parent) - xfs_ilock(src_dp, XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT); - else - xfs_lock_two_inodes(src_dp, target_dp, - XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT); - xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL); /* @@ -2974,9 +2958,9 @@ xfs_rename( * we can rely on either trans_commit or trans_cancel to unlock * them. */ - xfs_trans_ijoin(tp, src_dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, src_dp, XFS_ILOCK_EXCL); if (new_parent) - xfs_trans_ijoin(tp, target_dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, target_dp, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, src_ip, XFS_ILOCK_EXCL); if (target_ip) xfs_trans_ijoin(tp, target_ip, XFS_ILOCK_EXCL); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 71e8a81c91a3..10dcf27b4c85 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -56,7 +56,6 @@ typedef struct xfs_inode { /* Transaction and locking information. */ struct xfs_inode_log_item *i_itemp; /* logging information */ mrlock_t i_lock; /* inode lock */ - mrlock_t i_iolock; /* inode IO lock */ mrlock_t i_mmaplock; /* inode mmap IO lock */ atomic_t i_pincount; /* inode pin count */ spinlock_t i_flags_lock; /* inode i_flags lock */ @@ -333,7 +332,7 @@ static inline void xfs_ifunlock(struct xfs_inode *ip) * IOLOCK values * * 0-3 subclass value - * 4-7 PARENT subclass values + * 4-7 unused * * MMAPLOCK values * @@ -348,10 +347,8 @@ static inline void xfs_ifunlock(struct xfs_inode *ip) * */ #define XFS_IOLOCK_SHIFT 16 -#define XFS_IOLOCK_PARENT_VAL 4 -#define XFS_IOLOCK_MAX_SUBCLASS (XFS_IOLOCK_PARENT_VAL - 1) +#define XFS_IOLOCK_MAX_SUBCLASS 3 #define XFS_IOLOCK_DEP_MASK 0x000f0000 -#define XFS_IOLOCK_PARENT (XFS_IOLOCK_PARENT_VAL << XFS_IOLOCK_SHIFT) #define XFS_MMAPLOCK_SHIFT 20 #define XFS_MMAPLOCK_NUMORDER 0 diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a39197501a7c..fc563b82aea6 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -639,7 +639,7 @@ xfs_ioc_space( return error; xfs_ilock(ip, iolock); - error = xfs_break_layouts(inode, &iolock, false); + error = xfs_break_layouts(inode, &iolock); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 15a83813b708..0d147428971e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -950,6 +950,19 @@ static inline bool imap_needs_alloc(struct inode *inode, (IS_DAX(inode) && ISUNWRITTEN(imap)); } +static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags) +{ + /* + * COW writes will allocate delalloc space, so we need to make sure + * to take the lock exclusively here. + */ + if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) + return true; + if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE)) + return true; + return false; +} + static int xfs_file_iomap_begin( struct inode *inode, @@ -969,18 +982,14 @@ xfs_file_iomap_begin( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - if ((flags & IOMAP_WRITE) && !IS_DAX(inode) && - !xfs_get_extsz_hint(ip)) { + if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) && + !IS_DAX(inode) && !xfs_get_extsz_hint(ip)) { /* Reserve delalloc blocks for regular writeback. */ return xfs_file_iomap_begin_delay(inode, offset, length, flags, iomap); } - /* - * COW writes will allocate delalloc space, so we need to make sure - * to take the lock exclusively here. - */ - if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + if (need_excl_ilock(ip, flags)) { lockmode = XFS_ILOCK_EXCL; xfs_ilock(ip, XFS_ILOCK_EXCL); } else { @@ -993,17 +1002,41 @@ xfs_file_iomap_begin( offset_fsb = XFS_B_TO_FSBT(mp, offset); end_fsb = XFS_B_TO_FSB(mp, offset + length); + if (xfs_is_reflink_inode(ip) && + (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT)) { + shared = xfs_reflink_find_cow_mapping(ip, offset, &imap); + if (shared) { + xfs_iunlock(ip, lockmode); + goto alloc_done; + } + ASSERT(!isnullstartblock(imap.br_startblock)); + } + error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, 0); if (error) goto out_unlock; - if (flags & IOMAP_REPORT) { + if ((flags & IOMAP_REPORT) || + (xfs_is_reflink_inode(ip) && + (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))) { /* Trim the mapping to the nearest shared extent boundary. */ error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); if (error) goto out_unlock; + + /* + * We're here because we're trying to do a directio write to a + * region that isn't aligned to a filesystem block. If the + * extent is shared, fall back to buffered mode to handle the + * RMW. + */ + if (!(flags & IOMAP_REPORT) && shared) { + trace_xfs_reflink_bounce_dio_write(ip, &imap); + error = -EREMCHG; + goto out_unlock; + } } if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { @@ -1038,6 +1071,7 @@ xfs_file_iomap_begin( if (error) return error; +alloc_done: iomap->flags = IOMAP_F_NEW; trace_xfs_iomap_alloc(ip, offset, length, 0, &imap); } else { diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 405a65cd9d6b..c962999a87ab 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -983,15 +983,13 @@ xfs_vn_setattr( struct xfs_inode *ip = XFS_I(d_inode(dentry)); uint iolock = XFS_IOLOCK_EXCL; - xfs_ilock(ip, iolock); - error = xfs_break_layouts(d_inode(dentry), &iolock, true); - if (!error) { - xfs_ilock(ip, XFS_MMAPLOCK_EXCL); - iolock |= XFS_MMAPLOCK_EXCL; + error = xfs_break_layouts(d_inode(dentry), &iolock); + if (error) + return error; - error = xfs_vn_setattr_size(dentry, iattr); - } - xfs_iunlock(ip, iolock); + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); + error = xfs_setattr_size(ip, iattr); + xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); } else { error = xfs_vn_setattr_nonsize(dentry, iattr); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 56b7a2f6aaf2..4a98762ec8b4 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2025,7 +2025,7 @@ xlog_peek_buffer_cancelled( struct xlog *log, xfs_daddr_t blkno, uint len, - ushort flags) + unsigned short flags) { struct list_head *bucket; struct xfs_buf_cancel *bcp; @@ -2065,7 +2065,7 @@ xlog_check_buffer_cancelled( struct xlog *log, xfs_daddr_t blkno, uint len, - ushort flags) + unsigned short flags) { struct xfs_buf_cancel *bcp; diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 93a7aafa56d6..2f2dc3c09ad0 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -32,8 +32,7 @@ int xfs_break_layouts( struct inode *inode, - uint *iolock, - bool with_imutex) + uint *iolock) { struct xfs_inode *ip = XFS_I(inode); int error; @@ -42,12 +41,8 @@ xfs_break_layouts( while ((error = break_layout(inode, false) == -EWOULDBLOCK)) { xfs_iunlock(ip, *iolock); - if (with_imutex && (*iolock & XFS_IOLOCK_EXCL)) - inode_unlock(inode); error = break_layout(inode, true); *iolock = XFS_IOLOCK_EXCL; - if (with_imutex) - inode_lock(inode); xfs_ilock(ip, *iolock); } diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h index e8339f74966b..b587cb99b2b7 100644 --- a/fs/xfs/xfs_pnfs.h +++ b/fs/xfs/xfs_pnfs.h @@ -8,10 +8,10 @@ int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length, int xfs_fs_commit_blocks(struct inode *inode, struct iomap *maps, int nr_maps, struct iattr *iattr); -int xfs_break_layouts(struct inode *inode, uint *iolock, bool with_imutex); +int xfs_break_layouts(struct inode *inode, uint *iolock); #else static inline int -xfs_break_layouts(struct inode *inode, uint *iolock, bool with_imutex) +xfs_break_layouts(struct inode *inode, uint *iolock) { return 0; } diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index becf2465dd23..88fd03c66e99 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1251,13 +1251,11 @@ xfs_reflink_remap_range( return -EIO; /* Lock both files against IO */ - if (same_inode) { - xfs_ilock(src, XFS_IOLOCK_EXCL); + lock_two_nondirectories(inode_in, inode_out); + if (same_inode) xfs_ilock(src, XFS_MMAPLOCK_EXCL); - } else { - xfs_lock_two_inodes(src, dest, XFS_IOLOCK_EXCL); + else xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL); - } /* Don't touch certain kinds of inodes */ ret = -EPERM; @@ -1402,11 +1400,9 @@ xfs_reflink_remap_range( out_unlock: xfs_iunlock(src, XFS_MMAPLOCK_EXCL); - xfs_iunlock(src, XFS_IOLOCK_EXCL); - if (src->i_ino != dest->i_ino) { + if (!same_inode) xfs_iunlock(dest, XFS_MMAPLOCK_EXCL); - xfs_iunlock(dest, XFS_IOLOCK_EXCL); - } + unlock_two_nondirectories(inode_in, inode_out); if (ret) trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); return ret; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index ade4691e3f74..563d1d146b8c 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -943,7 +943,7 @@ xfs_fs_destroy_inode( trace_xfs_destroy_inode(ip); - ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock)); + ASSERT(!rwsem_is_locked(&inode->i_rwsem)); XFS_STATS_INC(ip->i_mount, vn_rele); XFS_STATS_INC(ip->i_mount, vn_remove); diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 58142aeeeea6..f2cb45ed1d54 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -238,8 +238,7 @@ xfs_symlink( if (error) goto out_release_inode; - xfs_ilock(dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL | - XFS_IOLOCK_PARENT | XFS_ILOCK_PARENT); + xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = true; /* @@ -287,7 +286,7 @@ xfs_symlink( * the transaction cancel unlocking dp so don't do it explicitly in the * error path. */ - xfs_trans_ijoin(tp, dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL); unlock_dp_on_error = false; /* @@ -412,7 +411,7 @@ out_release_inode: xfs_qm_dqrele(pdqp); if (unlock_dp_on_error) - xfs_iunlock(dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + xfs_iunlock(dp, XFS_ILOCK_EXCL); return error; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 97cb48f03dc7..66228c28c621 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -430,6 +430,7 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, const struct iov_iter *, gfp_t); diff --git a/include/linux/dax.h b/include/linux/dax.h index add6c4bc568f..8d1a5c47945f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -8,21 +8,46 @@ struct iomap_ops; -/* We use lowest available exceptional entry bit for locking */ +/* + * We use lowest available bit in exceptional entry for locking, one bit for + * the entry size (PMD) and two more to tell us if the entry is a huge zero + * page (HZP) or an empty entry that is just used for locking. In total four + * special bits. + * + * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and + * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem + * block allocation. + */ +#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) #define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) +#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) +#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) +#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) -ssize_t iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter, +static inline unsigned long dax_radix_sector(void *entry) +{ + return (unsigned long)entry >> RADIX_DAX_SHIFT; +} + +static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags) +{ + return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | + ((unsigned long)sector << RADIX_DAX_SHIFT) | + RADIX_DAX_ENTRY_LOCK); +} + +ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops); ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, get_block_t, dio_iodone_t, int flags); int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); -int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, +int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, struct iomap_ops *ops); int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); void dax_wake_mapping_entry_waiter(struct address_space *mapping, - pgoff_t index, bool wake_all); + pgoff_t index, void *entry, bool wake_all); #ifdef CONFIG_FS_DAX struct page *read_dax_sector(struct block_device *bdev, sector_t n); @@ -48,15 +73,32 @@ static inline int __dax_zero_page_range(struct block_device *bdev, } #endif -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) -int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, - unsigned int flags, get_block_t); -#else static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, get_block_t gb) { return VM_FAULT_FALLBACK; } + +#ifdef CONFIG_FS_DAX_PMD +static inline unsigned int dax_radix_order(void *entry) +{ + if ((unsigned long)entry & RADIX_DAX_PMD) + return PMD_SHIFT - PAGE_SHIFT; + return 0; +} +int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, unsigned int flags, struct iomap_ops *ops); +#else +static inline unsigned int dax_radix_order(void *entry) +{ + return 0; +} +static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, unsigned int flags, + struct iomap_ops *ops) +{ + return VM_FAULT_FALLBACK; +} #endif int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); #define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 7892f55a1866..a4c94b86401e 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -49,6 +49,8 @@ struct iomap { #define IOMAP_WRITE (1 << 0) /* writing, must allocate blocks */ #define IOMAP_ZERO (1 << 1) /* zeroing operation, may skip holes */ #define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */ +#define IOMAP_FAULT (1 << 3) /* mapping for page fault */ +#define IOMAP_DIRECT (1 << 4) /* direct I/O */ struct iomap_ops { /* @@ -82,4 +84,14 @@ int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, struct iomap_ops *ops); +/* + * Flags for direct I/O ->end_io: + */ +#define IOMAP_DIO_UNWRITTEN (1 << 0) /* covers unwritten extent(s) */ +#define IOMAP_DIO_COW (1 << 1) /* covers COW extent(s) */ +typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t ret, + unsigned flags); +ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, + struct iomap_ops *ops, iomap_dio_end_io_t end_io); + #endif /* LINUX_IOMAP_H */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index c1458fede1f9..1e327bb80838 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -338,9 +338,18 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, extern void lock_release(struct lockdep_map *lock, int nested, unsigned long ip); -#define lockdep_is_held(lock) lock_is_held(&(lock)->dep_map) +/* + * Same "read" as for lock_acquire(), except -1 means any. + */ +extern int lock_is_held_type(struct lockdep_map *lock, int read); + +static inline int lock_is_held(struct lockdep_map *lock) +{ + return lock_is_held_type(lock, -1); +} -extern int lock_is_held(struct lockdep_map *lock); +#define lockdep_is_held(lock) lock_is_held(&(lock)->dep_map) +#define lockdep_is_held_type(lock, r) lock_is_held_type(&(lock)->dep_map, (r)) extern void lock_set_class(struct lockdep_map *lock, const char *name, struct lock_class_key *key, unsigned int subclass, @@ -372,6 +381,14 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); WARN_ON(debug_locks && !lockdep_is_held(l)); \ } while (0) +#define lockdep_assert_held_exclusive(l) do { \ + WARN_ON(debug_locks && !lockdep_is_held_type(l, 0)); \ + } while (0) + +#define lockdep_assert_held_read(l) do { \ + WARN_ON(debug_locks && !lockdep_is_held_type(l, 1)); \ + } while (0) + #define lockdep_assert_held_once(l) do { \ WARN_ON_ONCE(debug_locks && !lockdep_is_held(l)); \ } while (0) @@ -428,7 +445,11 @@ struct lock_class_key { }; #define lockdep_depth(tsk) (0) +#define lockdep_is_held_type(l, r) (1) + #define lockdep_assert_held(l) do { (void)(l); } while (0) +#define lockdep_assert_held_exclusive(l) do { (void)(l); } while (0) +#define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) #define lockdep_recursing(tsk) (0) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 589d763a49b3..cff580a6edf9 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3188,7 +3188,7 @@ print_lock_nested_lock_not_held(struct task_struct *curr, return 0; } -static int __lock_is_held(struct lockdep_map *lock); +static int __lock_is_held(struct lockdep_map *lock, int read); /* * This gets called for every mutex_lock*()/spin_lock*() operation. @@ -3329,7 +3329,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, } chain_key = iterate_chain_key(chain_key, class_idx); - if (nest_lock && !__lock_is_held(nest_lock)) + if (nest_lock && !__lock_is_held(nest_lock, -1)) return print_lock_nested_lock_not_held(curr, hlock, ip); if (!validate_chain(curr, lock, hlock, chain_head, chain_key)) @@ -3576,7 +3576,7 @@ found_it: return 1; } -static int __lock_is_held(struct lockdep_map *lock) +static int __lock_is_held(struct lockdep_map *lock, int read) { struct task_struct *curr = current; int i; @@ -3584,8 +3584,12 @@ static int __lock_is_held(struct lockdep_map *lock) for (i = 0; i < curr->lockdep_depth; i++) { struct held_lock *hlock = curr->held_locks + i; - if (match_held_lock(hlock, lock)) - return 1; + if (match_held_lock(hlock, lock)) { + if (read == -1 || hlock->read == read) + return 1; + + return 0; + } } return 0; @@ -3769,7 +3773,7 @@ void lock_release(struct lockdep_map *lock, int nested, } EXPORT_SYMBOL_GPL(lock_release); -int lock_is_held(struct lockdep_map *lock) +int lock_is_held_type(struct lockdep_map *lock, int read) { unsigned long flags; int ret = 0; @@ -3781,13 +3785,13 @@ int lock_is_held(struct lockdep_map *lock) check_flags(flags); current->lockdep_recursion = 1; - ret = __lock_is_held(lock); + ret = __lock_is_held(lock, read); current->lockdep_recursion = 0; raw_local_irq_restore(flags); return ret; } -EXPORT_SYMBOL_GPL(lock_is_held); +EXPORT_SYMBOL_GPL(lock_is_held_type); struct pin_cookie lock_pin_lock(struct lockdep_map *lock) { diff --git a/mm/filemap.c b/mm/filemap.c index 849f459ad078..00ab94a882de 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -137,13 +137,12 @@ static int page_cache_tree_insert(struct address_space *mapping, } else { /* DAX can replace empty locked entry with a hole */ WARN_ON_ONCE(p != - (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | - RADIX_DAX_ENTRY_LOCK)); + dax_radix_locked_entry(0, RADIX_DAX_EMPTY)); /* DAX accounts exceptional entries as normal pages */ if (node) workingset_node_pages_dec(node); /* Wakeup waiters for exceptional entry lock */ - dax_wake_mapping_entry_waiter(mapping, page->index, + dax_wake_mapping_entry_waiter(mapping, page->index, p, false); } } |