diff options
Diffstat (limited to 'fs')
43 files changed, 2664 insertions, 532 deletions
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 16e198a26339..e33cc77699cd 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -47,11 +47,17 @@ const struct file_operations debugfs_noop_file_operations = { #define F_DENTRY(filp) ((filp)->f_path.dentry) +const void *debugfs_get_aux(const struct file *file) +{ + return DEBUGFS_I(file_inode(file))->aux; +} +EXPORT_SYMBOL_GPL(debugfs_get_aux); + const struct file_operations *debugfs_real_fops(const struct file *filp) { struct debugfs_fsdata *fsd = F_DENTRY(filp)->d_fsdata; - if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) { + if (!fsd) { /* * Urgh, we've been called w/o a protecting * debugfs_file_get(). @@ -84,9 +90,11 @@ static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode) return -EINVAL; d_fsd = READ_ONCE(dentry->d_fsdata); - if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { + if (d_fsd) { fsd = d_fsd; } else { + struct inode *inode = dentry->d_inode; + if (WARN_ON(mode == DBGFS_GET_ALREADY)) return -EINVAL; @@ -95,23 +103,38 @@ static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode) return -ENOMEM; if (mode == DBGFS_GET_SHORT) { - fsd->real_fops = NULL; - fsd->short_fops = (void *)((unsigned long)d_fsd & - ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); + const struct debugfs_short_fops *ops; + ops = fsd->short_fops = DEBUGFS_I(inode)->short_fops; + if (ops->llseek) + fsd->methods |= HAS_LSEEK; + if (ops->read) + fsd->methods |= HAS_READ; + if (ops->write) + fsd->methods |= HAS_WRITE; } else { - fsd->real_fops = (void *)((unsigned long)d_fsd & - ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); - fsd->short_fops = NULL; + const struct file_operations *ops; + ops = fsd->real_fops = DEBUGFS_I(inode)->real_fops; + if (ops->llseek) + fsd->methods |= HAS_LSEEK; + if (ops->read) + fsd->methods |= HAS_READ; + if (ops->write) + fsd->methods |= HAS_WRITE; + if (ops->unlocked_ioctl) + fsd->methods |= HAS_IOCTL; + if (ops->poll) + fsd->methods |= HAS_POLL; } refcount_set(&fsd->active_users, 1); init_completion(&fsd->active_users_drained); INIT_LIST_HEAD(&fsd->cancellations); mutex_init(&fsd->cancellations_mtx); - if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) { + d_fsd = cmpxchg(&dentry->d_fsdata, NULL, fsd); + if (d_fsd) { mutex_destroy(&fsd->cancellations_mtx); kfree(fsd); - fsd = READ_ONCE(dentry->d_fsdata); + fsd = d_fsd; } } @@ -208,8 +231,7 @@ void debugfs_enter_cancellation(struct file *file, return; fsd = READ_ONCE(dentry->d_fsdata); - if (WARN_ON(!fsd || - ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + if (WARN_ON(!fsd)) return; mutex_lock(&fsd->cancellations_mtx); @@ -240,8 +262,7 @@ void debugfs_leave_cancellation(struct file *file, return; fsd = READ_ONCE(dentry->d_fsdata); - if (WARN_ON(!fsd || - ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + if (WARN_ON(!fsd)) return; mutex_lock(&fsd->cancellations_mtx); @@ -322,13 +343,16 @@ const struct file_operations debugfs_open_proxy_file_operations = { #define PROTO(args...) args #define ARGS(args...) args -#define FULL_PROXY_FUNC(name, ret_type, filp, proto, args) \ +#define FULL_PROXY_FUNC(name, ret_type, filp, proto, args, bit, ret) \ static ret_type full_proxy_ ## name(proto) \ { \ - struct dentry *dentry = F_DENTRY(filp); \ + struct dentry *dentry = F_DENTRY(filp); \ + struct debugfs_fsdata *fsd = dentry->d_fsdata; \ const struct file_operations *real_fops; \ ret_type r; \ \ + if (!(fsd->methods & bit)) \ + return ret; \ r = debugfs_file_get(dentry); \ if (unlikely(r)) \ return r; \ @@ -338,17 +362,18 @@ static ret_type full_proxy_ ## name(proto) \ return r; \ } -#define FULL_PROXY_FUNC_BOTH(name, ret_type, filp, proto, args) \ +#define FULL_PROXY_FUNC_BOTH(name, ret_type, filp, proto, args, bit, ret) \ static ret_type full_proxy_ ## name(proto) \ { \ struct dentry *dentry = F_DENTRY(filp); \ - struct debugfs_fsdata *fsd; \ + struct debugfs_fsdata *fsd = dentry->d_fsdata; \ ret_type r; \ \ + if (!(fsd->methods & bit)) \ + return ret; \ r = debugfs_file_get(dentry); \ if (unlikely(r)) \ return r; \ - fsd = dentry->d_fsdata; \ if (fsd->real_fops) \ r = fsd->real_fops->name(args); \ else \ @@ -359,29 +384,32 @@ static ret_type full_proxy_ ## name(proto) \ FULL_PROXY_FUNC_BOTH(llseek, loff_t, filp, PROTO(struct file *filp, loff_t offset, int whence), - ARGS(filp, offset, whence)); + ARGS(filp, offset, whence), HAS_LSEEK, -ESPIPE); FULL_PROXY_FUNC_BOTH(read, ssize_t, filp, PROTO(struct file *filp, char __user *buf, size_t size, loff_t *ppos), - ARGS(filp, buf, size, ppos)); + ARGS(filp, buf, size, ppos), HAS_READ, -EINVAL); FULL_PROXY_FUNC_BOTH(write, ssize_t, filp, PROTO(struct file *filp, const char __user *buf, size_t size, loff_t *ppos), - ARGS(filp, buf, size, ppos)); + ARGS(filp, buf, size, ppos), HAS_WRITE, -EINVAL); FULL_PROXY_FUNC(unlocked_ioctl, long, filp, PROTO(struct file *filp, unsigned int cmd, unsigned long arg), - ARGS(filp, cmd, arg)); + ARGS(filp, cmd, arg), HAS_IOCTL, -ENOTTY); static __poll_t full_proxy_poll(struct file *filp, struct poll_table_struct *wait) { struct dentry *dentry = F_DENTRY(filp); + struct debugfs_fsdata *fsd = dentry->d_fsdata; __poll_t r = 0; const struct file_operations *real_fops; + if (!(fsd->methods & HAS_POLL)) + return DEFAULT_POLLMASK; if (debugfs_file_get(dentry)) return EPOLLHUP; @@ -393,9 +421,7 @@ static __poll_t full_proxy_poll(struct file *filp, static int full_proxy_release(struct inode *inode, struct file *filp) { - const struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = debugfs_real_fops(filp); - const struct file_operations *proxy_fops = filp->f_op; int r = 0; /* @@ -404,49 +430,21 @@ static int full_proxy_release(struct inode *inode, struct file *filp) * not to leak any resources. Releasers must not assume that * ->i_private is still being meaningful here. */ - if (real_fops && real_fops->release) + if (real_fops->release) r = real_fops->release(inode, filp); - replace_fops(filp, d_inode(dentry)->i_fop); - kfree(proxy_fops); fops_put(real_fops); return r; } -static void __full_proxy_fops_init(struct file_operations *proxy_fops, - struct debugfs_fsdata *fsd) -{ - proxy_fops->release = full_proxy_release; - - if ((fsd->real_fops && fsd->real_fops->llseek) || - (fsd->short_fops && fsd->short_fops->llseek)) - proxy_fops->llseek = full_proxy_llseek; - - if ((fsd->real_fops && fsd->real_fops->read) || - (fsd->short_fops && fsd->short_fops->read)) - proxy_fops->read = full_proxy_read; - - if ((fsd->real_fops && fsd->real_fops->write) || - (fsd->short_fops && fsd->short_fops->write)) - proxy_fops->write = full_proxy_write; - - if (fsd->real_fops && fsd->real_fops->poll) - proxy_fops->poll = full_proxy_poll; - - if (fsd->real_fops && fsd->real_fops->unlocked_ioctl) - proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl; -} - -static int full_proxy_open(struct inode *inode, struct file *filp, - enum dbgfs_get_mode mode) +static int full_proxy_open_regular(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops; - struct file_operations *proxy_fops = NULL; struct debugfs_fsdata *fsd; int r; - r = __debugfs_file_get(dentry, mode); + r = __debugfs_file_get(dentry, DBGFS_GET_REGULAR); if (r) return r == -EIO ? -ENOENT : r; @@ -456,7 +454,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp, if (r) goto out; - if (real_fops && !fops_get(real_fops)) { + if (!fops_get(real_fops)) { #ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) { @@ -472,55 +470,52 @@ static int full_proxy_open(struct inode *inode, struct file *filp, goto out; } - proxy_fops = kzalloc(sizeof(*proxy_fops), GFP_KERNEL); - if (!proxy_fops) { - r = -ENOMEM; - goto free_proxy; - } - __full_proxy_fops_init(proxy_fops, fsd); - replace_fops(filp, proxy_fops); - - if (!real_fops || real_fops->open) { - if (real_fops) - r = real_fops->open(inode, filp); - else - r = simple_open(inode, filp); + if (real_fops->open) { + r = real_fops->open(inode, filp); if (r) { - replace_fops(filp, d_inode(dentry)->i_fop); - goto free_proxy; - } else if (filp->f_op != proxy_fops) { + fops_put(real_fops); + } else if (filp->f_op != &debugfs_full_proxy_file_operations) { /* No protection against file removal anymore. */ WARN(1, "debugfs file owner replaced proxy fops: %pd", dentry); - goto free_proxy; + fops_put(real_fops); } } - - goto out; -free_proxy: - kfree(proxy_fops); - fops_put(real_fops); out: debugfs_file_put(dentry); return r; } -static int full_proxy_open_regular(struct inode *inode, struct file *filp) -{ - return full_proxy_open(inode, filp, DBGFS_GET_REGULAR); -} - const struct file_operations debugfs_full_proxy_file_operations = { .open = full_proxy_open_regular, + .release = full_proxy_release, + .llseek = full_proxy_llseek, + .read = full_proxy_read, + .write = full_proxy_write, + .poll = full_proxy_poll, + .unlocked_ioctl = full_proxy_unlocked_ioctl }; static int full_proxy_open_short(struct inode *inode, struct file *filp) { - return full_proxy_open(inode, filp, DBGFS_GET_SHORT); + struct dentry *dentry = F_DENTRY(filp); + int r; + + r = __debugfs_file_get(dentry, DBGFS_GET_SHORT); + if (r) + return r == -EIO ? -ENOENT : r; + r = debugfs_locked_down(inode, filp, NULL); + if (!r) + r = simple_open(inode, filp); + debugfs_file_put(dentry); + return r; } const struct file_operations debugfs_full_short_proxy_file_operations = { .open = full_proxy_open_short, + .llseek = full_proxy_llseek, + .read = full_proxy_read, + .write = full_proxy_write, }; ssize_t debugfs_attr_read(struct file *file, char __user *buf, diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index e752009de929..75715d8877ee 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -208,16 +208,34 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } +static struct kmem_cache *debugfs_inode_cachep __ro_after_init; + +static void init_once(void *foo) +{ + struct debugfs_inode_info *info = foo; + inode_init_once(&info->vfs_inode); +} + +static struct inode *debugfs_alloc_inode(struct super_block *sb) +{ + struct debugfs_inode_info *info; + info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL); + if (!info) + return NULL; + return &info->vfs_inode; +} + static void debugfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); - free_inode_nonrcu(inode); + kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode)); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .show_options = debugfs_show_options, + .alloc_inode = debugfs_alloc_inode, .free_inode = debugfs_free_inode, }; @@ -225,23 +243,18 @@ static void debugfs_release_dentry(struct dentry *dentry) { struct debugfs_fsdata *fsd = dentry->d_fsdata; - if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) - return; - - /* check it wasn't a dir (no fsdata) or automount (no real_fops) */ - if (fsd && (fsd->real_fops || fsd->short_fops)) { + if (fsd) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } - kfree(fsd); } static struct vfsmount *debugfs_automount(struct path *path) { - struct debugfs_fsdata *fsd = path->dentry->d_fsdata; + struct inode *inode = path->dentry->d_inode; - return fsd->automount(path->dentry, d_inode(path->dentry)->i_private); + return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private); } static const struct dentry_operations debugfs_dops = { @@ -411,6 +424,7 @@ static struct dentry *end_creating(struct dentry *dentry) static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, + const void *aux, const struct file_operations *proxy_fops, const void *real_fops) { @@ -441,9 +455,11 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, inode->i_private = data; inode->i_op = &debugfs_file_inode_operations; + if (!real_fops) + proxy_fops = &debugfs_noop_file_operations; inode->i_fop = proxy_fops; - dentry->d_fsdata = (void *)((unsigned long)real_fops | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); + DEBUGFS_I(inode)->raw = real_fops; + DEBUGFS_I(inode)->aux = aux; d_instantiate(dentry, inode); fsnotify_create(d_inode(dentry->d_parent), dentry); @@ -452,30 +468,22 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *debugfs_create_file_full(const char *name, umode_t mode, struct dentry *parent, void *data, + const void *aux, const struct file_operations *fops) { - if (WARN_ON((unsigned long)fops & - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) - return ERR_PTR(-EINVAL); - - return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_full_proxy_file_operations : - &debugfs_noop_file_operations, + return __debugfs_create_file(name, mode, parent, data, aux, + &debugfs_full_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_full); struct dentry *debugfs_create_file_short(const char *name, umode_t mode, - struct dentry *parent, void *data, - const struct debugfs_short_fops *fops) + struct dentry *parent, void *data, + const void *aux, + const struct debugfs_short_fops *fops) { - if (WARN_ON((unsigned long)fops & - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) - return ERR_PTR(-EINVAL); - - return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_full_short_proxy_file_operations : - &debugfs_noop_file_operations, + return __debugfs_create_file(name, mode, parent, data, aux, + &debugfs_full_short_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_short); @@ -512,9 +520,8 @@ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, const struct file_operations *fops) { - return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_open_proxy_file_operations : - &debugfs_noop_file_operations, + return __debugfs_create_file(name, mode, parent, data, NULL, + &debugfs_open_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); @@ -624,23 +631,13 @@ struct dentry *debugfs_create_automount(const char *name, void *data) { struct dentry *dentry = start_creating(name, parent); - struct debugfs_fsdata *fsd; struct inode *inode; if (IS_ERR(dentry)) return dentry; - fsd = kzalloc(sizeof(*fsd), GFP_KERNEL); - if (!fsd) { - failed_creating(dentry); - return ERR_PTR(-ENOMEM); - } - - fsd->automount = f; - if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); - kfree(fsd); return ERR_PTR(-EPERM); } @@ -648,14 +645,13 @@ struct dentry *debugfs_create_automount(const char *name, if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); - kfree(fsd); return failed_creating(dentry); } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; - dentry->d_fsdata = fsd; + DEBUGFS_I(inode)->automount = f; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); @@ -730,7 +726,7 @@ static void __debugfs_file_removed(struct dentry *dentry) */ smp_mb(); fsd = READ_ONCE(dentry->d_fsdata); - if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) + if (!fsd) return; /* if this was the last reference, we're done */ @@ -834,76 +830,70 @@ void debugfs_lookup_and_remove(const char *name, struct dentry *parent) EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); /** - * debugfs_rename - rename a file/directory in the debugfs filesystem - * @old_dir: a pointer to the parent dentry for the renamed object. This - * should be a directory dentry. - * @old_dentry: dentry of an object to be renamed. - * @new_dir: a pointer to the parent dentry where the object should be - * moved. This should be a directory dentry. - * @new_name: a pointer to a string containing the target name. + * debugfs_change_name - rename a file/directory in the debugfs filesystem + * @dentry: dentry of an object to be renamed. + * @fmt: format for new name * * This function renames a file/directory in debugfs. The target must not * exist for rename to succeed. * - * This function will return a pointer to old_dentry (which is updated to - * reflect renaming) if it succeeds. If an error occurs, ERR_PTR(-ERROR) - * will be returned. + * This function will return 0 on success and -E... on failure. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ -struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, - struct dentry *new_dir, const char *new_name) +int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...) { - int error; - struct dentry *dentry = NULL, *trap; + int error = 0; + const char *new_name; struct name_snapshot old_name; + struct dentry *parent, *target; + struct inode *dir; + va_list ap; - if (IS_ERR(old_dir)) - return old_dir; - if (IS_ERR(new_dir)) - return new_dir; - if (IS_ERR_OR_NULL(old_dentry)) - return old_dentry; - - trap = lock_rename(new_dir, old_dir); - /* Source or destination directories don't exist? */ - if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) - goto exit; - /* Source does not exist, cyclic rename, or mountpoint? */ - if (d_really_is_negative(old_dentry) || old_dentry == trap || - d_mountpoint(old_dentry)) - goto exit; - dentry = lookup_one_len(new_name, new_dir, strlen(new_name)); - /* Lookup failed, cyclic rename or target exists? */ - if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry)) - goto exit; - - take_dentry_name_snapshot(&old_name, old_dentry); - - error = simple_rename(&nop_mnt_idmap, d_inode(old_dir), old_dentry, - d_inode(new_dir), dentry, 0); - if (error) { - release_dentry_name_snapshot(&old_name); - goto exit; + if (IS_ERR_OR_NULL(dentry)) + return 0; + + va_start(ap, fmt); + new_name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!new_name) + return -ENOMEM; + + parent = dget_parent(dentry); + dir = d_inode(parent); + inode_lock(dir); + + take_dentry_name_snapshot(&old_name, dentry); + + if (WARN_ON_ONCE(dentry->d_parent != parent)) { + error = -EINVAL; + goto out; } - d_move(old_dentry, dentry); - fsnotify_move(d_inode(old_dir), d_inode(new_dir), &old_name.name, - d_is_dir(old_dentry), - NULL, old_dentry); + if (strcmp(old_name.name.name, new_name) == 0) + goto out; + target = lookup_one_len(new_name, parent, strlen(new_name)); + if (IS_ERR(target)) { + error = PTR_ERR(target); + goto out; + } + if (d_really_is_positive(target)) { + dput(target); + error = -EINVAL; + goto out; + } + simple_rename_timestamp(dir, dentry, dir, target); + d_move(dentry, target); + dput(target); + fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry); +out: release_dentry_name_snapshot(&old_name); - unlock_rename(new_dir, old_dir); - dput(dentry); - return old_dentry; -exit: - if (dentry && !IS_ERR(dentry)) - dput(dentry); - unlock_rename(new_dir, old_dir); - if (IS_ERR(dentry)) - return dentry; - return ERR_PTR(-EINVAL); + inode_unlock(dir); + dput(parent); + kfree_const(new_name); + return error; } -EXPORT_SYMBOL_GPL(debugfs_rename); +EXPORT_SYMBOL_GPL(debugfs_change_name); /** * debugfs_initialized - Tells whether debugfs has been registered @@ -939,12 +929,22 @@ static int __init debugfs_init(void) if (retval) return retval; - retval = register_filesystem(&debug_fs_type); - if (retval) + debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache", + sizeof(struct debugfs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, + init_once); + if (debugfs_inode_cachep == NULL) { sysfs_remove_mount_point(kernel_kobj, "debug"); - else - debugfs_registered = true; + return -ENOMEM; + } - return retval; + retval = register_filesystem(&debug_fs_type); + if (retval) { // Really not going to happen + sysfs_remove_mount_point(kernel_kobj, "debug"); + kmem_cache_destroy(debugfs_inode_cachep); + return retval; + } + debugfs_registered = true; + return 0; } core_initcall(debugfs_init); diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index bbae4a228ef4..93483fe84425 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -11,6 +11,22 @@ struct file_operations; +struct debugfs_inode_info { + struct inode vfs_inode; + union { + const void *raw; + const struct file_operations *real_fops; + const struct debugfs_short_fops *short_fops; + debugfs_automount_t automount; + }; + const void *aux; +}; + +static inline struct debugfs_inode_info *DEBUGFS_I(struct inode *inode) +{ + return container_of(inode, struct debugfs_inode_info, vfs_inode); +} + /* declared over in file.c */ extern const struct file_operations debugfs_noop_file_operations; extern const struct file_operations debugfs_open_proxy_file_operations; @@ -20,29 +36,25 @@ extern const struct file_operations debugfs_full_short_proxy_file_operations; struct debugfs_fsdata { const struct file_operations *real_fops; const struct debugfs_short_fops *short_fops; - union { - /* automount_fn is used when real_fops is NULL */ - debugfs_automount_t automount; - struct { - refcount_t active_users; - struct completion active_users_drained; - - /* protect cancellations */ - struct mutex cancellations_mtx; - struct list_head cancellations; - }; + struct { + refcount_t active_users; + struct completion active_users_drained; + + /* protect cancellations */ + struct mutex cancellations_mtx; + struct list_head cancellations; + unsigned int methods; }; }; -/* - * A dentry's ->d_fsdata either points to the real fops or to a - * dynamically allocated debugfs_fsdata instance. - * In order to distinguish between these two cases, a real fops - * pointer gets its lowest bit set. - */ -#define DEBUGFS_FSDATA_IS_REAL_FOPS_BIT BIT(0) +enum { + HAS_READ = 1, + HAS_WRITE = 2, + HAS_LSEEK = 4, + HAS_POLL = 8, + HAS_IOCTL = 16 +}; -/* Access BITS */ #define DEBUGFS_ALLOW_API BIT(0) #define DEBUGFS_ALLOW_MOUNT BIT(1) diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index 8674dbfbe59d..ca215a3cba3e 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -63,3 +63,15 @@ config FUSE_PASSTHROUGH to be performed directly on a backing file. If you want to allow passthrough operations, answer Y. + +config FUSE_IO_URING + bool "FUSE communication over io-uring" + default y + depends on FUSE_FS + depends on IO_URING + help + This allows sending FUSE requests over the io-uring interface and + also adds request core affinity. + + If you want to allow fuse server/client communication through io-uring, + answer Y diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile index 2c372180d631..3f0f312a31c1 100644 --- a/fs/fuse/Makefile +++ b/fs/fuse/Makefile @@ -15,5 +15,6 @@ fuse-y += iomode.o fuse-$(CONFIG_FUSE_DAX) += dax.o fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o fuse-$(CONFIG_SYSCTL) += sysctl.o +fuse-$(CONFIG_FUSE_IO_URING) += dev_uring.o virtiofs-y := virtio_fs.o diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index 9abbc2f2894f..0b6ee6dd1fd6 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -240,11 +240,12 @@ static int fuse_send_removemapping(struct inode *inode, args.opcode = FUSE_REMOVEMAPPING; args.nodeid = fi->nodeid; - args.in_numargs = 2; - args.in_args[0].size = sizeof(*inargp); - args.in_args[0].value = inargp; - args.in_args[1].size = inargp->count * sizeof(*remove_one); - args.in_args[1].value = remove_one; + args.in_numargs = 3; + fuse_set_zero_arg0(&args); + args.in_args[1].size = sizeof(*inargp); + args.in_args[1].value = inargp; + args.in_args[2].size = inargp->count * sizeof(*remove_one); + args.in_args[2].value = remove_one; return fuse_simple_request(fm, &args); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 27ccae63495d..5b5f789b37eb 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -6,7 +6,9 @@ See the file COPYING. */ +#include "dev_uring_i.h" #include "fuse_i.h" +#include "fuse_dev_i.h" #include <linux/init.h> #include <linux/module.h> @@ -28,23 +30,8 @@ MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); -/* Ordinary requests have even IDs, while interrupts IDs are odd */ -#define FUSE_INT_REQ_BIT (1ULL << 0) -#define FUSE_REQ_ID_STEP (1ULL << 1) - static struct kmem_cache *fuse_req_cachep; -static void end_requests(struct list_head *head); - -static struct fuse_dev *fuse_get_dev(struct file *file) -{ - /* - * Lockless access is OK, because file->private data is set - * once during mount and is valid until the file is released. - */ - return READ_ONCE(file->private_data); -} - static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req) { INIT_LIST_HEAD(&req->list); @@ -89,7 +76,8 @@ void fuse_set_initialized(struct fuse_conn *fc) static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background) { - return !fc->initialized || (for_background && fc->blocked); + return !fc->initialized || (for_background && fc->blocked) || + (fc->io_uring && !fuse_uring_ready(fc)); } static void fuse_drop_waiting(struct fuse_conn *fc) @@ -234,7 +222,7 @@ u64 fuse_get_unique(struct fuse_iqueue *fiq) } EXPORT_SYMBOL_GPL(fuse_get_unique); -static unsigned int fuse_req_hash(u64 unique) +unsigned int fuse_req_hash(u64 unique) { return hash_long(unique & ~FUSE_INT_REQ_BIT, FUSE_PQ_HASH_BITS); } @@ -250,7 +238,8 @@ __releases(fiq->lock) spin_unlock(&fiq->lock); } -static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_link *forget) +void fuse_dev_queue_forget(struct fuse_iqueue *fiq, + struct fuse_forget_link *forget) { spin_lock(&fiq->lock); if (fiq->connected) { @@ -263,7 +252,7 @@ static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_li } } -static void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) +void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) { spin_lock(&fiq->lock); if (list_empty(&req->intr_entry)) { @@ -580,7 +569,25 @@ ssize_t __fuse_simple_request(struct mnt_idmap *idmap, return ret; } -static bool fuse_request_queue_background(struct fuse_req *req) +#ifdef CONFIG_FUSE_IO_URING +static bool fuse_request_queue_background_uring(struct fuse_conn *fc, + struct fuse_req *req) +{ + struct fuse_iqueue *fiq = &fc->iq; + + req->in.h.unique = fuse_get_unique(fiq); + req->in.h.len = sizeof(struct fuse_in_header) + + fuse_len_args(req->args->in_numargs, + (struct fuse_arg *) req->args->in_args); + + return fuse_uring_queue_bq_req(req); +} +#endif + +/* + * @return true if queued + */ +static int fuse_request_queue_background(struct fuse_req *req) { struct fuse_mount *fm = req->fm; struct fuse_conn *fc = fm->fc; @@ -592,6 +599,12 @@ static bool fuse_request_queue_background(struct fuse_req *req) atomic_inc(&fc->num_waiting); } __set_bit(FR_ISREPLY, &req->flags); + +#ifdef CONFIG_FUSE_IO_URING + if (fuse_uring_ready(fc)) + return fuse_request_queue_background_uring(fc, req); +#endif + spin_lock(&fc->bg_lock); if (likely(fc->connected)) { fc->num_background++; @@ -692,22 +705,8 @@ static int unlock_request(struct fuse_req *req) return err; } -struct fuse_copy_state { - int write; - struct fuse_req *req; - struct iov_iter *iter; - struct pipe_buffer *pipebufs; - struct pipe_buffer *currbuf; - struct pipe_inode_info *pipe; - unsigned long nr_segs; - struct page *pg; - unsigned len; - unsigned offset; - unsigned move_pages:1; -}; - -static void fuse_copy_init(struct fuse_copy_state *cs, int write, - struct iov_iter *iter) +void fuse_copy_init(struct fuse_copy_state *cs, int write, + struct iov_iter *iter) { memset(cs, 0, sizeof(*cs)); cs->write = write; @@ -814,6 +813,9 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size) *size -= ncpy; cs->len -= ncpy; cs->offset += ncpy; + if (cs->is_uring) + cs->ring.copied_sz += ncpy; + return ncpy; } @@ -1068,9 +1070,9 @@ static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size) } /* Copy request arguments to/from userspace buffer */ -static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs, - unsigned argpages, struct fuse_arg *args, - int zeroing) +int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs, + unsigned argpages, struct fuse_arg *args, + int zeroing) { int err = 0; unsigned i; @@ -1760,7 +1762,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, args = &ap->args; args->nodeid = outarg->nodeid; args->opcode = FUSE_NOTIFY_REPLY; - args->in_numargs = 2; + args->in_numargs = 3; args->in_pages = true; args->end = fuse_retrieve_end; @@ -1788,9 +1790,10 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, } ra->inarg.offset = outarg->offset; ra->inarg.size = total_len; - args->in_args[0].size = sizeof(ra->inarg); - args->in_args[0].value = &ra->inarg; - args->in_args[1].size = total_len; + fuse_set_zero_arg0(args); + args->in_args[1].size = sizeof(ra->inarg); + args->in_args[1].value = &ra->inarg; + args->in_args[2].size = total_len; err = fuse_simple_notify_reply(fm, args, outarg->notify_unique); if (err) @@ -1885,7 +1888,7 @@ static void fuse_resend(struct fuse_conn *fc) spin_unlock(&fiq->lock); list_for_each_entry(req, &to_queue, list) clear_bit(FR_PENDING, &req->flags); - end_requests(&to_queue); + fuse_dev_end_requests(&to_queue); return; } /* iq and pq requests are both oldest to newest */ @@ -1934,7 +1937,7 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, } /* Look up request on processing list by unique ID */ -static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique) +struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique) { unsigned int hash = fuse_req_hash(unique); struct fuse_req *req; @@ -1946,10 +1949,17 @@ static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique) return NULL; } -static int copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, - unsigned nbytes) +int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, + unsigned nbytes) { - unsigned reqsize = sizeof(struct fuse_out_header); + + unsigned int reqsize = 0; + + /* + * Uring has all headers separated from args - args is payload only + */ + if (!cs->is_uring) + reqsize = sizeof(struct fuse_out_header); reqsize += fuse_len_args(args->out_numargs, args->out_args); @@ -2011,7 +2021,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, spin_lock(&fpq->lock); req = NULL; if (fpq->connected) - req = request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT); + req = fuse_request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT); err = -ENOENT; if (!req) { @@ -2049,7 +2059,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, if (oh.error) err = nbytes != sizeof(oh) ? -EINVAL : 0; else - err = copy_out_args(cs, req->args, nbytes); + err = fuse_copy_out_args(cs, req->args, nbytes); fuse_copy_finish(cs); spin_lock(&fpq->lock); @@ -2204,7 +2214,7 @@ static __poll_t fuse_dev_poll(struct file *file, poll_table *wait) } /* Abort all requests on the given list (pending or processing) */ -static void end_requests(struct list_head *head) +void fuse_dev_end_requests(struct list_head *head) { while (!list_empty(head)) { struct fuse_req *req; @@ -2307,7 +2317,13 @@ void fuse_abort_conn(struct fuse_conn *fc) wake_up_all(&fc->blocked_waitq); spin_unlock(&fc->lock); - end_requests(&to_end); + fuse_dev_end_requests(&to_end); + + /* + * fc->lock must not be taken to avoid conflicts with io-uring + * locks + */ + fuse_uring_abort(fc); } else { spin_unlock(&fc->lock); } @@ -2319,6 +2335,8 @@ void fuse_wait_aborted(struct fuse_conn *fc) /* matches implicit memory barrier in fuse_drop_waiting() */ smp_mb(); wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0); + + fuse_uring_wait_stopped_queues(fc); } int fuse_dev_release(struct inode *inode, struct file *file) @@ -2337,7 +2355,7 @@ int fuse_dev_release(struct inode *inode, struct file *file) list_splice_init(&fpq->processing[i], &to_end); spin_unlock(&fpq->lock); - end_requests(&to_end); + fuse_dev_end_requests(&to_end); /* Are we the last open device? */ if (atomic_dec_and_test(&fc->dev_count)) { @@ -2475,6 +2493,9 @@ const struct file_operations fuse_dev_operations = { .fasync = fuse_dev_fasync, .unlocked_ioctl = fuse_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, +#ifdef CONFIG_FUSE_IO_URING + .uring_cmd = fuse_uring_cmd, +#endif }; EXPORT_SYMBOL_GPL(fuse_dev_operations); diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c new file mode 100644 index 000000000000..ebd2931b4f2a --- /dev/null +++ b/fs/fuse/dev_uring.c @@ -0,0 +1,1319 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * FUSE: Filesystem in Userspace + * Copyright (c) 2023-2024 DataDirect Networks. + */ + +#include "fuse_i.h" +#include "dev_uring_i.h" +#include "fuse_dev_i.h" + +#include <linux/fs.h> +#include <linux/io_uring/cmd.h> + +static bool __read_mostly enable_uring; +module_param(enable_uring, bool, 0644); +MODULE_PARM_DESC(enable_uring, + "Enable userspace communication through io-uring"); + +#define FUSE_URING_IOV_SEGS 2 /* header and payload */ + + +bool fuse_uring_enabled(void) +{ + return enable_uring; +} + +struct fuse_uring_pdu { + struct fuse_ring_ent *ent; +}; + +static const struct fuse_iqueue_ops fuse_io_uring_ops; + +static void uring_cmd_set_ring_ent(struct io_uring_cmd *cmd, + struct fuse_ring_ent *ring_ent) +{ + struct fuse_uring_pdu *pdu = + io_uring_cmd_to_pdu(cmd, struct fuse_uring_pdu); + + pdu->ent = ring_ent; +} + +static struct fuse_ring_ent *uring_cmd_to_ring_ent(struct io_uring_cmd *cmd) +{ + struct fuse_uring_pdu *pdu = + io_uring_cmd_to_pdu(cmd, struct fuse_uring_pdu); + + return pdu->ent; +} + +static void fuse_uring_flush_bg(struct fuse_ring_queue *queue) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + + lockdep_assert_held(&queue->lock); + lockdep_assert_held(&fc->bg_lock); + + /* + * Allow one bg request per queue, ignoring global fc limits. + * This prevents a single queue from consuming all resources and + * eliminates the need for remote queue wake-ups when global + * limits are met but this queue has no more waiting requests. + */ + while ((fc->active_background < fc->max_background || + !queue->active_background) && + (!list_empty(&queue->fuse_req_bg_queue))) { + struct fuse_req *req; + + req = list_first_entry(&queue->fuse_req_bg_queue, + struct fuse_req, list); + fc->active_background++; + queue->active_background++; + + list_move_tail(&req->list, &queue->fuse_req_queue); + } +} + +static void fuse_uring_req_end(struct fuse_ring_ent *ent, struct fuse_req *req, + int error) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + + lockdep_assert_not_held(&queue->lock); + spin_lock(&queue->lock); + ent->fuse_req = NULL; + if (test_bit(FR_BACKGROUND, &req->flags)) { + queue->active_background--; + spin_lock(&fc->bg_lock); + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + } + + spin_unlock(&queue->lock); + + if (error) + req->out.h.error = error; + + clear_bit(FR_SENT, &req->flags); + fuse_request_end(req); +} + +/* Abort all list queued request on the given ring queue */ +static void fuse_uring_abort_end_queue_requests(struct fuse_ring_queue *queue) +{ + struct fuse_req *req; + LIST_HEAD(req_list); + + spin_lock(&queue->lock); + list_for_each_entry(req, &queue->fuse_req_queue, list) + clear_bit(FR_PENDING, &req->flags); + list_splice_init(&queue->fuse_req_queue, &req_list); + spin_unlock(&queue->lock); + + /* must not hold queue lock to avoid order issues with fi->lock */ + fuse_dev_end_requests(&req_list); +} + +void fuse_uring_abort_end_requests(struct fuse_ring *ring) +{ + int qid; + struct fuse_ring_queue *queue; + struct fuse_conn *fc = ring->fc; + + for (qid = 0; qid < ring->nr_queues; qid++) { + queue = READ_ONCE(ring->queues[qid]); + if (!queue) + continue; + + queue->stopped = true; + + WARN_ON_ONCE(ring->fc->max_background != UINT_MAX); + spin_lock(&queue->lock); + spin_lock(&fc->bg_lock); + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + spin_unlock(&queue->lock); + fuse_uring_abort_end_queue_requests(queue); + } +} + +void fuse_uring_destruct(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + int qid; + + if (!ring) + return; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = ring->queues[qid]; + struct fuse_ring_ent *ent, *next; + + if (!queue) + continue; + + WARN_ON(!list_empty(&queue->ent_avail_queue)); + WARN_ON(!list_empty(&queue->ent_w_req_queue)); + WARN_ON(!list_empty(&queue->ent_commit_queue)); + WARN_ON(!list_empty(&queue->ent_in_userspace)); + + list_for_each_entry_safe(ent, next, &queue->ent_released, + list) { + list_del_init(&ent->list); + kfree(ent); + } + + kfree(queue->fpq.processing); + kfree(queue); + ring->queues[qid] = NULL; + } + + kfree(ring->queues); + kfree(ring); + fc->ring = NULL; +} + +/* + * Basic ring setup for this connection based on the provided configuration + */ +static struct fuse_ring *fuse_uring_create(struct fuse_conn *fc) +{ + struct fuse_ring *ring; + size_t nr_queues = num_possible_cpus(); + struct fuse_ring *res = NULL; + size_t max_payload_size; + + ring = kzalloc(sizeof(*fc->ring), GFP_KERNEL_ACCOUNT); + if (!ring) + return NULL; + + ring->queues = kcalloc(nr_queues, sizeof(struct fuse_ring_queue *), + GFP_KERNEL_ACCOUNT); + if (!ring->queues) + goto out_err; + + max_payload_size = max(FUSE_MIN_READ_BUFFER, fc->max_write); + max_payload_size = max(max_payload_size, fc->max_pages * PAGE_SIZE); + + spin_lock(&fc->lock); + if (fc->ring) { + /* race, another thread created the ring in the meantime */ + spin_unlock(&fc->lock); + res = fc->ring; + goto out_err; + } + + init_waitqueue_head(&ring->stop_waitq); + + fc->ring = ring; + ring->nr_queues = nr_queues; + ring->fc = fc; + ring->max_payload_sz = max_payload_size; + atomic_set(&ring->queue_refs, 0); + + spin_unlock(&fc->lock); + return ring; + +out_err: + kfree(ring->queues); + kfree(ring); + return res; +} + +static struct fuse_ring_queue *fuse_uring_create_queue(struct fuse_ring *ring, + int qid) +{ + struct fuse_conn *fc = ring->fc; + struct fuse_ring_queue *queue; + struct list_head *pq; + + queue = kzalloc(sizeof(*queue), GFP_KERNEL_ACCOUNT); + if (!queue) + return NULL; + pq = kcalloc(FUSE_PQ_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); + if (!pq) { + kfree(queue); + return NULL; + } + + queue->qid = qid; + queue->ring = ring; + spin_lock_init(&queue->lock); + + INIT_LIST_HEAD(&queue->ent_avail_queue); + INIT_LIST_HEAD(&queue->ent_commit_queue); + INIT_LIST_HEAD(&queue->ent_w_req_queue); + INIT_LIST_HEAD(&queue->ent_in_userspace); + INIT_LIST_HEAD(&queue->fuse_req_queue); + INIT_LIST_HEAD(&queue->fuse_req_bg_queue); + INIT_LIST_HEAD(&queue->ent_released); + + queue->fpq.processing = pq; + fuse_pqueue_init(&queue->fpq); + + spin_lock(&fc->lock); + if (ring->queues[qid]) { + spin_unlock(&fc->lock); + kfree(queue->fpq.processing); + kfree(queue); + return ring->queues[qid]; + } + + /* + * write_once and lock as the caller mostly doesn't take the lock at all + */ + WRITE_ONCE(ring->queues[qid], queue); + spin_unlock(&fc->lock); + + return queue; +} + +static void fuse_uring_stop_fuse_req_end(struct fuse_req *req) +{ + clear_bit(FR_SENT, &req->flags); + req->out.h.error = -ECONNABORTED; + fuse_request_end(req); +} + +/* + * Release a request/entry on connection tear down + */ +static void fuse_uring_entry_teardown(struct fuse_ring_ent *ent) +{ + struct fuse_req *req; + struct io_uring_cmd *cmd; + + struct fuse_ring_queue *queue = ent->queue; + + spin_lock(&queue->lock); + cmd = ent->cmd; + ent->cmd = NULL; + req = ent->fuse_req; + ent->fuse_req = NULL; + if (req) { + /* remove entry from queue->fpq->processing */ + list_del_init(&req->list); + } + + /* + * The entry must not be freed immediately, due to access of direct + * pointer access of entries through IO_URING_F_CANCEL - there is a risk + * of race between daemon termination (which triggers IO_URING_F_CANCEL + * and accesses entries without checking the list state first + */ + list_move(&ent->list, &queue->ent_released); + ent->state = FRRS_RELEASED; + spin_unlock(&queue->lock); + + if (cmd) + io_uring_cmd_done(cmd, -ENOTCONN, 0, IO_URING_F_UNLOCKED); + + if (req) + fuse_uring_stop_fuse_req_end(req); +} + +static void fuse_uring_stop_list_entries(struct list_head *head, + struct fuse_ring_queue *queue, + enum fuse_ring_req_state exp_state) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_ring_ent *ent, *next; + ssize_t queue_refs = SSIZE_MAX; + LIST_HEAD(to_teardown); + + spin_lock(&queue->lock); + list_for_each_entry_safe(ent, next, head, list) { + if (ent->state != exp_state) { + pr_warn("entry teardown qid=%d state=%d expected=%d", + queue->qid, ent->state, exp_state); + continue; + } + + ent->state = FRRS_TEARDOWN; + list_move(&ent->list, &to_teardown); + } + spin_unlock(&queue->lock); + + /* no queue lock to avoid lock order issues */ + list_for_each_entry_safe(ent, next, &to_teardown, list) { + fuse_uring_entry_teardown(ent); + queue_refs = atomic_dec_return(&ring->queue_refs); + WARN_ON_ONCE(queue_refs < 0); + } +} + +static void fuse_uring_teardown_entries(struct fuse_ring_queue *queue) +{ + fuse_uring_stop_list_entries(&queue->ent_in_userspace, queue, + FRRS_USERSPACE); + fuse_uring_stop_list_entries(&queue->ent_avail_queue, queue, + FRRS_AVAILABLE); +} + +/* + * Log state debug info + */ +static void fuse_uring_log_ent_state(struct fuse_ring *ring) +{ + int qid; + struct fuse_ring_ent *ent; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = ring->queues[qid]; + + if (!queue) + continue; + + spin_lock(&queue->lock); + /* + * Log entries from the intermediate queue, the other queues + * should be empty + */ + list_for_each_entry(ent, &queue->ent_w_req_queue, list) { + pr_info(" ent-req-queue ring=%p qid=%d ent=%p state=%d\n", + ring, qid, ent, ent->state); + } + list_for_each_entry(ent, &queue->ent_commit_queue, list) { + pr_info(" ent-commit-queue ring=%p qid=%d ent=%p state=%d\n", + ring, qid, ent, ent->state); + } + spin_unlock(&queue->lock); + } + ring->stop_debug_log = 1; +} + +static void fuse_uring_async_stop_queues(struct work_struct *work) +{ + int qid; + struct fuse_ring *ring = + container_of(work, struct fuse_ring, async_teardown_work.work); + + /* XXX code dup */ + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = READ_ONCE(ring->queues[qid]); + + if (!queue) + continue; + + fuse_uring_teardown_entries(queue); + } + + /* + * Some ring entries might be in the middle of IO operations, + * i.e. in process to get handled by file_operations::uring_cmd + * or on the way to userspace - we could handle that with conditions in + * run time code, but easier/cleaner to have an async tear down handler + * If there are still queue references left + */ + if (atomic_read(&ring->queue_refs) > 0) { + if (time_after(jiffies, + ring->teardown_time + FUSE_URING_TEARDOWN_TIMEOUT)) + fuse_uring_log_ent_state(ring); + + schedule_delayed_work(&ring->async_teardown_work, + FUSE_URING_TEARDOWN_INTERVAL); + } else { + wake_up_all(&ring->stop_waitq); + } +} + +/* + * Stop the ring queues + */ +void fuse_uring_stop_queues(struct fuse_ring *ring) +{ + int qid; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = READ_ONCE(ring->queues[qid]); + + if (!queue) + continue; + + fuse_uring_teardown_entries(queue); + } + + if (atomic_read(&ring->queue_refs) > 0) { + ring->teardown_time = jiffies; + INIT_DELAYED_WORK(&ring->async_teardown_work, + fuse_uring_async_stop_queues); + schedule_delayed_work(&ring->async_teardown_work, + FUSE_URING_TEARDOWN_INTERVAL); + } else { + wake_up_all(&ring->stop_waitq); + } +} + +/* + * Handle IO_URING_F_CANCEL, typically should come on daemon termination. + * + * Releasing the last entry should trigger fuse_dev_release() if + * the daemon was terminated + */ +static void fuse_uring_cancel(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd); + struct fuse_ring_queue *queue; + bool need_cmd_done = false; + + /* + * direct access on ent - it must not be destructed as long as + * IO_URING_F_CANCEL might come up + */ + queue = ent->queue; + spin_lock(&queue->lock); + if (ent->state == FRRS_AVAILABLE) { + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + need_cmd_done = true; + ent->cmd = NULL; + } + spin_unlock(&queue->lock); + + if (need_cmd_done) { + /* no queue lock to avoid lock order issues */ + io_uring_cmd_done(cmd, -ENOTCONN, 0, issue_flags); + } +} + +static void fuse_uring_prepare_cancel(struct io_uring_cmd *cmd, int issue_flags, + struct fuse_ring_ent *ring_ent) +{ + uring_cmd_set_ring_ent(cmd, ring_ent); + io_uring_cmd_mark_cancelable(cmd, issue_flags); +} + +/* + * Checks for errors and stores it into the request + */ +static int fuse_uring_out_header_has_err(struct fuse_out_header *oh, + struct fuse_req *req, + struct fuse_conn *fc) +{ + int err; + + err = -EINVAL; + if (oh->unique == 0) { + /* Not supported through io-uring yet */ + pr_warn_once("notify through fuse-io-uring not supported\n"); + goto err; + } + + if (oh->error <= -ERESTARTSYS || oh->error > 0) + goto err; + + if (oh->error) { + err = oh->error; + goto err; + } + + err = -ENOENT; + if ((oh->unique & ~FUSE_INT_REQ_BIT) != req->in.h.unique) { + pr_warn_ratelimited("unique mismatch, expected: %llu got %llu\n", + req->in.h.unique, + oh->unique & ~FUSE_INT_REQ_BIT); + goto err; + } + + /* + * Is it an interrupt reply ID? + * XXX: Not supported through fuse-io-uring yet, it should not even + * find the request - should not happen. + */ + WARN_ON_ONCE(oh->unique & FUSE_INT_REQ_BIT); + + err = 0; +err: + return err; +} + +static int fuse_uring_copy_from_ring(struct fuse_ring *ring, + struct fuse_req *req, + struct fuse_ring_ent *ent) +{ + struct fuse_copy_state cs; + struct fuse_args *args = req->args; + struct iov_iter iter; + int err; + struct fuse_uring_ent_in_out ring_in_out; + + err = copy_from_user(&ring_in_out, &ent->headers->ring_ent_in_out, + sizeof(ring_in_out)); + if (err) + return -EFAULT; + + err = import_ubuf(ITER_SOURCE, ent->payload, ring->max_payload_sz, + &iter); + if (err) + return err; + + fuse_copy_init(&cs, 0, &iter); + cs.is_uring = 1; + cs.req = req; + + return fuse_copy_out_args(&cs, args, ring_in_out.payload_sz); +} + + /* + * Copy data from the req to the ring buffer + */ +static int fuse_uring_args_to_ring(struct fuse_ring *ring, struct fuse_req *req, + struct fuse_ring_ent *ent) +{ + struct fuse_copy_state cs; + struct fuse_args *args = req->args; + struct fuse_in_arg *in_args = args->in_args; + int num_args = args->in_numargs; + int err; + struct iov_iter iter; + struct fuse_uring_ent_in_out ent_in_out = { + .flags = 0, + .commit_id = req->in.h.unique, + }; + + err = import_ubuf(ITER_DEST, ent->payload, ring->max_payload_sz, &iter); + if (err) { + pr_info_ratelimited("fuse: Import of user buffer failed\n"); + return err; + } + + fuse_copy_init(&cs, 1, &iter); + cs.is_uring = 1; + cs.req = req; + + if (num_args > 0) { + /* + * Expectation is that the first argument is the per op header. + * Some op code have that as zero size. + */ + if (args->in_args[0].size > 0) { + err = copy_to_user(&ent->headers->op_in, in_args->value, + in_args->size); + if (err) { + pr_info_ratelimited( + "Copying the header failed.\n"); + return -EFAULT; + } + } + in_args++; + num_args--; + } + + /* copy the payload */ + err = fuse_copy_args(&cs, num_args, args->in_pages, + (struct fuse_arg *)in_args, 0); + if (err) { + pr_info_ratelimited("%s fuse_copy_args failed\n", __func__); + return err; + } + + ent_in_out.payload_sz = cs.ring.copied_sz; + err = copy_to_user(&ent->headers->ring_ent_in_out, &ent_in_out, + sizeof(ent_in_out)); + return err ? -EFAULT : 0; +} + +static int fuse_uring_copy_to_ring(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + int err; + + err = -EIO; + if (WARN_ON(ent->state != FRRS_FUSE_REQ)) { + pr_err("qid=%d ring-req=%p invalid state %d on send\n", + queue->qid, ent, ent->state); + return err; + } + + err = -EINVAL; + if (WARN_ON(req->in.h.unique == 0)) + return err; + + /* copy the request */ + err = fuse_uring_args_to_ring(ring, req, ent); + if (unlikely(err)) { + pr_info_ratelimited("Copy to ring failed: %d\n", err); + return err; + } + + /* copy fuse_in_header */ + err = copy_to_user(&ent->headers->in_out, &req->in.h, + sizeof(req->in.h)); + if (err) { + err = -EFAULT; + return err; + } + + return 0; +} + +static int fuse_uring_prepare_send(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + int err; + + err = fuse_uring_copy_to_ring(ent, req); + if (!err) + set_bit(FR_SENT, &req->flags); + else + fuse_uring_req_end(ent, req, err); + + return err; +} + +/* + * Write data to the ring buffer and send the request to userspace, + * userspace will read it + * This is comparable with classical read(/dev/fuse) + */ +static int fuse_uring_send_next_to_ring(struct fuse_ring_ent *ent, + struct fuse_req *req, + unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + int err; + struct io_uring_cmd *cmd; + + err = fuse_uring_prepare_send(ent, req); + if (err) + return err; + + spin_lock(&queue->lock); + cmd = ent->cmd; + ent->cmd = NULL; + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + spin_unlock(&queue->lock); + + io_uring_cmd_done(cmd, 0, 0, issue_flags); + return 0; +} + +/* + * Make a ring entry available for fuse_req assignment + */ +static void fuse_uring_ent_avail(struct fuse_ring_ent *ent, + struct fuse_ring_queue *queue) +{ + WARN_ON_ONCE(!ent->cmd); + list_move(&ent->list, &queue->ent_avail_queue); + ent->state = FRRS_AVAILABLE; +} + +/* Used to find the request on SQE commit */ +static void fuse_uring_add_to_pq(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_pqueue *fpq = &queue->fpq; + unsigned int hash; + + req->ring_entry = ent; + hash = fuse_req_hash(req->in.h.unique); + list_move_tail(&req->list, &fpq->processing[hash]); +} + +/* + * Assign a fuse queue entry to the given entry + */ +static void fuse_uring_add_req_to_ring_ent(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_conn *fc = req->fm->fc; + struct fuse_iqueue *fiq = &fc->iq; + + lockdep_assert_held(&queue->lock); + + if (WARN_ON_ONCE(ent->state != FRRS_AVAILABLE && + ent->state != FRRS_COMMIT)) { + pr_warn("%s qid=%d state=%d\n", __func__, ent->queue->qid, + ent->state); + } + + spin_lock(&fiq->lock); + clear_bit(FR_PENDING, &req->flags); + spin_unlock(&fiq->lock); + ent->fuse_req = req; + ent->state = FRRS_FUSE_REQ; + list_move(&ent->list, &queue->ent_w_req_queue); + fuse_uring_add_to_pq(ent, req); +} + +/* Fetch the next fuse request if available */ +static struct fuse_req *fuse_uring_ent_assign_req(struct fuse_ring_ent *ent) + __must_hold(&queue->lock) +{ + struct fuse_req *req; + struct fuse_ring_queue *queue = ent->queue; + struct list_head *req_queue = &queue->fuse_req_queue; + + lockdep_assert_held(&queue->lock); + + /* get and assign the next entry while it is still holding the lock */ + req = list_first_entry_or_null(req_queue, struct fuse_req, list); + if (req) + fuse_uring_add_req_to_ring_ent(ent, req); + + return req; +} + +/* + * Read data from the ring buffer, which user space has written to + * This is comparible with handling of classical write(/dev/fuse). + * Also make the ring request available again for new fuse requests. + */ +static void fuse_uring_commit(struct fuse_ring_ent *ent, struct fuse_req *req, + unsigned int issue_flags) +{ + struct fuse_ring *ring = ent->queue->ring; + struct fuse_conn *fc = ring->fc; + ssize_t err = 0; + + err = copy_from_user(&req->out.h, &ent->headers->in_out, + sizeof(req->out.h)); + if (err) { + req->out.h.error = -EFAULT; + goto out; + } + + err = fuse_uring_out_header_has_err(&req->out.h, req, fc); + if (err) { + /* req->out.h.error already set */ + goto out; + } + + err = fuse_uring_copy_from_ring(ring, req, ent); +out: + fuse_uring_req_end(ent, req, err); +} + +/* + * Get the next fuse req and send it + */ +static void fuse_uring_next_fuse_req(struct fuse_ring_ent *ent, + struct fuse_ring_queue *queue, + unsigned int issue_flags) +{ + int err; + struct fuse_req *req; + +retry: + spin_lock(&queue->lock); + fuse_uring_ent_avail(ent, queue); + req = fuse_uring_ent_assign_req(ent); + spin_unlock(&queue->lock); + + if (req) { + err = fuse_uring_send_next_to_ring(ent, req, issue_flags); + if (err) + goto retry; + } +} + +static int fuse_ring_ent_set_commit(struct fuse_ring_ent *ent) +{ + struct fuse_ring_queue *queue = ent->queue; + + lockdep_assert_held(&queue->lock); + + if (WARN_ON_ONCE(ent->state != FRRS_USERSPACE)) + return -EIO; + + ent->state = FRRS_COMMIT; + list_move(&ent->list, &queue->ent_commit_queue); + + return 0; +} + +/* FUSE_URING_CMD_COMMIT_AND_FETCH handler */ +static int fuse_uring_commit_fetch(struct io_uring_cmd *cmd, int issue_flags, + struct fuse_conn *fc) +{ + const struct fuse_uring_cmd_req *cmd_req = io_uring_sqe_cmd(cmd->sqe); + struct fuse_ring_ent *ent; + int err; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + uint64_t commit_id = READ_ONCE(cmd_req->commit_id); + unsigned int qid = READ_ONCE(cmd_req->qid); + struct fuse_pqueue *fpq; + struct fuse_req *req; + + err = -ENOTCONN; + if (!ring) + return err; + + if (qid >= ring->nr_queues) + return -EINVAL; + + queue = ring->queues[qid]; + if (!queue) + return err; + fpq = &queue->fpq; + + if (!READ_ONCE(fc->connected) || READ_ONCE(queue->stopped)) + return err; + + spin_lock(&queue->lock); + /* Find a request based on the unique ID of the fuse request + * This should get revised, as it needs a hash calculation and list + * search. And full struct fuse_pqueue is needed (memory overhead). + * As well as the link from req to ring_ent. + */ + req = fuse_request_find(fpq, commit_id); + err = -ENOENT; + if (!req) { + pr_info("qid=%d commit_id %llu not found\n", queue->qid, + commit_id); + spin_unlock(&queue->lock); + return err; + } + list_del_init(&req->list); + ent = req->ring_entry; + req->ring_entry = NULL; + + err = fuse_ring_ent_set_commit(ent); + if (err != 0) { + pr_info_ratelimited("qid=%d commit_id %llu state %d", + queue->qid, commit_id, ent->state); + spin_unlock(&queue->lock); + req->out.h.error = err; + clear_bit(FR_SENT, &req->flags); + fuse_request_end(req); + return err; + } + + ent->cmd = cmd; + spin_unlock(&queue->lock); + + /* without the queue lock, as other locks are taken */ + fuse_uring_prepare_cancel(cmd, issue_flags, ent); + fuse_uring_commit(ent, req, issue_flags); + + /* + * Fetching the next request is absolutely required as queued + * fuse requests would otherwise not get processed - committing + * and fetching is done in one step vs legacy fuse, which has separated + * read (fetch request) and write (commit result). + */ + fuse_uring_next_fuse_req(ent, queue, issue_flags); + return 0; +} + +static bool is_ring_ready(struct fuse_ring *ring, int current_qid) +{ + int qid; + struct fuse_ring_queue *queue; + bool ready = true; + + for (qid = 0; qid < ring->nr_queues && ready; qid++) { + if (current_qid == qid) + continue; + + queue = ring->queues[qid]; + if (!queue) { + ready = false; + break; + } + + spin_lock(&queue->lock); + if (list_empty(&queue->ent_avail_queue)) + ready = false; + spin_unlock(&queue->lock); + } + + return ready; +} + +/* + * fuse_uring_req_fetch command handling + */ +static void fuse_uring_do_register(struct fuse_ring_ent *ent, + struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + struct fuse_iqueue *fiq = &fc->iq; + + fuse_uring_prepare_cancel(cmd, issue_flags, ent); + + spin_lock(&queue->lock); + ent->cmd = cmd; + fuse_uring_ent_avail(ent, queue); + spin_unlock(&queue->lock); + + if (!ring->ready) { + bool ready = is_ring_ready(ring, queue->qid); + + if (ready) { + WRITE_ONCE(fiq->ops, &fuse_io_uring_ops); + WRITE_ONCE(ring->ready, true); + wake_up_all(&fc->blocked_waitq); + } + } +} + +/* + * sqe->addr is a ptr to an iovec array, iov[0] has the headers, iov[1] + * the payload + */ +static int fuse_uring_get_iovec_from_sqe(const struct io_uring_sqe *sqe, + struct iovec iov[FUSE_URING_IOV_SEGS]) +{ + struct iovec __user *uiov = u64_to_user_ptr(READ_ONCE(sqe->addr)); + struct iov_iter iter; + ssize_t ret; + + if (sqe->len != FUSE_URING_IOV_SEGS) + return -EINVAL; + + /* + * Direction for buffer access will actually be READ and WRITE, + * using write for the import should include READ access as well. + */ + ret = import_iovec(WRITE, uiov, FUSE_URING_IOV_SEGS, + FUSE_URING_IOV_SEGS, &iov, &iter); + if (ret < 0) + return ret; + + return 0; +} + +static struct fuse_ring_ent * +fuse_uring_create_ring_ent(struct io_uring_cmd *cmd, + struct fuse_ring_queue *queue) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_ring_ent *ent; + size_t payload_size; + struct iovec iov[FUSE_URING_IOV_SEGS]; + int err; + + err = fuse_uring_get_iovec_from_sqe(cmd->sqe, iov); + if (err) { + pr_info_ratelimited("Failed to get iovec from sqe, err=%d\n", + err); + return ERR_PTR(err); + } + + err = -EINVAL; + if (iov[0].iov_len < sizeof(struct fuse_uring_req_header)) { + pr_info_ratelimited("Invalid header len %zu\n", iov[0].iov_len); + return ERR_PTR(err); + } + + payload_size = iov[1].iov_len; + if (payload_size < ring->max_payload_sz) { + pr_info_ratelimited("Invalid req payload len %zu\n", + payload_size); + return ERR_PTR(err); + } + + err = -ENOMEM; + ent = kzalloc(sizeof(*ent), GFP_KERNEL_ACCOUNT); + if (!ent) + return ERR_PTR(err); + + INIT_LIST_HEAD(&ent->list); + + ent->queue = queue; + ent->headers = iov[0].iov_base; + ent->payload = iov[1].iov_base; + + atomic_inc(&ring->queue_refs); + return ent; +} + +/* + * Register header and payload buffer with the kernel and puts the + * entry as "ready to get fuse requests" on the queue + */ +static int fuse_uring_register(struct io_uring_cmd *cmd, + unsigned int issue_flags, struct fuse_conn *fc) +{ + const struct fuse_uring_cmd_req *cmd_req = io_uring_sqe_cmd(cmd->sqe); + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent; + int err; + unsigned int qid = READ_ONCE(cmd_req->qid); + + err = -ENOMEM; + if (!ring) { + ring = fuse_uring_create(fc); + if (!ring) + return err; + } + + if (qid >= ring->nr_queues) { + pr_info_ratelimited("fuse: Invalid ring qid %u\n", qid); + return -EINVAL; + } + + queue = ring->queues[qid]; + if (!queue) { + queue = fuse_uring_create_queue(ring, qid); + if (!queue) + return err; + } + + /* + * The created queue above does not need to be destructed in + * case of entry errors below, will be done at ring destruction time. + */ + + ent = fuse_uring_create_ring_ent(cmd, queue); + if (IS_ERR(ent)) + return PTR_ERR(ent); + + fuse_uring_do_register(ent, cmd, issue_flags); + + return 0; +} + +/* + * Entry function from io_uring to handle the given passthrough command + * (op code IORING_OP_URING_CMD) + */ +int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct fuse_dev *fud; + struct fuse_conn *fc; + u32 cmd_op = cmd->cmd_op; + int err; + + if ((unlikely(issue_flags & IO_URING_F_CANCEL))) { + fuse_uring_cancel(cmd, issue_flags); + return 0; + } + + /* This extra SQE size holds struct fuse_uring_cmd_req */ + if (!(issue_flags & IO_URING_F_SQE128)) + return -EINVAL; + + fud = fuse_get_dev(cmd->file); + if (!fud) { + pr_info_ratelimited("No fuse device found\n"); + return -ENOTCONN; + } + fc = fud->fc; + + /* Once a connection has io-uring enabled on it, it can't be disabled */ + if (!enable_uring && !fc->io_uring) { + pr_info_ratelimited("fuse-io-uring is disabled\n"); + return -EOPNOTSUPP; + } + + if (fc->aborted) + return -ECONNABORTED; + if (!fc->connected) + return -ENOTCONN; + + /* + * fuse_uring_register() needs the ring to be initialized, + * we need to know the max payload size + */ + if (!fc->initialized) + return -EAGAIN; + + switch (cmd_op) { + case FUSE_IO_URING_CMD_REGISTER: + err = fuse_uring_register(cmd, issue_flags, fc); + if (err) { + pr_info_once("FUSE_IO_URING_CMD_REGISTER failed err=%d\n", + err); + fc->io_uring = 0; + wake_up_all(&fc->blocked_waitq); + return err; + } + break; + case FUSE_IO_URING_CMD_COMMIT_AND_FETCH: + err = fuse_uring_commit_fetch(cmd, issue_flags, fc); + if (err) { + pr_info_once("FUSE_IO_URING_COMMIT_AND_FETCH failed err=%d\n", + err); + return err; + } + break; + default: + return -EINVAL; + } + + return -EIOCBQUEUED; +} + +static void fuse_uring_send(struct fuse_ring_ent *ent, struct io_uring_cmd *cmd, + ssize_t ret, unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + + spin_lock(&queue->lock); + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + ent->cmd = NULL; + spin_unlock(&queue->lock); + + io_uring_cmd_done(cmd, ret, 0, issue_flags); +} + +/* + * This prepares and sends the ring request in fuse-uring task context. + * User buffers are not mapped yet - the application does not have permission + * to write to it - this has to be executed in ring task context. + */ +static void fuse_uring_send_in_task(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd); + struct fuse_ring_queue *queue = ent->queue; + int err; + + if (!(issue_flags & IO_URING_F_TASK_DEAD)) { + err = fuse_uring_prepare_send(ent, ent->fuse_req); + if (err) { + fuse_uring_next_fuse_req(ent, queue, issue_flags); + return; + } + } else { + err = -ECANCELED; + } + + fuse_uring_send(ent, cmd, err, issue_flags); +} + +static struct fuse_ring_queue *fuse_uring_task_to_queue(struct fuse_ring *ring) +{ + unsigned int qid; + struct fuse_ring_queue *queue; + + qid = task_cpu(current); + + if (WARN_ONCE(qid >= ring->nr_queues, + "Core number (%u) exceeds nr queues (%zu)\n", qid, + ring->nr_queues)) + qid = 0; + + queue = ring->queues[qid]; + WARN_ONCE(!queue, "Missing queue for qid %d\n", qid); + + return queue; +} + +static void fuse_uring_dispatch_ent(struct fuse_ring_ent *ent) +{ + struct io_uring_cmd *cmd = ent->cmd; + + uring_cmd_set_ring_ent(cmd, ent); + io_uring_cmd_complete_in_task(cmd, fuse_uring_send_in_task); +} + +/* queue a fuse request and send it if a ring entry is available */ +void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req) +{ + struct fuse_conn *fc = req->fm->fc; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent = NULL; + int err; + + err = -EINVAL; + queue = fuse_uring_task_to_queue(ring); + if (!queue) + goto err; + + if (req->in.h.opcode != FUSE_NOTIFY_REPLY) + req->in.h.unique = fuse_get_unique(fiq); + + spin_lock(&queue->lock); + err = -ENOTCONN; + if (unlikely(queue->stopped)) + goto err_unlock; + + ent = list_first_entry_or_null(&queue->ent_avail_queue, + struct fuse_ring_ent, list); + if (ent) + fuse_uring_add_req_to_ring_ent(ent, req); + else + list_add_tail(&req->list, &queue->fuse_req_queue); + spin_unlock(&queue->lock); + + if (ent) + fuse_uring_dispatch_ent(ent); + + return; + +err_unlock: + spin_unlock(&queue->lock); +err: + req->out.h.error = err; + clear_bit(FR_PENDING, &req->flags); + fuse_request_end(req); +} + +bool fuse_uring_queue_bq_req(struct fuse_req *req) +{ + struct fuse_conn *fc = req->fm->fc; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent = NULL; + + queue = fuse_uring_task_to_queue(ring); + if (!queue) + return false; + + spin_lock(&queue->lock); + if (unlikely(queue->stopped)) { + spin_unlock(&queue->lock); + return false; + } + + list_add_tail(&req->list, &queue->fuse_req_bg_queue); + + ent = list_first_entry_or_null(&queue->ent_avail_queue, + struct fuse_ring_ent, list); + spin_lock(&fc->bg_lock); + fc->num_background++; + if (fc->num_background == fc->max_background) + fc->blocked = 1; + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + + /* + * Due to bg_queue flush limits there might be other bg requests + * in the queue that need to be handled first. Or no further req + * might be available. + */ + req = list_first_entry_or_null(&queue->fuse_req_queue, struct fuse_req, + list); + if (ent && req) { + fuse_uring_add_req_to_ring_ent(ent, req); + spin_unlock(&queue->lock); + + fuse_uring_dispatch_ent(ent); + } else { + spin_unlock(&queue->lock); + } + + return true; +} + +static const struct fuse_iqueue_ops fuse_io_uring_ops = { + /* should be send over io-uring as enhancement */ + .send_forget = fuse_dev_queue_forget, + + /* + * could be send over io-uring, but interrupts should be rare, + * no need to make the code complex + */ + .send_interrupt = fuse_dev_queue_interrupt, + .send_req = fuse_uring_queue_fuse_req, +}; diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h new file mode 100644 index 000000000000..2102b3d0c1ae --- /dev/null +++ b/fs/fuse/dev_uring_i.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * FUSE: Filesystem in Userspace + * Copyright (c) 2023-2024 DataDirect Networks. + */ + +#ifndef _FS_FUSE_DEV_URING_I_H +#define _FS_FUSE_DEV_URING_I_H + +#include "fuse_i.h" + +#ifdef CONFIG_FUSE_IO_URING + +#define FUSE_URING_TEARDOWN_TIMEOUT (5 * HZ) +#define FUSE_URING_TEARDOWN_INTERVAL (HZ/20) + +enum fuse_ring_req_state { + FRRS_INVALID = 0, + + /* The ring entry received from userspace and it is being processed */ + FRRS_COMMIT, + + /* The ring entry is waiting for new fuse requests */ + FRRS_AVAILABLE, + + /* The ring entry got assigned a fuse req */ + FRRS_FUSE_REQ, + + /* The ring entry is in or on the way to user space */ + FRRS_USERSPACE, + + /* The ring entry is in teardown */ + FRRS_TEARDOWN, + + /* The ring entry is released, but not freed yet */ + FRRS_RELEASED, +}; + +/** A fuse ring entry, part of the ring queue */ +struct fuse_ring_ent { + /* userspace buffer */ + struct fuse_uring_req_header __user *headers; + void __user *payload; + + /* the ring queue that owns the request */ + struct fuse_ring_queue *queue; + + /* fields below are protected by queue->lock */ + + struct io_uring_cmd *cmd; + + struct list_head list; + + enum fuse_ring_req_state state; + + struct fuse_req *fuse_req; +}; + +struct fuse_ring_queue { + /* + * back pointer to the main fuse uring structure that holds this + * queue + */ + struct fuse_ring *ring; + + /* queue id, corresponds to the cpu core */ + unsigned int qid; + + /* + * queue lock, taken when any value in the queue changes _and_ also + * a ring entry state changes. + */ + spinlock_t lock; + + /* available ring entries (struct fuse_ring_ent) */ + struct list_head ent_avail_queue; + + /* + * entries in the process of being committed or in the process + * to be sent to userspace + */ + struct list_head ent_w_req_queue; + struct list_head ent_commit_queue; + + /* entries in userspace */ + struct list_head ent_in_userspace; + + /* entries that are released */ + struct list_head ent_released; + + /* fuse requests waiting for an entry slot */ + struct list_head fuse_req_queue; + + /* background fuse requests */ + struct list_head fuse_req_bg_queue; + + struct fuse_pqueue fpq; + + unsigned int active_background; + + bool stopped; +}; + +/** + * Describes if uring is for communication and holds alls the data needed + * for uring communication + */ +struct fuse_ring { + /* back pointer */ + struct fuse_conn *fc; + + /* number of ring queues */ + size_t nr_queues; + + /* maximum payload/arg size */ + size_t max_payload_sz; + + struct fuse_ring_queue **queues; + + /* + * Log ring entry states on stop when entries cannot be released + */ + unsigned int stop_debug_log : 1; + + wait_queue_head_t stop_waitq; + + /* async tear down */ + struct delayed_work async_teardown_work; + + /* log */ + unsigned long teardown_time; + + atomic_t queue_refs; + + bool ready; +}; + +bool fuse_uring_enabled(void); +void fuse_uring_destruct(struct fuse_conn *fc); +void fuse_uring_stop_queues(struct fuse_ring *ring); +void fuse_uring_abort_end_requests(struct fuse_ring *ring); +int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); +void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req); +bool fuse_uring_queue_bq_req(struct fuse_req *req); + +static inline void fuse_uring_abort(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + + if (ring == NULL) + return; + + if (atomic_read(&ring->queue_refs) > 0) { + fuse_uring_abort_end_requests(ring); + fuse_uring_stop_queues(ring); + } +} + +static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + + if (ring) + wait_event(ring->stop_waitq, + atomic_read(&ring->queue_refs) == 0); +} + +static inline bool fuse_uring_ready(struct fuse_conn *fc) +{ + return fc->ring && fc->ring->ready; +} + +#else /* CONFIG_FUSE_IO_URING */ + +struct fuse_ring; + +static inline void fuse_uring_create(struct fuse_conn *fc) +{ +} + +static inline void fuse_uring_destruct(struct fuse_conn *fc) +{ +} + +static inline bool fuse_uring_enabled(void) +{ + return false; +} + +static inline void fuse_uring_abort(struct fuse_conn *fc) +{ +} + +static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc) +{ +} + +static inline bool fuse_uring_ready(struct fuse_conn *fc) +{ + return false; +} + +#endif /* CONFIG_FUSE_IO_URING */ + +#endif /* _FS_FUSE_DEV_URING_I_H */ diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index bf057cf7098d..be693a8a1010 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -175,9 +175,10 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args, memset(outarg, 0, sizeof(struct fuse_entry_out)); args->opcode = FUSE_LOOKUP; args->nodeid = nodeid; - args->in_numargs = 1; - args->in_args[0].size = name->len + 1; - args->in_args[0].value = name->name; + args->in_numargs = 2; + fuse_set_zero_arg0(args); + args->in_args[1].size = name->len + 1; + args->in_args[1].value = name->name; args->out_numargs = 1; args->out_args[0].size = sizeof(struct fuse_entry_out); args->out_args[0].value = outarg; @@ -929,11 +930,12 @@ static int fuse_symlink(struct mnt_idmap *idmap, struct inode *dir, FUSE_ARGS(args); args.opcode = FUSE_SYMLINK; - args.in_numargs = 2; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; - args.in_args[1].size = len; - args.in_args[1].value = link; + args.in_numargs = 3; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; + args.in_args[2].size = len; + args.in_args[2].value = link; return create_new_entry(idmap, fm, &args, dir, entry, S_IFLNK); } @@ -993,9 +995,10 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) args.opcode = FUSE_UNLINK; args.nodeid = get_node_id(dir); - args.in_numargs = 1; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; err = fuse_simple_request(fm, &args); if (!err) { fuse_dir_changed(dir); @@ -1016,9 +1019,10 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) args.opcode = FUSE_RMDIR; args.nodeid = get_node_id(dir); - args.in_numargs = 1; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; err = fuse_simple_request(fm, &args); if (!err) { fuse_dir_changed(dir); diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h new file mode 100644 index 000000000000..3b2bfe1248d3 --- /dev/null +++ b/fs/fuse/fuse_dev_i.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * FUSE: Filesystem in Userspace + * Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu> + */ +#ifndef _FS_FUSE_DEV_I_H +#define _FS_FUSE_DEV_I_H + +#include <linux/types.h> + +/* Ordinary requests have even IDs, while interrupts IDs are odd */ +#define FUSE_INT_REQ_BIT (1ULL << 0) +#define FUSE_REQ_ID_STEP (1ULL << 1) + +struct fuse_arg; +struct fuse_args; +struct fuse_pqueue; +struct fuse_req; +struct fuse_iqueue; +struct fuse_forget_link; + +struct fuse_copy_state { + int write; + struct fuse_req *req; + struct iov_iter *iter; + struct pipe_buffer *pipebufs; + struct pipe_buffer *currbuf; + struct pipe_inode_info *pipe; + unsigned long nr_segs; + struct page *pg; + unsigned int len; + unsigned int offset; + unsigned int move_pages:1; + unsigned int is_uring:1; + struct { + unsigned int copied_sz; /* copied size into the user buffer */ + } ring; +}; + +static inline struct fuse_dev *fuse_get_dev(struct file *file) +{ + /* + * Lockless access is OK, because file->private data is set + * once during mount and is valid until the file is released. + */ + return READ_ONCE(file->private_data); +} + +unsigned int fuse_req_hash(u64 unique); +struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique); + +void fuse_dev_end_requests(struct list_head *head); + +void fuse_copy_init(struct fuse_copy_state *cs, int write, + struct iov_iter *iter); +int fuse_copy_args(struct fuse_copy_state *cs, unsigned int numargs, + unsigned int argpages, struct fuse_arg *args, + int zeroing); +int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, + unsigned int nbytes); +void fuse_dev_queue_forget(struct fuse_iqueue *fiq, + struct fuse_forget_link *forget); +void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req); + +#endif + diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 74744c6f2860..fee96fe7887b 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -310,7 +310,7 @@ struct fuse_args { bool is_ext:1; bool is_pinned:1; bool invalidate_vmap:1; - struct fuse_in_arg in_args[3]; + struct fuse_in_arg in_args[4]; struct fuse_arg out_args[2]; void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error); /* Used for kvec iter backed by vmalloc address */ @@ -438,6 +438,10 @@ struct fuse_req { /** fuse_mount this request belongs to */ struct fuse_mount *fm; + +#ifdef CONFIG_FUSE_IO_URING + void *ring_entry; +#endif }; struct fuse_iqueue; @@ -863,6 +867,9 @@ struct fuse_conn { /* Use pages instead of pointer for kernel I/O */ unsigned int use_pages_for_kvec_io:1; + /* Use io_uring for communication */ + unsigned int io_uring; + /** Maximum stack depth for passthrough backing files */ int max_stack_depth; @@ -923,6 +930,11 @@ struct fuse_conn { /** IDR for backing files ids */ struct idr backing_files_map; #endif + +#ifdef CONFIG_FUSE_IO_URING + /** uring connection information*/ + struct fuse_ring *ring; +#endif }; /* @@ -947,6 +959,19 @@ struct fuse_mount { struct rcu_head rcu; }; +/* + * Empty header for FUSE opcodes without specific header needs. + * Used as a placeholder in args->in_args[0] for consistency + * across all FUSE operations, simplifying request handling. + */ +struct fuse_zero_header {}; + +static inline void fuse_set_zero_arg0(struct fuse_args *args) +{ + args->in_args[0].size = sizeof(struct fuse_zero_header); + args->in_args[0].value = NULL; +} + static inline struct fuse_mount *get_fuse_mount_super(struct super_block *sb) { return sb->s_fs_info; @@ -1220,6 +1245,11 @@ void fuse_change_entry_timeout(struct dentry *entry, struct fuse_entry_out *o); struct fuse_conn *fuse_conn_get(struct fuse_conn *fc); /** + * Initialize the fuse processing queue + */ +void fuse_pqueue_init(struct fuse_pqueue *fpq); + +/** * Initialize fuse_conn */ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm, diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 3ce4f4e81d09..e9db2cb8c150 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -7,6 +7,7 @@ */ #include "fuse_i.h" +#include "dev_uring_i.h" #include <linux/pagemap.h> #include <linux/slab.h> @@ -937,7 +938,7 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq, fiq->priv = priv; } -static void fuse_pqueue_init(struct fuse_pqueue *fpq) +void fuse_pqueue_init(struct fuse_pqueue *fpq) { unsigned int i; @@ -992,6 +993,8 @@ static void delayed_release(struct rcu_head *p) { struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu); + fuse_uring_destruct(fc); + put_user_ns(fc->user_ns); fc->release(fc); } @@ -1387,6 +1390,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, else ok = false; } + if (flags & FUSE_OVER_IO_URING && fuse_uring_enabled()) + fc->io_uring = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1446,6 +1451,13 @@ void fuse_send_init(struct fuse_mount *fm) if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) flags |= FUSE_PASSTHROUGH; + /* + * This is just an information flag for fuse server. No need to check + * the reply - server is either sending IORING_OP_URING_CMD or not. + */ + if (fuse_uring_enabled()) + flags |= FUSE_OVER_IO_URING; + ia->in.flags = flags; ia->in.flags2 = flags >> 32; diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 9f568d345c51..93dfb06b6cea 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -164,9 +164,10 @@ int fuse_removexattr(struct inode *inode, const char *name) args.opcode = FUSE_REMOVEXATTR; args.nodeid = get_node_id(inode); - args.in_numargs = 1; - args.in_args[0].size = strlen(name) + 1; - args.in_args[0].value = name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = strlen(name) + 1; + args.in_args[1].value = name; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fm->fc->no_removexattr = 1; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 0eb20012792f..d3f76101ad4b 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -170,7 +170,8 @@ config ROOT_NFS config NFS_FSCACHE bool "Provide NFS client caching support" - depends on NFS_FS=m && NETFS_SUPPORT || NFS_FS=y && NETFS_SUPPORT=y + depends on NFS_FS + select NETFS_SUPPORT select FSCACHE help Say Y here if you want NFS data to be cached locally on disc through diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 7832fb0369a1..8397c43358bd 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -718,7 +718,7 @@ __be32 nfs4_callback_offload(void *data, void *dummy, copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL); if (!copy) - return htonl(NFS4ERR_SERVERFAULT); + return cpu_to_be32(NFS4ERR_DELAY); spin_lock(&cps->clp->cl_lock); rcu_read_lock(); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 550ca934c9cf..3b0918ade53c 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -38,7 +38,7 @@ #include <linux/sunrpc/bc_xprt.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> - +#include <linux/nfslocalio.h> #include "nfs4_fs.h" #include "callback.h" @@ -186,7 +186,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) seqlock_init(&clp->cl_boot_lock); ktime_get_real_ts64(&clp->cl_nfssvc_boot); nfs_uuid_init(&clp->cl_uuid); - spin_lock_init(&clp->cl_localio_lock); + INIT_WORK(&clp->cl_local_probe_work, nfs_local_probe_async_work); #endif /* CONFIG_NFS_LOCALIO */ clp->cl_principal = "*"; @@ -244,7 +244,7 @@ static void pnfs_init_server(struct nfs_server *server) */ void nfs_free_client(struct nfs_client *clp) { - nfs_local_disable(clp); + nfs_localio_disable_client(clp); /* -EIO all pending I/O */ if (!IS_ERR(clp->cl_rpcclient)) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b08dbe96bc57..f45beea92d03 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -303,6 +303,7 @@ static void nfs_read_sync_pgio_error(struct list_head *head, int error) static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr) { get_dreq(hdr->dreq); + set_bit(NFS_IOHDR_ODIRECT, &hdr->flags); } static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index f78115c6c2c1..98b45b636be3 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -164,18 +164,17 @@ decode_name(struct xdr_stream *xdr, u32 *id) } static struct nfsd_file * -ff_local_open_fh(struct nfs_client *clp, const struct cred *cred, +ff_local_open_fh(struct pnfs_layout_segment *lseg, u32 ds_idx, + struct nfs_client *clp, const struct cred *cred, struct nfs_fh *fh, fmode_t mode) { - if (mode & FMODE_WRITE) { - /* - * Always request read and write access since this corresponds - * to a rw layout. - */ - mode |= FMODE_READ; - } +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); - return nfs_local_open_fh(clp, cred, fh, mode); + return nfs_local_open_fh(clp, cred, fh, &mirror->nfl, mode); +#else + return NULL; +#endif } static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1, @@ -247,6 +246,7 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags) spin_lock_init(&mirror->lock); refcount_set(&mirror->ref, 1); INIT_LIST_HEAD(&mirror->mirrors); + nfs_localio_file_init(&mirror->nfl); } return mirror; } @@ -257,6 +257,7 @@ static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror) ff_layout_remove_mirror(mirror); kfree(mirror->fh_versions); + nfs_close_local_fh(&mirror->nfl); cred = rcu_access_pointer(mirror->ro_cred); put_cred(cred); cred = rcu_access_pointer(mirror->rw_cred); @@ -847,6 +848,9 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs4_pnfs_ds *ds; u32 ds_idx; + if (NFS_SERVER(pgio->pg_inode)->flags & + (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) + pgio->pg_maxretrans = io_maxretrans; retry: pnfs_generic_pg_check_layout(pgio, req); /* Use full layout for now */ @@ -860,6 +864,8 @@ retry: if (!pgio->pg_lseg) goto out_nolseg; } + /* Reset wb_nio, since getting layout segment was successful */ + req->wb_nio = 0; ds = ff_layout_get_ds_for_read(pgio, &ds_idx); if (!ds) { @@ -876,14 +882,24 @@ retry: pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; pgio->pg_mirror_idx = ds_idx; - - if (NFS_SERVER(pgio->pg_inode)->flags & - (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) - pgio->pg_maxretrans = io_maxretrans; return; out_nolseg: - if (pgio->pg_error < 0) - return; + if (pgio->pg_error < 0) { + if (pgio->pg_error != -EAGAIN) + return; + /* Retry getting layout segment if lower layer returned -EAGAIN */ + if (pgio->pg_maxretrans && req->wb_nio++ > pgio->pg_maxretrans) { + if (NFS_SERVER(pgio->pg_inode)->flags & NFS_MOUNT_SOFTERR) + pgio->pg_error = -ETIMEDOUT; + else + pgio->pg_error = -EIO; + return; + } + pgio->pg_error = 0; + /* Sleep for 1 second before retrying */ + ssleep(1); + goto retry; + } out_mds: trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode, 0, NFS4_MAX_UINT64, IOMODE_READ, @@ -1820,7 +1836,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) hdr->mds_offset = offset; /* Start IO accounting for local read */ - localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, FMODE_READ); + localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ); if (localio) { hdr->task.tk_start = ktime_get(); ff_layout_read_record_layoutstats_start(&hdr->task, hdr); @@ -1896,7 +1912,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) hdr->args.offset = offset; /* Start IO accounting for local write */ - localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, + localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ|FMODE_WRITE); if (localio) { hdr->task.tk_start = ktime_get(); @@ -1981,7 +1997,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) data->args.fh = fh; /* Start IO accounting for local commit */ - localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, + localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ|FMODE_WRITE); if (localio) { data->task.tk_start = ktime_get(); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index f84b3fb0dddd..095df09017a5 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -83,6 +83,7 @@ struct nfs4_ff_layout_mirror { nfs4_stateid stateid; const struct cred __rcu *ro_cred; const struct cred __rcu *rw_cred; + struct nfs_file_localio nfl; refcount_t ref; spinlock_t lock; unsigned long flags; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 596f35170137..1aa67fca69b2 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1137,6 +1137,8 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); ctx->mdsthreshold = NULL; + nfs_localio_file_init(&ctx->nfl); + return ctx; } EXPORT_SYMBOL_GPL(alloc_nfs_open_context); @@ -1168,6 +1170,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) nfs_sb_deactive(sb); put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1)); kfree(ctx->mdsthreshold); + nfs_close_local_fh(&ctx->nfl); kfree_rcu(ctx, rcu_head); } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index e564bd11ba60..fae2c7ae4acc 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -455,11 +455,13 @@ extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* localio.c */ -extern void nfs_local_disable(struct nfs_client *); extern void nfs_local_probe(struct nfs_client *); +extern void nfs_local_probe_async(struct nfs_client *); +extern void nfs_local_probe_async_work(struct work_struct *); extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *, const struct cred *, struct nfs_fh *, + struct nfs_file_localio *, const fmode_t); extern int nfs_local_doio(struct nfs_client *, struct nfsd_file *, @@ -471,11 +473,12 @@ extern int nfs_local_commit(struct nfsd_file *, extern bool nfs_server_is_local(const struct nfs_client *clp); #else /* CONFIG_NFS_LOCALIO */ -static inline void nfs_local_disable(struct nfs_client *clp) {} static inline void nfs_local_probe(struct nfs_client *clp) {} +static inline void nfs_local_probe_async(struct nfs_client *clp) {} static inline struct nfsd_file * nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, - struct nfs_fh *fh, const fmode_t mode) + struct nfs_fh *fh, struct nfs_file_localio *nfl, + const fmode_t mode) { return NULL; } diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index 4b8618cf114c..5c21caeae075 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -35,6 +35,7 @@ struct nfs_local_kiocb { struct bio_vec *bvec; struct nfs_pgio_header *hdr; struct work_struct work; + void (*aio_complete_work)(struct work_struct *); struct nfsd_file *localio; }; @@ -48,9 +49,14 @@ struct nfs_local_fsync_ctx { static bool localio_enabled __read_mostly = true; module_param(localio_enabled, bool, 0644); +static bool localio_O_DIRECT_semantics __read_mostly = false; +module_param(localio_O_DIRECT_semantics, bool, 0644); +MODULE_PARM_DESC(localio_O_DIRECT_semantics, + "LOCALIO will use O_DIRECT semantics to filesystem."); + static inline bool nfs_client_is_local(const struct nfs_client *clp) { - return !!test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags); + return !!rcu_access_pointer(clp->cl_uuid.net); } bool nfs_server_is_local(const struct nfs_client *clp) @@ -116,30 +122,6 @@ const struct rpc_program nfslocalio_program = { }; /* - * nfs_local_enable - enable local i/o for an nfs_client - */ -static void nfs_local_enable(struct nfs_client *clp) -{ - spin_lock(&clp->cl_localio_lock); - set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags); - trace_nfs_local_enable(clp); - spin_unlock(&clp->cl_localio_lock); -} - -/* - * nfs_local_disable - disable local i/o for an nfs_client - */ -void nfs_local_disable(struct nfs_client *clp) -{ - spin_lock(&clp->cl_localio_lock); - if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) { - trace_nfs_local_disable(clp); - nfs_uuid_invalidate_one_client(&clp->cl_uuid); - } - spin_unlock(&clp->cl_localio_lock); -} - -/* * nfs_init_localioclient - Initialise an NFS localio client connection */ static struct rpc_clnt *nfs_init_localioclient(struct nfs_client *clp) @@ -178,7 +160,7 @@ static bool nfs_server_uuid_is_local(struct nfs_client *clp) rpc_shutdown_client(rpcclient_localio); /* Server is only local if it initialized required struct members */ - if (status || !clp->cl_uuid.net || !clp->cl_uuid.dom) + if (status || !rcu_access_pointer(clp->cl_uuid.net) || !clp->cl_uuid.dom) return false; return true; @@ -194,44 +176,64 @@ void nfs_local_probe(struct nfs_client *clp) /* Disallow localio if disabled via sysfs or AUTH_SYS isn't used */ if (!localio_enabled || clp->cl_rpcclient->cl_auth->au_flavor != RPC_AUTH_UNIX) { - nfs_local_disable(clp); + nfs_localio_disable_client(clp); return; } if (nfs_client_is_local(clp)) { /* If already enabled, disable and re-enable */ - nfs_local_disable(clp); + nfs_localio_disable_client(clp); } if (!nfs_uuid_begin(&clp->cl_uuid)) return; if (nfs_server_uuid_is_local(clp)) - nfs_local_enable(clp); + nfs_localio_enable_client(clp); nfs_uuid_end(&clp->cl_uuid); } EXPORT_SYMBOL_GPL(nfs_local_probe); +void nfs_local_probe_async_work(struct work_struct *work) +{ + struct nfs_client *clp = + container_of(work, struct nfs_client, cl_local_probe_work); + + nfs_local_probe(clp); +} + +void nfs_local_probe_async(struct nfs_client *clp) +{ + queue_work(nfsiod_workqueue, &clp->cl_local_probe_work); +} +EXPORT_SYMBOL_GPL(nfs_local_probe_async); + +static inline struct nfsd_file *nfs_local_file_get(struct nfsd_file *nf) +{ + return nfs_to->nfsd_file_get(nf); +} + +static inline void nfs_local_file_put(struct nfsd_file *nf) +{ + nfs_to->nfsd_file_put(nf); +} + /* - * nfs_local_open_fh - open a local filehandle in terms of nfsd_file + * __nfs_local_open_fh - open a local filehandle in terms of nfsd_file. * - * Returns a pointer to a struct nfsd_file or NULL + * Returns a pointer to a struct nfsd_file or ERR_PTR. + * Caller must release returned nfsd_file with nfs_to_nfsd_file_put_local(). */ -struct nfsd_file * -nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, - struct nfs_fh *fh, const fmode_t mode) +static struct nfsd_file * +__nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, struct nfs_file_localio *nfl, + const fmode_t mode) { struct nfsd_file *localio; - int status; - - if (!nfs_server_is_local(clp)) - return NULL; - if (mode & ~(FMODE_READ | FMODE_WRITE)) - return NULL; localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient, - cred, fh, mode); + cred, fh, nfl, mode); if (IS_ERR(localio)) { - status = PTR_ERR(localio); + int status = PTR_ERR(localio); trace_nfs_local_open_fh(fh, mode, status); switch (status) { case -ENOMEM: @@ -240,10 +242,59 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, /* Revalidate localio, will disable if unsupported */ nfs_local_probe(clp); } - return NULL; } return localio; } + +/* + * nfs_local_open_fh - open a local filehandle in terms of nfsd_file. + * First checking if the open nfsd_file is already cached, otherwise + * must __nfs_local_open_fh and insert the nfsd_file in nfs_file_localio. + * + * Returns a pointer to a struct nfsd_file or NULL. + */ +struct nfsd_file * +nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, struct nfs_file_localio *nfl, + const fmode_t mode) +{ + struct nfsd_file *nf, *new, __rcu **pnf; + + if (!nfs_server_is_local(clp)) + return NULL; + if (mode & ~(FMODE_READ | FMODE_WRITE)) + return NULL; + + if (mode & FMODE_WRITE) + pnf = &nfl->rw_file; + else + pnf = &nfl->ro_file; + + new = NULL; + rcu_read_lock(); + nf = rcu_dereference(*pnf); + if (!nf) { + rcu_read_unlock(); + new = __nfs_local_open_fh(clp, cred, fh, nfl, mode); + if (IS_ERR(new)) + return NULL; + /* try to swap in the pointer */ + spin_lock(&clp->cl_uuid.lock); + nf = rcu_dereference_protected(*pnf, 1); + if (!nf) { + nf = new; + new = NULL; + rcu_assign_pointer(*pnf, nf); + } + spin_unlock(&clp->cl_uuid.lock); + rcu_read_lock(); + } + nf = nfs_local_file_get(nf); + rcu_read_unlock(); + if (new) + nfs_to_nfsd_file_put_local(new); + return nf; +} EXPORT_SYMBOL_GPL(nfs_local_open_fh); static struct bio_vec * @@ -285,10 +336,19 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, kfree(iocb); return NULL; } - init_sync_kiocb(&iocb->kiocb, file); + + if (localio_O_DIRECT_semantics && + test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) { + iocb->kiocb.ki_filp = file; + iocb->kiocb.ki_flags = IOCB_DIRECT; + } else + init_sync_kiocb(&iocb->kiocb, file); + iocb->kiocb.ki_pos = hdr->args.offset; iocb->hdr = hdr; iocb->kiocb.ki_flags &= ~IOCB_APPEND; + iocb->aio_complete_work = NULL; + return iocb; } @@ -328,7 +388,7 @@ nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status) hdr->res.op_status = NFS4_OK; hdr->task.tk_status = 0; } else { - hdr->res.op_status = nfs4_stat_to_errno(status); + hdr->res.op_status = nfs_localio_errno_to_nfs4_stat(status); hdr->task.tk_status = status; } } @@ -338,11 +398,23 @@ nfs_local_pgio_release(struct nfs_local_kiocb *iocb) { struct nfs_pgio_header *hdr = iocb->hdr; - nfs_to_nfsd_file_put_local(iocb->localio); + nfs_local_file_put(iocb->localio); nfs_local_iocb_free(iocb); nfs_local_hdr_release(hdr, hdr->task.tk_ops); } +/* + * Complete the I/O from iocb->kiocb.ki_complete() + * + * Note that this function can be called from a bottom half context, + * hence we need to queue the rpc_call_done() etc to a workqueue + */ +static inline void nfs_local_pgio_aio_complete(struct nfs_local_kiocb *iocb) +{ + INIT_WORK(&iocb->work, iocb->aio_complete_work); + queue_work(nfsiod_workqueue, &iocb->work); +} + static void nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) { @@ -365,6 +437,23 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) status > 0 ? status : 0, hdr->res.eof); } +static void nfs_local_read_aio_complete_work(struct work_struct *work) +{ + struct nfs_local_kiocb *iocb = + container_of(work, struct nfs_local_kiocb, work); + + nfs_local_pgio_release(iocb); +} + +static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret) +{ + struct nfs_local_kiocb *iocb = + container_of(kiocb, struct nfs_local_kiocb, kiocb); + + nfs_local_read_done(iocb, ret); + nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */ +} + static void nfs_local_call_read(struct work_struct *work) { struct nfs_local_kiocb *iocb = @@ -379,10 +468,10 @@ static void nfs_local_call_read(struct work_struct *work) nfs_local_iter_init(&iter, iocb, READ); status = filp->f_op->read_iter(&iocb->kiocb, &iter); - WARN_ON_ONCE(status == -EIOCBQUEUED); - - nfs_local_read_done(iocb, status); - nfs_local_pgio_release(iocb); + if (status != -EIOCBQUEUED) { + nfs_local_read_done(iocb, status); + nfs_local_pgio_release(iocb); + } revert_creds(save_cred); } @@ -410,6 +499,11 @@ nfs_do_local_read(struct nfs_pgio_header *hdr, nfs_local_pgio_init(hdr, call_ops); hdr->res.eof = false; + if (iocb->kiocb.ki_flags & IOCB_DIRECT) { + iocb->kiocb.ki_complete = nfs_local_read_aio_complete; + iocb->aio_complete_work = nfs_local_read_aio_complete_work; + } + INIT_WORK(&iocb->work, nfs_local_call_read); queue_work(nfslocaliod_workqueue, &iocb->work); @@ -534,6 +628,24 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status) nfs_local_pgio_done(hdr, status); } +static void nfs_local_write_aio_complete_work(struct work_struct *work) +{ + struct nfs_local_kiocb *iocb = + container_of(work, struct nfs_local_kiocb, work); + + nfs_local_vfs_getattr(iocb); + nfs_local_pgio_release(iocb); +} + +static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret) +{ + struct nfs_local_kiocb *iocb = + container_of(kiocb, struct nfs_local_kiocb, kiocb); + + nfs_local_write_done(iocb, ret); + nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */ +} + static void nfs_local_call_write(struct work_struct *work) { struct nfs_local_kiocb *iocb = @@ -552,11 +664,11 @@ static void nfs_local_call_write(struct work_struct *work) file_start_write(filp); status = filp->f_op->write_iter(&iocb->kiocb, &iter); file_end_write(filp); - WARN_ON_ONCE(status == -EIOCBQUEUED); - - nfs_local_write_done(iocb, status); - nfs_local_vfs_getattr(iocb); - nfs_local_pgio_release(iocb); + if (status != -EIOCBQUEUED) { + nfs_local_write_done(iocb, status); + nfs_local_vfs_getattr(iocb); + nfs_local_pgio_release(iocb); + } revert_creds(save_cred); current->flags = old_flags; @@ -592,10 +704,16 @@ nfs_do_local_write(struct nfs_pgio_header *hdr, case NFS_FILE_SYNC: iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC; } + nfs_local_pgio_init(hdr, call_ops); nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable); + if (iocb->kiocb.ki_flags & IOCB_DIRECT) { + iocb->kiocb.ki_complete = nfs_local_write_aio_complete; + iocb->aio_complete_work = nfs_local_write_aio_complete_work; + } + INIT_WORK(&iocb->work, nfs_local_call_write); queue_work(nfslocaliod_workqueue, &iocb->work); @@ -626,8 +744,8 @@ int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio, if (status != 0) { if (status == -EAGAIN) - nfs_local_disable(clp); - nfs_to_nfsd_file_put_local(localio); + nfs_localio_disable_client(clp); + nfs_local_file_put(localio); hdr->task.tk_status = status; nfs_local_hdr_release(hdr, call_ops); } @@ -668,7 +786,7 @@ nfs_local_commit_done(struct nfs_commit_data *data, int status) data->task.tk_status = 0; } else { nfs_reset_boot_verifier(data->inode); - data->res.op_status = nfs4_stat_to_errno(status); + data->res.op_status = nfs_localio_errno_to_nfs4_stat(status); data->task.tk_status = status; } } @@ -678,7 +796,7 @@ nfs_local_release_commit_data(struct nfsd_file *localio, struct nfs_commit_data *data, const struct rpc_call_ops *call_ops) { - nfs_to_nfsd_file_put_local(localio); + nfs_local_file_put(localio); call_ops->rpc_call_done(&data->task, data); call_ops->rpc_release(data); } diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 1566163c6d85..7359e1a3bd84 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -844,6 +844,41 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, return status; } +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + +static unsigned nfs3_localio_probe_throttle __read_mostly = 0; +module_param(nfs3_localio_probe_throttle, uint, 0644); +MODULE_PARM_DESC(nfs3_localio_probe_throttle, + "Probe for NFSv3 LOCALIO every N IO requests. Must be power-of-2, defaults to 0 (probing disabled)."); + +static void nfs3_localio_probe(struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + + /* Throttled to reduce nfs_local_probe_async() frequency */ + if (!nfs3_localio_probe_throttle || nfs_server_is_local(clp)) + return; + + /* + * Try (re)enabling LOCALIO if isn't enabled -- admin deems + * it worthwhile to periodically check if LOCALIO possible by + * setting the 'nfs3_localio_probe_throttle' module parameter. + * + * This is useful if LOCALIO was previously enabled, but was + * disabled due to server restart, and IO has successfully + * completed in terms of normal RPC. + */ + if ((clp->cl_uuid.nfs3_localio_probe_count++ & + (nfs3_localio_probe_throttle - 1)) == 0) { + if (!nfs_server_is_local(clp)) + nfs_local_probe_async(clp); + } +} + +#else +static void nfs3_localio_probe(struct nfs_server *server) {} +#endif + static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { struct inode *inode = hdr->inode; @@ -855,8 +890,11 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; - if (task->tk_status >= 0 && !server->read_hdrsize) - cmpxchg(&server->read_hdrsize, 0, hdr->res.replen); + if (task->tk_status >= 0) { + if (!server->read_hdrsize) + cmpxchg(&server->read_hdrsize, 0, hdr->res.replen); + nfs3_localio_probe(server); + } nfs_invalidate_atime(inode); nfs_refresh_inode(inode, &hdr->fattr); @@ -886,8 +924,10 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr) if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; - if (task->tk_status >= 0) + if (task->tk_status >= 0) { nfs_writeback_update_inode(hdr); + nfs3_localio_probe(NFS_SERVER(inode)); + } return 0; } diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 531c9c20ef1d..1924c4a2077b 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -498,15 +498,15 @@ out_put_src_lock: return err; } -struct nfs42_offloadcancel_data { +struct nfs42_offload_data { struct nfs_server *seq_server; struct nfs42_offload_status_args args; struct nfs42_offload_status_res res; }; -static void nfs42_offload_cancel_prepare(struct rpc_task *task, void *calldata) +static void nfs42_offload_prepare(struct rpc_task *task, void *calldata) { - struct nfs42_offloadcancel_data *data = calldata; + struct nfs42_offload_data *data = calldata; nfs4_setup_sequence(data->seq_server->nfs_client, &data->args.osa_seq_args, @@ -515,7 +515,7 @@ static void nfs42_offload_cancel_prepare(struct rpc_task *task, void *calldata) static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata) { - struct nfs42_offloadcancel_data *data = calldata; + struct nfs42_offload_data *data = calldata; trace_nfs4_offload_cancel(&data->args, task->tk_status); nfs41_sequence_done(task, &data->res.osr_seq_res); @@ -525,22 +525,22 @@ static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata) rpc_restart_call_prepare(task); } -static void nfs42_free_offloadcancel_data(void *data) +static void nfs42_offload_release(void *data) { kfree(data); } static const struct rpc_call_ops nfs42_offload_cancel_ops = { - .rpc_call_prepare = nfs42_offload_cancel_prepare, + .rpc_call_prepare = nfs42_offload_prepare, .rpc_call_done = nfs42_offload_cancel_done, - .rpc_release = nfs42_free_offloadcancel_data, + .rpc_release = nfs42_offload_release, }; static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *stateid) { struct nfs_server *dst_server = NFS_SERVER(file_inode(dst)); - struct nfs42_offloadcancel_data *data = NULL; + struct nfs42_offload_data *data = NULL; struct nfs_open_context *ctx = nfs_file_open_context(dst); struct rpc_task *task; struct rpc_message msg = { @@ -552,14 +552,14 @@ static int nfs42_do_offload_cancel_async(struct file *dst, .rpc_message = &msg, .callback_ops = &nfs42_offload_cancel_ops, .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE, }; int status; if (!(dst_server->caps & NFS_CAP_OFFLOAD_CANCEL)) return -EOPNOTSUPP; - data = kzalloc(sizeof(struct nfs42_offloadcancel_data), GFP_KERNEL); + data = kzalloc(sizeof(struct nfs42_offload_data), GFP_KERNEL); if (data == NULL) return -ENOMEM; @@ -861,7 +861,7 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, .rpc_message = &msg, .callback_ops = &nfs42_layoutstat_ops, .callback_data = data, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE, }; struct rpc_task *task; @@ -1016,7 +1016,7 @@ int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg, struct rpc_task_setup task_setup = { .rpc_message = &msg, .callback_ops = &nfs42_layouterror_ops, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE, }; unsigned int i; diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 9e3ae53e2205..5072d7ea72e9 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -144,9 +144,11 @@ decode_putfh_maxsz + \ decode_offload_cancel_maxsz) #define NFS4_enc_copy_notify_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_copy_notify_maxsz) #define NFS4_dec_copy_notify_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_copy_notify_maxsz) #define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \ @@ -549,7 +551,7 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req, } /* - * Encode OFFLOAD_CANEL request + * Encode OFFLOAD_CANCEL request */ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req, struct xdr_stream *xdr, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 9a9f60a2291b..542cdf71229f 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1955,6 +1955,7 @@ restart: } rcu_read_unlock(); nfs4_free_state_owners(&freeme); + nfs_local_probe_async(clp); if (lost_locks) pr_warn("NFS: %s: lost %d locks\n", clp->cl_hostname, lost_locks); diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 1eab98c277fa..7a058bd8c566 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1714,38 +1714,6 @@ TRACE_EVENT(nfs_local_open_fh, ) ); -DECLARE_EVENT_CLASS(nfs_local_client_event, - TP_PROTO( - const struct nfs_client *clp - ), - - TP_ARGS(clp), - - TP_STRUCT__entry( - __field(unsigned int, protocol) - __string(server, clp->cl_hostname) - ), - - TP_fast_assign( - __entry->protocol = clp->rpc_ops->version; - __assign_str(server); - ), - - TP_printk( - "server=%s NFSv%u", __get_str(server), __entry->protocol - ) -); - -#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \ - DEFINE_EVENT(nfs_local_client_event, name, \ - TP_PROTO( \ - const struct nfs_client *clp \ - ), \ - TP_ARGS(clp)) - -DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_enable); -DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_disable); - DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index e27c07bd8929..11968dcb7243 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -961,8 +961,9 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) struct nfs_client *clp = NFS_SERVER(hdr->inode)->nfs_client; struct nfsd_file *localio = - nfs_local_open_fh(clp, hdr->cred, - hdr->args.fh, hdr->args.context->mode); + nfs_local_open_fh(clp, hdr->cred, hdr->args.fh, + &hdr->args.context->nfl, + hdr->args.context->mode); if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion) task_flags = RPC_TASK_MOVEABLE; diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index bf378ecd5d9f..7b59a40d40c0 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -280,9 +280,9 @@ void nfs_sysfs_link_rpc_client(struct nfs_server *server, char name[RPC_CLIENT_NAME_SIZE]; int ret; - strcpy(name, clnt->cl_program->name); - strcat(name, uniq ? uniq : ""); - strcat(name, "_client"); + strscpy(name, clnt->cl_program->name, sizeof(name)); + strncat(name, uniq ? uniq : "", sizeof(name) - strlen(name) - 1); + strncat(name, "_client", sizeof(name) - strlen(name) - 1); ret = sysfs_create_link_nowarn(&server->kobj, &clnt->cl_sysfs->kobject, name); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 50fa539611f5..aa3d8bea3ec0 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1826,7 +1826,8 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, task_flags = RPC_TASK_MOVEABLE; localio = nfs_local_open_fh(NFS_SERVER(inode)->nfs_client, data->cred, - data->args.fh, data->context->mode); + data->args.fh, &data->context->nfl, + data->context->mode); return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), data->mds_ops, how, RPC_TASK_CRED_NOREF | task_flags, localio); diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile index a5e54809701e..c10ead273ff2 100644 --- a/fs/nfs_common/Makefile +++ b/fs/nfs_common/Makefile @@ -6,8 +6,9 @@ obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o nfs_acl-objs := nfsacl.o +CFLAGS_localio_trace.o += -I$(src) obj-$(CONFIG_NFS_COMMON_LOCALIO_SUPPORT) += nfs_localio.o -nfs_localio-objs := nfslocalio.o +nfs_localio-objs := nfslocalio.o localio_trace.o obj-$(CONFIG_GRACE_PERIOD) += grace.o obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c index 34a115176f97..af09aed09fd2 100644 --- a/fs/nfs_common/common.c +++ b/fs/nfs_common/common.c @@ -15,7 +15,7 @@ static const struct { { NFS_OK, 0 }, { NFSERR_PERM, -EPERM }, { NFSERR_NOENT, -ENOENT }, - { NFSERR_IO, -errno_NFSERR_IO}, + { NFSERR_IO, -EIO }, { NFSERR_NXIO, -ENXIO }, /* { NFSERR_EAGAIN, -EAGAIN }, */ { NFSERR_ACCES, -EACCES }, @@ -45,7 +45,6 @@ static const struct { { NFSERR_SERVERFAULT, -EREMOTEIO }, { NFSERR_BADTYPE, -EBADTYPE }, { NFSERR_JUKEBOX, -EJUKEBOX }, - { -1, -EIO } }; /** @@ -59,26 +58,29 @@ int nfs_stat_to_errno(enum nfs_stat status) { int i; - for (i = 0; nfs_errtbl[i].stat != -1; i++) { + for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { if (nfs_errtbl[i].stat == (int)status) return nfs_errtbl[i].errno; } - return nfs_errtbl[i].errno; + return -EIO; } EXPORT_SYMBOL_GPL(nfs_stat_to_errno); /* * We need to translate between nfs v4 status return values and * the local errno values which may not be the same. + * + * nfs4_errtbl_common[] is used before more specialized mappings + * available in nfs4_errtbl[] or nfs4_errtbl_localio[]. */ static const struct { int stat; int errno; -} nfs4_errtbl[] = { +} nfs4_errtbl_common[] = { { NFS4_OK, 0 }, { NFS4ERR_PERM, -EPERM }, { NFS4ERR_NOENT, -ENOENT }, - { NFS4ERR_IO, -errno_NFSERR_IO}, + { NFS4ERR_IO, -EIO }, { NFS4ERR_NXIO, -ENXIO }, { NFS4ERR_ACCESS, -EACCES }, { NFS4ERR_EXIST, -EEXIST }, @@ -98,15 +100,20 @@ static const struct { { NFS4ERR_BAD_COOKIE, -EBADCOOKIE }, { NFS4ERR_NOTSUPP, -ENOTSUPP }, { NFS4ERR_TOOSMALL, -ETOOSMALL }, - { NFS4ERR_SERVERFAULT, -EREMOTEIO }, { NFS4ERR_BADTYPE, -EBADTYPE }, - { NFS4ERR_LOCKED, -EAGAIN }, { NFS4ERR_SYMLINK, -ELOOP }, - { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, { NFS4ERR_DEADLOCK, -EDEADLK }, +}; + +static const struct { + int stat; + int errno; +} nfs4_errtbl[] = { + { NFS4ERR_SERVERFAULT, -EREMOTEIO }, + { NFS4ERR_LOCKED, -EAGAIN }, + { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, { NFS4ERR_NOXATTR, -ENODATA }, { NFS4ERR_XATTR2BIG, -E2BIG }, - { -1, -EIO } }; /* @@ -116,7 +123,14 @@ static const struct { int nfs4_stat_to_errno(int stat) { int i; - for (i = 0; nfs4_errtbl[i].stat != -1; i++) { + + /* First check nfs4_errtbl_common */ + for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_common); i++) { + if (nfs4_errtbl_common[i].stat == stat) + return nfs4_errtbl_common[i].errno; + } + /* Then check nfs4_errtbl */ + for (i = 0; i < ARRAY_SIZE(nfs4_errtbl); i++) { if (nfs4_errtbl[i].stat == stat) return nfs4_errtbl[i].errno; } @@ -132,3 +146,56 @@ int nfs4_stat_to_errno(int stat) return -stat; } EXPORT_SYMBOL_GPL(nfs4_stat_to_errno); + +/* + * This table is useful for conversion from local errno to NFS error. + * It provides more logically correct mappings for use with LOCALIO + * (which is focused on converting from errno to NFS status). + */ +static const struct { + int stat; + int errno; +} nfs4_errtbl_localio[] = { + /* Map errors differently than nfs4_errtbl */ + { NFS4ERR_IO, -EREMOTEIO }, + { NFS4ERR_DELAY, -EAGAIN }, + { NFS4ERR_FBIG, -E2BIG }, + /* Map errors not handled by nfs4_errtbl */ + { NFS4ERR_STALE, -EBADF }, + { NFS4ERR_STALE, -EOPENSTALE }, + { NFS4ERR_DELAY, -ETIMEDOUT }, + { NFS4ERR_DELAY, -ERESTARTSYS }, + { NFS4ERR_DELAY, -ENOMEM }, + { NFS4ERR_IO, -ETXTBSY }, + { NFS4ERR_IO, -EBUSY }, + { NFS4ERR_SERVERFAULT, -ESERVERFAULT }, + { NFS4ERR_SERVERFAULT, -ENFILE }, + { NFS4ERR_IO, -EUCLEAN }, + { NFS4ERR_PERM, -ENOKEY }, +}; + +/* + * Convert an errno to an NFS error code for LOCALIO. + */ +__u32 nfs_localio_errno_to_nfs4_stat(int errno) +{ + int i; + + /* First check nfs4_errtbl_common */ + for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_common); i++) { + if (nfs4_errtbl_common[i].errno == errno) + return nfs4_errtbl_common[i].stat; + } + /* Then check nfs4_errtbl_localio */ + for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_localio); i++) { + if (nfs4_errtbl_localio[i].errno == errno) + return nfs4_errtbl_localio[i].stat; + } + /* If we cannot translate the error, the recovery routines should + * handle it. + * Note: remaining NFSv4 error codes have values > 10000, so should + * not conflict with native Linux error codes. + */ + return NFS4ERR_SERVERFAULT; +} +EXPORT_SYMBOL_GPL(nfs_localio_errno_to_nfs4_stat); diff --git a/fs/nfs_common/localio_trace.c b/fs/nfs_common/localio_trace.c new file mode 100644 index 000000000000..7decfe57abeb --- /dev/null +++ b/fs/nfs_common/localio_trace.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 Trond Myklebust <trond.myklebust@hammerspace.com> + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com> + */ +#include <linux/nfs_fs.h> +#include <linux/namei.h> + +#define CREATE_TRACE_POINTS +#include "localio_trace.h" diff --git a/fs/nfs_common/localio_trace.h b/fs/nfs_common/localio_trace.h new file mode 100644 index 000000000000..4055aec9ff8d --- /dev/null +++ b/fs/nfs_common/localio_trace.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Trond Myklebust <trond.myklebust@hammerspace.com> + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com> + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nfs_localio + +#if !defined(_TRACE_NFS_COMMON_LOCALIO_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NFS_COMMON_LOCALIO_H + +#include <linux/tracepoint.h> + +#include <trace/misc/fs.h> +#include <trace/misc/nfs.h> +#include <trace/misc/sunrpc.h> + +DECLARE_EVENT_CLASS(nfs_local_client_event, + TP_PROTO( + const struct nfs_client *clp + ), + + TP_ARGS(clp), + + TP_STRUCT__entry( + __field(unsigned int, protocol) + __string(server, clp->cl_hostname) + ), + + TP_fast_assign( + __entry->protocol = clp->rpc_ops->version; + __assign_str(server); + ), + + TP_printk( + "server=%s NFSv%u", __get_str(server), __entry->protocol + ) +); + +#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \ + DEFINE_EVENT(nfs_local_client_event, name, \ + TP_PROTO( \ + const struct nfs_client *clp \ + ), \ + TP_ARGS(clp)) + +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_localio_enable_client); +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_localio_disable_client); + +#endif /* _TRACE_NFS_COMMON_LOCALIO_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE localio_trace +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c index a74ec08f6c96..6a0bdea6d644 100644 --- a/fs/nfs_common/nfslocalio.c +++ b/fs/nfs_common/nfslocalio.c @@ -7,38 +7,67 @@ #include <linux/module.h> #include <linux/list.h> #include <linux/nfslocalio.h> +#include <linux/nfs3.h> +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> #include <net/netns/generic.h> +#include "localio_trace.h" + MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("NFS localio protocol bypass support"); -static DEFINE_SPINLOCK(nfs_uuid_lock); +static DEFINE_SPINLOCK(nfs_uuids_lock); /* * Global list of nfs_uuid_t instances - * that is protected by nfs_uuid_lock. + * that is protected by nfs_uuids_lock. */ static LIST_HEAD(nfs_uuids); +/* + * Lock ordering: + * 1: nfs_uuid->lock + * 2: nfs_uuids_lock + * 3: nfs_uuid->list_lock (aka nn->local_clients_lock) + * + * May skip locks in select cases, but never hold multiple + * locks out of order. + */ + void nfs_uuid_init(nfs_uuid_t *nfs_uuid) { - nfs_uuid->net = NULL; + RCU_INIT_POINTER(nfs_uuid->net, NULL); nfs_uuid->dom = NULL; + nfs_uuid->list_lock = NULL; INIT_LIST_HEAD(&nfs_uuid->list); + INIT_LIST_HEAD(&nfs_uuid->files); + spin_lock_init(&nfs_uuid->lock); + nfs_uuid->nfs3_localio_probe_count = 0; } EXPORT_SYMBOL_GPL(nfs_uuid_init); bool nfs_uuid_begin(nfs_uuid_t *nfs_uuid) { - spin_lock(&nfs_uuid_lock); - /* Is this nfs_uuid already in use? */ + spin_lock(&nfs_uuid->lock); + if (rcu_access_pointer(nfs_uuid->net)) { + /* This nfs_uuid is already in use */ + spin_unlock(&nfs_uuid->lock); + return false; + } + + spin_lock(&nfs_uuids_lock); if (!list_empty(&nfs_uuid->list)) { - spin_unlock(&nfs_uuid_lock); + /* This nfs_uuid is already in use */ + spin_unlock(&nfs_uuids_lock); + spin_unlock(&nfs_uuid->lock); return false; } - uuid_gen(&nfs_uuid->uuid); list_add_tail(&nfs_uuid->list, &nfs_uuids); - spin_unlock(&nfs_uuid_lock); + spin_unlock(&nfs_uuids_lock); + + uuid_gen(&nfs_uuid->uuid); + spin_unlock(&nfs_uuid->lock); return true; } @@ -46,12 +75,16 @@ EXPORT_SYMBOL_GPL(nfs_uuid_begin); void nfs_uuid_end(nfs_uuid_t *nfs_uuid) { - if (nfs_uuid->net == NULL) { - spin_lock(&nfs_uuid_lock); - if (nfs_uuid->net == NULL) + if (!rcu_access_pointer(nfs_uuid->net)) { + spin_lock(&nfs_uuid->lock); + if (!rcu_access_pointer(nfs_uuid->net)) { + /* Not local, remove from nfs_uuids */ + spin_lock(&nfs_uuids_lock); list_del_init(&nfs_uuid->list); - spin_unlock(&nfs_uuid_lock); - } + spin_unlock(&nfs_uuids_lock); + } + spin_unlock(&nfs_uuid->lock); + } } EXPORT_SYMBOL_GPL(nfs_uuid_end); @@ -69,68 +102,142 @@ static nfs_uuid_t * nfs_uuid_lookup_locked(const uuid_t *uuid) static struct module *nfsd_mod; void nfs_uuid_is_local(const uuid_t *uuid, struct list_head *list, - struct net *net, struct auth_domain *dom, - struct module *mod) + spinlock_t *list_lock, struct net *net, + struct auth_domain *dom, struct module *mod) { nfs_uuid_t *nfs_uuid; - spin_lock(&nfs_uuid_lock); + spin_lock(&nfs_uuids_lock); nfs_uuid = nfs_uuid_lookup_locked(uuid); - if (nfs_uuid) { - kref_get(&dom->ref); - nfs_uuid->dom = dom; - /* - * We don't hold a ref on the net, but instead put - * ourselves on a list so the net pointer can be - * invalidated. - */ - list_move(&nfs_uuid->list, list); - rcu_assign_pointer(nfs_uuid->net, net); - - __module_get(mod); - nfsd_mod = mod; + if (!nfs_uuid) { + spin_unlock(&nfs_uuids_lock); + return; } - spin_unlock(&nfs_uuid_lock); + + /* + * We don't hold a ref on the net, but instead put + * ourselves on @list (nn->local_clients) so the net + * pointer can be invalidated. + */ + spin_lock(list_lock); /* list_lock is nn->local_clients_lock */ + list_move(&nfs_uuid->list, list); + spin_unlock(list_lock); + + spin_unlock(&nfs_uuids_lock); + /* Once nfs_uuid is parented to @list, avoid global nfs_uuids_lock */ + spin_lock(&nfs_uuid->lock); + + __module_get(mod); + nfsd_mod = mod; + + nfs_uuid->list_lock = list_lock; + kref_get(&dom->ref); + nfs_uuid->dom = dom; + rcu_assign_pointer(nfs_uuid->net, net); + spin_unlock(&nfs_uuid->lock); } EXPORT_SYMBOL_GPL(nfs_uuid_is_local); -static void nfs_uuid_put_locked(nfs_uuid_t *nfs_uuid) +void nfs_localio_enable_client(struct nfs_client *clp) +{ + /* nfs_uuid_is_local() does the actual enablement */ + trace_nfs_localio_enable_client(clp); +} +EXPORT_SYMBOL_GPL(nfs_localio_enable_client); + +/* + * Cleanup the nfs_uuid_t embedded in an nfs_client. + * This is the long-form of nfs_uuid_init(). + */ +static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid) { - if (nfs_uuid->net) { - module_put(nfsd_mod); - nfs_uuid->net = NULL; + LIST_HEAD(local_files); + struct nfs_file_localio *nfl, *tmp; + + spin_lock(&nfs_uuid->lock); + if (unlikely(!rcu_access_pointer(nfs_uuid->net))) { + spin_unlock(&nfs_uuid->lock); + return false; } + RCU_INIT_POINTER(nfs_uuid->net, NULL); + if (nfs_uuid->dom) { auth_domain_put(nfs_uuid->dom); nfs_uuid->dom = NULL; } - list_del_init(&nfs_uuid->list); + + list_splice_init(&nfs_uuid->files, &local_files); + spin_unlock(&nfs_uuid->lock); + + /* Walk list of files and ensure their last references dropped */ + list_for_each_entry_safe(nfl, tmp, &local_files, list) { + nfs_close_local_fh(nfl); + cond_resched(); + } + + spin_lock(&nfs_uuid->lock); + BUG_ON(!list_empty(&nfs_uuid->files)); + + /* Remove client from nn->local_clients */ + if (nfs_uuid->list_lock) { + spin_lock(nfs_uuid->list_lock); + BUG_ON(list_empty(&nfs_uuid->list)); + list_del_init(&nfs_uuid->list); + spin_unlock(nfs_uuid->list_lock); + nfs_uuid->list_lock = NULL; + } + + module_put(nfsd_mod); + spin_unlock(&nfs_uuid->lock); + + return true; } -void nfs_uuid_invalidate_clients(struct list_head *list) +void nfs_localio_disable_client(struct nfs_client *clp) { + if (nfs_uuid_put(&clp->cl_uuid)) + trace_nfs_localio_disable_client(clp); +} +EXPORT_SYMBOL_GPL(nfs_localio_disable_client); + +void nfs_localio_invalidate_clients(struct list_head *nn_local_clients, + spinlock_t *nn_local_clients_lock) +{ + LIST_HEAD(local_clients); nfs_uuid_t *nfs_uuid, *tmp; + struct nfs_client *clp; - spin_lock(&nfs_uuid_lock); - list_for_each_entry_safe(nfs_uuid, tmp, list, list) - nfs_uuid_put_locked(nfs_uuid); - spin_unlock(&nfs_uuid_lock); + spin_lock(nn_local_clients_lock); + list_splice_init(nn_local_clients, &local_clients); + spin_unlock(nn_local_clients_lock); + list_for_each_entry_safe(nfs_uuid, tmp, &local_clients, list) { + if (WARN_ON(nfs_uuid->list_lock != nn_local_clients_lock)) + break; + clp = container_of(nfs_uuid, struct nfs_client, cl_uuid); + nfs_localio_disable_client(clp); + } } -EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_clients); +EXPORT_SYMBOL_GPL(nfs_localio_invalidate_clients); -void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid) +static void nfs_uuid_add_file(nfs_uuid_t *nfs_uuid, struct nfs_file_localio *nfl) { - if (nfs_uuid->net) { - spin_lock(&nfs_uuid_lock); - nfs_uuid_put_locked(nfs_uuid); - spin_unlock(&nfs_uuid_lock); + /* Add nfl to nfs_uuid->files if it isn't already */ + spin_lock(&nfs_uuid->lock); + if (list_empty(&nfl->list)) { + rcu_assign_pointer(nfl->nfs_uuid, nfs_uuid); + list_add_tail(&nfl->list, &nfs_uuid->files); } + spin_unlock(&nfs_uuid->lock); } -EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_one_client); +/* + * Caller is responsible for calling nfsd_net_put and + * nfsd_file_put (via nfs_to_nfsd_file_put_local). + */ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, struct rpc_clnt *rpc_clnt, const struct cred *cred, - const struct nfs_fh *nfs_fh, const fmode_t fmode) + const struct nfs_fh *nfs_fh, struct nfs_file_localio *nfl, + const fmode_t fmode) { struct net *net; struct nfsd_file *localio; @@ -139,7 +246,7 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, * Not running in nfsd context, so must safely get reference on nfsd_serv. * But the server may already be shutting down, if so disallow new localio. * uuid->net is NOT a counted reference, but rcu_read_lock() ensures that - * if uuid->net is not NULL, then calling nfsd_serv_try_get() is safe + * if uuid->net is not NULL, then calling nfsd_net_try_get() is safe * and if it succeeds we will have an implied reference to the net. * * Otherwise NFS may not have ref on NFSD and therefore cannot safely @@ -147,21 +254,62 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, */ rcu_read_lock(); net = rcu_dereference(uuid->net); - if (!net || !nfs_to->nfsd_serv_try_get(net)) { + if (!net || !nfs_to->nfsd_net_try_get(net)) { rcu_read_unlock(); return ERR_PTR(-ENXIO); } rcu_read_unlock(); - /* We have an implied reference to net thanks to nfsd_serv_try_get */ + /* We have an implied reference to net thanks to nfsd_net_try_get */ localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt, cred, nfs_fh, fmode); if (IS_ERR(localio)) nfs_to_nfsd_net_put(net); + else + nfs_uuid_add_file(uuid, nfl); return localio; } EXPORT_SYMBOL_GPL(nfs_open_local_fh); +void nfs_close_local_fh(struct nfs_file_localio *nfl) +{ + struct nfsd_file *ro_nf = NULL; + struct nfsd_file *rw_nf = NULL; + nfs_uuid_t *nfs_uuid; + + rcu_read_lock(); + nfs_uuid = rcu_dereference(nfl->nfs_uuid); + if (!nfs_uuid) { + /* regular (non-LOCALIO) NFS will hammer this */ + rcu_read_unlock(); + return; + } + + ro_nf = rcu_access_pointer(nfl->ro_file); + rw_nf = rcu_access_pointer(nfl->rw_file); + if (ro_nf || rw_nf) { + spin_lock(&nfs_uuid->lock); + if (ro_nf) + ro_nf = rcu_dereference_protected(xchg(&nfl->ro_file, NULL), 1); + if (rw_nf) + rw_nf = rcu_dereference_protected(xchg(&nfl->rw_file, NULL), 1); + + /* Remove nfl from nfs_uuid->files list */ + RCU_INIT_POINTER(nfl->nfs_uuid, NULL); + list_del_init(&nfl->list); + spin_unlock(&nfs_uuid->lock); + rcu_read_unlock(); + + if (ro_nf) + nfs_to_nfsd_file_put_local(ro_nf); + if (rw_nf) + nfs_to_nfsd_file_put_local(rw_nf); + return; + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(nfs_close_local_fh); + /* * The NFS LOCALIO code needs to call into NFSD using various symbols, * but cannot be statically linked, because that will make the NFS diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index dc5c9d8e8202..0e552d873eaa 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -39,6 +39,7 @@ #include <linux/fsnotify.h> #include <linux/seq_file.h> #include <linux/rhashtable.h> +#include <linux/nfslocalio.h> #include "vfs.h" #include "nfsd.h" @@ -391,7 +392,7 @@ nfsd_file_put(struct nfsd_file *nf) } /** - * nfsd_file_put_local - put nfsd_file reference and arm nfsd_serv_put in caller + * nfsd_file_put_local - put nfsd_file reference and arm nfsd_net_put in caller * @nf: nfsd_file of which to put the reference * * First save the associated net to return to caller, then put @@ -833,6 +834,14 @@ __nfsd_file_cache_purge(struct net *net) struct nfsd_file *nf; LIST_HEAD(dispose); +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + if (net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + nfs_localio_invalidate_clients(&nn->local_clients, + &nn->local_clients_lock); + } +#endif + rhltable_walk_enter(&nfsd_file_rhltable, &iter); do { rhashtable_walk_start(&iter); @@ -1222,10 +1231,9 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * a file. The security implications of this should be carefully * considered before use. * - * The nfsd_file object returned by this API is reference-counted - * and garbage-collected. The object is retained for a few - * seconds after the final nfsd_file_put() in case the caller - * wants to re-use it. + * The nfsd_file_object returned by this API is reference-counted + * but not garbage-collected. The object is unhashed after the + * final nfsd_file_put(). * * Return values: * %nfs_ok - @pnf points to an nfsd_file with its reference @@ -1247,7 +1255,7 @@ nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, __be32 beres; beres = nfsd_file_do_acquire(NULL, net, cred, client, - fhp, may_flags, NULL, pnf, true); + fhp, may_flags, NULL, pnf, false); put_cred(revert_creds(save_cred)); return beres; } diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index f441cb9f74d5..238647fa379e 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -25,10 +25,12 @@ #include "cache.h" static const struct nfsd_localio_operations nfsd_localio_ops = { - .nfsd_serv_try_get = nfsd_serv_try_get, - .nfsd_serv_put = nfsd_serv_put, + .nfsd_net_try_get = nfsd_net_try_get, + .nfsd_net_put = nfsd_net_put, .nfsd_open_local_fh = nfsd_open_local_fh, .nfsd_file_put_local = nfsd_file_put_local, + .nfsd_file_get = nfsd_file_get, + .nfsd_file_put = nfsd_file_put, .nfsd_file_file = nfsd_file_file, }; @@ -52,7 +54,7 @@ void nfsd_localio_ops_init(void) * avoid all the NFS overhead with reads, writes and commits. * * On successful return, returned nfsd_file will have its nf_net member - * set. Caller (NFS client) is responsible for calling nfsd_serv_put and + * set. Caller (NFS client) is responsible for calling nfsd_net_put and * nfsd_file_put (via nfs_to_nfsd_file_put_local). */ struct nfsd_file * @@ -114,6 +116,7 @@ static __be32 localio_proc_uuid_is_local(struct svc_rqst *rqstp) struct nfsd_net *nn = net_generic(net, nfsd_net_id); nfs_uuid_is_local(&argp->uuid, &nn->local_clients, + &nn->local_clients_lock, net, rqstp->rq_client, THIS_MODULE); return rpc_success; diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 4a07b8d0837b..3e2d0fde80a7 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -134,9 +134,10 @@ struct nfsd_net { struct svc_info nfsd_info; #define nfsd_serv nfsd_info.serv - struct percpu_ref nfsd_serv_ref; - struct completion nfsd_serv_confirm_done; - struct completion nfsd_serv_free_done; + + struct percpu_ref nfsd_net_ref; + struct completion nfsd_net_confirm_done; + struct completion nfsd_net_free_done; /* * clientid and stateid data for construction of net unique COPY @@ -213,6 +214,7 @@ struct nfsd_net { #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* Local clients to be invalidated when net is shut down */ + spinlock_t local_clients_lock; struct list_head local_clients; #endif }; @@ -223,8 +225,8 @@ struct nfsd_net { extern bool nfsd_support_version(int vers); extern unsigned int nfsd_net_id; -bool nfsd_serv_try_get(struct net *net); -void nfsd_serv_put(struct net *net); +bool nfsd_net_try_get(struct net *net); +void nfsd_net_put(struct net *net); void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn); void nfsd_reset_write_verifier(struct nfsd_net *nn); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 95ea4393305b..ce2a71e4904c 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2217,6 +2217,7 @@ static __net_init int nfsd_net_init(struct net *net) seqlock_init(&nn->writeverf_lock); nfsd_proc_stat_init(net); #if IS_ENABLED(CONFIG_NFS_LOCALIO) + spin_lock_init(&nn->local_clients_lock); INIT_LIST_HEAD(&nn->local_clients); #endif return 0; @@ -2234,14 +2235,15 @@ out_export_error: * nfsd_net_pre_exit - Disconnect localio clients from net namespace * @net: a network namespace that is about to be destroyed * - * This invalidated ->net pointers held by localio clients + * This invalidates ->net pointers held by localio clients * while they can still safely access nn->counter. */ static __net_exit void nfsd_net_pre_exit(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nfs_uuid_invalidate_clients(&nn->local_clients); + nfs_localio_invalidate_clients(&nn->local_clients, + &nn->local_clients_lock); } #endif diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 3f5104ed70bf..9b3d6cff0e1e 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -204,32 +204,32 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change return 0; } -bool nfsd_serv_try_get(struct net *net) __must_hold(rcu) +bool nfsd_net_try_get(struct net *net) __must_hold(rcu) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - return (nn && percpu_ref_tryget_live(&nn->nfsd_serv_ref)); + return (nn && percpu_ref_tryget_live(&nn->nfsd_net_ref)); } -void nfsd_serv_put(struct net *net) __must_hold(rcu) +void nfsd_net_put(struct net *net) __must_hold(rcu) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - percpu_ref_put(&nn->nfsd_serv_ref); + percpu_ref_put(&nn->nfsd_net_ref); } -static void nfsd_serv_done(struct percpu_ref *ref) +static void nfsd_net_done(struct percpu_ref *ref) { - struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref); + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref); - complete(&nn->nfsd_serv_confirm_done); + complete(&nn->nfsd_net_confirm_done); } -static void nfsd_serv_free(struct percpu_ref *ref) +static void nfsd_net_free(struct percpu_ref *ref) { - struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref); + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref); - complete(&nn->nfsd_serv_free_done); + complete(&nn->nfsd_net_free_done); } /* @@ -426,6 +426,10 @@ static void nfsd_shutdown_net(struct net *net) if (!nn->nfsd_net_up) return; + + percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); + wait_for_completion(&nn->nfsd_net_confirm_done); + nfsd_export_flush(net); nfs4_state_shutdown_net(net); nfsd_reply_cache_shutdown(nn); @@ -434,7 +438,10 @@ static void nfsd_shutdown_net(struct net *net) lockd_down(net); nn->lockd_up = false; } - percpu_ref_exit(&nn->nfsd_serv_ref); + + wait_for_completion(&nn->nfsd_net_free_done); + percpu_ref_exit(&nn->nfsd_net_ref); + nn->nfsd_net_up = false; nfsd_shutdown_generic(); } @@ -516,11 +523,6 @@ void nfsd_destroy_serv(struct net *net) lockdep_assert_held(&nfsd_mutex); - percpu_ref_kill_and_confirm(&nn->nfsd_serv_ref, nfsd_serv_done); - wait_for_completion(&nn->nfsd_serv_confirm_done); - wait_for_completion(&nn->nfsd_serv_free_done); - /* percpu_ref_exit is called in nfsd_shutdown_net */ - spin_lock(&nfsd_notifier_lock); nn->nfsd_serv = NULL; spin_unlock(&nfsd_notifier_lock); @@ -621,12 +623,12 @@ int nfsd_create_serv(struct net *net) if (nn->nfsd_serv) return 0; - error = percpu_ref_init(&nn->nfsd_serv_ref, nfsd_serv_free, + error = percpu_ref_init(&nn->nfsd_net_ref, nfsd_net_free, 0, GFP_KERNEL); if (error) return error; - init_completion(&nn->nfsd_serv_free_done); - init_completion(&nn->nfsd_serv_confirm_done); + init_completion(&nn->nfsd_net_free_done); + init_completion(&nn->nfsd_net_confirm_done); if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 1b508f543384..9729f071c5aa 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -206,8 +206,8 @@ static void orangefs_kernel_debug_init(void) pr_info("%s: overflow 1!\n", __func__); } - debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer, - &kernel_debug_fops); + debugfs_create_file_aux_num(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer, + 0, &kernel_debug_fops); } @@ -306,11 +306,10 @@ static void orangefs_client_debug_init(void) pr_info("%s: overflow! 2\n", __func__); } - client_debug_dentry = debugfs_create_file(ORANGEFS_CLIENT_DEBUG_FILE, - 0444, - debug_dir, - c_buffer, - &kernel_debug_fops); + client_debug_dentry = debugfs_create_file_aux_num( + ORANGEFS_CLIENT_DEBUG_FILE, + 0444, debug_dir, c_buffer, 1, + &kernel_debug_fops); } /* open ORANGEFS_KMOD_DEBUG_FILE or ORANGEFS_CLIENT_DEBUG_FILE.*/ @@ -418,8 +417,7 @@ static ssize_t orangefs_debug_write(struct file *file, * A service operation is required to set a new client-side * debug mask. */ - if (!strcmp(file->f_path.dentry->d_name.name, - ORANGEFS_KMOD_DEBUG_FILE)) { + if (!debugfs_get_aux_num(file)) { // kernel-debug debug_string_to_mask(buf, &orangefs_gossip_debug_mask, 0); debug_mask_to_string(&orangefs_gossip_debug_mask, 0); debug_string = kernel_debug_string; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 785408861c01..6931308876c4 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -817,7 +817,7 @@ EXPORT_SYMBOL_GPL(sysfs_emit_at); * Returns number of bytes written to @buf. */ ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { memcpy(buf, attr->private + off, count); |