diff options
Diffstat (limited to 'fs')
213 files changed, 3735 insertions, 2042 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 15a99f9c7253..39def020a074 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -500,10 +500,9 @@ void v9fs_session_close(struct v9fs_session_info *v9ses) } #ifdef CONFIG_9P_FSCACHE - if (v9ses->fscache) { + if (v9ses->fscache) v9fs_cache_session_put_cookie(v9ses); - kfree(v9ses->cachetag); - } + kfree(v9ses->cachetag); #endif kfree(v9ses->uname); kfree(v9ses->aname); diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index f708c45d5f66..29f11e10a7c7 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -420,24 +420,51 @@ affs_mode_to_prot(struct inode *inode) u32 prot = AFFS_I(inode)->i_protect; umode_t mode = inode->i_mode; + /* + * First, clear all RWED bits for owner, group, other. + * Then, recalculate them afresh. + * + * We'll always clear the delete-inhibit bit for the owner, as that is + * the classic single-user mode AmigaOS protection bit and we need to + * stay compatible with all scenarios. + * + * Since multi-user AmigaOS is an extension, we'll only set the + * delete-allow bit if any of the other bits in the same user class + * (group/other) are used. + */ + prot &= ~(FIBF_NOEXECUTE | FIBF_NOREAD + | FIBF_NOWRITE | FIBF_NODELETE + | FIBF_GRP_EXECUTE | FIBF_GRP_READ + | FIBF_GRP_WRITE | FIBF_GRP_DELETE + | FIBF_OTR_EXECUTE | FIBF_OTR_READ + | FIBF_OTR_WRITE | FIBF_OTR_DELETE); + + /* Classic single-user AmigaOS flags. These are inverted. */ if (!(mode & 0100)) prot |= FIBF_NOEXECUTE; if (!(mode & 0400)) prot |= FIBF_NOREAD; if (!(mode & 0200)) prot |= FIBF_NOWRITE; + + /* Multi-user extended flags. Not inverted. */ if (mode & 0010) prot |= FIBF_GRP_EXECUTE; if (mode & 0040) prot |= FIBF_GRP_READ; if (mode & 0020) prot |= FIBF_GRP_WRITE; + if (mode & 0070) + prot |= FIBF_GRP_DELETE; + if (mode & 0001) prot |= FIBF_OTR_EXECUTE; if (mode & 0004) prot |= FIBF_OTR_READ; if (mode & 0002) prot |= FIBF_OTR_WRITE; + if (mode & 0007) + prot |= FIBF_OTR_DELETE; AFFS_I(inode)->i_protect = prot; } diff --git a/fs/affs/file.c b/fs/affs/file.c index a85817f54483..ba084b0b214b 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -428,6 +428,24 @@ static int affs_write_begin(struct file *file, struct address_space *mapping, return ret; } +static int affs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int copied, + struct page *page, void *fsdata) +{ + struct inode *inode = mapping->host; + int ret; + + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + + /* Clear Archived bit on file writes, as AmigaOS would do */ + if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { + AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED; + mark_inode_dirty(inode); + } + + return ret; +} + static sector_t _affs_bmap(struct address_space *mapping, sector_t block) { return generic_block_bmap(mapping,block,affs_get_block); @@ -437,7 +455,7 @@ const struct address_space_operations affs_aops = { .readpage = affs_readpage, .writepage = affs_writepage, .write_begin = affs_write_begin, - .write_end = generic_write_end, + .write_end = affs_write_end, .direct_IO = affs_direct_IO, .bmap = _affs_bmap }; @@ -794,6 +812,12 @@ done: if (tmp > inode->i_size) inode->i_size = AFFS_I(inode)->mmu_private = tmp; + /* Clear Archived bit on file writes, as AmigaOS would do */ + if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { + AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED; + mark_inode_dirty(inode); + } + err_first_bh: unlock_page(page); put_page(page); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 78ba5f932287..296b489861a9 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -154,10 +154,17 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, return ERR_PTR(-ENOMEM); } + cell->name = kmalloc(namelen + 1, GFP_KERNEL); + if (!cell->name) { + kfree(cell); + return ERR_PTR(-ENOMEM); + } + cell->net = net; cell->name_len = namelen; for (i = 0; i < namelen; i++) cell->name[i] = tolower(name[i]); + cell->name[i] = 0; atomic_set(&cell->usage, 2); INIT_WORK(&cell->manager, afs_manage_cell); @@ -203,6 +210,7 @@ parse_failed: if (ret == -EINVAL) printk(KERN_ERR "kAFS: bad VL server IP address\n"); error: + kfree(cell->name); kfree(cell); _leave(" = %d", ret); return ERR_PTR(ret); @@ -483,6 +491,7 @@ static void afs_cell_destroy(struct rcu_head *rcu) afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers)); key_put(cell->anonymous_key); + kfree(cell->name); kfree(cell); _leave(" [destroyed]"); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index d1e1caa23c8b..3c486340b220 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -658,7 +658,8 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, cookie->ctx.actor = afs_lookup_filldir; cookie->name = dentry->d_name; - cookie->nr_fids = 1; /* slot 0 is saved for the fid we actually want */ + cookie->nr_fids = 2; /* slot 0 is saved for the fid we actually want + * and slot 1 for the directory */ read_seqlock_excl(&dvnode->cb_lock); dcbi = rcu_dereference_protected(dvnode->cb_interest, @@ -709,7 +710,11 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, if (!cookie->inodes) goto out_s; - for (i = 1; i < cookie->nr_fids; i++) { + cookie->fids[1] = dvnode->fid; + cookie->statuses[1].cb_break = afs_calc_vnode_cb_break(dvnode); + cookie->inodes[1] = igrab(&dvnode->vfs_inode); + + for (i = 2; i < cookie->nr_fids; i++) { scb = &cookie->statuses[i]; /* Find any inodes that already exist and get their diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 7503899c0a1b..f07e53ab808e 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -289,15 +289,17 @@ void afs_dynroot_depopulate(struct super_block *sb) net->dynroot_sb = NULL; mutex_unlock(&net->proc_cells_lock); - inode_lock(root->d_inode); - - /* Remove all the pins for dirs created for manually added cells */ - list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { - if (subdir->d_fsdata) { - subdir->d_fsdata = NULL; - dput(subdir); + if (root) { + inode_lock(root->d_inode); + + /* Remove all the pins for dirs created for manually added cells */ + list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { + if (subdir->d_fsdata) { + subdir->d_fsdata = NULL; + dput(subdir); + } } - } - inode_unlock(root->d_inode); + inode_unlock(root->d_inode); + } } diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 02e976ca5732..51ee3dd79700 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -92,8 +92,8 @@ responded: } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; alist->preferred = index; have_result = true; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 0a4fed9e706b..5c2729fc07e5 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -56,16 +56,15 @@ static void xdr_dump_bad(const __be32 *bp) /* * decode an AFSFetchStatus block */ -static int xdr_decode_AFSFetchStatus(const __be32 **_bp, - struct afs_call *call, - struct afs_status_cb *scb) +static void xdr_decode_AFSFetchStatus(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp; struct afs_file_status *status = &scb->status; bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus); u64 data_version, size; u32 type, abort_code; - int ret; abort_code = ntohl(xdr->abort_code); @@ -79,7 +78,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, */ status->abort_code = abort_code; scb->have_error = true; - goto good; + goto advance; } pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version)); @@ -89,7 +88,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, if (abort_code != 0 && inline_error) { status->abort_code = abort_code; scb->have_error = true; - goto good; + goto advance; } type = ntohl(xdr->type); @@ -125,15 +124,13 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, data_version |= (u64)ntohl(xdr->data_version_hi) << 32; status->data_version = data_version; scb->have_status = true; -good: - ret = 0; advance: *_bp = (const void *)*_bp + sizeof(*xdr); - return ret; + return; bad: xdr_dump_bad(*_bp); - ret = afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); + afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); goto advance; } @@ -254,9 +251,7 @@ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); xdr_decode_AFSCallBack(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); @@ -419,9 +414,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); xdr_decode_AFSCallBack(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); @@ -579,12 +572,8 @@ static int afs_deliver_fs_create_vnode(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; xdr_decode_AFSFid(&bp, call->out_fid); - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); + xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_AFSCallBack(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); @@ -693,9 +682,7 @@ static int afs_deliver_fs_dir_status_and_vol(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); @@ -786,12 +773,8 @@ static int afs_deliver_fs_link(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); + xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); @@ -880,12 +863,8 @@ static int afs_deliver_fs_symlink(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; xdr_decode_AFSFid(&bp, call->out_fid); - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); + xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); @@ -988,16 +967,12 @@ static int afs_deliver_fs_rename(struct afs_call *call) if (ret < 0) return ret; + bp = call->buffer; /* If the two dirs are the same, we have two copies of the same status * report, so we just decode it twice. */ - bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); @@ -1105,9 +1080,7 @@ static int afs_deliver_fs_store_data(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); @@ -1285,9 +1258,7 @@ static int afs_deliver_fs_store_status(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); @@ -1956,9 +1927,7 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); xdr_decode_AFSCallBack(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); @@ -2064,10 +2033,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) bp = call->buffer; scb = &call->out_scb[call->count]; - ret = xdr_decode_AFSFetchStatus(&bp, call, scb); - if (ret < 0) - return ret; - + xdr_decode_AFSFetchStatus(&bp, call, scb); call->count++; if (call->count < call->count2) goto more_counts; @@ -2245,9 +2211,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); call->unmarshall++; @@ -2328,9 +2292,7 @@ static int afs_deliver_fs_file_status_and_vol(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 46d2d7cb461d..a74e8e209454 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -171,6 +171,7 @@ static void afs_apply_status(struct afs_fs_cursor *fc, struct timespec64 t; umode_t mode; bool data_changed = false; + bool change_size = false; BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags)); @@ -226,6 +227,7 @@ static void afs_apply_status(struct afs_fs_cursor *fc, } else { set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); } + change_size = true; } else if (vnode->status.type == AFS_FTYPE_DIR) { /* Expected directory change is handled elsewhere so * that we can locally edit the directory and save on a @@ -233,11 +235,19 @@ static void afs_apply_status(struct afs_fs_cursor *fc, */ if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) data_changed = false; + change_size = true; } if (data_changed) { inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); - afs_set_i_size(vnode, status->size); + + /* Only update the size if the data version jumped. If the + * file is being modified locally, then we might have our own + * idea of what the size should be that's not the same as + * what's on the server. + */ + if (change_size) + afs_set_i_size(vnode, status->size); } } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 485cc3b2aaa8..7fe88d918b23 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -161,6 +161,7 @@ struct afs_call { bool upgrade; /* T to request service upgrade */ bool have_reply_time; /* T if have got reply_time */ bool intr; /* T if interruptible */ + bool unmarshalling_error; /* T if an unmarshalling error occurred */ u16 service_id; /* Actual service ID (after upgrade) */ unsigned int debug_id; /* Trace ID */ u32 operation_ID; /* operation ID for an incoming call */ @@ -396,7 +397,7 @@ struct afs_cell { struct afs_vlserver_list __rcu *vl_servers; u8 name_len; /* Length of name */ - char name[64 + 1]; /* Cell name, case-flattened and NUL-padded */ + char *name; /* Cell name, case-flattened and NUL-padded */ }; /* diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 52b19e9c1535..5334f1bd2bca 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -83,6 +83,7 @@ int afs_abort_to_error(u32 abort_code) case UAENOLCK: return -ENOLCK; case UAENOTEMPTY: return -ENOTEMPTY; case UAELOOP: return -ELOOP; + case UAEOVERFLOW: return -EOVERFLOW; case UAENOMEDIUM: return -ENOMEDIUM; case UAEDQUOT: return -EDQUOT; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index fba2ec3a3a9c..106b27011f6d 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -562,6 +562,7 @@ void afs_put_sysnames(struct afs_sysnames *sysnames) if (sysnames->subs[i] != afs_init_sysname && sysnames->subs[i] != sysnames->blank) kfree(sysnames->subs[i]); + kfree(sysnames); } } diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 52aa90fb4fbd..6adab30a8399 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -540,6 +540,8 @@ static void afs_deliver_to_call(struct afs_call *call) ret = call->type->deliver(call); state = READ_ONCE(call->state); + if (ret == 0 && call->unmarshalling_error) + ret = -EBADMSG; switch (ret) { case 0: afs_queue_call_work(call); @@ -963,5 +965,7 @@ noinline int afs_protocol_error(struct afs_call *call, int error, enum afs_eproto_cause cause) { trace_afs_protocol_error(call, error, cause); + if (call) + call->unmarshalling_error = true; return error; } diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index e3aa013c2177..081b7e5b13f5 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -92,8 +92,8 @@ responded: } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; alist->preferred = index; have_result = true; diff --git a/fs/afs/write.c b/fs/afs/write.c index cb76566763db..96b042af6248 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -194,11 +194,11 @@ int afs_write_end(struct file *file, struct address_space *mapping, i_size = i_size_read(&vnode->vfs_inode); if (maybe_i_size > i_size) { - spin_lock(&vnode->wb_lock); + write_seqlock(&vnode->cb_lock); i_size = i_size_read(&vnode->vfs_inode); if (maybe_i_size > i_size) i_size_write(&vnode->vfs_inode, maybe_i_size); - spin_unlock(&vnode->wb_lock); + write_sequnlock(&vnode->cb_lock); } if (!PageUptodate(page)) { @@ -811,6 +811,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) vmf->page->index, priv); SetPagePrivate(vmf->page); set_page_private(vmf->page, priv); + file_update_time(file); sb_end_pagefault(inode->i_sb); return VM_FAULT_LOCKED; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 8af7f093305d..d21cf61d86b9 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -179,21 +179,20 @@ static void xdr_dump_bad(const __be32 *bp) /* * Decode a YFSFetchStatus block */ -static int xdr_decode_YFSFetchStatus(const __be32 **_bp, - struct afs_call *call, - struct afs_status_cb *scb) +static void xdr_decode_YFSFetchStatus(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { const struct yfs_xdr_YFSFetchStatus *xdr = (const void *)*_bp; struct afs_file_status *status = &scb->status; u32 type; - int ret; status->abort_code = ntohl(xdr->abort_code); if (status->abort_code != 0) { if (status->abort_code == VNOVNODE) status->nlink = 0; scb->have_error = true; - goto good; + goto advance; } type = ntohl(xdr->type); @@ -221,15 +220,13 @@ static int xdr_decode_YFSFetchStatus(const __be32 **_bp, status->size = xdr_to_u64(xdr->size); status->data_version = xdr_to_u64(xdr->data_version); scb->have_status = true; -good: - ret = 0; advance: *_bp += xdr_size(xdr); - return ret; + return; bad: xdr_dump_bad(*_bp); - ret = afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); + afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); goto advance; } @@ -348,9 +345,7 @@ static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); xdr_decode_YFSCallBack(&bp, call, call->out_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); @@ -372,9 +367,7 @@ static int yfs_deliver_status_and_volsync(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); @@ -534,9 +527,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); xdr_decode_YFSCallBack(&bp, call, call->out_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); @@ -645,12 +636,8 @@ static int yfs_deliver_fs_create_vnode(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; xdr_decode_YFSFid(&bp, call->out_fid); - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); + xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_YFSCallBack(&bp, call, call->out_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); @@ -803,14 +790,9 @@ static int yfs_deliver_fs_remove_file2(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - + xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_YFSFid(&bp, &fid); - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); /* Was deleted if vnode->status.abort_code == VNOVNODE. */ xdr_decode_YFSVolSync(&bp, call->out_volsync); @@ -890,10 +872,7 @@ static int yfs_deliver_fs_remove(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - + xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); return 0; } @@ -975,12 +954,8 @@ static int yfs_deliver_fs_link(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); + xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1062,12 +1037,8 @@ static int yfs_deliver_fs_symlink(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; xdr_decode_YFSFid(&bp, call->out_fid); - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); + xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); @@ -1155,13 +1126,11 @@ static int yfs_deliver_fs_rename(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - + /* If the two dirs are the same, we have two copies of the same status + * report, so we just decode it twice. + */ + xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1846,9 +1815,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) bp = call->buffer; scb = &call->out_scb[call->count]; - ret = xdr_decode_YFSFetchStatus(&bp, call, scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, scb); call->count++; if (call->count < call->count2) @@ -2068,9 +2035,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) bp = call->buffer; yacl->inherit_flag = ntohl(*bp++); yacl->num_cleaned = ntohl(*bp++); - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 831a2b25ba79..196f9f64d075 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -571,7 +571,7 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - len = data_len + extra; + len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long); len = PAGE_ALIGN(len); realdatastart = vm_mmap(NULL, 0, len, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0); @@ -585,7 +585,9 @@ static int load_flat_file(struct linux_binprm *bprm, vm_munmap(textpos, text_len); goto err; } - datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN); + datapos = ALIGN(realdatastart + + MAX_SHARED_LIBS * sizeof(unsigned long), + FLAT_DATA_ALIGN); pr_debug("Allocated data+bss+stack (%u bytes): %lx\n", data_len + bss_len + stack_len, datapos); @@ -615,7 +617,7 @@ static int load_flat_file(struct linux_binprm *bprm, memp_size = len; } else { - len = text_len + data_len + extra; + len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32); len = PAGE_ALIGN(len); textpos = vm_mmap(NULL, 0, len, PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0); @@ -630,7 +632,9 @@ static int load_flat_file(struct linux_binprm *bprm, } realdatastart = textpos + ntohl(hdr->data_start); - datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN); + datapos = ALIGN(realdatastart + + MAX_SHARED_LIBS * sizeof(u32), + FLAT_DATA_ALIGN); reloc = (__be32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); @@ -647,9 +651,8 @@ static int load_flat_file(struct linux_binprm *bprm, (text_len + full_data - sizeof(struct flat_hdr)), 0); - if (datapos != realdatastart) - memmove((void *)datapos, (void *)realdatastart, - full_data); + memmove((void *) datapos, (void *) realdatastart, + full_data); #else /* * This is used on MMU systems mainly for testing. @@ -705,7 +708,8 @@ static int load_flat_file(struct linux_binprm *bprm, if (IS_ERR_VALUE(result)) { ret = result; pr_err("Unable to read code+data+bss, errno %d\n", ret); - vm_munmap(textpos, text_len + data_len + extra); + vm_munmap(textpos, text_len + data_len + extra + + MAX_SHARED_LIBS * sizeof(u32)); goto err; } } diff --git a/fs/block_dev.c b/fs/block_dev.c index 34644ce4b502..79272cdbe827 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1546,10 +1546,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) */ if (!for_part) { ret = devcgroup_inode_permission(bdev->bd_inode, perm); - if (ret != 0) { - bdput(bdev); + if (ret != 0) return ret; - } } restart: @@ -1618,8 +1616,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; BUG_ON(for_part); ret = __blkdev_get(whole, mode, 1); - if (ret) + if (ret) { + bdput(whole); goto out_clear; + } bdev->bd_contains = whole; bdev->bd_part = disk_get_part(disk, partno); if (!(disk->flags & GENHD_FL_UP) || @@ -1669,7 +1669,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) disk_unblock_events(disk); put_disk_and_module(disk); out: - bdput(bdev); return ret; } @@ -1736,6 +1735,9 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) bdput(whole); } + if (res) + bdput(bdev); + return res; } EXPORT_SYMBOL(blkdev_get); @@ -1855,6 +1857,16 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) struct gendisk *disk = bdev->bd_disk; struct block_device *victim = NULL; + /* + * Sync early if it looks like we're the last one. If someone else + * opens the block device between now and the decrement of bd_openers + * then we did a sync that we didn't need to, but that's not the end + * of the world and we want to avoid long (could be several minute) + * syncs while holding the mutex. + */ + if (bdev->bd_openers == 1) + sync_blockdev(bdev); + mutex_lock_nested(&bdev->bd_mutex, for_part); if (for_part) bdev->bd_part_count--; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index e5d85311d5d5..86e280edf804 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1422,6 +1422,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans, if (ret < 0 && ret != -ENOENT) { ulist_free(tmp); ulist_free(*roots); + *roots = NULL; return ret; } node = ulist_next(tmp, &uiter); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 2fead6c3c687..ace49a999ece 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -910,7 +910,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; - goto out_put_group; + goto out; } /* @@ -948,7 +948,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) { btrfs_add_delayed_iput(inode); - goto out_put_group; + goto out; } clear_nlink(inode); /* One for the block groups ref */ @@ -971,13 +971,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); if (ret < 0) - goto out_put_group; + goto out; if (ret > 0) btrfs_release_path(path); if (ret == 0) { ret = btrfs_del_item(trans, tree_root, path); if (ret) - goto out_put_group; + goto out; btrfs_release_path(path); } @@ -986,6 +986,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, &fs_info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node); + /* Once for the block groups rbtree */ + btrfs_put_block_group(block_group); + if (fs_info->first_logical_byte == block_group->key.objectid) fs_info->first_logical_byte = (u64)-1; spin_unlock(&fs_info->block_group_cache_lock); @@ -1094,10 +1097,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = remove_block_group_free_space(trans, block_group); if (ret) - goto out_put_group; - - /* Once for the block groups rbtree */ - btrfs_put_block_group(block_group); + goto out; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) @@ -1120,10 +1120,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, free_extent_map(em); } -out_put_group: +out: /* Once for the lookup reference */ btrfs_put_block_group(block_group); -out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1); btrfs_free_path(path); @@ -1167,7 +1166,7 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( free_extent_map(em); return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root, - num_items, 1); + num_items); } /* @@ -1187,7 +1186,6 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force) { struct btrfs_space_info *sinfo = cache->space_info; u64 num_bytes; - u64 sinfo_used; u64 min_allocable_bytes; int ret = -ENOSPC; @@ -1214,20 +1212,38 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force) num_bytes = cache->key.offset - cache->reserved - cache->pinned - cache->bytes_super - btrfs_block_group_used(&cache->item); - sinfo_used = btrfs_space_info_used(sinfo, true); /* - * sinfo_used + num_bytes should always <= sinfo->total_bytes. - * - * Here we make sure if we mark this bg RO, we still have enough - * free space as buffer (if min_allocable_bytes is not 0). + * Data never overcommits, even in mixed mode, so do just the straight + * check of left over space in how much we have allocated. */ - if (sinfo_used + num_bytes + min_allocable_bytes <= - sinfo->total_bytes) { + if (force) { + ret = 0; + } else if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA) { + u64 sinfo_used = btrfs_space_info_used(sinfo, true); + + /* + * Here we make sure if we mark this bg RO, we still have enough + * free space as buffer. + */ + if (sinfo_used + num_bytes <= sinfo->total_bytes) + ret = 0; + } else { + /* + * We overcommit metadata, so we need to do the + * btrfs_can_overcommit check here, and we need to pass in + * BTRFS_RESERVE_NO_FLUSH to give ourselves the most amount of + * leeway to allow us to mark this block group as read only. + */ + if (btrfs_can_overcommit(cache->fs_info, sinfo, num_bytes, + BTRFS_RESERVE_NO_FLUSH)) + ret = 0; + } + + if (!ret) { sinfo->bytes_readonly += num_bytes; cache->ro++; list_add_tail(&cache->ro_list, &sinfo->ro_bgs); - ret = 0; } out: spin_unlock(&cache->lock); @@ -1236,9 +1252,6 @@ out: btrfs_info(cache->fs_info, "unable to make block group %llu ro", cache->key.objectid); - btrfs_info(cache->fs_info, - "sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu", - sinfo_used, num_bytes, min_allocable_bytes); btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0); } return ret; @@ -2169,7 +2182,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group, return 0; } - if (trans->aborted) + if (TRANS_ABORTED(trans)) return 0; again: inode = lookup_free_space_inode(block_group, path); diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index d07bd41a7c1e..343400d49bd1 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -5,6 +5,7 @@ #include "block-rsv.h" #include "space-info.h" #include "transaction.h" +#include "block-group.h" static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, @@ -313,6 +314,8 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info) else block_rsv->full = 0; + if (block_rsv->size >= sinfo->total_bytes) + sinfo->force_alloc = CHUNK_ALLOC_FORCE; spin_unlock(&block_rsv->lock); spin_unlock(&sinfo->lock); } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index a989105d39c8..c05127f50637 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1339,6 +1339,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin), + eb_rewin, btrfs_header_level(eb_rewin)); btrfs_tree_read_lock(eb_rewin); __tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm); WARN_ON(btrfs_header_nritems(eb_rewin) > @@ -1412,7 +1414,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq) if (!eb) return NULL; - btrfs_tree_read_lock(eb); if (old_root) { btrfs_set_header_bytenr(eb, eb->start); btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV); @@ -1420,6 +1421,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq) btrfs_set_header_level(eb, old_root->level); btrfs_set_header_generation(eb, old_generation); } + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, + btrfs_header_level(eb)); + btrfs_tree_read_lock(eb); if (tm) __tree_mod_log_rewind(fs_info, eb, time_seq, tm); else diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 169075550a5a..23b4f38e2392 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -940,6 +940,8 @@ enum { BTRFS_ROOT_DEAD_RELOC_TREE, /* Mark dead root stored on device whose cleanup needs to be resumed */ BTRFS_ROOT_DEAD_TREE, + /* The root has a log tree. Used only for subvolume roots. */ + BTRFS_ROOT_HAS_LOG_TREE, }; /* @@ -988,8 +990,10 @@ struct btrfs_root { wait_queue_head_t log_writer_wait; wait_queue_head_t log_commit_wait[2]; struct list_head log_ctxs[2]; + /* Used only for log trees of subvolumes, not for the log root tree */ atomic_t log_writers; atomic_t log_commit[2]; + /* Used only for log trees of subvolumes, not for the log root tree */ atomic_t log_batch; int log_transid; /* No matter the commit succeeds or not*/ @@ -2411,7 +2415,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes); int btrfs_exclude_logged_extents(struct extent_buffer *eb); int btrfs_cross_ref_exist(struct btrfs_root *root, - u64 objectid, u64 offset, u64 bytenr); + u64 objectid, u64 offset, u64 bytenr, bool strict); struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, @@ -2465,6 +2469,7 @@ enum btrfs_reserve_flush_enum { BTRFS_RESERVE_FLUSH_LIMIT, BTRFS_RESERVE_FLUSH_EVICT, BTRFS_RESERVE_FLUSH_ALL, + BTRFS_RESERVE_FLUSH_ALL_STEAL, }; enum btrfs_flush_state { @@ -2816,7 +2821,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, u64 start, u64 len); noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, - u64 *ram_bytes); + u64 *ram_bytes, bool strict); void __btrfs_del_delalloc_inode(struct btrfs_root *root, struct btrfs_inode *inode); @@ -2951,6 +2956,8 @@ int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); +int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, @@ -2960,6 +2967,8 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, int btrfs_parse_options(struct btrfs_fs_info *info, char *options, unsigned long new_flags); int btrfs_sync_fs(struct super_block *sb, int wait); +char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, + u64 subvol_objectid); static inline __printf(2, 3) __cold void btrfs_no_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) @@ -3161,7 +3170,7 @@ do { \ /* Report first abort since mount */ \ if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \ &((trans)->fs_info->fs_state))) { \ - if ((errno) != -EIO) { \ + if ((errno) != -EIO && (errno) != -EROFS) { \ WARN(1, KERN_DEBUG \ "BTRFS: Transaction aborted (error %d)\n", \ (errno)); \ diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 5bcccfbcc7c1..a34ee9c2f315 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1151,7 +1151,7 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr) int ret = 0; bool count = (nr > 0); - if (trans->aborted) + if (TRANS_ABORTED(trans)) return -EIO; path = btrfs_alloc_path(); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 48890826b5e6..196bd241e701 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -562,6 +562,37 @@ static void btrfs_rm_dev_replace_unblocked(struct btrfs_fs_info *fs_info) wake_up(&fs_info->dev_replace.replace_wait); } +/* + * When finishing the device replace, before swapping the source device with the + * target device we must update the chunk allocation state in the target device, + * as it is empty because replace works by directly copying the chunks and not + * through the normal chunk allocation path. + */ +static int btrfs_set_target_alloc_state(struct btrfs_device *srcdev, + struct btrfs_device *tgtdev) +{ + struct extent_state *cached_state = NULL; + u64 start = 0; + u64 found_start; + u64 found_end; + int ret = 0; + + lockdep_assert_held(&srcdev->fs_info->chunk_mutex); + + while (!find_first_extent_bit(&srcdev->alloc_state, start, + &found_start, &found_end, + CHUNK_ALLOCATED, &cached_state)) { + ret = set_extent_bits(&tgtdev->alloc_state, found_start, + found_end, CHUNK_ALLOCATED); + if (ret) + break; + start = found_end + 1; + } + + free_extent_state(cached_state); + return ret; +} + static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret) { @@ -636,8 +667,14 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, dev_replace->time_stopped = ktime_get_real_seconds(); dev_replace->item_needs_writeback = 1; - /* replace old device with new one in mapping tree */ + /* + * Update allocation state in the new device and replace the old device + * with the new one in the mapping tree. + */ if (!scrub_ret) { + scrub_ret = btrfs_set_target_alloc_state(src_device, tgt_device); + if (scrub_ret) + goto error; btrfs_dev_replace_update_device_in_mapping_tree(fs_info, src_device, tgt_device); @@ -648,6 +685,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, btrfs_dev_name(src_device), src_device->devid, rcu_str_deref(tgt_device->name), scrub_ret); +error: up_write(&dev_replace->rwsem); mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&fs_info->fs_devices->device_list_mutex); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 273d1ccdd45d..cd65ef7c7c3f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -649,16 +649,15 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, goto err; if (memcmp_extent_buffer(eb, result, 0, csum_size)) { - u32 val; - u32 found = 0; - - memcpy(&found, result, csum_size); + u8 val[BTRFS_CSUM_SIZE] = { 0 }; read_extent_buffer(eb, &val, 0, csum_size); btrfs_warn_rl(fs_info, - "%s checksum verify failed on %llu wanted %x found %x level %d", + "%s checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d", fs_info->sb->s_id, eb->start, - val, found, btrfs_header_level(eb)); + CSUM_FMT_VALUE(csum_size, val), + CSUM_FMT_VALUE(csum_size, result), + btrfs_header_level(eb)); ret = -EUCLEAN; goto err; } @@ -1475,9 +1474,16 @@ int btrfs_init_fs_root(struct btrfs_root *root) spin_lock_init(&root->ino_cache_lock); init_waitqueue_head(&root->ino_cache_wait); - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + /* + * Don't assign anonymous block device to roots that are not exposed to + * userspace, the id pool is limited to 1M + */ + if (is_fstree(root->root_key.objectid) && + btrfs_root_refs(&root->root_item) > 0) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } mutex_lock(&root->objectid_mutex); ret = btrfs_find_highest_objectid(root, @@ -4470,6 +4476,7 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache) cache->io_ctl.inode = NULL; iput(inode); } + ASSERT(cache->io_ctl.pages == NULL); btrfs_put_block_group(cache); } diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index ddf28ecf17f9..93cceeba484c 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -57,9 +57,9 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, return type; } -static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, - int check_generation) +struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, + u64 root_objectid, u32 generation, + int check_generation) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root; @@ -152,7 +152,7 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh, return btrfs_get_dentry(sb, objectid, root_objectid, generation, 1); } -static struct dentry *btrfs_get_parent(struct dentry *child) +struct dentry *btrfs_get_parent(struct dentry *child) { struct inode *dir = d_inode(child); struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h index 57488ecd7d4e..f32f4113c976 100644 --- a/fs/btrfs/export.h +++ b/fs/btrfs/export.h @@ -18,4 +18,9 @@ struct btrfs_fid { u64 parent_root_objectid; } __attribute__ ((packed)); +struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, + u64 root_objectid, u32 generation, + int check_generation); +struct dentry *btrfs_get_parent(struct dentry *child); + #endif diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 47ecf7216b3e..388449101705 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -402,12 +402,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, if (type == BTRFS_SHARED_BLOCK_REF_KEY) { ASSERT(eb->fs_info); /* - * Every shared one has parent tree - * block, which must be aligned to - * nodesize. + * Every shared one has parent tree block, + * which must be aligned to sector size. */ if (offset && - IS_ALIGNED(offset, eb->fs_info->nodesize)) + IS_ALIGNED(offset, eb->fs_info->sectorsize)) return type; } } else if (is_data == BTRFS_REF_TYPE_DATA) { @@ -416,12 +415,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, if (type == BTRFS_SHARED_DATA_REF_KEY) { ASSERT(eb->fs_info); /* - * Every shared one has parent tree - * block, which must be aligned to - * nodesize. + * Every shared one has parent tree block, + * which must be aligned to sector size. */ if (offset && - IS_ALIGNED(offset, eb->fs_info->nodesize)) + IS_ALIGNED(offset, eb->fs_info->sectorsize)) return type; } } else { @@ -431,8 +429,9 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, } btrfs_print_leaf((struct extent_buffer *)eb); - btrfs_err(eb->fs_info, "eb %llu invalid extent inline ref type %d", - eb->start, type); + btrfs_err(eb->fs_info, + "eb %llu iref 0x%lx invalid extent inline ref type %d", + eb->start, (unsigned long)iref, type); WARN_ON(1); return BTRFS_REF_TYPE_INVALID; @@ -1306,8 +1305,10 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 *actual_bytes) { - int ret; + int ret = 0; u64 discarded_bytes = 0; + u64 end = bytenr + num_bytes; + u64 cur = bytenr; struct btrfs_bio *bbio = NULL; @@ -1316,15 +1317,23 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, * associated to its stripes that don't go away while we are discarding. */ btrfs_bio_counter_inc_blocked(fs_info); - /* Tell the block device(s) that the sectors can be discarded */ - ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, bytenr, &num_bytes, - &bbio, 0); - /* Error condition is -ENOMEM */ - if (!ret) { - struct btrfs_bio_stripe *stripe = bbio->stripes; + while (cur < end) { + struct btrfs_bio_stripe *stripe; int i; + num_bytes = end - cur; + /* Tell the block device(s) that the sectors can be discarded */ + ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, cur, + &num_bytes, &bbio, 0); + /* + * Error can be -ENOMEM, -ENOENT (no such chunk mapping) or + * -EOPNOTSUPP. For any such error, @num_bytes is not updated, + * thus we can't continue anyway. + */ + if (ret < 0) + goto out; + stripe = bbio->stripes; for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; struct request_queue *req_q; @@ -1341,10 +1350,19 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, stripe->physical, stripe->length, &bytes); - if (!ret) + if (!ret) { discarded_bytes += bytes; - else if (ret != -EOPNOTSUPP) - break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */ + } else if (ret != -EOPNOTSUPP) { + /* + * Logic errors or -ENOMEM, or -EIO, but + * unlikely to happen. + * + * And since there are two loops, explicitly + * go to out to avoid confusion. + */ + btrfs_put_bbio(bbio); + goto out; + } /* * Just in case we get back EOPNOTSUPP for some reason, @@ -1354,7 +1372,9 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, ret = 0; } btrfs_put_bbio(bbio); + cur += num_bytes; } +out: btrfs_bio_counter_dec(fs_info); if (actual_bytes) @@ -1561,7 +1581,7 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans, int err = 0; int metadata = !extent_op->is_data; - if (trans->aborted) + if (TRANS_ABORTED(trans)) return 0; if (metadata && !btrfs_fs_incompat(fs_info, SKINNY_METADATA)) @@ -1681,7 +1701,7 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, { int ret = 0; - if (trans->aborted) { + if (TRANS_ABORTED(trans)) { if (insert_reserved) btrfs_pin_extent(trans->fs_info, node->bytenr, node->num_bytes, 1); @@ -2169,7 +2189,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, int run_all = count == (unsigned long)-1; /* We'll clean this up in btrfs_cleanup_transaction */ - if (trans->aborted) + if (TRANS_ABORTED(trans)) return 0; if (test_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags)) @@ -2320,7 +2340,8 @@ static noinline int check_delayed_ref(struct btrfs_root *root, static noinline int check_committed_ref(struct btrfs_root *root, struct btrfs_path *path, - u64 objectid, u64 offset, u64 bytenr) + u64 objectid, u64 offset, u64 bytenr, + bool strict) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *extent_root = fs_info->extent_root; @@ -2362,9 +2383,13 @@ static noinline int check_committed_ref(struct btrfs_root *root, btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY)) goto out; - /* If extent created before last snapshot => it's definitely shared */ - if (btrfs_extent_generation(leaf, ei) <= - btrfs_root_last_snapshot(&root->root_item)) + /* + * If extent created before last snapshot => it's shared unless the + * snapshot has been deleted. Use the heuristic if strict is false. + */ + if (!strict && + (btrfs_extent_generation(leaf, ei) <= + btrfs_root_last_snapshot(&root->root_item))) goto out; iref = (struct btrfs_extent_inline_ref *)(ei + 1); @@ -2389,7 +2414,7 @@ out: } int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, - u64 bytenr) + u64 bytenr, bool strict) { struct btrfs_path *path; int ret; @@ -2400,7 +2425,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, do { ret = check_committed_ref(root, path, objectid, - offset, bytenr); + offset, bytenr, strict); if (ret && ret != -ENOENT) goto out; @@ -2892,7 +2917,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) else unpin = &fs_info->freed_extents[0]; - while (!trans->aborted) { + while (!TRANS_ABORTED(trans)) { struct extent_state *cached_state = NULL; mutex_lock(&fs_info->unused_bg_unpin_mutex); @@ -2924,7 +2949,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) u64 trimmed = 0; ret = -EROFS; - if (!trans->aborted) + if (!TRANS_ABORTED(trans)) ret = btrfs_discard_extent(fs_info, block_group->key.objectid, block_group->key.offset, @@ -4441,7 +4466,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, return ERR_PTR(-EUCLEAN); } - btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); + btrfs_set_buffer_lockdep_class(owner, buf, level); btrfs_tree_lock(buf); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); @@ -5221,7 +5246,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, goto out; } - trans = btrfs_start_transaction(tree_root, 0); + /* + * Use join to avoid potential EINTR from transaction start. See + * wait_reserve_ticket and the whole reservation callchain. + */ + if (for_reloc) + trans = btrfs_join_transaction(tree_root); + else + trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto out_free; @@ -5417,8 +5449,6 @@ out: */ if (!for_reloc && !root_dropped) btrfs_add_dead_root(root); - if (err && err != -EAGAIN) - btrfs_handle_fs_error(fs_info, err, NULL); return err; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 8aab286f2028..60c21cfb1948 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1923,7 +1923,8 @@ static int __process_pages_contig(struct address_space *mapping, if (!PageDirty(pages[i]) || pages[i]->mapping != mapping) { unlock_page(pages[i]); - put_page(pages[i]); + for (; i < ret; i++) + put_page(pages[i]); err = -EAGAIN; goto out; } @@ -4072,7 +4073,7 @@ retry: if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { ret = flush_write_bio(&epd); } else { - ret = -EUCLEAN; + ret = -EROFS; end_write_bio(&epd, ret); } return ret; @@ -4466,20 +4467,32 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) free_extent_map(em); break; } - if (!test_range_bit(tree, em->start, - extent_map_end(em) - 1, - EXTENT_LOCKED, 0, NULL)) { + if (test_range_bit(tree, em->start, + extent_map_end(em) - 1, + EXTENT_LOCKED, 0, NULL)) + goto next; + /* + * If it's not in the list of modified extents, used + * by a fast fsync, we can remove it. If it's being + * logged we can safely remove it since fsync took an + * extra reference on the em. + */ + if (list_empty(&em->list) || + test_bit(EXTENT_FLAG_LOGGING, &em->flags)) { set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &btrfs_inode->runtime_flags); remove_extent_mapping(map, em); /* once for the rb tree */ free_extent_map(em); } +next: start = extent_map_end(em); write_unlock(&map->lock); /* once for us */ free_extent_map(em); + + cond_resched(); /* Allow large-extent preemption. */ } } return try_release_extent_state(tree, page, mask); @@ -5025,25 +5038,28 @@ struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, static void check_buffer_tree_ref(struct extent_buffer *eb) { int refs; - /* the ref bit is tricky. We have to make sure it is set - * if we have the buffer dirty. Otherwise the - * code to free a buffer can end up dropping a dirty - * page + /* + * The TREE_REF bit is first set when the extent_buffer is added + * to the radix tree. It is also reset, if unset, when a new reference + * is created by find_extent_buffer. * - * Once the ref bit is set, it won't go away while the - * buffer is dirty or in writeback, and it also won't - * go away while we have the reference count on the - * eb bumped. + * It is only cleared in two cases: freeing the last non-tree + * reference to the extent_buffer when its STALE bit is set or + * calling releasepage when the tree reference is the only reference. * - * We can't just set the ref bit without bumping the - * ref on the eb because free_extent_buffer might - * see the ref bit and try to clear it. If this happens - * free_extent_buffer might end up dropping our original - * ref by mistake and freeing the page before we are able - * to add one more ref. + * In both cases, care is taken to ensure that the extent_buffer's + * pages are not under io. However, releasepage can be concurrently + * called with creating new references, which is prone to race + * conditions between the calls to check_buffer_tree_ref in those + * codepaths and clearing TREE_REF in try_release_extent_buffer. * - * So bump the ref count first, then set the bit. If someone - * beat us to it, drop the ref we added. + * The actual lifetime of the extent_buffer in the radix tree is + * adequately protected by the refcount, but the TREE_REF bit and + * its corresponding reference are not. To protect against this + * class of races, we call check_buffer_tree_ref from the codepaths + * which trigger io after they set eb->io_pages. Note that once io is + * initiated, TREE_REF can no longer be cleared, so that is the + * moment at which any such race is best fixed. */ refs = atomic_read(&eb->refs); if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) @@ -5493,6 +5509,11 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); eb->read_mirror = 0; atomic_set(&eb->io_pages, num_reads); + /* + * It is possible for releasepage to clear the TREE_REF bit before we + * set io_pages. See check_buffer_tree_ref for a more detailed comment. + */ + check_buffer_tree_ref(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; @@ -5586,9 +5607,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, } } -int read_extent_buffer_to_user(const struct extent_buffer *eb, - void __user *dstv, - unsigned long start, unsigned long len) +int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, + void __user *dstv, + unsigned long start, unsigned long len) { size_t cur; size_t offset; @@ -5609,7 +5630,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb, cur = min(len, (PAGE_SIZE - offset)); kaddr = page_address(page); - if (copy_to_user(dst, kaddr + offset, cur)) { + if (probe_user_write(dst, kaddr + offset, cur)) { ret = -EFAULT; break; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index cf3424d58fec..bc858c8cef0a 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -457,9 +457,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, void read_extent_buffer(const struct extent_buffer *eb, void *dst, unsigned long start, unsigned long len); -int read_extent_buffer_to_user(const struct extent_buffer *eb, - void __user *dst, unsigned long start, - unsigned long len); +int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, + void __user *dst, unsigned long start, + unsigned long len); void write_extent_buffer_fsid(struct extent_buffer *eb, const void *src); void write_extent_buffer_chunk_tree_uuid(struct extent_buffer *eb, const void *src); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index f62a179f85bb..2b8f29c07668 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -798,10 +798,12 @@ again: nritems = btrfs_header_nritems(path->nodes[0]); if (!nritems || (path->slots[0] >= nritems - 1)) { ret = btrfs_next_leaf(root, path); - if (ret == 1) + if (ret < 0) { + goto out; + } else if (ret > 0) { found_next = 1; - if (ret != 0) goto insert; + } slot = path->slots[0]; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 3cfbccacef7f..4126513e2429 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1546,8 +1546,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, return ret; } -static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) +int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1568,7 +1568,7 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, num_bytes = lockend - lockstart + 1; ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, - NULL, NULL, NULL); + NULL, NULL, NULL, false); if (ret <= 0) { ret = 0; btrfs_end_write_no_snapshotting(root); @@ -1647,7 +1647,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, if (ret < 0) { if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && - check_can_nocow(BTRFS_I(inode), pos, + btrfs_check_can_nocow(BTRFS_I(inode), pos, &write_bytes) > 0) { /* * For nodata cow case, no need to reserve @@ -1919,13 +1919,28 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, pos = iocb->ki_pos; count = iov_iter_count(from); if (iocb->ki_flags & IOCB_NOWAIT) { + size_t nocow_bytes = count; + /* * We will allocate space in case nodatacow is not set, * so bail */ if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { + btrfs_check_can_nocow(BTRFS_I(inode), pos, + &nocow_bytes) <= 0) { + inode_unlock(inode); + return -EAGAIN; + } + + /* check_can_nocow() locks the snapshot lock on success */ + btrfs_end_write_no_snapshotting(root); + /* + * There are holes in the range or parts of the range that must + * be COWed (shared extents, RO block groups, etc), so just bail + * out. + */ + if (nocow_bytes < count) { inode_unlock(inode); return -EAGAIN; } @@ -3130,14 +3145,14 @@ reserve_space: if (ret < 0) goto out; space_reserved = true; - ret = btrfs_qgroup_reserve_data(inode, &data_reserved, - alloc_start, bytes_to_reserve); - if (ret) - goto out; ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, &cached_state); if (ret) goto out; + ret = btrfs_qgroup_reserve_data(inode, &data_reserved, + alloc_start, bytes_to_reserve); + if (ret) + goto out; ret = btrfs_prealloc_file_range(inode, mode, alloc_start, alloc_end - alloc_start, i_blocksize(inode), diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index d86ada9c3c54..6e6be922b937 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1166,7 +1166,6 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root, ret = update_cache_item(trans, root, inode, path, offset, io_ctl->entries, io_ctl->bitmaps); out: - io_ctl_free(io_ctl); if (ret) { invalidate_inode_pages2(inode->i_mapping); BTRFS_I(inode)->generation = 0; @@ -1329,6 +1328,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, * them out later */ io_ctl_drop_pages(io_ctl); + io_ctl_free(io_ctl); unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, &cached_state); @@ -2166,7 +2166,7 @@ out: static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { - struct btrfs_free_space *left_info; + struct btrfs_free_space *left_info = NULL; struct btrfs_free_space *right_info; bool merged = false; u64 offset = info->offset; @@ -2181,7 +2181,7 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, if (right_info && rb_prev(&right_info->offset_index)) left_info = rb_entry(rb_prev(&right_info->offset_index), struct btrfs_free_space, offset_index); - else + else if (!right_info) left_info = tree_search_offset(ctl, offset - 1, 0, 0); if (right_info && !right_info->bitmap) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 94b0df3fb3c8..67b49b94c9cd 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -49,6 +49,7 @@ #include "qgroup.h" #include "delalloc-space.h" #include "block-group.h" +#include "space-info.h" struct btrfs_iget_args { struct btrfs_key *location; @@ -640,12 +641,18 @@ cont: page_error_op | PAGE_END_WRITEBACK); - for (i = 0; i < nr_pages; i++) { - WARN_ON(pages[i]->mapping); - put_page(pages[i]); + /* + * Ensure we only free the compressed pages if we have + * them allocated, as we can still reach here with + * inode_need_compress() == false. + */ + if (pages) { + for (i = 0; i < nr_pages; i++) { + WARN_ON(pages[i]->mapping); + put_page(pages[i]); + } + kfree(pages); } - kfree(pages); - return 0; } } @@ -974,6 +981,7 @@ static noinline int cow_file_range(struct inode *inode, u64 num_bytes; unsigned long ram_size; u64 cur_alloc_size = 0; + u64 min_alloc_size; u64 blocksize = fs_info->sectorsize; struct btrfs_key ins; struct extent_map *em; @@ -1024,10 +1032,26 @@ static noinline int cow_file_range(struct inode *inode, btrfs_drop_extent_cache(BTRFS_I(inode), start, start + num_bytes - 1, 0); + /* + * Relocation relies on the relocated extents to have exactly the same + * size as the original extents. Normally writeback for relocation data + * extents follows a NOCOW path because relocation preallocates the + * extents. However, due to an operation such as scrub turning a block + * group to RO mode, it may fallback to COW mode, so we must make sure + * an extent allocated during COW has exactly the requested size and can + * not be split into smaller extents, otherwise relocation breaks and + * fails during the stage where it updates the bytenr of file extent + * items. + */ + if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) + min_alloc_size = num_bytes; + else + min_alloc_size = fs_info->sectorsize; + while (num_bytes > 0) { cur_alloc_size = num_bytes; ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size, - fs_info->sectorsize, 0, alloc_hint, + min_alloc_size, 0, alloc_hint, &ins, 1, 1); if (ret < 0) goto out_unlock; @@ -1132,7 +1156,7 @@ out_unlock: */ if (extent_reserved) { extent_clear_unlock_delalloc(inode, start, - start + cur_alloc_size, + start + cur_alloc_size - 1, locked_page, clear_bits, page_ops); @@ -1322,6 +1346,73 @@ static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info, return 1; } +static int fallback_to_cow(struct inode *inode, struct page *locked_page, + const u64 start, const u64 end, + int *page_started, unsigned long *nr_written) +{ + const bool is_space_ino = btrfs_is_free_space_inode(BTRFS_I(inode)); + const bool is_reloc_ino = (BTRFS_I(inode)->root->root_key.objectid == + BTRFS_DATA_RELOC_TREE_OBJECTID); + const u64 range_bytes = end + 1 - start; + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + u64 range_start = start; + u64 count; + + /* + * If EXTENT_NORESERVE is set it means that when the buffered write was + * made we had not enough available data space and therefore we did not + * reserve data space for it, since we though we could do NOCOW for the + * respective file range (either there is prealloc extent or the inode + * has the NOCOW bit set). + * + * However when we need to fallback to COW mode (because for example the + * block group for the corresponding extent was turned to RO mode by a + * scrub or relocation) we need to do the following: + * + * 1) We increment the bytes_may_use counter of the data space info. + * If COW succeeds, it allocates a new data extent and after doing + * that it decrements the space info's bytes_may_use counter and + * increments its bytes_reserved counter by the same amount (we do + * this at btrfs_add_reserved_bytes()). So we need to increment the + * bytes_may_use counter to compensate (when space is reserved at + * buffered write time, the bytes_may_use counter is incremented); + * + * 2) We clear the EXTENT_NORESERVE bit from the range. We do this so + * that if the COW path fails for any reason, it decrements (through + * extent_clear_unlock_delalloc()) the bytes_may_use counter of the + * data space info, which we incremented in the step above. + * + * If we need to fallback to cow and the inode corresponds to a free + * space cache inode or an inode of the data relocation tree, we must + * also increment bytes_may_use of the data space_info for the same + * reason. Space caches and relocated data extents always get a prealloc + * extent for them, however scrub or balance may have set the block + * group that contains that extent to RO mode and therefore force COW + * when starting writeback. + */ + count = count_range_bits(io_tree, &range_start, end, range_bytes, + EXTENT_NORESERVE, 0); + if (count > 0 || is_space_ino || is_reloc_ino) { + u64 bytes = count; + struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; + struct btrfs_space_info *sinfo = fs_info->data_sinfo; + + if (is_space_ino || is_reloc_ino) + bytes = range_bytes; + + spin_lock(&sinfo->lock); + btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes); + spin_unlock(&sinfo->lock); + + if (count > 0) + clear_extent_bit(io_tree, start, end, EXTENT_NORESERVE, + 0, 0, NULL); + } + + return cow_file_range(inode, locked_page, start, end, page_started, + nr_written, 1); +} + /* * when nowcow writeback call back. This checks for snapshots or COW copies * of the extents that exist in the file, and COWs the file as required. @@ -1487,7 +1578,7 @@ next_slot: goto out_check; ret = btrfs_cross_ref_exist(root, ino, found_key.offset - - extent_offset, disk_bytenr); + extent_offset, disk_bytenr, false); if (ret) { /* * ret could be -EIO if the above fails to read @@ -1569,15 +1660,11 @@ out_check: * NOCOW, following one which needs to be COW'ed */ if (cow_start != (u64)-1) { - ret = cow_file_range(inode, locked_page, - cow_start, found_key.offset - 1, - page_started, nr_written, 1); - if (ret) { - if (nocow) - btrfs_dec_nocow_writers(fs_info, - disk_bytenr); + ret = fallback_to_cow(inode, locked_page, cow_start, + found_key.offset - 1, + page_started, nr_written); + if (ret) goto error; - } cow_start = (u64)-1; } @@ -1593,9 +1680,6 @@ out_check: ram_bytes, BTRFS_COMPRESS_NONE, BTRFS_ORDERED_PREALLOC); if (IS_ERR(em)) { - if (nocow) - btrfs_dec_nocow_writers(fs_info, - disk_bytenr); ret = PTR_ERR(em); goto error; } @@ -1660,8 +1744,8 @@ out_check: if (cow_start != (u64)-1) { cur_offset = end; - ret = cow_file_range(inode, locked_page, cow_start, end, - page_started, nr_written, 1); + ret = fallback_to_cow(inode, locked_page, cow_start, end, + page_started, nr_written); if (ret) goto error; } @@ -4250,7 +4334,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir) * 1 for the inode ref * 1 for the inode */ - return btrfs_start_transaction_fallback_global_rsv(root, 5, 5); + return btrfs_start_transaction_fallback_global_rsv(root, 5); } static int btrfs_unlink(struct inode *dir, struct dentry *dentry) @@ -4603,6 +4687,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) } } + free_anon_bdev(dest->anon_dev); + dest->anon_dev = 0; out_end_trans: trans->block_rsv = NULL; trans->bytes_reserved = 0; @@ -5047,11 +5133,13 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; char *kaddr; + bool only_release_metadata = false; u32 blocksize = fs_info->sectorsize; pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (blocksize - 1); struct page *page; gfp_t mask = btrfs_alloc_write_mask(mapping); + size_t write_bytes = blocksize; int ret = 0; u64 block_start; u64 block_end; @@ -5063,11 +5151,27 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, block_start = round_down(from, blocksize); block_end = block_start + blocksize - 1; - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, - block_start, blocksize); - if (ret) - goto out; + ret = btrfs_check_data_free_space(inode, &data_reserved, block_start, + blocksize); + if (ret < 0) { + if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) && + btrfs_check_can_nocow(BTRFS_I(inode), block_start, + &write_bytes) > 0) { + /* For nocow case, no need to reserve data space */ + only_release_metadata = true; + } else { + goto out; + } + } + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize); + if (ret < 0) { + if (!only_release_metadata) + btrfs_free_reserved_data_space(inode, data_reserved, + block_start, blocksize); + goto out; + } again: page = find_or_create_page(mapping, index, mask); if (!page) { @@ -5136,14 +5240,26 @@ again: set_page_dirty(page); unlock_extent_cached(io_tree, block_start, block_end, &cached_state); + if (only_release_metadata) + set_extent_bit(&BTRFS_I(inode)->io_tree, block_start, + block_end, EXTENT_NORESERVE, NULL, NULL, + GFP_NOFS); + out_unlock: - if (ret) - btrfs_delalloc_release_space(inode, data_reserved, block_start, - blocksize, true); + if (ret) { + if (only_release_metadata) + btrfs_delalloc_release_metadata(BTRFS_I(inode), + blocksize, true); + else + btrfs_delalloc_release_space(inode, data_reserved, + block_start, blocksize, true); + } btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); unlock_page(page); put_page(page); out: + if (only_release_metadata) + btrfs_end_write_no_snapshotting(BTRFS_I(inode)->root); extent_changeset_free(data_reserved); return ret; } @@ -7108,7 +7224,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, extent_type == BTRFS_FILE_EXTENT_PREALLOC) { /* Only regular file could have regular/prealloc extent */ if (!S_ISREG(inode->vfs_inode.i_mode)) { - ret = -EUCLEAN; + err = -EUCLEAN; btrfs_crit(fs_info, "regular/prealloc extent found for non-regular inode %llu", btrfs_ino(inode)); @@ -7443,7 +7559,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, */ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, - u64 *ram_bytes) + u64 *ram_bytes, bool strict) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_path *path; @@ -7521,8 +7637,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, * Do the same check as in btrfs_cross_ref_exist but without the * unnecessary search. */ - if (btrfs_file_extent_generation(leaf, fi) <= - btrfs_root_last_snapshot(&root->root_item)) + if (!strict && + (btrfs_file_extent_generation(leaf, fi) <= + btrfs_root_last_snapshot(&root->root_item))) goto out; backref_offset = btrfs_file_extent_offset(leaf, fi); @@ -7558,7 +7675,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, */ ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)), - key.offset - backref_offset, disk_bytenr); + key.offset - backref_offset, disk_bytenr, + strict); if (ret) { ret = 0; goto out; @@ -7779,7 +7897,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, block_start = em->block_start + (start - em->start); if (can_nocow_extent(inode, start, &len, &orig_start, - &orig_block_len, &ram_bytes) == 1 && + &orig_block_len, &ram_bytes, false) == 1 && btrfs_inc_nocow_writers(fs_info, block_start)) { struct extent_map *em2; @@ -8498,14 +8616,64 @@ err: return ret; } -static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) +/* + * If this succeeds, the btrfs_dio_private is responsible for cleaning up locked + * or ordered extents whether or not we submit any bios. + */ +static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, + struct inode *inode, + loff_t file_offset) { - struct inode *inode = dip->inode; + const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); + struct btrfs_dio_private *dip; + struct bio *bio; + + dip = kzalloc(sizeof(*dip), GFP_NOFS); + if (!dip) + return NULL; + + bio = btrfs_bio_clone(dio_bio); + bio->bi_private = dip; + btrfs_io_bio(bio)->logical = file_offset; + + dip->private = dio_bio->bi_private; + dip->inode = inode; + dip->logical_offset = file_offset; + dip->bytes = dio_bio->bi_iter.bi_size; + dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9; + dip->orig_bio = bio; + dip->dio_bio = dio_bio; + atomic_set(&dip->pending_bios, 1); + + if (write) { + struct btrfs_dio_data *dio_data = current->journal_info; + + /* + * Setting range start and end to the same value means that + * no cleanup will happen in btrfs_direct_IO + */ + dio_data->unsubmitted_oe_range_end = dip->logical_offset + + dip->bytes; + dio_data->unsubmitted_oe_range_start = + dio_data->unsubmitted_oe_range_end; + + bio->bi_end_io = btrfs_endio_direct_write; + } else { + bio->bi_end_io = btrfs_endio_direct_read; + dip->subio_endio = btrfs_subio_endio_read; + } + return dip; +} + +static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, + loff_t file_offset) +{ + const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_dio_private *dip; struct bio *bio; - struct bio *orig_bio = dip->orig_bio; - u64 start_sector = orig_bio->bi_iter.bi_sector; - u64 file_offset = dip->logical_offset; + struct bio *orig_bio; + u64 start_sector; int async_submit = 0; u64 submit_len; int clone_offset = 0; @@ -8514,11 +8682,24 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) blk_status_t status; struct btrfs_io_geometry geom; + dip = btrfs_create_dio_private(dio_bio, inode, file_offset); + if (!dip) { + if (!write) { + unlock_extent(&BTRFS_I(inode)->io_tree, file_offset, + file_offset + dio_bio->bi_iter.bi_size - 1); + } + dio_bio->bi_status = BLK_STS_RESOURCE; + dio_end_io(dio_bio); + return; + } + + orig_bio = dip->orig_bio; + start_sector = orig_bio->bi_iter.bi_sector; submit_len = orig_bio->bi_iter.bi_size; ret = btrfs_get_io_geometry(fs_info, btrfs_op(orig_bio), start_sector << 9, submit_len, &geom); if (ret) - return -EIO; + goto out_err; if (geom.len >= submit_len) { bio = orig_bio; @@ -8534,7 +8715,6 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) /* bio split */ ASSERT(geom.len <= INT_MAX); - atomic_inc(&dip->pending_bios); do { clone_len = min_t(int, submit_len, geom.len); @@ -8582,9 +8762,10 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) submit: status = btrfs_submit_dio_bio(bio, inode, file_offset, async_submit); if (!status) - return 0; + return; - bio_put(bio); + if (bio != orig_bio) + bio_put(bio); out_err: dip->errors = 1; /* @@ -8595,107 +8776,6 @@ out_err: */ if (atomic_dec_and_test(&dip->pending_bios)) bio_io_error(dip->orig_bio); - - /* bio_end_io() will handle error, so we needn't return it */ - return 0; -} - -static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, - loff_t file_offset) -{ - struct btrfs_dio_private *dip = NULL; - struct bio *bio = NULL; - struct btrfs_io_bio *io_bio; - bool write = (bio_op(dio_bio) == REQ_OP_WRITE); - int ret = 0; - - bio = btrfs_bio_clone(dio_bio); - - dip = kzalloc(sizeof(*dip), GFP_NOFS); - if (!dip) { - ret = -ENOMEM; - goto free_ordered; - } - - dip->private = dio_bio->bi_private; - dip->inode = inode; - dip->logical_offset = file_offset; - dip->bytes = dio_bio->bi_iter.bi_size; - dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9; - bio->bi_private = dip; - dip->orig_bio = bio; - dip->dio_bio = dio_bio; - atomic_set(&dip->pending_bios, 0); - io_bio = btrfs_io_bio(bio); - io_bio->logical = file_offset; - - if (write) { - bio->bi_end_io = btrfs_endio_direct_write; - } else { - bio->bi_end_io = btrfs_endio_direct_read; - dip->subio_endio = btrfs_subio_endio_read; - } - - /* - * Reset the range for unsubmitted ordered extents (to a 0 length range) - * even if we fail to submit a bio, because in such case we do the - * corresponding error handling below and it must not be done a second - * time by btrfs_direct_IO(). - */ - if (write) { - struct btrfs_dio_data *dio_data = current->journal_info; - - dio_data->unsubmitted_oe_range_end = dip->logical_offset + - dip->bytes; - dio_data->unsubmitted_oe_range_start = - dio_data->unsubmitted_oe_range_end; - } - - ret = btrfs_submit_direct_hook(dip); - if (!ret) - return; - - btrfs_io_bio_free_csum(io_bio); - -free_ordered: - /* - * If we arrived here it means either we failed to submit the dip - * or we either failed to clone the dio_bio or failed to allocate the - * dip. If we cloned the dio_bio and allocated the dip, we can just - * call bio_endio against our io_bio so that we get proper resource - * cleanup if we fail to submit the dip, otherwise, we must do the - * same as btrfs_endio_direct_[write|read] because we can't call these - * callbacks - they require an allocated dip and a clone of dio_bio. - */ - if (bio && dip) { - bio_io_error(bio); - /* - * The end io callbacks free our dip, do the final put on bio - * and all the cleanup and final put for dio_bio (through - * dio_end_io()). - */ - dip = NULL; - bio = NULL; - } else { - if (write) - __endio_write_update_ordered(inode, - file_offset, - dio_bio->bi_iter.bi_size, - false); - else - unlock_extent(&BTRFS_I(inode)->io_tree, file_offset, - file_offset + dio_bio->bi_iter.bi_size - 1); - - dio_bio->bi_status = BLK_STS_IOERR; - /* - * Releases and cleans up our dio_bio, no need to bio_put() - * nor bio_endio()/bio_io_error() against dio_bio. - */ - dio_end_io(dio_bio); - } - if (bio) - bio_put(bio); - kfree(dip); } static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, @@ -8772,9 +8852,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.overwrite = 1; inode_unlock(inode); relock = true; - } else if (iocb->ki_flags & IOCB_NOWAIT) { - ret = -EAGAIN; - goto out; } ret = btrfs_delalloc_reserve_space(inode, &data_reserved, offset, count); @@ -8997,20 +9074,17 @@ again: /* * Qgroup reserved space handler * Page here will be either - * 1) Already written to disk - * In this case, its reserved space is released from data rsv map - * and will be freed by delayed_ref handler finally. - * So even we call qgroup_free_data(), it won't decrease reserved - * space. - * 2) Not written to disk - * This means the reserved space should be freed here. However, - * if a truncate invalidates the page (by clearing PageDirty) - * and the page is accounted for while allocating extent - * in btrfs_check_data_free_space() we let delayed_ref to - * free the entire extent. + * 1) Already written to disk or ordered extent already submitted + * Then its QGROUP_RESERVED bit in io_tree is already cleaned. + * Qgroup will be handled by its qgroup_record then. + * btrfs_qgroup_free_data() call will do nothing here. + * + * 2) Not written to disk yet + * Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED + * bit of its io_tree, and free the qgroup reserved data space. + * Since the IO will never happen for this page. */ - if (PageDirty(page)) - btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | @@ -9485,7 +9559,7 @@ void btrfs_destroy_inode(struct inode *inode) btrfs_put_ordered_extent(ordered); } } - btrfs_qgroup_check_reserved_leak(inode); + btrfs_qgroup_check_reserved_leak(BTRFS_I(inode)); inode_tree_del(inode); btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0); } @@ -10947,7 +11021,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, free_extent_map(em); em = NULL; - ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL); + ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, true); if (ret < 0) { goto out; } else if (ret) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d88b8d8897cc..63394b450afc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -167,8 +167,11 @@ static int btrfs_ioctl_getflags(struct file *file, void __user *arg) return 0; } -/* Check if @flags are a supported and valid set of FS_*_FL flags */ -static int check_fsflags(unsigned int flags) +/* + * Check if @flags are a supported and valid set of FS_*_FL flags and that + * the old and new flags are not conflicting + */ +static int check_fsflags(unsigned int old_flags, unsigned int flags) { if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NOATIME_FL | FS_NODUMP_FL | \ @@ -177,9 +180,19 @@ static int check_fsflags(unsigned int flags) FS_NOCOW_FL)) return -EOPNOTSUPP; + /* COMPR and NOCOMP on new/old are valid */ if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL)) return -EINVAL; + if ((flags & FS_COMPR_FL) && (flags & FS_NOCOW_FL)) + return -EINVAL; + + /* NOCOW and compression options are mutually exclusive */ + if ((old_flags & FS_NOCOW_FL) && (flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + if ((flags & FS_NOCOW_FL) && (old_flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + return 0; } @@ -193,7 +206,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) unsigned int fsflags, old_fsflags; int ret; const char *comp = NULL; - u32 binode_flags = binode->flags; + u32 binode_flags; if (!inode_owner_or_capable(inode)) return -EPERM; @@ -204,22 +217,23 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (copy_from_user(&fsflags, arg, sizeof(fsflags))) return -EFAULT; - ret = check_fsflags(fsflags); - if (ret) - return ret; - ret = mnt_want_write_file(file); if (ret) return ret; inode_lock(inode); - fsflags = btrfs_mask_fsflags_for_type(inode, fsflags); old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); if (ret) goto out_unlock; + ret = check_fsflags(old_fsflags, fsflags); + if (ret) + goto out_unlock; + + binode_flags = binode->flags; if (fsflags & FS_SYNC_FL) binode_flags |= BTRFS_INODE_SYNC; else @@ -2091,9 +2105,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, sh.len = item_len; sh.transid = found_transid; - /* copy search result header */ - if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) { - ret = -EFAULT; + /* + * Copy search result header. If we fault then loop again so we + * can fault in the pages and -EFAULT there if there's a + * problem. Otherwise we'll fault and then copy the buffer in + * properly this next time through + */ + if (probe_user_write(ubuf + *sk_offset, &sh, sizeof(sh))) { + ret = 0; goto out; } @@ -2101,10 +2120,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, if (item_len) { char __user *up = ubuf + *sk_offset; - /* copy the item */ - if (read_extent_buffer_to_user(leaf, up, - item_off, item_len)) { - ret = -EFAULT; + /* + * Copy the item, same behavior as above, but reset the + * * sk_offset so we copy the full thing again. + */ + if (read_extent_buffer_to_user_nofault(leaf, up, + item_off, item_len)) { + ret = 0; + *sk_offset -= sizeof(sh); goto out; } @@ -2192,6 +2215,11 @@ static noinline int search_ioctl(struct inode *inode, key.offset = sk->min_offset; while (1) { + ret = fault_in_pages_writeable(ubuf + sk_offset, + *buf_size - sk_offset); + if (ret) + break; + ret = btrfs_search_forward(root, &key, path, sk->min_transid); if (ret != 0) { if (ret > 0) diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 9cb50577d982..f4edadf1067f 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -95,9 +95,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) * offset is supposed to be a tree block which * must be aligned to nodesize. */ - if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) - pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n", - offset, (unsigned long long)eb->fs_info->nodesize); + if (!IS_ALIGNED(offset, eb->fs_info->sectorsize)) + pr_info( + "\t\t\t(parent %llu not aligned to sectorsize %u)\n", + offset, eb->fs_info->sectorsize); break; case BTRFS_EXTENT_DATA_REF_KEY: dref = (struct btrfs_extent_data_ref *)(&iref->offset); @@ -112,8 +113,9 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) * must be aligned to nodesize. */ if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) - pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n", - offset, (unsigned long long)eb->fs_info->nodesize); + pr_info( + "\t\t\t(parent %llu not aligned to sectorsize %u)\n", + offset, eb->fs_info->sectorsize); break; default: pr_cont("(extent %llu has INVALID ref type %d)\n", diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 590defdf8860..04fd02e6124d 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2636,6 +2636,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, struct btrfs_root *quota_root; struct btrfs_qgroup *srcgroup; struct btrfs_qgroup *dstgroup; + bool need_rescan = false; u32 level_size = 0; u64 nums; @@ -2779,6 +2780,13 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, goto unlock; } ++i_qgroups; + + /* + * If we're doing a snapshot, and adding the snapshot to a new + * qgroup, the numbers are guaranteed to be incorrect. + */ + if (srcid) + need_rescan = true; } for (i = 0; i < inherit->num_ref_copies; ++i, i_qgroups += 2) { @@ -2798,6 +2806,9 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, dst->rfer = src->rfer - level_size; dst->rfer_cmpr = src->rfer_cmpr - level_size; + + /* Manually tweaking numbers certainly needs a rescan */ + need_rescan = true; } for (i = 0; i < inherit->num_excl_copies; ++i, i_qgroups += 2) { struct btrfs_qgroup *src; @@ -2816,6 +2827,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, dst->excl = src->excl + level_size; dst->excl_cmpr = src->excl_cmpr + level_size; + need_rescan = true; } unlock: @@ -2823,6 +2835,8 @@ unlock: out: if (!committing) mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (need_rescan) + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; return ret; } @@ -3755,7 +3769,7 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) * Check qgroup reserved space leaking, normally at destroy inode * time */ -void btrfs_qgroup_check_reserved_leak(struct inode *inode) +void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode) { struct extent_changeset changeset; struct ulist_node *unode; @@ -3763,19 +3777,19 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode) int ret; extent_changeset_init(&changeset); - ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1, + ret = clear_record_extent_bits(&inode->io_tree, 0, (u64)-1, EXTENT_QGROUP_RESERVED, &changeset); WARN_ON(ret < 0); if (WARN_ON(changeset.bytes_changed)) { ULIST_ITER_INIT(&iter); while ((unode = ulist_next(&changeset.range_changed, &iter))) { - btrfs_warn(BTRFS_I(inode)->root->fs_info, - "leaking qgroup reserved space, ino: %lu, start: %llu, end: %llu", - inode->i_ino, unode->val, unode->aux); + btrfs_warn(inode->root->fs_info, + "leaking qgroup reserved space, ino: %llu, start: %llu, end: %llu", + btrfs_ino(inode), unode->val, unode->aux); } - btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, - BTRFS_I(inode)->root->root_key.objectid, + btrfs_qgroup_free_refroot(inode->root->fs_info, + inode->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 17e8ac992c50..b0420c4f5d0e 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -399,7 +399,7 @@ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root); */ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes); -void btrfs_qgroup_check_reserved_leak(struct inode *inode); +void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode); /* btrfs_qgroup_swapped_blocks related functions */ void btrfs_qgroup_init_swapped_blocks( diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 454a1015d026..9a2f15f4c80e 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -286,6 +286,8 @@ static struct block_entry *add_block_entry(struct btrfs_fs_info *fs_info, exist_re = insert_root_entry(&exist->roots, re); if (exist_re) kfree(re); + } else { + kfree(re); } kfree(be); return exist; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index e890f09e2073..1bc57f7b91cf 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1468,6 +1468,9 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, int clear_rsv = 0; int ret; + if (!rc) + return 0; + /* * The subvolume has reloc tree but the swap is finished, no need to * create/update the dead reloc tree @@ -1475,13 +1478,25 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, if (reloc_root_is_dead(root)) return 0; + /* + * This is subtle but important. We do not do + * record_root_in_transaction for reloc roots, instead we record their + * corresponding fs root, and then here we update the last trans for the + * reloc root. This means that we have to do this for the entire life + * of the reloc root, regardless of which stage of the relocation we are + * in. + */ if (root->reloc_root) { reloc_root = root->reloc_root; reloc_root->last_trans = trans->transid; return 0; } - if (!rc || !rc->create_reloc_tree || + /* + * We are merging reloc roots, we do not need new reloc trees. Also + * reloc trees never need their own reloc tree. + */ + if (!rc->create_reloc_tree || root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) return 0; @@ -2312,12 +2327,20 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, btrfs_unlock_up_safe(path, 0); } - min_reserved = fs_info->nodesize * (BTRFS_MAX_LEVEL - 1) * 2; + /* + * In merge_reloc_root(), we modify the upper level pointer to swap the + * tree blocks between reloc tree and subvolume tree. Thus for tree + * block COW, we COW at most from level 1 to root level for each tree. + * + * Thus the needed metadata size is at most root_level * nodesize, + * and * 2 since we have two trees to COW. + */ + min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2; memset(&next_key, 0, sizeof(next_key)); while (1) { ret = btrfs_block_rsv_refill(root, rc->block_rsv, min_reserved, - BTRFS_RESERVE_FLUSH_ALL); + BTRFS_RESERVE_FLUSH_LIMIT); if (ret) { err = ret; goto out; @@ -2328,6 +2351,18 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, trans = NULL; goto out; } + + /* + * At this point we no longer have a reloc_control, so we can't + * depend on btrfs_init_reloc_root to update our last_trans. + * + * But that's ok, we started the trans handle on our + * corresponding fs_root, which means it's been added to the + * dirty list. At commit time we'll still call + * btrfs_update_reloc_root() and update our root item + * appropriately. + */ + reloc_root->last_trans = trans->transid; trans->block_rsv = rc->block_rsv; replaced = 0; @@ -2525,12 +2560,10 @@ again: reloc_root = list_entry(reloc_roots.next, struct btrfs_root, root_list); + root = read_fs_root(fs_info, reloc_root->root_key.offset); if (btrfs_root_refs(&reloc_root->root_item) > 0) { - root = read_fs_root(fs_info, - reloc_root->root_key.offset); BUG_ON(IS_ERR(root)); BUG_ON(root->reloc_root != reloc_root); - ret = merge_reloc_root(rc, root); if (ret) { if (list_empty(&reloc_root->root_list)) @@ -2539,6 +2572,13 @@ again: goto out; } } else { + if (!IS_ERR(root)) { + if (root->reloc_root == reloc_root) + root->reloc_root = NULL; + clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, + &root->state); + } + list_del_init(&reloc_root->root_list); /* Don't forget to queue this reloc root for cleanup */ list_add_tail(&reloc_root->reloc_dirty_list, @@ -4329,6 +4369,18 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info) return rc; } +static void free_reloc_control(struct reloc_control *rc) +{ + struct mapping_node *node, *tmp; + + free_reloc_roots(&rc->reloc_roots); + rbtree_postorder_for_each_entry_safe(node, tmp, + &rc->reloc_root_tree.rb_root, rb_node) + kfree(node); + + kfree(rc); +} + /* * Print the block group being relocated */ @@ -4461,7 +4513,7 @@ out: btrfs_dec_block_group_ro(rc->block_group); iput(rc->data_inode); btrfs_put_block_group(rc->block_group); - kfree(rc); + free_reloc_control(rc); return err; } @@ -4634,7 +4686,7 @@ out_clean: err = ret; out_unset: unset_reloc_control(rc); - kfree(rc); + free_reloc_control(rc); out: if (!list_empty(&reloc_roots)) free_reloc_roots(&reloc_roots); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index a7b043fd7a57..93d7cb56e44b 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3717,7 +3717,7 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, struct btrfs_fs_info *fs_info = sctx->fs_info; if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) - return -EIO; + return -EROFS; /* Seed devices of a new filesystem has their own generation. */ if (scrub_dev->fs_devices != fs_info->fs_devices) @@ -3742,50 +3742,84 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, return 0; } +static void scrub_workers_put(struct btrfs_fs_info *fs_info) +{ + if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt, + &fs_info->scrub_lock)) { + struct btrfs_workqueue *scrub_workers = NULL; + struct btrfs_workqueue *scrub_wr_comp = NULL; + struct btrfs_workqueue *scrub_parity = NULL; + + scrub_workers = fs_info->scrub_workers; + scrub_wr_comp = fs_info->scrub_wr_completion_workers; + scrub_parity = fs_info->scrub_parity_workers; + + fs_info->scrub_workers = NULL; + fs_info->scrub_wr_completion_workers = NULL; + fs_info->scrub_parity_workers = NULL; + mutex_unlock(&fs_info->scrub_lock); + + btrfs_destroy_workqueue(scrub_workers); + btrfs_destroy_workqueue(scrub_wr_comp); + btrfs_destroy_workqueue(scrub_parity); + } +} + /* * get a reference count on fs_info->scrub_workers. start worker if necessary */ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, int is_dev_replace) { + struct btrfs_workqueue *scrub_workers = NULL; + struct btrfs_workqueue *scrub_wr_comp = NULL; + struct btrfs_workqueue *scrub_parity = NULL; unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND; int max_active = fs_info->thread_pool_size; + int ret = -ENOMEM; - lockdep_assert_held(&fs_info->scrub_lock); + if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt)) + return 0; - if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { - ASSERT(fs_info->scrub_workers == NULL); - fs_info->scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", - flags, is_dev_replace ? 1 : max_active, 4); - if (!fs_info->scrub_workers) - goto fail_scrub_workers; - - ASSERT(fs_info->scrub_wr_completion_workers == NULL); - fs_info->scrub_wr_completion_workers = - btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, - max_active, 2); - if (!fs_info->scrub_wr_completion_workers) - goto fail_scrub_wr_completion_workers; + scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", flags, + is_dev_replace ? 1 : max_active, 4); + if (!scrub_workers) + goto fail_scrub_workers; - ASSERT(fs_info->scrub_parity_workers == NULL); - fs_info->scrub_parity_workers = - btrfs_alloc_workqueue(fs_info, "scrubparity", flags, + scrub_wr_comp = btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, max_active, 2); - if (!fs_info->scrub_parity_workers) - goto fail_scrub_parity_workers; + if (!scrub_wr_comp) + goto fail_scrub_wr_completion_workers; + scrub_parity = btrfs_alloc_workqueue(fs_info, "scrubparity", flags, + max_active, 2); + if (!scrub_parity) + goto fail_scrub_parity_workers; + + mutex_lock(&fs_info->scrub_lock); + if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { + ASSERT(fs_info->scrub_workers == NULL && + fs_info->scrub_wr_completion_workers == NULL && + fs_info->scrub_parity_workers == NULL); + fs_info->scrub_workers = scrub_workers; + fs_info->scrub_wr_completion_workers = scrub_wr_comp; + fs_info->scrub_parity_workers = scrub_parity; refcount_set(&fs_info->scrub_workers_refcnt, 1); - } else { - refcount_inc(&fs_info->scrub_workers_refcnt); + mutex_unlock(&fs_info->scrub_lock); + return 0; } - return 0; + /* Other thread raced in and created the workers for us */ + refcount_inc(&fs_info->scrub_workers_refcnt); + mutex_unlock(&fs_info->scrub_lock); + ret = 0; + btrfs_destroy_workqueue(scrub_parity); fail_scrub_parity_workers: - btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers); + btrfs_destroy_workqueue(scrub_wr_comp); fail_scrub_wr_completion_workers: - btrfs_destroy_workqueue(fs_info->scrub_workers); + btrfs_destroy_workqueue(scrub_workers); fail_scrub_workers: - return -ENOMEM; + return ret; } int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, @@ -3796,9 +3830,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, int ret; struct btrfs_device *dev; unsigned int nofs_flag; - struct btrfs_workqueue *scrub_workers = NULL; - struct btrfs_workqueue *scrub_wr_comp = NULL; - struct btrfs_workqueue *scrub_parity = NULL; if (btrfs_fs_closing(fs_info)) return -EAGAIN; @@ -3845,13 +3876,17 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (IS_ERR(sctx)) return PTR_ERR(sctx); + ret = scrub_workers_get(fs_info, is_dev_replace); + if (ret) + goto out_free_ctx; + mutex_lock(&fs_info->fs_devices->device_list_mutex); dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) && !is_dev_replace)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -ENODEV; - goto out_free_ctx; + goto out; } if (!is_dev_replace && !readonly && @@ -3860,7 +3895,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable", rcu_str_deref(dev->name)); ret = -EROFS; - goto out_free_ctx; + goto out; } mutex_lock(&fs_info->scrub_lock); @@ -3869,7 +3904,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EIO; - goto out_free_ctx; + goto out; } down_read(&fs_info->dev_replace.rwsem); @@ -3880,17 +3915,10 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EINPROGRESS; - goto out_free_ctx; + goto out; } up_read(&fs_info->dev_replace.rwsem); - ret = scrub_workers_get(fs_info, is_dev_replace); - if (ret) { - mutex_unlock(&fs_info->scrub_lock); - mutex_unlock(&fs_info->fs_devices->device_list_mutex); - goto out_free_ctx; - } - sctx->readonly = readonly; dev->scrub_ctx = sctx; mutex_unlock(&fs_info->fs_devices->device_list_mutex); @@ -3943,24 +3971,14 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_lock(&fs_info->scrub_lock); dev->scrub_ctx = NULL; - if (refcount_dec_and_test(&fs_info->scrub_workers_refcnt)) { - scrub_workers = fs_info->scrub_workers; - scrub_wr_comp = fs_info->scrub_wr_completion_workers; - scrub_parity = fs_info->scrub_parity_workers; - - fs_info->scrub_workers = NULL; - fs_info->scrub_wr_completion_workers = NULL; - fs_info->scrub_parity_workers = NULL; - } mutex_unlock(&fs_info->scrub_lock); - btrfs_destroy_workqueue(scrub_workers); - btrfs_destroy_workqueue(scrub_wr_comp); - btrfs_destroy_workqueue(scrub_parity); + scrub_workers_put(fs_info); scrub_put_ctx(sctx); return ret; - +out: + scrub_workers_put(fs_info); out_free_ctx: scrub_free_ctx(sctx); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 3eb0fec2488a..b0e5dfb9be7a 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -23,6 +23,7 @@ #include "btrfs_inode.h" #include "transaction.h" #include "compression.h" +#include "xattr.h" /* * Maximum number of references an extent can have in order for us to attempt to @@ -1256,12 +1257,21 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_) */ if (found->root == bctx->sctx->send_root) { /* - * TODO for the moment we don't accept clones from the inode - * that is currently send. We may change this when - * BTRFS_IOC_CLONE_RANGE supports cloning from and to the same - * file. + * If the source inode was not yet processed we can't issue a + * clone operation, as the source extent does not exist yet at + * the destination of the stream. */ - if (ino >= bctx->cur_objectid) + if (ino > bctx->cur_objectid) + return 0; + /* + * We clone from the inode currently being sent as long as the + * source extent is already processed, otherwise we could try + * to clone from an extent that does not exist yet at the + * destination of the stream. + */ + if (ino == bctx->cur_objectid && + offset + bctx->extent_len > + bctx->sctx->cur_inode_next_write_offset) return 0; } @@ -4536,6 +4546,10 @@ static int __process_new_xattr(int num, struct btrfs_key *di_key, struct fs_path *p; struct posix_acl_xattr_header dummy_acl; + /* Capabilities are emitted by finish_inode_if_needed */ + if (!strncmp(name, XATTR_NAME_CAPS, name_len)) + return 0; + p = fs_path_alloc(); if (!p) return -ENOMEM; @@ -5098,6 +5112,64 @@ static int send_extent_data(struct send_ctx *sctx, return 0; } +/* + * Search for a capability xattr related to sctx->cur_ino. If the capability is + * found, call send_set_xattr function to emit it. + * + * Return 0 if there isn't a capability, or when the capability was emitted + * successfully, or < 0 if an error occurred. + */ +static int send_capabilities(struct send_ctx *sctx) +{ + struct fs_path *fspath = NULL; + struct btrfs_path *path; + struct btrfs_dir_item *di; + struct extent_buffer *leaf; + unsigned long data_ptr; + char *buf = NULL; + int buf_len; + int ret = 0; + + path = alloc_path_for_send(); + if (!path) + return -ENOMEM; + + di = btrfs_lookup_xattr(NULL, sctx->send_root, path, sctx->cur_ino, + XATTR_NAME_CAPS, strlen(XATTR_NAME_CAPS), 0); + if (!di) { + /* There is no xattr for this inode */ + goto out; + } else if (IS_ERR(di)) { + ret = PTR_ERR(di); + goto out; + } + + leaf = path->nodes[0]; + buf_len = btrfs_dir_data_len(leaf, di); + + fspath = fs_path_alloc(); + buf = kmalloc(buf_len, GFP_KERNEL); + if (!fspath || !buf) { + ret = -ENOMEM; + goto out; + } + + ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, fspath); + if (ret < 0) + goto out; + + data_ptr = (unsigned long)(di + 1) + btrfs_dir_name_len(leaf, di); + read_extent_buffer(leaf, buf, data_ptr, buf_len); + + ret = send_set_xattr(sctx, fspath, XATTR_NAME_CAPS, + strlen(XATTR_NAME_CAPS), buf, buf_len); +out: + kfree(buf); + fs_path_free(fspath); + btrfs_free_path(path); + return ret; +} + static int clone_range(struct send_ctx *sctx, struct clone_root *clone_root, const u64 disk_byte, @@ -6001,6 +6073,10 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) goto out; } + ret = send_capabilities(sctx); + if (ret < 0) + goto out; + /* * If other directory inodes depended on our current directory * inode's move/rename, now do their move/rename operations. diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index e8a4b0ebe97f..90500b6c41fc 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -160,10 +160,9 @@ static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global) return (global->size << 1); } -static int can_overcommit(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, u64 bytes, - enum btrfs_reserve_flush_enum flush, - bool system_chunk) +int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, u64 bytes, + enum btrfs_reserve_flush_enum flush) { u64 profile; u64 avail; @@ -174,7 +173,7 @@ static int can_overcommit(struct btrfs_fs_info *fs_info, if (space_info->flags & BTRFS_BLOCK_GROUP_DATA) return 0; - if (system_chunk) + if (space_info->flags & BTRFS_BLOCK_GROUP_SYSTEM) profile = btrfs_system_alloc_profile(fs_info); else profile = btrfs_metadata_alloc_profile(fs_info); @@ -228,8 +227,8 @@ again: /* Check and see if our ticket can be satisified now. */ if ((used + ticket->bytes <= space_info->total_bytes) || - can_overcommit(fs_info, space_info, ticket->bytes, flush, - false)) { + btrfs_can_overcommit(fs_info, space_info, ticket->bytes, + flush)) { btrfs_space_info_update_bytes_may_use(fs_info, space_info, ticket->bytes); @@ -304,8 +303,8 @@ again: cache->key.objectid, cache->key.offset, btrfs_block_group_used(&cache->item), cache->pinned, cache->reserved, cache->ro ? "[readonly]" : ""); - btrfs_dump_free_space(cache, bytes); spin_unlock(&cache->lock); + btrfs_dump_free_space(cache, bytes); } if (++index < BTRFS_NR_RAID_TYPES) goto again; @@ -462,6 +461,7 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info, struct reserve_ticket *ticket = NULL; struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_block_rsv; struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv; + struct btrfs_block_rsv *trans_rsv = &fs_info->trans_block_rsv; struct btrfs_trans_handle *trans; u64 bytes_needed; u64 reclaim_bytes = 0; @@ -524,6 +524,11 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info, spin_lock(&delayed_refs_rsv->lock); reclaim_bytes += delayed_refs_rsv->reserved; spin_unlock(&delayed_refs_rsv->lock); + + spin_lock(&trans_rsv->lock); + reclaim_bytes += trans_rsv->reserved; + spin_unlock(&trans_rsv->lock); + if (reclaim_bytes >= bytes_needed) goto commit; bytes_needed -= reclaim_bytes; @@ -628,8 +633,7 @@ static void flush_space(struct btrfs_fs_info *fs_info, static inline u64 btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, - bool system_chunk) + struct btrfs_space_info *space_info) { struct reserve_ticket *ticket; u64 used; @@ -644,14 +648,14 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, return to_reclaim; to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); - if (can_overcommit(fs_info, space_info, to_reclaim, - BTRFS_RESERVE_FLUSH_ALL, system_chunk)) + if (btrfs_can_overcommit(fs_info, space_info, to_reclaim, + BTRFS_RESERVE_FLUSH_ALL)) return 0; used = btrfs_space_info_used(space_info, true); - if (can_overcommit(fs_info, space_info, SZ_1M, - BTRFS_RESERVE_FLUSH_ALL, system_chunk)) + if (btrfs_can_overcommit(fs_info, space_info, SZ_1M, + BTRFS_RESERVE_FLUSH_ALL)) expected = div_factor_fine(space_info->total_bytes, 95); else expected = div_factor_fine(space_info->total_bytes, 90); @@ -667,7 +671,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, - u64 used, bool system_chunk) + u64 used) { u64 thresh = div_factor_fine(space_info->total_bytes, 98); @@ -675,14 +679,41 @@ static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info, if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh) return 0; - if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info, - system_chunk)) + if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info)) return 0; return (used >= thresh && !btrfs_fs_closing(fs_info) && !test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)); } +static bool steal_from_global_rsv(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, + struct reserve_ticket *ticket) +{ + struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; + u64 min_bytes; + + if (global_rsv->space_info != space_info) + return false; + + spin_lock(&global_rsv->lock); + min_bytes = div_factor(global_rsv->size, 5); + if (global_rsv->reserved < min_bytes + ticket->bytes) { + spin_unlock(&global_rsv->lock); + return false; + } + global_rsv->reserved -= ticket->bytes; + ticket->bytes = 0; + list_del_init(&ticket->list); + wake_up(&ticket->wait); + space_info->tickets_id++; + if (global_rsv->reserved < global_rsv->size) + global_rsv->full = 0; + spin_unlock(&global_rsv->lock); + + return true; +} + /* * maybe_fail_all_tickets - we've exhausted our flushing, start failing tickets * @fs_info - fs_info for this fs @@ -715,6 +746,10 @@ static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info, ticket = list_first_entry(&space_info->tickets, struct reserve_ticket, list); + if (ticket->steal && + steal_from_global_rsv(fs_info, space_info, ticket)) + return true; + /* * may_commit_transaction will avoid committing the transaction * if it doesn't feel like the space reclaimed by the commit @@ -767,8 +802,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); spin_lock(&space_info->lock); - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info, - false); + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info); if (!to_reclaim) { space_info->flush = 0; spin_unlock(&space_info->lock); @@ -787,8 +821,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) return; } to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, - space_info, - false); + space_info); if (last_tickets_id == space_info->tickets_id) { flush_state++; } else { @@ -860,8 +893,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, int flush_state; spin_lock(&space_info->lock); - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info, - false); + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info); if (!to_reclaim) { spin_unlock(&space_info->lock); return; @@ -934,6 +966,7 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, switch (flush) { case BTRFS_RESERVE_FLUSH_ALL: + case BTRFS_RESERVE_FLUSH_ALL_STEAL: wait_reserve_ticket(fs_info, space_info, ticket); break; case BTRFS_RESERVE_FLUSH_LIMIT: @@ -992,8 +1025,7 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 orig_bytes, - enum btrfs_reserve_flush_enum flush, - bool system_chunk) + enum btrfs_reserve_flush_enum flush) { struct reserve_ticket ticket; u64 used; @@ -1015,8 +1047,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, */ if (!pending_tickets && ((used + orig_bytes <= space_info->total_bytes) || - can_overcommit(fs_info, space_info, orig_bytes, flush, - system_chunk))) { + btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) { btrfs_space_info_update_bytes_may_use(fs_info, space_info, orig_bytes); ret = 0; @@ -1033,7 +1064,9 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, ticket.bytes = orig_bytes; ticket.error = 0; init_waitqueue_head(&ticket.wait); - if (flush == BTRFS_RESERVE_FLUSH_ALL) { + ticket.steal = (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL); + if (flush == BTRFS_RESERVE_FLUSH_ALL || + flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) { list_add_tail(&ticket.list, &space_info->tickets); if (!space_info->flush) { space_info->flush = 1; @@ -1056,8 +1089,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, * the async reclaim as we will panic. */ if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) && - need_do_async_reclaim(fs_info, space_info, - used, system_chunk) && + need_do_async_reclaim(fs_info, space_info, used) && !work_busy(&fs_info->async_reclaim_work)) { trace_btrfs_trigger_flush(fs_info, space_info->flags, orig_bytes, flush, "preempt"); @@ -1094,10 +1126,9 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; int ret; - bool system_chunk = (root == fs_info->chunk_root); ret = __reserve_metadata_bytes(fs_info, block_rsv->space_info, - orig_bytes, flush, system_chunk); + orig_bytes, flush); if (ret == -ENOSPC && unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) { if (block_rsv != global_rsv && diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 8867e84aa33d..b9cffc62cafa 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -72,6 +72,7 @@ struct btrfs_space_info { struct reserve_ticket { u64 bytes; int error; + bool steal; struct list_head list; wait_queue_head_t wait; }; @@ -128,6 +129,9 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root, enum btrfs_reserve_flush_enum flush); void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info); +int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, u64 bytes, + enum btrfs_reserve_flush_enum flush); static inline void btrfs_space_info_free_bytes_may_use( struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index aea24202cd35..6a2ae208ff80 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -241,7 +241,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = trans->fs_info; - trans->aborted = errno; + WRITE_ONCE(trans->aborted, errno); /* Nothing used. The other threads that have joined this * transaction may be able to continue. */ if (!trans->dirty && list_empty(&trans->new_bgs)) { @@ -435,6 +435,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, char *compress_type; bool compress_force = false; enum btrfs_compression_type saved_compress_type; + int saved_compress_level; bool saved_compress_force; int no_compress = 0; @@ -517,6 +518,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, info->compress_type : BTRFS_COMPRESS_NONE; saved_compress_force = btrfs_test_opt(info, FORCE_COMPRESS); + saved_compress_level = info->compress_level; if (token == Opt_compress || token == Opt_compress_force || strncmp(args[0].from, "zlib", 4) == 0) { @@ -542,6 +544,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } else if (strncmp(args[0].from, "lzo", 3) == 0) { compress_type = "lzo"; info->compress_type = BTRFS_COMPRESS_LZO; + info->compress_level = 0; btrfs_set_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, NODATACOW); btrfs_clear_opt(info->mount_opt, NODATASUM); @@ -561,6 +564,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, no_compress = 0; } else if (strncmp(args[0].from, "no", 2) == 0) { compress_type = "no"; + info->compress_level = 0; + info->compress_type = 0; btrfs_clear_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); compress_force = false; @@ -581,11 +586,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, */ btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); } - if ((btrfs_test_opt(info, COMPRESS) && - (info->compress_type != saved_compress_type || - compress_force != saved_compress_force)) || - (!btrfs_test_opt(info, COMPRESS) && - no_compress == 1)) { + if (no_compress == 1) { + btrfs_info(info, "use no compression"); + } else if ((info->compress_type != saved_compress_type) || + (compress_force != saved_compress_force) || + (info->compress_level != saved_compress_level)) { btrfs_info(info, "%s %s compression, level %d", (compress_force) ? "force" : "use", compress_type, info->compress_level); @@ -1005,8 +1010,8 @@ out: return error; } -static char *get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, - u64 subvol_objectid) +char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, + u64 subvol_objectid) { struct btrfs_root *root = fs_info->tree_root; struct btrfs_root *fs_root; @@ -1287,6 +1292,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) { struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb); const char *compress_type; + const char *subvol_name; if (btrfs_test_opt(info, DEGRADED)) seq_puts(seq, ",degraded"); @@ -1371,8 +1377,13 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",ref_verify"); seq_printf(seq, ",subvolid=%llu", BTRFS_I(d_inode(dentry))->root->root_key.objectid); - seq_puts(seq, ",subvol="); - seq_dentry(seq, dentry, " \t\n\\"); + subvol_name = btrfs_get_subvol_name_from_objectid(info, + BTRFS_I(d_inode(dentry))->root->root_key.objectid); + if (!IS_ERR(subvol_name)) { + seq_puts(seq, ",subvol="); + seq_escape(seq, subvol_name, " \t\n\\"); + kfree(subvol_name); + } return 0; } @@ -1417,8 +1428,8 @@ static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid, goto out; } } - subvol_name = get_subvol_name_from_objectid(btrfs_sb(mnt->mnt_sb), - subvol_objectid); + subvol_name = btrfs_get_subvol_name_from_objectid( + btrfs_sb(mnt->mnt_sb), subvol_objectid); if (IS_ERR(subvol_name)) { root = ERR_CAST(subvol_name); subvol_name = NULL; @@ -1848,6 +1859,12 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) set_bit(BTRFS_FS_OPEN, &fs_info->flags); } out: + /* + * We need to set SB_I_VERSION here otherwise it'll get cleared by VFS, + * since the absence of the flag means it can be toggled off by remount. + */ + *flags |= SB_I_VERSION; + wake_up_process(fs_info->transaction_kthread); btrfs_remount_cleanup(fs_info, old_opts); return 0; @@ -2254,9 +2271,7 @@ static int btrfs_unfreeze(struct super_block *sb) static int btrfs_show_devname(struct seq_file *m, struct dentry *root) { struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); - struct btrfs_fs_devices *cur_devices; struct btrfs_device *dev, *first_dev = NULL; - struct list_head *head; /* * Lightweight locking of the devices. We should not need @@ -2266,18 +2281,13 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root) * least until the rcu_read_unlock. */ rcu_read_lock(); - cur_devices = fs_info->fs_devices; - while (cur_devices) { - head = &cur_devices->devices; - list_for_each_entry_rcu(dev, head, dev_list) { - if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) - continue; - if (!dev->name) - continue; - if (!first_dev || dev->devid < first_dev->devid) - first_dev = dev; - } - cur_devices = cur_devices->seed; + list_for_each_entry_rcu(dev, &fs_info->fs_devices->devices, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) + continue; + if (!dev->name) + continue; + if (!first_dev || dev->devid < first_dev->devid) + first_dev = dev; } if (first_dev) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index f6d3c80f2e28..5c299e1f2297 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -975,7 +975,9 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices, { int error = 0; struct btrfs_device *dev; + unsigned int nofs_flag; + nofs_flag = memalloc_nofs_save(); list_for_each_entry(dev, &fs_devices->devices, dev_list) { struct hd_struct *disk; struct kobject *disk_kobj; @@ -994,6 +996,7 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices, if (error) break; } + memalloc_nofs_restore(nofs_flag); return error; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index cdca0f656594..c346ee7ec18d 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -21,6 +21,7 @@ #include "dev-replace.h" #include "qgroup.h" #include "block-group.h" +#include "space-info.h" #define BTRFS_ROOT_TRANS_TAG 0 @@ -173,7 +174,7 @@ loop: cur_trans = fs_info->running_transaction; if (cur_trans) { - if (cur_trans->aborted) { + if (TRANS_ABORTED(cur_trans)) { spin_unlock(&fs_info->trans_lock); return cur_trans->aborted; } @@ -389,7 +390,7 @@ static inline int is_transaction_blocked(struct btrfs_transaction *trans) { return (trans->state >= TRANS_STATE_BLOCKED && trans->state < TRANS_STATE_UNBLOCKED && - !trans->aborted); + !TRANS_ABORTED(trans)); } /* wait for commit against the current transaction to become unblocked @@ -408,7 +409,7 @@ static void wait_current_trans(struct btrfs_fs_info *fs_info) wait_event(fs_info->transaction_wait, cur_trans->state >= TRANS_STATE_UNBLOCKED || - cur_trans->aborted); + TRANS_ABORTED(cur_trans)); btrfs_put_transaction(cur_trans); } else { spin_unlock(&fs_info->trans_lock); @@ -451,6 +452,7 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, u64 num_bytes = 0; u64 qgroup_reserved = 0; bool reloc_reserved = false; + bool do_chunk_alloc = false; int ret; /* Send isn't supposed to start transactions. */ @@ -491,7 +493,8 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, * refill that amount for whatever is missing in the reserve. */ num_bytes = btrfs_calc_insert_metadata_size(fs_info, num_items); - if (delayed_refs_rsv->full == 0) { + if (flush == BTRFS_RESERVE_FLUSH_ALL && + delayed_refs_rsv->full == 0) { delayed_refs_bytes = num_bytes; num_bytes <<= 1; } @@ -512,6 +515,9 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, delayed_refs_bytes); num_bytes -= delayed_refs_bytes; } + + if (rsv->space_info->force_alloc) + do_chunk_alloc = true; } else if (num_items == 0 && flush == BTRFS_RESERVE_FLUSH_ALL && !delayed_refs_rsv->full) { /* @@ -594,6 +600,19 @@ got_it: current->journal_info = h; /* + * If the space_info is marked ALLOC_FORCE then we'll get upgraded to + * ALLOC_FORCE the first run through, and then we won't allocate for + * anybody else who races in later. We don't care about the return + * value here. + */ + if (do_chunk_alloc && num_bytes) { + u64 flags = h->block_rsv->space_info->flags; + + btrfs_chunk_alloc(h, btrfs_get_alloc_profile(fs_info, flags), + CHUNK_ALLOC_NO_FORCE); + } + + /* * btrfs_record_root_in_trans() needs to alloc new extents, and may * call btrfs_join_transaction() while we're also starting a * transaction. @@ -627,43 +646,10 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( struct btrfs_root *root, - unsigned int num_items, - int min_factor) + unsigned int num_items) { - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_trans_handle *trans; - u64 num_bytes; - int ret; - - /* - * We have two callers: unlink and block group removal. The - * former should succeed even if we will temporarily exceed - * quota and the latter operates on the extent root so - * qgroup enforcement is ignored anyway. - */ - trans = start_transaction(root, num_items, TRANS_START, - BTRFS_RESERVE_FLUSH_ALL, false); - if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC) - return trans; - - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) - return trans; - - num_bytes = btrfs_calc_insert_metadata_size(fs_info, num_items); - ret = btrfs_cond_migrate_bytes(fs_info, &fs_info->trans_block_rsv, - num_bytes, min_factor); - if (ret) { - btrfs_end_transaction(trans); - return ERR_PTR(ret); - } - - trans->block_rsv = &fs_info->trans_block_rsv; - trans->bytes_reserved = num_bytes; - trace_btrfs_space_reservation(fs_info, "transaction", - trans->transid, num_bytes, 1); - - return trans; + return start_transaction(root, num_items, TRANS_START, + BTRFS_RESERVE_FLUSH_ALL_STEAL, false); } struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root) @@ -884,10 +870,13 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, if (throttle) btrfs_run_delayed_iputs(info); - if (trans->aborted || + if (TRANS_ABORTED(trans) || test_bit(BTRFS_FS_STATE_ERROR, &info->fs_state)) { wake_up_process(info->transaction_kthread); - err = -EIO; + if (TRANS_ABORTED(trans)) + err = trans->aborted; + else + err = -EROFS; } kmem_cache_free(btrfs_trans_handle_cachep, trans); @@ -1741,7 +1730,8 @@ static void wait_current_trans_commit_start(struct btrfs_fs_info *fs_info, struct btrfs_transaction *trans) { wait_event(fs_info->transaction_blocked_wait, - trans->state >= TRANS_STATE_COMMIT_START || trans->aborted); + trans->state >= TRANS_STATE_COMMIT_START || + TRANS_ABORTED(trans)); } /* @@ -1753,7 +1743,8 @@ static void wait_current_trans_commit_start_and_unblock( struct btrfs_transaction *trans) { wait_event(fs_info->transaction_wait, - trans->state >= TRANS_STATE_UNBLOCKED || trans->aborted); + trans->state >= TRANS_STATE_UNBLOCKED || + TRANS_ABORTED(trans)); } /* @@ -1971,7 +1962,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) trans->dirty = true; /* Stop the commit early if ->aborted is set */ - if (unlikely(READ_ONCE(cur_trans->aborted))) { + if (TRANS_ABORTED(cur_trans)) { ret = cur_trans->aborted; btrfs_end_transaction(trans); return ret; @@ -2045,7 +2036,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) wait_for_commit(cur_trans); - if (unlikely(cur_trans->aborted)) + if (TRANS_ABORTED(cur_trans)) ret = cur_trans->aborted; btrfs_put_transaction(cur_trans); @@ -2064,7 +2055,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) spin_unlock(&fs_info->trans_lock); wait_for_commit(prev_trans); - ret = prev_trans->aborted; + ret = READ_ONCE(prev_trans->aborted); btrfs_put_transaction(prev_trans); if (ret) @@ -2118,8 +2109,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) wait_event(cur_trans->writer_wait, atomic_read(&cur_trans->num_writers) == 1); - /* ->aborted might be set after the previous check, so check it */ - if (unlikely(READ_ONCE(cur_trans->aborted))) { + if (TRANS_ABORTED(cur_trans)) { ret = cur_trans->aborted; goto scrub_continue; } @@ -2237,7 +2227,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) * The tasks which save the space cache and inode cache may also * update ->aborted, check it. */ - if (unlikely(READ_ONCE(cur_trans->aborted))) { + if (TRANS_ABORTED(cur_trans)) { ret = cur_trans->aborted; mutex_unlock(&fs_info->tree_log_mutex); mutex_unlock(&fs_info->reloc_mutex); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 2c5a6f6e5bb0..7291a2a93075 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -116,6 +116,10 @@ struct btrfs_trans_handle { struct btrfs_block_rsv *orig_rsv; refcount_t use_count; unsigned int type; + /* + * Error code of transaction abort, set outside of locks and must use + * the READ_ONCE/WRITE_ONCE access + */ short aborted; bool adding_csums; bool allocating_chunk; @@ -127,6 +131,14 @@ struct btrfs_trans_handle { struct list_head new_bgs; }; +/* + * The abort status can be changed between calls and is not protected by locks. + * This accepts btrfs_transaction and btrfs_trans_handle as types. Once it's + * set to a non-zero value it does not change, so the macro should be in checks + * but is not necessary for further reads of the value. + */ +#define TRANS_ABORTED(trans) (unlikely(READ_ONCE((trans)->aborted))) + struct btrfs_pending_snapshot { struct dentry *dentry; struct inode *dir; @@ -181,8 +193,7 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, unsigned int num_items); struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( struct btrfs_root *root, - unsigned int num_items, - int min_factor); + unsigned int num_items); 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); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 0e44db066641..84b8d6ebf98f 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -674,6 +674,44 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, return 0; } +/* + * Enhanced version of chunk item checker. + * + * The common btrfs_check_chunk_valid() doesn't check item size since it needs + * to work on super block sys_chunk_array which doesn't have full item ptr. + */ +static int check_leaf_chunk_item(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, + struct btrfs_key *key, int slot) +{ + int num_stripes; + + if (btrfs_item_size_nr(leaf, slot) < sizeof(struct btrfs_chunk)) { + chunk_err(leaf, chunk, key->offset, + "invalid chunk item size: have %u expect [%zu, %u)", + btrfs_item_size_nr(leaf, slot), + sizeof(struct btrfs_chunk), + BTRFS_LEAF_DATA_SIZE(leaf->fs_info)); + return -EUCLEAN; + } + + num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + /* Let btrfs_check_chunk_valid() handle this error type */ + if (num_stripes == 0) + goto out; + + if (btrfs_chunk_item_size(num_stripes) != + btrfs_item_size_nr(leaf, slot)) { + chunk_err(leaf, chunk, key->offset, + "invalid chunk item size: have %u expect %lu", + btrfs_item_size_nr(leaf, slot), + btrfs_chunk_item_size(num_stripes)); + return -EUCLEAN; + } +out: + return btrfs_check_chunk_valid(leaf, chunk, key->offset); +} + __printf(3, 4) __cold static void dev_item_err(const struct extent_buffer *eb, int slot, @@ -772,7 +810,7 @@ static int check_inode_item(struct extent_buffer *leaf, /* Here we use super block generation + 1 to handle log tree */ if (btrfs_inode_generation(leaf, iitem) > super_gen + 1) { inode_item_err(fs_info, leaf, slot, - "invalid inode generation: has %llu expect (0, %llu]", + "invalid inode transid: has %llu expect [0, %llu]", btrfs_inode_generation(leaf, iitem), super_gen + 1); return -EUCLEAN; @@ -1265,7 +1303,7 @@ static int check_leaf_item(struct extent_buffer *leaf, break; case BTRFS_CHUNK_ITEM_KEY: chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); - ret = btrfs_check_chunk_valid(leaf, chunk, key->offset); + ret = check_leaf_chunk_item(leaf, chunk, key, slot); break; case BTRFS_DEV_ITEM_KEY: ret = check_dev_item(leaf, key, slot); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7d464b049507..7042b84edc89 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -167,6 +167,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans, if (ret) goto out; + set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } @@ -193,6 +194,9 @@ static int join_running_log_trans(struct btrfs_root *root) { int ret = -ENOENT; + if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) + return ret; + mutex_lock(&root->log_mutex); if (root->log_root) { ret = 0; @@ -3136,29 +3140,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); - atomic_inc(&log_root_tree->log_batch); - atomic_inc(&log_root_tree->log_writers); index2 = log_root_tree->log_transid % 2; list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); root_log_ctx.log_transid = log_root_tree->log_transid; - mutex_unlock(&log_root_tree->log_mutex); - - mutex_lock(&log_root_tree->log_mutex); - /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit * open until we drop the log_mutex. */ ret = update_log_root(trans, log, &new_root_item); - - if (atomic_dec_and_test(&log_root_tree->log_writers)) { - /* atomic_dec_and_test implies a barrier */ - cond_wake_up_nomb(&log_root_tree->log_writer_wait); - } - if (ret) { if (!list_empty(&root_log_ctx.list)) list_del_init(&root_log_ctx.list); @@ -3204,8 +3196,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, root_log_ctx.log_transid - 1); } - wait_for_writer(log_root_tree); - /* * now that we've moved on to the tree of log tree roots, * check the full commit flag again @@ -3327,6 +3317,7 @@ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root) if (root->log_root) { free_log_tree(trans, root->log_root); root->log_root = NULL; + clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); } return 0; } @@ -3482,11 +3473,13 @@ fail: btrfs_free_path(path); out_unlock: mutex_unlock(&dir->log_mutex); - if (ret == -ENOSPC) { + if (err == -ENOSPC) { btrfs_set_log_full_commit(trans); - ret = 0; - } else if (ret < 0) - btrfs_abort_transaction(trans, ret); + err = 0; + } else if (err < 0 && err != -ENOENT) { + /* ENOENT can be returned if the entry hasn't been fsynced yet */ + btrfs_abort_transaction(trans, err); + } btrfs_end_log_trans(root); @@ -4049,11 +4042,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, fs_info->csum_root, ds + cs, ds + cs + cl - 1, &ordered_sums, 0); - if (ret) { - btrfs_release_path(dst_path); - kfree(ins_data); - return ret; - } + if (ret) + break; } } } @@ -4066,7 +4056,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, * we have to do this after the loop above to avoid changing the * log tree while trying to change the log tree. */ - ret = 0; while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next, struct btrfs_ordered_sum, @@ -5007,6 +4996,138 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans, return ret; } +static int copy_inode_items_to_log(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, + struct btrfs_key *min_key, + const struct btrfs_key *max_key, + struct btrfs_path *path, + struct btrfs_path *dst_path, + const u64 logged_isize, + const bool recursive_logging, + const int inode_only, + struct btrfs_log_ctx *ctx, + bool *need_log_inode_item) +{ + struct btrfs_root *root = inode->root; + int ins_start_slot = 0; + int ins_nr = 0; + int ret; + + while (1) { + ret = btrfs_search_forward(root, min_key, path, trans->transid); + if (ret < 0) + return ret; + if (ret > 0) { + ret = 0; + break; + } +again: + /* Note, ins_nr might be > 0 here, cleanup outside the loop */ + if (min_key->objectid != max_key->objectid) + break; + if (min_key->type > max_key->type) + break; + + if (min_key->type == BTRFS_INODE_ITEM_KEY) + *need_log_inode_item = false; + + if ((min_key->type == BTRFS_INODE_REF_KEY || + min_key->type == BTRFS_INODE_EXTREF_KEY) && + inode->generation == trans->transid && + !recursive_logging) { + u64 other_ino = 0; + u64 other_parent = 0; + + ret = btrfs_check_ref_name_override(path->nodes[0], + path->slots[0], min_key, inode, + &other_ino, &other_parent); + if (ret < 0) { + return ret; + } else if (ret > 0 && ctx && + other_ino != btrfs_ino(BTRFS_I(ctx->inode))) { + if (ins_nr > 0) { + ins_nr++; + } else { + ins_nr = 1; + ins_start_slot = path->slots[0]; + } + ret = copy_items(trans, inode, dst_path, path, + ins_start_slot, ins_nr, + inode_only, logged_isize); + if (ret < 0) + return ret; + ins_nr = 0; + + ret = log_conflicting_inodes(trans, root, path, + ctx, other_ino, other_parent); + if (ret) + return ret; + btrfs_release_path(path); + goto next_key; + } + } + + /* Skip xattrs, we log them later with btrfs_log_all_xattrs() */ + if (min_key->type == BTRFS_XATTR_ITEM_KEY) { + if (ins_nr == 0) + goto next_slot; + ret = copy_items(trans, inode, dst_path, path, + ins_start_slot, + ins_nr, inode_only, logged_isize); + if (ret < 0) + return ret; + ins_nr = 0; + goto next_slot; + } + + if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) { + ins_nr++; + goto next_slot; + } else if (!ins_nr) { + ins_start_slot = path->slots[0]; + ins_nr = 1; + goto next_slot; + } + + ret = copy_items(trans, inode, dst_path, path, ins_start_slot, + ins_nr, inode_only, logged_isize); + if (ret < 0) + return ret; + ins_nr = 1; + ins_start_slot = path->slots[0]; +next_slot: + path->slots[0]++; + if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { + btrfs_item_key_to_cpu(path->nodes[0], min_key, + path->slots[0]); + goto again; + } + if (ins_nr) { + ret = copy_items(trans, inode, dst_path, path, + ins_start_slot, ins_nr, inode_only, + logged_isize); + if (ret < 0) + return ret; + ins_nr = 0; + } + btrfs_release_path(path); +next_key: + if (min_key->offset < (u64)-1) { + min_key->offset++; + } else if (min_key->type < max_key->type) { + min_key->type++; + min_key->offset = 0; + } else { + break; + } + } + if (ins_nr) + ret = copy_items(trans, inode, dst_path, path, ins_start_slot, + ins_nr, inode_only, logged_isize); + + return ret; +} + /* log a single inode in the tree log. * At least one parent directory for this inode must exist in the tree * or be logged already. @@ -5028,17 +5149,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, const loff_t end, struct btrfs_log_ctx *ctx) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_path *path; struct btrfs_path *dst_path; struct btrfs_key min_key; struct btrfs_key max_key; struct btrfs_root *log = root->log_root; int err = 0; - int ret; - int nritems; - int ins_start_slot = 0; - int ins_nr; + int ret = 0; bool fast_search = false; u64 ino = btrfs_ino(inode); struct extent_map_tree *em_tree = &inode->extent_tree; @@ -5074,15 +5191,19 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, max_key.offset = (u64)-1; /* - * Only run delayed items if we are a dir or a new file. - * Otherwise commit the delayed inode only, which is needed in - * order for the log replay code to mark inodes for link count - * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items). + * Only run delayed items if we are a directory. We want to make sure + * all directory indexes hit the fs/subvolume tree so we can find them + * and figure out which index ranges have to be logged. + * + * Otherwise commit the delayed inode only if the full sync flag is set, + * as we want to make sure an up to date version is in the subvolume + * tree so copy_inode_items_to_log() / copy_items() can find it and copy + * it to the log tree. For a non full sync, we always log the inode item + * based on the in-memory struct btrfs_inode which is always up to date. */ - if (S_ISDIR(inode->vfs_inode.i_mode) || - inode->generation > fs_info->last_trans_committed) + if (S_ISDIR(inode->vfs_inode.i_mode)) ret = btrfs_commit_inode_delayed_items(trans, inode); - else + else if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags)) ret = btrfs_commit_inode_delayed_inode(inode); if (ret) { @@ -5169,139 +5290,12 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, goto out_unlock; } - while (1) { - ins_nr = 0; - ret = btrfs_search_forward(root, &min_key, - path, trans->transid); - if (ret < 0) { - err = ret; - goto out_unlock; - } - if (ret != 0) - break; -again: - /* note, ins_nr might be > 0 here, cleanup outside the loop */ - if (min_key.objectid != ino) - break; - if (min_key.type > max_key.type) - break; - - if (min_key.type == BTRFS_INODE_ITEM_KEY) - need_log_inode_item = false; - - if ((min_key.type == BTRFS_INODE_REF_KEY || - min_key.type == BTRFS_INODE_EXTREF_KEY) && - inode->generation == trans->transid && - !recursive_logging) { - u64 other_ino = 0; - u64 other_parent = 0; - - ret = btrfs_check_ref_name_override(path->nodes[0], - path->slots[0], &min_key, inode, - &other_ino, &other_parent); - if (ret < 0) { - err = ret; - goto out_unlock; - } else if (ret > 0 && ctx && - other_ino != btrfs_ino(BTRFS_I(ctx->inode))) { - if (ins_nr > 0) { - ins_nr++; - } else { - ins_nr = 1; - ins_start_slot = path->slots[0]; - } - ret = copy_items(trans, inode, dst_path, path, - ins_start_slot, - ins_nr, inode_only, - logged_isize); - if (ret < 0) { - err = ret; - goto out_unlock; - } - ins_nr = 0; - - err = log_conflicting_inodes(trans, root, path, - ctx, other_ino, other_parent); - if (err) - goto out_unlock; - btrfs_release_path(path); - goto next_key; - } - } - - /* Skip xattrs, we log them later with btrfs_log_all_xattrs() */ - if (min_key.type == BTRFS_XATTR_ITEM_KEY) { - if (ins_nr == 0) - goto next_slot; - ret = copy_items(trans, inode, dst_path, path, - ins_start_slot, - ins_nr, inode_only, logged_isize); - if (ret < 0) { - err = ret; - goto out_unlock; - } - ins_nr = 0; - goto next_slot; - } - - if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) { - ins_nr++; - goto next_slot; - } else if (!ins_nr) { - ins_start_slot = path->slots[0]; - ins_nr = 1; - goto next_slot; - } - - ret = copy_items(trans, inode, dst_path, path, - ins_start_slot, ins_nr, inode_only, - logged_isize); - if (ret < 0) { - err = ret; - goto out_unlock; - } - ins_nr = 1; - ins_start_slot = path->slots[0]; -next_slot: - - nritems = btrfs_header_nritems(path->nodes[0]); - path->slots[0]++; - if (path->slots[0] < nritems) { - btrfs_item_key_to_cpu(path->nodes[0], &min_key, - path->slots[0]); - goto again; - } - if (ins_nr) { - ret = copy_items(trans, inode, dst_path, path, - ins_start_slot, - ins_nr, inode_only, logged_isize); - if (ret < 0) { - err = ret; - goto out_unlock; - } - ins_nr = 0; - } - btrfs_release_path(path); -next_key: - if (min_key.offset < (u64)-1) { - min_key.offset++; - } else if (min_key.type < max_key.type) { - min_key.type++; - min_key.offset = 0; - } else { - break; - } - } - if (ins_nr) { - ret = copy_items(trans, inode, dst_path, path, - ins_start_slot, ins_nr, inode_only, - logged_isize); - if (ret < 0) { - err = ret; - goto out_unlock; - } - ins_nr = 0; - } + err = copy_inode_items_to_log(trans, inode, &min_key, &max_key, + path, dst_path, logged_isize, + recursive_logging, inode_only, ctx, + &need_log_inode_item); + if (err) + goto out_unlock; btrfs_release_path(path); btrfs_release_path(dst_path); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3e64f49c394b..e798caee978e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4,6 +4,7 @@ */ #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/bio.h> #include <linux/slab.h> #include <linux/buffer_head.h> @@ -219,7 +220,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, * * global::fs_devs - add, remove, updates to the global list * - * does not protect: manipulation of the fs_devices::devices list! + * does not protect: manipulation of the fs_devices::devices list in general + * but in mount context it could be used to exclude list modifications by eg. + * scan ioctl * * btrfs_device::name - renames (write side), read is RCU * @@ -232,6 +235,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, * may be used to exclude some operations from running concurrently without any * modifications to the list (see write_all_supers) * + * Is not required at mount and close times, because our device list is + * protected by the uuid_mutex at that point. + * * balance_mutex * ------------- * protects balance structures (status, state) and context accessed from @@ -778,6 +784,11 @@ static int btrfs_free_stale_devices(const char *path, return ret; } +/* + * This is only used on mount, and we are protected from competing things + * messing with our fs_devices by the uuid_mutex, thus we do not need the + * fs_devices->device_list_mutex here. + */ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device, fmode_t flags, void *holder) @@ -1223,6 +1234,8 @@ again: &device->dev_state)) { if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state) && + !test_bit(BTRFS_DEV_STATE_MISSING, + &device->dev_state) && (!latest_dev || device->generation > latest_dev->generation)) { latest_dev = device; @@ -1416,8 +1429,14 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, int ret; lockdep_assert_held(&uuid_mutex); + /* + * The device_list_mutex cannot be taken here in case opening the + * underlying device takes further locks like bd_mutex. + * + * We also don't need the lock here as this is called during mount and + * exclusion is provided by uuid_mutex + */ - mutex_lock(&fs_devices->device_list_mutex); if (fs_devices->opened) { fs_devices->opened++; ret = 0; @@ -1425,7 +1444,6 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, list_sort(NULL, &fs_devices->devices, devid_cmp); ret = open_fs_devices(fs_devices, flags, holder); } - mutex_unlock(&fs_devices->device_list_mutex); return ret; } @@ -2769,8 +2787,18 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path ret = btrfs_commit_transaction(trans); } - /* Update ctime/mtime for libblkid */ + /* + * Now that we have written a new super block to this device, check all + * other fs_devices list if device_path alienates any other scanned + * device. + * We can ignore the return value as it typically returns -EINVAL and + * only succeeds if the device was an alien. + */ + btrfs_forget_devices(device_path); + + /* Update ctime/mtime for blkid or udev */ update_dev_time(device_path); + return ret; error_sysfs: @@ -3271,7 +3299,7 @@ static int insert_balance_item(struct btrfs_fs_info *fs_info, if (!path) return -ENOMEM; - trans = btrfs_start_transaction(root, 0); + trans = btrfs_start_transaction_fallback_global_rsv(root, 0); if (IS_ERR(trans)) { btrfs_free_path(path); return PTR_ERR(trans); @@ -4234,7 +4262,22 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, mutex_lock(&fs_info->balance_mutex); if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req)) btrfs_info(fs_info, "balance: paused"); - else if (ret == -ECANCELED && atomic_read(&fs_info->balance_cancel_req)) + /* + * Balance can be canceled by: + * + * - Regular cancel request + * Then ret == -ECANCELED and balance_cancel_req > 0 + * + * - Fatal signal to "btrfs" process + * Either the signal caught by wait_reserve_ticket() and callers + * got -EINTR, or caught by btrfs_should_cancel_balance() and + * got -ECANCELED. + * Either way, in this case balance_cancel_req = 0, and + * ret == -EINTR or ret == -ECANCELED. + * + * So here we only check the return value to catch canceled balance. + */ + else if (ret == -ECANCELED || ret == -EINTR) btrfs_info(fs_info, "balance: canceled"); else btrfs_info(fs_info, "balance: ended with status: %d", ret); @@ -4526,6 +4569,7 @@ static int btrfs_uuid_scan_kthread(void *data) goto skip; } update_tree: + btrfs_release_path(path); if (!btrfs_is_empty_uuid(root_item.uuid)) { ret = btrfs_uuid_tree_add(trans, root_item.uuid, BTRFS_UUID_KEY_SUBVOL, @@ -4550,6 +4594,7 @@ update_tree: } skip: + btrfs_release_path(path); if (trans) { ret = btrfs_end_transaction(trans); trans = NULL; @@ -4557,7 +4602,6 @@ skip: break; } - btrfs_release_path(path); if (key.offset < (u64)-1) { key.offset++; } else if (key.type < BTRFS_ROOT_ITEM_KEY) { @@ -5632,12 +5676,13 @@ void btrfs_put_bbio(struct btrfs_bio *bbio) * replace. */ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info, - u64 logical, u64 length, + u64 logical, u64 *length_ret, struct btrfs_bio **bbio_ret) { struct extent_map *em; struct map_lookup *map; struct btrfs_bio *bbio; + u64 length = *length_ret; u64 offset; u64 stripe_nr; u64 stripe_nr_end; @@ -5670,7 +5715,8 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info, } offset = logical - em->start; - length = min_t(u64, em->len - offset, length); + length = min_t(u64, em->start + em->len - logical, length); + *length_ret = length; stripe_len = map->stripe_len; /* @@ -6085,7 +6131,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, if (op == BTRFS_MAP_DISCARD) return __btrfs_map_block_for_discard(fs_info, logical, - *length, bbio_ret); + length, bbio_ret); ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom); if (ret < 0) @@ -6665,8 +6711,17 @@ static struct btrfs_device *add_missing_dev(struct btrfs_fs_devices *fs_devices, u64 devid, u8 *dev_uuid) { struct btrfs_device *device; + unsigned int nofs_flag; + /* + * We call this under the chunk_mutex, so we want to use NOFS for this + * allocation, however we don't want to change btrfs_alloc_device() to + * always do NOFS because we use it in a lot of other GFP_KERNEL safe + * places. + */ + nofs_flag = memalloc_nofs_save(); device = btrfs_alloc_device(NULL, &devid, dev_uuid); + memalloc_nofs_restore(nofs_flag); if (IS_ERR(device)) return device; @@ -7255,7 +7310,14 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) * otherwise we don't need it. */ mutex_lock(&uuid_mutex); - mutex_lock(&fs_info->chunk_mutex); + + /* + * It is possible for mount and umount to race in such a way that + * we execute this code path, but open_fs_devices failed to clear + * total_rw_bytes. We certainly want it cleared before reading the + * device items, so clear it here. + */ + fs_info->fs_devices->total_rw_bytes = 0; /* * Read all device items, and then all the chunk items. All @@ -7292,7 +7354,9 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) } else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) { struct btrfs_chunk *chunk; chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + mutex_lock(&fs_info->chunk_mutex); ret = read_one_chunk(&found_key, leaf, chunk); + mutex_unlock(&fs_info->chunk_mutex); if (ret) goto error; } @@ -7322,7 +7386,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) } ret = 0; error: - mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&uuid_mutex); btrfs_free_path(path); diff --git a/fs/buffer.c b/fs/buffer.c index 79c9562434a8..22d8ac4a8c40 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3170,6 +3170,15 @@ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { + /* + * The bh should be mapped, but it might not be if the + * device was hot-removed. Not much we can do but fail the I/O. + */ + if (!buffer_mapped(bh)) { + unlock_buffer(bh); + return -EIO; + } + get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index b2695919435e..af563d73d252 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2013,12 +2013,24 @@ ack: if (mutex_trylock(&session->s_mutex) == 0) { dout("inverting session/ino locks on %p\n", session); + session = ceph_get_mds_session(session); spin_unlock(&ci->i_ceph_lock); if (took_snap_rwsem) { up_read(&mdsc->snap_rwsem); took_snap_rwsem = 0; } - mutex_lock(&session->s_mutex); + if (session) { + mutex_lock(&session->s_mutex); + ceph_put_mds_session(session); + } else { + /* + * Because we take the reference while + * holding the i_ceph_lock, it should + * never be NULL. Throw a warning if it + * ever is. + */ + WARN_ON_ONCE(true); + } goto retry; } } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 2e4764fd1872..3367a8194f24 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -920,6 +920,10 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry, req->r_num_caps = 2; req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; + if (as_ctx.pagelist) { + req->r_pagelist = as_ctx.pagelist; + as_ctx.pagelist = NULL; + } err = ceph_mdsc_do_request(mdsc, dir, req); if (!err && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 79dc06881e78..e088843a7734 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -172,9 +172,16 @@ struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino) static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) { struct inode *inode = __lookup_inode(sb, ino); + int err; + if (IS_ERR(inode)) return ERR_CAST(inode); - if (inode->i_nlink == 0) { + /* We need LINK caps to reliably check i_nlink */ + err = ceph_do_getattr(inode, CEPH_CAP_LINK_SHARED, false); + if (err) + return ERR_PTR(err); + /* -ESTALE if inode as been unlinked and no file is open */ + if ((inode->i_nlink == 0) && (atomic_read(&inode->i_count) == 1)) { iput(inode); return ERR_PTR(-ESTALE); } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ce54a1b12819..a10711a6337a 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1260,6 +1260,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); struct page *pinned_page = NULL; + bool direct_lock = iocb->ki_flags & IOCB_DIRECT; ssize_t ret; int want, got = 0; int retry_op = 0, read = 0; @@ -1268,7 +1269,7 @@ again: dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n", inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode); - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_start_io_direct(inode); else ceph_start_io_read(inode); @@ -1325,7 +1326,7 @@ again: } ceph_put_cap_refs(ci, got); - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_end_io_direct(inode); else ceph_end_io_read(inode); @@ -2197,6 +2198,7 @@ const struct file_operations ceph_file_fops = { .mmap = ceph_mmap, .fsync = ceph_fsync, .lock = ceph_lock, + .setlease = simple_nosetlease, .flock = ceph_flock, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index c07407586ce8..660a878e20ef 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -754,8 +754,11 @@ static int fill_inode(struct inode *inode, struct page *locked_page, info_caps = le32_to_cpu(info->cap.caps); /* prealloc new cap struct */ - if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) + if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) { new_cap = ceph_get_cap(mdsc, caps_reservation); + if (!new_cap) + return -ENOMEM; + } /* * prealloc xattr data, if it looks like we'll need it. only diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index b79fe6549df6..0f21073a51a1 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3091,8 +3091,10 @@ static void handle_session(struct ceph_mds_session *session, goto bad; /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_64_safe(&p, end, features, bad); - p += len - sizeof(features); + if (len) { + ceph_decode_64_safe(&p, end, features, bad); + p += len - sizeof(features); + } } mutex_lock(&mdsc->mutex); @@ -4066,6 +4068,9 @@ static void delayed_work(struct work_struct *work) dout("mdsc delayed_work\n"); + if (mdsc->stopping) + return; + mutex_lock(&mdsc->mutex); renew_interval = mdsc->mdsmap->m_session_timeout >> 2; renew_caps = time_after_eq(jiffies, HZ*renew_interval + @@ -4141,7 +4146,6 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) return -ENOMEM; } - fsc->mdsc = mdsc; init_completion(&mdsc->safe_umount_waiters); init_waitqueue_head(&mdsc->session_close_wq); INIT_LIST_HEAD(&mdsc->waiting_for_map); @@ -4193,6 +4197,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) strscpy(mdsc->nodename, utsname()->nodename, sizeof(mdsc->nodename)); + + fsc->mdsc = mdsc; return 0; } @@ -4430,7 +4436,16 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc) static void ceph_mdsc_stop(struct ceph_mds_client *mdsc) { dout("stop\n"); - cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */ + /* + * Make sure the delayed work stopped before releasing + * the resources. + * + * Because the cancel_delayed_work_sync() will only + * guarantee that the work finishes executing. But the + * delayed work will re-arm itself again after that. + */ + flush_delayed_work(&mdsc->delayed_work); + if (mdsc->mdsmap) ceph_mdsmap_destroy(mdsc->mdsmap); kfree(mdsc->sessions); diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index 689162e2e175..3150c19cdc2f 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -530,8 +530,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_CTX) || (con != ASN1_CON) || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 0\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 0\n", + cls, con, tag, end); return 0; } @@ -541,8 +541,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_UNI) || (con != ASN1_CON) || (tag != ASN1_SEQ)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 1\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 1\n", + cls, con, tag, end); return 0; } @@ -552,8 +552,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_CTX) || (con != ASN1_CON) || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 0\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 0\n", + cls, con, tag, end); return 0; } @@ -564,8 +564,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_UNI) || (con != ASN1_CON) || (tag != ASN1_SEQ)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 1\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d sequence_end = %p exit 1\n", + cls, con, tag, sequence_end); return 0; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f9cbdfc1591b..b16c994414ab 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -268,8 +268,9 @@ struct smb_version_operations { int (*check_message)(char *, unsigned int, struct TCP_Server_Info *); bool (*is_oplock_break)(char *, struct TCP_Server_Info *); int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *); - void (*downgrade_oplock)(struct TCP_Server_Info *, - struct cifsInodeInfo *, bool); + void (*downgrade_oplock)(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache); /* process transaction2 response */ bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *, char *, int); @@ -1261,6 +1262,8 @@ struct cifsFileInfo { unsigned int f_flags; bool invalidHandle:1; /* file closed via session abend */ bool oplock_break_cancelled:1; + unsigned int oplock_epoch; /* epoch from the lease break */ + __u32 oplock_level; /* oplock/lease level from the lease break */ int count; spinlock_t file_info_lock; /* protects four flag/count fields above */ struct mutex fh_mutex; /* prevents reopen race after dead ses*/ @@ -1408,7 +1411,7 @@ struct cifsInodeInfo { unsigned int epoch; /* used to track lease state changes */ #define CIFS_INODE_PENDING_OPLOCK_BREAK (0) /* oplock break in progress */ #define CIFS_INODE_PENDING_WRITERS (1) /* Writes in progress */ -#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */ +#define CIFS_INODE_FLAG_UNUSED (2) /* Unused flag */ #define CIFS_INO_DELETE_PENDING (3) /* delete pending on server */ #define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */ #define CIFS_INO_LOCK (5) /* lock bit for synchronization */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 721b2560caa7..f5df2a4195c2 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -614,26 +614,26 @@ cifs_reconnect(struct TCP_Server_Info *server) try_to_freeze(); mutex_lock(&server->srv_mutex); +#ifdef CONFIG_CIFS_DFS_UPCALL /* * Set up next DFS target server (if any) for reconnect. If DFS * feature is disabled, then we will retry last server we * connected to before. */ + reconn_inval_dfs_target(server, cifs_sb, &tgt_list, &tgt_it); +#endif + rc = reconn_set_ipaddr(server); + if (rc) { + cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", + __func__, rc); + } + if (cifs_rdma_enabled(server)) rc = smbd_reconnect(server); else rc = generic_ip_connect(server); if (rc) { cifs_dbg(FYI, "reconnect error %d\n", rc); -#ifdef CONFIG_CIFS_DFS_UPCALL - reconn_inval_dfs_target(server, cifs_sb, &tgt_list, - &tgt_it); -#endif - rc = reconn_set_ipaddr(server); - if (rc) { - cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", - __func__, rc); - } mutex_unlock(&server->srv_mutex); msleep(3000); } else { @@ -5281,9 +5281,15 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) vol_info->nocase = master_tcon->nocase; vol_info->nohandlecache = master_tcon->nohandlecache; vol_info->local_lease = master_tcon->local_lease; + vol_info->no_lease = master_tcon->no_lease; + vol_info->resilient = master_tcon->use_resilient; + vol_info->persistent = master_tcon->use_persistent; + vol_info->handle_timeout = master_tcon->handle_timeout; vol_info->no_linux_ext = !master_tcon->unix_ext; + vol_info->linux_ext = master_tcon->posix_extensions; vol_info->sectype = master_tcon->ses->sectype; vol_info->sign = master_tcon->ses->sign; + vol_info->seal = master_tcon->seal; rc = cifs_set_vol_auth(vol_info, master_tcon->ses); if (rc) { @@ -5309,10 +5315,6 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) goto out; } - /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */ - if (tcon->posix_extensions) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; - if (cap_unix(ses)) reset_cifs_unix_caps(0, tcon, NULL, vol_info); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 4959dbe740f7..31d578739341 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4269,7 +4269,8 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; __SetPageLocked(page); - if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { + rc = add_to_page_cache_locked(page, mapping, page->index, gfp); + if (rc) { __ClearPageLocked(page); break; } @@ -4285,6 +4286,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, struct list_head *page_list, unsigned num_pages) { int rc; + int err = 0; struct list_head tmplist; struct cifsFileInfo *open_file = file->private_data; struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); @@ -4329,7 +4331,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, * the order of declining indexes. When we put the pages in * the rdata->pages, then we want them in increasing order. */ - while (!list_empty(page_list)) { + while (!list_empty(page_list) && !err) { unsigned int i, nr_pages, bytes, rsize; loff_t offset; struct page *page, *tpage; @@ -4362,9 +4364,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, return 0; } - rc = readpages_get_pages(mapping, page_list, rsize, &tmplist, + nr_pages = 0; + err = readpages_get_pages(mapping, page_list, rsize, &tmplist, &nr_pages, &offset, &bytes); - if (rc) { + if (!nr_pages) { add_credits_and_wake_if(server, credits, 0); break; } @@ -4675,12 +4678,13 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; + bool purge_cache = false; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); - server->ops->downgrade_oplock(server, cinode, - test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags)); + server->ops->downgrade_oplock(server, cinode, cfile->oplock_level, + cfile->oplock_epoch, &purge_cache); if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) && cifs_has_mand_locks(cinode)) { @@ -4695,18 +4699,21 @@ void cifs_oplock_break(struct work_struct *work) else break_lease(inode, O_WRONLY); rc = filemap_fdatawrite(inode->i_mapping); - if (!CIFS_CACHE_READ(cinode)) { + if (!CIFS_CACHE_READ(cinode) || purge_cache) { rc = filemap_fdatawait(inode->i_mapping); mapping_set_error(inode->i_mapping, rc); cifs_zap_mapping(inode); } cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc); + if (CIFS_CACHE_WRITE(cinode)) + goto oplock_break_ack; } rc = cifs_push_locks(cfile); if (rc) cifs_dbg(VFS, "Push locks rc = %d\n", rc); +oplock_break_ack: /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 5e6bc8fa4e46..17df90b5f57a 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -898,6 +898,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) { rc = cifs_acl_to_fattr(cifs_sb, &fattr, *inode, true, full_path, fid); + if (rc == -EREMOTE) + rc = 0; if (rc) { cifs_dbg(FYI, "%s: Get mode from SID failed. rc=%d\n", __func__, rc); @@ -906,6 +908,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) { rc = cifs_acl_to_fattr(cifs_sb, &fattr, *inode, false, full_path, fid); + if (rc == -EREMOTE) + rc = 0; if (rc) { cifs_dbg(FYI, "%s: Getting ACL failed with error: %d\n", __func__, rc); @@ -2264,6 +2268,15 @@ set_size_out: if (rc == 0) { cifsInode->server_eof = attrs->ia_size; cifs_setsize(inode, attrs->ia_size); + + /* + * The man page of truncate says if the size changed, + * then the st_ctime and st_mtime fields for the file + * are updated. + */ + attrs->ia_ctime = attrs->ia_mtime = current_time(inode); + attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME; + cifs_truncate_page(inode->i_mapping, inode->i_size); } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 5ad83bdb9bea..40ca394fd5de 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -488,21 +488,10 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &pCifsInode->flags); - /* - * Set flag if the server downgrades the oplock - * to L2 else clear. - */ - if (pSMB->OplockLevel) - set_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &pCifsInode->flags); - else - clear_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &pCifsInode->flags); - - cifs_queue_oplock_break(netfile); + netfile->oplock_epoch = 0; + netfile->oplock_level = pSMB->OplockLevel; netfile->oplock_break_cancelled = false; + cifs_queue_oplock_break(netfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 195766221a7a..e523c05a4487 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -369,12 +369,10 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr) static void cifs_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - if (set_level2) - cifs_set_oplock_level(cinode, OPLOCK_READ); - else - cifs_set_oplock_level(cinode, 0); + cifs_set_oplock_level(cinode, oplock); } static bool diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 14265b4bbcc0..7d875a47d022 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -509,15 +509,31 @@ cifs_ses_oplock_break(struct work_struct *work) kfree(lw); } +static void +smb2_queue_pending_open_break(struct tcon_link *tlink, __u8 *lease_key, + __le32 new_lease_state) +{ + struct smb2_lease_break_work *lw; + + lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); + if (!lw) { + cifs_put_tlink(tlink); + return; + } + + INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); + lw->tlink = tlink; + lw->lease_state = new_lease_state; + memcpy(lw->lease_key, lease_key, SMB2_LEASE_KEY_SIZE); + queue_work(cifsiod_wq, &lw->lease_break); +} + static bool -smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, - struct smb2_lease_break_work *lw) +smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp) { - bool found; __u8 lease_state; struct list_head *tmp; struct cifsFileInfo *cfile; - struct cifs_pending_open *open; struct cifsInodeInfo *cinode; int ack_req = le32_to_cpu(rsp->Flags & SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); @@ -534,7 +550,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, cifs_dbg(FYI, "found in the open list\n"); cifs_dbg(FYI, "lease key match, lease break 0x%x\n", - le32_to_cpu(rsp->NewLeaseState)); + lease_state); if (ack_req) cfile->oplock_break_cancelled = false; @@ -543,40 +559,38 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); - /* - * Set or clear flags depending on the lease state being READ. - * HANDLE caching flag should be added when the client starts - * to defer closing remote file handles with HANDLE leases. - */ - if (lease_state & SMB2_LEASE_READ_CACHING_HE) - set_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); - else - clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); + cfile->oplock_epoch = le16_to_cpu(rsp->Epoch); + cfile->oplock_level = lease_state; cifs_queue_oplock_break(cfile); - kfree(lw); return true; } - found = false; + return false; +} + +static struct cifs_pending_open * +smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon, + struct smb2_lease_break *rsp) +{ + __u8 lease_state = le32_to_cpu(rsp->NewLeaseState); + int ack_req = le32_to_cpu(rsp->Flags & + SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); + struct cifs_pending_open *open; + struct cifs_pending_open *found = NULL; + list_for_each_entry(open, &tcon->pending_opens, olist) { if (memcmp(open->lease_key, rsp->LeaseKey, SMB2_LEASE_KEY_SIZE)) continue; if (!found && ack_req) { - found = true; - memcpy(lw->lease_key, open->lease_key, - SMB2_LEASE_KEY_SIZE); - lw->tlink = cifs_get_tlink(open->tlink); - queue_work(cifsiod_wq, &lw->lease_break); + found = open; } cifs_dbg(FYI, "found in the pending open list\n"); cifs_dbg(FYI, "lease key match, lease break 0x%x\n", - le32_to_cpu(rsp->NewLeaseState)); + lease_state); open->oplock = lease_state; } @@ -592,14 +606,7 @@ smb2_is_valid_lease_break(char *buffer) struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct smb2_lease_break_work *lw; - - lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); - if (!lw) - return false; - - INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); - lw->lease_state = rsp->NewLeaseState; + struct cifs_pending_open *open; cifs_dbg(FYI, "Checking for lease break\n"); @@ -617,11 +624,27 @@ smb2_is_valid_lease_break(char *buffer) spin_lock(&tcon->open_file_lock); cifs_stats_inc( &tcon->stats.cifs_stats.num_oplock_brks); - if (smb2_tcon_has_lease(tcon, rsp, lw)) { + if (smb2_tcon_has_lease(tcon, rsp)) { spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); return true; } + open = smb2_tcon_find_pending_open_lease(tcon, + rsp); + if (open) { + __u8 lease_key[SMB2_LEASE_KEY_SIZE]; + struct tcon_link *tlink; + + tlink = cifs_get_tlink(open->tlink); + memcpy(lease_key, open->lease_key, + SMB2_LEASE_KEY_SIZE); + spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_tcp_ses_lock); + smb2_queue_pending_open_break(tlink, + lease_key, + rsp->NewLeaseState); + return true; + } spin_unlock(&tcon->open_file_lock); if (tcon->crfid.is_valid && @@ -639,7 +662,6 @@ smb2_is_valid_lease_break(char *buffer) } } spin_unlock(&cifs_tcp_ses_lock); - kfree(lw); cifs_dbg(FYI, "Can not process lease break - no lease matched\n"); return false; } @@ -701,18 +723,9 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); - /* - * Set flag if the server downgrades the oplock - * to L2 else clear. - */ - if (rsp->OplockLevel) - set_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); - else - clear_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); + cfile->oplock_epoch = 0; + cfile->oplock_level = rsp->OplockLevel; + spin_unlock(&cfile->file_info_lock); cifs_queue_oplock_break(cfile); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 58915d882285..776029a57e71 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -736,6 +736,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) /* close extra handle outside of crit sec */ SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); } + rc = 0; goto oshr_free; } @@ -1178,7 +1179,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_iov = si_iov; rqst[1].rq_nvec = 1; - len = sizeof(ea) + ea_name_len + ea_value_len + 1; + len = sizeof(*ea) + ea_name_len + ea_value_len + 1; ea = kzalloc(len, GFP_KERNEL); if (ea == NULL) { rc = -ENOMEM; @@ -1564,35 +1565,32 @@ smb2_ioctl_query_info(const unsigned int xid, if (le32_to_cpu(io_rsp->OutputCount) < qi.input_buffer_length) qi.input_buffer_length = le32_to_cpu(io_rsp->OutputCount); if (qi.input_buffer_length > 0 && - le32_to_cpu(io_rsp->OutputOffset) + qi.input_buffer_length > rsp_iov[1].iov_len) { - rc = -EFAULT; - goto iqinf_exit; - } - if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, - sizeof(qi.input_buffer_length))) { - rc = -EFAULT; - goto iqinf_exit; - } + le32_to_cpu(io_rsp->OutputOffset) + qi.input_buffer_length + > rsp_iov[1].iov_len) + goto e_fault; + + if (copy_to_user(&pqi->input_buffer_length, + &qi.input_buffer_length, + sizeof(qi.input_buffer_length))) + goto e_fault; + if (copy_to_user((void __user *)pqi + sizeof(struct smb_query_info), (const void *)io_rsp + le32_to_cpu(io_rsp->OutputOffset), - qi.input_buffer_length)) { - rc = -EFAULT; - goto iqinf_exit; - } + qi.input_buffer_length)) + goto e_fault; } else { pqi = (struct smb_query_info __user *)arg; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; if (le32_to_cpu(qi_rsp->OutputBufferLength) < qi.input_buffer_length) qi.input_buffer_length = le32_to_cpu(qi_rsp->OutputBufferLength); - if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, - sizeof(qi.input_buffer_length))) { - rc = -EFAULT; - goto iqinf_exit; - } - if (copy_to_user(pqi + 1, qi_rsp->Buffer, qi.input_buffer_length)) { - rc = -EFAULT; - goto iqinf_exit; - } + if (copy_to_user(&pqi->input_buffer_length, + &qi.input_buffer_length, + sizeof(qi.input_buffer_length))) + goto e_fault; + + if (copy_to_user(pqi + 1, qi_rsp->Buffer, + qi.input_buffer_length)) + goto e_fault; } iqinf_exit: @@ -1608,6 +1606,10 @@ smb2_ioctl_query_info(const unsigned int xid, free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); return rc; + +e_fault: + rc = -EFAULT; + goto iqinf_exit; } static ssize_t @@ -2969,6 +2971,11 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + /* + * We zero the range through ioctl, so we need remove the page caches + * first, otherwise the data may be inconsistent with the server. + */ + truncate_pagecache_range(inode, offset, offset + len - 1); /* if file not oplocked can't be sure whether asking to extend size */ if (!CIFS_CACHE_READ(cifsi)) @@ -3035,6 +3042,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, return rc; } + /* + * We implement the punch hole through ioctl, so we need remove the page + * caches first, otherwise the data may be inconsistent with the server. + */ + truncate_pagecache_range(inode, offset, offset + len - 1); + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); fsctl_buf.FileOffset = cpu_to_le64(offset); @@ -3319,22 +3332,38 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode, static void smb2_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - if (set_level2) - server->ops->set_oplock_level(cinode, SMB2_OPLOCK_LEVEL_II, - 0, NULL); - else - server->ops->set_oplock_level(cinode, 0, 0, NULL); + server->ops->set_oplock_level(cinode, oplock, 0, NULL); } static void -smb21_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) +smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache); + +static void +smb3_downgrade_oplock(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - server->ops->set_oplock_level(cinode, - set_level2 ? SMB2_LEASE_READ_CACHING_HE : - 0, 0, NULL); + unsigned int old_state = cinode->oplock; + unsigned int old_epoch = cinode->epoch; + unsigned int new_state; + + if (epoch > old_epoch) { + smb21_set_oplock_level(cinode, oplock, 0, NULL); + cinode->epoch = epoch; + } + + new_state = cinode->oplock; + *purge_cache = false; + + if ((old_state & CIFS_CACHE_READ_FLG) != 0 && + (new_state & CIFS_CACHE_READ_FLG) == 0) + *purge_cache = true; + else if (old_state == new_state && (epoch - old_epoch > 1)) + *purge_cache = true; } static void @@ -3678,7 +3707,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, if (rc) { cifs_server_dbg(VFS, "%s: Could not get %scryption key\n", __func__, enc ? "en" : "de"); - return 0; + return rc; } rc = smb3_crypto_aead_allocate(server); @@ -3857,7 +3886,8 @@ smb3_is_transform_hdr(void *buf) static int decrypt_raw_data(struct TCP_Server_Info *server, char *buf, unsigned int buf_data_size, struct page **pages, - unsigned int npages, unsigned int page_data_size) + unsigned int npages, unsigned int page_data_size, + bool is_offloaded) { struct kvec iov[2]; struct smb_rqst rqst = {NULL}; @@ -3883,7 +3913,8 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, memmove(buf, iov[1].iov_base, buf_data_size); - server->total_read = buf_data_size + page_data_size; + if (!is_offloaded) + server->total_read = buf_data_size + page_data_size; return rc; } @@ -4097,7 +4128,7 @@ static void smb2_decrypt_offload(struct work_struct *work) struct mid_q_entry *mid; rc = decrypt_raw_data(dw->server, dw->buf, dw->server->vals->read_rsp_size, - dw->ppages, dw->npages, dw->len); + dw->ppages, dw->npages, dw->len, true); if (rc) { cifs_dbg(VFS, "error decrypting rc=%d\n", rc); goto free_pages; @@ -4203,7 +4234,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid, non_offloaded_decrypt: rc = decrypt_raw_data(server, buf, server->vals->read_rsp_size, - pages, npages, len); + pages, npages, len, false); if (rc) goto free_pages; @@ -4259,7 +4290,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, server->total_read += length; buf_size = pdu_length - sizeof(struct smb2_transform_hdr); - length = decrypt_raw_data(server, buf, buf_size, NULL, 0, 0); + length = decrypt_raw_data(server, buf, buf_size, NULL, 0, 0, false); if (length) return length; @@ -4594,7 +4625,7 @@ struct smb_version_operations smb21_operations = { .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -4694,7 +4725,7 @@ struct smb_version_operations smb30_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb3_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb3_negotiate_wsize, @@ -4802,7 +4833,7 @@ struct smb_version_operations smb311_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb3_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb3_negotiate_wsize, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 06b1a86d76b1..7ff05c06f2a4 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1323,6 +1323,8 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) spnego_key = cifs_get_spnego_key(ses); if (IS_ERR(spnego_key)) { rc = PTR_ERR(spnego_key); + if (rc == -ENOKEY) + cifs_dbg(VFS, "Verify user has a krb5 ticket and keyutils is installed\n"); spnego_key = NULL; goto out; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 0abfde6d0b05..f264e1d36fe1 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1386,7 +1386,7 @@ struct smb2_oplock_break { struct smb2_lease_break { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* Must be 44 */ - __le16 Reserved; + __le16 Epoch; __le32 Flags; __u8 LeaseKey[16]; __le32 CurrentLeaseState; diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index fe1552cc8a0a..eafc49de4d7f 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -528,7 +528,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, const int timeout, const int flags, unsigned int *instance) { - int rc; + long rc; int *credits; int optype; long int t; diff --git a/fs/d_path.c b/fs/d_path.c index 0f1fc1743302..a69e2cd36e6e 100644 --- a/fs/d_path.c +++ b/fs/d_path.c @@ -102,6 +102,8 @@ restart: if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { struct mount *parent = READ_ONCE(mnt->mnt_parent); + struct mnt_namespace *mnt_ns; + /* Escaped? */ if (dentry != vfsmnt->mnt_root) { bptr = *buffer; @@ -116,7 +118,9 @@ restart: vfsmnt = &mnt->mnt; continue; } - if (is_mounted(vfsmnt) && !is_anon_ns(mnt->mnt_ns)) + mnt_ns = READ_ONCE(mnt->mnt_ns); + /* open-coded is_mounted() to use local mnt_ns */ + if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns)) error = 1; // absolute root else error = 2; // detached or not attached yet diff --git a/fs/dcache.c b/fs/dcache.c index e88cf0554e65..b2a7f1765f0b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -903,17 +903,19 @@ struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; + unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); + seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { - if (likely(ret == READ_ONCE(dentry->d_parent))) + if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index b43960794922..943637298f65 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -176,7 +176,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp) goto out; if (!fops_get(real_fops)) { -#ifdef MODULE +#ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) goto out; @@ -311,7 +311,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp) goto out; if (!fops_get(real_fops)) { -#ifdef MODULE +#ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) goto out; diff --git a/fs/dlm/config.c b/fs/dlm/config.c index 3b21082e1b55..3b1012a3c439 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -216,6 +216,7 @@ struct dlm_space { struct list_head members; struct mutex members_lock; int members_count; + struct dlm_nodes *nds; }; struct dlm_comms { @@ -424,6 +425,7 @@ static struct config_group *make_space(struct config_group *g, const char *name) INIT_LIST_HEAD(&sp->members); mutex_init(&sp->members_lock); sp->members_count = 0; + sp->nds = nds; return &sp->group; fail: @@ -445,6 +447,7 @@ static void drop_space(struct config_group *g, struct config_item *i) static void release_space(struct config_item *i) { struct dlm_space *sp = config_item_to_space(i); + kfree(sp->nds); kfree(sp); } diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 416d9de35679..4311d01b02a8 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -97,7 +97,6 @@ do { \ __LINE__, __FILE__, #x, jiffies); \ {do} \ printk("\n"); \ - BUG(); \ panic("DLM: Record message above and reboot.\n"); \ } \ } diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index afb8340918b8..c689359ca532 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -632,6 +632,9 @@ static int new_lockspace(const char *name, const char *cluster, wait_event(ls->ls_recover_lock_wait, test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags)); + /* let kobject handle freeing of ls if there's an error */ + do_unreg = 1; + ls->ls_kobj.kset = dlm_kset; error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL, "%s", ls->ls_name); @@ -639,9 +642,6 @@ static int new_lockspace(const char *name, const char *cluster, goto out_recoverd; kobject_uevent(&ls->ls_kobj, KOBJ_ADD); - /* let kobject handle freeing of ls if there's an error */ - do_unreg = 1; - /* This uevent triggers dlm_controld in userspace to add us to the group of nodes that are members of this lockspace (managed by the cluster infrastructure.) Once it's done that, it tells us who the diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index fa4f6447ddad..9760a52800b4 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -141,6 +141,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; + /* replace invalid slashes like kobject_set_name_vargs does for /sys/firmware/efi/vars. */ + strreplace(name, '/', '!'); + inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, is_removable); if (!inode) diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 3350ab65d892..b36b414cd7a7 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -8,31 +8,80 @@ #include <trace/events/erofs.h> -/* no locking */ -static int erofs_read_inode(struct inode *inode, void *data) +/* + * if inode is successfully read, return its inode page (or sometimes + * the inode payload page if it's an extended inode) in order to fill + * inline data if possible. + */ +static struct page *erofs_read_inode(struct inode *inode, + unsigned int *ofs) { + struct super_block *sb = inode->i_sb; + struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_inode *vi = EROFS_I(inode); - struct erofs_inode_compact *dic = data; - struct erofs_inode_extended *die; + const erofs_off_t inode_loc = iloc(sbi, vi->nid); + + erofs_blk_t blkaddr, nblks = 0; + struct page *page; + struct erofs_inode_compact *dic; + struct erofs_inode_extended *die, *copied = NULL; + unsigned int ifmt; + int err; - const unsigned int ifmt = le16_to_cpu(dic->i_format); - struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); - erofs_blk_t nblks = 0; + blkaddr = erofs_blknr(inode_loc); + *ofs = erofs_blkoff(inode_loc); - vi->datalayout = erofs_inode_datalayout(ifmt); + erofs_dbg("%s, reading inode nid %llu at %u of blkaddr %u", + __func__, vi->nid, *ofs, blkaddr); + + page = erofs_get_meta_page(sb, blkaddr); + if (IS_ERR(page)) { + erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld", + vi->nid, PTR_ERR(page)); + return page; + } + dic = page_address(page) + *ofs; + ifmt = le16_to_cpu(dic->i_format); + + vi->datalayout = erofs_inode_datalayout(ifmt); if (vi->datalayout >= EROFS_INODE_DATALAYOUT_MAX) { erofs_err(inode->i_sb, "unsupported datalayout %u of nid %llu", vi->datalayout, vi->nid); - DBG_BUGON(1); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_out; } switch (erofs_inode_version(ifmt)) { case EROFS_INODE_LAYOUT_EXTENDED: - die = data; - vi->inode_isize = sizeof(struct erofs_inode_extended); + /* check if the inode acrosses page boundary */ + if (*ofs + vi->inode_isize <= PAGE_SIZE) { + *ofs += vi->inode_isize; + die = (struct erofs_inode_extended *)dic; + } else { + const unsigned int gotten = PAGE_SIZE - *ofs; + + copied = kmalloc(vi->inode_isize, GFP_NOFS); + if (!copied) { + err = -ENOMEM; + goto err_out; + } + memcpy(copied, dic, gotten); + unlock_page(page); + put_page(page); + + page = erofs_get_meta_page(sb, blkaddr + 1); + if (IS_ERR(page)) { + erofs_err(sb, "failed to get inode payload page (nid: %llu), err %ld", + vi->nid, PTR_ERR(page)); + kfree(copied); + return page; + } + *ofs = vi->inode_isize - gotten; + memcpy((u8 *)copied + gotten, page_address(page), *ofs); + die = copied; + } vi->xattr_isize = erofs_xattr_ibody_size(die->i_xattr_icount); inode->i_mode = le16_to_cpu(die->i_mode); @@ -69,9 +118,12 @@ static int erofs_read_inode(struct inode *inode, void *data) /* total blocks for compressed files */ if (erofs_inode_is_data_compressed(vi->datalayout)) nblks = le32_to_cpu(die->i_u.compressed_blocks); + + kfree(copied); break; case EROFS_INODE_LAYOUT_COMPACT: vi->inode_isize = sizeof(struct erofs_inode_compact); + *ofs += vi->inode_isize; vi->xattr_isize = erofs_xattr_ibody_size(dic->i_xattr_icount); inode->i_mode = le16_to_cpu(dic->i_mode); @@ -111,8 +163,8 @@ static int erofs_read_inode(struct inode *inode, void *data) erofs_err(inode->i_sb, "unsupported on-disk inode version %u of nid %llu", erofs_inode_version(ifmt), vi->nid); - DBG_BUGON(1); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_out; } if (!nblks) @@ -120,13 +172,18 @@ static int erofs_read_inode(struct inode *inode, void *data) inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9; else inode->i_blocks = nblks << LOG_SECTORS_PER_BLOCK; - return 0; + return page; bogusimode: erofs_err(inode->i_sb, "bogus i_mode (%o) @ nid %llu", inode->i_mode, vi->nid); + err = -EFSCORRUPTED; +err_out: DBG_BUGON(1); - return -EFSCORRUPTED; + kfree(copied); + unlock_page(page); + put_page(page); + return ERR_PTR(err); } static int erofs_fill_symlink(struct inode *inode, void *data, @@ -146,7 +203,7 @@ static int erofs_fill_symlink(struct inode *inode, void *data, if (!lnk) return -ENOMEM; - m_pofs += vi->inode_isize + vi->xattr_isize; + m_pofs += vi->xattr_isize; /* inline symlink data shouldn't cross page boundary as well */ if (m_pofs + inode->i_size > PAGE_SIZE) { kfree(lnk); @@ -167,37 +224,17 @@ static int erofs_fill_symlink(struct inode *inode, void *data, static int erofs_fill_inode(struct inode *inode, int isdir) { - struct super_block *sb = inode->i_sb; struct erofs_inode *vi = EROFS_I(inode); struct page *page; - void *data; - int err; - erofs_blk_t blkaddr; unsigned int ofs; - erofs_off_t inode_loc; + int err = 0; trace_erofs_fill_inode(inode, isdir); - inode_loc = iloc(EROFS_SB(sb), vi->nid); - blkaddr = erofs_blknr(inode_loc); - ofs = erofs_blkoff(inode_loc); - - erofs_dbg("%s, reading inode nid %llu at %u of blkaddr %u", - __func__, vi->nid, ofs, blkaddr); - page = erofs_get_meta_page(sb, blkaddr); - - if (IS_ERR(page)) { - erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld", - vi->nid, PTR_ERR(page)); + /* read inode base data from disk */ + page = erofs_read_inode(inode, &ofs); + if (IS_ERR(page)) return PTR_ERR(page); - } - - DBG_BUGON(!PageUptodate(page)); - data = page_address(page); - - err = erofs_read_inode(inode, data + ofs); - if (err) - goto out_unlock; /* setup the new inode */ switch (inode->i_mode & S_IFMT) { @@ -210,7 +247,7 @@ static int erofs_fill_inode(struct inode *inode, int isdir) inode->i_fop = &erofs_dir_fops; break; case S_IFLNK: - err = erofs_fill_symlink(inode, data, ofs); + err = erofs_fill_symlink(inode, page_address(page), ofs); if (err) goto out_unlock; inode_nohighmem(inode); diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index b766c3ee5fa8..503bea20cde2 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -473,8 +473,6 @@ static int erofs_xattr_generic_get(const struct xattr_handler *handler, return -EOPNOTSUPP; break; case EROFS_XATTR_INDEX_TRUSTED: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; break; case EROFS_XATTR_INDEX_SECURITY: break; diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index faf950189bd7..568d5a493876 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -148,22 +148,22 @@ static inline void z_erofs_onlinepage_init(struct page *page) static inline void z_erofs_onlinepage_fixup(struct page *page, uintptr_t index, bool down) { - unsigned long *p, o, v, id; -repeat: - p = &page_private(page); - o = READ_ONCE(*p); + union z_erofs_onlinepage_converter u = { .v = &page_private(page) }; + int orig, orig_index, val; - id = o >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT; - if (id) { +repeat: + orig = atomic_read(u.o); + orig_index = orig >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT; + if (orig_index) { if (!index) return; - DBG_BUGON(id != index); + DBG_BUGON(orig_index != index); } - v = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) | - ((o & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down); - if (cmpxchg(p, o, v) != o) + val = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) | + ((orig & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down); + if (atomic_cmpxchg(u.o, orig, val) != orig) goto repeat; } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 6307c1d883e0..339453ac834c 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -218,8 +218,7 @@ struct eventpoll { struct file *file; /* used to optimize loop detection check */ - int visited; - struct list_head visited_list_link; + u64 gen; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ @@ -269,6 +268,8 @@ static long max_user_watches __read_mostly; */ static DEFINE_MUTEX(epmutex); +static u64 loop_check_gen = 0; + /* Used to check for epoll file descriptor inclusion loops */ static struct nested_calls poll_loop_ncalls; @@ -278,9 +279,6 @@ static struct kmem_cache *epi_cache __read_mostly; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __read_mostly; -/* Visited nodes during ep_loop_check(), so we can unset them when we finish */ -static LIST_HEAD(visited_list); - /* * List of files with newly added links, where we may need to limit the number * of emanating paths. Protected by the epmutex. @@ -1455,7 +1453,7 @@ static int reverse_path_check(void) static int ep_create_wakeup_source(struct epitem *epi) { - const char *name; + struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { @@ -1464,8 +1462,9 @@ static int ep_create_wakeup_source(struct epitem *epi) return -ENOMEM; } - name = epi->ffd.file->f_path.dentry->d_name.name; - ws = wakeup_source_register(NULL, name); + take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); + ws = wakeup_source_register(NULL, n.name.name); + release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; @@ -1527,6 +1526,22 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, RCU_INIT_POINTER(epi->ws, NULL); } + /* Add the current item to the list of active epoll hook for this file */ + spin_lock(&tfile->f_lock); + list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); + spin_unlock(&tfile->f_lock); + + /* + * Add the current item to the RB tree. All RB tree operations are + * protected by "mtx", and ep_insert() is called with "mtx" held. + */ + ep_rbtree_insert(ep, epi); + + /* now check if we've created too many backpaths */ + error = -EINVAL; + if (full_check && reverse_path_check()) + goto error_remove_epi; + /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); @@ -1549,22 +1564,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, if (epi->nwait < 0) goto error_unregister; - /* Add the current item to the list of active epoll hook for this file */ - spin_lock(&tfile->f_lock); - list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); - spin_unlock(&tfile->f_lock); - - /* - * Add the current item to the RB tree. All RB tree operations are - * protected by "mtx", and ep_insert() is called with "mtx" held. - */ - ep_rbtree_insert(ep, epi); - - /* now check if we've created too many backpaths */ - error = -EINVAL; - if (full_check && reverse_path_check()) - goto error_remove_epi; - /* We have to drop the new item inside our item list to keep track of it */ write_lock_irq(&ep->lock); @@ -1593,6 +1592,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, return 0; +error_unregister: + ep_unregister_pollwait(ep, epi); error_remove_epi: spin_lock(&tfile->f_lock); list_del_rcu(&epi->fllink); @@ -1600,9 +1601,6 @@ error_remove_epi: rb_erase_cached(&epi->rbn, &ep->rbr); -error_unregister: - ep_unregister_pollwait(ep, epi); - /* * We need to do this because an event could have been arrived on some * allocated wait queue. Note that we don't care about the ep->ovflist @@ -1969,13 +1967,12 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) struct epitem *epi; mutex_lock_nested(&ep->mtx, call_nests + 1); - ep->visited = 1; - list_add(&ep->visited_list_link, &visited_list); + ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { ep_tovisit = epi->ffd.file->private_data; - if (ep_tovisit->visited) + if (ep_tovisit->gen == loop_check_gen) continue; error = ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, epi->ffd.file, @@ -1991,9 +1988,11 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) * not already there, and calling reverse_path_check() * during ep_insert(). */ - if (list_empty(&epi->ffd.file->f_tfile_llink)) - list_add(&epi->ffd.file->f_tfile_llink, - &tfile_check_list); + if (list_empty(&epi->ffd.file->f_tfile_llink)) { + if (get_file_rcu(epi->ffd.file)) + list_add(&epi->ffd.file->f_tfile_llink, + &tfile_check_list); + } } } mutex_unlock(&ep->mtx); @@ -2014,18 +2013,8 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) */ static int ep_loop_check(struct eventpoll *ep, struct file *file) { - int ret; - struct eventpoll *ep_cur, *ep_next; - - ret = ep_call_nested(&poll_loop_ncalls, + return ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, file, ep, current); - /* clear visited list */ - list_for_each_entry_safe(ep_cur, ep_next, &visited_list, - visited_list_link) { - ep_cur->visited = 0; - list_del(&ep_cur->visited_list_link); - } - return ret; } static void clear_tfile_check_list(void) @@ -2037,6 +2026,7 @@ static void clear_tfile_check_list(void) file = list_first_entry(&tfile_check_list, struct file, f_tfile_llink); list_del_init(&file->f_tfile_llink); + fput(file); } INIT_LIST_HEAD(&tfile_check_list); } @@ -2186,19 +2176,20 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, mutex_lock_nested(&ep->mtx, 0); if (op == EPOLL_CTL_ADD) { if (!list_empty(&f.file->f_ep_links) || + ep->gen == loop_check_gen || is_file_epoll(tf.file)) { full_check = 1; mutex_unlock(&ep->mtx); mutex_lock(&epmutex); if (is_file_epoll(tf.file)) { error = -ELOOP; - if (ep_loop_check(ep, tf.file) != 0) { - clear_tfile_check_list(); + if (ep_loop_check(ep, tf.file) != 0) goto error_tgt_fput; - } - } else + } else { + get_file(tf.file); list_add(&tf.file->f_tfile_llink, &tfile_check_list); + } mutex_lock_nested(&ep->mtx, 0); if (is_file_epoll(tf.file)) { tep = tf.file->private_data; @@ -2222,8 +2213,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, error = ep_insert(ep, &epds, tf.file, fd, full_check); } else error = -EEXIST; - if (full_check) - clear_tfile_check_list(); break; case EPOLL_CTL_DEL: if (epi) @@ -2246,8 +2235,11 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, mutex_unlock(&ep->mtx); error_tgt_fput: - if (full_check) + if (full_check) { + clear_tfile_check_list(); + loop_check_gen++; mutex_unlock(&epmutex); + } fdput(tf); error_fput: diff --git a/fs/exec.c b/fs/exec.c index d62cd1d71098..de833553ae27 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1007,16 +1007,26 @@ ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len) } EXPORT_SYMBOL(read_code); +/* + * Maps the mm_struct mm into the current task struct. + * On success, this function returns with the mutex + * exec_update_mutex locked. + */ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; + int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm); + ret = mutex_lock_killable(&tsk->signal->exec_update_mutex); + if (ret) + return ret; + if (old_mm) { sync_mm_rss(old_mm); /* @@ -1028,9 +1038,11 @@ static int exec_mmap(struct mm_struct *mm) down_read(&old_mm->mmap_sem); if (unlikely(old_mm->core_state)) { up_read(&old_mm->mmap_sem); + mutex_unlock(&tsk->signal->exec_update_mutex); return -EINTR; } } + task_lock(tsk); active_mm = tsk->active_mm; membarrier_exec_mmap(mm); @@ -1285,11 +1297,12 @@ int flush_old_exec(struct linux_binprm * bprm) goto out; /* - * After clearing bprm->mm (to mark that current is using the - * prepared mm now), we have nothing left of the original + * After setting bprm->called_exec_mmap (to mark that current is + * using the prepared mm now), we have nothing left of the original * process. If anything from here on returns an error, the check * in search_binary_handler() will SEGV current. */ + bprm->called_exec_mmap = 1; bprm->mm = NULL; set_fs(USER_DS); @@ -1423,6 +1436,8 @@ static void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { + if (bprm->called_exec_mmap) + mutex_unlock(¤t->signal->exec_update_mutex); mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } @@ -1472,6 +1487,7 @@ void install_exec_creds(struct linux_binprm *bprm) * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm); + mutex_unlock(¤t->signal->exec_update_mutex); mutex_unlock(¤t->signal->cred_guard_mutex); } EXPORT_SYMBOL(install_exec_creds); @@ -1663,7 +1679,7 @@ int search_binary_handler(struct linux_binprm *bprm) read_lock(&binfmt_lock); put_binfmt(fmt); - if (retval < 0 && !bprm->mm) { + if (retval < 0 && bprm->called_exec_mmap) { /* we got to flush_old_exec() and failed after it */ read_unlock(&binfmt_lock); force_sigsegv(SIGSEGV); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 39c4772e96c9..d73103cdda21 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -93,8 +93,10 @@ static vm_fault_t ext2_dax_fault(struct vm_fault *vmf) struct inode *inode = file_inode(vmf->vma->vm_file); struct ext2_inode_info *ei = EXT2_I(inode); vm_fault_t ret; + bool write = (vmf->flags & FAULT_FLAG_WRITE) && + (vmf->vma->vm_flags & VM_SHARED); - if (vmf->flags & FAULT_FLAG_WRITE) { + if (write) { sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); } @@ -103,7 +105,7 @@ static vm_fault_t ext2_dax_fault(struct vm_fault *vmf) ret = dax_iomap_fault(vmf, PE_SIZE_PTE, NULL, NULL, &ext2_iomap_ops); up_read(&ei->dax_sem); - if (vmf->flags & FAULT_FLAG_WRITE) + if (write) sb_end_pagefault(inode->i_sb); return ret; } diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index fda7d3f5b4be..432c3febea6d 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -80,6 +80,7 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir) if (dir) le16_add_cpu(&desc->bg_used_dirs_count, -1); spin_unlock(sb_bgl_lock(EXT2_SB(sb), group)); + percpu_counter_inc(&EXT2_SB(sb)->s_freeinodes_counter); if (dir) percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter); mark_buffer_dirty(bh); @@ -528,7 +529,7 @@ got: goto fail; } - percpu_counter_add(&sbi->s_freeinodes_counter, -1); + percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index ff8e1205127e..97c56d061e61 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -68,7 +68,7 @@ static int add_system_zone(struct ext4_system_blocks *system_blks, ext4_fsblk_t start_blk, unsigned int count) { - struct ext4_system_zone *new_entry = NULL, *entry; + struct ext4_system_zone *new_entry, *entry; struct rb_node **n = &system_blks->root.rb_node, *node; struct rb_node *parent = NULL, *new_node = NULL; @@ -79,30 +79,20 @@ static int add_system_zone(struct ext4_system_blocks *system_blks, n = &(*n)->rb_left; else if (start_blk >= (entry->start_blk + entry->count)) n = &(*n)->rb_right; - else { - if (start_blk + count > (entry->start_blk + - entry->count)) - entry->count = (start_blk + count - - entry->start_blk); - new_node = *n; - new_entry = rb_entry(new_node, struct ext4_system_zone, - node); - break; - } + else /* Unexpected overlap of system zones. */ + return -EFSCORRUPTED; } - if (!new_entry) { - new_entry = kmem_cache_alloc(ext4_system_zone_cachep, - GFP_KERNEL); - if (!new_entry) - return -ENOMEM; - new_entry->start_blk = start_blk; - new_entry->count = count; - new_node = &new_entry->node; - - rb_link_node(new_node, parent, n); - rb_insert_color(new_node, &system_blks->root); - } + new_entry = kmem_cache_alloc(ext4_system_zone_cachep, + GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->start_blk = start_blk; + new_entry->count = count; + new_node = &new_entry->node; + + rb_link_node(new_node, parent, n); + rb_insert_color(new_node, &system_blks->root); /* Can we merge to the left? */ node = rb_prev(new_node); @@ -260,14 +250,6 @@ int ext4_setup_system_zone(struct super_block *sb) int flex_size = ext4_flex_bg_size(sbi); int ret; - if (!test_opt(sb, BLOCK_VALIDITY)) { - if (sbi->system_blks) - ext4_release_system_zone(sb); - return 0; - } - if (sbi->system_blks) - return 0; - system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL); if (!system_blks) return -ENOMEM; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 2743c6f8a457..0589e914663f 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -677,6 +677,7 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len, struct qstr qstr = {.name = str, .len = len }; const struct dentry *parent = READ_ONCE(dentry->d_parent); const struct inode *inode = READ_ONCE(parent->d_inode); + char strbuf[DNAME_INLINE_LEN]; if (!inode || !IS_CASEFOLDED(inode) || !EXT4_SB(inode->i_sb)->s_encoding) { @@ -685,6 +686,21 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len, return memcmp(str, name->name, len); } + /* + * If the dentry name is stored in-line, then it may be concurrently + * modified by a rename. If this happens, the VFS will eventually retry + * the lookup, so it doesn't matter what ->d_compare() returns. + * However, it's unsafe to call utf8_strncasecmp() with an unstable + * string. Therefore, we have to copy the name into a temporary buffer. + */ + if (len <= DNAME_INLINE_LEN - 1) { + memcpy(strbuf, str, len); + strbuf[len] = 0; + qstr.name = strbuf; + /* prevent compiler from optimizing out the temporary buffer */ + barrier(); + } + return ext4_ci_compare(inode, name, &qstr, false); } diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 98bd0e9ee7df..ca78fd709845 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -170,10 +170,13 @@ struct partial_cluster { (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) #define EXT_LAST_INDEX(__hdr__) \ (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) -#define EXT_MAX_EXTENT(__hdr__) \ - (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) +#define EXT_MAX_EXTENT(__hdr__) \ + ((le16_to_cpu((__hdr__)->eh_max)) ? \ + ((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \ + : 0) #define EXT_MAX_INDEX(__hdr__) \ - (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) + ((le16_to_cpu((__hdr__)->eh_max)) ? \ + ((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) : 0) static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode) { diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9bd44588eb77..3193f0b4a02d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3010,7 +3010,7 @@ again: * in use to avoid freeing it when removing blocks. */ if (sbi->s_cluster_ratio > 1) { - pblk = ext4_ext_pblock(ex) + end - ee_block + 2; + pblk = ext4_ext_pblock(ex) + end - ee_block + 1; partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index dbccf46f1770..37347ba868b7 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -108,6 +108,9 @@ static int ext4_getfsmap_helper(struct super_block *sb, /* Are we just counting mappings? */ if (info->gfi_head->fmh_count == 0) { + if (info->gfi_head->fmh_entries == UINT_MAX) + return EXT4_QUERY_RANGE_ABORT; + if (rec_fsblk > info->gfi_next_fsblk) info->gfi_head->fmh_entries++; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 5508baa11bb6..8a28d47bd502 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -44,30 +44,28 @@ */ static int ext4_sync_parent(struct inode *inode) { - struct dentry *dentry = NULL; - struct inode *next; + struct dentry *dentry, *next; int ret = 0; if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) return 0; - inode = igrab(inode); + dentry = d_find_any_alias(inode); + if (!dentry) + return 0; while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); - dentry = d_find_any_alias(inode); - if (!dentry) - break; - next = igrab(d_inode(dentry->d_parent)); + + next = dget_parent(dentry); dput(dentry); - if (!next) - break; - iput(inode); - inode = next; + dentry = next; + inode = dentry->d_inode; + /* * The directory inode may have gone through rmdir by now. But * the inode itself and its blocks are still allocated (we hold - * a reference to the inode so it didn't go through - * ext4_evict_inode()) and so we are safe to flush metadata - * blocks and the inode. + * a reference to the inode via its dentry), so it didn't go + * through ext4_evict_inode()) and so we are safe to flush + * metadata blocks and the inode. */ ret = sync_mapping_buffers(inode->i_mapping); if (ret) @@ -76,7 +74,7 @@ static int ext4_sync_parent(struct inode *inode) if (ret) break; } - iput(inode); + dput(dentry); return ret; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7e0c77de551b..95a8a04c77dd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3836,6 +3836,11 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; + loff_t offset = iocb->ki_pos; + loff_t size = i_size_read(inode); + + if (offset >= size) + return 0; /* * Shared inode_lock is enough for us - it protects against concurrent @@ -5310,7 +5315,7 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - if (ei->i_disksize != ext4_isize(inode->i_sb, raw_inode)) { + if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) { ext4_isize_set(raw_inode, ei->i_disksize); need_datasync = 1; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e1782b2e2e2d..e5d43d2ee474 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1901,8 +1901,15 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, BUG_ON(buddy == NULL); k = mb_find_next_zero_bit(buddy, max, 0); - BUG_ON(k >= max); - + if (k >= max) { + ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, + "%d free clusters of order %d. But found 0", + grp->bb_counters[i], i); + ext4_mark_group_bitmap_corrupted(ac->ac_sb, + e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + break; + } ac->ac_found++; ac->ac_b_ex.fe_len = 1 << i; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a564d0289a70..36a81b57012a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1392,8 +1392,8 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ - if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, - bh->b_size, offset)) + if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf, + buf_size, offset)) return -1; *res_dir = de; return 1; @@ -1852,7 +1852,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, blocksize, hinfo, map); map -= count; dx_sort_map(map, count); - /* Split the existing block in the middle, size-wise */ + /* Ensure that neither split block is over half full */ size = 0; move = 0; for (i = count-1; i >= 0; i--) { @@ -1862,8 +1862,18 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, size += map[i].size; move++; } - /* map index at which we will split */ - split = count - move; + /* + * map index at which we will split + * + * If the sum of active entries didn't exceed half the block size, just + * split it in half by count; each resulting block will have at least + * half the space free. + */ + if (i > 0) + split = count - move; + else + split = count/2; + hash2 = map[split].hash; continued = hash2 == map[split - 1].hash; dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n", @@ -2462,7 +2472,7 @@ int ext4_generic_delete_entry(handle_t *handle, de = (struct ext4_dir_entry_2 *)entry_buf; while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, - bh->b_data, bh->b_size, i)) + entry_buf, buf_size, i)) return -EFSCORRUPTED; if (de == de_del) { if (pde) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d3500eaf900e..4aae7e3e89a1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -66,10 +66,10 @@ static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static int ext4_commit_super(struct super_block *sb, int sync); -static void ext4_mark_recovery_complete(struct super_block *sb, +static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); -static void ext4_clear_journal_err(struct super_block *sb, - struct ext4_super_block *es); +static int ext4_clear_journal_err(struct super_block *sb, + struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); @@ -2034,6 +2034,16 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, #endif } else if (token == Opt_dax) { #ifdef CONFIG_FS_DAX + if (is_remount && test_opt(sb, DAX)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and dax"); + return -1; + } + if (is_remount && !(sbi->s_mount_opt & EXT4_MOUNT_DAX)) { + ext4_msg(sb, KERN_ERR, "can't change " + "dax mount option while remounting"); + return -1; + } ext4_msg(sb, KERN_WARNING, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); sbi->s_mount_opt |= m->mount_opt; @@ -2294,6 +2304,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); err = -EROFS; + goto done; } if (read_only) goto done; @@ -4552,11 +4563,13 @@ no_journal: ext4_set_resv_clusters(sb); - err = ext4_setup_system_zone(sb); - if (err) { - ext4_msg(sb, KERN_ERR, "failed to initialize system " - "zone (%d)", err); - goto failed_mount4a; + if (test_opt(sb, BLOCK_VALIDITY)) { + err = ext4_setup_system_zone(sb); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to initialize system " + "zone (%d)", err); + goto failed_mount4a; + } } ext4_ext_init(sb); @@ -4624,7 +4637,9 @@ no_journal: EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); - ext4_mark_recovery_complete(sb, es); + err = ext4_mark_recovery_complete(sb, es); + if (err) + goto failed_mount8; } if (EXT4_SB(sb)->s_journal) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) @@ -4667,10 +4682,8 @@ cantfind_ext4: ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto failed_mount; -#ifdef CONFIG_QUOTA failed_mount8: ext4_unregister_sysfs(sb); -#endif failed_mount7: ext4_unregister_li_request(sb); failed_mount6: @@ -4809,7 +4822,8 @@ static journal_t *ext4_get_journal(struct super_block *sb, struct inode *journal_inode; journal_t *journal; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return NULL; journal_inode = ext4_get_journal_inode(sb, journal_inum); if (!journal_inode) @@ -4839,7 +4853,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, struct ext4_super_block *es; struct block_device *bdev; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return NULL; bdev = ext4_blkdev_get(j_dev, sb); if (bdev == NULL) @@ -4930,8 +4945,10 @@ static int ext4_load_journal(struct super_block *sb, dev_t journal_dev; int err = 0; int really_read_only; + int journal_dev_ro; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return -EFSCORRUPTED; if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -4941,7 +4958,31 @@ static int ext4_load_journal(struct super_block *sb, } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); - really_read_only = bdev_read_only(sb->s_bdev); + if (journal_inum && journal_dev) { + ext4_msg(sb, KERN_ERR, + "filesystem has both journal inode and journal device!"); + return -EINVAL; + } + + if (journal_inum) { + journal = ext4_get_journal(sb, journal_inum); + if (!journal) + return -EINVAL; + } else { + journal = ext4_get_dev_journal(sb, journal_dev); + if (!journal) + return -EINVAL; + } + + journal_dev_ro = bdev_read_only(journal->j_dev); + really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro; + + if (journal_dev_ro && !sb_rdonly(sb)) { + ext4_msg(sb, KERN_ERR, + "journal device read-only, try mounting with '-o ro'"); + err = -EROFS; + goto err_out; + } /* * Are we loading a blank journal or performing recovery after a @@ -4956,27 +4997,14 @@ static int ext4_load_journal(struct super_block *sb, ext4_msg(sb, KERN_ERR, "write access " "unavailable, cannot proceed " "(try mounting with noload)"); - return -EROFS; + err = -EROFS; + goto err_out; } ext4_msg(sb, KERN_INFO, "write access will " "be enabled during recovery"); } } - if (journal_inum && journal_dev) { - ext4_msg(sb, KERN_ERR, "filesystem has both journal " - "and inode journals!"); - return -EINVAL; - } - - if (journal_inum) { - if (!(journal = ext4_get_journal(sb, journal_inum))) - return -EINVAL; - } else { - if (!(journal = ext4_get_dev_journal(sb, journal_dev))) - return -EINVAL; - } - if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); @@ -4996,12 +5024,16 @@ static int ext4_load_journal(struct super_block *sb, if (err) { ext4_msg(sb, KERN_ERR, "error loading journal"); - jbd2_journal_destroy(journal); - return err; + goto err_out; } EXT4_SB(sb)->s_journal = journal; - ext4_clear_journal_err(sb, es); + err = ext4_clear_journal_err(sb, es); + if (err) { + EXT4_SB(sb)->s_journal = NULL; + jbd2_journal_destroy(journal); + return err; + } if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -5012,6 +5044,10 @@ static int ext4_load_journal(struct super_block *sb, } return 0; + +err_out: + jbd2_journal_destroy(journal); + return err; } static int ext4_commit_super(struct super_block *sb, int sync) @@ -5024,13 +5060,6 @@ static int ext4_commit_super(struct super_block *sb, int sync) return error; /* - * The superblock bh should be mapped, but it might not be if the - * device was hot-removed. Not much we can do but fail the I/O. - */ - if (!buffer_mapped(sbh)) - return error; - - /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock * write time when we are mounting the root file system @@ -5097,26 +5126,32 @@ static int ext4_commit_super(struct super_block *sb, int sync) * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ -static void ext4_mark_recovery_complete(struct super_block *sb, - struct ext4_super_block *es) +static int ext4_mark_recovery_complete(struct super_block *sb, + struct ext4_super_block *es) { + int err; journal_t *journal = EXT4_SB(sb)->s_journal; if (!ext4_has_feature_journal(sb)) { - BUG_ON(journal != NULL); - return; + if (journal != NULL) { + ext4_error(sb, "Journal got removed while the fs was " + "mounted!"); + return -EFSCORRUPTED; + } + return 0; } jbd2_journal_lock_updates(journal); - if (jbd2_journal_flush(journal) < 0) + err = jbd2_journal_flush(journal); + if (err < 0) goto out; if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) { ext4_clear_feature_journal_needs_recovery(sb); ext4_commit_super(sb, 1); } - out: jbd2_journal_unlock_updates(journal); + return err; } /* @@ -5124,14 +5159,17 @@ out: * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ -static void ext4_clear_journal_err(struct super_block *sb, +static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es) { journal_t *journal; int j_errno; const char *errstr; - BUG_ON(!ext4_has_feature_journal(sb)); + if (!ext4_has_feature_journal(sb)) { + ext4_error(sb, "Journal got removed while the fs was mounted!"); + return -EFSCORRUPTED; + } journal = EXT4_SB(sb)->s_journal; @@ -5156,6 +5194,7 @@ static void ext4_clear_journal_err(struct super_block *sb, jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); } + return 0; } /* @@ -5298,7 +5337,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) { struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); - unsigned long old_sb_flags; + unsigned long old_sb_flags, vfs_flags; struct ext4_mount_options old_opts; int enable_quota = 0; ext4_group_t g; @@ -5341,6 +5380,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal && sbi->s_journal->j_task->io_context) journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; + /* + * Some options can be enabled by ext4 and/or by VFS mount flag + * either way we need to make sure it matches in both *flags and + * s_flags. Copy those selected flags from *flags to s_flags + */ + vfs_flags = SB_LAZYTIME | SB_I_VERSION; + sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); + if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; goto restore_opts; @@ -5366,12 +5413,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) err = -EINVAL; goto restore_opts; } - if (test_opt(sb, DAX)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "both data=journal and dax"); - err = -EINVAL; - goto restore_opts; - } } else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) { if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " @@ -5387,12 +5428,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) { - ext4_msg(sb, KERN_WARNING, "warning: refusing change of " - "dax flag with busy inodes while remounting"); - sbi->s_mount_opt ^= EXT4_MOUNT_DAX; - } - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) ext4_abort(sb, "Abort forced by user"); @@ -5406,9 +5441,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); } - if (*flags & SB_LAZYTIME) - sb->s_flags |= SB_LAZYTIME; - if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { err = -EROFS; @@ -5438,8 +5470,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); - if (sbi->s_journal) + if (sbi->s_journal) { + /* + * We let remount-ro finish even if marking fs + * as clean failed... + */ ext4_mark_recovery_complete(sb, es); + } if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); } else { @@ -5487,8 +5524,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * been changed by e2fsck since we originally mounted * the partition.) */ - if (sbi->s_journal) - ext4_clear_journal_err(sb, es); + if (sbi->s_journal) { + err = ext4_clear_journal_err(sb, es); + if (err) + goto restore_opts; + } sbi->s_mount_state = le16_to_cpu(es->s_state); err = ext4_setup_super(sb, es, 0); @@ -5518,7 +5558,17 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_register_li_request(sb, first_not_zeroed); } - ext4_setup_system_zone(sb); + /* + * Handle creation of system zone data early because it can fail. + * Releasing of existing data is done when we are sure remount will + * succeed. + */ + if (test_opt(sb, BLOCK_VALIDITY) && !sbi->system_blks) { + err = ext4_setup_system_zone(sb); + if (err) + goto restore_opts; + } + if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { err = ext4_commit_super(sb, 1); if (err) @@ -5539,8 +5589,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } } #endif + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) + ext4_release_system_zone(sb); + + /* + * Some options can be enabled by ext4 and/or by VFS mount flag + * either way we need to make sure it matches in both *flags and + * s_flags. Copy those selected flags from s_flags to *flags + */ + *flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags); - *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); return 0; @@ -5554,6 +5612,8 @@ restore_opts: sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) + ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 491f9ee4040e..894a61010ae9 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1820,8 +1820,11 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i, if (EXT4_I(inode)->i_file_acl) { /* The inode already has an extended attribute block. */ bs->bh = ext4_sb_bread(sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); - if (IS_ERR(bs->bh)) - return PTR_ERR(bs->bh); + if (IS_ERR(bs->bh)) { + error = PTR_ERR(bs->bh); + bs->bh = NULL; + return error; + } ea_bdebug(bs->bh, "b_count=%d, refcount=%d", atomic_read(&(bs->bh->b_count)), le32_to_cpu(BHDR(bs->bh)->h_refcount)); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index a28ffecc0f95..bbd07fe8a492 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -892,8 +892,8 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) int i; int err; - sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks), - GFP_KERNEL); + sbi->ckpt = f2fs_kvzalloc(sbi, array_size(blk_size, cp_blks), + GFP_KERNEL); if (!sbi->ckpt) return -ENOMEM; /* diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ec9a1f9ce2dd..68be334afc28 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2753,6 +2753,9 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter, unsigned long align = offset | iov_iter_alignment(iter); struct block_device *bdev = inode->i_sb->s_bdev; + if (iov_iter_rw(iter) == READ && offset >= i_size_read(inode)) + return 1; + if (align & blocksize_mask) { if (bdev) blkbits = blksize_bits(bdev_logical_block_size(bdev)); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 84280ad3786c..e9af46dc06f7 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -107,36 +107,28 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir, /* * Test whether a case-insensitive directory entry matches the filename * being searched for. - * - * Returns: 0 if the directory entry matches, more than 0 if it - * doesn't match or less than zero on error. */ -int f2fs_ci_compare(const struct inode *parent, const struct qstr *name, - const struct qstr *entry, bool quick) +static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name, + const struct qstr *entry, bool quick) { - const struct f2fs_sb_info *sbi = F2FS_SB(parent->i_sb); + const struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); const struct unicode_map *um = sbi->s_encoding; - int ret; + int res; if (quick) - ret = utf8_strncasecmp_folded(um, name, entry); + res = utf8_strncasecmp_folded(um, name, entry); else - ret = utf8_strncasecmp(um, name, entry); - - if (ret < 0) { - /* Handle invalid character sequence as either an error - * or as an opaque byte sequence. + res = utf8_strncasecmp(um, name, entry); + if (res < 0) { + /* + * In strict mode, ignore invalid names. In non-strict mode, + * fall back to treating them as opaque byte sequences. */ - if (f2fs_has_strict_mode(sbi)) - return -EINVAL; - - if (name->len != entry->len) - return 1; - - return !!memcmp(name->name, entry->name, name->len); + if (f2fs_has_strict_mode(sbi) || name->len != entry->len) + return false; + return !memcmp(name->name, entry->name, name->len); } - - return ret; + return res == 0; } static void f2fs_fname_setup_ci_filename(struct inode *dir, @@ -188,10 +180,10 @@ static inline bool f2fs_match_name(struct f2fs_dentry_ptr *d, if (cf_str->name) { struct qstr cf = {.name = cf_str->name, .len = cf_str->len}; - return !f2fs_ci_compare(parent, &cf, &entry, true); + return f2fs_match_ci_name(parent, &cf, &entry, true); } - return !f2fs_ci_compare(parent, fname->usr_fname, &entry, - false); + return f2fs_match_ci_name(parent, fname->usr_fname, &entry, + false); } #endif if (fscrypt_match_name(fname, d->filename[bit_pos], @@ -1067,17 +1059,41 @@ const struct file_operations f2fs_dir_operations = { static int f2fs_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { - struct qstr qstr = {.name = str, .len = len }; const struct dentry *parent = READ_ONCE(dentry->d_parent); - const struct inode *inode = READ_ONCE(parent->d_inode); + const struct inode *dir = READ_ONCE(parent->d_inode); + const struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + struct qstr entry = QSTR_INIT(str, len); + char strbuf[DNAME_INLINE_LEN]; + int res; + + if (!dir || !IS_CASEFOLDED(dir)) + goto fallback; - if (!inode || !IS_CASEFOLDED(inode)) { - if (len != name->len) - return -1; - return memcmp(str, name->name, len); + /* + * If the dentry name is stored in-line, then it may be concurrently + * modified by a rename. If this happens, the VFS will eventually retry + * the lookup, so it doesn't matter what ->d_compare() returns. + * However, it's unsafe to call utf8_strncasecmp() with an unstable + * string. Therefore, we have to copy the name into a temporary buffer. + */ + if (len <= DNAME_INLINE_LEN - 1) { + memcpy(strbuf, str, len); + strbuf[len] = 0; + entry.name = strbuf; + /* prevent compiler from optimizing out the temporary buffer */ + barrier(); } - return f2fs_ci_compare(inode, name, &qstr, false); + res = utf8_strncasecmp(sbi->s_encoding, name, &entry); + if (res >= 0) + return res; + + if (f2fs_has_strict_mode(sbi)) + return -EINVAL; +fallback: + if (len != name->len) + return 1; + return !!memcmp(str, name->name, len); } static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 3edde3d6d089..b3b7e63394be 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -138,6 +138,7 @@ struct f2fs_mount_info { int alloc_mode; /* segment allocation policy */ int fsync_mode; /* fsync policy */ bool test_dummy_encryption; /* test dummy encryption */ + block_t unusable_cap_perc; /* percentage for cap */ block_t unusable_cap; /* Amount of space allowed to be * unusable when disabling checkpoint */ @@ -2789,18 +2790,12 @@ static inline bool f2fs_may_extent_tree(struct inode *inode) static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi, size_t size, gfp_t flags) { - void *ret; - if (time_to_inject(sbi, FAULT_KMALLOC)) { f2fs_show_injection_info(FAULT_KMALLOC); return NULL; } - ret = kmalloc(size, flags); - if (ret) - return ret; - - return kvmalloc(size, flags); + return kmalloc(size, flags); } static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi, @@ -2959,11 +2954,6 @@ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, bool hot, bool set); struct dentry *f2fs_get_parent(struct dentry *child); -extern int f2fs_ci_compare(const struct inode *parent, - const struct qstr *name, - const struct qstr *entry, - bool quick); - /* * dir.c */ @@ -3071,7 +3061,7 @@ bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid); int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink); -void f2fs_recover_inline_xattr(struct inode *inode, struct page *page); +int f2fs_recover_inline_xattr(struct inode *inode, struct page *page); int f2fs_recover_xattr_data(struct inode *inode, struct page *page); int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, @@ -3497,7 +3487,7 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page); int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page); int f2fs_convert_inline_inode(struct inode *inode); int f2fs_write_inline_data(struct inode *inode, struct page *page); -bool f2fs_recover_inline_data(struct inode *inode, struct page *npage); +int f2fs_recover_inline_data(struct inode *inode, struct page *npage); struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, struct fscrypt_name *fname, struct page **res_page); int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index c3a9da79ac99..5d94abe467a4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2056,8 +2056,15 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) if (in != F2FS_GOING_DOWN_FULLSYNC) { ret = mnt_want_write_file(filp); - if (ret) + if (ret) { + if (ret == -EROFS) { + ret = 0; + f2fs_stop_checkpoint(sbi, false); + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); + trace_f2fs_shutdown(sbi, in, ret); + } return ret; + } } switch (in) { diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index e611d768efde..a78aa5480454 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1012,8 +1012,14 @@ next_step: block_t start_bidx; nid_t nid = le32_to_cpu(entry->nid); - /* stop BG_GC if there is not enough free sections. */ - if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) + /* + * stop BG_GC if there is not enough free sections. + * Or, stop GC if the segment becomes fully valid caused by + * race condition along with SSR block allocation. + */ + if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) || + get_valid_blocks(sbi, segno, false) == + sbi->blocks_per_seg) return submitted; if (check_valid_map(sbi, segno, off) == 0) diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 896db0416f0e..183388393c6a 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -252,7 +252,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) return 0; } -bool f2fs_recover_inline_data(struct inode *inode, struct page *npage) +int f2fs_recover_inline_data(struct inode *inode, struct page *npage) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode *ri = NULL; @@ -274,7 +274,8 @@ bool f2fs_recover_inline_data(struct inode *inode, struct page *npage) ri && (ri->i_inline & F2FS_INLINE_DATA)) { process_inline: ipage = f2fs_get_node_page(sbi, inode->i_ino); - f2fs_bug_on(sbi, IS_ERR(ipage)); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); f2fs_wait_on_page_writeback(ipage, NODE, true, true); @@ -287,21 +288,25 @@ process_inline: set_page_dirty(ipage); f2fs_put_page(ipage, 1); - return true; + return 1; } if (f2fs_has_inline_data(inode)) { ipage = f2fs_get_node_page(sbi, inode->i_ino); - f2fs_bug_on(sbi, IS_ERR(ipage)); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); f2fs_truncate_inline_inode(inode, ipage, 0); clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (f2fs_truncate_blocks(inode, 0, false)) - return false; + int ret; + + ret = f2fs_truncate_blocks(inode, 0, false); + if (ret) + return ret; goto process_inline; } - return false; + return 0; } struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index f14401a77d60..ed12e9668184 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2315,6 +2315,9 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, if (unlikely(nid >= nm_i->max_nid)) nid = 0; + if (unlikely(nid % NAT_ENTRY_PER_BLOCK)) + nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK; + /* Enough entries */ if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) return 0; @@ -2350,7 +2353,6 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, if (ret) { up_read(&nm_i->nat_tree_lock); - f2fs_bug_on(sbi, !mount); f2fs_err(sbi, "NAT is corrupt, run fsck to fix it"); return ret; } @@ -2512,7 +2514,7 @@ int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) return nr - nr_shrink; } -void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) +int f2fs_recover_inline_xattr(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; size_t inline_size; @@ -2520,7 +2522,8 @@ void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) struct f2fs_inode *ri; ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); - f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage)); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); ri = F2FS_INODE(page); if (ri->i_inline & F2FS_INLINE_XATTR) { @@ -2539,6 +2542,7 @@ void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) update_inode: f2fs_update_inode(inode, ipage); f2fs_put_page(ipage, 1); + return 0; } int f2fs_recover_xattr_data(struct inode *inode, struct page *page) @@ -2933,7 +2937,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) return 0; nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8); - nm_i->nat_bits = f2fs_kzalloc(sbi, + nm_i->nat_bits = f2fs_kvzalloc(sbi, nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL); if (!nm_i->nat_bits) return -ENOMEM; @@ -3066,9 +3070,9 @@ static int init_free_nid_cache(struct f2fs_sb_info *sbi) int i; nm_i->free_nid_bitmap = - f2fs_kzalloc(sbi, array_size(sizeof(unsigned char *), - nm_i->nat_blocks), - GFP_KERNEL); + f2fs_kvzalloc(sbi, array_size(sizeof(unsigned char *), + nm_i->nat_blocks), + GFP_KERNEL); if (!nm_i->free_nid_bitmap) return -ENOMEM; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 783773e4560d..5f230e981c48 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -514,7 +514,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, /* step 1: recover xattr */ if (IS_INODE(page)) { - f2fs_recover_inline_xattr(inode, page); + err = f2fs_recover_inline_xattr(inode, page); + if (err) + goto out; } else if (f2fs_has_xattr_block(ofs_of_node(page))) { err = f2fs_recover_xattr_data(inode, page); if (!err) @@ -523,8 +525,12 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, } /* step 2: recover inline data */ - if (f2fs_recover_inline_data(inode, page)) + err = f2fs_recover_inline_data(inode, page); + if (err) { + if (err == 1) + err = 0; goto out; + } /* step 3: recover data indices */ start = f2fs_start_bidx_of_node(ofs_of_node(page), inode); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 5e1d4d9243a9..fa461db696e7 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -277,6 +277,22 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).s_resgid)); } +static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi) +{ + if (!F2FS_OPTION(sbi).unusable_cap_perc) + return; + + if (F2FS_OPTION(sbi).unusable_cap_perc == 100) + F2FS_OPTION(sbi).unusable_cap = sbi->user_block_count; + else + F2FS_OPTION(sbi).unusable_cap = (sbi->user_block_count / 100) * + F2FS_OPTION(sbi).unusable_cap_perc; + + f2fs_info(sbi, "Adjust unusable cap for checkpoint=disable = %u / %u%%", + F2FS_OPTION(sbi).unusable_cap, + F2FS_OPTION(sbi).unusable_cap_perc); +} + static void init_once(void *foo) { struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo; @@ -790,12 +806,7 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; if (arg < 0 || arg > 100) return -EINVAL; - if (arg == 100) - F2FS_OPTION(sbi).unusable_cap = - sbi->user_block_count; - else - F2FS_OPTION(sbi).unusable_cap = - (sbi->user_block_count / 100) * arg; + F2FS_OPTION(sbi).unusable_cap_perc = arg; set_opt(sbi, DISABLE_CHECKPOINT); break; case Opt_checkpoint_disable_cap: @@ -1064,6 +1075,9 @@ static void f2fs_put_super(struct super_block *sb) int i; bool dropped; + /* unregister procfs/sysfs entries in advance to avoid race case */ + f2fs_unregister_sysfs(sbi); + f2fs_quota_off_umount(sb); /* prevent remaining shrinker jobs */ @@ -1127,8 +1141,6 @@ static void f2fs_put_super(struct super_block *sb) kvfree(sbi->ckpt); - f2fs_unregister_sysfs(sbi); - sb->s_fs_info = NULL; if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); @@ -1219,7 +1231,8 @@ static int f2fs_statfs_project(struct super_block *sb, limit >>= sb->s_blocksize_bits; if (limit && buf->f_blocks > limit) { - curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits; + curblock = (dquot->dq_dqb.dqb_curspace + + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; buf->f_blocks = limit; buf->f_bfree = buf->f_bavail = (buf->f_blocks > curblock) ? @@ -1735,6 +1748,7 @@ skip: (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0); limit_reserve_root(sbi); + adjust_unusable_cap_perc(sbi); *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); return 0; restore_gc: @@ -2888,7 +2902,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) if (nr_sectors & (bdev_zone_sectors(bdev) - 1)) FDEV(devi).nr_blkz++; - FDEV(devi).blkz_seq = f2fs_kzalloc(sbi, + FDEV(devi).blkz_seq = f2fs_kvzalloc(sbi, BITS_TO_LONGS(FDEV(devi).nr_blkz) * sizeof(unsigned long), GFP_KERNEL); @@ -3397,6 +3411,7 @@ try_onemore: sbi->reserved_blocks = 0; sbi->current_reserved_blocks = 0; limit_reserve_root(sbi); + adjust_unusable_cap_perc(sbi); for (i = 0; i < NR_INODE_TYPE; i++) { INIT_LIST_HEAD(&sbi->inode_list[i]); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 170934430d7d..029e693e201c 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -788,4 +788,5 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) } kobject_del(&sbi->s_kobj); kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 76ac9c7d32ec..5f6400ba82c0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -42,7 +42,6 @@ struct wb_writeback_work { long nr_pages; struct super_block *sb; - unsigned long *older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; @@ -144,7 +143,9 @@ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } @@ -1123,7 +1124,9 @@ void inode_io_list_del(struct inode *inode) struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); + spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); + spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } @@ -1172,8 +1175,10 @@ void sb_clear_inode_writeback(struct inode *inode) * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ -static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { + assert_spin_locked(&inode->i_lock); + if (!list_empty(&wb->b_dirty)) { struct inode *tail; @@ -1182,6 +1187,14 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); + inode->i_state &= ~I_SYNC_QUEUED; +} + +static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +{ + spin_lock(&inode->i_lock); + redirty_tail_locked(inode, wb); + spin_unlock(&inode->i_lock); } /* @@ -1220,16 +1233,13 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) #define EXPIRE_DIRTY_ATIME 0x0001 /* - * Move expired (dirtied before work->older_than_this) dirty inodes from + * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - int flags, - struct wb_writeback_work *work) + int flags, unsigned long dirtied_before) { - unsigned long *older_than_this = NULL; - unsigned long expire_time; LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; @@ -1237,21 +1247,17 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; - if ((flags & EXPIRE_DIRTY_ATIME) == 0) - older_than_this = work->older_than_this; - else if (!work->for_sync) { - expire_time = jiffies - (dirtytime_expire_interval * HZ); - older_than_this = &expire_time; - } while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (older_than_this && - inode_dirtied_after(inode, *older_than_this)) + if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; + spin_lock(&inode->i_lock); if (flags & EXPIRE_DIRTY_ATIME) - set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state); + inode->i_state |= I_DIRTY_TIME_EXPIRED; + inode->i_state |= I_SYNC_QUEUED; + spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) @@ -1289,18 +1295,22 @@ out: * | * +--> dequeue for IO */ -static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) +static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before) { int moved; + unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, dirtied_before); + if (!work->for_sync) + time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, - EXPIRE_DIRTY_ATIME, work); + EXPIRE_DIRTY_ATIME, time_expire_jif); if (moved) wb_io_lists_populated(wb); - trace_writeback_queue_io(wb, work, moved); + trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) @@ -1394,7 +1404,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * writeback is not making progress due to locked * buffers. Skip this inode for now. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); return; } @@ -1414,7 +1424,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* @@ -1422,10 +1432,11 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * such as delayed allocation during submission or metadata * updates after data IO completion. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); + inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); @@ -1669,8 +1680,8 @@ static long writeback_sb_inodes(struct super_block *sb, */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); - redirty_tail(inode, wb); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { @@ -1811,7 +1822,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) - queue_io(wb, &work); + queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); @@ -1831,7 +1842,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * - * older_than_this takes precedence over nr_to_write. So we'll only write back + * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, @@ -1839,14 +1850,11 @@ static long wb_writeback(struct bdi_writeback *wb, { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; - unsigned long oldest_jif; + unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; - oldest_jif = jiffies; - work->older_than_this = &oldest_jif; - blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { @@ -1880,14 +1888,14 @@ static long wb_writeback(struct bdi_writeback *wb, * safe. */ if (work->for_kupdate) { - oldest_jif = jiffies - + dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) - oldest_jif = jiffies; + dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) - queue_io(wb, work); + queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else @@ -2289,11 +2297,12 @@ void __mark_inode_dirty(struct inode *inode, int flags) inode->i_state |= flags; /* - * If the inode is being synced, just update its dirty state. - * The unlocker will place the inode on the appropriate - * superblock list, based upon its state. + * If the inode is queued for writeback by flush worker, just + * update its dirty state. Once the flush worker is done with + * the inode it will place it on the appropriate superblock + * list, based upon its state. */ - if (inode->i_state & I_SYNC) + if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4f2e4f38feb8..40c262b3f9ff 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -764,14 +764,14 @@ static int fuse_check_page(struct page *page) { if (page_mapcount(page) || page->mapping != NULL || - page_count(page) != 1 || (page->flags & PAGE_FLAGS_CHECK_AT_PREP & ~(1 << PG_locked | 1 << PG_referenced | 1 << PG_uptodate | 1 << PG_lru | 1 << PG_active | - 1 << PG_reclaim))) { + 1 << PG_reclaim | + 1 << PG_waiters))) { pr_warn("trying to steal weird page\n"); pr_warn(" page=%p index=%li flags=%08lx, count=%i, mapcount=%i, mapping=%p\n", page, page->index, page->flags, page_count(page), page_mapcount(page), page->mapping); return 1; @@ -786,15 +786,16 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) struct page *newpage; struct pipe_buffer *buf = cs->pipebufs; + get_page(oldpage); err = unlock_request(cs->req); if (err) - return err; + goto out_put_old; fuse_copy_finish(cs); err = pipe_buf_confirm(cs->pipe, buf); if (err) - return err; + goto out_put_old; BUG_ON(!cs->nr_segs); cs->currbuf = buf; @@ -834,7 +835,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL); if (err) { unlock_page(newpage); - return err; + goto out_put_old; } get_page(newpage); @@ -853,14 +854,19 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) if (err) { unlock_page(newpage); put_page(newpage); - return err; + goto out_put_old; } unlock_page(oldpage); + /* Drop ref for ap->pages[] array */ put_page(oldpage); cs->len = 0; - return 0; + err = 0; +out_put_old: + /* Drop ref obtained in this function */ + put_page(oldpage); + return err; out_fallback_unlock: unlock_page(newpage); @@ -869,10 +875,10 @@ out_fallback: cs->offset = buf->offset; err = lock_request(cs->req); - if (err) - return err; + if (!err) + err = 1; - return 1; + goto out_put_old; } static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, @@ -884,14 +890,16 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, if (cs->nr_segs == cs->pipe->buffers) return -EIO; + get_page(page); err = unlock_request(cs->req); - if (err) + if (err) { + put_page(page); return err; + } fuse_copy_finish(cs); buf = cs->pipebufs; - get_page(page); buf->page = page; buf->offset = offset; buf->len = count; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 3dd37a998ea9..ab4fc1255aca 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -18,6 +18,7 @@ #include <linux/swap.h> #include <linux/falloc.h> #include <linux/uio.h> +#include <linux/fs.h> static struct page **fuse_pages_alloc(unsigned int npages, gfp_t flags, struct fuse_page_desc **desc) @@ -712,6 +713,7 @@ static ssize_t fuse_async_req_send(struct fuse_conn *fc, spin_unlock(&io->lock); ia->ap.args.end = fuse_aio_complete_req; + ia->ap.args.may_block = io->should_dirty; err = fuse_simple_background(fc, &ia->ap.args, GFP_KERNEL); if (err) fuse_aio_complete_req(fc, &ia->ap.args, err); @@ -2147,10 +2149,8 @@ static int fuse_writepages(struct address_space *mapping, err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data); if (data.wpa) { - /* Ignore errors if we can write at least one page */ WARN_ON(!data.wpa->ia.ap.num_pages); fuse_writepages_send(&data); - err = 0; } if (data.ff) fuse_file_put(data.ff, false, false); @@ -2759,7 +2759,16 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, struct iovec *iov = iov_page; iov->iov_base = (void __user *)arg; - iov->iov_len = _IOC_SIZE(cmd); + + switch (cmd) { + case FS_IOC_GETFLAGS: + case FS_IOC_SETFLAGS: + iov->iov_len = sizeof(int); + break; + default: + iov->iov_len = _IOC_SIZE(cmd); + break; + } if (_IOC_DIR(cmd) & _IOC_WRITE) { in_iov = iov; @@ -3065,11 +3074,10 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) ssize_t ret = 0; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; - bool async_dio = ff->fc->async_dio; loff_t pos = 0; struct inode *inode; loff_t i_size; - size_t count = iov_iter_count(iter); + size_t count = iov_iter_count(iter), shortened = 0; loff_t offset = iocb->ki_pos; struct fuse_io_priv *io; @@ -3077,17 +3085,9 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) inode = file->f_mapping->host; i_size = i_size_read(inode); - if ((iov_iter_rw(iter) == READ) && (offset > i_size)) + if ((iov_iter_rw(iter) == READ) && (offset >= i_size)) return 0; - /* optimization for short read */ - if (async_dio && iov_iter_rw(iter) != WRITE && offset + count > i_size) { - if (offset >= i_size) - return 0; - iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset)); - count = iov_iter_count(iter); - } - io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL); if (!io) return -ENOMEM; @@ -3103,15 +3103,22 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) * By default, we want to optimize all I/Os with async request * submission to the client filesystem if supported. */ - io->async = async_dio; + io->async = ff->fc->async_dio; io->iocb = iocb; io->blocking = is_sync_kiocb(iocb); + /* optimization for short read */ + if (io->async && !io->write && offset + count > i_size) { + iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset)); + shortened = count - iov_iter_count(iter); + count -= shortened; + } + /* * We cannot asynchronously extend the size of a file. * In such case the aio will behave exactly like sync io. */ - if ((offset + count > i_size) && iov_iter_rw(iter) == WRITE) + if ((offset + count > i_size) && io->write) io->blocking = true; if (io->async && io->blocking) { @@ -3129,6 +3136,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } else { ret = __fuse_direct_read(io, iter, &pos); } + iov_iter_reexpand(iter, iov_iter_count(iter) + shortened); if (io->async) { bool blocking = io->blocking; @@ -3279,13 +3287,11 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; - if (fc->writeback_cache) { - inode_lock(inode_in); - err = fuse_writeback_range(inode_in, pos_in, pos_in + len); - inode_unlock(inode_in); - if (err) - return err; - } + inode_lock(inode_in); + err = fuse_writeback_range(inode_in, pos_in, pos_in + len - 1); + inode_unlock(inode_in); + if (err) + return err; inode_lock(inode_out); @@ -3293,11 +3299,27 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, if (err) goto out; - if (fc->writeback_cache) { - err = fuse_writeback_range(inode_out, pos_out, pos_out + len); - if (err) - goto out; - } + /* + * Write out dirty pages in the destination file before sending the COPY + * request to userspace. After the request is completed, truncate off + * pages (including partial ones) from the cache that have been copied, + * since these contain stale data at that point. + * + * This should be mostly correct, but if the COPY writes to partial + * pages (at the start or end) and the parts not covered by the COPY are + * written through a memory map after calling fuse_writeback_range(), + * then these partial page modifications will be lost on truncation. + * + * It is unlikely that someone would rely on such mixed style + * modifications. Yet this does give less guarantees than if the + * copying was performed with write(2). + * + * To fix this a i_mmap_sem style lock could be used to prevent new + * faults while the copy is ongoing. + */ + err = fuse_writeback_range(inode_out, pos_out, pos_out + len - 1); + if (err) + goto out; if (is_unstable) set_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state); @@ -3318,6 +3340,10 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, if (err) goto out; + truncate_inode_pages_range(inode_out->i_mapping, + ALIGN_DOWN(pos_out, PAGE_SIZE), + ALIGN(pos_out + outarg.size, PAGE_SIZE) - 1); + if (fc->writeback_cache) { fuse_write_update_size(inode_out, pos_out + outarg.size); file_update_time(file_out); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index ca344bf71404..d7cde216fc87 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -249,6 +249,7 @@ struct fuse_args { bool out_argvar:1; bool page_zeroing:1; bool page_replace:1; + bool may_block:1; struct fuse_in_arg in_args[3]; struct fuse_arg out_args[2]; void (*end)(struct fuse_conn *fc, struct fuse_args *args, int error); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 16aec32f7f3d..f58ab84b09fb 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -121,10 +121,12 @@ static void fuse_evict_inode(struct inode *inode) } } -static int fuse_remount_fs(struct super_block *sb, int *flags, char *data) +static int fuse_reconfigure(struct fs_context *fc) { + struct super_block *sb = fc->root->d_sb; + sync_filesystem(sb); - if (*flags & SB_MANDLOCK) + if (fc->sb_flags & SB_MANDLOCK) return -EINVAL; return 0; @@ -321,6 +323,8 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, loff_t offset, loff_t len) { + struct fuse_conn *fc = get_fuse_conn_super(sb); + struct fuse_inode *fi; struct inode *inode; pgoff_t pg_start; pgoff_t pg_end; @@ -329,6 +333,11 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, if (!inode) return -ENOENT; + fi = get_fuse_inode(inode); + spin_lock(&fi->lock); + fi->attr_version = atomic64_inc_return(&fc->attr_version); + spin_unlock(&fi->lock); + fuse_invalidate_attr(inode); forget_all_cached_acls(inode); if (offset >= 0) { @@ -473,6 +482,13 @@ static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param) struct fuse_fs_context *ctx = fc->fs_private; int opt; + /* + * Ignore options coming from mount(MS_REMOUNT) for backward + * compatibility. + */ + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) + return 0; + opt = fs_parse(fc, &fuse_fs_parameters, param, &result); if (opt < 0) return opt; @@ -815,7 +831,6 @@ static const struct super_operations fuse_super_operations = { .evict_inode = fuse_evict_inode, .write_inode = fuse_write_inode, .drop_inode = generic_delete_inode, - .remount_fs = fuse_remount_fs, .put_super = fuse_put_super, .umount_begin = fuse_umount_begin, .statfs = fuse_statfs, @@ -1289,6 +1304,7 @@ static int fuse_get_tree(struct fs_context *fc) static const struct fs_context_operations fuse_context_ops = { .free = fuse_free_fc, .parse_param = fuse_parse_param, + .reconfigure = fuse_reconfigure, .get_tree = fuse_get_tree, }; diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index a5c86048b96e..7505f8102762 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -55,6 +55,12 @@ struct virtio_fs_forget { struct list_head list; }; +struct virtio_fs_req_work { + struct fuse_req *req; + struct virtio_fs_vq *fsvq; + struct work_struct done_work; +}; + static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, struct fuse_req *req, bool in_flight); @@ -443,19 +449,67 @@ static void copy_args_from_argbuf(struct fuse_args *args, struct fuse_req *req) } /* Work function for request completion */ +static void virtio_fs_request_complete(struct fuse_req *req, + struct virtio_fs_vq *fsvq) +{ + struct fuse_pqueue *fpq = &fsvq->fud->pq; + struct fuse_conn *fc = fsvq->fud->fc; + struct fuse_args *args; + struct fuse_args_pages *ap; + unsigned int len, i, thislen; + struct page *page; + + /* + * TODO verify that server properly follows FUSE protocol + * (oh.uniq, oh.len) + */ + args = req->args; + copy_args_from_argbuf(args, req); + + if (args->out_pages && args->page_zeroing) { + len = args->out_args[args->out_numargs - 1].size; + ap = container_of(args, typeof(*ap), args); + for (i = 0; i < ap->num_pages; i++) { + thislen = ap->descs[i].length; + if (len < thislen) { + WARN_ON(ap->descs[i].offset); + page = ap->pages[i]; + zero_user_segment(page, len, thislen); + len = 0; + } else { + len -= thislen; + } + } + } + + spin_lock(&fpq->lock); + clear_bit(FR_SENT, &req->flags); + spin_unlock(&fpq->lock); + + fuse_request_end(fc, req); + spin_lock(&fsvq->lock); + dec_in_flight_req(fsvq); + spin_unlock(&fsvq->lock); +} + +static void virtio_fs_complete_req_work(struct work_struct *work) +{ + struct virtio_fs_req_work *w = + container_of(work, typeof(*w), done_work); + + virtio_fs_request_complete(w->req, w->fsvq); + kfree(w); +} + static void virtio_fs_requests_done_work(struct work_struct *work) { struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, done_work); struct fuse_pqueue *fpq = &fsvq->fud->pq; - struct fuse_conn *fc = fsvq->fud->fc; struct virtqueue *vq = fsvq->vq; struct fuse_req *req; - struct fuse_args_pages *ap; struct fuse_req *next; - struct fuse_args *args; - unsigned int len, i, thislen; - struct page *page; + unsigned int len; LIST_HEAD(reqs); /* Collect completed requests off the virtqueue */ @@ -473,38 +527,20 @@ static void virtio_fs_requests_done_work(struct work_struct *work) /* End requests */ list_for_each_entry_safe(req, next, &reqs, list) { - /* - * TODO verify that server properly follows FUSE protocol - * (oh.uniq, oh.len) - */ - args = req->args; - copy_args_from_argbuf(args, req); - - if (args->out_pages && args->page_zeroing) { - len = args->out_args[args->out_numargs - 1].size; - ap = container_of(args, typeof(*ap), args); - for (i = 0; i < ap->num_pages; i++) { - thislen = ap->descs[i].length; - if (len < thislen) { - WARN_ON(ap->descs[i].offset); - page = ap->pages[i]; - zero_user_segment(page, len, thislen); - len = 0; - } else { - len -= thislen; - } - } - } - - spin_lock(&fpq->lock); - clear_bit(FR_SENT, &req->flags); list_del_init(&req->list); - spin_unlock(&fpq->lock); - fuse_request_end(fc, req); - spin_lock(&fsvq->lock); - dec_in_flight_req(fsvq); - spin_unlock(&fsvq->lock); + /* blocking async request completes in a worker context */ + if (req->args->may_block) { + struct virtio_fs_req_work *w; + + w = kzalloc(sizeof(*w), GFP_NOFS | __GFP_NOFAIL); + INIT_WORK(&w->done_work, virtio_fs_complete_req_work); + w->fsvq = fsvq; + w->req = req; + schedule_work(&w->done_work); + } else { + virtio_fs_request_complete(req, fsvq); + } } } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index adbb8fef2216..50fa3e08c02f 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1350,9 +1350,15 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi return ret; } +/* + * NOTE: Never call gfs2_block_zero_range with an open transaction because it + * uses iomap write to perform its actions, which begin their own transactions + * (iomap_begin, page_prepare, etc.) + */ static int gfs2_block_zero_range(struct inode *inode, loff_t from, unsigned int length) { + BUG_ON(current->journal_info); return iomap_zero_range(inode, from, length, NULL, &gfs2_iomap_ops); } @@ -1413,6 +1419,16 @@ static int trunc_start(struct inode *inode, u64 newsize) u64 oldsize = inode->i_size; int error; + if (!gfs2_is_stuffed(ip)) { + unsigned int blocksize = i_blocksize(inode); + unsigned int offs = newsize & (blocksize - 1); + if (offs) { + error = gfs2_block_zero_range(inode, newsize, + blocksize - offs); + if (error) + return error; + } + } if (journaled) error = gfs2_trans_begin(sdp, RES_DINODE + RES_JDATA, GFS2_JTRUNC_REVOKES); else @@ -1426,19 +1442,10 @@ static int trunc_start(struct inode *inode, u64 newsize) gfs2_trans_add_meta(ip->i_gl, dibh); - if (gfs2_is_stuffed(ip)) { + if (gfs2_is_stuffed(ip)) gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize); - } else { - unsigned int blocksize = i_blocksize(inode); - unsigned int offs = newsize & (blocksize - 1); - if (offs) { - error = gfs2_block_zero_range(inode, newsize, - blocksize - offs); - if (error) - goto out; - } + else ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG; - } i_size_write(inode, newsize); ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode); @@ -2442,24 +2449,13 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length) struct inode *inode = file_inode(file); struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); + unsigned int blocksize = i_blocksize(inode); + loff_t start, end; int error; - if (gfs2_is_jdata(ip)) - error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_JDATA, - GFS2_JTRUNC_REVOKES); - else - error = gfs2_trans_begin(sdp, RES_DINODE, 0); - if (error) - return error; + if (!gfs2_is_stuffed(ip)) { + unsigned int start_off, end_len; - if (gfs2_is_stuffed(ip)) { - error = stuffed_zero_range(inode, offset, length); - if (error) - goto out; - } else { - unsigned int start_off, end_len, blocksize; - - blocksize = i_blocksize(inode); start_off = offset & (blocksize - 1); end_len = (offset + length) & (blocksize - 1); if (start_off) { @@ -2480,6 +2476,26 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length) } } + start = round_down(offset, blocksize); + end = round_up(offset + length, blocksize) - 1; + error = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (error) + return error; + + if (gfs2_is_jdata(ip)) + error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_JDATA, + GFS2_JTRUNC_REVOKES); + else + error = gfs2_trans_begin(sdp, RES_DINODE, 0); + if (error) + return error; + + if (gfs2_is_stuffed(ip)) { + error = stuffed_zero_range(inode, offset, length); + if (error) + goto out; + } + if (gfs2_is_jdata(ip)) { BUG_ON(!current->journal_info); gfs2_journaled_truncate_range(inode, offset, length); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 83cf64da474c..d5b9274662db 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -87,6 +87,8 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) memset(&tr, 0, sizeof(tr)); INIT_LIST_HEAD(&tr.tr_buf); INIT_LIST_HEAD(&tr.tr_databuf); + INIT_LIST_HEAD(&tr.tr_ail1_list); + INIT_LIST_HEAD(&tr.tr_ail2_list); tr.tr_revokes = atomic_read(&gl->gl_ail_count); if (!tr.tr_revokes) { diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 8466166f22e3..988bb7b17ed8 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -712,7 +712,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_trans_begin(sdp, blocks, 0); if (error) - goto fail_gunlock2; + goto fail_free_inode; if (blocks > 1) { ip->i_eattr = ip->i_no_addr + 1; @@ -723,7 +723,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) - goto fail_gunlock2; + goto fail_free_inode; BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags)); @@ -732,7 +732,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, goto fail_gunlock2; glock_set_object(ip->i_iopen_gh.gh_gl, ip); - gfs2_glock_put(io_gl); gfs2_set_iop(inode); insert_inode_hash(inode); @@ -765,6 +764,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, mark_inode_dirty(inode); d_instantiate(dentry, inode); + /* After instantiate, errors should result in evict which will destroy + * both inode and iopen glocks properly. */ if (file) { file->f_mode |= FMODE_CREATED; error = finish_open(file, dentry, gfs2_open_common); @@ -772,15 +773,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_glock_dq_uninit(ghs); gfs2_glock_dq_uninit(ghs + 1); clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + gfs2_glock_put(io_gl); return error; fail_gunlock3: glock_clear_object(io_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); - gfs2_glock_put(io_gl); fail_gunlock2: - if (io_gl) - clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { glock_clear_object(ip->i_gl, ip); diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 110e5c4db819..00a90fc72597 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -810,8 +810,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) tr = sdp->sd_log_tr; if (tr) { sdp->sd_log_tr = NULL; - INIT_LIST_HEAD(&tr->tr_ail1_list); - INIT_LIST_HEAD(&tr->tr_ail2_list); tr->tr_first = sdp->sd_log_flush_head; if (unlikely (state == SFS_FROZEN)) gfs2_assert_withdraw(sdp, !tr->tr_num_buf_new && !tr->tr_num_databuf_new); @@ -881,8 +879,10 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) * @new: New transaction to be merged */ -static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new) +static void gfs2_merge_trans(struct gfs2_sbd *sdp, struct gfs2_trans *new) { + struct gfs2_trans *old = sdp->sd_log_tr; + WARN_ON_ONCE(!test_bit(TR_ATTACHED, &old->tr_flags)); old->tr_num_buf_new += new->tr_num_buf_new; @@ -893,6 +893,11 @@ static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new) list_splice_tail_init(&new->tr_databuf, &old->tr_databuf); list_splice_tail_init(&new->tr_buf, &old->tr_buf); + + spin_lock(&sdp->sd_ail_lock); + list_splice_tail_init(&new->tr_ail1_list, &old->tr_ail1_list); + list_splice_tail_init(&new->tr_ail2_list, &old->tr_ail2_list); + spin_unlock(&sdp->sd_ail_lock); } static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) @@ -904,7 +909,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) gfs2_log_lock(sdp); if (sdp->sd_log_tr) { - gfs2_merge_trans(sdp->sd_log_tr, tr); + gfs2_merge_trans(sdp, tr); } else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) { gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags)); sdp->sd_log_tr = tr; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 18daf494abab..e0c55765b06d 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -911,7 +911,7 @@ fail: } static const match_table_t nolock_tokens = { - { Opt_jid, "jid=%d\n", }, + { Opt_jid, "jid=%d", }, { Opt_err, NULL }, }; @@ -1168,7 +1168,17 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) goto fail_per_node; } - if (!sb_rdonly(sb)) { + if (sb_rdonly(sb)) { + struct gfs2_holder freeze_gh; + + error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, + GL_EXACT, &freeze_gh); + if (error) { + fs_err(sdp, "can't make FS RO: %d\n", error); + goto fail_per_node; + } + gfs2_glock_dq_uninit(&freeze_gh); + } else { error = gfs2_make_fs_rw(sdp); if (error) { fs_err(sdp, "can't make FS RW: %d\n", error); diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 9d4227330de4..2a12d30ae0de 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -53,6 +53,8 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, sizeof(u64)); INIT_LIST_HEAD(&tr->tr_databuf); INIT_LIST_HEAD(&tr->tr_buf); + INIT_LIST_HEAD(&tr->tr_ail1_list); + INIT_LIST_HEAD(&tr->tr_ail2_list); sb_start_intwrite(sdp->sd_vfs); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 40306c1eab07..5fff7cb3582f 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1284,6 +1284,12 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_magic = HUGETLBFS_MAGIC; sb->s_op = &hugetlbfs_ops; sb->s_time_gran = 1; + + /* + * Due to the special and limited functionality of hugetlbfs, it does + * not work well as a stacking filesystem. + */ + sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; sb->s_root = d_make_root(hugetlbfs_get_root(sb, ctx)); if (!sb->s_root) goto out_free; diff --git a/fs/io_uring.c b/fs/io_uring.c index 7fa3cd3fff4d..4127ea027a14 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -267,6 +267,9 @@ struct io_ring_ctx { #if defined(CONFIG_UNIX) struct socket *ring_sock; #endif + + struct list_head task_list; + spinlock_t task_lock; }; struct sqe_submit { @@ -276,6 +279,7 @@ struct sqe_submit { bool has_user; bool needs_lock; bool needs_fixed_file; + u8 opcode; }; /* @@ -331,14 +335,18 @@ struct io_kiocb { #define REQ_F_ISREG 2048 /* regular file */ #define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */ #define REQ_F_TIMEOUT_NOSEQ 8192 /* no timeout sequence */ +#define REQ_F_CANCEL 16384 /* cancel request */ unsigned long fsize; u64 user_data; u32 result; u32 sequence; + struct files_struct *files; struct fs_struct *fs; struct work_struct work; + struct task_struct *work_task; + struct list_head task_list; }; #define IO_PLUG_THRESHOLD 2 @@ -425,6 +433,8 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->cancel_list); INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); + INIT_LIST_HEAD(&ctx->task_list); + spin_lock_init(&ctx->task_lock); return ctx; } @@ -492,10 +502,11 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx) static inline void io_queue_async_work(struct io_ring_ctx *ctx, struct io_kiocb *req) { + unsigned long flags; int rw = 0; if (req->submit.sqe) { - switch (req->submit.sqe->opcode) { + switch (req->submit.opcode) { case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: rw = !(req->rw.ki_flags & IOCB_DIRECT); @@ -503,6 +514,15 @@ static inline void io_queue_async_work(struct io_ring_ctx *ctx, } } + if (req->work.func == io_sq_wq_submit_work) { + req->files = current->files; + + spin_lock_irqsave(&ctx->task_lock, flags); + list_add(&req->task_list, &ctx->task_list); + req->work_task = NULL; + spin_unlock_irqrestore(&ctx->task_lock, flags); + } + queue_work(ctx->sqo_wq[rw], &req->work); } @@ -650,6 +670,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, state->cur_req++; } + INIT_LIST_HEAD(&req->task_list); req->file = NULL; req->ctx = ctx; req->flags = 0; @@ -1237,23 +1258,15 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, } static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw, - const struct sqe_submit *s, struct iovec **iovec, + struct io_kiocb *req, struct iovec **iovec, struct iov_iter *iter) { - const struct io_uring_sqe *sqe = s->sqe; + const struct io_uring_sqe *sqe = req->submit.sqe; void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); size_t sqe_len = READ_ONCE(sqe->len); u8 opcode; - /* - * We're reading ->opcode for the second time, but the first read - * doesn't care whether it's _FIXED or not, so it doesn't matter - * whether ->opcode changes concurrently. The first read does care - * about whether it is a READ or a WRITE, so we don't trust this read - * for that purpose and instead let the caller pass in the read/write - * flag. - */ - opcode = READ_ONCE(sqe->opcode); + opcode = req->submit.opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { ssize_t ret = io_import_fixed(ctx, rw, sqe, iter); @@ -1261,7 +1274,7 @@ static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw, return ret; } - if (!s->has_user) + if (!req->submit.has_user) return -EFAULT; #ifdef CONFIG_COMPAT @@ -1408,7 +1421,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, if (unlikely(!(file->f_mode & FMODE_READ))) return -EBADF; - ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter); + ret = io_import_iovec(req->ctx, READ, req, &iovec, &iter); if (ret < 0) return ret; @@ -1423,8 +1436,10 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, if (file->f_op->read_iter) ret2 = call_read_iter(file, kiocb, &iter); - else + else if (req->file->f_op->read) ret2 = loop_rw_iter(READ, file, kiocb, &iter); + else + ret2 = -EINVAL; /* * In case of a short read, punt to async. This can happen @@ -1473,7 +1488,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, if (unlikely(!(file->f_mode & FMODE_WRITE))) return -EBADF; - ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter); + ret = io_import_iovec(req->ctx, WRITE, req, &iovec, &iter); if (ret < 0) return ret; @@ -1514,8 +1529,10 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, if (file->f_op->write_iter) ret2 = call_write_iter(file, kiocb, &iter); - else + else if (req->file->f_op->write) ret2 = loop_rw_iter(WRITE, file, kiocb, &iter); + else + ret2 = -EINVAL; if (!force_nonblock) current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; @@ -2092,15 +2109,14 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct sqe_submit *s, bool force_nonblock) { - int ret, opcode; + int ret; req->user_data = READ_ONCE(s->sqe->user_data); if (unlikely(s->index >= ctx->sq_entries)) return -EINVAL; - opcode = READ_ONCE(s->sqe->opcode); - switch (opcode) { + switch (req->submit.opcode) { case IORING_OP_NOP: ret = io_nop(req, req->user_data); break; @@ -2164,10 +2180,10 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return 0; } -static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx, - const struct io_uring_sqe *sqe) +static struct async_list *io_async_list_from_req(struct io_ring_ctx *ctx, + struct io_kiocb *req) { - switch (sqe->opcode) { + switch (req->submit.opcode) { case IORING_OP_READV: case IORING_OP_READ_FIXED: return &ctx->pending_async[READ]; @@ -2179,12 +2195,10 @@ static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx, } } -static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) +static inline bool io_req_needs_user(struct io_kiocb *req) { - u8 opcode = READ_ONCE(sqe->opcode); - - return !(opcode == IORING_OP_READ_FIXED || - opcode == IORING_OP_WRITE_FIXED); + return !(req->submit.opcode == IORING_OP_READ_FIXED || + req->submit.opcode == IORING_OP_WRITE_FIXED); } static void io_sq_wq_submit_work(struct work_struct *work) @@ -2200,7 +2214,9 @@ static void io_sq_wq_submit_work(struct work_struct *work) int ret; old_cred = override_creds(ctx->creds); - async_list = io_async_list_from_sqe(ctx, req->submit.sqe); + async_list = io_async_list_from_req(ctx, req); + + allow_kernel_signal(SIGINT); restart: do { struct sqe_submit *s = &req->submit; @@ -2220,9 +2236,10 @@ restart: } ret = 0; - if (io_sqe_needs_user(sqe) && !cur_mm) { + if (io_req_needs_user(req) && !cur_mm) { if (!mmget_not_zero(ctx->sqo_mm)) { ret = -EFAULT; + goto end_req; } else { cur_mm = ctx->sqo_mm; use_mm(cur_mm); @@ -2232,6 +2249,18 @@ restart: } if (!ret) { + req->work_task = current; + + /* + * Pairs with the smp_store_mb() (B) in + * io_cancel_async_work(). + */ + smp_mb(); /* A */ + if (req->flags & REQ_F_CANCEL) { + ret = -ECANCELED; + goto end_req; + } + s->has_user = cur_mm != NULL; s->needs_lock = true; do { @@ -2247,6 +2276,10 @@ restart: cond_resched(); } while (1); } +end_req: + spin_lock_irq(&ctx->task_lock); + list_del_init(&req->task_list); + spin_unlock_irq(&ctx->task_lock); /* drop submission reference */ io_put_req(req); @@ -2311,6 +2344,7 @@ restart: } out: + disallow_signal(SIGINT); if (cur_mm) { set_fs(old_fs); unuse_mm(cur_mm); @@ -2351,15 +2385,24 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) list_del_init(&req->list); ret = false; } + + if (ret) { + struct io_ring_ctx *ctx = req->ctx; + + req->files = current->files; + + spin_lock_irq(&ctx->task_lock); + list_add(&req->task_list, &ctx->task_list); + req->work_task = NULL; + spin_unlock_irq(&ctx->task_lock); + } spin_unlock(&list->lock); return ret; } -static bool io_op_needs_file(const struct io_uring_sqe *sqe) +static bool io_op_needs_file(struct io_kiocb *req) { - int op = READ_ONCE(sqe->opcode); - - switch (op) { + switch (req->submit.opcode) { case IORING_OP_NOP: case IORING_OP_POLL_REMOVE: case IORING_OP_TIMEOUT: @@ -2387,7 +2430,7 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, */ req->sequence = s->sequence; - if (!io_op_needs_file(s->sqe)) + if (!io_op_needs_file(req)) return 0; if (flags & IOSQE_FIXED_FILE) { @@ -2428,7 +2471,7 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, s->sqe = sqe_copy; memcpy(&req->submit, s, sizeof(*s)); - list = io_async_list_from_sqe(ctx, s->sqe); + list = io_async_list_from_req(ctx, req); if (!io_add_to_prev_work(list, req)) { if (list) atomic_inc(&list->cnt); @@ -2538,6 +2581,7 @@ static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, goto err; } + memcpy(&req->submit, s, sizeof(*s)); ret = io_req_set_file(ctx, s, state, req); if (unlikely(ret)) { err_req: @@ -2550,7 +2594,7 @@ err: req->user_data = s->sqe->user_data; #if defined(CONFIG_NET) - switch (READ_ONCE(s->sqe->opcode)) { + switch (req->submit.opcode) { case IORING_OP_SENDMSG: case IORING_OP_RECVMSG: spin_lock(¤t->fs->lock); @@ -2665,6 +2709,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) if (head < ctx->sq_entries) { s->index = head; s->sqe = &ctx->sq_sqes[head]; + s->opcode = READ_ONCE(s->sqe->opcode); s->sequence = ctx->cached_sq_head; ctx->cached_sq_head++; return true; @@ -3368,6 +3413,9 @@ static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, return SIZE_MAX; #endif + if (sq_offset) + *sq_offset = off; + sq_array_size = array_size(sizeof(u32), sq_entries); if (sq_array_size == SIZE_MAX) return SIZE_MAX; @@ -3375,9 +3423,6 @@ static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, if (check_add_overflow(off, sq_array_size, &off)) return SIZE_MAX; - if (sq_offset) - *sq_offset = off; - return off; } @@ -3675,12 +3720,41 @@ static int io_uring_fasync(int fd, struct file *file, int on) return fasync_helper(fd, file, on, &ctx->cq_fasync); } +static void io_cancel_async_work(struct io_ring_ctx *ctx, + struct files_struct *files) +{ + struct io_kiocb *req; + + if (list_empty(&ctx->task_list)) + return; + + spin_lock_irq(&ctx->task_lock); + + list_for_each_entry(req, &ctx->task_list, task_list) { + if (files && req->files != files) + continue; + + /* + * The below executes an smp_mb(), which matches with the + * smp_mb() (A) in io_sq_wq_submit_work() such that either + * we store REQ_F_CANCEL flag to req->flags or we see the + * req->work_task setted in io_sq_wq_submit_work(). + */ + smp_store_mb(req->flags, req->flags | REQ_F_CANCEL); /* B */ + + if (req->work_task) + send_sig(SIGINT, req->work_task, 1); + } + spin_unlock_irq(&ctx->task_lock); +} + static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { mutex_lock(&ctx->uring_lock); percpu_ref_kill(&ctx->refs); mutex_unlock(&ctx->uring_lock); + io_cancel_async_work(ctx, NULL); io_kill_timeouts(ctx); io_poll_remove_all(ctx); io_iopoll_reap_events(ctx); @@ -3688,6 +3762,16 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_ring_ctx_free(ctx); } +static int io_uring_flush(struct file *file, void *data) +{ + struct io_ring_ctx *ctx = file->private_data; + + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) + io_cancel_async_work(ctx, data); + + return 0; +} + static int io_uring_release(struct inode *inode, struct file *file) { struct io_ring_ctx *ctx = file->private_data; @@ -3792,6 +3876,7 @@ out_fput: static const struct file_operations io_uring_fops = { .release = io_uring_release, + .flush = io_uring_flush, .mmap = io_uring_mmap, .poll = io_uring_poll, .fasync = io_uring_fasync, @@ -3803,6 +3888,10 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, struct io_rings *rings; size_t size, sq_array_offset; + /* make sure these are sane, as we already accounted them */ + ctx->sq_entries = p->sq_entries; + ctx->cq_entries = p->cq_entries; + size = rings_size(p->sq_entries, p->cq_entries, &sq_array_offset); if (size == SIZE_MAX) return -EOVERFLOW; @@ -3819,8 +3908,6 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, rings->cq_ring_entries = p->cq_entries; ctx->sq_mask = rings->sq_ring_mask; ctx->cq_mask = rings->cq_ring_mask; - ctx->sq_entries = rings->sq_ring_entries; - ctx->cq_entries = rings->cq_ring_entries; size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index e25901ae3ff4..80867a1a94f2 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -559,6 +559,7 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, if (PageUptodate(page)) return 0; + ClearPageError(page); do { iomap_adjust_read_range(inode, iop, &block_start, @@ -1040,20 +1041,19 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) lock_page(page); size = i_size_read(inode); - if ((page->mapping != inode->i_mapping) || - (page_offset(page) > size)) { + offset = page_offset(page); + if (page->mapping != inode->i_mapping || offset > size) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } /* page is wholly or partially inside EOF */ - if (((page->index + 1) << PAGE_SHIFT) > size) + if (offset > size - PAGE_SIZE) length = offset_in_page(size); else length = PAGE_SIZE; - offset = page_offset(page); while (length > 0) { ret = iomap_apply(inode, offset, length, IOMAP_WRITE | IOMAP_FAULT, ops, page, diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 7b5f76efef02..8c98fd92bf66 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -377,6 +377,16 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, return iomap_dio_bio_actor(inode, pos, length, dio, iomap); case IOMAP_INLINE: return iomap_dio_inline_actor(inode, pos, length, dio, iomap); + case IOMAP_DELALLOC: + /* + * DIO is not serialised against mmap() access at all, and so + * if the page_mkwrite occurs between the writeback and the + * iomap_apply() call in the DIO path, then it will see the + * DELALLOC block that the page-mkwrite allocated. + */ + pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n", + dio->iocb->ki_filp, current->comm); + return -EIO; default: WARN_ON_ONCE(1); return -EIO; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index c1ce2805c563..b7c5819bfc41 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -96,7 +96,6 @@ EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); EXPORT_SYMBOL(jbd2_inode_cache); -static void __journal_abort_soft (journal_t *journal, int errno); static int jbd2_journal_create_slab(size_t slab_size); #ifdef CONFIG_JBD2_DEBUG @@ -805,7 +804,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, "at offset %lu on %s\n", __func__, blocknr, journal->j_devname); err = -EIO; - __journal_abort_soft(journal, err); + jbd2_journal_abort(journal, err); } } else { *retp = blocknr; /* +journal->j_blk_offset */ @@ -1349,8 +1348,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) int ret; /* Buffer got discarded which means block device got invalidated */ - if (!buffer_mapped(bh)) + if (!buffer_mapped(bh)) { + unlock_buffer(bh); return -EIO; + } trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) @@ -2070,64 +2071,6 @@ int jbd2_journal_wipe(journal_t *journal, int write) return err; } -/* - * Journal abort has very specific semantics, which we describe - * for journal abort. - * - * Two internal functions, which provide abort to the jbd layer - * itself are here. - */ - -/* - * Quick version for internal journal use (doesn't lock the journal). - * Aborts hard --- we mark the abort as occurred, but do _nothing_ else, - * and don't attempt to make any other journal updates. - */ -void __jbd2_journal_abort_hard(journal_t *journal) -{ - transaction_t *transaction; - - if (journal->j_flags & JBD2_ABORT) - return; - - printk(KERN_ERR "Aborting journal on device %s.\n", - journal->j_devname); - - write_lock(&journal->j_state_lock); - journal->j_flags |= JBD2_ABORT; - transaction = journal->j_running_transaction; - if (transaction) - __jbd2_log_start_commit(journal, transaction->t_tid); - write_unlock(&journal->j_state_lock); -} - -/* Soft abort: record the abort error status in the journal superblock, - * but don't do any other IO. */ -static void __journal_abort_soft (journal_t *journal, int errno) -{ - int old_errno; - - write_lock(&journal->j_state_lock); - old_errno = journal->j_errno; - if (!journal->j_errno || errno == -ESHUTDOWN) - journal->j_errno = errno; - - if (journal->j_flags & JBD2_ABORT) { - write_unlock(&journal->j_state_lock); - if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) - jbd2_journal_update_sb_errno(journal); - return; - } - write_unlock(&journal->j_state_lock); - - __jbd2_journal_abort_hard(journal); - - jbd2_journal_update_sb_errno(journal); - write_lock(&journal->j_state_lock); - journal->j_flags |= JBD2_REC_ERR; - write_unlock(&journal->j_state_lock); -} - /** * void jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. @@ -2171,7 +2114,47 @@ static void __journal_abort_soft (journal_t *journal, int errno) void jbd2_journal_abort(journal_t *journal, int errno) { - __journal_abort_soft(journal, errno); + transaction_t *transaction; + + /* + * ESHUTDOWN always takes precedence because a file system check + * caused by any other journal abort error is not required after + * a shutdown triggered. + */ + write_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) { + int old_errno = journal->j_errno; + + write_unlock(&journal->j_state_lock); + if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) { + journal->j_errno = errno; + jbd2_journal_update_sb_errno(journal); + } + return; + } + + /* + * Mark the abort as occurred and start current running transaction + * to release all journaled buffer. + */ + pr_err("Aborting journal on device %s.\n", journal->j_devname); + + journal->j_flags |= JBD2_ABORT; + journal->j_errno = errno; + transaction = journal->j_running_transaction; + if (transaction) + __jbd2_log_start_commit(journal, transaction->t_tid); + write_unlock(&journal->j_state_lock); + + /* + * Record errno to the journal super block, so that fsck and jbd2 + * layer could realise that a filesystem check is needed. + */ + jbd2_journal_update_sb_errno(journal); + + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_REC_ERR; + write_unlock(&journal->j_state_lock); } /** diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index de992a70ddfe..90453309345d 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1983,6 +1983,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) */ static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { + J_ASSERT_JH(jh, jh->b_transaction != NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; jbd2_journal_put_journal_head(jh); @@ -2074,6 +2077,7 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, { struct buffer_head *head; struct buffer_head *bh; + bool has_write_io_error = false; int ret = 0; J_ASSERT(PageLocked(page)); @@ -2098,11 +2102,26 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, jbd_unlock_bh_state(bh); if (buffer_jbd(bh)) goto busy; + + /* + * If we free a metadata buffer which has been failed to + * write out, the jbd2 checkpoint procedure will not detect + * this failure and may lead to filesystem inconsistency + * after cleanup journal tail. + */ + if (buffer_write_io_error(bh)) { + pr_err("JBD2: Error while async write back metadata bh %llu.", + (unsigned long long)bh->b_blocknr); + has_write_io_error = true; + } } while ((bh = bh->b_this_page) != head); ret = try_to_free_buffers(page); busy: + if (has_write_io_error) + jbd2_journal_abort(journal, -EIO); + return ret; } @@ -2530,6 +2549,13 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) was_dirty = test_clear_buffer_jbddirty(bh); __jbd2_journal_temp_unlink_buffer(jh); + + /* + * b_transaction must be set, otherwise the new b_transaction won't + * be holding jh reference + */ + J_ASSERT_JH(jh, jh->b_transaction != NULL); + /* * We set b_transaction here because b_next_transaction will inherit * our jh reference and thus __jbd2_journal_file_buffer() must not diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index f20cff1194bb..776493713153 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -590,10 +590,14 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) int ret; uint32_t now = JFFS2_NOW(); + mutex_lock(&f->sem); for (fd = f->dents ; fd; fd = fd->next) { - if (fd->ino) + if (fd->ino) { + mutex_unlock(&f->sem); return -ENOTEMPTY; + } } + mutex_unlock(&f->sem); ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name, dentry->d_name.len, f, now); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e8c792b49616..c35bbaa19486 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -912,7 +912,7 @@ repeat: } fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, - &name, 0); + NULL, 0); iput(inode); } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 7cb5fd38eb14..7b09a9158e40 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -150,6 +150,25 @@ static int minix_remount (struct super_block * sb, int * flags, char * data) return 0; } +static bool minix_check_superblock(struct super_block *sb) +{ + struct minix_sb_info *sbi = minix_sb(sb); + + if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0) + return false; + + /* + * s_max_size must not exceed the block mapping limitation. This check + * is only needed for V1 filesystems, since V2/V3 support an extra level + * of indirect blocks which places the limit well above U32_MAX. + */ + if (sbi->s_version == MINIX_V1 && + sb->s_maxbytes > (7 + 512 + 512*512) * BLOCK_SIZE) + return false; + + return true; +} + static int minix_fill_super(struct super_block *s, void *data, int silent) { struct buffer_head *bh; @@ -185,7 +204,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) sbi->s_zmap_blocks = ms->s_zmap_blocks; sbi->s_firstdatazone = ms->s_firstdatazone; sbi->s_log_zone_size = ms->s_log_zone_size; - sbi->s_max_size = ms->s_max_size; + s->s_maxbytes = ms->s_max_size; s->s_magic = ms->s_magic; if (s->s_magic == MINIX_SUPER_MAGIC) { sbi->s_version = MINIX_V1; @@ -216,7 +235,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) sbi->s_zmap_blocks = m3s->s_zmap_blocks; sbi->s_firstdatazone = m3s->s_firstdatazone; sbi->s_log_zone_size = m3s->s_log_zone_size; - sbi->s_max_size = m3s->s_max_size; + s->s_maxbytes = m3s->s_max_size; sbi->s_ninodes = m3s->s_ninodes; sbi->s_nzones = m3s->s_zones; sbi->s_dirsize = 64; @@ -228,11 +247,12 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) } else goto out_no_fs; + if (!minix_check_superblock(s)) + goto out_illegal_sb; + /* * Allocate the buffer map to keep the superblock small. */ - if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0) - goto out_illegal_sb; i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh); map = kzalloc(i, GFP_KERNEL); if (!map) @@ -468,6 +488,13 @@ static struct inode *V1_minix_iget(struct inode *inode) iget_failed(inode); return ERR_PTR(-EIO); } + if (raw_inode->i_nlinks == 0) { + printk("MINIX-fs: deleted inode referenced: %lu\n", + inode->i_ino); + brelse(bh); + iget_failed(inode); + return ERR_PTR(-ESTALE); + } inode->i_mode = raw_inode->i_mode; i_uid_write(inode, raw_inode->i_uid); i_gid_write(inode, raw_inode->i_gid); @@ -501,6 +528,13 @@ static struct inode *V2_minix_iget(struct inode *inode) iget_failed(inode); return ERR_PTR(-EIO); } + if (raw_inode->i_nlinks == 0) { + printk("MINIX-fs: deleted inode referenced: %lu\n", + inode->i_ino); + brelse(bh); + iget_failed(inode); + return ERR_PTR(-ESTALE); + } inode->i_mode = raw_inode->i_mode; i_uid_write(inode, raw_inode->i_uid); i_gid_write(inode, raw_inode->i_gid); diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c index 043c3fdbc8e7..446148792f41 100644 --- a/fs/minix/itree_common.c +++ b/fs/minix/itree_common.c @@ -75,6 +75,7 @@ static int alloc_branch(struct inode *inode, int n = 0; int i; int parent = minix_new_block(inode); + int err = -ENOSPC; branch[0].key = cpu_to_block(parent); if (parent) for (n = 1; n < num; n++) { @@ -85,6 +86,11 @@ static int alloc_branch(struct inode *inode, break; branch[n].key = cpu_to_block(nr); bh = sb_getblk(inode->i_sb, parent); + if (!bh) { + minix_free_block(inode, nr); + err = -ENOMEM; + break; + } lock_buffer(bh); memset(bh->b_data, 0, bh->b_size); branch[n].bh = bh; @@ -103,7 +109,7 @@ static int alloc_branch(struct inode *inode, bforget(branch[i].bh); for (i = 0; i < n; i++) minix_free_block(inode, block_to_cpu(branch[i].key)); - return -ENOSPC; + return err; } static inline int splice_branch(struct inode *inode, diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c index 046cc96ee7ad..1fed906042aa 100644 --- a/fs/minix/itree_v1.c +++ b/fs/minix/itree_v1.c @@ -29,12 +29,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) if (block < 0) { printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", block, inode->i_sb->s_bdev); - } else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) { - if (printk_ratelimit()) - printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %pg\n", - block, inode->i_sb->s_bdev); - } else if (block < 7) { + return 0; + } + if ((u64)block * BLOCK_SIZE >= inode->i_sb->s_maxbytes) + return 0; + + if (block < 7) { offsets[n++] = block; } else if ((block -= 7) < 512) { offsets[n++] = 7; diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c index f7fc7ecccccc..9d00f31a2d9d 100644 --- a/fs/minix/itree_v2.c +++ b/fs/minix/itree_v2.c @@ -32,13 +32,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) if (block < 0) { printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", block, sb->s_bdev); - } else if ((u64)block * (u64)sb->s_blocksize >= - minix_sb(sb)->s_max_size) { - if (printk_ratelimit()) - printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %pg\n", - block, sb->s_bdev); - } else if (block < DIRCOUNT) { + return 0; + } + if ((u64)block * (u64)sb->s_blocksize >= sb->s_maxbytes) + return 0; + + if (block < DIRCOUNT) { offsets[n++] = block; } else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) { offsets[n++] = DIRCOUNT; diff --git a/fs/minix/minix.h b/fs/minix/minix.h index df081e8afcc3..168d45d3de73 100644 --- a/fs/minix/minix.h +++ b/fs/minix/minix.h @@ -32,7 +32,6 @@ struct minix_sb_info { unsigned long s_zmap_blocks; unsigned long s_firstdatazone; unsigned long s_log_zone_size; - unsigned long s_max_size; int s_dirsize; int s_namelen; struct buffer_head ** s_imap; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 05ed7be8a634..188b17a3b19e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -553,6 +553,9 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); do { + if (entry->label) + entry->label->len = NFS4_MAXLABELLEN; + status = xdr_decode(desc, entry, &stream); if (status != 0) { if (status == -EAGAIN) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 95dc90570786..387a2cfa7e17 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -140,6 +140,7 @@ static int nfs_file_flush(struct file *file, fl_owner_t id) { struct inode *inode = file_inode(file); + errseq_t since; dprintk("NFS: flush(%pD2)\n", file); @@ -148,7 +149,9 @@ nfs_file_flush(struct file *file, fl_owner_t id) return 0; /* Flush writes to the server and return any errors */ - return nfs_wb_all(inode); + since = filemap_sample_wb_err(file->f_mapping); + nfs_wb_all(inode); + return filemap_check_wb_err(file->f_mapping, since); } ssize_t @@ -580,12 +583,14 @@ static const struct vm_operations_struct nfs_file_vm_ops = { .page_mkwrite = nfs_vm_page_mkwrite, }; -static int nfs_need_check_write(struct file *filp, struct inode *inode) +static int nfs_need_check_write(struct file *filp, struct inode *inode, + int error) { struct nfs_open_context *ctx; ctx = nfs_file_open_context(filp); - if (nfs_ctx_key_to_expire(ctx, inode)) + if (nfs_error_is_fatal_on_server(error) || + nfs_ctx_key_to_expire(ctx, inode)) return 1; return 0; } @@ -596,6 +601,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(file); unsigned long written = 0; ssize_t result; + errseq_t since; + int error; result = nfs_key_timeout_notify(file, inode); if (result) @@ -620,6 +627,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos > i_size_read(inode)) nfs_revalidate_mapping(inode, file->f_mapping); + since = filemap_sample_wb_err(file->f_mapping); nfs_start_io_write(inode); result = generic_write_checks(iocb, from); if (result > 0) { @@ -638,7 +646,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) goto out; /* Return error values */ - if (nfs_need_check_write(file, inode)) { + error = filemap_check_wb_err(file->f_mapping, since); + if (nfs_need_check_write(file, inode, error)) { int err = nfs_wb_all(inode); if (err < 0) result = err; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 5657b7f2611f..1741d902b0d8 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -984,9 +984,8 @@ retry: goto out_mds; /* Use a direct mapping of ds_idx to pgio mirror_idx */ - if (WARN_ON_ONCE(pgio->pg_mirror_count != - FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))) - goto out_mds; + if (pgio->pg_mirror_count != FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)) + goto out_eagain; for (i = 0; i < pgio->pg_mirror_count; i++) { mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); @@ -1008,7 +1007,10 @@ retry: (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) pgio->pg_maxretrans = io_maxretrans; return; - +out_eagain: + pnfs_generic_pg_cleanup(pgio); + pgio->pg_error = -EAGAIN; + return; out_mds: trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode, 0, NFS4_MAX_UINT64, IOMODE_RW, @@ -1018,6 +1020,7 @@ out_mds: pgio->pg_lseg = NULL; pgio->pg_maxretrans = 0; nfs_pageio_reset_write_mds(pgio); + pgio->pg_error = -EAGAIN; } static unsigned int diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 3802c88e8372..6de41f741280 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -826,6 +826,8 @@ int nfs_getattr(const struct path *path, struct kstat *stat, do_update |= cache_validity & NFS_INO_INVALID_ATIME; if (request_mask & (STATX_CTIME|STATX_MTIME)) do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE; + if (request_mask & STATX_BLOCKS) + do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { /* Update the attribute cache */ if (!(server->flags & NFS_MOUNT_NOAC)) @@ -1750,7 +1752,8 @@ out_noforce: status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME - | NFS_INO_INVALID_MTIME); + | NFS_INO_INVALID_MTIME + | NFS_INO_INVALID_BLOCKS); return status; } @@ -1857,7 +1860,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED - | NFS_INO_REVAL_PAGECACHE); + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_INVALID_BLOCKS); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); @@ -2019,8 +2023,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; - else + else { + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_BLOCKS + | NFS_INO_REVAL_FORCED); cache_revalidated = false; + } /* Update attrtimeo value if we're out of the unstable period */ if (attr_changed) { diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index fb55c04cdc6b..534b6fd70ffd 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -109,6 +109,7 @@ static int nfs4_file_flush(struct file *file, fl_owner_t id) { struct inode *inode = file_inode(file); + errseq_t since; dprintk("NFS: flush(%pD2)\n", file); @@ -124,7 +125,9 @@ nfs4_file_flush(struct file *file, fl_owner_t id) return filemap_fdatawrite(file->f_mapping); /* Flush writes to the server and return any errors */ - return nfs_wb_all(inode); + since = filemap_sample_wb_err(file->f_mapping); + nfs_wb_all(inode); + return filemap_check_wb_err(file->f_mapping, since); } #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e257653f25ab..00435556db0c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -774,6 +774,14 @@ static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, slot->seq_nr_last_acked = seqnr; } +static void nfs4_probe_sequence(struct nfs_client *client, const struct cred *cred, + struct nfs4_slot *slot) +{ + struct rpc_task *task = _nfs41_proc_sequence(client, cred, slot, true); + if (!IS_ERR(task)) + rpc_put_task_async(task); +} + static int nfs41_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res) { @@ -790,6 +798,7 @@ static int nfs41_sequence_process(struct rpc_task *task, goto out; session = slot->table->session; + clp = session->clp; trace_nfs4_sequence_done(session, res); @@ -804,7 +813,6 @@ static int nfs41_sequence_process(struct rpc_task *task, nfs4_slot_sequence_acked(slot, slot->seq_nr); /* Update the slot's sequence and clientid lease timer */ slot->seq_done = 1; - clp = session->clp; do_renew_lease(clp, res->sr_timestamp); /* Check sequence flags */ nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags, @@ -852,10 +860,18 @@ static int nfs41_sequence_process(struct rpc_task *task, /* * Were one or more calls using this slot interrupted? * If the server never received the request, then our - * transmitted slot sequence number may be too high. + * transmitted slot sequence number may be too high. However, + * if the server did receive the request then it might + * accidentally give us a reply with a mismatched operation. + * We can sort this out by sending a lone sequence operation + * to the server on the same slot. */ if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) { slot->seq_nr--; + if (task->tk_msg.rpc_proc != &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE]) { + nfs4_probe_sequence(clp, task->tk_msg.rpc_cred, slot); + res->sr_slot = NULL; + } goto retry_nowait; } /* @@ -3241,8 +3257,10 @@ static int _nfs4_do_setattr(struct inode *inode, /* Servers should only apply open mode checks for file size changes */ truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false; - if (!truncate) + if (!truncate) { + nfs4_inode_make_writeable(inode); goto zero_stateid; + } if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) { /* Use that stateid */ @@ -5795,8 +5813,6 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, return ret; if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL)) return -ENOENT; - if (buflen < label.len) - return -ERANGE; return 0; } @@ -7218,7 +7234,12 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, err = nfs4_set_lock_state(state, fl); if (err != 0) return err; - err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); + do { + err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); + if (err != -NFS4ERR_DELAY) + break; + ssleep(1); + } while (err == -NFS4ERR_DELAY); return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err); } @@ -7870,7 +7891,7 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata) } static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = { - .rpc_call_done = &nfs4_bind_one_conn_to_session_done, + .rpc_call_done = nfs4_bind_one_conn_to_session_done, }; /* diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 7c0ff1a3b591..677751bc3a33 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4169,7 +4169,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, return -EIO; if (len < NFS4_MAXLABELLEN) { if (label) { - memcpy(label->label, p, len); + if (label->len) { + if (label->len < len) + return -ERANGE; + memcpy(label->label, p, len); + } label->len = len; label->pi = pi; label->lfs = lfs; diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 361cc10d6f95..c8081d2b4166 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1147,7 +1147,12 @@ TRACE_EVENT(nfs_xdr_status, __field(unsigned int, task_id) __field(unsigned int, client_id) __field(u32, xid) + __field(int, version) __field(unsigned long, error) + __string(program, + xdr->rqst->rq_task->tk_client->cl_program->name) + __string(procedure, + xdr->rqst->rq_task->tk_msg.rpc_proc->p_name) ), TP_fast_assign( @@ -1157,13 +1162,19 @@ TRACE_EVENT(nfs_xdr_status, __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->version = task->tk_client->cl_vers; __entry->error = error; + __assign_str(program, + task->tk_client->cl_program->name) + __assign_str(procedure, task->tk_msg.rpc_proc->p_name) ), TP_printk( - "task:%u@%d xid=0x%08x error=%ld (%s)", + "task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)", __entry->task_id, __entry->client_id, __entry->xid, - -__entry->error, nfs_show_status(__entry->error) + __get_str(program), __entry->version, + __get_str(procedure), -__entry->error, + nfs_show_status(__entry->error) ) ); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index b736912098ee..f4407dd426bf 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -133,47 +133,70 @@ nfs_async_iocounter_wait(struct rpc_task *task, struct nfs_lock_context *l_ctx) EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait); /* - * nfs_page_group_lock - lock the head of the page group - * @req - request in group that is to be locked + * nfs_page_set_headlock - set the request PG_HEADLOCK + * @req: request that is to be locked * - * this lock must be held when traversing or modifying the page - * group list + * this lock must be held when modifying req->wb_head * * return 0 on success, < 0 on error */ int -nfs_page_group_lock(struct nfs_page *req) +nfs_page_set_headlock(struct nfs_page *req) { - struct nfs_page *head = req->wb_head; - - WARN_ON_ONCE(head != head->wb_head); - - if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags)) + if (!test_and_set_bit(PG_HEADLOCK, &req->wb_flags)) return 0; - set_bit(PG_CONTENDED1, &head->wb_flags); + set_bit(PG_CONTENDED1, &req->wb_flags); smp_mb__after_atomic(); - return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, + return wait_on_bit_lock(&req->wb_flags, PG_HEADLOCK, TASK_UNINTERRUPTIBLE); } /* - * nfs_page_group_unlock - unlock the head of the page group - * @req - request in group that is to be unlocked + * nfs_page_clear_headlock - clear the request PG_HEADLOCK + * @req: request that is to be locked */ void -nfs_page_group_unlock(struct nfs_page *req) +nfs_page_clear_headlock(struct nfs_page *req) { - struct nfs_page *head = req->wb_head; - - WARN_ON_ONCE(head != head->wb_head); - smp_mb__before_atomic(); - clear_bit(PG_HEADLOCK, &head->wb_flags); + clear_bit(PG_HEADLOCK, &req->wb_flags); smp_mb__after_atomic(); - if (!test_bit(PG_CONTENDED1, &head->wb_flags)) + if (!test_bit(PG_CONTENDED1, &req->wb_flags)) return; - wake_up_bit(&head->wb_flags, PG_HEADLOCK); + wake_up_bit(&req->wb_flags, PG_HEADLOCK); +} + +/* + * nfs_page_group_lock - lock the head of the page group + * @req: request in group that is to be locked + * + * this lock must be held when traversing or modifying the page + * group list + * + * return 0 on success, < 0 on error + */ +int +nfs_page_group_lock(struct nfs_page *req) +{ + int ret; + + ret = nfs_page_set_headlock(req); + if (ret || req->wb_head == req) + return ret; + return nfs_page_set_headlock(req->wb_head); +} + +/* + * nfs_page_group_unlock - unlock the head of the page group + * @req: request in group that is to be unlocked + */ +void +nfs_page_group_unlock(struct nfs_page *req) +{ + if (req != req->wb_head) + nfs_page_clear_headlock(req->wb_head); + nfs_page_clear_headlock(req); } /* diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 443639cbb0cf..9c2b07ce57b2 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1198,31 +1198,27 @@ out: return status; } +static bool +pnfs_layout_segments_returnable(struct pnfs_layout_hdr *lo, + enum pnfs_iomode iomode, + u32 seq) +{ + struct pnfs_layout_range recall_range = { + .length = NFS4_MAX_UINT64, + .iomode = iomode, + }; + return pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &recall_range, seq) != -EBUSY; +} + /* Return true if layoutreturn is needed */ static bool pnfs_layout_need_return(struct pnfs_layout_hdr *lo) { - struct pnfs_layout_segment *s; - enum pnfs_iomode iomode; - u32 seq; - if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) return false; - - seq = lo->plh_return_seq; - iomode = lo->plh_return_iomode; - - /* Defer layoutreturn until all recalled lsegs are done */ - list_for_each_entry(s, &lo->plh_segs, pls_list) { - if (seq && pnfs_seqid_is_newer(s->pls_seq, seq)) - continue; - if (iomode != IOMODE_ANY && s->pls_range.iomode != iomode) - continue; - if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) - return false; - } - - return true; + return pnfs_layout_segments_returnable(lo, lo->plh_return_iomode, + lo->plh_return_seq); } static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) @@ -2362,16 +2358,6 @@ out_forget: return ERR_PTR(-EAGAIN); } -static int -mark_lseg_invalid_or_return(struct pnfs_layout_segment *lseg, - struct list_head *tmp_list) -{ - if (!mark_lseg_invalid(lseg, tmp_list)) - return 0; - pnfs_cache_lseg_for_layoutreturn(lseg->pls_layout, lseg); - return 1; -} - /** * pnfs_mark_matching_lsegs_return - Free or return matching layout segments * @lo: pointer to layout header @@ -2408,7 +2394,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); - if (mark_lseg_invalid_or_return(lseg, tmp_list)) + if (mark_lseg_invalid(lseg, tmp_list)) continue; remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 58c8317dd7d8..613c3ef23e07 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -425,22 +425,28 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, destroy_list = (subreq->wb_this_page == old_head) ? NULL : subreq->wb_this_page; + /* Note: lock subreq in order to change subreq->wb_head */ + nfs_page_set_headlock(subreq); WARN_ON_ONCE(old_head != subreq->wb_head); /* make sure old group is not used */ subreq->wb_this_page = subreq; + subreq->wb_head = subreq; clear_bit(PG_REMOVE, &subreq->wb_flags); /* Note: races with nfs_page_group_destroy() */ if (!kref_read(&subreq->wb_kref)) { /* Check if we raced with nfs_page_group_destroy() */ - if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) + if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) { + nfs_page_clear_headlock(subreq); nfs_free_request(subreq); + } else + nfs_page_clear_headlock(subreq); continue; } + nfs_page_clear_headlock(subreq); - subreq->wb_head = subreq; nfs_release_request(old_head); if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) { diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 10ec5ecdf117..65c331f75e9c 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -78,6 +78,8 @@ enum { /* Checksum this amount of the request */ #define RC_CSUMLEN (256U) +int nfsd_drc_slab_create(void); +void nfsd_drc_slab_free(void); int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); int nfsd_cache_lookup(struct svc_rqst *); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 3007b8945d38..51c08ae79063 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -133,9 +133,13 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) struct nfsd_file_mark, nfm_mark)); mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); - fsnotify_put_mark(mark); - if (likely(nfm)) + if (nfm) { + fsnotify_put_mark(mark); break; + } + /* Avoid soft lockup race with nfsd_file_mark_put() */ + fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group); + fsnotify_put_mark(mark); } else mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 9a4ef815fb8c..ed53e206a299 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -139,7 +139,6 @@ struct nfsd_net { * Duplicate reply cache */ struct nfsd_drc_bucket *drc_hashtbl; - struct kmem_cache *drc_slab; /* max number of entries allowed in the cache */ unsigned int max_drc_entries; diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index afca3287184b..efe55d101b0e 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1230,6 +1230,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) err = setup_callback_client(clp, &conn, ses); if (err) { nfsd4_mark_cb_down(clp, err); + if (c) + svc_xprt_put(c->cn_xprt); return; } } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8650a97e2ba9..8cb2f744dde6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -495,6 +495,8 @@ find_any_file(struct nfs4_file *f) { struct nfsd_file *ret; + if (!f) + return NULL; spin_lock(&f->fi_lock); ret = __nfs4_get_fd(f, O_RDWR); if (!ret) { @@ -506,6 +508,17 @@ find_any_file(struct nfs4_file *f) return ret; } +static struct nfsd_file *find_deleg_file(struct nfs4_file *f) +{ + struct nfsd_file *ret = NULL; + + spin_lock(&f->fi_lock); + if (f->fi_deleg_file) + ret = nfsd_file_get(f->fi_deleg_file); + spin_unlock(&f->fi_lock); + return ret; +} + static atomic_long_t num_delegations; unsigned long max_delegations; @@ -1262,6 +1275,12 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop) nfs4_free_stateowner(sop); } +static bool +nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp) +{ + return list_empty(&stp->st_perfile); +} + static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp) { struct nfs4_file *fp = stp->st_stid.sc_file; @@ -1332,9 +1351,11 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); + if (!unhash_ol_stateid(stp)) + return false; list_del_init(&stp->st_locks); nfs4_unhash_stid(&stp->st_stid); - return unhash_ol_stateid(stp); + return true; } static void release_lock_stateid(struct nfs4_ol_stateid *stp) @@ -1399,13 +1420,12 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, static bool unhash_open_stateid(struct nfs4_ol_stateid *stp, struct list_head *reaplist) { - bool unhashed; - lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); - unhashed = unhash_ol_stateid(stp); + if (!unhash_ol_stateid(stp)) + return false; release_open_stateid_locks(stp, reaplist); - return unhashed; + return true; } static void release_open_stateid(struct nfs4_ol_stateid *stp) @@ -2378,6 +2398,8 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) oo = ols->st_stateowner; nf = st->sc_file; file = find_any_file(nf); + if (!file) + return 0; seq_printf(s, "- 0x%16phN: { type: open, ", &st->sc_stateid); @@ -2411,6 +2433,8 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) oo = ols->st_stateowner; nf = st->sc_file; file = find_any_file(nf); + if (!file) + return 0; seq_printf(s, "- 0x%16phN: { type: lock, ", &st->sc_stateid); @@ -2439,7 +2463,9 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) ds = delegstateid(st); nf = st->sc_file; - file = nf->fi_deleg_file; + file = find_deleg_file(nf); + if (!file) + return 0; seq_printf(s, "- 0x%16phN: { type: deleg, ", &st->sc_stateid); @@ -2451,6 +2477,7 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) nfs4_show_superblock(s, file); seq_printf(s, " }\n"); + nfsd_file_put(file); return 0; } @@ -6249,21 +6276,21 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, } static struct nfs4_ol_stateid * -find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp) +find_lock_stateid(const struct nfs4_lockowner *lo, + const struct nfs4_ol_stateid *ost) { struct nfs4_ol_stateid *lst; - struct nfs4_client *clp = lo->lo_owner.so_client; - lockdep_assert_held(&clp->cl_lock); + lockdep_assert_held(&ost->st_stid.sc_client->cl_lock); - list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) { - if (lst->st_stid.sc_type != NFS4_LOCK_STID) - continue; - if (lst->st_stid.sc_file == fp) { - refcount_inc(&lst->st_stid.sc_count); - return lst; + /* If ost is not hashed, ost->st_locks will not be valid */ + if (!nfs4_ol_stateid_unhashed(ost)) + list_for_each_entry(lst, &ost->st_locks, st_locks) { + if (lst->st_stateowner == &lo->lo_owner) { + refcount_inc(&lst->st_stid.sc_count); + return lst; + } } - } return NULL; } @@ -6279,11 +6306,11 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); retry: spin_lock(&clp->cl_lock); - spin_lock(&fp->fi_lock); - retstp = find_lock_stateid(lo, fp); + if (nfs4_ol_stateid_unhashed(open_stp)) + goto out_close; + retstp = find_lock_stateid(lo, open_stp); if (retstp) - goto out_unlock; - + goto out_found; refcount_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = NFS4_LOCK_STID; stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); @@ -6292,22 +6319,26 @@ retry: stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + spin_lock(&fp->fi_lock); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); -out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&clp->cl_lock); - if (retstp) { - if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { - nfs4_put_stid(&retstp->st_stid); - goto retry; - } - /* To keep mutex tracking happy */ - mutex_unlock(&stp->st_mutex); - stp = retstp; - } return stp; +out_found: + spin_unlock(&clp->cl_lock); + if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { + nfs4_put_stid(&retstp->st_stid); + goto retry; + } + /* To keep mutex tracking happy */ + mutex_unlock(&stp->st_mutex); + return retstp; +out_close: + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + return NULL; } static struct nfs4_ol_stateid * @@ -6322,7 +6353,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, *new = false; spin_lock(&clp->cl_lock); - lst = find_lock_stateid(lo, fi); + lst = find_lock_stateid(lo, ost); spin_unlock(&clp->cl_lock); if (lst != NULL) { if (nfsd4_lock_ol_stateid(lst) == nfs_ok) @@ -7705,9 +7736,14 @@ nfs4_state_start_net(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; - ret = nfs4_state_create_net(net); + ret = get_nfsdfs(net); if (ret) return ret; + ret = nfs4_state_create_net(net); + if (ret) { + mntput(nn->nfsd_mnt); + return ret; + } locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) @@ -7776,6 +7812,7 @@ nfs4_state_shutdown_net(struct net *net) nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); + mntput(nn->nfsd_mnt); } void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 533d0fc3c96b..d6f244559e75 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3530,17 +3530,17 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, u32 zzz = 0; int pad; + /* + * svcrdma requires every READ payload to start somewhere + * in xdr->pages. + */ + if (xdr->iov == xdr->buf->head) { + xdr->iov = NULL; + xdr->end = xdr->p; + } + len = maxcount; v = 0; - - thislen = min_t(long, len, ((void *)xdr->end - (void *)xdr->p)); - p = xdr_reserve_space(xdr, (thislen+3)&~3); - WARN_ON_ONCE(!p); - resp->rqstp->rq_vec[v].iov_base = p; - resp->rqstp->rq_vec[v].iov_len = thislen; - v++; - len -= thislen; - while (len) { thislen = min_t(long, len, PAGE_SIZE); p = xdr_reserve_space(xdr, (thislen+3)&~3); @@ -3559,6 +3559,8 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, read->rd_length = maxcount; if (nfserr) return nfserr; + if (svc_encode_read_payload(resp->rqstp, starting_len + 8, maxcount)) + return nfserr_io; xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3)); tmp = htonl(eof); diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 96352ab7bd81..4a258065188e 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -36,6 +36,8 @@ struct nfsd_drc_bucket { spinlock_t cache_lock; }; +static struct kmem_cache *drc_slab; + static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc); @@ -95,7 +97,7 @@ nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, { struct svc_cacherep *rp; - rp = kmem_cache_alloc(nn->drc_slab, GFP_KERNEL); + rp = kmem_cache_alloc(drc_slab, GFP_KERNEL); if (rp) { rp->c_state = RC_UNUSED; rp->c_type = RC_NOCACHE; @@ -129,7 +131,7 @@ nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, atomic_dec(&nn->num_drc_entries); nn->drc_mem_usage -= sizeof(*rp); } - kmem_cache_free(nn->drc_slab, rp); + kmem_cache_free(drc_slab, rp); } static void @@ -141,6 +143,18 @@ nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, spin_unlock(&b->cache_lock); } +int nfsd_drc_slab_create(void) +{ + drc_slab = kmem_cache_create("nfsd_drc", + sizeof(struct svc_cacherep), 0, 0, NULL); + return drc_slab ? 0: -ENOMEM; +} + +void nfsd_drc_slab_free(void) +{ + kmem_cache_destroy(drc_slab); +} + int nfsd_reply_cache_init(struct nfsd_net *nn) { unsigned int hashsize; @@ -159,18 +173,13 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) if (status) goto out_nomem; - nn->drc_slab = kmem_cache_create("nfsd_drc", - sizeof(struct svc_cacherep), 0, 0, NULL); - if (!nn->drc_slab) - goto out_shrinker; - nn->drc_hashtbl = kcalloc(hashsize, sizeof(*nn->drc_hashtbl), GFP_KERNEL); if (!nn->drc_hashtbl) { nn->drc_hashtbl = vzalloc(array_size(hashsize, sizeof(*nn->drc_hashtbl))); if (!nn->drc_hashtbl) - goto out_slab; + goto out_shrinker; } for (i = 0; i < hashsize; i++) { @@ -180,8 +189,6 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) nn->drc_hashsize = hashsize; return 0; -out_slab: - kmem_cache_destroy(nn->drc_slab); out_shrinker: unregister_shrinker(&nn->nfsd_reply_cache_shrinker); out_nomem: @@ -209,8 +216,6 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) nn->drc_hashtbl = NULL; nn->drc_hashsize = 0; - kmem_cache_destroy(nn->drc_slab); - nn->drc_slab = NULL; } /* @@ -464,8 +469,7 @@ found_entry: rtn = RC_REPLY; break; default: - printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type); - nfsd_reply_cache_free_locked(b, rp, nn); + WARN_ONCE(1, "nfsd: bad repcache type %d\n", rp->c_type); } goto out; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index d77c5261c03c..be418fccc9d8 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1335,6 +1335,7 @@ void nfsd_client_rmdir(struct dentry *dentry) WARN_ON_ONCE(ret); fsnotify_rmdir(dir, dentry); d_delete(dentry); + dput(dentry); inode_unlock(dir); } @@ -1424,6 +1425,18 @@ static struct file_system_type nfsd_fs_type = { }; MODULE_ALIAS_FS("nfsd"); +int get_nfsdfs(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct vfsmount *mnt; + + mnt = vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL); + if (IS_ERR(mnt)) + return PTR_ERR(mnt); + nn->nfsd_mnt = mnt; + return 0; +} + #ifdef CONFIG_PROC_FS static int create_proc_exports_entry(void) { @@ -1452,7 +1465,6 @@ unsigned int nfsd_net_id; static __net_init int nfsd_init_net(struct net *net) { int retval; - struct vfsmount *mnt; struct nfsd_net *nn = net_generic(net, nfsd_net_id); retval = nfsd_export_init(net); @@ -1479,16 +1491,8 @@ static __net_init int nfsd_init_net(struct net *net) init_waitqueue_head(&nn->ntf_wq); seqlock_init(&nn->boot_lock); - mnt = vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL); - if (IS_ERR(mnt)) { - retval = PTR_ERR(mnt); - goto out_mount_err; - } - nn->nfsd_mnt = mnt; return 0; -out_mount_err: - nfsd_reply_cache_shutdown(nn); out_drc_error: nfsd_idmap_shutdown(net); out_idmap_error: @@ -1501,7 +1505,6 @@ static __net_exit void nfsd_exit_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - mntput(nn->nfsd_mnt); nfsd_reply_cache_shutdown(nn); nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); @@ -1534,6 +1537,9 @@ static int __init init_nfsd(void) goto out_free_slabs; nfsd_fault_inject_init(); /* nfsd fault injection controls */ nfsd_stat_init(); /* Statistics */ + retval = nfsd_drc_slab_create(); + if (retval) + goto out_free_stat; nfsd_lockd_init(); /* lockd->nfsd callbacks */ retval = create_proc_exports_entry(); if (retval) @@ -1547,6 +1553,8 @@ out_free_all: remove_proc_entry("fs/nfs", NULL); out_free_lockd: nfsd_lockd_shutdown(); + nfsd_drc_slab_free(); +out_free_stat: nfsd_stat_shutdown(); nfsd_fault_inject_cleanup(); nfsd4_exit_pnfs(); @@ -1561,6 +1569,7 @@ out_unregister_pernet: static void __exit exit_nfsd(void) { + nfsd_drc_slab_free(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); nfsd_stat_shutdown(); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index af2947551e9c..4ff0c5318a02 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -87,6 +87,8 @@ int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_destroy(struct net *net); +int get_nfsdfs(struct net *); + struct nfsdfs_client { struct kref cl_ref; void (*cl_release)(struct kref *kref); @@ -97,6 +99,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, struct nfsdfs_client *ncl, u32 id, const struct tree_descr *); void nfsd_client_rmdir(struct dentry *dentry); + #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL extern const struct svc_version nfsd_acl_version2; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index ffc78a0e28b2..b073bdc2e6e8 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -228,7 +228,7 @@ TRACE_EVENT(nfsd_file_acquire, TP_ARGS(rqstp, hash, inode, may_flags, nf, status), TP_STRUCT__entry( - __field(__be32, xid) + __field(u32, xid) __field(unsigned int, hash) __field(void *, inode) __field(unsigned int, may_flags) @@ -236,11 +236,11 @@ TRACE_EVENT(nfsd_file_acquire, __field(unsigned long, nf_flags) __field(unsigned char, nf_may) __field(struct file *, nf_file) - __field(__be32, status) + __field(u32, status) ), TP_fast_assign( - __entry->xid = rqstp->rq_xid; + __entry->xid = be32_to_cpu(rqstp->rq_xid); __entry->hash = hash; __entry->inode = inode; __entry->may_flags = may_flags; @@ -248,15 +248,15 @@ TRACE_EVENT(nfsd_file_acquire, __entry->nf_flags = nf ? nf->nf_flags : 0; __entry->nf_may = nf ? nf->nf_may : 0; __entry->nf_file = nf ? nf->nf_file : NULL; - __entry->status = status; + __entry->status = be32_to_cpu(status); ), TP_printk("xid=0x%x hash=0x%x inode=0x%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=0x%p status=%u", - be32_to_cpu(__entry->xid), __entry->hash, __entry->inode, + __entry->xid, __entry->hash, __entry->inode, show_nf_may(__entry->may_flags), __entry->nf_ref, show_nf_flags(__entry->nf_flags), show_nf_may(__entry->nf_may), __entry->nf_file, - be32_to_cpu(__entry->status)) + __entry->status) ); DECLARE_EVENT_CLASS(nfsd_file_search_class, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 005d1802ab40..b6f4b552c9af 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1184,6 +1184,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode = 0; iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type; + if (!IS_POSIXACL(dirp)) + iap->ia_mode &= ~current_umask(); + err = 0; host_err = 0; switch (type) { @@ -1416,6 +1419,9 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; } + if (!IS_POSIXACL(dirp)) + iap->ia_mode &= ~current_umask(); + host_err = vfs_create(dirp, dchild, iap->ia_mode, true); if (host_err < 0) { fh_drop_write(fhp); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index d4359a1df3d5..84933a0af49b 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1809,6 +1809,12 @@ int ntfs_read_inode_mount(struct inode *vi) brelse(bh); } + if (le32_to_cpu(m->bytes_allocated) != vol->mft_record_size) { + ntfs_error(sb, "Incorrect mft record size %u in superblock, should be %u.", + le32_to_cpu(m->bytes_allocated), vol->mft_record_size); + goto err_out; + } + /* Apply the mst fixups. */ if (post_read_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size)) { /* FIXME: Try to use the $MFTMirr now. */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 8a2e284ccfcd..50a863fc1779 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -689,6 +689,12 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res, &ocfs2_nfs_sync_lops, osb); } +static void ocfs2_nfs_sync_lock_init(struct ocfs2_super *osb) +{ + ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); + init_rwsem(&osb->nfs_sync_rwlock); +} + void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb) { struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres; @@ -2855,14 +2861,25 @@ int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex) if (ocfs2_is_hard_readonly(osb)) return -EROFS; + if (ex) + down_write(&osb->nfs_sync_rwlock); + else + down_read(&osb->nfs_sync_rwlock); + if (ocfs2_mount_local(osb)) return 0; status = ocfs2_cluster_lock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE, 0, 0); - if (status < 0) + if (status < 0) { mlog(ML_ERROR, "lock on nfs sync lock failed %d\n", status); + if (ex) + up_write(&osb->nfs_sync_rwlock); + else + up_read(&osb->nfs_sync_rwlock); + } + return status; } @@ -2873,6 +2890,10 @@ void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex) if (!ocfs2_mount_local(osb)) ocfs2_cluster_unlock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE); + if (ex) + up_write(&osb->nfs_sync_rwlock); + else + up_read(&osb->nfs_sync_rwlock); } int ocfs2_trim_fs_lock(struct ocfs2_super *osb, @@ -3340,7 +3361,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) local: ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb); ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb); - ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); + ocfs2_nfs_sync_lock_init(osb); ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb); osb->cconn = conn; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 9150cfa4df7d..0a8cd8e59a92 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -326,8 +326,8 @@ struct ocfs2_super spinlock_t osb_lock; u32 s_next_generation; unsigned long osb_flags; - s16 s_inode_steal_slot; - s16 s_meta_steal_slot; + u16 s_inode_steal_slot; + u16 s_meta_steal_slot; atomic_t s_num_inodes_stolen; atomic_t s_num_meta_stolen; @@ -394,6 +394,7 @@ struct ocfs2_super struct ocfs2_lock_res osb_super_lockres; struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; + struct rw_semaphore nfs_sync_rwlock; struct ocfs2_lock_res osb_trim_fs_lockres; struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 0db4a7ec58a2..dcef83c8796d 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -290,7 +290,7 @@ #define OCFS2_MAX_SLOTS 255 /* Slot map indicator for an empty slot */ -#define OCFS2_INVALID_SLOT -1 +#define OCFS2_INVALID_SLOT ((u16)-1) #define OCFS2_VOL_UUID_LEN 16 #define OCFS2_MAX_VOL_LABEL_LEN 64 @@ -326,8 +326,8 @@ struct ocfs2_system_inode_info { enum { BAD_BLOCK_SYSTEM_INODE = 0, GLOBAL_INODE_ALLOC_SYSTEM_INODE, +#define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE, -#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE HEARTBEAT_SYSTEM_INODE, GLOBAL_BITMAP_SYSTEM_INODE, USER_QUOTA_SYSTEM_INODE, diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 69c21a3843af..5e0eaea47405 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -879,9 +879,9 @@ static void __ocfs2_set_steal_slot(struct ocfs2_super *osb, int slot, int type) { spin_lock(&osb->osb_lock); if (type == INODE_ALLOC_SYSTEM_INODE) - osb->s_inode_steal_slot = slot; + osb->s_inode_steal_slot = (u16)slot; else if (type == EXTENT_ALLOC_SYSTEM_INODE) - osb->s_meta_steal_slot = slot; + osb->s_meta_steal_slot = (u16)slot; spin_unlock(&osb->osb_lock); } @@ -2827,9 +2827,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res) goto bail; } - inode_alloc_inode = - ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE, - suballoc_slot); + if (suballoc_slot == (u16)OCFS2_INVALID_SLOT) + inode_alloc_inode = ocfs2_get_system_file_inode(osb, + GLOBAL_INODE_ALLOC_SYSTEM_INODE, suballoc_slot); + else + inode_alloc_inode = ocfs2_get_system_file_inode(osb, + INODE_ALLOC_SYSTEM_INODE, suballoc_slot); if (!inode_alloc_inode) { /* the error code could be inaccurate, but we are not able to * get the correct one. */ diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index c81e86c62380..70d8857b161d 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -78,7 +78,7 @@ struct mount_options unsigned long commit_interval; unsigned long mount_opt; unsigned int atime_quantum; - signed short slot; + unsigned short slot; int localalloc_opt; unsigned int resv_level; int dir_resv_level; @@ -1334,7 +1334,7 @@ static int ocfs2_parse_options(struct super_block *sb, goto bail; } if (option) - mopt->slot = (s16)option; + mopt->slot = (u16)option; break; case Opt_commit: if (match_int(&args[0], &option)) { diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index a5612abc0936..bcd4fd5ad175 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -311,23 +311,8 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { int ret; - struct orangefs_read_options *ro; - orangefs_stats.reads++; - /* - * Remember how they set "count" in read(2) or pread(2) or whatever - - * users can use count as a knob to control orangefs io size and later - * we can try to help them fill as many pages as possible in readpage. - */ - if (!iocb->ki_filp->private_data) { - iocb->ki_filp->private_data = kmalloc(sizeof *ro, GFP_KERNEL); - if (!iocb->ki_filp->private_data) - return(ENOMEM); - ro = iocb->ki_filp->private_data; - ro->blksiz = iter->count; - } - down_read(&file_inode(iocb->ki_filp)->i_rwsem); ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp)); if (ret) @@ -615,12 +600,6 @@ static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl) return rc; } -static int orangefs_file_open(struct inode * inode, struct file *file) -{ - file->private_data = NULL; - return generic_file_open(inode, file); -} - static int orangefs_flush(struct file *file, fl_owner_t id) { /* @@ -634,9 +613,6 @@ static int orangefs_flush(struct file *file, fl_owner_t id) struct inode *inode = file->f_mapping->host; int r; - kfree(file->private_data); - file->private_data = NULL; - if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); inode->i_state &= ~I_DIRTY_TIME; @@ -659,7 +635,7 @@ const struct file_operations orangefs_file_operations = { .lock = orangefs_lock, .unlocked_ioctl = orangefs_ioctl, .mmap = orangefs_file_mmap, - .open = orangefs_file_open, + .open = generic_file_open, .flush = orangefs_flush, .release = orangefs_file_release, .fsync = orangefs_fsync, diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index efb12197da18..636892ffec0b 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -259,46 +259,19 @@ static int orangefs_readpage(struct file *file, struct page *page) pgoff_t index; /* which page */ struct page *next_page; char *kaddr; - struct orangefs_read_options *ro = file->private_data; loff_t read_size; - loff_t roundedup; int buffer_index = -1; /* orangefs shared memory slot */ int slot_index; /* index into slot */ int remaining; /* - * If they set some miniscule size for "count" in read(2) - * (for example) then let's try to read a page, or the whole file - * if it is smaller than a page. Once "count" goes over a page - * then lets round up to the highest page size multiple that is - * less than or equal to "count" and do that much orangefs IO and - * try to fill as many pages as we can from it. - * - * "count" should be represented in ro->blksiz. - * - * inode->i_size = file size. + * Get up to this many bytes from Orangefs at a time and try + * to fill them into the page cache at once. Tests with dd made + * this seem like a reasonable static number, if there was + * interest perhaps this number could be made setable through + * sysfs... */ - if (ro) { - if (ro->blksiz < PAGE_SIZE) { - if (inode->i_size < PAGE_SIZE) - read_size = inode->i_size; - else - read_size = PAGE_SIZE; - } else { - roundedup = ((PAGE_SIZE - 1) & ro->blksiz) ? - ((ro->blksiz + PAGE_SIZE) & ~(PAGE_SIZE -1)) : - ro->blksiz; - if (roundedup > inode->i_size) - read_size = inode->i_size; - else - read_size = roundedup; - - } - } else { - read_size = PAGE_SIZE; - } - if (!read_size) - read_size = PAGE_SIZE; + read_size = 524288; if (PageDirty(page)) orangefs_launder_page(page); diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 34a6c99fa29b..3003007681a0 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -239,10 +239,6 @@ struct orangefs_write_range { kgid_t gid; }; -struct orangefs_read_options { - ssize_t blksiz; -}; - extern struct orangefs_stats orangefs_stats; /* diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 73c9775215b3..11dd8177770d 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -482,7 +482,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb, if (IS_ERR_OR_NULL(this)) return this; - if (WARN_ON(ovl_dentry_real_at(this, layer->idx) != real)) { + if (ovl_dentry_real_at(this, layer->idx) != real) { dput(this); this = ERR_PTR(-EIO); } diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 15e4fa288475..7a08a576f7b2 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -21,13 +21,16 @@ static char ovl_whatisit(struct inode *inode, struct inode *realinode) return 'm'; } +/* No atime modificaton nor notify on underlying */ +#define OVL_OPEN_FLAGS (O_NOATIME | FMODE_NONOTIFY) + static struct file *ovl_open_realfile(const struct file *file, struct inode *realinode) { struct inode *inode = file_inode(file); struct file *realfile; const struct cred *old_cred; - int flags = file->f_flags | O_NOATIME | FMODE_NONOTIFY; + int flags = file->f_flags | OVL_OPEN_FLAGS; old_cred = ovl_override_creds(inode->i_sb); realfile = open_with_fake_path(&file->f_path, flags, realinode, @@ -48,8 +51,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags) struct inode *inode = file_inode(file); int err; - /* No atime modificaton on underlying */ - flags |= O_NOATIME | FMODE_NONOTIFY; + flags |= OVL_OPEN_FLAGS; /* If some flag changed that cannot be changed then something's amiss */ if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK)) @@ -102,7 +104,7 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, } /* Did the flags change since open? */ - if (unlikely((file->f_flags ^ real->file->f_flags) & ~O_NOATIME)) + if (unlikely((file->f_flags ^ real->file->f_flags) & ~OVL_OPEN_FLAGS)) return ovl_change_flags(real->file, file->f_flags); return 0; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 7621ff176d15..d6b724beb304 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1258,6 +1258,18 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) if (!ofs->config.nfs_export && !ofs->upper_mnt) return true; + /* + * We allow using single lower with null uuid for index and nfs_export + * for example to support those features with single lower squashfs. + * To avoid regressions in setups of overlay with re-formatted lower + * squashfs, do not allow decoding origin with lower null uuid unless + * user opted-in to one of the new features that require following the + * lower inode of non-dir upper. + */ + if (!ofs->config.index && !ofs->config.metacopy && !ofs->config.xino && + uuid_is_null(uuid)) + return false; + for (i = 0; i < ofs->numlowerfs; i++) { /* * We use uuid to associate an overlay lower file handle with a @@ -1344,14 +1356,23 @@ static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs, if (err < 0) goto out; + /* + * Check if lower root conflicts with this overlay layers before + * checking if it is in-use as upperdir/workdir of "another" + * mount, because we do not bother to check in ovl_is_inuse() if + * the upperdir/workdir is in fact in-use by our + * upperdir/workdir. + */ err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir"); if (err) goto out; if (ovl_is_inuse(stack[i].dentry)) { err = ovl_report_in_use(ofs, "lowerdir"); - if (err) + if (err) { + iput(trap); goto out; + } } mnt = clone_private_mount(&stack[i]); diff --git a/fs/proc/base.c b/fs/proc/base.c index ebea9501afb8..b690074e65ff 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -403,11 +403,11 @@ print0: static int lock_trace(struct task_struct *task) { - int err = mutex_lock_killable(&task->signal->cred_guard_mutex); + int err = mutex_lock_killable(&task->signal->exec_update_mutex); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); return -EPERM; } return 0; @@ -415,7 +415,7 @@ static int lock_trace(struct task_struct *task) static void unlock_trace(struct task_struct *task) { - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); } #ifdef CONFIG_STACKTRACE @@ -1036,7 +1036,6 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { - static DEFINE_MUTEX(oom_adj_mutex); struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; @@ -1076,7 +1075,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) struct task_struct *p = find_lock_task_mm(task); if (p) { - if (atomic_read(&p->mm->mm_users) > 1) { + if (test_bit(MMF_MULTIPROCESS, &p->mm->flags)) { mm = p->mm; mmgrab(mm); } @@ -2770,7 +2769,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh unsigned long flags; int result; - result = mutex_lock_killable(&task->signal->cred_guard_mutex); + result = mutex_lock_killable(&task->signal->exec_update_mutex); if (result) return result; @@ -2806,7 +2805,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh result = 0; out_unlock: - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); return result; } diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index cdf5b8ae2583..74a60bae2b23 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -275,6 +275,9 @@ static int pstore_compress(const void *in, void *out, { int ret; + if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION)) + return -EINVAL; + ret = crypto_comp_compress(tfm, in, inlen, out, &outlen); if (ret) { pr_err("crypto_comp_compress failed, ret = %d!\n", ret); @@ -661,7 +664,7 @@ static void decompress_record(struct pstore_record *record) int unzipped_len; char *unzipped, *workspace; - if (!record->compressed) + if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION) || !record->compressed) return; /* Only PSTORE_TYPE_DMESG support compression. */ diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 53429c29c784..276c27fb9928 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -284,6 +284,7 @@ static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot) d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); + d->dqb_pad = 0; if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 414695454956..355523f4a4bf 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -224,7 +224,7 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, if (!pages) goto out_free; - nr = find_get_pages(inode->i_mapping, &pgoff, lpages, pages); + nr = find_get_pages_contig(inode->i_mapping, pgoff, lpages, pages); if (nr != lpages) goto out_free_pages; /* leave if some pages were missing */ diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 6419e6dacc39..ac35ddf0dd60 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1553,11 +1553,7 @@ void reiserfs_read_locked_inode(struct inode *inode, * set version 1, version 2 could be used too, because stat data * key is the same in both versions */ - key.version = KEY_FORMAT_3_5; - key.on_disk_key.k_dir_id = dirino; - key.on_disk_key.k_objectid = inode->i_ino; - key.on_disk_key.k_offset = 0; - key.on_disk_key.k_type = 0; + _make_cpu_key(&key, KEY_FORMAT_3_5, dirino, inode->i_ino, 0, 0, 3); /* look for the object's stat data */ retval = search_item(inode->i_sb, &key, &path_to_sd); @@ -2165,7 +2161,8 @@ out_end_trans: out_inserted_sd: clear_nlink(inode); th->t_trans_id = 0; /* so the caller can't use this handle later */ - unlock_new_inode(inode); /* OK to do even if we hadn't locked it */ + if (inode->i_state & I_NEW) + unlock_new_inode(inode); iput(inode); return err; } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index a6bce5b1fb1d..1b9c7a387dc7 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1258,6 +1258,10 @@ static int reiserfs_parse_options(struct super_block *s, "turned on."); return 0; } + if (qf_names[qtype] != + REISERFS_SB(s)->s_qf_names[qtype]) + kfree(qf_names[qtype]); + qf_names[qtype] = NULL; if (*arg) { /* Some filename specified? */ if (REISERFS_SB(s)->s_qf_names[qtype] && strcmp(REISERFS_SB(s)->s_qf_names[qtype], @@ -1287,10 +1291,6 @@ static int reiserfs_parse_options(struct super_block *s, else *mount_options |= 1 << REISERFS_GRPQUOTA; } else { - if (qf_names[qtype] != - REISERFS_SB(s)->s_qf_names[qtype]) - kfree(qf_names[qtype]); - qf_names[qtype] = NULL; if (qtype == USRQUOTA) *mount_options &= ~(1 << REISERFS_USRQUOTA); else diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 28b241cd6987..fe63a7c3e0da 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -674,6 +674,13 @@ reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer, if (get_inode_sd_version(inode) == STAT_DATA_V1) return -EOPNOTSUPP; + /* + * priv_root needn't be initialized during mount so allow initial + * lookups to succeed. + */ + if (!REISERFS_SB(inode->i_sb)->priv_root) + return 0; + dentry = xattr_lookup(inode, name, XATTR_REPLACE); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c index 6b2b4362089e..b57b3ffcbc32 100644 --- a/fs/romfs/storage.c +++ b/fs/romfs/storage.c @@ -217,10 +217,8 @@ int romfs_dev_read(struct super_block *sb, unsigned long pos, size_t limit; limit = romfs_maxsize(sb); - if (pos >= limit) + if (pos >= limit || buflen > limit - pos) return -EIO; - if (buflen > limit - pos) - buflen = limit - pos; #ifdef CONFIG_ROMFS_ON_MTD if (sb->s_mtd) diff --git a/fs/signalfd.c b/fs/signalfd.c index 44b6845b071c..5b78719be445 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -314,9 +314,10 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, { sigset_t mask; - if (sizemask != sizeof(sigset_t) || - copy_from_user(&mask, user_mask, sizeof(mask))) + if (sizemask != sizeof(sigset_t)) return -EINVAL; + if (copy_from_user(&mask, user_mask, sizeof(mask))) + return -EFAULT; return do_signalfd4(ufd, &mask, flags); } @@ -325,9 +326,10 @@ SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask, { sigset_t mask; - if (sizemask != sizeof(sigset_t) || - copy_from_user(&mask, user_mask, sizeof(mask))) + if (sizemask != sizeof(sigset_t)) return -EINVAL; + if (copy_from_user(&mask, user_mask, sizeof(mask))) + return -EFAULT; return do_signalfd4(ufd, &mask, 0); } diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 8ceb51478800..7e4bfaf2871f 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -225,7 +225,7 @@ int ubifs_is_mapped(const struct ubifs_info *c, int lnum) int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, int offs, int quiet, int must_chk_crc) { - int err = -EINVAL, type, node_len; + int err = -EINVAL, type, node_len, dump_node = 1; uint32_t crc, node_crc, magic; const struct ubifs_ch *ch = buf; @@ -278,10 +278,22 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, out_len: if (!quiet) ubifs_err(c, "bad node length %d", node_len); + if (type == UBIFS_DATA_NODE && node_len > UBIFS_DATA_NODE_SZ) + dump_node = 0; out: if (!quiet) { ubifs_err(c, "bad node at LEB %d:%d", lnum, offs); - ubifs_dump_node(c, buf); + if (dump_node) { + ubifs_dump_node(c, buf); + } else { + int safe_len = min3(node_len, c->leb_size - offs, + (int)UBIFS_MAX_DATA_NODE_SZ); + pr_err("\tprevent out-of-bounds memory access\n"); + pr_err("\ttruncated data node length %d\n", safe_len); + pr_err("\tcorrupted data node:\n"); + print_hex_dump(KERN_ERR, "\t", DUMP_PREFIX_OFFSET, 32, 1, + buf, safe_len, 0); + } dump_stack(); } return err; diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 826dad0243dc..5f2ac5ef0891 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -539,7 +539,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, const struct fscrypt_name *nm, const struct inode *inode, int deletion, int xent) { - int err, dlen, ilen, len, lnum, ino_offs, dent_offs; + int err, dlen, ilen, len, lnum, ino_offs, dent_offs, orphan_added = 0; int aligned_dlen, aligned_ilen, sync = IS_DIRSYNC(dir); int last_reference = !!(deletion && inode->i_nlink == 0); struct ubifs_inode *ui = ubifs_inode(inode); @@ -630,6 +630,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, goto out_finish; } ui->del_cmtno = c->cmt_no; + orphan_added = 1; } err = write_head(c, BASEHD, dent, len, &lnum, &dent_offs, sync); @@ -702,7 +703,7 @@ out_release: kfree(dent); out_ro: ubifs_ro_mode(c, err); - if (last_reference) + if (orphan_added) ubifs_delete_orphan(c, inode->i_ino); finish_reservation(c); return err; @@ -905,6 +906,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) ubifs_err(c, "dead directory entry '%s', error %d", xent->name, err); ubifs_ro_mode(c, err); + kfree(xent); goto out_release; } ubifs_assert(c, ubifs_inode(xino)->xattr); @@ -1217,7 +1219,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, void *p; union ubifs_key key; struct ubifs_dent_node *dent, *dent2; - int err, dlen1, dlen2, ilen, lnum, offs, len; + int err, dlen1, dlen2, ilen, lnum, offs, len, orphan_added = 0; int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ; int last_reference = !!(new_inode && new_inode->i_nlink == 0); int move = (old_dir != new_dir); @@ -1333,6 +1335,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, goto out_finish; } new_ui->del_cmtno = c->cmt_no; + orphan_added = 1; } err = write_head(c, BASEHD, dent, len, &lnum, &offs, sync); @@ -1414,7 +1417,7 @@ out_release: release_head(c, BASEHD); out_ro: ubifs_ro_mode(c, err); - if (last_reference) + if (orphan_added) ubifs_delete_orphan(c, new_inode->i_ino); out_finish: finish_reservation(c); diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 7dd740e3692d..283f9eb48410 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -157,7 +157,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) int err = 0; ino_t xattr_inum; union ubifs_key key; - struct ubifs_dent_node *xent; + struct ubifs_dent_node *xent, *pxent = NULL; struct fscrypt_name nm = {0}; struct ubifs_orphan *xattr_orphan; struct ubifs_orphan *orphan; @@ -181,11 +181,16 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) xattr_inum = le64_to_cpu(xent->inum); xattr_orphan = orphan_add(c, xattr_inum, orphan); - if (IS_ERR(xattr_orphan)) + if (IS_ERR(xattr_orphan)) { + kfree(xent); return PTR_ERR(xattr_orphan); + } + kfree(pxent); + pxent = xent; key_read(c, &xent->key, &key); } + kfree(pxent); return 0; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index ea80036d7897..97a192eb9949 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -139,21 +139,24 @@ void udf_evict_inode(struct inode *inode) struct udf_inode_info *iinfo = UDF_I(inode); int want_delete = 0; - if (!inode->i_nlink && !is_bad_inode(inode)) { - want_delete = 1; - udf_setsize(inode, 0); - udf_update_inode(inode, IS_SYNC(inode)); + if (!is_bad_inode(inode)) { + if (!inode->i_nlink) { + want_delete = 1; + udf_setsize(inode, 0); + udf_update_inode(inode, IS_SYNC(inode)); + } + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && + inode->i_size != iinfo->i_lenExtents) { + udf_warn(inode->i_sb, + "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n", + inode->i_ino, inode->i_mode, + (unsigned long long)inode->i_size, + (unsigned long long)iinfo->i_lenExtents); + } } truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); - if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && - inode->i_size != iinfo->i_lenExtents) { - udf_warn(inode->i_sb, "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n", - inode->i_ino, inode->i_mode, - (unsigned long long)inode->i_size, - (unsigned long long)iinfo->i_lenExtents); - } kfree(iinfo->i_ext.i_data); iinfo->i_ext.i_data = NULL; udf_clear_extent_cache(inode); diff --git a/fs/udf/super.c b/fs/udf/super.c index 4baa1ca91e9b..a0cd766b41cd 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1352,6 +1352,12 @@ static int udf_load_sparable_map(struct super_block *sb, (int)spm->numSparingTables); return -EIO; } + if (le32_to_cpu(spm->sizeSparingTable) > sb->s_blocksize) { + udf_err(sb, "error loading logical volume descriptor: " + "Too big sparing table size (%u)\n", + le32_to_cpu(spm->sizeSparingTable)); + return -EIO; + } for (i = 0; i < spm->numSparingTables; i++) { loc = le32_to_cpu(spm->locSparingTable[i]); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 1da0be667409..e3b69fb280e8 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -101,7 +101,7 @@ static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 gene struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; struct inode *inode; - if (ino < UFS_ROOTINO || ino > uspi->s_ncg * uspi->s_ipg) + if (ino < UFS_ROOTINO || ino > (u64)uspi->s_ncg * uspi->s_ipg) return ERR_PTR(-ESTALE); inode = ufs_iget(sb, ino); diff --git a/fs/xattr.c b/fs/xattr.c index 90dd78f0eb27..f2854570d411 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -204,10 +204,22 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, return error; } - +/** + * __vfs_setxattr_locked: set an extended attribute while holding the inode + * lock + * + * @dentry - object to perform setxattr on + * @name - xattr name to set + * @value - value to set @name to + * @size - size of @value + * @flags - flags to pass into filesystem operations + * @delegated_inode - on return, will contain an inode pointer that + * a delegation was broken on, NULL if none. + */ int -vfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) +__vfs_setxattr_locked(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -216,15 +228,40 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (error) return error; - inode_lock(inode); error = security_inode_setxattr(dentry, name, value, size, flags); if (error) goto out; + error = try_break_deleg(inode, delegated_inode); + if (error) + goto out; + error = __vfs_setxattr_noperm(dentry, name, value, size, flags); out: + return error; +} +EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); + +int +vfs_setxattr(struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) +{ + struct inode *inode = dentry->d_inode; + struct inode *delegated_inode = NULL; + int error; + +retry_deleg: + inode_lock(inode); + error = __vfs_setxattr_locked(dentry, name, value, size, flags, + &delegated_inode); inode_unlock(inode); + + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); @@ -378,8 +415,18 @@ __vfs_removexattr(struct dentry *dentry, const char *name) } EXPORT_SYMBOL(__vfs_removexattr); +/** + * __vfs_removexattr_locked: set an extended attribute while holding the inode + * lock + * + * @dentry - object to perform setxattr on + * @name - name of xattr to remove + * @delegated_inode - on return, will contain an inode pointer that + * a delegation was broken on, NULL if none. + */ int -vfs_removexattr(struct dentry *dentry, const char *name) +__vfs_removexattr_locked(struct dentry *dentry, const char *name, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -388,11 +435,14 @@ vfs_removexattr(struct dentry *dentry, const char *name) if (error) return error; - inode_lock(inode); error = security_inode_removexattr(dentry, name); if (error) goto out; + error = try_break_deleg(inode, delegated_inode); + if (error) + goto out; + error = __vfs_removexattr(dentry, name); if (!error) { @@ -401,12 +451,32 @@ vfs_removexattr(struct dentry *dentry, const char *name) } out: + return error; +} +EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); + +int +vfs_removexattr(struct dentry *dentry, const char *name) +{ + struct inode *inode = dentry->d_inode; + struct inode *delegated_inode = NULL; + int error; + +retry_deleg: + inode_lock(inode); + error = __vfs_removexattr_locked(dentry, name, &delegated_inode); inode_unlock(inode); + + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } + return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); - /* * Extended attribute SET operations */ diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 533b04aaf6f6..0a36f532cf86 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2598,6 +2598,13 @@ xfs_agf_verify( be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp))) return __this_address; + if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks) + return __this_address; + + if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) || + be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length)) + return __this_address; + if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 || be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 || be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > XFS_BTREE_MAXLEVELS || @@ -2609,6 +2616,10 @@ xfs_agf_verify( be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > XFS_BTREE_MAXLEVELS)) return __this_address; + if (xfs_sb_version_hasrmapbt(&mp->m_sb) && + be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length)) + return __this_address; + /* * during growfs operations, the perag is not fully initialised, * so we can't use it for any useful checking. growfs ensures we can't @@ -2623,6 +2634,11 @@ xfs_agf_verify( return __this_address; if (xfs_sb_version_hasreflink(&mp->m_sb) && + be32_to_cpu(agf->agf_refcount_blocks) > + be32_to_cpu(agf->agf_length)) + return __this_address; + + if (xfs_sb_version_hasreflink(&mp->m_sb) && (be32_to_cpu(agf->agf_refcount_level) < 1 || be32_to_cpu(agf->agf_refcount_level) > XFS_BTREE_MAXLEVELS)) return __this_address; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index f0089e862216..de33efc9b4f9 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -453,13 +453,15 @@ xfs_attr_copy_value( * special case for dev/uuid inodes, they have fixed size data forks. */ int -xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes) +xfs_attr_shortform_bytesfit( + struct xfs_inode *dp, + int bytes) { - int offset; - int minforkoff; /* lower limit on valid forkoff locations */ - int maxforkoff; /* upper limit on valid forkoff locations */ - int dsize; - xfs_mount_t *mp = dp->i_mount; + struct xfs_mount *mp = dp->i_mount; + int64_t dsize; + int minforkoff; + int maxforkoff; + int offset; /* rounded down */ offset = (XFS_LITINO(mp, dp->i_d.di_version) - bytes) >> 3; @@ -525,7 +527,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes) * A data fork btree root must have space for at least * MINDBTPTRS key/ptr pairs if the data fork is small or empty. */ - minforkoff = max(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS)); + minforkoff = max_t(int64_t, dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS)); minforkoff = roundup(minforkoff, 8) >> 3; /* attr fork btree root can have at least this many key/ptr pairs */ @@ -583,8 +585,8 @@ xfs_attr_shortform_create(xfs_da_args_t *args) ASSERT(ifp->if_flags & XFS_IFINLINE); } xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK); - hdr = (xfs_attr_sf_hdr_t *)ifp->if_u1.if_data; - hdr->count = 0; + hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data; + memset(hdr, 0, sizeof(*hdr)); hdr->totsize = cpu_to_be16(sizeof(*hdr)); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); } @@ -924,7 +926,7 @@ xfs_attr_shortform_verify( char *endp; struct xfs_ifork *ifp; int i; - int size; + int64_t size; ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL); ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK); @@ -946,8 +948,10 @@ xfs_attr_shortform_verify( * struct xfs_attr_sf_entry has a variable length. * Check the fixed-offset parts of the structure are * within the data buffer. + * xfs_attr_sf_entry is defined with a 1-byte variable + * array at the end, so we must subtract that off. */ - if (((char *)sfep + sizeof(*sfep)) >= endp) + if (((char *)sfep + sizeof(*sfep) - 1) >= endp) return __this_address; /* Don't allow names with known bad length. */ @@ -1447,7 +1451,9 @@ xfs_attr3_leaf_add_work( for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr->freemap[i].base == tmp) { ichdr->freemap[i].base += sizeof(xfs_attr_leaf_entry_t); - ichdr->freemap[i].size -= sizeof(xfs_attr_leaf_entry_t); + ichdr->freemap[i].size -= + min_t(uint16_t, ichdr->freemap[i].size, + sizeof(xfs_attr_leaf_entry_t)); } } ichdr->usedbytes += xfs_attr_leaf_entsize(leaf, args->index); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 3f76da11197c..f8db3fe616df 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5376,16 +5376,17 @@ __xfs_bunmapi( } div_u64_rem(del.br_startblock, mp->m_sb.sb_rextsize, &mod); if (mod) { + xfs_extlen_t off = mp->m_sb.sb_rextsize - mod; + /* * Realtime extent is lined up at the end but not * at the front. We'll get rid of full extents if * we can. */ - mod = mp->m_sb.sb_rextsize - mod; - if (del.br_blockcount > mod) { - del.br_blockcount -= mod; - del.br_startoff += mod; - del.br_startblock += mod; + if (del.br_blockcount > off) { + del.br_blockcount -= off; + del.br_startoff += off; + del.br_startblock += off; } else if (del.br_startoff == start && (del.br_state == XFS_EXT_UNWRITTEN || tp->t_blk_res == 0)) { @@ -5403,6 +5404,7 @@ __xfs_bunmapi( continue; } else if (del.br_state == XFS_EXT_UNWRITTEN) { struct xfs_bmbt_irec prev; + xfs_fileoff_t unwrite_start; /* * This one is already unwritten. @@ -5416,12 +5418,13 @@ __xfs_bunmapi( ASSERT(!isnullstartblock(prev.br_startblock)); ASSERT(del.br_startblock == prev.br_startblock + prev.br_blockcount); - if (prev.br_startoff < start) { - mod = start - prev.br_startoff; - prev.br_blockcount -= mod; - prev.br_startblock += mod; - prev.br_startoff = start; - } + unwrite_start = max3(start, + del.br_startoff - mod, + prev.br_startoff); + mod = unwrite_start - prev.br_startoff; + prev.br_startoff = unwrite_start; + prev.br_startblock += mod; + prev.br_blockcount -= mod; prev.br_state = XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent_unwritten_real(tp, ip, whichfork, &icur, &cur, @@ -6179,7 +6182,7 @@ xfs_bmap_validate_extent( isrt = XFS_IS_REALTIME_INODE(ip); endfsb = irec->br_startblock + irec->br_blockcount - 1; - if (isrt) { + if (isrt && whichfork == XFS_DATA_FORK) { if (!xfs_verify_rtbno(mp, irec->br_startblock)) return __this_address; if (!xfs_verify_rtbno(mp, endfsb)) diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 705c4f562758..99d5b2ed67f2 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -210,6 +210,7 @@ __xfs_dir3_free_read( if (fa) { xfs_verifier_error(*bpp, -EFSCORRUPTED, fa); xfs_trans_brelse(tp, *bpp); + *bpp = NULL; return -EFSCORRUPTED; } diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 85f14fc2a8da..ae16ca7c422a 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -628,7 +628,7 @@ xfs_dir2_sf_verify( int i; int i8count; int offset; - int size; + int64_t size; int error; uint8_t filetype; diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 588d44613094..443cf33f6666 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -679,7 +679,7 @@ xfs_ialloc_ag_alloc( args.minalignslop = igeo->cluster_align - 1; /* Allow space for the inode btree to split. */ - args.minleft = igeo->inobt_maxlevels - 1; + args.minleft = igeo->inobt_maxlevels; if ((error = xfs_alloc_vextent(&args))) return error; @@ -727,7 +727,7 @@ xfs_ialloc_ag_alloc( /* * Allow space for the inode btree to split. */ - args.minleft = igeo->inobt_maxlevels - 1; + args.minleft = igeo->inobt_maxlevels; if ((error = xfs_alloc_vextent(&args))) return error; } diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c index 7bc87408f1a0..52451809c478 100644 --- a/fs/xfs/libxfs/xfs_iext_tree.c +++ b/fs/xfs/libxfs/xfs_iext_tree.c @@ -596,7 +596,7 @@ xfs_iext_realloc_root( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { - size_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec); + int64_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec); void *new; /* account for the prev/next pointers */ diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index c643beeb5a24..8fdd0424070e 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -129,7 +129,7 @@ xfs_init_local_fork( struct xfs_inode *ip, int whichfork, const void *data, - int size) + int64_t size) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); int mem_size = size, real_size = 0; @@ -467,11 +467,11 @@ xfs_iroot_realloc( void xfs_idata_realloc( struct xfs_inode *ip, - int byte_diff, + int64_t byte_diff, int whichfork) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); - int new_size = (int)ifp->if_bytes + byte_diff; + int64_t new_size = ifp->if_bytes + byte_diff; ASSERT(new_size >= 0); ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork)); @@ -552,7 +552,7 @@ xfs_iextents_copy( struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); struct xfs_iext_cursor icur; struct xfs_bmbt_irec rec; - int copied = 0; + int64_t copied = 0; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); ASSERT(ifp->if_bytes > 0); diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 00c62ce170d0..7b845c052fb4 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -13,16 +13,16 @@ struct xfs_dinode; * File incore extent information, present for each of data & attr forks. */ struct xfs_ifork { - int if_bytes; /* bytes in if_u1 */ - unsigned int if_seq; /* fork mod counter */ + int64_t if_bytes; /* bytes in if_u1 */ struct xfs_btree_block *if_broot; /* file's incore btree root */ - short if_broot_bytes; /* bytes allocated for root */ - unsigned char if_flags; /* per-fork flags */ + unsigned int if_seq; /* fork mod counter */ int if_height; /* height of the extent tree */ union { void *if_root; /* extent tree root */ char *if_data; /* inline file data */ } if_u1; + short if_broot_bytes; /* bytes allocated for root */ + unsigned char if_flags; /* per-fork flags */ }; /* @@ -93,12 +93,14 @@ int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *); void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, struct xfs_inode_log_item *, int); void xfs_idestroy_fork(struct xfs_inode *, int); -void xfs_idata_realloc(struct xfs_inode *, int, int); +void xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, + int whichfork); void xfs_iroot_realloc(struct xfs_inode *, int, int); int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); -void xfs_init_local_fork(struct xfs_inode *, int, const void *, int); +void xfs_init_local_fork(struct xfs_inode *ip, int whichfork, + const void *data, int64_t size); xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp); void xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur, diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 8ea1efc97b41..42085e70c01a 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -1018,7 +1018,6 @@ xfs_rtalloc_query_range( struct xfs_mount *mp = tp->t_mountp; xfs_rtblock_t rtstart; xfs_rtblock_t rtend; - xfs_rtblock_t rem; int is_free; int error = 0; @@ -1027,13 +1026,12 @@ xfs_rtalloc_query_range( if (low_rec->ar_startext >= mp->m_sb.sb_rextents || low_rec->ar_startext == high_rec->ar_startext) return 0; - if (high_rec->ar_startext > mp->m_sb.sb_rextents) - high_rec->ar_startext = mp->m_sb.sb_rextents; + high_rec->ar_startext = min(high_rec->ar_startext, + mp->m_sb.sb_rextents - 1); /* Iterate the bitmap, looking for discrepancies. */ rtstart = low_rec->ar_startext; - rem = high_rec->ar_startext - rtstart; - while (rem) { + while (rtstart <= high_rec->ar_startext) { /* Is the first block free? */ error = xfs_rtcheck_range(mp, tp, rtstart, 1, 1, &rtend, &is_free); @@ -1042,7 +1040,7 @@ xfs_rtalloc_query_range( /* How long does the extent go for? */ error = xfs_rtfind_forw(mp, tp, rtstart, - high_rec->ar_startext - 1, &rtend); + high_rec->ar_startext, &rtend); if (error) break; @@ -1055,7 +1053,6 @@ xfs_rtalloc_query_range( break; } - rem -= rtend - rtstart + 1; rtstart = rtend + 1; } diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index a9ad90926b87..6c7354abd0ae 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -36,6 +36,7 @@ xfs_trans_ijoin( ASSERT(iip->ili_lock_flags == 0); iip->ili_lock_flags = lock_flags; + ASSERT(!xfs_iflags_test(ip, XFS_ISTALE)); /* * Get a log_item_desc to point at the new item. @@ -91,6 +92,7 @@ xfs_trans_log_inode( ASSERT(ip->i_itemp != NULL); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + ASSERT(!xfs_iflags_test(ip, XFS_ISTALE)); /* * Don't bother with i_lock for the I_DIRTY_TIME check here, as races diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index d12bbd526e7c..b3584cd2cc16 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -197,6 +197,24 @@ xfs_calc_inode_chunk_res( } /* + * Per-extent log reservation for the btree changes involved in freeing or + * allocating a realtime extent. We have to be able to log as many rtbitmap + * blocks as needed to mark inuse MAXEXTLEN blocks' worth of realtime extents, + * as well as the realtime summary block. + */ +unsigned int +xfs_rtalloc_log_count( + struct xfs_mount *mp, + unsigned int num_ops) +{ + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + unsigned int rtbmp_bytes; + + rtbmp_bytes = (MAXEXTLEN / mp->m_sb.sb_rextsize) / NBBY; + return (howmany(rtbmp_bytes, blksz) + 1) * num_ops; +} + +/* * Various log reservation values. * * These are based on the size of the file system block because that is what @@ -218,13 +236,21 @@ xfs_calc_inode_chunk_res( /* * In a write transaction we can allocate a maximum of 2 - * extents. This gives: + * extents. This gives (t1): * the inode getting the new extents: inode size * the inode's bmap btree: max depth * block size * the agfs of the ags from which the extents are allocated: 2 * sector * the superblock free block counter: sector size * the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size - * And the bmap_finish transaction can free bmap blocks in a join: + * Or, if we're writing to a realtime file (t2): + * the inode getting the new extents: inode size + * the inode's bmap btree: max depth * block size + * the agfs of the ags from which the extents are allocated: 2 * sector + * the superblock free block counter: sector size + * the realtime bitmap: ((MAXEXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 1 block + * the allocation btrees: 2 trees * (2 * max depth - 1) * block size + * And the bmap_finish transaction can free bmap blocks in a join (t3): * the agfs of the ags containing the blocks: 2 * sector size * the agfls of the ags containing the blocks: 2 * sector size * the super block free block counter: sector size @@ -234,40 +260,72 @@ STATIC uint xfs_calc_write_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 1) + + unsigned int t1, t2, t3; + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + + t1 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), blksz) + + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + + if (xfs_sb_version_hasrealtime(&mp->m_sb)) { + t2 = xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), - XFS_FSB_TO_B(mp, 1)) + + blksz) + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), - XFS_FSB_TO_B(mp, 1)))); + xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 1), blksz) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1), blksz); + } else { + t2 = 0; + } + + t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + + return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); } /* - * In truncating a file we free up to two extents at once. We can modify: + * In truncating a file we free up to two extents at once. We can modify (t1): * the inode being truncated: inode size * the inode's bmap btree: (max depth + 1) * block size - * And the bmap_finish transaction can free the blocks and bmap blocks: + * And the bmap_finish transaction can free the blocks and bmap blocks (t2): * the agf for each of the ags: 4 * sector size * the agfl for each of the ags: 4 * sector size * the super block to reflect the freed blocks: sector size * worst case split in allocation btrees per extent assuming 4 extents: * 4 exts * 2 trees * (2 * max depth - 1) * block size + * Or, if it's a realtime file (t3): + * the agf for each of the ags: 2 * sector size + * the agfl for each of the ags: 2 * sector size + * the super block to reflect the freed blocks: sector size + * the realtime bitmap: 2 exts * ((MAXEXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 2 exts * 1 block + * worst case split in allocation btrees per extent assuming 2 extents: + * 2 exts * 2 trees * (2 * max depth - 1) * block size */ STATIC uint xfs_calc_itruncate_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 1) + - xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), - XFS_FSB_TO_B(mp, 1)))); + unsigned int t1, t2, t3; + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + + t1 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, blksz); + + t2 = xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), blksz); + + if (xfs_sb_version_hasrealtime(&mp->m_sb)) { + t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 2), blksz) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + } else { + t3 = 0; + } + + return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); } /* diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index 88221c7a04cc..7ad3659c5d2a 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -57,8 +57,8 @@ XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK) #define XFS_IALLOC_SPACE_RES(mp) \ (M_IGEO(mp)->ialloc_blks + \ - (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \ - (M_IGEO(mp)->inobt_maxlevels - 1))) + ((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \ + M_IGEO(mp)->inobt_maxlevels)) /* * Space reservation values for various transactions. diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index fa6ea6407992..392fb4df5c12 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -45,9 +45,27 @@ xchk_setup_inode_bmap( */ if (S_ISREG(VFS_I(sc->ip)->i_mode) && sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) { + struct address_space *mapping = VFS_I(sc->ip)->i_mapping; + inode_dio_wait(VFS_I(sc->ip)); - error = filemap_write_and_wait(VFS_I(sc->ip)->i_mapping); - if (error) + + /* + * Try to flush all incore state to disk before we examine the + * space mappings for the data fork. Leave accumulated errors + * in the mapping for the writer threads to consume. + * + * On ENOSPC or EIO writeback errors, we continue into the + * extent mapping checks because write failures do not + * necessarily imply anything about the correctness of the file + * metadata. The metadata and the file data could be on + * completely separate devices; a media failure might only + * affect a subset of the disk, etc. We can handle delalloc + * extents in the scrubber, so leaving them in memory is fine. + */ + error = filemap_fdatawrite(mapping); + if (!error) + error = filemap_fdatawait_keep_errors(mapping); + if (error && (error != -ENOSPC && error != -EIO)) goto out; } diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 1e2e11721eb9..20eca2d8e7c7 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -152,6 +152,9 @@ xchk_dir_actor( xname.type = XFS_DIR3_FT_UNKNOWN; error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL); + /* ENOENT means the hash lookup failed and the dir is corrupt */ + if (error == -ENOENT) + error = -EFSCORRUPTED; if (!xchk_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset, &error)) goto out; diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 15c8c5f3f688..720bef577998 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -167,6 +167,7 @@ xchk_teardown( xfs_irele(sc->ip); sc->ip = NULL; } + sb_end_write(sc->mp->m_super); if (sc->flags & XCHK_REAPING_DISABLED) xchk_start_reaping(sc); if (sc->flags & XCHK_HAS_QUOTAOFFLOCK) { @@ -489,6 +490,14 @@ xfs_scrub_metadata( sc.ops = &meta_scrub_ops[sm->sm_type]; sc.sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type); retry_op: + /* + * If freeze runs concurrently with a scrub, the freeze can be delayed + * indefinitely as we walk the filesystem and iterate over metadata + * buffers. Freeze quiesces the log (which waits for the buffer LRU to + * be emptied) and that won't happen while checking is running. + */ + sb_start_write(mp->m_super); + /* Set up for the operation. */ error = sc.ops->setup(&sc, ip); if (error) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 4f443703065e..d6d78e127625 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1039,6 +1039,7 @@ out_trans_cancel: goto out_unlock; } +/* Caller must first wait for the completion of any pending DIOs if required. */ int xfs_flush_unmap_range( struct xfs_inode *ip, @@ -1050,9 +1051,6 @@ xfs_flush_unmap_range( xfs_off_t rounding, start, end; int error; - /* wait for the completion of any pending DIOs */ - inode_dio_wait(inode); - rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE); start = round_down(offset, rounding); end = round_up(offset + len, rounding) - 1; @@ -1084,10 +1082,6 @@ xfs_free_file_space( if (len <= 0) /* if nothing being freed */ return 0; - error = xfs_flush_unmap_range(ip, offset, len); - if (error) - return error; - startoffset_fsb = XFS_B_TO_FSB(mp, offset); endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len); @@ -1760,7 +1754,7 @@ xfs_swap_extents( if (xfs_inode_has_cow_data(tip)) { error = xfs_reflink_cancel_cow_range(tip, 0, NULLFILEOFF, true); if (error) - return error; + goto out_unlock; } /* diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 0abba171aa89..1264ac63e4e5 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1162,8 +1162,10 @@ xfs_buf_ioend( bp->b_ops->verify_read(bp); } - if (!bp->b_error) + if (!bp->b_error) { + bp->b_flags &= ~XBF_WRITE_FAIL; bp->b_flags |= XBF_DONE; + } if (bp->b_iodone) (*(bp->b_iodone))(bp); @@ -1223,7 +1225,7 @@ xfs_bwrite( bp->b_flags |= XBF_WRITE; bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | - XBF_WRITE_FAIL | XBF_DONE); + XBF_DONE); error = xfs_buf_submit(bp); if (error) @@ -1929,7 +1931,7 @@ xfs_buf_delwri_submit_buffers( * synchronously. Otherwise, drop the buffer from the delwri * queue and submit async. */ - bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL); + bp->b_flags &= ~_XBF_DELWRI_Q; bp->b_flags |= XBF_WRITE; if (wait_list) { bp->b_flags &= ~XBF_ASYNC; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index aeb95e7391c1..3cbf248af51f 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1116,13 +1116,12 @@ xfs_qm_dqflush( dqb = bp->b_addr + dqp->q_bufoffset; ddqp = &dqb->dd_diskdq; - /* - * A simple sanity check in case we got a corrupted dquot. - */ - fa = xfs_dqblk_verify(mp, dqb, be32_to_cpu(ddqp->d_id), 0); + /* sanity check the in-core structure before we flush */ + fa = xfs_dquot_verify(mp, &dqp->q_core, be32_to_cpu(dqp->q_core.d_id), + 0); if (fa) { xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS", - be32_to_cpu(ddqp->d_id), fa); + be32_to_cpu(dqp->q_core.d_id), fa); xfs_buf_relse(bp); xfs_dqfunlock(dqp); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1ffb179f35d2..203065a64765 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -818,6 +818,36 @@ xfs_file_fallocate( if (error) goto out_unlock; + /* + * Must wait for all AIO to complete before we continue as AIO can + * change the file size on completion without holding any locks we + * currently hold. We must do this first because AIO can update both + * the on disk and in memory inode sizes, and the operations that follow + * require the in-memory size to be fully up-to-date. + */ + inode_dio_wait(inode); + + /* + * Now AIO and DIO has drained we flush and (if necessary) invalidate + * the cached range over the first operation we are about to run. + * + * We care about zero and collapse here because they both run a hole + * punch over the range first. Because that can zero data, and the range + * of invalidation for the shift operations is much larger, we still do + * the required flush for collapse in xfs_prepare_shift(). + * + * Insert has the same range requirements as collapse, and we extend the + * file first which can zero data. Hence insert has the same + * flush/invalidate requirements as collapse and so they are both + * handled at the right time by xfs_prepare_shift(). + */ + if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE | + FALLOC_FL_COLLAPSE_RANGE)) { + error = xfs_flush_unmap_range(ip, offset, len); + if (error) + goto out_unlock; + } + if (mode & FALLOC_FL_PUNCH_HOLE) { error = xfs_free_file_space(ip, offset, len); if (error) @@ -1172,6 +1202,14 @@ __xfs_filemap_fault( return ret; } +static inline bool +xfs_is_write_fault( + struct vm_fault *vmf) +{ + return (vmf->flags & FAULT_FLAG_WRITE) && + (vmf->vma->vm_flags & VM_SHARED); +} + static vm_fault_t xfs_filemap_fault( struct vm_fault *vmf) @@ -1179,7 +1217,7 @@ xfs_filemap_fault( /* DAX can shortcut the normal fault path on write faults! */ return __xfs_filemap_fault(vmf, PE_SIZE_PTE, IS_DAX(file_inode(vmf->vma->vm_file)) && - (vmf->flags & FAULT_FLAG_WRITE)); + xfs_is_write_fault(vmf)); } static vm_fault_t @@ -1192,7 +1230,7 @@ xfs_filemap_huge_fault( /* DAX can shortcut the normal fault path on write faults! */ return __xfs_filemap_fault(vmf, pe_size, - (vmf->flags & FAULT_FLAG_WRITE)); + xfs_is_write_fault(vmf)); } static vm_fault_t diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index d082143feb5a..01c0933a4d10 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -26,7 +26,7 @@ #include "xfs_rtalloc.h" /* Convert an xfs_fsmap to an fsmap. */ -void +static void xfs_fsmap_from_internal( struct fsmap *dest, struct xfs_fsmap *src) @@ -154,8 +154,7 @@ xfs_fsmap_owner_from_rmap( /* getfsmap query state */ struct xfs_getfsmap_info { struct xfs_fsmap_head *head; - xfs_fsmap_format_t formatter; /* formatting fn */ - void *format_arg; /* format buffer */ + struct fsmap *fsmap_recs; /* mapping records */ struct xfs_buf *agf_bp; /* AGF, for refcount queries */ xfs_daddr_t next_daddr; /* next daddr we expect */ u64 missing_owner; /* owner of holes */ @@ -223,6 +222,20 @@ xfs_getfsmap_is_shared( return 0; } +static inline void +xfs_getfsmap_format( + struct xfs_mount *mp, + struct xfs_fsmap *xfm, + struct xfs_getfsmap_info *info) +{ + struct fsmap *rec; + + trace_xfs_getfsmap_mapping(mp, xfm); + + rec = &info->fsmap_recs[info->head->fmh_entries++]; + xfs_fsmap_from_internal(rec, xfm); +} + /* * Format a reverse mapping for getfsmap, having translated rm_startblock * into the appropriate daddr units. @@ -255,6 +268,9 @@ xfs_getfsmap_helper( /* Are we just counting mappings? */ if (info->head->fmh_count == 0) { + if (info->head->fmh_entries == UINT_MAX) + return -ECANCELED; + if (rec_daddr > info->next_daddr) info->head->fmh_entries++; @@ -284,10 +300,7 @@ xfs_getfsmap_helper( fmr.fmr_offset = 0; fmr.fmr_length = rec_daddr - info->next_daddr; fmr.fmr_flags = FMR_OF_SPECIAL_OWNER; - error = info->formatter(&fmr, info->format_arg); - if (error) - return error; - info->head->fmh_entries++; + xfs_getfsmap_format(mp, &fmr, info); } if (info->last) @@ -319,11 +332,8 @@ xfs_getfsmap_helper( if (shared) fmr.fmr_flags |= FMR_OF_SHARED; } - error = info->formatter(&fmr, info->format_arg); - if (error) - return error; - info->head->fmh_entries++; + xfs_getfsmap_format(mp, &fmr, info); out: rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount); if (info->next_daddr < rec_daddr) @@ -791,11 +801,11 @@ xfs_getfsmap_check_keys( #endif /* CONFIG_XFS_RT */ /* - * Get filesystem's extents as described in head, and format for - * output. Calls formatter to fill the user's buffer until all - * extents are mapped, until the passed-in head->fmh_count slots have - * been filled, or until the formatter short-circuits the loop, if it - * is tracking filled-in extents on its own. + * Get filesystem's extents as described in head, and format for output. Fills + * in the supplied records array until there are no more reverse mappings to + * return or head.fmh_entries == head.fmh_count. In the second case, this + * function returns -ECANCELED to indicate that more records would have been + * returned. * * Key to Confusion * ---------------- @@ -815,8 +825,7 @@ int xfs_getfsmap( struct xfs_mount *mp, struct xfs_fsmap_head *head, - xfs_fsmap_format_t formatter, - void *arg) + struct fsmap *fsmap_recs) { struct xfs_trans *tp = NULL; struct xfs_fsmap dkeys[2]; /* per-dev keys */ @@ -891,10 +900,17 @@ xfs_getfsmap( info.next_daddr = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; - info.formatter = formatter; - info.format_arg = arg; + info.fsmap_recs = fsmap_recs; info.head = head; + /* + * If fsmap runs concurrently with a scrub, the freeze can be delayed + * indefinitely as we walk the rmapbt and iterate over metadata + * buffers. Freeze quiesces the log (which waits for the buffer LRU to + * be emptied) and that won't happen while we're reading buffers. + */ + sb_start_write(mp->m_super); + /* For each device we support... */ for (i = 0; i < XFS_GETFSMAP_DEVS; i++) { /* Is this device within the range the user asked for? */ @@ -934,6 +950,7 @@ xfs_getfsmap( if (tp) xfs_trans_cancel(tp); + sb_end_write(mp->m_super); head->fmh_oflags = FMH_OF_DEV_T; return error; } diff --git a/fs/xfs/xfs_fsmap.h b/fs/xfs/xfs_fsmap.h index c6c57739b862..a0775788e7b1 100644 --- a/fs/xfs/xfs_fsmap.h +++ b/fs/xfs/xfs_fsmap.h @@ -27,13 +27,9 @@ struct xfs_fsmap_head { struct xfs_fsmap fmh_keys[2]; /* low and high keys */ }; -void xfs_fsmap_from_internal(struct fsmap *dest, struct xfs_fsmap *src); void xfs_fsmap_to_internal(struct xfs_fsmap *dest, struct fsmap *src); -/* fsmap to userspace formatter - copy to user & advance pointer */ -typedef int (*xfs_fsmap_format_t)(struct xfs_fsmap *, void *); - int xfs_getfsmap(struct xfs_mount *mp, struct xfs_fsmap_head *head, - xfs_fsmap_format_t formatter, void *arg); + struct fsmap *out_recs); #endif /* __XFS_FSMAP_H__ */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index d95dc9b0f0bb..a1135b86e79f 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1132,7 +1132,7 @@ restart: goto out_ifunlock; xfs_iunpin_wait(ip); } - if (xfs_iflags_test(ip, XFS_ISTALE) || xfs_inode_clean(ip)) { + if (xfs_inode_clean(ip)) { xfs_ifunlock(ip); goto reclaim; } @@ -1219,6 +1219,7 @@ reclaim: xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_qm_dqdetach(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL); + ASSERT(xfs_inode_clean(ip)); __xfs_inode_free(ip); return error; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 18f4b262e61c..b339ff93df99 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1761,10 +1761,31 @@ xfs_inactive_ifree( return error; } + /* + * We do not hold the inode locked across the entire rolling transaction + * here. We only need to hold it for the first transaction that + * xfs_ifree() builds, which may mark the inode XFS_ISTALE if the + * underlying cluster buffer is freed. Relogging an XFS_ISTALE inode + * here breaks the relationship between cluster buffer invalidation and + * stale inode invalidation on cluster buffer item journal commit + * completion, and can result in leaving dirty stale inodes hanging + * around in memory. + * + * We have no need for serialising this inode operation against other + * operations - we freed the inode and hence reallocation is required + * and that will serialise on reallocating the space the deferops need + * to free. Hence we can unlock the inode on the first commit of + * the transaction rather than roll it right through the deferops. This + * avoids relogging the XFS_ISTALE inode. + * + * We check that xfs_ifree() hasn't grown an internal transaction roll + * by asserting that the inode is still locked when it returns. + */ xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, 0); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); error = xfs_ifree(tp, ip); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); if (error) { /* * If we fail to free the inode, shut down. The cancel @@ -1777,7 +1798,6 @@ xfs_inactive_ifree( xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); } xfs_trans_cancel(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } @@ -1795,7 +1815,6 @@ xfs_inactive_ifree( xfs_notice(mp, "%s: xfs_trans_commit returned error %d", __func__, error); - xfs_iunlock(ip, XFS_ILOCK_EXCL); return 0; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index c93c4b7328ef..bf0435dbec43 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -622,6 +622,7 @@ xfs_ioc_space( error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP); if (error) goto out_unlock; + inode_dio_wait(inode); switch (bf->l_whence) { case 0: /*SEEK_SET*/ @@ -1831,39 +1832,17 @@ out_free_buf: return error; } -struct getfsmap_info { - struct xfs_mount *mp; - struct fsmap_head __user *data; - unsigned int idx; - __u32 last_flags; -}; - -STATIC int -xfs_getfsmap_format(struct xfs_fsmap *xfm, void *priv) -{ - struct getfsmap_info *info = priv; - struct fsmap fm; - - trace_xfs_getfsmap_mapping(info->mp, xfm); - - info->last_flags = xfm->fmr_flags; - xfs_fsmap_from_internal(&fm, xfm); - if (copy_to_user(&info->data->fmh_recs[info->idx++], &fm, - sizeof(struct fsmap))) - return -EFAULT; - - return 0; -} - STATIC int xfs_ioc_getfsmap( struct xfs_inode *ip, struct fsmap_head __user *arg) { - struct getfsmap_info info = { NULL }; struct xfs_fsmap_head xhead = {0}; struct fsmap_head head; - bool aborted = false; + struct fsmap *recs; + unsigned int count; + __u32 last_flags = 0; + bool done = false; int error; if (copy_from_user(&head, arg, sizeof(struct fsmap_head))) @@ -1875,38 +1854,112 @@ xfs_ioc_getfsmap( sizeof(head.fmh_keys[1].fmr_reserved))) return -EINVAL; + /* + * Use an internal memory buffer so that we don't have to copy fsmap + * data to userspace while holding locks. Start by trying to allocate + * up to 128k for the buffer, but fall back to a single page if needed. + */ + count = min_t(unsigned int, head.fmh_count, + 131072 / sizeof(struct fsmap)); + recs = kvzalloc(count * sizeof(struct fsmap), GFP_KERNEL); + if (!recs) { + count = min_t(unsigned int, head.fmh_count, + PAGE_SIZE / sizeof(struct fsmap)); + recs = kvzalloc(count * sizeof(struct fsmap), GFP_KERNEL); + if (!recs) + return -ENOMEM; + } + xhead.fmh_iflags = head.fmh_iflags; - xhead.fmh_count = head.fmh_count; xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]); xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]); trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]); trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]); - info.mp = ip->i_mount; - info.data = arg; - error = xfs_getfsmap(ip->i_mount, &xhead, xfs_getfsmap_format, &info); - if (error == -ECANCELED) { - error = 0; - aborted = true; - } else if (error) - return error; + head.fmh_entries = 0; + do { + struct fsmap __user *user_recs; + struct fsmap *last_rec; + + user_recs = &arg->fmh_recs[head.fmh_entries]; + xhead.fmh_entries = 0; + xhead.fmh_count = min_t(unsigned int, count, + head.fmh_count - head.fmh_entries); + + /* Run query, record how many entries we got. */ + error = xfs_getfsmap(ip->i_mount, &xhead, recs); + switch (error) { + case 0: + /* + * There are no more records in the result set. Copy + * whatever we got to userspace and break out. + */ + done = true; + break; + case -ECANCELED: + /* + * The internal memory buffer is full. Copy whatever + * records we got to userspace and go again if we have + * not yet filled the userspace buffer. + */ + error = 0; + break; + default: + goto out_free; + } + head.fmh_entries += xhead.fmh_entries; + head.fmh_oflags = xhead.fmh_oflags; - /* If we didn't abort, set the "last" flag in the last fmx */ - if (!aborted && info.idx) { - info.last_flags |= FMR_OF_LAST; - if (copy_to_user(&info.data->fmh_recs[info.idx - 1].fmr_flags, - &info.last_flags, sizeof(info.last_flags))) - return -EFAULT; + /* + * If the caller wanted a record count or there aren't any + * new records to return, we're done. + */ + if (head.fmh_count == 0 || xhead.fmh_entries == 0) + break; + + /* Copy all the records we got out to userspace. */ + if (copy_to_user(user_recs, recs, + xhead.fmh_entries * sizeof(struct fsmap))) { + error = -EFAULT; + goto out_free; + } + + /* Remember the last record flags we copied to userspace. */ + last_rec = &recs[xhead.fmh_entries - 1]; + last_flags = last_rec->fmr_flags; + + /* Set up the low key for the next iteration. */ + xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec); + trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]); + } while (!done && head.fmh_entries < head.fmh_count); + + /* + * If there are no more records in the query result set and we're not + * in counting mode, mark the last record returned with the LAST flag. + */ + if (done && head.fmh_count > 0 && head.fmh_entries > 0) { + struct fsmap __user *user_rec; + + last_flags |= FMR_OF_LAST; + user_rec = &arg->fmh_recs[head.fmh_entries - 1]; + + if (copy_to_user(&user_rec->fmr_flags, &last_flags, + sizeof(last_flags))) { + error = -EFAULT; + goto out_free; + } } /* copy back header */ - head.fmh_entries = xhead.fmh_entries; - head.fmh_oflags = xhead.fmh_oflags; - if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) - return -EFAULT; + if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) { + error = -EFAULT; + goto out_free; + } - return 0; +out_free: + kmem_free(recs); + return error; } STATIC int diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index f780e223b118..239c9548b156 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1002,9 +1002,15 @@ xfs_file_iomap_begin( * I/O, which must be block aligned, we need to report the * newly allocated address. If the data fork has a hole, copy * the COW fork mapping to avoid allocating to the data fork. + * + * Otherwise, ensure that the imap range does not extend past + * the range allocated/found in cmap. */ if (directio || imap.br_startblock == HOLESTARTBLOCK) imap = cmap; + else + xfs_trim_extent(&imap, cmap.br_startoff, + cmap.br_blockcount); end_fsb = imap.br_startoff + imap.br_blockcount; length = XFS_FSB_TO_B(mp, end_fsb) - offset; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 6a4fd1738b08..904d8285c226 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1005,6 +1005,7 @@ xfs_reflink_remap_extent( xfs_filblks_t rlen; xfs_filblks_t unmap_len; xfs_off_t newlen; + int64_t qres; int error; unmap_len = irec->br_startoff + irec->br_blockcount - destoff; @@ -1027,13 +1028,19 @@ xfs_reflink_remap_extent( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); - /* If we're not just clearing space, then do we have enough quota? */ - if (real_extent) { - error = xfs_trans_reserve_quota_nblks(tp, ip, - irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS); - if (error) - goto out_cancel; - } + /* + * Reserve quota for this operation. We don't know if the first unmap + * in the dest file will cause a bmap btree split, so we always reserve + * at least enough blocks for that split. If the extent being mapped + * in is written, we need to reserve quota for that too. + */ + qres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); + if (real_extent) + qres += irec->br_blockcount; + error = xfs_trans_reserve_quota_nblks(tp, ip, qres, 0, + XFS_QMOPT_RES_REGBLKS); + if (error) + goto out_cancel; trace_xfs_reflink_remap(ip, irec->br_startoff, irec->br_blockcount, irec->br_startblock); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 4a48a8c75b4f..b58366937082 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -247,6 +247,9 @@ xfs_rtallocate_extent_block( end = XFS_BLOCKTOBIT(mp, bbno + 1) - 1; i <= end; i++) { + /* Make sure we don't scan off the end of the rt volume. */ + maxlen = min(mp->m_sb.sb_rextents, i + maxlen) - i; + /* * See if there's a free extent of maxlen starting at i. * If it's not so then next will contain the first non-free. @@ -442,6 +445,14 @@ xfs_rtallocate_extent_near( */ if (bno >= mp->m_sb.sb_rextents) bno = mp->m_sb.sb_rextents - 1; + + /* Make sure we don't run off the end of the rt volume. */ + maxlen = min(mp->m_sb.sb_rextents, bno + maxlen) - bno; + if (maxlen < minlen) { + *rtblock = NULLRTBLOCK; + return 0; + } + /* * Try the exact allocation first. */ diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h index e9f810fc6731..43585850f154 100644 --- a/fs/xfs/xfs_sysfs.h +++ b/fs/xfs/xfs_sysfs.h @@ -32,9 +32,11 @@ xfs_sysfs_init( struct xfs_kobj *parent_kobj, const char *name) { + struct kobject *parent; + + parent = parent_kobj ? &parent_kobj->kobject : NULL; init_completion(&kobj->complete); - return kobject_init_and_add(&kobj->kobject, ktype, - &parent_kobj->kobject, "%s", name); + return kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name); } static inline void diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index f4795fdb7389..b32a66452d44 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -306,6 +306,11 @@ xfs_trans_alloc( * * Note the zero-length reservation; this transaction MUST be cancelled * without any dirty data. + * + * Callers should obtain freeze protection to avoid two conflicts with fs + * freezing: (1) having active transactions trip the m_active_trans ASSERTs; + * and (2) grabbing buffers at the same time that freeze is trying to drain + * the buffer LRU list. */ int xfs_trans_alloc_empty( diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 16457465833b..904780dd74aa 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -646,7 +646,7 @@ xfs_trans_dqresv( } } if (ninos > 0) { - total_count = be64_to_cpu(dqp->q_core.d_icount) + ninos; + total_count = dqp->q_res_icount + ninos; timer = be32_to_cpu(dqp->q_core.d_itimer); warns = be16_to_cpu(dqp->q_core.d_iwarns); warnlimit = dqp->q_mount->m_quotainfo->qi_iwarnlimit; |