On Wed, May 13, 2020 at 11:17:17AM -0700, Darrick J. Wong wrote: > On Wed, May 13, 2020 at 04:35:26PM +0200, Jan Kara wrote: > > On Tue 12-05-20 22:43:22, ira.weiny@xxxxxxxxx wrote: > > > From: Ira Weiny <ira.weiny@xxxxxxxxx> > > > > > > We add 'always', 'never', and 'inode' (default). '-o dax' continue to > > > operate the same. > > > > > > Specifically we introduce a 2nd DAX mount flag EXT4_MOUNT2_DAX_NEVER and set > > > it and EXT4_MOUNT_DAX_ALWAYS appropriately. > > > > > > We also force EXT4_MOUNT2_DAX_NEVER if !CONFIG_FS_DAX. > > > > > > https://lore.kernel.org/lkml/20200405061945.GA94792@xxxxxxxxxxxxxxxxxxxxxxxxx/ > > > > > > Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx> > > > > > > --- > > > Changes from RFC: > > > Combine remount check for DAX_NEVER with DAX_ALWAYS > > > Update ext4_should_enable_dax() > > > --- > > > fs/ext4/ext4.h | 1 + > > > fs/ext4/inode.c | 2 ++ > > > fs/ext4/super.c | 43 +++++++++++++++++++++++++++++++++++++------ > > > 3 files changed, 40 insertions(+), 6 deletions(-) > > > > > > diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h > > > index 86a0994332ce..01d1de838896 100644 > > > --- a/fs/ext4/ext4.h > > > +++ b/fs/ext4/ext4.h > > > @@ -1168,6 +1168,7 @@ struct ext4_inode_info { > > > blocks */ > > > #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated > > > file systems */ > > > +#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */ > > > > > > #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly > > > specified journal checksum */ > > > diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c > > > index 23e42a223235..140b1930e2f4 100644 > > > --- a/fs/ext4/inode.c > > > +++ b/fs/ext4/inode.c > > > @@ -4400,6 +4400,8 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) > > > > > > static bool ext4_should_enable_dax(struct inode *inode) > > > { > > > + if (test_opt2(inode->i_sb, DAX_NEVER)) > > > + return false; > > > if (!S_ISREG(inode->i_mode)) > > > return false; > > > if (ext4_should_journal_data(inode)) > > > diff --git a/fs/ext4/super.c b/fs/ext4/super.c > > > index 5ec900fdf73c..e01a040a58a9 100644 > > > --- a/fs/ext4/super.c > > > +++ b/fs/ext4/super.c > > > @@ -1505,6 +1505,7 @@ enum { > > > Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, > > > Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, > > > Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax, > > > + Opt_dax_str, > > > Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, > > > Opt_nowarn_on_error, Opt_mblk_io_submit, > > > Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize, > > > @@ -1570,6 +1571,7 @@ static const match_table_t tokens = { > > > {Opt_barrier, "barrier"}, > > > {Opt_nobarrier, "nobarrier"}, > > > {Opt_i_version, "i_version"}, > > > + {Opt_dax_str, "dax=%s"}, > > > > Hum, maybe it would be easier to handle this like we do with e.g. 'data=' > > mount option? I.e. like: > > > > {Opt_dax_always, "dax=always"}, > > {Opt_dax_never, "dax=never"}, > > {Opt_dax_inode, "dax=inode"), > > > > and then handle these three tokens... Not that it would be a big difference > > but that's why we usually handle mount options with small "enums" in ext4. We could, but at this point it would need to be reworked for the new option parsing code anyway... I've kind of been waiting to see if another round of those patches were submitted but looks like they are taking more work. > > I was hoping that we could hoist the tristate enum bits out of XFS and > simply share them across the three DAX filesystems, but I have no idea > if that will work with a filesystem that hasn't been converted to the > new mount option parsing api. I'm betting no. :/ > > (FWIW see enum xfs_dax_mode and struct constant_table dax_param_enums in > fs/xfs/xfs_super.c in the for-next tree.) > > Hm, otoh I don't see any recent posting of an ext4 mount parsing > conversion series, so yeah this is probably as good as can be done until > that happens. > That is my thinking. I wanted to get this series out because as a feature it would be nice if this went in together with XFS for 5.8. But I understand if we want to wait. Ira > > --D > > > Honza > > > > > {Opt_dax, "dax"}, > > > {Opt_stripe, "stripe=%u"}, > > > {Opt_delalloc, "delalloc"}, > > > @@ -1767,6 +1769,7 @@ static const struct mount_opts { > > > {Opt_min_batch_time, 0, MOPT_GTE0}, > > > {Opt_inode_readahead_blks, 0, MOPT_GTE0}, > > > {Opt_init_itable, 0, MOPT_GTE0}, > > > + {Opt_dax_str, 0, MOPT_STRING}, > > > {Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET}, > > > {Opt_stripe, 0, MOPT_GTE0}, > > > {Opt_resuid, 0, MOPT_GTE0}, > > > @@ -2076,13 +2079,32 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, > > > } > > > sbi->s_jquota_fmt = m->mount_opt; > > > #endif > > > - } else if (token == Opt_dax) { > > > + } else if (token == Opt_dax || token == Opt_dax_str) { > > > #ifdef CONFIG_FS_DAX > > > - ext4_msg(sb, KERN_WARNING, > > > - "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); > > > - sbi->s_mount_opt |= m->mount_opt; > > > + char *tmp = match_strdup(&args[0]); > > > + > > > + if (!tmp || !strcmp(tmp, "always")) { > > > + ext4_msg(sb, KERN_WARNING, > > > + "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); > > > + sbi->s_mount_opt |= EXT4_MOUNT_DAX_ALWAYS; > > > + sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER; > > > + } else if (!strcmp(tmp, "never")) { > > > + sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER; > > > + sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; > > > + } else if (!strcmp(tmp, "inode")) { > > > + sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; > > > + sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER; > > > + } else { > > > + ext4_msg(sb, KERN_WARNING, "DAX invalid option."); > > > + kfree(tmp); > > > + return -1; > > > + } > > > + > > > + kfree(tmp); > > > #else > > > ext4_msg(sb, KERN_INFO, "dax option not supported"); > > > + sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER; > > > + sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; > > > return -1; > > > #endif > > > } else if (token == Opt_data_err_abort) { > > > @@ -2306,6 +2328,13 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, > > > if (DUMMY_ENCRYPTION_ENABLED(sbi)) > > > SEQ_OPTS_PUTS("test_dummy_encryption"); > > > > > > + if (test_opt2(sb, DAX_NEVER)) > > > + SEQ_OPTS_PUTS("dax=never"); > > > + else if (test_opt(sb, DAX_ALWAYS)) > > > + SEQ_OPTS_PUTS("dax=always"); > > > + else > > > + SEQ_OPTS_PUTS("dax=inode"); > > > + > > > ext4_show_quota_options(seq, sb); > > > return 0; > > > } > > > @@ -5425,10 +5454,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) > > > goto restore_opts; > > > } > > > > > > - if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX_ALWAYS) { > > > + if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX_ALWAYS || > > > + (sbi->s_mount_opt2 ^ old_opts.s_mount_opt2) & EXT4_MOUNT2_DAX_NEVER) { > > > ext4_msg(sb, KERN_WARNING, "warning: refusing change of " > > > - "dax flag with busy inodes while remounting"); > > > + "dax mount option with busy inodes while remounting"); > > > sbi->s_mount_opt ^= EXT4_MOUNT_DAX_ALWAYS; > > > + sbi->s_mount_opt2 ^= EXT4_MOUNT2_DAX_NEVER; > > > } > > > > > > if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) > > > -- > > > 2.25.1 > > > > > -- > > Jan Kara <jack@xxxxxxxx> > > SUSE Labs, CR
