diff options
Diffstat (limited to 'fs/dax.c')
| -rw-r--r-- | fs/dax.c | 660 |
1 files changed, 452 insertions, 208 deletions
@@ -11,7 +11,6 @@ #include <linux/buffer_head.h> #include <linux/dax.h> #include <linux/fs.h> -#include <linux/genhd.h> #include <linux/highmem.h> #include <linux/memcontrol.h> #include <linux/mm.h> @@ -25,6 +24,7 @@ #include <linux/sizes.h> #include <linux/mmu_notifier.h> #include <linux/iomap.h> +#include <linux/rmap.h> #include <asm/pgalloc.h> #define CREATE_TRACE_POINTS @@ -334,13 +334,35 @@ static unsigned long dax_end_pfn(void *entry) for (pfn = dax_to_pfn(entry); \ pfn < dax_end_pfn(entry); pfn++) +static inline bool dax_mapping_is_cow(struct address_space *mapping) +{ + return (unsigned long)mapping == PAGE_MAPPING_DAX_COW; +} + +/* + * Set the page->mapping with FS_DAX_MAPPING_COW flag, increase the refcount. + */ +static inline void dax_mapping_set_cow(struct page *page) +{ + if ((uintptr_t)page->mapping != PAGE_MAPPING_DAX_COW) { + /* + * Reset the index if the page was already mapped + * regularly before. + */ + if (page->mapping) + page->index = 1; + page->mapping = (void *)PAGE_MAPPING_DAX_COW; + } + page->index++; +} + /* - * TODO: for reflink+dax we need a way to associate a single page with - * multiple address_space instances at different linear_page_index() - * offsets. + * When it is called in dax_insert_entry(), the cow flag will indicate that + * whether this entry is shared by multiple files. If so, set the page->mapping + * FS_DAX_MAPPING_COW, and use page->index as refcount. */ static void dax_associate_entry(void *entry, struct address_space *mapping, - struct vm_area_struct *vma, unsigned long address) + struct vm_area_struct *vma, unsigned long address, bool cow) { unsigned long size = dax_entry_size(entry), pfn, index; int i = 0; @@ -352,9 +374,13 @@ static void dax_associate_entry(void *entry, struct address_space *mapping, for_each_mapped_pfn(entry, pfn) { struct page *page = pfn_to_page(pfn); - WARN_ON_ONCE(page->mapping); - page->mapping = mapping; - page->index = index + i++; + if (cow) { + dax_mapping_set_cow(page); + } else { + WARN_ON_ONCE(page->mapping); + page->mapping = mapping; + page->index = index + i++; + } } } @@ -370,7 +396,12 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping, struct page *page = pfn_to_page(pfn); WARN_ON_ONCE(trunc && page_ref_count(page) > 1); - WARN_ON_ONCE(page->mapping && page->mapping != mapping); + if (dax_mapping_is_cow(page->mapping)) { + /* keep the CoW flag if this page is still shared */ + if (page->index-- > 0) + continue; + } else + WARN_ON_ONCE(page->mapping && page->mapping != mapping); page->mapping = NULL; page->index = 0; } @@ -390,7 +421,7 @@ static struct page *dax_busy_page(void *entry) } /* - * dax_lock_mapping_entry - Lock the DAX entry corresponding to a page + * dax_lock_page - Lock the DAX entry corresponding to a page * @page: The page whose entry we want to lock * * Context: Process context. @@ -456,6 +487,69 @@ void dax_unlock_page(struct page *page, dax_entry_t cookie) } /* + * dax_lock_mapping_entry - Lock the DAX entry corresponding to a mapping + * @mapping: the file's mapping whose entry we want to lock + * @index: the offset within this file + * @page: output the dax page corresponding to this dax entry + * + * Return: A cookie to pass to dax_unlock_mapping_entry() or 0 if the entry + * could not be locked. + */ +dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, pgoff_t index, + struct page **page) +{ + XA_STATE(xas, NULL, 0); + void *entry; + + rcu_read_lock(); + for (;;) { + entry = NULL; + if (!dax_mapping(mapping)) + break; + + xas.xa = &mapping->i_pages; + xas_lock_irq(&xas); + xas_set(&xas, index); + entry = xas_load(&xas); + if (dax_is_locked(entry)) { + rcu_read_unlock(); + wait_entry_unlocked(&xas, entry); + rcu_read_lock(); + continue; + } + if (!entry || + dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + /* + * Because we are looking for entry from file's mapping + * and index, so the entry may not be inserted for now, + * or even a zero/empty entry. We don't think this is + * an error case. So, return a special value and do + * not output @page. + */ + entry = (void *)~0UL; + } else { + *page = pfn_to_page(dax_to_pfn(entry)); + dax_lock_entry(&xas, entry); + } + xas_unlock_irq(&xas); + break; + } + rcu_read_unlock(); + return (dax_entry_t)entry; +} + +void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index, + dax_entry_t cookie) +{ + XA_STATE(xas, &mapping->i_pages, index); + + if (cookie == ~0UL) + return; + + dax_unlock_entry(&xas, (void *)cookie); +} + +/* * Find page cache entry at given index. If it is a DAX entry, return it * with the entry locked. If the page cache doesn't contain an entry at * that index, add a locked empty entry. @@ -709,48 +803,69 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, return __dax_invalidate_entry(mapping, index, false); } -static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_dev, - sector_t sector, struct page *to, unsigned long vaddr) +static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos) +{ + return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset); +} + +static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter) { + pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos); void *vto, *kaddr; - pgoff_t pgoff; long rc; int id; - rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff); - if (rc) - return rc; - id = dax_read_lock(); - rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL); + rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, DAX_ACCESS, + &kaddr, NULL); if (rc < 0) { dax_read_unlock(id); return rc; } - vto = kmap_atomic(to); - copy_user_page(vto, (void __force *)kaddr, vaddr, to); + vto = kmap_atomic(vmf->cow_page); + copy_user_page(vto, kaddr, vmf->address, vmf->cow_page); kunmap_atomic(vto); dax_read_unlock(id); return 0; } /* + * MAP_SYNC on a dax mapping guarantees dirty metadata is + * flushed on write-faults (non-cow), but not read-faults. + */ +static bool dax_fault_is_synchronous(const struct iomap_iter *iter, + struct vm_area_struct *vma) +{ + return (iter->flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC) && + (iter->iomap.flags & IOMAP_F_DIRTY); +} + +static bool dax_fault_is_cow(const struct iomap_iter *iter) +{ + return (iter->flags & IOMAP_WRITE) && + (iter->iomap.flags & IOMAP_F_SHARED); +} + +/* * 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_entry(struct xa_state *xas, - struct address_space *mapping, struct vm_fault *vmf, - void *entry, pfn_t pfn, unsigned long flags, bool dirty) +static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf, + const struct iomap_iter *iter, void *entry, pfn_t pfn, + unsigned long flags) { + struct address_space *mapping = vmf->vma->vm_file->f_mapping; void *new_entry = dax_make_entry(pfn, flags); + bool dirty = !dax_fault_is_synchronous(iter, vmf->vma); + bool cow = dax_fault_is_cow(iter); if (dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) { + if (cow || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) { unsigned long index = xas->xa_index; /* we are replacing a zero page with block mapping */ if (dax_is_pmd_entry(entry)) @@ -762,11 +877,12 @@ static void *dax_insert_entry(struct xa_state *xas, xas_reset(xas); xas_lock_irq(xas); - if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + if (cow || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { void *old; dax_disassociate_entry(entry, mapping, false); - dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address); + dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address, + cow); /* * Only swap our new entry into the page cache if the current * entry is a zero page or an empty entry. If a normal PTE or @@ -786,99 +902,19 @@ static void *dax_insert_entry(struct xa_state *xas, if (dirty) xas_set_mark(xas, PAGECACHE_TAG_DIRTY); + if (cow) + xas_set_mark(xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irq(xas); return entry; } -static inline -unsigned long pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma) -{ - unsigned long address; - - address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); - return address; -} - -/* Walk all mappings of a given index of a file and writeprotect them */ -static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index, - unsigned long pfn) -{ - struct vm_area_struct *vma; - pte_t pte, *ptep = NULL; - pmd_t *pmdp = NULL; - spinlock_t *ptl; - - i_mmap_lock_read(mapping); - vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) { - struct mmu_notifier_range range; - unsigned long address; - - cond_resched(); - - if (!(vma->vm_flags & VM_SHARED)) - continue; - - address = pgoff_address(index, vma); - - /* - * follow_invalidate_pte() will use the range to call - * mmu_notifier_invalidate_range_start() on our behalf before - * taking any lock. - */ - if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep, - &pmdp, &ptl)) - continue; - - /* - * No need to call mmu_notifier_invalidate_range() as we are - * downgrading page table protection not changing it to point - * to a new page. - * - * See Documentation/vm/mmu_notifier.rst - */ - if (pmdp) { -#ifdef CONFIG_FS_DAX_PMD - pmd_t pmd; - - if (pfn != pmd_pfn(*pmdp)) - goto unlock_pmd; - if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp)) - goto unlock_pmd; - - flush_cache_page(vma, address, pfn); - pmd = pmdp_invalidate(vma, address, pmdp); - pmd = pmd_wrprotect(pmd); - pmd = pmd_mkclean(pmd); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); -unlock_pmd: -#endif - spin_unlock(ptl); - } else { - if (pfn != pte_pfn(*ptep)) - goto unlock_pte; - if (!pte_dirty(*ptep) && !pte_write(*ptep)) - goto unlock_pte; - - flush_cache_page(vma, address, pfn); - pte = ptep_clear_flush(vma, address, ptep); - pte = pte_wrprotect(pte); - pte = pte_mkclean(pte); - set_pte_at(vma->vm_mm, address, ptep, pte); -unlock_pte: - pte_unmap_unlock(ptep, ptl); - } - - mmu_notifier_invalidate_range_end(&range); - } - i_mmap_unlock_read(mapping); -} - static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev, struct address_space *mapping, void *entry) { - unsigned long pfn, index, count; + unsigned long pfn, index, count, end; long ret = 0; + struct vm_area_struct *vma; /* * A page got tagged dirty in DAX mapping? Something is seriously @@ -936,8 +972,16 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev, pfn = dax_to_pfn(entry); count = 1UL << dax_entry_order(entry); index = xas->xa_index & ~(count - 1); + end = index + count - 1; + + /* Walk all mappings of a given index of a file and writeprotect them */ + i_mmap_lock_read(mapping); + vma_interval_tree_foreach(vma, &mapping->i_mmap, index, end) { + pfn_mkclean_range(pfn, count, index, vma); + cond_resched(); + } + i_mmap_unlock_read(mapping); - dax_entry_mkclean(mapping, index, pfn); dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE); /* * After we have flushed the cache, we can clear the dirty tag. There @@ -1005,29 +1049,22 @@ int dax_writeback_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); -static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos) -{ - return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9; -} - -static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, - pfn_t *pfnp) +static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos, + size_t size, void **kaddr, pfn_t *pfnp) { - const sector_t sector = dax_iomap_sector(iomap, pos); - pgoff_t pgoff; - int id, rc; + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + int id, rc = 0; long length; - rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff); - if (rc) - return rc; id = dax_read_lock(); length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size), - NULL, pfnp); + DAX_ACCESS, kaddr, pfnp); if (length < 0) { rc = length; goto out; } + if (!pfnp) + goto out_check_addr; rc = -EINVAL; if (PFN_PHYS(length) < size) goto out; @@ -1037,11 +1074,71 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, if (length > 1 && !pfn_t_devmap(*pfnp)) goto out; rc = 0; + +out_check_addr: + if (!kaddr) + goto out; + if (!*kaddr) + rc = -EFAULT; out: dax_read_unlock(id); return rc; } +/** + * dax_iomap_cow_copy - Copy the data from source to destination before write + * @pos: address to do copy from. + * @length: size of copy operation. + * @align_size: aligned w.r.t align_size (either PMD_SIZE or PAGE_SIZE) + * @srcmap: iomap srcmap + * @daddr: destination address to copy to. + * + * This can be called from two places. Either during DAX write fault (page + * aligned), to copy the length size data to daddr. Or, while doing normal DAX + * write operation, dax_iomap_actor() might call this to do the copy of either + * start or end unaligned address. In the latter case the rest of the copy of + * aligned ranges is taken care by dax_iomap_actor() itself. + */ +static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size, + const struct iomap *srcmap, void *daddr) +{ + loff_t head_off = pos & (align_size - 1); + size_t size = ALIGN(head_off + length, align_size); + loff_t end = pos + length; + loff_t pg_end = round_up(end, align_size); + bool copy_all = head_off == 0 && end == pg_end; + void *saddr = 0; + int ret = 0; + + ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL); + if (ret) + return ret; + + if (copy_all) { + ret = copy_mc_to_kernel(daddr, saddr, length); + return ret ? -EIO : 0; + } + + /* Copy the head part of the range */ + if (head_off) { + ret = copy_mc_to_kernel(daddr, saddr, head_off); + if (ret) + return -EIO; + } + + /* Copy the tail part of the range */ + if (end < pg_end) { + loff_t tail_off = head_off + length; + loff_t tail_len = pg_end - end; + + ret = copy_mc_to_kernel(daddr + tail_off, saddr + tail_off, + tail_len); + if (ret) + return -EIO; + } + return 0; +} + /* * The user has performed a load from a hole in the file. Allocating a new * page in the file would cause excessive storage usage for workloads with @@ -1049,17 +1146,15 @@ out: * If this page is ever written to we will re-fault and change the mapping to * point to real DAX storage instead. */ -static vm_fault_t dax_load_hole(struct xa_state *xas, - struct address_space *mapping, void **entry, - struct vm_fault *vmf) +static vm_fault_t dax_load_hole(struct xa_state *xas, struct vm_fault *vmf, + const struct iomap_iter *iter, void **entry) { - struct inode *inode = mapping->host; + struct inode *inode = iter->inode; unsigned long vaddr = vmf->address; pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr)); vm_fault_t ret; - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, - DAX_ZERO_PAGE, false); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_ZERO_PAGE); ret = vmf_insert_mixed(vmf->vma, vaddr, pfn); trace_dax_load_hole(inode, vmf, ret); @@ -1068,7 +1163,7 @@ static vm_fault_t dax_load_hole(struct xa_state *xas, #ifdef CONFIG_FS_DAX_PMD static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, - const struct iomap *iomap, void **entry) + const struct iomap_iter *iter, void **entry) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; @@ -1086,8 +1181,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, goto fallback; pfn = page_to_pfn_t(zero_page); - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, - DAX_PMD | DAX_ZERO_PAGE, false); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, + DAX_PMD | DAX_ZERO_PAGE); if (arch_needs_pgtable_deposit()) { pgtable = pte_alloc_one(vma->vm_mm); @@ -1120,63 +1215,120 @@ fallback: } #else static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, - const struct iomap *iomap, void **entry) + const struct iomap_iter *iter, void **entry) { return VM_FAULT_FALLBACK; } #endif /* CONFIG_FS_DAX_PMD */ -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) +static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size) { - sector_t sector = iomap_sector(iomap, pos & PAGE_MASK); - pgoff_t pgoff; - long rc, id; - void *kaddr; - bool page_aligned = false; + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); unsigned offset = offset_in_page(pos); - unsigned size = min_t(u64, PAGE_SIZE - offset, length); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + void *kaddr; + long ret; + + ret = dax_direct_access(iomap->dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, + NULL); + if (ret < 0) + return ret; + memset(kaddr + offset, 0, size); + if (srcmap->addr != iomap->addr) { + ret = dax_iomap_cow_copy(pos, size, PAGE_SIZE, srcmap, + kaddr); + if (ret < 0) + return ret; + dax_flush(iomap->dax_dev, kaddr, PAGE_SIZE); + } else + dax_flush(iomap->dax_dev, kaddr + offset, size); + return ret; +} - if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) && - (size == PAGE_SIZE)) - page_aligned = true; +static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero) +{ + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + u64 length = iomap_length(iter); + s64 written = 0; + + /* already zeroed? we're done. */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + do { + unsigned offset = offset_in_page(pos); + unsigned size = min_t(u64, PAGE_SIZE - offset, length); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + long rc; + int id; + + id = dax_read_lock(); + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) + rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); + else + rc = dax_memzero(iter, pos, size); + dax_read_unlock(id); - rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff); - if (rc) - return rc; + if (rc < 0) + return rc; + pos += size; + length -= size; + written += size; + } while (length > 0); - id = dax_read_lock(); + if (did_zero) + *did_zero = true; + return written; +} - if (page_aligned) - rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); - else - rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL); - if (rc < 0) { - dax_read_unlock(id); - return rc; - } +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops) +{ + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_DAX | IOMAP_ZERO, + }; + int ret; - if (!page_aligned) { - memset(kaddr + offset, 0, size); - dax_flush(iomap->dax_dev, kaddr + offset, size); - } - dax_read_unlock(id); - return size; + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = dax_zero_iter(&iter, did_zero); + return ret; } +EXPORT_SYMBOL_GPL(dax_zero_range); + +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops) +{ + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!off) + return 0; + return dax_zero_range(inode, pos, blocksize - off, did_zero, ops); +} +EXPORT_SYMBOL_GPL(dax_truncate_page); static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) { const struct iomap *iomap = &iomi->iomap; + const struct iomap *srcmap = &iomi->srcmap; loff_t length = iomap_length(iomi); loff_t pos = iomi->pos; - struct block_device *bdev = iomap->bdev; struct dax_device *dax_dev = iomap->dax_dev; loff_t end = pos + length, done = 0; + bool write = iov_iter_rw(iter) == WRITE; ssize_t ret = 0; size_t xfer; int id; - if (iov_iter_rw(iter) == READ) { + if (!write) { end = min(end, i_size_read(iomi->inode)); if (pos >= end) return 0; @@ -1185,7 +1337,12 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, return iov_iter_zero(min(length, end - pos), iter); } - if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED)) + /* + * In DAX mode, enforce either pure overwrites of written extents, or + * writes to unwritten extents as part of a copy-on-write operation. + */ + if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED && + !(iomap->flags & IOMAP_F_SHARED))) return -EIO; /* @@ -1203,9 +1360,9 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, while (pos < end) { unsigned offset = pos & (PAGE_SIZE - 1); const size_t size = ALIGN(length + offset, PAGE_SIZE); - const sector_t sector = dax_iomap_sector(iomap, pos); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); ssize_t map_len; - pgoff_t pgoff; + bool recovery = false; void *kaddr; if (fatal_signal_pending(current)) { @@ -1213,29 +1370,38 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, break; } - ret = bdev_dax_pgoff(bdev, sector, size, &pgoff); - if (ret) - break; - map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), - &kaddr, NULL); + DAX_ACCESS, &kaddr, NULL); + if (map_len == -EIO && iov_iter_rw(iter) == WRITE) { + map_len = dax_direct_access(dax_dev, pgoff, + PHYS_PFN(size), DAX_RECOVERY_WRITE, + &kaddr, NULL); + if (map_len > 0) + recovery = true; + } if (map_len < 0) { ret = map_len; break; } + if (write && + srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) { + ret = dax_iomap_cow_copy(pos, length, PAGE_SIZE, srcmap, + kaddr); + if (ret) + break; + } + map_len = PFN_PHYS(map_len); kaddr += offset; map_len -= offset; if (map_len > end - pos) map_len = end - pos; - /* - * The userspace address for the memory copy has already been - * validated via access_ok() in either vfs_read() or - * vfs_write(), depending on which operation we are doing. - */ - if (iov_iter_rw(iter) == WRITE) + if (recovery) + xfer = dax_recovery_write(dax_dev, pgoff, kaddr, + map_len, iter); + else if (write) xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); else @@ -1274,10 +1440,14 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, .inode = iocb->ki_filp->f_mapping->host, .pos = iocb->ki_pos, .len = iov_iter_count(iter), + .flags = IOMAP_DAX, }; loff_t done = 0; int ret; + if (!iomi.len) + return 0; + if (iov_iter_rw(iter) == WRITE) { lockdep_assert_held_write(&iomi.inode->i_rwsem); iomi.flags |= IOMAP_WRITE; @@ -1305,17 +1475,6 @@ static vm_fault_t dax_fault_return(int error) } /* - * MAP_SYNC on a dax mapping guarantees dirty metadata is - * flushed on write-faults (non-cow), but not read-faults. - */ -static bool dax_fault_is_synchronous(unsigned long flags, - struct vm_area_struct *vma, const struct iomap *iomap) -{ - return (flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC) - && (iomap->flags & IOMAP_F_DIRTY); -} - -/* * When handling a synchronous page fault and the inode need a fsync, we can * insert the PTE/PMD into page tables only after that fsync happened. Skip * insertion for now and return the pfn so that caller can insert it after the @@ -1332,19 +1491,16 @@ static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn) static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf, const struct iomap_iter *iter) { - sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos); - unsigned long vaddr = vmf->address; vm_fault_t ret; int error = 0; switch (iter->iomap.type) { case IOMAP_HOLE: case IOMAP_UNWRITTEN: - clear_user_highpage(vmf->cow_page, vaddr); + clear_user_highpage(vmf->cow_page, vmf->address); break; case IOMAP_MAPPED: - error = copy_cow_page_dax(iter->iomap.bdev, iter->iomap.dax_dev, - sector, vmf->cow_page, vaddr); + error = copy_cow_page_dax(vmf, iter); break; default: WARN_ON_ONCE(1); @@ -1375,15 +1531,15 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, const struct iomap_iter *iter, pfn_t *pfnp, struct xa_state *xas, void **entry, bool pmd) { - struct address_space *mapping = vmf->vma->vm_file->f_mapping; const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = &iter->srcmap; size_t size = pmd ? PMD_SIZE : PAGE_SIZE; loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT; - bool write = vmf->flags & FAULT_FLAG_WRITE; - bool sync = dax_fault_is_synchronous(iter->flags, vmf->vma, iomap); + bool write = iter->flags & IOMAP_WRITE; unsigned long entry_flags = pmd ? DAX_PMD : 0; int err = 0; pfn_t pfn; + void *kaddr; if (!pmd && vmf->cow_page) return dax_fault_cow_page(vmf, iter); @@ -1392,23 +1548,29 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, if (!write && (iomap->type == IOMAP_UNWRITTEN || iomap->type == IOMAP_HOLE)) { if (!pmd) - return dax_load_hole(xas, mapping, entry, vmf); - return dax_pmd_load_hole(xas, vmf, iomap, entry); + return dax_load_hole(xas, vmf, iter, entry); + return dax_pmd_load_hole(xas, vmf, iter, entry); } - if (iomap->type != IOMAP_MAPPED) { + if (iomap->type != IOMAP_MAPPED && !(iomap->flags & IOMAP_F_SHARED)) { WARN_ON_ONCE(1); return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS; } - err = dax_iomap_pfn(&iter->iomap, pos, size, &pfn); + err = dax_iomap_direct_access(iomap, pos, size, &kaddr, &pfn); if (err) return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err); - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, entry_flags, - write && !sync); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, entry_flags); + + if (write && + srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) { + err = dax_iomap_cow_copy(pos, size, size, srcmap, kaddr); + if (err) + return dax_fault_return(err); + } - if (sync) + if (dax_fault_is_synchronous(iter, vmf->vma)) return dax_fault_synchronous_pfnp(pfnp, pfn); /* insert PMD pfn */ @@ -1430,7 +1592,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, .inode = mapping->host, .pos = (loff_t)vmf->pgoff << PAGE_SHIFT, .len = PAGE_SIZE, - .flags = IOMAP_FAULT, + .flags = IOMAP_DAX | IOMAP_FAULT, }; vm_fault_t ret = 0; void *entry; @@ -1539,7 +1701,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, struct iomap_iter iter = { .inode = mapping->host, .len = PMD_SIZE, - .flags = IOMAP_FAULT, + .flags = IOMAP_DAX | IOMAP_FAULT, }; vm_fault_t ret = VM_FAULT_FALLBACK; pgoff_t max_pgoff; @@ -1714,3 +1876,85 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, return dax_insert_pfn_mkwrite(vmf, pfn, order); } EXPORT_SYMBOL_GPL(dax_finish_sync_fault); + +static loff_t dax_range_compare_iter(struct iomap_iter *it_src, + struct iomap_iter *it_dest, u64 len, bool *same) +{ + const struct iomap *smap = &it_src->iomap; + const struct iomap *dmap = &it_dest->iomap; + loff_t pos1 = it_src->pos, pos2 = it_dest->pos; + void *saddr, *daddr; + int id, ret; + + len = min(len, min(smap->length, dmap->length)); + + if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) { + *same = true; + return len; + } + + if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) { + *same = false; + return 0; + } + + id = dax_read_lock(); + ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE), + &saddr, NULL); + if (ret < 0) + goto out_unlock; + + ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE), + &daddr, NULL); + if (ret < 0) + goto out_unlock; + + *same = !memcmp(saddr, daddr, len); + if (!*same) + len = 0; + dax_read_unlock(id); + return len; + +out_unlock: + dax_read_unlock(id); + return -EIO; +} + +int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dst, loff_t dstoff, loff_t len, bool *same, + const struct iomap_ops *ops) +{ + struct iomap_iter src_iter = { + .inode = src, + .pos = srcoff, + .len = len, + .flags = IOMAP_DAX, + }; + struct iomap_iter dst_iter = { + .inode = dst, + .pos = dstoff, + .len = len, + .flags = IOMAP_DAX, + }; + int ret; + + while ((ret = iomap_iter(&src_iter, ops)) > 0) { + while ((ret = iomap_iter(&dst_iter, ops)) > 0) { + dst_iter.processed = dax_range_compare_iter(&src_iter, + &dst_iter, len, same); + } + if (ret <= 0) + src_iter.processed = ret; + } + return ret; +} + +int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *ops) +{ + return __generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, ops); +} +EXPORT_SYMBOL_GPL(dax_remap_file_range_prep); |