diff options
author | Al Viro <viro@zeniv.linux.org.uk> | 2017-04-03 01:06:59 -0400 |
---|---|---|
committer | Al Viro <viro@zeniv.linux.org.uk> | 2017-04-03 01:06:59 -0400 |
commit | a8e28440016bfb23bec266c4c66eacca6ea2d48b (patch) | |
tree | 27d528294f7886c434c8072a034d211acc06d077 /fs | |
parent | 2b5efc089769cd2aa583880d29416d00e7441f39 (diff) | |
parent | 3209f68b3ca4667069923a325c88b21131bfdf9f (diff) | |
download | op-kernel-dev-a8e28440016bfb23bec266c4c66eacca6ea2d48b.zip op-kernel-dev-a8e28440016bfb23bec266c4c66eacca6ea2d48b.tar.gz |
Merge branch 'work.statx' into for-next
Diffstat (limited to 'fs')
89 files changed, 1132 insertions, 841 deletions
diff --git a/fs/afs/callback.c b/fs/afs/callback.c index b29447e..25d404d 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 2edbdcb..3062cce 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 ba7b71f..0d5b850 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 ac8e766..19f76ae 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 1e4897a..aae55dd 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 5dfa569..a690136 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 */ @@ -374,8 +377,8 @@ 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 +560,6 @@ 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 +720,7 @@ 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 91ea1aa..100b207 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 d4fb0af..bd3b65c 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 419ef05..8f76b13 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; + 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; + goto save_error; case -ENODATA: case -EBADMSG: case -EMSGSIZE: @@ -471,7 +494,7 @@ static void afs_deliver_to_call(struct afs_call *call) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(afs_socket, call->rxcall, abort_code, EBADMSG, "KUM"); - goto do_abort; + 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); diff --git a/fs/afs/security.c b/fs/afs/security.c index 8d01042..ecb86a6 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 d4066ab..c001b1f 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/vlocation.c b/fs/afs/vlocation.c index d7d8dd8..37b7c3b 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/write.c b/fs/afs/write.c index c83c1a0..2d2fccd 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/btrfs/ctree.h b/fs/btrfs/ctree.h index 29b7fc2..c411590 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1259,7 +1259,7 @@ 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 08b74da..eb1ee7b 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; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 28e8192..27fdb25 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 c40060c..a18510b 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; } @@ -10509,9 +10523,9 @@ 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 +10570,7 @@ 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 a5da750..a59801d 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2948,20 +2948,20 @@ 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 +2976,8 @@ 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 456c890..a60d5bf 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/crypto/crypto.c b/fs/crypto/crypto.c index 02a7a92..6d6eca3 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 13052b8..37b4989 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 fdbb8af..e39696e 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 d5d896f..8cdfddc 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 14b76da..4908906 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); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 7d398d3..9382db9 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/ext4/ext4.h b/fs/ext4/ext4.h index f493af6..fb69ee2 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 8210c1f..cefa983 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 30a9f21..375fb1c 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 7385e6a..b9ffa9f 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 578f8c3..c992ef2 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 6ad612c..07e5e14 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 2e03a0a..a9448db 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 73b184d..5c8fc53 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 67636ac..996e790 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 a77df37..ee2d0a48 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 4650c9b..8d5c62b 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 e849f83..0a6e115 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 9496717..481aa8d 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 4bd7a8b..29ef708 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 338d2f7..a2c05f2 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/fs-writeback.c b/fs/fs-writeback.c index ef60059..63ee294 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/gfs2/incore.h b/fs/gfs2/incore.h index c45084a..511e1ed 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/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8f96461..7163fe0 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -695,14 +695,11 @@ 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 +730,6 @@ 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 +737,6 @@ 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 +924,18 @@ 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; } @@ -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 a1a359b..5adc2fb 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 cfc38b5..f9aefcd 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 8e4dc7a..ac2dfe0 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/nfs/callback.c b/fs/nfs/callback.c index bb79972..7737745 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 91a8d61..390ada8 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) { diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index fb499a3..f92ba8d 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/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 44347f4..acd30ba 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 2896cb8..79323b5 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 f956ca2..d913e81 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 f4f39b0..98b34c9 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 e5a6f24..457cfeb 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 09ca5095..7b38fed 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -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, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 5ae9d64..8346ccb 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 1b18368..201ca3f 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 f0369e3..80ce289 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 63f77b4..590e1e3 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 9414b49..7250b95 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/write.c b/fs/nfs/write.c index e75b056..abb2c8a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1784,7 +1784,8 @@ 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 +1794,8 @@ 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; } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 73e75ac..8bf8f66 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 fa82b77..03a7e9d 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 786a4a2..31e1f95 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++; + } } /* diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 4348027..d0ab7e5 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1863,7 +1863,7 @@ 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/overlayfs/util.c b/fs/overlayfs/util.c index 1953986..6e610a2 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" @@ -130,9 +130,13 @@ 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 +159,6 @@ 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, @@ -509,46 +510,38 @@ 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) -{ - 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) +static noinline_for_stack int +cp_statx(const 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; } /** @@ -570,10 +563,10 @@ 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); @@ -581,7 +574,8 @@ SYSCALL_DEFINE5(statx, error = vfs_statx_fd(dfd, &stat, mask, flags); if (error) return error; - return statx_set_result(&stat, buffer); + + return cp_statx(&stat, buffer); } /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */ diff --git a/fs/timerfd.c b/fs/timerfd.c index 384fa75..c543cdb 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/userfaultfd.c b/fs/userfaultfd.c index 973607d..1d227b0 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; diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 2dfdc62..70a5b55 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 689f746..f0fc84f 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 a9c66d4..9bd104f 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 f93072b..fd55db4 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 d04547f..eb00bc1 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -125,6 +125,8 @@ 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_mount *mp, struct xfs_dir2_sf_hdr *sfp, + int size); /* 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 c6809ff..96b45cd 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -629,6 +629,93 @@ xfs_dir2_sf_check( } #endif /* DEBUG */ +/* Verify the consistency of an inline directory. */ +int +xfs_dir2_sf_verify( + struct xfs_mount *mp, + struct xfs_dir2_sf_hdr *sfp, + int size) +{ + struct xfs_dir2_sf_entry *sfep; + struct xfs_dir2_sf_entry *next_sfep; + char *endp; + const struct xfs_dir_ops *dops; + xfs_ino_t ino; + int i; + int i8count; + int offset; + __uint8_t filetype; + + dops = xfs_dir_get_ops(mp, NULL); + + /* + * Give up if the directory is way too short. + */ + XFS_WANT_CORRUPTED_RETURN(mp, size > + offsetof(struct xfs_dir2_sf_hdr, parent)); + XFS_WANT_CORRUPTED_RETURN(mp, size >= + xfs_dir2_sf_hdr_size(sfp->i8count)); + + endp = (char *)sfp + size; + + /* Check .. entry */ + ino = dops->sf_get_parent_ino(sfp); + i8count = ino > XFS_DIR2_MAX_SHORT_INUM; + XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino)); + 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. + */ + XFS_WANT_CORRUPTED_RETURN(mp, + ((char *)sfep + sizeof(*sfep)) < endp); + + /* Don't allow names with known bad length. */ + XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen > 0); + XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen < MAXNAMELEN); + + /* + * 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); + XFS_WANT_CORRUPTED_RETURN(mp, endp >= (char *)next_sfep); + + /* Check that the offsets always increase. */ + XFS_WANT_CORRUPTED_RETURN(mp, + xfs_dir2_sf_get_offset(sfep) >= offset); + + /* Check the inode number. */ + ino = dops->sf_get_ino(sfp, sfep); + i8count += ino > XFS_DIR2_MAX_SHORT_INUM; + XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino)); + + /* Check the file type. */ + filetype = dops->sf_get_ftype(sfep); + XFS_WANT_CORRUPTED_RETURN(mp, filetype < XFS_DIR3_FT_MAX); + + offset = xfs_dir2_sf_get_offset(sfep) + + dops->data_entsize(sfep->namelen); + + sfep = next_sfep; + } + XFS_WANT_CORRUPTED_RETURN(mp, i8count == sfp->i8count); + XFS_WANT_CORRUPTED_RETURN(mp, (void *)sfep == (void *)endp); + + /* Make sure this whole thing ought to be in local format. */ + XFS_WANT_CORRUPTED_RETURN(mp, offset + + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + + (uint)sizeof(xfs_dir2_block_tail_t) <= mp->m_dir_geo->blksize); + + 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 25c1e07..9653e96 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; @@ -320,6 +322,7 @@ xfs_iformat_local( int whichfork, int size) { + int error; /* * If the size is unreasonable, then something @@ -336,6 +339,14 @@ xfs_iformat_local( return -EFSCORRUPTED; } + if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) { + error = xfs_dir2_sf_verify(ip->i_mount, + (struct xfs_dir2_sf_hdr *)XFS_DFORK_DPTR(dip), + size); + if (error) + return error; + } + xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size); return 0; } @@ -856,7 +867,7 @@ xfs_iextents_copy( * In these cases, the format always takes precedence, because the * format indicates the current state of the fork. */ -void +int xfs_iflush_fork( xfs_inode_t *ip, xfs_dinode_t *dip, @@ -866,6 +877,7 @@ xfs_iflush_fork( char *cp; xfs_ifork_t *ifp; xfs_mount_t *mp; + int error; static const short brootflag[2] = { XFS_ILOG_DBROOT, XFS_ILOG_ABROOT }; static const short dataflag[2] = @@ -874,7 +886,7 @@ xfs_iflush_fork( { XFS_ILOG_DEXT, XFS_ILOG_AEXT }; if (!iip) - return; + return 0; ifp = XFS_IFORK_PTR(ip, whichfork); /* * This can happen if we gave up in iformat in an error path, @@ -882,12 +894,19 @@ xfs_iflush_fork( */ if (!ifp) { ASSERT(whichfork == XFS_ATTR_FORK); - return; + return 0; } cp = XFS_DFORK_PTR(dip, whichfork); mp = ip->i_mount; switch (XFS_IFORK_FORMAT(ip, whichfork)) { case XFS_DINODE_FMT_LOCAL: + if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) { + error = xfs_dir2_sf_verify(mp, + (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data, + ifp->if_bytes); + if (error) + return error; + } if ((iip->ili_fields & dataflag[whichfork]) && (ifp->if_bytes > 0)) { ASSERT(ifp->if_u1.if_data != NULL); @@ -940,6 +959,7 @@ xfs_iflush_fork( ASSERT(0); break; } + return 0; } /* diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 7fb8365..132dc59 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -140,7 +140,7 @@ typedef struct xfs_ifork { struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state); int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *); -void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, +int xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, struct xfs_inode_log_item *, int); void xfs_idestroy_fork(struct xfs_inode *, int); void xfs_idata_realloc(struct xfs_inode *, int, int); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index bf65a9e..6149429 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_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 003a99b..ad9396e 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 7234b97..3531f8f 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 edfa6a5..c7fe2c2 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1615,7 +1615,7 @@ 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; @@ -3475,6 +3475,7 @@ xfs_iflush_int( struct xfs_inode_log_item *iip = ip->i_itemp; struct xfs_dinode *dip; struct xfs_mount *mp = ip->i_mount; + int error; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); ASSERT(xfs_isiflocked(ip)); @@ -3557,9 +3558,14 @@ xfs_iflush_int( if (ip->i_d.di_flushiter == DI_MAX_FLUSH) ip->i_d.di_flushiter = 0; - xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK); - if (XFS_IFORK_Q(ip)) - xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK); + error = xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK); + if (error) + return error; + if (XFS_IFORK_Q(ip)) { + error = xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK); + if (error) + return error; + } xfs_inobp_check(mp, bp); /* diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 41662fb..288ee5b 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 229cc6a..ebfc133 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 66e8817..2a6d9b1 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 diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 450bde6..688ebff 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 da6d08f..4a84c5e 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 33ac9b8..d29a796 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 890862f..685c042 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.", |