From patchwork Sun Feb 13 12:58:32 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12744572 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id A09E1365 for ; Sun, 13 Feb 2022 12:59:51 +0000 (UTC) IronPort-Data: A9a23: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 IronPort-HdrOrdr: A9a23:ZCsgAqhGJWnWRItFyewITUkRQnBQXuYji2hC6mlwRA09TyX4rbHLoB1/73LJYVkqNk3I5urrBEDtexLhHP1OkOws1NWZLWrbUQKTRekM0WKI+UyDJ8SRzI5g/JYlW61/Jfm1NlJikPv9iTPSL/8QhPWB74Ck7N2z80tQ X-IronPort-AV: E=Sophos;i="5.88,333,1635177600"; d="scan'208";a="121469419" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 13 Feb 2022 20:58:38 +0800 Received: from G08CNEXMBPEKD04.g08.fujitsu.local (unknown [10.167.33.201]) by cn.fujitsu.com (Postfix) with ESMTP id 3C2374D169D8; Sun, 13 Feb 2022 20:58:34 +0800 (CST) Received: from G08CNEXJMPEKD02.g08.fujitsu.local (10.167.33.202) by G08CNEXMBPEKD04.g08.fujitsu.local (10.167.33.201) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Sun, 13 Feb 2022 20:58:36 +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, 13 Feb 2022 20:58:35 +0800 Received: from irides.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, 13 Feb 2022 20:58:33 +0800 From: Shiyang Ruan To: CC: , , , , , , , , Subject: [PATCH v10.1 1/9] dax: Introduce holder for dax_device Date: Sun, 13 Feb 2022 20:58:32 +0800 Message-ID: <20220213125832.2722009-1-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: References: Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: 3C2374D169D8.A0F17 X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No v10.1 update: - Fix build error reported by kernel test robot - Add return code to dax_register_holder() - Add write lock to prevent concurrent registrations - Rename dax_get_holder() to dax_holder() - Add kernel doc for new added functions To easily track filesystem from a pmem device, we introduce a holder for dax_device structure, and also its operation. This holder is used to remember who is using this dax_device: - When it is the backend of a filesystem, the holder will be the instance of this filesystem. - When this pmem device is one of the targets in a mapped device, the holder will be this mapped device. In this case, the mapped device has its own dax_device and it will follow the first rule. So that we can finally track to the filesystem we needed. The holder and holder_ops will be set when filesystem is being mounted, or an target device is being activated. Signed-off-by: Shiyang Ruan --- drivers/dax/super.c | 95 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/dax.h | 30 ++++++++++++++ 2 files changed, 125 insertions(+) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e3029389d809..d7fb4c36bf16 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -21,6 +21,9 @@ * @cdev: optional character interface for "device dax" * @private: dax driver private data * @flags: state and boolean properties + * @ops: operations for dax_device + * @holder_data: holder of a dax_device: could be filesystem or mapped device + * @holder_ops: operations for the inner holder */ struct dax_device { struct inode inode; @@ -28,6 +31,9 @@ struct dax_device { void *private; unsigned long flags; const struct dax_operations *ops; + void *holder_data; + struct percpu_rw_semaphore holder_rwsem; + const struct dax_holder_operations *holder_ops; }; static dev_t dax_devt; @@ -193,6 +199,29 @@ int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, } EXPORT_SYMBOL_GPL(dax_zero_page_range); +int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, + u64 len, int mf_flags) +{ + int rc, id; + + id = dax_read_lock(); + if (!dax_alive(dax_dev)) { + rc = -ENXIO; + goto out; + } + + if (!dax_dev->holder_ops) { + rc = -EOPNOTSUPP; + goto out; + } + + rc = dax_dev->holder_ops->notify_failure(dax_dev, off, len, mf_flags); +out: + dax_read_unlock(id); + return rc; +} +EXPORT_SYMBOL_GPL(dax_holder_notify_failure); + #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size) @@ -268,6 +297,13 @@ void kill_dax(struct dax_device *dax_dev) clear_bit(DAXDEV_ALIVE, &dax_dev->flags); synchronize_srcu(&dax_srcu); + + /* Lock to prevent concurrent registrations. */ + percpu_down_write(&dax_dev->holder_rwsem); + /* clear holder data */ + dax_dev->holder_ops = NULL; + dax_dev->holder_data = NULL; + percpu_up_write(&dax_dev->holder_rwsem); } EXPORT_SYMBOL_GPL(kill_dax); @@ -393,6 +429,7 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) dax_dev->ops = ops; dax_dev->private = private; + percpu_init_rwsem(&dax_dev->holder_rwsem); return dax_dev; err_dev: @@ -409,6 +446,64 @@ void put_dax(struct dax_device *dax_dev) } EXPORT_SYMBOL_GPL(put_dax); +/** + * dax_holder() - obtain the holder of a dax device + * @dax_dev: a dax_device instance + + * Return: the holder's data which represents the holder if registered, + * otherwize NULL. + */ +void *dax_holder(struct dax_device *dax_dev) +{ + if (!dax_alive(dax_dev)) + return NULL; + + return dax_dev->holder_data; +} +EXPORT_SYMBOL_GPL(dax_holder); + +/** + * dax_register_holder() - register a holder to a dax device + * @dax_dev: a dax_device instance + * @holder: a pointer to a holder's data which represents the holder + * @ops: operations of this holder + + * Return: negative errno if an error occurs, otherwise 0. + */ +int dax_register_holder(struct dax_device *dax_dev, void *holder, + const struct dax_holder_operations *ops) +{ + if (!dax_alive(dax_dev)) + return -ENXIO; + + /* Already registered */ + if (dax_holder(dax_dev)) + return -EBUSY; + + /* Lock to prevent concurrent registrations. */ + percpu_down_write(&dax_dev->holder_rwsem); + dax_dev->holder_data = holder; + dax_dev->holder_ops = ops; + percpu_up_write(&dax_dev->holder_rwsem); + + return 0; +} +EXPORT_SYMBOL_GPL(dax_register_holder); + +/** + * dax_unregister_holder() - unregister the holder for a dax device + * @dax_dev: a dax_device instance + */ +void dax_unregister_holder(struct dax_device *dax_dev) +{ + if (!dax_alive(dax_dev)) + return; + + dax_dev->holder_data = NULL; + dax_dev->holder_ops = NULL; +} +EXPORT_SYMBOL_GPL(dax_unregister_holder); + /** * inode_dax: convert a public inode into its dax_dev * @inode: An inode with i_cdev pointing to a dax_dev diff --git a/include/linux/dax.h b/include/linux/dax.h index 9fc5f99a0ae2..9800d84e5b7d 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -32,8 +32,24 @@ struct dax_operations { int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; +struct dax_holder_operations { + /* + * notify_failure - notify memory failure into inner holder device + * @dax_dev: the dax device which contains the holder + * @offset: offset on this dax device where memory failure occurs + * @len: length of this memory failure event + * @flags: action flags for memory failure handler + */ + int (*notify_failure)(struct dax_device *dax_dev, u64 offset, + u64 len, int mf_flags); +}; + #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); +int dax_register_holder(struct dax_device *dax_dev, void *holder, + const struct dax_holder_operations *ops); +void dax_unregister_holder(struct dax_device *dax_dev); +void *dax_holder(struct dax_device *dax_dev); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); @@ -53,6 +69,18 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, return dax_synchronous(dax_dev); } #else +static inline int dax_register_holder(struct dax_device *dax_dev, void *holder, + const struct dax_holder_operations *ops) +{ + return 0; +} +static inline void dax_unregister_holder(struct dax_device *dax_dev) +{ +} +static inline void *dax_holder(struct dax_device *dax_dev) +{ + return NULL; +} static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { @@ -185,6 +213,8 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); +int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len, + int mf_flags); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, From patchwork Sun Feb 13 13:02:24 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyang Ruan X-Patchwork-Id: 12744573 Received: from heian.cn.fujitsu.com (mail.cn.fujitsu.com [183.91.158.132]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 359FF365 for ; Sun, 13 Feb 2022 13:02:28 +0000 (UTC) IronPort-Data: A9a23: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 IronPort-HdrOrdr: A9a23:G+psY6nzboX0taoWyHyHPQX1Zl3pDfIQ3DAbv31ZSRFFG/Fw9vre+MjzsCWYtN9/Yh8dcK+7UpVoLUm8yXcX2/h1AV7BZniEhILAFugLgrcKqAeQeREWmNQ86Y5QN4B6CPDVSWNxlNvG5mCDeOoI8Z2q97+JiI7lo0tQcQ== X-IronPort-AV: E=Sophos;i="5.88,333,1635177600"; d="scan'208";a="121469485" Received: from unknown (HELO cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 13 Feb 2022 21:02:28 +0800 Received: from G08CNEXMBPEKD05.g08.fujitsu.local (unknown [10.167.33.204]) by cn.fujitsu.com (Postfix) with ESMTP id 0EDFD4D169D8; Sun, 13 Feb 2022 21:02:25 +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, 13 Feb 2022 21:02:27 +0800 Received: from irides.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, 13 Feb 2022 21:02:24 +0800 From: Shiyang Ruan To: CC: , , , , , , , , Subject: [PATCH v10.1 8/9] xfs: Implement ->notify_failure() for XFS Date: Sun, 13 Feb 2022 21:02:24 +0800 Message-ID: <20220213130224.2723912-1-ruansy.fnst@fujitsu.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20220201204140.GC8338@magnolia> References: <20220201204140.GC8338@magnolia> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-yoursite-MailScanner-ID: 0EDFD4D169D8.A8F86 X-yoursite-MailScanner: Found to be clean X-yoursite-MailScanner-From: ruansy.fnst@fujitsu.com X-Spam-Status: No v10.1 update: - Handle the error code returns by dax_register_holder() - In v10.1, dax_register_holder() will hold a write lock so XFS doesn't need to hold a lock - Fix the mistake in failure notification over two AGs - Fix the year in copyright message Introduce xfs_notify_failure.c to handle failure related works, such as implement ->notify_failure(), register/unregister dax holder in xfs, and so on. If the rmap feature of XFS enabled, we can query it to find files and metadata which are associated with the corrupt data. For now all we do is kill processes with that file mapped into their address spaces, but future patches could actually do something about corrupt metadata. After that, the memory failure needs to notify the processes who are using those files. Signed-off-by: Shiyang Ruan --- fs/xfs/Makefile | 1 + fs/xfs/xfs_buf.c | 12 ++ fs/xfs/xfs_fsops.c | 3 + fs/xfs/xfs_mount.h | 1 + fs/xfs/xfs_notify_failure.c | 225 ++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_notify_failure.h | 10 ++ 6 files changed, 252 insertions(+) create mode 100644 fs/xfs/xfs_notify_failure.c create mode 100644 fs/xfs/xfs_notify_failure.h diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 04611a1068b4..389970b3e13b 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -84,6 +84,7 @@ xfs-y += xfs_aops.o \ xfs_message.o \ xfs_mount.o \ xfs_mru_cache.o \ + xfs_notify_failure.o \ xfs_pwork.o \ xfs_reflink.o \ xfs_stats.o \ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index b45e0d50a405..941e8825cee6 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -19,6 +19,7 @@ #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_ag.h" +#include "xfs_notify_failure.h" static struct kmem_cache *xfs_buf_cache; @@ -1892,6 +1893,8 @@ xfs_free_buftarg( list_lru_destroy(&btp->bt_lru); blkdev_issue_flush(btp->bt_bdev); + if (btp->bt_daxdev) + dax_unregister_holder(btp->bt_daxdev); fs_put_dax(btp->bt_daxdev); kmem_free(btp); @@ -1939,6 +1942,7 @@ xfs_alloc_buftarg( struct block_device *bdev) { xfs_buftarg_t *btp; + int error; btp = kmem_zalloc(sizeof(*btp), KM_NOFS); @@ -1946,6 +1950,14 @@ xfs_alloc_buftarg( btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off); + if (btp->bt_daxdev) { + error = dax_register_holder(btp->bt_daxdev, mp, + &xfs_dax_holder_operations); + if (error) { + xfs_err(mp, "DAX device already in use?!"); + goto error_free; + } + } /* * Buffer IO error rate limiting. Limit it to no more than 10 messages diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 33e26690a8c4..d4d36c5bef11 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -542,6 +542,9 @@ xfs_do_force_shutdown( } else if (flags & SHUTDOWN_CORRUPT_INCORE) { tag = XFS_PTAG_SHUTDOWN_CORRUPT; why = "Corruption of in-memory data"; + } else if (flags & SHUTDOWN_CORRUPT_ONDISK) { + tag = XFS_PTAG_SHUTDOWN_CORRUPT; + why = "Corruption of on-disk metadata"; } else { tag = XFS_PTAG_SHUTDOWN_IOERROR; why = "Metadata I/O Error"; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 00720a02e761..47ff4ac53c4c 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -435,6 +435,7 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname, #define SHUTDOWN_LOG_IO_ERROR 0x0002 /* write attempt to the log failed */ #define SHUTDOWN_FORCE_UMOUNT 0x0004 /* shutdown from a forced unmount */ #define SHUTDOWN_CORRUPT_INCORE 0x0008 /* corrupt in-memory data structures */ +#define SHUTDOWN_CORRUPT_ONDISK 0x0010 /* corrupt metadata on device */ #define XFS_SHUTDOWN_STRINGS \ { SHUTDOWN_META_IO_ERROR, "metadata_io" }, \ diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c new file mode 100644 index 000000000000..aa67662210a1 --- /dev/null +++ b/fs/xfs/xfs_notify_failure.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Fujitsu. All Rights Reserved. + */ + +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_alloc.h" +#include "xfs_bit.h" +#include "xfs_btree.h" +#include "xfs_inode.h" +#include "xfs_icache.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_trans.h" + +#include +#include + +struct failure_info { + xfs_agblock_t startblock; + xfs_extlen_t blockcount; + int mf_flags; +}; + +#if IS_ENABLED(CONFIG_MEMORY_FAILURE) && IS_ENABLED(CONFIG_FS_DAX) +static pgoff_t +xfs_failure_pgoff( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rec, + const struct failure_info *notify) +{ + uint64_t pos = rec->rm_offset; + + if (notify->startblock > rec->rm_startblock) + pos += XFS_FSB_TO_B(mp, + notify->startblock - rec->rm_startblock); + return pos >> PAGE_SHIFT; +} + +static unsigned long +xfs_failure_pgcnt( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rec, + const struct failure_info *notify) +{ + xfs_agblock_t end_rec; + xfs_agblock_t end_notify; + xfs_agblock_t start_cross; + xfs_agblock_t end_cross; + + start_cross = max(rec->rm_startblock, notify->startblock); + + end_rec = rec->rm_startblock + rec->rm_blockcount; + end_notify = notify->startblock + notify->blockcount; + end_cross = min(end_rec, end_notify); + + return XFS_FSB_TO_B(mp, end_cross - start_cross) >> PAGE_SHIFT; +} + +static int +xfs_dax_failure_fn( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *data) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip; + struct failure_info *notify = data; + int error = 0; + + if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) || + (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + + /* Get files that incore, filter out others that are not in use. */ + error = xfs_iget(mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE, + 0, &ip); + /* Continue the rmap query if the inode isn't incore */ + if (error == -ENODATA) + return 0; + if (error) + return error; + + error = mf_dax_kill_procs(VFS_I(ip)->i_mapping, + xfs_failure_pgoff(mp, rec, notify), + xfs_failure_pgcnt(mp, rec, notify), + notify->mf_flags); + xfs_irele(ip); + return error; +} +#else +static int +xfs_dax_failure_fn( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *data) +{ + struct xfs_mount *mp = cur->bc_mp; + + /* No other option besides shutting down the fs. */ + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; +} +#endif /* CONFIG_MEMORY_FAILURE && CONFIG_FS_DAX */ + +static int +xfs_dax_notify_ddev_failure( + struct xfs_mount *mp, + xfs_daddr_t daddr, + xfs_daddr_t bblen, + int mf_flags) +{ + struct xfs_trans *tp = NULL; + struct xfs_btree_cur *cur = NULL; + struct xfs_buf *agf_bp = NULL; + int error = 0; + xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr); + xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); + xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen); + xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno); + + error = xfs_trans_alloc_empty(mp, &tp); + if (error) + return error; + + for (; agno <= end_agno; agno++) { + struct xfs_rmap_irec ri_low = { }; + struct xfs_rmap_irec ri_high; + struct failure_info notify; + struct xfs_agf *agf; + xfs_agblock_t agend; + + error = xfs_alloc_read_agf(mp, tp, agno, 0, &agf_bp); + if (error) + break; + + cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, agf_bp->b_pag); + + /* + * Set the rmap range from ri_low to ri_high, which represents + * a [start, end] where we looking for the files or metadata. + * The part of range out of a AG will be ignored. So, it's fine + * to set ri_low to "startblock" in all loops. When it reaches + * the last AG, set the ri_high to "endblock" to make sure we + * actually end at the end. + */ + memset(&ri_high, 0xFF, sizeof(ri_high)); + ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno); + if (agno == end_agno) + ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); + + agf = agf_bp->b_addr; + agend = min(be32_to_cpu(agf->agf_length), + ri_high.rm_startblock); + notify.startblock = ri_low.rm_startblock; + notify.blockcount = agend - ri_low.rm_startblock; + + error = xfs_rmap_query_range(cur, &ri_low, &ri_high, + xfs_dax_failure_fn, ¬ify); + xfs_btree_del_cursor(cur, error); + xfs_trans_brelse(tp, agf_bp); + if (error) + break; + + fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0); + } + + xfs_trans_cancel(tp); + return error; +} + +static int +xfs_dax_notify_failure( + struct dax_device *dax_dev, + u64 offset, + u64 len, + int mf_flags) +{ + struct xfs_mount *mp = dax_holder(dax_dev); + + if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { + xfs_warn(mp, + "notify_failure() not supported on realtime device!"); + return -EOPNOTSUPP; + } + + if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev && + mp->m_logdev_targp != mp->m_ddev_targp) { + xfs_err(mp, "ondisk log corrupt, shutting down fs!"); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + + if (!xfs_has_rmapbt(mp)) { + xfs_warn(mp, "notify_failure() needs rmapbt enabled!"); + return -EOPNOTSUPP; + } + + /* Ignore the range out of filesystem area */ + if ((offset + len) < mp->m_ddev_targp->bt_dax_part_off) + return -ENXIO; + if (offset > (mp->m_ddev_targp->bt_dax_part_off + + mp->m_ddev_targp->bt_bdev->bd_nr_sectors)) + return -ENXIO; + + if (offset > mp->m_ddev_targp->bt_dax_part_off) + offset -= mp->m_ddev_targp->bt_dax_part_off; + else + offset = 0; + + return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len), + mf_flags); +} + +const struct dax_holder_operations xfs_dax_holder_operations = { + .notify_failure = xfs_dax_notify_failure, +}; diff --git a/fs/xfs/xfs_notify_failure.h b/fs/xfs/xfs_notify_failure.h new file mode 100644 index 000000000000..76187b9620f9 --- /dev/null +++ b/fs/xfs/xfs_notify_failure.h @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Fujitsu. All Rights Reserved. + */ +#ifndef __XFS_NOTIFY_FAILURE_H__ +#define __XFS_NOTIFY_FAILURE_H__ + +extern const struct dax_holder_operations xfs_dax_holder_operations; + +#endif /* __XFS_NOTIFY_FAILURE_H__ */