From patchwork Sun Aug 29 12:25:11 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12463883 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 4EBF13FC1 for ; Sun, 29 Aug 2021 12:25:40 +0000 (UTC) IronPort-HdrOrdr: A9a23:pYVjQ69v+m6hu8mGYMhuk+DkI+orL9Y04lQ7vn2ZKCYlFvBw8vrCoB1173HJYUkqMk3I9ergBEDiewK4yXcW2/hzAV7KZmCP11dAR7sSj7cKrQeBJwTOssZZ1YpFN5N1EcDMCzFB5vrS0U2VFMkBzbC8nJyVuQ== X-IronPort-AV: E=Sophos;i="5.84,361,1620662400"; d="scan'208";a="113656444" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 29 Aug 2021 20:25:31 +0800 Received: from G08CNEXMBPEKD06.g08.fujitsu.local (unknown [10.167.33.206]) by cn.fujitsu.com (Postfix) with ESMTP id 2221E4D0D9D0; Sun, 29 Aug 2021 20:25:29 +0800 (CST) Received: from G08CNEXJMPEKD02.g08.fujitsu.local (10.167.33.202) by G08CNEXMBPEKD06.g08.fujitsu.local (10.167.33.206) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 29 Aug 2021 20:25:28 +0800 Received: from G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.85) by G08CNEXJMPEKD02.g08.fujitsu.local (10.167.33.202) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 29 Aug 2021 20:25:30 +0800 Received: from irides.mr.mr.mr (10.167.225.141) by G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.209) with Microsoft SMTP Server id 15.0.1497.23 via Frontend Transport; Sun, 29 Aug 2021 20:25:27 +0800 From: Shiyang Ruan To: , , CC: , , , , , , , , , Ritesh Harjani Subject: [PATCH v8 1/7] fsdax: Output address in dax_iomap_pfn() and rename it Date: Sun, 29 Aug 2021 20:25:11 +0800 Message-ID: <20210829122517.1648171-2-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> References: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: 2221E4D0D9D0.A0D76 X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No Add address output in dax_iomap_pfn() in order to perform a memcpy() in CoW case. Since this function both output address and pfn, rename it to dax_iomap_direct_access(). Signed-off-by: Shiyang Ruan Reviewed-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Dan Williams --- fs/dax.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 118c9e2923f5..9fb6218f42be 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1010,8 +1010,8 @@ 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; @@ -1023,11 +1023,13 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, return rc; id = dax_read_lock(); length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size), - NULL, pfnp); + kaddr, pfnp); if (length < 0) { rc = length; goto out; } + if (!pfnp) + goto out_check_addr; rc = -EINVAL; if (PFN_PHYS(length) < size) goto out; @@ -1037,6 +1039,12 @@ 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; @@ -1401,7 +1409,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS; } - err = dax_iomap_pfn(&iter->iomap, pos, size, &pfn); + err = dax_iomap_direct_access(&iter->iomap, pos, size, NULL, &pfn); if (err) return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err); From patchwork Sun Aug 29 12:25:12 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12463887 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 105063FCB for ; Sun, 29 Aug 2021 12:25:42 +0000 (UTC) IronPort-HdrOrdr: A9a23:7Ux0964OELSYhhYtlwPXwPTXdLJyesId70hD6qkRc20wTiX8ra2TdZsguyMc9wx6ZJhNo7G90cq7MBbhHPxOkOos1N6ZNWGIhILCFvAB0WKN+V3dMhy73utc+IMlSKJmFeD3ZGIQse/KpCW+DPYsqePqzJyV X-IronPort-AV: E=Sophos;i="5.84,361,1620662400"; d="scan'208";a="113656445" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 29 Aug 2021 20:25:31 +0800 Received: from G08CNEXMBPEKD05.g08.fujitsu.local (unknown [10.167.33.204]) by cn.fujitsu.com (Postfix) with ESMTP id A5C6C4D0D9D6; Sun, 29 Aug 2021 20:25:29 +0800 (CST) Received: from G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.85) by G08CNEXMBPEKD05.g08.fujitsu.local (10.167.33.204) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 29 Aug 2021 20:25:32 +0800 Received: from irides.mr.mr.mr (10.167.225.141) by G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.209) with Microsoft SMTP Server id 15.0.1497.23 via Frontend Transport; Sun, 29 Aug 2021 20:25:28 +0800 From: Shiyang Ruan To: , , CC: , , , , , , , , Subject: [PATCH v8 2/7] fsdax: Introduce dax_iomap_cow_copy() Date: Sun, 29 Aug 2021 20:25:12 +0800 Message-ID: <20210829122517.1648171-3-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> References: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: A5C6C4D0D9D6.A481C X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No In the case where the iomap is a write operation and iomap is not equal to srcmap after iomap_begin, we consider it is a CoW operation. In this case, the destination (iomap->addr) points to a newly allocated extent. It is needed to copy the data from srcmap to the extent. In theory, it is better to copy the head and tail ranges which is outside of the non-aligned area instead of copying the whole aligned range. But in dax page fault, it will always be an aligned range. So copy the whole range in this case. Signed-off-by: Shiyang Ruan Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- fs/dax.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 83 insertions(+), 5 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 9fb6218f42be..792116b14782 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1050,6 +1050,60 @@ static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos, 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 @@ -1175,16 +1229,18 @@ 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; @@ -1193,7 +1249,12 @@ 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; /* @@ -1232,6 +1293,14 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, break; } + if (write && + srcmap->addr != 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; @@ -1243,7 +1312,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, * 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 (write) xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); else @@ -1385,6 +1454,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, { 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; @@ -1392,6 +1462,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, 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); @@ -1404,18 +1475,25 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, return dax_pmd_load_hole(xas, vmf, iomap, 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_direct_access(&iter->iomap, pos, size, NULL, &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); + if (write && + srcmap->addr != 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) return dax_fault_synchronous_pfnp(pfnp, pfn); From patchwork Sun Aug 29 12:25:13 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12463891 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id F1DEB3FCB for ; Sun, 29 Aug 2021 12:25:44 +0000 (UTC) IronPort-HdrOrdr: A9a23:41nuca+3DiieefykfdBuk+DkI+orL9Y04lQ7vn2ZKCYlFvBw8vrCoB1173HJYUkqMk3I9ergBEDiewK4yXcW2/hzAV7KZmCP11dAR7sSj7cKrQeBJwTOssZZ1YpFN5N1EcDMCzFB5vrS0U2VFMkBzbC8nJyVuQ== X-IronPort-AV: E=Sophos;i="5.84,361,1620662400"; d="scan'208";a="113656447" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 29 Aug 2021 20:25:37 +0800 Received: from G08CNEXMBPEKD06.g08.fujitsu.local (unknown [10.167.33.206]) by cn.fujitsu.com (Postfix) with ESMTP id 354584D0D4A1; Sun, 29 Aug 2021 20:25:36 +0800 (CST) Received: from G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.85) by G08CNEXMBPEKD06.g08.fujitsu.local (10.167.33.206) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 29 Aug 2021 20:25:30 +0800 Received: from irides.mr.mr.mr (10.167.225.141) by G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.209) with Microsoft SMTP Server id 15.0.1497.23 via Frontend Transport; Sun, 29 Aug 2021 20:25:29 +0800 From: Shiyang Ruan To: , , CC: , , , , , , , , , Goldwyn Rodrigues , Ritesh Harjani Subject: [PATCH v8 3/7] fsdax: Replace mmap entry in case of CoW Date: Sun, 29 Aug 2021 20:25:13 +0800 Message-ID: <20210829122517.1648171-4-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> References: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: 354584D0D4A1.A13A8 X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No We replace the existing entry to the newly allocated one in case of CoW. Also, we mark the entry as PAGECACHE_TAG_TOWRITE so writeback marks this entry as writeprotected. This helps us snapshots so new write pagefaults after snapshots trigger a CoW. Signed-off-by: Goldwyn Rodrigues Signed-off-by: Shiyang Ruan Reviewed-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Darrick J. Wong --- fs/dax.c | 73 +++++++++++++++++++++++++++++++------------------------- 1 file changed, 40 insertions(+), 33 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 792116b14782..f4acb79cb811 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -734,6 +734,23 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d 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 @@ -741,16 +758,19 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d * 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)) @@ -762,7 +782,7 @@ 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); @@ -786,6 +806,9 @@ 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; } @@ -1111,17 +1134,15 @@ static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size, * 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); @@ -1130,7 +1151,7 @@ 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; @@ -1148,8 +1169,8 @@ 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); @@ -1381,17 +1402,6 @@ static vm_fault_t dax_fault_return(int error) return vmf_error(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 @@ -1452,13 +1462,11 @@ 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; @@ -1471,8 +1479,8 @@ 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 && !(iomap->flags & IOMAP_F_SHARED)) { @@ -1484,8 +1492,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, 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->addr != IOMAP_HOLE && srcmap->addr != iomap->addr) { @@ -1494,7 +1501,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, 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 */ From patchwork Sun Aug 29 12:25:14 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12463889 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 654D23FC1 for ; Sun, 29 Aug 2021 12:25:44 +0000 (UTC) IronPort-HdrOrdr: A9a23:P/GwVajJOW7yQGzQc4r5mzTSLnBQXuYji2hC6mlwRA09TyX4rbHLoB1/73LJYVkqNk3I5urrBEDtexLhHP1OkOws1NWZLWrbUQKTRekM0WKI+UyDJ8SRzI5g/JYlW61/Jfm1NlJikPv9iTPSL/8QhPWB74Ck7N2z80tQ X-IronPort-AV: E=Sophos;i="5.84,361,1620662400"; d="scan'208";a="113656448" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 29 Aug 2021 20:25:37 +0800 Received: from G08CNEXMBPEKD04.g08.fujitsu.local (unknown [10.167.33.201]) by cn.fujitsu.com (Postfix) with ESMTP id 29FEA4D0D9D0; Sun, 29 Aug 2021 20:25:37 +0800 (CST) Received: from G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.85) by G08CNEXMBPEKD04.g08.fujitsu.local (10.167.33.201) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 29 Aug 2021 20:25:38 +0800 Received: from irides.mr.mr.mr (10.167.225.141) by G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.209) with Microsoft SMTP Server id 15.0.1497.23 via Frontend Transport; Sun, 29 Aug 2021 20:25:36 +0800 From: Shiyang Ruan To: , , CC: , , , , , , , , , Ritesh Harjani Subject: [PATCH v8 4/7] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Date: Sun, 29 Aug 2021 20:25:14 +0800 Message-ID: <20210829122517.1648171-5-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> References: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: 29FEA4D0D9D0.A371E X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No Punch hole on a reflinked file needs dax_iomap_cow_copy() too. Otherwise, data in not aligned area will be not correct. So, add the srcmap to dax_iomap_zero() and replace memset() as dax_iomap_cow_copy(). Signed-off-by: Shiyang Ruan Reviewed-by: Ritesh Harjani Reviewed-by: Darrick J. Wong --- fs/dax.c | 26 ++++++++++++++++---------- fs/iomap/buffered-io.c | 4 ++-- include/linux/dax.h | 3 ++- 3 files changed, 20 insertions(+), 13 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index f4acb79cb811..b294900e574e 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1209,7 +1209,8 @@ 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) +s64 dax_iomap_zero(loff_t pos, u64 length, const struct iomap *iomap, + const struct iomap *srcmap) { sector_t sector = iomap_sector(iomap, pos & PAGE_MASK); pgoff_t pgoff; @@ -1231,19 +1232,24 @@ s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) if (page_aligned) rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); - else + else { rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL); - if (rc < 0) { - dax_read_unlock(id); - return rc; - } - - if (!page_aligned) { + if (rc < 0) + goto out; memset(kaddr + offset, 0, size); - dax_flush(iomap->dax_dev, kaddr + offset, size); + if (iomap->addr != srcmap->addr) { + rc = dax_iomap_cow_copy(pos, size, PAGE_SIZE, srcmap, + kaddr); + if (rc < 0) + goto out; + dax_flush(iomap->dax_dev, kaddr, PAGE_SIZE); + } else + dax_flush(iomap->dax_dev, kaddr + offset, size); } + +out: dax_read_unlock(id); - return size; + return rc < 0 ? rc : size; } static loff_t dax_iomap_iter(const struct iomap_iter *iomi, diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 71b4806266d7..6e8d40877d01 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -889,7 +889,7 @@ static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - struct iomap *iomap = &iter->iomap; + const struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); @@ -903,7 +903,7 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) s64 bytes; if (IS_DAX(iter->inode)) - bytes = dax_iomap_zero(pos, length, iomap); + bytes = dax_iomap_zero(pos, length, iomap, srcmap); else bytes = __iomap_zero_iter(iter, pos, length); if (bytes < 0) diff --git a/include/linux/dax.h b/include/linux/dax.h index b52f084aa643..c63559605369 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -237,7 +237,8 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); +s64 dax_iomap_zero(loff_t pos, u64 length, const struct iomap *iomap, + const struct iomap *srcmap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); From patchwork Sun Aug 29 12:25:15 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12463893 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 734F03FC6 for ; Sun, 29 Aug 2021 12:25:50 +0000 (UTC) IronPort-HdrOrdr: A9a23:om/8n6xe1hAuYF2p9C7SKrPwEL1zdoMgy1knxilNoH1uA6ilfqWV8cjzuiWbtN9vYhsdcLy7WZVoIkmskKKdg7NhXotKNTOO0ASVxepZnOnfKlPbexHWx6p00KdMV+xEAsTsMF4St63HyTj9P9E+4NTvysyVuds= X-IronPort-AV: E=Sophos;i="5.84,361,1620662400"; d="scan'208";a="113656459" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 29 Aug 2021 20:25:50 +0800 Received: from G08CNEXMBPEKD04.g08.fujitsu.local (unknown [10.167.33.201]) by cn.fujitsu.com (Postfix) with ESMTP id A9CD64D0D9D0; Sun, 29 Aug 2021 20:25:43 +0800 (CST) Received: from G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.85) by G08CNEXMBPEKD04.g08.fujitsu.local (10.167.33.201) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 29 Aug 2021 20:25:39 +0800 Received: from irides.mr.mr.mr (10.167.225.141) by G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.209) with Microsoft SMTP Server id 15.0.1497.23 via Frontend Transport; Sun, 29 Aug 2021 20:25:37 +0800 From: Shiyang Ruan To: , , CC: , , , , , , , , , Goldwyn Rodrigues Subject: [PATCH v8 5/7] fsdax: Dedup file range to use a compare function Date: Sun, 29 Aug 2021 20:25:15 +0800 Message-ID: <20210829122517.1648171-6-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> References: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: A9CD64D0D9D0.A3367 X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No With dax we cannot deal with readpage() etc. So, we create a dax comparison function which is similar with vfs_dedupe_file_range_compare(). And introduce dax_remap_file_range_prep() for filesystem use. Signed-off-by: Goldwyn Rodrigues Signed-off-by: Shiyang Ruan Reviewed-by: Darrick J. Wong --- fs/dax.c | 79 ++++++++++++++++++++++++++++++++++++++++++++ fs/remap_range.c | 39 +++++++++++++++++----- fs/xfs/xfs_reflink.c | 8 +++-- include/linux/dax.h | 8 +++++ include/linux/fs.h | 12 ++++--- 5 files changed, 132 insertions(+), 14 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index b294900e574e..a1232d6b7e37 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1813,3 +1813,82 @@ 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, 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; + loff_t len = min(smap->length, dmap->length); + void *saddr, *daddr; + int id, ret; + + 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, + }; + struct iomap_iter dst_iter = { + .inode = dst, + .pos = dstoff, + .len = len, + }; + 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, 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); diff --git a/fs/remap_range.c b/fs/remap_range.c index e4a5fdd7ad7b..b68a29562902 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "internal.h" #include @@ -199,9 +200,9 @@ static void vfs_unlock_two_pages(struct page *page1, struct page *page2) * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races. */ -static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same) +int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same) { loff_t src_poff; loff_t dest_poff; @@ -280,6 +281,7 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, out_error: return error; } +EXPORT_SYMBOL(vfs_dedupe_file_range_compare); /* * Check that the two inodes are eligible for cloning, the ranges make @@ -289,9 +291,11 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, * If there's an error, then the usual negative error code is returned. * Otherwise returns 0 with *len set to the request length. */ -int generic_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) +int +__generic_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 *dax_read_ops) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -351,8 +355,18 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; - ret = vfs_dedupe_file_range_compare(inode_in, pos_in, - inode_out, pos_out, *len, &is_same); + if (*len == 0) + return 0; + + if (!IS_DAX(inode_in)) + ret = vfs_dedupe_file_range_compare(inode_in, pos_in, + inode_out, pos_out, *len, &is_same); + else if (dax_read_ops) + ret = dax_dedupe_file_range_compare(inode_in, pos_in, + inode_out, pos_out, *len, &is_same, + dax_read_ops); + else + return -EINVAL; if (ret) return ret; if (!is_same) @@ -370,6 +384,15 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, return ret; } +EXPORT_SYMBOL(__generic_remap_file_range_prep); + +int generic_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) +{ + return __generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, NULL); +} EXPORT_SYMBOL(generic_remap_file_range_prep); loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index c256104772cb..28effe537d07 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1332,8 +1332,12 @@ xfs_reflink_remap_prep( if (IS_DAX(inode_in) || IS_DAX(inode_out)) goto out_unlock; - ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, - len, remap_flags); + if (!IS_DAX(inode_in)) + ret = generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags); + else + ret = dax_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, &xfs_read_iomap_ops); if (ret || *len == 0) goto out_unlock; diff --git a/include/linux/dax.h b/include/linux/dax.h index c63559605369..8ecd125434ef 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -239,6 +239,14 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); s64 dax_iomap_zero(loff_t pos, u64 length, const struct iomap *iomap, const struct iomap *srcmap); +int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same, + const struct iomap_ops *ops); +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); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..3e9922aac200 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -71,6 +71,7 @@ struct fsverity_operations; struct fs_context; struct fs_parameter_spec; struct fileattr; +struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -2126,10 +2127,13 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags); -extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *count, - unsigned int remap_flags); +int __generic_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 *dax_read_ops); +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *count, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); From patchwork Sun Aug 29 12:25:16 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12463895 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 7BB743FC6 for ; Sun, 29 Aug 2021 12:25:56 +0000 (UTC) IronPort-HdrOrdr: A9a23:GUOow6zr/8aI6j5AsWZfKrPwEL1zdoMgy1knxilNoH1uA6ilfqWV8cjzuiWbtN9vYhsdcLy7WZVoIkmskKKdg7NhXotKNTOO0ASVxepZnOnfKlPbexHWx6p00KdMV+xEAsTsMF4St63HyTj9P9E+4NTvysyVuds= X-IronPort-AV: E=Sophos;i="5.84,361,1620662400"; d="scan'208";a="113656472" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 29 Aug 2021 20:25:56 +0800 Received: from G08CNEXMBPEKD05.g08.fujitsu.local (unknown [10.167.33.204]) by cn.fujitsu.com (Postfix) with ESMTP id F21474D0D4A1; Sun, 29 Aug 2021 20:25:49 +0800 (CST) Received: from G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.85) by G08CNEXMBPEKD05.g08.fujitsu.local (10.167.33.204) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 29 Aug 2021 20:25:47 +0800 Received: from irides.mr.mr.mr (10.167.225.141) by G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.209) with Microsoft SMTP Server id 15.0.1497.23 via Frontend Transport; Sun, 29 Aug 2021 20:25:43 +0800 From: Shiyang Ruan To: , , CC: , , , , , , , , Subject: [PATCH v8 6/7] xfs: support CoW in fsdax mode Date: Sun, 29 Aug 2021 20:25:16 +0800 Message-ID: <20210829122517.1648171-7-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> References: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: F21474D0D4A1.A3EE9 X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No In fsdax mode, WRITE and ZERO on a shared extent need CoW performed. After that, new allocated extents needs to be remapped to the file. Add an implementation of ->iomap_end() for dax write ops to do the remapping work. Signed-off-by: Shiyang Ruan --- fs/dax.c | 39 ++++++++++++++++++++++++++++++++++++--- fs/iomap/buffered-io.c | 3 ++- fs/xfs/xfs_bmap_util.c | 3 +-- fs/xfs/xfs_file.c | 4 ++-- fs/xfs/xfs_iomap.c | 32 +++++++++++++++++++++++++++++++- fs/xfs/xfs_iomap.h | 32 ++++++++++++++++++++++++++++++++ fs/xfs/xfs_iops.c | 7 +++---- fs/xfs/xfs_reflink.c | 3 +-- include/linux/dax.h | 4 ++++ include/linux/iomap.h | 1 + 10 files changed, 113 insertions(+), 15 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index a1232d6b7e37..88541b734f97 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1401,6 +1401,39 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, } EXPORT_SYMBOL_GPL(dax_iomap_rw); +int +dax_iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, + bool *did_zero, const struct iomap_ops *ops) +{ + struct iomap_iter iomi = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_ZERO, + }; + int ret; + + while ((ret = iomap_iter(&iomi, ops)) > 0) + iomi.processed = iomap_zero_iter(&iomi, did_zero); + + return ret; +} +EXPORT_SYMBOL_GPL(dax_iomap_zero_range); + +int +dax_iomap_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_iomap_zero_range(inode, pos, blocksize - off, did_zero, ops); +} +EXPORT_SYMBOL_GPL(dax_iomap_truncate_page); + static vm_fault_t dax_fault_return(int error) { if (error == 0) @@ -1521,7 +1554,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, } static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, - int *iomap_errp, const struct iomap_ops *ops) + int *iomap_errp, const struct iomap_ops *ops) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; XA_STATE(xas, &mapping->i_pages, vmf->pgoff); @@ -1631,7 +1664,7 @@ static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state *xas, } static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, - const struct iomap_ops *ops) + const struct iomap_ops *ops) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER); @@ -1732,7 +1765,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, * successfully. */ vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, - pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops) + pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops) { switch (pe_size) { case PE_SIZE_PTE: diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 6e8d40877d01..6341a1328def 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -887,7 +887,7 @@ static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) return iomap_write_end(iter, pos, bytes, bytes, page); } -static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) +loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { const struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); @@ -918,6 +918,7 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) return written; } +EXPORT_SYMBOL_GPL(iomap_zero_iter); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 213a97a921bb..f1b7a2637a1d 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1009,8 +1009,7 @@ xfs_free_file_space( return 0; if (offset + len > XFS_ISIZE(ip)) len = XFS_ISIZE(ip) - offset; - error = iomap_zero_range(VFS_I(ip), offset, len, NULL, - &xfs_buffered_write_iomap_ops); + error = xfs_iomap_zero_range(ip, offset, len, NULL); if (error) return error; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index cc3cfb12df53..d57f94c523c7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -704,7 +704,7 @@ xfs_file_dax_write( pos = iocb->ki_pos; trace_xfs_file_dax_write(iocb, from); - ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops); + ret = dax_iomap_rw(iocb, from, &xfs_dax_write_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); @@ -1329,7 +1329,7 @@ __xfs_filemap_fault( ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, (write_fault && !vmf->cow_page) ? - &xfs_direct_write_iomap_ops : + &xfs_dax_write_iomap_ops : &xfs_read_iomap_ops); if (ret & VM_FAULT_NEEDDSYNC) ret = dax_finish_sync_fault(vmf, pe_size, pfn); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d8cd2583dedb..c037a47004f9 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -761,7 +761,8 @@ xfs_direct_write_iomap_begin( /* may drop and re-acquire the ilock */ error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared, - &lockmode, flags & IOMAP_DIRECT); + &lockmode, + (flags & IOMAP_DIRECT) || IS_DAX(inode)); if (error) goto out_unlock; if (shared) @@ -854,6 +855,35 @@ const struct iomap_ops xfs_direct_write_iomap_ops = { .iomap_begin = xfs_direct_write_iomap_begin, }; +static int +xfs_dax_write_iomap_end( + struct inode *inode, + loff_t pos, + loff_t length, + ssize_t written, + unsigned flags, + struct iomap *iomap) +{ + int error = 0; + struct xfs_inode *ip = XFS_I(inode); + bool cow = xfs_is_cow_inode(ip); + const struct iomap_iter *iter = + container_of(iomap, typeof(*iter), iomap); + + if (cow) { + if (iter->processed <= 0) + xfs_reflink_cancel_cow_range(ip, pos, length, true); + else + error = xfs_reflink_end_cow(ip, pos, iter->processed); + } + return error ?: iter->processed; +} + +const struct iomap_ops xfs_dax_write_iomap_ops = { + .iomap_begin = xfs_direct_write_iomap_begin, + .iomap_end = xfs_dax_write_iomap_end, +}; + static int xfs_buffered_write_iomap_begin( struct inode *inode, diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 7d3703556d0e..1ca9f9102523 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -45,5 +45,37 @@ extern const struct iomap_ops xfs_direct_write_iomap_ops; extern const struct iomap_ops xfs_read_iomap_ops; extern const struct iomap_ops xfs_seek_iomap_ops; extern const struct iomap_ops xfs_xattr_iomap_ops; +extern const struct iomap_ops xfs_dax_write_iomap_ops; + +static inline int +xfs_iomap_zero_range( + struct xfs_inode *ip, + loff_t pos, + loff_t len, + bool *did_zero) +{ + struct inode *inode = VFS_I(ip); + + return IS_DAX(inode) + ? dax_iomap_zero_range(inode, pos, len, did_zero, + &xfs_dax_write_iomap_ops) + : iomap_zero_range(inode, pos, len, did_zero, + &xfs_buffered_write_iomap_ops); +} + +static inline int +xfs_iomap_truncate_page( + struct xfs_inode *ip, + loff_t pos, + bool *did_zero) +{ + struct inode *inode = VFS_I(ip); + + return IS_DAX(inode) + ? dax_iomap_truncate_page(inode, pos, did_zero, + &xfs_dax_write_iomap_ops) + : iomap_truncate_page(inode, pos, did_zero, + &xfs_buffered_write_iomap_ops); +} #endif /* __XFS_IOMAP_H__*/ diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 93c082db04b7..0380f6942bc0 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -911,8 +911,8 @@ xfs_setattr_size( */ if (newsize > oldsize) { trace_xfs_zero_eof(ip, oldsize, newsize - oldsize); - error = iomap_zero_range(inode, oldsize, newsize - oldsize, - &did_zeroing, &xfs_buffered_write_iomap_ops); + error = xfs_iomap_zero_range(ip, oldsize, newsize - oldsize, + &did_zeroing); } else { /* * iomap won't detect a dirty page over an unwritten block (or a @@ -924,8 +924,7 @@ xfs_setattr_size( newsize); if (error) return error; - error = iomap_truncate_page(inode, newsize, &did_zeroing, - &xfs_buffered_write_iomap_ops); + error = xfs_iomap_truncate_page(ip, newsize, &did_zeroing); } if (error) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 28effe537d07..13e461cf2055 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1269,8 +1269,7 @@ xfs_reflink_zero_posteof( return 0; trace_xfs_zero_eof(ip, isize, pos - isize); - return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL, - &xfs_buffered_write_iomap_ops); + return xfs_iomap_zero_range(ip, isize, pos - isize, NULL); } /* diff --git a/include/linux/dax.h b/include/linux/dax.h index 8ecd125434ef..96b1f0bb4ab8 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -237,6 +237,10 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); +int dax_iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, + bool *did_zero, const struct iomap_ops *ops); +int dax_iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); s64 dax_iomap_zero(loff_t pos, u64 length, const struct iomap *iomap, const struct iomap *srcmap); int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 24f8489583ca..b32cbdb74c49 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -235,6 +235,7 @@ int iomap_migrate_page(struct address_space *mapping, struct page *newpage, #endif int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); +loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, From patchwork Sun Aug 29 12:25:17 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12463897 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id B3E1F3FC6 for ; Sun, 29 Aug 2021 12:26:02 +0000 (UTC) IronPort-HdrOrdr: A9a23:S8vJoqjzGyl/1NnrZVeaRdGVgnBQXj4ji2hC6mlwRA09TySZ//rBoB19726TtN9xYgBYpTnuAsm9qB/nmaKdpLNhWItKPzOW31dATrsSjrcKqgeIc0aVm9K1l50QF5SWY+eQMbEVt6nHCXGDYrQdKce8gd2VrNab33FwVhtrdq0lyw94DzyQGkpwSBIuP+tDKLOsotpAuyG7eWkaKuCyBnw+VeDFoNHR0L38ZxpuPW9c1CC+ySOv9KXhEwWVmjMXUzZ0y78k9mTf1yzVj5/Ty82G9g== X-IronPort-AV: E=Sophos;i="5.84,361,1620662400"; d="scan'208";a="113656488" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 29 Aug 2021 20:26:02 +0800 Received: from G08CNEXMBPEKD06.g08.fujitsu.local (unknown [10.167.33.206]) by cn.fujitsu.com (Postfix) with ESMTP id 77ACE4D0D9D7; Sun, 29 Aug 2021 20:25:56 +0800 (CST) Received: from G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.85) by G08CNEXMBPEKD06.g08.fujitsu.local (10.167.33.206) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 29 Aug 2021 20:25:50 +0800 Received: from irides.mr.mr.mr (10.167.225.141) by G08CNEXCHPEKD09.g08.fujitsu.local (10.167.33.209) with Microsoft SMTP Server id 15.0.1497.23 via Frontend Transport; Sun, 29 Aug 2021 20:25:50 +0800 From: Shiyang Ruan To: , , CC: , , , , , , , , Subject: [PATCH v8 7/7] xfs: Add dax dedupe support Date: Sun, 29 Aug 2021 20:25:17 +0800 Message-ID: <20210829122517.1648171-8-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> References: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: 77ACE4D0D9D7.A3E34 X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No Introduce xfs_mmaplock_two_inodes_and_break_dax_layout() for dax files who are going to be deduped. After that, call compare range function only when files are both DAX or not. Signed-off-by: Shiyang Ruan Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_file.c | 2 +- fs/xfs/xfs_inode.c | 57 ++++++++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_inode.h | 1 + fs/xfs/xfs_reflink.c | 4 ++-- 4 files changed, 61 insertions(+), 3 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index d57f94c523c7..e23f2cfa4da8 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -846,7 +846,7 @@ xfs_wait_dax_page( xfs_ilock(ip, XFS_MMAPLOCK_EXCL); } -static int +int xfs_break_dax_layouts( struct inode *inode, bool *retry) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 990b72ae3635..4b44d9d1e42a 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3727,6 +3727,59 @@ xfs_iolock_two_inodes_and_break_layout( return 0; } +static int +xfs_mmaplock_two_inodes_and_break_dax_layout( + struct xfs_inode *ip1, + struct xfs_inode *ip2) +{ + int error, attempts = 0; + bool retry; + struct page *page; + struct xfs_log_item *lp; + + if (ip1->i_ino > ip2->i_ino) + swap(ip1, ip2); + +again: + retry = false; + /* Lock the first inode */ + xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); + error = xfs_break_dax_layouts(VFS_I(ip1), &retry); + if (error || retry) { + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + goto again; + } + + if (ip1 == ip2) + return 0; + + /* Nested lock the second inode */ + lp = &ip1->i_itemp->ili_item; + if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) { + if (!xfs_ilock_nowait(ip2, + xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1))) { + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + if ((++attempts % 5) == 0) + delay(1); /* Don't just spin the CPU */ + goto again; + } + } else + xfs_ilock(ip2, xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1)); + /* + * We cannot use xfs_break_dax_layouts() directly here because it may + * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable + * for this nested lock case. + */ + page = dax_layout_busy_page(VFS_I(ip2)->i_mapping); + if (page && page_ref_count(page) != 1) { + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + goto again; + } + + return 0; +} + /* * Lock two inodes so that userspace cannot initiate I/O via file syscalls or * mmap activity. @@ -3741,6 +3794,10 @@ xfs_ilock2_io_mmap( ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2)); if (ret) return ret; + + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) + return xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2); + if (ip1 == ip2) xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); else diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 4b6703dbffb8..f1547330b087 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -456,6 +456,7 @@ enum xfs_prealloc_flags { int xfs_update_prealloc_flags(struct xfs_inode *ip, enum xfs_prealloc_flags flags); +int xfs_break_dax_layouts(struct inode *inode, bool *retry); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 13e461cf2055..86c737c2baeb 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1327,8 +1327,8 @@ xfs_reflink_remap_prep( if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) goto out_unlock; - /* Don't share DAX file data for now. */ - if (IS_DAX(inode_in) || IS_DAX(inode_out)) + /* Don't share DAX file data with non-DAX file. */ + if (IS_DAX(inode_in) != IS_DAX(inode_out)) goto out_unlock; if (!IS_DAX(inode_in))