| Message ID | 74359fdc83688fb1aac1cb2c336fbd725590a131.1708709155.git.john@groves.net (mailing list archive) |
|---|---|
| State | Handled Elsewhere, archived |
| Headers | show |
| Series | Introduce the famfs shared-memory file system | expand |
On Fri, 23 Feb 2024 11:41:54 -0600 John Groves <John@Groves.net> wrote: > Famfs works on both /dev/pmem and /dev/dax devices. This commit introduces > the function that opens a block (pmem) device and the struct > dax_holder_operations that are needed for that ABI. > > In this commit, support for opening character /dev/dax is stubbed. A > later commit introduces this capability. > > Signed-off-by: John Groves <john@groves.net> Formatting comments mostly same as previous patches, so I'll stop repeating them. > --- > fs/famfs/famfs_inode.c | 83 ++++++++++++++++++++++++++++++++++++++++++ > 1 file changed, 83 insertions(+) > > diff --git a/fs/famfs/famfs_inode.c b/fs/famfs/famfs_inode.c > index 3329aff000d1..82c861998093 100644 > --- a/fs/famfs/famfs_inode.c > +++ b/fs/famfs/famfs_inode.c > @@ -68,5 +68,88 @@ static const struct super_operations famfs_ops = { > .show_options = famfs_show_options, > }; > > +/*************************************************************************************** > + * dax_holder_operations for block dax > + */ > + > +static int > +famfs_blk_dax_notify_failure( > + struct dax_device *dax_devp, > + u64 offset, > + u64 len, > + int mf_flags) > +{ > + > + pr_err("%s: dax_devp %llx offset %llx len %lld mf_flags %x\n", > + __func__, (u64)dax_devp, (u64)offset, (u64)len, mf_flags); > + return -EOPNOTSUPP; > +} > + > +const struct dax_holder_operations famfs_blk_dax_holder_ops = { > + .notify_failure = famfs_blk_dax_notify_failure, > +}; > + > +static int > +famfs_open_char_device( > + struct super_block *sb, > + struct fs_context *fc) > +{ > + pr_err("%s: Root device is %s, but your kernel does not support famfs on /dev/dax\n", > + __func__, fc->source); > + return -ENODEV; > +} > + > +/** > + * famfs_open_device() > + * > + * Open the memory device. If it looks like /dev/dax, call famfs_open_char_device(). > + * Otherwise try to open it as a block/pmem device. > + */ > +static int > +famfs_open_device( > + struct super_block *sb, > + struct fs_context *fc) > +{ > + struct famfs_fs_info *fsi = sb->s_fs_info; > + struct dax_device *dax_devp; > + u64 start_off = 0; > + struct bdev_handle *handlep; Definitely don't force alignment in local parameter definitions. Always goes wrong and makes for unreadable mess in patches! > + > + if (fsi->dax_devp) { > + pr_err("%s: already mounted\n", __func__); Fine to fail but worth a error message? Not sure on convention on this but seems noisy and maybe in userspace control which isn't good. > + return -EALREADY; > + } > + > + if (strstr(fc->source, "/dev/dax")) /* There is probably a better way to check this */ > + return famfs_open_char_device(sb, fc); > + > + if (!strstr(fc->source, "/dev/pmem")) { /* There is probably a better way to check this */ > + pr_err("%s: primary backing dev (%s) is not pmem\n", > + __func__, fc->source); > + return -EINVAL; > + } > + > + handlep = bdev_open_by_path(fc->source, FAMFS_BLKDEV_MODE, fsi, &fs_holder_ops); > + if (IS_ERR(handlep->bdev)) { > + pr_err("%s: failed blkdev_get_by_path(%s)\n", __func__, fc->source); > + return PTR_ERR(handlep->bdev); > + } > + > + dax_devp = fs_dax_get_by_bdev(handlep->bdev, &start_off, > + fsi /* holder */, > + &famfs_blk_dax_holder_ops); > + if (IS_ERR(dax_devp)) { > + pr_err("%s: unable to get daxdev from handlep->bdev\n", __func__); > + bdev_release(handlep); > + return -ENODEV; > + } > + fsi->bdev_handle = handlep; > + fsi->dax_devp = dax_devp; > + > + pr_notice("%s: root device is block dax (%s)\n", __func__, fc->source); pr_debug() Kernel log is too noisy anyway! + I'd assume we can tell this succeeded in lots of other ways. > + return 0; > +} > + > + > > MODULE_LICENSE("GPL");
On 24/02/26 12:56PM, Jonathan Cameron wrote: > On Fri, 23 Feb 2024 11:41:54 -0600 > John Groves <John@Groves.net> wrote: > > > Famfs works on both /dev/pmem and /dev/dax devices. This commit introduces > > the function that opens a block (pmem) device and the struct > > dax_holder_operations that are needed for that ABI. > > > > In this commit, support for opening character /dev/dax is stubbed. A > > later commit introduces this capability. > > > > Signed-off-by: John Groves <john@groves.net> > > Formatting comments mostly same as previous patches, so I'll stop repeating them. I tried to bulk apply those recommendations. > > > --- > > fs/famfs/famfs_inode.c | 83 ++++++++++++++++++++++++++++++++++++++++++ > > 1 file changed, 83 insertions(+) > > > > diff --git a/fs/famfs/famfs_inode.c b/fs/famfs/famfs_inode.c > > index 3329aff000d1..82c861998093 100644 > > --- a/fs/famfs/famfs_inode.c > > +++ b/fs/famfs/famfs_inode.c > > @@ -68,5 +68,88 @@ static const struct super_operations famfs_ops = { > > .show_options = famfs_show_options, > > }; > > > > +/*************************************************************************************** > > + * dax_holder_operations for block dax > > + */ > > + > > +static int > > +famfs_blk_dax_notify_failure( > > + struct dax_device *dax_devp, > > + u64 offset, > > + u64 len, > > + int mf_flags) > > +{ > > + > > + pr_err("%s: dax_devp %llx offset %llx len %lld mf_flags %x\n", > > + __func__, (u64)dax_devp, (u64)offset, (u64)len, mf_flags); > > + return -EOPNOTSUPP; > > +} > > + > > +const struct dax_holder_operations famfs_blk_dax_holder_ops = { > > + .notify_failure = famfs_blk_dax_notify_failure, > > +}; > > + > > +static int > > +famfs_open_char_device( > > + struct super_block *sb, > > + struct fs_context *fc) > > +{ > > + pr_err("%s: Root device is %s, but your kernel does not support famfs on /dev/dax\n", > > + __func__, fc->source); > > + return -ENODEV; > > +} > > + > > +/** > > + * famfs_open_device() > > + * > > + * Open the memory device. If it looks like /dev/dax, call famfs_open_char_device(). > > + * Otherwise try to open it as a block/pmem device. > > + */ > > +static int > > +famfs_open_device( > > + struct super_block *sb, > > + struct fs_context *fc) > > +{ > > + struct famfs_fs_info *fsi = sb->s_fs_info; > > + struct dax_device *dax_devp; > > + u64 start_off = 0; > > + struct bdev_handle *handlep; > Definitely don't force alignment in local parameter definitions. > Always goes wrong and makes for unreadable mess in patches! Okay, undone. Everywhere. > > > + > > + if (fsi->dax_devp) { > > + pr_err("%s: already mounted\n", __func__); > Fine to fail but worth a error message? Not sure on convention on this but seems noisy > and maybe in userspace control which isn't good. Changing to pr_debug. Would be good to have access to it in that way > > + return -EALREADY; > > + } > > + > > + if (strstr(fc->source, "/dev/dax")) /* There is probably a better way to check this */ > > + return famfs_open_char_device(sb, fc); > > + > > + if (!strstr(fc->source, "/dev/pmem")) { /* There is probably a better way to check this */ > > + pr_err("%s: primary backing dev (%s) is not pmem\n", > > + __func__, fc->source); > > + return -EINVAL; > > + } > > + > > + handlep = bdev_open_by_path(fc->source, FAMFS_BLKDEV_MODE, fsi, &fs_holder_ops); > > + if (IS_ERR(handlep->bdev)) { > > + pr_err("%s: failed blkdev_get_by_path(%s)\n", __func__, fc->source); > > + return PTR_ERR(handlep->bdev); > > + } > > + > > + dax_devp = fs_dax_get_by_bdev(handlep->bdev, &start_off, > > + fsi /* holder */, > > + &famfs_blk_dax_holder_ops); > > + if (IS_ERR(dax_devp)) { > > + pr_err("%s: unable to get daxdev from handlep->bdev\n", __func__); > > + bdev_release(handlep); > > + return -ENODEV; > > + } > > + fsi->bdev_handle = handlep; > > + fsi->dax_devp = dax_devp; > > + > > + pr_notice("%s: root device is block dax (%s)\n", __func__, fc->source); > > pr_debug() Kernel log is too noisy anyway! + I'd assume we can tell this succeeded > in lots of other ways. Done > > > > + return 0; > > +} > > + > > + > > > > MODULE_LICENSE("GPL"); Thanks, John >
On Fri, Feb 23, 2024 at 11:41:54AM -0600, John Groves wrote: > Famfs works on both /dev/pmem and /dev/dax devices. This commit introduces > the function that opens a block (pmem) device and the struct > dax_holder_operations that are needed for that ABI. > > In this commit, support for opening character /dev/dax is stubbed. A > later commit introduces this capability. > > Signed-off-by: John Groves <john@groves.net> > --- > fs/famfs/famfs_inode.c | 83 ++++++++++++++++++++++++++++++++++++++++++ > 1 file changed, 83 insertions(+) > > diff --git a/fs/famfs/famfs_inode.c b/fs/famfs/famfs_inode.c > index 3329aff000d1..82c861998093 100644 > --- a/fs/famfs/famfs_inode.c > +++ b/fs/famfs/famfs_inode.c > @@ -68,5 +68,88 @@ static const struct super_operations famfs_ops = { > .show_options = famfs_show_options, > }; > > +/*************************************************************************************** > + * dax_holder_operations for block dax > + */ > + > +static int > +famfs_blk_dax_notify_failure( > + struct dax_device *dax_devp, > + u64 offset, > + u64 len, > + int mf_flags) > +{ > + > + pr_err("%s: dax_devp %llx offset %llx len %lld mf_flags %x\n", > + __func__, (u64)dax_devp, (u64)offset, (u64)len, mf_flags); > + return -EOPNOTSUPP; > +} > + > +const struct dax_holder_operations famfs_blk_dax_holder_ops = { > + .notify_failure = famfs_blk_dax_notify_failure, > +}; > + > +static int > +famfs_open_char_device( > + struct super_block *sb, > + struct fs_context *fc) > +{ > + pr_err("%s: Root device is %s, but your kernel does not support famfs on /dev/dax\n", > + __func__, fc->source); > + return -ENODEV; > +} > + > +/** > + * famfs_open_device() > + * > + * Open the memory device. If it looks like /dev/dax, call famfs_open_char_device(). > + * Otherwise try to open it as a block/pmem device. > + */ > +static int > +famfs_open_device( I'm confused why that function is added here but it's completely unclear in what wider context it's called. This is really hard to follow. > + struct super_block *sb, > + struct fs_context *fc) > +{ > + struct famfs_fs_info *fsi = sb->s_fs_info; > + struct dax_device *dax_devp; > + u64 start_off = 0; > + struct bdev_handle *handlep; > + > + if (fsi->dax_devp) { > + pr_err("%s: already mounted\n", __func__); > + return -EALREADY; > + } > + > + if (strstr(fc->source, "/dev/dax")) /* There is probably a better way to check this */ > + return famfs_open_char_device(sb, fc); > + > + if (!strstr(fc->source, "/dev/pmem")) { /* There is probably a better way to check this */ Yeah, this is not just a bit ugly but also likely wrong because: sudo mount --bind /dev/pmem /opt/muhaha fsconfig(fd_fs, FSCONFIG_SET_STRING, "source", "/opt/muhaha", [...]) or a simple mknod to create that device somewhere else. You likely want: lookup_bdev(fc->source, &dev); if (!DEVICE_NUMBER_SOMETHING_SOMETHING_SANE(dev)) return invalfc(fc, "SOMETHING SOMETHING... bdev_open_by_dev(dev, ....) (This reminds me that I should get back to making it possible to specify "source" as a file descriptor instead of a mere string with the new mount api...) > + pr_err("%s: primary backing dev (%s) is not pmem\n", > + __func__, fc->source); > + return -EINVAL; > + } > + > + handlep = bdev_open_by_path(fc->source, FAMFS_BLKDEV_MODE, fsi, &fs_holder_ops); Hm, I suspected that FAMFS_BLKDEV_MODE would be wrong based on: https://lore.kernel.org/r/13556dbbd8d0f51bc31e3bdec796283fe85c6baf.1708709155.git.john@groves.net It's defined as FMODE_READ | FMODE_WRITE which is wrong. But these helpers want BLOCK_OPEN_READ | BLOCK_OPEN_WRITE. > + if (IS_ERR(handlep->bdev)) { @bdev_handle will be gone as of v6.9 so you might want to wait until then to resend. > + pr_err("%s: failed blkdev_get_by_path(%s)\n", __func__, fc->source); > + return PTR_ERR(handlep->bdev); > + } > + > + dax_devp = fs_dax_get_by_bdev(handlep->bdev, &start_off, > + fsi /* holder */, > + &famfs_blk_dax_holder_ops); > + if (IS_ERR(dax_devp)) { > + pr_err("%s: unable to get daxdev from handlep->bdev\n", __func__); > + bdev_release(handlep); > + return -ENODEV; > + } > + fsi->bdev_handle = handlep; > + fsi->dax_devp = dax_devp; > + > + pr_notice("%s: root device is block dax (%s)\n", __func__, fc->source); > + return 0; > +} > + > + > > MODULE_LICENSE("GPL"); > -- > 2.43.0 >
On 24/02/27 02:39PM, Christian Brauner wrote: > On Fri, Feb 23, 2024 at 11:41:54AM -0600, John Groves wrote: > > Famfs works on both /dev/pmem and /dev/dax devices. This commit introduces > > the function that opens a block (pmem) device and the struct > > dax_holder_operations that are needed for that ABI. > > > > In this commit, support for opening character /dev/dax is stubbed. A > > later commit introduces this capability. > > > > Signed-off-by: John Groves <john@groves.net> > > --- > > fs/famfs/famfs_inode.c | 83 ++++++++++++++++++++++++++++++++++++++++++ > > 1 file changed, 83 insertions(+) > > > > diff --git a/fs/famfs/famfs_inode.c b/fs/famfs/famfs_inode.c > > index 3329aff000d1..82c861998093 100644 > > --- a/fs/famfs/famfs_inode.c > > +++ b/fs/famfs/famfs_inode.c > > @@ -68,5 +68,88 @@ static const struct super_operations famfs_ops = { > > .show_options = famfs_show_options, > > }; > > > > +/*************************************************************************************** > > + * dax_holder_operations for block dax > > + */ > > + > > +static int > > +famfs_blk_dax_notify_failure( > > + struct dax_device *dax_devp, > > + u64 offset, > > + u64 len, > > + int mf_flags) > > +{ > > + > > + pr_err("%s: dax_devp %llx offset %llx len %lld mf_flags %x\n", > > + __func__, (u64)dax_devp, (u64)offset, (u64)len, mf_flags); > > + return -EOPNOTSUPP; > > +} > > + > > +const struct dax_holder_operations famfs_blk_dax_holder_ops = { > > + .notify_failure = famfs_blk_dax_notify_failure, > > +}; > > + > > +static int > > +famfs_open_char_device( > > + struct super_block *sb, > > + struct fs_context *fc) > > +{ > > + pr_err("%s: Root device is %s, but your kernel does not support famfs on /dev/dax\n", > > + __func__, fc->source); > > + return -ENODEV; > > +} > > + > > +/** > > + * famfs_open_device() > > + * > > + * Open the memory device. If it looks like /dev/dax, call famfs_open_char_device(). > > + * Otherwise try to open it as a block/pmem device. > > + */ > > +static int > > +famfs_open_device( > > I'm confused why that function is added here but it's completely unclear > in what wider context it's called. This is really hard to follow. First, thank you for taking the time to do a thoughtful review. I didn't factor this series correctly. The next one will be "module-operations-up" unless you or somebody suggests a more sensible approach. Some background that might be useful: this work is really targeted for /dev/dax, but it started on /dev/pmem because the iomap interface wasn't working on /dev/dax. This patch addresses that (the dev_dax_iomap commits), although it's likely that code will evolve. The current famfs code base tries to support both pmem (block) and /dev/dax (char), but I'm now thinking it should move to /dev/dax-only (no block support). /dev/pmem devices can converted to /dev/dax mode anyway, so I'm not sure there is a reason to support both interfaces. (Need to think a bit more on that...). > > > + struct super_block *sb, > > + struct fs_context *fc) > > +{ > > + struct famfs_fs_info *fsi = sb->s_fs_info; > > + struct dax_device *dax_devp; > > + u64 start_off = 0; > > + struct bdev_handle *handlep; > > + > > + if (fsi->dax_devp) { > > + pr_err("%s: already mounted\n", __func__); > > + return -EALREADY; > > + } > > + > > + if (strstr(fc->source, "/dev/dax")) /* There is probably a better way to check this */ > > + return famfs_open_char_device(sb, fc); > > + > > + if (!strstr(fc->source, "/dev/pmem")) { /* There is probably a better way to check this */ > > Yeah, this is not just a bit ugly but also likely wrong because: > > sudo mount --bind /dev/pmem /opt/muhaha > > fsconfig(fd_fs, FSCONFIG_SET_STRING, "source", "/opt/muhaha", [...]) > > or a simple mknod to create that device somewhere else. You likely want: > > lookup_bdev(fc->source, &dev); > > if (!DEVICE_NUMBER_SOMETHING_SOMETHING_SANE(dev)) > return invalfc(fc, "SOMETHING SOMETHING... > > bdev_open_by_dev(dev, ....) > > (This reminds me that I should get back to making it possible to specify > "source" as a file descriptor instead of a mere string with the new > mount api...) All good points - sorry for the flakyness here. I think the solution is to stop trying to support both pmem and dax. Then I don't need to distinguish between different device types. > > > + pr_err("%s: primary backing dev (%s) is not pmem\n", > > + __func__, fc->source); > > + return -EINVAL; > > + } > > + > > + handlep = bdev_open_by_path(fc->source, FAMFS_BLKDEV_MODE, fsi, &fs_holder_ops); > > Hm, I suspected that FAMFS_BLKDEV_MODE would be wrong based on: > https://lore.kernel.org/r/13556dbbd8d0f51bc31e3bdec796283fe85c6baf.1708709155.git.john@groves.net > > It's defined as FMODE_READ | FMODE_WRITE which is wrong. But these > helpers want BLOCK_OPEN_READ | BLOCK_OPEN_WRITE. Dropping pmem/block support will also make this go away > > > + if (IS_ERR(handlep->bdev)) { > > @bdev_handle will be gone as of v6.9 so you might want to wait until > then to resend. And this dependency will also disappear... Thank you!! John
diff --git a/fs/famfs/famfs_inode.c b/fs/famfs/famfs_inode.c index 3329aff000d1..82c861998093 100644 --- a/fs/famfs/famfs_inode.c +++ b/fs/famfs/famfs_inode.c @@ -68,5 +68,88 @@ static const struct super_operations famfs_ops = { .show_options = famfs_show_options, }; +/*************************************************************************************** + * dax_holder_operations for block dax + */ + +static int +famfs_blk_dax_notify_failure( + struct dax_device *dax_devp, + u64 offset, + u64 len, + int mf_flags) +{ + + pr_err("%s: dax_devp %llx offset %llx len %lld mf_flags %x\n", + __func__, (u64)dax_devp, (u64)offset, (u64)len, mf_flags); + return -EOPNOTSUPP; +} + +const struct dax_holder_operations famfs_blk_dax_holder_ops = { + .notify_failure = famfs_blk_dax_notify_failure, +}; + +static int +famfs_open_char_device( + struct super_block *sb, + struct fs_context *fc) +{ + pr_err("%s: Root device is %s, but your kernel does not support famfs on /dev/dax\n", + __func__, fc->source); + return -ENODEV; +} + +/** + * famfs_open_device() + * + * Open the memory device. If it looks like /dev/dax, call famfs_open_char_device(). + * Otherwise try to open it as a block/pmem device. + */ +static int +famfs_open_device( + struct super_block *sb, + struct fs_context *fc) +{ + struct famfs_fs_info *fsi = sb->s_fs_info; + struct dax_device *dax_devp; + u64 start_off = 0; + struct bdev_handle *handlep; + + if (fsi->dax_devp) { + pr_err("%s: already mounted\n", __func__); + return -EALREADY; + } + + if (strstr(fc->source, "/dev/dax")) /* There is probably a better way to check this */ + return famfs_open_char_device(sb, fc); + + if (!strstr(fc->source, "/dev/pmem")) { /* There is probably a better way to check this */ + pr_err("%s: primary backing dev (%s) is not pmem\n", + __func__, fc->source); + return -EINVAL; + } + + handlep = bdev_open_by_path(fc->source, FAMFS_BLKDEV_MODE, fsi, &fs_holder_ops); + if (IS_ERR(handlep->bdev)) { + pr_err("%s: failed blkdev_get_by_path(%s)\n", __func__, fc->source); + return PTR_ERR(handlep->bdev); + } + + dax_devp = fs_dax_get_by_bdev(handlep->bdev, &start_off, + fsi /* holder */, + &famfs_blk_dax_holder_ops); + if (IS_ERR(dax_devp)) { + pr_err("%s: unable to get daxdev from handlep->bdev\n", __func__); + bdev_release(handlep); + return -ENODEV; + } + fsi->bdev_handle = handlep; + fsi->dax_devp = dax_devp; + + pr_notice("%s: root device is block dax (%s)\n", __func__, fc->source); + return 0; +} + + MODULE_LICENSE("GPL");
Famfs works on both /dev/pmem and /dev/dax devices. This commit introduces the function that opens a block (pmem) device and the struct dax_holder_operations that are needed for that ABI. In this commit, support for opening character /dev/dax is stubbed. A later commit introduces this capability. Signed-off-by: John Groves <john@groves.net> --- fs/famfs/famfs_inode.c | 83 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+)