diff options
Diffstat (limited to 'fs/dax.c')
-rw-r--r-- | fs/dax.c | 157 |
1 files changed, 90 insertions, 67 deletions
@@ -709,26 +709,26 @@ 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, &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; @@ -1005,22 +1005,13 @@ 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) { - const sector_t sector = dax_iomap_sector(iomap, pos); - pgoff_t pgoff; + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); int id, rc; 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); @@ -1126,42 +1117,87 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, } #endif /* CONFIG_FS_DAX_PMD */ -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) +static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, + unsigned int offset, size_t size) { - sector_t sector = iomap_sector(iomap, pos & PAGE_MASK); - pgoff_t pgoff; - long rc, id; void *kaddr; - bool page_aligned = false; - unsigned offset = offset_in_page(pos); - unsigned size = min_t(u64, PAGE_SIZE - offset, length); + long ret; - if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) && - (size == PAGE_SIZE)) - page_aligned = true; + ret = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL); + if (ret > 0) { + memset(kaddr + offset, 0, size); + dax_flush(dax_dev, kaddr + offset, size); + } + return ret; +} - rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff); - if (rc) - return rc; +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(iomap->dax_dev, pgoff, offset, size); + dax_read_unlock(id); - id = dax_read_lock(); + if (rc < 0) + return rc; + pos += size; + length -= size; + written += size; + if (did_zero) + *did_zero = true; + } while (length > 0); - 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; - } + return written; +} - if (!page_aligned) { - memset(kaddr + offset, 0, size); - dax_flush(iomap->dax_dev, kaddr + offset, size); - } - dax_read_unlock(id); - return size; +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; + + 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) @@ -1169,7 +1205,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, const struct iomap *iomap = &iomi->iomap; 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; ssize_t ret = 0; @@ -1203,9 +1238,8 @@ 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; void *kaddr; if (fatal_signal_pending(current)) { @@ -1213,10 +1247,6 @@ 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); if (map_len < 0) { @@ -1230,11 +1260,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, 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) xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); @@ -1274,6 +1299,7 @@ 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; @@ -1332,19 +1358,16 @@ 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); @@ -1430,7 +1453,7 @@ 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 +1562,7 @@ 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; |