diff options
Diffstat (limited to 'fs')
53 files changed, 888 insertions, 551 deletions
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 4f1b6f466ff5..b86195e4dc6c 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -505,18 +505,14 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) struct afs_call *call = container_of(work, struct afs_call, work); struct afs_uuid *r = call->request; - struct { - __be32 match; - } reply; - _enter(""); if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0) - reply.match = htonl(0); + afs_send_empty_reply(call); else - reply.match = htonl(1); + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + 1, 1, "K-1"); - afs_send_simple_reply(call, &reply, sizeof(reply)); afs_put_call(call); _leave(""); } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index e640d67274be..81207dc3c997 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -440,7 +440,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, * iterate through the data blob that lists the contents of an AFS directory */ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, - struct key *key) + struct key *key, afs_dataversion_t *_dir_version) { struct afs_vnode *dvnode = AFS_FS_I(dir); struct afs_xdr_dir_page *dbuf; @@ -460,6 +460,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, req = afs_read_dir(dvnode, key); if (IS_ERR(req)) return PTR_ERR(req); + *_dir_version = req->data_version; /* round the file position up to the next entry boundary */ ctx->pos += sizeof(union afs_xdr_dirent) - 1; @@ -514,7 +515,10 @@ out: */ static int afs_readdir(struct file *file, struct dir_context *ctx) { - return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file)); + afs_dataversion_t dir_version; + + return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file), + &dir_version); } /* @@ -555,7 +559,8 @@ static int afs_lookup_one_filldir(struct dir_context *ctx, const char *name, * - just returns the FID the dentry name maps to if found */ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, - struct afs_fid *fid, struct key *key) + struct afs_fid *fid, struct key *key, + afs_dataversion_t *_dir_version) { struct afs_super_info *as = dir->i_sb->s_fs_info; struct afs_lookup_one_cookie cookie = { @@ -568,7 +573,7 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); /* search the directory */ - ret = afs_dir_iterate(dir, &cookie.ctx, key); + ret = afs_dir_iterate(dir, &cookie.ctx, key, _dir_version); if (ret < 0) { _leave(" = %d [iter]", ret); return ret; @@ -642,6 +647,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, struct afs_server *server; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; struct inode *inode = NULL, *ti; + afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version); int ret, i; _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); @@ -669,12 +675,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, cookie->fids[i].vid = as->volume->vid; /* search the directory */ - ret = afs_dir_iterate(dir, &cookie->ctx, key); + ret = afs_dir_iterate(dir, &cookie->ctx, key, &data_version); if (ret < 0) { inode = ERR_PTR(ret); goto out; } + dentry->d_fsdata = (void *)(unsigned long)data_version; + inode = ERR_PTR(-ENOENT); if (!cookie->found) goto out; @@ -968,7 +976,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) struct dentry *parent; struct inode *inode; struct key *key; - long dir_version, de_version; + afs_dataversion_t dir_version; + long de_version; int ret; if (flags & LOOKUP_RCU) @@ -1014,20 +1023,20 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) * on a 32-bit system, we only have 32 bits in the dentry to store the * version. */ - dir_version = (long)dir->status.data_version; + dir_version = dir->status.data_version; de_version = (long)dentry->d_fsdata; - if (de_version == dir_version) - goto out_valid; + if (de_version == (long)dir_version) + goto out_valid_noupdate; - dir_version = (long)dir->invalid_before; - if (de_version - dir_version >= 0) + dir_version = dir->invalid_before; + if (de_version - (long)dir_version >= 0) goto out_valid; _debug("dir modified"); afs_stat_v(dir, n_reval); /* search the directory for this vnode */ - ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key); + ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key, &dir_version); switch (ret) { case 0: /* the filename maps to something */ @@ -1080,7 +1089,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) } out_valid: - dentry->d_fsdata = (void *)dir_version; + dentry->d_fsdata = (void *)(unsigned long)dir_version; +out_valid_noupdate: dput(parent); key_put(key); _leave(" = 1 [valid]"); @@ -1186,6 +1196,20 @@ static void afs_prep_for_new_inode(struct afs_fs_cursor *fc, } /* + * Note that a dentry got changed. We need to set d_fsdata to the data version + * number derived from the result of the operation. It doesn't matter if + * d_fsdata goes backwards as we'll just revalidate. + */ +static void afs_update_dentry_version(struct afs_fs_cursor *fc, + struct dentry *dentry, + struct afs_status_cb *scb) +{ + if (fc->ac.error == 0) + dentry->d_fsdata = + (void *)(unsigned long)scb->status.data_version; +} + +/* * create a directory on an AFS filesystem */ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) @@ -1227,6 +1251,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1319,6 +1344,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, scb); + afs_update_dentry_version(&fc, dentry, scb); ret = afs_end_vnode_operation(&fc); if (ret == 0) { afs_dir_remove_subdir(dentry); @@ -1458,6 +1484,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) &data_version, &scb[0]); afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, &data_version_2, &scb[1]); + afs_update_dentry_version(&fc, dentry, &scb[0]); ret = afs_end_vnode_operation(&fc); if (ret == 0 && !(scb[1].have_status || scb[1].have_error)) ret = afs_dir_remove_link(dvnode, dentry, key); @@ -1526,6 +1553,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1607,6 +1635,7 @@ static int afs_link(struct dentry *from, struct inode *dir, afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, NULL, &scb[1]); ihold(&vnode->vfs_inode); + afs_update_dentry_version(&fc, dentry, &scb[0]); d_instantiate(dentry, &vnode->vfs_inode); mutex_unlock(&vnode->io_lock); @@ -1686,6 +1715,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1791,6 +1821,17 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, } } + /* This bit is potentially nasty as there's a potential race with + * afs_d_revalidate{,_rcu}(). We have to change d_fsdata on the dentry + * to reflect it's new parent's new data_version after the op, but + * d_revalidate may see old_dentry between the op having taken place + * and the version being updated. + * + * So drop the old_dentry for now to make other threads go through + * lookup instead - which we hold a lock against. + */ + d_drop(old_dentry); + ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) { afs_dataversion_t orig_data_version; @@ -1802,9 +1843,9 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, if (orig_dvnode != new_dvnode) { if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) { afs_end_vnode_operation(&fc); - goto error_rehash; + goto error_rehash_old; } - new_data_version = new_dvnode->status.data_version; + new_data_version = new_dvnode->status.data_version + 1; } else { new_data_version = orig_data_version; new_scb = &scb[0]; @@ -1827,7 +1868,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, } ret = afs_end_vnode_operation(&fc); if (ret < 0) - goto error_rehash; + goto error_rehash_old; } if (ret == 0) { @@ -1853,10 +1894,26 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, drop_nlink(new_inode); spin_unlock(&new_inode->i_lock); } + + /* Now we can update d_fsdata on the dentries to reflect their + * new parent's data_version. + * + * Note that if we ever implement RENAME_EXCHANGE, we'll have + * to update both dentries with opposing dir versions. + */ + if (new_dvnode != orig_dvnode) { + afs_update_dentry_version(&fc, old_dentry, &scb[1]); + afs_update_dentry_version(&fc, new_dentry, &scb[1]); + } else { + afs_update_dentry_version(&fc, old_dentry, &scb[0]); + afs_update_dentry_version(&fc, new_dentry, &scb[0]); + } d_move(old_dentry, new_dentry); goto error_tmp; } +error_rehash_old: + d_rehash(new_dentry); error_rehash: if (rehash) d_rehash(rehash); diff --git a/fs/afs/file.c b/fs/afs/file.c index 56b69576274d..dd3c55c9101c 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -191,11 +191,13 @@ void afs_put_read(struct afs_read *req) int i; if (refcount_dec_and_test(&req->usage)) { - for (i = 0; i < req->nr_pages; i++) - if (req->pages[i]) - put_page(req->pages[i]); - if (req->pages != req->array) - kfree(req->pages); + if (req->pages) { + for (i = 0; i < req->nr_pages; i++) + if (req->pages[i]) + put_page(req->pages[i]); + if (req->pages != req->array) + kfree(req->pages); + } kfree(req); } } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 1ce73e014139..114f281f3687 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -339,8 +339,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->tmp_u = htonl(0); afs_extract_to_tmp(call); } + /* Fall through */ - /* Fall through - and extract the returned data length */ + /* extract the returned data length */ case 1: _debug("extract data length"); ret = afs_extract_data(call, true); @@ -366,8 +367,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->bvec[0].bv_page = req->pages[req->index]; iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); + /* Fall through */ - /* Fall through - and extract the returned data */ + /* extract the returned data */ case 2: _debug("extract data %zu/%llu", iov_iter_count(&call->iter), req->remain); @@ -394,8 +396,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) /* Discard any excess data the server gave us */ iov_iter_discard(&call->iter, READ, req->actual_len - req->len); call->unmarshall = 3; - /* Fall through */ + case 3: _debug("extract discard %zu/%llu", iov_iter_count(&call->iter), req->actual_len - req->len); @@ -407,8 +409,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) no_more_data: call->unmarshall = 4; afs_extract_to_buf(call, (21 + 3 + 6) * 4); + /* Fall through */ - /* Fall through - and extract the metadata */ + /* extract the metadata */ case 4: ret = afs_extract_data(call, false); if (ret < 0) @@ -1471,8 +1474,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) case 0: call->unmarshall++; afs_extract_to_buf(call, 12 * 4); + /* Fall through */ - /* Fall through - and extract the returned status record */ + /* extract the returned status record */ case 1: _debug("extract status"); ret = afs_extract_data(call, true); @@ -1483,8 +1487,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) xdr_decode_AFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ - /* Fall through - and extract the volume name length */ + /* extract the volume name length */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -1498,8 +1503,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the volume name */ + /* extract the volume name */ case 3: _debug("extract volname"); ret = afs_extract_data(call, true); @@ -1511,8 +1517,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message length */ + /* extract the offline message length */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -1526,8 +1533,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message */ + /* extract the offline message */ case 5: _debug("extract offline"); ret = afs_extract_data(call, true); @@ -1540,8 +1548,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day length */ + /* extract the message of the day length */ case 6: ret = afs_extract_data(call, true); if (ret < 0) @@ -1555,8 +1564,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day */ + /* extract the message of the day */ case 7: _debug("extract motd"); ret = afs_extract_data(call, false); @@ -1850,8 +1860,9 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the capabilities word count */ + /* Extract the capabilities word count */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -1863,8 +1874,9 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) call->count2 = count; iov_iter_discard(&call->iter, READ, count * sizeof(__be32)); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract capabilities words */ + /* Extract capabilities words */ case 2: ret = afs_extract_data(call, false); if (ret < 0) @@ -2020,9 +2032,9 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file status count and array in two steps */ - /* Fall through */ case 1: _debug("extract status count"); ret = afs_extract_data(call, true); @@ -2039,8 +2051,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_counts: afs_extract_to_buf(call, 21 * sizeof(__be32)); - /* Fall through */ + case 2: _debug("extract status array %u", call->count); ret = afs_extract_data(call, true); @@ -2060,9 +2072,9 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ /* Extract the callback count and array in two steps */ - /* Fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -2078,8 +2090,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_cbs: afs_extract_to_buf(call, 3 * sizeof(__be32)); - /* Fall through */ + case 4: _debug("extract CB array"); ret = afs_extract_data(call, true); @@ -2096,8 +2108,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, 6 * sizeof(__be32)); call->unmarshall++; - /* Fall through */ + case 5: ret = afs_extract_data(call, false); if (ret < 0) @@ -2193,6 +2205,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* extract the returned data length */ case 1: @@ -2210,6 +2223,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) acl->size = call->count2; afs_extract_begin(call, acl->data, size); call->unmarshall++; + /* Fall through */ /* extract the returned data */ case 2: @@ -2219,6 +2233,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) afs_extract_to_buf(call, (21 + 6) * 4); call->unmarshall++; + /* Fall through */ /* extract the metadata */ case 3: diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index d7e0fd3c00df..cfb0ac4bd039 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -56,23 +56,24 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) struct afs_uuid__xdr *xdr; struct afs_uuid *uuid; int j; + int n = entry->nr_servers; tmp = ntohl(uvldb->serverFlags[i]); if (tmp & AFS_VLSF_DONTUSE || (new_only && !(tmp & AFS_VLSF_NEWREPSITE))) continue; if (tmp & AFS_VLSF_RWVOL) { - entry->fs_mask[i] |= AFS_VOL_VTM_RW; + entry->fs_mask[n] |= AFS_VOL_VTM_RW; if (vlflags & AFS_VLF_BACKEXISTS) - entry->fs_mask[i] |= AFS_VOL_VTM_BAK; + entry->fs_mask[n] |= AFS_VOL_VTM_BAK; } if (tmp & AFS_VLSF_ROVOL) - entry->fs_mask[i] |= AFS_VOL_VTM_RO; - if (!entry->fs_mask[i]) + entry->fs_mask[n] |= AFS_VOL_VTM_RO; + if (!entry->fs_mask[n]) continue; xdr = &uvldb->serverNumber[i]; - uuid = (struct afs_uuid *)&entry->fs_server[i]; + uuid = (struct afs_uuid *)&entry->fs_server[n]; uuid->time_low = xdr->time_low; uuid->time_mid = htons(ntohl(xdr->time_mid)); uuid->time_hi_and_version = htons(ntohl(xdr->time_hi_and_version)); diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 18722aaeda33..2575503170fc 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -450,8 +450,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) req->offset = req->pos & (PAGE_SIZE - 1); afs_extract_to_tmp64(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the returned data length */ + /* extract the returned data length */ case 1: _debug("extract data length"); ret = afs_extract_data(call, true); @@ -477,8 +478,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) call->bvec[0].bv_page = req->pages[req->index]; iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); + /* Fall through */ - /* Fall through - and extract the returned data */ + /* extract the returned data */ case 2: _debug("extract data %zu/%llu", iov_iter_count(&call->iter), req->remain); @@ -505,8 +507,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) /* Discard any excess data the server gave us */ iov_iter_discard(&call->iter, READ, req->actual_len - req->len); call->unmarshall = 3; - /* Fall through */ + case 3: _debug("extract discard %zu/%llu", iov_iter_count(&call->iter), req->actual_len - req->len); @@ -521,8 +523,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); + /* Fall through */ - /* Fall through - and extract the metadata */ + /* extract the metadata */ case 4: ret = afs_extract_data(call, false); if (ret < 0) @@ -539,8 +542,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) req->file_size = call->out_scb->status.size; call->unmarshall++; - /* Fall through */ + case 5: break; } @@ -1429,8 +1432,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) case 0: call->unmarshall++; afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus)); + /* Fall through */ - /* Fall through - and extract the returned status record */ + /* extract the returned status record */ case 1: _debug("extract status"); ret = afs_extract_data(call, true); @@ -1441,8 +1445,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) xdr_decode_YFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ - /* Fall through - and extract the volume name length */ + /* extract the volume name length */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -1456,8 +1461,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the volume name */ + /* extract the volume name */ case 3: _debug("extract volname"); ret = afs_extract_data(call, true); @@ -1469,8 +1475,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message length */ + /* extract the offline message length */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -1484,8 +1491,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message */ + /* extract the offline message */ case 5: _debug("extract offline"); ret = afs_extract_data(call, true); @@ -1498,8 +1506,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day length */ + /* extract the message of the day length */ case 6: ret = afs_extract_data(call, true); if (ret < 0) @@ -1513,8 +1522,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day */ + /* extract the message of the day */ case 7: _debug("extract motd"); ret = afs_extract_data(call, false); @@ -1526,8 +1536,8 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) _debug("motd '%s'", p); call->unmarshall++; - /* Fall through */ + case 8: break; } @@ -1805,9 +1815,9 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file status count and array in two steps */ - /* Fall through */ case 1: _debug("extract status count"); ret = afs_extract_data(call, true); @@ -1824,8 +1834,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_counts: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus)); - /* Fall through */ + case 2: _debug("extract status array %u", call->count); ret = afs_extract_data(call, true); @@ -1845,9 +1855,9 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ /* Extract the callback count and array in two steps */ - /* Fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -1863,8 +1873,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_cbs: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack)); - /* Fall through */ + case 4: _debug("extract CB array"); ret = afs_extract_data(call, true); @@ -1881,8 +1891,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; - /* Fall through */ + case 5: ret = afs_extract_data(call, false); if (ret < 0) @@ -1892,8 +1902,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; - /* Fall through */ + case 6: break; } @@ -1978,6 +1988,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file ACL length */ case 1: @@ -1999,6 +2010,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) iov_iter_discard(&call->iter, READ, size); } call->unmarshall++; + /* Fall through */ /* Extract the file ACL */ case 2: @@ -2008,6 +2020,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the volume ACL length */ case 3: @@ -2029,6 +2042,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) iov_iter_discard(&call->iter, READ, size); } call->unmarshall++; + /* Fall through */ /* Extract the volume ACL */ case 4: @@ -2041,6 +2055,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; + /* Fall through */ /* extract the metadata */ case 5: @@ -2057,6 +2072,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; + /* Fall through */ case 6: break; diff --git a/fs/block_dev.c b/fs/block_dev.c index 4707dfff991b..677cb364d33f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1139,8 +1139,7 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) * Pointer to the block device containing @bdev on success, ERR_PTR() * value on failure. */ -static struct block_device *bd_start_claiming(struct block_device *bdev, - void *holder) +struct block_device *bd_start_claiming(struct block_device *bdev, void *holder) { struct gendisk *disk; struct block_device *whole; @@ -1187,6 +1186,62 @@ static struct block_device *bd_start_claiming(struct block_device *bdev, return ERR_PTR(err); } } +EXPORT_SYMBOL(bd_start_claiming); + +static void bd_clear_claiming(struct block_device *whole, void *holder) +{ + lockdep_assert_held(&bdev_lock); + /* tell others that we're done */ + BUG_ON(whole->bd_claiming != holder); + whole->bd_claiming = NULL; + wake_up_bit(&whole->bd_claiming, 0); +} + +/** + * bd_finish_claiming - finish claiming of a block device + * @bdev: block device of interest + * @whole: whole block device (returned from bd_start_claiming()) + * @holder: holder that has claimed @bdev + * + * Finish exclusive open of a block device. Mark the device as exlusively + * open by the holder and wake up all waiters for exclusive open to finish. + */ +void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, + void *holder) +{ + spin_lock(&bdev_lock); + BUG_ON(!bd_may_claim(bdev, whole, holder)); + /* + * Note that for a whole device bd_holders will be incremented twice, + * and bd_holder will be set to bd_may_claim before being set to holder + */ + whole->bd_holders++; + whole->bd_holder = bd_may_claim; + bdev->bd_holders++; + bdev->bd_holder = holder; + bd_clear_claiming(whole, holder); + spin_unlock(&bdev_lock); +} +EXPORT_SYMBOL(bd_finish_claiming); + +/** + * bd_abort_claiming - abort claiming of a block device + * @bdev: block device of interest + * @whole: whole block device (returned from bd_start_claiming()) + * @holder: holder that has claimed @bdev + * + * Abort claiming of a block device when the exclusive open failed. This can be + * also used when exclusive open is not actually desired and we just needed + * to block other exclusive openers for a while. + */ +void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, + void *holder) +{ + spin_lock(&bdev_lock); + bd_clear_claiming(whole, holder); + spin_unlock(&bdev_lock); +} +EXPORT_SYMBOL(bd_abort_claiming); #ifdef CONFIG_SYSFS struct bd_holder_disk { @@ -1656,29 +1711,10 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) /* finish claiming */ mutex_lock(&bdev->bd_mutex); - spin_lock(&bdev_lock); - - if (!res) { - BUG_ON(!bd_may_claim(bdev, whole, holder)); - /* - * Note that for a whole device bd_holders - * will be incremented twice, and bd_holder - * will be set to bd_may_claim before being - * set to holder - */ - whole->bd_holders++; - whole->bd_holder = bd_may_claim; - bdev->bd_holders++; - bdev->bd_holder = holder; - } - - /* tell others that we're done */ - BUG_ON(whole->bd_claiming != holder); - whole->bd_claiming = NULL; - wake_up_bit(&whole->bd_claiming, 0); - - spin_unlock(&bdev_lock); - + if (!res) + bd_finish_claiming(bdev, whole, holder); + else + bd_abort_claiming(bdev, whole, holder); /* * Block event polling for write claims if requested. Any * write holder makes the write_holder state stick until diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 212b4a854f2c..38651fae7f21 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -4,6 +4,7 @@ config BTRFS_FS tristate "Btrfs filesystem support" select CRYPTO select CRYPTO_CRC32C + select LIBCRC32C select ZLIB_INFLATE select ZLIB_DEFLATE select LZO_COMPRESS diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 89116afda7a2..e5d85311d5d5 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1483,7 +1483,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr, ulist_init(roots); ulist_init(tmp); - trans = btrfs_attach_transaction(root); + trans = btrfs_join_transaction_nostart(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 299e11e6c554..94660063a162 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -401,7 +401,6 @@ struct btrfs_dev_replace { struct raid_kobject { u64 flags; struct kobject kobj; - struct list_head list; }; /* @@ -915,8 +914,6 @@ struct btrfs_fs_info { u32 thread_pool_size; struct kobject *space_info_kobj; - struct list_head pending_raid_kobjs; - spinlock_t pending_raid_kobjs_lock; /* uncontended */ u64 total_pinned; @@ -2698,7 +2695,6 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr); int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, u64 type, u64 chunk_offset, u64 size); -void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info); struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( struct btrfs_fs_info *fs_info, const u64 chunk_offset); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 41a2bd2e0c56..97beb351a10c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2683,8 +2683,6 @@ int open_ctree(struct super_block *sb, INIT_LIST_HEAD(&fs_info->delayed_iputs); INIT_LIST_HEAD(&fs_info->delalloc_roots); INIT_LIST_HEAD(&fs_info->caching_block_groups); - INIT_LIST_HEAD(&fs_info->pending_raid_kobjs); - spin_lock_init(&fs_info->pending_raid_kobjs_lock); spin_lock_init(&fs_info->delalloc_root_lock); spin_lock_init(&fs_info->trans_lock); spin_lock_init(&fs_info->fs_roots_radix_lock); @@ -4106,6 +4104,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_destroy(&fs_info->dev_replace.bio_counter); cleanup_srcu_struct(&fs_info->subvol_srcu); + btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d3b58e388535..8b7eb22d508a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4,6 +4,7 @@ */ #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/pagemap.h> #include <linux/writeback.h> @@ -7888,33 +7889,6 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) return 0; } -/* link_block_group will queue up kobjects to add when we're reclaim-safe */ -void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info) -{ - struct btrfs_space_info *space_info; - struct raid_kobject *rkobj; - LIST_HEAD(list); - int ret = 0; - - spin_lock(&fs_info->pending_raid_kobjs_lock); - list_splice_init(&fs_info->pending_raid_kobjs, &list); - spin_unlock(&fs_info->pending_raid_kobjs_lock); - - list_for_each_entry(rkobj, &list, list) { - space_info = btrfs_find_space_info(fs_info, rkobj->flags); - - ret = kobject_add(&rkobj->kobj, &space_info->kobj, - "%s", btrfs_bg_type_to_raid_name(rkobj->flags)); - if (ret) { - kobject_put(&rkobj->kobj); - break; - } - } - if (ret) - btrfs_warn(fs_info, - "failed to add kobject for block cache, ignoring"); -} - static void link_block_group(struct btrfs_block_group_cache *cache) { struct btrfs_space_info *space_info = cache->space_info; @@ -7929,18 +7903,36 @@ static void link_block_group(struct btrfs_block_group_cache *cache) up_write(&space_info->groups_sem); if (first) { - struct raid_kobject *rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS); + struct raid_kobject *rkobj; + unsigned int nofs_flag; + int ret; + + /* + * Setup a NOFS context because kobject_add(), deep in its call + * chain, does GFP_KERNEL allocations, and we are often called + * in a context where if reclaim is triggered we can deadlock + * (we are either holding a transaction handle or some lock + * required for a transaction commit). + */ + nofs_flag = memalloc_nofs_save(); + rkobj = kzalloc(sizeof(*rkobj), GFP_KERNEL); if (!rkobj) { + memalloc_nofs_restore(nofs_flag); btrfs_warn(cache->fs_info, "couldn't alloc memory for raid level kobject"); return; } rkobj->flags = cache->flags; kobject_init(&rkobj->kobj, &btrfs_raid_ktype); - - spin_lock(&fs_info->pending_raid_kobjs_lock); - list_add_tail(&rkobj->list, &fs_info->pending_raid_kobjs); - spin_unlock(&fs_info->pending_raid_kobjs_lock); + ret = kobject_add(&rkobj->kobj, &space_info->kobj, "%s", + btrfs_bg_type_to_raid_name(rkobj->flags)); + memalloc_nofs_restore(nofs_flag); + if (ret) { + kobject_put(&rkobj->kobj); + btrfs_warn(fs_info, + "failed to add kobject for block cache, ignoring"); + return; + } space_info->block_group_kobjs[index] = &rkobj->kobj; } } @@ -8206,7 +8198,6 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) inc_block_group_ro(cache, 1); } - btrfs_add_raid_kobjects(info); btrfs_init_global_block_rsv(info); ret = check_chunk_block_group_mappings(info); error: @@ -8975,6 +8966,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) struct btrfs_device *device; struct list_head *devices; u64 group_trimmed; + u64 range_end = U64_MAX; u64 start; u64 end; u64 trimmed = 0; @@ -8984,16 +8976,23 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) int dev_ret = 0; int ret = 0; + /* + * Check range overflow if range->len is set. + * The default range->len is U64_MAX. + */ + if (range->len != U64_MAX && + check_add_overflow(range->start, range->len, &range_end)) + return -EINVAL; + cache = btrfs_lookup_first_block_group(fs_info, range->start); for (; cache; cache = next_block_group(cache)) { - if (cache->key.objectid >= (range->start + range->len)) { + if (cache->key.objectid >= range_end) { btrfs_put_block_group(cache); break; } start = max(range->start, cache->key.objectid); - end = min(range->start + range->len, - cache->key.objectid + cache->key.offset); + end = min(range_end, cache->key.objectid + cache->key.offset); if (end - start >= range->minlen) { if (!block_group_cache_done(cache)) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1af069a9a0c7..ee582a36653d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -395,10 +395,31 @@ static noinline int add_async_extent(struct async_chunk *cow, return 0; } +/* + * Check if the inode has flags compatible with compression + */ +static inline bool inode_can_compress(struct inode *inode) +{ + if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW || + BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) + return false; + return true; +} + +/* + * Check if the inode needs to be submitted to compression, based on mount + * options, defragmentation, properties or heuristics. + */ static inline int inode_need_compress(struct inode *inode, u64 start, u64 end) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + if (!inode_can_compress(inode)) { + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: unexpected compression for ino %llu\n", + btrfs_ino(BTRFS_I(inode))); + return 0; + } /* force compress */ if (btrfs_test_opt(fs_info, FORCE_COMPRESS)) return 1; @@ -1631,7 +1652,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page, } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); - } else if (!inode_need_compress(inode, start, end)) { + } else if (!inode_can_compress(inode) || + !inode_need_compress(inode, start, end)) { ret = cow_file_range(inode, locked_page, start, end, end, page_started, nr_written, 1, NULL); } else { diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 98fccce4208c..393eceda57c8 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -346,9 +346,12 @@ void btrfs_tree_unlock(struct extent_buffer *eb) if (blockers) { btrfs_assert_no_spinning_writers(eb); eb->blocking_writers--; - /* Use the lighter barrier after atomic */ - smp_mb__after_atomic(); - cond_wake_up_nomb(&eb->write_lock_wq); + /* + * We need to order modifying blocking_writers above with + * actually waking up the sleepers to ensure they see the + * updated value of blocking_writers + */ + cond_wake_up(&eb->write_lock_wq); } else { btrfs_assert_spinning_writers_put(eb); write_unlock(&eb->lock); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 1744ba8b2754..ae7f64a8facb 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -985,13 +985,14 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, struct extent_state **cached_state) { struct btrfs_ordered_extent *ordered; - struct extent_state *cachedp = NULL; + struct extent_state *cache = NULL; + struct extent_state **cachedp = &cache; if (cached_state) - cachedp = *cached_state; + cachedp = cached_state; while (1) { - lock_extent_bits(tree, start, end, &cachedp); + lock_extent_bits(tree, start, end, cachedp); ordered = btrfs_lookup_ordered_range(inode, start, end - start + 1); if (!ordered) { @@ -1001,10 +1002,10 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, * aren't exposing it outside of this function */ if (!cached_state) - refcount_dec(&cachedp->refs); + refcount_dec(&cache->refs); break; } - unlock_extent_cached(tree, start, end, &cachedp); + unlock_extent_cached(tree, start, end, cachedp); btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1); btrfs_put_ordered_extent(ordered); } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 69b59bf75882..c3c0c064c25d 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6322,68 +6322,21 @@ static int changed_extent(struct send_ctx *sctx, { int ret = 0; - if (sctx->cur_ino != sctx->cmp_key->objectid) { - - if (result == BTRFS_COMPARE_TREE_CHANGED) { - struct extent_buffer *leaf_l; - struct extent_buffer *leaf_r; - struct btrfs_file_extent_item *ei_l; - struct btrfs_file_extent_item *ei_r; - - leaf_l = sctx->left_path->nodes[0]; - leaf_r = sctx->right_path->nodes[0]; - ei_l = btrfs_item_ptr(leaf_l, - sctx->left_path->slots[0], - struct btrfs_file_extent_item); - ei_r = btrfs_item_ptr(leaf_r, - sctx->right_path->slots[0], - struct btrfs_file_extent_item); - - /* - * We may have found an extent item that has changed - * only its disk_bytenr field and the corresponding - * inode item was not updated. This case happens due to - * very specific timings during relocation when a leaf - * that contains file extent items is COWed while - * relocation is ongoing and its in the stage where it - * updates data pointers. So when this happens we can - * safely ignore it since we know it's the same extent, - * but just at different logical and physical locations - * (when an extent is fully replaced with a new one, we - * know the generation number must have changed too, - * since snapshot creation implies committing the current - * transaction, and the inode item must have been updated - * as well). - * This replacement of the disk_bytenr happens at - * relocation.c:replace_file_extents() through - * relocation.c:btrfs_reloc_cow_block(). - */ - if (btrfs_file_extent_generation(leaf_l, ei_l) == - btrfs_file_extent_generation(leaf_r, ei_r) && - btrfs_file_extent_ram_bytes(leaf_l, ei_l) == - btrfs_file_extent_ram_bytes(leaf_r, ei_r) && - btrfs_file_extent_compression(leaf_l, ei_l) == - btrfs_file_extent_compression(leaf_r, ei_r) && - btrfs_file_extent_encryption(leaf_l, ei_l) == - btrfs_file_extent_encryption(leaf_r, ei_r) && - btrfs_file_extent_other_encoding(leaf_l, ei_l) == - btrfs_file_extent_other_encoding(leaf_r, ei_r) && - btrfs_file_extent_type(leaf_l, ei_l) == - btrfs_file_extent_type(leaf_r, ei_r) && - btrfs_file_extent_disk_bytenr(leaf_l, ei_l) != - btrfs_file_extent_disk_bytenr(leaf_r, ei_r) && - btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) == - btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) && - btrfs_file_extent_offset(leaf_l, ei_l) == - btrfs_file_extent_offset(leaf_r, ei_r) && - btrfs_file_extent_num_bytes(leaf_l, ei_l) == - btrfs_file_extent_num_bytes(leaf_r, ei_r)) - return 0; - } - - inconsistent_snapshot_error(sctx, result, "extent"); - return -EIO; - } + /* + * We have found an extent item that changed without the inode item + * having changed. This can happen either after relocation (where the + * disk_bytenr of an extent item is replaced at + * relocation.c:replace_file_extents()) or after deduplication into a + * file in both the parent and send snapshots (where an extent item can + * get modified or replaced with a new one). Note that deduplication + * updates the inode item, but it only changes the iversion (sequence + * field in the inode item) of the inode, so if a file is deduplicated + * the same amount of times in both the parent and send snapshots, its + * iversion becames the same in both snapshots, whence the inode item is + * the same on both snapshots. + */ + if (sctx->cur_ino != sctx->cmp_key->objectid) + return 0; if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) { if (result != BTRFS_COMPARE_TREE_DELETED) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 3b8ae1a8f02d..e3adb714c04b 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -28,15 +28,18 @@ static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { [TRANS_STATE_COMMIT_START] = (__TRANS_START | __TRANS_ATTACH), [TRANS_STATE_COMMIT_DOING] = (__TRANS_START | __TRANS_ATTACH | - __TRANS_JOIN), + __TRANS_JOIN | + __TRANS_JOIN_NOSTART), [TRANS_STATE_UNBLOCKED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | - __TRANS_JOIN_NOLOCK), + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), [TRANS_STATE_COMPLETED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | - __TRANS_JOIN_NOLOCK), + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), }; void btrfs_put_transaction(struct btrfs_transaction *transaction) @@ -543,7 +546,8 @@ again: ret = join_transaction(fs_info, type); if (ret == -EBUSY) { wait_current_trans(fs_info); - if (unlikely(type == TRANS_ATTACH)) + if (unlikely(type == TRANS_ATTACH || + type == TRANS_JOIN_NOSTART)) ret = -ENOENT; } } while (ret == -EBUSY); @@ -660,6 +664,16 @@ struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root } /* + * Similar to regular join but it never starts a transaction when none is + * running or after waiting for the current one to finish. + */ +struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root) +{ + return start_transaction(root, 0, TRANS_JOIN_NOSTART, + BTRFS_RESERVE_NO_FLUSH, true); +} + +/* * btrfs_attach_transaction() - catch the running transaction * * It is used when we want to commit the current the transaction, but @@ -2037,6 +2051,16 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) } } else { spin_unlock(&fs_info->trans_lock); + /* + * The previous transaction was aborted and was already removed + * from the list of transactions at fs_info->trans_list. So we + * abort to prevent writing a new superblock that reflects a + * corrupt state (pointing to trees with unwritten nodes/leafs). + */ + if (test_bit(BTRFS_FS_STATE_TRANS_ABORTED, &fs_info->fs_state)) { + ret = -EROFS; + goto cleanup_transaction; + } } extwriter_counter_dec(cur_trans, trans->type); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 527ea94b57d9..2c5a6f6e5bb0 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -94,11 +94,13 @@ struct btrfs_transaction { #define __TRANS_JOIN (1U << 11) #define __TRANS_JOIN_NOLOCK (1U << 12) #define __TRANS_DUMMY (1U << 13) +#define __TRANS_JOIN_NOSTART (1U << 14) #define TRANS_START (__TRANS_START | __TRANS_FREEZABLE) #define TRANS_ATTACH (__TRANS_ATTACH) #define TRANS_JOIN (__TRANS_JOIN | __TRANS_FREEZABLE) #define TRANS_JOIN_NOLOCK (__TRANS_JOIN_NOLOCK) +#define TRANS_JOIN_NOSTART (__TRANS_JOIN_NOSTART) #define TRANS_EXTWRITERS (__TRANS_START | __TRANS_ATTACH) @@ -183,6 +185,7 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( int min_factor); struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root); +struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction_barrier( struct btrfs_root *root); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a13ddba1ebc3..a447d3ec48d5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3087,16 +3087,6 @@ static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) if (ret) return ret; - /* - * We add the kobjects here (and after forcing data chunk creation) - * since relocation is the only place we'll create chunks of a new - * type at runtime. The only place where we'll remove the last - * chunk of a type is the call immediately below this one. Even - * so, we're protected against races with the cleaner thread since - * we're covered by the delete_unused_bgs_mutex. - */ - btrfs_add_raid_kobjects(fs_info); - trans = btrfs_start_trans_remove_block_group(root->fs_info, chunk_offset); if (IS_ERR(trans)) { @@ -3223,9 +3213,6 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info, btrfs_end_transaction(trans); if (ret < 0) return ret; - - btrfs_add_raid_kobjects(fs_info); - return 1; } } @@ -5941,6 +5928,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 stripe_len; u64 raid56_full_stripe_start = (u64)-1; int data_stripes; + int ret = 0; ASSERT(op != BTRFS_MAP_DISCARD); @@ -5961,8 +5949,8 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, btrfs_crit(fs_info, "stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu", stripe_offset, offset, em->start, logical, stripe_len); - free_extent_map(em); - return -EINVAL; + ret = -EINVAL; + goto out; } /* stripe_offset is the offset of this block in its stripe */ @@ -6009,7 +5997,10 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom->stripe_offset = stripe_offset; io_geom->raid56_stripe_offset = raid56_full_stripe_start; - return 0; +out: + /* once for us */ + free_extent_map(em); + return ret; } static int __btrfs_map_block(struct btrfs_fs_info *fs_info, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a4830ced0f98..a15a6e738eb5 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1113,6 +1113,7 @@ cifs_demultiplex_thread(void *p) mempool_resize(cifs_req_poolp, length + cifs_min_rcv); set_freezable(); + allow_signal(SIGKILL); while (server->tcpStatus != CifsExiting) { if (try_to_freeze()) continue; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index a5bc1b671c12..64a5864127be 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3489,7 +3489,15 @@ fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, unsigned int orig_len, static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf, unsigned int buflen) { - sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf)); + void *addr; + /* + * VMAP_STACK (at least) puts stack into the vmalloc address space + */ + if (is_vmalloc_addr(buf)) + addr = vmalloc_to_page(buf); + else + addr = virt_to_page(buf); + sg_set_page(sg, addr, buflen, offset_in_page(buf)); } /* Assumes the first rqst has a transform header as the first iov. @@ -4070,7 +4078,6 @@ receive_encrypted_standard(struct TCP_Server_Info *server, { int ret, length; char *buf = server->smallbuf; - char *tmpbuf; struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; @@ -4100,18 +4107,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, return length; next_is_large = server->large_buf; - one_more: +one_more: shdr = (struct smb2_sync_hdr *)buf; if (shdr->NextCommand) { - if (next_is_large) { - tmpbuf = server->bigbuf; + if (next_is_large) next_buffer = (char *)cifs_buf_get(); - } else { - tmpbuf = server->smallbuf; + else next_buffer = (char *)cifs_small_buf_get(); - } memcpy(next_buffer, - tmpbuf + le32_to_cpu(shdr->NextCommand), + buf + le32_to_cpu(shdr->NextCommand), pdu_length - le32_to_cpu(shdr->NextCommand)); } @@ -4140,12 +4144,21 @@ receive_encrypted_standard(struct TCP_Server_Info *server, pdu_length -= le32_to_cpu(shdr->NextCommand); server->large_buf = next_is_large; if (next_is_large) - server->bigbuf = next_buffer; + server->bigbuf = buf = next_buffer; else - server->smallbuf = next_buffer; - - buf += le32_to_cpu(shdr->NextCommand); + server->smallbuf = buf = next_buffer; goto one_more; + } else if (ret != 0) { + /* + * ret != 0 here means that we didn't get to handle_mid() thus + * server->smallbuf and server->bigbuf are still valid. We need + * to free next_buffer because it is not going to be used + * anywhere. + */ + if (next_is_large) + free_rsp_buf(CIFS_LARGE_BUFFER, next_buffer); + else + free_rsp_buf(CIFS_SMALL_BUFFER, next_buffer); } return ret; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index c8cd7b6cdda2..31e4a1b0b170 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -252,7 +252,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) if (tcon == NULL) return 0; - if (smb2_command == SMB2_TREE_CONNECT) + if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL) return 0; if (tcon->tidStatus == CifsExiting) { @@ -1196,7 +1196,12 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) else req->SecurityMode = 0; +#ifdef CONFIG_CIFS_DFS_UPCALL + req->Capabilities = cpu_to_le32(SMB2_GLOBAL_CAP_DFS); +#else req->Capabilities = 0; +#endif /* DFS_UPCALL */ + req->Channel = 0; /* MBZ */ sess_data->iov[0].iov_base = (char *)req; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 6e30949d9f77..a7ec2d3dff92 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -638,9 +638,6 @@ COMPATIBLE_IOCTL(PPPIOCDISCONN) COMPATIBLE_IOCTL(PPPIOCATTCHAN) COMPATIBLE_IOCTL(PPPIOCGCHAN) COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS) -/* PPPOX */ -COMPATIBLE_IOCTL(PPPOEIOCSFWD) -COMPATIBLE_IOCTL(PPPOEIOCDFWD) /* Big A */ /* sparc only */ /* Big Q for sound/OSS */ diff --git a/fs/coredump.c b/fs/coredump.c index e42e17e55bfd..b1ea7dfbd149 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -7,6 +7,7 @@ #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> +#include <linux/ctype.h> #include <linux/string.h> #include <linux/init.h> #include <linux/pagemap.h> @@ -187,11 +188,13 @@ put_exe_file: * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ -static int format_corename(struct core_name *cn, struct coredump_params *cprm) +static int format_corename(struct core_name *cn, struct coredump_params *cprm, + size_t **argv, int *argc) { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); + bool was_space = false; int pid_in_pattern = 0; int err = 0; @@ -201,12 +204,35 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) return -ENOMEM; cn->corename[0] = '\0'; - if (ispipe) + if (ispipe) { + int argvs = sizeof(core_pattern) / 2; + (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL); + if (!(*argv)) + return -ENOMEM; + (*argv)[(*argc)++] = 0; ++pat_ptr; + } /* Repeat as long as we have more pattern to process and more output space */ while (*pat_ptr) { + /* + * Split on spaces before doing template expansion so that + * %e and %E don't get split if they have spaces in them + */ + if (ispipe) { + if (isspace(*pat_ptr)) { + was_space = true; + pat_ptr++; + continue; + } else if (was_space) { + was_space = false; + err = cn_printf(cn, "%c", '\0'); + if (err) + return err; + (*argv)[(*argc)++] = cn->used; + } + } if (*pat_ptr != '%') { err = cn_printf(cn, "%c", *pat_ptr++); } else { @@ -546,6 +572,8 @@ void do_coredump(const kernel_siginfo_t *siginfo) struct cred *cred; int retval = 0; int ispipe; + size_t *argv = NULL; + int argc = 0; struct files_struct *displaced; /* require nonrelative corefile path and be extra careful */ bool need_suid_safe = false; @@ -592,9 +620,10 @@ void do_coredump(const kernel_siginfo_t *siginfo) old_cred = override_creds(cred); - ispipe = format_corename(&cn, &cprm); + ispipe = format_corename(&cn, &cprm, &argv, &argc); if (ispipe) { + int argi; int dump_count; char **helper_argv; struct subprocess_info *sub_info; @@ -637,12 +666,16 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto fail_dropcount; } - helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL); + helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), + GFP_KERNEL); if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory\n", __func__); goto fail_dropcount; } + for (argi = 0; argi < argc; argi++) + helper_argv[argi] = cn.corename + argv[argi]; + helper_argv[argi] = NULL; retval = -ENOMEM; sub_info = call_usermodehelper_setup(helper_argv[0], @@ -652,7 +685,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) retval = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); - argv_free(helper_argv); + kfree(helper_argv); if (retval) { printk(KERN_INFO "Core dump to |%s pipe failed\n", cn.corename); @@ -766,6 +799,7 @@ fail_dropcount: if (ispipe) atomic_dec(&core_dump_count); fail_unlock: + kfree(argv); kfree(cn.corename); coredump_finish(mm, core_dumped); revert_creds(old_cred); @@ -266,7 +266,7 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry) static void put_unlocked_entry(struct xa_state *xas, void *entry) { /* If we were the only waiter woken, wake the next one */ - if (entry && dax_is_conflict(entry)) + if (entry && !dax_is_conflict(entry)) dax_wake_entry(xas, entry, false); } @@ -600,7 +600,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping) * guaranteed to either see new references or prevent new * references from being established. */ - unmap_mapping_range(mapping, 0, 0, 1); + unmap_mapping_range(mapping, 0, 0, 0); xas_lock_irq(&xas); xas_for_each(&xas, entry, ULONG_MAX) { diff --git a/fs/exec.c b/fs/exec.c index c71cbfe6826a..f7f6a140856a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1828,7 +1828,7 @@ static int __do_execve_file(int fd, struct filename *filename, membarrier_execve(current); rseq_execve(current); acct_update_integrals(current); - task_numa_free(current); + task_numa_free(current, false); free_bprm(bprm); kfree(pathbuf); if (filename) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index f8d46df8fa9e..3e58a6f697dd 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1653,19 +1653,12 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) { struct f2fs_inode_info *fi = F2FS_I(inode); - u32 oldflags; /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) return -EPERM; - oldflags = fi->i_flags; - - if ((iflags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL)) - if (!capable(CAP_LINUX_IMMUTABLE)) - return -EPERM; - - fi->i_flags = iflags | (oldflags & ~mask); + fi->i_flags = iflags | (fi->i_flags & ~mask); if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); @@ -1770,7 +1763,8 @@ static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - u32 fsflags; + struct f2fs_inode_info *fi = F2FS_I(inode); + u32 fsflags, old_fsflags; u32 iflags; int ret; @@ -1794,8 +1788,14 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) inode_lock(inode); + old_fsflags = f2fs_iflags_to_fsflags(fi->i_flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); + if (ret) + goto out; + ret = f2fs_setflags_common(inode, iflags, f2fs_fsflags_to_iflags(F2FS_SETTABLE_FS_FL)); +out: inode_unlock(inode); mnt_drop_write_file(filp); return ret; @@ -2855,52 +2855,32 @@ static inline u32 f2fs_xflags_to_iflags(u32 xflags) return iflags; } -static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) +static void f2fs_fill_fsxattr(struct inode *inode, struct fsxattr *fa) { - struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - struct fsxattr fa; - memset(&fa, 0, sizeof(struct fsxattr)); - fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags); + simple_fill_fsxattr(fa, f2fs_iflags_to_xflags(fi->i_flags)); if (f2fs_sb_has_project_quota(F2FS_I_SB(inode))) - fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, - fi->i_projid); - - if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) - return -EFAULT; - return 0; + fa->fsx_projid = from_kprojid(&init_user_ns, fi->i_projid); } -static int f2fs_ioctl_check_project(struct inode *inode, struct fsxattr *fa) +static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) { - /* - * Project Quota ID state is only allowed to change from within the init - * namespace. Enforce that restriction only if we are trying to change - * the quota ID state. Everything else is allowed in user namespaces. - */ - if (current_user_ns() == &init_user_ns) - return 0; + struct inode *inode = file_inode(filp); + struct fsxattr fa; - if (__kprojid_val(F2FS_I(inode)->i_projid) != fa->fsx_projid) - return -EINVAL; - - if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) { - if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT)) - return -EINVAL; - } else { - if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) - return -EINVAL; - } + f2fs_fill_fsxattr(inode, &fa); + if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) + return -EFAULT; return 0; } static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - struct fsxattr fa; + struct fsxattr fa, old_fa; u32 iflags; int err; @@ -2923,9 +2903,12 @@ static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) return err; inode_lock(inode); - err = f2fs_ioctl_check_project(inode, &fa); + + f2fs_fill_fsxattr(inode, &old_fa); + err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa); if (err) goto out; + err = f2fs_setflags_common(inode, iflags, f2fs_xflags_to_iflags(F2FS_SUPPORTED_XFLAGS)); if (err) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 6691f526fa40..8974672db78f 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -796,6 +796,29 @@ static int move_data_block(struct inode *inode, block_t bidx, if (lfs_mode) down_write(&fio.sbi->io_order_lock); + mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi), + fio.old_blkaddr, false); + if (!mpage) + goto up_out; + + fio.encrypted_page = mpage; + + /* read source block in mpage */ + if (!PageUptodate(mpage)) { + err = f2fs_submit_page_bio(&fio); + if (err) { + f2fs_put_page(mpage, 1); + goto up_out; + } + lock_page(mpage); + if (unlikely(mpage->mapping != META_MAPPING(fio.sbi) || + !PageUptodate(mpage))) { + err = -EIO; + f2fs_put_page(mpage, 1); + goto up_out; + } + } + f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, &sum, CURSEG_COLD_DATA, NULL, false); @@ -803,44 +826,18 @@ static int move_data_block(struct inode *inode, block_t bidx, newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); if (!fio.encrypted_page) { err = -ENOMEM; - goto recover_block; - } - - mpage = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), - fio.old_blkaddr, FGP_LOCK, GFP_NOFS); - if (mpage) { - bool updated = false; - - if (PageUptodate(mpage)) { - memcpy(page_address(fio.encrypted_page), - page_address(mpage), PAGE_SIZE); - updated = true; - } f2fs_put_page(mpage, 1); - invalidate_mapping_pages(META_MAPPING(fio.sbi), - fio.old_blkaddr, fio.old_blkaddr); - if (updated) - goto write_page; - } - - err = f2fs_submit_page_bio(&fio); - if (err) - goto put_page_out; - - /* write page */ - lock_page(fio.encrypted_page); - - if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) { - err = -EIO; - goto put_page_out; - } - if (unlikely(!PageUptodate(fio.encrypted_page))) { - err = -EIO; - goto put_page_out; + goto recover_block; } -write_page: + /* write target block */ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true); + memcpy(page_address(fio.encrypted_page), + page_address(mpage), PAGE_SIZE); + f2fs_put_page(mpage, 1); + invalidate_mapping_pages(META_MAPPING(fio.sbi), + fio.old_blkaddr, fio.old_blkaddr); + set_page_dirty(fio.encrypted_page); if (clear_page_dirty_for_io(fio.encrypted_page)) dec_page_count(fio.sbi, F2FS_DIRTY_META); @@ -871,11 +868,12 @@ write_page: put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: - if (lfs_mode) - up_write(&fio.sbi->io_order_lock); if (err) f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, true, true); +up_out: + if (lfs_mode) + up_write(&fio.sbi->io_order_lock); put_out: f2fs_put_dnode(&dn); out: diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 6de6cda44031..78a1b873e48a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2422,6 +2422,12 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, size_t crc_offset = 0; __u32 crc = 0; + if (le32_to_cpu(raw_super->magic) != F2FS_SUPER_MAGIC) { + f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)", + F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); + return -EINVAL; + } + /* Check checksum_offset and crc in superblock */ if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) { crc_offset = le32_to_cpu(raw_super->checksum_offset); @@ -2429,26 +2435,20 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, offsetof(struct f2fs_super_block, crc)) { f2fs_info(sbi, "Invalid SB checksum offset: %zu", crc_offset); - return 1; + return -EFSCORRUPTED; } crc = le32_to_cpu(raw_super->crc); if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) { f2fs_info(sbi, "Invalid SB checksum value: %u", crc); - return 1; + return -EFSCORRUPTED; } } - if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { - f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)", - F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); - return 1; - } - /* Currently, support only 4KB page cache size */ if (F2FS_BLKSIZE != PAGE_SIZE) { f2fs_info(sbi, "Invalid page_cache_size (%lu), supports only 4KB", PAGE_SIZE); - return 1; + return -EFSCORRUPTED; } /* Currently, support only 4KB block size */ @@ -2456,14 +2456,14 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, if (blocksize != F2FS_BLKSIZE) { f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB", blocksize); - return 1; + return -EFSCORRUPTED; } /* check log blocks per segment */ if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { f2fs_info(sbi, "Invalid log blocks per segment (%u)", le32_to_cpu(raw_super->log_blocks_per_seg)); - return 1; + return -EFSCORRUPTED; } /* Currently, support 512/1024/2048/4096 bytes sector size */ @@ -2473,7 +2473,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, F2FS_MIN_LOG_SECTOR_SIZE) { f2fs_info(sbi, "Invalid log sectorsize (%u)", le32_to_cpu(raw_super->log_sectorsize)); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->log_sectors_per_block) + le32_to_cpu(raw_super->log_sectorsize) != @@ -2481,7 +2481,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, f2fs_info(sbi, "Invalid log sectors per block(%u) log sectorsize(%u)", le32_to_cpu(raw_super->log_sectors_per_block), le32_to_cpu(raw_super->log_sectorsize)); - return 1; + return -EFSCORRUPTED; } segment_count = le32_to_cpu(raw_super->segment_count); @@ -2495,7 +2495,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, if (segment_count > F2FS_MAX_SEGMENT || segment_count < F2FS_MIN_SEGMENTS) { f2fs_info(sbi, "Invalid segment count (%u)", segment_count); - return 1; + return -EFSCORRUPTED; } if (total_sections > segment_count || @@ -2503,25 +2503,25 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, segs_per_sec > segment_count || !segs_per_sec) { f2fs_info(sbi, "Invalid segment/section count (%u, %u x %u)", segment_count, total_sections, segs_per_sec); - return 1; + return -EFSCORRUPTED; } if ((segment_count / segs_per_sec) < total_sections) { f2fs_info(sbi, "Small segment_count (%u < %u * %u)", segment_count, segs_per_sec, total_sections); - return 1; + return -EFSCORRUPTED; } if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) { f2fs_info(sbi, "Wrong segment_count / block_count (%u > %llu)", segment_count, le64_to_cpu(raw_super->block_count)); - return 1; + return -EFSCORRUPTED; } if (secs_per_zone > total_sections || !secs_per_zone) { f2fs_info(sbi, "Wrong secs_per_zone / total_sections (%u, %u)", secs_per_zone, total_sections); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION || raw_super->hot_ext_count > F2FS_MAX_EXTENSION || @@ -2531,7 +2531,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, le32_to_cpu(raw_super->extension_count), raw_super->hot_ext_count, F2FS_MAX_EXTENSION); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->cp_payload) > @@ -2539,7 +2539,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, f2fs_info(sbi, "Insane cp_payload (%u > %u)", le32_to_cpu(raw_super->cp_payload), blocks_per_seg - F2FS_CP_PACKS); - return 1; + return -EFSCORRUPTED; } /* check reserved ino info */ @@ -2550,12 +2550,12 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, le32_to_cpu(raw_super->node_ino), le32_to_cpu(raw_super->meta_ino), le32_to_cpu(raw_super->root_ino)); - return 1; + return -EFSCORRUPTED; } /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ if (sanity_check_area_boundary(sbi, bh)) - return 1; + return -EFSCORRUPTED; return 0; } @@ -2870,10 +2870,10 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, } /* sanity checking of raw super */ - if (sanity_check_raw_super(sbi, bh)) { + err = sanity_check_raw_super(sbi, bh); + if (err) { f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock", block + 1); - err = -EFSCORRUPTED; brelse(bh); continue; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 79581b9bdebb..4f8b5fd6c81f 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -390,6 +390,19 @@ static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h) return mp->mp_aheight - x - 1; } +static sector_t metapath_to_block(struct gfs2_sbd *sdp, struct metapath *mp) +{ + sector_t factor = 1, block = 0; + int hgt; + + for (hgt = mp->mp_fheight - 1; hgt >= 0; hgt--) { + if (hgt < mp->mp_aheight) + block += mp->mp_list[hgt] * factor; + factor *= sdp->sd_inptrs; + } + return block; +} + static void release_metapath(struct metapath *mp) { int i; @@ -430,60 +443,84 @@ static inline unsigned int gfs2_extent_length(struct buffer_head *bh, __be64 *pt return ptr - first; } -typedef const __be64 *(*gfs2_metadata_walker)( - struct metapath *mp, - const __be64 *start, const __be64 *end, - u64 factor, void *data); +enum walker_status { WALK_STOP, WALK_FOLLOW, WALK_CONTINUE }; + +/* + * gfs2_metadata_walker - walk an indirect block + * @mp: Metapath to indirect block + * @ptrs: Number of pointers to look at + * + * When returning WALK_FOLLOW, the walker must update @mp to point at the right + * indirect block to follow. + */ +typedef enum walker_status (*gfs2_metadata_walker)(struct metapath *mp, + unsigned int ptrs); -#define WALK_STOP ((__be64 *)0) -#define WALK_NEXT ((__be64 *)1) +/* + * gfs2_walk_metadata - walk a tree of indirect blocks + * @inode: The inode + * @mp: Starting point of walk + * @max_len: Maximum number of blocks to walk + * @walker: Called during the walk + * + * Returns 1 if the walk was stopped by @walker, 0 if we went past @max_len or + * past the end of metadata, and a negative error code otherwise. + */ -static int gfs2_walk_metadata(struct inode *inode, sector_t lblock, - u64 len, struct metapath *mp, gfs2_metadata_walker walker, - void *data) +static int gfs2_walk_metadata(struct inode *inode, struct metapath *mp, + u64 max_len, gfs2_metadata_walker walker) { - struct metapath clone; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); - const __be64 *start, *end, *ptr; u64 factor = 1; unsigned int hgt; - int ret = 0; + int ret; - for (hgt = ip->i_height - 1; hgt >= mp->mp_aheight; hgt--) + /* + * The walk starts in the lowest allocated indirect block, which may be + * before the position indicated by @mp. Adjust @max_len accordingly + * to avoid a short walk. + */ + for (hgt = mp->mp_fheight - 1; hgt >= mp->mp_aheight; hgt--) { + max_len += mp->mp_list[hgt] * factor; + mp->mp_list[hgt] = 0; factor *= sdp->sd_inptrs; + } for (;;) { - u64 step; + u16 start = mp->mp_list[hgt]; + enum walker_status status; + unsigned int ptrs; + u64 len; /* Walk indirect block. */ - start = metapointer(hgt, mp); - end = metaend(hgt, mp); - - step = (end - start) * factor; - if (step > len) - end = start + DIV_ROUND_UP_ULL(len, factor); - - ptr = walker(mp, start, end, factor, data); - if (ptr == WALK_STOP) + ptrs = (hgt >= 1 ? sdp->sd_inptrs : sdp->sd_diptrs) - start; + len = ptrs * factor; + if (len > max_len) + ptrs = DIV_ROUND_UP_ULL(max_len, factor); + status = walker(mp, ptrs); + switch (status) { + case WALK_STOP: + return 1; + case WALK_FOLLOW: + BUG_ON(mp->mp_aheight == mp->mp_fheight); + ptrs = mp->mp_list[hgt] - start; + len = ptrs * factor; break; - if (step >= len) + case WALK_CONTINUE: break; - len -= step; - if (ptr != WALK_NEXT) { - BUG_ON(!*ptr); - mp->mp_list[hgt] += ptr - start; - goto fill_up_metapath; } + if (len >= max_len) + break; + max_len -= len; + if (status == WALK_FOLLOW) + goto fill_up_metapath; lower_metapath: /* Decrease height of metapath. */ - if (mp != &clone) { - clone_metapath(&clone, mp); - mp = &clone; - } brelse(mp->mp_bh[hgt]); mp->mp_bh[hgt] = NULL; + mp->mp_list[hgt] = 0; if (!hgt) break; hgt--; @@ -491,10 +528,7 @@ lower_metapath: /* Advance in metadata tree. */ (mp->mp_list[hgt])++; - start = metapointer(hgt, mp); - end = metaend(hgt, mp); - if (start >= end) { - mp->mp_list[hgt] = 0; + if (mp->mp_list[hgt] >= sdp->sd_inptrs) { if (!hgt) break; goto lower_metapath; @@ -502,44 +536,36 @@ lower_metapath: fill_up_metapath: /* Increase height of metapath. */ - if (mp != &clone) { - clone_metapath(&clone, mp); - mp = &clone; - } ret = fillup_metapath(ip, mp, ip->i_height - 1); if (ret < 0) - break; + return ret; hgt += ret; for (; ret; ret--) do_div(factor, sdp->sd_inptrs); mp->mp_aheight = hgt + 1; } - if (mp == &clone) - release_metapath(mp); - return ret; + return 0; } -struct gfs2_hole_walker_args { - u64 blocks; -}; - -static const __be64 *gfs2_hole_walker(struct metapath *mp, - const __be64 *start, const __be64 *end, - u64 factor, void *data) +static enum walker_status gfs2_hole_walker(struct metapath *mp, + unsigned int ptrs) { - struct gfs2_hole_walker_args *args = data; - const __be64 *ptr; + const __be64 *start, *ptr, *end; + unsigned int hgt; + + hgt = mp->mp_aheight - 1; + start = metapointer(hgt, mp); + end = start + ptrs; for (ptr = start; ptr < end; ptr++) { if (*ptr) { - args->blocks += (ptr - start) * factor; + mp->mp_list[hgt] += ptr - start; if (mp->mp_aheight == mp->mp_fheight) return WALK_STOP; - return ptr; /* increase height */ + return WALK_FOLLOW; } } - args->blocks += (end - start) * factor; - return WALK_NEXT; + return WALK_CONTINUE; } /** @@ -557,12 +583,24 @@ static const __be64 *gfs2_hole_walker(struct metapath *mp, static int gfs2_hole_size(struct inode *inode, sector_t lblock, u64 len, struct metapath *mp, struct iomap *iomap) { - struct gfs2_hole_walker_args args = { }; - int ret = 0; + struct metapath clone; + u64 hole_size; + int ret; - ret = gfs2_walk_metadata(inode, lblock, len, mp, gfs2_hole_walker, &args); - if (!ret) - iomap->length = args.blocks << inode->i_blkbits; + clone_metapath(&clone, mp); + ret = gfs2_walk_metadata(inode, &clone, len, gfs2_hole_walker); + if (ret < 0) + goto out; + + if (ret == 1) + hole_size = metapath_to_block(GFS2_SB(inode), &clone) - lblock; + else + hole_size = len; + iomap->length = hole_size << inode->i_blkbits; + ret = 0; + +out: + release_metapath(&clone); return ret; } @@ -1002,11 +1040,16 @@ static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, unsigned copied, struct page *page, struct iomap *iomap) { + struct gfs2_trans *tr = current->journal_info; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); if (page && !gfs2_is_stuffed(ip)) gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + + if (tr->tr_num_buf_new) + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + gfs2_trans_end(sdp); } @@ -1099,8 +1142,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, tr = current->journal_info; if (tr->tr_num_buf_new) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - else - gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]); gfs2_trans_end(sdp); } @@ -1181,10 +1222,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (ip->i_qadata && ip->i_qadata->qa_qd_num) gfs2_quota_unlock(ip); + + if (unlikely(!written)) + goto out_unlock; + if (iomap->flags & IOMAP_F_SIZE_CHANGED) mark_inode_dirty(inode); - gfs2_write_unlock(inode); + set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); +out_unlock: + gfs2_write_unlock(inode); out: return 0; } diff --git a/fs/io_uring.c b/fs/io_uring.c index e2a66e12fbc6..24bbe3cb7ad4 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -202,7 +202,7 @@ struct async_list { struct file *file; off_t io_end; - size_t io_pages; + size_t io_len; }; struct io_ring_ctx { @@ -333,7 +333,8 @@ struct io_kiocb { #define REQ_F_IO_DRAIN 16 /* drain existing IO first */ #define REQ_F_IO_DRAINED 32 /* drain done */ #define REQ_F_LINK 64 /* linked sqes */ -#define REQ_F_FAIL_LINK 128 /* fail rest of links */ +#define REQ_F_LINK_DONE 128 /* linked sqes done */ +#define REQ_F_FAIL_LINK 256 /* fail rest of links */ u64 user_data; u32 result; u32 sequence; @@ -429,7 +430,7 @@ static inline bool io_sequence_defer(struct io_ring_ctx *ctx, if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) return false; - return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped; + return req->sequence != ctx->cached_cq_tail + ctx->sq_ring->dropped; } static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) @@ -632,6 +633,7 @@ static void io_req_link_next(struct io_kiocb *req) nxt->flags |= REQ_F_LINK; } + nxt->flags |= REQ_F_LINK_DONE; INIT_WORK(&nxt->work, io_sq_wq_submit_work); queue_work(req->ctx->sqo_wq, &nxt->work); } @@ -1064,8 +1066,42 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, */ offset = buf_addr - imu->ubuf; iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); - if (offset) - iov_iter_advance(iter, offset); + + if (offset) { + /* + * Don't use iov_iter_advance() here, as it's really slow for + * using the latter parts of a big fixed buffer - it iterates + * over each segment manually. We can cheat a bit here, because + * we know that: + * + * 1) it's a BVEC iter, we set it up + * 2) all bvecs are PAGE_SIZE in size, except potentially the + * first and last bvec + * + * So just find our index, and adjust the iterator afterwards. + * If the offset is within the first bvec (or the whole first + * bvec, just use iov_iter_advance(). This makes it easier + * since we can just skip the first segment, which may not + * be PAGE_SIZE aligned. + */ + const struct bio_vec *bvec = imu->bvec; + + if (offset <= bvec->bv_len) { + iov_iter_advance(iter, offset); + } else { + unsigned long seg_skip; + + /* skip first vec */ + offset -= bvec->bv_len; + seg_skip = 1 + (offset >> PAGE_SHIFT); + + iter->bvec = bvec + seg_skip; + iter->nr_segs -= seg_skip; + iter->count -= bvec->bv_len + offset; + iter->iov_offset = offset & ~PAGE_MASK; + } + } + return 0; } @@ -1120,28 +1156,26 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) off_t io_end = kiocb->ki_pos + len; if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) { - unsigned long max_pages; + unsigned long max_bytes; /* Use 8x RA size as a decent limiter for both reads/writes */ - max_pages = filp->f_ra.ra_pages; - if (!max_pages) - max_pages = VM_READAHEAD_PAGES; - max_pages *= 8; - - /* If max pages are exceeded, reset the state */ - len >>= PAGE_SHIFT; - if (async_list->io_pages + len <= max_pages) { + max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3); + if (!max_bytes) + max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3); + + /* If max len are exceeded, reset the state */ + if (async_list->io_len + len <= max_bytes) { req->flags |= REQ_F_SEQ_PREV; - async_list->io_pages += len; + async_list->io_len += len; } else { io_end = 0; - async_list->io_pages = 0; + async_list->io_len = 0; } } /* New file? Reset state. */ if (async_list->file != filp) { - async_list->io_pages = 0; + async_list->io_len = 0; async_list->file = filp; } async_list->io_end = io_end; @@ -1630,6 +1664,8 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) INIT_LIST_HEAD(&poll->wait.entry); init_waitqueue_func_entry(&poll->wait, io_poll_wake); + INIT_LIST_HEAD(&req->list); + mask = vfs_poll(poll->file, &ipt.pt) & poll->events; spin_lock_irq(&ctx->completion_lock); @@ -1800,6 +1836,7 @@ restart: do { struct sqe_submit *s = &req->submit; const struct io_uring_sqe *sqe = s->sqe; + unsigned int flags = req->flags; /* Ensure we clear previously set non-block flag */ req->rw.ki_flags &= ~IOCB_NOWAIT; @@ -1844,6 +1881,10 @@ restart: /* async context always use a copy of the sqe */ kfree(sqe); + /* req from defer and link list needn't decrease async cnt */ + if (flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) + goto out; + if (!async_list) break; if (!list_empty(&req_list)) { @@ -1891,6 +1932,7 @@ restart: } } +out: if (cur_mm) { set_fs(old_fs); unuse_mm(cur_mm); @@ -1917,6 +1959,10 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) ret = true; spin_lock(&list->lock); list_add_tail(&req->list, &list->list); + /* + * Ensure we see a simultaneous modification from io_sq_wq_submit_work() + */ + smp_mb(); if (!atomic_read(&list->cnt)) { list_del_init(&req->list); ret = false; @@ -1977,6 +2023,15 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, { int ret; + ret = io_req_defer(ctx, req, s->sqe); + if (ret) { + if (ret != -EIOCBQUEUED) { + io_free_req(req); + io_cqring_add_event(ctx, s->sqe->user_data, ret); + } + return 0; + } + ret = __io_submit_sqe(ctx, req, s, true); if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { struct io_uring_sqe *sqe_copy; @@ -2049,13 +2104,6 @@ err: return; } - ret = io_req_defer(ctx, req, s->sqe); - if (ret) { - if (ret != -EIOCBQUEUED) - goto err_req; - return; - } - /* * If we already have a head request, queue this one for async * submittal once the head completes. If we don't have a head but diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile index 2d165388d952..93cd11938bf5 100644 --- a/fs/iomap/Makefile +++ b/fs/iomap/Makefile @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-or-newer +# SPDX-License-Identifier: GPL-2.0-or-later # # Copyright (c) 2019 Oracle. # All Rights Reserved. diff --git a/fs/namespace.c b/fs/namespace.c index 6464ea4acba9..d28d30b13043 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1463,7 +1463,6 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); - if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { @@ -1471,10 +1470,11 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); - hlist_add_head(&p->mnt_umount, &unmounted); } } change_mnt_propagation(p, MS_PRIVATE); + if (disconnect) + hlist_add_head(&p->mnt_umount, &unmounted); } } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 0ff3facf81da..071b90a45933 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -153,7 +153,7 @@ again: /* Block nfs4_proc_unlck */ mutex_lock(&sp->so_delegreturn_mutex); seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); - err = nfs4_open_delegation_recall(ctx, state, stateid, type); + err = nfs4_open_delegation_recall(ctx, state, stateid); if (!err) err = nfs_delegation_claim_locks(state, stateid); if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) @@ -1046,6 +1046,22 @@ void nfs_test_expired_all_delegations(struct nfs_client *clp) nfs4_schedule_state_manager(clp); } +static void +nfs_delegation_test_free_expired(struct inode *inode, + nfs4_stateid *stateid, + const struct cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + const struct nfs4_minor_version_ops *ops = server->nfs_client->cl_mvops; + int status; + + if (!cred) + return; + status = ops->test_and_free_expired(server, stateid, cred); + if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) + nfs_remove_bad_delegation(inode, stateid); +} + /** * nfs_reap_expired_delegations - reap expired delegations * @clp: nfs_client to process @@ -1057,7 +1073,6 @@ void nfs_test_expired_all_delegations(struct nfs_client *clp) */ void nfs_reap_expired_delegations(struct nfs_client *clp) { - const struct nfs4_minor_version_ops *ops = clp->cl_mvops; struct nfs_delegation *delegation; struct nfs_server *server; struct inode *inode; @@ -1088,11 +1103,7 @@ restart: nfs4_stateid_copy(&stateid, &delegation->stateid); clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags); rcu_read_unlock(); - if (cred != NULL && - ops->test_and_free_expired(server, &stateid, cred) < 0) { - nfs_revoke_delegation(inode, &stateid); - nfs_inode_find_state_and_recover(inode, &stateid); - } + nfs_delegation_test_free_expired(inode, &stateid, cred); put_cred(cred); if (nfs4_server_rebooted(clp)) { nfs_inode_mark_test_expired_delegation(server,inode); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 5799777df5ec..9eb87ae4c982 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -63,7 +63,7 @@ void nfs_reap_expired_delegations(struct nfs_client *clp); /* NFSv4 delegation-related procedures */ int nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, const nfs4_stateid *stateid, int issync); -int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type); +int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid); int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred); bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode); diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 53507aa96b0b..3800ab6f08fa 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -114,6 +114,10 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int struct rb_node **p, *parent; int diff; + nfss->fscache_key = NULL; + nfss->fscache = NULL; + if (!(nfss->options & NFS_OPTION_FSCACHE)) + return; if (!uniq) { uniq = ""; ulen = 1; @@ -226,10 +230,11 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) void nfs_fscache_init_inode(struct inode *inode) { struct nfs_fscache_inode_auxdata auxdata; + struct nfs_server *nfss = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode); nfsi->fscache = NULL; - if (!S_ISREG(inode->i_mode)) + if (!(nfss->fscache && S_ISREG(inode->i_mode))) return; memset(&auxdata, 0, sizeof(auxdata)); diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 25a75e40d91d..ad041cfbf9ec 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -182,7 +182,7 @@ static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) */ static inline const char *nfs_server_fscache_state(struct nfs_server *server) { - if (server->fscache && (server->options & NFS_OPTION_FSCACHE)) + if (server->fscache) return "yes"; return "no "; } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index d778dad9a75e..3564da1ba8a1 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -465,7 +465,8 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, const struct cred *, gfp_t); extern void nfs4_put_state_owner(struct nfs4_state_owner *); -extern void nfs4_purge_state_owners(struct nfs_server *); +extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *); +extern void nfs4_free_state_owners(struct list_head *head); extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *); extern void nfs4_put_open_state(struct nfs4_state *); extern void nfs4_close_state(struct nfs4_state *, fmode_t); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 616393a01c06..da6204025a2d 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -758,9 +758,12 @@ out: static void nfs4_destroy_server(struct nfs_server *server) { + LIST_HEAD(freeme); + nfs_server_return_all_delegations(server); unset_pnfs_layoutdriver(server); - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); + nfs4_free_state_owners(&freeme); } /* diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 39896afc6edf..1406858bae6c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1683,6 +1683,14 @@ static void nfs_state_set_open_stateid(struct nfs4_state *state, write_sequnlock(&state->seqlock); } +static void nfs_state_clear_open_state_flags(struct nfs4_state *state) +{ + clear_bit(NFS_O_RDWR_STATE, &state->flags); + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + clear_bit(NFS_OPEN_STATE, &state->flags); +} + static void nfs_state_set_delegation(struct nfs4_state *state, const nfs4_stateid *deleg_stateid, fmode_t fmode) @@ -1907,8 +1915,9 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); update: - update_open_stateid(state, &data->o_res.stateid, NULL, - data->o_arg.fmode); + if (!update_open_stateid(state, &data->o_res.stateid, + NULL, data->o_arg.fmode)) + return ERR_PTR(-EAGAIN); refcount_inc(&state->count); return state; @@ -1973,8 +1982,11 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); - update_open_stateid(state, &data->o_res.stateid, NULL, - data->o_arg.fmode); + if (!update_open_stateid(state, &data->o_res.stateid, + NULL, data->o_arg.fmode)) { + nfs4_put_open_state(state); + state = ERR_PTR(-EAGAIN); + } out: nfs_release_seqid(data->o_arg.seqid); return state; @@ -2074,13 +2086,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state * { int ret; - /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */ - clear_bit(NFS_O_RDWR_STATE, &state->flags); - clear_bit(NFS_O_WRONLY_STATE, &state->flags); - clear_bit(NFS_O_RDONLY_STATE, &state->flags); /* memory barrier prior to reading state->n_* */ - clear_bit(NFS_DELEGATED_STATE, &state->flags); - clear_bit(NFS_OPEN_STATE, &state->flags); smp_rmb(); ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE); if (ret != 0) @@ -2156,6 +2162,8 @@ static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *sta ctx = nfs4_state_find_open_context(state); if (IS_ERR(ctx)) return -EAGAIN; + clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_open_state_flags(state); ret = nfs4_do_open_reclaim(ctx, state); put_nfs_open_context(ctx); return ret; @@ -2171,18 +2179,17 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct case -ENOENT: case -EAGAIN: case -ESTALE: + case -ETIMEDOUT: break; case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: case -NFS4ERR_DEADSESSION: - set_bit(NFS_DELEGATED_STATE, &state->flags); nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); return -EAGAIN; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_STALE_STATEID: - set_bit(NFS_DELEGATED_STATE, &state->flags); /* Don't recall a delegation if it was lost */ nfs4_schedule_lease_recovery(server->nfs_client); return -EAGAIN; @@ -2203,7 +2210,6 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct return -EAGAIN; case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: - set_bit(NFS_DELEGATED_STATE, &state->flags); ssleep(1); return -EAGAIN; case -ENOMEM: @@ -2219,8 +2225,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct } int nfs4_open_delegation_recall(struct nfs_open_context *ctx, - struct nfs4_state *state, const nfs4_stateid *stateid, - fmode_t type) + struct nfs4_state *state, const nfs4_stateid *stateid) { struct nfs_server *server = NFS_SERVER(state->inode); struct nfs4_opendata *opendata; @@ -2231,20 +2236,23 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, if (IS_ERR(opendata)) return PTR_ERR(opendata); nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); - nfs_state_clear_delegation(state); - switch (type & (FMODE_READ|FMODE_WRITE)) { - case FMODE_READ|FMODE_WRITE: - case FMODE_WRITE: + if (!test_bit(NFS_O_RDWR_STATE, &state->flags)) { err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE); if (err) - break; + goto out; + } + if (!test_bit(NFS_O_WRONLY_STATE, &state->flags)) { err = nfs4_open_recover_helper(opendata, FMODE_WRITE); if (err) - break; - /* Fall through */ - case FMODE_READ: + goto out; + } + if (!test_bit(NFS_O_RDONLY_STATE, &state->flags)) { err = nfs4_open_recover_helper(opendata, FMODE_READ); + if (err) + goto out; } + nfs_state_clear_delegation(state); +out: nfs4_opendata_put(opendata); return nfs4_handle_delegation_recall_error(server, state, stateid, NULL, err); } @@ -2492,6 +2500,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, if (!ctx) { nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1, 1); data->is_recover = true; + task_setup_data.flags |= RPC_TASK_TIMEOUT; } else { nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1, 0); pnfs_lgopen_prepare(data, ctx); @@ -2698,6 +2707,7 @@ static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { /* NFSv4.0 doesn't allow for delegation recovery on open expire */ nfs40_clear_delegation_stateid(state); + nfs_state_clear_open_state_flags(state); return nfs4_open_expired(sp, state); } @@ -2740,13 +2750,13 @@ out_free: return -NFS4ERR_EXPIRED; } -static void nfs41_check_delegation_stateid(struct nfs4_state *state) +static int nfs41_check_delegation_stateid(struct nfs4_state *state) { struct nfs_server *server = NFS_SERVER(state->inode); nfs4_stateid stateid; struct nfs_delegation *delegation; const struct cred *cred = NULL; - int status; + int status, ret = NFS_OK; /* Get the delegation credential for use by test/free_stateid */ rcu_read_lock(); @@ -2754,20 +2764,15 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) if (delegation == NULL) { rcu_read_unlock(); nfs_state_clear_delegation(state); - return; + return NFS_OK; } nfs4_stateid_copy(&stateid, &delegation->stateid); - if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { - rcu_read_unlock(); - nfs_state_clear_delegation(state); - return; - } if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags)) { rcu_read_unlock(); - return; + return NFS_OK; } if (delegation->cred) @@ -2777,9 +2782,24 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) trace_nfs4_test_delegation_stateid(state, NULL, status); if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) nfs_finish_clear_delegation_stateid(state, &stateid); + else + ret = status; - if (delegation->cred) - put_cred(cred); + put_cred(cred); + return ret; +} + +static void nfs41_delegation_recover_stateid(struct nfs4_state *state) +{ + nfs4_stateid tmp; + + if (test_bit(NFS_DELEGATED_STATE, &state->flags) && + nfs4_copy_delegation_stateid(state->inode, state->state, + &tmp, NULL) && + nfs4_stateid_match_other(&state->stateid, &tmp)) + nfs_state_set_delegation(state, &tmp, state->state); + else + nfs_state_clear_delegation(state); } /** @@ -2849,21 +2869,12 @@ static int nfs41_check_open_stateid(struct nfs4_state *state) const struct cred *cred = state->owner->so_cred; int status; - if (test_bit(NFS_OPEN_STATE, &state->flags) == 0) { - if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) { - if (nfs4_have_delegation(state->inode, state->state)) - return NFS_OK; - return -NFS4ERR_OPENMODE; - } + if (test_bit(NFS_OPEN_STATE, &state->flags) == 0) return -NFS4ERR_BAD_STATEID; - } status = nfs41_test_and_free_expired_stateid(server, stateid, cred); trace_nfs4_test_open_stateid(state, NULL, status); if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) { - clear_bit(NFS_O_RDONLY_STATE, &state->flags); - clear_bit(NFS_O_WRONLY_STATE, &state->flags); - clear_bit(NFS_O_RDWR_STATE, &state->flags); - clear_bit(NFS_OPEN_STATE, &state->flags); + nfs_state_clear_open_state_flags(state); stateid->type = NFS4_INVALID_STATEID_TYPE; return status; } @@ -2876,7 +2887,11 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { int status; - nfs41_check_delegation_stateid(state); + status = nfs41_check_delegation_stateid(state); + if (status != NFS_OK) + return status; + nfs41_delegation_recover_stateid(state); + status = nfs41_check_expired_locks(state); if (status != NFS_OK) return status; @@ -3201,7 +3216,7 @@ static int _nfs4_do_setattr(struct inode *inode, if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) { /* Use that stateid */ - } else if (ctx != NULL) { + } else if (ctx != NULL && ctx->state) { struct nfs_lock_context *l_ctx; if (!nfs4_valid_open_stateid(ctx->state)) return -EBADF; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 9afd051a4876..cad4e064b328 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -624,24 +624,39 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp) /** * nfs4_purge_state_owners - Release all cached state owners * @server: nfs_server with cached state owners to release + * @head: resulting list of state owners * * Called at umount time. Remaining state owners will be on * the LRU with ref count of zero. + * Note that the state owners are not freed, but are added + * to the list @head, which can later be used as an argument + * to nfs4_free_state_owners. */ -void nfs4_purge_state_owners(struct nfs_server *server) +void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head) { struct nfs_client *clp = server->nfs_client; struct nfs4_state_owner *sp, *tmp; - LIST_HEAD(doomed); spin_lock(&clp->cl_lock); list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) { - list_move(&sp->so_lru, &doomed); + list_move(&sp->so_lru, head); nfs4_remove_state_owner_locked(sp); } spin_unlock(&clp->cl_lock); +} - list_for_each_entry_safe(sp, tmp, &doomed, so_lru) { +/** + * nfs4_purge_state_owners - Release all cached state owners + * @head: resulting list of state owners + * + * Frees a list of state owners that was generated by + * nfs4_purge_state_owners + */ +void nfs4_free_state_owners(struct list_head *head) +{ + struct nfs4_state_owner *sp, *tmp; + + list_for_each_entry_safe(sp, tmp, head, so_lru) { list_del(&sp->so_lru); nfs4_free_state_owner(sp); } @@ -1463,7 +1478,7 @@ void nfs_inode_find_state_and_recover(struct inode *inode, nfs4_schedule_state_manager(clp); } -static void nfs4_state_mark_open_context_bad(struct nfs4_state *state) +static void nfs4_state_mark_open_context_bad(struct nfs4_state *state, int err) { struct inode *inode = state->inode; struct nfs_inode *nfsi = NFS_I(inode); @@ -1474,6 +1489,8 @@ static void nfs4_state_mark_open_context_bad(struct nfs4_state *state) if (ctx->state != state) continue; set_bit(NFS_CONTEXT_BAD, &ctx->flags); + pr_warn("NFSv4: state recovery failed for open file %pd2, " + "error = %d\n", ctx->dentry, err); } rcu_read_unlock(); } @@ -1481,7 +1498,7 @@ static void nfs4_state_mark_open_context_bad(struct nfs4_state *state) static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error) { set_bit(NFS_STATE_RECOVERY_FAILED, &state->flags); - nfs4_state_mark_open_context_bad(state); + nfs4_state_mark_open_context_bad(state, error); } @@ -1512,6 +1529,7 @@ restart: switch (status) { case 0: break; + case -ETIMEDOUT: case -ESTALE: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: @@ -1605,6 +1623,7 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops) { struct nfs4_state *state; + unsigned int loop = 0; int status = 0; /* Note: we rely on the sp->so_states list being ordered @@ -1631,8 +1650,10 @@ restart: switch (status) { default: - if (status >= 0) + if (status >= 0) { + loop = 0; break; + } printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status); /* Fall through */ case -ENOENT: @@ -1646,6 +1667,10 @@ restart: break; case -EAGAIN: ssleep(1); + if (loop++ < 10) { + set_bit(ops->state_flag_bit, &state->flags); + break; + } /* Fall through */ case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: @@ -1658,11 +1683,13 @@ restart: case -NFS4ERR_EXPIRED: case -NFS4ERR_NO_GRACE: nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state); + /* Fall through */ case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -ETIMEDOUT: goto out_err; } nfs4_put_open_state(state); @@ -1856,12 +1883,13 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov struct nfs4_state_owner *sp; struct nfs_server *server; struct rb_node *pos; + LIST_HEAD(freeme); int status = 0; restart: rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); spin_lock(&clp->cl_lock); for (pos = rb_first(&server->state_owners); pos != NULL; @@ -1890,6 +1918,7 @@ restart: spin_unlock(&clp->cl_lock); } rcu_read_unlock(); + nfs4_free_state_owners(&freeme); return 0; } @@ -1945,7 +1974,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) return -EPERM; case -EACCES: case -NFS4ERR_DELAY: - case -ETIMEDOUT: case -EAGAIN: ssleep(1); break; @@ -2574,7 +2602,7 @@ static void nfs4_state_manager(struct nfs_client *clp) } /* Now recover expired state... */ - if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) { + if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) { section = "reclaim nograce"; status = nfs4_do_reclaim(clp, clp->cl_mvops->nograce_recovery_ops); @@ -2582,6 +2610,7 @@ static void nfs4_state_manager(struct nfs_client *clp) continue; if (status < 0) goto out_error; + clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state); } nfs4_end_drain_session(clp); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 75bd5b552ba4..4525d5acae38 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1903,12 +1903,6 @@ lookup_again: goto out_unlock; } - if (!nfs4_valid_open_stateid(ctx->state)) { - trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, - PNFS_UPDATE_LAYOUT_INVALID_OPEN); - goto out_unlock; - } - /* * Choose a stateid for the LAYOUTGET. If we don't have a layout * stateid, or it has been invalidated, then we must use the open @@ -1939,6 +1933,7 @@ lookup_again: iomode == IOMODE_RW ? FMODE_WRITE : FMODE_READ, NULL, &stateid, NULL); if (status != 0) { + lseg = ERR_PTR(status); trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_INVALID_OPEN); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 628631e2e34f..703f595dce90 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2260,6 +2260,7 @@ nfs_compare_remount_data(struct nfs_server *nfss, data->acdirmin != nfss->acdirmin / HZ || data->acdirmax != nfss->acdirmax / HZ || data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) || + (data->options & NFS_OPTION_FSCACHE) != (nfss->options & NFS_OPTION_FSCACHE) || data->nfs_server.port != nfss->port || data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen || !rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address, diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 385f3aaa2448..90c830e3758e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -3825,7 +3825,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb); int low_bucket = 0, bucket, high_bucket; struct ocfs2_xattr_bucket *search; - u32 last_hash; u64 blkno, lower_blkno = 0; search = ocfs2_xattr_bucket_new(inode); @@ -3869,8 +3868,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, if (xh->xh_count) xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1]; - last_hash = le32_to_cpu(xe->xe_name_hash); - /* record lower_blkno which may be the insert place. */ lower_blkno = blkno; diff --git a/fs/open.c b/fs/open.c index b5b80469b93d..a59abe3c669a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -374,6 +374,25 @@ long do_faccessat(int dfd, const char __user *filename, int mode) override_cred->cap_permitted; } + /* + * The new set of credentials can *only* be used in + * task-synchronous circumstances, and does not need + * RCU freeing, unless somebody then takes a separate + * reference to it. + * + * NOTE! This is _only_ true because this credential + * is used purely for override_creds() that installs + * it as the subjective cred. Other threads will be + * accessing ->real_cred, not the subjective cred. + * + * If somebody _does_ make a copy of this (using the + * 'get_current_cred()' function), that will clear the + * non_rcu field, because now that other user may be + * expecting RCU freeing. But normal thread-synchronous + * cred accesses will keep things non-RCY. + */ + override_cred->non_rcu = 1; + old_cred = override_creds(override_cred); retry: res = user_path_at(dfd, filename, lookup_flags, &path); diff --git a/fs/seq_file.c b/fs/seq_file.c index 04f09689cd6d..1600034a929b 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -119,6 +119,7 @@ static int traverse(struct seq_file *m, loff_t offset) } if (seq_has_overflowed(m)) goto Eoverflow; + p = m->op->next(m, p, &m->index); if (pos + m->count > offset) { m->from = offset - pos; m->count -= m->from; @@ -126,7 +127,6 @@ static int traverse(struct seq_file *m, loff_t offset) } pos += m->count; m->count = 0; - p = m->op->next(m, p, &m->index); if (pos == offset) break; } diff --git a/fs/super.c b/fs/super.c index 113c58f19425..5960578a4076 100644 --- a/fs/super.c +++ b/fs/super.c @@ -478,13 +478,10 @@ EXPORT_SYMBOL(generic_shutdown_super); bool mount_capable(struct fs_context *fc) { - struct user_namespace *user_ns = fc->global ? &init_user_ns - : fc->user_ns; - if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) return capable(CAP_SYS_ADMIN); else - return ns_capable(user_ns, CAP_SYS_ADMIN); + return ns_capable(fc->user_ns, CAP_SYS_ADMIN); } /** diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index baf0b72c0a37..07aad70f3931 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3835,15 +3835,28 @@ xfs_bmapi_read( XFS_STATS_INC(mp, xs_blk_mapr); ifp = XFS_IFORK_PTR(ip, whichfork); + if (!ifp) { + /* No CoW fork? Return a hole. */ + if (whichfork == XFS_COW_FORK) { + mval->br_startoff = bno; + mval->br_startblock = HOLESTARTBLOCK; + mval->br_blockcount = len; + mval->br_state = XFS_EXT_NORM; + *nmap = 1; + return 0; + } - /* No CoW fork? Return a hole. */ - if (whichfork == XFS_COW_FORK && !ifp) { - mval->br_startoff = bno; - mval->br_startblock = HOLESTARTBLOCK; - mval->br_blockcount = len; - mval->br_state = XFS_EXT_NORM; - *nmap = 1; - return 0; + /* + * A missing attr ifork implies that the inode says we're in + * extents or btree format but failed to pass the inode fork + * verifier while trying to load it. Treat that as a file + * corruption too. + */ +#ifdef DEBUG + xfs_alert(mp, "%s: inode %llu missing fork %d", + __func__, ip->i_ino, whichfork); +#endif /* DEBUG */ + return -EFSCORRUPTED; } if (!(ifp->if_flags & XFS_IFEXTENTS)) { diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index d1c77fd0815d..0bf56e94bfe9 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -487,10 +487,8 @@ xfs_da3_split( ASSERT(state->path.active == 0); oldblk = &state->path.blk[0]; error = xfs_da3_root_split(state, oldblk, addblk); - if (error) { - addblk->bp = NULL; - return error; /* GROT: dir is inconsistent */ - } + if (error) + goto out; /* * Update pointers to the node which used to be block 0 and just got @@ -505,7 +503,10 @@ xfs_da3_split( */ node = oldblk->bp->b_addr; if (node->hdr.info.forw) { - ASSERT(be32_to_cpu(node->hdr.info.forw) == addblk->blkno); + if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) { + error = -EFSCORRUPTED; + goto out; + } node = addblk->bp->b_addr; node->hdr.info.back = cpu_to_be32(oldblk->blkno); xfs_trans_log_buf(state->args->trans, addblk->bp, @@ -514,15 +515,19 @@ xfs_da3_split( } node = oldblk->bp->b_addr; if (node->hdr.info.back) { - ASSERT(be32_to_cpu(node->hdr.info.back) == addblk->blkno); + if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) { + error = -EFSCORRUPTED; + goto out; + } node = addblk->bp->b_addr; node->hdr.info.forw = cpu_to_be32(oldblk->blkno); xfs_trans_log_buf(state->args->trans, addblk->bp, XFS_DA_LOGRANGE(node, &node->hdr.info, sizeof(node->hdr.info))); } +out: addblk->bp = NULL; - return 0; + return error; } /* diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index afcc6642690a..1fc44efc344d 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -741,7 +741,8 @@ xfs_dir2_leafn_lookup_for_entry( ents = dp->d_ops->leaf_ents_p(leaf); xfs_dir3_leaf_check(dp, bp); - ASSERT(leafhdr.count > 0); + if (leafhdr.count <= 0) + return -EFSCORRUPTED; /* * Look up the hash value in the leaf entries. diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index 94c4f1de1922..77ff9f97bcda 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -278,7 +278,11 @@ xchk_da_btree_block_check_sibling( /* Compare upper level pointer to sibling pointer. */ if (ds->state->altpath.blk[level].blkno != sibling) xchk_da_set_corrupt(ds, level); - xfs_trans_brelse(ds->dargs.trans, ds->state->altpath.blk[level].bp); + if (ds->state->altpath.blk[level].bp) { + xfs_trans_brelse(ds->dargs.trans, + ds->state->altpath.blk[level].bp); + ds->state->altpath.blk[level].bp = NULL; + } out: return error; } diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index a8a06bb78ea8..f5c955d35be4 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -272,6 +272,7 @@ xfs_bulkstat_to_bstat( struct xfs_bstat *bs1, const struct xfs_bulkstat *bstat) { + /* memset is needed here because of padding holes in the structure. */ memset(bs1, 0, sizeof(struct xfs_bstat)); bs1->bs_ino = bstat->bs_ino; bs1->bs_mode = bstat->bs_mode; @@ -388,6 +389,8 @@ xfs_inumbers_to_inogrp( struct xfs_inogrp *ig1, const struct xfs_inumbers *ig) { + /* memset is needed here because of padding holes in the structure. */ + memset(ig1, 0, sizeof(struct xfs_inogrp)); ig1->xi_startino = ig->xi_startino; ig1->xi_alloccount = ig->xi_alloccount; ig1->xi_allocmask = ig->xi_allocmask; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 00e9f5c388d3..7fc3c1ad36bc 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -429,10 +429,7 @@ xfs_log_reserve( ASSERT(*ticp == NULL); tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent, - KM_SLEEP | KM_MAYFAIL); - if (!tic) - return -ENOMEM; - + KM_SLEEP); *ticp = tic; xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt |