From: Christoph Hellwig hch@lst.de

commit de7a866fd41b227b0aa6e9cbeb0dae221c12f542 upstream.

There is no point in splitting the fields like this in an purely in-memory structure.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Chandan Babu R chandan.babu@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/libxfs/xfs_inode_buf.c | 11 +++++------ fs/xfs/libxfs/xfs_inode_buf.h | 3 +-- fs/xfs/xfs_dquot.c | 2 +- fs/xfs/xfs_icache.c | 4 ++-- fs/xfs/xfs_inode.c | 6 +++--- fs/xfs/xfs_inode.h | 21 +-------------------- fs/xfs/xfs_inode_item.c | 4 ++-- fs/xfs/xfs_ioctl.c | 8 ++++---- fs/xfs/xfs_iops.c | 2 +- fs/xfs/xfs_itable.c | 2 +- fs/xfs/xfs_qm.c | 8 ++++---- fs/xfs/xfs_qm_bhv.c | 2 +- 12 files changed, 26 insertions(+), 47 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 28ab3c5255e1..e1faf48eb002 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -213,13 +213,12 @@ xfs_inode_from_disk( to->di_version = from->di_version; if (to->di_version == 1) { set_nlink(inode, be16_to_cpu(from->di_onlink)); - to->di_projid_lo = 0; - to->di_projid_hi = 0; + to->di_projid = 0; to->di_version = 2; } else { set_nlink(inode, be32_to_cpu(from->di_nlink)); - to->di_projid_lo = be16_to_cpu(from->di_projid_lo); - to->di_projid_hi = be16_to_cpu(from->di_projid_hi); + to->di_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 | + be16_to_cpu(from->di_projid_lo); }

to->di_format = from->di_format; @@ -279,8 +278,8 @@ xfs_inode_to_disk( to->di_format = from->di_format; to->di_uid = cpu_to_be32(from->di_uid); to->di_gid = cpu_to_be32(from->di_gid); - to->di_projid_lo = cpu_to_be16(from->di_projid_lo); - to->di_projid_hi = cpu_to_be16(from->di_projid_hi); + to->di_projid_lo = cpu_to_be16(from->di_projid & 0xffff); + to->di_projid_hi = cpu_to_be16(from->di_projid >> 16);

memset(to->di_pad, 0, sizeof(to->di_pad)); to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec); diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index ab0f84165317..af3ff02b4a8d 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -21,8 +21,7 @@ struct xfs_icdinode { uint16_t di_flushiter; /* incremented on flush */ uint32_t di_uid; /* owner's user id */ uint32_t di_gid; /* owner's group id */ - uint16_t di_projid_lo; /* lower part of owner's project id */ - uint16_t di_projid_hi; /* higher part of owner's project id */ + uint32_t di_projid; /* owner's project id */ xfs_fsize_t di_size; /* number of bytes in file */ xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */ xfs_extlen_t di_extsize; /* basic/minimum extent size for file */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 6231b155e7f3..f59c3265dae7 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -863,7 +863,7 @@ xfs_qm_id_for_quotatype( case XFS_DQ_GROUP: return ip->i_d.di_gid; case XFS_DQ_PROJ: - return xfs_get_projid(ip); + return ip->i_d.di_projid; } ASSERT(0); return 0; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index a1135b86e79f..8e6dc04c14d4 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1430,7 +1430,7 @@ xfs_inode_match_id( return 0;

if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) && - xfs_get_projid(ip) != eofb->eof_prid) + ip->i_d.di_projid != eofb->eof_prid) return 0;

return 1; @@ -1454,7 +1454,7 @@ xfs_inode_match_id_union( return 1;

if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) && - xfs_get_projid(ip) == eofb->eof_prid) + ip->i_d.di_projid == eofb->eof_prid) return 1;

return 0; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 02f77a359972..891f03a3fd91 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -809,7 +809,7 @@ xfs_ialloc( ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid()); ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid()); inode->i_rdev = rdev; - xfs_set_projid(ip, prid); + ip->i_d.di_projid = prid;

if (pip && XFS_INHERIT_GID(pip)) { ip->i_d.di_gid = pip->i_d.di_gid; @@ -1418,7 +1418,7 @@ xfs_link( * the tree quota mechanism could be circumvented. */ if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && - (xfs_get_projid(tdp) != xfs_get_projid(sip)))) { + tdp->i_d.di_projid != sip->i_d.di_projid)) { error = -EXDEV; goto error_return; } @@ -3299,7 +3299,7 @@ xfs_rename( * tree quota mechanism would be circumvented. */ if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && - (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) { + target_dp->i_d.di_projid != src_ip->i_d.di_projid)) { error = -EXDEV; goto out_trans_cancel; } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index e493d491b7cc..62b963d3b23d 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -177,30 +177,11 @@ xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned short flags) return ret; }

-/* - * Project quota id helpers (previously projid was 16bit only - * and using two 16bit values to hold new 32bit projid was chosen - * to retain compatibility with "old" filesystems). - */ -static inline prid_t -xfs_get_projid(struct xfs_inode *ip) -{ - return (prid_t)ip->i_d.di_projid_hi << 16 | ip->i_d.di_projid_lo; -} - -static inline void -xfs_set_projid(struct xfs_inode *ip, - prid_t projid) -{ - ip->i_d.di_projid_hi = (uint16_t) (projid >> 16); - ip->i_d.di_projid_lo = (uint16_t) (projid & 0xffff); -} - static inline prid_t xfs_get_initial_prid(struct xfs_inode *dp) { if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) - return xfs_get_projid(dp); + return dp->i_d.di_projid;

return XFS_PROJID_DEFAULT; } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 83b8f5655636..a3df39033c00 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -310,8 +310,8 @@ xfs_inode_to_log_dinode( to->di_format = from->di_format; to->di_uid = from->di_uid; to->di_gid = from->di_gid; - to->di_projid_lo = from->di_projid_lo; - to->di_projid_hi = from->di_projid_hi; + to->di_projid_lo = from->di_projid & 0xffff; + to->di_projid_hi = from->di_projid >> 16;

memset(to->di_pad, 0, sizeof(to->di_pad)); memset(to->di_pad3, 0, sizeof(to->di_pad3)); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 7b7a009425e2..fd40a0644b75 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1144,7 +1144,7 @@ xfs_fill_fsxattr( fa->fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog; fa->fsx_cowextsize = ip->i_d.di_cowextsize << ip->i_mount->m_sb.sb_blocklog; - fa->fsx_projid = xfs_get_projid(ip); + fa->fsx_projid = ip->i_d.di_projid;

if (attr) { if (ip->i_afp) { @@ -1597,7 +1597,7 @@ xfs_ioctl_setattr( }

if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && - xfs_get_projid(ip) != fa->fsx_projid) { + ip->i_d.di_projid != fa->fsx_projid) { code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp, capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); if (code) /* out of quota */ @@ -1634,13 +1634,13 @@ xfs_ioctl_setattr( VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);

/* Change the ownerships and register project quota modifications */ - if (xfs_get_projid(ip) != fa->fsx_projid) { + if (ip->i_d.di_projid != fa->fsx_projid) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) { olddquot = xfs_qm_vop_chown(tp, ip, &ip->i_pdquot, pdqp); } ASSERT(ip->i_d.di_version > 1); - xfs_set_projid(ip, fa->fsx_projid); + ip->i_d.di_projid = fa->fsx_projid; }

/* diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 80dd05f8f1af..05adfea93ad9 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -668,7 +668,7 @@ xfs_setattr_nonsize( ASSERT(gdqp == NULL); error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid), xfs_kgid_to_gid(gid), - xfs_get_projid(ip), + ip->i_d.di_projid, qflags, &udqp, &gdqp, NULL); if (error) return error; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 884950adbd16..f1f4c4dde0a8 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -84,7 +84,7 @@ xfs_bulkstat_one_int( /* xfs_iget returns the following without needing * further change. */ - buf->bs_projectid = xfs_get_projid(ip); + buf->bs_projectid = ip->i_d.di_projid; buf->bs_ino = ino; buf->bs_uid = dic->di_uid; buf->bs_gid = dic->di_gid; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 6b23ebd3f54f..8867589bfc3c 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -347,7 +347,7 @@ xfs_qm_dqattach_locked( }

if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) { - error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ, + error = xfs_qm_dqattach_one(ip, ip->i_d.di_projid, XFS_DQ_PROJ, doalloc, &ip->i_pdquot); if (error) goto done; @@ -1715,7 +1715,7 @@ xfs_qm_vop_dqalloc( } } if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) { - if (xfs_get_projid(ip) != prid) { + if (ip->i_d.di_projid != prid) { xfs_iunlock(ip, lockflags); error = xfs_qm_dqget(mp, (xfs_dqid_t)prid, XFS_DQ_PROJ, true, &pq); @@ -1849,7 +1849,7 @@ xfs_qm_vop_chown_reserve( }

if (XFS_IS_PQUOTA_ON(ip->i_mount) && pdqp && - xfs_get_projid(ip) != be32_to_cpu(pdqp->q_core.d_id)) { + ip->i_d.di_projid != be32_to_cpu(pdqp->q_core.d_id)) { prjflags = XFS_QMOPT_ENOSPC; pdq_delblks = pdqp; if (delblks) { @@ -1950,7 +1950,7 @@ xfs_qm_vop_create_dqattach( } if (pdqp && XFS_IS_PQUOTA_ON(mp)) { ASSERT(ip->i_pdquot == NULL); - ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id)); + ASSERT(ip->i_d.di_projid == be32_to_cpu(pdqp->q_core.d_id));

ip->i_pdquot = xfs_qm_dqhold(pdqp); xfs_trans_mod_dquot(tp, pdqp, XFS_TRANS_DQ_ICOUNT, 1); diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index b784a3751fe2..fc2fa418919f 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -60,7 +60,7 @@ xfs_qm_statvfs( struct xfs_mount *mp = ip->i_mount; struct xfs_dquot *dqp;

- if (!xfs_qm_dqget(mp, xfs_get_projid(ip), XFS_DQ_PROJ, false, &dqp)) { + if (!xfs_qm_dqget(mp, ip->i_d.di_projid, XFS_DQ_PROJ, false, &dqp)) { xfs_fill_statvfs_from_dquot(statp, dqp); xfs_qm_dqput(dqp); }

From: Christoph Hellwig hch@lst.de

commit 542951592c99ff7b15c050954c051dd6dd6c0f97 upstream.

Use the Linux inode i_uid/i_gid members everywhere and just convert from/to the scalar value when reading or writing the on-disk inode.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Chandan Babu R chandan.babu@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/libxfs/xfs_inode_buf.c | 10 ++++----- fs/xfs/libxfs/xfs_inode_buf.h | 2 -- fs/xfs/xfs_dquot.c | 4 ++-- fs/xfs/xfs_inode.c | 14 ++++-------- fs/xfs/xfs_inode_item.c | 4 ++-- fs/xfs/xfs_ioctl.c | 6 +++--- fs/xfs/xfs_iops.c | 6 +----- fs/xfs/xfs_itable.c | 4 ++-- fs/xfs/xfs_qm.c | 40 ++++++++++++++++++++++------------- fs/xfs/xfs_quota.h | 4 ++-- fs/xfs/xfs_symlink.c | 4 +--- 11 files changed, 46 insertions(+), 52 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index c7e4d51fe975..94cd6ec666a2 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -222,10 +222,8 @@ xfs_inode_from_disk( }

to->di_format = from->di_format; - to->di_uid = be32_to_cpu(from->di_uid); - inode->i_uid = xfs_uid_to_kuid(to->di_uid); - to->di_gid = be32_to_cpu(from->di_gid); - inode->i_gid = xfs_gid_to_kgid(to->di_gid); + inode->i_uid = xfs_uid_to_kuid(be32_to_cpu(from->di_uid)); + inode->i_gid = xfs_gid_to_kgid(be32_to_cpu(from->di_gid)); to->di_flushiter = be16_to_cpu(from->di_flushiter);

/* @@ -278,8 +276,8 @@ xfs_inode_to_disk(

to->di_version = from->di_version; to->di_format = from->di_format; - to->di_uid = cpu_to_be32(from->di_uid); - to->di_gid = cpu_to_be32(from->di_gid); + to->di_uid = cpu_to_be32(xfs_kuid_to_uid(inode->i_uid)); + to->di_gid = cpu_to_be32(xfs_kgid_to_gid(inode->i_gid)); to->di_projid_lo = cpu_to_be16(from->di_projid & 0xffff); to->di_projid_hi = cpu_to_be16(from->di_projid >> 16);

diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index af3ff02b4a8d..0cb11fcc74b6 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -19,8 +19,6 @@ struct xfs_icdinode { int8_t di_version; /* inode version */ int8_t di_format; /* format of di_c data */ uint16_t di_flushiter; /* incremented on flush */ - uint32_t di_uid; /* owner's user id */ - uint32_t di_gid; /* owner's group id */ uint32_t di_projid; /* owner's project id */ xfs_fsize_t di_size; /* number of bytes in file */ xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index f59c3265dae7..14f4d2ed87db 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -859,9 +859,9 @@ xfs_qm_id_for_quotatype( { switch (type) { case XFS_DQ_USER: - return ip->i_d.di_uid; + return xfs_kuid_to_uid(VFS_I(ip)->i_uid); case XFS_DQ_GROUP: - return ip->i_d.di_gid; + return xfs_kgid_to_gid(VFS_I(ip)->i_gid); case XFS_DQ_PROJ: return ip->i_d.di_projid; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 99f82bdb3db9..9d6ad669adc5 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -807,18 +807,15 @@ xfs_ialloc( inode->i_mode = mode; set_nlink(inode, nlink); inode->i_uid = current_fsuid(); - ip->i_d.di_uid = xfs_kuid_to_uid(inode->i_uid); inode->i_rdev = rdev; ip->i_d.di_projid = prid;

if (pip && XFS_INHERIT_GID(pip)) { inode->i_gid = VFS_I(pip)->i_gid; - ip->i_d.di_gid = pip->i_d.di_gid; if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode)) inode->i_mode |= S_ISGID; } else { inode->i_gid = current_fsgid(); - ip->i_d.di_gid = xfs_kgid_to_gid(inode->i_gid); }

/* @@ -826,9 +823,8 @@ xfs_ialloc( * ID or one of the supplementary group IDs, the S_ISGID bit is cleared * (and only if the irix_sgid_inherit compatibility variable is set). */ - if ((irix_sgid_inherit) && - (inode->i_mode & S_ISGID) && - (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid)))) + if (irix_sgid_inherit && + (inode->i_mode & S_ISGID) && !in_group_p(inode->i_gid)) inode->i_mode &= ~S_ISGID;

ip->i_d.di_size = 0; @@ -1157,8 +1153,7 @@ xfs_create( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()), - xfs_kgid_to_gid(current_fsgid()), prid, + error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1308,8 +1303,7 @@ xfs_create_tmpfile( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()), - xfs_kgid_to_gid(current_fsgid()), prid, + error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index a3df39033c00..91f9f7a539ae 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -308,8 +308,8 @@ xfs_inode_to_log_dinode(

to->di_version = from->di_version; to->di_format = from->di_format; - to->di_uid = from->di_uid; - to->di_gid = from->di_gid; + to->di_uid = xfs_kuid_to_uid(inode->i_uid); + to->di_gid = xfs_kgid_to_gid(inode->i_gid); to->di_projid_lo = from->di_projid & 0xffff; to->di_projid_hi = from->di_projid >> 16;

diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index fd40a0644b75..6d3abb84451c 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1572,9 +1572,9 @@ xfs_ioctl_setattr( * because the i_*dquot fields will get updated anyway. */ if (XFS_IS_QUOTA_ON(mp)) { - code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid, - ip->i_d.di_gid, fa->fsx_projid, - XFS_QMOPT_PQUOTA, &udqp, NULL, &pdqp); + code = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid, + VFS_I(ip)->i_gid, fa->fsx_projid, + XFS_QMOPT_PQUOTA, &udqp, NULL, &pdqp); if (code) return code; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 838acd7f2e47..757f6f898e85 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -666,9 +666,7 @@ xfs_setattr_nonsize( */ ASSERT(udqp == NULL); ASSERT(gdqp == NULL); - error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid), - xfs_kgid_to_gid(gid), - ip->i_d.di_projid, + error = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_d.di_projid, qflags, &udqp, &gdqp, NULL); if (error) return error; @@ -737,7 +735,6 @@ xfs_setattr_nonsize( olddquot1 = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp); } - ip->i_d.di_uid = xfs_kuid_to_uid(uid); inode->i_uid = uid; } if (!gid_eq(igid, gid)) { @@ -749,7 +746,6 @@ xfs_setattr_nonsize( olddquot2 = xfs_qm_vop_chown(tp, ip, &ip->i_gdquot, gdqp); } - ip->i_d.di_gid = xfs_kgid_to_gid(gid); inode->i_gid = gid; } } diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index f1f4c4dde0a8..a0ab1c382325 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -86,8 +86,8 @@ xfs_bulkstat_one_int( */ buf->bs_projectid = ip->i_d.di_projid; buf->bs_ino = ino; - buf->bs_uid = dic->di_uid; - buf->bs_gid = dic->di_gid; + buf->bs_uid = xfs_kuid_to_uid(inode->i_uid); + buf->bs_gid = xfs_kgid_to_gid(inode->i_gid); buf->bs_size = dic->di_size;

buf->bs_nlink = inode->i_nlink; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 8867589bfc3c..c036c55739d8 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -331,16 +331,18 @@ xfs_qm_dqattach_locked( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) { - error = xfs_qm_dqattach_one(ip, ip->i_d.di_uid, XFS_DQ_USER, - doalloc, &ip->i_udquot); + error = xfs_qm_dqattach_one(ip, + xfs_kuid_to_uid(VFS_I(ip)->i_uid), + XFS_DQ_USER, doalloc, &ip->i_udquot); if (error) goto done; ASSERT(ip->i_udquot); }

if (XFS_IS_GQUOTA_ON(mp) && !ip->i_gdquot) { - error = xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP, - doalloc, &ip->i_gdquot); + error = xfs_qm_dqattach_one(ip, + xfs_kgid_to_gid(VFS_I(ip)->i_gid), + XFS_DQ_GROUP, doalloc, &ip->i_gdquot); if (error) goto done; ASSERT(ip->i_gdquot); @@ -1630,8 +1632,8 @@ xfs_qm_dqfree_one( int xfs_qm_vop_dqalloc( struct xfs_inode *ip, - xfs_dqid_t uid, - xfs_dqid_t gid, + kuid_t uid, + kgid_t gid, prid_t prid, uint flags, struct xfs_dquot **O_udqpp, @@ -1639,6 +1641,7 @@ xfs_qm_vop_dqalloc( struct xfs_dquot **O_pdqpp) { struct xfs_mount *mp = ip->i_mount; + struct inode *inode = VFS_I(ip); struct xfs_dquot *uq = NULL; struct xfs_dquot *gq = NULL; struct xfs_dquot *pq = NULL; @@ -1652,7 +1655,7 @@ xfs_qm_vop_dqalloc( xfs_ilock(ip, lockflags);

if ((flags & XFS_QMOPT_INHERIT) && XFS_INHERIT_GID(ip)) - gid = ip->i_d.di_gid; + gid = inode->i_gid;

/* * Attach the dquot(s) to this inode, doing a dquot allocation @@ -1667,7 +1670,7 @@ xfs_qm_vop_dqalloc( }

if ((flags & XFS_QMOPT_UQUOTA) && XFS_IS_UQUOTA_ON(mp)) { - if (ip->i_d.di_uid != uid) { + if (!uid_eq(inode->i_uid, uid)) { /* * What we need is the dquot that has this uid, and * if we send the inode to dqget, the uid of the inode @@ -1678,7 +1681,8 @@ xfs_qm_vop_dqalloc( * holding ilock. */ xfs_iunlock(ip, lockflags); - error = xfs_qm_dqget(mp, uid, XFS_DQ_USER, true, &uq); + error = xfs_qm_dqget(mp, xfs_kuid_to_uid(uid), + XFS_DQ_USER, true, &uq); if (error) { ASSERT(error != -ENOENT); return error; @@ -1699,9 +1703,10 @@ xfs_qm_vop_dqalloc( } } if ((flags & XFS_QMOPT_GQUOTA) && XFS_IS_GQUOTA_ON(mp)) { - if (ip->i_d.di_gid != gid) { + if (!gid_eq(inode->i_gid, gid)) { xfs_iunlock(ip, lockflags); - error = xfs_qm_dqget(mp, gid, XFS_DQ_GROUP, true, &gq); + error = xfs_qm_dqget(mp, xfs_kgid_to_gid(gid), + XFS_DQ_GROUP, true, &gq); if (error) { ASSERT(error != -ENOENT); goto error_rele; @@ -1827,7 +1832,8 @@ xfs_qm_vop_chown_reserve( XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS;

if (XFS_IS_UQUOTA_ON(mp) && udqp && - ip->i_d.di_uid != be32_to_cpu(udqp->q_core.d_id)) { + xfs_kuid_to_uid(VFS_I(ip)->i_uid) != + be32_to_cpu(udqp->q_core.d_id)) { udq_delblks = udqp; /* * If there are delayed allocation blocks, then we have to @@ -1840,7 +1846,8 @@ xfs_qm_vop_chown_reserve( } } if (XFS_IS_GQUOTA_ON(ip->i_mount) && gdqp && - ip->i_d.di_gid != be32_to_cpu(gdqp->q_core.d_id)) { + xfs_kgid_to_gid(VFS_I(ip)->i_gid) != + be32_to_cpu(gdqp->q_core.d_id)) { gdq_delblks = gdqp; if (delblks) { ASSERT(ip->i_gdquot); @@ -1937,14 +1944,17 @@ xfs_qm_vop_create_dqattach(

if (udqp && XFS_IS_UQUOTA_ON(mp)) { ASSERT(ip->i_udquot == NULL); - ASSERT(ip->i_d.di_uid == be32_to_cpu(udqp->q_core.d_id)); + ASSERT(xfs_kuid_to_uid(VFS_I(ip)->i_uid) == + be32_to_cpu(udqp->q_core.d_id));

ip->i_udquot = xfs_qm_dqhold(udqp); xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1); } if (gdqp && XFS_IS_GQUOTA_ON(mp)) { ASSERT(ip->i_gdquot == NULL); - ASSERT(ip->i_d.di_gid == be32_to_cpu(gdqp->q_core.d_id)); + ASSERT(xfs_kgid_to_gid(VFS_I(ip)->i_gid) == + be32_to_cpu(gdqp->q_core.d_id)); + ip->i_gdquot = xfs_qm_dqhold(gdqp); xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1); } diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index efe42ae7a2f3..aa8fc1f55fbd 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -86,7 +86,7 @@ extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, struct xfs_mount *, struct xfs_dquot *, struct xfs_dquot *, struct xfs_dquot *, int64_t, long, uint);

-extern int xfs_qm_vop_dqalloc(struct xfs_inode *, xfs_dqid_t, xfs_dqid_t, +extern int xfs_qm_vop_dqalloc(struct xfs_inode *, kuid_t, kgid_t, prid_t, uint, struct xfs_dquot **, struct xfs_dquot **, struct xfs_dquot **); extern void xfs_qm_vop_create_dqattach(struct xfs_trans *, struct xfs_inode *, @@ -109,7 +109,7 @@ extern void xfs_qm_unmount_quotas(struct xfs_mount *);

#else static inline int -xfs_qm_vop_dqalloc(struct xfs_inode *ip, xfs_dqid_t uid, xfs_dqid_t gid, +xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid, prid_t prid, uint flags, struct xfs_dquot **udqp, struct xfs_dquot **gdqp, struct xfs_dquot **pdqp) { diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index ed66fd2de327..97336fb9119a 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -191,9 +191,7 @@ xfs_symlink( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, - xfs_kuid_to_uid(current_fsuid()), - xfs_kgid_to_gid(current_fsgid()), prid, + error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error)

From: Christoph Hellwig hch@lst.de

commit b81b79f4eda2ea98ae5695c0b6eb384c8d90b74d upstream.

Add a new wrapper to check if a file system supports the v3 inode format with a larger dinode core. Previously we used xfs_sb_version_hascrc for that, which is technically correct but a little confusing to read.

Also move xfs_dinode_good_version next to xfs_sb_version_has_v3inode so that we have one place that documents the superblock version to inode version relationship.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Brian Foster bfoster@redhat.com Reviewed-by: Chandan Rajendra chandanrlinux@gmail.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Chandan Babu R chandan.babu@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/libxfs/xfs_format.h | 17 +++++++++++++++++ fs/xfs/libxfs/xfs_ialloc.c | 4 ++-- fs/xfs/libxfs/xfs_inode_buf.c | 17 +++-------------- fs/xfs/libxfs/xfs_inode_buf.h | 2 -- fs/xfs/libxfs/xfs_trans_resv.c | 2 +- fs/xfs/xfs_buf_item.c | 2 +- fs/xfs/xfs_log_recover.c | 2 +- 7 files changed, 25 insertions(+), 21 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 1f24473121f0..c20c4dd6e1d3 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -497,6 +497,23 @@ static inline bool xfs_sb_version_hascrc(struct xfs_sb *sbp) return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5; }

+/* + * v5 file systems support V3 inodes only, earlier file systems support + * v2 and v1 inodes. + */ +static inline bool xfs_sb_version_has_v3inode(struct xfs_sb *sbp) +{ + return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5; +} + +static inline bool xfs_dinode_good_version(struct xfs_sb *sbp, + uint8_t version) +{ + if (xfs_sb_version_has_v3inode(sbp)) + return version == 3; + return version == 1 || version == 2; +} + static inline bool xfs_sb_version_has_pquotino(struct xfs_sb *sbp) { return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5; diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index c3e0c2f61be4..ddf92b14223a 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -303,7 +303,7 @@ xfs_ialloc_inode_init( * That means for v3 inode we log the entire buffer rather than just the * inode cores. */ - if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (xfs_sb_version_has_v3inode(&mp->m_sb)) { version = 3; ino = XFS_AGINO_TO_INO(mp, agno, XFS_AGB_TO_AGINO(mp, agbno));

@@ -2818,7 +2818,7 @@ xfs_ialloc_setup_geometry( * cannot change the behavior. */ igeo->inode_cluster_size_raw = XFS_INODE_BIG_CLUSTER_SIZE; - if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (xfs_sb_version_has_v3inode(&mp->m_sb)) { int new_size = igeo->inode_cluster_size_raw;

new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 947c2aac66bd..c4fdb0c012aa 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -44,17 +44,6 @@ xfs_inobp_check( } #endif

-bool -xfs_dinode_good_version( - struct xfs_mount *mp, - __u8 version) -{ - if (xfs_sb_version_hascrc(&mp->m_sb)) - return version == 3; - - return version == 1 || version == 2; -} - /* * If we are doing readahead on an inode buffer, we might be in log recovery * reading an inode allocation buffer that hasn't yet been replayed, and hence @@ -93,7 +82,7 @@ xfs_inode_buf_verify( dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog)); unlinked_ino = be32_to_cpu(dip->di_next_unlinked); di_ok = xfs_verify_magic16(bp, dip->di_magic) && - xfs_dinode_good_version(mp, dip->di_version) && + xfs_dinode_good_version(&mp->m_sb, dip->di_version) && xfs_verify_agino_or_null(mp, agno, unlinked_ino); if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP))) { @@ -454,7 +443,7 @@ xfs_dinode_verify(

/* Verify v3 integrity information first */ if (dip->di_version >= 3) { - if (!xfs_sb_version_hascrc(&mp->m_sb)) + if (!xfs_sb_version_has_v3inode(&mp->m_sb)) return __this_address; if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize, XFS_DINODE_CRC_OFF)) @@ -629,7 +618,7 @@ xfs_iread(

/* shortcut IO on inode allocation if possible */ if ((iget_flags & XFS_IGET_CREATE) && - xfs_sb_version_hascrc(&mp->m_sb) && + xfs_sb_version_has_v3inode(&mp->m_sb) && !(mp->m_flags & XFS_MOUNT_IKEEP)) { /* initialise the on-disk inode core */ memset(&ip->i_d, 0, sizeof(ip->i_d)); diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 0cb11fcc74b6..f1b73ecb1d82 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -59,8 +59,6 @@ void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from); void xfs_log_dinode_to_disk(struct xfs_log_dinode *from, struct xfs_dinode *to);

-bool xfs_dinode_good_version(struct xfs_mount *mp, __u8 version); - #if defined(DEBUG) void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *); #else diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 824073a839ac..8ece346def97 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -187,7 +187,7 @@ xfs_calc_inode_chunk_res( XFS_FSB_TO_B(mp, 1)); if (alloc) { /* icreate tx uses ordered buffers */ - if (xfs_sb_version_hascrc(&mp->m_sb)) + if (xfs_sb_version_has_v3inode(&mp->m_sb)) return res; size = XFS_FSB_TO_B(mp, 1); } diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index b1452117e442..f98260ed6d51 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -328,7 +328,7 @@ xfs_buf_item_format( * occurs during recovery. */ if (bip->bli_flags & XFS_BLI_INODE_BUF) { - if (xfs_sb_version_hascrc(&lip->li_mountp->m_sb) || + if (xfs_sb_version_has_v3inode(&lip->li_mountp->m_sb) || !((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) && xfs_log_item_in_current_chkpt(lip))) bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF; diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 6c60cdd10d33..598a8c00a082 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3018,7 +3018,7 @@ xlog_recover_inode_pass2( * superblock flag to determine whether we need to look at di_flushiter * to skip replay when the on disk inode is newer than the log one */ - if (!xfs_sb_version_hascrc(&mp->m_sb) && + if (!xfs_sb_version_has_v3inode(&mp->m_sb) && ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) { /* * Deal with the wrap case, DI_MAX_FLUSH is less

From: Christoph Hellwig hch@lst.de

commit b3d1d37544d8c98be610df0ed66c884ff18748d5 upstream.

di_flags2 is initialized to zero for v4 and earlier file systems. This means di_flags2 can only be non-zero for a v5 file systems, in which case both the parent and child inodes can store the field. Remove the extra di_version check, and also remove the rather pointless local di_flags2 variable while at it.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Brian Foster bfoster@redhat.com Reviewed-by: Chandan Rajendra chandanrlinux@gmail.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Chandan Babu R chandan.babu@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_inode.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 9d6ad669adc5..cb44bdf1c22e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -902,20 +902,13 @@ xfs_ialloc(

ip->i_d.di_flags |= di_flags; } - if (pip && - (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) && - pip->i_d.di_version == 3 && - ip->i_d.di_version == 3) { - uint64_t di_flags2 = 0; - + if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY)) { if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) { - di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; + ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; ip->i_d.di_cowextsize = pip->i_d.di_cowextsize; } if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) - di_flags2 |= XFS_DIFLAG2_DAX; - - ip->i_d.di_flags2 |= di_flags2; + ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX; } /* FALLTHROUGH */ case S_IFLNK:

From: Christoph Hellwig hch@lst.de

commit 01ea173e103edd5ec41acec65b9261b87e123fc2 upstream.

XFS always inherits the SGID bit if it is set on the parent inode, while the generic inode_init_owner does not do this in a few cases where it can create a possible security problem, see commit 0fa3ecd87848 ("Fix up non-directory creation in SGID directories") for details.

Switch XFS to use the generic helper for the normal path to fix this, just keeping the simple field inheritance open coded for the case of the non-sgid case with the bsdgrpid mount option.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_inode.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 6bc565c186ca..568a9332efd2 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -750,6 +750,7 @@ xfs_ialloc( xfs_buf_t **ialloc_context, xfs_inode_t **ipp) { + struct inode *dir = pip ? VFS_I(pip) : NULL; struct xfs_mount *mp = tp->t_mountp; xfs_ino_t ino; xfs_inode_t *ip; @@ -795,18 +796,17 @@ xfs_ialloc( return error; ASSERT(ip != NULL); inode = VFS_I(ip); - inode->i_mode = mode; set_nlink(inode, nlink); - inode->i_uid = current_fsuid(); inode->i_rdev = rdev; ip->i_d.di_projid = prid;

- if (pip && XFS_INHERIT_GID(pip)) { - inode->i_gid = VFS_I(pip)->i_gid; - if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode)) - inode->i_mode |= S_ISGID; + if (dir && !(dir->i_mode & S_ISGID) && + (mp->m_flags & XFS_MOUNT_GRPID)) { + inode->i_uid = current_fsuid(); + inode->i_gid = dir->i_gid; + inode->i_mode = mode; } else { - inode->i_gid = current_fsgid(); + inode_init_owner(inode, dir, mode); }

/*

From: "Darrick J. Wong" darrick.wong@oracle.com

commit 6519f708cc355c4834edbe1885c8542c0e7ef907 uptream.

[ Slightly modify fs/xfs/xfs_linux.h to resolve merge conflicts ]

Redefine XFS_IS_CORRUPT so that it reports corruptions only via xfs_corruption_report. Since these are on-disk contents (and not checks of internal state), we don't ever want to panic the kernel. This also amends the corruption report to recommend unmounting and running xfs_repair.

Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Chandan Babu R chandan.babu@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_error.c | 2 +- fs/xfs/xfs_linux.h | 6 ++++++ 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index e9acd58248f9..182b70464b71 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -335,7 +335,7 @@ xfs_corruption_error( int linenum, xfs_failaddr_t failaddr) { - if (level <= xfs_error_level) + if (buf && level <= xfs_error_level) xfs_hex_dump(buf, bufsize); xfs_error_report(tag, level, mp, filename, linenum, failaddr); xfs_alert(mp, "Corruption detected. Unmount and run xfs_repair"); diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index f4f52ac5628c..4f6f09157f0d 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -217,6 +217,12 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, #endif /* XFS_WARN */ #endif /* DEBUG */

+#define XFS_IS_CORRUPT(mp, expr) \ + (unlikely(expr) ? xfs_corruption_error(#expr, XFS_ERRLEVEL_LOW, (mp), \ + NULL, 0, __FILE__, __LINE__, \ + __this_address), \ + true : false) + #define STATIC static noinline

#ifdef CONFIG_XFS_RT

From: Brian Foster bfoster@redhat.com

commit 1cd738b13ae9b29e03d6149f0246c61f76e81fcf upstream.

[ Slightly modify fs/xfs/libxfs/xfs_btree.c to resolve merge conflicts ]

The assert in xfs_btree_del_cursor() checks that the bmapbt block allocation field has been handled correctly before the cursor is freed. This field is used for accurate calculation of indirect block reservation requirements (for delayed allocations), for example. generic/019 reproduces a scenario where this assert fails because the filesystem has shutdown while in the middle of a bmbt record insertion. This occurs after a bmbt block has been allocated via the cursor but before the higher level bmap function (i.e. xfs_bmap_add_extent_hole_real()) completes and resets the field.

Update the assert to accommodate the transient state if the filesystem has shutdown. While here, clean up the indentation and comments in the function.

Signed-off-by: Brian Foster bfoster@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/libxfs/xfs_btree.c | 30 +++++++++++------------------- 1 file changed, 11 insertions(+), 19 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 8c43cac15832..121251651fea 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -354,20 +354,17 @@ xfs_btree_free_block( */ void xfs_btree_del_cursor( - xfs_btree_cur_t *cur, /* btree cursor */ - int error) /* del because of error */ + struct xfs_btree_cur *cur, /* btree cursor */ + int error) /* del because of error */ { - int i; /* btree level */ + int i; /* btree level */

/* - * Clear the buffer pointers, and release the buffers. - * If we're doing this in the face of an error, we - * need to make sure to inspect all of the entries - * in the bc_bufs array for buffers to be unlocked. - * This is because some of the btree code works from - * level n down to 0, and if we get an error along - * the way we won't have initialized all the entries - * down to 0. + * Clear the buffer pointers and release the buffers. If we're doing + * this because of an error, inspect all of the entries in the bc_bufs + * array for buffers to be unlocked. This is because some of the btree + * code works from level n down to 0, and if we get an error along the + * way we won't have initialized all the entries down to 0. */ for (i = 0; i < cur->bc_nlevels; i++) { if (cur->bc_bufs[i]) @@ -375,15 +372,10 @@ xfs_btree_del_cursor( else if (!error) break; } - /* - * Can't free a bmap cursor without having dealt with the - * allocated indirect blocks' accounting. - */ + ASSERT(cur->bc_btnum != XFS_BTNUM_BMAP || - cur->bc_private.b.allocated == 0); - /* - * Free the cursor. - */ + cur->bc_private.b.allocated == 0 || + XFS_FORCED_SHUTDOWN(cur->bc_mp)); kmem_zone_free(xfs_btree_cur_zone, cur); }

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

commit d336f7ebc65007f5831e2297e6f3383ae8dbf8ed upstream.

[ Slightly modify fs/xfs/xfs_mount.c to resolve merge conflicts ]

If we allocate quota inodes in the process of mounting a filesystem but then decide to abort the mount, it's possible that the quota inodes are sitting around pinned by the log. Now that inode reclaim relies on the AIL to flush inodes, we have to force the log and push the AIL in between releasing the quota inodes and kicking off reclaim to tear down all the incore inodes. Do this by extracting the bits we need from the unmount path and reusing them. As an added bonus, failed writes during a failed mount will not retry forever now.

This was originally found during a fuzz test of metadata directories (xfs/1546), but the actual symptom was that reclaim hung up on the quota inodes.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Dave Chinner dchinner@redhat.com Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_mount.c | 90 +++++++++++++++++++++++----------------------- 1 file changed, 44 insertions(+), 46 deletions(-)

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 2860966af6c2..2277f21c4f14 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -674,6 +674,47 @@ xfs_check_summary_counts( return xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount); }

+/* + * Flush and reclaim dirty inodes in preparation for unmount. Inodes and + * internal inode structures can be sitting in the CIL and AIL at this point, + * so we need to unpin them, write them back and/or reclaim them before unmount + * can proceed. + * + * An inode cluster that has been freed can have its buffer still pinned in + * memory because the transaction is still sitting in a iclog. The stale inodes + * on that buffer will be pinned to the buffer until the transaction hits the + * disk and the callbacks run. Pushing the AIL will skip the stale inodes and + * may never see the pinned buffer, so nothing will push out the iclog and + * unpin the buffer. + * + * Hence we need to force the log to unpin everything first. However, log + * forces don't wait for the discards they issue to complete, so we have to + * explicitly wait for them to complete here as well. + * + * Then we can tell the world we are unmounting so that error handling knows + * that the filesystem is going away and we should error out anything that we + * have been retrying in the background. This will prevent never-ending + * retries in AIL pushing from hanging the unmount. + * + * Finally, we can push the AIL to clean all the remaining dirty objects, then + * reclaim the remaining inodes that are still in memory at this point in time. + */ +static void +xfs_unmount_flush_inodes( + struct xfs_mount *mp) +{ + xfs_log_force(mp, XFS_LOG_SYNC); + xfs_extent_busy_wait_all(mp); + flush_workqueue(xfs_discard_wq); + + mp->m_flags |= XFS_MOUNT_UNMOUNTING; + + xfs_ail_push_all_sync(mp->m_ail); + cancel_delayed_work_sync(&mp->m_reclaim_work); + xfs_reclaim_inodes(mp, SYNC_WAIT); + xfs_health_unmount(mp); +} + /* * This function does the following on an initial mount of a file system: * - reads the superblock from disk and init the mount struct @@ -1047,7 +1088,7 @@ xfs_mountfs( /* Clean out dquots that might be in memory after quotacheck. */ xfs_qm_unmount(mp); /* - * Cancel all delayed reclaim work and reclaim the inodes directly. + * Flush all inode reclamation work and flush the log. * We have to do this /after/ rtunmount and qm_unmount because those * two will have scheduled delayed reclaim for the rt/quota inodes. * @@ -1057,11 +1098,8 @@ xfs_mountfs( * qm_unmount_quotas and therefore rely on qm_unmount to release the * quota inodes. */ - cancel_delayed_work_sync(&mp->m_reclaim_work); - xfs_reclaim_inodes(mp, SYNC_WAIT); - xfs_health_unmount(mp); + xfs_unmount_flush_inodes(mp); out_log_dealloc: - mp->m_flags |= XFS_MOUNT_UNMOUNTING; xfs_log_mount_cancel(mp); out_fail_wait: if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) @@ -1102,47 +1140,7 @@ xfs_unmountfs( xfs_rtunmount_inodes(mp); xfs_irele(mp->m_rootip);

- /* - * We can potentially deadlock here if we have an inode cluster - * that has been freed has its buffer still pinned in memory because - * the transaction is still sitting in a iclog. The stale inodes - * on that buffer will have their flush locks held until the - * transaction hits the disk and the callbacks run. the inode - * flush takes the flush lock unconditionally and with nothing to - * push out the iclog we will never get that unlocked. hence we - * need to force the log first. - */ - xfs_log_force(mp, XFS_LOG_SYNC); - - /* - * Wait for all busy extents to be freed, including completion of - * any discard operation. - */ - xfs_extent_busy_wait_all(mp); - flush_workqueue(xfs_discard_wq); - - /* - * We now need to tell the world we are unmounting. This will allow - * us to detect that the filesystem is going away and we should error - * out anything that we have been retrying in the background. This will - * prevent neverending retries in AIL pushing from hanging the unmount. - */ - mp->m_flags |= XFS_MOUNT_UNMOUNTING; - - /* - * Flush all pending changes from the AIL. - */ - xfs_ail_push_all_sync(mp->m_ail); - - /* - * And reclaim all inodes. At this point there should be no dirty - * inodes and none should be pinned or locked, but use synchronous - * reclaim just to be sure. We can stop background inode reclaim - * here as well if it is still running. - */ - cancel_delayed_work_sync(&mp->m_reclaim_work); - xfs_reclaim_inodes(mp, SYNC_WAIT); - xfs_health_unmount(mp); + xfs_unmount_flush_inodes(mp);

xfs_qm_unmount(mp);