From 684b413b5483f57c890c171b9400076a0143b918 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Fri, 18 Sep 2026 16:06:42 +0200 Subject: virtio_blk: set the zone write granularity virtblk_read_zoned_limits() reads the write granularity that the device reports in virtio_blk_zoned_characteristics and assigns it to the physical block size and to io_min, but never to the limit that is named after it. queue_limits.zone_write_granularity is left at zero, so blk_validate_zoned_limits() raises it to the logical block size: if (lim->zone_write_granularity < lim->logical_block_size) lim->zone_write_granularity = lim->logical_block_size; A device that reports a granularity coarser than its logical block size, which is what the field exists to express, therefore has it silently reduced. A 512e host managed disk passed through to a guest reports a logical block size of 512 and a write granularity of 4096, and the guest ends up with a zone write granularity of 512. bio_split_alignment() returns lim->zone_write_granularity if it is non-zero and bio_split_io_at() may split a bio with as per bio_split_alignment(). This can real to the write getting rejected by the host drive, as the write is not aligned to the physical block size. zonefs also takes its block size from bdev_zone_write_granularity(), so it would incorrectly use 512 on a disk that requires 4096. sd_zbc_read_zones() sets the limit from the physical block size for the same reason. NVMe ZNS and null_blk leave it unset, but the fallback gives the right answer for them, as their write granularity is the logical block size. virtio carries a separate value that may exceed it. Set the zone write granularity from the value that the device reports. Fixes: 95bfec41bd3d ("virtio-blk: add support for zoned block devices") Signed-off-by: Niklas Cassel Reviewed-by: Stefan Hajnoczi Link: https://patch.msgid.link/20260918140641.2031075-2-cassel@kernel.org Signed-off-by: Jens Axboe --- fs/ext4/fsync.c | 176 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 176 insertions(+) create mode 100644 fs/ext4/fsync.c (limited to 'fs/ext4/fsync.c') diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c new file mode 100644 index 000000000..2999c2cc8 --- /dev/null +++ b/fs/ext4/fsync.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext4/fsync.c + * + * Copyright (C) 1993 Stephen Tweedie (sct@redhat.com) + * from + * Copyright (C) 1992 Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * from + * linux/fs/minix/truncate.c Copyright (C) 1991, 1992 Linus Torvalds + * + * ext4fs fsync primitive + * + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + * + * Removed unnecessary code duplication for little endian machines + * and excessive __inline__s. + * Andi Kleen, 1997 + * + * Major simplications and cleanup - we only need to do the metadata, because + * we can depend on generic_block_fdatasync() to sync the data blocks. + */ + +#include +#include +#include +#include +#include +#include + +#include "ext4.h" +#include "ext4_jbd2.h" + +#include + +/* + * If we're not journaling and this is a just-created file, we have to + * sync our parent directory (if it was freshly created) since + * otherwise it will only be written by writeback, leaving a huge + * window during which a crash may lose the file. This may apply for + * the parent directory's parent as well, and so on recursively, if + * they are also freshly created. + */ +static int ext4_sync_parent(struct inode *inode) +{ + struct dentry *dentry, *next; + int ret = 0; + + if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) + return 0; + dentry = d_find_any_alias(inode); + if (!dentry) + return 0; + while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { + ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); + + next = dget_parent(dentry); + dput(dentry); + dentry = next; + inode = dentry->d_inode; + + /* + * The directory inode may have gone through rmdir by now. But + * the inode itself and its blocks are still allocated (we hold + * a reference to the inode via its dentry), so it didn't go + * through ext4_evict_inode()) and so we are safe to flush + * metadata blocks and the inode. + */ + ret = sync_inode_metadata(inode, 1); + if (ret) + break; + } + dput(dentry); + return ret; +} + +static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end, + int datasync, bool *needs_barrier) +{ + struct inode *inode = file->f_inode; + int ret; + + ret = sync_inode_metadata(inode, 1); + if (ret) + return ret; + ret = ext4_sync_parent(inode); + + if (test_opt(inode->i_sb, BARRIER)) + *needs_barrier = true; + + return ret; +} + +static int ext4_fsync_journal(struct inode *inode, bool datasync, + bool *needs_barrier) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; + tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; + + /* + * Fastcommit does not really support fsync on directories or other + * special files. Force a full commit. + */ + if (!S_ISREG(inode->i_mode)) + return ext4_force_commit(inode->i_sb); + + if (journal->j_flags & JBD2_BARRIER && + !jbd2_trans_will_send_data_barrier(journal, commit_tid)) + *needs_barrier = true; + + return ext4_fc_commit(journal, commit_tid); +} + +/* + * akpm: A new design for ext4_sync_file(). + * + * This is only called from sys_fsync(), sys_fdatasync() and sys_msync(). + * There cannot be a transaction open by this task. + * Another task could have dirtied this inode. Its data can be in any + * state in the journalling system. + * + * What we do is just kick off a commit and wait on it. This will snapshot the + * inode to disk. + */ +int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) +{ + int ret = 0, err; + bool needs_barrier = false; + struct inode *inode = file->f_mapping->host; + + ret = ext4_emergency_state(inode->i_sb); + if (unlikely(ret)) + return ret; + + ASSERT(ext4_journal_current_handle() == NULL); + + trace_ext4_sync_file_enter(file, datasync); + + if (sb_rdonly(inode->i_sb)) + goto out; + + ret = file_write_and_wait_range(file, start, end); + if (ret) + goto out; + + if (!EXT4_SB(inode->i_sb)->s_journal) { + ret = ext4_fsync_nojournal(file, start, end, datasync, + &needs_barrier); + if (needs_barrier) + goto issue_flush; + goto out; + } + + /* + * The caller's filemap_fdatawrite()/wait will sync the data. + * Metadata is in the journal, we wait for proper transaction to + * commit here. + */ + ret = ext4_fsync_journal(inode, datasync, &needs_barrier); + +issue_flush: + if (needs_barrier) { + err = blkdev_issue_flush(inode->i_sb->s_bdev); + if (!ret) + ret = err; + } +out: + err = file_check_and_advance_wb_err(file); + if (ret == 0) + ret = err; + trace_ext4_sync_file_exit(inode, ret); + return ret; +} -- cgit v1.3.1