From: Christoph Hellwig hch@lst.de

commit 9ff4490e2ab364ec433f15668ef3f5edfb53feca upstream.

oss.sgi.com is long dead, refer to the current linux-xfs list instead.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- Documentation/ABI/testing/sysfs-fs-xfs | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-fs-xfs b/Documentation/ABI/testing/sysfs-fs-xfs index f704925f6fe9..82d8e2f79834 100644 --- a/Documentation/ABI/testing/sysfs-fs-xfs +++ b/Documentation/ABI/testing/sysfs-fs-xfs @@ -1,7 +1,7 @@ What: /sys/fs/xfs/<disk>/log/log_head_lsn Date: July 2014 KernelVersion: 3.17 -Contact: xfs@oss.sgi.com +Contact: linux-xfs@vger.kernel.org Description: The log sequence number (LSN) of the current head of the log. The LSN is exported in "cycle:basic block" format. @@ -10,7 +10,7 @@ Users: xfstests What: /sys/fs/xfs/<disk>/log/log_tail_lsn Date: July 2014 KernelVersion: 3.17 -Contact: xfs@oss.sgi.com +Contact: linux-xfs@vger.kernel.org Description: The log sequence number (LSN) of the current tail of the log. The LSN is exported in "cycle:basic block" format. @@ -18,7 +18,7 @@ Description: What: /sys/fs/xfs/<disk>/log/reserve_grant_head Date: July 2014 KernelVersion: 3.17 -Contact: xfs@oss.sgi.com +Contact: linux-xfs@vger.kernel.org Description: The current state of the log reserve grant head. It represents the total log reservation of all currently @@ -29,7 +29,7 @@ Users: xfstests What: /sys/fs/xfs/<disk>/log/write_grant_head Date: July 2014 KernelVersion: 3.17 -Contact: xfs@oss.sgi.com +Contact: linux-xfs@vger.kernel.org Description: The current state of the log write grant head. It represents the total log reservation of all currently

From: "Darrick J. Wong" djwong@kernel.org

commit 150bb10a28b9c8709ae227fc898d9cf6136faa1e upstream.

generic/388 has an annoying tendency to fail like this during log recovery:

XFS (sda4): Unmounting Filesystem 435fe39b-82b6-46ef-be56-819499585130 XFS (sda4): Mounting V5 Filesystem 435fe39b-82b6-46ef-be56-819499585130 XFS (sda4): Starting recovery (logdev: internal) 00000000: 49 4e 81 b6 03 02 00 00 00 00 00 07 00 00 00 07 IN.............. 00000010: 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00 10 ................ 00000020: 35 9a 8b c1 3e 6e 81 00 35 9a 8b c1 3f dc b7 00 5...>n..5...?... 00000030: 35 9a 8b c1 3f dc b7 00 00 00 00 00 00 3c 86 4f 5...?........<.O 00000040: 00 00 00 00 00 00 02 f3 00 00 00 00 00 00 00 00 ................ 00000050: 00 00 1f 01 00 00 00 00 00 00 00 02 b2 74 c9 0b .............t.. 00000060: ff ff ff ff d7 45 73 10 00 00 00 00 00 00 00 2d .....Es........- 00000070: 00 00 07 92 00 01 fe 30 00 00 00 00 00 00 00 1a .......0........ 00000080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000090: 35 9a 8b c1 3b 55 0c 00 00 00 00 00 04 27 b2 d1 5...;U.......'.. 000000a0: 43 5f e3 9b 82 b6 46 ef be 56 81 94 99 58 51 30 C_....F..V...XQ0 XFS (sda4): Internal error Bad dinode after recovery at line 539 of file fs/xfs/xfs_inode_item_recover.c. Caller xlog_recover_items_pass2+0x4e/0xc0 [xfs] CPU: 0 PID: 2189311 Comm: mount Not tainted 6.9.0-rc4-djwx #rc4 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20171121_152543-x86-ol7-builder-01.us.oracle.com-4.el7.1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x4f/0x60 xfs_corruption_error+0x90/0xa0 xlog_recover_inode_commit_pass2+0x5f1/0xb00 xlog_recover_items_pass2+0x4e/0xc0 xlog_recover_commit_trans+0x2db/0x350 xlog_recovery_process_trans+0xab/0xe0 xlog_recover_process_data+0xa7/0x130 xlog_do_recovery_pass+0x398/0x840 xlog_do_log_recovery+0x62/0xc0 xlog_do_recover+0x34/0x1d0 xlog_recover+0xe9/0x1a0 xfs_log_mount+0xff/0x260 xfs_mountfs+0x5d9/0xb60 xfs_fs_fill_super+0x76b/0xa30 get_tree_bdev+0x124/0x1d0 vfs_get_tree+0x17/0xa0 path_mount+0x72b/0xa90 __x64_sys_mount+0x112/0x150 do_syscall_64+0x49/0x100 entry_SYSCALL_64_after_hwframe+0x4b/0x53 </TASK> XFS (sda4): Corruption detected. Unmount and run xfs_repair XFS (sda4): Metadata corruption detected at xfs_dinode_verify.part.0+0x739/0x920 [xfs], inode 0x427b2d1 XFS (sda4): Filesystem has been shut down due to log error (0x2). XFS (sda4): Please unmount the filesystem and rectify the problem(s). XFS (sda4): log mount/recovery failed: error -117 XFS (sda4): log mount failed

This inode log item recovery failing the dinode verifier after replaying the contents of the inode log item into the ondisk inode. Looking back into what the kernel was doing at the time of the fs shutdown, a thread was in the middle of running a series of transactions, each of which committed changes to the inode.

At some point in the middle of that chain, an invalid (at least according to the verifier) change was committed. Had the filesystem not shut down in the middle of the chain, a subsequent transaction would have corrected the invalid state and nobody would have noticed. But that's not what happened here. Instead, the invalid inode state was committed to the ondisk log, so log recovery tripped over it.

The actual defect here was an overzealous inode verifier, which was fixed in a separate patch. This patch adds some transaction precommit functions for CONFIG_XFS_DEBUG=y mode so that we can detect these kinds of transient errors at transaction commit time, where it's much easier to find the root cause.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/Kconfig | 12 ++++++++++++ fs/xfs/xfs.h | 4 ++++ fs/xfs/xfs_buf_item.c | 32 ++++++++++++++++++++++++++++++++ fs/xfs/xfs_dquot_item.c | 31 +++++++++++++++++++++++++++++++ fs/xfs/xfs_inode_item.c | 32 ++++++++++++++++++++++++++++++++ 5 files changed, 111 insertions(+)

diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 567fb37274d3..ced0e6272aef 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -204,6 +204,18 @@ config XFS_DEBUG

Say N unless you are an XFS developer, or you play one on TV.

+config XFS_DEBUG_EXPENSIVE + bool "XFS expensive debugging checks" + depends on XFS_FS && XFS_DEBUG + help + Say Y here to get an XFS build with expensive debugging checks + enabled. These checks may affect performance significantly. + + Note that the resulting code will be HUGER and SLOWER, and probably + not useful unless you are debugging a particular problem. + + Say N unless you are an XFS developer, or you play one on TV. + config XFS_ASSERT_FATAL bool "XFS fatal asserts" default y diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h index f6ffb4f248f7..9355ccad9503 100644 --- a/fs/xfs/xfs.h +++ b/fs/xfs/xfs.h @@ -10,6 +10,10 @@ #define DEBUG 1 #endif

+#ifdef CONFIG_XFS_DEBUG_EXPENSIVE +#define DEBUG_EXPENSIVE 1 +#endif + #ifdef CONFIG_XFS_ASSERT_FATAL #define XFS_ASSERT_FATAL 1 #endif diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 023d4e0385dd..b02ce568de0c 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -22,6 +22,7 @@ #include "xfs_trace.h" #include "xfs_log.h" #include "xfs_log_priv.h" +#include "xfs_error.h"

struct kmem_cache *xfs_buf_item_cache; @@ -781,8 +782,39 @@ xfs_buf_item_committed( return lsn; }

+#ifdef DEBUG_EXPENSIVE +static int +xfs_buf_item_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_buf_log_item *bip = BUF_ITEM(lip); + struct xfs_buf *bp = bip->bli_buf; + struct xfs_mount *mp = bp->b_mount; + xfs_failaddr_t fa; + + if (!bp->b_ops || !bp->b_ops->verify_struct) + return 0; + if (bip->bli_flags & XFS_BLI_STALE) + return 0; + + fa = bp->b_ops->verify_struct(bp); + if (fa) { + xfs_buf_verifier_error(bp, -EFSCORRUPTED, bp->b_ops->name, + bp->b_addr, BBTOB(bp->b_length), fa); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + ASSERT(fa == NULL); + } + + return 0; +} +#else +# define xfs_buf_item_precommit NULL +#endif + static const struct xfs_item_ops xfs_buf_item_ops = { .iop_size = xfs_buf_item_size, + .iop_precommit = xfs_buf_item_precommit, .iop_format = xfs_buf_item_format, .iop_pin = xfs_buf_item_pin, .iop_unpin = xfs_buf_item_unpin, diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 6a1aae799cf1..7d19091215b0 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -17,6 +17,7 @@ #include "xfs_trans_priv.h" #include "xfs_qm.h" #include "xfs_log.h" +#include "xfs_error.h"

static inline struct xfs_dq_logitem *DQUOT_ITEM(struct xfs_log_item *lip) { @@ -193,8 +194,38 @@ xfs_qm_dquot_logitem_committing( return xfs_qm_dquot_logitem_release(lip); }

+#ifdef DEBUG_EXPENSIVE +static int +xfs_qm_dquot_logitem_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; + struct xfs_mount *mp = dqp->q_mount; + struct xfs_disk_dquot ddq = { }; + xfs_failaddr_t fa; + + xfs_dquot_to_disk(&ddq, dqp); + fa = xfs_dquot_verify(mp, &ddq, dqp->q_id); + if (fa) { + XFS_CORRUPTION_ERROR("Bad dquot during logging", + XFS_ERRLEVEL_LOW, mp, &ddq, sizeof(ddq)); + xfs_alert(mp, + "Metadata corruption detected at %pS, dquot 0x%x", + fa, dqp->q_id); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + ASSERT(fa == NULL); + } + + return 0; +} +#else +# define xfs_qm_dquot_logitem_precommit NULL +#endif + static const struct xfs_item_ops xfs_dquot_item_ops = { .iop_size = xfs_qm_dquot_logitem_size, + .iop_precommit = xfs_qm_dquot_logitem_precommit, .iop_format = xfs_qm_dquot_logitem_format, .iop_pin = xfs_qm_dquot_logitem_pin, .iop_unpin = xfs_qm_dquot_logitem_unpin, diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 155a8b312875..b55ad3b7b113 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -36,6 +36,36 @@ xfs_inode_item_sort( return INODE_ITEM(lip)->ili_inode->i_ino; }

+#ifdef DEBUG_EXPENSIVE +static void +xfs_inode_item_precommit_check( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_dinode *dip; + xfs_failaddr_t fa; + + dip = kzalloc(mp->m_sb.sb_inodesize, GFP_KERNEL | GFP_NOFS); + if (!dip) { + ASSERT(dip != NULL); + return; + } + + xfs_inode_to_disk(ip, dip, 0); + xfs_dinode_calc_crc(mp, dip); + fa = xfs_dinode_verify(mp, ip->i_ino, dip); + if (fa) { + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, + sizeof(*dip), fa); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + ASSERT(fa == NULL); + } + kfree(dip); +} +#else +# define xfs_inode_item_precommit_check(ip) ((void)0) +#endif + /* * Prior to finally logging the inode, we have to ensure that all the * per-modification inode state changes are applied. This includes VFS inode @@ -168,6 +198,8 @@ xfs_inode_item_precommit( iip->ili_fields |= (flags | iip->ili_last_fields); spin_unlock(&iip->ili_lock);

+ xfs_inode_item_precommit_check(ip); + /* * We are done with the log item transaction dirty state, so clear it so * that it doesn't pollute future transactions.

From: "Darrick J. Wong" djwong@kernel.org

commit 24a4e1cb322e2bf0f3a1afd1978b610a23aa8f36 upstream.

I noticed that callers of xfs_qm_vop_dqalloc use the following code to compute the anticipated uid of the new file:

mapped_fsuid(idmap, &init_user_ns);

whereas the VFS uses a slightly different computation for actually assigning i_uid:

mapped_fsuid(idmap, i_user_ns(inode));

Technically, these are not the same things. According to Christian Brauner, the only time that inode->i_sb->s_user_ns != &init_user_ns is when the filesystem was mounted in a new mount namespace by an unpriviledged user. XFS does not allow this, which is why we've never seen bug reports about quotas being incorrect or the uid checks in xfs_qm_vop_create_dqattach tripping debug assertions.

However, this /is/ a logic bomb, so let's make the code consistent.

Link: https://lore.kernel.org/linux-fsdevel/20240617-weitblick-gefertigt-4a41f3711... Fixes: c14329d39f2d ("fs: port fs{g,u}id helpers to mnt_idmap") Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_inode.c | 16 ++++++++++------ fs/xfs/xfs_symlink.c | 8 +++++--- 2 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 7aa73855fab6..1e50cc9a29db 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -982,10 +982,12 @@ xfs_create( prid = xfs_get_initial_prid(dp);

/* - * Make sure that we have allocated dquot(s) on disk. + * Make sure that we have allocated dquot(s) on disk. The uid/gid + * computation code must match what the VFS uses to assign i_[ug]id. + * INHERIT adjusts the gid computation for setgid/grpid systems. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns), - mapped_fsgid(idmap, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, i_user_ns(VFS_I(dp))), + mapped_fsgid(idmap, i_user_ns(VFS_I(dp))), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1131,10 +1133,12 @@ xfs_create_tmpfile( prid = xfs_get_initial_prid(dp);

/* - * Make sure that we have allocated dquot(s) on disk. + * Make sure that we have allocated dquot(s) on disk. The uid/gid + * computation code must match what the VFS uses to assign i_[ug]id. + * INHERIT adjusts the gid computation for setgid/grpid systems. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns), - mapped_fsgid(idmap, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, i_user_ns(VFS_I(dp))), + mapped_fsgid(idmap, i_user_ns(VFS_I(dp))), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 85e433df6a3f..b08be64dd10b 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -191,10 +191,12 @@ xfs_symlink( prid = xfs_get_initial_prid(dp);

/* - * Make sure that we have allocated dquot(s) on disk. + * Make sure that we have allocated dquot(s) on disk. The uid/gid + * computation code must match what the VFS uses to assign i_[ug]id. + * INHERIT adjusts the gid computation for setgid/grpid systems. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns), - mapped_fsgid(idmap, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, i_user_ns(VFS_I(dp))), + mapped_fsgid(idmap, i_user_ns(VFS_I(dp))), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error)

From: "Darrick J. Wong" djwong@kernel.org

commit 00acb28d96746f78389f23a7b5309a917b45c12f upstream.

[backport: dependency of d3b689d and f23660f]

Move the two public symbols in xfs_file.c to xfs_file.h. We're about to add more public symbols in that source file, so let's finally create the header file.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_file.c | 1 + fs/xfs/xfs_file.h | 12 ++++++++++++ fs/xfs/xfs_ioctl.c | 1 + fs/xfs/xfs_iops.c | 1 + fs/xfs/xfs_iops.h | 3 --- 5 files changed, 15 insertions(+), 3 deletions(-) create mode 100644 fs/xfs/xfs_file.h

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index e33e5e13b95f..b9b3240a3c1f 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -24,6 +24,7 @@ #include "xfs_pnfs.h" #include "xfs_iomap.h" #include "xfs_reflink.h" +#include "xfs_file.h"

#include <linux/dax.h> #include <linux/falloc.h> diff --git a/fs/xfs/xfs_file.h b/fs/xfs/xfs_file.h new file mode 100644 index 000000000000..7d39e3eca56d --- /dev/null +++ b/fs/xfs/xfs_file.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000-2005 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#ifndef __XFS_FILE_H__ +#define __XFS_FILE_H__ + +extern const struct file_operations xfs_file_operations; +extern const struct file_operations xfs_dir_file_operations; + +#endif /* __XFS_FILE_H__ */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 535f6d38cdb5..df4bf0d56aad 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -38,6 +38,7 @@ #include "xfs_reflink.h" #include "xfs_ioctl.h" #include "xfs_xattr.h" +#include "xfs_file.h"

#include <linux/mount.h> #include <linux/namei.h> diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index b8ec045708c3..f9466311dfea 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -25,6 +25,7 @@ #include "xfs_error.h" #include "xfs_ioctl.h" #include "xfs_xattr.h" +#include "xfs_file.h"

#include <linux/posix_acl.h> #include <linux/security.h> diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index 7f84a0843b24..52d6d510a21d 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -8,9 +8,6 @@

struct xfs_inode;

-extern const struct file_operations xfs_file_operations; -extern const struct file_operations xfs_dir_file_operations; - extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size);

int xfs_vn_setattr_size(struct mnt_idmap *idmap,

From: "Darrick J. Wong" djwong@kernel.org

commit ee20808d848c87a51e176706d81b95a21747d6cf upstream.

[backport: dependency of d3b689d and f23660f]

Create a new helper function to calculate the fundamental allocation unit (i.e. the smallest unit of space we can allocate) of a file. Things are going to get hairy with range-exchange on the realtime device, so prepare for this now.

Remove the static attribute from xfs_is_falloc_aligned since the next patch will need it.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_file.c | 32 ++++++++++++-------------------- fs/xfs/xfs_file.h | 3 +++ fs/xfs/xfs_inode.c | 13 +++++++++++++ fs/xfs/xfs_inode.h | 2 ++ 4 files changed, 30 insertions(+), 20 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index b9b3240a3c1f..dc26b732aa24 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -39,33 +39,25 @@ static const struct vm_operations_struct xfs_file_vm_ops; * Decide if the given file range is aligned to the size of the fundamental * allocation unit for the file. */ -static bool +bool xfs_is_falloc_aligned( struct xfs_inode *ip, loff_t pos, long long int len) { - struct xfs_mount *mp = ip->i_mount; - uint64_t mask; - - if (XFS_IS_REALTIME_INODE(ip)) { - if (!is_power_of_2(mp->m_sb.sb_rextsize)) { - u64 rextbytes; - u32 mod; - - rextbytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); - div_u64_rem(pos, rextbytes, &mod); - if (mod) - return false; - div_u64_rem(len, rextbytes, &mod); - return mod == 0; - } - mask = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize) - 1; - } else { - mask = mp->m_sb.sb_blocksize - 1; + unsigned int alloc_unit = xfs_inode_alloc_unitsize(ip); + + if (!is_power_of_2(alloc_unit)) { + u32 mod; + + div_u64_rem(pos, alloc_unit, &mod); + if (mod) + return false; + div_u64_rem(len, alloc_unit, &mod); + return mod == 0; }

- return !((pos | len) & mask); + return !((pos | len) & (alloc_unit - 1)); }

/* diff --git a/fs/xfs/xfs_file.h b/fs/xfs/xfs_file.h index 7d39e3eca56d..2ad91f755caf 100644 --- a/fs/xfs/xfs_file.h +++ b/fs/xfs/xfs_file.h @@ -9,4 +9,7 @@ extern const struct file_operations xfs_file_operations; extern const struct file_operations xfs_dir_file_operations;

+bool xfs_is_falloc_aligned(struct xfs_inode *ip, loff_t pos, + long long int len); + #endif /* __XFS_FILE_H__ */ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 1e50cc9a29db..6f7dca1c14c7 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3782,3 +3782,16 @@ xfs_inode_reload_unlinked(

return error; } + +/* Returns the size of fundamental allocation unit for a file, in bytes. */ +unsigned int +xfs_inode_alloc_unitsize( + struct xfs_inode *ip) +{ + unsigned int blocks = 1; + + if (XFS_IS_REALTIME_INODE(ip)) + blocks = ip->i_mount->m_sb.sb_rextsize; + + return XFS_FSB_TO_B(ip->i_mount, blocks); +} diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 3beb470f1892..0f2999b84e7d 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -622,4 +622,6 @@ xfs_inode_unlinked_incomplete( int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip); int xfs_inode_reload_unlinked(struct xfs_inode *ip);

+unsigned int xfs_inode_alloc_unitsize(struct xfs_inode *ip); + #endif /* __XFS_INODE_H__ */

From: John Garry john.g.garry@oracle.com

commit d3b689d7c711a9f36d3e48db9eaa75784a892f4c upstream.

Currently xfs_flush_unmap_range() does unmap for a full RT extent range, which we also want to ensure is clean and idle.

This code change is originally from Dave Chinner.

Reviewed-by: Christoph Hellwig hch@lst.de4 Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_bmap_util.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index f9d72d8e3c35..7336402f1efa 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -963,14 +963,18 @@ xfs_flush_unmap_range( xfs_off_t offset, xfs_off_t len) { - struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); xfs_off_t rounding, start, end; int error;

- rounding = max_t(xfs_off_t, mp->m_sb.sb_blocksize, PAGE_SIZE); - start = round_down(offset, rounding); - end = round_up(offset + len, rounding) - 1; + /* + * Make sure we extend the flush out to extent alignment + * boundaries so any extent range overlapping the start/end + * of the modification we are about to do is clean and idle. + */ + rounding = max_t(xfs_off_t, xfs_inode_alloc_unitsize(ip), PAGE_SIZE); + start = rounddown_64(offset, rounding); + end = roundup_64(offset + len, rounding) - 1;

error = filemap_write_and_wait_range(inode->i_mapping, start, end); if (error)

From: John Garry john.g.garry@oracle.com

commit f23660f059470ec7043748da7641e84183c23bc8 upstream.

The RT extent range must be considered in the xfs_flush_unmap_range() call to stabilize the boundary.

This code change is originally from Dave Chinner.

Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_bmap_util.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 7336402f1efa..1fa10a83da0b 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1059,7 +1059,7 @@ xfs_prepare_shift( struct xfs_inode *ip, loff_t offset) { - struct xfs_mount *mp = ip->i_mount; + unsigned int rounding; int error;

/* @@ -1077,11 +1077,13 @@ xfs_prepare_shift( * with the full range of the operation. If we don't, a COW writeback * completion could race with an insert, front merge with the start * extent (after split) during the shift and corrupt the file. Start - * with the block just prior to the start to stabilize the boundary. + * with the allocation unit just prior to the start to stabilize the + * boundary. */ - offset = round_down(offset, mp->m_sb.sb_blocksize); + rounding = xfs_inode_alloc_unitsize(ip); + offset = rounddown_64(offset, rounding); if (offset) - offset -= mp->m_sb.sb_blocksize; + offset -= rounding;

/* * Writeback and invalidate cache for the remainder of the file as we're

From: lei lu llfamsec@gmail.com

commit 0c7fcdb6d06cdf8b19b57c17605215b06afa864a upstream.

This adds sanity checks for xfs_dir2_data_unused and xfs_dir2_data_entry to make sure don't stray beyond valid memory region. Before patching, the loop simply checks that the start offset of the dup and dep is within the range. So in a crafted image, if last entry is xfs_dir2_data_unused, we can change dup->length to dup->length-1 and leave 1 byte of space. In the next traversal, this space will be considered as dup or dep. We may encounter an out of bound read when accessing the fixed members.

In the patch, we make sure that the remaining bytes large enough to hold an unused entry before accessing xfs_dir2_data_unused and xfs_dir2_data_unused is XFS_DIR2_DATA_ALIGN byte aligned. We also make sure that the remaining bytes large enough to hold a dirent with a single-byte name before accessing xfs_dir2_data_entry.

Signed-off-by: lei lu llfamsec@gmail.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/libxfs/xfs_dir2_data.c | 31 ++++++++++++++++++++++++++----- fs/xfs/libxfs/xfs_dir2_priv.h | 7 +++++++ 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index dbcf58979a59..e1d5da6d8d4a 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -177,6 +177,14 @@ __xfs_dir3_data_check( while (offset < end) { struct xfs_dir2_data_unused *dup = bp->b_addr + offset; struct xfs_dir2_data_entry *dep = bp->b_addr + offset; + unsigned int reclen; + + /* + * Are the remaining bytes large enough to hold an + * unused entry? + */ + if (offset > end - xfs_dir2_data_unusedsize(1)) + return __this_address;

/* * If it's unused, look for the space in the bestfree table. @@ -186,9 +194,13 @@ __xfs_dir3_data_check( if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { xfs_failaddr_t fa;

+ reclen = xfs_dir2_data_unusedsize( + be16_to_cpu(dup->length)); if (lastfree != 0) return __this_address; - if (offset + be16_to_cpu(dup->length) > end) + if (be16_to_cpu(dup->length) != reclen) + return __this_address; + if (offset + reclen > end) return __this_address; if (be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) != offset) @@ -206,10 +218,18 @@ __xfs_dir3_data_check( be16_to_cpu(bf[2].length)) return __this_address; } - offset += be16_to_cpu(dup->length); + offset += reclen; lastfree = 1; continue; } + + /* + * This is not an unused entry. Are the remaining bytes + * large enough for a dirent with a single-byte name? + */ + if (offset > end - xfs_dir2_data_entsize(mp, 1)) + return __this_address; + /* * It's a real entry. Validate the fields. * If this is a block directory then make sure it's @@ -218,9 +238,10 @@ __xfs_dir3_data_check( */ if (dep->namelen == 0) return __this_address; - if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber))) + reclen = xfs_dir2_data_entsize(mp, dep->namelen); + if (offset + reclen > end) return __this_address; - if (offset + xfs_dir2_data_entsize(mp, dep->namelen) > end) + if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber))) return __this_address; if (be16_to_cpu(*xfs_dir2_data_entry_tag_p(mp, dep)) != offset) return __this_address; @@ -244,7 +265,7 @@ __xfs_dir3_data_check( if (i >= be32_to_cpu(btp->count)) return __this_address; } - offset += xfs_dir2_data_entsize(mp, dep->namelen); + offset += reclen; } /* * Need to have seen all the entries and all the bestfree slots. diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h index 7404a9ff1a92..9046d08554e9 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -187,6 +187,13 @@ void xfs_dir2_sf_put_ftype(struct xfs_mount *mp, extern int xfs_readdir(struct xfs_trans *tp, struct xfs_inode *dp, struct dir_context *ctx, size_t bufsize);

+static inline unsigned int +xfs_dir2_data_unusedsize( + unsigned int len) +{ + return round_up(len, XFS_DIR2_DATA_ALIGN); +} + static inline unsigned int xfs_dir2_data_entsize( struct xfs_mount *mp,

From: Chen Ni nichen@iscas.ac.cn

commit 7bf888fa26e8f22bed4bc3965ab2a2953104ff96 upstream.

Replace a comma between expression statements by a semicolon.

Fixes: 178b48d588ea ("xfs: remove the for_each_xbitmap_ helpers") Signed-off-by: Chen Ni nichen@iscas.ac.cn Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/scrub/agheader_repair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 876a2f41b063..058b6c305224 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -705,7 +705,7 @@ xrep_agfl_init_header( * step. */ xagb_bitmap_init(&af.used_extents); - af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp), + af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp); xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af); error = xagb_bitmap_disunion(agfl_extents, &af.used_extents); if (error)

From: "Darrick J. Wong" djwong@kernel.org

commit 19ebc8f84ea12e18dd6c8d3ecaf87bcf4666eee1 upstream.

[backport: only apply fix for 3934e8ebb7cc6]

Since file_path() takes the output buffer as one of its arguments, we might as well have it format directly into the tracepoint's char array instead of wasting stack space.

Fixes: 3934e8ebb7cc6 ("xfs: create a big array data structure") Fixes: 5076a6040ca16 ("xfs: support in-memory buffer cache targets") Reported-by: kernel test robot lkp@intel.com Closes: https://lore.kernel.org/oe-kbuild-all/202403290419.HPcyvqZu-lkp@intel.com/ Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/scrub/trace.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index df49ca2e8c23..0497a2d681e5 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -784,18 +784,16 @@ TRACE_EVENT(xfile_create, TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, ino) - __array(char, pathname, 256) + __array(char, pathname, MAXNAMELEN) ), TP_fast_assign( - char pathname[257]; char *path;

__entry->ino = file_inode(xf->file)->i_ino; - memset(pathname, 0, sizeof(pathname)); - path = file_path(xf->file, pathname, sizeof(pathname) - 1); + path = file_path(xf->file, __entry->pathname, MAXNAMELEN); if (IS_ERR(path)) - path = "(unknown)"; - strncpy(__entry->pathname, path, sizeof(__entry->pathname)); + strncpy(__entry->pathname, "(unknown)", + sizeof(__entry->pathname)); ), TP_printk("xfino 0x%lx path '%s'", __entry->ino,

From: Julian Sun sunjunchao2870@gmail.com

commit af5d92f2fad818663da2ce073b6fe15b9d56ffdc upstream.

In the macro definition of XFS_DQUOT_LOGRES, a parameter is accepted, but it is not used. Hence, it should be removed.

This patch has only passed compilation test, but it should be fine.

Signed-off-by: Julian Sun sunjunchao2870@gmail.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/libxfs/xfs_quota_defs.h | 2 +- fs/xfs/libxfs/xfs_trans_resv.c | 28 ++++++++++++++-------------- 2 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index cb035da3f990..fb05f44f6c75 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -56,7 +56,7 @@ typedef uint8_t xfs_dqtype_t; * And, of course, we also need to take into account the dquot log format item * used to describe each dquot. */ -#define XFS_DQUOT_LOGRES(mp) \ +#define XFS_DQUOT_LOGRES \ ((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6)

#define XFS_IS_QUOTA_ON(mp) ((mp)->m_qflags & XFS_ALL_QUOTA_ACCT) diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 5b2f27cbdb80..1bb2891b26ff 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -334,11 +334,11 @@ xfs_calc_write_reservation( blksz); t1 += adj; t3 += adj; - return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); + return XFS_DQUOT_LOGRES + max3(t1, t2, t3); }

t4 = xfs_calc_refcountbt_reservation(mp, 1); - return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3)); + return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3)); }

unsigned int @@ -406,11 +406,11 @@ xfs_calc_itruncate_reservation( xfs_refcountbt_block_count(mp, 4), blksz);

- return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); + return XFS_DQUOT_LOGRES + max3(t1, t2, t3); }

t4 = xfs_calc_refcountbt_reservation(mp, 2); - return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3)); + return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3)); }

unsigned int @@ -436,7 +436,7 @@ STATIC uint xfs_calc_rename_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + max((xfs_calc_inode_res(mp, 5) + xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1))), @@ -475,7 +475,7 @@ STATIC uint xfs_calc_link_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_iunlink_remove_reservation(mp) + max((xfs_calc_inode_res(mp, 2) + xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), @@ -513,7 +513,7 @@ STATIC uint xfs_calc_remove_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_iunlink_add_reservation(mp) + max((xfs_calc_inode_res(mp, 2) + xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), @@ -572,7 +572,7 @@ xfs_calc_icreate_resv_alloc( STATIC uint xfs_calc_icreate_reservation(xfs_mount_t *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + max(xfs_calc_icreate_resv_alloc(mp), xfs_calc_create_resv_modify(mp)); } @@ -581,7 +581,7 @@ STATIC uint xfs_calc_create_tmpfile_reservation( struct xfs_mount *mp) { - uint res = XFS_DQUOT_LOGRES(mp); + uint res = XFS_DQUOT_LOGRES;

res += xfs_calc_icreate_resv_alloc(mp); return res + xfs_calc_iunlink_add_reservation(mp); @@ -630,7 +630,7 @@ STATIC uint xfs_calc_ifree_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + xfs_calc_iunlink_remove_reservation(mp) + @@ -647,7 +647,7 @@ STATIC uint xfs_calc_ichange_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);

@@ -756,7 +756,7 @@ STATIC uint xfs_calc_addafork_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) + xfs_calc_buf_res(1, mp->m_dir_geo->blksize) + @@ -804,7 +804,7 @@ STATIC uint xfs_calc_attrsetm_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) + xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1)); @@ -844,7 +844,7 @@ STATIC uint xfs_calc_attrrm_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + max((xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1)) +

From: "Darrick J. Wong" djwong@kernel.org

commit 73c34b0b85d46bf9c2c0b367aeaffa1e2481b136 upstream.

It turns out that I misunderstood the difference between the attr and attr2 feature bits. "attr" means that at some point an attr fork was created somewhere in the filesystem. "attr2" means that inodes have variable-sized forks, but says nothing about whether or not there actually /are/ attr forks in the system.

If we have an attr fork, we only need to check that attr is set.

Fixes: 99d9d8d05da26 ("xfs: scrub inode block mappings") Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/scrub/bmap.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 75588915572e..9dfa310df311 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -857,7 +857,13 @@ xchk_bmap( } break; case XFS_ATTR_FORK: - if (!xfs_has_attr(mp) && !xfs_has_attr2(mp)) + /* + * "attr" means that an attr fork was created at some point in + * the life of this filesystem. "attr2" means that inodes have + * variable-sized data/attr fork areas. Hence we only check + * attr here. + */ + if (!xfs_has_attr(mp)) xchk_ino_set_corrupt(sc, sc->ip->i_ino); break; default:

From: Zizhi Wo wozizhi@huawei.com

commit 68415b349f3f16904f006275757f4fcb34b8ee43 upstream.

I notice a rmap query bug in xfs_io fsmap: [root@fedora ~]# xfs_io -c 'fsmap -vvvv' /mnt EXT: DEV BLOCK-RANGE OWNER FILE-OFFSET AG AG-OFFSET TOTAL 0: 253:16 [0..7]: static fs metadata 0 (0..7) 8 1: 253:16 [8..23]: per-AG metadata 0 (8..23) 16 2: 253:16 [24..39]: inode btree 0 (24..39) 16 3: 253:16 [40..47]: per-AG metadata 0 (40..47) 8 4: 253:16 [48..55]: refcount btree 0 (48..55) 8 5: 253:16 [56..103]: per-AG metadata 0 (56..103) 48 6: 253:16 [104..127]: free space 0 (104..127) 24 ......

Bug: [root@fedora ~]# xfs_io -c 'fsmap -vvvv -d 0 3' /mnt [root@fedora ~]# Normally, we should be able to get one record, but we got nothing.

The root cause of this problem lies in the incorrect setting of rm_owner in the rmap query. In the case of the initial query where the owner is not set, __xfs_getfsmap_datadev() first sets info->high.rm_owner to ULLONG_MAX. This is done to prevent any omissions when comparing rmap items. However, if the current ag is detected to be the last one, the function sets info's high_irec based on the provided key. If high->rm_owner is not specified, it should continue to be set to ULLONG_MAX; otherwise, there will be issues with interval omissions. For example, consider "start" and "end" within the same block. If high->rm_owner == 0, it will be smaller than the founded record in rmapbt, resulting in a query with no records. The main call stack is as follows:

xfs_ioc_getfsmap xfs_getfsmap xfs_getfsmap_datadev_rmapbt __xfs_getfsmap_datadev info->high.rm_owner = ULLONG_MAX if (pag->pag_agno == end_ag) xfs_fsmap_owner_to_rmap // set info->high.rm_owner = 0 because fmr_owner == -1ULL dest->rm_owner = 0 // get nothing xfs_getfsmap_datadev_rmapbt_query

The problem can be resolved by simply modify the xfs_fsmap_owner_to_rmap function internal logic to achieve.

After applying this patch, the above problem have been solved: [root@fedora ~]# xfs_io -c 'fsmap -vvvv -d 0 3' /mnt EXT: DEV BLOCK-RANGE OWNER FILE-OFFSET AG AG-OFFSET TOTAL 0: 253:16 [0..7]: static fs metadata 0 (0..7) 8

Fixes: e89c041338ed ("xfs: implement the GETFSMAP ioctl") Signed-off-by: Zizhi Wo wozizhi@huawei.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_fsmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 8982c5d6cbd0..85953dbd4283 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -71,7 +71,7 @@ xfs_fsmap_owner_to_rmap( switch (src->fmr_owner) { case 0: /* "lowest owner id possible" */ case -1ULL: /* "highest owner id possible" */ - dest->rm_owner = 0; + dest->rm_owner = src->fmr_owner; break; case XFS_FMR_OWN_FREE: dest->rm_owner = XFS_RMAP_OWN_NULL;

From: "Darrick J. Wong" djwong@kernel.org

commit 16e1fbdce9c8d084863fd63cdaff8fb2a54e2f88 upstream.

Take the grow lock when we're expanding the realtime volume, like we do for the other growfs calls.

Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Catherine Hoang catherine.hoang@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_rtalloc.c | 38 +++++++++++++++++++++++++------------- 1 file changed, 25 insertions(+), 13 deletions(-)

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 608db1ab88a4..9268961d887c 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -953,34 +953,39 @@ xfs_growfs_rt( /* Needs to have been mounted with an rt device. */ if (!XFS_IS_REALTIME_MOUNT(mp)) return -EINVAL; + + if (!mutex_trylock(&mp->m_growlock)) + return -EWOULDBLOCK; /* * Mount should fail if the rt bitmap/summary files don't load, but * we'll check anyway. */ + error = -EINVAL; if (!mp->m_rbmip || !mp->m_rsumip) - return -EINVAL; + goto out_unlock;

/* Shrink not supported. */ if (in->newblocks <= sbp->sb_rblocks) - return -EINVAL; + goto out_unlock;

/* Can only change rt extent size when adding rt volume. */ if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize) - return -EINVAL; + goto out_unlock;

/* Range check the extent size. */ if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE || XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE) - return -EINVAL; + goto out_unlock;

/* Unsupported realtime features. */ + error = -EOPNOTSUPP; if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp) || xfs_has_quota(mp)) - return -EOPNOTSUPP; + goto out_unlock;

nrblocks = in->newblocks; error = xfs_sb_validate_fsb_count(sbp, nrblocks); if (error) - return error; + goto out_unlock; /* * Read in the last block of the device, make sure it exists. */ @@ -988,7 +993,7 @@ xfs_growfs_rt( XFS_FSB_TO_BB(mp, nrblocks - 1), XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); if (error) - return error; + goto out_unlock; xfs_buf_relse(bp);

/* @@ -996,8 +1001,10 @@ xfs_growfs_rt( */ nrextents = nrblocks; do_div(nrextents, in->extsize); - if (!xfs_validate_rtextents(nrextents)) - return -EINVAL; + if (!xfs_validate_rtextents(nrextents)) { + error = -EINVAL; + goto out_unlock; + } nrbmblocks = howmany_64(nrextents, NBBY * sbp->sb_blocksize); nrextslog = xfs_compute_rextslog(nrextents); nrsumlevels = nrextslog + 1; @@ -1009,8 +1016,11 @@ xfs_growfs_rt( * the log. This prevents us from getting a log overflow, * since we'll log basically the whole summary file at once. */ - if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1)) - return -EINVAL; + if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1)) { + error = -EINVAL; + goto out_unlock; + } + /* * Get the old block counts for bitmap and summary inodes. * These can't change since other growfs callers are locked out. @@ -1022,10 +1032,10 @@ xfs_growfs_rt( */ error = xfs_growfs_rt_alloc(mp, rbmblocks, nrbmblocks, mp->m_rbmip); if (error) - return error; + goto out_unlock; error = xfs_growfs_rt_alloc(mp, rsumblocks, nrsumblocks, mp->m_rsumip); if (error) - return error; + goto out_unlock;

rsum_cache = mp->m_rsum_cache; if (nrbmblocks != sbp->sb_rbmblocks) @@ -1190,6 +1200,8 @@ xfs_growfs_rt( } }

+out_unlock: + mutex_unlock(&mp->m_growlock); return error; }