From: John Groves Famfs file maps (fmaps) may reference multiple daxdevs. Before passing an fmap that references a new daxdev, the daxdev is pushed into the kernel via FAMFSIOC_DAXDEV_OPEN). This adds daxdevs to daxdev_table for index-based resolution from famfs extents to daxdevs. Signed-off-by: John Groves --- fs/famfs/famfs_file.c | 74 ++++++++++++++++++++++++++++++++ include/uapi/linux/famfs_ioctl.h | 24 +++++++++++ 2 files changed, 98 insertions(+) diff --git a/fs/famfs/famfs_file.c b/fs/famfs/famfs_file.c index e7f271ce6d03..e11a55ecf8d7 100644 --- a/fs/famfs/famfs_file.c +++ b/fs/famfs/famfs_file.c @@ -287,6 +287,76 @@ famfs_file_init_dax(struct file *file, void __user *arg) return rc; } +/** + * famfs_daxdev_open() - FAMFSIOC_DAXDEV_OPEN ioctl handler + * @file: any file in the famfs mount (the table is per-superblock) + * @arg: ptr to struct famfs_ioc_daxdev in user space + * + * Register a devdax device (identified by path) into the mount's daxdev table + * at the caller-specified index, so files whose extents reference that index + * can be mapped. The path is resolved by lookup_daxdev() - the same helper the + * mount uses for the primary daxdev - so every slot is resolved identically. + * Registering exposes raw device memory, so it requires CAP_SYS_RAWIO. + */ +static int +famfs_daxdev_open(struct file *file, void __user *arg) +{ + struct super_block *sb = file_inode(file)->i_sb; + struct famfs_fs_info *fsi = sb->s_fs_info; + struct famfs_ioc_daxdev dd; + dev_t devno; + char *path; + int rc; + + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + if (copy_from_user(&dd, arg, sizeof(dd))) + return -EFAULT; + + /* @flags is reserved; reject non-zero so it stays available */ + if (dd.flags) + return -EINVAL; + + /* + * If this daxdev index is already populated there is nothing to do. + * The index is cluster-invariant, so a valid slot already names this + * device; skip the path resolution entirely. install_daxdev() rechecks + * ->valid under the write lock, so this is purely an optimization. + */ + scoped_guard(rwsem_read, &fsi->devlist_sem) { + if (dd.daxdev_index >= fsi->dax_devlist->nslots) + return -EINVAL; + if (fsi->dax_devlist->devlist[dd.daxdev_index].valid) + return 0; + } + + if (dd.daxdev_path_len == 0 || dd.daxdev_path_len >= PATH_MAX) + return -EINVAL; + + /* +1 so the terminating NUL is included within the bound */ + path = strndup_user((const char __user *)(uintptr_t)dd.daxdev_path, + dd.daxdev_path_len + 1); + if (IS_ERR(path)) + return PTR_ERR(path); + + rc = lookup_daxdev(path, &devno); + if (rc) + goto out; + + /* + * The daxdev table is allocated at mount time (for the slot-0 primary), + * so it is always present here; no need to allocate it. + */ + rc = famfs_install_daxdev(fsi, sb, dd.daxdev_index, devno, path); + if (rc) + pr_debug("%s: failed to install daxdev index %llu (%s)\n", + __func__, dd.daxdev_index, path); +out: + kfree(path); + return rc; +} + /** * famfs_file_ioctl() - Top-level famfs file ioctl handler * @file: the file @@ -308,6 +378,10 @@ famfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) rc = 0; break; + case FAMFSIOC_DAXDEV_OPEN: + rc = famfs_daxdev_open(file, (void __user *)arg); + break; + case FAMFSIOC_MAP_CREATE: rc = famfs_file_init_dax(file, (void __user *)arg); break; diff --git a/include/uapi/linux/famfs_ioctl.h b/include/uapi/linux/famfs_ioctl.h index b4eb373c1ade..751d8b033c2e 100644 --- a/include/uapi/linux/famfs_ioctl.h +++ b/include/uapi/linux/famfs_ioctl.h @@ -77,6 +77,29 @@ struct famfs_ioc_fmap_header { __u64 reserved1; }; +/** + * struct famfs_ioc_daxdev - register an additional backing daxdev by path + * @daxdev_index: the (cluster-invariant) index this daxdev occupies in + * extent dev_index fields. Index 0 is the mount-time primary. + * @daxdev_path: userspace pointer to the devdax device path (e.g. + * "/dev/dax0.0"); resolved in the kernel the same way the + * mount primary is. + * @daxdev_path_len: length of the path string, not counting the NUL. + * @flags: reserved; must be zero. + * + * Standalone famfs registers every daxdev by path: the mount primary comes in + * as the mount device name, and slots 1..n come in here. (This deliberately + * differs from fuse's fd-based FUSE_DEV_IOC_DAXDEV_OPEN; each side is uniform + * within itself.) Passing the path by pointer keeps the struct fixed-size, so + * longer paths never require an ABI change. + */ +struct famfs_ioc_daxdev { + __u64 daxdev_index; + __u64 daxdev_path; + __u32 daxdev_path_len; + __u32 flags; +}; + #define FAMFSIOC_MAGIC 'u' /* famfs file ioctl opcodes */ @@ -87,5 +110,6 @@ struct famfs_ioc_fmap_header { * famfs_ioc_fmap_header followed by the extent list (see above). */ #define FAMFSIOC_MAP_CREATE _IOW(FAMFSIOC_MAGIC, 0x51, struct famfs_ioc_fmap_header) +#define FAMFSIOC_DAXDEV_OPEN _IOW(FAMFSIOC_MAGIC, 0x52, struct famfs_ioc_daxdev) #endif /* FAMFS_IOCTL_H */ -- 2.53.0