From: Dave Chinner dchinner@redhat.com

commit 756b1c343333a5aefcc26b0409f3fd16f72281bf upstream.

Because the iomap code using PF_MEMALLOC_NOFS to detect transaction recursion in XFS is just wrong. Remove it from the iomap code and replace it with XFS specific internal checks using current->journal_info instead.

[djwong: This change also realigns the lifetime of NOFS flag changes to match the incore transaction, instead of the inconsistent scheme we have now.]

Fixes: 9070733b4efa ("xfs: abstract PF_FSTRANS to PF_MEMALLOC_NOFS") Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Amir Goldstein amir73il@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/iomap/buffered-io.c | 7 ------- fs/xfs/libxfs/xfs_btree.c | 12 ++++++++++-- fs/xfs/xfs_aops.c | 17 +++++++++++++++-- fs/xfs/xfs_trans.c | 20 +++++--------------- fs/xfs/xfs_trans.h | 30 ++++++++++++++++++++++++++++++ 5 files changed, 60 insertions(+), 26 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index dd33b31b0a82..86297f59b43e 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1460,13 +1460,6 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) PF_MEMALLOC)) goto redirty;

- /* - * Given that we do not allow direct reclaim to call us, we should - * never be called in a recursive filesystem reclaim context. - */ - if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS)) - goto redirty; - /* * Is this page beyond the end of the file? * diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 98c82f4935e1..24c7d30e41df 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -2811,7 +2811,7 @@ xfs_btree_split_worker( struct xfs_btree_split_args *args = container_of(work, struct xfs_btree_split_args, work); unsigned long pflags; - unsigned long new_pflags = PF_MEMALLOC_NOFS; + unsigned long new_pflags = 0;

/* * we are in a transaction context here, but may also be doing work @@ -2823,12 +2823,20 @@ xfs_btree_split_worker( new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;

current_set_flags_nested(&pflags, new_pflags); + xfs_trans_set_context(args->cur->bc_tp);

args->result = __xfs_btree_split(args->cur, args->level, args->ptrp, args->key, args->curp, args->stat); - complete(args->done);

+ xfs_trans_clear_context(args->cur->bc_tp); current_restore_flags_nested(&pflags, new_pflags); + + /* + * Do not access args after complete() has run here. We don't own args + * and the owner may run and free args before we return here. + */ + complete(args->done); + }

/* diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 4b76a32d2f16..953de843d9c3 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -62,7 +62,7 @@ xfs_setfilesize_trans_alloc( * We hand off the transaction to the completion thread now, so * clear the flag here. */ - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); + xfs_trans_clear_context(tp); return 0; }

@@ -125,7 +125,7 @@ xfs_setfilesize_ioend( * thus we need to mark ourselves as being in a transaction manually. * Similarly for freeze protection. */ - current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); + xfs_trans_set_context(tp); __sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);

/* we abort the update if there was an IO error */ @@ -577,6 +577,12 @@ xfs_vm_writepage( { struct xfs_writepage_ctx wpc = { };

+ if (WARN_ON_ONCE(current->journal_info)) { + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return 0; + } + return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops); }

@@ -587,6 +593,13 @@ xfs_vm_writepages( { struct xfs_writepage_ctx wpc = { };

+ /* + * Writing back data in a transaction context can result in recursive + * transactions. This is bad, so issue a warning and get out of here. + */ + if (WARN_ON_ONCE(current->journal_info)) + return 0; + xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops); } diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index c94e71f741b6..2d7deacea2cf 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -68,6 +68,7 @@ xfs_trans_free( xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);

trace_xfs_trans_free(tp, _RET_IP_); + xfs_trans_clear_context(tp); if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT)) sb_end_intwrite(tp->t_mountp->m_super); xfs_trans_free_dqinfo(tp); @@ -119,7 +120,8 @@ xfs_trans_dup(

ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used; tp->t_rtx_res = tp->t_rtx_res_used; - ntp->t_pflags = tp->t_pflags; + + xfs_trans_switch_context(tp, ntp);

/* move deferred ops over to the new tp */ xfs_defer_move(ntp, tp); @@ -153,9 +155,6 @@ xfs_trans_reserve( int error = 0; bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;

- /* Mark this thread as being in a transaction */ - current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); - /* * Attempt to reserve the needed disk blocks by decrementing * the number needed from the number available. This will @@ -163,10 +162,8 @@ xfs_trans_reserve( */ if (blocks > 0) { error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd); - if (error != 0) { - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); + if (error != 0) return -ENOSPC; - } tp->t_blk_res += blocks; }

@@ -240,9 +237,6 @@ xfs_trans_reserve( xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd); tp->t_blk_res = 0; } - - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); - return error; }

@@ -266,6 +260,7 @@ xfs_trans_alloc( tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL); if (!(flags & XFS_TRANS_NO_WRITECOUNT)) sb_start_intwrite(mp->m_super); + xfs_trans_set_context(tp);

/* * Zero-reservation ("empty") transactions can't modify anything, so @@ -878,7 +873,6 @@ __xfs_trans_commit(

xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);

- current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); xfs_trans_free(tp);

/* @@ -910,7 +904,6 @@ __xfs_trans_commit( xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket); tp->t_ticket = NULL; } - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); xfs_trans_free_items(tp, !!error); xfs_trans_free(tp);

@@ -970,9 +963,6 @@ xfs_trans_cancel( tp->t_ticket = NULL; }

- /* mark this thread as no longer being in a transaction */ - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); - xfs_trans_free_items(tp, dirty); xfs_trans_free(tp); } diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 084658946cc8..075eeade4f7d 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -268,4 +268,34 @@ xfs_trans_item_relog( return lip->li_ops->iop_relog(lip, tp); }

+static inline void +xfs_trans_set_context( + struct xfs_trans *tp) +{ + ASSERT(current->journal_info == NULL); + tp->t_pflags = memalloc_nofs_save(); + current->journal_info = tp; +} + +static inline void +xfs_trans_clear_context( + struct xfs_trans *tp) +{ + if (current->journal_info == tp) { + memalloc_nofs_restore(tp->t_pflags); + current->journal_info = NULL; + } +} + +static inline void +xfs_trans_switch_context( + struct xfs_trans *old_tp, + struct xfs_trans *new_tp) +{ + ASSERT(current->journal_info == old_tp); + new_tp->t_pflags = old_tp->t_pflags; + old_tp->t_pflags = 0; + current->journal_info = new_tp; +} + #endif /* __XFS_TRANS_H__ */

From: Pavel Reichl preichl@redhat.com

commit 92cf7d36384b99d5a57bf4422904a3c16dc4527a upstream.

Skip the warnings about mount option being deprecated if we are remounting and deprecated option state is not changing.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=211605 Fix-suggested-by: Eric Sandeen sandeen@redhat.com Signed-off-by: Pavel Reichl preichl@redhat.com

Reviewed-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Carlos Maiolino cmaiolino@redhat.com 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 --- fs/xfs/xfs_super.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index cba47adbbfdc..04af5d17abc7 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1155,6 +1155,22 @@ suffix_kstrtoint( return ret; }

+static inline void +xfs_fs_warn_deprecated( + struct fs_context *fc, + struct fs_parameter *param, + uint64_t flag, + bool value) +{ + /* Don't print the warning if reconfiguring and current mount point + * already had the flag set + */ + if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) && + !!(XFS_M(fc->root->d_sb)->m_flags & flag) == value) + return; + xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key); +} + /* * Set mount state from a mount option. * @@ -1294,19 +1310,19 @@ xfs_fc_parse_param( #endif /* Following mount options will be removed in September 2025 */ case Opt_ikeep: - xfs_warn(parsing_mp, "%s mount option is deprecated.", param->key); + xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, true); parsing_mp->m_flags |= XFS_MOUNT_IKEEP; return 0; case Opt_noikeep: - xfs_warn(parsing_mp, "%s mount option is deprecated.", param->key); + xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, false); parsing_mp->m_flags &= ~XFS_MOUNT_IKEEP; return 0; case Opt_attr2: - xfs_warn(parsing_mp, "%s mount option is deprecated.", param->key); + xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_ATTR2, true); parsing_mp->m_flags |= XFS_MOUNT_ATTR2; return 0; case Opt_noattr2: - xfs_warn(parsing_mp, "%s mount option is deprecated.", param->key); + xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_NOATTR2, true); parsing_mp->m_flags &= ~XFS_MOUNT_ATTR2; parsing_mp->m_flags |= XFS_MOUNT_NOATTR2; return 0;

From: Anthony Iliopoulos ailiop@suse.com

commit 25dfa65f814951a33072bcbae795989d817858da upstream.

Removal of kmem_zone_init wrappers accidentally changed a slab cache name from "xfs_trans" to "xf_trans". Fix this so that userspace consumers of /proc/slabinfo and /sys/kernel/slab can find it again.

Fixes: b1231760e443 ("xfs: Remove slab init wrappers") Signed-off-by: Anthony Iliopoulos ailiop@suse.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 Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 04af5d17abc7..6323974d6b3e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1934,7 +1934,7 @@ xfs_init_zones(void) if (!xfs_ifork_zone) goto out_destroy_da_state_zone;

- xfs_trans_zone = kmem_cache_create("xf_trans", + xfs_trans_zone = kmem_cache_create("xfs_trans", sizeof(struct xfs_trans), 0, 0, NULL); if (!xfs_trans_zone)

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

commit d4f74e162d238ce00a640af5f0611c3f51dad70e upstream.

The final parameter of filemap_write_and_wait_range is the end of the range to flush, not the length of the range to flush.

Fixes: 46afb0628b86 ("xfs: only flush the unshared range in xfs_reflink_unshare") Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Chandan Babu R chandanrlinux@gmail.com Reviewed-by: Brian Foster bfoster@redhat.com Signed-off-by: Amir Goldstein amir73il@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_reflink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 6fa05fb78189..aa46b75d75af 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1503,7 +1503,8 @@ xfs_reflink_unshare( if (error) goto out;

- error = filemap_write_and_wait_range(inode->i_mapping, offset, len); + error = filemap_write_and_wait_range(inode->i_mapping, offset, + offset + len - 1); if (error) goto out;