From 0aa7c6990e7de06131cdc14ef4abfcab017c24a0 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:34 -0800 Subject: [PATCH] fuse: clean up fuse_lookup() Simplify fuse_lookup() and related functions. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dir.c | 75 ++++++++++++++++++----------------------------------------- 1 file changed, 23 insertions(+), 52 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 51f5da652771..0d1438a9dab3 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -13,7 +13,6 @@ #include #include #include -#include static inline unsigned long time_to_jiffies(unsigned long sec, unsigned long nsec) @@ -22,6 +21,13 @@ static inline unsigned long time_to_jiffies(unsigned long sec, return jiffies + timespec_to_jiffies(&ts); } +static void fuse_change_timeout(struct dentry *entry, struct fuse_entry_out *o) +{ + struct fuse_inode *fi = get_fuse_inode(entry->d_inode); + entry->d_time = time_to_jiffies(o->entry_valid, o->entry_valid_nsec); + fi->i_time = time_to_jiffies(o->attr_valid, o->attr_valid_nsec); +} + static void fuse_lookup_init(struct fuse_req *req, struct inode *dir, struct dentry *entry, struct fuse_entry_out *outarg) @@ -66,10 +72,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) return 0; fuse_change_attributes(inode, &outarg.attr); - entry->d_time = time_to_jiffies(outarg.entry_valid, - outarg.entry_valid_nsec); - fi->i_time = time_to_jiffies(outarg.attr_valid, - outarg.attr_valid_nsec); + fuse_change_timeout(entry, &outarg); } return 1; } @@ -96,8 +99,8 @@ static struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, }; -static int fuse_lookup_iget(struct inode *dir, struct dentry *entry, - struct inode **inodep) +static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, + struct nameidata *nd) { int err; struct fuse_entry_out outarg; @@ -106,11 +109,11 @@ static int fuse_lookup_iget(struct inode *dir, struct dentry *entry, struct fuse_req *req; if (entry->d_name.len > FUSE_NAME_MAX) - return -ENAMETOOLONG; + return ERR_PTR(-ENAMETOOLONG); req = fuse_get_request(fc); if (!req) - return -EINTR; + return ERR_PTR(-EINTR); fuse_lookup_init(req, dir, entry, &outarg); request_send(fc, req); @@ -122,24 +125,22 @@ static int fuse_lookup_iget(struct inode *dir, struct dentry *entry, &outarg.attr); if (!inode) { fuse_send_forget(fc, req, outarg.nodeid, 1); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } } fuse_put_request(fc, req); if (err && err != -ENOENT) - return err; + return ERR_PTR(err); - if (inode) { - struct fuse_inode *fi = get_fuse_inode(inode); - entry->d_time = time_to_jiffies(outarg.entry_valid, - outarg.entry_valid_nsec); - fi->i_time = time_to_jiffies(outarg.attr_valid, - outarg.attr_valid_nsec); + if (inode && dir_alias(inode)) { + iput(inode); + return ERR_PTR(-EIO); } - + d_add(entry, inode); entry->d_op = &fuse_dentry_operations; - *inodep = inode; - return 0; + if (inode) + fuse_change_timeout(entry, &outarg); + return NULL; } void fuse_invalidate_attr(struct inode *inode) @@ -163,7 +164,6 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, struct fuse_open_in inarg; struct fuse_open_out outopen; struct fuse_entry_out outentry; - struct fuse_inode *fi; struct fuse_file *ff; struct file *file; int flags = nd->intent.open.flags - 1; @@ -224,13 +224,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, goto out_put_request; } fuse_put_request(fc, req); - entry->d_time = time_to_jiffies(outentry.entry_valid, - outentry.entry_valid_nsec); - fi = get_fuse_inode(inode); - fi->i_time = time_to_jiffies(outentry.attr_valid, - outentry.attr_valid_nsec); - d_instantiate(entry, inode); + fuse_change_timeout(entry, &outentry); file = lookup_instantiate_filp(nd, entry, generic_file_open); if (IS_ERR(file)) { ff->fh = outopen.fh; @@ -254,7 +249,6 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, { struct fuse_entry_out outarg; struct inode *inode; - struct fuse_inode *fi; int err; req->in.h.nodeid = get_node_id(dir); @@ -286,14 +280,8 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, return -EIO; } - entry->d_time = time_to_jiffies(outarg.entry_valid, - outarg.entry_valid_nsec); - - fi = get_fuse_inode(inode); - fi->i_time = time_to_jiffies(outarg.attr_valid, - outarg.attr_valid_nsec); - d_instantiate(entry, inode); + fuse_change_timeout(entry, &outarg); fuse_invalidate_attr(dir); return 0; } @@ -883,23 +871,6 @@ static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, return err; } -static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, - struct nameidata *nd) -{ - struct inode *inode; - int err; - - err = fuse_lookup_iget(dir, entry, &inode); - if (err) - return ERR_PTR(err); - if (inode && dir_alias(inode)) { - iput(inode); - return ERR_PTR(-EIO); - } - d_add(entry, inode); - return NULL; -} - static int fuse_setxattr(struct dentry *entry, const char *name, const void *value, size_t size, int flags) { -- cgit v1.2.2 From 4633a22e7added835fd1d4b072dbcc4474aa3017 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:36 -0800 Subject: [PATCH] fuse: clean up page offset calculation Use page_offset() instead of doing page offset calculation by hand. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/file.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 2ca86141d13a..18aafa6c9af4 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -272,7 +272,6 @@ static int fuse_readpage(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); - loff_t pos = (loff_t) page->index << PAGE_CACHE_SHIFT; struct fuse_req *req = fuse_get_request(fc); int err = -EINTR; if (!req) @@ -281,7 +280,7 @@ static int fuse_readpage(struct file *file, struct page *page) req->out.page_zeroing = 1; req->num_pages = 1; req->pages[0] = page; - fuse_send_read(req, file, inode, pos, PAGE_CACHE_SIZE); + fuse_send_read(req, file, inode, page_offset(page), PAGE_CACHE_SIZE); err = req->out.h.error; fuse_put_request(fc, req); if (!err) @@ -295,7 +294,7 @@ static int fuse_readpage(struct file *file, struct page *page) static int fuse_send_readpages(struct fuse_req *req, struct file *file, struct inode *inode) { - loff_t pos = (loff_t) req->pages[0]->index << PAGE_CACHE_SHIFT; + loff_t pos = page_offset(req->pages[0]); size_t count = req->num_pages << PAGE_CACHE_SHIFT; unsigned i; req->out.page_zeroing = 1; @@ -402,7 +401,7 @@ static int fuse_commit_write(struct file *file, struct page *page, unsigned count = to - offset; struct inode *inode = page->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); - loff_t pos = ((loff_t) page->index << PAGE_CACHE_SHIFT) + offset; + loff_t pos = page_offset(page) + offset; struct fuse_req *req = fuse_get_request(fc); if (!req) return -EINTR; -- cgit v1.2.2 From 45714d65618407bce1fd0271bc58303ce14b0785 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:36 -0800 Subject: [PATCH] fuse: bump interface version Change interface version to 7.4. Following changes will need backward compatibility support, so store the minor version returned by userspace. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 2 ++ fs/fuse/fuse_i.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 8f873e621f41..e5bc3f8eebd0 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -178,6 +178,8 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) if (req->misc.init_in_out.major != FUSE_KERNEL_VERSION) fc->conn_error = 1; + fc->minor = req->misc.init_in_out.minor; + /* After INIT reply is received other requests can go out. So do (FUSE_MAX_OUTSTANDING - 1) number of up()s on outstanding_sem. The last up() is done in diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 0ea5301f86be..2d4835e54c90 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -272,6 +272,9 @@ struct fuse_conn { /** Is create not implemented by fs? */ unsigned no_create : 1; + /** Negotiated minor version */ + unsigned minor; + /** Backing dev info */ struct backing_dev_info bdi; }; -- cgit v1.2.2 From de5f12025572ef8fcffa4be5453061725acfb754 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:37 -0800 Subject: [PATCH] fuse: add frsize to statfs reply Add 'frsize' member to the statfs reply. I'm not sure if sending f_fsid will ever be needed, but just in case leave some space at the end of the structure, so less compatibility mess would be required. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/inode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/fuse') diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e69a546844d0..3b928a02af04 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -218,6 +218,7 @@ static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr { stbuf->f_type = FUSE_SUPER_MAGIC; stbuf->f_bsize = attr->bsize; + stbuf->f_frsize = attr->frsize; stbuf->f_blocks = attr->blocks; stbuf->f_bfree = attr->bfree; stbuf->f_bavail = attr->bavail; @@ -238,10 +239,12 @@ static int fuse_statfs(struct super_block *sb, struct kstatfs *buf) if (!req) return -EINTR; + memset(&outarg, 0, sizeof(outarg)); req->in.numargs = 0; req->in.h.opcode = FUSE_STATFS; req->out.numargs = 1; - req->out.args[0].size = sizeof(outarg); + req->out.args[0].size = + fc->minor < 4 ? FUSE_COMPAT_STATFS_SIZE : sizeof(outarg); req->out.args[0].value = &outarg; request_send(fc, req); err = req->out.h.error; -- cgit v1.2.2 From 8cbdf1e6f6876b37d2a0d96fd15ea9f90f7d51c1 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:38 -0800 Subject: [PATCH] fuse: support caching negative dentries Add support for caching negative dentries. Up till now, ->d_revalidate() always forced a new lookup on these. Now let the lookup method return a zero node ID (not used for anything else) meaning a negative entry, but with a positive cache timeout. The old way of signaling negative entry (replying ENOENT) still works. Userspace should check the ABI minor version to see whether sending a zero ID is allowed by the kernel or not. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dir.c | 64 +++++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 43 insertions(+), 21 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 0d1438a9dab3..4c127f2bc814 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -23,9 +23,26 @@ static inline unsigned long time_to_jiffies(unsigned long sec, static void fuse_change_timeout(struct dentry *entry, struct fuse_entry_out *o) { - struct fuse_inode *fi = get_fuse_inode(entry->d_inode); entry->d_time = time_to_jiffies(o->entry_valid, o->entry_valid_nsec); - fi->i_time = time_to_jiffies(o->attr_valid, o->attr_valid_nsec); + if (entry->d_inode) + get_fuse_inode(entry->d_inode)->i_time = + time_to_jiffies(o->attr_valid, o->attr_valid_nsec); +} + +void fuse_invalidate_attr(struct inode *inode) +{ + get_fuse_inode(inode)->i_time = jiffies - 1; +} + +static void fuse_invalidate_entry_cache(struct dentry *entry) +{ + entry->d_time = jiffies - 1; +} + +static void fuse_invalidate_entry(struct dentry *entry) +{ + d_invalidate(entry); + fuse_invalidate_entry_cache(entry); } static void fuse_lookup_init(struct fuse_req *req, struct inode *dir, @@ -45,15 +62,22 @@ static void fuse_lookup_init(struct fuse_req *req, struct inode *dir, static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) { - if (!entry->d_inode || is_bad_inode(entry->d_inode)) + struct inode *inode = entry->d_inode; + + if (inode && is_bad_inode(inode)) return 0; else if (time_after(jiffies, entry->d_time)) { int err; struct fuse_entry_out outarg; - struct inode *inode = entry->d_inode; - struct fuse_inode *fi = get_fuse_inode(inode); - struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_req *req = fuse_get_request(fc); + struct fuse_conn *fc; + struct fuse_req *req; + + fuse_invalidate_entry_cache(entry); + if (!inode) + return 0; + + fc = get_fuse_conn(inode); + req = fuse_get_request(fc); if (!req) return 0; @@ -61,6 +85,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) request_send(fc, req); err = req->out.h.error; if (!err) { + struct fuse_inode *fi = get_fuse_inode(inode); if (outarg.nodeid != get_node_id(inode)) { fuse_send_forget(fc, req, outarg.nodeid, 1); return 0; @@ -118,9 +143,9 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, fuse_lookup_init(req, dir, entry, &outarg); request_send(fc, req); err = req->out.h.error; - if (!err && invalid_nodeid(outarg.nodeid)) + if (!err && outarg.nodeid && invalid_nodeid(outarg.nodeid)) err = -EIO; - if (!err) { + if (!err && outarg.nodeid) { inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, &outarg.attr); if (!inode) { @@ -138,22 +163,13 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, } d_add(entry, inode); entry->d_op = &fuse_dentry_operations; - if (inode) + if (!err) fuse_change_timeout(entry, &outarg); + else + fuse_invalidate_entry_cache(entry); return NULL; } -void fuse_invalidate_attr(struct inode *inode) -{ - get_fuse_inode(inode)->i_time = jiffies - 1; -} - -static void fuse_invalidate_entry(struct dentry *entry) -{ - d_invalidate(entry); - entry->d_time = jiffies - 1; -} - static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, struct nameidata *nd) { @@ -387,6 +403,7 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) inode->i_nlink = 0; fuse_invalidate_attr(inode); fuse_invalidate_attr(dir); + fuse_invalidate_entry_cache(entry); } else if (err == -EINTR) fuse_invalidate_entry(entry); return err; @@ -412,6 +429,7 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) if (!err) { entry->d_inode->i_nlink = 0; fuse_invalidate_attr(dir); + fuse_invalidate_entry_cache(entry); } else if (err == -EINTR) fuse_invalidate_entry(entry); return err; @@ -447,6 +465,10 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent, fuse_invalidate_attr(olddir); if (olddir != newdir) fuse_invalidate_attr(newdir); + + /* newent will end up negative */ + if (newent->d_inode) + fuse_invalidate_entry_cache(newent); } else if (err == -EINTR) { /* If request was interrupted, DEITY only knows if the rename actually took place. If the invalidation -- cgit v1.2.2 From 6f9f11806af8ad3a107714a3ece56c1c4fafd047 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:39 -0800 Subject: [PATCH] fuse: add code documentation Document some not-so-trivial functions. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dir.c | 99 +++++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 90 insertions(+), 9 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 4c127f2bc814..fead7f49e2ca 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -14,6 +14,15 @@ #include #include +/* + * FUSE caches dentries and attributes with separate timeout. The + * time in jiffies until the dentry/attributes are valid is stored in + * dentry->d_time and fuse_inode->i_time respectively. + */ + +/* + * Calculate the time in jiffies until a dentry/attributes are valid + */ static inline unsigned long time_to_jiffies(unsigned long sec, unsigned long nsec) { @@ -21,6 +30,10 @@ static inline unsigned long time_to_jiffies(unsigned long sec, return jiffies + timespec_to_jiffies(&ts); } +/* + * Set dentry and possibly attribute timeouts from the lookup/mk* + * replies + */ static void fuse_change_timeout(struct dentry *entry, struct fuse_entry_out *o) { entry->d_time = time_to_jiffies(o->entry_valid, o->entry_valid_nsec); @@ -29,16 +42,32 @@ static void fuse_change_timeout(struct dentry *entry, struct fuse_entry_out *o) time_to_jiffies(o->attr_valid, o->attr_valid_nsec); } +/* + * Mark the attributes as stale, so that at the next call to + * ->getattr() they will be fetched from userspace + */ void fuse_invalidate_attr(struct inode *inode) { get_fuse_inode(inode)->i_time = jiffies - 1; } +/* + * Just mark the entry as stale, so that a next attempt to look it up + * will result in a new lookup call to userspace + * + * This is called when a dentry is about to become negative and the + * timeout is unknown (unlink, rmdir, rename and in some cases + * lookup) + */ static void fuse_invalidate_entry_cache(struct dentry *entry) { entry->d_time = jiffies - 1; } +/* + * Same as fuse_invalidate_entry_cache(), but also try to remove the + * dentry from the hash + */ static void fuse_invalidate_entry(struct dentry *entry) { d_invalidate(entry); @@ -60,6 +89,15 @@ static void fuse_lookup_init(struct fuse_req *req, struct inode *dir, req->out.args[0].value = outarg; } +/* + * Check whether the dentry is still valid + * + * If the entry validity timeout has expired and the dentry is + * positive, try to redo the lookup. If the lookup results in a + * different inode, then let the VFS invalidate the dentry and redo + * the lookup once more. If the lookup results in the same inode, + * then refresh the attributes, timeouts and mark the dentry valid. + */ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) { struct inode *inode = entry->d_inode; @@ -72,6 +110,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) struct fuse_conn *fc; struct fuse_req *req; + /* Doesn't hurt to "reset" the validity timeout */ fuse_invalidate_entry_cache(entry); if (!inode) return 0; @@ -102,10 +141,13 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) return 1; } +/* + * Check if there's already a hashed alias of this directory inode. + * If yes, then lookup and mkdir must not create a new alias. + */ static int dir_alias(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { - /* Don't allow creating an alias to a directory */ struct dentry *alias = d_find_alias(inode); if (alias) { dput(alias); @@ -170,6 +212,12 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, return NULL; } +/* + * Atomic create+open operation + * + * If the filesystem doesn't support this, then fall back to separate + * 'mknod' + 'open' requests. + */ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, struct nameidata *nd) { @@ -236,6 +284,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, if (!inode) { flags &= ~(O_CREAT | O_EXCL | O_TRUNC); ff->fh = outopen.fh; + /* Special release, with inode = NULL, this will + trigger a 'forget' request when the release is + complete */ fuse_send_release(fc, ff, outentry.nodeid, NULL, flags, 0); goto out_put_request; } @@ -259,6 +310,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, return err; } +/* + * Code shared between mknod, mkdir, symlink and link + */ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, struct inode *dir, struct dentry *entry, int mode) @@ -576,6 +630,15 @@ static int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task) return 0; } +/* + * Check whether the inode attributes are still valid + * + * If the attribute validity timeout has expired, then fetch the fresh + * attributes with a 'getattr' request + * + * I'm not sure why cached attributes are never returned for the root + * inode, this is probably being too cautious. + */ static int fuse_revalidate(struct dentry *entry) { struct inode *inode = entry->d_inode; @@ -623,6 +686,19 @@ static int fuse_access(struct inode *inode, int mask) return err; } +/* + * Check permission. The two basic access models of FUSE are: + * + * 1) Local access checking ('default_permissions' mount option) based + * on file mode. This is the plain old disk filesystem permission + * modell. + * + * 2) "Remote" access checking, where server is responsible for + * checking permission in each inode operation. An exception to this + * is if ->permission() was invoked from sys_access() in which case an + * access request is sent. Execute permission is still checked + * locally based on file mode. + */ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) { struct fuse_conn *fc = get_fuse_conn(inode); @@ -641,14 +717,10 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) err = generic_permission(inode, mask, NULL); } - /* FIXME: Need some mechanism to revoke permissions: - currently if the filesystem suddenly changes the - file mode, we will not be informed about it, and - continue to allow access to the file/directory. - - This is actually not so grave, since the user can - simply keep access to the file/directory anyway by - keeping it open... */ + /* Note: the opposite of the above test does not + exist. So if permissions are revoked this won't be + noticed immediately, only after the attribute + timeout has expired */ return err; } else { @@ -816,6 +888,15 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) } } +/* + * Set attributes, and at the same time refresh them. + * + * Truncation is slightly complicated, because the 'truncate' request + * may fail, in which case we don't want to touch the mapping. + * vmtruncate() doesn't allow for this case. So do the rlimit + * checking by hand and call vmtruncate() only after the file has + * actually been truncated. + */ static int fuse_setattr(struct dentry *entry, struct iattr *attr) { struct inode *inode = entry->d_inode; -- cgit v1.2.2 From 248d86e87d12da19eee602075f05a49a5215288b Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:39 -0800 Subject: [PATCH] fuse: fail file operations on bad inode Make file operations on a bad inode fail. This just makes things a bit more consistent. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dir.c | 7 ++++++- fs/fuse/file.c | 35 +++++++++++++++++++++++++++++++---- 2 files changed, 37 insertions(+), 5 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index fead7f49e2ca..9a6075de961f 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -773,7 +773,12 @@ static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir) struct page *page; struct inode *inode = file->f_dentry->d_inode; struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_req *req = fuse_get_request(fc); + struct fuse_req *req; + + if (is_bad_inode(inode)) + return -EIO; + + req = fuse_get_request(fc); if (!req) return -EINTR; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 18aafa6c9af4..c989f0e9456b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -163,6 +163,9 @@ static int fuse_flush(struct file *file) struct fuse_flush_in inarg; int err; + if (is_bad_inode(inode)) + return -EIO; + if (fc->no_flush) return 0; @@ -199,6 +202,9 @@ int fuse_fsync_common(struct file *file, struct dentry *de, int datasync, struct fuse_fsync_in inarg; int err; + if (is_bad_inode(inode)) + return -EIO; + if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir)) return 0; @@ -272,8 +278,15 @@ static int fuse_readpage(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_req *req = fuse_get_request(fc); - int err = -EINTR; + struct fuse_req *req; + int err; + + err = -EIO; + if (is_bad_inode(inode)) + goto out; + + err = -EINTR; + req = fuse_get_request(fc); if (!req) goto out; @@ -344,6 +357,10 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_readpages_data data; int err; + + if (is_bad_inode(inode)) + return -EIO; + data.file = file; data.inode = inode; data.req = fuse_get_request(fc); @@ -402,7 +419,12 @@ static int fuse_commit_write(struct file *file, struct page *page, struct inode *inode = page->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); loff_t pos = page_offset(page) + offset; - struct fuse_req *req = fuse_get_request(fc); + struct fuse_req *req; + + if (is_bad_inode(inode)) + return -EIO; + + req = fuse_get_request(fc); if (!req) return -EINTR; @@ -474,7 +496,12 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf, size_t nmax = write ? fc->max_write : fc->max_read; loff_t pos = *ppos; ssize_t res = 0; - struct fuse_req *req = fuse_get_request(fc); + struct fuse_req *req; + + if (is_bad_inode(inode)) + return -EIO; + + req = fuse_get_request(fc); if (!req) return -EINTR; -- cgit v1.2.2 From 1d3d752b471d2a3a1d5e4fe177e5e7d52abb4e4c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:40 -0800 Subject: [PATCH] fuse: clean up request size limit checking Change the way a too large request is handled. Until now in this case the device read returned -EINVAL and the operation returned -EIO. Make it more flexibible by not returning -EINVAL from the read, but restarting it instead. Also remove the fixed limit on setxattr data and let the filesystem provide as large a read buffer as it needs to handle the extended attribute data. The symbolic link length is already checked by VFS to be less than PATH_MAX, so the extra check against FUSE_SYMLINK_MAX is not needed. The check in fuse_create_open() against FUSE_NAME_MAX is not needed, since the dentry has already been looked up, and hence the name already checked. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 26 ++++++++++++++++---------- fs/fuse/dir.c | 14 +------------- fs/fuse/fuse_i.h | 9 ++++++--- fs/fuse/inode.c | 2 +- 4 files changed, 24 insertions(+), 27 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index e5bc3f8eebd0..1afdffdf80db 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -617,6 +617,7 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, struct fuse_copy_state cs; unsigned reqsize; + restart: spin_lock(&fuse_lock); fc = file->private_data; err = -EPERM; @@ -632,20 +633,25 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, req = list_entry(fc->pending.next, struct fuse_req, list); list_del_init(&req->list); - spin_unlock(&fuse_lock); in = &req->in; - reqsize = req->in.h.len; - fuse_copy_init(&cs, 1, req, iov, nr_segs); - err = -EINVAL; - if (iov_length(iov, nr_segs) >= reqsize) { - err = fuse_copy_one(&cs, &in->h, sizeof(in->h)); - if (!err) - err = fuse_copy_args(&cs, in->numargs, in->argpages, - (struct fuse_arg *) in->args, 0); + reqsize = in->h.len; + /* If request is too large, reply with an error and restart the read */ + if (iov_length(iov, nr_segs) < reqsize) { + req->out.h.error = -EIO; + /* SETXATTR is special, since it may contain too large data */ + if (in->h.opcode == FUSE_SETXATTR) + req->out.h.error = -E2BIG; + request_end(fc, req); + goto restart; } + spin_unlock(&fuse_lock); + fuse_copy_init(&cs, 1, req, iov, nr_segs); + err = fuse_copy_one(&cs, &in->h, sizeof(in->h)); + if (!err) + err = fuse_copy_args(&cs, in->numargs, in->argpages, + (struct fuse_arg *) in->args, 0); fuse_copy_finish(&cs); - spin_lock(&fuse_lock); req->locked = 0; if (!err && req->interrupted) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 9a6075de961f..f156392d019e 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -236,10 +236,6 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, if (fc->no_create) goto out; - err = -ENAMETOOLONG; - if (entry->d_name.len > FUSE_NAME_MAX) - goto out; - err = -EINTR; req = fuse_get_request(fc); if (!req) @@ -413,12 +409,7 @@ static int fuse_symlink(struct inode *dir, struct dentry *entry, { struct fuse_conn *fc = get_fuse_conn(dir); unsigned len = strlen(link) + 1; - struct fuse_req *req; - - if (len > FUSE_SYMLINK_MAX) - return -ENAMETOOLONG; - - req = fuse_get_request(fc); + struct fuse_req *req = fuse_get_request(fc); if (!req) return -EINTR; @@ -988,9 +979,6 @@ static int fuse_setxattr(struct dentry *entry, const char *name, struct fuse_setxattr_in inarg; int err; - if (size > FUSE_XATTR_SIZE_MAX) - return -E2BIG; - if (fc->no_setxattr) return -EOPNOTSUPP; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 2d4835e54c90..17fd368559cd 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -21,6 +21,12 @@ /** If more requests are outstanding, then the operation will block */ #define FUSE_MAX_OUTSTANDING 10 +/** Maximum size of data in a write request */ +#define FUSE_MAX_WRITE 4096 + +/** It could be as large as PATH_MAX, but would that have any uses? */ +#define FUSE_NAME_MAX 1024 + /** If the FUSE_DEFAULT_PERMISSIONS flag is given, the filesystem module will check permissions based on the file mode. Otherwise no permission checking is done in the kernel */ @@ -108,9 +114,6 @@ struct fuse_out { struct fuse_arg args[3]; }; -struct fuse_req; -struct fuse_conn; - /** * A request to the client */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 3b928a02af04..3580b9e12345 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -485,7 +485,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->max_read = d.max_read; if (fc->max_read / PAGE_CACHE_SIZE < fc->bdi.ra_pages) fc->bdi.ra_pages = fc->max_read / PAGE_CACHE_SIZE; - fc->max_write = FUSE_MAX_IN / 2; + fc->max_write = FUSE_MAX_WRITE; err = -ENOMEM; root = get_root_inode(sb, d.rootmode); -- cgit v1.2.2 From 3ec870d524c9150add120475c8ddcfa50574f98e Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:41 -0800 Subject: [PATCH] fuse: make maximum write data configurable Make the maximum size of write data configurable by the filesystem. The previous fixed 4096 limit only worked on architectures where the page size is less or equal to this. This change make writing work on other architectures too, and also lets the filesystem receive bigger write requests in direct_io mode. Normal writes which go through the page cache are still limited to a page sized chunk per request. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 48 ++++++++++++++++++++++++++++++------------------ fs/fuse/fuse_i.h | 6 ++---- fs/fuse/inode.c | 1 - 3 files changed, 32 insertions(+), 23 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 1afdffdf80db..e08ab4702d97 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -148,6 +148,26 @@ void fuse_release_background(struct fuse_req *req) spin_unlock(&fuse_lock); } +static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) +{ + int i; + struct fuse_init_out *arg = &req->misc.init_out; + + if (arg->major != FUSE_KERNEL_VERSION) + fc->conn_error = 1; + else { + fc->minor = arg->minor; + fc->max_write = arg->minor < 5 ? 4096 : arg->max_write; + } + + /* After INIT reply is received other requests can go + out. So do (FUSE_MAX_OUTSTANDING - 1) number of + up()s on outstanding_sem. The last up() is done in + fuse_putback_request() */ + for (i = 1; i < FUSE_MAX_OUTSTANDING; i++) + up(&fc->outstanding_sem); +} + /* * This function is called when a request is finished. Either a reply * has arrived or it was interrupted (and not yet sent) or some error @@ -172,21 +192,9 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) up_read(&fc->sbput_sem); } wake_up(&req->waitq); - if (req->in.h.opcode == FUSE_INIT) { - int i; - - if (req->misc.init_in_out.major != FUSE_KERNEL_VERSION) - fc->conn_error = 1; - - fc->minor = req->misc.init_in_out.minor; - - /* After INIT reply is received other requests can go - out. So do (FUSE_MAX_OUTSTANDING - 1) number of - up()s on outstanding_sem. The last up() is done in - fuse_putback_request() */ - for (i = 1; i < FUSE_MAX_OUTSTANDING; i++) - up(&fc->outstanding_sem); - } else if (req->in.h.opcode == FUSE_RELEASE && req->inode == NULL) { + if (req->in.h.opcode == FUSE_INIT) + process_init_reply(fc, req); + else if (req->in.h.opcode == FUSE_RELEASE && req->inode == NULL) { /* Special case for failed iget in CREATE */ u64 nodeid = req->in.h.nodeid; __fuse_get_request(req); @@ -359,7 +367,7 @@ void fuse_send_init(struct fuse_conn *fc) /* This is called from fuse_read_super() so there's guaranteed to be a request available */ struct fuse_req *req = do_get_request(fc); - struct fuse_init_in_out *arg = &req->misc.init_in_out; + struct fuse_init_in *arg = &req->misc.init_in; arg->major = FUSE_KERNEL_VERSION; arg->minor = FUSE_KERNEL_MINOR_VERSION; req->in.h.opcode = FUSE_INIT; @@ -367,8 +375,12 @@ void fuse_send_init(struct fuse_conn *fc) req->in.args[0].size = sizeof(*arg); req->in.args[0].value = arg; req->out.numargs = 1; - req->out.args[0].size = sizeof(*arg); - req->out.args[0].value = arg; + /* Variable length arguement used for backward compatibility + with interface version < 7.5. Rest of init_out is zeroed + by do_get_request(), so a short reply is not a problem */ + req->out.argvar = 1; + req->out.args[0].size = sizeof(struct fuse_init_out); + req->out.args[0].value = &req->misc.init_out; request_send_background(fc, req); } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 17fd368559cd..74c8d098a14a 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -21,9 +21,6 @@ /** If more requests are outstanding, then the operation will block */ #define FUSE_MAX_OUTSTANDING 10 -/** Maximum size of data in a write request */ -#define FUSE_MAX_WRITE 4096 - /** It could be as large as PATH_MAX, but would that have any uses? */ #define FUSE_NAME_MAX 1024 @@ -162,7 +159,8 @@ struct fuse_req { union { struct fuse_forget_in forget_in; struct fuse_release_in release_in; - struct fuse_init_in_out init_in_out; + struct fuse_init_in init_in; + struct fuse_init_out init_out; } misc; /** page vector */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 3580b9e12345..e4541869831e 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -485,7 +485,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->max_read = d.max_read; if (fc->max_read / PAGE_CACHE_SIZE < fc->bdi.ra_pages) fc->bdi.ra_pages = fc->max_read / PAGE_CACHE_SIZE; - fc->max_write = FUSE_MAX_WRITE; err = -ENOMEM; root = get_root_inode(sb, d.rootmode); -- cgit v1.2.2 From 6ad84acab972f4dfc78e6fdb04c419f82c497d29 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:42 -0800 Subject: [PATCH] fuse: ensure progress in read and write In direct_io mode, send at least one page per reqest. Previously it was possible that reqests with zero data were sent, and hence the read/write didn't make any progress, resulting in an infinite (though interruptible) loop. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/file.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index c989f0e9456b..05dedddf4289 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -475,7 +475,7 @@ static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf, nbytes = min(nbytes, (unsigned) FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT); npages = (nbytes + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; - npages = min(npages, FUSE_MAX_PAGES_PER_REQ); + npages = min(max(npages, 1), FUSE_MAX_PAGES_PER_REQ); down_read(¤t->mm->mmap_sem); npages = get_user_pages(current, current->mm, user_addr, npages, write, 0, req->pages, NULL); @@ -506,7 +506,6 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf, return -EINTR; while (count) { - size_t tmp; size_t nres; size_t nbytes = min(count, nmax); int err = fuse_get_user_pages(req, buf, nbytes, !write); @@ -514,8 +513,8 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf, res = err; break; } - tmp = (req->num_pages << PAGE_SHIFT) - req->page_offset; - nbytes = min(nbytes, tmp); + nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset; + nbytes = min(count, nbytes); if (write) nres = fuse_send_write(req, file, inode, pos, nbytes); else -- cgit v1.2.2 From 39ee059affaf57a152c64cd3a0adc3f48f02ed71 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jan 2006 00:19:43 -0800 Subject: [PATCH] fuse: check file type in lookup Previously invalid types were quietly changed to regular files, but at revalidation the inode was changed to bad. This was rather inconsistent behavior. Now check if the type is valid on initial lookup, and return -EIO if not. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dir.c | 27 ++++++++++++++++++++------- fs/fuse/inode.c | 8 ++------ 2 files changed, 22 insertions(+), 13 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index f156392d019e..417bcee466f6 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -166,6 +166,12 @@ static struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, }; +static inline int valid_mode(int m) +{ + return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) || + S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m); +} + static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, struct nameidata *nd) { @@ -185,7 +191,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, fuse_lookup_init(req, dir, entry, &outarg); request_send(fc, req); err = req->out.h.error; - if (!err && outarg.nodeid && invalid_nodeid(outarg.nodeid)) + if (!err && ((outarg.nodeid && invalid_nodeid(outarg.nodeid)) || + !valid_mode(outarg.attr.mode))) err = -EIO; if (!err && outarg.nodeid) { inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, @@ -328,10 +335,13 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, fuse_put_request(fc, req); return err; } - if (invalid_nodeid(outarg.nodeid)) { - fuse_put_request(fc, req); - return -EIO; - } + err = -EIO; + if (invalid_nodeid(outarg.nodeid)) + goto out_put_request; + + if ((outarg.attr.mode ^ mode) & S_IFMT) + goto out_put_request; + inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, &outarg.attr); if (!inode) { @@ -340,8 +350,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, } fuse_put_request(fc, req); - /* Don't allow userspace to do really stupid things... */ - if (((inode->i_mode ^ mode) & S_IFMT) || dir_alias(inode)) { + if (dir_alias(inode)) { iput(inode); return -EIO; } @@ -350,6 +359,10 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, fuse_change_timeout(entry, &outarg); fuse_invalidate_attr(dir); return 0; + + out_put_request: + fuse_put_request(fc, req); + return err; } static int fuse_mknod(struct inode *dir, struct dentry *entry, int mode, diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e4541869831e..04c80cc957a3 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -135,12 +135,8 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) fuse_init_common(inode); init_special_inode(inode, inode->i_mode, new_decode_dev(attr->rdev)); - } else { - /* Don't let user create weird files */ - inode->i_mode = S_IFREG; - fuse_init_common(inode); - fuse_init_file_inode(inode); - } + } else + BUG(); } static int fuse_inode_eq(struct inode *inode, void *_nodeidp) -- cgit v1.2.2 From 1b1dcc1b57a49136f118a0f16367256ff9994a69 Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Mon, 9 Jan 2006 15:59:24 -0800 Subject: [PATCH] mutex subsystem, semaphore to mutex: VFS, ->i_sem This patch converts the inode semaphore to a mutex. I have tested it on XFS and compiled as much as one can consider on an ia64. Anyway your luck with it might be different. Modified-by: Ingo Molnar (finished the conversion) Signed-off-by: Jes Sorensen Signed-off-by: Ingo Molnar --- fs/fuse/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 05dedddf4289..63d2980df5c9 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -560,9 +560,9 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf, struct inode *inode = file->f_dentry->d_inode; ssize_t res; /* Don't allow parallel writes to the same file */ - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); res = fuse_direct_io(file, buf, count, ppos, 1); - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); return res; } -- cgit v1.2.2 From 222f1d69183f10d70a37de5785698fe0aa363c12 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:25 -0800 Subject: [PATCH] fuse: fuse_copy_finish() order fix fuse_copy_finish() must be called before request_end(), since the later might sleep, and no sleeping is allowed between fuse_copy_one() and fuse_copy_finish() because of kmap_atomic()/kunmap_atomic() used in them. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index e08ab4702d97..9af88953db69 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -773,8 +773,10 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, list_del_init(&req->list); if (req->interrupted) { - request_end(fc, req); + spin_unlock(&fuse_lock); fuse_copy_finish(&cs); + spin_lock(&fuse_lock); + request_end(fc, req); return -ENOENT; } req->out.h = oh; -- cgit v1.2.2 From f43b155a5a8a95b06bc0b4474fbb7311c7e9709a Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:26 -0800 Subject: [PATCH] fuse: fix request_end() This function used the request object after decrementing its reference count and releasing the lock. This could in theory lead to all sorts of problems. Fix and simplify at the same time. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 9af88953db69..de402e4d8bce 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -171,19 +171,17 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) /* * This function is called when a request is finished. Either a reply * has arrived or it was interrupted (and not yet sent) or some error - * occurred during communication with userspace, or the device file was - * closed. It decreases the reference count for the request. In case - * of a background request the reference to the stored objects are - * released. The requester thread is woken up (if still waiting), and - * finally the request is either freed or put on the unused_list + * occurred during communication with userspace, or the device file + * was closed. In case of a background request the reference to the + * stored objects are released. The requester thread is woken up (if + * still waiting), and finally the reference to the request is + * released * * Called with fuse_lock, unlocks it */ static void request_end(struct fuse_conn *fc, struct fuse_req *req) { - int putback; req->finished = 1; - putback = atomic_dec_and_test(&req->count); spin_unlock(&fuse_lock); if (req->background) { down_read(&fc->sbput_sem); @@ -197,13 +195,11 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) else if (req->in.h.opcode == FUSE_RELEASE && req->inode == NULL) { /* Special case for failed iget in CREATE */ u64 nodeid = req->in.h.nodeid; - __fuse_get_request(req); fuse_reset_request(req); fuse_send_forget(fc, req, nodeid, 1); - putback = 0; + return; } - if (putback) - fuse_putback_request(fc, req); + fuse_put_request(fc, req); } /* -- cgit v1.2.2 From b3bebd94bbe4e59dfa23d85b0296a4ce8ebcc6c7 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:27 -0800 Subject: [PATCH] fuse: handle error INIT reply Handle the case when the INIT request is answered with an error. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index de402e4d8bce..8244e89a8dd6 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -153,7 +153,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) int i; struct fuse_init_out *arg = &req->misc.init_out; - if (arg->major != FUSE_KERNEL_VERSION) + if (req->out.h.error || arg->major != FUSE_KERNEL_VERSION) fc->conn_error = 1; else { fc->minor = arg->minor; -- cgit v1.2.2 From 8bfc016d2e2fff71c6843257f0fd0b60876331ed Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:28 -0800 Subject: [PATCH] fuse: uninline some functions Inline keyword is unnecessary in most cases. Clean them up. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 21 ++++++++++----------- fs/fuse/dir.c | 12 +++++------- fs/fuse/file.c | 5 ++--- 3 files changed, 17 insertions(+), 21 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 8244e89a8dd6..d76432b757c9 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -21,7 +21,7 @@ MODULE_ALIAS_MISCDEV(FUSE_MINOR); static kmem_cache_t *fuse_req_cachep; -static inline struct fuse_conn *fuse_get_conn(struct file *file) +static struct fuse_conn *fuse_get_conn(struct file *file) { struct fuse_conn *fc; spin_lock(&fuse_lock); @@ -32,7 +32,7 @@ static inline struct fuse_conn *fuse_get_conn(struct file *file) return fc; } -static inline void fuse_request_init(struct fuse_req *req) +static void fuse_request_init(struct fuse_req *req) { memset(req, 0, sizeof(*req)); INIT_LIST_HEAD(&req->list); @@ -53,7 +53,7 @@ void fuse_request_free(struct fuse_req *req) kmem_cache_free(fuse_req_cachep, req); } -static inline void block_sigs(sigset_t *oldset) +static void block_sigs(sigset_t *oldset) { sigset_t mask; @@ -61,7 +61,7 @@ static inline void block_sigs(sigset_t *oldset) sigprocmask(SIG_BLOCK, &mask, oldset); } -static inline void restore_sigs(sigset_t *oldset) +static void restore_sigs(sigset_t *oldset) { sigprocmask(SIG_SETMASK, oldset, NULL); } @@ -385,7 +385,7 @@ void fuse_send_init(struct fuse_conn *fc) * anything that could cause a page-fault. If the request was already * interrupted bail out. */ -static inline int lock_request(struct fuse_req *req) +static int lock_request(struct fuse_req *req) { int err = 0; if (req) { @@ -404,7 +404,7 @@ static inline int lock_request(struct fuse_req *req) * requester thread is currently waiting for it to be unlocked, so * wake it up. */ -static inline void unlock_request(struct fuse_req *req) +static void unlock_request(struct fuse_req *req) { if (req) { spin_lock(&fuse_lock); @@ -440,7 +440,7 @@ static void fuse_copy_init(struct fuse_copy_state *cs, int write, } /* Unmap and put previous page of userspace buffer */ -static inline void fuse_copy_finish(struct fuse_copy_state *cs) +static void fuse_copy_finish(struct fuse_copy_state *cs) { if (cs->mapaddr) { kunmap_atomic(cs->mapaddr, KM_USER0); @@ -489,8 +489,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) } /* Do as much copy to/from userspace buffer as we can */ -static inline int fuse_copy_do(struct fuse_copy_state *cs, void **val, - unsigned *size) +static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size) { unsigned ncpy = min(*size, cs->len); if (val) { @@ -510,8 +509,8 @@ static inline int fuse_copy_do(struct fuse_copy_state *cs, void **val, * Copy a page in the request to/from the userspace buffer. Must be * done atomically */ -static inline int fuse_copy_page(struct fuse_copy_state *cs, struct page *page, - unsigned offset, unsigned count, int zeroing) +static int fuse_copy_page(struct fuse_copy_state *cs, struct page *page, + unsigned offset, unsigned count, int zeroing) { if (page && zeroing && count < PAGE_SIZE) { void *mapaddr = kmap_atomic(page, KM_USER1); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 417bcee466f6..e47fa3a2b4af 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -23,8 +23,7 @@ /* * Calculate the time in jiffies until a dentry/attributes are valid */ -static inline unsigned long time_to_jiffies(unsigned long sec, - unsigned long nsec) +static unsigned long time_to_jiffies(unsigned long sec, unsigned long nsec) { struct timespec ts = {sec, nsec}; return jiffies + timespec_to_jiffies(&ts); @@ -157,7 +156,7 @@ static int dir_alias(struct inode *inode) return 0; } -static inline int invalid_nodeid(u64 nodeid) +static int invalid_nodeid(u64 nodeid) { return !nodeid || nodeid == FUSE_ROOT_ID; } @@ -166,7 +165,7 @@ static struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, }; -static inline int valid_mode(int m) +static int valid_mode(int m) { return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) || S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m); @@ -763,9 +762,8 @@ static int parse_dirfile(char *buf, size_t nbytes, struct file *file, return 0; } -static inline size_t fuse_send_readdir(struct fuse_req *req, struct file *file, - struct inode *inode, loff_t pos, - size_t count) +static size_t fuse_send_readdir(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, size_t count) { return fuse_send_read_common(req, file, inode, pos, count, 1); } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 63d2980df5c9..52557664a89e 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -267,9 +267,8 @@ size_t fuse_send_read_common(struct fuse_req *req, struct file *file, return req->out.args[0].size; } -static inline size_t fuse_send_read(struct fuse_req *req, struct file *file, - struct inode *inode, loff_t pos, - size_t count) +static size_t fuse_send_read(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, size_t count) { return fuse_send_read_common(req, file, inode, pos, count, 0); } -- cgit v1.2.2 From 6383bdaa2ed2d461d9f4d369dfaa9d610fc972e3 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:29 -0800 Subject: [PATCH] fuse: miscellaneous cleanup - remove some unneeded assignments - use kzalloc instead of kmalloc + memset - simplify setting sb->s_fs_info - in fuse_send_init() use fuse_get_request() instead of do_get_request() helper Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 4 ++-- fs/fuse/fuse_i.h | 7 +------ fs/fuse/inode.c | 10 +++------- 3 files changed, 6 insertions(+), 15 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index d76432b757c9..4f1ca7b119ed 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -361,8 +361,8 @@ void request_send_background(struct fuse_conn *fc, struct fuse_req *req) void fuse_send_init(struct fuse_conn *fc) { /* This is called from fuse_read_super() so there's guaranteed - to be a request available */ - struct fuse_req *req = do_get_request(fc); + to be exactly one request available */ + struct fuse_req *req = fuse_get_request(fc); struct fuse_init_in *arg = &req->misc.init_in; arg->major = FUSE_KERNEL_VERSION; arg->minor = FUSE_KERNEL_MINOR_VERSION; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 74c8d098a14a..27937e8018eb 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -280,14 +280,9 @@ struct fuse_conn { struct backing_dev_info bdi; }; -static inline struct fuse_conn **get_fuse_conn_super_p(struct super_block *sb) -{ - return (struct fuse_conn **) &sb->s_fs_info; -} - static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb) { - return *get_fuse_conn_super_p(sb); + return sb->s_fs_info; } static inline struct fuse_conn *get_fuse_conn(struct inode *inode) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 04c80cc957a3..ceee75df7b32 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -200,9 +200,6 @@ static void fuse_put_super(struct super_block *sb) spin_lock(&fuse_lock); fc->mounted = 0; - fc->user_id = 0; - fc->group_id = 0; - fc->flags = 0; /* Flush all readers on this fs */ wake_up_all(&fc->waitq); up_write(&fc->sbput_sem); @@ -379,16 +376,15 @@ static struct fuse_conn *new_conn(void) { struct fuse_conn *fc; - fc = kmalloc(sizeof(*fc), GFP_KERNEL); + fc = kzalloc(sizeof(*fc), GFP_KERNEL); if (fc != NULL) { int i; - memset(fc, 0, sizeof(*fc)); init_waitqueue_head(&fc->waitq); INIT_LIST_HEAD(&fc->pending); INIT_LIST_HEAD(&fc->processing); INIT_LIST_HEAD(&fc->unused_list); INIT_LIST_HEAD(&fc->background); - sema_init(&fc->outstanding_sem, 0); + sema_init(&fc->outstanding_sem, 1); /* One for INIT */ init_rwsem(&fc->sbput_sem); for (i = 0; i < FUSE_MAX_OUTSTANDING; i++) { struct fuse_req *req = fuse_request_alloc(); @@ -420,7 +416,7 @@ static struct fuse_conn *get_conn(struct file *file, struct super_block *sb) fc = ERR_PTR(-EINVAL); } else { file->private_data = fc; - *get_fuse_conn_super_p(sb) = fc; + sb->s_fs_info = fc; fc->mounted = 1; fc->connected = 1; fc->count = 2; -- cgit v1.2.2 From 83cfd4935124b165e942c317dc3e9ebb0a3e6a63 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:31 -0800 Subject: [PATCH] fuse: introduce unified request state The state of request was made up of 2 bitfields (->sent and ->finished) and of the fact that the request was on a list or not. Unify this into a single state field. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 14 ++++++++------ fs/fuse/fuse_i.h | 16 +++++++++++----- 2 files changed, 19 insertions(+), 11 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4f1ca7b119ed..bc8a3846a4bf 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -181,7 +181,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) */ static void request_end(struct fuse_conn *fc, struct fuse_req *req) { - req->finished = 1; + req->state = FUSE_REQ_FINISHED; spin_unlock(&fuse_lock); if (req->background) { down_read(&fc->sbput_sem); @@ -250,10 +250,10 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req) spin_unlock(&fuse_lock); block_sigs(&oldset); - wait_event_interruptible(req->waitq, req->finished); + wait_event_interruptible(req->waitq, req->state == FUSE_REQ_FINISHED); restore_sigs(&oldset); spin_lock(&fuse_lock); - if (req->finished) + if (req->state == FUSE_REQ_FINISHED) return; req->out.h.error = -EINTR; @@ -268,10 +268,10 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req) wait_event(req->waitq, !req->locked); spin_lock(&fuse_lock); } - if (!req->sent && !list_empty(&req->list)) { + if (req->state == FUSE_REQ_PENDING) { list_del(&req->list); __fuse_put_request(req); - } else if (!req->finished && req->sent) + } else if (req->state == FUSE_REQ_SENT) background_request(fc, req); } @@ -306,6 +306,7 @@ static void queue_request(struct fuse_conn *fc, struct fuse_req *req) fc->outstanding_debt++; } list_add_tail(&req->list, &fc->pending); + req->state = FUSE_REQ_PENDING; wake_up(&fc->waitq); } @@ -639,6 +640,7 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, goto err_unlock; req = list_entry(fc->pending.next, struct fuse_req, list); + req->state = FUSE_REQ_READING; list_del_init(&req->list); in = &req->in; @@ -672,7 +674,7 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, if (!req->isreply) request_end(fc, req); else { - req->sent = 1; + req->state = FUSE_REQ_SENT; list_add_tail(&req->list, &fc->processing); spin_unlock(&fuse_lock); } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 27937e8018eb..8cc87ebeed2e 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -111,6 +111,15 @@ struct fuse_out { struct fuse_arg args[3]; }; +/** The request state */ +enum fuse_req_state { + FUSE_REQ_INIT = 0, + FUSE_REQ_PENDING, + FUSE_REQ_READING, + FUSE_REQ_SENT, + FUSE_REQ_FINISHED +}; + /** * A request to the client */ @@ -140,11 +149,8 @@ struct fuse_req { /** Data is being copied to/from the request */ unsigned locked:1; - /** Request has been sent to userspace */ - unsigned sent:1; - - /** The request is finished */ - unsigned finished:1; + /** State of the request */ + enum fuse_req_state state; /** The request input */ struct fuse_in in; -- cgit v1.2.2 From d77a1d5b611742c538364f041ff4610d27b14fe7 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:31 -0800 Subject: [PATCH] fuse: introduce list for requests under I/O Create a new list for requests in the process of being transfered to/from userspace. This will be needed to be able to abort all requests even those currently under I/O Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 8 ++++---- fs/fuse/fuse_i.h | 7 +++++-- fs/fuse/inode.c | 1 + 3 files changed, 10 insertions(+), 6 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index bc8a3846a4bf..609875dbd212 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -181,6 +181,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) */ static void request_end(struct fuse_conn *fc, struct fuse_req *req) { + list_del(&req->list); req->state = FUSE_REQ_FINISHED; spin_unlock(&fuse_lock); if (req->background) { @@ -641,7 +642,7 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, req = list_entry(fc->pending.next, struct fuse_req, list); req->state = FUSE_REQ_READING; - list_del_init(&req->list); + list_move(&req->list, &fc->io); in = &req->in; reqsize = in->h.len; @@ -675,7 +676,7 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, request_end(fc, req); else { req->state = FUSE_REQ_SENT; - list_add_tail(&req->list, &fc->processing); + list_move_tail(&req->list, &fc->processing); spin_unlock(&fuse_lock); } return reqsize; @@ -768,7 +769,6 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, if (!req) goto err_unlock; - list_del_init(&req->list); if (req->interrupted) { spin_unlock(&fuse_lock); fuse_copy_finish(&cs); @@ -776,6 +776,7 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, request_end(fc, req); return -ENOENT; } + list_move(&req->list, &fc->io); req->out.h = oh; req->locked = 1; cs.req = req; @@ -835,7 +836,6 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head) while (!list_empty(head)) { struct fuse_req *req; req = list_entry(head->next, struct fuse_req, list); - list_del_init(&req->list); req->out.h.error = -ECONNABORTED; request_end(fc, req); spin_lock(&fuse_lock); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 8cc87ebeed2e..5742253164d9 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -124,8 +124,8 @@ enum fuse_req_state { * A request to the client */ struct fuse_req { - /** This can be on either unused_list, pending or processing - lists in fuse_conn */ + /** This can be on either unused_list, pending processing or + io lists in fuse_conn */ struct list_head list; /** Entry on the background list */ @@ -223,6 +223,9 @@ struct fuse_conn { /** The list of requests being processed */ struct list_head processing; + /** The list of requests under I/O */ + struct list_head io; + /** Requests put in the background (RELEASE or any other interrupted request) */ struct list_head background; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ceee75df7b32..d7aaffe979dd 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -382,6 +382,7 @@ static struct fuse_conn *new_conn(void) init_waitqueue_head(&fc->waitq); INIT_LIST_HEAD(&fc->pending); INIT_LIST_HEAD(&fc->processing); + INIT_LIST_HEAD(&fc->io); INIT_LIST_HEAD(&fc->unused_list); INIT_LIST_HEAD(&fc->background); sema_init(&fc->outstanding_sem, 1); /* One for INIT */ -- cgit v1.2.2 From 9ba7cbba100bdaca7316d71d6c6298e61191f8b2 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:34 -0800 Subject: [PATCH] fuse: extend semantics of connected flag The ->connected flag for a fuse_conn object previously only indicated whether the device file for this connection is currently open or not. Change it's meaning so that it indicates whether the connection is active or not: now either umount or device release will clear the flag. The separate ->mounted flag is still needed for handling background requests. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 6 +++--- fs/fuse/fuse_i.h | 3 ++- fs/fuse/inode.c | 1 + 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 609875dbd212..5cd43bf917a4 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -26,7 +26,7 @@ static struct fuse_conn *fuse_get_conn(struct file *file) struct fuse_conn *fc; spin_lock(&fuse_lock); fc = file->private_data; - if (fc && !fc->mounted) + if (fc && !fc->connected) fc = NULL; spin_unlock(&fuse_lock); return fc; @@ -594,7 +594,7 @@ static void request_wait(struct fuse_conn *fc) DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&fc->waitq, &wait); - while (fc->mounted && list_empty(&fc->pending)) { + while (fc->connected && list_empty(&fc->pending)) { set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) break; @@ -634,7 +634,7 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, goto err_unlock; request_wait(fc); err = -ENODEV; - if (!fc->mounted) + if (!fc->connected) goto err_unlock; err = -ERESTARTSYS; if (list_empty(&fc->pending)) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 5742253164d9..e824a09d3151 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -249,7 +249,8 @@ struct fuse_conn { /** Mount is active */ unsigned mounted : 1; - /** Connection established */ + /** Connection established, cleared on umount and device + release */ unsigned connected : 1; /** Connection failed (version mismatch) */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d7aaffe979dd..d6a09fdaa941 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -200,6 +200,7 @@ static void fuse_put_super(struct super_block *sb) spin_lock(&fuse_lock); fc->mounted = 0; + fc->connected = 0; /* Flush all readers on this fs */ wake_up_all(&fc->waitq); up_write(&fc->sbput_sem); -- cgit v1.2.2 From f543f253f3aa721a24557d7df8259145bb01b734 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:35 -0800 Subject: [PATCH] fuse: make fuse connection a kobject Kobjectify fuse_conn, and make it visible under /sys/fs/fuse/connections. Lacking any natural naming, connections are numbered. This patch doesn't add any attributes, just the infrastructure. Signed-off-by: Miklos Szeredi Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 4 +- fs/fuse/fuse_i.h | 17 +++-- fs/fuse/inode.c | 186 +++++++++++++++++++++++++++++++++++++++++++++---------- 3 files changed, 164 insertions(+), 43 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 5cd43bf917a4..de4a0a0bda8a 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -852,9 +852,11 @@ static int fuse_dev_release(struct inode *inode, struct file *file) fc->connected = 0; end_requests(fc, &fc->pending); end_requests(fc, &fc->processing); - fuse_release_conn(fc); } spin_unlock(&fuse_lock); + if (fc) + kobject_put(&fc->kobj); + return 0; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index e824a09d3151..6ef1e5f5873b 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -196,9 +196,6 @@ struct fuse_req { * unmounted. */ struct fuse_conn { - /** Reference count */ - int count; - /** The user id for this mount */ uid_t user_id; @@ -288,6 +285,9 @@ struct fuse_conn { /** Backing dev info */ struct backing_dev_info bdi; + + /** kobject */ + struct kobject kobj; }; static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb) @@ -300,6 +300,11 @@ static inline struct fuse_conn *get_fuse_conn(struct inode *inode) return get_fuse_conn_super(inode->i_sb); } +static inline struct fuse_conn *get_fuse_conn_kobj(struct kobject *obj) +{ + return container_of(obj, struct fuse_conn, kobj); +} + static inline struct fuse_inode *get_fuse_inode(struct inode *inode) { return container_of(inode, struct fuse_inode, inode); @@ -399,12 +404,6 @@ void fuse_init_symlink(struct inode *inode); */ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr); -/** - * Check if the connection can be released, and if yes, then free the - * connection structure - */ -void fuse_release_conn(struct fuse_conn *fc); - /** * Initialize the client device */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d6a09fdaa941..514b700c863d 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -24,6 +24,13 @@ MODULE_LICENSE("GPL"); spinlock_t fuse_lock; static kmem_cache_t *fuse_inode_cachep; +static struct subsystem connections_subsys; + +struct fuse_conn_attr { + struct attribute attr; + ssize_t (*show)(struct fuse_conn *, char *); + ssize_t (*store)(struct fuse_conn *, const char *, size_t); +}; #define FUSE_SUPER_MAGIC 0x65735546 @@ -201,11 +208,12 @@ static void fuse_put_super(struct super_block *sb) spin_lock(&fuse_lock); fc->mounted = 0; fc->connected = 0; + spin_unlock(&fuse_lock); + up_write(&fc->sbput_sem); /* Flush all readers on this fs */ wake_up_all(&fc->waitq); - up_write(&fc->sbput_sem); - fuse_release_conn(fc); - spin_unlock(&fuse_lock); + kobject_del(&fc->kobj); + kobject_put(&fc->kobj); } static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr) @@ -354,8 +362,10 @@ static int fuse_show_options(struct seq_file *m, struct vfsmount *mnt) return 0; } -static void free_conn(struct fuse_conn *fc) +static void fuse_conn_release(struct kobject *kobj) { + struct fuse_conn *fc = get_fuse_conn_kobj(kobj); + while (!list_empty(&fc->unused_list)) { struct fuse_req *req; req = list_entry(fc->unused_list.next, struct fuse_req, list); @@ -365,20 +375,12 @@ static void free_conn(struct fuse_conn *fc) kfree(fc); } -/* Must be called with the fuse lock held */ -void fuse_release_conn(struct fuse_conn *fc) -{ - fc->count--; - if (!fc->count) - free_conn(fc); -} - static struct fuse_conn *new_conn(void) { struct fuse_conn *fc; fc = kzalloc(sizeof(*fc), GFP_KERNEL); - if (fc != NULL) { + if (fc) { int i; init_waitqueue_head(&fc->waitq); INIT_LIST_HEAD(&fc->pending); @@ -388,10 +390,12 @@ static struct fuse_conn *new_conn(void) INIT_LIST_HEAD(&fc->background); sema_init(&fc->outstanding_sem, 1); /* One for INIT */ init_rwsem(&fc->sbput_sem); + kobj_set_kset_s(fc, connections_subsys); + kobject_init(&fc->kobj); for (i = 0; i < FUSE_MAX_OUTSTANDING; i++) { struct fuse_req *req = fuse_request_alloc(); if (!req) { - free_conn(fc); + kobject_put(&fc->kobj); return NULL; } list_add(&req->list, &fc->unused_list); @@ -406,25 +410,32 @@ static struct fuse_conn *new_conn(void) static struct fuse_conn *get_conn(struct file *file, struct super_block *sb) { struct fuse_conn *fc; + int err; + err = -EINVAL; if (file->f_op != &fuse_dev_operations) - return ERR_PTR(-EINVAL); + goto out_err; + + err = -ENOMEM; fc = new_conn(); - if (fc == NULL) - return ERR_PTR(-ENOMEM); + if (!fc) + goto out_err; + spin_lock(&fuse_lock); - if (file->private_data) { - free_conn(fc); - fc = ERR_PTR(-EINVAL); - } else { - file->private_data = fc; - sb->s_fs_info = fc; - fc->mounted = 1; - fc->connected = 1; - fc->count = 2; - } + err = -EINVAL; + if (file->private_data) + goto out_unlock; + + kobject_get(&fc->kobj); + file->private_data = fc; spin_unlock(&fuse_lock); return fc; + + out_unlock: + spin_unlock(&fuse_lock); + kobject_put(&fc->kobj); + out_err: + return ERR_PTR(err); } static struct inode *get_root_inode(struct super_block *sb, unsigned mode) @@ -447,12 +458,23 @@ static struct super_operations fuse_super_operations = { .show_options = fuse_show_options, }; +static unsigned long long conn_id(void) +{ + static unsigned long long ctr = 1; + unsigned long long val; + spin_lock(&fuse_lock); + val = ctr++; + spin_unlock(&fuse_lock); + return val; +} + static int fuse_fill_super(struct super_block *sb, void *data, int silent) { struct fuse_conn *fc; struct inode *root; struct fuse_mount_data d; struct file *file; + struct dentry *root_dentry; int err; if (!parse_fuse_opt((char *) data, &d)) @@ -480,23 +502,42 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (fc->max_read / PAGE_CACHE_SIZE < fc->bdi.ra_pages) fc->bdi.ra_pages = fc->max_read / PAGE_CACHE_SIZE; + /* Used by get_root_inode() */ + sb->s_fs_info = fc; + err = -ENOMEM; root = get_root_inode(sb, d.rootmode); - if (root == NULL) + if (!root) goto err; - sb->s_root = d_alloc_root(root); - if (!sb->s_root) { + root_dentry = d_alloc_root(root); + if (!root_dentry) { iput(root); goto err; } + + err = kobject_set_name(&fc->kobj, "%llu", conn_id()); + if (err) + goto err_put_root; + + err = kobject_add(&fc->kobj); + if (err) + goto err_put_root; + + sb->s_root = root_dentry; + spin_lock(&fuse_lock); + fc->mounted = 1; + fc->connected = 1; + spin_unlock(&fuse_lock); + fuse_send_init(fc); + return 0; + err_put_root: + dput(root_dentry); err: - spin_lock(&fuse_lock); - fuse_release_conn(fc); - spin_unlock(&fuse_lock); + kobject_put(&fc->kobj); return err; } @@ -514,6 +555,50 @@ static struct file_system_type fuse_fs_type = { .kill_sb = kill_anon_super, }; +static struct attribute *fuse_conn_attrs[] = { + NULL, +}; + +static ssize_t fuse_conn_attr_show(struct kobject *kobj, + struct attribute *attr, + char *page) +{ + struct fuse_conn_attr *fca = + container_of(attr, struct fuse_conn_attr, attr); + + if (fca->show) + return fca->show(get_fuse_conn_kobj(kobj), page); + else + return -EACCES; +} + +static ssize_t fuse_conn_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *page, size_t count) +{ + struct fuse_conn_attr *fca = + container_of(attr, struct fuse_conn_attr, attr); + + if (fca->store) + return fca->store(get_fuse_conn_kobj(kobj), page, count); + else + return -EACCES; +} + +static struct sysfs_ops fuse_conn_sysfs_ops = { + .show = &fuse_conn_attr_show, + .store = &fuse_conn_attr_store, +}; + +static struct kobj_type ktype_fuse_conn = { + .release = fuse_conn_release, + .sysfs_ops = &fuse_conn_sysfs_ops, + .default_attrs = fuse_conn_attrs, +}; + +static decl_subsys(fuse, NULL, NULL); +static decl_subsys(connections, &ktype_fuse_conn, NULL); + static void fuse_inode_init_once(void *foo, kmem_cache_t *cachep, unsigned long flags) { @@ -551,6 +636,34 @@ static void fuse_fs_cleanup(void) kmem_cache_destroy(fuse_inode_cachep); } +static int fuse_sysfs_init(void) +{ + int err; + + kset_set_kset_s(&fuse_subsys, fs_subsys); + err = subsystem_register(&fuse_subsys); + if (err) + goto out_err; + + kset_set_kset_s(&connections_subsys, fuse_subsys); + err = subsystem_register(&connections_subsys); + if (err) + goto out_fuse_unregister; + + return 0; + + out_fuse_unregister: + subsystem_unregister(&fuse_subsys); + out_err: + return err; +} + +static void fuse_sysfs_cleanup(void) +{ + subsystem_unregister(&connections_subsys); + subsystem_unregister(&fuse_subsys); +} + static int __init fuse_init(void) { int res; @@ -567,8 +680,14 @@ static int __init fuse_init(void) if (res) goto err_fs_cleanup; + res = fuse_sysfs_init(); + if (res) + goto err_dev_cleanup; + return 0; + err_dev_cleanup: + fuse_dev_cleanup(); err_fs_cleanup: fuse_fs_cleanup(); err: @@ -579,6 +698,7 @@ static void __exit fuse_exit(void) { printk(KERN_DEBUG "fuse exit\n"); + fuse_sysfs_cleanup(); fuse_fs_cleanup(); fuse_dev_cleanup(); } -- cgit v1.2.2 From 0cd5b88553acf0611474dbaf8e43770eed268060 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:38 -0800 Subject: [PATCH] fuse: add number of waiting requests attribute This patch adds the 'waiting' attribute which indicates how many filesystem requests are currently waiting to be completed. A non-zero value without any filesystem activity indicates a hung or deadlocked filesystem. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 12 +++++++++--- fs/fuse/fuse_i.h | 3 +++ fs/fuse/inode.c | 9 +++++++++ 3 files changed, 21 insertions(+), 3 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index de4a0a0bda8a..c72e44b58d09 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -109,18 +109,24 @@ struct fuse_req *fuse_get_request(struct fuse_conn *fc) int intr; sigset_t oldset; + atomic_inc(&fc->num_waiting); block_sigs(&oldset); intr = down_interruptible(&fc->outstanding_sem); restore_sigs(&oldset); - return intr ? NULL : do_get_request(fc); + if (intr) { + atomic_dec(&fc->num_waiting); + return NULL; + } + return do_get_request(fc); } static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req) { spin_lock(&fuse_lock); - if (req->preallocated) + if (req->preallocated) { + atomic_dec(&fc->num_waiting); list_add(&req->list, &fc->unused_list); - else + } else fuse_request_free(req); /* If we are in debt decrease that first */ diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 6ef1e5f5873b..bcb453f68111 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -280,6 +280,9 @@ struct fuse_conn { /** Is create not implemented by fs? */ unsigned no_create : 1; + /** The number of requests waiting for completion */ + atomic_t num_waiting; + /** Negotiated minor version */ unsigned minor; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 514b700c863d..182235923cdd 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -555,7 +555,16 @@ static struct file_system_type fuse_fs_type = { .kill_sb = kill_anon_super, }; +static ssize_t fuse_conn_waiting_show(struct fuse_conn *fc, char *page) +{ + return sprintf(page, "%i\n", atomic_read(&fc->num_waiting)); +} + +static struct fuse_conn_attr fuse_conn_waiting = + __ATTR(waiting, 0400, fuse_conn_waiting_show, NULL); + static struct attribute *fuse_conn_attrs[] = { + &fuse_conn_waiting.attr, NULL, }; -- cgit v1.2.2 From 69a53bf267fa58b89aa659d121dfe38436562a30 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:41 -0800 Subject: [PATCH] fuse: add connection aborting Add ability to abort a filesystem connection. With the introduction of asynchronous reads, the ability to interrupt any request is not enough to dissolve deadlocks, since now waiting for the request completion (page unlocked) is independent of the actual request, so in a deadlock all threads will be uninterruptible. The solution is to make it possible to abort all requests, even those currently undergoing I/O to/from userspace. The natural interface for this is 'mount -f mountpoint', but that only works as long as the filesystem is attached. So also add an 'abort' attribute to the sysfs view of the connection. Signed-off-by: Miklos Szeredi Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++---- fs/fuse/fuse_i.h | 7 ++++-- fs/fuse/inode.c | 16 +++++++++++++ 3 files changed, 88 insertions(+), 6 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index c72e44b58d09..60c222517ccd 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -260,11 +260,13 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req) wait_event_interruptible(req->waitq, req->state == FUSE_REQ_FINISHED); restore_sigs(&oldset); spin_lock(&fuse_lock); - if (req->state == FUSE_REQ_FINISHED) + if (req->state == FUSE_REQ_FINISHED && !req->interrupted) return; - req->out.h.error = -EINTR; - req->interrupted = 1; + if (!req->interrupted) { + req->out.h.error = -EINTR; + req->interrupted = 1; + } if (req->locked) { /* This is uninterruptible sleep, because data is being copied to/from the buffers of req. During @@ -770,6 +772,10 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, goto err_finish; spin_lock(&fuse_lock); + err = -ENOENT; + if (!fc->connected) + goto err_unlock; + req = request_find(fc, oh.unique); err = -EINVAL; if (!req) @@ -836,7 +842,11 @@ static unsigned fuse_dev_poll(struct file *file, poll_table *wait) return mask; } -/* Abort all requests on the given list (pending or processing) */ +/* + * Abort all requests on the given list (pending or processing) + * + * This function releases and reacquires fuse_lock + */ static void end_requests(struct fuse_conn *fc, struct list_head *head) { while (!list_empty(head)) { @@ -848,6 +858,59 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head) } } +/* + * Abort requests under I/O + * + * The requests are set to interrupted and finished, and the request + * waiter is woken up. This will make request_wait_answer() wait + * until the request is unlocked and then return. + */ +static void end_io_requests(struct fuse_conn *fc) +{ + while (!list_empty(&fc->io)) { + struct fuse_req *req; + req = list_entry(fc->io.next, struct fuse_req, list); + req->interrupted = 1; + req->out.h.error = -ECONNABORTED; + req->state = FUSE_REQ_FINISHED; + list_del_init(&req->list); + wake_up(&req->waitq); + } +} + +/* + * Abort all requests. + * + * Emergency exit in case of a malicious or accidental deadlock, or + * just a hung filesystem. + * + * The same effect is usually achievable through killing the + * filesystem daemon and all users of the filesystem. The exception + * is the combination of an asynchronous request and the tricky + * deadlock (see Documentation/filesystems/fuse.txt). + * + * During the aborting, progression of requests from the pending and + * processing lists onto the io list, and progression of new requests + * onto the pending list is prevented by req->connected being false. + * + * Progression of requests under I/O to the processing list is + * prevented by the req->interrupted flag being true for these + * requests. For this reason requests on the io list must be aborted + * first. + */ +void fuse_abort_conn(struct fuse_conn *fc) +{ + spin_lock(&fuse_lock); + if (fc->connected) { + fc->connected = 0; + end_io_requests(fc); + end_requests(fc, &fc->pending); + end_requests(fc, &fc->processing); + wake_up_all(&fc->waitq); + } + spin_unlock(&fuse_lock); +} + static int fuse_dev_release(struct inode *inode, struct file *file) { struct fuse_conn *fc; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index bcb453f68111..e6381db41df9 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -246,8 +246,8 @@ struct fuse_conn { /** Mount is active */ unsigned mounted : 1; - /** Connection established, cleared on umount and device - release */ + /** Connection established, cleared on umount, connection + abort and device release */ unsigned connected : 1; /** Connection failed (version mismatch) */ @@ -463,6 +463,9 @@ void request_send_background(struct fuse_conn *fc, struct fuse_req *req); */ void fuse_release_background(struct fuse_req *req); +/* Abort all requests */ +void fuse_abort_conn(struct fuse_conn *fc); + /** * Get the attributes of a file */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 182235923cdd..d359d8de22a4 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -196,6 +196,11 @@ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, return inode; } +static void fuse_umount_begin(struct super_block *sb) +{ + fuse_abort_conn(get_fuse_conn_super(sb)); +} + static void fuse_put_super(struct super_block *sb) { struct fuse_conn *fc = get_fuse_conn_super(sb); @@ -454,6 +459,7 @@ static struct super_operations fuse_super_operations = { .read_inode = fuse_read_inode, .clear_inode = fuse_clear_inode, .put_super = fuse_put_super, + .umount_begin = fuse_umount_begin, .statfs = fuse_statfs, .show_options = fuse_show_options, }; @@ -560,11 +566,21 @@ static ssize_t fuse_conn_waiting_show(struct fuse_conn *fc, char *page) return sprintf(page, "%i\n", atomic_read(&fc->num_waiting)); } +static ssize_t fuse_conn_abort_store(struct fuse_conn *fc, const char *page, + size_t count) +{ + fuse_abort_conn(fc); + return count; +} + static struct fuse_conn_attr fuse_conn_waiting = __ATTR(waiting, 0400, fuse_conn_waiting_show, NULL); +static struct fuse_conn_attr fuse_conn_abort = + __ATTR(abort, 0600, NULL, fuse_conn_abort_store); static struct attribute *fuse_conn_attrs[] = { &fuse_conn_waiting.attr, + &fuse_conn_abort.attr, NULL, }; -- cgit v1.2.2 From 64c6d8ed4c55f0a99b1b81558851da80c8d58244 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:42 -0800 Subject: [PATCH] fuse: add asynchronous request support Add possibility for requests to run asynchronously and call an 'end' callback when finished. With this, the special handling of the INIT and RELEASE requests can be cleaned up too. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 42 ++++++++++++++++++++++++++++-------------- fs/fuse/file.c | 10 ++++++++++ fs/fuse/fuse_i.h | 5 +++++ 3 files changed, 43 insertions(+), 14 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 60c222517ccd..99325547604f 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -172,6 +172,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fuse_putback_request() */ for (i = 1; i < FUSE_MAX_OUTSTANDING; i++) up(&fc->outstanding_sem); + + fuse_put_request(fc, req); } /* @@ -180,13 +182,15 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) * occurred during communication with userspace, or the device file * was closed. In case of a background request the reference to the * stored objects are released. The requester thread is woken up (if - * still waiting), and finally the reference to the request is - * released + * still waiting), the 'end' callback is called if given, else the + * reference to the request is released * * Called with fuse_lock, unlocks it */ static void request_end(struct fuse_conn *fc, struct fuse_req *req) { + void (*end) (struct fuse_conn *, struct fuse_req *) = req->end; + req->end = NULL; list_del(&req->list); req->state = FUSE_REQ_FINISHED; spin_unlock(&fuse_lock); @@ -197,16 +201,10 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) up_read(&fc->sbput_sem); } wake_up(&req->waitq); - if (req->in.h.opcode == FUSE_INIT) - process_init_reply(fc, req); - else if (req->in.h.opcode == FUSE_RELEASE && req->inode == NULL) { - /* Special case for failed iget in CREATE */ - u64 nodeid = req->in.h.nodeid; - fuse_reset_request(req); - fuse_send_forget(fc, req, nodeid, 1); - return; - } - fuse_put_request(fc, req); + if (end) + end(fc, req); + else + fuse_put_request(fc, req); } /* @@ -387,6 +385,7 @@ void fuse_send_init(struct fuse_conn *fc) req->out.argvar = 1; req->out.args[0].size = sizeof(struct fuse_init_out); req->out.args[0].value = &req->misc.init_out; + req->end = process_init_reply; request_send_background(fc, req); } @@ -864,17 +863,32 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head) * The requests are set to interrupted and finished, and the request * waiter is woken up. This will make request_wait_answer() wait * until the request is unlocked and then return. + * + * If the request is asynchronous, then the end function needs to be + * called after waiting for the request to be unlocked (if it was + * locked). */ static void end_io_requests(struct fuse_conn *fc) { while (!list_empty(&fc->io)) { - struct fuse_req *req; - req = list_entry(fc->io.next, struct fuse_req, list); + struct fuse_req *req = + list_entry(fc->io.next, struct fuse_req, list); + void (*end) (struct fuse_conn *, struct fuse_req *) = req->end; + req->interrupted = 1; req->out.h.error = -ECONNABORTED; req->state = FUSE_REQ_FINISHED; list_del_init(&req->list); wake_up(&req->waitq); + if (end) { + req->end = NULL; + /* The end function will consume this reference */ + __fuse_get_request(req); + spin_unlock(&fuse_lock); + wait_event(req->waitq, !req->locked); + end(fc, req); + spin_lock(&fuse_lock); + } } } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 52557664a89e..043d5b36846d 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -113,6 +113,14 @@ int fuse_open_common(struct inode *inode, struct file *file, int isdir) return err; } +/* Special case for failed iget in CREATE */ +static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req) +{ + u64 nodeid = req->in.h.nodeid; + fuse_reset_request(req); + fuse_send_forget(fc, req, nodeid, 1); +} + void fuse_send_release(struct fuse_conn *fc, struct fuse_file *ff, u64 nodeid, struct inode *inode, int flags, int isdir) { @@ -128,6 +136,8 @@ void fuse_send_release(struct fuse_conn *fc, struct fuse_file *ff, req->in.args[0].size = sizeof(struct fuse_release_in); req->in.args[0].value = inarg; request_send_background(fc, req); + if (!inode) + req->end = fuse_release_end; kfree(ff); } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index e6381db41df9..145098056ca6 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -120,6 +120,8 @@ enum fuse_req_state { FUSE_REQ_FINISHED }; +struct fuse_conn; + /** * A request to the client */ @@ -186,6 +188,9 @@ struct fuse_req { /** File used in the request (or NULL) */ struct file *file; + + /** Request completion callback */ + void (*end)(struct fuse_conn *, struct fuse_req *); }; /** -- cgit v1.2.2 From 9b9a04693fa2d9e60933154e4c4aca83c219ef0a Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:44 -0800 Subject: [PATCH] fuse: move INIT handling to inode.c Now the INIT requests can be completely handled in inode.c and the fuse_send_init() function need not be global any more. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 45 --------------------------------------------- fs/fuse/fuse_i.h | 5 ----- fs/fuse/inode.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 45 insertions(+), 50 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 99325547604f..4526da8907c6 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -154,28 +154,6 @@ void fuse_release_background(struct fuse_req *req) spin_unlock(&fuse_lock); } -static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) -{ - int i; - struct fuse_init_out *arg = &req->misc.init_out; - - if (req->out.h.error || arg->major != FUSE_KERNEL_VERSION) - fc->conn_error = 1; - else { - fc->minor = arg->minor; - fc->max_write = arg->minor < 5 ? 4096 : arg->max_write; - } - - /* After INIT reply is received other requests can go - out. So do (FUSE_MAX_OUTSTANDING - 1) number of - up()s on outstanding_sem. The last up() is done in - fuse_putback_request() */ - for (i = 1; i < FUSE_MAX_OUTSTANDING; i++) - up(&fc->outstanding_sem); - - fuse_put_request(fc, req); -} - /* * This function is called when a request is finished. Either a reply * has arrived or it was interrupted (and not yet sent) or some error @@ -366,29 +344,6 @@ void request_send_background(struct fuse_conn *fc, struct fuse_req *req) request_send_nowait(fc, req); } -void fuse_send_init(struct fuse_conn *fc) -{ - /* This is called from fuse_read_super() so there's guaranteed - to be exactly one request available */ - struct fuse_req *req = fuse_get_request(fc); - struct fuse_init_in *arg = &req->misc.init_in; - arg->major = FUSE_KERNEL_VERSION; - arg->minor = FUSE_KERNEL_MINOR_VERSION; - req->in.h.opcode = FUSE_INIT; - req->in.numargs = 1; - req->in.args[0].size = sizeof(*arg); - req->in.args[0].value = arg; - req->out.numargs = 1; - /* Variable length arguement used for backward compatibility - with interface version < 7.5. Rest of init_out is zeroed - by do_get_request(), so a short reply is not a problem */ - req->out.argvar = 1; - req->out.args[0].size = sizeof(struct fuse_init_out); - req->out.args[0].value = &req->misc.init_out; - req->end = process_init_reply; - request_send_background(fc, req); -} - /* * Lock the request. Up to the next unlock_request() there mustn't be * anything that could cause a page-fault. If the request was already diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 145098056ca6..926b41c959d5 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -480,8 +480,3 @@ int fuse_do_getattr(struct inode *inode); * Invalidate inode attributes */ void fuse_invalidate_attr(struct inode *inode); - -/** - * Send the INIT message - */ -void fuse_send_init(struct fuse_conn *fc); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d359d8de22a4..8683e7254d53 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -464,6 +464,51 @@ static struct super_operations fuse_super_operations = { .show_options = fuse_show_options, }; +static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) +{ + int i; + struct fuse_init_out *arg = &req->misc.init_out; + + if (req->out.h.error || arg->major != FUSE_KERNEL_VERSION) + fc->conn_error = 1; + else { + fc->minor = arg->minor; + fc->max_write = arg->minor < 5 ? 4096 : arg->max_write; + } + + /* After INIT reply is received other requests can go + out. So do (FUSE_MAX_OUTSTANDING - 1) number of + up()s on outstanding_sem. The last up() is done in + fuse_putback_request() */ + for (i = 1; i < FUSE_MAX_OUTSTANDING; i++) + up(&fc->outstanding_sem); + + fuse_put_request(fc, req); +} + +static void fuse_send_init(struct fuse_conn *fc) +{ + /* This is called from fuse_read_super() so there's guaranteed + to be exactly one request available */ + struct fuse_req *req = fuse_get_request(fc); + struct fuse_init_in *arg = &req->misc.init_in; + arg->major = FUSE_KERNEL_VERSION; + arg->minor = FUSE_KERNEL_MINOR_VERSION; + req->in.h.opcode = FUSE_INIT; + req->in.numargs = 1; + req->in.args[0].size = sizeof(*arg); + req->in.args[0].value = arg; + req->out.numargs = 1; + /* Variable length arguement used for backward compatibility + with interface version < 7.5. Rest of init_out is zeroed + by do_get_request(), so a short reply is not a problem */ + req->out.argvar = 1; + req->out.args[0].size = sizeof(struct fuse_init_out); + req->out.args[0].value = &req->misc.init_out; + req->end = process_init_reply; + request_send_background(fc, req); +} + static unsigned long long conn_id(void) { static unsigned long long ctr = 1; -- cgit v1.2.2 From 361b1eb55ea84181505c7f0674ca1205da1127ab Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:45 -0800 Subject: [PATCH] fuse: READ request initialization Add a separate function for filling in the READ request. This will make it possible to send asynchronous READ requests as well as synchronous ones. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dir.c | 10 +++------- fs/fuse/file.c | 24 +++++++++++------------- fs/fuse/fuse_i.h | 8 ++++---- 3 files changed, 18 insertions(+), 24 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index e47fa3a2b4af..21fd59c7bc24 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -762,12 +762,6 @@ static int parse_dirfile(char *buf, size_t nbytes, struct file *file, return 0; } -static size_t fuse_send_readdir(struct fuse_req *req, struct file *file, - struct inode *inode, loff_t pos, size_t count) -{ - return fuse_send_read_common(req, file, inode, pos, count, 1); -} - static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir) { int err; @@ -791,7 +785,9 @@ static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir) } req->num_pages = 1; req->pages[0] = page; - nbytes = fuse_send_readdir(req, file, inode, file->f_pos, PAGE_SIZE); + fuse_read_fill(req, file, inode, file->f_pos, PAGE_SIZE, FUSE_READDIR); + request_send(fc, req); + nbytes = req->out.args[0].size; err = req->out.h.error; fuse_put_request(fc, req); if (!err) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 043d5b36846d..4a0b0f9a2179 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -250,19 +250,16 @@ static int fuse_fsync(struct file *file, struct dentry *de, int datasync) return fuse_fsync_common(file, de, datasync, 0); } -size_t fuse_send_read_common(struct fuse_req *req, struct file *file, - struct inode *inode, loff_t pos, size_t count, - int isdir) +void fuse_read_fill(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, size_t count, int opcode) { - struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_file *ff = file->private_data; - struct fuse_read_in inarg; + struct fuse_read_in *inarg = &req->misc.read_in; - memset(&inarg, 0, sizeof(struct fuse_read_in)); - inarg.fh = ff->fh; - inarg.offset = pos; - inarg.size = count; - req->in.h.opcode = isdir ? FUSE_READDIR : FUSE_READ; + inarg->fh = ff->fh; + inarg->offset = pos; + inarg->size = count; + req->in.h.opcode = opcode; req->in.h.nodeid = get_node_id(inode); req->inode = inode; req->file = file; @@ -273,14 +270,15 @@ size_t fuse_send_read_common(struct fuse_req *req, struct file *file, req->out.argvar = 1; req->out.numargs = 1; req->out.args[0].size = count; - request_send(fc, req); - return req->out.args[0].size; } static size_t fuse_send_read(struct fuse_req *req, struct file *file, struct inode *inode, loff_t pos, size_t count) { - return fuse_send_read_common(req, file, inode, pos, count, 0); + struct fuse_conn *fc = get_fuse_conn(inode); + fuse_read_fill(req, file, inode, pos, count, FUSE_READ); + request_send(fc, req); + return req->out.args[0].size; } static int fuse_readpage(struct file *file, struct page *page) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 926b41c959d5..7ed1d3c53b8a 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -169,6 +169,7 @@ struct fuse_req { struct fuse_release_in release_in; struct fuse_init_in init_in; struct fuse_init_out init_out; + struct fuse_read_in read_in; } misc; /** page vector */ @@ -354,11 +355,10 @@ void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req, unsigned long nodeid, u64 nlookup); /** - * Send READ or READDIR request + * Initialize READ or READDIR request */ -size_t fuse_send_read_common(struct fuse_req *req, struct file *file, - struct inode *inode, loff_t pos, size_t count, - int isdir); +void fuse_read_fill(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, size_t count, int opcode); /** * Send OPEN or OPENDIR request -- cgit v1.2.2 From c1aa96a52e9594fb16296c0d76c2066773d62933 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:46 -0800 Subject: [PATCH] fuse: use asynchronous READ requests for readpages This patch changes fuse_readpages() to send READ requests asynchronously. This makes it possible for userspace filesystems to utilize the kernel readahead logic instead of having to implement their own (resulting in double caching). Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/file.c | 44 +++++++++++++++++++++++++++----------------- 1 file changed, 27 insertions(+), 17 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 4a0b0f9a2179..a7ef5e716f3c 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -265,7 +265,7 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, req->file = file; req->in.numargs = 1; req->in.args[0].size = sizeof(struct fuse_read_in); - req->in.args[0].value = &inarg; + req->in.args[0].value = inarg; req->out.argpages = 1; req->out.argvar = 1; req->out.numargs = 1; @@ -311,21 +311,33 @@ static int fuse_readpage(struct file *file, struct page *page) return err; } -static int fuse_send_readpages(struct fuse_req *req, struct file *file, - struct inode *inode) +static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req) { - loff_t pos = page_offset(req->pages[0]); - size_t count = req->num_pages << PAGE_CACHE_SHIFT; - unsigned i; - req->out.page_zeroing = 1; - fuse_send_read(req, file, inode, pos, count); + int i; + + fuse_invalidate_attr(req->pages[0]->mapping->host); /* atime changed */ + for (i = 0; i < req->num_pages; i++) { struct page *page = req->pages[i]; if (!req->out.h.error) SetPageUptodate(page); + else + SetPageError(page); unlock_page(page); } - return req->out.h.error; + fuse_put_request(fc, req); +} + +static void fuse_send_readpages(struct fuse_req *req, struct file *file, + struct inode *inode) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + loff_t pos = page_offset(req->pages[0]); + size_t count = req->num_pages << PAGE_CACHE_SHIFT; + req->out.page_zeroing = 1; + req->end = fuse_readpages_end; + fuse_read_fill(req, file, inode, pos, count, FUSE_READ); + request_send_background(fc, req); } struct fuse_readpages_data { @@ -345,12 +357,12 @@ static int fuse_readpages_fill(void *_data, struct page *page) (req->num_pages == FUSE_MAX_PAGES_PER_REQ || (req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read || req->pages[req->num_pages - 1]->index + 1 != page->index)) { - int err = fuse_send_readpages(req, data->file, inode); - if (err) { + fuse_send_readpages(req, data->file, inode); + data->req = req = fuse_get_request(fc); + if (!req) { unlock_page(page); - return err; + return -EINTR; } - fuse_reset_request(req); } req->pages[req->num_pages] = page; req->num_pages ++; @@ -375,10 +387,8 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, return -EINTR; err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data); - if (!err && data.req->num_pages) - err = fuse_send_readpages(data.req, file, inode); - fuse_put_request(fc, data.req); - fuse_invalidate_attr(inode); /* atime changed */ + if (!err) + fuse_send_readpages(data.req, file, inode); return err; } -- cgit v1.2.2 From 095da6cbb6a1c54c19b11190218eb0fbac666b6d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jan 2006 22:14:52 -0800 Subject: [PATCH] fuse: fix bitfield race Fix race in setting bitfields of fuse_conn. Spotted by Andrew Morton. The two fields ->connected and ->mounted were always changed with the fuse_lock held. But other bitfields in the same structure were changed without the lock. In theory this could lead to losing the assignment of even the ones under lock. The chosen solution is to change these two fields to be a full unsigned type. The other bitfields aren't "important" enough to warrant the extra complexity of full locking or changing them to bitops. For all bitfields document why they are safe wrt. concurrent assignments. Also make the initialization of the 'num_waiting' atomic counter explicit. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/fuse_i.h | 24 +++++++++++++++++++++--- fs/fuse/inode.c | 2 ++ 2 files changed, 23 insertions(+), 3 deletions(-) (limited to 'fs/fuse') diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 7ed1d3c53b8a..46cf933aa3bf 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -94,6 +94,11 @@ struct fuse_out { /** Header returned from userspace */ struct fuse_out_header h; + /* + * The following bitfields are not changed during the request + * processing + */ + /** Last argument is variable length (can be shorter than arg->size) */ unsigned argvar:1; @@ -136,6 +141,12 @@ struct fuse_req { /** refcount */ atomic_t count; + /* + * The following bitfields are either set once before the + * request is queued or setting/clearing them is protected by + * fuse_lock + */ + /** True if the request has reply */ unsigned isreply:1; @@ -250,15 +261,22 @@ struct fuse_conn { u64 reqctr; /** Mount is active */ - unsigned mounted : 1; + unsigned mounted; /** Connection established, cleared on umount, connection abort and device release */ - unsigned connected : 1; + unsigned connected; - /** Connection failed (version mismatch) */ + /** Connection failed (version mismatch). Cannot race with + setting other bitfields since it is only set once in INIT + reply, before any other request, and never cleared */ unsigned conn_error : 1; + /* + * The following bitfields are only for optimization purposes + * and hence races in setting them will not cause malfunction + */ + /** Is fsync not implemented by fs? */ unsigned no_fsync : 1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 8683e7254d53..c755a0440a66 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -397,6 +397,7 @@ static struct fuse_conn *new_conn(void) init_rwsem(&fc->sbput_sem); kobj_set_kset_s(fc, connections_subsys); kobject_init(&fc->kobj); + atomic_set(&fc->num_waiting, 0); for (i = 0; i < FUSE_MAX_OUTSTANDING; i++) { struct fuse_req *req = fuse_request_alloc(); if (!req) { @@ -492,6 +493,7 @@ static void fuse_send_init(struct fuse_conn *fc) to be exactly one request available */ struct fuse_req *req = fuse_get_request(fc); struct fuse_init_in *arg = &req->misc.init_in; + arg->major = FUSE_KERNEL_VERSION; arg->minor = FUSE_KERNEL_MINOR_VERSION; req->in.h.opcode = FUSE_INIT; -- cgit v1.2.2