diff options
Diffstat (limited to 'fs')
173 files changed, 3482 insertions, 2845 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index a89f3cfe3c7d..c202930086ed 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -333,10 +333,6 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, goto err_names; init_rwsem(&v9ses->rename_sem); - rc = bdi_setup_and_register(&v9ses->bdi, "9p"); - if (rc) - goto err_names; - v9ses->uid = INVALID_UID; v9ses->dfltuid = V9FS_DEFUID; v9ses->dfltgid = V9FS_DEFGID; @@ -345,7 +341,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, if (IS_ERR(v9ses->clnt)) { rc = PTR_ERR(v9ses->clnt); p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n"); - goto err_bdi; + goto err_names; } v9ses->flags = V9FS_ACCESS_USER; @@ -415,8 +411,6 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, err_clnt: p9_client_destroy(v9ses->clnt); -err_bdi: - bdi_destroy(&v9ses->bdi); err_names: kfree(v9ses->uname); kfree(v9ses->aname); @@ -445,8 +439,6 @@ void v9fs_session_close(struct v9fs_session_info *v9ses) kfree(v9ses->uname); kfree(v9ses->aname); - bdi_destroy(&v9ses->bdi); - spin_lock(&v9fs_sessionlist_lock); list_del(&v9ses->slist); spin_unlock(&v9fs_sessionlist_lock); diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 443d12e02043..76eaf49abd3a 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -114,7 +114,6 @@ struct v9fs_session_info { kuid_t uid; /* if ACCESS_SINGLE, the uid that has access */ struct p9_client *clnt; /* 9p client */ struct list_head slist; /* list of sessions registered with v9fs */ - struct backing_dev_info bdi; struct rw_semaphore rename_sem; }; diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index de3ed8629196..a0965fb587a5 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -72,10 +72,12 @@ static int v9fs_set_super(struct super_block *s, void *data) * */ -static void +static int v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, int flags, void *data) { + int ret; + sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize_bits = fls(v9ses->maxdata - 1); sb->s_blocksize = 1 << sb->s_blocksize_bits; @@ -85,7 +87,11 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_xattr = v9fs_xattr_handlers; } else sb->s_op = &v9fs_super_ops; - sb->s_bdi = &v9ses->bdi; + + ret = super_setup_bdi(sb); + if (ret) + return ret; + if (v9ses->cache) sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE; @@ -99,6 +105,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, #endif save_mount_options(sb, data); + return 0; } /** @@ -138,7 +145,9 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, retval = PTR_ERR(sb); goto clunk_fid; } - v9fs_fill_super(sb, v9ses, flags, data); + retval = v9fs_fill_super(sb, v9ses, flags, data); + if (retval) + goto release_sb; if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) sb->s_d_op = &v9fs_cached_dentry_operations; diff --git a/fs/afs/callback.c b/fs/afs/callback.c index b29447e03ede..25d404d22cae 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -362,7 +362,7 @@ static void afs_callback_updater(struct work_struct *work) { struct afs_server *server; struct afs_vnode *vnode, *xvnode; - time_t now; + time64_t now; long timeout; int ret; @@ -370,7 +370,7 @@ static void afs_callback_updater(struct work_struct *work) _enter(""); - now = get_seconds(); + now = ktime_get_real_seconds(); /* find the first vnode to update */ spin_lock(&server->cb_lock); @@ -424,7 +424,8 @@ static void afs_callback_updater(struct work_struct *work) /* and then reschedule */ _debug("reschedule"); - vnode->update_at = get_seconds() + afs_vnode_update_timeout; + vnode->update_at = ktime_get_real_seconds() + + afs_vnode_update_timeout; spin_lock(&server->cb_lock); diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 2edbdcbf6432..3062cceb5c2a 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -187,7 +187,6 @@ static int afs_deliver_cb_callback(struct afs_call *call) struct afs_callback *cb; struct afs_server *server; __be32 *bp; - u32 tmp; int ret, loop; _enter("{%u}", call->unmarshall); @@ -249,9 +248,9 @@ static int afs_deliver_cb_callback(struct afs_call *call) if (ret < 0) return ret; - tmp = ntohl(call->tmp); - _debug("CB count: %u", tmp); - if (tmp != call->count && tmp != 0) + call->count2 = ntohl(call->tmp); + _debug("CB count: %u", call->count2); + if (call->count2 != call->count && call->count2 != 0) return -EBADMSG; call->offset = 0; call->unmarshall++; @@ -259,14 +258,14 @@ static int afs_deliver_cb_callback(struct afs_call *call) case 4: _debug("extract CB array"); ret = afs_extract_data(call, call->buffer, - call->count * 3 * 4, false); + call->count2 * 3 * 4, false); if (ret < 0) return ret; _debug("unmarshall CB array"); cb = call->request; bp = call->buffer; - for (loop = call->count; loop > 0; loop--, cb++) { + for (loop = call->count2; loop > 0; loop--, cb++) { cb->version = ntohl(*bp++); cb->expiry = ntohl(*bp++); cb->type = ntohl(*bp++); diff --git a/fs/afs/file.c b/fs/afs/file.c index ba7b71fba34b..0d5b8508869b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -30,6 +30,7 @@ static int afs_readpages(struct file *filp, struct address_space *mapping, const struct file_operations afs_file_operations = { .open = afs_open, + .flush = afs_flush, .release = afs_release, .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, @@ -184,10 +185,13 @@ int afs_page_filler(void *data, struct page *page) if (!req) goto enomem; + /* We request a full page. If the page is a partial one at the + * end of the file, the server will return a short read and the + * unmarshalling code will clear the unfilled space. + */ atomic_set(&req->usage, 1); req->pos = (loff_t)page->index << PAGE_SHIFT; - req->len = min_t(size_t, i_size_read(inode) - req->pos, - PAGE_SIZE); + req->len = PAGE_SIZE; req->nr_pages = 1; req->pages[0] = page; get_page(page); @@ -208,7 +212,13 @@ int afs_page_filler(void *data, struct page *page) fscache_uncache_page(vnode->cache, page); #endif BUG_ON(PageFsCache(page)); - goto error; + + if (ret == -EINTR || + ret == -ENOMEM || + ret == -ERESTARTSYS || + ret == -EAGAIN) + goto error; + goto io_error; } SetPageUptodate(page); @@ -227,10 +237,12 @@ int afs_page_filler(void *data, struct page *page) _leave(" = 0"); return 0; +io_error: + SetPageError(page); + goto error; enomem: ret = -ENOMEM; error: - SetPageError(page); unlock_page(page); _leave(" = %d", ret); return ret; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index ac8e766978dc..19f76ae36982 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -17,6 +17,12 @@ #include "afs_fs.h" /* + * We need somewhere to discard into in case the server helpfully returns more + * than we asked for in FS.FetchData{,64}. + */ +static u8 afs_discard_buffer[64]; + +/* * decode an AFSFid block */ static void xdr_decode_AFSFid(const __be32 **_bp, struct afs_fid *fid) @@ -105,7 +111,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp, vnode->vfs_inode.i_mode = mode; } - vnode->vfs_inode.i_ctime.tv_sec = status->mtime_server; + vnode->vfs_inode.i_ctime.tv_sec = status->mtime_client; vnode->vfs_inode.i_mtime = vnode->vfs_inode.i_ctime; vnode->vfs_inode.i_atime = vnode->vfs_inode.i_ctime; vnode->vfs_inode.i_version = data_version; @@ -139,7 +145,7 @@ static void xdr_decode_AFSCallBack(const __be32 **_bp, struct afs_vnode *vnode) vnode->cb_version = ntohl(*bp++); vnode->cb_expiry = ntohl(*bp++); vnode->cb_type = ntohl(*bp++); - vnode->cb_expires = vnode->cb_expiry + get_seconds(); + vnode->cb_expires = vnode->cb_expiry + ktime_get_real_seconds(); *_bp = bp; } @@ -315,7 +321,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) void *buffer; int ret; - _enter("{%u,%zu/%u;%u/%llu}", + _enter("{%u,%zu/%u;%llu/%llu}", call->unmarshall, call->offset, call->count, req->remain, req->actual_len); @@ -353,12 +359,6 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) req->actual_len |= ntohl(call->tmp); _debug("DATA length: %llu", req->actual_len); - /* Check that the server didn't want to send us extra. We - * might want to just discard instead, but that requires - * cooperation from AF_RXRPC. - */ - if (req->actual_len > req->len) - return -EBADMSG; req->remain = req->actual_len; call->offset = req->pos & (PAGE_SIZE - 1); @@ -368,6 +368,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->unmarshall++; begin_page: + ASSERTCMP(req->index, <, req->nr_pages); if (req->remain > PAGE_SIZE - call->offset) size = PAGE_SIZE - call->offset; else @@ -378,7 +379,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) /* extract the returned data */ case 3: - _debug("extract data %u/%llu %zu/%u", + _debug("extract data %llu/%llu %zu/%u", req->remain, req->actual_len, call->offset, call->count); buffer = kmap(req->pages[req->index]); @@ -389,19 +390,40 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (call->offset == PAGE_SIZE) { if (req->page_done) req->page_done(call, req); + req->index++; if (req->remain > 0) { - req->index++; call->offset = 0; + if (req->index >= req->nr_pages) { + call->unmarshall = 4; + goto begin_discard; + } goto begin_page; } } + goto no_more_data; + + /* Discard any excess data the server gave us */ + begin_discard: + case 4: + size = min_t(loff_t, sizeof(afs_discard_buffer), req->remain); + call->count = size; + _debug("extract discard %llu/%llu %zu/%u", + req->remain, req->actual_len, call->offset, call->count); + + call->offset = 0; + ret = afs_extract_data(call, afs_discard_buffer, call->count, true); + req->remain -= call->offset; + if (ret < 0) + return ret; + if (req->remain > 0) + goto begin_discard; no_more_data: call->offset = 0; - call->unmarshall++; + call->unmarshall = 5; /* extract the metadata */ - case 4: + case 5: ret = afs_extract_data(call, call->buffer, (21 + 3 + 6) * 4, false); if (ret < 0) @@ -416,16 +438,17 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->offset = 0; call->unmarshall++; - case 5: + case 6: break; } - if (call->count < PAGE_SIZE) { - buffer = kmap(req->pages[req->index]); - memset(buffer + call->count, 0, PAGE_SIZE - call->count); - kunmap(req->pages[req->index]); + for (; req->index < req->nr_pages; req->index++) { + if (call->count < PAGE_SIZE) + zero_user_segment(req->pages[req->index], + call->count, PAGE_SIZE); if (req->page_done) req->page_done(call, req); + call->count = 0; } _leave(" = 0 [done]"); @@ -711,8 +734,8 @@ int afs_fs_create(struct afs_server *server, memset(bp, 0, padsz); bp = (void *) bp + padsz; } - *bp++ = htonl(AFS_SET_MODE); - *bp++ = 0; /* mtime */ + *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); + *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(mode & S_IALLUGO); /* unix mode */ @@ -980,8 +1003,8 @@ int afs_fs_symlink(struct afs_server *server, memset(bp, 0, c_padsz); bp = (void *) bp + c_padsz; } - *bp++ = htonl(AFS_SET_MODE); - *bp++ = 0; /* mtime */ + *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); + *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(S_IRWXUGO); /* unix mode */ @@ -1180,8 +1203,8 @@ static int afs_fs_store_data64(struct afs_server *server, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique); - *bp++ = 0; /* mask */ - *bp++ = 0; /* mtime */ + *bp++ = htonl(AFS_SET_MTIME); /* mask */ + *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = 0; /* unix mode */ @@ -1213,7 +1236,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, _enter(",%x,{%x:%u},,", key_serial(wb->key), vnode->fid.vid, vnode->fid.vnode); - size = to - offset; + size = (loff_t)to - (loff_t)offset; if (first != last) size += (loff_t)(last - first) << PAGE_SHIFT; pos = (loff_t)first << PAGE_SHIFT; @@ -1257,8 +1280,8 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique); - *bp++ = 0; /* mask */ - *bp++ = 0; /* mtime */ + *bp++ = htonl(AFS_SET_MTIME); /* mask */ + *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = 0; /* unix mode */ diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1e4897a048d2..aae55dd15108 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -54,8 +54,21 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) inode->i_fop = &afs_dir_file_operations; break; case AFS_FTYPE_SYMLINK: - inode->i_mode = S_IFLNK | vnode->status.mode; - inode->i_op = &page_symlink_inode_operations; + /* Symlinks with a mode of 0644 are actually mountpoints. */ + if ((vnode->status.mode & 0777) == 0644) { + inode->i_flags |= S_AUTOMOUNT; + + spin_lock(&vnode->lock); + set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); + spin_unlock(&vnode->lock); + + inode->i_mode = S_IFDIR | 0555; + inode->i_op = &afs_mntpt_inode_operations; + inode->i_fop = &afs_mntpt_file_operations; + } else { + inode->i_mode = S_IFLNK | vnode->status.mode; + inode->i_op = &page_symlink_inode_operations; + } inode_nohighmem(inode); break; default: @@ -70,27 +83,15 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) set_nlink(inode, vnode->status.nlink); inode->i_uid = vnode->status.owner; - inode->i_gid = GLOBAL_ROOT_GID; + inode->i_gid = vnode->status.group; inode->i_size = vnode->status.size; - inode->i_ctime.tv_sec = vnode->status.mtime_server; + inode->i_ctime.tv_sec = vnode->status.mtime_client; inode->i_ctime.tv_nsec = 0; inode->i_atime = inode->i_mtime = inode->i_ctime; inode->i_blocks = 0; inode->i_generation = vnode->fid.unique; inode->i_version = vnode->status.data_version; inode->i_mapping->a_ops = &afs_fs_aops; - - /* check to see whether a symbolic link is really a mountpoint */ - if (vnode->status.type == AFS_FTYPE_SYMLINK) { - afs_mntpt_check_symlink(vnode, key); - - if (test_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags)) { - inode->i_mode = S_IFDIR | vnode->status.mode; - inode->i_op = &afs_mntpt_inode_operations; - inode->i_fop = &afs_mntpt_file_operations; - } - } - return 0; } @@ -245,12 +246,13 @@ struct inode *afs_iget(struct super_block *sb, struct key *key, vnode->cb_version = 0; vnode->cb_expiry = 0; vnode->cb_type = 0; - vnode->cb_expires = get_seconds(); + vnode->cb_expires = ktime_get_real_seconds(); } else { vnode->cb_version = cb->version; vnode->cb_expiry = cb->expiry; vnode->cb_type = cb->type; - vnode->cb_expires = vnode->cb_expiry + get_seconds(); + vnode->cb_expires = vnode->cb_expiry + + ktime_get_real_seconds(); } } @@ -323,7 +325,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) !test_bit(AFS_VNODE_CB_BROKEN, &vnode->flags) && !test_bit(AFS_VNODE_MODIFIED, &vnode->flags) && !test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) { - if (vnode->cb_expires < get_seconds() + 10) { + if (vnode->cb_expires < ktime_get_real_seconds() + 10) { _debug("callback expired"); set_bit(AFS_VNODE_CB_BROKEN, &vnode->flags); } else { @@ -444,7 +446,7 @@ void afs_evict_inode(struct inode *inode) mutex_lock(&vnode->permits_lock); permits = vnode->permits; - rcu_assign_pointer(vnode->permits, NULL); + RCU_INIT_POINTER(vnode->permits, NULL); mutex_unlock(&vnode->permits_lock); if (permits) call_rcu(&permits->rcu, afs_zap_permits); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 5dfa56903a2d..393672997cc2 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -11,6 +11,7 @@ #include <linux/compiler.h> #include <linux/kernel.h> +#include <linux/ktime.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/rxrpc.h> @@ -90,7 +91,10 @@ struct afs_call { unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ unsigned first_offset; /* offset into mapping[first] */ - unsigned last_to; /* amount of mapping[last] */ + union { + unsigned last_to; /* amount of mapping[last] */ + unsigned count2; /* count used in unmarshalling */ + }; unsigned char unmarshall; /* unmarshalling phase */ bool incoming; /* T if incoming call */ bool send_pages; /* T if data from mapping should be sent */ @@ -127,12 +131,11 @@ struct afs_call_type { */ struct afs_read { loff_t pos; /* Where to start reading */ - loff_t len; /* How much to read */ + loff_t len; /* How much we're asking for */ loff_t actual_len; /* How much we're actually getting */ + loff_t remain; /* Amount remaining */ atomic_t usage; - unsigned int remain; /* Amount remaining */ unsigned int index; /* Which page we're reading into */ - unsigned int pg_offset; /* Offset in page we're at */ unsigned int nr_pages; void (*page_done)(struct afs_call *, struct afs_read *); struct page *pages[]; @@ -247,7 +250,7 @@ struct afs_cache_vhash { */ struct afs_vlocation { atomic_t usage; - time_t time_of_death; /* time at which put reduced usage to 0 */ + time64_t time_of_death; /* time at which put reduced usage to 0 */ struct list_head link; /* link in cell volume location list */ struct list_head grave; /* link in master graveyard list */ struct list_head update; /* link in master update list */ @@ -258,7 +261,7 @@ struct afs_vlocation { struct afs_cache_vlocation vldb; /* volume information DB record */ struct afs_volume *vols[3]; /* volume access record pointer (index by type) */ wait_queue_head_t waitq; /* status change waitqueue */ - time_t update_at; /* time at which record should be updated */ + time64_t update_at; /* time at which record should be updated */ spinlock_t lock; /* access lock */ afs_vlocation_state_t state; /* volume location state */ unsigned short upd_rej_cnt; /* ENOMEDIUM count during update */ @@ -271,7 +274,7 @@ struct afs_vlocation { */ struct afs_server { atomic_t usage; - time_t time_of_death; /* time at which put reduced usage to 0 */ + time64_t time_of_death; /* time at which put reduced usage to 0 */ struct in_addr addr; /* server address */ struct afs_cell *cell; /* cell in which server resides */ struct list_head link; /* link in cell's server list */ @@ -315,7 +318,6 @@ struct afs_volume { unsigned short rjservers; /* number of servers discarded due to -ENOMEDIUM */ struct afs_server *servers[8]; /* servers on which volume resides (ordered) */ struct rw_semaphore server_sem; /* lock for accessing current server */ - struct backing_dev_info bdi; }; /* @@ -374,8 +376,8 @@ struct afs_vnode { struct rb_node server_rb; /* link in server->fs_vnodes */ struct rb_node cb_promise; /* link in server->cb_promises */ struct work_struct cb_broken_work; /* work to be done on callback break */ - time_t cb_expires; /* time at which callback expires */ - time_t cb_expires_at; /* time used to order cb_promise */ + time64_t cb_expires; /* time at which callback expires */ + time64_t cb_expires_at; /* time used to order cb_promise */ unsigned cb_version; /* callback version */ unsigned cb_expiry; /* callback expiry time */ afs_callback_type_t cb_type; /* type of callback */ @@ -557,7 +559,6 @@ extern const struct inode_operations afs_autocell_inode_operations; extern const struct file_operations afs_mntpt_file_operations; extern struct vfsmount *afs_d_automount(struct path *); -extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *); extern void afs_mntpt_kill_timer(void); /* @@ -718,6 +719,7 @@ extern int afs_writepages(struct address_space *, struct writeback_control *); extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *); extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *); extern int afs_writeback_all(struct afs_vnode *); +extern int afs_flush(struct file *, fl_owner_t); extern int afs_fsync(struct file *, loff_t, loff_t, int); diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 91ea1aa0d8b3..100b207efc9e 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -84,6 +84,8 @@ int afs_abort_to_error(u32 abort_code) case RXKADDATALEN: return -EKEYREJECTED; case RXKADILLEGALLEVEL: return -EKEYREJECTED; + case RXGEN_OPCODE: return -ENOTSUPP; + default: return -EREMOTEIO; } } diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index d4fb0afc0097..bd3b65cde282 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -47,59 +47,6 @@ static DECLARE_DELAYED_WORK(afs_mntpt_expiry_timer, afs_mntpt_expiry_timed_out); static unsigned long afs_mntpt_expiry_timeout = 10 * 60; /* - * check a symbolic link to see whether it actually encodes a mountpoint - * - sets the AFS_VNODE_MOUNTPOINT flag on the vnode appropriately - */ -int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key) -{ - struct page *page; - size_t size; - char *buf; - int ret; - - _enter("{%x:%u,%u}", - vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); - - /* read the contents of the symlink into the pagecache */ - page = read_cache_page(AFS_VNODE_TO_I(vnode)->i_mapping, 0, - afs_page_filler, key); - if (IS_ERR(page)) { - ret = PTR_ERR(page); - goto out; - } - - ret = -EIO; - if (PageError(page)) - goto out_free; - - buf = kmap(page); - - /* examine the symlink's contents */ - size = vnode->status.size; - _debug("symlink to %*.*s", (int) size, (int) size, buf); - - if (size > 2 && - (buf[0] == '%' || buf[0] == '#') && - buf[size - 1] == '.' - ) { - _debug("symlink is a mountpoint"); - spin_lock(&vnode->lock); - set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); - vnode->vfs_inode.i_flags |= S_AUTOMOUNT; - spin_unlock(&vnode->lock); - } - - ret = 0; - - kunmap(page); -out_free: - put_page(page); -out: - _leave(" = %d", ret); - return ret; -} - -/* * no valid lookup procedure on this sort of dir */ static struct dentry *afs_mntpt_lookup(struct inode *dir, diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 419ef05dcb5e..d5990eb160bd 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -259,67 +259,74 @@ void afs_flat_call_destructor(struct afs_call *call) call->buffer = NULL; } +#define AFS_BVEC_MAX 8 + +/* + * Load the given bvec with the next few pages. + */ +static void afs_load_bvec(struct afs_call *call, struct msghdr *msg, + struct bio_vec *bv, pgoff_t first, pgoff_t last, + unsigned offset) +{ + struct page *pages[AFS_BVEC_MAX]; + unsigned int nr, n, i, to, bytes = 0; + + nr = min_t(pgoff_t, last - first + 1, AFS_BVEC_MAX); + n = find_get_pages_contig(call->mapping, first, nr, pages); + ASSERTCMP(n, ==, nr); + + msg->msg_flags |= MSG_MORE; + for (i = 0; i < nr; i++) { + to = PAGE_SIZE; + if (first + i >= last) { + to = call->last_to; + msg->msg_flags &= ~MSG_MORE; + } + bv[i].bv_page = pages[i]; + bv[i].bv_len = to - offset; + bv[i].bv_offset = offset; + bytes += to - offset; + offset = 0; + } + + iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes); +} + /* * attach the data from a bunch of pages on an inode to a call */ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) { - struct page *pages[8]; - unsigned count, n, loop, offset, to; + struct bio_vec bv[AFS_BVEC_MAX]; + unsigned int bytes, nr, loop, offset; pgoff_t first = call->first, last = call->last; int ret; - _enter(""); - offset = call->first_offset; call->first_offset = 0; do { - _debug("attach %lx-%lx", first, last); - - count = last - first + 1; - if (count > ARRAY_SIZE(pages)) - count = ARRAY_SIZE(pages); - n = find_get_pages_contig(call->mapping, first, count, pages); - ASSERTCMP(n, ==, count); - - loop = 0; - do { - struct bio_vec bvec = {.bv_page = pages[loop], - .bv_offset = offset}; - msg->msg_flags = 0; - to = PAGE_SIZE; - if (first + loop >= last) - to = call->last_to; - else - msg->msg_flags = MSG_MORE; - bvec.bv_len = to - offset; - offset = 0; - - _debug("- range %u-%u%s", - offset, to, msg->msg_flags ? " [more]" : ""); - iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, - &bvec, 1, to - offset); - - /* have to change the state *before* sending the last - * packet as RxRPC might give us the reply before it - * returns from sending the request */ - if (first + loop >= last) - call->state = AFS_CALL_AWAIT_REPLY; - ret = rxrpc_kernel_send_data(afs_socket, call->rxcall, - msg, to - offset); - if (ret < 0) - break; - } while (++loop < count); - first += count; - - for (loop = 0; loop < count; loop++) - put_page(pages[loop]); + afs_load_bvec(call, msg, bv, first, last, offset); + offset = 0; + bytes = msg->msg_iter.count; + nr = msg->msg_iter.nr_segs; + + /* Have to change the state *before* sending the last + * packet as RxRPC might give us the reply before it + * returns from sending the request. + */ + if (first + nr - 1 >= last) + call->state = AFS_CALL_AWAIT_REPLY; + ret = rxrpc_kernel_send_data(afs_socket, call->rxcall, + msg, bytes); + for (loop = 0; loop < nr; loop++) + put_page(bv[loop].bv_page); if (ret < 0) break; + + first += nr; } while (first <= last); - _leave(" = %d", ret); return ret; } @@ -333,6 +340,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, struct rxrpc_call *rxcall; struct msghdr msg; struct kvec iov[1]; + size_t offset; + u32 abort_code; int ret; _enter("%x,{%d},", addr->s_addr, ntohs(call->port)); @@ -381,9 +390,11 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, msg.msg_controllen = 0; msg.msg_flags = (call->send_pages ? MSG_MORE : 0); - /* have to change the state *before* sending the last packet as RxRPC - * might give us the reply before it returns from sending the - * request */ + /* We have to change the state *before* sending the last packet as + * rxrpc might give us the reply before it returns from sending the + * request. Further, if the send fails, we may already have been given + * a notification and may have collected it. + */ if (!call->send_pages) call->state = AFS_CALL_AWAIT_REPLY; ret = rxrpc_kernel_send_data(afs_socket, rxcall, @@ -405,7 +416,17 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, return afs_wait_for_call_to_complete(call); error_do_abort: - rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, -ret, "KSD"); + call->state = AFS_CALL_COMPLETE; + if (ret != -ECONNABORTED) { + rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, + ret, "KSD"); + } else { + abort_code = 0; + offset = 0; + rxrpc_kernel_recv_data(afs_socket, rxcall, NULL, 0, &offset, + false, &abort_code); + ret = call->type->abort_to_error(abort_code); + } error_kill_call: afs_put_call(call); _leave(" = %d", ret); @@ -452,16 +473,18 @@ static void afs_deliver_to_call(struct afs_call *call) case -EINPROGRESS: case -EAGAIN: goto out; + case -ECONNABORTED: + goto call_complete; case -ENOTCONN: abort_code = RX_CALL_DEAD; rxrpc_kernel_abort_call(afs_socket, call->rxcall, - abort_code, -ret, "KNC"); - goto do_abort; + abort_code, ret, "KNC"); + goto save_error; case -ENOTSUPP: - abort_code = RX_INVALID_OPERATION; + abort_code = RXGEN_OPCODE; rxrpc_kernel_abort_call(afs_socket, call->rxcall, - abort_code, -ret, "KIV"); - goto do_abort; + abort_code, ret, "KIV"); + goto save_error; case -ENODATA: case -EBADMSG: case -EMSGSIZE: @@ -470,8 +493,8 @@ static void afs_deliver_to_call(struct afs_call *call) if (call->state != AFS_CALL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(afs_socket, call->rxcall, - abort_code, EBADMSG, "KUM"); - goto do_abort; + abort_code, -EBADMSG, "KUM"); + goto save_error; } } @@ -482,8 +505,9 @@ out: _leave(""); return; -do_abort: +save_error: call->error = ret; +call_complete: call->state = AFS_CALL_COMPLETE; goto done; } @@ -493,7 +517,6 @@ do_abort: */ static int afs_wait_for_call_to_complete(struct afs_call *call) { - const char *abort_why; int ret; DECLARE_WAITQUEUE(myself, current); @@ -512,13 +535,8 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) continue; } - abort_why = "KWC"; - ret = call->error; - if (call->state == AFS_CALL_COMPLETE) - break; - abort_why = "KWI"; - ret = -EINTR; - if (signal_pending(current)) + if (call->state == AFS_CALL_COMPLETE || + signal_pending(current)) break; schedule(); } @@ -526,13 +544,14 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) remove_wait_queue(&call->waitq, &myself); __set_current_state(TASK_RUNNING); - /* kill the call */ + /* Kill off the call if it's still live. */ if (call->state < AFS_CALL_COMPLETE) { - _debug("call incomplete"); + _debug("call interrupted"); rxrpc_kernel_abort_call(afs_socket, call->rxcall, - RX_CALL_DEAD, -ret, abort_why); + RX_USER_ABORT, -EINTR, "KWI"); } + ret = call->error; _debug("call complete"); afs_put_call(call); _leave(" = %d", ret); @@ -735,7 +754,7 @@ void afs_send_empty_reply(struct afs_call *call) case -ENOMEM: _debug("oom"); rxrpc_kernel_abort_call(afs_socket, call->rxcall, - RX_USER_ABORT, ENOMEM, "KOO"); + RX_USER_ABORT, -ENOMEM, "KOO"); default: _leave(" [error]"); return; @@ -773,7 +792,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) if (n == -ENOMEM) { _debug("oom"); rxrpc_kernel_abort_call(afs_socket, call->rxcall, - RX_USER_ABORT, ENOMEM, "KOO"); + RX_USER_ABORT, -ENOMEM, "KOO"); } _leave(" [error]"); } diff --git a/fs/afs/security.c b/fs/afs/security.c index 8d010422dc89..ecb86a670180 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -114,7 +114,7 @@ void afs_clear_permits(struct afs_vnode *vnode) mutex_lock(&vnode->permits_lock); permits = vnode->permits; - rcu_assign_pointer(vnode->permits, NULL); + RCU_INIT_POINTER(vnode->permits, NULL); mutex_unlock(&vnode->permits_lock); if (permits) @@ -340,17 +340,22 @@ int afs_permission(struct inode *inode, int mask) } else { if (!(access & AFS_ACE_LOOKUP)) goto permission_denied; + if ((mask & MAY_EXEC) && !(inode->i_mode & S_IXUSR)) + goto permission_denied; if (mask & (MAY_EXEC | MAY_READ)) { if (!(access & AFS_ACE_READ)) goto permission_denied; + if (!(inode->i_mode & S_IRUSR)) + goto permission_denied; } else if (mask & MAY_WRITE) { if (!(access & AFS_ACE_WRITE)) goto permission_denied; + if (!(inode->i_mode & S_IWUSR)) + goto permission_denied; } } key_put(key); - ret = generic_permission(inode, mask); _leave(" = %d", ret); return ret; diff --git a/fs/afs/server.c b/fs/afs/server.c index d4066ab7dd55..c001b1f2455f 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -242,7 +242,7 @@ void afs_put_server(struct afs_server *server) spin_lock(&afs_server_graveyard_lock); if (atomic_read(&server->usage) == 0) { list_move_tail(&server->grave, &afs_server_graveyard); - server->time_of_death = get_seconds(); + server->time_of_death = ktime_get_real_seconds(); queue_delayed_work(afs_wq, &afs_server_reaper, afs_server_timeout * HZ); } @@ -277,9 +277,9 @@ static void afs_reap_server(struct work_struct *work) LIST_HEAD(corpses); struct afs_server *server; unsigned long delay, expiry; - time_t now; + time64_t now; - now = get_seconds(); + now = ktime_get_real_seconds(); spin_lock(&afs_server_graveyard_lock); while (!list_empty(&afs_server_graveyard)) { diff --git a/fs/afs/super.c b/fs/afs/super.c index fbdb022b75a2..c79633e5cfd8 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -319,7 +319,10 @@ static int afs_fill_super(struct super_block *sb, sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; - sb->s_bdi = &as->volume->bdi; + ret = super_setup_bdi(sb); + if (ret) + return ret; + sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE; strlcpy(sb->s_id, as->volume->vlocation->vldb.name, sizeof(sb->s_id)); /* allocate the root inode and dentry */ diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index d7d8dd8c0b31..37b7c3b342a6 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -340,7 +340,8 @@ static void afs_vlocation_queue_for_updates(struct afs_vlocation *vl) struct afs_vlocation *xvl; /* wait at least 10 minutes before updating... */ - vl->update_at = get_seconds() + afs_vlocation_update_timeout; + vl->update_at = ktime_get_real_seconds() + + afs_vlocation_update_timeout; spin_lock(&afs_vlocation_updates_lock); @@ -506,7 +507,7 @@ void afs_put_vlocation(struct afs_vlocation *vl) if (atomic_read(&vl->usage) == 0) { _debug("buried"); list_move_tail(&vl->grave, &afs_vlocation_graveyard); - vl->time_of_death = get_seconds(); + vl->time_of_death = ktime_get_real_seconds(); queue_delayed_work(afs_wq, &afs_vlocation_reap, afs_vlocation_timeout * HZ); @@ -543,11 +544,11 @@ static void afs_vlocation_reaper(struct work_struct *work) LIST_HEAD(corpses); struct afs_vlocation *vl; unsigned long delay, expiry; - time_t now; + time64_t now; _enter(""); - now = get_seconds(); + now = ktime_get_real_seconds(); spin_lock(&afs_vlocation_graveyard_lock); while (!list_empty(&afs_vlocation_graveyard)) { @@ -622,13 +623,13 @@ static void afs_vlocation_updater(struct work_struct *work) { struct afs_cache_vlocation vldb; struct afs_vlocation *vl, *xvl; - time_t now; + time64_t now; long timeout; int ret; _enter(""); - now = get_seconds(); + now = ktime_get_real_seconds(); /* find a record to update */ spin_lock(&afs_vlocation_updates_lock); @@ -684,7 +685,8 @@ static void afs_vlocation_updater(struct work_struct *work) /* and then reschedule */ _debug("reschedule"); - vl->update_at = get_seconds() + afs_vlocation_update_timeout; + vl->update_at = ktime_get_real_seconds() + + afs_vlocation_update_timeout; spin_lock(&afs_vlocation_updates_lock); diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 546f9d01710b..db73d6dad02b 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -106,11 +106,6 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params) volume->cell = params->cell; volume->vid = vlocation->vldb.vid[params->type]; - volume->bdi.ra_pages = VM_MAX_READAHEAD*1024/PAGE_SIZE; - ret = bdi_setup_and_register(&volume->bdi, "afs"); - if (ret) - goto error_bdi; - init_rwsem(&volume->server_sem); /* look up all the applicable server records */ @@ -156,8 +151,6 @@ error: return ERR_PTR(ret); error_discard: - bdi_destroy(&volume->bdi); -error_bdi: up_write(¶ms->cell->vl_sem); for (loop = volume->nservers - 1; loop >= 0; loop--) @@ -207,7 +200,6 @@ void afs_put_volume(struct afs_volume *volume) for (loop = volume->nservers - 1; loop >= 0; loop--) afs_put_server(volume->servers[loop]); - bdi_destroy(&volume->bdi); kfree(volume); _leave(" [destroyed]"); diff --git a/fs/afs/write.c b/fs/afs/write.c index c83c1a0e851f..2d2fccd5044b 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -84,10 +84,9 @@ void afs_put_writeback(struct afs_writeback *wb) * partly or wholly fill a page that's under preparation for writing */ static int afs_fill_page(struct afs_vnode *vnode, struct key *key, - loff_t pos, struct page *page) + loff_t pos, unsigned int len, struct page *page) { struct afs_read *req; - loff_t i_size; int ret; _enter(",,%llu", (unsigned long long)pos); @@ -99,14 +98,10 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key, atomic_set(&req->usage, 1); req->pos = pos; + req->len = len; req->nr_pages = 1; req->pages[0] = page; - - i_size = i_size_read(&vnode->vfs_inode); - if (pos + PAGE_SIZE > i_size) - req->len = i_size - pos; - else - req->len = PAGE_SIZE; + get_page(page); ret = afs_vnode_fetch_data(vnode, key, req); afs_put_read(req); @@ -159,12 +154,12 @@ int afs_write_begin(struct file *file, struct address_space *mapping, kfree(candidate); return -ENOMEM; } - *pagep = page; - /* page won't leak in error case: it eventually gets cleaned off LRU */ if (!PageUptodate(page) && len != PAGE_SIZE) { - ret = afs_fill_page(vnode, key, index << PAGE_SHIFT, page); + ret = afs_fill_page(vnode, key, pos & PAGE_MASK, PAGE_SIZE, page); if (ret < 0) { + unlock_page(page); + put_page(page); kfree(candidate); _leave(" = %d [prep]", ret); return ret; @@ -172,6 +167,9 @@ int afs_write_begin(struct file *file, struct address_space *mapping, SetPageUptodate(page); } + /* page won't leak in error case: it eventually gets cleaned off LRU */ + *pagep = page; + try_again: spin_lock(&vnode->writeback_lock); @@ -233,7 +231,7 @@ flush_conflicting_wb: if (wb->state == AFS_WBACK_PENDING) wb->state = AFS_WBACK_CONFLICTING; spin_unlock(&vnode->writeback_lock); - if (PageDirty(page)) { + if (clear_page_dirty_for_io(page)) { ret = afs_write_back_from_locked_page(wb, page); if (ret < 0) { afs_put_writeback(candidate); @@ -257,7 +255,9 @@ int afs_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); + struct key *key = file->private_data; loff_t i_size, maybe_i_size; + int ret; _enter("{%x:%u},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); @@ -273,6 +273,20 @@ int afs_write_end(struct file *file, struct address_space *mapping, spin_unlock(&vnode->writeback_lock); } + if (!PageUptodate(page)) { + if (copied < len) { + /* Try and load any missing data from the server. The + * unmarshalling routine will take care of clearing any + * bits that are beyond the EOF. + */ + ret = afs_fill_page(vnode, key, pos + copied, + len - copied, page); + if (ret < 0) + return ret; + } + SetPageUptodate(page); + } + set_page_dirty(page); if (PageDirty(page)) _debug("dirtied"); @@ -307,10 +321,14 @@ static void afs_kill_pages(struct afs_vnode *vnode, bool error, ASSERTCMP(pv.nr, ==, count); for (loop = 0; loop < count; loop++) { - ClearPageUptodate(pv.pages[loop]); + struct page *page = pv.pages[loop]; + ClearPageUptodate(page); if (error) - SetPageError(pv.pages[loop]); - end_page_writeback(pv.pages[loop]); + SetPageError(page); + if (PageWriteback(page)) + end_page_writeback(page); + if (page->index >= first) + first = page->index + 1; } __pagevec_release(&pv); @@ -335,8 +353,6 @@ static int afs_write_back_from_locked_page(struct afs_writeback *wb, _enter(",%lx", primary_page->index); count = 1; - if (!clear_page_dirty_for_io(primary_page)) - BUG(); if (test_set_page_writeback(primary_page)) BUG(); @@ -502,17 +518,17 @@ static int afs_writepages_region(struct address_space *mapping, */ lock_page(page); - if (page->mapping != mapping) { + if (page->mapping != mapping || !PageDirty(page)) { unlock_page(page); put_page(page); continue; } - if (wbc->sync_mode != WB_SYNC_NONE) - wait_on_page_writeback(page); - - if (PageWriteback(page) || !PageDirty(page)) { + if (PageWriteback(page)) { unlock_page(page); + if (wbc->sync_mode != WB_SYNC_NONE) + wait_on_page_writeback(page); + put_page(page); continue; } @@ -523,6 +539,8 @@ static int afs_writepages_region(struct address_space *mapping, wb->state = AFS_WBACK_WRITING; spin_unlock(&wb->vnode->writeback_lock); + if (!clear_page_dirty_for_io(page)) + BUG(); ret = afs_write_back_from_locked_page(wb, page); unlock_page(page); put_page(page); @@ -746,6 +764,20 @@ out: } /* + * Flush out all outstanding writes on a file opened for writing when it is + * closed. + */ +int afs_flush(struct file *file, fl_owner_t id) +{ + _enter(""); + + if ((file->f_mode & FMODE_WRITE) == 0) + return 0; + + return vfs_fsync(file, 0); +} + +/* * notification that a previously read-only page is about to become writable * - if it returns an error, the caller will deliver a bus error signal */ diff --git a/fs/block_dev.c b/fs/block_dev.c index 2eca00ec4370..9ccabe3bb7de 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -885,6 +885,8 @@ static void bdev_evict_inode(struct inode *inode) spin_lock(&bdev_lock); list_del_init(&bdev->bd_list); spin_unlock(&bdev_lock); + /* Detach inode from wb early as bdi_put() may free bdi->wb */ + inode_detach_wb(inode); if (bdev->bd_bdi != &noop_backing_dev_info) { bdi_put(bdev->bd_bdi); bdev->bd_bdi = &noop_backing_dev_info; @@ -1451,7 +1453,6 @@ int revalidate_disk(struct gendisk *disk) if (disk->fops->revalidate_disk) ret = disk->fops->revalidate_disk(disk); - blk_integrity_revalidate(disk); bdev = bdget_disk(disk, 0); if (!bdev) return ret; @@ -1556,8 +1557,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; - if (bdev->bd_bdi == &noop_backing_dev_info) - bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); if (!partno) { ret = -ENXIO; @@ -1622,6 +1621,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); } + + if (bdev->bd_bdi == &noop_backing_dev_info) + bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); } else { if (bdev->bd_contains == bdev) { ret = 0; @@ -1653,8 +1655,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = NULL; bdev->bd_part = NULL; bdev->bd_queue = NULL; - bdi_put(bdev->bd_bdi); - bdev->bd_bdi = &noop_backing_dev_info; if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; @@ -1876,12 +1876,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) kill_bdev(bdev); bdev_write_inode(bdev); - /* - * Detaching bdev inode from its wb in __destroy_inode() - * is too late: the queue which embeds its bdi (along with - * root wb) can be gone as soon as we put_disk() below. - */ - inode_detach_wb(bdev->bd_inode); } if (bdev->bd_contains == bdev) { if (disk->fops->release) @@ -2074,7 +2068,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, loff_t len) { struct block_device *bdev = I_BDEV(bdev_file_inode(file)); - struct request_queue *q = bdev_get_queue(bdev); struct address_space *mapping; loff_t end = start + len - 1; loff_t isize; @@ -2110,18 +2103,13 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, - GFP_KERNEL, false); + GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: - /* Only punch if the device can do zeroing discard. */ - if (!blk_queue_discard(q) || !q->limits.discard_zeroes_data) - return -EOPNOTSUPP; - error = blkdev_issue_discard(bdev, start >> 9, len >> 9, - GFP_KERNEL, 0); + error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, + GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: - if (!blk_queue_discard(q)) - return -EOPNOTSUPP; error = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0); break; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 29b7fc28c607..3e21211e99c3 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -810,7 +810,6 @@ struct btrfs_fs_info { struct btrfs_super_block *super_for_commit; struct super_block *sb; struct inode *btree_inode; - struct backing_dev_info bdi; struct mutex tree_log_mutex; struct mutex transaction_kthread_mutex; struct mutex cleaner_mutex; @@ -1259,7 +1258,7 @@ struct btrfs_root { atomic_t will_be_snapshoted; /* For qgroup metadata space reserve */ - atomic_t qgroup_meta_rsv; + atomic64_t qgroup_meta_rsv; }; static inline u32 btrfs_inode_sectorsize(const struct inode *inode) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 08b74daf35d0..061c1d1f774f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1342,7 +1342,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, atomic_set(&root->orphan_inodes, 0); atomic_set(&root->refs, 1); atomic_set(&root->will_be_snapshoted, 0); - atomic_set(&root->qgroup_meta_rsv, 0); + atomic64_set(&root->qgroup_meta_rsv, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; @@ -1808,21 +1808,6 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits) return ret; } -static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) -{ - int err; - - err = bdi_setup_and_register(bdi, "btrfs"); - if (err) - return err; - - bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE; - bdi->congested_fn = btrfs_congested_fn; - bdi->congested_data = info; - bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; - return 0; -} - /* * called by the kthread helper functions to finally call the bio end_io * functions. This is where read checksum verification actually happens @@ -2601,16 +2586,10 @@ int open_ctree(struct super_block *sb, goto fail; } - ret = setup_bdi(fs_info, &fs_info->bdi); - if (ret) { - err = ret; - goto fail_srcu; - } - ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); if (ret) { err = ret; - goto fail_bdi; + goto fail_srcu; } fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); @@ -2718,7 +2697,6 @@ int open_ctree(struct super_block *sb, sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); - sb->s_bdi = &fs_info->bdi; btrfs_init_btree_inode(fs_info); @@ -2915,9 +2893,12 @@ int open_ctree(struct super_block *sb, goto fail_sb_buffer; } - fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super); - fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages, - SZ_4M / PAGE_SIZE); + sb->s_bdi->congested_fn = btrfs_congested_fn; + sb->s_bdi->congested_data = fs_info; + sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; + sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE; + sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); + sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE); sb->s_blocksize = sectorsize; sb->s_blocksize_bits = blksize_bits(sectorsize); @@ -3285,8 +3266,6 @@ fail_delalloc_bytes: percpu_counter_destroy(&fs_info->delalloc_bytes); fail_dirty_metadata_bytes: percpu_counter_destroy(&fs_info->dirty_metadata_bytes); -fail_bdi: - bdi_destroy(&fs_info->bdi); fail_srcu: cleanup_srcu_struct(&fs_info->subvol_srcu); fail: @@ -4007,7 +3986,6 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); percpu_counter_destroy(&fs_info->bio_counter); - bdi_destroy(&fs_info->bdi); cleanup_srcu_struct(&fs_info->subvol_srcu); btrfs_free_stripe_hash_table(fs_info); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 28e81922a21c..27fdb250b446 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1714,7 +1714,8 @@ static int __process_pages_contig(struct address_space *mapping, * can we find nothing at @index. */ ASSERT(page_ops & PAGE_LOCK); - return ret; + err = -EAGAIN; + goto out; } for (i = 0; i < ret; i++) { @@ -2583,26 +2584,36 @@ static void end_bio_extent_readpage(struct bio *bio) if (tree->ops) { ret = tree->ops->readpage_io_failed_hook(page, mirror); - if (!ret && !bio->bi_error) - uptodate = 1; - } else { + if (ret == -EAGAIN) { + /* + * Data inode's readpage_io_failed_hook() always + * returns -EAGAIN. + * + * The generic bio_readpage_error handles errors + * the following way: If possible, new read + * requests are created and submitted and will + * end up in end_bio_extent_readpage as well (if + * we're lucky, not in the !uptodate case). In + * that case it returns 0 and we just go on with + * the next page in our bio. If it can't handle + * the error it will return -EIO and we remain + * responsible for that page. + */ + ret = bio_readpage_error(bio, offset, page, + start, end, mirror); + if (ret == 0) { + uptodate = !bio->bi_error; + offset += len; + continue; + } + } + /* - * The generic bio_readpage_error handles errors the - * following way: If possible, new read requests are - * created and submitted and will end up in - * end_bio_extent_readpage as well (if we're lucky, not - * in the !uptodate case). In that case it returns 0 and - * we just go on with the next page in our bio. If it - * can't handle the error it will return -EIO and we - * remain responsible for that page. + * metadata's readpage_io_failed_hook() always returns + * -EIO and fixes nothing. -EIO is also returned if + * data inode error could not be fixed. */ - ret = bio_readpage_error(bio, offset, page, start, end, - mirror); - if (ret == 0) { - uptodate = !bio->bi_error; - offset += len; - continue; - } + ASSERT(ret == -EIO); } readpage_ok: if (likely(uptodate)) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c40060cc481f..5e71f1ea3391 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6709,6 +6709,20 @@ static noinline int uncompress_inline(struct btrfs_path *path, max_size = min_t(unsigned long, PAGE_SIZE, max_size); ret = btrfs_decompress(compress_type, tmp, page, extent_offset, inline_size, max_size); + + /* + * decompression code contains a memset to fill in any space between the end + * of the uncompressed data and the end of max_size in case the decompressed + * data ends up shorter than ram_bytes. That doesn't cover the hole between + * the end of an inline extent and the beginning of the next block, so we + * cover that region here. + */ + + if (max_size + pg_offset < PAGE_SIZE) { + char *map = kmap(page); + memset(map + pg_offset + max_size, 0, PAGE_SIZE - max_size - pg_offset); + kunmap(page); + } kfree(tmp); return ret; } @@ -7896,7 +7910,6 @@ struct btrfs_retry_complete { static void btrfs_retry_endio_nocsum(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; - struct inode *inode; struct bio_vec *bvec; int i; @@ -7904,12 +7917,12 @@ static void btrfs_retry_endio_nocsum(struct bio *bio) goto end; ASSERT(bio->bi_vcnt == 1); - inode = bio->bi_io_vec->bv_page->mapping->host; - ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode)); + ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode)); done->uptodate = 1; bio_for_each_segment_all(bvec, bio, i) - clean_io_failure(BTRFS_I(done->inode), done->start, bvec->bv_page, 0); + clean_io_failure(BTRFS_I(done->inode), done->start, + bvec->bv_page, 0); end: complete(&done->done); bio_put(bio); @@ -7959,8 +7972,10 @@ next_block_or_try_again: start += sectorsize; - if (nr_sectors--) { + nr_sectors--; + if (nr_sectors) { pgoff += sectorsize; + ASSERT(pgoff < PAGE_SIZE); goto next_block_or_try_again; } } @@ -7972,9 +7987,7 @@ static void btrfs_retry_endio(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); - struct inode *inode; struct bio_vec *bvec; - u64 start; int uptodate; int ret; int i; @@ -7984,11 +7997,8 @@ static void btrfs_retry_endio(struct bio *bio) uptodate = 1; - start = done->start; - ASSERT(bio->bi_vcnt == 1); - inode = bio->bi_io_vec->bv_page->mapping->host; - ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode)); + ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode)); bio_for_each_segment_all(bvec, bio, i) { ret = __readpage_endio_check(done->inode, io_bio, i, @@ -8066,8 +8076,10 @@ next: ASSERT(nr_sectors); - if (--nr_sectors) { + nr_sectors--; + if (nr_sectors) { pgoff += sectorsize; + ASSERT(pgoff < PAGE_SIZE); goto next_block; } } @@ -10509,9 +10521,9 @@ out_inode: } __attribute__((const)) -static int dummy_readpage_io_failed_hook(struct page *page, int failed_mirror) +static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror) { - return 0; + return -EAGAIN; } static const struct inode_operations btrfs_dir_inode_operations = { @@ -10556,7 +10568,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = { .submit_bio_hook = btrfs_submit_bio_hook, .readpage_end_io_hook = btrfs_readpage_end_io_hook, .merge_bio_hook = btrfs_merge_bio_hook, - .readpage_io_failed_hook = dummy_readpage_io_failed_hook, + .readpage_io_failed_hook = btrfs_readpage_io_failed_hook, /* optional callbacks */ .fill_delalloc = run_delalloc_range, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a5da750c1087..afbea61d957e 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1042,9 +1042,12 @@ static void report_reserved_underflow(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup, u64 num_bytes) { - btrfs_warn(fs_info, +#ifdef CONFIG_BTRFS_DEBUG + WARN_ON(qgroup->reserved < num_bytes); + btrfs_debug(fs_info, "qgroup %llu reserved space underflow, have: %llu, to free: %llu", qgroup->qgroupid, qgroup->reserved, num_bytes); +#endif qgroup->reserved = 0; } /* @@ -1075,7 +1078,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, qgroup->excl += sign * num_bytes; qgroup->excl_cmpr += sign * num_bytes; if (sign > 0) { - if (WARN_ON(qgroup->reserved < num_bytes)) + if (qgroup->reserved < num_bytes) report_reserved_underflow(fs_info, qgroup, num_bytes); else qgroup->reserved -= num_bytes; @@ -1100,7 +1103,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, WARN_ON(sign < 0 && qgroup->excl < num_bytes); qgroup->excl += sign * num_bytes; if (sign > 0) { - if (WARN_ON(qgroup->reserved < num_bytes)) + if (qgroup->reserved < num_bytes) report_reserved_underflow(fs_info, qgroup, num_bytes); else @@ -2469,7 +2472,7 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, qg = unode_aux_to_qgroup(unode); - if (WARN_ON(qg->reserved < num_bytes)) + if (qg->reserved < num_bytes) report_reserved_underflow(fs_info, qg, num_bytes); else qg->reserved -= num_bytes; @@ -2948,20 +2951,20 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, ret = qgroup_reserve(root, num_bytes, enforce); if (ret < 0) return ret; - atomic_add(num_bytes, &root->qgroup_meta_rsv); + atomic64_add(num_bytes, &root->qgroup_meta_rsv); return ret; } void btrfs_qgroup_free_meta_all(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; - int reserved; + u64 reserved; if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || !is_fstree(root->objectid)) return; - reserved = atomic_xchg(&root->qgroup_meta_rsv, 0); + reserved = atomic64_xchg(&root->qgroup_meta_rsv, 0); if (reserved == 0) return; btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved); @@ -2976,8 +2979,8 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes) return; BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); - WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes); - atomic_sub(num_bytes, &root->qgroup_meta_rsv); + WARN_ON(atomic64_read(&root->qgroup_meta_rsv) < num_bytes); + atomic64_sub(num_bytes, &root->qgroup_meta_rsv); btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes); } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 456c8901489b..a60d5bfb8a49 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6305,8 +6305,13 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) goto out; } + /* + * Check that we don't overflow at later allocations, we request + * clone_sources_count + 1 items, and compare to unsigned long inside + * access_ok. + */ if (arg->clone_sources_count > - ULLONG_MAX / sizeof(*arg->clone_sources)) { + ULONG_MAX / sizeof(struct clone_root) - 1) { ret = -EINVAL; goto out; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index da687dc79cce..72a053c9a7f0 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -549,16 +549,19 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, case Opt_ssd: btrfs_set_and_info(info, SSD, "use ssd allocation scheme"); + btrfs_clear_opt(info->mount_opt, NOSSD); break; case Opt_ssd_spread: btrfs_set_and_info(info, SSD_SPREAD, "use spread ssd allocation scheme"); btrfs_set_opt(info->mount_opt, SSD); + btrfs_clear_opt(info->mount_opt, NOSSD); break; case Opt_nossd: btrfs_set_and_info(info, NOSSD, "not using ssd allocation scheme"); btrfs_clear_opt(info->mount_opt, SSD); + btrfs_clear_opt(info->mount_opt, SSD_SPREAD); break; case Opt_barrier: btrfs_clear_and_info(info, NOBARRIER, @@ -1133,6 +1136,13 @@ static int btrfs_fill_super(struct super_block *sb, #endif sb->s_flags |= MS_I_VERSION; sb->s_iflags |= SB_I_CGROUPWB; + + err = super_setup_bdi(sb); + if (err) { + btrfs_err(fs_info, "super_setup_bdi failed"); + return err; + } + err = open_ctree(sb, fs_devices, (char *)data); if (err) { btrfs_err(fs_info, "open_ctree failed"); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 73d56eef5e60..ab8a66d852f9 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6213,7 +6213,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, for (dev_nr = 0; dev_nr < total_devs; dev_nr++) { dev = bbio->stripes[dev_nr].dev; if (!dev || !dev->bdev || - (bio_op(bio) == REQ_OP_WRITE && !dev->writeable)) { + (bio_op(first_bio) == REQ_OP_WRITE && !dev->writeable)) { bbio_error(bbio, first_bio, logical); continue; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 1a3e1b40799a..9ecb2fd348cb 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -578,7 +578,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) writeback_stat = atomic_long_inc_return(&fsc->writeback_count); if (writeback_stat > CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb)) - set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); + set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); set_page_writeback(page); err = ceph_osdc_writepages(osdc, ceph_vino(inode), @@ -700,7 +700,7 @@ static void writepages_finish(struct ceph_osd_request *req) if (atomic_long_dec_return(&fsc->writeback_count) < CONGESTION_OFF_THRESH( fsc->mount_options->congestion_kb)) - clear_bdi_congested(&fsc->backing_dev_info, + clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); if (rc < 0) @@ -979,7 +979,7 @@ get_more_pages: if (atomic_long_inc_return(&fsc->writeback_count) > CONGESTION_ON_THRESH( fsc->mount_options->congestion_kb)) { - set_bdi_congested(&fsc->backing_dev_info, + set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); } diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index f2ae393e2c31..3ef11bc8d728 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -251,7 +251,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) goto out; snprintf(name, sizeof(name), "../../bdi/%s", - dev_name(fsc->backing_dev_info.dev)); + dev_name(fsc->sb->s_bdi->dev)); fsc->debugfs_bdi = debugfs_create_symlink("bdi", fsc->client->debugfs_dir, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index d449e1c03cbd..d3119fe3ab45 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2071,11 +2071,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) if (inode_dirty_flags) __mark_inode_dirty(inode, inode_dirty_flags); - if (ia_valid & ATTR_MODE) { - err = posix_acl_chmod(inode, attr->ia_mode); - if (err) - goto out_put; - } if (mask) { req->r_inode = inode; @@ -2089,13 +2084,11 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) ceph_cap_string(dirtied), mask); ceph_mdsc_put_request(req); - if (mask & CEPH_SETATTR_SIZE) - __ceph_do_pending_vmtruncate(inode); - ceph_free_cap_flush(prealloc_cf); - return err; -out_put: - ceph_mdsc_put_request(req); ceph_free_cap_flush(prealloc_cf); + + if (err >= 0 && (mask & CEPH_SETATTR_SIZE)) + __ceph_do_pending_vmtruncate(inode); + return err; } @@ -2114,7 +2107,12 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) if (err != 0) return err; - return __ceph_setattr(inode, attr); + err = __ceph_setattr(inode, attr); + + if (err >= 0 && (attr->ia_valid & ATTR_MODE)) + err = posix_acl_chmod(inode, attr->ia_mode); + + return err; } /* diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 0ec8d0114e57..a8c81b2052ca 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -579,10 +579,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, atomic_long_set(&fsc->writeback_count, 0); - err = bdi_init(&fsc->backing_dev_info); - if (err < 0) - goto fail_client; - err = -ENOMEM; /* * The number of concurrent works can be high but they don't need @@ -590,7 +586,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, */ fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1); if (fsc->wb_wq == NULL) - goto fail_bdi; + goto fail_client; fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1); if (fsc->pg_inv_wq == NULL) goto fail_wb_wq; @@ -624,8 +620,6 @@ fail_pg_inv_wq: destroy_workqueue(fsc->pg_inv_wq); fail_wb_wq: destroy_workqueue(fsc->wb_wq); -fail_bdi: - bdi_destroy(&fsc->backing_dev_info); fail_client: ceph_destroy_client(fsc->client); fail: @@ -643,8 +637,6 @@ static void destroy_fs_client(struct ceph_fs_client *fsc) destroy_workqueue(fsc->pg_inv_wq); destroy_workqueue(fsc->trunc_wq); - bdi_destroy(&fsc->backing_dev_info); - mempool_destroy(fsc->wb_pagevec_pool); destroy_mount_options(fsc->mount_options); @@ -937,33 +929,32 @@ static int ceph_compare_super(struct super_block *sb, void *data) */ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); -static int ceph_register_bdi(struct super_block *sb, - struct ceph_fs_client *fsc) +static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc) { int err; + err = super_setup_bdi_name(sb, "ceph-%ld", + atomic_long_inc_return(&bdi_seq)); + if (err) + return err; + /* set ra_pages based on rasize mount option? */ if (fsc->mount_options->rasize >= PAGE_SIZE) - fsc->backing_dev_info.ra_pages = + sb->s_bdi->ra_pages = (fsc->mount_options->rasize + PAGE_SIZE - 1) >> PAGE_SHIFT; else - fsc->backing_dev_info.ra_pages = - VM_MAX_READAHEAD * 1024 / PAGE_SIZE; + sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE; if (fsc->mount_options->rsize > fsc->mount_options->rasize && fsc->mount_options->rsize >= PAGE_SIZE) - fsc->backing_dev_info.io_pages = + sb->s_bdi->io_pages = (fsc->mount_options->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT; else if (fsc->mount_options->rsize == 0) - fsc->backing_dev_info.io_pages = ULONG_MAX; + sb->s_bdi->io_pages = ULONG_MAX; - err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld", - atomic_long_inc_return(&bdi_seq)); - if (!err) - sb->s_bdi = &fsc->backing_dev_info; - return err; + return 0; } static struct dentry *ceph_mount(struct file_system_type *fs_type, @@ -1018,7 +1009,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, dout("get_sb got existing client %p\n", fsc); } else { dout("get_sb using new client %p\n", fsc); - err = ceph_register_bdi(sb, fsc); + err = ceph_setup_bdi(sb, fsc); if (err < 0) { res = ERR_PTR(err); goto out_splat; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index fe6b9cfc4013..176186b12457 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -92,8 +92,6 @@ struct ceph_fs_client { struct workqueue_struct *trunc_wq; atomic_long_t writeback_count; - struct backing_dev_info backing_dev_info; - #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_dentry_lru, *debugfs_caps; struct dentry *debugfs_congestion_kb; diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 07ed81cf1552..cbd216b57239 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -68,7 +68,6 @@ struct cifs_sb_info { umode_t mnt_dir_mode; unsigned int mnt_cifs_flags; char *mountdata; /* options received at mount time or via DFS refs */ - struct backing_dev_info bdi; struct delayed_work prune_tlinks; struct rcu_head rcu; char *prepath; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 15e1db8738ae..d0d11b73b2af 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -37,6 +37,7 @@ #include <linux/freezer.h> #include <linux/namei.h> #include <linux/random.h> +#include <linux/uuid.h> #include <linux/xattr.h> #include <net/ipv6.h> #include "cifsfs.h" @@ -138,7 +139,12 @@ cifs_read_super(struct super_block *sb) sb->s_magic = CIFS_MAGIC_NUMBER; sb->s_op = &cifs_super_ops; sb->s_xattr = cifs_xattr_handlers; - sb->s_bdi = &cifs_sb->bdi; + rc = super_setup_bdi(sb); + if (rc) + goto out_no_root; + /* tune readahead according to rsize */ + sb->s_bdi->ra_pages = cifs_sb->rsize / PAGE_SIZE; + sb->s_blocksize = CIFS_MAX_MSGSIZE; sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */ inode = cifs_root_iget(sb); @@ -972,6 +978,86 @@ out: return rc; } +ssize_t cifs_file_copychunk_range(unsigned int xid, + struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, + size_t len, unsigned int flags) +{ + struct inode *src_inode = file_inode(src_file); + struct inode *target_inode = file_inode(dst_file); + struct cifsFileInfo *smb_file_src; + struct cifsFileInfo *smb_file_target; + struct cifs_tcon *src_tcon; + struct cifs_tcon *target_tcon; + ssize_t rc; + + cifs_dbg(FYI, "copychunk range\n"); + + if (src_inode == target_inode) { + rc = -EINVAL; + goto out; + } + + if (!src_file->private_data || !dst_file->private_data) { + rc = -EBADF; + cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); + goto out; + } + + rc = -EXDEV; + smb_file_target = dst_file->private_data; + smb_file_src = src_file->private_data; + src_tcon = tlink_tcon(smb_file_src->tlink); + target_tcon = tlink_tcon(smb_file_target->tlink); + + if (src_tcon->ses != target_tcon->ses) { + cifs_dbg(VFS, "source and target of copy not on same server\n"); + goto out; + } + + /* + * Note: cifs case is easier than btrfs since server responsible for + * checks for proper open modes and file type and if it wants + * server could even support copy of range where source = target + */ + lock_two_nondirectories(target_inode, src_inode); + + cifs_dbg(FYI, "about to flush pages\n"); + /* should we flush first and last page first */ + truncate_inode_pages(&target_inode->i_data, 0); + + if (target_tcon->ses->server->ops->copychunk_range) + rc = target_tcon->ses->server->ops->copychunk_range(xid, + smb_file_src, smb_file_target, off, len, destoff); + else + rc = -EOPNOTSUPP; + + /* force revalidate of size and timestamps of target file now + * that target is updated on the server + */ + CIFS_I(target_inode)->time = 0; + /* although unlocking in the reverse order from locking is not + * strictly necessary here it is a little cleaner to be consistent + */ + unlock_two_nondirectories(src_inode, target_inode); + +out: + return rc; +} + +static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, + size_t len, unsigned int flags) +{ + unsigned int xid = get_xid(); + ssize_t rc; + + rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff, + len, flags); + free_xid(xid); + return rc; +} + const struct file_operations cifs_file_ops = { .read_iter = cifs_loose_read_iter, .write_iter = cifs_file_write_iter, @@ -984,6 +1070,7 @@ const struct file_operations cifs_file_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1001,6 +1088,7 @@ const struct file_operations cifs_file_strict_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1018,6 +1106,7 @@ const struct file_operations cifs_file_direct_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, @@ -1035,6 +1124,7 @@ const struct file_operations cifs_file_nobrl_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1051,6 +1141,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1067,6 +1158,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, @@ -1078,6 +1170,7 @@ const struct file_operations cifs_dir_ops = { .release = cifs_closedir, .read = generic_read_dir, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .llseek = generic_file_llseek, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index da717fee3026..30bf89b1fd9a 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -139,6 +139,11 @@ extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); # define cifs_listxattr NULL #endif +extern ssize_t cifs_file_copychunk_range(unsigned int xid, + struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, + size_t len, unsigned int flags); + extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); #ifdef CONFIG_CIFS_NFSD_EXPORT extern const struct export_operations cifs_export_ops; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index d42dd3288647..37f5a41cc50c 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -243,6 +243,7 @@ struct smb_version_operations { /* verify the message */ int (*check_message)(char *, unsigned int, struct TCP_Server_Info *); bool (*is_oplock_break)(char *, struct TCP_Server_Info *); + int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *); void (*downgrade_oplock)(struct TCP_Server_Info *, struct cifsInodeInfo *, bool); /* process transaction2 response */ @@ -407,9 +408,10 @@ struct smb_version_operations { char * (*create_lease_buf)(u8 *, u8); /* parse lease context buffer and return oplock/epoch info */ __u8 (*parse_lease_buf)(void *, unsigned int *); - int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file, - struct cifsFileInfo *target_file, u64 src_off, u64 len, - u64 dest_off); + ssize_t (*copychunk_range)(const unsigned int, + struct cifsFileInfo *src_file, + struct cifsFileInfo *target_file, + u64 src_off, u64 len, u64 dest_off); int (*duplicate_extents)(const unsigned int, struct cifsFileInfo *src, struct cifsFileInfo *target_file, u64 src_off, u64 len, u64 dest_off); @@ -946,7 +948,6 @@ struct cifs_tcon { bool use_persistent:1; /* use persistent instead of durable handles */ #ifdef CONFIG_CIFS_SMB2 bool print:1; /* set if connection to printer share */ - bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */ __le32 capabilities; __u32 share_flags; __u32 maximal_access; @@ -1343,6 +1344,7 @@ struct mid_q_entry { void *callback_data; /* general purpose pointer for callback */ void *resp_buf; /* pointer to received SMB header */ int mid_state; /* wish this were enum but can not pass to wait_event */ + unsigned int mid_flags; __le16 command; /* smb command code */ bool large_buf:1; /* if valid response, is pointer to large buf */ bool multiRsp:1; /* multiple trans2 responses for one request */ @@ -1350,6 +1352,12 @@ struct mid_q_entry { bool decrypted:1; /* decrypted entry */ }; +struct close_cancelled_open { + struct cifs_fid fid; + struct cifs_tcon *tcon; + struct work_struct work; +}; + /* Make code in transport.c a little cleaner by moving update of optional stats into function below */ #ifdef CONFIG_CIFS_STATS2 @@ -1481,6 +1489,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param, #define MID_RESPONSE_MALFORMED 0x10 #define MID_SHUTDOWN 0x20 +/* Flags */ +#define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */ + /* Types of response buffer returned from SendReceive2 */ #define CIFS_NO_BUFFER 0 /* Response buffer not returned */ #define CIFS_SMALL_BUFFER 1 diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 066950671929..5d21f00ae341 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1428,6 +1428,8 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) length = cifs_discard_remaining_data(server); dequeue_mid(mid, rdata->result); + mid->resp_buf = server->smallbuf; + server->smallbuf = NULL; return length; } @@ -1541,6 +1543,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return cifs_readv_discard(server, mid); dequeue_mid(mid, false); + mid->resp_buf = server->smallbuf; + server->smallbuf = NULL; return length; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9ae695ae3ed7..9bc0b4d6d065 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -35,6 +35,7 @@ #include <linux/pagevec.h> #include <linux/freezer.h> #include <linux/namei.h> +#include <linux/uuid.h> #include <linux/uaccess.h> #include <asm/processor.h> #include <linux/inet.h> @@ -904,10 +905,19 @@ cifs_demultiplex_thread(void *p) server->lstrp = jiffies; if (mid_entry != NULL) { + if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) && + mid_entry->mid_state == MID_RESPONSE_RECEIVED && + server->ops->handle_cancelled_mid) + server->ops->handle_cancelled_mid( + mid_entry->resp_buf, + server); + if (!mid_entry->multiRsp || mid_entry->multiEnd) mid_entry->callback(mid_entry); - } else if (!server->ops->is_oplock_break || - !server->ops->is_oplock_break(buf, server)) { + } else if (server->ops->is_oplock_break && + server->ops->is_oplock_break(buf, server)) { + cifs_dbg(FYI, "Received oplock break\n"); + } else { cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n", atomic_read(&midCount)); cifs_dump_mem("Received Data is: ", buf, @@ -2903,16 +2913,14 @@ match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data) { struct cifs_sb_info *old = CIFS_SB(sb); struct cifs_sb_info *new = mnt_data->cifs_sb; + bool old_set = old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH; + bool new_set = new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH; - if (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) { - if (!(new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)) - return 0; - /* The prepath should be null terminated strings */ - if (strcmp(new->prepath, old->prepath)) - return 0; - + if (old_set && new_set && !strcmp(new->prepath, old->prepath)) return 1; - } + else if (!old_set && !new_set) + return 1; + return 0; } @@ -3683,10 +3691,6 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info) int referral_walks_count = 0; #endif - rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs"); - if (rc) - return rc; - #ifdef CONFIG_CIFS_DFS_UPCALL try_mount_again: /* cleanup activities if we're chasing a referral */ @@ -3714,7 +3718,6 @@ try_mount_again: server = cifs_get_tcp_session(volume_info); if (IS_ERR(server)) { rc = PTR_ERR(server); - bdi_destroy(&cifs_sb->bdi); goto out; } if ((volume_info->max_credits < 20) || @@ -3744,6 +3747,9 @@ try_mount_again: if (IS_ERR(tcon)) { rc = PTR_ERR(tcon); tcon = NULL; + if (rc == -EACCES) + goto mount_fail_check; + goto remote_path_check; } @@ -3768,9 +3774,6 @@ try_mount_again: cifs_sb->wsize = server->ops->negotiate_wsize(tcon, volume_info); cifs_sb->rsize = server->ops->negotiate_rsize(tcon, volume_info); - /* tune readahead according to rsize */ - cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_SIZE; - remote_path_check: #ifdef CONFIG_CIFS_DFS_UPCALL /* @@ -3887,7 +3890,6 @@ mount_fail_check: cifs_put_smb_ses(ses); else cifs_put_tcp_session(server, 0); - bdi_destroy(&cifs_sb->bdi); } out: @@ -4090,7 +4092,6 @@ cifs_umount(struct cifs_sb_info *cifs_sb) } spin_unlock(&cifs_sb->tlink_tree_lock); - bdi_destroy(&cifs_sb->bdi); kfree(cifs_sb->mountdata); kfree(cifs_sb->prepath); call_rcu(&cifs_sb->rcu, delayed_free); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index aa3debbba826..21d404535739 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2597,7 +2597,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, wdata->credits = credits; if (!wdata->cfile->invalidHandle || - !cifs_reopen_file(wdata->cfile, false)) + !(rc = cifs_reopen_file(wdata->cfile, false))) rc = server->ops->async_writev(wdata, cifs_uncached_writedata_release); if (rc) { @@ -3022,7 +3022,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, rdata->credits = credits; if (!rdata->cfile->invalidHandle || - !cifs_reopen_file(rdata->cfile, true)) + !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); error: if (rc) { @@ -3617,7 +3617,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, } if (!rdata->cfile->invalidHandle || - !cifs_reopen_file(rdata->cfile, true)) + !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); if (rc) { add_credits_and_wake_if(server, rdata->credits, 0); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 001528781b6b..7f4bba574930 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -34,71 +34,14 @@ #include "cifs_ioctl.h" #include <linux/btrfs.h> -static int cifs_file_clone_range(unsigned int xid, struct file *src_file, - struct file *dst_file) -{ - struct inode *src_inode = file_inode(src_file); - struct inode *target_inode = file_inode(dst_file); - struct cifsFileInfo *smb_file_src; - struct cifsFileInfo *smb_file_target; - struct cifs_tcon *src_tcon; - struct cifs_tcon *target_tcon; - int rc; - - cifs_dbg(FYI, "ioctl clone range\n"); - - if (!src_file->private_data || !dst_file->private_data) { - rc = -EBADF; - cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); - goto out; - } - - rc = -EXDEV; - smb_file_target = dst_file->private_data; - smb_file_src = src_file->private_data; - src_tcon = tlink_tcon(smb_file_src->tlink); - target_tcon = tlink_tcon(smb_file_target->tlink); - - if (src_tcon->ses != target_tcon->ses) { - cifs_dbg(VFS, "source and target of copy not on same server\n"); - goto out; - } - - /* - * Note: cifs case is easier than btrfs since server responsible for - * checks for proper open modes and file type and if it wants - * server could even support copy of range where source = target - */ - lock_two_nondirectories(target_inode, src_inode); - - cifs_dbg(FYI, "about to flush pages\n"); - /* should we flush first and last page first */ - truncate_inode_pages(&target_inode->i_data, 0); - - if (target_tcon->ses->server->ops->clone_range) - rc = target_tcon->ses->server->ops->clone_range(xid, - smb_file_src, smb_file_target, 0, src_inode->i_size, 0); - else - rc = -EOPNOTSUPP; - - /* force revalidate of size and timestamps of target file now - that target is updated on the server */ - CIFS_I(target_inode)->time = 0; - /* although unlocking in the reverse order from locking is not - strictly necessary here it is a little cleaner to be consistent */ - unlock_two_nondirectories(src_inode, target_inode); -out: - return rc; -} - -static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, +static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file, unsigned long srcfd) { int rc; struct fd src_file; struct inode *src_inode; - cifs_dbg(FYI, "ioctl clone range\n"); + cifs_dbg(FYI, "ioctl copychunk range\n"); /* the destination must be opened for writing */ if (!(dst_file->f_mode & FMODE_WRITE)) { cifs_dbg(FYI, "file target not open for write\n"); @@ -129,8 +72,10 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, if (S_ISDIR(src_inode->i_mode)) goto out_fput; - rc = cifs_file_clone_range(xid, src_file.file, dst_file); - + rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0, + src_inode->i_size, 0); + if (rc > 0) + rc = 0; out_fput: fdput(src_file); out_drop_write: @@ -251,7 +196,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) } break; case CIFS_IOC_COPYCHUNK_FILE: - rc = cifs_ioctl_clone(xid, filep, arg); + rc = cifs_ioctl_copychunk(xid, filep, arg); break; case CIFS_IOC_SET_INTEGRITY: if (pSMBFile == NULL) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index d3fb11529ed9..843787850435 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -167,13 +167,11 @@ cifs_buf_get(void) /* clear the first few header bytes */ /* for most paths, more is cleared in header_assemble */ - if (ret_buf) { - memset(ret_buf, 0, buf_size + 3); - atomic_inc(&bufAllocCount); + memset(ret_buf, 0, buf_size + 3); + atomic_inc(&bufAllocCount); #ifdef CONFIG_CIFS_STATS2 - atomic_inc(&totBufAllocCount); + atomic_inc(&totBufAllocCount); #endif /* CONFIG_CIFS_STATS2 */ - } return ret_buf; } @@ -201,15 +199,13 @@ cifs_small_buf_get(void) albeit slightly larger than necessary and maxbuffersize defaults to this and can not be bigger */ ret_buf = mempool_alloc(cifs_sm_req_poolp, GFP_NOFS); - if (ret_buf) { /* No need to clear memory here, cleared in header assemble */ /* memset(ret_buf, 0, sizeof(struct smb_hdr) + 27);*/ - atomic_inc(&smBufAllocCount); + atomic_inc(&smBufAllocCount); #ifdef CONFIG_CIFS_STATS2 - atomic_inc(&totSmBufAllocCount); + atomic_inc(&totSmBufAllocCount); #endif /* CONFIG_CIFS_STATS2 */ - } return ret_buf; } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index cc93ba4da9b5..27bc360c7ffd 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -1015,6 +1015,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile) return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; } +static bool +cifs_can_echo(struct TCP_Server_Info *server) +{ + if (server->tcpStatus == CifsGood) + return true; + + return false; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1049,6 +1058,7 @@ struct smb_version_operations smb1_operations = { .get_dfs_refer = CIFSGetDFSRefer, .qfs_tcon = cifs_qfs_tcon, .is_path_accessible = cifs_is_path_accessible, + .can_echo = cifs_can_echo, .query_path_info = cifs_query_path_info, .query_file_info = cifs_query_file_info, .get_srv_inum = cifs_get_srv_inum, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index fd516ea8b8f8..1a04b3a5beb1 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -659,3 +659,49 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n"); return false; } + +void +smb2_cancelled_close_fid(struct work_struct *work) +{ + struct close_cancelled_open *cancelled = container_of(work, + struct close_cancelled_open, work); + + cifs_dbg(VFS, "Close unmatched open\n"); + + SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid, + cancelled->fid.volatile_fid); + cifs_put_tcon(cancelled->tcon); + kfree(cancelled); +} + +int +smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server) +{ + struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer); + struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer; + struct cifs_tcon *tcon; + struct close_cancelled_open *cancelled; + + if (sync_hdr->Command != SMB2_CREATE || + sync_hdr->Status != STATUS_SUCCESS) + return 0; + + cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL); + if (!cancelled) + return -ENOMEM; + + tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId, + sync_hdr->TreeId); + if (!tcon) { + kfree(cancelled); + return -ENOENT; + } + + cancelled->fid.persistent_fid = rsp->PersistentFileId; + cancelled->fid.volatile_fid = rsp->VolatileFileId; + cancelled->tcon = tcon; + INIT_WORK(&cancelled->work, smb2_cancelled_close_fid); + queue_work(cifsiod_wq, &cancelled->work); + + return 0; +} diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 0231108d9387..152e37f2ad92 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -21,6 +21,7 @@ #include <linux/vfs.h> #include <linux/falloc.h> #include <linux/scatterlist.h> +#include <linux/uuid.h> #include <crypto/aead.h> #include "cifsglob.h" #include "smb2pdu.h" @@ -592,8 +593,8 @@ req_res_key_exit: return rc; } -static int -smb2_clone_range(const unsigned int xid, +static ssize_t +smb2_copychunk_range(const unsigned int xid, struct cifsFileInfo *srcfile, struct cifsFileInfo *trgtfile, u64 src_off, u64 len, u64 dest_off) @@ -605,13 +606,14 @@ smb2_clone_range(const unsigned int xid, struct cifs_tcon *tcon; int chunks_copied = 0; bool chunk_sizes_updated = false; + ssize_t bytes_written, total_bytes_written = 0; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); if (pcchunk == NULL) return -ENOMEM; - cifs_dbg(FYI, "in smb2_clone_range - about to call request res key\n"); + cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n"); /* Request a key from the server to identify the source of the copy */ rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink), srcfile->fid.persistent_fid, @@ -669,14 +671,16 @@ smb2_clone_range(const unsigned int xid, } chunks_copied++; - src_off += le32_to_cpu(retbuf->TotalBytesWritten); - dest_off += le32_to_cpu(retbuf->TotalBytesWritten); - len -= le32_to_cpu(retbuf->TotalBytesWritten); + bytes_written = le32_to_cpu(retbuf->TotalBytesWritten); + src_off += bytes_written; + dest_off += bytes_written; + len -= bytes_written; + total_bytes_written += bytes_written; - cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n", + cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n", le32_to_cpu(retbuf->ChunksWritten), le32_to_cpu(retbuf->ChunkBytesWritten), - le32_to_cpu(retbuf->TotalBytesWritten)); + bytes_written); } else if (rc == -EINVAL) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) goto cchunk_out; @@ -713,7 +717,10 @@ smb2_clone_range(const unsigned int xid, cchunk_out: kfree(pcchunk); kfree(retbuf); - return rc; + if (rc) + return rc; + else + return total_bytes_written; } static int @@ -2322,6 +2329,7 @@ struct smb_version_operations smb20_operations = { .clear_stats = smb2_clear_stats, .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -2377,7 +2385,7 @@ struct smb_version_operations smb20_operations = { .set_oplock_level = smb2_set_oplock_level, .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, - .clone_range = smb2_clone_range, + .copychunk_range = smb2_copychunk_range, .wp_retry_size = smb2_wp_retry_size, .dir_needs_close = smb2_dir_needs_close, .get_dfs_refer = smb2_get_dfs_refer, @@ -2404,6 +2412,7 @@ struct smb_version_operations smb21_operations = { .clear_stats = smb2_clear_stats, .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -2459,7 +2468,7 @@ struct smb_version_operations smb21_operations = { .set_oplock_level = smb21_set_oplock_level, .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, - .clone_range = smb2_clone_range, + .copychunk_range = smb2_copychunk_range, .wp_retry_size = smb2_wp_retry_size, .dir_needs_close = smb2_dir_needs_close, .enum_snapshots = smb3_enum_snapshots, @@ -2488,6 +2497,7 @@ struct smb_version_operations smb30_operations = { .print_stats = smb2_print_stats, .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -2545,7 +2555,7 @@ struct smb_version_operations smb30_operations = { .set_oplock_level = smb3_set_oplock_level, .create_lease_buf = smb3_create_lease_buf, .parse_lease_buf = smb3_parse_lease_buf, - .clone_range = smb2_clone_range, + .copychunk_range = smb2_copychunk_range, .duplicate_extents = smb2_duplicate_extents, .validate_negotiate = smb3_validate_negotiate, .wp_retry_size = smb2_wp_retry_size, @@ -2582,6 +2592,7 @@ struct smb_version_operations smb311_operations = { .print_stats = smb2_print_stats, .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -2639,7 +2650,7 @@ struct smb_version_operations smb311_operations = { .set_oplock_level = smb3_set_oplock_level, .create_lease_buf = smb3_create_lease_buf, .parse_lease_buf = smb3_parse_lease_buf, - .clone_range = smb2_clone_range, + .copychunk_range = smb2_copychunk_range, .duplicate_extents = smb2_duplicate_extents, /* .validate_negotiate = smb3_validate_negotiate, */ /* not used in 3.11 */ .wp_retry_size = smb2_wp_retry_size, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 7446496850a3..fb0da096c2ce 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -33,6 +33,7 @@ #include <linux/vfs.h> #include <linux/task_io_accounting_ops.h> #include <linux/uaccess.h> +#include <linux/uuid.h> #include <linux/pagemap.h> #include <linux/xattr.h> #include "smb2pdu.h" @@ -562,8 +563,10 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) * but for time being this is our only auth choice so doesn't matter. * We just found a server which sets blob length to zero expecting raw. */ - if (blob_length == 0) + if (blob_length == 0) { cifs_dbg(FYI, "missing security blob on negprot\n"); + server->sec_ntlmssp = true; + } rc = cifs_enable_signing(server, ses->sign); if (rc) @@ -1171,9 +1174,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, else return -EIO; - if (tcon && tcon->bad_network_name) - return -ENOENT; - unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL); if (unc_path == NULL) return -ENOMEM; @@ -1185,6 +1185,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, return -EINVAL; } + /* SMB2 TREE_CONNECT request must be called with TreeId == 0 */ + if (tcon) + tcon->tid = 0; + rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req); if (rc) { kfree(unc_path); @@ -1273,8 +1277,6 @@ tcon_exit: tcon_error_exit: if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) { cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); - if (tcon) - tcon->bad_network_name = true; } goto tcon_exit; } @@ -2177,6 +2179,9 @@ void smb2_reconnect_server(struct work_struct *work) struct cifs_tcon *tcon, *tcon2; struct list_head tmp_list; int tcon_exist = false; + int rc; + int resched = false; + /* Prevent simultaneous reconnects that can corrupt tcon->rlist list */ mutex_lock(&server->reconnect_mutex); @@ -2204,13 +2209,18 @@ void smb2_reconnect_server(struct work_struct *work) spin_unlock(&cifs_tcp_ses_lock); list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) { - if (!smb2_reconnect(SMB2_INTERNAL_CMD, tcon)) + rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon); + if (!rc) cifs_reopen_persistent_handles(tcon); + else + resched = true; list_del_init(&tcon->rlist); cifs_put_tcon(tcon); } cifs_dbg(FYI, "Reconnecting tcons finished\n"); + if (resched) + queue_delayed_work(cifsiod_wq, &server->reconnect, 2 * HZ); mutex_unlock(&server->reconnect_mutex); /* now we can safely release srv struct */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 69e35873b1de..6853454fc871 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -48,6 +48,10 @@ extern struct mid_q_entry *smb2_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst); extern struct mid_q_entry *smb2_setup_async_request( struct TCP_Server_Info *server, struct smb_rqst *rqst); +extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server, + __u64 ses_id); +extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server, + __u64 ses_id, __u32 tid); extern int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server); extern int smb3_calc_signature(struct smb_rqst *rqst, @@ -164,6 +168,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, const u64 persistent_fid, const u64 volatile_fid, const __u8 oplock_level); +extern int smb2_handle_cancelled_mid(char *buffer, + struct TCP_Server_Info *server); +void smb2_cancelled_close_fid(struct work_struct *work); extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, struct kstatfs *FSData); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 7c3bb1bd7eed..c69ec96e92ac 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -115,23 +115,70 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server) return 0; } -struct cifs_ses * -smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id) +static struct cifs_ses * +smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id) { struct cifs_ses *ses; - spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { if (ses->Suid != ses_id) continue; - spin_unlock(&cifs_tcp_ses_lock); return ses; } + + return NULL; +} + +struct cifs_ses * +smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id) +{ + struct cifs_ses *ses; + + spin_lock(&cifs_tcp_ses_lock); + ses = smb2_find_smb_ses_unlocked(server, ses_id); spin_unlock(&cifs_tcp_ses_lock); + return ses; +} + +static struct cifs_tcon * +smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid) +{ + struct cifs_tcon *tcon; + + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + if (tcon->tid != tid) + continue; + ++tcon->tc_count; + return tcon; + } + return NULL; } +/* + * Obtain tcon corresponding to the tid in the given + * cifs_ses + */ + +struct cifs_tcon * +smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) +{ + struct cifs_ses *ses; + struct cifs_tcon *tcon; + + spin_lock(&cifs_tcp_ses_lock); + ses = smb2_find_smb_ses_unlocked(server, ses_id); + if (!ses) { + spin_unlock(&cifs_tcp_ses_lock); + return NULL; + } + tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid); + spin_unlock(&cifs_tcp_ses_lock); + + return tcon; +} + int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) { @@ -491,23 +538,19 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr, } temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS); - if (temp == NULL) - return temp; - else { - memset(temp, 0, sizeof(struct mid_q_entry)); - temp->mid = le64_to_cpu(shdr->MessageId); - temp->pid = current->pid; - temp->command = shdr->Command; /* Always LE */ - temp->when_alloc = jiffies; - temp->server = server; - - /* - * The default is for the mid to be synchronous, so the - * default callback just wakes up the current task. - */ - temp->callback = cifs_wake_up_task; - temp->callback_data = current; - } + memset(temp, 0, sizeof(struct mid_q_entry)); + temp->mid = le64_to_cpu(shdr->MessageId); + temp->pid = current->pid; + temp->command = shdr->Command; /* Always LE */ + temp->when_alloc = jiffies; + temp->server = server; + + /* + * The default is for the mid to be synchronous, so the + * default callback just wakes up the current task. + */ + temp->callback = cifs_wake_up_task; + temp->callback_data = current; atomic_inc(&midCount); temp->mid_state = MID_REQUEST_ALLOCATED; diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 526f0533cb4e..4d64b5b8fc9c 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -55,26 +55,22 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) } temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS); - if (temp == NULL) - return temp; - else { - memset(temp, 0, sizeof(struct mid_q_entry)); - temp->mid = get_mid(smb_buffer); - temp->pid = current->pid; - temp->command = cpu_to_le16(smb_buffer->Command); - cifs_dbg(FYI, "For smb_command %d\n", smb_buffer->Command); + memset(temp, 0, sizeof(struct mid_q_entry)); + temp->mid = get_mid(smb_buffer); + temp->pid = current->pid; + temp->command = cpu_to_le16(smb_buffer->Command); + cifs_dbg(FYI, "For smb_command %d\n", smb_buffer->Command); /* do_gettimeofday(&temp->when_sent);*/ /* easier to use jiffies */ - /* when mid allocated can be before when sent */ - temp->when_alloc = jiffies; - temp->server = server; + /* when mid allocated can be before when sent */ + temp->when_alloc = jiffies; + temp->server = server; - /* - * The default is for the mid to be synchronous, so the - * default callback just wakes up the current task. - */ - temp->callback = cifs_wake_up_task; - temp->callback_data = current; - } + /* + * The default is for the mid to be synchronous, so the + * default callback just wakes up the current task. + */ + temp->callback = cifs_wake_up_task; + temp->callback_data = current; atomic_inc(&midCount); temp->mid_state = MID_REQUEST_ALLOCATED; @@ -752,9 +748,11 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, rc = wait_for_response(ses->server, midQ); if (rc != 0) { + cifs_dbg(FYI, "Cancelling wait for mid %llu\n", midQ->mid); send_cancel(ses->server, rqst, midQ); spin_lock(&GlobalMid_Lock); if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + midQ->mid_flags |= MID_WAIT_CANCELLED; midQ->callback = DeleteMidQEntry; spin_unlock(&GlobalMid_Lock); add_credits(ses->server, 1, optype); diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 2dea594da199..6058df380cc0 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -183,10 +183,6 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) goto unlock_out; } - error = bdi_setup_and_register(&vc->bdi, "coda"); - if (error) - goto unlock_out; - vc->vc_sb = sb; mutex_unlock(&vc->vc_mutex); @@ -197,7 +193,10 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) sb->s_magic = CODA_SUPER_MAGIC; sb->s_op = &coda_super_operations; sb->s_d_op = &coda_dentry_operations; - sb->s_bdi = &vc->bdi; + + error = super_setup_bdi(sb); + if (error) + goto error; /* get root fid from Venus: this needs the root inode */ error = venus_rootfid(sb, &fid); @@ -228,7 +227,6 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) error: mutex_lock(&vc->vc_mutex); - bdi_destroy(&vc->bdi); vc->vc_sb = NULL; sb->s_fs_info = NULL; unlock_out: @@ -240,7 +238,6 @@ static void coda_put_super(struct super_block *sb) { struct venus_comm *vcp = coda_vcp(sb); mutex_lock(&vcp->vc_mutex); - bdi_destroy(&vcp->bdi); vcp->vc_sb = NULL; sb->s_fs_info = NULL; mutex_unlock(&vcp->vc_mutex); diff --git a/fs/compat.c b/fs/compat.c index c61b506f5bc9..190b38b39d9e 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -15,555 +15,14 @@ * published by the Free Software Foundation. */ -#include <linux/stddef.h> -#include <linux/kernel.h> -#include <linux/linkage.h> #include <linux/compat.h> -#include <linux/errno.h> -#include <linux/time.h> -#include <linux/cred.h> -#include <linux/fs.h> -#include <linux/fcntl.h> -#include <linux/namei.h> -#include <linux/file.h> -#include <linux/fdtable.h> -#include <linux/vfs.h> -#include <linux/ioctl.h> -#include <linux/init.h> #include <linux/ncp_mount.h> #include <linux/nfs4_mount.h> #include <linux/syscalls.h> -#include <linux/ctype.h> -#include <linux/dirent.h> -#include <linux/fsnotify.h> -#include <linux/highuid.h> -#include <linux/personality.h> -#include <linux/rwsem.h> -#include <linux/tsacct_kern.h> -#include <linux/security.h> -#include <linux/highmem.h> -#include <linux/signal.h> -#include <linux/poll.h> -#include <linux/mm.h> -#include <linux/fs_struct.h> #include <linux/slab.h> -#include <linux/pagemap.h> -#include <linux/aio.h> - #include <linux/uaccess.h> -#include <asm/mmu_context.h> -#include <asm/ioctls.h> #include "internal.h" -/* - * Not all architectures have sys_utime, so implement this in terms - * of sys_utimes. - */ -COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, - struct compat_utimbuf __user *, t) -{ - struct timespec tv[2]; - - if (t) { - if (get_user(tv[0].tv_sec, &t->actime) || - get_user(tv[1].tv_sec, &t->modtime)) - return -EFAULT; - tv[0].tv_nsec = 0; - tv[1].tv_nsec = 0; - } - return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0); -} - -COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags) -{ - struct timespec tv[2]; - - if (t) { - if (compat_get_timespec(&tv[0], &t[0]) || - compat_get_timespec(&tv[1], &t[1])) - return -EFAULT; - - if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT) - return 0; - } - return do_utimes(dfd, filename, t ? tv : NULL, flags); -} - -COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t) -{ - struct timespec tv[2]; - - if (t) { - if (get_user(tv[0].tv_sec, &t[0].tv_sec) || - get_user(tv[0].tv_nsec, &t[0].tv_usec) || - get_user(tv[1].tv_sec, &t[1].tv_sec) || - get_user(tv[1].tv_nsec, &t[1].tv_usec)) - return -EFAULT; - if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 || - tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0) - return -EINVAL; - tv[0].tv_nsec *= 1000; - tv[1].tv_nsec *= 1000; - } - return do_utimes(dfd, filename, t ? tv : NULL, 0); -} - -COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t) -{ - return compat_sys_futimesat(AT_FDCWD, filename, t); -} - -static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) -{ - struct compat_stat tmp; - - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) - return -EOVERFLOW; - - memset(&tmp, 0, sizeof(tmp)); - tmp.st_dev = old_encode_dev(stat->dev); - tmp.st_ino = stat->ino; - if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) - return -EOVERFLOW; - tmp.st_mode = stat->mode; - tmp.st_nlink = stat->nlink; - if (tmp.st_nlink != stat->nlink) - return -EOVERFLOW; - SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); - SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = old_encode_dev(stat->rdev); - if ((u64) stat->size > MAX_NON_LFS) - return -EOVERFLOW; - tmp.st_size = stat->size; - tmp.st_atime = stat->atime.tv_sec; - tmp.st_atime_nsec = stat->atime.tv_nsec; - tmp.st_mtime = stat->mtime.tv_sec; - tmp.st_mtime_nsec = stat->mtime.tv_nsec; - tmp.st_ctime = stat->ctime.tv_sec; - tmp.st_ctime_nsec = stat->ctime.tv_nsec; - tmp.st_blocks = stat->blocks; - tmp.st_blksize = stat->blksize; - return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; -} - -COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename, - struct compat_stat __user *, statbuf) -{ - struct kstat stat; - int error; - - error = vfs_stat(filename, &stat); - if (error) - return error; - return cp_compat_stat(&stat, statbuf); -} - -COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename, - struct compat_stat __user *, statbuf) -{ - struct kstat stat; - int error; - - error = vfs_lstat(filename, &stat); - if (error) - return error; - return cp_compat_stat(&stat, statbuf); -} - -#ifndef __ARCH_WANT_STAT64 -COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd, - const char __user *, filename, - struct compat_stat __user *, statbuf, int, flag) -{ - struct kstat stat; - int error; - - error = vfs_fstatat(dfd, filename, &stat, flag); - if (error) - return error; - return cp_compat_stat(&stat, statbuf); -} -#endif - -COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd, - struct compat_stat __user *, statbuf) -{ - struct kstat stat; - int error = vfs_fstat(fd, &stat); - - if (!error) - error = cp_compat_stat(&stat, statbuf); - return error; -} - -static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf) -{ - - if (sizeof ubuf->f_blocks == 4) { - if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail | - kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) - return -EOVERFLOW; - /* f_files and f_ffree may be -1; it's okay - * to stuff that into 32 bits */ - if (kbuf->f_files != 0xffffffffffffffffULL - && (kbuf->f_files & 0xffffffff00000000ULL)) - return -EOVERFLOW; - if (kbuf->f_ffree != 0xffffffffffffffffULL - && (kbuf->f_ffree & 0xffffffff00000000ULL)) - return -EOVERFLOW; - } - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) || - __put_user(kbuf->f_type, &ubuf->f_type) || - __put_user(kbuf->f_bsize, &ubuf->f_bsize) || - __put_user(kbuf->f_blocks, &ubuf->f_blocks) || - __put_user(kbuf->f_bfree, &ubuf->f_bfree) || - __put_user(kbuf->f_bavail, &ubuf->f_bavail) || - __put_user(kbuf->f_files, &ubuf->f_files) || - __put_user(kbuf->f_ffree, &ubuf->f_ffree) || - __put_user(kbuf->f_namelen, &ubuf->f_namelen) || - __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || - __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || - __put_user(kbuf->f_frsize, &ubuf->f_frsize) || - __put_user(kbuf->f_flags, &ubuf->f_flags) || - __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) - return -EFAULT; - return 0; -} - -/* - * The following statfs calls are copies of code from fs/statfs.c and - * should be checked against those from time to time - */ -COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf) -{ - struct kstatfs tmp; - int error = user_statfs(pathname, &tmp); - if (!error) - error = put_compat_statfs(buf, &tmp); - return error; -} - -COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf) -{ - struct kstatfs tmp; - int error = fd_statfs(fd, &tmp); - if (!error) - error = put_compat_statfs(buf, &tmp); - return error; -} - -static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf) -{ - if (sizeof(ubuf->f_bsize) == 4) { - if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen | - kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL) - return -EOVERFLOW; - /* f_files and f_ffree may be -1; it's okay - * to stuff that into 32 bits */ - if (kbuf->f_files != 0xffffffffffffffffULL - && (kbuf->f_files & 0xffffffff00000000ULL)) - return -EOVERFLOW; - if (kbuf->f_ffree != 0xffffffffffffffffULL - && (kbuf->f_ffree & 0xffffffff00000000ULL)) - return -EOVERFLOW; - } - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) || - __put_user(kbuf->f_type, &ubuf->f_type) || - __put_user(kbuf->f_bsize, &ubuf->f_bsize) || - __put_user(kbuf->f_blocks, &ubuf->f_blocks) || - __put_user(kbuf->f_bfree, &ubuf->f_bfree) || - __put_user(kbuf->f_bavail, &ubuf->f_bavail) || - __put_user(kbuf->f_files, &ubuf->f_files) || - __put_user(kbuf->f_ffree, &ubuf->f_ffree) || - __put_user(kbuf->f_namelen, &ubuf->f_namelen) || - __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || - __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || - __put_user(kbuf->f_frsize, &ubuf->f_frsize) || - __put_user(kbuf->f_flags, &ubuf->f_flags) || - __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) - return -EFAULT; - return 0; -} - -COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf) -{ - struct kstatfs tmp; - int error; - - if (sz != sizeof(*buf)) - return -EINVAL; - - error = user_statfs(pathname, &tmp); - if (!error) - error = put_compat_statfs64(buf, &tmp); - return error; -} - -COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf) -{ - struct kstatfs tmp; - int error; - - if (sz != sizeof(*buf)) - return -EINVAL; - - error = fd_statfs(fd, &tmp); - if (!error) - error = put_compat_statfs64(buf, &tmp); - return error; -} - -/* - * This is a copy of sys_ustat, just dealing with a structure layout. - * Given how simple this syscall is that apporach is more maintainable - * than the various conversion hacks. - */ -COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u) -{ - struct compat_ustat tmp; - struct kstatfs sbuf; - int err = vfs_ustat(new_decode_dev(dev), &sbuf); - if (err) - return err; - - memset(&tmp, 0, sizeof(struct compat_ustat)); - tmp.f_tfree = sbuf.f_bfree; - tmp.f_tinode = sbuf.f_ffree; - if (copy_to_user(u, &tmp, sizeof(struct compat_ustat))) - return -EFAULT; - return 0; -} - -static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) -{ - if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || - __get_user(kfl->l_type, &ufl->l_type) || - __get_user(kfl->l_whence, &ufl->l_whence) || - __get_user(kfl->l_start, &ufl->l_start) || - __get_user(kfl->l_len, &ufl->l_len) || - __get_user(kfl->l_pid, &ufl->l_pid)) - return -EFAULT; - return 0; -} - -static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) -{ - if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) || - __put_user(kfl->l_type, &ufl->l_type) || - __put_user(kfl->l_whence, &ufl->l_whence) || - __put_user(kfl->l_start, &ufl->l_start) || - __put_user(kfl->l_len, &ufl->l_len) || - __put_user(kfl->l_pid, &ufl->l_pid)) - return -EFAULT; - return 0; -} - -#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64 -static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl) -{ - if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || - __get_user(kfl->l_type, &ufl->l_type) || - __get_user(kfl->l_whence, &ufl->l_whence) || - __get_user(kfl->l_start, &ufl->l_start) || - __get_user(kfl->l_len, &ufl->l_len) || - __get_user(kfl->l_pid, &ufl->l_pid)) - return -EFAULT; - return 0; -} -#endif - -#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64 -static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl) -{ - if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) || - __put_user(kfl->l_type, &ufl->l_type) || - __put_user(kfl->l_whence, &ufl->l_whence) || - __put_user(kfl->l_start, &ufl->l_start) || - __put_user(kfl->l_len, &ufl->l_len) || - __put_user(kfl->l_pid, &ufl->l_pid)) - return -EFAULT; - return 0; -} -#endif - -static unsigned int -convert_fcntl_cmd(unsigned int cmd) -{ - switch (cmd) { - case F_GETLK64: - return F_GETLK; - case F_SETLK64: - return F_SETLK; - case F_SETLKW64: - return F_SETLKW; - } - - return cmd; -} - -COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, - compat_ulong_t, arg) -{ - mm_segment_t old_fs; - struct flock f; - long ret; - unsigned int conv_cmd; - - switch (cmd) { - case F_GETLK: - case F_SETLK: - case F_SETLKW: - ret = get_compat_flock(&f, compat_ptr(arg)); - if (ret != 0) - break; - old_fs = get_fs(); - set_fs(KERNEL_DS); - ret = sys_fcntl(fd, cmd, (unsigned long)&f); - set_fs(old_fs); - if (cmd == F_GETLK && ret == 0) { - /* GETLK was successful and we need to return the data... - * but it needs to fit in the compat structure. - * l_start shouldn't be too big, unless the original - * start + end is greater than COMPAT_OFF_T_MAX, in which - * case the app was asking for trouble, so we return - * -EOVERFLOW in that case. - * l_len could be too big, in which case we just truncate it, - * and only allow the app to see that part of the conflicting - * lock that might make sense to it anyway - */ - - if (f.l_start > COMPAT_OFF_T_MAX) - ret = -EOVERFLOW; - if (f.l_len > COMPAT_OFF_T_MAX) - f.l_len = COMPAT_OFF_T_MAX; - if (ret == 0) - ret = put_compat_flock(&f, compat_ptr(arg)); - } - break; - - case F_GETLK64: - case F_SETLK64: - case F_SETLKW64: - case F_OFD_GETLK: - case F_OFD_SETLK: - case F_OFD_SETLKW: - ret = get_compat_flock64(&f, compat_ptr(arg)); - if (ret != 0) - break; - old_fs = get_fs(); - set_fs(KERNEL_DS); - conv_cmd = convert_fcntl_cmd(cmd); - ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f); - set_fs(old_fs); - if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) { - /* need to return lock information - see above for commentary */ - if (f.l_start > COMPAT_LOFF_T_MAX) - ret = -EOVERFLOW; - if (f.l_len > COMPAT_LOFF_T_MAX) - f.l_len = COMPAT_LOFF_T_MAX; - if (ret == 0) - ret = put_compat_flock64(&f, compat_ptr(arg)); - } - break; - - default: - ret = sys_fcntl(fd, cmd, arg); - break; - } - return ret; -} - -COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, - compat_ulong_t, arg) -{ - switch (cmd) { - case F_GETLK64: - case F_SETLK64: - case F_SETLKW64: - case F_OFD_GETLK: - case F_OFD_SETLK: - case F_OFD_SETLKW: - return -EINVAL; - } - return compat_sys_fcntl64(fd, cmd, arg); -} - -/* A write operation does a read from user space and vice versa */ -#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ) - -ssize_t compat_rw_copy_check_uvector(int type, - const struct compat_iovec __user *uvector, unsigned long nr_segs, - unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer) -{ - compat_ssize_t tot_len; - struct iovec *iov = *ret_pointer = fast_pointer; - ssize_t ret = 0; - int seg; - - /* - * SuS says "The readv() function *may* fail if the iovcnt argument - * was less than or equal to 0, or greater than {IOV_MAX}. Linux has - * traditionally returned zero for zero segments, so... - */ - if (nr_segs == 0) - goto out; - - ret = -EINVAL; - if (nr_segs > UIO_MAXIOV) - goto out; - if (nr_segs > fast_segs) { - ret = -ENOMEM; - iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); - if (iov == NULL) - goto out; - } - *ret_pointer = iov; - - ret = -EFAULT; - if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector))) - goto out; - - /* - * Single unix specification: - * We should -EINVAL if an element length is not >= 0 and fitting an - * ssize_t. - * - * In Linux, the total length is limited to MAX_RW_COUNT, there is - * no overflow possibility. - */ - tot_len = 0; - ret = -EINVAL; - for (seg = 0; seg < nr_segs; seg++) { - compat_uptr_t buf; - compat_ssize_t len; - - if (__get_user(len, &uvector->iov_len) || - __get_user(buf, &uvector->iov_base)) { - ret = -EFAULT; - goto out; - } - if (len < 0) /* size_t not fitting in compat_ssize_t .. */ - goto out; - if (type >= 0 && - !access_ok(vrfy_dir(type), compat_ptr(buf), len)) { - ret = -EFAULT; - goto out; - } - if (len > MAX_RW_COUNT - tot_len) - len = MAX_RW_COUNT - tot_len; - tot_len += len; - iov->iov_base = compat_ptr(buf); - iov->iov_len = (compat_size_t) len; - uvector++; - iov++; - } - ret = tot_len; - -out: - return ret; -} - struct compat_ncp_mount_data { compat_int_t version; compat_uint_t ncp_fd; @@ -744,653 +203,3 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, out: return retval; } - -struct compat_old_linux_dirent { - compat_ulong_t d_ino; - compat_ulong_t d_offset; - unsigned short d_namlen; - char d_name[1]; -}; - -struct compat_readdir_callback { - struct dir_context ctx; - struct compat_old_linux_dirent __user *dirent; - int result; -}; - -static int compat_fillonedir(struct dir_context *ctx, const char *name, - int namlen, loff_t offset, u64 ino, - unsigned int d_type) -{ - struct compat_readdir_callback *buf = - container_of(ctx, struct compat_readdir_callback, ctx); - struct compat_old_linux_dirent __user *dirent; - compat_ulong_t d_ino; - - if (buf->result) - return -EINVAL; - d_ino = ino; - if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { - buf->result = -EOVERFLOW; - return -EOVERFLOW; - } - buf->result++; - dirent = buf->dirent; - if (!access_ok(VERIFY_WRITE, dirent, - (unsigned long)(dirent->d_name + namlen + 1) - - (unsigned long)dirent)) - goto efault; - if ( __put_user(d_ino, &dirent->d_ino) || - __put_user(offset, &dirent->d_offset) || - __put_user(namlen, &dirent->d_namlen) || - __copy_to_user(dirent->d_name, name, namlen) || - __put_user(0, dirent->d_name + namlen)) - goto efault; - return 0; -efault: - buf->result = -EFAULT; - return -EFAULT; -} - -COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, - struct compat_old_linux_dirent __user *, dirent, unsigned int, count) -{ - int error; - struct fd f = fdget_pos(fd); - struct compat_readdir_callback buf = { - .ctx.actor = compat_fillonedir, - .dirent = dirent - }; - - if (!f.file) - return -EBADF; - - error = iterate_dir(f.file, &buf.ctx); - if (buf.result) - error = buf.result; - - fdput_pos(f); - return error; -} - -struct compat_linux_dirent { - compat_ulong_t d_ino; - compat_ulong_t d_off; - unsigned short d_reclen; - char d_name[1]; -}; - -struct compat_getdents_callback { - struct dir_context ctx; - struct compat_linux_dirent __user *current_dir; - struct compat_linux_dirent __user *previous; - int count; - int error; -}; - -static int compat_filldir(struct dir_context *ctx, const char *name, int namlen, - loff_t offset, u64 ino, unsigned int d_type) -{ - struct compat_linux_dirent __user * dirent; - struct compat_getdents_callback *buf = - container_of(ctx, struct compat_getdents_callback, ctx); - compat_ulong_t d_ino; - int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + - namlen + 2, sizeof(compat_long_t)); - - buf->error = -EINVAL; /* only used if we fail.. */ - if (reclen > buf->count) - return -EINVAL; - d_ino = ino; - if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { - buf->error = -EOVERFLOW; - return -EOVERFLOW; - } - dirent = buf->previous; - if (dirent) { - if (signal_pending(current)) - return -EINTR; - if (__put_user(offset, &dirent->d_off)) - goto efault; - } - dirent = buf->current_dir; - if (__put_user(d_ino, &dirent->d_ino)) - goto efault; - if (__put_user(reclen, &dirent->d_reclen)) - goto efault; - if (copy_to_user(dirent->d_name, name, namlen)) - goto efault; - if (__put_user(0, dirent->d_name + namlen)) - goto efault; - if (__put_user(d_type, (char __user *) dirent + reclen - 1)) - goto efault; - buf->previous = dirent; - dirent = (void __user *)dirent + reclen; - buf->current_dir = dirent; - buf->count -= reclen; - return 0; -efault: - buf->error = -EFAULT; - return -EFAULT; -} - -COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, - struct compat_linux_dirent __user *, dirent, unsigned int, count) -{ - struct fd f; - struct compat_linux_dirent __user * lastdirent; - struct compat_getdents_callback buf = { - .ctx.actor = compat_filldir, - .current_dir = dirent, - .count = count - }; - int error; - - if (!access_ok(VERIFY_WRITE, dirent, count)) - return -EFAULT; - - f = fdget_pos(fd); - if (!f.file) - return -EBADF; - - error = iterate_dir(f.file, &buf.ctx); - if (error >= 0) - error = buf.error; - lastdirent = buf.previous; - if (lastdirent) { - if (put_user(buf.ctx.pos, &lastdirent->d_off)) - error = -EFAULT; - else - error = count - buf.count; - } - fdput_pos(f); - return error; -} - -#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64 - -struct compat_getdents_callback64 { - struct dir_context ctx; - struct linux_dirent64 __user *current_dir; - struct linux_dirent64 __user *previous; - int count; - int error; -}; - -static int compat_filldir64(struct dir_context *ctx, const char *name, - int namlen, loff_t offset, u64 ino, - unsigned int d_type) -{ - struct linux_dirent64 __user *dirent; - struct compat_getdents_callback64 *buf = - container_of(ctx, struct compat_getdents_callback64, ctx); - int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, - sizeof(u64)); - u64 off; - - buf->error = -EINVAL; /* only used if we fail.. */ - if (reclen > buf->count) - return -EINVAL; - dirent = buf->previous; - - if (dirent) { - if (signal_pending(current)) - return -EINTR; - if (__put_user_unaligned(offset, &dirent->d_off)) - goto efault; - } - dirent = buf->current_dir; - if (__put_user_unaligned(ino, &dirent->d_ino)) - goto efault; - off = 0; - if (__put_user_unaligned(off, &dirent->d_off)) - goto efault; - if (__put_user(reclen, &dirent->d_reclen)) - goto efault; - if (__put_user(d_type, &dirent->d_type)) - goto efault; - if (copy_to_user(dirent->d_name, name, namlen)) - goto efault; - if (__put_user(0, dirent->d_name + namlen)) - goto efault; - buf->previous = dirent; - dirent = (void __user *)dirent + reclen; - buf->current_dir = dirent; - buf->count -= reclen; - return 0; -efault: - buf->error = -EFAULT; - return -EFAULT; -} - -COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd, - struct linux_dirent64 __user *, dirent, unsigned int, count) -{ - struct fd f; - struct linux_dirent64 __user * lastdirent; - struct compat_getdents_callback64 buf = { - .ctx.actor = compat_filldir64, - .current_dir = dirent, - .count = count - }; - int error; - - if (!access_ok(VERIFY_WRITE, dirent, count)) - return -EFAULT; - - f = fdget_pos(fd); - if (!f.file) - return -EBADF; - - error = iterate_dir(f.file, &buf.ctx); - if (error >= 0) - error = buf.error; - lastdirent = buf.previous; - if (lastdirent) { - typeof(lastdirent->d_off) d_off = buf.ctx.pos; - if (__put_user_unaligned(d_off, &lastdirent->d_off)) - error = -EFAULT; - else - error = count - buf.count; - } - fdput_pos(f); - return error; -} -#endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */ - -/* - * Exactly like fs/open.c:sys_open(), except that it doesn't set the - * O_LARGEFILE flag. - */ -COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) -{ - return do_sys_open(AT_FDCWD, filename, flags, mode); -} - -/* - * Exactly like fs/open.c:sys_openat(), except that it doesn't set the - * O_LARGEFILE flag. - */ -COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) -{ - return do_sys_open(dfd, filename, flags, mode); -} - -#define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) - -static int poll_select_copy_remaining(struct timespec *end_time, void __user *p, - int timeval, int ret) -{ - struct timespec ts; - - if (!p) - return ret; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - - /* No update for zero timeout */ - if (!end_time->tv_sec && !end_time->tv_nsec) - return ret; - - ktime_get_ts(&ts); - ts = timespec_sub(*end_time, ts); - if (ts.tv_sec < 0) - ts.tv_sec = ts.tv_nsec = 0; - - if (timeval) { - struct compat_timeval rtv; - - rtv.tv_sec = ts.tv_sec; - rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC; - - if (!copy_to_user(p, &rtv, sizeof(rtv))) - return ret; - } else { - struct compat_timespec rts; - - rts.tv_sec = ts.tv_sec; - rts.tv_nsec = ts.tv_nsec; - - if (!copy_to_user(p, &rts, sizeof(rts))) - return ret; - } - /* - * If an application puts its timeval in read-only memory, we - * don't want the Linux-specific update to the timeval to - * cause a fault after the select has completed - * successfully. However, because we're not updating the - * timeval, we can't restart the system call. - */ - -sticky: - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - return ret; -} - -/* - * Ooo, nasty. We need here to frob 32-bit unsigned longs to - * 64-bit unsigned longs. - */ -static -int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, - unsigned long *fdset) -{ - nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); - if (ufdset) { - unsigned long odd; - - if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t))) - return -EFAULT; - - odd = nr & 1UL; - nr &= ~1UL; - while (nr) { - unsigned long h, l; - if (__get_user(l, ufdset) || __get_user(h, ufdset+1)) - return -EFAULT; - ufdset += 2; - *fdset++ = h << 32 | l; - nr -= 2; - } - if (odd && __get_user(*fdset, ufdset)) - return -EFAULT; - } else { - /* Tricky, must clear full unsigned long in the - * kernel fdset at the end, this makes sure that - * actually happens. - */ - memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t)); - } - return 0; -} - -static -int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, - unsigned long *fdset) -{ - unsigned long odd; - nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); - - if (!ufdset) - return 0; - - odd = nr & 1UL; - nr &= ~1UL; - while (nr) { - unsigned long h, l; - l = *fdset++; - h = l >> 32; - if (__put_user(l, ufdset) || __put_user(h, ufdset+1)) - return -EFAULT; - ufdset += 2; - nr -= 2; - } - if (odd && __put_user(*fdset, ufdset)) - return -EFAULT; - return 0; -} - - -/* - * This is a virtual copy of sys_select from fs/select.c and probably - * should be compared to it from time to time - */ - -/* - * We can actually return ERESTARTSYS instead of EINTR, but I'd - * like to be certain this leads to no problems. So I return - * EINTR just for safety. - * - * Update: ERESTARTSYS breaks at least the xview clock binary, so - * I'm trying ERESTARTNOHAND which restart only when you want to. - */ -int compat_core_sys_select(int n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct timespec *end_time) -{ - fd_set_bits fds; - void *bits; - int size, max_fds, ret = -EINVAL; - struct fdtable *fdt; - long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; - - if (n < 0) - goto out_nofds; - - /* max_fds can increase, so grab it once to avoid race */ - rcu_read_lock(); - fdt = files_fdtable(current->files); - max_fds = fdt->max_fds; - rcu_read_unlock(); - if (n > max_fds) - n = max_fds; - - /* - * We need 6 bitmaps (in/out/ex for both incoming and outgoing), - * since we used fdset we need to allocate memory in units of - * long-words. - */ - size = FDS_BYTES(n); - bits = stack_fds; - if (size > sizeof(stack_fds) / 6) { - bits = kmalloc(6 * size, GFP_KERNEL); - ret = -ENOMEM; - if (!bits) - goto out_nofds; - } - fds.in = (unsigned long *) bits; - fds.out = (unsigned long *) (bits + size); - fds.ex = (unsigned long *) (bits + 2*size); - fds.res_in = (unsigned long *) (bits + 3*size); - fds.res_out = (unsigned long *) (bits + 4*size); - fds.res_ex = (unsigned long *) (bits + 5*size); - - if ((ret = compat_get_fd_set(n, inp, fds.in)) || - (ret = compat_get_fd_set(n, outp, fds.out)) || - (ret = compat_get_fd_set(n, exp, fds.ex))) - goto out; - zero_fd_set(n, fds.res_in); - zero_fd_set(n, fds.res_out); - zero_fd_set(n, fds.res_ex); - - ret = do_select(n, &fds, end_time); - - if (ret < 0) - goto out; - if (!ret) { - ret = -ERESTARTNOHAND; - if (signal_pending(current)) - goto out; - ret = 0; - } - - if (compat_set_fd_set(n, inp, fds.res_in) || - compat_set_fd_set(n, outp, fds.res_out) || - compat_set_fd_set(n, exp, fds.res_ex)) - ret = -EFAULT; -out: - if (bits != stack_fds) - kfree(bits); -out_nofds: - return ret; -} - -COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, - compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, - struct compat_timeval __user *, tvp) -{ - struct timespec end_time, *to = NULL; - struct compat_timeval tv; - int ret; - - if (tvp) { - if (copy_from_user(&tv, tvp, sizeof(tv))) - return -EFAULT; - - to = &end_time; - if (poll_select_set_timeout(to, - tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), - (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) - return -EINVAL; - } - - ret = compat_core_sys_select(n, inp, outp, exp, to); - ret = poll_select_copy_remaining(&end_time, tvp, 1, ret); - - return ret; -} - -struct compat_sel_arg_struct { - compat_ulong_t n; - compat_uptr_t inp; - compat_uptr_t outp; - compat_uptr_t exp; - compat_uptr_t tvp; -}; - -COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) -{ - struct compat_sel_arg_struct a; - - if (copy_from_user(&a, arg, sizeof(a))) - return -EFAULT; - return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), - compat_ptr(a.exp), compat_ptr(a.tvp)); -} - -static long do_compat_pselect(int n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask, - compat_size_t sigsetsize) -{ - compat_sigset_t ss32; - sigset_t ksigmask, sigsaved; - struct compat_timespec ts; - struct timespec end_time, *to = NULL; - int ret; - - if (tsp) { - if (copy_from_user(&ts, tsp, sizeof(ts))) - return -EFAULT; - - to = &end_time; - if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) - return -EINVAL; - } - - if (sigmask) { - if (sigsetsize != sizeof(compat_sigset_t)) - return -EINVAL; - if (copy_from_user(&ss32, sigmask, sizeof(ss32))) - return -EFAULT; - sigset_from_compat(&ksigmask, &ss32); - - sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); - } - - ret = compat_core_sys_select(n, inp, outp, exp, to); - ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); - - if (ret == -ERESTARTNOHAND) { - /* - * Don't restore the signal mask yet. Let do_signal() deliver - * the signal on the way back to userspace, before the signal - * mask is restored. - */ - if (sigmask) { - memcpy(¤t->saved_sigmask, &sigsaved, - sizeof(sigsaved)); - set_restore_sigmask(); - } - } else if (sigmask) - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - - return ret; -} - -COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, - compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, - struct compat_timespec __user *, tsp, void __user *, sig) -{ - compat_size_t sigsetsize = 0; - compat_uptr_t up = 0; - - if (sig) { - if (!access_ok(VERIFY_READ, sig, - sizeof(compat_uptr_t)+sizeof(compat_size_t)) || - __get_user(up, (compat_uptr_t __user *)sig) || - __get_user(sigsetsize, - (compat_size_t __user *)(sig+sizeof(up)))) - return -EFAULT; - } - return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up), - sigsetsize); -} - -COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, - unsigned int, nfds, struct compat_timespec __user *, tsp, - const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) -{ - compat_sigset_t ss32; - sigset_t ksigmask, sigsaved; - struct compat_timespec ts; - struct timespec end_time, *to = NULL; - int ret; - - if (tsp) { - if (copy_from_user(&ts, tsp, sizeof(ts))) - return -EFAULT; - - to = &end_time; - if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) - return -EINVAL; - } - - if (sigmask) { - if (sigsetsize != sizeof(compat_sigset_t)) - return -EINVAL; - if (copy_from_user(&ss32, sigmask, sizeof(ss32))) - return -EFAULT; - sigset_from_compat(&ksigmask, &ss32); - - sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); - } - - ret = do_sys_poll(ufds, nfds, to); - - /* We can restart this syscall, usually */ - if (ret == -EINTR) { - /* - * Don't restore the signal mask yet. Let do_signal() deliver - * the signal on the way back to userspace, before the signal - * mask is restored. - */ - if (sigmask) { - memcpy(¤t->saved_sigmask, &sigsaved, - sizeof(sigsaved)); - set_restore_sigmask(); - } - ret = -ERESTARTNOHAND; - } else if (sigmask) - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - - ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); - - return ret; -} - -#ifdef CONFIG_FHANDLE -/* - * Exactly like fs/open.c:sys_open_by_handle_at(), except that it - * doesn't set the O_LARGEFILE flag. - */ -COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd, - struct file_handle __user *, handle, int, flags) -{ - return do_handle_open(mountdirfd, handle, flags); -} -#endif diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 02a7a9286449..6d6eca394d4d 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -327,7 +327,6 @@ EXPORT_SYMBOL(fscrypt_decrypt_page); static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *dir; - struct fscrypt_info *ci; int dir_has_key, cached_with_key; if (flags & LOOKUP_RCU) @@ -339,18 +338,11 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) return 0; } - ci = d_inode(dir)->i_crypt_info; - if (ci && ci->ci_keyring_key && - (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | - (1 << KEY_FLAG_REVOKED) | - (1 << KEY_FLAG_DEAD)))) - ci = NULL; - /* this should eventually be an flag in d_flags */ spin_lock(&dentry->d_lock); cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY; spin_unlock(&dentry->d_lock); - dir_has_key = (ci != NULL); + dir_has_key = (d_inode(dir)->i_crypt_info != NULL); dput(dir); /* diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 13052b85c393..37b49894c762 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -350,7 +350,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, fname->disk_name.len = iname->len; return 0; } - ret = fscrypt_get_crypt_info(dir); + ret = fscrypt_get_encryption_info(dir); if (ret && ret != -EOPNOTSUPP) return ret; diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index fdbb8af32eaf..e39696e64494 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -67,7 +67,6 @@ struct fscrypt_info { u8 ci_filename_mode; u8 ci_flags; struct crypto_skcipher *ci_ctfm; - struct key *ci_keyring_key; u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; }; @@ -101,7 +100,4 @@ extern int fscrypt_do_page_crypto(const struct inode *inode, extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags); -/* keyinfo.c */ -extern int fscrypt_get_crypt_info(struct inode *); - #endif /* _FSCRYPT_PRIVATE_H */ diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index d5d896fa5a71..8cdfddce2b34 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -95,6 +95,7 @@ static int validate_user_key(struct fscrypt_info *crypt_info, kfree(description); if (IS_ERR(keyring_key)) return PTR_ERR(keyring_key); + down_read(&keyring_key->sem); if (keyring_key->type != &key_type_logon) { printk_once(KERN_WARNING @@ -102,11 +103,9 @@ static int validate_user_key(struct fscrypt_info *crypt_info, res = -ENOKEY; goto out; } - down_read(&keyring_key->sem); ukp = user_key_payload_locked(keyring_key); if (ukp->datalen != sizeof(struct fscrypt_key)) { res = -EINVAL; - up_read(&keyring_key->sem); goto out; } master_key = (struct fscrypt_key *)ukp->data; @@ -117,17 +116,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info, "%s: key size incorrect: %d\n", __func__, master_key->size); res = -ENOKEY; - up_read(&keyring_key->sem); goto out; } res = derive_key_aes(ctx->nonce, master_key->raw, raw_key); - up_read(&keyring_key->sem); - if (res) - goto out; - - crypt_info->ci_keyring_key = keyring_key; - return 0; out: + up_read(&keyring_key->sem); key_put(keyring_key); return res; } @@ -169,12 +162,11 @@ static void put_crypt_info(struct fscrypt_info *ci) if (!ci) return; - key_put(ci->ci_keyring_key); crypto_free_skcipher(ci->ci_ctfm); kmem_cache_free(fscrypt_info_cachep, ci); } -int fscrypt_get_crypt_info(struct inode *inode) +int fscrypt_get_encryption_info(struct inode *inode) { struct fscrypt_info *crypt_info; struct fscrypt_context ctx; @@ -184,21 +176,15 @@ int fscrypt_get_crypt_info(struct inode *inode) u8 *raw_key = NULL; int res; + if (inode->i_crypt_info) + return 0; + res = fscrypt_initialize(inode->i_sb->s_cop->flags); if (res) return res; if (!inode->i_sb->s_cop->get_context) return -EOPNOTSUPP; -retry: - crypt_info = ACCESS_ONCE(inode->i_crypt_info); - if (crypt_info) { - if (!crypt_info->ci_keyring_key || - key_validate(crypt_info->ci_keyring_key) == 0) - return 0; - fscrypt_put_encryption_info(inode, crypt_info); - goto retry; - } res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); if (res < 0) { @@ -229,7 +215,6 @@ retry: crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; crypt_info->ci_ctfm = NULL; - crypt_info->ci_keyring_key = NULL; memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, sizeof(crypt_info->ci_master_key)); @@ -273,14 +258,8 @@ retry: if (res) goto out; - kzfree(raw_key); - raw_key = NULL; - if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) { - put_crypt_info(crypt_info); - goto retry; - } - return 0; - + if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL) + crypt_info = NULL; out: if (res == -ENOKEY) res = 0; @@ -288,6 +267,7 @@ out: kzfree(raw_key); return res; } +EXPORT_SYMBOL(fscrypt_get_encryption_info); void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci) { @@ -305,17 +285,3 @@ void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci) put_crypt_info(ci); } EXPORT_SYMBOL(fscrypt_put_encryption_info); - -int fscrypt_get_encryption_info(struct inode *inode) -{ - struct fscrypt_info *ci = inode->i_crypt_info; - - if (!ci || - (ci->ci_keyring_key && - (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | - (1 << KEY_FLAG_REVOKED) | - (1 << KEY_FLAG_DEAD))))) - return fscrypt_get_crypt_info(inode); - return 0; -} -EXPORT_SYMBOL(fscrypt_get_encryption_info); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 14b76da71269..4908906d54d5 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -33,17 +33,10 @@ static int create_encryption_context_from_policy(struct inode *inode, const struct fscrypt_policy *policy) { struct fscrypt_context ctx; - int res; if (!inode->i_sb->s_cop->set_context) return -EOPNOTSUPP; - if (inode->i_sb->s_cop->prepare_context) { - res = inode->i_sb->s_cop->prepare_context(inode); - if (res) - return res; - } - ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1; memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE); @@ -373,6 +373,22 @@ restart: } spin_lock_irq(&mapping->tree_lock); + if (!entry) { + /* + * We needed to drop the page_tree lock while calling + * radix_tree_preload() and we didn't have an entry to + * lock. See if another thread inserted an entry at + * our index during this time. + */ + entry = __radix_tree_lookup(&mapping->page_tree, index, + NULL, &slot); + if (entry) { + radix_tree_preload_end(); + spin_unlock_irq(&mapping->tree_lock); + goto restart; + } + } + if (pmd_downgrade) { radix_tree_delete(&mapping->page_tree, index); mapping->nrexceptional--; @@ -388,19 +404,12 @@ restart: if (err) { spin_unlock_irq(&mapping->tree_lock); /* - * Someone already created the entry? This is a - * normal failure when inserting PMDs in a range - * that already contains PTEs. In that case we want - * to return -EEXIST immediately. - */ - if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD)) - goto restart; - /* - * Our insertion of a DAX PMD entry failed, most - * likely because it collided with a PTE sized entry - * at a different index in the PMD range. We haven't - * inserted anything into the radix tree and have no - * waiters to wake. + * Our insertion of a DAX entry failed, most likely + * because we were inserting a PMD entry and it + * collided with a PTE sized entry at a different + * index in the PMD range. We haven't inserted + * anything into the radix tree and have no waiters to + * wake. */ return ERR_PTR(err); } @@ -982,7 +991,7 @@ int __dax_zero_page_range(struct block_device *bdev, sector_t sector, sector_t start_sector = dax.sector + (offset >> 9); return blkdev_issue_zeroout(bdev, start_sector, - length >> 9, GFP_NOFS, true); + length >> 9, GFP_NOFS, 0); } else { if (dax_map_atomic(bdev, &dax) < 0) return PTR_ERR(dax.addr); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 7d398d300e97..9382db998ec9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -743,7 +743,7 @@ static int tcp_accept_from_sock(struct connection *con) newsock->type = con->sock->type; newsock->ops = con->sock->ops; - result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK); + result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true); if (result < 0) goto accept_err; diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 95c1c8d34539..9c351bf757b2 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -349,7 +349,6 @@ struct ecryptfs_mount_crypt_stat { struct ecryptfs_sb_info { struct super_block *wsi_sb; struct ecryptfs_mount_crypt_stat mount_crypt_stat; - struct backing_dev_info bdi; }; /* file private data. */ diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 151872dcc1f4..9014479d0160 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -519,12 +519,11 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags goto out; } - rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs"); + rc = super_setup_bdi(s); if (rc) goto out1; ecryptfs_set_superblock_private(s, sbi); - s->s_bdi = &sbi->bdi; /* ->kill_sb() will take care of sbi after that point */ sbi = NULL; @@ -633,7 +632,6 @@ static void ecryptfs_kill_block_super(struct super_block *sb) if (!sb_info) return; ecryptfs_destroy_mount_crypt_stat(&sb_info->mount_crypt_stat); - bdi_destroy(&sb_info->bdi); kmem_cache_free(ecryptfs_sb_info_cache, sb_info); } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 341251421ced..5420767c9b68 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -42,6 +42,7 @@ #include <linux/seq_file.h> #include <linux/compat.h> #include <linux/rculist.h> +#include <net/busy_poll.h> /* * LOCKING: @@ -224,6 +225,11 @@ struct eventpoll { /* used to optimize loop detection check */ int visited; struct list_head visited_list_link; + +#ifdef CONFIG_NET_RX_BUSY_POLL + /* used to track busy poll napi_id */ + unsigned int napi_id; +#endif }; /* Wait structure used by the poll hooks */ @@ -384,6 +390,77 @@ static inline int ep_events_available(struct eventpoll *ep) return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR; } +#ifdef CONFIG_NET_RX_BUSY_POLL +static bool ep_busy_loop_end(void *p, unsigned long start_time) +{ + struct eventpoll *ep = p; + + return ep_events_available(ep) || busy_loop_timeout(start_time); +} +#endif /* CONFIG_NET_RX_BUSY_POLL */ + +/* + * Busy poll if globally on and supporting sockets found && no events, + * busy loop will return if need_resched or ep_events_available. + * + * we must do our busy polling with irqs enabled + */ +static void ep_busy_loop(struct eventpoll *ep, int nonblock) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + unsigned int napi_id = READ_ONCE(ep->napi_id); + + if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) + napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep); +#endif +} + +static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + if (ep->napi_id) + ep->napi_id = 0; +#endif +} + +/* + * Set epoll busy poll NAPI ID from sk. + */ +static inline void ep_set_busy_poll_napi_id(struct epitem *epi) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + struct eventpoll *ep; + unsigned int napi_id; + struct socket *sock; + struct sock *sk; + int err; + + if (!net_busy_loop_on()) + return; + + sock = sock_from_file(epi->ffd.file, &err); + if (!sock) + return; + + sk = sock->sk; + if (!sk) + return; + + napi_id = READ_ONCE(sk->sk_napi_id); + ep = epi->ep; + + /* Non-NAPI IDs can be rejected + * or + * Nothing to do if we already have this ID + */ + if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id) + return; + + /* record NAPI ID for use in next busy poll */ + ep->napi_id = napi_id; +#endif +} + /** * ep_call_nested - Perform a bound (possibly) nested call, by checking * that the recursion limit is not exceeded, and that @@ -1022,6 +1099,8 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k spin_lock_irqsave(&ep->lock, flags); + ep_set_busy_poll_napi_id(epi); + /* * If the event mask does not contain any poll(2) event, we consider the * descriptor to be disabled. This condition is likely the effect of the @@ -1363,6 +1442,9 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, /* We have to drop the new item inside our item list to keep track of it */ spin_lock_irqsave(&ep->lock, flags); + /* record NAPI ID of new item if present */ + ep_set_busy_poll_napi_id(epi); + /* If the file is already "ready" we drop it inside the ready list */ if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); @@ -1637,10 +1719,21 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, } fetch_events: + + if (!ep_events_available(ep)) + ep_busy_loop(ep, timed_out); + spin_lock_irqsave(&ep->lock, flags); if (!ep_events_available(ep)) { /* + * Busy poll timed out. Drop NAPI ID for now, we can add + * it back in when we have moved a socket with a valid NAPI + * ID onto the ready list. + */ + ep_reset_busy_poll_napi_id(ep); + + /* * We don't have any available event to return to the caller. * We need to sleep here, and we will be wake up by * ep_poll_callback() when events will become available. diff --git a/fs/exec.c b/fs/exec.c index 65145a3df065..72934df68471 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1320,6 +1320,7 @@ void setup_new_exec(struct linux_binprm * bprm) else set_dumpable(current->mm, suid_dumpable); + arch_setup_new_exec(); perf_event_exec(); __set_task_comm(current, kbasename(bprm->filename), true); diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h index 2e86086bc940..5dc392404559 100644 --- a/fs/exofs/exofs.h +++ b/fs/exofs/exofs.h @@ -64,7 +64,6 @@ struct exofs_dev { * our extension to the in-memory superblock */ struct exofs_sb_info { - struct backing_dev_info bdi; /* register our bdi with VFS */ struct exofs_sb_stats s_ess; /* Written often, pre-allocate*/ int s_timeout; /* timeout for OSD operations */ uint64_t s_nextid; /* highest object ID used */ diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 1076a4233b39..819624cfc8da 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -464,7 +464,6 @@ static void exofs_put_super(struct super_block *sb) sbi->one_comp.obj.partition); exofs_sysfs_sb_del(sbi); - bdi_destroy(&sbi->bdi); exofs_free_sbi(sbi); sb->s_fs_info = NULL; } @@ -809,8 +808,12 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) __sbi_read_stats(sbi); /* set up operation vectors */ - sbi->bdi.ra_pages = __ra_pages(&sbi->layout); - sb->s_bdi = &sbi->bdi; + ret = super_setup_bdi(sb); + if (ret) { + EXOFS_DBGMSG("Failed to super_setup_bdi\n"); + goto free_sbi; + } + sb->s_bdi->ra_pages = __ra_pages(&sbi->layout); sb->s_fs_info = sbi; sb->s_op = &exofs_sops; sb->s_export_op = &exofs_export_ops; @@ -836,14 +839,6 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) goto free_sbi; } - ret = bdi_setup_and_register(&sbi->bdi, "exofs"); - if (ret) { - EXOFS_DBGMSG("Failed to bdi_setup_and_register\n"); - dput(sb->s_root); - sb->s_root = NULL; - goto free_sbi; - } - exofs_sysfs_dbg_print(); _exofs_print_device("Mounting", opts->dev_name, ore_comp_dev(&sbi->oc, 0), diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f493af666591..fb69ee2388db 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2466,6 +2466,7 @@ extern int ext4_setattr(struct dentry *, struct iattr *); extern int ext4_getattr(const struct path *, struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); extern void ext4_clear_inode(struct inode *); +extern int ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int ext4_sync_inode(handle_t *, struct inode *); extern void ext4_dirty_inode(struct inode *, int); extern int ext4_change_inode_journal_flag(struct inode *, int); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8210c1f43556..cefa9835f275 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -744,7 +744,7 @@ const struct file_operations ext4_file_operations = { const struct inode_operations ext4_file_inode_operations = { .setattr = ext4_setattr, - .getattr = ext4_getattr, + .getattr = ext4_file_getattr, .listxattr = ext4_listxattr, .get_acl = ext4_get_acl, .set_acl = ext4_set_acl, diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 30a9f210d1e3..375fb1c05d49 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1169,10 +1169,9 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, set_buffer_uptodate(dir_block); err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); if (err) - goto out; + return err; set_buffer_verified(dir_block); -out: - return err; + return ext4_mark_inode_dirty(handle, inode); } static int ext4_convert_inline_data_nolock(handle_t *handle, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7385e6a6b6cb..b9ffa9f4191f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5390,17 +5390,52 @@ err_out: int ext4_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - struct inode *inode; - unsigned long long delalloc_blocks; + struct inode *inode = d_inode(path->dentry); + struct ext4_inode *raw_inode; + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned int flags; + + if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) { + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = ei->i_crtime.tv_sec; + stat->btime.tv_nsec = ei->i_crtime.tv_nsec; + } + + flags = ei->i_flags & EXT4_FL_USER_VISIBLE; + if (flags & EXT4_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (flags & EXT4_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (flags & EXT4_ENCRYPT_FL) + stat->attributes |= STATX_ATTR_ENCRYPTED; + if (flags & EXT4_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (flags & EXT4_NODUMP_FL) + stat->attributes |= STATX_ATTR_NODUMP; + + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP); - inode = d_inode(path->dentry); generic_fillattr(inode, stat); + return 0; +} + +int ext4_file_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) +{ + struct inode *inode = d_inode(path->dentry); + u64 delalloc_blocks; + + ext4_getattr(path, stat, request_mask, query_flags); /* * If there is inline data in the inode, the inode will normally not * have data blocks allocated (it may have an external xattr block). * Report at least one sector for such files, so tools like tar, rsync, - * others doen't incorrectly think the file is completely sparse. + * others don't incorrectly think the file is completely sparse. */ if (unlikely(ext4_has_inline_data(inode))) stat->blocks += (stat->size + 511) >> 9; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 578f8c33fb44..c992ef2c2f94 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -511,7 +511,7 @@ mext_check_arguments(struct inode *orig_inode, if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) != (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) { ext4_debug("ext4 move extent: orig and donor's start " - "offset are not alligned [ino:orig %lu, donor %lu]\n", + "offsets are not aligned [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 6ad612c576fc..07e5e1405771 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3912,6 +3912,7 @@ const struct inode_operations ext4_dir_inode_operations = { .tmpfile = ext4_tmpfile, .rename = ext4_rename2, .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, .get_acl = ext4_get_acl, .set_acl = ext4_set_acl, @@ -3920,6 +3921,7 @@ const struct inode_operations ext4_dir_inode_operations = { const struct inode_operations ext4_special_inode_operations = { .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, .get_acl = ext4_get_acl, .set_acl = ext4_set_acl, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2e03a0a88d92..a9448db1cf7e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1120,17 +1120,16 @@ static int ext4_get_context(struct inode *inode, void *ctx, size_t len) EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len); } -static int ext4_prepare_context(struct inode *inode) -{ - return ext4_convert_inline_data(inode); -} - static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { handle_t *handle = fs_data; int res, res2, retries = 0; + res = ext4_convert_inline_data(inode); + if (res) + return res; + /* * If a journal handle was specified, then the encryption context is * being set on a new inode via inheritance and is part of a larger @@ -1196,7 +1195,6 @@ static unsigned ext4_max_namelen(struct inode *inode) static const struct fscrypt_operations ext4_cryptops = { .key_prefix = "ext4:", .get_context = ext4_get_context, - .prepare_context = ext4_prepare_context, .set_context = ext4_set_context, .dummy_context = ext4_dummy_context, .is_encrypted = ext4_encrypted_inode, diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index 73b184d161fc..5c8fc53cb0e5 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -85,17 +85,20 @@ errout: const struct inode_operations ext4_encrypted_symlink_inode_operations = { .get_link = ext4_encrypted_get_link, .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, }; const struct inode_operations ext4_symlink_inode_operations = { .get_link = page_get_link, .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, }; const struct inode_operations ext4_fast_symlink_inode_operations = { .get_link = simple_get_link, .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, }; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 67636acf7624..996e7900d4c8 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -131,31 +131,26 @@ static __le32 ext4_xattr_block_csum(struct inode *inode, } static int ext4_xattr_block_csum_verify(struct inode *inode, - sector_t block_nr, - struct ext4_xattr_header *hdr) + struct buffer_head *bh) { - if (ext4_has_metadata_csum(inode->i_sb) && - (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr))) - return 0; - return 1; -} - -static void ext4_xattr_block_csum_set(struct inode *inode, - sector_t block_nr, - struct ext4_xattr_header *hdr) -{ - if (!ext4_has_metadata_csum(inode->i_sb)) - return; + struct ext4_xattr_header *hdr = BHDR(bh); + int ret = 1; - hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr); + if (ext4_has_metadata_csum(inode->i_sb)) { + lock_buffer(bh); + ret = (hdr->h_checksum == ext4_xattr_block_csum(inode, + bh->b_blocknr, hdr)); + unlock_buffer(bh); + } + return ret; } -static inline int ext4_handle_dirty_xattr_block(handle_t *handle, - struct inode *inode, - struct buffer_head *bh) +static void ext4_xattr_block_csum_set(struct inode *inode, + struct buffer_head *bh) { - ext4_xattr_block_csum_set(inode, bh->b_blocknr, BHDR(bh)); - return ext4_handle_dirty_metadata(handle, inode, bh); + if (ext4_has_metadata_csum(inode->i_sb)) + BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode, + bh->b_blocknr, BHDR(bh)); } static inline const struct xattr_handler * @@ -233,7 +228,7 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) return -EFSCORRUPTED; - if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) + if (!ext4_xattr_block_csum_verify(inode, bh)) return -EFSBADCRC; error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size, bh->b_data); @@ -618,23 +613,22 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, } } + ext4_xattr_block_csum_set(inode, bh); /* * Beware of this ugliness: Releasing of xattr block references * from different inodes can race and so we have to protect * from a race where someone else frees the block (and releases * its journal_head) before we are done dirtying the buffer. In * nojournal mode this race is harmless and we actually cannot - * call ext4_handle_dirty_xattr_block() with locked buffer as + * call ext4_handle_dirty_metadata() with locked buffer as * that function can call sync_dirty_buffer() so for that case * we handle the dirtying after unlocking the buffer. */ if (ext4_handle_valid(handle)) - error = ext4_handle_dirty_xattr_block(handle, inode, - bh); + error = ext4_handle_dirty_metadata(handle, inode, bh); unlock_buffer(bh); if (!ext4_handle_valid(handle)) - error = ext4_handle_dirty_xattr_block(handle, inode, - bh); + error = ext4_handle_dirty_metadata(handle, inode, bh); if (IS_SYNC(inode)) ext4_handle_sync(handle); dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1)); @@ -863,13 +857,14 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, ext4_xattr_cache_insert(ext4_mb_cache, bs->bh); } + ext4_xattr_block_csum_set(inode, bs->bh); unlock_buffer(bs->bh); if (error == -EFSCORRUPTED) goto bad_block; if (!error) - error = ext4_handle_dirty_xattr_block(handle, - inode, - bs->bh); + error = ext4_handle_dirty_metadata(handle, + inode, + bs->bh); if (error) goto cleanup; goto inserted; @@ -967,10 +962,11 @@ inserted: ce->e_reusable = 0; ea_bdebug(new_bh, "reusing; refcount now=%d", ref); + ext4_xattr_block_csum_set(inode, new_bh); unlock_buffer(new_bh); - error = ext4_handle_dirty_xattr_block(handle, - inode, - new_bh); + error = ext4_handle_dirty_metadata(handle, + inode, + new_bh); if (error) goto cleanup_dquot; } @@ -1020,11 +1016,12 @@ getblk_failed: goto getblk_failed; } memcpy(new_bh->b_data, s->base, new_bh->b_size); + ext4_xattr_block_csum_set(inode, new_bh); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); ext4_xattr_cache_insert(ext4_mb_cache, new_bh); - error = ext4_handle_dirty_xattr_block(handle, - inode, new_bh); + error = ext4_handle_dirty_metadata(handle, inode, + new_bh); if (error) goto cleanup; } diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index a77df377e2e8..ee2d0a485fc3 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -196,6 +196,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS); si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE; si->base_mem += NM_I(sbi)->nat_blocks / 8; + si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short); get_cache: si->cache_mem = 0; diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 4650c9b85de7..8d5c62b07b28 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -750,7 +750,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, dentry_blk = page_address(page); bit_pos = dentry - dentry_blk->dentry; for (i = 0; i < slots; i++) - clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); + __clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); /* Let's check and deallocate this dentry page */ bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index e849f83d6114..0a6e115562f6 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -561,6 +561,8 @@ struct f2fs_nm_info { struct mutex build_lock; /* lock for build free nids */ unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE]; unsigned char *nat_block_bitmap; + unsigned short *free_nid_count; /* free nid count of NAT block */ + spinlock_t free_nid_lock; /* protect updating of nid count */ /* for checkpoint */ char *nat_bitmap; /* NAT bitmap pointer */ diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 94967171dee8..481aa8dc79f4 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -338,9 +338,6 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, set_nat_flag(e, IS_CHECKPOINTED, false); __set_nat_cache_dirty(nm_i, e); - if (enabled_nat_bits(sbi, NULL) && new_blkaddr == NEW_ADDR) - clear_bit_le(NAT_BLOCK_OFFSET(ni->nid), nm_i->empty_nat_bits); - /* update fsync_mark if its inode nat entry is still alive */ if (ni->nid != ni->ino) e = __lookup_nat_cache(nm_i, ni->ino); @@ -1823,7 +1820,8 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid) kmem_cache_free(free_nid_slab, i); } -void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, bool set) +static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, + bool set, bool build, bool locked) { struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid); @@ -1833,9 +1831,18 @@ void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, bool set) return; if (set) - set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); else - clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + + if (!locked) + spin_lock(&nm_i->free_nid_lock); + if (set) + nm_i->free_nid_count[nat_ofs]++; + else if (!build) + nm_i->free_nid_count[nat_ofs]--; + if (!locked) + spin_unlock(&nm_i->free_nid_lock); } static void scan_nat_page(struct f2fs_sb_info *sbi, @@ -1847,7 +1854,10 @@ static void scan_nat_page(struct f2fs_sb_info *sbi, unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid); int i; - set_bit_le(nat_ofs, nm_i->nat_block_bitmap); + if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap)) + return; + + __set_bit_le(nat_ofs, nm_i->nat_block_bitmap); i = start_nid % NAT_ENTRY_PER_BLOCK; @@ -1861,7 +1871,7 @@ static void scan_nat_page(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, blk_addr == NEW_ADDR); if (blk_addr == NULL_ADDR) freed = add_free_nid(sbi, start_nid, true); - update_free_nid_bitmap(sbi, start_nid, freed); + update_free_nid_bitmap(sbi, start_nid, freed, true, false); } } @@ -1877,6 +1887,8 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi) for (i = 0; i < nm_i->nat_blocks; i++) { if (!test_bit_le(i, nm_i->nat_block_bitmap)) continue; + if (!nm_i->free_nid_count[i]) + continue; for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) { nid_t nid; @@ -1907,58 +1919,6 @@ out: up_read(&nm_i->nat_tree_lock); } -static int scan_nat_bits(struct f2fs_sb_info *sbi) -{ - struct f2fs_nm_info *nm_i = NM_I(sbi); - struct page *page; - unsigned int i = 0; - nid_t nid; - - if (!enabled_nat_bits(sbi, NULL)) - return -EAGAIN; - - down_read(&nm_i->nat_tree_lock); -check_empty: - i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i); - if (i >= nm_i->nat_blocks) { - i = 0; - goto check_partial; - } - - for (nid = i * NAT_ENTRY_PER_BLOCK; nid < (i + 1) * NAT_ENTRY_PER_BLOCK; - nid++) { - if (unlikely(nid >= nm_i->max_nid)) - break; - add_free_nid(sbi, nid, true); - } - - if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS) - goto out; - i++; - goto check_empty; - -check_partial: - i = find_next_zero_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i); - if (i >= nm_i->nat_blocks) { - disable_nat_bits(sbi, true); - up_read(&nm_i->nat_tree_lock); - return -EINVAL; - } - - nid = i * NAT_ENTRY_PER_BLOCK; - page = get_current_nat_page(sbi, nid); - scan_nat_page(sbi, page, nid); - f2fs_put_page(page, 1); - - if (nm_i->nid_cnt[FREE_NID_LIST] < MAX_FREE_NIDS) { - i++; - goto check_partial; - } -out: - up_read(&nm_i->nat_tree_lock); - return 0; -} - static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) { struct f2fs_nm_info *nm_i = NM_I(sbi); @@ -1980,21 +1940,6 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) if (nm_i->nid_cnt[FREE_NID_LIST]) return; - - /* try to find free nids with nat_bits */ - if (!scan_nat_bits(sbi) && nm_i->nid_cnt[FREE_NID_LIST]) - return; - } - - /* find next valid candidate */ - if (enabled_nat_bits(sbi, NULL)) { - int idx = find_next_zero_bit_le(nm_i->full_nat_bits, - nm_i->nat_blocks, 0); - - if (idx >= nm_i->nat_blocks) - set_sbi_flag(sbi, SBI_NEED_FSCK); - else - nid = idx * NAT_ENTRY_PER_BLOCK; } /* readahead nat pages to be scanned */ @@ -2081,7 +2026,7 @@ retry: __insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false); nm_i->available_nids--; - update_free_nid_bitmap(sbi, *nid, false); + update_free_nid_bitmap(sbi, *nid, false, false, false); spin_unlock(&nm_i->nid_list_lock); return true; @@ -2137,7 +2082,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) nm_i->available_nids++; - update_free_nid_bitmap(sbi, nid, true); + update_free_nid_bitmap(sbi, nid, true, false, false); spin_unlock(&nm_i->nid_list_lock); @@ -2383,7 +2328,7 @@ add_out: list_add_tail(&nes->set_list, head); } -void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, +static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, struct page *page) { struct f2fs_nm_info *nm_i = NM_I(sbi); @@ -2402,16 +2347,16 @@ void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, valid++; } if (valid == 0) { - set_bit_le(nat_index, nm_i->empty_nat_bits); - clear_bit_le(nat_index, nm_i->full_nat_bits); + __set_bit_le(nat_index, nm_i->empty_nat_bits); + __clear_bit_le(nat_index, nm_i->full_nat_bits); return; } - clear_bit_le(nat_index, nm_i->empty_nat_bits); + __clear_bit_le(nat_index, nm_i->empty_nat_bits); if (valid == NAT_ENTRY_PER_BLOCK) - set_bit_le(nat_index, nm_i->full_nat_bits); + __set_bit_le(nat_index, nm_i->full_nat_bits); else - clear_bit_le(nat_index, nm_i->full_nat_bits); + __clear_bit_le(nat_index, nm_i->full_nat_bits); } static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, @@ -2467,11 +2412,11 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, add_free_nid(sbi, nid, false); spin_lock(&NM_I(sbi)->nid_list_lock); NM_I(sbi)->available_nids++; - update_free_nid_bitmap(sbi, nid, true); + update_free_nid_bitmap(sbi, nid, true, false, false); spin_unlock(&NM_I(sbi)->nid_list_lock); } else { spin_lock(&NM_I(sbi)->nid_list_lock); - update_free_nid_bitmap(sbi, nid, false); + update_free_nid_bitmap(sbi, nid, false, false, false); spin_unlock(&NM_I(sbi)->nid_list_lock); } } @@ -2577,6 +2522,40 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) return 0; } +inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned int i = 0; + nid_t nid, last_nid; + + if (!enabled_nat_bits(sbi, NULL)) + return; + + for (i = 0; i < nm_i->nat_blocks; i++) { + i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i); + if (i >= nm_i->nat_blocks) + break; + + __set_bit_le(i, nm_i->nat_block_bitmap); + + nid = i * NAT_ENTRY_PER_BLOCK; + last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK; + + spin_lock(&nm_i->free_nid_lock); + for (; nid < last_nid; nid++) + update_free_nid_bitmap(sbi, nid, true, true, true); + spin_unlock(&nm_i->free_nid_lock); + } + + for (i = 0; i < nm_i->nat_blocks; i++) { + i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i); + if (i >= nm_i->nat_blocks) + break; + + __set_bit_le(i, nm_i->nat_block_bitmap); + } +} + static int init_node_manager(struct f2fs_sb_info *sbi) { struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi); @@ -2638,7 +2617,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) return 0; } -int init_free_nid_cache(struct f2fs_sb_info *sbi) +static int init_free_nid_cache(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); @@ -2651,6 +2630,14 @@ int init_free_nid_cache(struct f2fs_sb_info *sbi) GFP_KERNEL); if (!nm_i->nat_block_bitmap) return -ENOMEM; + + nm_i->free_nid_count = f2fs_kvzalloc(nm_i->nat_blocks * + sizeof(unsigned short), GFP_KERNEL); + if (!nm_i->free_nid_count) + return -ENOMEM; + + spin_lock_init(&nm_i->free_nid_lock); + return 0; } @@ -2670,6 +2657,9 @@ int build_node_manager(struct f2fs_sb_info *sbi) if (err) return err; + /* load free nid status from nat_bits table */ + load_free_nid_bitmap(sbi); + build_free_nids(sbi, true, true); return 0; } @@ -2730,6 +2720,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) kvfree(nm_i->nat_block_bitmap); kvfree(nm_i->free_nid_bitmap); + kvfree(nm_i->free_nid_count); kfree(nm_i->nat_bitmap); kfree(nm_i->nat_bits); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 4bd7a8b19332..29ef7088c558 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1163,6 +1163,12 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) if (f2fs_discard_en(sbi) && !f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; + + /* don't overwrite by SSR to keep node chain */ + if (se->type == CURSEG_WARM_NODE) { + if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) + se->ckpt_valid_blocks++; + } } else { if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) { #ifdef CONFIG_F2FS_CHECK_FS diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 338d2f73eb29..a2c05f2ada6d 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1359,6 +1359,16 @@ out: return 0; } +static void fat_dummy_inode_init(struct inode *inode) +{ + /* Initialize this dummy inode to work as no-op. */ + MSDOS_I(inode)->mmu_private = 0; + MSDOS_I(inode)->i_start = 0; + MSDOS_I(inode)->i_logstart = 0; + MSDOS_I(inode)->i_attrs = 0; + MSDOS_I(inode)->i_pos = 0; +} + static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); @@ -1803,12 +1813,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; - MSDOS_I(fat_inode)->i_pos = 0; + fat_dummy_inode_init(fat_inode); sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; + fat_dummy_inode_init(fsinfo_inode); fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); diff --git a/fs/fcntl.c b/fs/fcntl.c index be8fbe289087..8bd81c2e89b2 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -23,6 +23,7 @@ #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/shmem_fs.h> +#include <linux/compat.h> #include <asm/poll.h> #include <asm/siginfo.h> @@ -420,6 +421,162 @@ out: } #endif +#ifdef CONFIG_COMPAT +static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) +{ + if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || + __get_user(kfl->l_type, &ufl->l_type) || + __get_user(kfl->l_whence, &ufl->l_whence) || + __get_user(kfl->l_start, &ufl->l_start) || + __get_user(kfl->l_len, &ufl->l_len) || + __get_user(kfl->l_pid, &ufl->l_pid)) + return -EFAULT; + return 0; +} + +static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) +{ + if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) || + __put_user(kfl->l_type, &ufl->l_type) || + __put_user(kfl->l_whence, &ufl->l_whence) || + __put_user(kfl->l_start, &ufl->l_start) || + __put_user(kfl->l_len, &ufl->l_len) || + __put_user(kfl->l_pid, &ufl->l_pid)) + return -EFAULT; + return 0; +} + +#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64 +static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl) +{ + if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || + __get_user(kfl->l_type, &ufl->l_type) || + __get_user(kfl->l_whence, &ufl->l_whence) || + __get_user(kfl->l_start, &ufl->l_start) || + __get_user(kfl->l_len, &ufl->l_len) || + __get_user(kfl->l_pid, &ufl->l_pid)) + return -EFAULT; + return 0; +} +#endif + +#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64 +static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl) +{ + if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) || + __put_user(kfl->l_type, &ufl->l_type) || + __put_user(kfl->l_whence, &ufl->l_whence) || + __put_user(kfl->l_start, &ufl->l_start) || + __put_user(kfl->l_len, &ufl->l_len) || + __put_user(kfl->l_pid, &ufl->l_pid)) + return -EFAULT; + return 0; +} +#endif + +static unsigned int +convert_fcntl_cmd(unsigned int cmd) +{ + switch (cmd) { + case F_GETLK64: + return F_GETLK; + case F_SETLK64: + return F_SETLK; + case F_SETLKW64: + return F_SETLKW; + } + + return cmd; +} + +COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, + compat_ulong_t, arg) +{ + mm_segment_t old_fs; + struct flock f; + long ret; + unsigned int conv_cmd; + + switch (cmd) { + case F_GETLK: + case F_SETLK: + case F_SETLKW: + ret = get_compat_flock(&f, compat_ptr(arg)); + if (ret != 0) + break; + old_fs = get_fs(); + set_fs(KERNEL_DS); + ret = sys_fcntl(fd, cmd, (unsigned long)&f); + set_fs(old_fs); + if (cmd == F_GETLK && ret == 0) { + /* GETLK was successful and we need to return the data... + * but it needs to fit in the compat structure. + * l_start shouldn't be too big, unless the original + * start + end is greater than COMPAT_OFF_T_MAX, in which + * case the app was asking for trouble, so we return + * -EOVERFLOW in that case. + * l_len could be too big, in which case we just truncate it, + * and only allow the app to see that part of the conflicting + * lock that might make sense to it anyway + */ + + if (f.l_start > COMPAT_OFF_T_MAX) + ret = -EOVERFLOW; + if (f.l_len > COMPAT_OFF_T_MAX) + f.l_len = COMPAT_OFF_T_MAX; + if (ret == 0) + ret = put_compat_flock(&f, compat_ptr(arg)); + } + break; + + case F_GETLK64: + case F_SETLK64: + case F_SETLKW64: + case F_OFD_GETLK: + case F_OFD_SETLK: + case F_OFD_SETLKW: + ret = get_compat_flock64(&f, compat_ptr(arg)); + if (ret != 0) + break; + old_fs = get_fs(); + set_fs(KERNEL_DS); + conv_cmd = convert_fcntl_cmd(cmd); + ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f); + set_fs(old_fs); + if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) { + /* need to return lock information - see above for commentary */ + if (f.l_start > COMPAT_LOFF_T_MAX) + ret = -EOVERFLOW; + if (f.l_len > COMPAT_LOFF_T_MAX) + f.l_len = COMPAT_LOFF_T_MAX; + if (ret == 0) + ret = put_compat_flock64(&f, compat_ptr(arg)); + } + break; + + default: + ret = sys_fcntl(fd, cmd, arg); + break; + } + return ret; +} + +COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, + compat_ulong_t, arg) +{ + switch (cmd) { + case F_GETLK64: + case F_SETLK64: + case F_SETLKW64: + case F_OFD_GETLK: + case F_OFD_SETLK: + case F_OFD_SETLKW: + return -EINVAL; + } + return compat_sys_fcntl64(fd, cmd, arg); +} +#endif + /* Table to convert sigio signal codes into poll band bitmaps */ static const long band_table[NSIGPOLL] = { diff --git a/fs/fhandle.c b/fs/fhandle.c index 5559168d5637..58a61f55e0d0 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -9,6 +9,7 @@ #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/uaccess.h> +#include <linux/compat.h> #include "internal.h" #include "mount.h" @@ -264,3 +265,15 @@ SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd, ret = do_handle_open(mountdirfd, handle, flags); return ret; } + +#ifdef CONFIG_COMPAT +/* + * Exactly like fs/open.c:sys_open_by_handle_at(), except that it + * doesn't set the O_LARGEFILE flag. + */ +COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd, + struct file_handle __user *, handle, int, flags) +{ + return do_handle_open(mountdirfd, handle, flags); +} +#endif diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index ef600591d96f..63ee2940775c 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -173,19 +173,33 @@ static void wb_wakeup(struct bdi_writeback *wb) spin_unlock_bh(&wb->work_lock); } +static void finish_writeback_work(struct bdi_writeback *wb, + struct wb_writeback_work *work) +{ + struct wb_completion *done = work->done; + + if (work->auto_free) + kfree(work); + if (done && atomic_dec_and_test(&done->cnt)) + wake_up_all(&wb->bdi->wb_waitq); +} + static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); - spin_lock_bh(&wb->work_lock); - if (!test_bit(WB_registered, &wb->state)) - goto out_unlock; if (work->done) atomic_inc(&work->done->cnt); - list_add_tail(&work->list, &wb->work_list); - mod_delayed_work(bdi_wq, &wb->dwork, 0); -out_unlock: + + spin_lock_bh(&wb->work_lock); + + if (test_bit(WB_registered, &wb->state)) { + list_add_tail(&work->list, &wb->work_list); + mod_delayed_work(bdi_wq, &wb->dwork, 0); + } else + finish_writeback_work(wb, work); + spin_unlock_bh(&wb->work_lock); } @@ -1873,16 +1887,9 @@ static long wb_do_writeback(struct bdi_writeback *wb) set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { - struct wb_completion *done = work->done; - trace_writeback_exec(wb, work); - wrote += wb_writeback(wb, work); - - if (work->auto_free) - kfree(work); - if (done && atomic_dec_and_test(&done->cnt)) - wake_up_all(&wb->bdi->wb_waitq); + finish_writeback_work(wb, work); } /* diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index b681b43c766e..c2d7f3a92679 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -382,9 +382,9 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) wake_up(&fc->blocked_waitq); if (fc->num_background == fc->congestion_threshold && - fc->connected && fc->bdi_initialized) { - clear_bdi_congested(&fc->bdi, BLK_RW_SYNC); - clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC); + fc->connected && fc->sb) { + clear_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC); + clear_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC); } fc->num_background--; fc->active_background--; @@ -573,10 +573,9 @@ void fuse_request_send_background_locked(struct fuse_conn *fc, fc->num_background++; if (fc->num_background == fc->max_background) fc->blocked = 1; - if (fc->num_background == fc->congestion_threshold && - fc->bdi_initialized) { - set_bdi_congested(&fc->bdi, BLK_RW_SYNC); - set_bdi_congested(&fc->bdi, BLK_RW_ASYNC); + if (fc->num_background == fc->congestion_threshold && fc->sb) { + set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC); + set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC); } list_add_tail(&req->list, &fc->bg_queue); flush_bg_queue(fc); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 32ac2c9b09c0..f33341d9501a 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -527,9 +527,6 @@ struct fuse_conn { /** Filesystem supports NFS exporting. Only set in INIT */ unsigned export_support:1; - /** Set if bdi is valid */ - unsigned bdi_initialized:1; - /** write-back cache policy (default is write-through) */ unsigned writeback_cache:1; @@ -631,9 +628,6 @@ struct fuse_conn { /** Negotiated minor version */ unsigned minor; - /** Backing dev info */ - struct backing_dev_info bdi; - /** Entry on the fuse_conn_list */ struct list_head entry; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 6fe6a88ecb4a..73cf05135252 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -386,12 +386,6 @@ static void fuse_send_destroy(struct fuse_conn *fc) } } -static void fuse_bdi_destroy(struct fuse_conn *fc) -{ - if (fc->bdi_initialized) - bdi_destroy(&fc->bdi); -} - static void fuse_put_super(struct super_block *sb) { struct fuse_conn *fc = get_fuse_conn_super(sb); @@ -403,7 +397,6 @@ static void fuse_put_super(struct super_block *sb) list_del(&fc->entry); fuse_ctl_remove_conn(fc); mutex_unlock(&fuse_mutex); - fuse_bdi_destroy(fc); fuse_conn_put(fc); } @@ -928,7 +921,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->no_flock = 1; } - fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages); + fc->sb->s_bdi->ra_pages = + min(fc->sb->s_bdi->ra_pages, ra_pages); fc->minor = arg->minor; fc->max_write = arg->minor < 5 ? 4096 : arg->max_write; fc->max_write = max_t(unsigned, 4096, fc->max_write); @@ -944,7 +938,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->major = FUSE_KERNEL_VERSION; arg->minor = FUSE_KERNEL_MINOR_VERSION; - arg->max_readahead = fc->bdi.ra_pages * PAGE_SIZE; + arg->max_readahead = fc->sb->s_bdi->ra_pages * PAGE_SIZE; arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | @@ -976,27 +970,18 @@ static void fuse_free_conn(struct fuse_conn *fc) static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) { int err; + char *suffix = ""; - fc->bdi.name = "fuse"; - fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE; - /* fuse does it's own writeback accounting */ - fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT; - - err = bdi_init(&fc->bdi); + if (sb->s_bdev) + suffix = "-fuseblk"; + err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev), + MINOR(fc->dev), suffix); if (err) return err; - fc->bdi_initialized = 1; - - if (sb->s_bdev) { - err = bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk", - MAJOR(fc->dev), MINOR(fc->dev)); - } else { - err = bdi_register_dev(&fc->bdi, fc->dev); - } - - if (err) - return err; + sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE; + /* fuse does it's own writeback accounting */ + sb->s_bdi->capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT; /* * For a single fuse filesystem use max 1% of dirty + @@ -1010,7 +995,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) * * /sys/class/bdi/<bdi>/max_ratio */ - bdi_set_max_ratio(&fc->bdi, 1); + bdi_set_max_ratio(sb->s_bdi, 1); return 0; } @@ -1113,8 +1098,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (err) goto err_dev_free; - sb->s_bdi = &fc->bdi; - /* Handle umasking inside the fuse code */ if (sb->s_flags & MS_POSIXACL) fc->dont_mask = 1; @@ -1182,7 +1165,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) err_dev_free: fuse_dev_free(fud); err_put_conn: - fuse_bdi_destroy(fc); fuse_conn_put(fc); err_fput: fput(file); diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index c45084ac642d..511e1ed7e2de 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -207,7 +207,7 @@ struct lm_lockname { struct gfs2_sbd *ln_sbd; u64 ln_number; unsigned int ln_type; -}; +} __packed __aligned(sizeof(int)); #define lm_name_equal(name1, name2) \ (((name1)->ln_number == (name2)->ln_number) && \ diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index b108e7ba81af..ed67548b286c 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -23,6 +23,7 @@ #include <linux/quotaops.h> #include <linux/lockdep.h> #include <linux/module.h> +#include <linux/backing-dev.h> #include "gfs2.h" #include "incore.h" @@ -1222,12 +1223,7 @@ static int set_gfs2_super(struct super_block *s, void *data) { s->s_bdev = data; s->s_dev = s->s_bdev->bd_dev; - - /* - * We set the bdi here to the queue backing, file systems can - * overwrite this in ->fill_super() - */ - s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info; + s->s_bdi = bdi_get(s->s_bdev->bd_bdi); return 0; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8f96461236f6..dde861387a40 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -136,17 +136,26 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops; + /* + * Offset passed to mmap (before page shift) could have been + * negative when represented as a (l)off_t. + */ + if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0) + return -EINVAL; + if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; vma_len = (loff_t)(vma->vm_end - vma->vm_start); + len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + /* check for overflow */ + if (len < vma_len) + return -EINVAL; inode_lock(inode); file_accessed(file); ret = -ENOMEM; - len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); - if (hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, @@ -155,7 +164,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) ret = 0; if (vma->vm_flags & VM_WRITE && inode->i_size < len) - inode->i_size = len; + i_size_write(inode, len); out: inode_unlock(inode); @@ -695,14 +704,11 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, inode = new_inode(sb); if (inode) { - struct hugetlbfs_inode_info *info; inode->i_ino = get_next_ino(); inode->i_mode = S_IFDIR | config->mode; inode->i_uid = config->uid; inode->i_gid = config->gid; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); - info = HUGETLBFS_I(inode); - mpol_shared_policy_init(&info->policy, NULL); inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ @@ -733,7 +739,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, inode = new_inode(sb); if (inode) { - struct hugetlbfs_inode_info *info; inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, @@ -741,15 +746,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, inode->i_mapping->a_ops = &hugetlbfs_aops; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_mapping->private_data = resv_map; - info = HUGETLBFS_I(inode); - /* - * The policy is initialized here even if we are creating a - * private inode because initialization simply creates an - * an empty rb tree and calls rwlock_init(), later when we - * call mpol_free_shared_policy() it will just return because - * the rb tree will still be empty. - */ - mpol_shared_policy_init(&info->policy, NULL); switch (mode & S_IFMT) { default: init_special_inode(inode, mode, dev); @@ -937,6 +933,18 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) hugetlbfs_inc_free_inodes(sbinfo); return NULL; } + + /* + * Any time after allocation, hugetlbfs_destroy_inode can be called + * for the inode. mpol_free_shared_policy is unconditionally called + * as part of hugetlbfs_destroy_inode. So, initialize policy here + * in case of a quick call to destroy. + * + * Note that the policy is initialized even if we are creating a + * private inode. This simplifies hugetlbfs_destroy_inode. + */ + mpol_shared_policy_init(&p->policy, NULL); + return &p->vfs_inode; } diff --git a/fs/internal.h b/fs/internal.h index 11c6d89dce9c..076751d90ba2 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -108,8 +108,6 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname, extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, const char *, const struct open_flags *); -extern long do_handle_open(int mountdirfd, - struct file_handle __user *ufh, int open_flag); extern int open_check_o_direct(struct file *f); extern int vfs_open(const struct path *, struct file *, const struct cred *); extern struct file *filp_clone_open(struct file *); diff --git a/fs/iomap.c b/fs/iomap.c index 3ca1a8e44135..141c3cd55a8b 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -846,7 +846,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); size_t count = iov_iter_count(iter); - loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0; + loff_t pos = iocb->ki_pos, start = pos; + loff_t end = iocb->ki_pos + count - 1, ret = 0; unsigned int flags = IOMAP_DIRECT; struct blk_plug plug; struct iomap_dio *dio; @@ -887,12 +888,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, } if (mapping->nrpages) { - ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); + ret = filemap_write_and_wait_range(mapping, start, end); if (ret) goto out_free_dio; ret = invalidate_inode_pages2_range(mapping, - iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); + start >> PAGE_SHIFT, end >> PAGE_SHIFT); WARN_ON_ONCE(ret); ret = 0; } @@ -941,6 +942,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, __set_current_state(TASK_RUNNING); } + ret = iomap_dio_complete(dio); + /* * Try again to invalidate clean pages which might have been cached by * non-direct readahead, or faulted in by get_user_pages() if the source @@ -949,12 +952,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, * this invalidation fails, tough, the write still worked... */ if (iov_iter_rw(iter) == WRITE && mapping->nrpages) { - ret = invalidate_inode_pages2_range(mapping, - iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(ret); + int err = invalidate_inode_pages2_range(mapping, + start >> PAGE_SHIFT, end >> PAGE_SHIFT); + WARN_ON_ONCE(err); } - return iomap_dio_complete(dio); + return ret; out_free_dio: kfree(dio); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index a1a359bfcc9c..5adc2fb62b0f 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1125,10 +1125,8 @@ static journal_t *journal_init_common(struct block_device *bdev, /* Set up a default-sized revoke table for the new mount. */ err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH); - if (err) { - kfree(journal); - return NULL; - } + if (err) + goto err_cleanup; spin_lock_init(&journal->j_history_lock); @@ -1145,23 +1143,25 @@ static journal_t *journal_init_common(struct block_device *bdev, journal->j_wbufsize = n; journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *), GFP_KERNEL); - if (!journal->j_wbuf) { - kfree(journal); - return NULL; - } + if (!journal->j_wbuf) + goto err_cleanup; bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); if (!bh) { pr_err("%s: Cannot get buffer for journal superblock\n", __func__); - kfree(journal->j_wbuf); - kfree(journal); - return NULL; + goto err_cleanup; } journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; return journal; + +err_cleanup: + kfree(journal->j_wbuf); + jbd2_journal_destroy_revoke(journal); + kfree(journal); + return NULL; } /* jbd2_journal_init_dev and jbd2_journal_init_inode: diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index cfc38b552118..f9aefcda5854 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -280,6 +280,7 @@ int jbd2_journal_init_revoke(journal_t *journal, int hash_size) fail1: jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]); + journal->j_revoke_table[0] = NULL; fail0: return -ENOMEM; } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 8e4dc7ab584c..ac2dfe0c5a9c 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -809,7 +809,8 @@ void kernfs_drain_open_files(struct kernfs_node *kn) if (kn->flags & KERNFS_HAS_MMAP) unmap_mapping_range(inode->i_mapping, 0, 0, 1); - kernfs_release_file(kn, of); + if (kn->flags & KERNFS_HAS_RELEASE) + kernfs_release_file(kn, of); } mutex_unlock(&kernfs_open_file_mutex); diff --git a/fs/namei.c b/fs/namei.c index d41fab78798b..19dcf62133cc 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2145,6 +2145,9 @@ static const char *path_init(struct nameidata *nd, unsigned flags) int retval = 0; const char *s = nd->name->name; + if (!*s) + flags &= ~LOOKUP_RCU; + nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT; nd->depth = 0; diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index d5606099712a..6d0f14c86099 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -554,12 +554,11 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent) sb->s_magic = NCP_SUPER_MAGIC; sb->s_op = &ncp_sops; sb->s_d_op = &ncp_dentry_operations; - sb->s_bdi = &server->bdi; server = NCP_SBP(sb); memset(server, 0, sizeof(*server)); - error = bdi_setup_and_register(&server->bdi, "ncpfs"); + error = super_setup_bdi(sb); if (error) goto out_fput; @@ -568,7 +567,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent) if (data.info_fd != -1) { struct socket *info_sock = sockfd_lookup(data.info_fd, &error); if (!info_sock) - goto out_bdi; + goto out_fput; server->info_sock = info_sock; error = -EBADFD; if (info_sock->type != SOCK_STREAM) @@ -746,8 +745,6 @@ out_nls: out_fput2: if (server->info_sock) sockfd_put(server->info_sock); -out_bdi: - bdi_destroy(&server->bdi); out_fput: sockfd_put(sock); out: @@ -788,7 +785,6 @@ static void ncp_put_super(struct super_block *sb) kill_pid(server->m.wdog_pid, SIGTERM, 1); put_pid(server->m.wdog_pid); - bdi_destroy(&server->bdi); kfree(server->priv.data); kfree(server->auth.object_name); vfree(server->rxbuf); diff --git a/fs/ncpfs/ncp_fs_sb.h b/fs/ncpfs/ncp_fs_sb.h index 55e26fd80886..366fd63cc506 100644 --- a/fs/ncpfs/ncp_fs_sb.h +++ b/fs/ncpfs/ncp_fs_sb.h @@ -143,7 +143,6 @@ struct ncp_server { size_t len; __u8 data[128]; } unexpected_packet; - struct backing_dev_info bdi; }; extern void ncp_tcp_rcv_proc(struct work_struct *work); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index bb79972dc638..773774531aff 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -232,12 +232,12 @@ static struct svc_serv_ops nfs41_cb_sv_ops = { .svo_module = THIS_MODULE, }; -struct svc_serv_ops *nfs4_cb_sv_ops[] = { +static struct svc_serv_ops *nfs4_cb_sv_ops[] = { [0] = &nfs40_cb_sv_ops, [1] = &nfs41_cb_sv_ops, }; #else -struct svc_serv_ops *nfs4_cb_sv_ops[] = { +static struct svc_serv_ops *nfs4_cb_sv_ops[] = { [0] = &nfs40_cb_sv_ops, [1] = NULL, }; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 91a8d610ba0f..04d15a0045e3 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -325,10 +325,33 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat return NULL; } -static bool nfs_client_init_is_complete(const struct nfs_client *clp) +/* + * Return true if @clp is done initializing, false if still working on it. + * + * Use nfs_client_init_status to check if it was successful. + */ +bool nfs_client_init_is_complete(const struct nfs_client *clp) { return clp->cl_cons_state <= NFS_CS_READY; } +EXPORT_SYMBOL_GPL(nfs_client_init_is_complete); + +/* + * Return 0 if @clp was successfully initialized, -errno otherwise. + * + * This must be called *after* nfs_client_init_is_complete() returns true, + * otherwise it will pop WARN_ON_ONCE and return -EINVAL + */ +int nfs_client_init_status(const struct nfs_client *clp) +{ + /* called without checking nfs_client_init_is_complete */ + if (clp->cl_cons_state > NFS_CS_READY) { + WARN_ON_ONCE(1); + return -EINVAL; + } + return clp->cl_cons_state; +} +EXPORT_SYMBOL_GPL(nfs_client_init_status); int nfs_wait_client_init_complete(const struct nfs_client *clp) { @@ -738,9 +761,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->rsize = NFS_MAX_FILE_IO_SIZE; server->rpages = (server->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT; - server->backing_dev_info.name = "nfs"; - server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD; - if (server->wsize > max_rpc_payload) server->wsize = max_rpc_payload; if (server->wsize > NFS_MAX_FILE_IO_SIZE) @@ -894,12 +914,6 @@ struct nfs_server *nfs_alloc_server(void) return NULL; } - if (bdi_init(&server->backing_dev_info)) { - nfs_free_iostats(server->io_stats); - kfree(server); - return NULL; - } - ida_init(&server->openowner_id); ida_init(&server->lockowner_id); pnfs_init_server(server); @@ -930,7 +944,6 @@ void nfs_free_server(struct nfs_server *server) ida_destroy(&server->lockowner_id); ida_destroy(&server->openowner_id); nfs_free_iostats(server->io_stats); - bdi_destroy(&server->backing_dev_info); kfree(server); nfs_release_automount_timer(); dprintk("<-- nfs_free_server()\n"); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index fb499a3f21b5..f92ba8d6c556 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2055,7 +2055,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); - struct dentry *dentry = NULL, *rehash = NULL; + struct dentry *dentry = NULL; struct rpc_task *task; int error = -EBUSY; @@ -2078,10 +2078,8 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, * To prevent any new references to the target during the * rename, we unhash the dentry in advance. */ - if (!d_unhashed(new_dentry)) { + if (!d_unhashed(new_dentry)) d_drop(new_dentry); - rehash = new_dentry; - } if (d_count(new_dentry) > 2) { int err; @@ -2098,7 +2096,6 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; new_dentry = dentry; - rehash = NULL; new_inode = NULL; } } @@ -2119,8 +2116,6 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, error = task->tk_status; rpc_put_task(task); out: - if (rehash) - d_rehash(rehash); trace_nfs_rename_exit(old_dir, old_dentry, new_dir, new_dentry, error); /* new dentry created? */ diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index aab32fc3d6a8..c1b5fed7c863 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -537,7 +537,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, if (put_dreq(dreq)) nfs_direct_complete(dreq); - return 0; + return requested_bytes; } /** @@ -566,7 +566,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = mapping->host; struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; - ssize_t result = -EINVAL; + ssize_t result = -EINVAL, requested; size_t count = iov_iter_count(iter); nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); @@ -600,14 +600,19 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) nfs_start_io_direct(inode); NFS_I(inode)->read_io += count; - result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); + requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); nfs_end_io_direct(inode); - if (!result) { + if (requested > 0) { result = nfs_direct_wait(dreq); - if (result > 0) + if (result > 0) { + requested -= result; iocb->ki_pos += result; + } + iov_iter_revert(iter, requested); + } else { + result = requested; } out_release: @@ -954,7 +959,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, if (put_dreq(dreq)) nfs_direct_write_complete(dreq); - return 0; + return requested_bytes; } /** @@ -979,7 +984,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, */ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) { - ssize_t result = -EINVAL; + ssize_t result = -EINVAL, requested; size_t count; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -1022,7 +1027,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) nfs_start_io_direct(inode); - result = nfs_direct_write_schedule_iovec(dreq, iter, pos); + requested = nfs_direct_write_schedule_iovec(dreq, iter, pos); if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, @@ -1031,13 +1036,17 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) nfs_end_io_direct(inode); - if (!result) { + if (requested > 0) { result = nfs_direct_wait(dreq); if (result > 0) { + requested -= result; iocb->ki_pos = pos + result; /* XXX: should check the generic_write_sync retval */ generic_write_sync(iocb, result); } + iov_iter_revert(iter, requested); + } else { + result = requested; } out_release: nfs_direct_req_release(dreq); diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 44347f4bdc15..acd30baca461 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -202,10 +202,10 @@ static int filelayout_async_handle_error(struct rpc_task *task, task->tk_status); nfs4_mark_deviceid_unavailable(devid); pnfs_error_mark_layout_for_return(inode, lseg); - pnfs_set_lo_fail(lseg); rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: + pnfs_set_lo_fail(lseg); reset: dprintk("%s Retry through MDS. Error %d\n", __func__, task->tk_status); @@ -560,6 +560,50 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) return PNFS_ATTEMPTED; } +static int +filelayout_check_deviceid(struct pnfs_layout_hdr *lo, + struct nfs4_filelayout_segment *fl, + gfp_t gfp_flags) +{ + struct nfs4_deviceid_node *d; + struct nfs4_file_layout_dsaddr *dsaddr; + int status = -EINVAL; + + /* find and reference the deviceid */ + d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &fl->deviceid, + lo->plh_lc_cred, gfp_flags); + if (d == NULL) + goto out; + + dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node); + /* Found deviceid is unavailable */ + if (filelayout_test_devid_unavailable(&dsaddr->id_node)) + goto out_put; + + fl->dsaddr = dsaddr; + + if (fl->first_stripe_index >= dsaddr->stripe_count) { + dprintk("%s Bad first_stripe_index %u\n", + __func__, fl->first_stripe_index); + goto out_put; + } + + if ((fl->stripe_type == STRIPE_SPARSE && + fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) || + (fl->stripe_type == STRIPE_DENSE && + fl->num_fh != dsaddr->stripe_count)) { + dprintk("%s num_fh %u not valid for given packing\n", + __func__, fl->num_fh); + goto out_put; + } + status = 0; +out: + return status; +out_put: + nfs4_fl_put_deviceid(dsaddr); + goto out; +} + /* * filelayout_check_layout() * @@ -572,11 +616,8 @@ static int filelayout_check_layout(struct pnfs_layout_hdr *lo, struct nfs4_filelayout_segment *fl, struct nfs4_layoutget_res *lgr, - struct nfs4_deviceid *id, gfp_t gfp_flags) { - struct nfs4_deviceid_node *d; - struct nfs4_file_layout_dsaddr *dsaddr; int status = -EINVAL; dprintk("--> %s\n", __func__); @@ -601,41 +642,10 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo, goto out; } - /* find and reference the deviceid */ - d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), id, - lo->plh_lc_cred, gfp_flags); - if (d == NULL) - goto out; - - dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node); - /* Found deviceid is unavailable */ - if (filelayout_test_devid_unavailable(&dsaddr->id_node)) - goto out_put; - - fl->dsaddr = dsaddr; - - if (fl->first_stripe_index >= dsaddr->stripe_count) { - dprintk("%s Bad first_stripe_index %u\n", - __func__, fl->first_stripe_index); - goto out_put; - } - - if ((fl->stripe_type == STRIPE_SPARSE && - fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) || - (fl->stripe_type == STRIPE_DENSE && - fl->num_fh != dsaddr->stripe_count)) { - dprintk("%s num_fh %u not valid for given packing\n", - __func__, fl->num_fh); - goto out_put; - } - status = 0; out: dprintk("--> %s returns %d\n", __func__, status); return status; -out_put: - nfs4_fl_put_deviceid(dsaddr); - goto out; } static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl) @@ -657,7 +667,6 @@ static int filelayout_decode_layout(struct pnfs_layout_hdr *flo, struct nfs4_filelayout_segment *fl, struct nfs4_layoutget_res *lgr, - struct nfs4_deviceid *id, gfp_t gfp_flags) { struct xdr_stream stream; @@ -682,9 +691,9 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, if (unlikely(!p)) goto out_err; - memcpy(id, p, sizeof(*id)); + memcpy(&fl->deviceid, p, sizeof(fl->deviceid)); p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); - nfs4_print_deviceid(id); + nfs4_print_deviceid(&fl->deviceid); nfl_util = be32_to_cpup(p++); if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS) @@ -831,15 +840,14 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, { struct nfs4_filelayout_segment *fl; int rc; - struct nfs4_deviceid id; dprintk("--> %s\n", __func__); fl = kzalloc(sizeof(*fl), gfp_flags); if (!fl) return NULL; - rc = filelayout_decode_layout(layoutid, fl, lgr, &id, gfp_flags); - if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id, gfp_flags)) { + rc = filelayout_decode_layout(layoutid, fl, lgr, gfp_flags); + if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, gfp_flags)) { _filelayout_free_lseg(fl); return NULL; } @@ -888,18 +896,51 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, return min(stripe_unit - (unsigned int)stripe_offset, size); } +static struct pnfs_layout_segment * +fl_pnfs_update_layout(struct inode *ino, + struct nfs_open_context *ctx, + loff_t pos, + u64 count, + enum pnfs_iomode iomode, + bool strict_iomode, + gfp_t gfp_flags) +{ + struct pnfs_layout_segment *lseg = NULL; + struct pnfs_layout_hdr *lo; + struct nfs4_filelayout_segment *fl; + int status; + + lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode, + gfp_flags); + if (!lseg) + lseg = ERR_PTR(-ENOMEM); + if (IS_ERR(lseg)) + goto out; + + lo = NFS_I(ino)->layout; + fl = FILELAYOUT_LSEG(lseg); + + status = filelayout_check_deviceid(lo, fl, gfp_flags); + if (status) + lseg = ERR_PTR(status); +out: + if (IS_ERR(lseg)) + pnfs_put_lseg(lseg); + return lseg; +} + static void filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { if (!pgio->pg_lseg) { - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, - 0, - NFS4_MAX_UINT64, - IOMODE_READ, - false, - GFP_KERNEL); + pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_READ, + false, + GFP_KERNEL); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -919,13 +960,13 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, int status; if (!pgio->pg_lseg) { - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, - 0, - NFS4_MAX_UINT64, - IOMODE_RW, - false, - GFP_NOFS); + pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_RW, + false, + GFP_NOFS); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h index 2896cb833a11..79323b5dab0c 100644 --- a/fs/nfs/filelayout/filelayout.h +++ b/fs/nfs/filelayout/filelayout.h @@ -55,15 +55,16 @@ struct nfs4_file_layout_dsaddr { }; struct nfs4_filelayout_segment { - struct pnfs_layout_segment generic_hdr; - u32 stripe_type; - u32 commit_through_mds; - u32 stripe_unit; - u32 first_stripe_index; - u64 pattern_offset; - struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */ - unsigned int num_fh; - struct nfs_fh **fh_array; + struct pnfs_layout_segment generic_hdr; + u32 stripe_type; + u32 commit_through_mds; + u32 stripe_unit; + u32 first_stripe_index; + u64 pattern_offset; + struct nfs4_deviceid deviceid; + struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */ + unsigned int num_fh; + struct nfs_fh **fh_array; }; struct nfs4_filelayout { diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index f956ca20a8a3..d913e818858f 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -266,6 +266,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); struct nfs4_pnfs_ds *ret = ds; struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode); + int status; if (ds == NULL) { printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", @@ -277,9 +278,14 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) if (ds->ds_clp) goto out_test_devid; - nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, dataserver_retrans, 4, s->nfs_client->cl_minorversion); + if (status) { + nfs4_mark_deviceid_unavailable(devid); + ret = NULL; + goto out; + } out_test_devid: if (ret->ds_clp == NULL || diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index f4f39b0ab09b..98b34c9b0564 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -175,7 +175,19 @@ ff_layout_no_read_on_rw(struct pnfs_layout_segment *lseg) static inline bool ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node) { - return nfs4_test_deviceid_unavailable(node); + /* + * Flexfiles should never mark a DS unavailable, but if it does + * print a (ratelimited) warning as this can affect performance. + */ + if (nfs4_test_deviceid_unavailable(node)) { + u32 *p = (u32 *)node->deviceid.data; + + pr_warn_ratelimited("NFS: flexfiles layout referencing an " + "unavailable device [%x%x%x%x]\n", + p[0], p[1], p[2], p[3]); + return true; + } + return false; } static inline int diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e5a6f248697b..457cfeb1d5c1 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -208,6 +208,10 @@ static bool ff_layout_mirror_valid(struct pnfs_layout_segment *lseg, } else goto outerr; } + + if (IS_ERR(mirror->mirror_ds)) + goto outerr; + if (mirror->mirror_ds->ds == NULL) { struct nfs4_deviceid_node *devid; devid = &mirror->mirror_ds->id_node; @@ -384,6 +388,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, struct inode *ino = lseg->pls_layout->plh_inode; struct nfs_server *s = NFS_SERVER(ino); unsigned int max_payload; + int status; if (!ff_layout_mirror_valid(lseg, mirror, true)) { pr_err_ratelimited("NFS: %s: No data server for offset index %d\n", @@ -404,7 +409,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, /* FIXME: For now we assume the server sent only one version of NFS * to use for the DS. */ - nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, dataserver_retrans, mirror->mirror_ds->ds_versions[0].version, mirror->mirror_ds->ds_versions[0].minor_version); @@ -420,11 +425,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, mirror->mirror_ds->ds_versions[0].wsize = max_payload; goto out; } +out_fail: ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), mirror, lseg->pls_range.offset, lseg->pls_range.length, NFS4ERR_NXIO, OP_ILLEGAL, GFP_NOIO); -out_fail: if (fail_return || !ff_layout_has_available_ds(lseg)) pnfs_error_mark_layout_for_return(ino, lseg); ds = NULL; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 09ca5095c04e..9dc65d7ae754 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -139,7 +139,7 @@ struct nfs_mount_request { }; struct nfs_mount_info { - void (*fill_super)(struct super_block *, struct nfs_mount_info *); + int (*fill_super)(struct super_block *, struct nfs_mount_info *); int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *); struct nfs_parsed_mount_data *parsed; struct nfs_clone_mount *cloned; @@ -186,6 +186,8 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); +extern bool nfs_client_init_is_complete(const struct nfs_client *clp); +extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, @@ -405,7 +407,7 @@ struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void * struct dentry * nfs_xdev_mount_common(struct file_system_type *, int, const char *, struct nfs_mount_info *); void nfs_kill_super(struct super_block *); -void nfs_fill_super(struct super_block *, struct nfs_mount_info *); +int nfs_fill_super(struct super_block *, struct nfs_mount_info *); extern struct rpc_stat nfs_rpcstat; @@ -456,7 +458,7 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ -void nfs_clone_super(struct super_block *, struct nfs_mount_info *); +int nfs_clone_super(struct super_block *, struct nfs_mount_info *); void nfs_umount_begin(struct super_block *); int nfs_statfs(struct dentry *, struct kstatfs *); int nfs_show_options(struct seq_file *, struct dentry *); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 5ae9d64ea08b..8346ccbf2d52 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1023,9 +1023,9 @@ static void nfs4_session_set_rwsize(struct nfs_server *server) server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead; server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead; - if (server->rsize > server_resp_sz) + if (!server->rsize || server->rsize > server_resp_sz) server->rsize = server_resp_sz; - if (server->wsize > server_rqst_sz) + if (!server->wsize || server->wsize > server_rqst_sz) server->wsize = server_rqst_sz; #endif /* CONFIG_NFS_V4_1 */ } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1b183686c6d4..201ca3f2c4ba 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2258,8 +2258,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred, if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0) return 0; - /* even though OPEN succeeded, access is denied. Close the file */ - nfs4_close_state(state, fmode); return -EACCES; } @@ -2444,17 +2442,14 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) } nfs4_stateid_copy(&stateid, &delegation->stateid); - if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) || + !test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, + &delegation->flags)) { rcu_read_unlock(); nfs_finish_clear_delegation_stateid(state, &stateid); return; } - if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags)) { - rcu_read_unlock(); - return; - } - cred = get_rpccred(delegation->cred); rcu_read_unlock(); status = nfs41_test_and_free_expired_stateid(server, &stateid, cred); @@ -7427,11 +7422,11 @@ static void nfs4_exchange_id_release(void *data) struct nfs41_exchange_id_data *cdata = (struct nfs41_exchange_id_data *)data; - nfs_put_client(cdata->args.client); if (cdata->xprt) { xprt_put(cdata->xprt); rpc_clnt_xprt_switch_put(cdata->args.client->cl_rpcclient); } + nfs_put_client(cdata->args.client); kfree(cdata->res.impl_id); kfree(cdata->res.server_scope); kfree(cdata->res.server_owner); @@ -7538,10 +7533,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, task_setup_data.callback_data = calldata; task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) { - status = PTR_ERR(task); - goto out_impl_id; - } + if (IS_ERR(task)) + return PTR_ERR(task); if (!xprt) { status = rpc_wait_for_completion_task(task); @@ -7569,6 +7562,7 @@ out_server_owner: kfree(calldata->res.server_owner); out_calldata: kfree(calldata); + nfs_put_client(clp); goto out; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index f0369e362753..80ce289eea05 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3942,7 +3942,7 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, if (len <= 0) goto out; dprintk("%s: name=%s\n", __func__, group_name->data); - return NFS_ATTR_FATTR_OWNER_NAME; + return NFS_ATTR_FATTR_GROUP_NAME; } else { len = xdr_stream_decode_opaque_inline(xdr, (void **)&p, XDR_MAX_NETOBJ); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 63f77b49a586..590e1e35781f 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -367,7 +367,7 @@ void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags); void nfs4_pnfs_v3_ds_connect_unload(void); -void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, +int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, unsigned int retrans, u32 version, u32 minor_version); struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 9414b492439f..7250b95549ec 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -745,15 +745,17 @@ out: /* * Create an rpc connection to the nfs4_pnfs_ds data server. * Currently only supports IPv4 and IPv6 addresses. - * If connection fails, make devid unavailable. + * If connection fails, make devid unavailable and return a -errno. */ -void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, +int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, unsigned int retrans, u32 version, u32 minor_version) { - if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { - int err = 0; + int err; +again: + err = 0; + if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { if (version == 3) { err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo, retrans); @@ -766,12 +768,29 @@ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, err = -EPROTONOSUPPORT; } - if (err) - nfs4_mark_deviceid_unavailable(devid); nfs4_clear_ds_conn_bit(ds); } else { nfs4_wait_ds_connect(ds); + + /* what was waited on didn't connect AND didn't mark unavail */ + if (!ds->ds_clp && !nfs4_test_deviceid_unavailable(devid)) + goto again; } + + /* + * At this point the ds->ds_clp should be ready, but it might have + * hit an error. + */ + if (!err) { + if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) { + WARN_ON_ONCE(ds->ds_clp || + !nfs4_test_deviceid_unavailable(devid)); + return -EINVAL; + } + err = nfs_client_init_status(ds->ds_clp); + } + + return err; } EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 54e0f9f2dd94..dc69314d455e 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2315,18 +2315,17 @@ inline void nfs_initialise_sb(struct super_block *sb) sb->s_blocksize = nfs_block_bits(server->wsize, &sb->s_blocksize_bits); - sb->s_bdi = &server->backing_dev_info; - nfs_super_set_maxbytes(sb, server->maxfilesize); } /* * Finish setting up an NFS2/3 superblock */ -void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) +int nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) { struct nfs_parsed_mount_data *data = mount_info->parsed; struct nfs_server *server = NFS_SB(sb); + int ret; sb->s_blocksize_bits = 0; sb->s_blocksize = 0; @@ -2344,13 +2343,21 @@ void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) } nfs_initialise_sb(sb); + + ret = super_setup_bdi_name(sb, "%u:%u", MAJOR(server->s_dev), + MINOR(server->s_dev)); + if (ret) + return ret; + sb->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD; + return 0; + } EXPORT_SYMBOL_GPL(nfs_fill_super); /* * Finish setting up a cloned NFS2/3/4 superblock */ -void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info) +int nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info) { const struct super_block *old_sb = mount_info->cloned->sb; struct nfs_server *server = NFS_SB(sb); @@ -2370,6 +2377,10 @@ void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info) } nfs_initialise_sb(sb); + + sb->s_bdi = bdi_get(old_sb->s_bdi); + + return 0; } static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags) @@ -2522,11 +2533,6 @@ static void nfs_get_cache_cookie(struct super_block *sb, } #endif -static int nfs_bdi_register(struct nfs_server *server) -{ - return bdi_register_dev(&server->backing_dev_info, server->s_dev); -} - int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot, struct nfs_mount_info *mount_info) { @@ -2594,17 +2600,14 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, nfs_free_server(server); server = NULL; } else { - error = nfs_bdi_register(server); - if (error) { - mntroot = ERR_PTR(error); - goto error_splat_super; - } server->super = s; } if (!s->s_root) { /* initial superblock/root creation */ - mount_info->fill_super(s, mount_info); + error = mount_info->fill_super(s, mount_info); + if (error) + goto error_splat_super; nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e75b056f46f4..cc341fc7fd44 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -263,16 +263,15 @@ int nfs_congestion_kb; static void nfs_set_page_writeback(struct page *page) { - struct nfs_server *nfss = NFS_SERVER(page_file_mapping(page)->host); + struct inode *inode = page_file_mapping(page)->host; + struct nfs_server *nfss = NFS_SERVER(inode); int ret = test_set_page_writeback(page); WARN_ON_ONCE(ret != 0); if (atomic_long_inc_return(&nfss->writeback) > - NFS_CONGESTION_ON_THRESH) { - set_bdi_congested(&nfss->backing_dev_info, - BLK_RW_ASYNC); - } + NFS_CONGESTION_ON_THRESH) + set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); } static void nfs_end_page_writeback(struct nfs_page *req) @@ -285,7 +284,7 @@ static void nfs_end_page_writeback(struct nfs_page *req) end_page_writeback(req->wb_page); if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) - clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); + clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); } @@ -1784,7 +1783,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) (long long)req_offset(req)); if (status < 0) { nfs_context_set_write_error(req->wb_context, status); - nfs_inode_remove_request(req); + if (req->wb_page) + nfs_inode_remove_request(req); dprintk_cont(", error = %d\n", status); goto next; } @@ -1793,7 +1793,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) * returned by the server against all stored verfs. */ if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) { /* We have a match */ - nfs_inode_remove_request(req); + if (req->wb_page) + nfs_inode_remove_request(req); dprintk_cont(" OK\n"); goto next; } @@ -1806,7 +1807,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) } nfss = NFS_SERVER(data->inode); if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) - clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); + clear_bdi_congested(inode_to_bdi(data->inode), BLK_RW_ASYNC); nfs_init_cinfo(&cinfo, data->inode, data->dreq); nfs_commit_end(cinfo.mds); diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 92b4b41d19d2..fb5213afc854 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -242,10 +242,11 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, req->cmd[4] = bufflen & 0xff; req->cmd_len = COMMAND_SIZE(INQUIRY); - error = blk_execute_rq(rq->q, NULL, rq, 1); - if (error) { + blk_execute_rq(rq->q, NULL, rq, 1); + if (req->result) { pr_err("pNFS: INQUIRY 0x83 failed with: %x\n", - rq->errors); + req->result); + error = -EIO; goto out_put_request; } diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index dba2ff8eaa68..452334694a5d 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -358,6 +358,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, { unsigned int len, v, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); + struct kvec *head = rqstp->rq_arg.head; + struct kvec *tail = rqstp->rq_arg.tail; p = decode_fh(p, &args->fh); if (!p) @@ -367,6 +369,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, args->count = ntohl(*p++); args->stable = ntohl(*p++); len = args->len = ntohl(*p++); + if ((void *)p > head->iov_base + head->iov_len) + return 0; /* * The count must equal the amount of data passed. */ @@ -377,9 +381,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Check to make sure that we got the right number of * bytes. */ - hdr = (void*)p - rqstp->rq_arg.head[0].iov_base; - dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len - + rqstp->rq_arg.tail[0].iov_len - hdr; + hdr = (void*)p - head->iov_base; + dlen = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len - hdr; /* * Round the length of the data which was specified up to * the next multiple of XDR units and then compare that @@ -396,7 +399,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, len = args->len = max_blocksize; } rqstp->rq_vec[0].iov_base = (void*)p; - rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr; + rqstp->rq_vec[0].iov_len = head->iov_len - hdr; v = 0; while (len > rqstp->rq_vec[v].iov_len) { len -= rqstp->rq_vec[v].iov_len; @@ -471,6 +474,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, /* first copy and check from the first page */ old = (char*)p; vec = &rqstp->rq_arg.head[0]; + if ((void *)old > vec->iov_base + vec->iov_len) + return 0; avail = vec->iov_len - (old - (char*)vec->iov_base); while (len && avail && *old) { *new++ = *old++; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index cbeeda1e94a2..d86031b6ad79 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2489,7 +2489,7 @@ bool nfsd4_spo_must_allow(struct svc_rqst *rqstp) int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op) { - if (op->opnum == OP_ILLEGAL) + if (op->opnum == OP_ILLEGAL || op->status == nfserr_notsupp) return op_encode_hdr_size * sizeof(__be32); BUG_ON(OPDESC(op)->op_rsize_bop == NULL); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 73e75ac90525..8bf8f667a8cf 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -538,13 +538,21 @@ out_free: static ssize_t nfsd_print_version_support(char *buf, int remaining, const char *sep, - unsigned vers, unsigned minor) + unsigned vers, int minor) { - const char *format = (minor == 0) ? "%s%c%u" : "%s%c%u.%u"; + const char *format = minor < 0 ? "%s%c%u" : "%s%c%u.%u"; bool supported = !!nfsd_vers(vers, NFSD_TEST); - if (vers == 4 && !nfsd_minorversion(minor, NFSD_TEST)) + if (vers == 4 && minor >= 0 && + !nfsd_minorversion(minor, NFSD_TEST)) supported = false; + if (minor == 0 && supported) + /* + * special case for backward compatability. + * +4.0 is never reported, it is implied by + * +4, unless -4.0 is present. + */ + return 0; return snprintf(buf, remaining, format, sep, supported ? '+' : '-', vers, minor); } @@ -554,7 +562,6 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) char *mesg = buf; char *vers, *minorp, sign; int len, num, remaining; - unsigned minor; ssize_t tlen = 0; char *sep; struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); @@ -575,6 +582,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) if (len <= 0) return -EINVAL; do { enum vers_op cmd; + unsigned minor; sign = *vers; if (sign == '+' || sign == '-') num = simple_strtol((vers+1), &minorp, 0); @@ -585,8 +593,8 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) return -EINVAL; if (kstrtouint(minorp+1, 0, &minor) < 0) return -EINVAL; - } else - minor = 0; + } + cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET; switch(num) { case 2: @@ -594,8 +602,20 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) nfsd_vers(num, cmd); break; case 4: - if (nfsd_minorversion(minor, cmd) >= 0) - break; + if (*minorp == '.') { + if (nfsd_minorversion(minor, cmd) < 0) + return -EINVAL; + } else if ((cmd == NFSD_SET) != nfsd_vers(num, NFSD_TEST)) { + /* + * Either we have +4 and no minors are enabled, + * or we have -4 and at least one minor is enabled. + * In either case, propagate 'cmd' to all minors. + */ + minor = 0; + while (nfsd_minorversion(minor, cmd) >= 0) + minor++; + } + break; default: return -EINVAL; } @@ -612,9 +632,11 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) sep = ""; remaining = SIMPLE_TRANSACTION_LIMIT; for (num=2 ; num <= 4 ; num++) { + int minor; if (!nfsd_vers(num, NFSD_AVAIL)) continue; - minor = 0; + + minor = -1; do { len = nfsd_print_version_support(buf, remaining, sep, num, minor); @@ -624,7 +646,8 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) buf += len; tlen += len; minor++; - sep = " "; + if (len) + sep = " "; } while (num == 4 && minor <= NFSD_SUPPORTED_MINOR_VERSION); } out: diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index fa82b7707e85..03a7e9da4da0 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -786,6 +786,7 @@ nfserrno (int errno) { nfserr_serverfault, -ESERVERFAULT }, { nfserr_serverfault, -ENFILE }, { nfserr_io, -EUCLEAN }, + { nfserr_perm, -ENOKEY }, }; int i; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 786a4a2cb2d7..59979f0bbd4b 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -167,7 +167,8 @@ nfsd_adjust_nfsd_versions4(void) int nfsd_minorversion(u32 minorversion, enum vers_op change) { - if (minorversion > NFSD_SUPPORTED_MINOR_VERSION) + if (minorversion > NFSD_SUPPORTED_MINOR_VERSION && + change != NFSD_AVAIL) return -1; switch(change) { case NFSD_SET: @@ -415,23 +416,20 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) void nfsd_reset_versions(void) { - int found_one = 0; int i; - for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) { - if (nfsd_program.pg_vers[i]) - found_one = 1; - } + for (i = 0; i < NFSD_NRVERS; i++) + if (nfsd_vers(i, NFSD_TEST)) + return; - if (!found_one) { - for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) - nfsd_program.pg_vers[i] = nfsd_version[i]; -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) - nfsd_acl_program.pg_vers[i] = - nfsd_acl_version[i]; -#endif - } + for (i = 0; i < NFSD_NRVERS; i++) + if (i != 4) + nfsd_vers(i, NFSD_SET); + else { + int minor = 0; + while (nfsd_minorversion(minor, NFSD_SET) >= 0) + minor++; + } } /* @@ -749,6 +747,37 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr) return nfserr; } +/* + * A write procedure can have a large argument, and a read procedure can + * have a large reply, but no NFSv2 or NFSv3 procedure has argument and + * reply that can both be larger than a page. The xdr code has taken + * advantage of this assumption to be a sloppy about bounds checking in + * some cases. Pending a rewrite of the NFSv2/v3 xdr code to fix that + * problem, we enforce these assumptions here: + */ +static bool nfs_request_too_big(struct svc_rqst *rqstp, + struct svc_procedure *proc) +{ + /* + * The ACL code has more careful bounds-checking and is not + * susceptible to this problem: + */ + if (rqstp->rq_prog != NFS_PROGRAM) + return false; + /* + * Ditto NFSv4 (which can in theory have argument and reply both + * more than a page): + */ + if (rqstp->rq_vers >= 4) + return false; + /* The reply will be small, we're OK: */ + if (proc->pc_xdrressize > 0 && + proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE)) + return false; + + return rqstp->rq_arg.len > PAGE_SIZE; +} + int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { @@ -761,6 +790,11 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_vers, rqstp->rq_proc); proc = rqstp->rq_procinfo; + if (nfs_request_too_big(rqstp, proc)) { + dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers); + *statp = rpc_garbage_args; + return 1; + } /* * Give the xdr decoder a chance to change this if it wants * (necessary in the NFSv4.0 compound case) diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 41b468a6a90f..de07ff625777 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -280,6 +280,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_writeargs *args) { unsigned int len, hdr, dlen; + struct kvec *head = rqstp->rq_arg.head; int v; p = decode_fh(p, &args->fh); @@ -300,9 +301,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Check to make sure that we got the right number of * bytes. */ - hdr = (void*)p - rqstp->rq_arg.head[0].iov_base; - dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len - - hdr; + hdr = (void*)p - head->iov_base; + if (hdr > head->iov_len) + return 0; + dlen = head->iov_len + rqstp->rq_arg.page_len - hdr; /* * Round the length of the data which was specified up to @@ -316,7 +318,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, return 0; rqstp->rq_vec[0].iov_base = (void*)p; - rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr; + rqstp->rq_vec[0].iov_len = head->iov_len - hdr; v = 0; while (len > rqstp->rq_vec[v].iov_len) { len -= rqstp->rq_vec[v].iov_len; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 19d50f600e8d..9aaf6ca77569 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1004,7 +1004,7 @@ out_nfserr: else err = nfserrno(host_err); if (test_bit(RQ_LOCAL, &rqstp->rq_flags)) - tsk_restore_flags(current, pflags, PF_LESS_THROTTLE); + current_restore_flags(pflags, PF_LESS_THROTTLE); return err; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index e1872f36147f..926682981d61 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1068,7 +1068,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_time_gran = 1; sb->s_max_links = NILFS_LINK_MAX; - sb->s_bdi = bdev_get_queue(sb->s_bdev)->backing_dev_info; + sb->s_bdi = bdi_get(sb->s_bdev->bd_bdi); err = load_nilfs(nilfs, sb); if (err) diff --git a/fs/nsfs.c b/fs/nsfs.c index 1656843e87d2..323f492e0822 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -91,6 +91,7 @@ slow: return ERR_PTR(-ENOMEM); } d_instantiate(dentry, inode); + dentry->d_flags |= DCACHE_RCUACCESS; dentry->d_fsdata = (void *)ns->ops; d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry); if (d) { diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 4348027384f5..5b51c31c892d 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1460,27 +1460,10 @@ static void o2net_rx_until_empty(struct work_struct *work) static int o2net_set_nodelay(struct socket *sock) { - int ret, val = 1; - mm_segment_t oldfs; + int val = 1; - oldfs = get_fs(); - set_fs(KERNEL_DS); - - /* - * Dear unsuspecting programmer, - * - * Don't use sock_setsockopt() for SOL_TCP. It doesn't check its level - * argument and assumes SOL_SOCKET so, say, your TCP_NODELAY will - * silently turn into SO_DEBUG. - * - * Yours, - * Keeper of hilariously fragile interfaces. - */ - ret = sock->ops->setsockopt(sock, SOL_TCP, TCP_NODELAY, - (char __user *)&val, sizeof(val)); - - set_fs(oldfs); - return ret; + return kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, + (void *)&val, sizeof(val)); } static int o2net_set_usertimeout(struct socket *sock) @@ -1488,7 +1471,7 @@ static int o2net_set_usertimeout(struct socket *sock) int user_timeout = O2NET_TCP_USER_TIMEOUT; return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT, - (char *)&user_timeout, sizeof(user_timeout)); + (void *)&user_timeout, sizeof(user_timeout)); } static void o2net_initialize_handshake(void) @@ -1863,7 +1846,7 @@ static int o2net_accept_one(struct socket *sock, int *more) new_sock->type = sock->type; new_sock->ops = sock->ops; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false); if (ret < 0) goto out; diff --git a/fs/open.c b/fs/open.c index 949cef29c3bb..4d23f729dcc6 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1078,6 +1078,26 @@ SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, return do_sys_open(dfd, filename, flags, mode); } +#ifdef CONFIG_COMPAT +/* + * Exactly like sys_open(), except that it doesn't set the + * O_LARGEFILE flag. + */ +COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) +{ + return do_sys_open(AT_FDCWD, filename, flags, mode); +} + +/* + * Exactly like sys_openat(), except that it doesn't set the + * O_LARGEFILE flag. + */ +COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) +{ + return do_sys_open(dfd, filename, flags, mode); +} +#endif + #ifndef __alpha__ /* diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index c4ab6fdf17a0..e1534c9bab16 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -208,14 +208,19 @@ restart: continue; /* * Skip ops whose filesystem we don't know about unless - * it is being mounted. + * it is being mounted or unmounted. It is possible for + * a filesystem we don't know about to be unmounted if + * it fails to mount in the kernel after userspace has + * been sent the mount request. */ /* XXX: is there a better way to detect this? */ } else if (ret == -1 && !(op->upcall.type == ORANGEFS_VFS_OP_FS_MOUNT || op->upcall.type == - ORANGEFS_VFS_OP_GETATTR)) { + ORANGEFS_VFS_OP_GETATTR || + op->upcall.type == + ORANGEFS_VFS_OP_FS_UMOUNT)) { gossip_debug(GOSSIP_DEV_DEBUG, "orangefs: skipping op tag %llu %s\n", llu(op->tag), get_opname_string(op)); diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index e6bbc8083d77..1cd37ebc4f25 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -114,7 +114,6 @@ static ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inod struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); struct orangefs_khandle *handle = &orangefs_inode->refn.khandle; struct orangefs_kernel_op_s *new_op = NULL; - struct iov_iter saved = *iter; int buffer_index = -1; ssize_t ret; @@ -193,7 +192,7 @@ populate_shared_memory: orangefs_bufmap_put(buffer_index); buffer_index = -1; if (type == ORANGEFS_IO_WRITE) - *iter = saved; + iov_iter_revert(iter, total_size); gossip_debug(GOSSIP_FILE_DEBUG, "%s:going to repopulate_shared_memory.\n", __func__); diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 6333cbbdfef7..83b506020718 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -521,13 +521,11 @@ int orangefs_bufmap_copy_from_iovec(struct iov_iter *iter, size_t n = size; if (n > PAGE_SIZE) n = PAGE_SIZE; - n = copy_page_from_iter(page, 0, n, iter); - if (!n) + if (copy_page_from_iter(page, 0, n, iter) != n) return -EFAULT; size -= n; } return 0; - } /* diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 5e48a0be9761..8afac46fcc87 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -249,6 +249,7 @@ struct orangefs_sb_info_s { char devname[ORANGEFS_MAX_SERVER_ADDR_LEN]; struct super_block *sb; int mount_pending; + int no_list; struct list_head list; }; diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 67c24351a67f..629d8c917fa6 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -263,8 +263,13 @@ int orangefs_remount(struct orangefs_sb_info_s *orangefs_sb) if (!new_op) return -ENOMEM; new_op->upcall.req.features.features = 0; - ret = service_operation(new_op, "orangefs_features", 0); - orangefs_features = new_op->downcall.resp.features.features; + ret = service_operation(new_op, "orangefs_features", + ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX); + if (!ret) + orangefs_features = + new_op->downcall.resp.features.features; + else + orangefs_features = 0; op_release(new_op); } else { orangefs_features = 0; @@ -488,7 +493,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst, if (ret) { d = ERR_PTR(ret); - goto free_op; + goto free_sb_and_op; } /* @@ -514,6 +519,9 @@ struct dentry *orangefs_mount(struct file_system_type *fst, spin_unlock(&orangefs_superblocks_lock); op_release(new_op); + /* Must be removed from the list now. */ + ORANGEFS_SB(sb)->no_list = 0; + if (orangefs_userspace_version >= 20906) { new_op = op_alloc(ORANGEFS_VFS_OP_FEATURES); if (!new_op) @@ -528,6 +536,10 @@ struct dentry *orangefs_mount(struct file_system_type *fst, return dget(sb->s_root); +free_sb_and_op: + /* Will call orangefs_kill_sb with sb not in list. */ + ORANGEFS_SB(sb)->no_list = 1; + deactivate_locked_super(sb); free_op: gossip_err("orangefs_mount: mount request failed with %d\n", ret); if (ret == -EINVAL) { @@ -553,12 +565,14 @@ void orangefs_kill_sb(struct super_block *sb) */ orangefs_unmount_sb(sb); - /* remove the sb from our list of orangefs specific sb's */ - - spin_lock(&orangefs_superblocks_lock); - __list_del_entry(&ORANGEFS_SB(sb)->list); /* not list_del_init */ - ORANGEFS_SB(sb)->list.prev = NULL; - spin_unlock(&orangefs_superblocks_lock); + if (!ORANGEFS_SB(sb)->no_list) { + /* remove the sb from our list of orangefs specific sb's */ + spin_lock(&orangefs_superblocks_lock); + /* not list_del_init */ + __list_del_entry(&ORANGEFS_SB(sb)->list); + ORANGEFS_SB(sb)->list.prev = NULL; + spin_unlock(&orangefs_superblocks_lock); + } /* * make sure that ORANGEFS_DEV_REMOUNT_ALL loop that might've seen us diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 1953986ee6bc..6e610a205e15 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -12,7 +12,6 @@ #include <linux/slab.h> #include <linux/cred.h> #include <linux/xattr.h> -#include <linux/sched/signal.h> #include "overlayfs.h" #include "ovl_entry.h" diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 8f91ec66baa3..d04ea4349909 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1074,6 +1074,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || + (table->proc_handler == proc_douintvec) || (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || (table->proc_handler == proc_dointvec_userhz_jiffies) || diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f08bd31c1081..312578089544 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -900,7 +900,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp); + pmd_t pmd = *pmdp; + + /* See comment in change_huge_pmd() */ + pmdp_invalidate(vma, addr, pmdp); + if (pmd_dirty(*pmdp)) + pmd = pmd_mkdirty(pmd); + if (pmd_young(*pmdp)) + pmd = pmd_mkyoung(pmd); pmd = pmd_wrprotect(pmd); pmd = pmd_clear_soft_dirty(pmd); diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c index 899d0ba0bd6c..06aab07b6bb7 100644 --- a/fs/pstore/ftrace.c +++ b/fs/pstore/ftrace.c @@ -37,6 +37,12 @@ static void notrace pstore_ftrace_call(unsigned long ip, { unsigned long flags; struct pstore_ftrace_record rec = {}; + struct pstore_record record = { + .type = PSTORE_TYPE_FTRACE, + .buf = (char *)&rec, + .size = sizeof(rec), + .psi = psinfo, + }; if (unlikely(oops_in_progress)) return; @@ -47,8 +53,7 @@ static void notrace pstore_ftrace_call(unsigned long ip, rec.parent_ip = parent_ip; pstore_ftrace_write_timestamp(&rec, pstore_ftrace_stamp++); pstore_ftrace_encode_cpu(&rec, raw_smp_processor_id()); - psinfo->write_buf(PSTORE_TYPE_FTRACE, 0, NULL, 0, (void *)&rec, - 0, sizeof(rec), psinfo); + psinfo->write(&record); local_irq_restore(flags); } @@ -117,7 +122,7 @@ void pstore_register_ftrace(void) { struct dentry *file; - if (!psinfo->write_buf) + if (!psinfo->write) return; pstore_ftrace_dir = debugfs_create_dir("pstore", NULL); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 57c0646479f5..792a4e5f9226 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -47,12 +47,8 @@ static LIST_HEAD(allpstore); struct pstore_private { struct list_head list; - struct pstore_info *psi; - enum pstore_type_id type; - u64 id; - int count; - ssize_t size; - char data[]; + struct pstore_record *record; + size_t total_size; }; struct pstore_ftrace_seq_data { @@ -63,6 +59,17 @@ struct pstore_ftrace_seq_data { #define REC_SIZE sizeof(struct pstore_ftrace_record) +static void free_pstore_private(struct pstore_private *private) +{ + if (!private) + return; + if (private->record) { + kfree(private->record->buf); + kfree(private->record); + } + kfree(private); +} + static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos) { struct pstore_private *ps = s->private; @@ -72,9 +79,9 @@ static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos) if (!data) return NULL; - data->off = ps->size % REC_SIZE; + data->off = ps->total_size % REC_SIZE; data->off += *pos * REC_SIZE; - if (data->off + REC_SIZE > ps->size) { + if (data->off + REC_SIZE > ps->total_size) { kfree(data); return NULL; } @@ -94,7 +101,7 @@ static void *pstore_ftrace_seq_next(struct seq_file *s, void *v, loff_t *pos) struct pstore_ftrace_seq_data *data = v; data->off += REC_SIZE; - if (data->off + REC_SIZE > ps->size) + if (data->off + REC_SIZE > ps->total_size) return NULL; (*pos)++; @@ -105,7 +112,9 @@ static int pstore_ftrace_seq_show(struct seq_file *s, void *v) { struct pstore_private *ps = s->private; struct pstore_ftrace_seq_data *data = v; - struct pstore_ftrace_record *rec = (void *)(ps->data + data->off); + struct pstore_ftrace_record *rec; + + rec = (struct pstore_ftrace_record *)(ps->record->buf + data->off); seq_printf(s, "CPU:%d ts:%llu %08lx %08lx %pf <- %pF\n", pstore_ftrace_decode_cpu(rec), @@ -125,7 +134,7 @@ static const struct seq_operations pstore_ftrace_seq_ops = { static int pstore_check_syslog_permissions(struct pstore_private *ps) { - switch (ps->type) { + switch (ps->record->type) { case PSTORE_TYPE_DMESG: case PSTORE_TYPE_CONSOLE: return check_syslog_permissions(SYSLOG_ACTION_READ_ALL, @@ -141,9 +150,10 @@ static ssize_t pstore_file_read(struct file *file, char __user *userbuf, struct seq_file *sf = file->private_data; struct pstore_private *ps = sf->private; - if (ps->type == PSTORE_TYPE_FTRACE) + if (ps->record->type == PSTORE_TYPE_FTRACE) return seq_read(file, userbuf, count, ppos); - return simple_read_from_buffer(userbuf, count, ppos, ps->data, ps->size); + return simple_read_from_buffer(userbuf, count, ppos, + ps->record->buf, ps->total_size); } static int pstore_file_open(struct inode *inode, struct file *file) @@ -157,7 +167,7 @@ static int pstore_file_open(struct inode *inode, struct file *file) if (err) return err; - if (ps->type == PSTORE_TYPE_FTRACE) + if (ps->record->type == PSTORE_TYPE_FTRACE) sops = &pstore_ftrace_seq_ops; err = seq_open(file, sops); @@ -193,20 +203,19 @@ static const struct file_operations pstore_file_operations = { static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = d_inode(dentry)->i_private; + struct pstore_record *record = p->record; int err; err = pstore_check_syslog_permissions(p); if (err) return err; - if (p->psi->erase) { - mutex_lock(&p->psi->read_mutex); - p->psi->erase(p->type, p->id, p->count, - d_inode(dentry)->i_ctime, p->psi); - mutex_unlock(&p->psi->read_mutex); - } else { + if (!record->psi->erase) return -EPERM; - } + + mutex_lock(&record->psi->read_mutex); + record->psi->erase(record); + mutex_unlock(&record->psi->read_mutex); return simple_unlink(dir, dentry); } @@ -221,7 +230,7 @@ static void pstore_evict_inode(struct inode *inode) spin_lock_irqsave(&allpstore_lock, flags); list_del(&p->list); spin_unlock_irqrestore(&allpstore_lock, flags); - kfree(p); + free_pstore_private(p); } } @@ -302,23 +311,23 @@ bool pstore_is_mounted(void) * Load it up with "size" bytes of data from "buf". * Set the mtime & ctime to the date that this record was originally stored. */ -int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, - char *data, bool compressed, size_t size, - struct timespec time, struct pstore_info *psi) +int pstore_mkfile(struct dentry *root, struct pstore_record *record) { - struct dentry *root = pstore_sb->s_root; struct dentry *dentry; struct inode *inode; int rc = 0; char name[PSTORE_NAMELEN]; struct pstore_private *private, *pos; unsigned long flags; + size_t size = record->size + record->ecc_notice_size; + + WARN_ON(!inode_is_locked(d_inode(root))); spin_lock_irqsave(&allpstore_lock, flags); list_for_each_entry(pos, &allpstore, list) { - if (pos->type == type && - pos->id == id && - pos->psi == psi) { + if (pos->record->type == record->type && + pos->record->id == record->id && + pos->record->psi == record->psi) { rc = -EEXIST; break; } @@ -328,72 +337,74 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, return rc; rc = -ENOMEM; - inode = pstore_get_inode(pstore_sb); + inode = pstore_get_inode(root->d_sb); if (!inode) goto fail; inode->i_mode = S_IFREG | 0444; inode->i_fop = &pstore_file_operations; - private = kmalloc(sizeof *private + size, GFP_KERNEL); + private = kzalloc(sizeof(*private), GFP_KERNEL); if (!private) goto fail_alloc; - private->type = type; - private->id = id; - private->count = count; - private->psi = psi; + private->record = record; - switch (type) { + switch (record->type) { case PSTORE_TYPE_DMESG: scnprintf(name, sizeof(name), "dmesg-%s-%lld%s", - psname, id, compressed ? ".enc.z" : ""); + record->psi->name, record->id, + record->compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: - scnprintf(name, sizeof(name), "console-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "console-%s-%lld", + record->psi->name, record->id); break; case PSTORE_TYPE_FTRACE: - scnprintf(name, sizeof(name), "ftrace-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "ftrace-%s-%lld", + record->psi->name, record->id); break; case PSTORE_TYPE_MCE: - scnprintf(name, sizeof(name), "mce-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "mce-%s-%lld", + record->psi->name, record->id); break; case PSTORE_TYPE_PPC_RTAS: - scnprintf(name, sizeof(name), "rtas-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "rtas-%s-%lld", + record->psi->name, record->id); break; case PSTORE_TYPE_PPC_OF: scnprintf(name, sizeof(name), "powerpc-ofw-%s-%lld", - psname, id); + record->psi->name, record->id); break; case PSTORE_TYPE_PPC_COMMON: scnprintf(name, sizeof(name), "powerpc-common-%s-%lld", - psname, id); + record->psi->name, record->id); break; case PSTORE_TYPE_PMSG: - scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "pmsg-%s-%lld", + record->psi->name, record->id); break; case PSTORE_TYPE_PPC_OPAL: - sprintf(name, "powerpc-opal-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "powerpc-opal-%s-%lld", + record->psi->name, record->id); break; case PSTORE_TYPE_UNKNOWN: - scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "unknown-%s-%lld", + record->psi->name, record->id); break; default: scnprintf(name, sizeof(name), "type%d-%s-%lld", - type, psname, id); + record->type, record->psi->name, record->id); break; } - inode_lock(d_inode(root)); - dentry = d_alloc_name(root, name); if (!dentry) - goto fail_lockedalloc; + goto fail_private; - memcpy(private->data, data, size); - inode->i_size = private->size = size; + inode->i_size = private->total_size = size; inode->i_private = private; - if (time.tv_sec) - inode->i_mtime = inode->i_ctime = time; + if (record->time.tv_sec) + inode->i_mtime = inode->i_ctime = record->time; d_add(dentry, inode); @@ -401,13 +412,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, list_add(&private->list, &allpstore); spin_unlock_irqrestore(&allpstore_lock, flags); - inode_unlock(d_inode(root)); - return 0; -fail_lockedalloc: - inode_unlock(d_inode(root)); - kfree(private); +fail_private: + free_pstore_private(private); fail_alloc: iput(inode); @@ -415,6 +423,27 @@ fail: return rc; } +/* + * Read all the records from the persistent store. Create + * files in our filesystem. Don't warn about -EEXIST errors + * when we are re-scanning the backing store looking to add new + * error records. + */ +void pstore_get_records(int quiet) +{ + struct pstore_info *psi = psinfo; + struct dentry *root; + + if (!psi || !pstore_sb) + return; + + root = pstore_sb->s_root; + + inode_lock(d_inode(root)); + pstore_get_backend_records(psi, root, quiet); + inode_unlock(d_inode(root)); +} + static int pstore_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index da416e6591c9..c416e653dc4f 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -25,10 +25,10 @@ extern struct pstore_info *psinfo; extern void pstore_set_kmsg_bytes(int); extern void pstore_get_records(int); -extern int pstore_mkfile(enum pstore_type_id, char *psname, u64 id, - int count, char *data, bool compressed, - size_t size, struct timespec time, - struct pstore_info *psi); +extern void pstore_get_backend_records(struct pstore_info *psi, + struct dentry *root, int quiet); +extern int pstore_mkfile(struct dentry *root, + struct pstore_record *record); extern bool pstore_is_mounted(void); #endif diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index efab7b64925b..d468eec9b8a6 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -267,7 +267,7 @@ static void free_zlib(void) big_oops_buf_sz = 0; } -static struct pstore_zbackend backend_zlib = { +static const struct pstore_zbackend backend_zlib = { .compress = compress_zlib, .decompress = decompress_zlib, .allocate = allocate_zlib, @@ -328,7 +328,7 @@ static void free_lzo(void) big_oops_buf_sz = 0; } -static struct pstore_zbackend backend_lzo = { +static const struct pstore_zbackend backend_lzo = { .compress = compress_lzo, .decompress = decompress_lzo, .allocate = allocate_lzo, @@ -393,7 +393,7 @@ static void free_lz4(void) big_oops_buf_sz = 0; } -static struct pstore_zbackend backend_lz4 = { +static const struct pstore_zbackend backend_lz4 = { .compress = compress_lz4, .decompress = decompress_lz4, .allocate = allocate_lz4, @@ -402,7 +402,7 @@ static struct pstore_zbackend backend_lz4 = { }; #endif -static struct pstore_zbackend *zbackend = +static const struct pstore_zbackend *zbackend = #if defined(CONFIG_PSTORE_ZLIB_COMPRESS) &backend_zlib; #elif defined(CONFIG_PSTORE_LZO_COMPRESS) @@ -484,7 +484,6 @@ static void pstore_dump(struct kmsg_dumper *dumper, { unsigned long total = 0; const char *why; - u64 id; unsigned int part = 1; unsigned long flags = 0; int is_locked; @@ -506,48 +505,59 @@ static void pstore_dump(struct kmsg_dumper *dumper, oopscount++; while (total < kmsg_bytes) { char *dst; - unsigned long size; - int hsize; + size_t dst_size; + int header_size; int zipped_len = -1; - size_t len; - bool compressed = false; - size_t total_len; + size_t dump_size; + struct pstore_record record = { + .type = PSTORE_TYPE_DMESG, + .count = oopscount, + .reason = reason, + .part = part, + .compressed = false, + .buf = psinfo->buf, + .psi = psinfo, + }; if (big_oops_buf && is_locked) { dst = big_oops_buf; - size = big_oops_buf_sz; + dst_size = big_oops_buf_sz; } else { dst = psinfo->buf; - size = psinfo->bufsize; + dst_size = psinfo->bufsize; } - hsize = sprintf(dst, "%s#%d Part%u\n", why, oopscount, part); - size -= hsize; + /* Write dump header. */ + header_size = snprintf(dst, dst_size, "%s#%d Part%u\n", why, + oopscount, part); + dst_size -= header_size; - if (!kmsg_dump_get_buffer(dumper, true, dst + hsize, - size, &len)) + /* Write dump contents. */ + if (!kmsg_dump_get_buffer(dumper, true, dst + header_size, + dst_size, &dump_size)) break; if (big_oops_buf && is_locked) { zipped_len = pstore_compress(dst, psinfo->buf, - hsize + len, psinfo->bufsize); + header_size + dump_size, + psinfo->bufsize); if (zipped_len > 0) { - compressed = true; - total_len = zipped_len; + record.compressed = true; + record.size = zipped_len; } else { - total_len = copy_kmsg_to_buffer(hsize, len); + record.size = copy_kmsg_to_buffer(header_size, + dump_size); } } else { - total_len = hsize + len; + record.size = header_size + dump_size; } - ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - oopscount, compressed, total_len, psinfo); + ret = psinfo->write(&record); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; - total += total_len; + total += record.size; part++; } if (is_locked) @@ -577,8 +587,11 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) const char *e = s + c; while (s < e) { + struct pstore_record record = { + .type = PSTORE_TYPE_CONSOLE, + .psi = psinfo, + }; unsigned long flags; - u64 id; if (c > psinfo->bufsize) c = psinfo->bufsize; @@ -589,8 +602,9 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) } else { spin_lock_irqsave(&psinfo->buf_lock, flags); } - psinfo->write_buf(PSTORE_TYPE_CONSOLE, 0, &id, 0, - s, 0, c, psinfo); + record.buf = (char *)s; + record.size = c; + psinfo->write(&record); spin_unlock_irqrestore(&psinfo->buf_lock, flags); s += c; c = e - s; @@ -618,48 +632,30 @@ static void pstore_register_console(void) {} static void pstore_unregister_console(void) {} #endif -static int pstore_write_compat(enum pstore_type_id type, - enum kmsg_dump_reason reason, - u64 *id, unsigned int part, int count, - bool compressed, size_t size, - struct pstore_info *psi) -{ - return psi->write_buf(type, reason, id, part, psinfo->buf, compressed, - size, psi); -} - -static int pstore_write_buf_user_compat(enum pstore_type_id type, - enum kmsg_dump_reason reason, - u64 *id, unsigned int part, - const char __user *buf, - bool compressed, size_t size, - struct pstore_info *psi) -{ - unsigned long flags = 0; - size_t i, bufsize = size; - long ret = 0; - - if (unlikely(!access_ok(VERIFY_READ, buf, size))) - return -EFAULT; - if (bufsize > psinfo->bufsize) - bufsize = psinfo->bufsize; - spin_lock_irqsave(&psinfo->buf_lock, flags); - for (i = 0; i < size; ) { - size_t c = min(size - i, bufsize); - - ret = __copy_from_user(psinfo->buf, buf + i, c); - if (unlikely(ret != 0)) { - ret = -EFAULT; - break; - } - ret = psi->write_buf(type, reason, id, part, psinfo->buf, - compressed, c, psi); - if (unlikely(ret < 0)) - break; - i += c; +static int pstore_write_user_compat(struct pstore_record *record, + const char __user *buf) +{ + int ret = 0; + + if (record->buf) + return -EINVAL; + + record->buf = kmalloc(record->size, GFP_KERNEL); + if (!record->buf) + return -ENOMEM; + + if (unlikely(copy_from_user(record->buf, buf, record->size))) { + ret = -EFAULT; + goto out; } - spin_unlock_irqrestore(&psinfo->buf_lock, flags); - return unlikely(ret < 0) ? ret : size; + + ret = record->psi->write(record); + +out: + kfree(record->buf); + record->buf = NULL; + + return unlikely(ret < 0) ? ret : record->size; } /* @@ -673,19 +669,35 @@ int pstore_register(struct pstore_info *psi) { struct module *owner = psi->owner; - if (backend && strcmp(backend, psi->name)) + if (backend && strcmp(backend, psi->name)) { + pr_warn("ignoring unexpected backend '%s'\n", psi->name); return -EPERM; + } + + /* Sanity check flags. */ + if (!psi->flags) { + pr_warn("backend '%s' must support at least one frontend\n", + psi->name); + return -EINVAL; + } + + /* Check for required functions. */ + if (!psi->read || !psi->write) { + pr_warn("backend '%s' must implement read() and write()\n", + psi->name); + return -EINVAL; + } spin_lock(&pstore_lock); if (psinfo) { + pr_warn("backend '%s' already loaded: ignoring '%s'\n", + psinfo->name, psi->name); spin_unlock(&pstore_lock); return -EBUSY; } - if (!psi->write) - psi->write = pstore_write_compat; - if (!psi->write_buf_user) - psi->write_buf_user = pstore_write_buf_user_compat; + if (!psi->write_user) + psi->write_user = pstore_write_user_compat; psinfo = psi; mutex_init(&psinfo->read_mutex); spin_unlock(&pstore_lock); @@ -709,6 +721,7 @@ int pstore_register(struct pstore_info *psi) if (psi->flags & PSTORE_FLAGS_PMSG) pstore_register_pmsg(); + /* Start watching for new records, if desired. */ if (pstore_update_ms >= 0) { pstore_timer.expires = jiffies + msecs_to_jiffies(pstore_update_ms); @@ -721,16 +734,21 @@ int pstore_register(struct pstore_info *psi) */ backend = psi->name; - module_put(owner); - pr_info("Registered %s as persistent store backend\n", psi->name); + module_put(owner); + return 0; } EXPORT_SYMBOL_GPL(pstore_register); void pstore_unregister(struct pstore_info *psi) { + /* Stop timer and make sure all work has finished. */ + pstore_update_ms = -1; + del_timer_sync(&pstore_timer); + flush_work(&pstore_work); + if (psi->flags & PSTORE_FLAGS_PMSG) pstore_unregister_pmsg(); if (psi->flags & PSTORE_FLAGS_FTRACE) @@ -747,66 +765,99 @@ void pstore_unregister(struct pstore_info *psi) } EXPORT_SYMBOL_GPL(pstore_unregister); +static void decompress_record(struct pstore_record *record) +{ + int unzipped_len; + char *decompressed; + + /* Only PSTORE_TYPE_DMESG support compression. */ + if (!record->compressed || record->type != PSTORE_TYPE_DMESG) { + pr_warn("ignored compressed record type %d\n", record->type); + return; + } + + /* No compression method has created the common buffer. */ + if (!big_oops_buf) { + pr_warn("no decompression buffer allocated\n"); + return; + } + + unzipped_len = pstore_decompress(record->buf, big_oops_buf, + record->size, big_oops_buf_sz); + if (unzipped_len <= 0) { + pr_err("decompression failed: %d\n", unzipped_len); + return; + } + + /* Build new buffer for decompressed contents. */ + decompressed = kmalloc(unzipped_len + record->ecc_notice_size, + GFP_KERNEL); + if (!decompressed) { + pr_err("decompression ran out of memory\n"); + return; + } + memcpy(decompressed, big_oops_buf, unzipped_len); + + /* Append ECC notice to decompressed buffer. */ + memcpy(decompressed + unzipped_len, record->buf + record->size, + record->ecc_notice_size); + + /* Swap out compresed contents with decompressed contents. */ + kfree(record->buf); + record->buf = decompressed; + record->size = unzipped_len; + record->compressed = false; +} + /* - * Read all the records from the persistent store. Create + * Read all the records from one persistent store backend. Create * files in our filesystem. Don't warn about -EEXIST errors * when we are re-scanning the backing store looking to add new * error records. */ -void pstore_get_records(int quiet) -{ - struct pstore_info *psi = psinfo; - char *buf = NULL; - ssize_t size; - u64 id; - int count; - enum pstore_type_id type; - struct timespec time; - int failed = 0, rc; - bool compressed; - int unzipped_len = -1; - ssize_t ecc_notice_size = 0; - - if (!psi) +void pstore_get_backend_records(struct pstore_info *psi, + struct dentry *root, int quiet) +{ + int failed = 0; + + if (!psi || !root) return; mutex_lock(&psi->read_mutex); if (psi->open && psi->open(psi)) goto out; - while ((size = psi->read(&id, &type, &count, &time, &buf, &compressed, - &ecc_notice_size, psi)) > 0) { - if (compressed && (type == PSTORE_TYPE_DMESG)) { - if (big_oops_buf) - unzipped_len = pstore_decompress(buf, - big_oops_buf, size, - big_oops_buf_sz); - - if (unzipped_len > 0) { - if (ecc_notice_size) - memcpy(big_oops_buf + unzipped_len, - buf + size, ecc_notice_size); - kfree(buf); - buf = big_oops_buf; - size = unzipped_len; - compressed = false; - } else { - pr_err("decompression failed;returned %d\n", - unzipped_len); - compressed = true; - } + /* + * Backend callback read() allocates record.buf. decompress_record() + * may reallocate record.buf. On success, pstore_mkfile() will keep + * the record.buf, so free it only on failure. + */ + for (;;) { + struct pstore_record *record; + int rc; + + record = kzalloc(sizeof(*record), GFP_KERNEL); + if (!record) { + pr_err("out of memory creating record\n"); + break; + } + record->psi = psi; + + record->size = psi->read(record); + + /* No more records left in backend? */ + if (record->size <= 0) + break; + + decompress_record(record); + rc = pstore_mkfile(root, record); + if (rc) { + /* pstore_mkfile() did not take record, so free it. */ + kfree(record->buf); + kfree(record); + if (rc != -EEXIST || !quiet) + failed++; } - rc = pstore_mkfile(type, psi->name, id, count, buf, - compressed, size + ecc_notice_size, - time, psi); - if (unzipped_len < 0) { - /* Free buffer other than big oops */ - kfree(buf); - buf = NULL; - } else - unzipped_len = -1; - if (rc && (rc != -EEXIST || !quiet)) - failed++; } if (psi->close) psi->close(psi); @@ -830,7 +881,9 @@ static void pstore_timefunc(unsigned long dummy) schedule_work(&pstore_work); } - mod_timer(&pstore_timer, jiffies + msecs_to_jiffies(pstore_update_ms)); + if (pstore_update_ms >= 0) + mod_timer(&pstore_timer, + jiffies + msecs_to_jiffies(pstore_update_ms)); } module_param(backend, charp, 0444); diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index 78f6176c020f..209755e0d7c8 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -15,7 +15,6 @@ #include <linux/device.h> #include <linux/fs.h> #include <linux/uaccess.h> -#include <linux/vmalloc.h> #include "internal.h" static DEFINE_MUTEX(pmsg_lock); @@ -23,19 +22,22 @@ static DEFINE_MUTEX(pmsg_lock); static ssize_t write_pmsg(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - u64 id; + struct pstore_record record = { + .type = PSTORE_TYPE_PMSG, + .size = count, + .psi = psinfo, + }; int ret; if (!count) return 0; - /* check outside lock, page in any data. write_buf_user also checks */ + /* check outside lock, page in any data. write_user also checks */ if (!access_ok(VERIFY_READ, buf, count)) return -EFAULT; mutex_lock(&pmsg_lock); - ret = psinfo->write_buf_user(PSTORE_TYPE_PMSG, 0, &id, 0, buf, 0, count, - psinfo); + ret = psinfo->write_user(&record, buf); mutex_unlock(&pmsg_lock); return ret ? ret : count; } diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 11f918d34b1e..5523df7f17ef 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -235,35 +235,34 @@ static ssize_t ftrace_log_combine(struct persistent_ram_zone *dest, return 0; } -static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, - int *count, struct timespec *time, - char **buf, bool *compressed, - ssize_t *ecc_notice_size, - struct pstore_info *psi) +static ssize_t ramoops_pstore_read(struct pstore_record *record) { ssize_t size = 0; - struct ramoops_context *cxt = psi->data; + struct ramoops_context *cxt = record->psi->data; struct persistent_ram_zone *prz = NULL; int header_length = 0; bool free_prz = false; - /* Ramoops headers provide time stamps for PSTORE_TYPE_DMESG, but + /* + * Ramoops headers provide time stamps for PSTORE_TYPE_DMESG, but * PSTORE_TYPE_CONSOLE and PSTORE_TYPE_FTRACE don't currently have * valid time stamps, so it is initialized to zero. */ - time->tv_sec = 0; - time->tv_nsec = 0; - *compressed = false; + record->time.tv_sec = 0; + record->time.tv_nsec = 0; + record->compressed = false; /* Find the next valid persistent_ram_zone for DMESG */ while (cxt->dump_read_cnt < cxt->max_dump_cnt && !prz) { prz = ramoops_get_next_prz(cxt->dprzs, &cxt->dump_read_cnt, - cxt->max_dump_cnt, id, type, + cxt->max_dump_cnt, &record->id, + &record->type, PSTORE_TYPE_DMESG, 1); if (!prz_ok(prz)) continue; header_length = ramoops_read_kmsg_hdr(persistent_ram_old(prz), - time, compressed); + &record->time, + &record->compressed); /* Clear and skip this DMESG record if it has no valid header */ if (!header_length) { persistent_ram_free_old(prz); @@ -274,18 +273,20 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, if (!prz_ok(prz)) prz = ramoops_get_next_prz(&cxt->cprz, &cxt->console_read_cnt, - 1, id, type, PSTORE_TYPE_CONSOLE, 0); + 1, &record->id, &record->type, + PSTORE_TYPE_CONSOLE, 0); if (!prz_ok(prz)) prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt, - 1, id, type, PSTORE_TYPE_PMSG, 0); + 1, &record->id, &record->type, + PSTORE_TYPE_PMSG, 0); /* ftrace is last since it may want to dynamically allocate memory. */ if (!prz_ok(prz)) { if (!(cxt->flags & RAMOOPS_FLAG_FTRACE_PER_CPU)) { prz = ramoops_get_next_prz(cxt->fprzs, - &cxt->ftrace_read_cnt, 1, id, type, - PSTORE_TYPE_FTRACE, 0); + &cxt->ftrace_read_cnt, 1, &record->id, + &record->type, PSTORE_TYPE_FTRACE, 0); } else { /* * Build a new dummy record which combines all the @@ -302,8 +303,10 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, while (cxt->ftrace_read_cnt < cxt->max_ftrace_cnt) { prz_next = ramoops_get_next_prz(cxt->fprzs, &cxt->ftrace_read_cnt, - cxt->max_ftrace_cnt, id, - type, PSTORE_TYPE_FTRACE, 0); + cxt->max_ftrace_cnt, + &record->id, + &record->type, + PSTORE_TYPE_FTRACE, 0); if (!prz_ok(prz_next)) continue; @@ -316,7 +319,7 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, if (size) goto out; } - *id = 0; + record->id = 0; prz = tmp_prz; } } @@ -329,17 +332,19 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, size = persistent_ram_old_size(prz) - header_length; /* ECC correction notice */ - *ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0); + record->ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0); - *buf = kmalloc(size + *ecc_notice_size + 1, GFP_KERNEL); - if (*buf == NULL) { + record->buf = kmalloc(size + record->ecc_notice_size + 1, GFP_KERNEL); + if (record->buf == NULL) { size = -ENOMEM; goto out; } - memcpy(*buf, (char *)persistent_ram_old(prz) + header_length, size); + memcpy(record->buf, (char *)persistent_ram_old(prz) + header_length, + size); - persistent_ram_ecc_string(prz, *buf + size, *ecc_notice_size + 1); + persistent_ram_ecc_string(prz, record->buf + size, + record->ecc_notice_size + 1); out: if (free_prz) { @@ -373,23 +378,18 @@ static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz, return len; } -static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, - enum kmsg_dump_reason reason, - u64 *id, unsigned int part, - const char *buf, - bool compressed, size_t size, - struct pstore_info *psi) +static int notrace ramoops_pstore_write(struct pstore_record *record) { - struct ramoops_context *cxt = psi->data; + struct ramoops_context *cxt = record->psi->data; struct persistent_ram_zone *prz; - size_t hlen; + size_t size, hlen; - if (type == PSTORE_TYPE_CONSOLE) { + if (record->type == PSTORE_TYPE_CONSOLE) { if (!cxt->cprz) return -ENOMEM; - persistent_ram_write(cxt->cprz, buf, size); + persistent_ram_write(cxt->cprz, record->buf, record->size); return 0; - } else if (type == PSTORE_TYPE_FTRACE) { + } else if (record->type == PSTORE_TYPE_FTRACE) { int zonenum; if (!cxt->fprzs) @@ -402,33 +402,36 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, else zonenum = 0; - persistent_ram_write(cxt->fprzs[zonenum], buf, size); + persistent_ram_write(cxt->fprzs[zonenum], record->buf, + record->size); return 0; - } else if (type == PSTORE_TYPE_PMSG) { + } else if (record->type == PSTORE_TYPE_PMSG) { pr_warn_ratelimited("PMSG shouldn't call %s\n", __func__); return -EINVAL; } - if (type != PSTORE_TYPE_DMESG) + if (record->type != PSTORE_TYPE_DMESG) return -EINVAL; - /* Out of the various dmesg dump types, ramoops is currently designed + /* + * Out of the various dmesg dump types, ramoops is currently designed * to only store crash logs, rather than storing general kernel logs. */ - if (reason != KMSG_DUMP_OOPS && - reason != KMSG_DUMP_PANIC) + if (record->reason != KMSG_DUMP_OOPS && + record->reason != KMSG_DUMP_PANIC) return -EINVAL; /* Skip Oopes when configured to do so. */ - if (reason == KMSG_DUMP_OOPS && !cxt->dump_oops) + if (record->reason == KMSG_DUMP_OOPS && !cxt->dump_oops) return -EINVAL; - /* Explicitly only take the first part of any new crash. + /* + * Explicitly only take the first part of any new crash. * If our buffer is larger than kmsg_bytes, this can never happen, * and if our buffer is smaller than kmsg_bytes, we don't want the * report split across multiple records. */ - if (part != 1) + if (record->part != 1) return -ENOSPC; if (!cxt->dprzs) @@ -436,53 +439,50 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, prz = cxt->dprzs[cxt->dump_write_cnt]; - hlen = ramoops_write_kmsg_hdr(prz, compressed); + /* Build header and append record contents. */ + hlen = ramoops_write_kmsg_hdr(prz, record->compressed); + size = record->size; if (size + hlen > prz->buffer_size) size = prz->buffer_size - hlen; - persistent_ram_write(prz, buf, size); + persistent_ram_write(prz, record->buf, size); cxt->dump_write_cnt = (cxt->dump_write_cnt + 1) % cxt->max_dump_cnt; return 0; } -static int notrace ramoops_pstore_write_buf_user(enum pstore_type_id type, - enum kmsg_dump_reason reason, - u64 *id, unsigned int part, - const char __user *buf, - bool compressed, size_t size, - struct pstore_info *psi) +static int notrace ramoops_pstore_write_user(struct pstore_record *record, + const char __user *buf) { - if (type == PSTORE_TYPE_PMSG) { - struct ramoops_context *cxt = psi->data; + if (record->type == PSTORE_TYPE_PMSG) { + struct ramoops_context *cxt = record->psi->data; if (!cxt->mprz) return -ENOMEM; - return persistent_ram_write_user(cxt->mprz, buf, size); + return persistent_ram_write_user(cxt->mprz, buf, record->size); } return -EINVAL; } -static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count, - struct timespec time, struct pstore_info *psi) +static int ramoops_pstore_erase(struct pstore_record *record) { - struct ramoops_context *cxt = psi->data; + struct ramoops_context *cxt = record->psi->data; struct persistent_ram_zone *prz; - switch (type) { + switch (record->type) { case PSTORE_TYPE_DMESG: - if (id >= cxt->max_dump_cnt) + if (record->id >= cxt->max_dump_cnt) return -EINVAL; - prz = cxt->dprzs[id]; + prz = cxt->dprzs[record->id]; break; case PSTORE_TYPE_CONSOLE: prz = cxt->cprz; break; case PSTORE_TYPE_FTRACE: - if (id >= cxt->max_ftrace_cnt) + if (record->id >= cxt->max_ftrace_cnt) return -EINVAL; - prz = cxt->fprzs[id]; + prz = cxt->fprzs[record->id]; break; case PSTORE_TYPE_PMSG: prz = cxt->mprz; @@ -503,8 +503,8 @@ static struct ramoops_context oops_cxt = { .name = "ramoops", .open = ramoops_pstore_open, .read = ramoops_pstore_read, - .write_buf = ramoops_pstore_write_buf, - .write_buf_user = ramoops_pstore_write_buf_user, + .write = ramoops_pstore_write, + .write_user = ramoops_pstore_write_user, .erase = ramoops_pstore_erase, }, }; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index bc927e30bdcc..e11672aa4575 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -532,7 +532,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, } /* Initialize general buffer state. */ - prz->buffer_lock = __RAW_SPIN_LOCK_UNLOCKED(buffer_lock); + raw_spin_lock_init(&prz->buffer_lock); prz->flags = flags; ret = persistent_ram_buffer_map(start, size, prz, memtype); diff --git a/fs/read_write.c b/fs/read_write.c index c4f88afbc67f..47c1d4484df9 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -841,6 +841,81 @@ out: return ret; } +#ifdef CONFIG_COMPAT +ssize_t compat_rw_copy_check_uvector(int type, + const struct compat_iovec __user *uvector, unsigned long nr_segs, + unsigned long fast_segs, struct iovec *fast_pointer, + struct iovec **ret_pointer) +{ + compat_ssize_t tot_len; + struct iovec *iov = *ret_pointer = fast_pointer; + ssize_t ret = 0; + int seg; + + /* + * SuS says "The readv() function *may* fail if the iovcnt argument + * was less than or equal to 0, or greater than {IOV_MAX}. Linux has + * traditionally returned zero for zero segments, so... + */ + if (nr_segs == 0) + goto out; + + ret = -EINVAL; + if (nr_segs > UIO_MAXIOV) + goto out; + if (nr_segs > fast_segs) { + ret = -ENOMEM; + iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); + if (iov == NULL) + goto out; + } + *ret_pointer = iov; + + ret = -EFAULT; + if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector))) + goto out; + + /* + * Single unix specification: + * We should -EINVAL if an element length is not >= 0 and fitting an + * ssize_t. + * + * In Linux, the total length is limited to MAX_RW_COUNT, there is + * no overflow possibility. + */ + tot_len = 0; + ret = -EINVAL; + for (seg = 0; seg < nr_segs; seg++) { + compat_uptr_t buf; + compat_ssize_t len; + + if (__get_user(len, &uvector->iov_len) || + __get_user(buf, &uvector->iov_base)) { + ret = -EFAULT; + goto out; + } + if (len < 0) /* size_t not fitting in compat_ssize_t .. */ + goto out; + if (type >= 0 && + !access_ok(vrfy_dir(type), compat_ptr(buf), len)) { + ret = -EFAULT; + goto out; + } + if (len > MAX_RW_COUNT - tot_len) + len = MAX_RW_COUNT - tot_len; + tot_len += len; + iov->iov_base = compat_ptr(buf); + iov->iov_len = (compat_size_t) len; + uvector++; + iov++; + } + ret = tot_len; + +out: + return ret; +} +#endif + static ssize_t __do_readv_writev(int type, struct file *file, struct iov_iter *iter, loff_t *pos, int flags) { diff --git a/fs/readdir.c b/fs/readdir.c index 0e8a7f355f7a..89659549c09d 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -18,6 +18,7 @@ #include <linux/security.h> #include <linux/syscalls.h> #include <linux/unistd.h> +#include <linux/compat.h> #include <linux/uaccess.h> @@ -324,3 +325,167 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, fdput_pos(f); return error; } + +#ifdef CONFIG_COMPAT +struct compat_old_linux_dirent { + compat_ulong_t d_ino; + compat_ulong_t d_offset; + unsigned short d_namlen; + char d_name[1]; +}; + +struct compat_readdir_callback { + struct dir_context ctx; + struct compat_old_linux_dirent __user *dirent; + int result; +}; + +static int compat_fillonedir(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) +{ + struct compat_readdir_callback *buf = + container_of(ctx, struct compat_readdir_callback, ctx); + struct compat_old_linux_dirent __user *dirent; + compat_ulong_t d_ino; + + if (buf->result) + return -EINVAL; + d_ino = ino; + if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { + buf->result = -EOVERFLOW; + return -EOVERFLOW; + } + buf->result++; + dirent = buf->dirent; + if (!access_ok(VERIFY_WRITE, dirent, + (unsigned long)(dirent->d_name + namlen + 1) - + (unsigned long)dirent)) + goto efault; + if ( __put_user(d_ino, &dirent->d_ino) || + __put_user(offset, &dirent->d_offset) || + __put_user(namlen, &dirent->d_namlen) || + __copy_to_user(dirent->d_name, name, namlen) || + __put_user(0, dirent->d_name + namlen)) + goto efault; + return 0; +efault: + buf->result = -EFAULT; + return -EFAULT; +} + +COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, + struct compat_old_linux_dirent __user *, dirent, unsigned int, count) +{ + int error; + struct fd f = fdget_pos(fd); + struct compat_readdir_callback buf = { + .ctx.actor = compat_fillonedir, + .dirent = dirent + }; + + if (!f.file) + return -EBADF; + + error = iterate_dir(f.file, &buf.ctx); + if (buf.result) + error = buf.result; + + fdput_pos(f); + return error; +} + +struct compat_linux_dirent { + compat_ulong_t d_ino; + compat_ulong_t d_off; + unsigned short d_reclen; + char d_name[1]; +}; + +struct compat_getdents_callback { + struct dir_context ctx; + struct compat_linux_dirent __user *current_dir; + struct compat_linux_dirent __user *previous; + int count; + int error; +}; + +static int compat_filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct compat_linux_dirent __user * dirent; + struct compat_getdents_callback *buf = + container_of(ctx, struct compat_getdents_callback, ctx); + compat_ulong_t d_ino; + int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + + namlen + 2, sizeof(compat_long_t)); + + buf->error = -EINVAL; /* only used if we fail.. */ + if (reclen > buf->count) + return -EINVAL; + d_ino = ino; + if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { + buf->error = -EOVERFLOW; + return -EOVERFLOW; + } + dirent = buf->previous; + if (dirent) { + if (signal_pending(current)) + return -EINTR; + if (__put_user(offset, &dirent->d_off)) + goto efault; + } + dirent = buf->current_dir; + if (__put_user(d_ino, &dirent->d_ino)) + goto efault; + if (__put_user(reclen, &dirent->d_reclen)) + goto efault; + if (copy_to_user(dirent->d_name, name, namlen)) + goto efault; + if (__put_user(0, dirent->d_name + namlen)) + goto efault; + if (__put_user(d_type, (char __user *) dirent + reclen - 1)) + goto efault; + buf->previous = dirent; + dirent = (void __user *)dirent + reclen; + buf->current_dir = dirent; + buf->count -= reclen; + return 0; +efault: + buf->error = -EFAULT; + return -EFAULT; +} + +COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, + struct compat_linux_dirent __user *, dirent, unsigned int, count) +{ + struct fd f; + struct compat_linux_dirent __user * lastdirent; + struct compat_getdents_callback buf = { + .ctx.actor = compat_filldir, + .current_dir = dirent, + .count = count + }; + int error; + + if (!access_ok(VERIFY_WRITE, dirent, count)) + return -EFAULT; + + f = fdget_pos(fd); + if (!f.file) + return -EBADF; + + error = iterate_dir(f.file, &buf.ctx); + if (error >= 0) + error = buf.error; + lastdirent = buf.previous; + if (lastdirent) { + if (put_user(buf.ctx.pos, &lastdirent->d_off)) + error = -EFAULT; + else + error = count - buf.count; + } + fdput_pos(f); + return error; +} +#endif diff --git a/fs/select.c b/fs/select.c index e2112270d75a..bd4b2ccfd346 100644 --- a/fs/select.c +++ b/fs/select.c @@ -338,6 +338,53 @@ sticky: return ret; } +/* + * Scalable version of the fd_set. + */ + +typedef struct { + unsigned long *in, *out, *ex; + unsigned long *res_in, *res_out, *res_ex; +} fd_set_bits; + +/* + * How many longwords for "nr" bits? + */ +#define FDS_BITPERLONG (8*sizeof(long)) +#define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG) +#define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) + +/* + * We do a VERIFY_WRITE here even though we are only reading this time: + * we'll write to it eventually.. + * + * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. + */ +static inline +int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) +{ + nr = FDS_BYTES(nr); + if (ufdset) + return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0; + + memset(fdset, 0, nr); + return 0; +} + +static inline unsigned long __must_check +set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) +{ + if (ufdset) + return __copy_to_user(ufdset, fdset, FDS_BYTES(nr)); + return 0; +} + +static inline +void zero_fd_set(unsigned long nr, unsigned long *fdset) +{ + memset(fdset, 0, FDS_BYTES(nr)); +} + #define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) @@ -401,7 +448,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in, wait->_key |= POLLOUT_SET; } -int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) +static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; @@ -409,7 +456,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) int retval, i, timed_out = 0; u64 slack = 0; unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; - unsigned long busy_end = 0; + unsigned long busy_start = 0; rcu_read_lock(); retval = max_select_fd(n, fds); @@ -512,11 +559,11 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { - if (!busy_end) { - busy_end = busy_loop_end_time(); + if (!busy_start) { + busy_start = busy_loop_current_time(); continue; } - if (!busy_loop_timeout(busy_end)) + if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; @@ -800,7 +847,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait, int timed_out = 0, count = 0; u64 slack = 0; unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; - unsigned long busy_end = 0; + unsigned long busy_start = 0; /* Optimise the no-wait case */ if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { @@ -853,11 +900,11 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait, /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { - if (!busy_end) { - busy_end = busy_loop_end_time(); + if (!busy_start) { + busy_start = busy_loop_current_time(); continue; } - if (!busy_loop_timeout(busy_end)) + if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; @@ -881,7 +928,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait, #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ sizeof(struct pollfd)) -int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, +static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, struct timespec64 *end_time) { struct poll_wqueues table; @@ -1053,3 +1100,373 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, return ret; } + +#ifdef CONFIG_COMPAT +#define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) + +static +int compat_poll_select_copy_remaining(struct timespec *end_time, void __user *p, + int timeval, int ret) +{ + struct timespec ts; + + if (!p) + return ret; + + if (current->personality & STICKY_TIMEOUTS) + goto sticky; + + /* No update for zero timeout */ + if (!end_time->tv_sec && !end_time->tv_nsec) + return ret; + + ktime_get_ts(&ts); + ts = timespec_sub(*end_time, ts); + if (ts.tv_sec < 0) + ts.tv_sec = ts.tv_nsec = 0; + + if (timeval) { + struct compat_timeval rtv; + + rtv.tv_sec = ts.tv_sec; + rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC; + + if (!copy_to_user(p, &rtv, sizeof(rtv))) + return ret; + } else { + struct compat_timespec rts; + + rts.tv_sec = ts.tv_sec; + rts.tv_nsec = ts.tv_nsec; + + if (!copy_to_user(p, &rts, sizeof(rts))) + return ret; + } + /* + * If an application puts its timeval in read-only memory, we + * don't want the Linux-specific update to the timeval to + * cause a fault after the select has completed + * successfully. However, because we're not updating the + * timeval, we can't restart the system call. + */ + +sticky: + if (ret == -ERESTARTNOHAND) + ret = -EINTR; + return ret; +} + +/* + * Ooo, nasty. We need here to frob 32-bit unsigned longs to + * 64-bit unsigned longs. + */ +static +int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, + unsigned long *fdset) +{ + nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); + if (ufdset) { + unsigned long odd; + + if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t))) + return -EFAULT; + + odd = nr & 1UL; + nr &= ~1UL; + while (nr) { + unsigned long h, l; + if (__get_user(l, ufdset) || __get_user(h, ufdset+1)) + return -EFAULT; + ufdset += 2; + *fdset++ = h << 32 | l; + nr -= 2; + } + if (odd && __get_user(*fdset, ufdset)) + return -EFAULT; + } else { + /* Tricky, must clear full unsigned long in the + * kernel fdset at the end, this makes sure that + * actually happens. + */ + memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t)); + } + return 0; +} + +static +int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, + unsigned long *fdset) +{ + unsigned long odd; + nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); + + if (!ufdset) + return 0; + + odd = nr & 1UL; + nr &= ~1UL; + while (nr) { + unsigned long h, l; + l = *fdset++; + h = l >> 32; + if (__put_user(l, ufdset) || __put_user(h, ufdset+1)) + return -EFAULT; + ufdset += 2; + nr -= 2; + } + if (odd && __put_user(*fdset, ufdset)) + return -EFAULT; + return 0; +} + + +/* + * This is a virtual copy of sys_select from fs/select.c and probably + * should be compared to it from time to time + */ + +/* + * We can actually return ERESTARTSYS instead of EINTR, but I'd + * like to be certain this leads to no problems. So I return + * EINTR just for safety. + * + * Update: ERESTARTSYS breaks at least the xview clock binary, so + * I'm trying ERESTARTNOHAND which restart only when you want to. + */ +static int compat_core_sys_select(int n, compat_ulong_t __user *inp, + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + struct timespec *end_time) +{ + fd_set_bits fds; + void *bits; + int size, max_fds, ret = -EINVAL; + struct fdtable *fdt; + long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; + + if (n < 0) + goto out_nofds; + + /* max_fds can increase, so grab it once to avoid race */ + rcu_read_lock(); + fdt = files_fdtable(current->files); + max_fds = fdt->max_fds; + rcu_read_unlock(); + if (n > max_fds) + n = max_fds; + + /* + * We need 6 bitmaps (in/out/ex for both incoming and outgoing), + * since we used fdset we need to allocate memory in units of + * long-words. + */ + size = FDS_BYTES(n); + bits = stack_fds; + if (size > sizeof(stack_fds) / 6) { + bits = kmalloc(6 * size, GFP_KERNEL); + ret = -ENOMEM; + if (!bits) + goto out_nofds; + } + fds.in = (unsigned long *) bits; + fds.out = (unsigned long *) (bits + size); + fds.ex = (unsigned long *) (bits + 2*size); + fds.res_in = (unsigned long *) (bits + 3*size); + fds.res_out = (unsigned long *) (bits + 4*size); + fds.res_ex = (unsigned long *) (bits + 5*size); + + if ((ret = compat_get_fd_set(n, inp, fds.in)) || + (ret = compat_get_fd_set(n, outp, fds.out)) || + (ret = compat_get_fd_set(n, exp, fds.ex))) + goto out; + zero_fd_set(n, fds.res_in); + zero_fd_set(n, fds.res_out); + zero_fd_set(n, fds.res_ex); + + ret = do_select(n, &fds, end_time); + + if (ret < 0) + goto out; + if (!ret) { + ret = -ERESTARTNOHAND; + if (signal_pending(current)) + goto out; + ret = 0; + } + + if (compat_set_fd_set(n, inp, fds.res_in) || + compat_set_fd_set(n, outp, fds.res_out) || + compat_set_fd_set(n, exp, fds.res_ex)) + ret = -EFAULT; +out: + if (bits != stack_fds) + kfree(bits); +out_nofds: + return ret; +} + +COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, + compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, + struct compat_timeval __user *, tvp) +{ + struct timespec end_time, *to = NULL; + struct compat_timeval tv; + int ret; + + if (tvp) { + if (copy_from_user(&tv, tvp, sizeof(tv))) + return -EFAULT; + + to = &end_time; + if (poll_select_set_timeout(to, + tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), + (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) + return -EINVAL; + } + + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = compat_poll_select_copy_remaining(&end_time, tvp, 1, ret); + + return ret; +} + +struct compat_sel_arg_struct { + compat_ulong_t n; + compat_uptr_t inp; + compat_uptr_t outp; + compat_uptr_t exp; + compat_uptr_t tvp; +}; + +COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) +{ + struct compat_sel_arg_struct a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), + compat_ptr(a.exp), compat_ptr(a.tvp)); +} + +static long do_compat_pselect(int n, compat_ulong_t __user *inp, + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask, + compat_size_t sigsetsize) +{ + compat_sigset_t ss32; + sigset_t ksigmask, sigsaved; + struct compat_timespec ts; + struct timespec end_time, *to = NULL; + int ret; + + if (tsp) { + if (copy_from_user(&ts, tsp, sizeof(ts))) + return -EFAULT; + + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } + + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&ksigmask, &ss32); + + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret); + + if (ret == -ERESTARTNOHAND) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return ret; +} + +COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, + compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, + struct compat_timespec __user *, tsp, void __user *, sig) +{ + compat_size_t sigsetsize = 0; + compat_uptr_t up = 0; + + if (sig) { + if (!access_ok(VERIFY_READ, sig, + sizeof(compat_uptr_t)+sizeof(compat_size_t)) || + __get_user(up, (compat_uptr_t __user *)sig) || + __get_user(sigsetsize, + (compat_size_t __user *)(sig+sizeof(up)))) + return -EFAULT; + } + return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up), + sigsetsize); +} + +COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, + unsigned int, nfds, struct compat_timespec __user *, tsp, + const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) +{ + compat_sigset_t ss32; + sigset_t ksigmask, sigsaved; + struct compat_timespec ts; + struct timespec end_time, *to = NULL; + int ret; + + if (tsp) { + if (copy_from_user(&ts, tsp, sizeof(ts))) + return -EFAULT; + + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } + + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&ksigmask, &ss32); + + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + ret = do_sys_poll(ufds, nfds, to); + + /* We can restart this syscall, usually */ + if (ret == -EINTR) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + ret = -ERESTARTNOHAND; + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret); + + return ret; +} +#endif diff --git a/fs/splice.c b/fs/splice.c index 006ba50f4ece..540c4a44756c 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -247,11 +247,6 @@ ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf) } EXPORT_SYMBOL(add_to_pipe); -void spd_release_page(struct splice_pipe_desc *spd, unsigned int i) -{ - put_page(spd->pages[i]); -} - /* * Check if we need to grow the arrays holding pages and partial page * descriptions. @@ -393,7 +388,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct iov_iter to; struct page **pages; unsigned int nr_pages; - size_t offset, dummy, copied = 0; + size_t offset, base, copied = 0; ssize_t res; int i; @@ -408,12 +403,11 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len + offset); - res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &dummy); + res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base); if (res <= 0) return -ENOMEM; - BUG_ON(dummy); - nr_pages = DIV_ROUND_UP(res, PAGE_SIZE); + nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE); vec = __vec; if (nr_pages > PIPE_DEF_BUFFERS) { @@ -1359,6 +1353,8 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov, struct fd f; long error; + if (unlikely(flags & ~SPLICE_F_ALL)) + return -EINVAL; if (unlikely(nr_segs > UIO_MAXIOV)) return -EINVAL; else if (unlikely(!nr_segs)) @@ -1409,6 +1405,9 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, if (unlikely(!len)) return 0; + if (unlikely(flags & ~SPLICE_F_ALL)) + return -EINVAL; + error = -EBADF; in = fdget(fd_in); if (in.file) { @@ -1737,6 +1736,9 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) struct fd in; int error; + if (unlikely(flags & ~SPLICE_F_ALL)) + return -EINVAL; + if (unlikely(!len)) return 0; diff --git a/fs/stat.c b/fs/stat.c index fa0be59340cc..f494b182c7c7 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -15,6 +15,7 @@ #include <linux/cred.h> #include <linux/syscalls.h> #include <linux/pagemap.h> +#include <linux/compat.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -130,9 +131,13 @@ EXPORT_SYMBOL(vfs_getattr); int vfs_statx_fd(unsigned int fd, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - struct fd f = fdget_raw(fd); + struct fd f; int error = -EBADF; + if (query_flags & ~KSTAT_QUERY_FLAGS) + return -EINVAL; + + f = fdget_raw(fd); if (f.file) { error = vfs_getattr(&f.file->f_path, stat, request_mask, query_flags); @@ -155,9 +160,6 @@ EXPORT_SYMBOL(vfs_statx_fd); * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink * at the given name from being referenced. * - * The caller must have preset stat->request_mask as for vfs_getattr(). The - * flags are also used to load up stat->query_flags. - * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_statx(int dfd, const char __user *filename, int flags, @@ -509,58 +511,50 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename, } #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */ -static inline int __put_timestamp(struct timespec *kts, - struct statx_timestamp __user *uts) +static noinline_for_stack int +cp_statx(const struct kstat *stat, struct statx __user *buffer) { - return (__put_user(kts->tv_sec, &uts->tv_sec ) || - __put_user(kts->tv_nsec, &uts->tv_nsec ) || - __put_user(0, &uts->__reserved )); -} - -/* - * Set the statx results. - */ -static long statx_set_result(struct kstat *stat, struct statx __user *buffer) -{ - uid_t uid = from_kuid_munged(current_user_ns(), stat->uid); - gid_t gid = from_kgid_munged(current_user_ns(), stat->gid); - - if (__put_user(stat->result_mask, &buffer->stx_mask ) || - __put_user(stat->mode, &buffer->stx_mode ) || - __clear_user(&buffer->__spare0, sizeof(buffer->__spare0)) || - __put_user(stat->nlink, &buffer->stx_nlink ) || - __put_user(uid, &buffer->stx_uid ) || - __put_user(gid, &buffer->stx_gid ) || - __put_user(stat->attributes, &buffer->stx_attributes ) || - __put_user(stat->blksize, &buffer->stx_blksize ) || - __put_user(MAJOR(stat->rdev), &buffer->stx_rdev_major ) || - __put_user(MINOR(stat->rdev), &buffer->stx_rdev_minor ) || - __put_user(MAJOR(stat->dev), &buffer->stx_dev_major ) || - __put_user(MINOR(stat->dev), &buffer->stx_dev_minor ) || - __put_timestamp(&stat->atime, &buffer->stx_atime ) || - __put_timestamp(&stat->btime, &buffer->stx_btime ) || - __put_timestamp(&stat->ctime, &buffer->stx_ctime ) || - __put_timestamp(&stat->mtime, &buffer->stx_mtime ) || - __put_user(stat->ino, &buffer->stx_ino ) || - __put_user(stat->size, &buffer->stx_size ) || - __put_user(stat->blocks, &buffer->stx_blocks ) || - __clear_user(&buffer->__spare1, sizeof(buffer->__spare1)) || - __clear_user(&buffer->__spare2, sizeof(buffer->__spare2))) - return -EFAULT; - - return 0; + struct statx tmp; + + memset(&tmp, 0, sizeof(tmp)); + + tmp.stx_mask = stat->result_mask; + tmp.stx_blksize = stat->blksize; + tmp.stx_attributes = stat->attributes; + tmp.stx_nlink = stat->nlink; + tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid); + tmp.stx_mode = stat->mode; + tmp.stx_ino = stat->ino; + tmp.stx_size = stat->size; + tmp.stx_blocks = stat->blocks; + tmp.stx_attributes_mask = stat->attributes_mask; + tmp.stx_atime.tv_sec = stat->atime.tv_sec; + tmp.stx_atime.tv_nsec = stat->atime.tv_nsec; + tmp.stx_btime.tv_sec = stat->btime.tv_sec; + tmp.stx_btime.tv_nsec = stat->btime.tv_nsec; + tmp.stx_ctime.tv_sec = stat->ctime.tv_sec; + tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec; + tmp.stx_mtime.tv_sec = stat->mtime.tv_sec; + tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec; + tmp.stx_rdev_major = MAJOR(stat->rdev); + tmp.stx_rdev_minor = MINOR(stat->rdev); + tmp.stx_dev_major = MAJOR(stat->dev); + tmp.stx_dev_minor = MINOR(stat->dev); + + return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } /** * sys_statx - System call to get enhanced stats * @dfd: Base directory to pathwalk from *or* fd to stat. - * @filename: File to stat *or* NULL. + * @filename: File to stat or "" with AT_EMPTY_PATH * @flags: AT_* flags to control pathwalk. * @mask: Parts of statx struct actually required. * @buffer: Result buffer. * - * Note that if filename is NULL, then it does the equivalent of fstat() using - * dfd to indicate the file of interest. + * Note that fstat() can be emulated by setting dfd to the fd of interest, + * supplying "" as the filename and setting AT_EMPTY_PATH in the flags. */ SYSCALL_DEFINE5(statx, int, dfd, const char __user *, filename, unsigned, flags, @@ -570,20 +564,103 @@ SYSCALL_DEFINE5(statx, struct kstat stat; int error; + if (mask & STATX__RESERVED) + return -EINVAL; if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE) return -EINVAL; - if (!access_ok(VERIFY_WRITE, buffer, sizeof(*buffer))) - return -EFAULT; - if (filename) - error = vfs_statx(dfd, filename, flags, &stat, mask); - else - error = vfs_statx_fd(dfd, &stat, mask, flags); + error = vfs_statx(dfd, filename, flags, &stat, mask); if (error) return error; - return statx_set_result(&stat, buffer); + + return cp_statx(&stat, buffer); +} + +#ifdef CONFIG_COMPAT +static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) +{ + struct compat_stat tmp; + + if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + return -EOVERFLOW; + + memset(&tmp, 0, sizeof(tmp)); + tmp.st_dev = old_encode_dev(stat->dev); + tmp.st_ino = stat->ino; + if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) + return -EOVERFLOW; + tmp.st_mode = stat->mode; + tmp.st_nlink = stat->nlink; + if (tmp.st_nlink != stat->nlink) + return -EOVERFLOW; + SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); + tmp.st_rdev = old_encode_dev(stat->rdev); + if ((u64) stat->size > MAX_NON_LFS) + return -EOVERFLOW; + tmp.st_size = stat->size; + tmp.st_atime = stat->atime.tv_sec; + tmp.st_atime_nsec = stat->atime.tv_nsec; + tmp.st_mtime = stat->mtime.tv_sec; + tmp.st_mtime_nsec = stat->mtime.tv_nsec; + tmp.st_ctime = stat->ctime.tv_sec; + tmp.st_ctime_nsec = stat->ctime.tv_nsec; + tmp.st_blocks = stat->blocks; + tmp.st_blksize = stat->blksize; + return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; } +COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename, + struct compat_stat __user *, statbuf) +{ + struct kstat stat; + int error; + + error = vfs_stat(filename, &stat); + if (error) + return error; + return cp_compat_stat(&stat, statbuf); +} + +COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename, + struct compat_stat __user *, statbuf) +{ + struct kstat stat; + int error; + + error = vfs_lstat(filename, &stat); + if (error) + return error; + return cp_compat_stat(&stat, statbuf); +} + +#ifndef __ARCH_WANT_STAT64 +COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd, + const char __user *, filename, + struct compat_stat __user *, statbuf, int, flag) +{ + struct kstat stat; + int error; + + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_compat_stat(&stat, statbuf); +} +#endif + +COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd, + struct compat_stat __user *, statbuf) +{ + struct kstat stat; + int error = vfs_fstat(fd, &stat); + + if (!error) + error = cp_compat_stat(&stat, statbuf); + return error; +} +#endif + /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */ void __inode_add_bytes(struct inode *inode, loff_t bytes) { diff --git a/fs/statfs.c b/fs/statfs.c index 13ae259d4879..4e4623c7a126 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -7,6 +7,7 @@ #include <linux/statfs.h> #include <linux/security.h> #include <linux/uaccess.h> +#include <linux/compat.h> #include "internal.h" static int flags_by_mnt(int mnt_flags) @@ -239,3 +240,142 @@ SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf) return copy_to_user(ubuf, &tmp, sizeof(struct ustat)) ? -EFAULT : 0; } + +#ifdef CONFIG_COMPAT +static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf) +{ + if (sizeof ubuf->f_blocks == 4) { + if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail | + kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) + return -EOVERFLOW; + /* f_files and f_ffree may be -1; it's okay + * to stuff that into 32 bits */ + if (kbuf->f_files != 0xffffffffffffffffULL + && (kbuf->f_files & 0xffffffff00000000ULL)) + return -EOVERFLOW; + if (kbuf->f_ffree != 0xffffffffffffffffULL + && (kbuf->f_ffree & 0xffffffff00000000ULL)) + return -EOVERFLOW; + } + if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) || + __put_user(kbuf->f_type, &ubuf->f_type) || + __put_user(kbuf->f_bsize, &ubuf->f_bsize) || + __put_user(kbuf->f_blocks, &ubuf->f_blocks) || + __put_user(kbuf->f_bfree, &ubuf->f_bfree) || + __put_user(kbuf->f_bavail, &ubuf->f_bavail) || + __put_user(kbuf->f_files, &ubuf->f_files) || + __put_user(kbuf->f_ffree, &ubuf->f_ffree) || + __put_user(kbuf->f_namelen, &ubuf->f_namelen) || + __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || + __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || + __put_user(kbuf->f_frsize, &ubuf->f_frsize) || + __put_user(kbuf->f_flags, &ubuf->f_flags) || + __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) + return -EFAULT; + return 0; +} + +/* + * The following statfs calls are copies of code from fs/statfs.c and + * should be checked against those from time to time + */ +COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf) +{ + struct kstatfs tmp; + int error = user_statfs(pathname, &tmp); + if (!error) + error = put_compat_statfs(buf, &tmp); + return error; +} + +COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf) +{ + struct kstatfs tmp; + int error = fd_statfs(fd, &tmp); + if (!error) + error = put_compat_statfs(buf, &tmp); + return error; +} + +static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf) +{ + if (sizeof(ubuf->f_bsize) == 4) { + if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen | + kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL) + return -EOVERFLOW; + /* f_files and f_ffree may be -1; it's okay + * to stuff that into 32 bits */ + if (kbuf->f_files != 0xffffffffffffffffULL + && (kbuf->f_files & 0xffffffff00000000ULL)) + return -EOVERFLOW; + if (kbuf->f_ffree != 0xffffffffffffffffULL + && (kbuf->f_ffree & 0xffffffff00000000ULL)) + return -EOVERFLOW; + } + if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) || + __put_user(kbuf->f_type, &ubuf->f_type) || + __put_user(kbuf->f_bsize, &ubuf->f_bsize) || + __put_user(kbuf->f_blocks, &ubuf->f_blocks) || + __put_user(kbuf->f_bfree, &ubuf->f_bfree) || + __put_user(kbuf->f_bavail, &ubuf->f_bavail) || + __put_user(kbuf->f_files, &ubuf->f_files) || + __put_user(kbuf->f_ffree, &ubuf->f_ffree) || + __put_user(kbuf->f_namelen, &ubuf->f_namelen) || + __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || + __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || + __put_user(kbuf->f_frsize, &ubuf->f_frsize) || + __put_user(kbuf->f_flags, &ubuf->f_flags) || + __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) + return -EFAULT; + return 0; +} + +COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf) +{ + struct kstatfs tmp; + int error; + + if (sz != sizeof(*buf)) + return -EINVAL; + + error = user_statfs(pathname, &tmp); + if (!error) + error = put_compat_statfs64(buf, &tmp); + return error; +} + +COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf) +{ + struct kstatfs tmp; + int error; + + if (sz != sizeof(*buf)) + return -EINVAL; + + error = fd_statfs(fd, &tmp); + if (!error) + error = put_compat_statfs64(buf, &tmp); + return error; +} + +/* + * This is a copy of sys_ustat, just dealing with a structure layout. + * Given how simple this syscall is that apporach is more maintainable + * than the various conversion hacks. + */ +COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u) +{ + struct compat_ustat tmp; + struct kstatfs sbuf; + int err = vfs_ustat(new_decode_dev(dev), &sbuf); + if (err) + return err; + + memset(&tmp, 0, sizeof(struct compat_ustat)); + tmp.f_tfree = sbuf.f_bfree; + tmp.f_tinode = sbuf.f_ffree; + if (copy_to_user(u, &tmp, sizeof(struct compat_ustat))) + return -EFAULT; + return 0; +} +#endif diff --git a/fs/super.c b/fs/super.c index b8b6a086c03b..adb0c0de428c 100644 --- a/fs/super.c +++ b/fs/super.c @@ -446,6 +446,10 @@ void generic_shutdown_super(struct super_block *sb) hlist_del_init(&sb->s_instances); spin_unlock(&sb_lock); up_write(&sb->s_umount); + if (sb->s_bdi != &noop_backing_dev_info) { + bdi_put(sb->s_bdi); + sb->s_bdi = &noop_backing_dev_info; + } } EXPORT_SYMBOL(generic_shutdown_super); @@ -1049,12 +1053,8 @@ static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; s->s_dev = s->s_bdev->bd_dev; + s->s_bdi = bdi_get(s->s_bdev->bd_bdi); - /* - * We set the bdi here to the queue backing, file systems can - * overwrite this in ->fill_super() - */ - s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info; return 0; } @@ -1256,6 +1256,49 @@ out: } /* + * Setup private BDI for given superblock. It gets automatically cleaned up + * in generic_shutdown_super(). + */ +int super_setup_bdi_name(struct super_block *sb, char *fmt, ...) +{ + struct backing_dev_info *bdi; + int err; + va_list args; + + bdi = bdi_alloc(GFP_KERNEL); + if (!bdi) + return -ENOMEM; + + bdi->name = sb->s_type->name; + + va_start(args, fmt); + err = bdi_register_va(bdi, fmt, args); + va_end(args); + if (err) { + bdi_put(bdi); + return err; + } + WARN_ON(sb->s_bdi != &noop_backing_dev_info); + sb->s_bdi = bdi; + + return 0; +} +EXPORT_SYMBOL(super_setup_bdi_name); + +/* + * Setup private BDI for given superblock. I gets automatically cleaned up + * in generic_shutdown_super(). + */ +int super_setup_bdi(struct super_block *sb) +{ + static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); + + return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name, + atomic_long_inc_return(&bdi_seq)); +} +EXPORT_SYMBOL(super_setup_bdi); + +/* * This is an internal function, please use sb_end_{write,pagefault,intwrite} * instead. */ diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index b803213d1307..39c75a86c67f 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -108,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; - size_t len; + ssize_t len; /* * If buf != of->prealloc_buf, we don't know how @@ -117,13 +117,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, if (WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; len = ops->show(kobj, of->kn->priv, buf); + if (len < 0) + return len; if (pos) { if (len <= pos) return 0; len -= pos; memmove(buf, buf + pos, len); } - return min(count, len); + return min_t(ssize_t, count, len); } /* kernfs write callback for regular sysfs files */ diff --git a/fs/timerfd.c b/fs/timerfd.c index 384fa759a563..c543cdb5f8ed 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -400,9 +400,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) clockid != CLOCK_BOOTTIME_ALARM)) return -EINVAL; - if (!capable(CAP_WAKE_ALARM) && - (clockid == CLOCK_REALTIME_ALARM || - clockid == CLOCK_BOOTTIME_ALARM)) + if ((clockid == CLOCK_REALTIME_ALARM || + clockid == CLOCK_BOOTTIME_ALARM) && + !capable(CAP_WAKE_ALARM)) return -EPERM; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -449,7 +449,7 @@ static int do_timerfd_settime(int ufd, int flags, return ret; ctx = f.file->private_data; - if (!capable(CAP_WAKE_ALARM) && isalarm(ctx)) { + if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) { fdput(f); return -EPERM; } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 1e712a364680..718b749fa11a 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -32,6 +32,7 @@ #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/random.h> +#include <linux/ctype.h> #include "ubifs.h" static DEFINE_SPINLOCK(dbg_lock); @@ -286,8 +287,10 @@ void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode) break; } - pr_err("\t%d: %s (%s)\n", - count++, dent->name, get_dent_type(dent->type)); + pr_err("\t%d: inode %llu, type %s, len %d\n", + count++, (unsigned long long) le64_to_cpu(dent->inum), + get_dent_type(dent->type), + le16_to_cpu(dent->nlen)); fname_name(&nm) = dent->name; fname_len(&nm) = le16_to_cpu(dent->nlen); @@ -464,7 +467,8 @@ void ubifs_dump_node(const struct ubifs_info *c, const void *node) pr_err("(bad name length, not printing, bad or corrupted node)"); else { for (i = 0; i < nlen && dent->name[i]; i++) - pr_cont("%c", dent->name[i]); + pr_cont("%c", isprint(dent->name[i]) ? + dent->name[i] : '?'); } pr_cont("\n"); diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 30825d882aa9..b777bddaa1dd 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -606,8 +606,8 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) } while (1) { - dbg_gen("feed '%s', ino %llu, new f_pos %#x", - dent->name, (unsigned long long)le64_to_cpu(dent->inum), + dbg_gen("ino %llu, new f_pos %#x", + (unsigned long long)le64_to_cpu(dent->inum), key_hash_flash(c, &dent->key)); ubifs_assert(le64_to_cpu(dent->ch.sqnum) > ubifs_inode(dir)->creat_sqnum); @@ -748,6 +748,11 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, goto out_fname; lock_2_inodes(dir, inode); + + /* Handle O_TMPFILE corner case, it is allowed to link a O_TMPFILE. */ + if (inode->i_nlink == 0) + ubifs_delete_orphan(c, inode->i_ino); + inc_nlink(inode); ihold(inode); inode->i_ctime = ubifs_current_time(inode); @@ -768,6 +773,8 @@ out_cancel: dir->i_size -= sz_change; dir_ui->ui_size = dir->i_size; drop_nlink(inode); + if (inode->i_nlink == 0) + ubifs_add_orphan(c, inode->i_ino); unlock_2_inodes(dir, inode); ubifs_release_budget(c, &req); iput(inode); @@ -1068,8 +1075,10 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, } err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); - if (err) + if (err) { + kfree(dev); goto out_budg; + } sz_change = CALC_DENT_SIZE(fname_len(&nm)); @@ -1316,9 +1325,6 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, unsigned int uninitialized_var(saved_nlink); struct fscrypt_name old_nm, new_nm; - if (flags & ~RENAME_NOREPLACE) - return -EINVAL; - /* * Budget request settings: deletion direntry, new direntry, removing * the old inode, and changing old and new parent directory inodes. diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index b73811bd7676..cf4cc99b75b5 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1827,7 +1827,6 @@ static void ubifs_put_super(struct super_block *sb) } ubifs_umount(c); - bdi_destroy(&c->bdi); ubi_close_volume(c->ubi); mutex_unlock(&c->umount_mutex); } @@ -2019,29 +2018,25 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) goto out; } + err = ubifs_parse_options(c, data, 0); + if (err) + goto out_close; + /* * UBIFS provides 'backing_dev_info' in order to disable read-ahead. For * UBIFS, I/O is not deferred, it is done immediately in readpage, * which means the user would have to wait not just for their own I/O * but the read-ahead I/O as well i.e. completely pointless. * - * Read-ahead will be disabled because @c->bdi.ra_pages is 0. + * Read-ahead will be disabled because @sb->s_bdi->ra_pages is 0. Also + * @sb->s_bdi->capabilities are initialized to 0 so there won't be any + * writeback happening. */ - c->bdi.name = "ubifs", - c->bdi.capabilities = 0; - err = bdi_init(&c->bdi); + err = super_setup_bdi_name(sb, "ubifs_%d_%d", c->vi.ubi_num, + c->vi.vol_id); if (err) goto out_close; - err = bdi_register(&c->bdi, NULL, "ubifs_%d_%d", - c->vi.ubi_num, c->vi.vol_id); - if (err) - goto out_bdi; - - err = ubifs_parse_options(c, data, 0); - if (err) - goto out_bdi; - sb->s_bdi = &c->bdi; sb->s_fs_info = c; sb->s_magic = UBIFS_SUPER_MAGIC; sb->s_blocksize = UBIFS_BLOCK_SIZE; @@ -2080,8 +2075,6 @@ out_umount: ubifs_umount(c); out_unlock: mutex_unlock(&c->umount_mutex); -out_bdi: - bdi_destroy(&c->bdi); out_close: ubi_close_volume(c->ubi); out: diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 4d57e488038e..4da10a6d702a 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -972,7 +972,6 @@ struct ubifs_debug_info; * struct ubifs_info - UBIFS file-system description data structure * (per-superblock). * @vfs_sb: VFS @struct super_block object - * @bdi: backing device info object to make VFS happy and disable read-ahead * * @highest_inum: highest used inode number * @max_sqnum: current global sequence number @@ -1220,7 +1219,6 @@ struct ubifs_debug_info; */ struct ubifs_info { struct super_block *vfs_sb; - struct backing_dev_info bdi; ino_t highest_inum; unsigned long long max_sqnum; @@ -1461,7 +1459,6 @@ extern const struct inode_operations ubifs_file_inode_operations; extern const struct file_operations ubifs_dir_operations; extern const struct inode_operations ubifs_dir_inode_operations; extern const struct inode_operations ubifs_symlink_inode_operations; -extern struct backing_dev_info ubifs_backing_dev_info; extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT]; /* io.c */ diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 973607df579d..f7555fc25877 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -138,8 +138,6 @@ out: * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to the userfaultfd context. - * - * Returns: In case of success, returns not zero. */ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx) { @@ -267,6 +265,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, { struct mm_struct *mm = ctx->mm; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; @@ -277,7 +276,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto out; + pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); @@ -490,7 +492,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) * in such case. */ down_read(&mm->mmap_sem); - ret = 0; + ret = VM_FAULT_NOPAGE; } } @@ -527,10 +529,11 @@ out: return ret; } -static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, - struct userfaultfd_wait_queue *ewq) +static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, + struct userfaultfd_wait_queue *ewq) { - int ret = 0; + if (WARN_ON_ONCE(current->flags & PF_EXITING)) + goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); @@ -547,8 +550,16 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, break; if (ACCESS_ONCE(ctx->released) || fatal_signal_pending(current)) { - ret = -1; __remove_wait_queue(&ctx->event_wqh, &ewq->wq); + if (ewq->msg.event == UFFD_EVENT_FORK) { + struct userfaultfd_ctx *new; + + new = (struct userfaultfd_ctx *) + (unsigned long) + ewq->msg.arg.reserved.reserved1; + + userfaultfd_ctx_put(new); + } break; } @@ -566,9 +577,8 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, * ctx may go away after this if the userfault pseudo fd is * already released. */ - +out: userfaultfd_ctx_put(ctx); - return ret; } static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, @@ -626,7 +636,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) return 0; } -static int dup_fctx(struct userfaultfd_fork_ctx *fctx) +static void dup_fctx(struct userfaultfd_fork_ctx *fctx) { struct userfaultfd_ctx *ctx = fctx->orig; struct userfaultfd_wait_queue ewq; @@ -636,17 +646,15 @@ static int dup_fctx(struct userfaultfd_fork_ctx *fctx) ewq.msg.event = UFFD_EVENT_FORK; ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; - return userfaultfd_event_wait_completion(ctx, &ewq); + userfaultfd_event_wait_completion(ctx, &ewq); } void dup_userfaultfd_complete(struct list_head *fcs) { - int ret = 0; struct userfaultfd_fork_ctx *fctx, *n; list_for_each_entry_safe(fctx, n, fcs, list) { - if (!ret) - ret = dup_fctx(fctx); + dup_fctx(fctx); list_del(&fctx->list); kfree(fctx); } @@ -689,8 +697,7 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, userfaultfd_event_wait_completion(ctx, &ewq); } -void userfaultfd_remove(struct vm_area_struct *vma, - struct vm_area_struct **prev, +bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; @@ -699,13 +706,11 @@ void userfaultfd_remove(struct vm_area_struct *vma, ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) - return; + return true; userfaultfd_ctx_get(ctx); up_read(&mm->mmap_sem); - *prev = NULL; /* We wait for ACK w/o the mmap semaphore */ - msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; @@ -714,7 +719,7 @@ void userfaultfd_remove(struct vm_area_struct *vma, userfaultfd_event_wait_completion(ctx, &ewq); - down_read(&mm->mmap_sem); + return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, @@ -775,34 +780,6 @@ void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) } } -void userfaultfd_exit(struct mm_struct *mm) -{ - struct vm_area_struct *vma = mm->mmap; - - /* - * We can do the vma walk without locking because the caller - * (exit_mm) knows it now has exclusive access - */ - while (vma) { - struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; - - if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) { - struct userfaultfd_wait_queue ewq; - - userfaultfd_ctx_get(ctx); - - msg_init(&ewq.msg); - ewq.msg.event = UFFD_EVENT_EXIT; - - userfaultfd_event_wait_completion(ctx, &ewq); - - ctx->features &= ~UFFD_FEATURE_EVENT_EXIT; - } - - vma = vma->vm_next; - } -} - static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; @@ -1779,7 +1756,7 @@ static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) * protocols: aa:... bb:... */ seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n", - pending, total, UFFD_API, UFFD_API_FEATURES, + pending, total, UFFD_API, ctx->features, UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS); } #endif diff --git a/fs/utimes.c b/fs/utimes.c index 32b15b3f6629..6571d8c848a0 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -1,14 +1,10 @@ -#include <linux/compiler.h> #include <linux/file.h> -#include <linux/fs.h> -#include <linux/linkage.h> #include <linux/mount.h> #include <linux/namei.h> -#include <linux/sched.h> -#include <linux/stat.h> #include <linux/utime.h> #include <linux/syscalls.h> #include <linux/uaccess.h> +#include <linux/compat.h> #include <asm/unistd.h> #ifdef __ARCH_WANT_SYS_UTIME @@ -219,3 +215,63 @@ SYSCALL_DEFINE2(utimes, char __user *, filename, { return sys_futimesat(AT_FDCWD, filename, utimes); } + +#ifdef CONFIG_COMPAT +/* + * Not all architectures have sys_utime, so implement this in terms + * of sys_utimes. + */ +COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, + struct compat_utimbuf __user *, t) +{ + struct timespec tv[2]; + + if (t) { + if (get_user(tv[0].tv_sec, &t->actime) || + get_user(tv[1].tv_sec, &t->modtime)) + return -EFAULT; + tv[0].tv_nsec = 0; + tv[1].tv_nsec = 0; + } + return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0); +} + +COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags) +{ + struct timespec tv[2]; + + if (t) { + if (compat_get_timespec(&tv[0], &t[0]) || + compat_get_timespec(&tv[1], &t[1])) + return -EFAULT; + + if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT) + return 0; + } + return do_utimes(dfd, filename, t ? tv : NULL, flags); +} + +COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t) +{ + struct timespec tv[2]; + + if (t) { + if (get_user(tv[0].tv_sec, &t[0].tv_sec) || + get_user(tv[0].tv_nsec, &t[0].tv_usec) || + get_user(tv[1].tv_sec, &t[1].tv_sec) || + get_user(tv[1].tv_nsec, &t[1].tv_usec)) + return -EFAULT; + if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 || + tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0) + return -EINVAL; + tv[0].tv_nsec *= 1000; + tv[1].tv_nsec *= 1000; + } + return do_utimes(dfd, filename, t ? tv : NULL, 0); +} + +COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t) +{ + return compat_sys_futimesat(AT_FDCWD, filename, t); +} +#endif diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 2dfdc62f795e..70a5b55e0870 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -25,24 +25,6 @@ #include "kmem.h" #include "xfs_message.h" -/* - * Greedy allocation. May fail and may return vmalloced memory. - */ -void * -kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize) -{ - void *ptr; - size_t kmsize = maxsize; - - while (!(ptr = vzalloc(kmsize))) { - if ((kmsize >>= 1) <= minsize) - kmsize = minsize; - } - if (ptr) - *size = kmsize; - return ptr; -} - void * kmem_alloc(size_t size, xfs_km_flags_t flags) { diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index 689f746224e7..f0fc84fcaac2 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -69,8 +69,6 @@ static inline void kmem_free(const void *ptr) } -extern void *kmem_zalloc_greedy(size_t *, size_t, size_t); - static inline void * kmem_zalloc(size_t size, xfs_km_flags_t flags) { diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index a9c66d47757a..9bd104f32908 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -763,8 +763,8 @@ xfs_bmap_extents_to_btree( args.type = XFS_ALLOCTYPE_START_BNO; args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino); } else if (dfops->dop_low) { -try_another_ag: args.type = XFS_ALLOCTYPE_START_BNO; +try_another_ag: args.fsbno = *firstblock; } else { args.type = XFS_ALLOCTYPE_NEAR_BNO; @@ -790,13 +790,17 @@ try_another_ag: if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) && args.fsbno == NULLFSBLOCK && args.type == XFS_ALLOCTYPE_NEAR_BNO) { - dfops->dop_low = true; + args.type = XFS_ALLOCTYPE_FIRST_AG; goto try_another_ag; } + if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { + xfs_iroot_realloc(ip, -1, whichfork); + xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); + return -ENOSPC; + } /* * Allocation can't fail, the space was reserved. */ - ASSERT(args.fsbno != NULLFSBLOCK); ASSERT(*firstblock == NULLFSBLOCK || args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock)); *firstblock = cur->bc_private.b.firstblock = args.fsbno; @@ -4150,6 +4154,19 @@ xfs_bmapi_read( return 0; } +/* + * Add a delayed allocation extent to an inode. Blocks are reserved from the + * global pool and the extent inserted into the inode in-core extent tree. + * + * On entry, got refers to the first extent beyond the offset of the extent to + * allocate or eof is specified if no such extent exists. On return, got refers + * to the extent record that was inserted to the inode fork. + * + * Note that the allocated extent may have been merged with contiguous extents + * during insertion into the inode fork. Thus, got does not reflect the current + * state of the inode fork on return. If necessary, the caller can use lastx to + * look up the updated record in the inode fork. + */ int xfs_bmapi_reserve_delalloc( struct xfs_inode *ip, @@ -4236,13 +4253,8 @@ xfs_bmapi_reserve_delalloc( got->br_startblock = nullstartblock(indlen); got->br_blockcount = alen; got->br_state = XFS_EXT_NORM; - xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got); - /* - * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay - * might have merged it into one of the neighbouring ones. - */ - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got); + xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got); /* * Tag the inode if blocks were preallocated. Note that COW fork @@ -4254,10 +4266,6 @@ xfs_bmapi_reserve_delalloc( if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len)) xfs_inode_set_cowblocks_tag(ip); - ASSERT(got->br_startoff <= aoff); - ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen); - ASSERT(isnullstartblock(got->br_startblock)); - ASSERT(got->br_state == XFS_EXT_NORM); return 0; out_unreserve_blocks: diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index f93072b58a58..fd55db479385 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -447,8 +447,8 @@ xfs_bmbt_alloc_block( if (args.fsbno == NULLFSBLOCK) { args.fsbno = be64_to_cpu(start->l); -try_another_ag: args.type = XFS_ALLOCTYPE_START_BNO; +try_another_ag: /* * Make sure there is sufficient room left in the AG to * complete a full tree split for an extent insert. If @@ -488,8 +488,8 @@ try_another_ag: if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) && args.fsbno == NULLFSBLOCK && args.type == XFS_ALLOCTYPE_NEAR_BNO) { - cur->bc_private.b.dfops->dop_low = true; args.fsbno = cur->bc_private.b.firstblock; + args.type = XFS_ALLOCTYPE_FIRST_AG; goto try_another_ag; } @@ -506,7 +506,7 @@ try_another_ag: goto error0; cur->bc_private.b.dfops->dop_low = true; } - if (args.fsbno == NULLFSBLOCK) { + if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); *stat = 0; return 0; diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h index d04547fcf274..39f8604f764e 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -125,6 +125,7 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino); extern int xfs_dir2_sf_lookup(struct xfs_da_args *args); extern int xfs_dir2_sf_removename(struct xfs_da_args *args); extern int xfs_dir2_sf_replace(struct xfs_da_args *args); +extern int xfs_dir2_sf_verify(struct xfs_inode *ip); /* xfs_dir2_readdir.c */ extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx, diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index c6809ff41197..e84af093b2ab 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -629,6 +629,112 @@ xfs_dir2_sf_check( } #endif /* DEBUG */ +/* Verify the consistency of an inline directory. */ +int +xfs_dir2_sf_verify( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_dir2_sf_hdr *sfp; + struct xfs_dir2_sf_entry *sfep; + struct xfs_dir2_sf_entry *next_sfep; + char *endp; + const struct xfs_dir_ops *dops; + struct xfs_ifork *ifp; + xfs_ino_t ino; + int i; + int i8count; + int offset; + int size; + int error; + __uint8_t filetype; + + ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL); + /* + * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops, + * so we can only trust the mountpoint to have the right pointer. + */ + dops = xfs_dir_get_ops(mp, NULL); + + ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data; + size = ifp->if_bytes; + + /* + * Give up if the directory is way too short. + */ + if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) || + size < xfs_dir2_sf_hdr_size(sfp->i8count)) + return -EFSCORRUPTED; + + endp = (char *)sfp + size; + + /* Check .. entry */ + ino = dops->sf_get_parent_ino(sfp); + i8count = ino > XFS_DIR2_MAX_SHORT_INUM; + error = xfs_dir_ino_validate(mp, ino); + if (error) + return error; + offset = dops->data_first_offset; + + /* Check all reported entries */ + sfep = xfs_dir2_sf_firstentry(sfp); + for (i = 0; i < sfp->count; i++) { + /* + * struct xfs_dir2_sf_entry has a variable length. + * Check the fixed-offset parts of the structure are + * within the data buffer. + */ + if (((char *)sfep + sizeof(*sfep)) >= endp) + return -EFSCORRUPTED; + + /* Don't allow names with known bad length. */ + if (sfep->namelen == 0) + return -EFSCORRUPTED; + + /* + * Check that the variable-length part of the structure is + * within the data buffer. The next entry starts after the + * name component, so nextentry is an acceptable test. + */ + next_sfep = dops->sf_nextentry(sfp, sfep); + if (endp < (char *)next_sfep) + return -EFSCORRUPTED; + + /* Check that the offsets always increase. */ + if (xfs_dir2_sf_get_offset(sfep) < offset) + return -EFSCORRUPTED; + + /* Check the inode number. */ + ino = dops->sf_get_ino(sfp, sfep); + i8count += ino > XFS_DIR2_MAX_SHORT_INUM; + error = xfs_dir_ino_validate(mp, ino); + if (error) + return error; + + /* Check the file type. */ + filetype = dops->sf_get_ftype(sfep); + if (filetype >= XFS_DIR3_FT_MAX) + return -EFSCORRUPTED; + + offset = xfs_dir2_sf_get_offset(sfep) + + dops->data_entsize(sfep->namelen); + + sfep = next_sfep; + } + if (i8count != sfp->i8count) + return -EFSCORRUPTED; + if ((void *)sfep != (void *)endp) + return -EFSCORRUPTED; + + /* Make sure this whole thing ought to be in local format. */ + if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + + (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize) + return -EFSCORRUPTED; + + return 0; +} + /* * Create a new (shortform) directory. */ diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 25c1e078aef6..8a37efe04de3 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -33,6 +33,8 @@ #include "xfs_trace.h" #include "xfs_attr_sf.h" #include "xfs_da_format.h" +#include "xfs_da_btree.h" +#include "xfs_dir2_priv.h" kmem_zone_t *xfs_ifork_zone; @@ -210,6 +212,16 @@ xfs_iformat_fork( if (error) return error; + /* Check inline dir contents. */ + if (S_ISDIR(VFS_I(ip)->i_mode) && + dip->di_format == XFS_DINODE_FMT_LOCAL) { + error = xfs_dir2_sf_verify(ip); + if (error) { + xfs_idestroy_fork(ip, XFS_DATA_FORK); + return error; + } + } + if (xfs_is_reflink_inode(ip)) { ASSERT(ip->i_cowfp == NULL); xfs_ifork_init_cow(ip); @@ -320,7 +332,6 @@ xfs_iformat_local( int whichfork, int size) { - /* * If the size is unreasonable, then something * is wrong and we just bail out rather than crash in diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index bf65a9ea8642..61494295d92f 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -274,54 +274,49 @@ xfs_end_io( struct xfs_ioend *ioend = container_of(work, struct xfs_ioend, io_work); struct xfs_inode *ip = XFS_I(ioend->io_inode); + xfs_off_t offset = ioend->io_offset; + size_t size = ioend->io_size; int error = ioend->io_bio->bi_error; /* - * Set an error if the mount has shut down and proceed with end I/O - * processing so it can perform whatever cleanups are necessary. + * Just clean up the in-memory strutures if the fs has been shut down. */ - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { error = -EIO; + goto done; + } /* - * For a CoW extent, we need to move the mapping from the CoW fork - * to the data fork. If instead an error happened, just dump the - * new blocks. + * Clean up any COW blocks on an I/O error. */ - if (ioend->io_type == XFS_IO_COW) { - if (error) - goto done; - if (ioend->io_bio->bi_error) { - error = xfs_reflink_cancel_cow_range(ip, - ioend->io_offset, ioend->io_size); - goto done; + if (unlikely(error)) { + switch (ioend->io_type) { + case XFS_IO_COW: + xfs_reflink_cancel_cow_range(ip, offset, size, true); + break; } - error = xfs_reflink_end_cow(ip, ioend->io_offset, - ioend->io_size); - if (error) - goto done; + + goto done; } /* - * For unwritten extents we need to issue transactions to convert a - * range to normal written extens after the data I/O has finished. - * Detecting and handling completion IO errors is done individually - * for each case as different cleanup operations need to be performed - * on error. + * Success: commit the COW or unwritten blocks if needed. */ - if (ioend->io_type == XFS_IO_UNWRITTEN) { - if (error) - goto done; - error = xfs_iomap_write_unwritten(ip, ioend->io_offset, - ioend->io_size); - } else if (ioend->io_append_trans) { - error = xfs_setfilesize_ioend(ioend, error); - } else { - ASSERT(!xfs_ioend_is_append(ioend) || - ioend->io_type == XFS_IO_COW); + switch (ioend->io_type) { + case XFS_IO_COW: + error = xfs_reflink_end_cow(ip, offset, size); + break; + case XFS_IO_UNWRITTEN: + error = xfs_iomap_write_unwritten(ip, offset, size); + break; + default: + ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); + break; } done: + if (ioend->io_append_trans) + error = xfs_setfilesize_ioend(ioend, error); xfs_destroy_ioend(ioend, error); } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 8b75dcea5966..8795e9cd867c 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -81,7 +81,7 @@ xfs_zero_extent( return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)), block << (mp->m_super->s_blocksize_bits - 9), count_fsb << (mp->m_super->s_blocksize_bits - 9), - GFP_NOFS, true); + GFP_NOFS, 0); } int @@ -1311,8 +1311,16 @@ xfs_free_file_space( /* * Now that we've unmap all full blocks we'll have to zero out any * partial block at the beginning and/or end. xfs_zero_range is - * smart enough to skip any holes, including those we just created. + * smart enough to skip any holes, including those we just created, + * but we must take care not to zero beyond EOF and enlarge i_size. */ + + if (offset >= XFS_ISIZE(ip)) + return 0; + + if (offset + len > XFS_ISIZE(ip)) + len = XFS_ISIZE(ip) - offset; + return xfs_zero_range(ip, offset, len, NULL); } diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 003a99b83bd8..ad9396e516f6 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -71,22 +71,11 @@ xfs_dir2_sf_getdents( struct xfs_da_geometry *geo = args->geo; ASSERT(dp->i_df.if_flags & XFS_IFINLINE); - /* - * Give up if the directory is way too short. - */ - if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) { - ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount)); - return -EIO; - } - ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; - if (dp->i_d.di_size < xfs_dir2_sf_hdr_size(sfp->i8count)) - return -EFSCORRUPTED; - /* * If the block number in the offset is out of range, we're done. */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 7234b9748c36..3531f8f72fa5 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1608,7 +1608,7 @@ xfs_inode_free_cowblocks( xfs_ilock(ip, XFS_IOLOCK_EXCL); xfs_ilock(ip, XFS_MMAPLOCK_EXCL); - ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF); + ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); xfs_iunlock(ip, XFS_IOLOCK_EXCL); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index edfa6a55b064..7605d8396596 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -50,6 +50,7 @@ #include "xfs_log.h" #include "xfs_bmap_btree.h" #include "xfs_reflink.h" +#include "xfs_dir2_priv.h" kmem_zone_t *xfs_inode_zone; @@ -1615,7 +1616,7 @@ xfs_itruncate_extents( /* Remove all pending CoW reservations. */ error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block, - last_block); + last_block, true); if (error) goto out; @@ -3546,6 +3547,12 @@ xfs_iflush_int( if (ip->i_d.di_version < 3) ip->i_d.di_flushiter++; + /* Check the inline directory data. */ + if (S_ISDIR(VFS_I(ip)->i_mode) && + ip->i_d.di_format == XFS_DINODE_FMT_LOCAL && + xfs_dir2_sf_verify(ip)) + goto corrupt_out; + /* * Copy the dirty parts of the inode into the on-disk inode. We always * copy out the core of the inode, because if the inode is dirty at all diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 41662fb14e87..288ee5b840d7 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -630,6 +630,11 @@ retry: goto out_unlock; } + /* + * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch + * them out if the write happens to fail. + */ + iomap->flags = IOMAP_F_NEW; trace_xfs_iomap_alloc(ip, offset, count, 0, &got); done: if (isnullstartblock(got.br_startblock)) @@ -1071,16 +1076,22 @@ xfs_file_iomap_end_delalloc( struct xfs_inode *ip, loff_t offset, loff_t length, - ssize_t written) + ssize_t written, + struct iomap *iomap) { struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t start_fsb; xfs_fileoff_t end_fsb; int error = 0; - /* behave as if the write failed if drop writes is enabled */ - if (xfs_mp_drop_writes(mp)) + /* + * Behave as if the write failed if drop writes is enabled. Set the NEW + * flag to force delalloc cleanup. + */ + if (xfs_mp_drop_writes(mp)) { + iomap->flags |= IOMAP_F_NEW; written = 0; + } /* * start_fsb refers to the first unused block after a short write. If @@ -1094,14 +1105,14 @@ xfs_file_iomap_end_delalloc( end_fsb = XFS_B_TO_FSB(mp, offset + length); /* - * Trim back delalloc blocks if we didn't manage to write the whole - * range reserved. + * Trim delalloc blocks if they were allocated by this write and we + * didn't manage to write the whole range. * * We don't need to care about racing delalloc as we hold i_mutex * across the reserve/allocate/unreserve calls. If there are delalloc * blocks in the range, they are ours. */ - if (start_fsb < end_fsb) { + if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) { truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb), XFS_FSB_TO_B(mp, end_fsb) - 1); @@ -1131,7 +1142,7 @@ xfs_file_iomap_end( { if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC) return xfs_file_iomap_end_delalloc(XFS_I(inode), offset, - length, written); + length, written, iomap); return 0; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 229cc6a6d8ef..ebfc13350f9a 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -516,6 +516,20 @@ xfs_vn_getattr( stat->blocks = XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks); + if (ip->i_d.di_version == 3) { + if (request_mask & STATX_BTIME) { + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = ip->i_d.di_crtime.t_sec; + stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec; + } + } + + if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (ip->i_d.di_flags & XFS_DIFLAG_APPEND) + stat->attributes |= STATX_ATTR_APPEND; + if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP) + stat->attributes |= STATX_ATTR_NODUMP; switch (inode->i_mode & S_IFMT) { case S_IFBLK: diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 66e881790c17..26d67ce3c18d 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -361,7 +361,6 @@ xfs_bulkstat( xfs_agino_t agino; /* inode # in allocation group */ xfs_agnumber_t agno; /* allocation group number */ xfs_btree_cur_t *cur; /* btree cursor for ialloc btree */ - size_t irbsize; /* size of irec buffer in bytes */ xfs_inobt_rec_incore_t *irbuf; /* start of irec buffer */ int nirbuf; /* size of irbuf */ int ubcount; /* size of user's buffer */ @@ -388,11 +387,10 @@ xfs_bulkstat( *ubcountp = 0; *done = 0; - irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4); + irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP); if (!irbuf) return -ENOMEM; - - nirbuf = irbsize / sizeof(*irbuf); + nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf); /* * Loop over the allocation groups, starting from the last @@ -585,7 +583,7 @@ xfs_inumbers( return error; bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer))); - buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP); + buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP); do { struct xfs_inobt_rec_incore r; int stat; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 450bde68bb75..688ebff1f663 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -513,8 +513,7 @@ STATIC void xfs_set_inoalignment(xfs_mount_t *mp) { if (xfs_sb_version_hasalign(&mp->m_sb) && - mp->m_sb.sb_inoalignmt >= - XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)) + mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp)) mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1; else mp->m_inoalign_mask = 0; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index da6d08fb359c..4a84c5ea266d 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -548,14 +548,18 @@ xfs_reflink_trim_irec_to_next_cow( } /* - * Cancel all pending CoW reservations for some block range of an inode. + * Cancel CoW reservations for some block range of an inode. + * + * If cancel_real is true this function cancels all COW fork extents for the + * inode; if cancel_real is false, real extents are not cleared. */ int xfs_reflink_cancel_cow_blocks( struct xfs_inode *ip, struct xfs_trans **tpp, xfs_fileoff_t offset_fsb, - xfs_fileoff_t end_fsb) + xfs_fileoff_t end_fsb, + bool cancel_real) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); struct xfs_bmbt_irec got, del; @@ -579,7 +583,7 @@ xfs_reflink_cancel_cow_blocks( &idx, &got, &del); if (error) break; - } else { + } else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) { xfs_trans_ijoin(*tpp, ip, 0); xfs_defer_init(&dfops, &firstfsb); @@ -621,13 +625,17 @@ xfs_reflink_cancel_cow_blocks( } /* - * Cancel all pending CoW reservations for some byte range of an inode. + * Cancel CoW reservations for some byte range of an inode. + * + * If cancel_real is true this function cancels all COW fork extents for the + * inode; if cancel_real is false, real extents are not cleared. */ int xfs_reflink_cancel_cow_range( struct xfs_inode *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool cancel_real) { struct xfs_trans *tp; xfs_fileoff_t offset_fsb; @@ -653,7 +661,8 @@ xfs_reflink_cancel_cow_range( xfs_trans_ijoin(tp, ip, 0); /* Scrape out the old CoW reservations */ - error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb); + error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb, + cancel_real); if (error) goto out_cancel; @@ -1450,7 +1459,7 @@ next: * We didn't find any shared blocks so turn off the reflink flag. * First, get rid of any leftover CoW mappings. */ - error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF); + error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true); if (error) return error; diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 33ac9b8db683..d29a7967f029 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -39,9 +39,9 @@ extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip, extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip, struct xfs_trans **tpp, xfs_fileoff_t offset_fsb, - xfs_fileoff_t end_fsb); + xfs_fileoff_t end_fsb, bool cancel_real); extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset, - xfs_off_t count); + xfs_off_t count, bool cancel_real); extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 890862f2447c..685c042a120f 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -953,7 +953,7 @@ xfs_fs_destroy_inode( XFS_STATS_INC(ip->i_mount, vn_remove); if (xfs_is_reflink_inode(ip)) { - error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF); + error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true); if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount)) xfs_warn(ip->i_mount, "Error %d while evicting CoW blocks for inode %llu.", |