diff options
Diffstat (limited to 'fs')
474 files changed, 19602 insertions, 10552 deletions
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index aaee1e6584e6..60cd4ba04afc 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -58,7 +58,7 @@ extern const struct file_operations v9fs_mmap_file_operations_dotl; extern struct kmem_cache *v9fs_inode_cache; struct inode *v9fs_alloc_inode(struct super_block *sb); -void v9fs_destroy_inode(struct inode *inode); +void v9fs_free_inode(struct inode *inode); struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t); int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 72b779bc0942..24050e866e64 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -253,21 +253,15 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) } /** - * v9fs_destroy_inode - destroy an inode + * v9fs_free_inode - destroy an inode * */ -static void v9fs_i_callback(struct rcu_head *head) +void v9fs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(v9fs_inode_cache, V9FS_I(inode)); } -void v9fs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, v9fs_i_callback); -} - int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t rdev) { diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index d13d35cf69c0..67d1b965adcd 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -344,7 +344,7 @@ static int v9fs_write_inode_dotl(struct inode *inode, static const struct super_operations v9fs_super_ops = { .alloc_inode = v9fs_alloc_inode, - .destroy_inode = v9fs_destroy_inode, + .free_inode = v9fs_free_inode, .statfs = simple_statfs, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, @@ -354,7 +354,7 @@ static const struct super_operations v9fs_super_ops = { static const struct super_operations v9fs_super_ops_dotl = { .alloc_inode = v9fs_alloc_inode, - .destroy_inode = v9fs_destroy_inode, + .free_inode = v9fs_free_inode, .statfs = v9fs_statfs, .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, diff --git a/fs/Makefile b/fs/Makefile index ab21f060f661..c9aea23aba56 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -13,7 +13,7 @@ obj-y := open.o read_write.o file_table.o super.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o splice.o sync.o utimes.o d_path.o \ stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ - fs_types.o fs_context.o fs_parser.o + fs_types.o fs_context.o fs_parser.o fsopen.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o block_dev.o direct-io.o mpage.o @@ -25,7 +25,7 @@ obj-$(CONFIG_PROC_FS) += proc_namespace.o obj-y += notify/ obj-$(CONFIG_EPOLL) += eventpoll.o -obj-$(CONFIG_ANON_INODES) += anon_inodes.o +obj-y += anon_inodes.o obj-$(CONFIG_SIGNALFD) += signalfd.o obj-$(CONFIG_TIMERFD) += timerfd.o obj-$(CONFIG_EVENTFD) += eventfd.o diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c index 0fbfd0b04ae0..382c9d7ad375 100644 --- a/fs/adfs/dir_f.c +++ b/fs/adfs/dir_f.c @@ -24,8 +24,11 @@ static inline unsigned int adfs_readval(unsigned char *p, int len) switch (len) { case 4: val |= p[3] << 24; + /* fall through */ case 3: val |= p[2] << 16; + /* fall through */ case 2: val |= p[1] << 8; + /* fall through */ default: val |= p[0]; } return val; @@ -35,8 +38,11 @@ static inline void adfs_writeval(unsigned char *p, int len, unsigned int val) { switch (len) { case 4: p[3] = val >> 24; + /* fall through */ case 3: p[2] = val >> 16; + /* fall through */ case 2: p[1] = val >> 8; + /* fall through */ default: p[0] = val; } } diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 7e099a7a4eb1..2a83655c408f 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -248,17 +248,11 @@ static struct inode *adfs_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void adfs_i_callback(struct rcu_head *head) +static void adfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(adfs_inode_cachep, ADFS_I(inode)); } -static void adfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, adfs_i_callback); -} - static void init_once(void *foo) { struct adfs_inode_info *ei = (struct adfs_inode_info *) foo; @@ -290,7 +284,7 @@ static void destroy_inodecache(void) static const struct super_operations adfs_sops = { .alloc_inode = adfs_alloc_inode, - .destroy_inode = adfs_destroy_inode, + .free_inode = adfs_free_inode, .drop_inode = generic_delete_inode, .write_inode = adfs_write_inode, .put_super = adfs_put_super, diff --git a/fs/affs/super.c b/fs/affs/super.c index d1ad11a8a4a5..7370228eefb2 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -111,17 +111,11 @@ static struct inode *affs_alloc_inode(struct super_block *sb) return &i->vfs_inode; } -static void affs_i_callback(struct rcu_head *head) +static void affs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(affs_inode_cachep, AFFS_I(inode)); } -static void affs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, affs_i_callback); -} - static void init_once(void *foo) { struct affs_inode_info *ei = (struct affs_inode_info *) foo; @@ -155,7 +149,7 @@ static void destroy_inodecache(void) static const struct super_operations affs_sops = { .alloc_inode = affs_alloc_inode, - .destroy_inode = affs_destroy_inode, + .free_inode = affs_free_inode, .write_inode = affs_write_inode, .evict_inode = affs_evict_inode, .put_super = affs_put_super, @@ -487,7 +481,7 @@ got_root: break; case MUFS_OFS: affs_set_opt(sbi->s_flags, SF_MUFS); - /* fall thru */ + /* fall through */ case FS_OFS: affs_set_opt(sbi->s_flags, SF_OFS); sb->s_flags |= SB_NOEXEC; @@ -495,6 +489,7 @@ got_root: case MUFS_DCOFS: case MUFS_INTLOFS: affs_set_opt(sbi->s_flags, SF_MUFS); + /* fall through */ case FS_DCOFS: case FS_INTLOFS: affs_set_opt(sbi->s_flags, SF_INTL); diff --git a/fs/afs/Makefile b/fs/afs/Makefile index 0738e2bf5193..cbf31f6cd177 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -13,6 +13,7 @@ kafs-y := \ cmservice.o \ dir.o \ dir_edit.o \ + dir_silly.o \ dynroot.o \ file.o \ flock.o \ diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index 967db336d11a..9eaff55df7b4 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -251,7 +251,7 @@ struct afs_vlserver_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry _enter("%s", cell->name); ret = dns_query("afsdb", cell->name, cell->name_len, "srv=1", - &result, _expiry); + &result, _expiry, true); if (ret < 0) { _leave(" = %d [dns]", ret); return ERR_PTR(ret); diff --git a/fs/afs/afs.h b/fs/afs/afs.h index d12ffb457e47..3f4e460c6655 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -23,6 +23,9 @@ #define AFSPATHMAX 1024 /* Maximum length of a pathname plus NUL */ #define AFSOPAQUEMAX 1024 /* Maximum length of an opaque field */ +#define AFS_VL_MAX_LIFESPAN (120 * HZ) +#define AFS_PROBE_MAX_LIFESPAN (30 * HZ) + typedef u64 afs_volid_t; typedef u64 afs_vnodeid_t; typedef u64 afs_dataversion_t; @@ -69,8 +72,8 @@ typedef enum { struct afs_callback { time64_t expires_at; /* Time at which expires */ - unsigned version; /* Callback version */ - afs_callback_type_t type; /* Type of callback */ + //unsigned version; /* Callback version */ + //afs_callback_type_t type; /* Type of callback */ }; struct afs_callback_break { @@ -144,6 +147,15 @@ struct afs_file_status { u32 abort_code; /* Abort if bulk-fetching this failed */ }; +struct afs_status_cb { + struct afs_file_status status; + struct afs_callback callback; + unsigned int cb_break; /* Pre-op callback break counter */ + bool have_status; /* True if status record was retrieved */ + bool have_cb; /* True if cb record was retrieved */ + bool have_error; /* True if status.abort_code indicates an error */ +}; + /* * AFS file status change request */ diff --git a/fs/afs/afs_fs.h b/fs/afs/afs_fs.h index ddfa88a7a9c0..18a54ca422f8 100644 --- a/fs/afs/afs_fs.h +++ b/fs/afs/afs_fs.h @@ -17,8 +17,10 @@ enum AFS_FS_Operations { FSFETCHDATA = 130, /* AFS Fetch file data */ + FSFETCHACL = 131, /* AFS Fetch file ACL */ FSFETCHSTATUS = 132, /* AFS Fetch file status */ FSSTOREDATA = 133, /* AFS Store file data */ + FSSTOREACL = 134, /* AFS Store file ACL */ FSSTORESTATUS = 135, /* AFS Store file status */ FSREMOVEFILE = 136, /* AFS Remove a file */ FSCREATEFILE = 137, /* AFS Create a file */ diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 1c7955f5cdaf..d441bef72163 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -94,15 +94,15 @@ int afs_register_server_cb_interest(struct afs_vnode *vnode, struct afs_server *server = entry->server; again: - if (vnode->cb_interest && - likely(vnode->cb_interest == entry->cb_interest)) + vcbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->io_lock)); + if (vcbi && likely(vcbi == entry->cb_interest)) return 0; read_lock(&slist->lock); cbi = afs_get_cb_interest(entry->cb_interest); read_unlock(&slist->lock); - vcbi = vnode->cb_interest; if (vcbi) { if (vcbi == cbi) { afs_put_cb_interest(afs_v2net(vnode), cbi); @@ -114,8 +114,9 @@ again: */ if (cbi && vcbi->server == cbi->server) { write_seqlock(&vnode->cb_lock); - old = vnode->cb_interest; - vnode->cb_interest = cbi; + old = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + rcu_assign_pointer(vnode->cb_interest, cbi); write_sequnlock(&vnode->cb_lock); afs_put_cb_interest(afs_v2net(vnode), old); return 0; @@ -160,8 +161,9 @@ again: */ write_seqlock(&vnode->cb_lock); - old = vnode->cb_interest; - vnode->cb_interest = cbi; + old = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + rcu_assign_pointer(vnode->cb_interest, cbi); vnode->cb_s_break = cbi->server->cb_s_break; vnode->cb_v_break = vnode->volume->cb_v_break; clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); @@ -191,10 +193,11 @@ void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi) vi = NULL; write_unlock(&cbi->server->cb_break_lock); - kfree(vi); + if (vi) + kfree_rcu(vi, rcu); afs_put_server(net, cbi->server); } - kfree(cbi); + kfree_rcu(cbi, rcu); } } @@ -203,8 +206,7 @@ void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi) */ void afs_init_callback_state(struct afs_server *server) { - if (!test_and_clear_bit(AFS_SERVER_FL_NEW, &server->flags)) - server->cb_s_break++; + server->cb_s_break++; } /* @@ -219,14 +221,8 @@ void __afs_break_callback(struct afs_vnode *vnode) vnode->cb_break++; afs_clear_permits(vnode); - spin_lock(&vnode->lock); - - _debug("break callback"); - - if (list_empty(&vnode->granted_locks) && - !list_empty(&vnode->pending_locks)) + if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB) afs_lock_may_be_available(vnode); - spin_unlock(&vnode->lock); } } diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 9de46116c749..9c3b07ba2222 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -123,6 +123,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, const char *name, unsigned int namelen, const char *addresses) { + struct afs_vlserver_list *vllist; struct afs_cell *cell; int i, ret; @@ -151,18 +152,14 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, atomic_set(&cell->usage, 2); INIT_WORK(&cell->manager, afs_manage_cell); - cell->flags = ((1 << AFS_CELL_FL_NOT_READY) | - (1 << AFS_CELL_FL_NO_LOOKUP_YET)); INIT_LIST_HEAD(&cell->proc_volumes); rwlock_init(&cell->proc_lock); rwlock_init(&cell->vl_servers_lock); - /* Fill in the VL server list if we were given a list of addresses to - * use. + /* Provide a VL server list, filling it in if we were given a list of + * addresses to use. */ if (addresses) { - struct afs_vlserver_list *vllist; - vllist = afs_parse_text_addrs(net, addresses, strlen(addresses), ':', VL_SERVICE, AFS_VL_PORT); @@ -171,19 +168,32 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, goto parse_failed; } - rcu_assign_pointer(cell->vl_servers, vllist); + vllist->source = DNS_RECORD_FROM_CONFIG; + vllist->status = DNS_LOOKUP_NOT_DONE; cell->dns_expiry = TIME64_MAX; - __clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags); } else { + ret = -ENOMEM; + vllist = afs_alloc_vlserver_list(0); + if (!vllist) + goto error; + vllist->source = DNS_RECORD_UNAVAILABLE; + vllist->status = DNS_LOOKUP_NOT_DONE; cell->dns_expiry = ktime_get_real_seconds(); } + rcu_assign_pointer(cell->vl_servers, vllist); + + cell->dns_source = vllist->source; + cell->dns_status = vllist->status; + smp_store_release(&cell->dns_lookup_count, 1); /* vs source/status */ + _leave(" = %p", cell); return cell; parse_failed: if (ret == -EINVAL) printk(KERN_ERR "kAFS: bad VL server IP address\n"); +error: kfree(cell); _leave(" = %d", ret); return ERR_PTR(ret); @@ -208,6 +218,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, { struct afs_cell *cell, *candidate, *cursor; struct rb_node *parent, **pp; + enum afs_cell_state state; int ret, n; _enter("%s,%s", name, vllist); @@ -267,18 +278,16 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, wait_for_cell: _debug("wait_for_cell"); - ret = wait_on_bit(&cell->flags, AFS_CELL_FL_NOT_READY, TASK_INTERRUPTIBLE); - smp_rmb(); - - switch (READ_ONCE(cell->state)) { - case AFS_CELL_FAILED: + wait_var_event(&cell->state, + ({ + state = smp_load_acquire(&cell->state); /* vs error */ + state == AFS_CELL_ACTIVE || state == AFS_CELL_FAILED; + })); + + /* Check the state obtained from the wait check. */ + if (state == AFS_CELL_FAILED) { ret = cell->error; goto error; - default: - _debug("weird %u %d", cell->state, cell->error); - goto error; - case AFS_CELL_ACTIVE: - break; } _leave(" = %p [cell]", cell); @@ -360,16 +369,46 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) /* * Update a cell's VL server address list from the DNS. */ -static void afs_update_cell(struct afs_cell *cell) +static int afs_update_cell(struct afs_cell *cell) { - struct afs_vlserver_list *vllist, *old; + struct afs_vlserver_list *vllist, *old = NULL, *p; unsigned int min_ttl = READ_ONCE(afs_cell_min_ttl); unsigned int max_ttl = READ_ONCE(afs_cell_max_ttl); time64_t now, expiry = 0; + int ret = 0; _enter("%s", cell->name); vllist = afs_dns_query(cell, &expiry); + if (IS_ERR(vllist)) { + ret = PTR_ERR(vllist); + + _debug("%s: fail %d", cell->name, ret); + if (ret == -ENOMEM) + goto out_wake; + + ret = -ENOMEM; + vllist = afs_alloc_vlserver_list(0); + if (!vllist) + goto out_wake; + + switch (ret) { + case -ENODATA: + case -EDESTADDRREQ: + vllist->status = DNS_LOOKUP_GOT_NOT_FOUND; + break; + case -EAGAIN: + case -ECONNREFUSED: + vllist->status = DNS_LOOKUP_GOT_TEMP_FAILURE; + break; + default: + vllist->status = DNS_LOOKUP_GOT_LOCAL_FAILURE; + break; + } + } + + _debug("%s: got list %d %d", cell->name, vllist->source, vllist->status); + cell->dns_status = vllist->status; now = ktime_get_real_seconds(); if (min_ttl > max_ttl) @@ -379,48 +418,47 @@ static void afs_update_cell(struct afs_cell *cell) else if (expiry > now + max_ttl) expiry = now + max_ttl; - if (IS_ERR(vllist)) { - switch (PTR_ERR(vllist)) { - case -ENODATA: - case -EDESTADDRREQ: + _debug("%s: status %d", cell->name, vllist->status); + if (vllist->source == DNS_RECORD_UNAVAILABLE) { + switch (vllist->status) { + case DNS_LOOKUP_GOT_NOT_FOUND: /* The DNS said that the cell does not exist or there * weren't any addresses to be had. */ - set_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags); - clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags); cell->dns_expiry = expiry; break; - case -EAGAIN: - case -ECONNREFUSED: + case DNS_LOOKUP_BAD: + case DNS_LOOKUP_GOT_LOCAL_FAILURE: + case DNS_LOOKUP_GOT_TEMP_FAILURE: + case DNS_LOOKUP_GOT_NS_FAILURE: default: - set_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags); cell->dns_expiry = now + 10; break; } - - cell->error = -EDESTADDRREQ; } else { - clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags); - clear_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags); - - /* Exclusion on changing vl_addrs is achieved by a - * non-reentrant work item. - */ - old = rcu_dereference_protected(cell->vl_servers, true); - rcu_assign_pointer(cell->vl_servers, vllist); cell->dns_expiry = expiry; - - if (old) - afs_put_vlserverlist(cell->net, old); } - if (test_and_clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags)) - wake_up_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET); + /* Replace the VL server list if the new record has servers or the old + * record doesn't. + */ + write_lock(&cell->vl_servers_lock); + p = rcu_dereference_protected(cell->vl_servers, true); + if (vllist->nr_servers > 0 || p->nr_servers == 0) { + rcu_assign_pointer(cell->vl_servers, vllist); + cell->dns_source = vllist->source; + old = p; + } + write_unlock(&cell->vl_servers_lock); + afs_put_vlserverlist(cell->net, old); - now = ktime_get_real_seconds(); - afs_set_cell_timer(cell->net, cell->dns_expiry - now); - _leave(""); +out_wake: + smp_store_release(&cell->dns_lookup_count, + cell->dns_lookup_count + 1); /* vs source/status */ + wake_up_var(&cell->dns_lookup_count); + _leave(" = %d", ret); + return ret; } /* @@ -491,8 +529,7 @@ void afs_put_cell(struct afs_net *net, struct afs_cell *cell) now = ktime_get_real_seconds(); cell->last_inactive = now; expire_delay = 0; - if (!test_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags) && - !test_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags)) + if (cell->vl_servers->nr_servers) expire_delay = afs_cell_gc_delay; if (atomic_dec_return(&cell->usage) > 1) @@ -623,11 +660,13 @@ again: goto final_destruction; if (cell->state == AFS_CELL_FAILED) goto done; - cell->state = AFS_CELL_UNSET; + smp_store_release(&cell->state, AFS_CELL_UNSET); + wake_up_var(&cell->state); goto again; case AFS_CELL_UNSET: - cell->state = AFS_CELL_ACTIVATING; + smp_store_release(&cell->state, AFS_CELL_ACTIVATING); + wake_up_var(&cell->state); goto again; case AFS_CELL_ACTIVATING: @@ -635,28 +674,29 @@ again: if (ret < 0) goto activation_failed; - cell->state = AFS_CELL_ACTIVE; - smp_wmb(); - clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags); - wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY); + smp_store_release(&cell->state, AFS_CELL_ACTIVE); + wake_up_var(&cell->state); goto again; case AFS_CELL_ACTIVE: if (atomic_read(&cell->usage) > 1) { - time64_t now = ktime_get_real_seconds(); - if (cell->dns_expiry <= now && net->live) - afs_update_cell(cell); + if (test_and_clear_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags)) { + ret = afs_update_cell(cell); + if (ret < 0) + cell->error = ret; + } goto done; } - cell->state = AFS_CELL_DEACTIVATING; + smp_store_release(&cell->state, AFS_CELL_DEACTIVATING); + wake_up_var(&cell->state); goto again; case AFS_CELL_DEACTIVATING: - set_bit(AFS_CELL_FL_NOT_READY, &cell->flags); if (atomic_read(&cell->usage) > 1) goto reverse_deactivation; afs_deactivate_cell(net, cell); - cell->state = AFS_CELL_INACTIVE; + smp_store_release(&cell->state, AFS_CELL_INACTIVE); + wake_up_var(&cell->state); goto again; default: @@ -669,17 +709,13 @@ activation_failed: cell->error = ret; afs_deactivate_cell(net, cell); - cell->state = AFS_CELL_FAILED; - smp_wmb(); - if (test_and_clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags)) - wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY); + smp_store_release(&cell->state, AFS_CELL_FAILED); /* vs error */ + wake_up_var(&cell->state); goto again; reverse_deactivation: - cell->state = AFS_CELL_ACTIVE; - smp_wmb(); - clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags); - wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY); + smp_store_release(&cell->state, AFS_CELL_ACTIVE); + wake_up_var(&cell->state); _leave(" [deact->act]"); return; @@ -739,11 +775,16 @@ void afs_manage_cells(struct work_struct *work) } if (usage == 1) { + struct afs_vlserver_list *vllist; time64_t expire_at = cell->last_inactive; - if (!test_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags) && - !test_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags)) + read_lock(&cell->vl_servers_lock); + vllist = rcu_dereference_protected( + cell->vl_servers, + lockdep_is_held(&cell->vl_servers_lock)); + if (vllist->nr_servers > 0) expire_at += afs_cell_gc_delay; + read_unlock(&cell->vl_servers_lock); if (purging || expire_at <= now) sched_cell = true; else if (expire_at < next_manage) @@ -751,10 +792,8 @@ void afs_manage_cells(struct work_struct *work) } if (!purging) { - if (cell->dns_expiry <= now) + if (test_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags)) sched_cell = true; - else if (cell->dns_expiry <= next_manage) - next_manage = cell->dns_expiry; } if (sched_cell) diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 8ee5972893ed..01437cfe5432 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -34,7 +34,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *); static int afs_deliver_yfs_cb_callback(struct afs_call *); #define CM_NAME(name) \ - const char afs_SRXCB##name##_name[] __tracepoint_string = \ + char afs_SRXCB##name##_name[] __tracepoint_string = \ "CB." #name /* @@ -213,7 +213,7 @@ static int afs_find_cm_server_by_peer(struct afs_call *call) return 0; } - call->cm_server = server; + call->server = server; return afs_record_cm_probe(call, server); } @@ -234,7 +234,7 @@ static int afs_find_cm_server_by_uuid(struct afs_call *call, return 0; } - call->cm_server = server; + call->server = server; return afs_record_cm_probe(call, server); } @@ -260,8 +260,8 @@ static void SRXAFSCB_CallBack(struct work_struct *work) * server holds up change visibility till it receives our reply so as * to maintain cache coherency. */ - if (call->cm_server) - afs_break_callbacks(call->cm_server, call->count, call->request); + if (call->server) + afs_break_callbacks(call->server, call->count, call->request); afs_send_empty_reply(call); afs_put_call(call); @@ -285,6 +285,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) call->unmarshall++; /* extract the FID array and its count in two steps */ + /* fall through */ case 1: _debug("extract FID count"); ret = afs_extract_data(call, true); @@ -304,6 +305,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) afs_extract_to_buf(call, call->count * 3 * 4); call->unmarshall++; + /* Fall through */ case 2: _debug("extract FID array"); ret = afs_extract_data(call, true); @@ -329,6 +331,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) call->unmarshall++; /* extract the callback array and its count in two steps */ + /* fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -344,6 +347,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) iov_iter_discard(&call->iter, READ, call->count2 * 3 * 4); call->unmarshall++; + /* Fall through */ case 4: _debug("extract discard %zu/%u", iov_iter_count(&call->iter), call->count2 * 3 * 4); @@ -372,10 +376,10 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) { struct afs_call *call = container_of(work, struct afs_call, work); - _enter("{%p}", call->cm_server); + _enter("{%p}", call->server); - if (call->cm_server) - afs_init_callback_state(call->cm_server); + if (call->server) + afs_init_callback_state(call->server); afs_send_empty_reply(call); afs_put_call(call); _leave(""); @@ -422,6 +426,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) afs_extract_to_buf(call, 11 * sizeof(__be32)); call->unmarshall++; + /* Fall through */ case 1: _debug("extract UUID"); ret = afs_extract_data(call, false); @@ -537,6 +542,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) afs_extract_to_buf(call, 11 * sizeof(__be32)); call->unmarshall++; + /* Fall through */ case 1: _debug("extract UUID"); ret = afs_extract_data(call, false); @@ -673,6 +679,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call) call->unmarshall++; /* extract the FID array and its count in two steps */ + /* Fall through */ case 1: _debug("extract FID count"); ret = afs_extract_data(call, true); @@ -692,6 +699,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call) afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ case 2: _debug("extract FID array"); ret = afs_extract_data(call, false); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 8a2562e3a316..79d93a26759a 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/task_io_accounting_ops.h> #include "internal.h" +#include "afs_fs.h" #include "xdr_fs.h" static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, @@ -26,6 +27,7 @@ static int afs_dir_open(struct inode *inode, struct file *file); static int afs_readdir(struct file *file, struct dir_context *ctx); static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); static int afs_d_delete(const struct dentry *dentry); +static void afs_d_iput(struct dentry *dentry, struct inode *inode); static int afs_lookup_one_filldir(struct dir_context *ctx, const char *name, int nlen, loff_t fpos, u64 ino, unsigned dtype); static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen, @@ -85,6 +87,7 @@ const struct dentry_operations afs_fs_dentry_operations = { .d_delete = afs_d_delete, .d_release = afs_d_release, .d_automount = afs_d_automount, + .d_iput = afs_d_iput, }; struct afs_lookup_one_cookie { @@ -100,8 +103,8 @@ struct afs_lookup_cookie { bool found; bool one_only; unsigned short nr_fids; - struct afs_file_status *statuses; - struct afs_callback *callbacks; + struct inode **inodes; + struct afs_status_cb *statuses; struct afs_fid fids[50]; }; @@ -160,6 +163,38 @@ error: } /* + * Check the contents of a directory that we've just read. + */ +static bool afs_dir_check_pages(struct afs_vnode *dvnode, struct afs_read *req) +{ + struct afs_xdr_dir_page *dbuf; + unsigned int i, j, qty = PAGE_SIZE / sizeof(union afs_xdr_dir_block); + + for (i = 0; i < req->nr_pages; i++) + if (!afs_dir_check_page(dvnode, req->pages[i], req->actual_len)) + goto bad; + return true; + +bad: + pr_warn("DIR %llx:%llx f=%llx l=%llx al=%llx r=%llx\n", + dvnode->fid.vid, dvnode->fid.vnode, + req->file_size, req->len, req->actual_len, req->remain); + pr_warn("DIR %llx %x %x %x\n", + req->pos, req->index, req->nr_pages, req->offset); + + for (i = 0; i < req->nr_pages; i++) { + dbuf = kmap(req->pages[i]); + for (j = 0; j < qty; j++) { + union afs_xdr_dir_block *block = &dbuf->blocks[j]; + + pr_warn("[%02x] %32phN\n", i * qty + j, block); + } + kunmap(req->pages[i]); + } + return false; +} + +/* * open an AFS directory file */ static int afs_dir_open(struct inode *inode, struct file *file) @@ -277,6 +312,7 @@ retry: goto error; if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { + trace_afs_reload_dir(dvnode); ret = afs_fetch_data(dvnode, key, req); if (ret < 0) goto error_unlock; @@ -288,10 +324,8 @@ retry: /* Validate the data we just read. */ ret = -EIO; - for (i = 0; i < req->nr_pages; i++) - if (!afs_dir_check_page(dvnode, req->pages[i], - req->actual_len)) - goto error_unlock; + if (!afs_dir_check_pages(dvnode, req)) + goto error_unlock; // TODO: Trim excess pages @@ -605,12 +639,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, struct key *key) { struct afs_lookup_cookie *cookie; - struct afs_cb_interest *cbi = NULL; + struct afs_cb_interest *dcbi, *cbi = NULL; struct afs_super_info *as = dir->i_sb->s_fs_info; - struct afs_iget_data data; + struct afs_status_cb *scb; + struct afs_iget_data iget_data; struct afs_fs_cursor fc; - struct afs_vnode *dvnode = AFS_FS_I(dir); - struct inode *inode = NULL; + struct afs_server *server; + struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; + struct inode *inode = NULL, *ti; int ret, i; _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); @@ -624,10 +660,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, cookie->nr_fids = 1; /* slot 0 is saved for the fid we actually want */ read_seqlock_excl(&dvnode->cb_lock); - if (dvnode->cb_interest && - dvnode->cb_interest->server && - test_bit(AFS_SERVER_FL_NO_IBULK, &dvnode->cb_interest->server->flags)) - cookie->one_only = true; + dcbi = rcu_dereference_protected(dvnode->cb_interest, + lockdep_is_held(&dvnode->cb_lock.lock)); + if (dcbi) { + server = dcbi->server; + if (server && + test_bit(AFS_SERVER_FL_NO_IBULK, &server->flags)) + cookie->one_only = true; + } read_sequnlock_excl(&dvnode->cb_lock); for (i = 0; i < 50; i++) @@ -645,24 +685,43 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, goto out; /* Check to see if we already have an inode for the primary fid. */ - data.volume = dvnode->volume; - data.fid = cookie->fids[0]; - inode = ilookup5(dir->i_sb, cookie->fids[0].vnode, afs_iget5_test, &data); + iget_data.fid = cookie->fids[0]; + iget_data.volume = dvnode->volume; + iget_data.cb_v_break = dvnode->volume->cb_v_break; + iget_data.cb_s_break = 0; + inode = ilookup5(dir->i_sb, cookie->fids[0].vnode, + afs_iget5_test, &iget_data); if (inode) goto out; /* Need space for examining all the selected files */ inode = ERR_PTR(-ENOMEM); - cookie->statuses = kcalloc(cookie->nr_fids, sizeof(struct afs_file_status), - GFP_KERNEL); + cookie->statuses = kvcalloc(cookie->nr_fids, sizeof(struct afs_status_cb), + GFP_KERNEL); if (!cookie->statuses) goto out; - cookie->callbacks = kcalloc(cookie->nr_fids, sizeof(struct afs_callback), - GFP_KERNEL); - if (!cookie->callbacks) + cookie->inodes = kcalloc(cookie->nr_fids, sizeof(struct inode *), + GFP_KERNEL); + if (!cookie->inodes) goto out_s; + for (i = 1; i < cookie->nr_fids; i++) { + scb = &cookie->statuses[i]; + + /* Find any inodes that already exist and get their + * callback counters. + */ + iget_data.fid = cookie->fids[i]; + ti = ilookup5_nowait(dir->i_sb, iget_data.fid.vnode, + afs_iget5_test, &iget_data); + if (!IS_ERR_OR_NULL(ti)) { + vnode = AFS_FS_I(ti); + scb->cb_break = afs_calc_vnode_cb_break(vnode); + cookie->inodes[i] = ti; + } + } + /* Try FS.InlineBulkStatus first. Abort codes for the individual * lookups contained therein are stored in the reply without aborting * the whole operation. @@ -671,7 +730,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, goto no_inline_bulk_status; inode = ERR_PTR(-ERESTARTSYS); - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { while (afs_select_fileserver(&fc)) { if (test_bit(AFS_SERVER_FL_NO_IBULK, &fc.cbi->server->flags)) { @@ -679,11 +738,12 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, fc.ac.error = -ECONNABORTED; break; } + iget_data.cb_v_break = dvnode->volume->cb_v_break; + iget_data.cb_s_break = fc.cbi->server->cb_s_break; afs_fs_inline_bulk_status(&fc, afs_v2net(dvnode), cookie->fids, cookie->statuses, - cookie->callbacks, cookie->nr_fids, NULL); } @@ -704,15 +764,16 @@ no_inline_bulk_status: * any of the lookups fails - so, for the moment, revert to * FS.FetchStatus for just the primary fid. */ - cookie->nr_fids = 1; inode = ERR_PTR(-ERESTARTSYS); - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { while (afs_select_fileserver(&fc)) { + iget_data.cb_v_break = dvnode->volume->cb_v_break; + iget_data.cb_s_break = fc.cbi->server->cb_s_break; + scb = &cookie->statuses[0]; afs_fs_fetch_status(&fc, afs_v2net(dvnode), cookie->fids, - cookie->statuses, - cookie->callbacks, + scb, NULL); } @@ -724,26 +785,36 @@ no_inline_bulk_status: if (IS_ERR(inode)) goto out_c; - for (i = 0; i < cookie->nr_fids; i++) - cookie->statuses[i].abort_code = 0; - success: /* Turn all the files into inodes and save the first one - which is the * one we actually want. */ - if (cookie->statuses[0].abort_code != 0) - inode = ERR_PTR(afs_abort_to_error(cookie->statuses[0].abort_code)); + scb = &cookie->statuses[0]; + if (scb->status.abort_code != 0) + inode = ERR_PTR(afs_abort_to_error(scb->status.abort_code)); for (i = 0; i < cookie->nr_fids; i++) { - struct inode *ti; + struct afs_status_cb *scb = &cookie->statuses[i]; - if (cookie->statuses[i].abort_code != 0) + if (!scb->have_status && !scb->have_error) continue; - ti = afs_iget(dir->i_sb, key, &cookie->fids[i], - &cookie->statuses[i], - &cookie->callbacks[i], - cbi); + if (cookie->inodes[i]) { + afs_vnode_commit_status(&fc, AFS_FS_I(cookie->inodes[i]), + scb->cb_break, NULL, scb); + continue; + } + + if (scb->status.abort_code != 0) + continue; + + iget_data.fid = cookie->fids[i]; + ti = afs_iget(dir->i_sb, key, &iget_data, scb, cbi, dvnode); + if (!IS_ERR(ti)) + afs_cache_permit(AFS_FS_I(ti), key, + 0 /* Assume vnode->cb_break is 0 */ + + iget_data.cb_v_break, + scb); if (i == 0) { inode = ti; } else { @@ -754,9 +825,13 @@ success: out_c: afs_put_cb_interest(afs_v2net(dvnode), cbi); - kfree(cookie->callbacks); + if (cookie->inodes) { + for (i = 0; i < cookie->nr_fids; i++) + iput(cookie->inodes[i]); + kfree(cookie->inodes); + } out_s: - kfree(cookie->statuses); + kvfree(cookie->statuses); out: kfree(cookie); return inode; @@ -875,8 +950,14 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, (void *)(unsigned long)dvnode->status.data_version; } d = d_splice_alias(inode, dentry); - if (!IS_ERR_OR_NULL(d)) + if (!IS_ERR_OR_NULL(d)) { d->d_fsdata = dentry->d_fsdata; + trace_afs_lookup(dvnode, &d->d_name, + inode ? AFS_FS_I(inode) : NULL); + } else { + trace_afs_lookup(dvnode, &dentry->d_name, + inode ? AFS_FS_I(inode) : NULL); + } return d; } @@ -1053,6 +1134,16 @@ zap: } /* + * Clean up sillyrename files on dentry removal. + */ +static void afs_d_iput(struct dentry *dentry, struct inode *inode) +{ + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) + afs_silly_iput(dentry, inode); + iput(inode); +} + +/* * handle dentry release */ void afs_d_release(struct dentry *dentry) @@ -1065,9 +1156,8 @@ void afs_d_release(struct dentry *dentry) */ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, struct dentry *new_dentry, - struct afs_fid *newfid, - struct afs_file_status *newstatus, - struct afs_callback *newcb) + struct afs_iget_data *new_data, + struct afs_status_cb *new_scb) { struct afs_vnode *vnode; struct inode *inode; @@ -1076,7 +1166,7 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, return; inode = afs_iget(fc->vnode->vfs_inode.i_sb, fc->key, - newfid, newstatus, newcb, fc->cbi); + new_data, new_scb, fc->cbi, fc->vnode); if (IS_ERR(inode)) { /* ENOMEM or EINTR at a really inconvenient time - just abandon * the new directory on the server. @@ -1087,22 +1177,29 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, vnode = AFS_FS_I(inode); set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); - afs_vnode_commit_status(fc, vnode, 0); + if (fc->ac.error == 0) + afs_cache_permit(vnode, fc->key, vnode->cb_break, new_scb); d_instantiate(new_dentry, inode); } +static void afs_prep_for_new_inode(struct afs_fs_cursor *fc, + struct afs_iget_data *iget_data) +{ + iget_data->volume = fc->vnode->volume; + iget_data->cb_v_break = fc->vnode->volume->cb_v_break; + iget_data->cb_s_break = fc->cbi->server->cb_s_break; +} + /* * create a directory on an AFS filesystem */ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { - struct afs_file_status newstatus; + struct afs_iget_data iget_data; + struct afs_status_cb *scb; struct afs_fs_cursor fc; - struct afs_callback newcb; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct afs_fid newfid; struct key *key; - u64 data_version = dvnode->status.data_version; int ret; mode |= S_IFDIR; @@ -1110,23 +1207,32 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) _enter("{%llx:%llu},{%pd},%ho", dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_create(&fc, dentry->d_name.name, mode, data_version, - &newfid, &newstatus, &newcb); + afs_prep_for_new_inode(&fc, &iget_data); + afs_fs_create(&fc, dentry->d_name.name, mode, + &scb[0], &iget_data.fid, &scb[1]); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); - afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, &newcb); + afs_check_for_remote_deletion(&fc, dvnode); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) goto error_key; @@ -1136,15 +1242,18 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (ret == 0 && test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_add(dvnode, &dentry->d_name, &newfid, + afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, afs_edit_dir_for_create); key_put(key); + kfree(scb); _leave(" = 0"); return 0; error_key: key_put(key); +error_scb: + kfree(scb); error: d_drop(dentry); _leave(" = %d", ret); @@ -1171,15 +1280,19 @@ static void afs_dir_remove_subdir(struct dentry *dentry) */ static int afs_rmdir(struct inode *dir, struct dentry *dentry) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL; struct key *key; - u64 data_version = dvnode->status.data_version; int ret; _enter("{%llx:%llu},{%pd}", dvnode->fid.vid, dvnode->fid.vnode, dentry); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); @@ -1194,15 +1307,23 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) goto error_key; } + if (vnode) { + ret = down_write_killable(&vnode->rmdir_lock); + if (ret < 0) + goto error_key; + } + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_remove(&fc, vnode, dentry->d_name.name, true, - data_version); + afs_fs_remove(&fc, vnode, dentry->d_name.name, true, scb); } - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); if (ret == 0) { afs_dir_remove_subdir(dentry); @@ -1212,9 +1333,12 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) } } + if (vnode) + up_write(&vnode->rmdir_lock); error_key: key_put(key); error: + kfree(scb); return ret; } @@ -1228,32 +1352,27 @@ error: * However, if we didn't have a callback promise outstanding, or it was * outstanding on a different server, then it won't break it either... */ -static int afs_dir_remove_link(struct dentry *dentry, struct key *key, - unsigned long d_version_before, - unsigned long d_version_after) +static int afs_dir_remove_link(struct afs_vnode *dvnode, struct dentry *dentry, + struct key *key) { - bool dir_valid; int ret = 0; - /* There were no intervening changes on the server if the version - * number we got back was incremented by exactly 1. - */ - dir_valid = (d_version_after == d_version_before + 1); - if (d_really_is_positive(dentry)) { struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { /* Already done */ - } else if (dir_valid) { + } else if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { + write_seqlock(&vnode->cb_lock); drop_nlink(&vnode->vfs_inode); if (vnode->vfs_inode.i_nlink == 0) { set_bit(AFS_VNODE_DELETED, &vnode->flags); - clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + __afs_break_callback(vnode); } + write_sequnlock(&vnode->cb_lock); ret = 0; } else { - clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + afs_break_callback(vnode); if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) kdebug("AFS_VNODE_DELETED"); @@ -1274,10 +1393,10 @@ static int afs_dir_remove_link(struct dentry *dentry, struct key *key, static int afs_unlink(struct inode *dir, struct dentry *dentry) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL; struct key *key; - unsigned long d_version = (unsigned long)dentry->d_fsdata; - u64 data_version = dvnode->status.data_version; + bool need_rehash = false; int ret; _enter("{%llx:%llu},{%pd}", @@ -1286,10 +1405,15 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) if (dentry->d_name.len >= AFSNAMEMAX) return -ENAMETOOLONG; + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } /* Try to make sure we have a callback promise on the victim. */ @@ -1300,39 +1424,63 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) goto error_key; } + spin_lock(&dentry->d_lock); + if (vnode && d_count(dentry) > 1) { + spin_unlock(&dentry->d_lock); + /* Start asynchronous writeout of the inode */ + write_inode_now(d_inode(dentry), 0); + ret = afs_sillyrename(dvnode, vnode, dentry, key); + goto error_key; + } + if (!d_unhashed(dentry)) { + /* Prevent a race with RCU lookup. */ + __d_drop(dentry); + need_rehash = true; + } + spin_unlock(&dentry->d_lock); + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + afs_dataversion_t data_version_2 = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); + fc.cb_break_2 = afs_calc_vnode_cb_break(vnode); if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) && !test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) { yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name, - data_version); + &scb[0], &scb[1]); if (fc.ac.error != -ECONNABORTED || fc.ac.abort_code != RXGEN_OPCODE) continue; set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags); } - afs_fs_remove(&fc, vnode, dentry->d_name.name, false, - data_version); + afs_fs_remove(&fc, vnode, dentry->d_name.name, false, &scb[0]); } - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, + &data_version_2, &scb[1]); ret = afs_end_vnode_operation(&fc); - if (ret == 0) - ret = afs_dir_remove_link( - dentry, key, d_version, - (unsigned long)dvnode->status.data_version); + if (ret == 0 && !(scb[1].have_status || scb[1].have_error)) + ret = afs_dir_remove_link(dvnode, dentry, key); if (ret == 0 && test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_edit_dir_remove(dvnode, &dentry->d_name, afs_edit_dir_for_unlink); } + if (need_rehash && ret < 0 && ret != -ENOENT) + d_rehash(dentry); + error_key: key_put(key); +error_scb: + kfree(scb); error: _leave(" = %d", ret); return ret; @@ -1344,13 +1492,11 @@ error: static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { + struct afs_iget_data iget_data; struct afs_fs_cursor fc; - struct afs_file_status newstatus; - struct afs_callback newcb; + struct afs_status_cb *scb; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct afs_fid newfid; struct key *key; - u64 data_version = dvnode->status.data_version; int ret; mode |= S_IFREG; @@ -1368,17 +1514,26 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, goto error; } + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error_scb; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_create(&fc, dentry->d_name.name, mode, data_version, - &newfid, &newstatus, &newcb); + afs_prep_for_new_inode(&fc, &iget_data); + afs_fs_create(&fc, dentry->d_name.name, mode, + &scb[0], &iget_data.fid, &scb[1]); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); - afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, &newcb); + afs_check_for_remote_deletion(&fc, dvnode); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) goto error_key; @@ -1387,13 +1542,16 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, } if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_add(dvnode, &dentry->d_name, &newfid, + afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, afs_edit_dir_for_create); + kfree(scb); key_put(key); _leave(" = 0"); return 0; +error_scb: + kfree(scb); error_key: key_put(key); error: @@ -1409,15 +1567,12 @@ static int afs_link(struct dentry *from, struct inode *dir, struct dentry *dentry) { struct afs_fs_cursor fc; - struct afs_vnode *dvnode, *vnode; + struct afs_status_cb *scb; + struct afs_vnode *dvnode = AFS_FS_I(dir); + struct afs_vnode *vnode = AFS_FS_I(d_inode(from)); struct key *key; - u64 data_version; int ret; - vnode = AFS_FS_I(d_inode(from)); - dvnode = AFS_FS_I(dir); - data_version = dvnode->status.data_version; - _enter("{%llx:%llu},{%llx:%llu},{%pd}", vnode->fid.vid, vnode->fid.vnode, dvnode->fid.vid, dvnode->fid.vnode, @@ -1427,14 +1582,21 @@ static int afs_link(struct dentry *from, struct inode *dir, if (dentry->d_name.len >= AFSNAMEMAX) goto error; + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + if (mutex_lock_interruptible_nested(&vnode->io_lock, 1) < 0) { afs_end_vnode_operation(&fc); goto error_key; @@ -1443,11 +1605,14 @@ static int afs_link(struct dentry *from, struct inode *dir, while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); fc.cb_break_2 = afs_calc_vnode_cb_break(vnode); - afs_fs_link(&fc, vnode, dentry->d_name.name, data_version); + afs_fs_link(&fc, vnode, dentry->d_name.name, + &scb[0], &scb[1]); } - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); - afs_vnode_commit_status(&fc, vnode, fc.cb_break_2); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, + NULL, &scb[1]); ihold(&vnode->vfs_inode); d_instantiate(dentry, &vnode->vfs_inode); @@ -1464,11 +1629,14 @@ static int afs_link(struct dentry *from, struct inode *dir, afs_edit_dir_for_link); key_put(key); + kfree(scb); _leave(" = 0"); return 0; error_key: key_put(key); +error_scb: + kfree(scb); error: d_drop(dentry); _leave(" = %d", ret); @@ -1481,12 +1649,11 @@ error: static int afs_symlink(struct inode *dir, struct dentry *dentry, const char *content) { + struct afs_iget_data iget_data; struct afs_fs_cursor fc; - struct afs_file_status newstatus; + struct afs_status_cb *scb; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct afs_fid newfid; struct key *key; - u64 data_version = dvnode->status.data_version; int ret; _enter("{%llx:%llu},{%pd},%s", @@ -1501,24 +1668,32 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, if (strlen(content) >= AFSPATHMAX) goto error; + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_symlink(&fc, dentry->d_name.name, - content, data_version, - &newfid, &newstatus); + afs_prep_for_new_inode(&fc, &iget_data); + afs_fs_symlink(&fc, dentry->d_name.name, content, + &scb[0], &iget_data.fid, &scb[1]); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); - afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, NULL); + afs_check_for_remote_deletion(&fc, dvnode); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) goto error_key; @@ -1527,15 +1702,18 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, } if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_add(dvnode, &dentry->d_name, &newfid, + afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, afs_edit_dir_for_symlink); key_put(key); + kfree(scb); _leave(" = 0"); return 0; error_key: key_put(key); +error_scb: + kfree(scb); error: d_drop(dentry); _leave(" = %d", ret); @@ -1550,20 +1728,24 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, unsigned int flags) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *orig_dvnode, *new_dvnode, *vnode; + struct dentry *tmp = NULL, *rehash = NULL; + struct inode *new_inode; struct key *key; - u64 orig_data_version, new_data_version; bool new_negative = d_is_negative(new_dentry); int ret; if (flags) return -EINVAL; + /* Don't allow silly-rename files be moved around. */ + if (old_dentry->d_flags & DCACHE_NFSFS_RENAMED) + return -EINVAL; + vnode = AFS_FS_I(d_inode(old_dentry)); orig_dvnode = AFS_FS_I(old_dir); new_dvnode = AFS_FS_I(new_dir); - orig_data_version = orig_dvnode->status.data_version; - new_data_version = new_dvnode->status.data_version; _enter("{%llx:%llu},{%llx:%llu},{%llx:%llu},{%pd}", orig_dvnode->fid.vid, orig_dvnode->fid.vnode, @@ -1571,54 +1753,126 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dvnode->fid.vid, new_dvnode->fid.vnode, new_dentry); + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(orig_dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; + } + + /* For non-directories, check whether the target is busy and if so, + * make a copy of the dentry and then do a silly-rename. If the + * silly-rename succeeds, the copied dentry is hashed and becomes the + * new target. + */ + if (d_is_positive(new_dentry) && !d_is_dir(new_dentry)) { + /* To prevent any new references to the target during the + * rename, we unhash the dentry in advance. + */ + if (!d_unhashed(new_dentry)) { + d_drop(new_dentry); + rehash = new_dentry; + } + + if (d_count(new_dentry) > 2) { + /* copy the target dentry's name */ + ret = -ENOMEM; + tmp = d_alloc(new_dentry->d_parent, + &new_dentry->d_name); + if (!tmp) + goto error_rehash; + + ret = afs_sillyrename(new_dvnode, + AFS_FS_I(d_inode(new_dentry)), + new_dentry, key); + if (ret) + goto error_rehash; + + new_dentry = tmp; + rehash = NULL; + new_negative = true; + } } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, orig_dvnode, key)) { + if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) { + afs_dataversion_t orig_data_version; + afs_dataversion_t new_data_version; + struct afs_status_cb *new_scb = &scb[1]; + + orig_data_version = orig_dvnode->status.data_version + 1; + if (orig_dvnode != new_dvnode) { if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) { afs_end_vnode_operation(&fc); - goto error_key; + goto error_rehash; } + new_data_version = new_dvnode->status.data_version; + } else { + new_data_version = orig_data_version; + new_scb = &scb[0]; } + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode); fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode); afs_fs_rename(&fc, old_dentry->d_name.name, new_dvnode, new_dentry->d_name.name, - orig_data_version, new_data_version); + &scb[0], new_scb); } - afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break); - afs_vnode_commit_status(&fc, new_dvnode, fc.cb_break_2); - if (orig_dvnode != new_dvnode) + afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break, + &orig_data_version, &scb[0]); + if (new_dvnode != orig_dvnode) { + afs_vnode_commit_status(&fc, new_dvnode, fc.cb_break_2, + &new_data_version, &scb[1]); mutex_unlock(&new_dvnode->io_lock); + } ret = afs_end_vnode_operation(&fc); if (ret < 0) - goto error_key; + goto error_rehash; } if (ret == 0) { + if (rehash) + d_rehash(rehash); if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags)) afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name, - afs_edit_dir_for_rename); + afs_edit_dir_for_rename_0); if (!new_negative && test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags)) afs_edit_dir_remove(new_dvnode, &new_dentry->d_name, - afs_edit_dir_for_rename); + afs_edit_dir_for_rename_1); if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags)) afs_edit_dir_add(new_dvnode, &new_dentry->d_name, - &vnode->fid, afs_edit_dir_for_rename); + &vnode->fid, afs_edit_dir_for_rename_2); + + new_inode = d_inode(new_dentry); + if (new_inode) { + spin_lock(&new_inode->i_lock); + if (new_inode->i_nlink > 0) + drop_nlink(new_inode); + spin_unlock(&new_inode->i_lock); + } + d_move(old_dentry, new_dentry); + goto error_tmp; } -error_key: +error_rehash: + if (rehash) + d_rehash(rehash); +error_tmp: + if (tmp) + dput(tmp); key_put(key); +error_scb: + kfree(scb); error: _leave(" = %d", ret); return ret; diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c new file mode 100644 index 000000000000..28f4aa015229 --- /dev/null +++ b/fs/afs/dir_silly.c @@ -0,0 +1,254 @@ +/* AFS silly rename handling + * + * Copyright (C) 2019 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * - Derived from NFS's sillyrename. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/fsnotify.h> +#include "internal.h" + +/* + * Actually perform the silly rename step. + */ +static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode, + struct dentry *old, struct dentry *new, + struct key *key) +{ + struct afs_fs_cursor fc; + struct afs_status_cb *scb; + int ret = -ERESTARTSYS; + + _enter("%pd,%pd", old, new); + + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + + trace_afs_silly_rename(vnode, false); + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t dir_data_version = dvnode->status.data_version + 1; + + while (afs_select_fileserver(&fc)) { + fc.cb_break = afs_calc_vnode_cb_break(dvnode); + afs_fs_rename(&fc, old->d_name.name, + dvnode, new->d_name.name, + scb, scb); + } + + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &dir_data_version, scb); + ret = afs_end_vnode_operation(&fc); + } + + if (ret == 0) { + spin_lock(&old->d_lock); + old->d_flags |= DCACHE_NFSFS_RENAMED; + spin_unlock(&old->d_lock); + if (dvnode->silly_key != key) { + key_put(dvnode->silly_key); + dvnode->silly_key = key_get(key); + } + + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + afs_edit_dir_remove(dvnode, &old->d_name, + afs_edit_dir_for_silly_0); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + afs_edit_dir_add(dvnode, &new->d_name, + &vnode->fid, afs_edit_dir_for_silly_1); + + /* vfs_unlink and the like do not issue this when a file is + * sillyrenamed, so do it here. + */ + fsnotify_nameremove(old, 0); + } + + kfree(scb); + _leave(" = %d", ret); + return ret; +} + +/** + * afs_sillyrename - Perform a silly-rename of a dentry + * + * AFS is stateless and the server doesn't know when the client is holding a + * file open. To prevent application problems when a file is unlinked while + * it's still open, the client performs a "silly-rename". That is, it renames + * the file to a hidden file in the same directory, and only performs the + * unlink once the last reference to it is put. + * + * The final cleanup is done during dentry_iput. + */ +int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode, + struct dentry *dentry, struct key *key) +{ + static unsigned int sillycounter; + struct dentry *sdentry = NULL; + unsigned char silly[16]; + int ret = -EBUSY; + + _enter(""); + + /* We don't allow a dentry to be silly-renamed twice. */ + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) + return -EBUSY; + + sdentry = NULL; + do { + int slen; + + dput(sdentry); + sillycounter++; + + /* Create a silly name. Note that the ".__afs" prefix is + * understood by the salvager and must not be changed. + */ + slen = scnprintf(silly, sizeof(silly), ".__afs%04X", sillycounter); + sdentry = lookup_one_len(silly, dentry->d_parent, slen); + + /* N.B. Better to return EBUSY here ... it could be dangerous + * to delete the file while it's in use. + */ + if (IS_ERR(sdentry)) + goto out; + } while (!d_is_negative(sdentry)); + + ihold(&vnode->vfs_inode); + + ret = afs_do_silly_rename(dvnode, vnode, dentry, sdentry, key); + switch (ret) { + case 0: + /* The rename succeeded. */ + d_move(dentry, sdentry); + break; + case -ERESTARTSYS: + /* The result of the rename is unknown. Play it safe by forcing + * a new lookup. + */ + d_drop(dentry); + d_drop(sdentry); + } + + iput(&vnode->vfs_inode); + dput(sdentry); +out: + _leave(" = %d", ret); + return ret; +} + +/* + * Tell the server to remove a sillyrename file. + */ +static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode, + struct dentry *dentry, struct key *key) +{ + struct afs_fs_cursor fc; + struct afs_status_cb *scb; + int ret = -ERESTARTSYS; + + _enter(""); + + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + + trace_afs_silly_rename(vnode, true); + if (afs_begin_vnode_operation(&fc, dvnode, key, false)) { + afs_dataversion_t dir_data_version = dvnode->status.data_version + 1; + + while (afs_select_fileserver(&fc)) { + fc.cb_break = afs_calc_vnode_cb_break(dvnode); + + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) && + !test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) { + yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name, + &scb[0], &scb[1]); + if (fc.ac.error != -ECONNABORTED || + fc.ac.abort_code != RXGEN_OPCODE) + continue; + set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags); + } + + afs_fs_remove(&fc, vnode, dentry->d_name.name, false, &scb[0]); + } + + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &dir_data_version, &scb[0]); + ret = afs_end_vnode_operation(&fc); + if (ret == 0) { + drop_nlink(&vnode->vfs_inode); + if (vnode->vfs_inode.i_nlink == 0) { + set_bit(AFS_VNODE_DELETED, &vnode->flags); + clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } + } + if (ret == 0 && + test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + afs_edit_dir_remove(dvnode, &dentry->d_name, + afs_edit_dir_for_unlink); + } + + kfree(scb); + _leave(" = %d", ret); + return ret; +} + +/* + * Remove sillyrename file on iput. + */ +int afs_silly_iput(struct dentry *dentry, struct inode *inode) +{ + struct afs_vnode *dvnode = AFS_FS_I(d_inode(dentry->d_parent)); + struct afs_vnode *vnode = AFS_FS_I(inode); + struct dentry *alias; + int ret; + + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + + _enter("%p{%pd},%llx", dentry, dentry, vnode->fid.vnode); + + down_read(&dvnode->rmdir_lock); + + alias = d_alloc_parallel(dentry->d_parent, &dentry->d_name, &wq); + if (IS_ERR(alias)) { + up_read(&dvnode->rmdir_lock); + return 0; + } + + if (!d_in_lookup(alias)) { + /* We raced with lookup... See if we need to transfer the + * sillyrename information to the aliased dentry. + */ + ret = 0; + spin_lock(&alias->d_lock); + if (d_really_is_positive(alias) && + !(alias->d_flags & DCACHE_NFSFS_RENAMED)) { + alias->d_flags |= DCACHE_NFSFS_RENAMED; + ret = 1; + } + spin_unlock(&alias->d_lock); + up_read(&dvnode->rmdir_lock); + dput(alias); + return ret; + } + + /* Stop lock-release from complaining. */ + spin_lock(&vnode->lock); + vnode->lock_state = AFS_VNODE_LOCK_DELETED; + trace_afs_flock_ev(vnode, NULL, afs_flock_silly_delete, 0); + spin_unlock(&vnode->lock); + + afs_do_silly_unlink(dvnode, vnode, dentry, dvnode->silly_key); + up_read(&dvnode->rmdir_lock); + d_lookup_done(alias); + dput(alias); + return 1; +} diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index a9ba81ddf154..af1689d1f32e 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -46,7 +46,7 @@ static int afs_probe_cell_name(struct dentry *dentry) return 0; } - ret = dns_query("afsdb", name, len, "srv=1", NULL, NULL); + ret = dns_query("afsdb", name, len, "srv=1", NULL, NULL, false); if (ret == -ENODATA) ret = -EDESTADDRREQ; return ret; @@ -261,8 +261,7 @@ int afs_dynroot_populate(struct super_block *sb) struct afs_net *net = afs_sb2net(sb); int ret; - if (mutex_lock_interruptible(&net->proc_cells_lock) < 0) - return -ERESTARTSYS; + mutex_lock(&net->proc_cells_lock); net->dynroot_sb = sb; hlist_for_each_entry(cell, &net->proc_cells, proc_link) { diff --git a/fs/afs/file.c b/fs/afs/file.c index 323ae9912203..11e69c5fb7ab 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -170,11 +170,12 @@ int afs_release(struct inode *inode, struct file *file) { struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_file *af = file->private_data; + int ret = 0; _enter("{%llx:%llu},", vnode->fid.vid, vnode->fid.vnode); if ((file->f_mode & FMODE_WRITE)) - return vfs_fsync(file, 0); + ret = vfs_fsync(file, 0); file->private_data = NULL; if (af->wb) @@ -182,8 +183,8 @@ int afs_release(struct inode *inode, struct file *file) key_put(af->key); kfree(af); afs_prune_wb_keys(vnode); - _leave(" = 0"); - return 0; + _leave(" = %d", ret); + return ret; } /* @@ -227,6 +228,7 @@ static void afs_file_readpage_read_complete(struct page *page, int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *desc) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; int ret; _enter("%s{%llx:%llu.%u},%x,,,", @@ -236,15 +238,22 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de vnode->fid.unique, key_serial(key)); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_fetch_data(&fc, desc); + afs_fs_fetch_data(&fc, scb, desc); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); } @@ -254,6 +263,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de &afs_v2net(vnode)->n_fetch_bytes); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -300,6 +310,8 @@ int afs_page_filler(void *data, struct page *page) /* page will not be cached */ case -ENOBUFS: _debug("cache said ENOBUFS"); + + /* fall through */ default: go_on: req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *), @@ -402,10 +414,10 @@ static int afs_readpage(struct file *file, struct page *page) /* * Make pages available as they're filled. */ -static void afs_readpages_page_done(struct afs_call *call, struct afs_read *req) +static void afs_readpages_page_done(struct afs_read *req) { #ifdef CONFIG_AFS_FSCACHE - struct afs_vnode *vnode = call->reply[0]; + struct afs_vnode *vnode = req->vnode; #endif struct page *page = req->pages[req->index]; @@ -459,6 +471,7 @@ static int afs_readpages_one(struct file *file, struct address_space *mapping, return -ENOMEM; refcount_set(&req->usage, 1); + req->vnode = vnode; req->page_done = afs_readpages_page_done; req->pos = first->index; req->pos <<= PAGE_SHIFT; diff --git a/fs/afs/flock.c b/fs/afs/flock.c index e432bd27a2e7..ed3ac03682d7 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -13,9 +13,11 @@ #define AFS_LOCK_GRANTED 0 #define AFS_LOCK_PENDING 1 +#define AFS_LOCK_YOUR_TRY 2 struct workqueue_struct *afs_lock_manager; +static void afs_next_locker(struct afs_vnode *vnode, int error); static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl); static void afs_fl_release_private(struct file_lock *fl); @@ -24,6 +26,14 @@ static const struct file_lock_operations afs_lock_ops = { .fl_release_private = afs_fl_release_private, }; +static inline void afs_set_lock_state(struct afs_vnode *vnode, enum afs_lock_state state) +{ + _debug("STATE %u -> %u", vnode->lock_state, state); + vnode->lock_state = state; +} + +static atomic_t afs_file_lock_debug_id; + /* * if the callback is broken on this vnode, then the lock may now be available */ @@ -31,7 +41,11 @@ void afs_lock_may_be_available(struct afs_vnode *vnode) { _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); - queue_delayed_work(afs_lock_manager, &vnode->lock_work, 0); + spin_lock(&vnode->lock); + if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB) + afs_next_locker(vnode, 0); + trace_afs_flock_ev(vnode, NULL, afs_flock_callback_break, 0); + spin_unlock(&vnode->lock); } /* @@ -40,8 +54,35 @@ void afs_lock_may_be_available(struct afs_vnode *vnode) */ static void afs_schedule_lock_extension(struct afs_vnode *vnode) { - queue_delayed_work(afs_lock_manager, &vnode->lock_work, - AFS_LOCKWAIT * HZ / 2); + ktime_t expires_at, now, duration; + u64 duration_j; + + expires_at = ktime_add_ms(vnode->locked_at, AFS_LOCKWAIT * 1000 / 2); + now = ktime_get_real(); + duration = ktime_sub(expires_at, now); + if (duration <= 0) + duration_j = 0; + else + duration_j = nsecs_to_jiffies(ktime_to_ns(duration)); + + queue_delayed_work(afs_lock_manager, &vnode->lock_work, duration_j); +} + +/* + * In the case of successful completion of a lock operation, record the time + * the reply appeared and start the lock extension timer. + */ +void afs_lock_op_done(struct afs_call *call) +{ + struct afs_vnode *vnode = call->lvnode; + + if (call->error == 0) { + spin_lock(&vnode->lock); + trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0); + vnode->locked_at = call->reply_time; + afs_schedule_lock_extension(vnode); + spin_unlock(&vnode->lock); + } } /* @@ -49,22 +90,90 @@ static void afs_schedule_lock_extension(struct afs_vnode *vnode) * first lock in the queue is itself a readlock) * - the caller must hold the vnode lock */ -static void afs_grant_locks(struct afs_vnode *vnode, struct file_lock *fl) +static void afs_grant_locks(struct afs_vnode *vnode) { struct file_lock *p, *_p; + bool exclusive = (vnode->lock_type == AFS_LOCK_WRITE); - list_move_tail(&fl->fl_u.afs.link, &vnode->granted_locks); - if (fl->fl_type == F_RDLCK) { - list_for_each_entry_safe(p, _p, &vnode->pending_locks, - fl_u.afs.link) { - if (p->fl_type == F_RDLCK) { - p->fl_u.afs.state = AFS_LOCK_GRANTED; - list_move_tail(&p->fl_u.afs.link, - &vnode->granted_locks); - wake_up(&p->fl_wait); - } + list_for_each_entry_safe(p, _p, &vnode->pending_locks, fl_u.afs.link) { + if (!exclusive && p->fl_type == F_WRLCK) + continue; + + list_move_tail(&p->fl_u.afs.link, &vnode->granted_locks); + p->fl_u.afs.state = AFS_LOCK_GRANTED; + trace_afs_flock_op(vnode, p, afs_flock_op_grant); + wake_up(&p->fl_wait); + } +} + +/* + * If an error is specified, reject every pending lock that matches the + * authentication and type of the lock we failed to get. If there are any + * remaining lockers, try to wake up one of them to have a go. + */ +static void afs_next_locker(struct afs_vnode *vnode, int error) +{ + struct file_lock *p, *_p, *next = NULL; + struct key *key = vnode->lock_key; + unsigned int fl_type = F_RDLCK; + + _enter(""); + + if (vnode->lock_type == AFS_LOCK_WRITE) + fl_type = F_WRLCK; + + list_for_each_entry_safe(p, _p, &vnode->pending_locks, fl_u.afs.link) { + if (error && + p->fl_type == fl_type && + afs_file_key(p->fl_file) == key) { + list_del_init(&p->fl_u.afs.link); + p->fl_u.afs.state = error; + wake_up(&p->fl_wait); } + + /* Select the next locker to hand off to. */ + if (next && + (next->fl_type == F_WRLCK || p->fl_type == F_RDLCK)) + continue; + next = p; + } + + vnode->lock_key = NULL; + key_put(key); + + if (next) { + afs_set_lock_state(vnode, AFS_VNODE_LOCK_SETTING); + next->fl_u.afs.state = AFS_LOCK_YOUR_TRY; + trace_afs_flock_op(vnode, next, afs_flock_op_wake); + wake_up(&next->fl_wait); + } else { + afs_set_lock_state(vnode, AFS_VNODE_LOCK_NONE); + trace_afs_flock_ev(vnode, NULL, afs_flock_no_lockers, 0); } + + _leave(""); +} + +/* + * Kill off all waiters in the the pending lock queue due to the vnode being + * deleted. + */ +static void afs_kill_lockers_enoent(struct afs_vnode *vnode) +{ + struct file_lock *p; + + afs_set_lock_state(vnode, AFS_VNODE_LOCK_DELETED); + + while (!list_empty(&vnode->pending_locks)) { + p = list_entry(vnode->pending_locks.next, + struct file_lock, fl_u.afs.link); + list_del_init(&p->fl_u.afs.link); + p->fl_u.afs.state = -ENOENT; + wake_up(&p->fl_wait); + } + + key_put(vnode->lock_key); + vnode->lock_key = NULL; } /* @@ -73,6 +182,7 @@ static void afs_grant_locks(struct afs_vnode *vnode, struct file_lock *fl) static int afs_set_lock(struct afs_vnode *vnode, struct key *key, afs_lock_type_t type) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; int ret; @@ -83,18 +193,23 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key, vnode->fid.unique, key_serial(key), type); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_set_lock(&fc, type); + afs_fs_set_lock(&fc, type, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); ret = afs_end_vnode_operation(&fc); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -104,6 +219,7 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key, */ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; int ret; @@ -114,18 +230,23 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) vnode->fid.unique, key_serial(key)); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, false)) { while (afs_select_current_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_extend_lock(&fc); + afs_fs_extend_lock(&fc, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); ret = afs_end_vnode_operation(&fc); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -135,6 +256,7 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) */ static int afs_release_lock(struct afs_vnode *vnode, struct key *key) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; int ret; @@ -145,18 +267,23 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key) vnode->fid.unique, key_serial(key)); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, false)) { while (afs_select_current_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_release_lock(&fc); + afs_fs_release_lock(&fc, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); ret = afs_end_vnode_operation(&fc); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -170,8 +297,6 @@ void afs_lock_work(struct work_struct *work) { struct afs_vnode *vnode = container_of(work, struct afs_vnode, lock_work.work); - struct file_lock *fl, *next; - afs_lock_type_t type; struct key *key; int ret; @@ -183,35 +308,28 @@ again: _debug("wstate %u for %p", vnode->lock_state, vnode); switch (vnode->lock_state) { case AFS_VNODE_LOCK_NEED_UNLOCK: - _debug("unlock"); - vnode->lock_state = AFS_VNODE_LOCK_UNLOCKING; + afs_set_lock_state(vnode, AFS_VNODE_LOCK_UNLOCKING); + trace_afs_flock_ev(vnode, NULL, afs_flock_work_unlocking, 0); spin_unlock(&vnode->lock); /* attempt to release the server lock; if it fails, we just * wait 5 minutes and it'll expire anyway */ ret = afs_release_lock(vnode, vnode->lock_key); - if (ret < 0) + if (ret < 0 && vnode->lock_state != AFS_VNODE_LOCK_DELETED) { + trace_afs_flock_ev(vnode, NULL, afs_flock_release_fail, + ret); printk(KERN_WARNING "AFS:" " Failed to release lock on {%llx:%llx} error %d\n", vnode->fid.vid, vnode->fid.vnode, ret); - - spin_lock(&vnode->lock); - key_put(vnode->lock_key); - vnode->lock_key = NULL; - vnode->lock_state = AFS_VNODE_LOCK_NONE; - - if (list_empty(&vnode->pending_locks)) { - spin_unlock(&vnode->lock); - return; } - /* The new front of the queue now owns the state variables. */ - next = list_entry(vnode->pending_locks.next, - struct file_lock, fl_u.afs.link); - vnode->lock_key = key_get(afs_file_key(next->fl_file)); - vnode->lock_type = (next->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; - vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB; - goto again; + spin_lock(&vnode->lock); + if (ret == -ENOENT) + afs_kill_lockers_enoent(vnode); + else + afs_next_locker(vnode, 0); + spin_unlock(&vnode->lock); + return; /* If we've already got a lock, then it must be time to extend that * lock as AFS locks time out after 5 minutes. @@ -222,87 +340,57 @@ again: ASSERT(!list_empty(&vnode->granted_locks)); key = key_get(vnode->lock_key); - vnode->lock_state = AFS_VNODE_LOCK_EXTENDING; + afs_set_lock_state(vnode, AFS_VNODE_LOCK_EXTENDING); + trace_afs_flock_ev(vnode, NULL, afs_flock_work_extending, 0); spin_unlock(&vnode->lock); ret = afs_extend_lock(vnode, key); /* RPC */ key_put(key); - if (ret < 0) + if (ret < 0) { + trace_afs_flock_ev(vnode, NULL, afs_flock_extend_fail, + ret); pr_warning("AFS: Failed to extend lock on {%llx:%llx} error %d\n", vnode->fid.vid, vnode->fid.vnode, ret); + } spin_lock(&vnode->lock); + if (ret == -ENOENT) { + afs_kill_lockers_enoent(vnode); + spin_unlock(&vnode->lock); + return; + } + if (vnode->lock_state != AFS_VNODE_LOCK_EXTENDING) goto again; - vnode->lock_state = AFS_VNODE_LOCK_GRANTED; + afs_set_lock_state(vnode, AFS_VNODE_LOCK_GRANTED); - if (ret == 0) - afs_schedule_lock_extension(vnode); - else + if (ret != 0) queue_delayed_work(afs_lock_manager, &vnode->lock_work, HZ * 10); spin_unlock(&vnode->lock); _leave(" [ext]"); return; - /* If we don't have a granted lock, then we must've been called - * back by the server, and so if might be possible to get a - * lock we're currently waiting for. - */ + /* If we're waiting for a callback to indicate lock release, we can't + * actually rely on this, so need to recheck at regular intervals. The + * problem is that the server might not notify us if the lock just + * expires (say because a client died) rather than being explicitly + * released. + */ case AFS_VNODE_LOCK_WAITING_FOR_CB: - _debug("get"); - - key = key_get(vnode->lock_key); - type = vnode->lock_type; - vnode->lock_state = AFS_VNODE_LOCK_SETTING; + _debug("retry"); + afs_next_locker(vnode, 0); spin_unlock(&vnode->lock); + return; - ret = afs_set_lock(vnode, key, type); /* RPC */ - key_put(key); - - spin_lock(&vnode->lock); - switch (ret) { - case -EWOULDBLOCK: - _debug("blocked"); - break; - case 0: - _debug("acquired"); - vnode->lock_state = AFS_VNODE_LOCK_GRANTED; - /* Fall through */ - default: - /* Pass the lock or the error onto the first locker in - * the list - if they're looking for this type of lock. - * If they're not, we assume that whoever asked for it - * took a signal. - */ - if (list_empty(&vnode->pending_locks)) { - _debug("withdrawn"); - vnode->lock_state = AFS_VNODE_LOCK_NEED_UNLOCK; - goto again; - } - - fl = list_entry(vnode->pending_locks.next, - struct file_lock, fl_u.afs.link); - type = (fl->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; - if (vnode->lock_type != type) { - _debug("changed"); - vnode->lock_state = AFS_VNODE_LOCK_NEED_UNLOCK; - goto again; - } - - fl->fl_u.afs.state = ret; - if (ret == 0) - afs_grant_locks(vnode, fl); - else - list_del_init(&fl->fl_u.afs.link); - wake_up(&fl->fl_wait); - spin_unlock(&vnode->lock); - _leave(" [granted]"); - return; - } + case AFS_VNODE_LOCK_DELETED: + afs_kill_lockers_enoent(vnode); + spin_unlock(&vnode->lock); + return; + /* Fall through */ default: /* Looks like a lock request was withdrawn. */ spin_unlock(&vnode->lock); @@ -319,14 +407,16 @@ again: */ static void afs_defer_unlock(struct afs_vnode *vnode) { - _enter(""); + _enter("%u", vnode->lock_state); - if (vnode->lock_state == AFS_VNODE_LOCK_GRANTED || - vnode->lock_state == AFS_VNODE_LOCK_EXTENDING) { + if (list_empty(&vnode->granted_locks) && + (vnode->lock_state == AFS_VNODE_LOCK_GRANTED || + vnode->lock_state == AFS_VNODE_LOCK_EXTENDING)) { cancel_delayed_work(&vnode->lock_work); - vnode->lock_state = AFS_VNODE_LOCK_NEED_UNLOCK; - afs_lock_may_be_available(vnode); + afs_set_lock_state(vnode, AFS_VNODE_LOCK_NEED_UNLOCK); + trace_afs_flock_ev(vnode, NULL, afs_flock_defer_unlock, 0); + queue_delayed_work(afs_lock_manager, &vnode->lock_work, 0); } } @@ -335,7 +425,7 @@ static void afs_defer_unlock(struct afs_vnode *vnode) * whether we think that we have a locking permit. */ static int afs_do_setlk_check(struct afs_vnode *vnode, struct key *key, - afs_lock_type_t type, bool can_sleep) + enum afs_flock_mode mode, afs_lock_type_t type) { afs_access_t access; int ret; @@ -363,160 +453,177 @@ static int afs_do_setlk_check(struct afs_vnode *vnode, struct key *key, if (type == AFS_LOCK_READ) { if (!(access & (AFS_ACE_INSERT | AFS_ACE_WRITE | AFS_ACE_LOCK))) return -EACCES; - if (vnode->status.lock_count == -1 && !can_sleep) - return -EAGAIN; /* Write locked */ } else { if (!(access & (AFS_ACE_INSERT | AFS_ACE_WRITE))) return -EACCES; - if (vnode->status.lock_count != 0 && !can_sleep) - return -EAGAIN; /* Locked */ } return 0; } /* - * Remove the front runner from the pending queue. - * - The caller must hold vnode->lock. - */ -static void afs_dequeue_lock(struct afs_vnode *vnode, struct file_lock *fl) -{ - struct file_lock *next; - - _enter(""); - - /* ->lock_type, ->lock_key and ->lock_state only belong to this - * file_lock if we're at the front of the pending queue or if we have - * the lock granted or if the lock_state is NEED_UNLOCK or UNLOCKING. - */ - if (vnode->granted_locks.next == &fl->fl_u.afs.link && - vnode->granted_locks.prev == &fl->fl_u.afs.link) { - list_del_init(&fl->fl_u.afs.link); - afs_defer_unlock(vnode); - return; - } - - if (!list_empty(&vnode->granted_locks) || - vnode->pending_locks.next != &fl->fl_u.afs.link) { - list_del_init(&fl->fl_u.afs.link); - return; - } - - list_del_init(&fl->fl_u.afs.link); - key_put(vnode->lock_key); - vnode->lock_key = NULL; - vnode->lock_state = AFS_VNODE_LOCK_NONE; - - if (list_empty(&vnode->pending_locks)) - return; - - /* The new front of the queue now owns the state variables. */ - next = list_entry(vnode->pending_locks.next, - struct file_lock, fl_u.afs.link); - vnode->lock_key = key_get(afs_file_key(next->fl_file)); - vnode->lock_type = (next->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; - vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB; - afs_lock_may_be_available(vnode); -} - -/* * request a lock on a file on the server */ static int afs_do_setlk(struct file *file, struct file_lock *fl) { struct inode *inode = locks_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); + enum afs_flock_mode mode = AFS_FS_S(inode->i_sb)->flock_mode; afs_lock_type_t type; struct key *key = afs_file_key(file); + bool partial, no_server_lock = false; int ret; - _enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type); + if (mode == afs_flock_mode_unset) + mode = afs_flock_mode_openafs; - /* only whole-file locks are supported */ - if (fl->fl_start != 0 || fl->fl_end != OFFSET_MAX) - return -EINVAL; + _enter("{%llx:%llu},%llu-%llu,%u,%u", + vnode->fid.vid, vnode->fid.vnode, + fl->fl_start, fl->fl_end, fl->fl_type, mode); fl->fl_ops = &afs_lock_ops; INIT_LIST_HEAD(&fl->fl_u.afs.link); fl->fl_u.afs.state = AFS_LOCK_PENDING; + partial = (fl->fl_start != 0 || fl->fl_end != OFFSET_MAX); type = (fl->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; + if (mode == afs_flock_mode_write && partial) + type = AFS_LOCK_WRITE; - ret = afs_do_setlk_check(vnode, key, type, fl->fl_flags & FL_SLEEP); + ret = afs_do_setlk_check(vnode, key, mode, type); if (ret < 0) return ret; - spin_lock(&vnode->lock); + trace_afs_flock_op(vnode, fl, afs_flock_op_set_lock); - /* If we've already got a readlock on the server then we instantly - * grant another readlock, irrespective of whether there are any - * pending writelocks. + /* AFS3 protocol only supports full-file locks and doesn't provide any + * method of upgrade/downgrade, so we need to emulate for partial-file + * locks. + * + * The OpenAFS client only gets a server lock for a full-file lock and + * keeps partial-file locks local. Allow this behaviour to be emulated + * (as the default). */ - if (type == AFS_LOCK_READ && - vnode->lock_state == AFS_VNODE_LOCK_GRANTED && - vnode->lock_type == AFS_LOCK_READ) { - _debug("instant readlock"); - ASSERT(!list_empty(&vnode->granted_locks)); - goto share_existing_lock; + if (mode == afs_flock_mode_local || + (partial && mode == afs_flock_mode_openafs)) { + no_server_lock = true; + goto skip_server_lock; } + spin_lock(&vnode->lock); list_add_tail(&fl->fl_u.afs.link, &vnode->pending_locks); + ret = -ENOENT; + if (vnode->lock_state == AFS_VNODE_LOCK_DELETED) + goto error_unlock; + + /* If we've already got a lock on the server then try to move to having + * the VFS grant the requested lock. Note that this means that other + * clients may get starved out. + */ + _debug("try %u", vnode->lock_state); + if (vnode->lock_state == AFS_VNODE_LOCK_GRANTED) { + if (type == AFS_LOCK_READ) { + _debug("instant readlock"); + list_move_tail(&fl->fl_u.afs.link, &vnode->granted_locks); + fl->fl_u.afs.state = AFS_LOCK_GRANTED; + goto vnode_is_locked_u; + } + + if (vnode->lock_type == AFS_LOCK_WRITE) { + _debug("instant writelock"); + list_move_tail(&fl->fl_u.afs.link, &vnode->granted_locks); + fl->fl_u.afs.state = AFS_LOCK_GRANTED; + goto vnode_is_locked_u; + } + } + + if (vnode->lock_state == AFS_VNODE_LOCK_NONE && + !(fl->fl_flags & FL_SLEEP)) { + ret = -EAGAIN; + if (type == AFS_LOCK_READ) { + if (vnode->status.lock_count == -1) + goto lock_is_contended; /* Write locked */ + } else { + if (vnode->status.lock_count != 0) + goto lock_is_contended; /* Locked */ + } + } + if (vnode->lock_state != AFS_VNODE_LOCK_NONE) goto need_to_wait; +try_to_lock: /* We don't have a lock on this vnode and we aren't currently waiting * for one either, so ask the server for a lock. * * Note that we need to be careful if we get interrupted by a signal * after dispatching the request as we may still get the lock, even * though we don't wait for the reply (it's not too bad a problem - the - * lock will expire in 10 mins anyway). + * lock will expire in 5 mins anyway). */ - _debug("not locked"); + trace_afs_flock_ev(vnode, fl, afs_flock_try_to_lock, 0); vnode->lock_key = key_get(key); vnode->lock_type = type; - vnode->lock_state = AFS_VNODE_LOCK_SETTING; + afs_set_lock_state(vnode, AFS_VNODE_LOCK_SETTING); spin_unlock(&vnode->lock); ret = afs_set_lock(vnode, key, type); /* RPC */ spin_lock(&vnode->lock); switch (ret) { + case -EKEYREJECTED: + case -EKEYEXPIRED: + case -EKEYREVOKED: + case -EPERM: + case -EACCES: + fl->fl_u.afs.state = ret; + trace_afs_flock_ev(vnode, fl, afs_flock_fail_perm, ret); + list_del_init(&fl->fl_u.afs.link); + afs_next_locker(vnode, ret); + goto error_unlock; + + case -ENOENT: + fl->fl_u.afs.state = ret; + trace_afs_flock_ev(vnode, fl, afs_flock_fail_other, ret); + list_del_init(&fl->fl_u.afs.link); + afs_kill_lockers_enoent(vnode); + goto error_unlock; + default: - goto abort_attempt; + fl->fl_u.afs.state = ret; + trace_afs_flock_ev(vnode, fl, afs_flock_fail_other, ret); + list_del_init(&fl->fl_u.afs.link); + afs_next_locker(vnode, 0); + goto error_unlock; case -EWOULDBLOCK: /* The server doesn't have a lock-waiting queue, so the client * will have to retry. The server will break the outstanding * callbacks on a file when a lock is released. */ - _debug("would block"); ASSERT(list_empty(&vnode->granted_locks)); ASSERTCMP(vnode->pending_locks.next, ==, &fl->fl_u.afs.link); - vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB; - goto need_to_wait; + goto lock_is_contended; case 0: - _debug("acquired"); - break; + afs_set_lock_state(vnode, AFS_VNODE_LOCK_GRANTED); + trace_afs_flock_ev(vnode, fl, afs_flock_acquired, type); + afs_grant_locks(vnode); + goto vnode_is_locked_u; } - /* we've acquired a server lock, but it needs to be renewed after 5 - * mins */ - vnode->lock_state = AFS_VNODE_LOCK_GRANTED; - afs_schedule_lock_extension(vnode); - -share_existing_lock: - /* the lock has been granted as far as we're concerned... */ - fl->fl_u.afs.state = AFS_LOCK_GRANTED; - list_move_tail(&fl->fl_u.afs.link, &vnode->granted_locks); - -given_lock: - /* ... but we do still need to get the VFS's blessing */ +vnode_is_locked_u: spin_unlock(&vnode->lock); - - ret = posix_lock_file(file, fl, NULL); +vnode_is_locked: + /* the lock has been granted by the server... */ + ASSERTCMP(fl->fl_u.afs.state, ==, AFS_LOCK_GRANTED); + +skip_server_lock: + /* ... but the VFS still needs to distribute access on this client. */ + trace_afs_flock_ev(vnode, fl, afs_flock_vfs_locking, 0); + ret = locks_lock_file_wait(file, fl); + trace_afs_flock_ev(vnode, fl, afs_flock_vfs_lock, ret); if (ret < 0) goto vfs_rejected_lock; @@ -528,38 +635,62 @@ given_lock: _leave(" = 0"); return 0; +lock_is_contended: + if (!(fl->fl_flags & FL_SLEEP)) { + list_del_init(&fl->fl_u.afs.link); + afs_next_locker(vnode, 0); + ret = -EAGAIN; + goto error_unlock; + } + + afs_set_lock_state(vnode, AFS_VNODE_LOCK_WAITING_FOR_CB); + trace_afs_flock_ev(vnode, fl, afs_flock_would_block, ret); + queue_delayed_work(afs_lock_manager, &vnode->lock_work, HZ * 5); + need_to_wait: /* We're going to have to wait. Either this client doesn't have a lock * on the server yet and we need to wait for a callback to occur, or - * the client does have a lock on the server, but it belongs to some - * other process(es) and is incompatible with the lock we want. + * the client does have a lock on the server, but it's shared and we + * need an exclusive lock. */ - ret = -EAGAIN; - if (fl->fl_flags & FL_SLEEP) { - spin_unlock(&vnode->lock); + spin_unlock(&vnode->lock); - _debug("sleep"); - ret = wait_event_interruptible(fl->fl_wait, - fl->fl_u.afs.state != AFS_LOCK_PENDING); + trace_afs_flock_ev(vnode, fl, afs_flock_waiting, 0); + ret = wait_event_interruptible(fl->fl_wait, + fl->fl_u.afs.state != AFS_LOCK_PENDING); + trace_afs_flock_ev(vnode, fl, afs_flock_waited, ret); + if (fl->fl_u.afs.state >= 0 && fl->fl_u.afs.state != AFS_LOCK_GRANTED) { spin_lock(&vnode->lock); - } - if (fl->fl_u.afs.state == AFS_LOCK_GRANTED) - goto given_lock; - if (fl->fl_u.afs.state < 0) - ret = fl->fl_u.afs.state; + switch (fl->fl_u.afs.state) { + case AFS_LOCK_YOUR_TRY: + fl->fl_u.afs.state = AFS_LOCK_PENDING; + goto try_to_lock; + case AFS_LOCK_PENDING: + if (ret > 0) { + /* We need to retry the lock. We may not be + * notified by the server if it just expired + * rather than being released. + */ + ASSERTCMP(vnode->lock_state, ==, AFS_VNODE_LOCK_WAITING_FOR_CB); + afs_set_lock_state(vnode, AFS_VNODE_LOCK_SETTING); + fl->fl_u.afs.state = AFS_LOCK_PENDING; + goto try_to_lock; + } + goto error_unlock; + case AFS_LOCK_GRANTED: + default: + break; + } -abort_attempt: - /* we aren't going to get the lock, either because we're unwilling to - * wait, or because some signal happened */ - _debug("abort"); - afs_dequeue_lock(vnode, fl); + spin_unlock(&vnode->lock); + } -error_unlock: - spin_unlock(&vnode->lock); - _leave(" = %d", ret); - return ret; + if (fl->fl_u.afs.state == AFS_LOCK_GRANTED) + goto vnode_is_locked; + ret = fl->fl_u.afs.state; + goto error; vfs_rejected_lock: /* The VFS rejected the lock we just obtained, so we have to discard @@ -567,11 +698,17 @@ vfs_rejected_lock: * deal with. */ _debug("vfs refused %d", ret); + if (no_server_lock) + goto error; spin_lock(&vnode->lock); list_del_init(&fl->fl_u.afs.link); - if (list_empty(&vnode->granted_locks)) - afs_defer_unlock(vnode); - goto error_unlock; + afs_defer_unlock(vnode); + +error_unlock: + spin_unlock(&vnode->lock); +error: + _leave(" = %d", ret); + return ret; } /* @@ -584,14 +721,12 @@ static int afs_do_unlk(struct file *file, struct file_lock *fl) _enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type); + trace_afs_flock_op(vnode, fl, afs_flock_op_unlock); + /* Flush all pending writes before doing anything with locks. */ vfs_fsync(file, 0); - /* only whole-file unlocks are supported */ - if (fl->fl_start != 0 || fl->fl_end != OFFSET_MAX) - return -EINVAL; - - ret = posix_lock_file(file, fl, NULL); + ret = locks_lock_file_wait(file, fl); _leave(" = %d [%u]", ret, vnode->lock_state); return ret; } @@ -607,23 +742,29 @@ static int afs_do_getlk(struct file *file, struct file_lock *fl) _enter(""); + if (vnode->lock_state == AFS_VNODE_LOCK_DELETED) + return -ENOENT; + fl->fl_type = F_UNLCK; /* check local lock records first */ posix_test_lock(file, fl); if (fl->fl_type == F_UNLCK) { /* no local locks; consult the server */ - ret = afs_fetch_status(vnode, key, false); + ret = afs_fetch_status(vnode, key, false, NULL); if (ret < 0) goto error; lock_count = READ_ONCE(vnode->status.lock_count); - if (lock_count > 0) - fl->fl_type = F_RDLCK; - else - fl->fl_type = F_WRLCK; - fl->fl_start = 0; - fl->fl_end = OFFSET_MAX; + if (lock_count != 0) { + if (lock_count > 0) + fl->fl_type = F_RDLCK; + else + fl->fl_type = F_WRLCK; + fl->fl_start = 0; + fl->fl_end = OFFSET_MAX; + fl->fl_pid = 0; + } } ret = 0; @@ -638,6 +779,8 @@ error: int afs_lock(struct file *file, int cmd, struct file_lock *fl) { struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); + enum afs_flock_operation op; + int ret; _enter("{%llx:%llu},%d,{t=%x,fl=%x,r=%Ld:%Ld}", vnode->fid.vid, vnode->fid.vnode, cmd, @@ -650,9 +793,23 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl) if (IS_GETLK(cmd)) return afs_do_getlk(file, fl); + + fl->fl_u.afs.debug_id = atomic_inc_return(&afs_file_lock_debug_id); + trace_afs_flock_op(vnode, fl, afs_flock_op_lock); + if (fl->fl_type == F_UNLCK) - return afs_do_unlk(file, fl); - return afs_do_setlk(file, fl); + ret = afs_do_unlk(file, fl); + else + ret = afs_do_setlk(file, fl); + + switch (ret) { + case 0: op = afs_flock_op_return_ok; break; + case -EAGAIN: op = afs_flock_op_return_eagain; break; + case -EDEADLK: op = afs_flock_op_return_edeadlk; break; + default: op = afs_flock_op_return_error; break; + } + trace_afs_flock_op(vnode, fl, op); + return ret; } /* @@ -661,6 +818,8 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl) int afs_flock(struct file *file, int cmd, struct file_lock *fl) { struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); + enum afs_flock_operation op; + int ret; _enter("{%llx:%llu},%d,{t=%x,fl=%x}", vnode->fid.vid, vnode->fid.vnode, cmd, @@ -676,10 +835,23 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; + fl->fl_u.afs.debug_id = atomic_inc_return(&afs_file_lock_debug_id); + trace_afs_flock_op(vnode, fl, afs_flock_op_flock); + /* we're simulating flock() locks using posix locks on the server */ if (fl->fl_type == F_UNLCK) - return afs_do_unlk(file, fl); - return afs_do_setlk(file, fl); + ret = afs_do_unlk(file, fl); + else + ret = afs_do_setlk(file, fl); + + switch (ret) { + case 0: op = afs_flock_op_return_ok; break; + case -EAGAIN: op = afs_flock_op_return_eagain; break; + case -EDEADLK: op = afs_flock_op_return_edeadlk; break; + default: op = afs_flock_op_return_error; break; + } + trace_afs_flock_op(vnode, fl, op); + return ret; } /* @@ -694,7 +866,10 @@ static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl) _enter(""); + new->fl_u.afs.debug_id = atomic_inc_return(&afs_file_lock_debug_id); + spin_lock(&vnode->lock); + trace_afs_flock_op(vnode, new, afs_flock_op_copy_lock); list_add(&new->fl_u.afs.link, &fl->fl_u.afs.link); spin_unlock(&vnode->lock); } @@ -710,7 +885,12 @@ static void afs_fl_release_private(struct file_lock *fl) _enter(""); spin_lock(&vnode->lock); - afs_dequeue_lock(vnode, fl); + + trace_afs_flock_op(vnode, fl, afs_flock_op_release_lock); + list_del_init(&fl->fl_u.afs.link); + if (list_empty(&vnode->granted_locks)) + afs_defer_unlock(vnode); + _debug("state %u for %p", vnode->lock_state, vnode); spin_unlock(&vnode->lock); } diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 3a9eaec06756..9b7266209343 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -33,8 +33,8 @@ static bool afs_fs_probe_done(struct afs_server *server) void afs_fileserver_probe_result(struct afs_call *call) { struct afs_addr_list *alist = call->alist; - struct afs_server *server = call->reply[0]; - unsigned int server_index = (long)call->reply[1]; + struct afs_server *server = call->server; + unsigned int server_index = call->server_index; unsigned int index = call->addr_ix; unsigned int rtt = UINT_MAX; bool have_result = false; @@ -141,8 +141,8 @@ static int afs_do_probe_fileserver(struct afs_net *net, struct afs_addr_cursor ac = { .index = 0, }; + struct afs_call *call; bool in_progress = false; - int err; _enter("%pU", &server->uuid); @@ -156,12 +156,13 @@ static int afs_do_probe_fileserver(struct afs_net *net, server->probe.rtt = UINT_MAX; for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { - err = afs_fs_get_capabilities(net, server, &ac, key, server_index, - true); - if (err == -EINPROGRESS) + call = afs_fs_get_capabilities(net, server, &ac, key, server_index); + if (!IS_ERR(call)) { + afs_put_call(call); in_progress = true; - else - afs_prioritise_error(_e, err, ac.abort_code); + } else { + afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code); + } } if (!in_progress) diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 0b37867b5c20..48298408d6ac 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -60,78 +60,17 @@ static void xdr_dump_bad(const __be32 *bp) } /* - * Update the core inode struct from a returned status record. - */ -void afs_update_inode_from_status(struct afs_vnode *vnode, - struct afs_file_status *status, - const afs_dataversion_t *expected_version, - u8 flags) -{ - struct timespec64 t; - umode_t mode; - - t = status->mtime_client; - vnode->vfs_inode.i_ctime = t; - vnode->vfs_inode.i_mtime = t; - vnode->vfs_inode.i_atime = t; - - if (flags & (AFS_VNODE_META_CHANGED | AFS_VNODE_NOT_YET_SET)) { - vnode->vfs_inode.i_uid = make_kuid(&init_user_ns, status->owner); - vnode->vfs_inode.i_gid = make_kgid(&init_user_ns, status->group); - set_nlink(&vnode->vfs_inode, status->nlink); - - mode = vnode->vfs_inode.i_mode; - mode &= ~S_IALLUGO; - mode |= status->mode; - barrier(); - vnode->vfs_inode.i_mode = mode; - } - - if (!(flags & AFS_VNODE_NOT_YET_SET)) { - if (expected_version && - *expected_version != status->data_version) { - _debug("vnode modified %llx on {%llx:%llu} [exp %llx]", - (unsigned long long) status->data_version, - vnode->fid.vid, vnode->fid.vnode, - (unsigned long long) *expected_version); - vnode->invalid_before = status->data_version; - if (vnode->status.type == AFS_FTYPE_DIR) { - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - afs_stat_v(vnode, n_inval); - } else { - set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); - } - } 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 - * download. - */ - if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - flags &= ~AFS_VNODE_DATA_CHANGED; - } - } - - if (flags & (AFS_VNODE_DATA_CHANGED | AFS_VNODE_NOT_YET_SET)) { - inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); - i_size_write(&vnode->vfs_inode, status->size); - } -} - -/* * decode an AFSFetchStatus block */ -static int xdr_decode_AFSFetchStatus(struct afs_call *call, - const __be32 **_bp, - struct afs_file_status *status, - struct afs_vnode *vnode, - const afs_dataversion_t *expected_version, - struct afs_read *read_req) +static int 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; - u8 flags = 0; abort_code = ntohl(xdr->abort_code); @@ -144,6 +83,7 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, * case. */ status->abort_code = abort_code; + scb->have_error = true; return 0; } @@ -161,44 +101,25 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, case AFS_FTYPE_FILE: case AFS_FTYPE_DIR: case AFS_FTYPE_SYMLINK: - if (type != status->type && - vnode && - !test_bit(AFS_VNODE_UNSET, &vnode->flags)) { - pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n", - vnode->fid.vid, - vnode->fid.vnode, - vnode->fid.unique, - status->type, type); - goto bad; - } status->type = type; break; default: goto bad; } -#define EXTRACT_M(FIELD) \ - do { \ - u32 x = ntohl(xdr->FIELD); \ - if (status->FIELD != x) { \ - flags |= AFS_VNODE_META_CHANGED; \ - status->FIELD = x; \ - } \ - } while (0) - - EXTRACT_M(nlink); - EXTRACT_M(author); - EXTRACT_M(owner); - EXTRACT_M(caller_access); /* call ticket dependent */ - EXTRACT_M(anon_access); - EXTRACT_M(mode); - EXTRACT_M(group); + status->nlink = ntohl(xdr->nlink); + status->author = ntohl(xdr->author); + status->owner = ntohl(xdr->owner); + status->caller_access = ntohl(xdr->caller_access); /* Ticket dependent */ + status->anon_access = ntohl(xdr->anon_access); + status->mode = ntohl(xdr->mode) & S_IALLUGO; + status->group = ntohl(xdr->group); + status->lock_count = ntohl(xdr->lock_count); status->mtime_client.tv_sec = ntohl(xdr->mtime_client); status->mtime_client.tv_nsec = 0; status->mtime_server.tv_sec = ntohl(xdr->mtime_server); status->mtime_server.tv_nsec = 0; - status->lock_count = ntohl(xdr->lock_count); size = (u64)ntohl(xdr->size_lo); size |= (u64)ntohl(xdr->size_hi) << 32; @@ -206,25 +127,10 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, data_version = (u64)ntohl(xdr->data_version_lo); data_version |= (u64)ntohl(xdr->data_version_hi) << 32; - if (data_version != status->data_version) { - status->data_version = data_version; - flags |= AFS_VNODE_DATA_CHANGED; - } - - if (read_req) { - read_req->data_version = data_version; - read_req->file_size = size; - } + status->data_version = data_version; + scb->have_status = true; *_bp = (const void *)*_bp + sizeof(*xdr); - - if (vnode) { - if (test_bit(AFS_VNODE_UNSET, &vnode->flags)) - flags |= AFS_VNODE_NOT_YET_SET; - afs_update_inode_from_status(vnode, status, expected_version, - flags); - } - return 0; bad: @@ -232,77 +138,22 @@ bad: return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); } -/* - * Decode the file status. We need to lock the target vnode if we're going to - * update its status so that stat() sees the attributes update atomically. - */ -static int afs_decode_status(struct afs_call *call, - const __be32 **_bp, - struct afs_file_status *status, - struct afs_vnode *vnode, - const afs_dataversion_t *expected_version, - struct afs_read *read_req) +static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry) { - int ret; - - if (!vnode) - return xdr_decode_AFSFetchStatus(call, _bp, status, vnode, - expected_version, read_req); - - write_seqlock(&vnode->cb_lock); - ret = xdr_decode_AFSFetchStatus(call, _bp, status, vnode, - expected_version, read_req); - write_sequnlock(&vnode->cb_lock); - return ret; + return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry; } -/* - * decode an AFSCallBack block - */ -static void xdr_decode_AFSCallBack(struct afs_call *call, - struct afs_vnode *vnode, - const __be32 **_bp) +static void xdr_decode_AFSCallBack(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { - struct afs_cb_interest *old, *cbi = call->cbi; + struct afs_callback *cb = &scb->callback; const __be32 *bp = *_bp; - u32 cb_expiry; - - write_seqlock(&vnode->cb_lock); - - if (!afs_cb_is_broken(call->cb_break, vnode, cbi)) { - vnode->cb_version = ntohl(*bp++); - cb_expiry = ntohl(*bp++); - vnode->cb_type = ntohl(*bp++); - vnode->cb_expires_at = cb_expiry + ktime_get_real_seconds(); - old = vnode->cb_interest; - if (old != call->cbi) { - vnode->cb_interest = cbi; - cbi = old; - } - set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - } else { - bp += 3; - } - write_sequnlock(&vnode->cb_lock); - call->cbi = cbi; - *_bp = bp; -} - -static ktime_t xdr_decode_expiry(struct afs_call *call, u32 expiry) -{ - return ktime_add_ns(call->reply_time, expiry * NSEC_PER_SEC); -} - -static void xdr_decode_AFSCallBack_raw(struct afs_call *call, - const __be32 **_bp, - struct afs_callback *cb) -{ - const __be32 *bp = *_bp; - - cb->version = ntohl(*bp++); + bp++; /* version */ cb->expires_at = xdr_decode_expiry(call, ntohl(*bp++)); - cb->type = ntohl(*bp++); + bp++; /* type */ + scb->have_cb = true; *_bp = bp; } @@ -395,7 +246,6 @@ static void xdr_decode_AFSFetchVolumeStatus(const __be32 **_bp, */ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -403,16 +253,13 @@ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) if (ret < 0) return ret; - _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_AFSCallBack(call, vnode, &bp); - xdr_decode_AFSVolSync(&bp, call->reply[1]); + xdr_decode_AFSCallBack(&bp, call, call->out_scb); + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -431,8 +278,8 @@ static const struct afs_call_type afs_RXFSFetchStatus_vnode = { /* * fetch the status information for a file */ -int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsync, - bool new_inode) +int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_status_cb *scb, + struct afs_volsync *volsync) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -440,7 +287,7 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_file_status(fc, volsync, new_inode); + return yfs_fs_fetch_file_status(fc, scb, volsync); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); @@ -453,10 +300,8 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy } call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = volsync; - call->expected_version = new_inode ? 1 : vnode->status.data_version; - call->want_reply_time = true; + call->out_scb = scb; + call->out_volsync = volsync; /* marshall the parameters */ bp = call->request; @@ -465,10 +310,12 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -476,8 +323,7 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy */ static int afs_deliver_fs_fetch_data(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; - struct afs_read *req = call->reply[2]; + struct afs_read *req = call->read_request; const __be32 *bp; unsigned int size; int ret; @@ -498,7 +344,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) afs_extract_to_tmp(call); } - /* extract the returned data length */ + /* Fall through - and extract the returned data length */ case 1: _debug("extract data length"); ret = afs_extract_data(call, true); @@ -525,7 +371,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); - /* extract the returned data */ + /* Fall through - and extract the returned data */ case 2: _debug("extract data %zu/%llu", iov_iter_count(&call->iter), req->remain); @@ -539,7 +385,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (req->offset == PAGE_SIZE) { req->offset = 0; if (req->page_done) - req->page_done(call, req); + req->page_done(req); req->index++; if (req->remain > 0) goto begin_page; @@ -552,6 +398,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) /* Discard any excess data the server gave us */ iov_iter_discard(&call->iter, READ, req->actual_len - req->len); call->unmarshall = 3; + + /* Fall through */ case 3: _debug("extract discard %zu/%llu", iov_iter_count(&call->iter), req->actual_len - req->len); @@ -564,19 +412,21 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->unmarshall = 4; afs_extract_to_buf(call, (21 + 3 + 6) * 4); - /* extract the metadata */ + /* Fall through - and extract the metadata */ case 4: ret = afs_extract_data(call, false); if (ret < 0) return ret; bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &vnode->status.data_version, req); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_AFSCallBack(call, vnode, &bp); - xdr_decode_AFSVolSync(&bp, call->reply[1]); + xdr_decode_AFSCallBack(&bp, call, call->out_scb); + xdr_decode_AFSVolSync(&bp, call->out_volsync); + + req->data_version = call->out_scb->status.data_version; + req->file_size = call->out_scb->status.size; call->unmarshall++; @@ -589,7 +439,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) zero_user_segment(req->pages[req->index], req->offset, PAGE_SIZE); if (req->page_done) - req->page_done(call, req); + req->page_done(req); req->offset = 0; } @@ -599,7 +449,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) static void afs_fetch_data_destructor(struct afs_call *call) { - struct afs_read *req = call->reply[2]; + struct afs_read *req = call->read_request; afs_put_read(req); afs_flat_call_destructor(call); @@ -625,7 +475,9 @@ static const struct afs_call_type afs_RXFSFetchData64 = { /* * fetch data from a very large file */ -static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, struct afs_read *req) +static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, + struct afs_status_cb *scb, + struct afs_read *req) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -639,11 +491,9 @@ static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, struct afs_read *req) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = NULL; /* volsync */ - call->reply[2] = req; - call->expected_version = vnode->status.data_version; - call->want_reply_time = true; + call->out_scb = scb; + call->out_volsync = NULL; + call->read_request = req; /* marshall the parameters */ bp = call->request; @@ -657,16 +507,19 @@ static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, struct afs_read *req) bp[7] = htonl(lower_32_bits(req->len)); refcount_inc(&req->usage); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* * fetch data from a file */ -int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) +int afs_fs_fetch_data(struct afs_fs_cursor *fc, + struct afs_status_cb *scb, + struct afs_read *req) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -674,12 +527,12 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_data(fc, req); + return yfs_fs_fetch_data(fc, scb, req); if (upper_32_bits(req->pos) || upper_32_bits(req->len) || upper_32_bits(req->pos + req->len)) - return afs_fs_fetch_data64(fc, req); + return afs_fs_fetch_data64(fc, scb, req); _enter(""); @@ -688,11 +541,9 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = NULL; /* volsync */ - call->reply[2] = req; - call->expected_version = vnode->status.data_version; - call->want_reply_time = true; + call->out_scb = scb; + call->out_volsync = NULL; + call->read_request = req; /* marshall the parameters */ bp = call->request; @@ -704,10 +555,11 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) bp[5] = htonl(lower_32_bits(req->len)); refcount_inc(&req->usage); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -715,28 +567,24 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) */ static int afs_deliver_fs_create_vnode(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; - _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call); if (ret < 0) return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_AFSFid(&bp, call->reply[1]); - ret = afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + xdr_decode_AFSFid(&bp, call->out_fid); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_AFSCallBack_raw(call, &bp, call->reply[3]); - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSCallBack(&bp, call, call->out_scb); + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -765,24 +613,23 @@ static const struct afs_call_type afs_RXFSMakeDir = { int afs_fs_create(struct afs_fs_cursor *fc, const char *name, umode_t mode, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus, - struct afs_callback *newcb) + struct afs_status_cb *new_scb) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, padsz; __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)){ if (S_ISDIR(mode)) - return yfs_fs_make_dir(fc, name, mode, current_data_version, - newfid, newstatus, newcb); + return yfs_fs_make_dir(fc, name, mode, dvnode_scb, + newfid, new_scb); else - return yfs_fs_create_file(fc, name, mode, current_data_version, - newfid, newstatus, newcb); + return yfs_fs_create_file(fc, name, mode, dvnode_scb, + newfid, new_scb); } _enter(""); @@ -798,19 +645,16 @@ int afs_fs_create(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->reply[3] = newcb; - call->expected_version = current_data_version + 1; - call->want_reply_time = true; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = new_scb; /* marshall the parameters */ bp = call->request; *bp++ = htonl(S_ISDIR(mode) ? FSMAKEDIR : FSCREATEFILE); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(dvnode->fid.vid); + *bp++ = htonl(dvnode->fid.vnode); + *bp++ = htonl(dvnode->fid.unique); *bp++ = htonl(namesz); memcpy(bp, name, namesz); bp = (void *) bp + namesz; @@ -819,39 +663,38 @@ int afs_fs_create(struct afs_fs_cursor *fc, bp = (void *) bp + padsz; } *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); - *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ + *bp++ = htonl(dvnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(mode & S_IALLUGO); /* unix mode */ *bp++ = 0; /* segment size */ afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* - * deliver reply data to an FS.RemoveFile or FS.RemoveDir + * Deliver reply data to any operation that returns directory status and volume + * sync. */ -static int afs_deliver_fs_remove(struct afs_call *call) +static int afs_deliver_fs_dir_status_and_vol(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; - _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call); if (ret < 0) return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -863,14 +706,14 @@ static int afs_deliver_fs_remove(struct afs_call *call) static const struct afs_call_type afs_RXFSRemoveFile = { .name = "FS.RemoveFile", .op = afs_FS_RemoveFile, - .deliver = afs_deliver_fs_remove, + .deliver = afs_deliver_fs_dir_status_and_vol, .destructor = afs_flat_call_destructor, }; static const struct afs_call_type afs_RXFSRemoveDir = { .name = "FS.RemoveDir", .op = afs_FS_RemoveDir, - .deliver = afs_deliver_fs_remove, + .deliver = afs_deliver_fs_dir_status_and_vol, .destructor = afs_flat_call_destructor, }; @@ -878,7 +721,7 @@ static const struct afs_call_type afs_RXFSRemoveDir = { * remove a file or directory */ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, bool isdir, u64 current_data_version) + const char *name, bool isdir, struct afs_status_cb *dvnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -887,7 +730,7 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_remove(fc, vnode, name, isdir, current_data_version); + return yfs_fs_remove(fc, vnode, name, isdir, dvnode_scb); _enter(""); @@ -902,9 +745,7 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; /* marshall the parameters */ bp = call->request; @@ -921,8 +762,10 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, } afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &dvnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -930,7 +773,6 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int afs_deliver_fs_link(struct afs_call *call) { - struct afs_vnode *dvnode = call->reply[0], *vnode = call->reply[1]; const __be32 *bp; int ret; @@ -942,14 +784,13 @@ static int afs_deliver_fs_link(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = afs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -969,7 +810,9 @@ static const struct afs_call_type afs_RXFSLink = { * make a hard link */ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, u64 current_data_version) + const char *name, + struct afs_status_cb *dvnode_scb, + struct afs_status_cb *vnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -978,7 +821,7 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_link(fc, vnode, name, current_data_version); + return yfs_fs_link(fc, vnode, name, dvnode_scb, vnode_scb); _enter(""); @@ -991,9 +834,8 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_scb = vnode_scb; /* marshall the parameters */ bp = call->request; @@ -1013,8 +855,10 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, *bp++ = htonl(vnode->fid.unique); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &vnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1022,7 +866,6 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int afs_deliver_fs_symlink(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -1034,15 +877,14 @@ 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->reply[1]); - ret = afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + xdr_decode_AFSFid(&bp, call->out_fid); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1064,19 +906,19 @@ static const struct afs_call_type afs_RXFSSymlink = { int afs_fs_symlink(struct afs_fs_cursor *fc, const char *name, const char *contents, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus) + struct afs_status_cb *new_scb) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, padsz, c_namesz, c_padsz; __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_symlink(fc, name, contents, current_data_version, - newfid, newstatus); + return yfs_fs_symlink(fc, name, contents, dvnode_scb, + newfid, new_scb); _enter(""); @@ -1094,17 +936,16 @@ int afs_fs_symlink(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = new_scb; /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSYMLINK); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(dvnode->fid.vid); + *bp++ = htonl(dvnode->fid.vnode); + *bp++ = htonl(dvnode->fid.unique); *bp++ = htonl(namesz); memcpy(bp, name, namesz); bp = (void *) bp + namesz; @@ -1120,15 +961,17 @@ int afs_fs_symlink(struct afs_fs_cursor *fc, bp = (void *) bp + c_padsz; } *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); - *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ + *bp++ = htonl(dvnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(S_IRWXUGO); /* unix mode */ *bp++ = 0; /* segment size */ afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1136,29 +979,24 @@ int afs_fs_symlink(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_rename(struct afs_call *call) { - struct afs_vnode *orig_dvnode = call->reply[0], *new_dvnode = call->reply[1]; const __be32 *bp; int ret; - _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call); if (ret < 0) return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &orig_dvnode->status, orig_dvnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - if (new_dvnode != orig_dvnode) { - ret = afs_decode_status(call, &bp, &new_dvnode->status, new_dvnode, - &call->expected_version_2, NULL); + if (call->out_dir_scb != call->out_scb) { + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; } - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1175,14 +1013,14 @@ static const struct afs_call_type afs_RXFSRename = { }; /* - * create a symbolic link + * Rename/move a file or directory. */ int afs_fs_rename(struct afs_fs_cursor *fc, const char *orig_name, struct afs_vnode *new_dvnode, const char *new_name, - u64 current_orig_data_version, - u64 current_new_data_version) + struct afs_status_cb *orig_dvnode_scb, + struct afs_status_cb *new_dvnode_scb) { struct afs_vnode *orig_dvnode = fc->vnode; struct afs_call *call; @@ -1193,8 +1031,8 @@ int afs_fs_rename(struct afs_fs_cursor *fc, if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) return yfs_fs_rename(fc, orig_name, new_dvnode, new_name, - current_orig_data_version, - current_new_data_version); + orig_dvnode_scb, + new_dvnode_scb); _enter(""); @@ -1214,10 +1052,8 @@ int afs_fs_rename(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = orig_dvnode; - call->reply[1] = new_dvnode; - call->expected_version = current_orig_data_version + 1; - call->expected_version_2 = current_new_data_version + 1; + call->out_dir_scb = orig_dvnode_scb; + call->out_scb = new_dvnode_scb; /* marshall the parameters */ bp = call->request; @@ -1245,8 +1081,10 @@ int afs_fs_rename(struct afs_fs_cursor *fc, } afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &orig_dvnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call2(call, &orig_dvnode->fid, orig_name, new_name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1254,7 +1092,6 @@ int afs_fs_rename(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_store_data(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -1266,13 +1103,10 @@ 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 = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ - - afs_pages_written_back(vnode, call); + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1302,7 +1136,8 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, struct address_space *mapping, pgoff_t first, pgoff_t last, unsigned offset, unsigned to, - loff_t size, loff_t pos, loff_t i_size) + loff_t size, loff_t pos, loff_t i_size, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1320,13 +1155,12 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, call->key = fc->key; call->mapping = mapping; - call->reply[0] = vnode; call->first = first; call->last = last; call->first_offset = offset; call->last_to = to; call->send_pages = true; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1350,7 +1184,9 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, *bp++ = htonl((u32) i_size); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1358,7 +1194,8 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, */ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, pgoff_t first, pgoff_t last, - unsigned offset, unsigned to) + unsigned offset, unsigned to, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1367,7 +1204,7 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_store_data(fc, mapping, first, last, offset, to); + return yfs_fs_store_data(fc, mapping, first, last, offset, to, scb); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); @@ -1388,7 +1225,7 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, if (pos >> 32 || i_size >> 32 || size >> 32 || (pos + size) >> 32) return afs_fs_store_data64(fc, mapping, first, last, offset, to, - size, pos, i_size); + size, pos, i_size, scb); call = afs_alloc_flat_call(net, &afs_RXFSStoreData, (4 + 6 + 3) * 4, @@ -1398,13 +1235,12 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, call->key = fc->key; call->mapping = mapping; - call->reply[0] = vnode; call->first = first; call->last = last; call->first_offset = offset; call->last_to = to; call->send_pages = true; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1426,7 +1262,9 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1434,7 +1272,6 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, */ static int afs_deliver_fs_store_status(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -1446,11 +1283,10 @@ 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 = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1484,7 +1320,8 @@ static const struct afs_call_type afs_RXFSStoreData64_as_Status = { * set the attributes on a very large file, using FS.StoreData rather than * FS.StoreStatus so as to alter the file size also */ -static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) +static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1503,8 +1340,7 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1524,14 +1360,17 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* * set the attributes on a file, using FS.StoreData rather than FS.StoreStatus * so as to alter the file size also */ -static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) +static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1543,7 +1382,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) ASSERT(attr->ia_valid & ATTR_SIZE); if (attr->ia_size >> 32) - return afs_fs_setattr_size64(fc, attr); + return afs_fs_setattr_size64(fc, attr, scb); call = afs_alloc_flat_call(net, &afs_RXFSStoreData_as_Status, (4 + 6 + 3) * 4, @@ -1552,8 +1391,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1570,14 +1408,17 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* * set the attributes on a file, using FS.StoreData if there's a change in file * size, and FS.StoreStatus otherwise */ -int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) +int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1585,10 +1426,10 @@ int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_setattr(fc, attr); + return yfs_fs_setattr(fc, attr, scb); if (attr->ia_valid & ATTR_SIZE) - return afs_fs_setattr_size(fc, attr); + return afs_fs_setattr_size(fc, attr, scb); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); @@ -1600,8 +1441,7 @@ int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1614,7 +1454,9 @@ int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1634,7 +1476,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) call->unmarshall++; afs_extract_to_buf(call, 12 * 4); - /* extract the returned status record */ + /* Fall through - and extract the returned status record */ case 1: _debug("extract status"); ret = afs_extract_data(call, true); @@ -1642,11 +1484,11 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_AFSFetchVolumeStatus(&bp, call->reply[1]); + xdr_decode_AFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); - /* extract the volume name length */ + /* Fall through - and extract the volume name length */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -1658,23 +1500,23 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_volname_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; - /* extract the volume name */ + /* Fall through - and extract the volume name */ case 3: _debug("extract volname"); ret = afs_extract_data(call, true); if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; - /* extract the offline message length */ + /* Fall through - and extract the offline message length */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -1686,24 +1528,24 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_offline_msg_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; - /* extract the offline message */ + /* Fall through - and extract the offline message */ case 5: _debug("extract offline"); ret = afs_extract_data(call, true); if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("offline '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; - /* extract the message of the day length */ + /* Fall through - and extract the message of the day length */ case 6: ret = afs_extract_data(call, true); if (ret < 0) @@ -1715,17 +1557,17 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_motd_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; - /* extract the message of the day */ + /* Fall through - and extract the message of the day */ case 7: _debug("extract motd"); ret = afs_extract_data(call, false); if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("motd '%s'", p); @@ -1740,23 +1582,13 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) } /* - * destroy an FS.GetVolumeStatus call - */ -static void afs_get_volume_status_call_destructor(struct afs_call *call) -{ - kfree(call->reply[2]); - call->reply[2] = NULL; - afs_flat_call_destructor(call); -} - -/* * FS.GetVolumeStatus operation type */ static const struct afs_call_type afs_RXFSGetVolumeStatus = { .name = "FS.GetVolumeStatus", .op = afs_FS_GetVolumeStatus, .deliver = afs_deliver_fs_get_volume_status, - .destructor = afs_get_volume_status_call_destructor, + .destructor = afs_flat_call_destructor, }; /* @@ -1769,27 +1601,19 @@ int afs_fs_get_volume_status(struct afs_fs_cursor *fc, struct afs_call *call; struct afs_net *net = afs_v2net(vnode); __be32 *bp; - void *tmpbuf; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) return yfs_fs_get_volume_status(fc, vs); _enter(""); - tmpbuf = kmalloc(AFSOPAQUEMAX, GFP_KERNEL); - if (!tmpbuf) - return -ENOMEM; - - call = afs_alloc_flat_call(net, &afs_RXFSGetVolumeStatus, 2 * 4, 12 * 4); - if (!call) { - kfree(tmpbuf); + call = afs_alloc_flat_call(net, &afs_RXFSGetVolumeStatus, 2 * 4, + max(12 * 4, AFSOPAQUEMAX + 1)); + if (!call) return -ENOMEM; - } call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = vs; - call->reply[2] = tmpbuf; + call->out_volstatus = vs; /* marshall the parameters */ bp = call->request; @@ -1798,7 +1622,9 @@ int afs_fs_get_volume_status(struct afs_fs_cursor *fc, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1817,7 +1643,7 @@ static int afs_deliver_fs_xxxx_lock(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1830,6 +1656,7 @@ static const struct afs_call_type afs_RXFSSetLock = { .name = "FS.SetLock", .op = afs_FS_SetLock, .deliver = afs_deliver_fs_xxxx_lock, + .done = afs_lock_op_done, .destructor = afs_flat_call_destructor, }; @@ -1840,6 +1667,7 @@ static const struct afs_call_type afs_RXFSExtendLock = { .name = "FS.ExtendLock", .op = afs_FS_ExtendLock, .deliver = afs_deliver_fs_xxxx_lock, + .done = afs_lock_op_done, .destructor = afs_flat_call_destructor, }; @@ -1856,7 +1684,8 @@ static const struct afs_call_type afs_RXFSReleaseLock = { /* * Set a lock on a file */ -int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) +int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1864,7 +1693,7 @@ int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_set_lock(fc, type); + return yfs_fs_set_lock(fc, type, scb); _enter(""); @@ -1873,7 +1702,8 @@ int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1884,14 +1714,16 @@ int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) *bp++ = htonl(type); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_calli(call, &vnode->fid, type); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* * extend a lock on a file */ -int afs_fs_extend_lock(struct afs_fs_cursor *fc) +int afs_fs_extend_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1899,7 +1731,7 @@ int afs_fs_extend_lock(struct afs_fs_cursor *fc) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_extend_lock(fc); + return yfs_fs_extend_lock(fc, scb); _enter(""); @@ -1908,7 +1740,8 @@ int afs_fs_extend_lock(struct afs_fs_cursor *fc) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1919,13 +1752,15 @@ int afs_fs_extend_lock(struct afs_fs_cursor *fc) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* * release a lock on a file */ -int afs_fs_release_lock(struct afs_fs_cursor *fc) +int afs_fs_release_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1933,7 +1768,7 @@ int afs_fs_release_lock(struct afs_fs_cursor *fc) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_release_lock(fc); + return yfs_fs_release_lock(fc, scb); _enter(""); @@ -1942,7 +1777,8 @@ int afs_fs_release_lock(struct afs_fs_cursor *fc) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1953,7 +1789,9 @@ int afs_fs_release_lock(struct afs_fs_cursor *fc) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1998,7 +1836,8 @@ int afs_fs_give_up_all_callbacks(struct afs_net *net, *bp++ = htonl(FSGIVEUPALLCALLBACKS); /* Can't take a ref on server */ - return afs_make_call(ac, call, GFP_NOFS, false); + afs_make_call(ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, ac); } /* @@ -2016,7 +1855,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; - /* Extract the capabilities word count */ + /* Fall through - and extract the capabilities word count */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -2029,7 +1868,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) iov_iter_discard(&call->iter, READ, count * sizeof(__be32)); call->unmarshall++; - /* Extract capabilities words */ + /* Fall through - and extract capabilities words */ case 2: ret = afs_extract_data(call, false); if (ret < 0) @@ -2045,14 +1884,6 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) return 0; } -static void afs_destroy_fs_get_capabilities(struct afs_call *call) -{ - struct afs_server *server = call->reply[0]; - - afs_put_server(call->net, server); - afs_flat_call_destructor(call); -} - /* * FS.GetCapabilities operation type */ @@ -2061,19 +1892,18 @@ static const struct afs_call_type afs_RXFSGetCapabilities = { .op = afs_FS_GetCapabilities, .deliver = afs_deliver_fs_get_capabilities, .done = afs_fileserver_probe_result, - .destructor = afs_destroy_fs_get_capabilities, + .destructor = afs_flat_call_destructor, }; /* * Probe a fileserver for the capabilities that it supports. This can * return up to 196 words. */ -int afs_fs_get_capabilities(struct afs_net *net, - struct afs_server *server, - struct afs_addr_cursor *ac, - struct key *key, - unsigned int server_index, - bool async) +struct afs_call *afs_fs_get_capabilities(struct afs_net *net, + struct afs_server *server, + struct afs_addr_cursor *ac, + struct key *key, + unsigned int server_index) { struct afs_call *call; __be32 *bp; @@ -2082,13 +1912,14 @@ int afs_fs_get_capabilities(struct afs_net *net, call = afs_alloc_flat_call(net, &afs_RXFSGetCapabilities, 1 * 4, 16 * 4); if (!call) - return -ENOMEM; + return ERR_PTR(-ENOMEM); call->key = key; - call->reply[0] = afs_get_server(server); - call->reply[1] = (void *)(long)server_index; + call->server = afs_get_server(server); + call->server_index = server_index; call->upgrade = true; - call->want_reply_time = true; + call->async = true; + call->max_lifespan = AFS_PROBE_MAX_LIFESPAN; /* marshall the parameters */ bp = call->request; @@ -2096,7 +1927,8 @@ int afs_fs_get_capabilities(struct afs_net *net, /* Can't take a ref on server */ trace_afs_make_fs_call(call, NULL); - return afs_make_call(ac, call, GFP_NOFS, async); + afs_make_call(ac, call, GFP_NOFS); + return call; } /* @@ -2104,10 +1936,6 @@ int afs_fs_get_capabilities(struct afs_net *net, */ static int afs_deliver_fs_fetch_status(struct afs_call *call) { - struct afs_file_status *status = call->reply[1]; - struct afs_callback *callback = call->reply[2]; - struct afs_volsync *volsync = call->reply[3]; - struct afs_fid *fid = call->reply[0]; const __be32 *bp; int ret; @@ -2115,16 +1943,13 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call) if (ret < 0) return ret; - _enter("{%llx:%llu}", fid->vid, fid->vnode); - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, status, NULL, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_AFSCallBack_raw(call, &bp, callback); - xdr_decode_AFSVolSync(&bp, volsync); + xdr_decode_AFSCallBack(&bp, call, call->out_scb); + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -2146,15 +1971,14 @@ static const struct afs_call_type afs_RXFSFetchStatus = { int afs_fs_fetch_status(struct afs_fs_cursor *fc, struct afs_net *net, struct afs_fid *fid, - struct afs_file_status *status, - struct afs_callback *callback, + struct afs_status_cb *scb, struct afs_volsync *volsync) { struct afs_call *call; __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_status(fc, net, fid, status, callback, volsync); + return yfs_fs_fetch_status(fc, net, fid, scb, volsync); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), fid->vid, fid->vnode); @@ -2166,12 +1990,9 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = fid; - call->reply[1] = status; - call->reply[2] = callback; - call->reply[3] = volsync; - call->expected_version = 1; /* vnode->status.data_version */ - call->want_reply_time = true; + call->out_fid = fid; + call->out_scb = scb; + call->out_volsync = volsync; /* marshall the parameters */ bp = call->request; @@ -2180,10 +2001,11 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, bp[2] = htonl(fid->vnode); bp[3] = htonl(fid->unique); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -2191,9 +2013,7 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) { - struct afs_file_status *statuses; - struct afs_callback *callbacks; - struct afs_vnode *vnode = call->reply[0]; + struct afs_status_cb *scb; const __be32 *bp; u32 tmp; int ret; @@ -2206,6 +2026,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; /* Extract the file status count and array in two steps */ + /* Fall through */ case 1: _debug("extract status count"); ret = afs_extract_data(call, true); @@ -2223,6 +2044,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) more_counts: afs_extract_to_buf(call, 21 * sizeof(__be32)); + /* Fall through */ case 2: _debug("extract status array %u", call->count); ret = afs_extract_data(call, true); @@ -2230,10 +2052,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; bp = call->buffer; - statuses = call->reply[1]; - ret = afs_decode_status(call, &bp, &statuses[call->count], - call->count == 0 ? vnode : NULL, - NULL, NULL); + scb = &call->out_scb[call->count]; + ret = xdr_decode_AFSFetchStatus(&bp, call, scb); if (ret < 0) return ret; @@ -2246,6 +2066,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_tmp(call); /* Extract the callback count and array in two steps */ + /* Fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -2262,6 +2083,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) more_cbs: afs_extract_to_buf(call, 3 * sizeof(__be32)); + /* Fall through */ case 4: _debug("extract CB array"); ret = afs_extract_data(call, true); @@ -2270,13 +2092,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) _debug("unmarshall CB array"); bp = call->buffer; - callbacks = call->reply[2]; - callbacks[call->count].version = ntohl(bp[0]); - callbacks[call->count].expires_at = xdr_decode_expiry(call, ntohl(bp[1])); - callbacks[call->count].type = ntohl(bp[2]); - statuses = call->reply[1]; - if (call->count == 0 && vnode && statuses[0].abort_code == 0) - xdr_decode_AFSCallBack(call, vnode, &bp); + scb = &call->out_scb[call->count]; + xdr_decode_AFSCallBack(&bp, call, scb); call->count++; if (call->count < call->count2) goto more_cbs; @@ -2284,13 +2101,14 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, 6 * sizeof(__be32)); call->unmarshall++; + /* Fall through */ case 5: ret = afs_extract_data(call, false); if (ret < 0) return ret; bp = call->buffer; - xdr_decode_AFSVolSync(&bp, call->reply[3]); + xdr_decode_AFSVolSync(&bp, call->out_volsync); call->unmarshall++; @@ -2318,8 +2136,7 @@ static const struct afs_call_type afs_RXFSInlineBulkStatus = { int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, struct afs_net *net, struct afs_fid *fids, - struct afs_file_status *statuses, - struct afs_callback *callbacks, + struct afs_status_cb *statuses, unsigned int nr_fids, struct afs_volsync *volsync) { @@ -2328,7 +2145,7 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, int i; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_inline_bulk_status(fc, net, fids, statuses, callbacks, + return yfs_fs_inline_bulk_status(fc, net, fids, statuses, nr_fids, volsync); _enter(",%x,{%llx:%llu},%u", @@ -2343,12 +2160,9 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = NULL; /* vnode for fid[0] */ - call->reply[1] = statuses; - call->reply[2] = callbacks; - call->reply[3] = volsync; + call->out_scb = statuses; + call->out_volsync = volsync; call->count2 = nr_fids; - call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -2360,8 +2174,204 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, *bp++ = htonl(fids[i].unique); } - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &fids[0]); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); +} + +/* + * deliver reply data to an FS.FetchACL + */ +static int afs_deliver_fs_fetch_acl(struct afs_call *call) +{ + struct afs_acl *acl; + const __be32 *bp; + unsigned int size; + int ret; + + _enter("{%u}", call->unmarshall); + + switch (call->unmarshall) { + case 0: + afs_extract_to_tmp(call); + call->unmarshall++; + + /* extract the returned data length */ + case 1: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + size = call->count2 = ntohl(call->tmp); + size = round_up(size, 4); + + acl = kmalloc(struct_size(acl, data, size), GFP_KERNEL); + if (!acl) + return -ENOMEM; + call->ret_acl = acl; + acl->size = call->count2; + afs_extract_begin(call, acl->data, size); + call->unmarshall++; + + /* extract the returned data */ + case 2: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + afs_extract_to_buf(call, (21 + 6) * 4); + call->unmarshall++; + + /* extract the metadata */ + case 3: + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; + + bp = call->buffer; + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); + if (ret < 0) + return ret; + xdr_decode_AFSVolSync(&bp, call->out_volsync); + + call->unmarshall++; + + case 4: + break; + } + + _leave(" = 0 [done]"); + return 0; +} + +static void afs_destroy_fs_fetch_acl(struct afs_call *call) +{ + kfree(call->ret_acl); + afs_flat_call_destructor(call); +} + +/* + * FS.FetchACL operation type + */ +static const struct afs_call_type afs_RXFSFetchACL = { + .name = "FS.FetchACL", + .op = afs_FS_FetchACL, + .deliver = afs_deliver_fs_fetch_acl, + .destructor = afs_destroy_fs_fetch_acl, +}; + +/* + * Fetch the ACL for a file. + */ +struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *fc, + struct afs_status_cb *scb) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + + call = afs_alloc_flat_call(net, &afs_RXFSFetchACL, 16, (21 + 6) * 4); + if (!call) { + fc->ac.error = -ENOMEM; + return ERR_PTR(-ENOMEM); + } + + call->key = fc->key; + call->ret_acl = NULL; + call->out_scb = scb; + call->out_volsync = NULL; + + /* marshall the parameters */ + bp = call->request; + bp[0] = htonl(FSFETCHACL); + bp[1] = htonl(vnode->fid.vid); + bp[2] = htonl(vnode->fid.vnode); + bp[3] = htonl(vnode->fid.unique); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + afs_make_call(&fc->ac, call, GFP_KERNEL); + return (struct afs_acl *)afs_wait_for_call_to_complete(call, &fc->ac); +} + +/* + * Deliver reply data to any operation that returns file status and volume + * sync. + */ +static int afs_deliver_fs_file_status_and_vol(struct afs_call *call) +{ + const __be32 *bp; + int ret; + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + bp = call->buffer; + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); + if (ret < 0) + return ret; + xdr_decode_AFSVolSync(&bp, call->out_volsync); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * FS.StoreACL operation type + */ +static const struct afs_call_type afs_RXFSStoreACL = { + .name = "FS.StoreACL", + .op = afs_FS_StoreACL, + .deliver = afs_deliver_fs_file_status_and_vol, + .destructor = afs_flat_call_destructor, +}; + +/* + * Fetch the ACL for a file. + */ +int afs_fs_store_acl(struct afs_fs_cursor *fc, const struct afs_acl *acl, + struct afs_status_cb *scb) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + size_t size; + __be32 *bp; + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + + size = round_up(acl->size, 4); + call = afs_alloc_flat_call(net, &afs_RXFSStoreACL, + 5 * 4 + size, (21 + 6) * 4); + if (!call) { + fc->ac.error = -ENOMEM; + return -ENOMEM; + } + + call->key = fc->key; + call->out_scb = scb; + call->out_volsync = NULL; + + /* marshall the parameters */ + bp = call->request; + bp[0] = htonl(FSSTOREACL); + bp[1] = htonl(vnode->fid.vid); + bp[2] = htonl(vnode->fid.vnode); + bp[3] = htonl(vnode->fid.unique); + bp[4] = htonl(acl->size); + memcpy(&bp[5], acl->data, acl->size); + if (acl->size != size) + memset((void *)&bp[5] + acl->size, 0, size - acl->size); + + trace_afs_make_fs_call(call, &vnode->fid); + afs_make_call(&fc->ac, call, GFP_KERNEL); + return afs_wait_for_call_to_complete(call, &fc->ac); } diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1a4ce07fb406..b42d9d09669c 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -23,47 +23,86 @@ #include <linux/namei.h> #include <linux/iversion.h> #include "internal.h" +#include "afs_fs.h" static const struct inode_operations afs_symlink_inode_operations = { .get_link = page_get_link, .listxattr = afs_listxattr, }; +static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode) +{ + static unsigned long once_only; + + pr_warn("kAFS: AFS vnode with undefined type %u\n", + vnode->status.type); + pr_warn("kAFS: A=%d m=%o s=%llx v=%llx\n", + vnode->status.abort_code, + vnode->status.mode, + vnode->status.size, + vnode->status.data_version); + pr_warn("kAFS: vnode %llx:%llx:%x\n", + vnode->fid.vid, + vnode->fid.vnode, + vnode->fid.unique); + if (parent_vnode) + pr_warn("kAFS: dir %llx:%llx:%x\n", + parent_vnode->fid.vid, + parent_vnode->fid.vnode, + parent_vnode->fid.unique); + + if (!test_and_set_bit(0, &once_only)) + dump_stack(); +} + /* * Initialise an inode from the vnode status. */ -static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key) +static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, + struct afs_cb_interest *cbi, + struct afs_vnode *parent_vnode, + struct afs_status_cb *scb) { + struct afs_cb_interest *old_cbi = NULL; + struct afs_file_status *status = &scb->status; struct inode *inode = AFS_VNODE_TO_I(vnode); + struct timespec64 t; _debug("FS: ft=%d lk=%d sz=%llu ver=%Lu mod=%hu", - vnode->status.type, - vnode->status.nlink, - (unsigned long long) vnode->status.size, - vnode->status.data_version, - vnode->status.mode); + status->type, + status->nlink, + (unsigned long long) status->size, + status->data_version, + status->mode); + + write_seqlock(&vnode->cb_lock); - read_seqlock_excl(&vnode->cb_lock); + vnode->status = *status; - afs_update_inode_from_status(vnode, &vnode->status, NULL, - AFS_VNODE_NOT_YET_SET); + t = status->mtime_client; + inode->i_ctime = t; + inode->i_mtime = t; + inode->i_atime = t; + inode->i_uid = make_kuid(&init_user_ns, status->owner); + inode->i_gid = make_kgid(&init_user_ns, status->group); + set_nlink(&vnode->vfs_inode, status->nlink); - switch (vnode->status.type) { + switch (status->type) { case AFS_FTYPE_FILE: - inode->i_mode = S_IFREG | vnode->status.mode; + inode->i_mode = S_IFREG | status->mode; inode->i_op = &afs_file_inode_operations; inode->i_fop = &afs_file_operations; inode->i_mapping->a_ops = &afs_fs_aops; break; case AFS_FTYPE_DIR: - inode->i_mode = S_IFDIR | vnode->status.mode; + inode->i_mode = S_IFDIR | status->mode; inode->i_op = &afs_dir_inode_operations; inode->i_fop = &afs_dir_file_operations; inode->i_mapping->a_ops = &afs_dir_aops; break; case AFS_FTYPE_SYMLINK: /* Symlinks with a mode of 0644 are actually mountpoints. */ - if ((vnode->status.mode & 0777) == 0644) { + if ((status->mode & 0777) == 0644) { inode->i_flags |= S_AUTOMOUNT; set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); @@ -73,30 +112,192 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key) inode->i_fop = &afs_mntpt_file_operations; inode->i_mapping->a_ops = &afs_fs_aops; } else { - inode->i_mode = S_IFLNK | vnode->status.mode; + inode->i_mode = S_IFLNK | status->mode; inode->i_op = &afs_symlink_inode_operations; inode->i_mapping->a_ops = &afs_fs_aops; } inode_nohighmem(inode); break; default: - printk("kAFS: AFS vnode with undefined type\n"); - read_sequnlock_excl(&vnode->cb_lock); + dump_vnode(vnode, parent_vnode); + write_sequnlock(&vnode->cb_lock); return afs_protocol_error(NULL, -EBADMSG, afs_eproto_file_type); } - inode->i_blocks = 0; - vnode->invalid_before = vnode->status.data_version; + /* + * Estimate 512 bytes blocks used, rounded up to nearest 1K + * for consistency with other AFS clients. + */ + inode->i_blocks = ((i_size_read(inode) + 1023) >> 10) << 1; + i_size_write(&vnode->vfs_inode, status->size); + + vnode->invalid_before = status->data_version; + inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); - read_sequnlock_excl(&vnode->cb_lock); + if (!scb->have_cb) { + /* it's a symlink we just created (the fileserver + * didn't give us a callback) */ + vnode->cb_expires_at = ktime_get_real_seconds(); + } else { + vnode->cb_expires_at = scb->callback.expires_at; + old_cbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + if (cbi != old_cbi) + rcu_assign_pointer(vnode->cb_interest, afs_get_cb_interest(cbi)); + else + old_cbi = NULL; + set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } + + write_sequnlock(&vnode->cb_lock); + afs_put_cb_interest(afs_v2net(vnode), old_cbi); return 0; } /* + * Update the core inode struct from a returned status record. + */ +static void afs_apply_status(struct afs_fs_cursor *fc, + struct afs_vnode *vnode, + struct afs_status_cb *scb, + const afs_dataversion_t *expected_version) +{ + struct afs_file_status *status = &scb->status; + struct timespec64 t; + umode_t mode; + bool data_changed = false; + + BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags)); + + if (status->type != vnode->status.type) { + pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n", + vnode->fid.vid, + vnode->fid.vnode, + vnode->fid.unique, + status->type, vnode->status.type); + afs_protocol_error(NULL, -EBADMSG, afs_eproto_bad_status); + return; + } + + if (status->nlink != vnode->status.nlink) + set_nlink(&vnode->vfs_inode, status->nlink); + + if (status->owner != vnode->status.owner) + vnode->vfs_inode.i_uid = make_kuid(&init_user_ns, status->owner); + + if (status->group != vnode->status.group) + vnode->vfs_inode.i_gid = make_kgid(&init_user_ns, status->group); + + if (status->mode != vnode->status.mode) { + mode = vnode->vfs_inode.i_mode; + mode &= ~S_IALLUGO; + mode |= status->mode; + WRITE_ONCE(vnode->vfs_inode.i_mode, mode); + } + + t = status->mtime_client; + vnode->vfs_inode.i_ctime = t; + vnode->vfs_inode.i_mtime = t; + vnode->vfs_inode.i_atime = t; + + if (vnode->status.data_version != status->data_version) + data_changed = true; + + vnode->status = *status; + + if (expected_version && + *expected_version != status->data_version) { + kdebug("vnode modified %llx on {%llx:%llu} [exp %llx] %s", + (unsigned long long) status->data_version, + vnode->fid.vid, vnode->fid.vnode, + (unsigned long long) *expected_version, + fc->type ? fc->type->name : "???"); + vnode->invalid_before = status->data_version; + if (vnode->status.type == AFS_FTYPE_DIR) { + if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) + afs_stat_v(vnode, n_inval); + } else { + set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); + } + } 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 + * download. + */ + if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) + data_changed = false; + } + + if (data_changed) { + inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); + i_size_write(&vnode->vfs_inode, status->size); + } +} + +/* + * Apply a callback to a vnode. + */ +static void afs_apply_callback(struct afs_fs_cursor *fc, + struct afs_vnode *vnode, + struct afs_status_cb *scb, + unsigned int cb_break) +{ + struct afs_cb_interest *old; + struct afs_callback *cb = &scb->callback; + + if (!afs_cb_is_broken(cb_break, vnode, fc->cbi)) { + vnode->cb_expires_at = cb->expires_at; + old = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + if (old != fc->cbi) { + rcu_assign_pointer(vnode->cb_interest, afs_get_cb_interest(fc->cbi)); + afs_put_cb_interest(afs_v2net(vnode), old); + } + set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } +} + +/* + * Apply the received status and callback to an inode all in the same critical + * section to avoid races with afs_validate(). + */ +void afs_vnode_commit_status(struct afs_fs_cursor *fc, + struct afs_vnode *vnode, + unsigned int cb_break, + const afs_dataversion_t *expected_version, + struct afs_status_cb *scb) +{ + if (fc->ac.error != 0) + return; + + write_seqlock(&vnode->cb_lock); + + if (scb->have_error) { + if (scb->status.abort_code == VNOVNODE) { + set_bit(AFS_VNODE_DELETED, &vnode->flags); + clear_nlink(&vnode->vfs_inode); + __afs_break_callback(vnode); + } + } else { + if (scb->have_status) + afs_apply_status(fc, vnode, scb, expected_version); + if (scb->have_cb) + afs_apply_callback(fc, vnode, scb, cb_break); + } + + write_sequnlock(&vnode->cb_lock); + + if (fc->ac.error == 0 && scb->have_status) + afs_cache_permit(vnode, fc->key, cb_break, scb); +} + +/* * Fetch file status from the volume. */ -int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) +int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool is_new, + afs_access_t *_caller_access) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; int ret; @@ -105,18 +306,38 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, vnode->flags); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_fetch_file_status(&fc, NULL, new_inode); + afs_fs_fetch_file_status(&fc, scb, NULL); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + if (fc.error) { + /* Do nothing. */ + } else if (is_new) { + ret = afs_inode_init_from_status(vnode, key, fc.cbi, + NULL, scb); + fc.error = ret; + if (ret == 0) + afs_cache_permit(vnode, key, fc.cb_break, scb); + } else { + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); + } + afs_check_for_remote_deletion(&fc, vnode); ret = afs_end_vnode_operation(&fc); } + if (ret == 0 && _caller_access) + *_caller_access = scb->status.caller_access; + kfree(scb); _leave(" = %d", ret); return ret; } @@ -126,10 +347,10 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) */ int afs_iget5_test(struct inode *inode, void *opaque) { - struct afs_iget_data *data = opaque; + struct afs_iget_data *iget_data = opaque; struct afs_vnode *vnode = AFS_FS_I(inode); - return memcmp(&vnode->fid, &data->fid, sizeof(data->fid)) == 0; + return memcmp(&vnode->fid, &iget_data->fid, sizeof(iget_data->fid)) == 0; } /* @@ -147,17 +368,19 @@ static int afs_iget5_pseudo_dir_test(struct inode *inode, void *opaque) */ static int afs_iget5_set(struct inode *inode, void *opaque) { - struct afs_iget_data *data = opaque; + struct afs_iget_data *iget_data = opaque; struct afs_vnode *vnode = AFS_FS_I(inode); - vnode->fid = data->fid; - vnode->volume = data->volume; + vnode->fid = iget_data->fid; + vnode->volume = iget_data->volume; + vnode->cb_v_break = iget_data->cb_v_break; + vnode->cb_s_break = iget_data->cb_s_break; /* YFS supports 96-bit vnode IDs, but Linux only supports * 64-bit inode numbers. */ - inode->i_ino = data->fid.vnode; - inode->i_generation = data->fid.unique; + inode->i_ino = iget_data->fid.vnode; + inode->i_generation = iget_data->fid.unique; return 0; } @@ -167,38 +390,42 @@ static int afs_iget5_set(struct inode *inode, void *opaque) */ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) { - struct afs_iget_data data; struct afs_super_info *as; struct afs_vnode *vnode; struct inode *inode; static atomic_t afs_autocell_ino; + struct afs_iget_data iget_data = { + .cb_v_break = 0, + .cb_s_break = 0, + }; + _enter(""); as = sb->s_fs_info; if (as->volume) { - data.volume = as->volume; - data.fid.vid = as->volume->vid; + iget_data.volume = as->volume; + iget_data.fid.vid = as->volume->vid; } if (root) { - data.fid.vnode = 1; - data.fid.unique = 1; + iget_data.fid.vnode = 1; + iget_data.fid.unique = 1; } else { - data.fid.vnode = atomic_inc_return(&afs_autocell_ino); - data.fid.unique = 0; + iget_data.fid.vnode = atomic_inc_return(&afs_autocell_ino); + iget_data.fid.unique = 0; } - inode = iget5_locked(sb, data.fid.vnode, + inode = iget5_locked(sb, iget_data.fid.vnode, afs_iget5_pseudo_dir_test, afs_iget5_set, - &data); + &iget_data); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); } _debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }", - inode, inode->i_ino, data.fid.vid, data.fid.vnode, - data.fid.unique); + inode, inode->i_ino, iget_data.fid.vid, iget_data.fid.vnode, + iget_data.fid.unique); vnode = AFS_FS_I(inode); @@ -216,9 +443,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) set_nlink(inode, 2); inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; - inode->i_ctime.tv_sec = get_seconds(); - inode->i_ctime.tv_nsec = 0; - inode->i_atime = inode->i_mtime = inode->i_ctime; + inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode); inode->i_blocks = 0; inode_set_iversion_raw(inode, 0); inode->i_generation = 0; @@ -271,22 +496,24 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) * inode retrieval */ struct inode *afs_iget(struct super_block *sb, struct key *key, - struct afs_fid *fid, struct afs_file_status *status, - struct afs_callback *cb, struct afs_cb_interest *cbi) + struct afs_iget_data *iget_data, + struct afs_status_cb *scb, + struct afs_cb_interest *cbi, + struct afs_vnode *parent_vnode) { - struct afs_iget_data data = { .fid = *fid }; struct afs_super_info *as; struct afs_vnode *vnode; + struct afs_fid *fid = &iget_data->fid; struct inode *inode; int ret; _enter(",{%llx:%llu.%u},,", fid->vid, fid->vnode, fid->unique); as = sb->s_fs_info; - data.volume = as->volume; + iget_data->volume = as->volume; inode = iget5_locked(sb, fid->vnode, afs_iget5_test, afs_iget5_set, - &data); + iget_data); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); @@ -303,43 +530,25 @@ struct inode *afs_iget(struct super_block *sb, struct key *key, return inode; } - if (!status) { + if (!scb) { /* it's a remotely extant inode */ - ret = afs_fetch_status(vnode, key, true); + ret = afs_fetch_status(vnode, key, true, NULL); if (ret < 0) goto bad_inode; } else { - /* it's an inode we just created */ - memcpy(&vnode->status, status, sizeof(vnode->status)); - - if (!cb) { - /* it's a symlink we just created (the fileserver - * didn't give us a callback) */ - vnode->cb_version = 0; - vnode->cb_type = 0; - vnode->cb_expires_at = ktime_get(); - } else { - vnode->cb_version = cb->version; - vnode->cb_type = cb->type; - vnode->cb_expires_at = cb->expires_at; - vnode->cb_interest = afs_get_cb_interest(cbi); - set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - } - - vnode->cb_expires_at += ktime_get_real_seconds(); + ret = afs_inode_init_from_status(vnode, key, cbi, parent_vnode, + scb); + if (ret < 0) + goto bad_inode; } - ret = afs_inode_init_from_status(vnode, key); - if (ret < 0) - goto bad_inode; - afs_get_inode_cache(vnode); /* success */ clear_bit(AFS_VNODE_UNSET, &vnode->flags); inode->i_flags |= S_NOATIME; unlock_new_inode(inode); - _leave(" = %p [CB { v=%u t=%u }]", inode, vnode->cb_version, vnode->cb_type); + _leave(" = %p", inode); return inode; /* failure */ @@ -371,6 +580,66 @@ void afs_zap_data(struct afs_vnode *vnode) } /* + * Check the validity of a vnode/inode. + */ +bool afs_check_validity(struct afs_vnode *vnode) +{ + struct afs_cb_interest *cbi; + struct afs_server *server; + struct afs_volume *volume = vnode->volume; + time64_t now = ktime_get_real_seconds(); + bool valid, need_clear = false; + unsigned int cb_break, cb_s_break, cb_v_break; + int seq = 0; + + do { + read_seqbegin_or_lock(&vnode->cb_lock, &seq); + cb_v_break = READ_ONCE(volume->cb_v_break); + cb_break = vnode->cb_break; + + if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { + cbi = rcu_dereference(vnode->cb_interest); + server = rcu_dereference(cbi->server); + cb_s_break = READ_ONCE(server->cb_s_break); + + if (vnode->cb_s_break != cb_s_break || + vnode->cb_v_break != cb_v_break) { + vnode->cb_s_break = cb_s_break; + vnode->cb_v_break = cb_v_break; + need_clear = true; + valid = false; + } else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) { + need_clear = true; + valid = false; + } else if (vnode->cb_expires_at - 10 <= now) { + need_clear = true; + valid = false; + } else { + valid = true; + } + } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { + valid = true; + } else { + vnode->cb_v_break = cb_v_break; + valid = false; + } + + } while (need_seqretry(&vnode->cb_lock, seq)); + + done_seqretry(&vnode->cb_lock, seq); + + if (need_clear) { + write_seqlock(&vnode->cb_lock); + if (cb_break == vnode->cb_break) + __afs_break_callback(vnode); + write_sequnlock(&vnode->cb_lock); + valid = false; + } + + return valid; +} + +/* * validate a vnode/inode * - there are several things we need to check * - parent dir data changes (rm, rmdir, rename, mkdir, create, link, @@ -381,7 +650,6 @@ void afs_zap_data(struct afs_vnode *vnode) */ int afs_validate(struct afs_vnode *vnode, struct key *key) { - time64_t now = ktime_get_real_seconds(); bool valid; int ret; @@ -389,36 +657,9 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) vnode->fid.vid, vnode->fid.vnode, vnode->flags, key_serial(key)); - /* Quickly check the callback state. Ideally, we'd use read_seqbegin - * here, but we have no way to pass the net namespace to the RCU - * cleanup for the server record. - */ - read_seqlock_excl(&vnode->cb_lock); - - if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { - if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break || - vnode->cb_v_break != vnode->volume->cb_v_break) { - vnode->cb_s_break = vnode->cb_interest->server->cb_s_break; - vnode->cb_v_break = vnode->volume->cb_v_break; - valid = false; - } else if (vnode->status.type == AFS_FTYPE_DIR && - (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) || - vnode->cb_expires_at - 10 <= now)) { - valid = false; - } else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) || - vnode->cb_expires_at - 10 <= now) { - valid = false; - } else { - valid = true; - } - } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { - valid = true; - } else { - vnode->cb_v_break = vnode->volume->cb_v_break; - valid = false; - } - - read_sequnlock_excl(&vnode->cb_lock); + rcu_read_lock(); + valid = afs_check_validity(vnode); + rcu_read_unlock(); if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) clear_nlink(&vnode->vfs_inode); @@ -434,7 +675,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) * access */ if (!test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { _debug("not promised"); - ret = afs_fetch_status(vnode, key, false); + ret = afs_fetch_status(vnode, key, false, NULL); if (ret < 0) { if (ret == -ENOENT) { set_bit(AFS_VNODE_DELETED, &vnode->flags); @@ -505,6 +746,7 @@ int afs_drop_inode(struct inode *inode) */ void afs_evict_inode(struct inode *inode) { + struct afs_cb_interest *cbi; struct afs_vnode *vnode; vnode = AFS_FS_I(inode); @@ -521,10 +763,14 @@ void afs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); clear_inode(inode); - if (vnode->cb_interest) { - afs_put_cb_interest(afs_i2net(inode), vnode->cb_interest); - vnode->cb_interest = NULL; + write_seqlock(&vnode->cb_lock); + cbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + if (cbi) { + afs_put_cb_interest(afs_i2net(inode), cbi); + rcu_assign_pointer(vnode->cb_interest, NULL); } + write_sequnlock(&vnode->cb_lock); while (!list_empty(&vnode->wb_keys)) { struct afs_wb_key *wbk = list_entry(vnode->wb_keys.next, @@ -544,7 +790,10 @@ void afs_evict_inode(struct inode *inode) } #endif + afs_prune_wb_keys(vnode); afs_put_permits(rcu_access_pointer(vnode->permit_cache)); + key_put(vnode->silly_key); + vnode->silly_key = NULL; key_put(vnode->lock_key); vnode->lock_key = NULL; _leave(""); @@ -556,9 +805,10 @@ void afs_evict_inode(struct inode *inode) int afs_setattr(struct dentry *dentry, struct iattr *attr) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); struct key *key; - int ret; + int ret = -ENOMEM; _enter("{%llx:%llu},{n=%pd},%x", vnode->fid.vid, vnode->fid.vnode, dentry, @@ -570,6 +820,10 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) return 0; } + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + /* flush any dirty data outstanding on a regular file */ if (S_ISREG(vnode->vfs_inode.i_mode)) filemap_write_and_wait(vnode->vfs_inode.i_mapping); @@ -580,25 +834,33 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) key = afs_request_key(vnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, false)) { + afs_dataversion_t data_version = vnode->status.data_version; + + if (attr->ia_valid & ATTR_SIZE) + data_version++; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_setattr(&fc, attr); + afs_fs_setattr(&fc, attr, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); } if (!(attr->ia_valid & ATTR_FILE)) key_put(key); +error_scb: + kfree(scb); error: _leave(" = %d", ret); return ret; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index bb1f244b2b3a..2073c1a3ab4b 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -36,11 +36,24 @@ struct pagevec; struct afs_call; +/* + * Partial file-locking emulation mode. (The problem being that AFS3 only + * allows whole-file locks and no upgrading/downgrading). + */ +enum afs_flock_mode { + afs_flock_mode_unset, + afs_flock_mode_local, /* Local locking only */ + afs_flock_mode_openafs, /* Don't get server lock for a partial lock */ + afs_flock_mode_strict, /* Always get a server lock for a partial lock */ + afs_flock_mode_write, /* Get an exclusive server lock for a partial lock */ +}; + struct afs_fs_context { bool force; /* T to force cell type */ bool autocell; /* T if set auto mount operation */ bool dyn_root; /* T if dynamic root */ bool no_cell; /* T if the source is "none" (for dynroot) */ + enum afs_flock_mode flock_mode; /* Partial file-locking emulation mode */ afs_voltype_t type; /* type of volume requested */ unsigned int volnamesz; /* size of volume name */ const char *volname; /* name of volume to mount */ @@ -53,6 +66,8 @@ struct afs_fs_context { struct afs_iget_data { struct afs_fid fid; struct afs_volume *volume; /* volume on which resides */ + unsigned int cb_v_break; /* Pre-fetch volume break count */ + unsigned int cb_s_break; /* Pre-fetch server break count */ }; enum afs_call_state { @@ -98,8 +113,12 @@ struct afs_call { struct rxrpc_call *rxcall; /* RxRPC call handle */ struct key *key; /* security for this call */ struct afs_net *net; /* The network namespace */ - struct afs_server *cm_server; /* Server affected by incoming CM call */ + union { + struct afs_server *server; + struct afs_vlserver *vlserver; + }; struct afs_cb_interest *cbi; /* Callback interest for server used */ + struct afs_vnode *lvnode; /* vnode being locked */ void *request; /* request data (first part) */ struct address_space *mapping; /* Pages being written from */ struct iov_iter iter; /* Buffer iterator */ @@ -109,7 +128,20 @@ struct afs_call { struct bio_vec bvec[1]; }; void *buffer; /* reply receive buffer */ - void *reply[4]; /* Where to put the reply */ + union { + long ret0; /* Value to reply with instead of 0 */ + struct afs_addr_list *ret_alist; + struct afs_vldb_entry *ret_vldb; + struct afs_acl *ret_acl; + }; + struct afs_fid *out_fid; + struct afs_status_cb *out_dir_scb; + struct afs_status_cb *out_scb; + struct yfs_acl *out_yacl; + struct afs_volsync *out_volsync; + struct afs_volume_status *out_volstatus; + struct afs_read *read_request; + unsigned int server_index; pgoff_t first; /* first page in mapping to deal with */ pgoff_t last; /* last page in mapping to deal with */ atomic_t usage; @@ -118,10 +150,10 @@ struct afs_call { int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ u32 epoch; + unsigned int max_lifespan; /* Maximum lifespan to set if not 0 */ unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ unsigned first_offset; /* offset into mapping[first] */ - unsigned int cb_break; /* cb_break + cb_s_break before the call */ union { unsigned last_to; /* amount of mapping[last] */ unsigned count2; /* count used in unmarshalling */ @@ -132,9 +164,9 @@ struct afs_call { bool send_pages; /* T if data from mapping should be sent */ bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ - bool ret_reply0; /* T if should return reply[0] on success */ bool upgrade; /* T to request service upgrade */ - bool want_reply_time; /* T if want reply_time */ + bool have_reply_time; /* T if have got reply_time */ + bool intr; /* T if interruptible */ u16 service_id; /* Actual service ID (after upgrade) */ unsigned int debug_id; /* Trace ID */ u32 operation_ID; /* operation ID for an incoming call */ @@ -146,8 +178,6 @@ struct afs_call { } __attribute__((packed)); __be64 tmp64; }; - afs_dataversion_t expected_version; /* Updated version expected from store */ - afs_dataversion_t expected_version_2; /* 2nd updated version expected from store */ ktime_t reply_time; /* Time of first reply packet */ }; @@ -208,7 +238,8 @@ struct afs_read { unsigned int index; /* Which page we're reading into */ unsigned int nr_pages; unsigned int offset; /* offset into current page */ - void (*page_done)(struct afs_call *, struct afs_read *); + struct afs_vnode *vnode; + void (*page_done)(struct afs_read *); struct page **pages; struct page *array[]; }; @@ -221,6 +252,7 @@ struct afs_super_info { struct net *net_ns; /* Network namespace */ struct afs_cell *cell; /* The cell in which the volume resides */ struct afs_volume *volume; /* volume record */ + enum afs_flock_mode flock_mode:8; /* File locking emulation mode */ bool dyn_root; /* True if dynamic root */ }; @@ -353,13 +385,13 @@ struct afs_cell { time64_t last_inactive; /* Time of last drop of usage count */ atomic_t usage; unsigned long flags; -#define AFS_CELL_FL_NOT_READY 0 /* The cell record is not ready for use */ -#define AFS_CELL_FL_NO_GC 1 /* The cell was added manually, don't auto-gc */ -#define AFS_CELL_FL_NOT_FOUND 2 /* Permanent DNS error */ -#define AFS_CELL_FL_DNS_FAIL 3 /* Failed to access DNS */ -#define AFS_CELL_FL_NO_LOOKUP_YET 4 /* Not completed first DNS lookup yet */ +#define AFS_CELL_FL_NO_GC 0 /* The cell was added manually, don't auto-gc */ +#define AFS_CELL_FL_DO_LOOKUP 1 /* DNS lookup requested */ enum afs_cell_state state; short error; + enum dns_record_source dns_source:8; /* Latest source of data from lookup */ + enum dns_lookup_status dns_status:8; /* Latest status of data from lookup */ + unsigned int dns_lookup_count; /* Counter of DNS lookups */ /* Active fileserver interaction state. */ struct list_head proc_volumes; /* procfs volume list */ @@ -474,7 +506,6 @@ struct afs_server { time64_t put_time; /* Time at which last put */ time64_t update_at; /* Time at which to next update the record */ unsigned long flags; -#define AFS_SERVER_FL_NEW 0 /* New server, don't inc cb_s_break */ #define AFS_SERVER_FL_NOT_READY 1 /* The record is not ready for use */ #define AFS_SERVER_FL_NOT_FOUND 2 /* VL server says no such server */ #define AFS_SERVER_FL_VL_FAIL 3 /* Failed to access VL server */ @@ -525,7 +556,10 @@ struct afs_server { struct afs_vol_interest { struct hlist_node srv_link; /* Link in server->cb_volumes */ struct hlist_head cb_interests; /* List of callback interests on the server */ - afs_volid_t vid; /* Volume ID to match */ + union { + struct rcu_head rcu; + afs_volid_t vid; /* Volume ID to match */ + }; unsigned int usage; }; @@ -537,7 +571,10 @@ struct afs_cb_interest { struct afs_vol_interest *vol_interest; struct afs_server *server; /* Server on which this interest resides */ struct super_block *sb; /* Superblock on which inodes reside */ - afs_volid_t vid; /* Volume ID to match */ + union { + struct rcu_head rcu; + afs_volid_t vid; /* Volume ID to match */ + }; refcount_t usage; }; @@ -600,6 +637,7 @@ enum afs_lock_state { AFS_VNODE_LOCK_EXTENDING, /* We're extending a lock on the server */ AFS_VNODE_LOCK_NEED_UNLOCK, /* We need to unlock on the server */ AFS_VNODE_LOCK_UNLOCKING, /* We're telling the server to unlock */ + AFS_VNODE_LOCK_DELETED, /* The vnode has been deleted whilst we have a lock */ }; /* @@ -621,6 +659,8 @@ struct afs_vnode { struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */ struct mutex io_lock; /* Lock for serialising I/O on this mutex */ struct rw_semaphore validate_lock; /* lock for validating this vnode */ + struct rw_semaphore rmdir_lock; /* Lock for rmdir vs sillyrename */ + struct key *silly_key; /* Silly rename key */ spinlock_t wb_lock; /* lock for wb_keys */ spinlock_t lock; /* waitqueue/flags lock */ unsigned long flags; @@ -639,19 +679,18 @@ struct afs_vnode { struct list_head granted_locks; /* locks granted on this file */ struct delayed_work lock_work; /* work to be done in locking */ struct key *lock_key; /* Key to be used in lock ops */ + ktime_t locked_at; /* Time at which lock obtained */ enum afs_lock_state lock_state : 8; afs_lock_type_t lock_type : 8; /* outstanding callback notification on this file */ - struct afs_cb_interest *cb_interest; /* Server on which this resides */ + struct afs_cb_interest __rcu *cb_interest; /* Server on which this resides */ unsigned int cb_s_break; /* Mass break counter on ->server */ unsigned int cb_v_break; /* Mass break counter on ->volume */ unsigned int cb_break; /* Break counter on vnode */ seqlock_t cb_lock; /* Lock for ->cb_interest, ->status, ->cb_*break */ time64_t cb_expires_at; /* time at which callback expires */ - unsigned cb_version; /* callback version */ - afs_callback_type_t cb_type; /* type of callback */ }; static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode) @@ -738,6 +777,7 @@ struct afs_vl_cursor { * Cursor for iterating over a set of fileservers. */ struct afs_fs_cursor { + const struct afs_call_type *type; /* Type of call done */ struct afs_addr_cursor ac; struct afs_vnode *vnode; struct afs_server_list *server_list; /* Current server list (pins ref) */ @@ -755,6 +795,7 @@ struct afs_fs_cursor { #define AFS_FS_CURSOR_VNOVOL 0x0008 /* Set if seen VNOVOL */ #define AFS_FS_CURSOR_CUR_ONLY 0x0010 /* Set if current server only (file lock held) */ #define AFS_FS_CURSOR_NO_VSLEEP 0x0020 /* Set to prevent sleep on VBUSY, VOFFLINE, ... */ +#define AFS_FS_CURSOR_INTR 0x0040 /* Set if op is interruptible */ unsigned short nr_iterations; /* Number of server iterations */ }; @@ -827,7 +868,7 @@ static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) { - return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break; + return vnode->cb_break + vnode->cb_v_break; } static inline bool afs_cb_is_broken(unsigned int cb_break, @@ -835,7 +876,6 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, const struct afs_cb_interest *cbi) { return !cbi || cb_break != (vnode->cb_break + - cbi->server->cb_s_break + vnode->volume->cb_v_break); } @@ -875,6 +915,13 @@ extern void afs_edit_dir_add(struct afs_vnode *, struct qstr *, struct afs_fid * extern void afs_edit_dir_remove(struct afs_vnode *, struct qstr *, enum afs_edit_dir_reason); /* + * dir_silly.c + */ +extern int afs_sillyrename(struct afs_vnode *, struct afs_vnode *, + struct dentry *, struct key *); +extern int afs_silly_iput(struct dentry *, struct inode *); + +/* * dynroot.c */ extern const struct file_operations afs_dynroot_file_operations; @@ -907,6 +954,7 @@ extern void afs_put_read(struct afs_read *); */ extern struct workqueue_struct *afs_lock_manager; +extern void afs_lock_op_done(struct afs_call *); extern void afs_lock_work(struct work_struct *); extern void afs_lock_may_be_available(struct afs_vnode *); extern int afs_lock(struct file *, int, struct file_lock *); @@ -915,41 +963,48 @@ extern int afs_flock(struct file *, int, struct file_lock *); /* * fsclient.c */ -#define AFS_VNODE_NOT_YET_SET 0x01 -#define AFS_VNODE_META_CHANGED 0x02 -#define AFS_VNODE_DATA_CHANGED 0x04 -extern void afs_update_inode_from_status(struct afs_vnode *, struct afs_file_status *, - const afs_dataversion_t *, u8); - -extern int afs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_volsync *, bool); +extern int afs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_status_cb *, + struct afs_volsync *); extern int afs_fs_give_up_callbacks(struct afs_net *, struct afs_server *); -extern int afs_fs_fetch_data(struct afs_fs_cursor *, struct afs_read *); -extern int afs_fs_create(struct afs_fs_cursor *, const char *, umode_t, u64, - struct afs_fid *, struct afs_file_status *, struct afs_callback *); -extern int afs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, u64); -extern int afs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); -extern int afs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, u64, - struct afs_fid *, struct afs_file_status *); +extern int afs_fs_fetch_data(struct afs_fs_cursor *, struct afs_status_cb *, struct afs_read *); +extern int afs_fs_create(struct afs_fs_cursor *, const char *, umode_t, + struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); +extern int afs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, + struct afs_status_cb *); +extern int afs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); +extern int afs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, + struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); extern int afs_fs_rename(struct afs_fs_cursor *, const char *, - struct afs_vnode *, const char *, u64, u64); + struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); extern int afs_fs_store_data(struct afs_fs_cursor *, struct address_space *, - pgoff_t, pgoff_t, unsigned, unsigned); -extern int afs_fs_setattr(struct afs_fs_cursor *, struct iattr *); + pgoff_t, pgoff_t, unsigned, unsigned, struct afs_status_cb *); +extern int afs_fs_setattr(struct afs_fs_cursor *, struct iattr *, struct afs_status_cb *); extern int afs_fs_get_volume_status(struct afs_fs_cursor *, struct afs_volume_status *); -extern int afs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t); -extern int afs_fs_extend_lock(struct afs_fs_cursor *); -extern int afs_fs_release_lock(struct afs_fs_cursor *); +extern int afs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t, struct afs_status_cb *); +extern int afs_fs_extend_lock(struct afs_fs_cursor *, struct afs_status_cb *); +extern int afs_fs_release_lock(struct afs_fs_cursor *, struct afs_status_cb *); extern int afs_fs_give_up_all_callbacks(struct afs_net *, struct afs_server *, struct afs_addr_cursor *, struct key *); -extern int afs_fs_get_capabilities(struct afs_net *, struct afs_server *, - struct afs_addr_cursor *, struct key *, unsigned int, bool); +extern struct afs_call *afs_fs_get_capabilities(struct afs_net *, struct afs_server *, + struct afs_addr_cursor *, struct key *, + unsigned int); extern int afs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, unsigned int, - struct afs_volsync *); + struct afs_fid *, struct afs_status_cb *, + unsigned int, struct afs_volsync *); extern int afs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, struct afs_volsync *); + struct afs_fid *, struct afs_status_cb *, + struct afs_volsync *); + +struct afs_acl { + u32 size; + u8 data[]; +}; + +extern struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *, struct afs_status_cb *); +extern int afs_fs_store_acl(struct afs_fs_cursor *, const struct afs_acl *, + struct afs_status_cb *); /* * fs_probe.c @@ -961,14 +1016,20 @@ extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long); /* * inode.c */ -extern int afs_fetch_status(struct afs_vnode *, struct key *, bool); +extern void afs_vnode_commit_status(struct afs_fs_cursor *, + struct afs_vnode *, + unsigned int, + const afs_dataversion_t *, + struct afs_status_cb *); +extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *); extern int afs_iget5_test(struct inode *, void *); extern struct inode *afs_iget_pseudo_dir(struct super_block *, bool); extern struct inode *afs_iget(struct super_block *, struct key *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, - struct afs_cb_interest *); + struct afs_iget_data *, struct afs_status_cb *, + struct afs_cb_interest *, + struct afs_vnode *); extern void afs_zap_data(struct afs_vnode *); +extern bool afs_check_validity(struct afs_vnode *); extern int afs_validate(struct afs_vnode *, struct key *); extern int afs_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int afs_setattr(struct dentry *, struct iattr *); @@ -1061,7 +1122,7 @@ static inline void afs_put_sysnames(struct afs_sysnames *sysnames) {} * rotate.c */ extern bool afs_begin_vnode_operation(struct afs_fs_cursor *, struct afs_vnode *, - struct key *); + struct key *, bool); extern bool afs_select_fileserver(struct afs_fs_cursor *); extern bool afs_select_current_fileserver(struct afs_fs_cursor *); extern int afs_end_vnode_operation(struct afs_fs_cursor *); @@ -1075,7 +1136,8 @@ extern int __net_init afs_open_socket(struct afs_net *); extern void __net_exit afs_close_socket(struct afs_net *); extern void afs_charge_preallocation(struct work_struct *); extern void afs_put_call(struct afs_call *); -extern long afs_make_call(struct afs_addr_cursor *, struct afs_call *, gfp_t, bool); +extern void afs_make_call(struct afs_addr_cursor *, struct afs_call *, gfp_t); +extern long afs_wait_for_call_to_complete(struct afs_call *, struct afs_addr_cursor *); extern struct afs_call *afs_alloc_flat_call(struct afs_net *, const struct afs_call_type *, size_t, size_t); @@ -1085,6 +1147,12 @@ extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); extern int afs_extract_data(struct afs_call *, bool); extern int afs_protocol_error(struct afs_call *, int, enum afs_eproto_cause); +static inline void afs_set_fc_call(struct afs_call *call, struct afs_fs_cursor *fc) +{ + call->intr = fc->flags & AFS_FS_CURSOR_INTR; + fc->type = call->type; +} + static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size) { call->kvec[0].iov_base = buf; @@ -1165,7 +1233,8 @@ static inline void afs_set_call_complete(struct afs_call *call, */ extern void afs_put_permits(struct afs_permits *); extern void afs_clear_permits(struct afs_vnode *); -extern void afs_cache_permit(struct afs_vnode *, struct key *, unsigned int); +extern void afs_cache_permit(struct afs_vnode *, struct key *, unsigned int, + struct afs_status_cb *); extern void afs_zap_permits(struct rcu_head *); extern struct key *afs_request_key(struct afs_cell *); extern int afs_check_permit(struct afs_vnode *, struct key *, afs_access_t *); @@ -1220,8 +1289,8 @@ extern void afs_fs_exit(void); extern struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *, const char *, int); extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *, const uuid_t *); -extern int afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *, struct key *, - struct afs_vlserver *, unsigned int, bool); +extern struct afs_call *afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *, + struct key *, struct afs_vlserver *, unsigned int); extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *, const uuid_t *); /* @@ -1291,7 +1360,6 @@ extern int afs_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata); extern int afs_writepage(struct page *, struct writeback_control *); extern int afs_writepages(struct address_space *, struct writeback_control *); -extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *); extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *); extern int afs_fsync(struct file *, loff_t, loff_t, int); extern vm_fault_t afs_page_mkwrite(struct vm_fault *vmf); @@ -1307,33 +1375,52 @@ extern ssize_t afs_listxattr(struct dentry *, char *, size_t); /* * yfsclient.c */ -extern int yfs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_volsync *, bool); -extern int yfs_fs_fetch_data(struct afs_fs_cursor *, struct afs_read *); -extern int yfs_fs_create_file(struct afs_fs_cursor *, const char *, umode_t, u64, - struct afs_fid *, struct afs_file_status *, struct afs_callback *); -extern int yfs_fs_make_dir(struct afs_fs_cursor *, const char *, umode_t, u64, - struct afs_fid *, struct afs_file_status *, struct afs_callback *); -extern int yfs_fs_remove_file2(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); -extern int yfs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, u64); -extern int yfs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); -extern int yfs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, u64, - struct afs_fid *, struct afs_file_status *); -extern int yfs_fs_rename(struct afs_fs_cursor *, const char *, - struct afs_vnode *, const char *, u64, u64); +extern int yfs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_status_cb *, + struct afs_volsync *); +extern int yfs_fs_fetch_data(struct afs_fs_cursor *, struct afs_status_cb *, struct afs_read *); +extern int yfs_fs_create_file(struct afs_fs_cursor *, const char *, umode_t, struct afs_status_cb *, + struct afs_fid *, struct afs_status_cb *); +extern int yfs_fs_make_dir(struct afs_fs_cursor *, const char *, umode_t, struct afs_status_cb *, + struct afs_fid *, struct afs_status_cb *); +extern int yfs_fs_remove_file2(struct afs_fs_cursor *, struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); +extern int yfs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, + struct afs_status_cb *); +extern int yfs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); +extern int yfs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, + struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); +extern int yfs_fs_rename(struct afs_fs_cursor *, const char *, struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); extern int yfs_fs_store_data(struct afs_fs_cursor *, struct address_space *, - pgoff_t, pgoff_t, unsigned, unsigned); -extern int yfs_fs_setattr(struct afs_fs_cursor *, struct iattr *); + pgoff_t, pgoff_t, unsigned, unsigned, struct afs_status_cb *); +extern int yfs_fs_setattr(struct afs_fs_cursor *, struct iattr *, struct afs_status_cb *); extern int yfs_fs_get_volume_status(struct afs_fs_cursor *, struct afs_volume_status *); -extern int yfs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t); -extern int yfs_fs_extend_lock(struct afs_fs_cursor *); -extern int yfs_fs_release_lock(struct afs_fs_cursor *); +extern int yfs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t, struct afs_status_cb *); +extern int yfs_fs_extend_lock(struct afs_fs_cursor *, struct afs_status_cb *); +extern int yfs_fs_release_lock(struct afs_fs_cursor *, struct afs_status_cb *); extern int yfs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, struct afs_volsync *); + struct afs_fid *, struct afs_status_cb *, + struct afs_volsync *); extern int yfs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, unsigned int, - struct afs_volsync *); + struct afs_fid *, struct afs_status_cb *, + unsigned int, struct afs_volsync *); + +struct yfs_acl { + struct afs_acl *acl; /* Dir/file/symlink ACL */ + struct afs_acl *vol_acl; /* Whole volume ACL */ + u32 inherit_flag; /* True if ACL is inherited from parent dir */ + u32 num_cleaned; /* Number of ACEs removed due to subject removal */ + unsigned int flags; +#define YFS_ACL_WANT_ACL 0x01 /* Set if caller wants ->acl */ +#define YFS_ACL_WANT_VOL_ACL 0x02 /* Set if caller wants ->vol_acl */ +}; + +extern void yfs_free_opaque_acl(struct yfs_acl *); +extern struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *, struct yfs_acl *, + struct afs_status_cb *); +extern int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *, const struct afs_acl *, + struct afs_status_cb *); /* * Miscellaneous inline functions. @@ -1348,14 +1435,6 @@ static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode) return &vnode->vfs_inode; } -static inline void afs_vnode_commit_status(struct afs_fs_cursor *fc, - struct afs_vnode *vnode, - unsigned int cb_break) -{ - if (fc->ac.error == 0) - afs_cache_permit(vnode, fc->key, cb_break); -} - static inline void afs_check_for_remote_deletion(struct afs_fs_cursor *fc, struct afs_vnode *vnode) { diff --git a/fs/afs/misc.c b/fs/afs/misc.c index bbb1fd51b019..7f2af061ea06 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -131,33 +131,42 @@ void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code) if (e->error == -ETIMEDOUT || e->error == -ETIME) return; + /* Fall through */ case -ETIMEDOUT: case -ETIME: if (e->error == -ENOMEM || e->error == -ENONET) return; + /* Fall through */ case -ENOMEM: case -ENONET: if (e->error == -ERFKILL) return; + /* Fall through */ case -ERFKILL: if (e->error == -EADDRNOTAVAIL) return; + /* Fall through */ case -EADDRNOTAVAIL: if (e->error == -ENETUNREACH) return; + /* Fall through */ case -ENETUNREACH: if (e->error == -EHOSTUNREACH) return; + /* Fall through */ case -EHOSTUNREACH: if (e->error == -EHOSTDOWN) return; + /* Fall through */ case -EHOSTDOWN: if (e->error == -ECONNREFUSED) return; + /* Fall through */ case -ECONNREFUSED: if (e->error == -ECONNRESET) return; + /* Fall through */ case -ECONNRESET: /* Responded, but call expired. */ if (e->responded) return; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index be2ee3bbd0a9..371501d28e08 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -53,7 +53,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v) seq_printf(m, "%3u %6lld %2u %s\n", atomic_read(&cell->usage), cell->dns_expiry - ktime_get_real_seconds(), - vllist ? vllist->nr_servers : 0, + vllist->nr_servers, cell->name); return 0; } @@ -296,8 +296,8 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v) if (v == SEQ_START_TOKEN) { seq_printf(m, "# source %s, status %s\n", - dns_record_sources[vllist->source], - dns_lookup_statuses[vllist->status]); + dns_record_sources[vllist ? vllist->source : 0], + dns_lookup_statuses[vllist ? vllist->status : 0]); return 0; } @@ -336,7 +336,7 @@ static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos) if (pos == 0) return SEQ_START_TOKEN; - if (!vllist || pos - 1 >= vllist->nr_servers) + if (pos - 1 >= vllist->nr_servers) return NULL; return &vllist->servers[pos - 1]; diff --git a/fs/afs/protocol_yfs.h b/fs/afs/protocol_yfs.h index d443e2bfa094..915b9d10cdf3 100644 --- a/fs/afs/protocol_yfs.h +++ b/fs/afs/protocol_yfs.h @@ -31,9 +31,9 @@ enum YFS_CM_Operations { }; enum YFS_FS_Operations { - YFSFETCHACL = 64131, /* YFS Fetch file ACL */ + YFSFETCHACL = 64131, /* YFS Fetch file AFS3 ACL */ YFSFETCHSTATUS = 64132, /* YFS Fetch file status */ - YFSSTOREACL = 64134, /* YFS Store file ACL */ + YFSSTOREACL = 64134, /* YFS Store file AFS3 ACL */ YFSSTORESTATUS = 64135, /* YFS Store file status */ YFSREMOVEFILE = 64136, /* YFS Remove a file */ YFSCREATEFILE = 64137, /* YFS Create a file */ @@ -49,7 +49,7 @@ enum YFS_FS_Operations { YFSRELEASELOCK = 64158, /* YFS Release a file lock */ YFSLOOKUP = 64161, /* YFS lookup file in directory */ YFSFLUSHCPS = 64165, - YFSFETCHOPAQUEACL = 64168, + YFSFETCHOPAQUEACL = 64168, /* YFS Fetch file YFS ACL */ YFSWHOAMI = 64170, YFSREMOVEACL = 64171, YFSREMOVEFILE2 = 64173, diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index c3ae324781f8..b00c739e0e63 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -25,7 +25,7 @@ * them here also using the io_lock. */ bool afs_begin_vnode_operation(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - struct key *key) + struct key *key, bool intr) { memset(fc, 0, sizeof(*fc)); fc->vnode = vnode; @@ -33,10 +33,15 @@ bool afs_begin_vnode_operation(struct afs_fs_cursor *fc, struct afs_vnode *vnode fc->ac.error = SHRT_MAX; fc->error = -EDESTADDRREQ; - if (mutex_lock_interruptible(&vnode->io_lock) < 0) { - fc->error = -EINTR; - fc->flags |= AFS_FS_CURSOR_STOP; - return false; + if (intr) { + fc->flags |= AFS_FS_CURSOR_INTR; + if (mutex_lock_interruptible(&vnode->io_lock) < 0) { + fc->error = -EINTR; + fc->flags |= AFS_FS_CURSOR_STOP; + return false; + } + } else { + mutex_lock(&vnode->io_lock); } if (vnode->lock_state != AFS_VNODE_LOCK_NONE) @@ -61,7 +66,8 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, fc->untried = (1UL << fc->server_list->nr_servers) - 1; fc->index = READ_ONCE(fc->server_list->preferred); - cbi = vnode->cb_interest; + cbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->io_lock)); if (cbi) { /* See if the vnode's preferred record is still available */ for (i = 0; i < fc->server_list->nr_servers; i++) { @@ -82,8 +88,8 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, /* Note that the callback promise is effectively broken */ write_seqlock(&vnode->cb_lock); - ASSERTCMP(cbi, ==, vnode->cb_interest); - vnode->cb_interest = NULL; + ASSERTCMP(cbi, ==, rcu_access_pointer(vnode->cb_interest)); + rcu_assign_pointer(vnode->cb_interest, NULL); if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) vnode->cb_break++; write_sequnlock(&vnode->cb_lock); @@ -118,10 +124,14 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code) */ static bool afs_sleep_and_retry(struct afs_fs_cursor *fc) { - msleep_interruptible(1000); - if (signal_pending(current)) { - fc->error = -ERESTARTSYS; - return false; + if (fc->flags & AFS_FS_CURSOR_INTR) { + msleep_interruptible(1000); + if (signal_pending(current)) { + fc->error = -ERESTARTSYS; + return false; + } + } else { + msleep(1000); } return true; @@ -408,7 +418,9 @@ selected_server: if (error < 0) goto failed_set_error; - fc->cbi = afs_get_cb_interest(vnode->cb_interest); + fc->cbi = afs_get_cb_interest( + rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->io_lock))); read_lock(&server->fs_lock); alist = rcu_dereference_protected(server->addresses, @@ -459,6 +471,8 @@ no_more_servers: s->probe.abort_code); } + error = e.error; + failed_set_error: fc->error = error; failed: @@ -476,12 +490,15 @@ failed: bool afs_select_current_fileserver(struct afs_fs_cursor *fc) { struct afs_vnode *vnode = fc->vnode; - struct afs_cb_interest *cbi = vnode->cb_interest; + struct afs_cb_interest *cbi; struct afs_addr_list *alist; int error = fc->ac.error; _enter(""); + cbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->io_lock)); + switch (error) { case SHRT_MAX: if (!cbi) { @@ -490,7 +507,7 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc) return false; } - fc->cbi = afs_get_cb_interest(vnode->cb_interest); + fc->cbi = afs_get_cb_interest(cbi); read_lock(&cbi->server->fs_lock); alist = rcu_dereference_protected(cbi->server->addresses, diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 2c588f9bbbda..4fa5ce92b9b9 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -21,7 +21,6 @@ struct workqueue_struct *afs_async_calls; static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long); -static long afs_wait_for_call_to_complete(struct afs_call *, struct afs_addr_cursor *); static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long); static void afs_delete_async_call(struct work_struct *); static void afs_process_async_call(struct work_struct *); @@ -189,7 +188,7 @@ void afs_put_call(struct afs_call *call) if (call->type->destructor) call->type->destructor(call); - afs_put_server(call->net, call->cm_server); + afs_put_server(call->net, call->server); afs_put_cb_interest(call->net, call->cbi); afs_put_addrlist(call->alist); kfree(call->request); @@ -361,10 +360,10 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) } /* - * initiate a call + * Initiate a call and synchronously queue up the parameters for dispatch. Any + * error is stored into the call struct, which the caller must check for. */ -long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, - gfp_t gfp, bool async) +void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) { struct sockaddr_rxrpc *srx = &ac->alist->addrs[ac->index]; struct rxrpc_call *rxcall; @@ -382,7 +381,6 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, call, call->type->name, key_serial(call->key), atomic_read(&call->net->nr_outstanding_calls)); - call->async = async; call->addr_ix = ac->index; call->alist = afs_get_addrlist(ac->alist); @@ -415,10 +413,11 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key, (unsigned long)call, tx_total_len, gfp, - (async ? + (call->async ? afs_wake_up_async_call : afs_wake_up_call_waiter), call->upgrade, + call->intr, call->debug_id); if (IS_ERR(rxcall)) { ret = PTR_ERR(rxcall); @@ -428,6 +427,10 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, call->rxcall = rxcall; + if (call->max_lifespan) + rxrpc_kernel_set_max_life(call->net->socket, rxcall, + call->max_lifespan); + /* send the request */ iov[0].iov_base = call->request; iov[0].iov_len = call->request_size; @@ -453,13 +456,11 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, /* Note that at this point, we may have received the reply or an abort * - and an asynchronous call may already have completed. + * + * afs_wait_for_call_to_complete(call, ac) + * must be called to synchronously clean up. */ - if (call->async) { - afs_put_call(call); - return -EINPROGRESS; - } - - return afs_wait_for_call_to_complete(call, ac); + return; error_do_abort: if (ret != -ECONNABORTED) { @@ -495,9 +496,7 @@ error_kill_call: ac->error = ret; call->state = AFS_CALL_COMPLETE; - afs_put_call(call); _leave(" = %d", ret); - return ret; } /* @@ -535,11 +534,11 @@ static void afs_deliver_to_call(struct afs_call *call) return; } - if (call->want_reply_time && + if (!call->have_reply_time && rxrpc_kernel_get_reply_time(call->net->socket, call->rxcall, &call->reply_time)) - call->want_reply_time = false; + call->have_reply_time = true; ret = call->type->deliver(call); state = READ_ONCE(call->state); @@ -572,13 +571,17 @@ static void afs_deliver_to_call(struct afs_call *call) case -ENODATA: case -EBADMSG: case -EMSGSIZE: - default: abort_code = RXGEN_CC_UNMARSHAL; if (state != AFS_CALL_CL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, ret, "KUM"); goto local_abort; + default: + abort_code = RX_USER_ABORT; + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + abort_code, ret, "KER"); + goto local_abort; } } @@ -600,28 +603,33 @@ call_complete: } /* - * wait synchronously for a call to complete + * Wait synchronously for a call to complete and clean up the call struct. */ -static long afs_wait_for_call_to_complete(struct afs_call *call, - struct afs_addr_cursor *ac) +long afs_wait_for_call_to_complete(struct afs_call *call, + struct afs_addr_cursor *ac) { signed long rtt2, timeout; long ret; bool stalled = false; u64 rtt; u32 life, last_life; + bool rxrpc_complete = false; DECLARE_WAITQUEUE(myself, current); _enter(""); + ret = call->error; + if (ret < 0) + goto out; + rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall); rtt2 = nsecs_to_jiffies64(rtt) * 2; if (rtt2 < 2) rtt2 = 2; timeout = rtt2; - last_life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); + rxrpc_kernel_check_life(call->net->socket, call->rxcall, &last_life); add_wait_queue(&call->waitq, &myself); for (;;) { @@ -639,8 +647,13 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, if (afs_check_call_state(call, AFS_CALL_COMPLETE)) break; - life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); - if (timeout == 0 && + if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall, &life)) { + /* rxrpc terminated the call. */ + rxrpc_complete = true; + break; + } + + if (call->intr && timeout == 0 && life == last_life && signal_pending(current)) { if (stalled) break; @@ -663,12 +676,16 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, remove_wait_queue(&call->waitq, &myself); __set_current_state(TASK_RUNNING); - /* Kill off the call if it's still live. */ if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) { - _debug("call interrupted"); - if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - RX_USER_ABORT, -EINTR, "KWI")) - afs_set_call_complete(call, -EINTR, 0); + if (rxrpc_complete) { + afs_set_call_complete(call, call->error, call->abort_code); + } else { + /* Kill off the call if it's still live. */ + _debug("call interrupted"); + if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + RX_USER_ABORT, -EINTR, "KWI")) + afs_set_call_complete(call, -EINTR, 0); + } } spin_lock_bh(&call->state_lock); @@ -679,16 +696,16 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, ret = ac->error; switch (ret) { case 0: - if (call->ret_reply0) { - ret = (long)call->reply[0]; - call->reply[0] = NULL; - } + ret = call->ret0; + call->ret0 = 0; + /* Fall through */ case -ECONNABORTED: ac->responded = true; break; } +out: _debug("call complete"); afs_put_call(call); _leave(" = %p", (void *)ret); @@ -909,6 +926,7 @@ void afs_send_empty_reply(struct afs_call *call) _debug("oom"); rxrpc_kernel_abort_call(net->socket, call->rxcall, RX_USER_ABORT, -ENOMEM, "KOO"); + /* Fall through */ default: _leave(" [error]"); return; diff --git a/fs/afs/security.c b/fs/afs/security.c index 5f58a9a17e69..5d8ece98561e 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -87,11 +87,9 @@ void afs_clear_permits(struct afs_vnode *vnode) permits = rcu_dereference_protected(vnode->permit_cache, lockdep_is_held(&vnode->lock)); RCU_INIT_POINTER(vnode->permit_cache, NULL); - vnode->cb_break++; spin_unlock(&vnode->lock); - if (permits) - afs_put_permits(permits); + afs_put_permits(permits); } /* @@ -118,10 +116,10 @@ static void afs_hash_permits(struct afs_permits *permits) * as the ACL *may* have changed. */ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, - unsigned int cb_break) + unsigned int cb_break, struct afs_status_cb *scb) { struct afs_permits *permits, *xpermits, *replacement, *zap, *new = NULL; - afs_access_t caller_access = READ_ONCE(vnode->status.caller_access); + afs_access_t caller_access = scb->status.caller_access; size_t size = 0; bool changed = false; int i, j; @@ -148,7 +146,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, } if (afs_cb_is_broken(cb_break, vnode, - vnode->cb_interest)) { + rcu_dereference(vnode->cb_interest))) { changed = true; break; } @@ -178,7 +176,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, } } - if (afs_cb_is_broken(cb_break, vnode, vnode->cb_interest)) + if (afs_cb_is_broken(cb_break, vnode, rcu_dereference(vnode->cb_interest))) goto someone_else_changed_it; /* We need a ref on any permits list we want to copy as we'll have to @@ -255,14 +253,16 @@ found: kfree(new); + rcu_read_lock(); spin_lock(&vnode->lock); zap = rcu_access_pointer(vnode->permit_cache); - if (!afs_cb_is_broken(cb_break, vnode, vnode->cb_interest) && + if (!afs_cb_is_broken(cb_break, vnode, rcu_dereference(vnode->cb_interest)) && zap == permits) rcu_assign_pointer(vnode->permit_cache, replacement); else zap = replacement; spin_unlock(&vnode->lock); + rcu_read_unlock(); afs_put_permits(zap); out_put: afs_put_permits(permits); @@ -322,13 +322,12 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key, */ _debug("no valid permit"); - ret = afs_fetch_status(vnode, key, false); + ret = afs_fetch_status(vnode, key, false, _access); if (ret < 0) { *_access = 0; _leave(" = %d", ret); return ret; } - *_access = vnode->status.caller_access; } _leave(" = 0 [access %x]", *_access); diff --git a/fs/afs/server.c b/fs/afs/server.c index 642afa2e9783..52c170b59cfd 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -226,7 +226,6 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, RCU_INIT_POINTER(server->addresses, alist); server->addr_version = alist->version; server->uuid = *uuid; - server->flags = (1UL << AFS_SERVER_FL_NEW); server->update_at = ktime_get_real_seconds() + afs_server_update_delay; rwlock_init(&server->fs_lock); INIT_HLIST_HEAD(&server->cb_volumes); @@ -522,8 +521,15 @@ static noinline bool afs_update_server_record(struct afs_fs_cursor *fc, struct a alist = afs_vl_lookup_addrs(fc->vnode->volume->cell, fc->key, &server->uuid); if (IS_ERR(alist)) { - fc->ac.error = PTR_ERR(alist); - _leave(" = f [%d]", fc->ac.error); + if ((PTR_ERR(alist) == -ERESTARTSYS || + PTR_ERR(alist) == -EINTR) && + !(fc->flags & AFS_FS_CURSOR_INTR) && + server->addresses) { + _leave(" = t [intr]"); + return true; + } + fc->error = PTR_ERR(alist); + _leave(" = f [%d]", fc->error); return false; } @@ -575,7 +581,11 @@ retry: ret = wait_on_bit(&server->flags, AFS_SERVER_FL_UPDATING, TASK_INTERRUPTIBLE); if (ret == -ERESTARTSYS) { - fc->ac.error = ret; + if (!(fc->flags & AFS_FS_CURSOR_INTR) && server->addresses) { + _leave(" = t [intr]"); + return true; + } + fc->error = ret; _leave(" = f [intr]"); return false; } diff --git a/fs/afs/super.c b/fs/afs/super.c index 5adf012b8e27..f18911e8d770 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -33,6 +33,7 @@ static void afs_i_init_once(void *foo); static void afs_kill_super(struct super_block *sb); static struct inode *afs_alloc_inode(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); +static void afs_free_inode(struct inode *inode); static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); static int afs_show_devname(struct seq_file *m, struct dentry *root); static int afs_show_options(struct seq_file *m, struct dentry *root); @@ -45,7 +46,7 @@ struct file_system_type afs_fs_type = { .init_fs_context = afs_init_fs_context, .parameters = &afs_fs_parameters, .kill_sb = afs_kill_super, - .fs_flags = 0, + .fs_flags = FS_RENAME_DOES_D_MOVE, }; MODULE_ALIAS_FS("afs"); @@ -56,6 +57,7 @@ static const struct super_operations afs_super_ops = { .alloc_inode = afs_alloc_inode, .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, + .free_inode = afs_free_inode, .evict_inode = afs_evict_inode, .show_devname = afs_show_devname, .show_options = afs_show_options, @@ -67,19 +69,30 @@ static atomic_t afs_count_active_inodes; enum afs_param { Opt_autocell, Opt_dyn, + Opt_flock, Opt_source, }; static const struct fs_parameter_spec afs_param_specs[] = { fsparam_flag ("autocell", Opt_autocell), fsparam_flag ("dyn", Opt_dyn), + fsparam_enum ("flock", Opt_flock), fsparam_string("source", Opt_source), {} }; +static const struct fs_parameter_enum afs_param_enums[] = { + { Opt_flock, "local", afs_flock_mode_local }, + { Opt_flock, "openafs", afs_flock_mode_openafs }, + { Opt_flock, "strict", afs_flock_mode_strict }, + { Opt_flock, "write", afs_flock_mode_write }, + {} +}; + static const struct fs_parameter_description afs_fs_parameters = { .name = "kAFS", .specs = afs_param_specs, + .enums = afs_param_enums, }; /* @@ -182,11 +195,22 @@ static int afs_show_devname(struct seq_file *m, struct dentry *root) static int afs_show_options(struct seq_file *m, struct dentry *root) { struct afs_super_info *as = AFS_FS_S(root->d_sb); + const char *p = NULL; if (as->dyn_root) seq_puts(m, ",dyn"); if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags)) seq_puts(m, ",autocell"); + switch (as->flock_mode) { + case afs_flock_mode_unset: break; + case afs_flock_mode_local: p = "local"; break; + case afs_flock_mode_openafs: p = "openafs"; break; + case afs_flock_mode_strict: p = "strict"; break; + case afs_flock_mode_write: p = "write"; break; + } + if (p) + seq_printf(m, ",flock=%s", p); + return 0; } @@ -315,6 +339,10 @@ static int afs_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->dyn_root = true; break; + case Opt_flock: + ctx->flock_mode = result.uint_32; + break; + default: return -EINVAL; } @@ -398,7 +426,7 @@ static int afs_set_super(struct super_block *sb, struct fs_context *fc) static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) { struct afs_super_info *as = AFS_FS_S(sb); - struct afs_fid fid; + struct afs_iget_data iget_data; struct inode *inode = NULL; int ret; @@ -423,11 +451,13 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) } else { sprintf(sb->s_id, "%llu", as->volume->vid); afs_activate_volume(as->volume); - fid.vid = as->volume->vid; - fid.vnode = 1; - fid.vnode_hi = 0; - fid.unique = 1; - inode = afs_iget(sb, ctx->key, &fid, NULL, NULL, NULL); + iget_data.fid.vid = as->volume->vid; + iget_data.fid.vnode = 1; + iget_data.fid.vnode_hi = 0; + iget_data.fid.unique = 1; + iget_data.cb_v_break = as->volume->cb_v_break; + iget_data.cb_s_break = 0; + inode = afs_iget(sb, ctx->key, &iget_data, NULL, NULL, NULL); } if (IS_ERR(inode)) @@ -466,6 +496,7 @@ static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc) as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL); if (as) { as->net_ns = get_net(fc->net_ns); + as->flock_mode = ctx->flock_mode; if (ctx->dyn_root) { as->dyn_root = true; } else { @@ -550,6 +581,7 @@ static int afs_get_tree(struct fs_context *fc) } fc->root = dget(sb->s_root); + trace_afs_get_tree(as->cell, as->volume); _leave(" = 0 [%p]", sb); return 0; @@ -647,24 +679,23 @@ static struct inode *afs_alloc_inode(struct super_block *sb) vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; - vnode->cb_interest = NULL; + RCU_INIT_POINTER(vnode->cb_interest, NULL); #ifdef CONFIG_AFS_FSCACHE vnode->cache = NULL; #endif vnode->flags = 1 << AFS_VNODE_UNSET; - vnode->cb_type = 0; vnode->lock_state = AFS_VNODE_LOCK_NONE; + init_rwsem(&vnode->rmdir_lock); + _leave(" = %p", &vnode->vfs_inode); return &vnode->vfs_inode; } -static void afs_i_callback(struct rcu_head *head) +static void afs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); - struct afs_vnode *vnode = AFS_FS_I(inode); - kmem_cache_free(afs_inode_cachep, vnode); + kmem_cache_free(afs_inode_cachep, AFS_FS_I(inode)); } /* @@ -678,9 +709,8 @@ static void afs_destroy_inode(struct inode *inode) _debug("DESTROY INODE %p", inode); - ASSERTCMP(vnode->cb_interest, ==, NULL); + ASSERTCMP(rcu_access_pointer(vnode->cb_interest), ==, NULL); - call_rcu(&inode->i_rcu, afs_i_callback); atomic_dec(&afs_count_active_inodes); } @@ -712,7 +742,7 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) return PTR_ERR(key); ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { fc.flags |= AFS_FS_CURSOR_NO_VSLEEP; while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); @@ -720,7 +750,6 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) } afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); ret = afs_end_vnode_operation(&fc); } diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c index b4f1a84519b9..61e25010ff33 100644 --- a/fs/afs/vl_list.c +++ b/fs/afs/vl_list.c @@ -232,18 +232,16 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell, if (bs.status > NR__dns_lookup_status) bs.status = NR__dns_lookup_status; + /* See if we can update an old server record */ server = NULL; - if (previous) { - /* See if we can update an old server record */ - for (i = 0; i < previous->nr_servers; i++) { - struct afs_vlserver *p = previous->servers[i].server; - - if (p->name_len == bs.name_len && - p->port == bs.port && - strncasecmp(b, p->name, bs.name_len) == 0) { - server = afs_get_vlserver(p); - break; - } + for (i = 0; i < previous->nr_servers; i++) { + struct afs_vlserver *p = previous->servers[i].server; + + if (p->name_len == bs.name_len && + p->port == bs.port && + strncasecmp(b, p->name, bs.name_len) == 0) { + server = afs_get_vlserver(p); + break; } } diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index f402ee8171a1..beb991563939 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -33,8 +33,8 @@ static bool afs_vl_probe_done(struct afs_vlserver *server) void afs_vlserver_probe_result(struct afs_call *call) { struct afs_addr_list *alist = call->alist; - struct afs_vlserver *server = call->reply[0]; - unsigned int server_index = (long)call->reply[1]; + struct afs_vlserver *server = call->vlserver; + unsigned int server_index = call->server_index; unsigned int index = call->addr_ix; unsigned int rtt = UINT_MAX; bool have_result = false; @@ -141,8 +141,8 @@ static bool afs_do_probe_vlserver(struct afs_net *net, struct afs_addr_cursor ac = { .index = 0, }; + struct afs_call *call; bool in_progress = false; - int err; _enter("%s", server->name); @@ -156,12 +156,14 @@ static bool afs_do_probe_vlserver(struct afs_net *net, server->probe.rtt = UINT_MAX; for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { - err = afs_vl_get_capabilities(net, &ac, key, server, - server_index, true); - if (err == -EINPROGRESS) + call = afs_vl_get_capabilities(net, &ac, key, server, + server_index); + if (!IS_ERR(call)) { + afs_put_call(call); in_progress = true; - else - afs_prioritise_error(_e, err, ac.abort_code); + } else { + afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code); + } } if (!in_progress) diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index 7adde83a0648..3f845489a9f0 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -43,11 +43,29 @@ bool afs_begin_vlserver_operation(struct afs_vl_cursor *vc, struct afs_cell *cel static bool afs_start_vl_iteration(struct afs_vl_cursor *vc) { struct afs_cell *cell = vc->cell; + unsigned int dns_lookup_count; + + if (cell->dns_source == DNS_RECORD_UNAVAILABLE || + cell->dns_expiry <= ktime_get_real_seconds()) { + dns_lookup_count = smp_load_acquire(&cell->dns_lookup_count); + set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags); + queue_work(afs_wq, &cell->manager); + + if (cell->dns_source == DNS_RECORD_UNAVAILABLE) { + if (wait_var_event_interruptible( + &cell->dns_lookup_count, + smp_load_acquire(&cell->dns_lookup_count) + != dns_lookup_count) < 0) { + vc->error = -ERESTARTSYS; + return false; + } + } - if (wait_on_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET, - TASK_INTERRUPTIBLE)) { - vc->error = -ERESTARTSYS; - return false; + /* Status load is ordered after lookup counter load */ + if (cell->dns_source == DNS_RECORD_UNAVAILABLE) { + vc->error = -EDESTADDRREQ; + return false; + } } read_lock(&cell->vl_servers_lock); @@ -55,7 +73,7 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc) rcu_dereference_protected(cell->vl_servers, lockdep_is_held(&cell->vl_servers_lock))); read_unlock(&cell->vl_servers_lock); - if (!vc->server_list || !vc->server_list->nr_servers) + if (!vc->server_list->nr_servers) return false; vc->untried = (1UL << vc->server_list->nr_servers) - 1; diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index c3d9e5a5f67e..3d4b9836a2e2 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -34,7 +34,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) /* unmarshall the reply once we've received all of it */ uvldb = call->buffer; - entry = call->reply[0]; + entry = call->ret_vldb; nr_servers = ntohl(uvldb->nServers); if (nr_servers > AFS_NMAXNSERVERS) @@ -110,7 +110,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) static void afs_destroy_vl_get_entry_by_name_u(struct afs_call *call) { - kfree(call->reply[0]); + kfree(call->ret_vldb); afs_flat_call_destructor(call); } @@ -155,8 +155,8 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc, } call->key = vc->key; - call->reply[0] = entry; - call->ret_reply0 = true; + call->ret_vldb = entry; + call->max_lifespan = AFS_VL_MAX_LIFESPAN; /* Marshall the parameters */ bp = call->request; @@ -167,7 +167,8 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc, memset((void *)bp + volnamesz, 0, padsz); trace_afs_make_vl_call(call); - return (struct afs_vldb_entry *)afs_make_call(&vc->ac, call, GFP_KERNEL, false); + afs_make_call(&vc->ac, call, GFP_KERNEL); + return (struct afs_vldb_entry *)afs_wait_for_call_to_complete(call, &vc->ac); } /* @@ -195,7 +196,9 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) sizeof(struct afs_uuid__xdr) + 3 * sizeof(__be32)); call->unmarshall++; - /* Extract the returned uuid, uniquifier, nentries and blkaddrs size */ + /* Extract the returned uuid, uniquifier, nentries and + * blkaddrs size */ + /* Fall through */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -211,7 +214,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) if (!alist) return -ENOMEM; alist->version = uniquifier; - call->reply[0] = alist; + call->ret_alist = alist; call->count = count; call->count2 = nentries; call->unmarshall++; @@ -220,13 +223,13 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) count = min(call->count, 4U); afs_extract_to_buf(call, count * sizeof(__be32)); - /* Extract entries */ + /* Fall through - and extract entries */ case 2: ret = afs_extract_data(call, call->count > 4); if (ret < 0) return ret; - alist = call->reply[0]; + alist = call->ret_alist; bp = call->buffer; count = min(call->count, 4U); for (i = 0; i < count; i++) @@ -246,8 +249,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) static void afs_vl_get_addrs_u_destructor(struct afs_call *call) { - afs_put_server(call->net, (struct afs_server *)call->reply[0]); - kfree(call->reply[1]); + afs_put_addrlist(call->ret_alist); return afs_flat_call_destructor(call); } @@ -284,8 +286,8 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc, return ERR_PTR(-ENOMEM); call->key = vc->key; - call->reply[0] = NULL; - call->ret_reply0 = true; + call->ret_alist = NULL; + call->max_lifespan = AFS_VL_MAX_LIFESPAN; /* Marshall the parameters */ bp = call->request; @@ -304,7 +306,8 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc, r->uuid.node[i] = htonl(u->node[i]); trace_afs_make_vl_call(call); - return (struct afs_addr_list *)afs_make_call(&vc->ac, call, GFP_KERNEL, false); + afs_make_call(&vc->ac, call, GFP_KERNEL); + return (struct afs_addr_list *)afs_wait_for_call_to_complete(call, &vc->ac); } /* @@ -323,7 +326,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; - /* Extract the capabilities word count */ + /* Fall through - and extract the capabilities word count */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -336,7 +339,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call) call->unmarshall++; afs_extract_discard(call, count * sizeof(__be32)); - /* Extract capabilities words */ + /* Fall through - and extract capabilities words */ case 2: ret = afs_extract_data(call, false); if (ret < 0) @@ -354,9 +357,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call) static void afs_destroy_vl_get_capabilities(struct afs_call *call) { - struct afs_vlserver *server = call->reply[0]; - - afs_put_vlserver(call->net, server); + afs_put_vlserver(call->net, call->vlserver); afs_flat_call_destructor(call); } @@ -378,12 +379,11 @@ static const struct afs_call_type afs_RXVLGetCapabilities = { * We use this to probe for service upgrade to determine what the server at the * other end supports. */ -int afs_vl_get_capabilities(struct afs_net *net, - struct afs_addr_cursor *ac, - struct key *key, - struct afs_vlserver *server, - unsigned int server_index, - bool async) +struct afs_call *afs_vl_get_capabilities(struct afs_net *net, + struct afs_addr_cursor *ac, + struct key *key, + struct afs_vlserver *server, + unsigned int server_index) { struct afs_call *call; __be32 *bp; @@ -392,13 +392,14 @@ int afs_vl_get_capabilities(struct afs_net *net, call = afs_alloc_flat_call(net, &afs_RXVLGetCapabilities, 1 * 4, 16 * 4); if (!call) - return -ENOMEM; + return ERR_PTR(-ENOMEM); call->key = key; - call->reply[0] = afs_get_vlserver(server); - call->reply[1] = (void *)(long)server_index; + call->vlserver = afs_get_vlserver(server); + call->server_index = server_index; call->upgrade = true; - call->want_reply_time = true; + call->async = true; + call->max_lifespan = AFS_PROBE_MAX_LIFESPAN; /* marshall the parameters */ bp = call->request; @@ -406,7 +407,8 @@ int afs_vl_get_capabilities(struct afs_net *net, /* Can't take a ref on server */ trace_afs_make_vl_call(call); - return afs_make_call(ac, call, GFP_KERNEL, async); + afs_make_call(ac, call, GFP_KERNEL); + return call; } /* @@ -436,6 +438,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) /* Extract the returned uuid, uniquifier, fsEndpoints count and * either the first fsEndpoint type or the volEndpoints * count if there are no fsEndpoints. */ + /* Fall through */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -454,7 +457,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) if (!alist) return -ENOMEM; alist->version = uniquifier; - call->reply[0] = alist; + call->ret_alist = alist; if (call->count == 0) goto extract_volendpoints; @@ -476,13 +479,13 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) afs_extract_to_buf(call, size); call->unmarshall = 2; - /* Extract fsEndpoints[] entries */ + /* Fall through - and extract fsEndpoints[] entries */ case 2: ret = afs_extract_data(call, true); if (ret < 0) return ret; - alist = call->reply[0]; + alist = call->ret_alist; bp = call->buffer; switch (call->count2) { case YFS_ENDPOINT_IPV4: @@ -529,6 +532,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) * extract the type of the next endpoint when we extract the * data of the current one, but this is the first... */ + /* Fall through */ case 3: ret = afs_extract_data(call, true); if (ret < 0) @@ -555,7 +559,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) afs_extract_to_buf(call, size); call->unmarshall = 4; - /* Extract volEndpoints[] entries */ + /* Fall through - and extract volEndpoints[] entries */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -591,7 +595,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) afs_extract_discard(call, 0); call->unmarshall = 5; - /* Done */ + /* Fall through - Done */ case 5: ret = afs_extract_data(call, false); if (ret < 0) @@ -602,7 +606,6 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) break; } - alist = call->reply[0]; _leave(" = 0 [done]"); return 0; } @@ -637,8 +640,8 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc, return ERR_PTR(-ENOMEM); call->key = vc->key; - call->reply[0] = NULL; - call->ret_reply0 = true; + call->ret_alist = NULL; + call->max_lifespan = AFS_VL_MAX_LIFESPAN; /* Marshall the parameters */ bp = call->request; @@ -647,5 +650,6 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc, memcpy(bp, uuid, sizeof(*uuid)); /* Type opr_uuid */ trace_afs_make_vl_call(call); - return (struct afs_addr_list *)afs_make_call(&vc->ac, call, GFP_KERNEL, false); + afs_make_call(&vc->ac, call, GFP_KERNEL); + return (struct afs_addr_list *)afs_wait_for_call_to_complete(call, &vc->ac); } diff --git a/fs/afs/write.c b/fs/afs/write.c index 72efcfcf9f95..8bcab95f1127 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -264,6 +264,7 @@ static void afs_kill_pages(struct address_space *mapping, first = page->index + 1; lock_page(page); generic_error_remove_page(mapping, page); + unlock_page(page); } __pagevec_release(&pv); @@ -313,6 +314,46 @@ static void afs_redirty_pages(struct writeback_control *wbc, } /* + * completion of write to server + */ +static void afs_pages_written_back(struct afs_vnode *vnode, + pgoff_t first, pgoff_t last) +{ + struct pagevec pv; + unsigned long priv; + unsigned count, loop; + + _enter("{%llx:%llu},{%lx-%lx}", + vnode->fid.vid, vnode->fid.vnode, first, last); + + pagevec_init(&pv); + + do { + _debug("done %lx-%lx", first, last); + + count = last - first + 1; + if (count > PAGEVEC_SIZE) + count = PAGEVEC_SIZE; + pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping, + first, count, pv.pages); + ASSERTCMP(pv.nr, ==, count); + + for (loop = 0; loop < count; loop++) { + priv = page_private(pv.pages[loop]); + trace_afs_page_dirty(vnode, tracepoint_string("clear"), + pv.pages[loop]->index, priv); + set_page_private(pv.pages[loop], 0); + end_page_writeback(pv.pages[loop]); + } + first += count; + __pagevec_release(&pv); + } while (first <= last); + + afs_prune_wb_keys(vnode); + _leave(""); +} + +/* * write to a file */ static int afs_store_data(struct address_space *mapping, @@ -321,6 +362,7 @@ static int afs_store_data(struct address_space *mapping, { struct afs_vnode *vnode = AFS_FS_I(mapping->host); struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_wb_key *wbk = NULL; struct list_head *p; int ret = -ENOKEY, ret2; @@ -332,6 +374,10 @@ static int afs_store_data(struct address_space *mapping, vnode->fid.unique, first, last, offset, to); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + return -ENOMEM; + spin_lock(&vnode->wb_lock); p = vnode->wb_keys.next; @@ -350,6 +396,7 @@ try_next_key: spin_unlock(&vnode->wb_lock); afs_put_wb_key(wbk); + kfree(scb); _leave(" = %d [no keys]", ret); return ret; @@ -360,14 +407,19 @@ found_key: _debug("USE WB KEY %u", key_serial(wbk->key)); ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, wbk->key)) { + if (afs_begin_vnode_operation(&fc, vnode, wbk->key, false)) { + afs_dataversion_t data_version = vnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_store_data(&fc, mapping, first, last, offset, to); + afs_fs_store_data(&fc, mapping, first, last, offset, to, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); + if (fc.ac.error == 0) + afs_pages_written_back(vnode, first, last); ret = afs_end_vnode_operation(&fc); } @@ -392,6 +444,7 @@ found_key: } afs_put_wb_key(wbk); + kfree(scb); _leave(" = %d", ret); return ret; } @@ -678,46 +731,6 @@ int afs_writepages(struct address_space *mapping, } /* - * completion of write to server - */ -void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call) -{ - struct pagevec pv; - unsigned long priv; - unsigned count, loop; - pgoff_t first = call->first, last = call->last; - - _enter("{%llx:%llu},{%lx-%lx}", - vnode->fid.vid, vnode->fid.vnode, first, last); - - pagevec_init(&pv); - - do { - _debug("done %lx-%lx", first, last); - - count = last - first + 1; - if (count > PAGEVEC_SIZE) - count = PAGEVEC_SIZE; - pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping, - first, count, pv.pages); - ASSERTCMP(pv.nr, ==, count); - - for (loop = 0; loop < count; loop++) { - priv = page_private(pv.pages[loop]); - trace_afs_page_dirty(vnode, tracepoint_string("clear"), - pv.pages[loop]->index, priv); - set_page_private(pv.pages[loop], 0); - end_page_writeback(pv.pages[loop]); - } - first += count; - __pagevec_release(&pv); - } while (first <= last); - - afs_prune_wb_keys(vnode); - _leave(""); -} - -/* * write to an AFS file */ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index a2cdf25573e2..17f58fea7ec1 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -16,9 +16,14 @@ #include "internal.h" static const char afs_xattr_list[] = + "afs.acl\0" "afs.cell\0" "afs.fid\0" - "afs.volume"; + "afs.volume\0" + "afs.yfs.acl\0" + "afs.yfs.acl_inherited\0" + "afs.yfs.acl_num_cleaned\0" + "afs.yfs.vol_acl"; /* * Retrieve a list of the supported xattrs. @@ -34,6 +39,300 @@ ssize_t afs_listxattr(struct dentry *dentry, char *buffer, size_t size) } /* + * Get a file's ACL. + */ +static int afs_xattr_get_acl(const struct xattr_handler *handler, + struct dentry *dentry, + struct inode *inode, const char *name, + void *buffer, size_t size) +{ + struct afs_fs_cursor fc; + struct afs_status_cb *scb; + struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_acl *acl = NULL; + struct key *key; + int ret = -ENOMEM; + + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + goto error; + + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto error_scb; + } + + ret = -ERESTARTSYS; + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + + while (afs_select_fileserver(&fc)) { + fc.cb_break = afs_calc_vnode_cb_break(vnode); + acl = afs_fs_fetch_acl(&fc, scb); + } + + afs_check_for_remote_deletion(&fc, fc.vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); + ret = afs_end_vnode_operation(&fc); + } + + if (ret == 0) { + ret = acl->size; + if (size > 0) { + if (acl->size <= size) + memcpy(buffer, acl->data, acl->size); + else + ret = -ERANGE; + } + kfree(acl); + } + + key_put(key); +error_scb: + kfree(scb); +error: + return ret; +} + +/* + * Set a file's AFS3 ACL. + */ +static int afs_xattr_set_acl(const struct xattr_handler *handler, + struct dentry *dentry, + struct inode *inode, const char *name, + const void *buffer, size_t size, int flags) +{ + struct afs_fs_cursor fc; + struct afs_status_cb *scb; + struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_acl *acl = NULL; + struct key *key; + int ret = -ENOMEM; + + if (flags == XATTR_CREATE) + return -EINVAL; + + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + goto error; + + acl = kmalloc(sizeof(*acl) + size, GFP_KERNEL); + if (!acl) + goto error_scb; + + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto error_acl; + } + + acl->size = size; + memcpy(acl->data, buffer, size); + + ret = -ERESTARTSYS; + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + + while (afs_select_fileserver(&fc)) { + fc.cb_break = afs_calc_vnode_cb_break(vnode); + afs_fs_store_acl(&fc, acl, scb); + } + + afs_check_for_remote_deletion(&fc, fc.vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); + ret = afs_end_vnode_operation(&fc); + } + + key_put(key); +error_acl: + kfree(acl); +error_scb: + kfree(scb); +error: + return ret; +} + +static const struct xattr_handler afs_xattr_afs_acl_handler = { + .name = "afs.acl", + .get = afs_xattr_get_acl, + .set = afs_xattr_set_acl, +}; + +/* + * Get a file's YFS ACL. + */ +static int afs_xattr_get_yfs(const struct xattr_handler *handler, + struct dentry *dentry, + struct inode *inode, const char *name, + void *buffer, size_t size) +{ + struct afs_fs_cursor fc; + struct afs_status_cb *scb; + struct afs_vnode *vnode = AFS_FS_I(inode); + struct yfs_acl *yacl = NULL; + struct key *key; + char buf[16], *data; + int which = 0, dsize, ret = -ENOMEM; + + if (strcmp(name, "acl") == 0) + which = 0; + else if (strcmp(name, "acl_inherited") == 0) + which = 1; + else if (strcmp(name, "acl_num_cleaned") == 0) + which = 2; + else if (strcmp(name, "vol_acl") == 0) + which = 3; + else + return -EOPNOTSUPP; + + yacl = kzalloc(sizeof(struct yfs_acl), GFP_KERNEL); + if (!yacl) + goto error; + + if (which == 0) + yacl->flags |= YFS_ACL_WANT_ACL; + else if (which == 3) + yacl->flags |= YFS_ACL_WANT_VOL_ACL; + + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + goto error_yacl; + + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto error_scb; + } + + ret = -ERESTARTSYS; + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + + while (afs_select_fileserver(&fc)) { + fc.cb_break = afs_calc_vnode_cb_break(vnode); + yfs_fs_fetch_opaque_acl(&fc, yacl, scb); + } + + afs_check_for_remote_deletion(&fc, fc.vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); + ret = afs_end_vnode_operation(&fc); + } + + if (ret < 0) + goto error_key; + + switch (which) { + case 0: + data = yacl->acl->data; + dsize = yacl->acl->size; + break; + case 1: + data = buf; + dsize = snprintf(buf, sizeof(buf), "%u", yacl->inherit_flag); + break; + case 2: + data = buf; + dsize = snprintf(buf, sizeof(buf), "%u", yacl->num_cleaned); + break; + case 3: + data = yacl->vol_acl->data; + dsize = yacl->vol_acl->size; + break; + default: + ret = -EOPNOTSUPP; + goto error_key; + } + + ret = dsize; + if (size > 0) { + if (dsize > size) { + ret = -ERANGE; + goto error_key; + } + memcpy(buffer, data, dsize); + } + +error_key: + key_put(key); +error_scb: + kfree(scb); +error_yacl: + yfs_free_opaque_acl(yacl); +error: + return ret; +} + +/* + * Set a file's YFS ACL. + */ +static int afs_xattr_set_yfs(const struct xattr_handler *handler, + struct dentry *dentry, + struct inode *inode, const char *name, + const void *buffer, size_t size, int flags) +{ + struct afs_fs_cursor fc; + struct afs_status_cb *scb; + struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_acl *acl = NULL; + struct key *key; + int ret = -ENOMEM; + + if (flags == XATTR_CREATE || + strcmp(name, "acl") != 0) + return -EINVAL; + + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + goto error; + + acl = kmalloc(sizeof(*acl) + size, GFP_KERNEL); + if (!acl) + goto error_scb; + + acl->size = size; + memcpy(acl->data, buffer, size); + + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto error_acl; + } + + ret = -ERESTARTSYS; + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + + while (afs_select_fileserver(&fc)) { + fc.cb_break = afs_calc_vnode_cb_break(vnode); + yfs_fs_store_opaque_acl2(&fc, acl, scb); + } + + afs_check_for_remote_deletion(&fc, fc.vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); + ret = afs_end_vnode_operation(&fc); + } + +error_acl: + kfree(acl); + key_put(key); +error_scb: + kfree(scb); +error: + return ret; +} + +static const struct xattr_handler afs_xattr_yfs_handler = { + .prefix = "afs.yfs.", + .get = afs_xattr_get_yfs, + .set = afs_xattr_set_yfs, +}; + +/* * Get the name of the cell on which a file resides. */ static int afs_xattr_get_cell(const struct xattr_handler *handler, @@ -50,7 +349,7 @@ static int afs_xattr_get_cell(const struct xattr_handler *handler, return namelen; if (namelen > size) return -ERANGE; - memcpy(buffer, cell->name, size); + memcpy(buffer, cell->name, namelen); return namelen; } @@ -69,11 +368,20 @@ static int afs_xattr_get_fid(const struct xattr_handler *handler, void *buffer, size_t size) { struct afs_vnode *vnode = AFS_FS_I(inode); - char text[8 + 1 + 8 + 1 + 8 + 1]; + char text[16 + 1 + 24 + 1 + 8 + 1]; size_t len; - len = sprintf(text, "%llx:%llx:%x", - vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); + /* The volume ID is 64-bit, the vnode ID is 96-bit and the + * uniquifier is 32-bit. + */ + len = sprintf(text, "%llx:", vnode->fid.vid); + if (vnode->fid.vnode_hi) + len += sprintf(text + len, "%x%016llx", + vnode->fid.vnode_hi, vnode->fid.vnode); + else + len += sprintf(text + len, "%llx", vnode->fid.vnode); + len += sprintf(text + len, ":%x", vnode->fid.unique); + if (size == 0) return len; if (len > size) @@ -104,7 +412,7 @@ static int afs_xattr_get_volume(const struct xattr_handler *handler, return namelen; if (namelen > size) return -ERANGE; - memcpy(buffer, volname, size); + memcpy(buffer, volname, namelen); return namelen; } @@ -114,8 +422,10 @@ static const struct xattr_handler afs_xattr_afs_volume_handler = { }; const struct xattr_handler *afs_xattr_handlers[] = { + &afs_xattr_afs_acl_handler, &afs_xattr_afs_cell_handler, &afs_xattr_afs_fid_handler, &afs_xattr_afs_volume_handler, + &afs_xattr_yfs_handler, /* afs.yfs. prefix */ NULL }; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 6e97a42d24d1..10de675dc6fc 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -183,24 +183,19 @@ static void xdr_dump_bad(const __be32 *bp) /* * Decode a YFSFetchStatus block */ -static int xdr_decode_YFSFetchStatus(struct afs_call *call, - const __be32 **_bp, - struct afs_file_status *status, - struct afs_vnode *vnode, - const afs_dataversion_t *expected_version, - struct afs_read *read_req) +static int 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; - u8 flags = 0; status->abort_code = ntohl(xdr->abort_code); if (status->abort_code != 0) { - if (vnode && status->abort_code == VNOVNODE) { - set_bit(AFS_VNODE_DELETED, &vnode->flags); + if (status->abort_code == VNOVNODE) status->nlink = 0; - __afs_break_callback(vnode); - } + scb->have_error = true; return 0; } @@ -209,77 +204,28 @@ static int xdr_decode_YFSFetchStatus(struct afs_call *call, case AFS_FTYPE_FILE: case AFS_FTYPE_DIR: case AFS_FTYPE_SYMLINK: - if (type != status->type && - vnode && - !test_bit(AFS_VNODE_UNSET, &vnode->flags)) { - pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n", - vnode->fid.vid, - vnode->fid.vnode, - vnode->fid.unique, - status->type, type); - goto bad; - } status->type = type; break; default: goto bad; } -#define EXTRACT_M4(FIELD) \ - do { \ - u32 x = ntohl(xdr->FIELD); \ - if (status->FIELD != x) { \ - flags |= AFS_VNODE_META_CHANGED; \ - status->FIELD = x; \ - } \ - } while (0) - -#define EXTRACT_M8(FIELD) \ - do { \ - u64 x = xdr_to_u64(xdr->FIELD); \ - if (status->FIELD != x) { \ - flags |= AFS_VNODE_META_CHANGED; \ - status->FIELD = x; \ - } \ - } while (0) - -#define EXTRACT_D8(FIELD) \ - do { \ - u64 x = xdr_to_u64(xdr->FIELD); \ - if (status->FIELD != x) { \ - flags |= AFS_VNODE_DATA_CHANGED; \ - status->FIELD = x; \ - } \ - } while (0) - - EXTRACT_M4(nlink); - EXTRACT_D8(size); - EXTRACT_D8(data_version); - EXTRACT_M8(author); - EXTRACT_M8(owner); - EXTRACT_M8(group); - EXTRACT_M4(mode); - EXTRACT_M4(caller_access); /* call ticket dependent */ - EXTRACT_M4(anon_access); - - status->mtime_client = xdr_to_time(xdr->mtime_client); - status->mtime_server = xdr_to_time(xdr->mtime_server); - status->lock_count = ntohl(xdr->lock_count); - - if (read_req) { - read_req->data_version = status->data_version; - read_req->file_size = status->size; - } + status->nlink = ntohl(xdr->nlink); + status->author = xdr_to_u64(xdr->author); + status->owner = xdr_to_u64(xdr->owner); + status->caller_access = ntohl(xdr->caller_access); /* Ticket dependent */ + status->anon_access = ntohl(xdr->anon_access); + status->mode = ntohl(xdr->mode) & S_IALLUGO; + status->group = xdr_to_u64(xdr->group); + status->lock_count = ntohl(xdr->lock_count); + + status->mtime_client = xdr_to_time(xdr->mtime_client); + status->mtime_server = xdr_to_time(xdr->mtime_server); + status->size = xdr_to_u64(xdr->size); + status->data_version = xdr_to_u64(xdr->data_version); + scb->have_status = true; *_bp += xdr_size(xdr); - - if (vnode) { - if (test_bit(AFS_VNODE_UNSET, &vnode->flags)) - flags |= AFS_VNODE_NOT_YET_SET; - afs_update_inode_from_status(vnode, status, expected_version, - flags); - } - return 0; bad: @@ -288,73 +234,20 @@ bad: } /* - * Decode the file status. We need to lock the target vnode if we're going to - * update its status so that stat() sees the attributes update atomically. - */ -static int yfs_decode_status(struct afs_call *call, - const __be32 **_bp, - struct afs_file_status *status, - struct afs_vnode *vnode, - const afs_dataversion_t *expected_version, - struct afs_read *read_req) -{ - int ret; - - if (!vnode) - return xdr_decode_YFSFetchStatus(call, _bp, status, vnode, - expected_version, read_req); - - write_seqlock(&vnode->cb_lock); - ret = xdr_decode_YFSFetchStatus(call, _bp, status, vnode, - expected_version, read_req); - write_sequnlock(&vnode->cb_lock); - return ret; -} - -/* * Decode a YFSCallBack block */ -static void xdr_decode_YFSCallBack(struct afs_call *call, - struct afs_vnode *vnode, - const __be32 **_bp) -{ - struct yfs_xdr_YFSCallBack *xdr = (void *)*_bp; - struct afs_cb_interest *old, *cbi = call->cbi; - u64 cb_expiry; - - write_seqlock(&vnode->cb_lock); - - if (!afs_cb_is_broken(call->cb_break, vnode, cbi)) { - cb_expiry = xdr_to_u64(xdr->expiration_time); - do_div(cb_expiry, 10 * 1000 * 1000); - vnode->cb_version = ntohl(xdr->version); - vnode->cb_type = ntohl(xdr->type); - vnode->cb_expires_at = cb_expiry + ktime_get_real_seconds(); - old = vnode->cb_interest; - if (old != call->cbi) { - vnode->cb_interest = cbi; - cbi = old; - } - set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - } - - write_sequnlock(&vnode->cb_lock); - call->cbi = cbi; - *_bp += xdr_size(xdr); -} - -static void xdr_decode_YFSCallBack_raw(const __be32 **_bp, - struct afs_callback *cb) +static void xdr_decode_YFSCallBack(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { struct yfs_xdr_YFSCallBack *x = (void *)*_bp; - u64 cb_expiry; - - cb_expiry = xdr_to_u64(x->expiration_time); - do_div(cb_expiry, 10 * 1000 * 1000); - cb->version = ntohl(x->version); - cb->type = ntohl(x->type); - cb->expires_at = cb_expiry + ktime_get_real_seconds(); + struct afs_callback *cb = &scb->callback; + ktime_t cb_expiry; + cb_expiry = call->reply_time; + cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100); + cb->expires_at = ktime_divns(cb_expiry, NSEC_PER_SEC); + scb->have_cb = true; *_bp += xdr_size(x); } @@ -442,11 +335,10 @@ static void xdr_decode_YFSFetchVolumeStatus(const __be32 **_bp, } /* - * deliver reply data to an FS.FetchStatus + * Deliver a reply that's a status, callback and volsync. */ -static int yfs_deliver_fs_fetch_status_vnode(struct afs_call *call) +static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -454,16 +346,36 @@ static int yfs_deliver_fs_fetch_status_vnode(struct afs_call *call) if (ret < 0) return ret; - _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); + if (ret < 0) + return ret; + xdr_decode_YFSCallBack(&bp, call, call->out_scb); + xdr_decode_YFSVolSync(&bp, call->out_volsync); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * Deliver reply data to operations that just return a file status and a volume + * sync record. + */ +static int yfs_deliver_status_and_volsync(struct afs_call *call) +{ + const __be32 *bp; + int ret; + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + bp = call->buffer; + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_YFSCallBack(call, vnode, &bp); - xdr_decode_YFSVolSync(&bp, call->reply[1]); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -475,15 +387,15 @@ static int yfs_deliver_fs_fetch_status_vnode(struct afs_call *call) static const struct afs_call_type yfs_RXYFSFetchStatus_vnode = { .name = "YFS.FetchStatus(vnode)", .op = yfs_FS_FetchStatus, - .deliver = yfs_deliver_fs_fetch_status_vnode, + .deliver = yfs_deliver_fs_status_cb_and_volsync, .destructor = afs_flat_call_destructor, }; /* * Fetch the status information for a file. */ -int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsync, - bool new_inode) +int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_status_cb *scb, + struct afs_volsync *volsync) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -505,9 +417,8 @@ int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy } call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = volsync; - call->expected_version = new_inode ? 1 : vnode->status.data_version; + call->out_scb = scb; + call->out_volsync = volsync; /* marshall the parameters */ bp = call->request; @@ -516,10 +427,11 @@ int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy bp = xdr_encode_YFSFid(bp, &vnode->fid); yfs_check_req(call, bp); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -527,8 +439,7 @@ int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy */ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; - struct afs_read *req = call->reply[2]; + struct afs_read *req = call->read_request; const __be32 *bp; unsigned int size; int ret; @@ -544,7 +455,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) afs_extract_to_tmp64(call); call->unmarshall++; - /* extract the returned data length */ + /* Fall through - and extract the returned data length */ case 1: _debug("extract data length"); ret = afs_extract_data(call, true); @@ -571,7 +482,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); - /* extract the returned data */ + /* Fall through - and extract the returned data */ case 2: _debug("extract data %zu/%llu", iov_iter_count(&call->iter), req->remain); @@ -585,7 +496,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) if (req->offset == PAGE_SIZE) { req->offset = 0; if (req->page_done) - req->page_done(call, req); + req->page_done(req); req->index++; if (req->remain > 0) goto begin_page; @@ -598,6 +509,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) /* Discard any excess data the server gave us */ iov_iter_discard(&call->iter, READ, req->actual_len - req->len); call->unmarshall = 3; + + /* Fall through */ case 3: _debug("extract discard %zu/%llu", iov_iter_count(&call->iter), req->actual_len - req->len); @@ -613,22 +526,25 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); - /* extract the metadata */ + /* Fall through - and extract the metadata */ case 4: ret = afs_extract_data(call, false); if (ret < 0) return ret; bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &vnode->status.data_version, req); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_YFSCallBack(call, vnode, &bp); - xdr_decode_YFSVolSync(&bp, call->reply[1]); + xdr_decode_YFSCallBack(&bp, call, call->out_scb); + xdr_decode_YFSVolSync(&bp, call->out_volsync); + + req->data_version = call->out_scb->status.data_version; + req->file_size = call->out_scb->status.size; call->unmarshall++; + /* Fall through */ case 5: break; } @@ -638,7 +554,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) zero_user_segment(req->pages[req->index], req->offset, PAGE_SIZE); if (req->page_done) - req->page_done(call, req); + req->page_done(req); req->offset = 0; } @@ -648,9 +564,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) static void yfs_fetch_data_destructor(struct afs_call *call) { - struct afs_read *req = call->reply[2]; - - afs_put_read(req); + afs_put_read(call->read_request); afs_flat_call_destructor(call); } @@ -667,7 +581,8 @@ static const struct afs_call_type yfs_RXYFSFetchData64 = { /* * Fetch data from a file. */ -int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) +int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_status_cb *scb, + struct afs_read *req) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -689,11 +604,9 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = NULL; /* volsync */ - call->reply[2] = req; - call->expected_version = vnode->status.data_version; - call->want_reply_time = true; + call->out_scb = scb; + call->out_volsync = NULL; + call->read_request = req; /* marshall the parameters */ bp = call->request; @@ -705,10 +618,11 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) yfs_check_req(call, bp); refcount_inc(&req->usage); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -716,7 +630,6 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) */ static int yfs_deliver_fs_create_vnode(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -728,16 +641,15 @@ 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->reply[1]); - ret = yfs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + xdr_decode_YFSFid(&bp, call->out_fid); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_YFSCallBack_raw(&bp, call->reply[3]); - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSCallBack(&bp, call, call->out_scb); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -759,14 +671,13 @@ static const struct afs_call_type afs_RXFSCreateFile = { int yfs_fs_create_file(struct afs_fs_cursor *fc, const char *name, umode_t mode, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus, - struct afs_callback *newcb) + struct afs_status_cb *new_scb) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, rplsz; __be32 *bp; @@ -790,25 +701,25 @@ int yfs_fs_create_file(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->reply[3] = newcb; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = new_scb; /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSCREATEFILE); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &dvnode->fid); bp = xdr_encode_string(bp, name, namesz); bp = xdr_encode_YFSStoreStatus_mode(bp, mode); bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */ yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } static const struct afs_call_type yfs_RXFSMakeDir = { @@ -824,14 +735,13 @@ static const struct afs_call_type yfs_RXFSMakeDir = { int yfs_fs_make_dir(struct afs_fs_cursor *fc, const char *name, umode_t mode, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus, - struct afs_callback *newcb) + struct afs_status_cb *new_scb) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, rplsz; __be32 *bp; @@ -854,24 +764,24 @@ int yfs_fs_make_dir(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->reply[3] = newcb; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = new_scb; /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSMAKEDIR); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &dvnode->fid); bp = xdr_encode_string(bp, name, namesz); bp = xdr_encode_YFSStoreStatus_mode(bp, mode); yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -879,8 +789,6 @@ int yfs_fs_make_dir(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_remove_file2(struct afs_call *call) { - struct afs_vnode *dvnode = call->reply[0]; - struct afs_vnode *vnode = call->reply[1]; struct afs_fid fid; const __be32 *bp; int ret; @@ -891,20 +799,18 @@ static int yfs_deliver_fs_remove_file2(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; xdr_decode_YFSFid(&bp, &fid); - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; /* Was deleted if vnode->status.abort_code == VNOVNODE. */ - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); return 0; } @@ -922,7 +828,8 @@ static const struct afs_call_type yfs_RXYFSRemoveFile2 = { * Remove a file and retrieve new file status. */ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, u64 current_data_version) + const char *name, struct afs_status_cb *dvnode_scb, + struct afs_status_cb *vnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -947,9 +854,8 @@ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_scb = vnode_scb; /* marshall the parameters */ bp = call->request; @@ -960,8 +866,10 @@ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &dvnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -969,7 +877,6 @@ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_remove(struct afs_call *call) { - struct afs_vnode *dvnode = call->reply[0]; const __be32 *bp; int ret; @@ -979,14 +886,12 @@ static int yfs_deliver_fs_remove(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); return 0; } @@ -1011,7 +916,8 @@ static const struct afs_call_type yfs_RXYFSRemoveDir = { * remove a file or directory */ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, bool isdir, u64 current_data_version) + const char *name, bool isdir, + struct afs_status_cb *dvnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -1034,9 +940,7 @@ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; /* marshall the parameters */ bp = call->request; @@ -1047,8 +951,10 @@ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &dvnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1056,7 +962,6 @@ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_link(struct afs_call *call) { - struct afs_vnode *dvnode = call->reply[0], *vnode = call->reply[1]; const __be32 *bp; int ret; @@ -1066,16 +971,14 @@ static int yfs_deliver_fs_link(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; } @@ -1094,7 +997,9 @@ static const struct afs_call_type yfs_RXYFSLink = { * Make a hard link. */ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, u64 current_data_version) + const char *name, + struct afs_status_cb *dvnode_scb, + struct afs_status_cb *vnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -1118,9 +1023,8 @@ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_scb = vnode_scb; /* marshall the parameters */ bp = call->request; @@ -1132,8 +1036,10 @@ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &vnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1141,7 +1047,6 @@ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_symlink(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -1153,15 +1058,14 @@ 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->reply[1]); - ret = yfs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + xdr_decode_YFSFid(&bp, call->out_fid); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1183,9 +1087,9 @@ static const struct afs_call_type yfs_RXYFSSymlink = { int yfs_fs_symlink(struct afs_fs_cursor *fc, const char *name, const char *contents, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus) + struct afs_status_cb *vnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -1212,10 +1116,9 @@ int yfs_fs_symlink(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = vnode_scb; /* marshall the parameters */ bp = call->request; @@ -1228,8 +1131,10 @@ int yfs_fs_symlink(struct afs_fs_cursor *fc, yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &dvnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1237,8 +1142,6 @@ int yfs_fs_symlink(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_rename(struct afs_call *call) { - struct afs_vnode *orig_dvnode = call->reply[0]; - struct afs_vnode *new_dvnode = call->reply[1]; const __be32 *bp; int ret; @@ -1248,20 +1151,17 @@ static int yfs_deliver_fs_rename(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &orig_dvnode->status, orig_dvnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - if (new_dvnode != orig_dvnode) { - ret = yfs_decode_status(call, &bp, &new_dvnode->status, new_dvnode, - &call->expected_version_2, NULL); + if (call->out_dir_scb != call->out_scb) { + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; } - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; } @@ -1283,8 +1183,8 @@ int yfs_fs_rename(struct afs_fs_cursor *fc, const char *orig_name, struct afs_vnode *new_dvnode, const char *new_name, - u64 current_orig_data_version, - u64 current_new_data_version) + struct afs_status_cb *orig_dvnode_scb, + struct afs_status_cb *new_dvnode_scb) { struct afs_vnode *orig_dvnode = fc->vnode; struct afs_call *call; @@ -1310,10 +1210,8 @@ int yfs_fs_rename(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = orig_dvnode; - call->reply[1] = new_dvnode; - call->expected_version = current_orig_data_version + 1; - call->expected_version_2 = current_new_data_version + 1; + call->out_dir_scb = orig_dvnode_scb; + call->out_scb = new_dvnode_scb; /* marshall the parameters */ bp = call->request; @@ -1326,37 +1224,10 @@ int yfs_fs_rename(struct afs_fs_cursor *fc, yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &orig_dvnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); -} - -/* - * Deliver reply data to a YFS.StoreData64 operation. - */ -static int yfs_deliver_fs_store_data(struct afs_call *call) -{ - struct afs_vnode *vnode = call->reply[0]; - const __be32 *bp; - int ret; - - _enter(""); - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, NULL); - - afs_pages_written_back(vnode, call); - - _leave(" = 0 [done]"); - return 0; + trace_afs_make_fs_call2(call, &orig_dvnode->fid, orig_name, new_name); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1365,7 +1236,7 @@ static int yfs_deliver_fs_store_data(struct afs_call *call) static const struct afs_call_type yfs_RXYFSStoreData64 = { .name = "YFS.StoreData64", .op = yfs_FS_StoreData64, - .deliver = yfs_deliver_fs_store_data, + .deliver = yfs_deliver_status_and_volsync, .destructor = afs_flat_call_destructor, }; @@ -1374,7 +1245,8 @@ static const struct afs_call_type yfs_RXYFSStoreData64 = { */ int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, pgoff_t first, pgoff_t last, - unsigned offset, unsigned to) + unsigned offset, unsigned to, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1412,13 +1284,12 @@ int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, call->key = fc->key; call->mapping = mapping; - call->reply[0] = vnode; call->first = first; call->last = last; call->first_offset = offset; call->last_to = to; call->send_pages = true; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1433,34 +1304,9 @@ int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); -} - -/* - * deliver reply data to an FS.StoreStatus - */ -static int yfs_deliver_fs_store_status(struct afs_call *call) -{ - struct afs_vnode *vnode = call->reply[0]; - const __be32 *bp; - int ret; - - _enter(""); - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, NULL); - - _leave(" = 0 [done]"); - return 0; + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1469,14 +1315,14 @@ static int yfs_deliver_fs_store_status(struct afs_call *call) static const struct afs_call_type yfs_RXYFSStoreStatus = { .name = "YFS.StoreStatus", .op = yfs_FS_StoreStatus, - .deliver = yfs_deliver_fs_store_status, + .deliver = yfs_deliver_status_and_volsync, .destructor = afs_flat_call_destructor, }; static const struct afs_call_type yfs_RXYFSStoreData64_as_Status = { .name = "YFS.StoreData64", .op = yfs_FS_StoreData64, - .deliver = yfs_deliver_fs_store_status, + .deliver = yfs_deliver_status_and_volsync, .destructor = afs_flat_call_destructor, }; @@ -1484,7 +1330,8 @@ static const struct afs_call_type yfs_RXYFSStoreData64_as_Status = { * Set the attributes on a file, using YFS.StoreData64 rather than * YFS.StoreStatus so as to alter the file size also. */ -static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) +static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1505,8 +1352,7 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1521,14 +1367,17 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* * Set the attributes on a file, using YFS.StoreData64 if there's a change in * file size, and YFS.StoreStatus otherwise. */ -int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) +int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1536,7 +1385,7 @@ int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) __be32 *bp; if (attr->ia_valid & ATTR_SIZE) - return yfs_fs_setattr_size(fc, attr); + return yfs_fs_setattr_size(fc, attr, scb); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); @@ -1551,8 +1400,7 @@ int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1564,7 +1412,9 @@ int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1584,7 +1434,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) call->unmarshall++; afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus)); - /* extract the returned status record */ + /* Fall through - and extract the returned status record */ case 1: _debug("extract status"); ret = afs_extract_data(call, true); @@ -1592,11 +1442,11 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_YFSFetchVolumeStatus(&bp, call->reply[1]); + xdr_decode_YFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); - /* extract the volume name length */ + /* Fall through - and extract the volume name length */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -1608,23 +1458,23 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_volname_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; - /* extract the volume name */ + /* Fall through - and extract the volume name */ case 3: _debug("extract volname"); ret = afs_extract_data(call, true); if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; - /* extract the offline message length */ + /* Fall through - and extract the offline message length */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -1636,24 +1486,24 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_offline_msg_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; - /* extract the offline message */ + /* Fall through - and extract the offline message */ case 5: _debug("extract offline"); ret = afs_extract_data(call, true); if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("offline '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; - /* extract the message of the day length */ + /* Fall through - and extract the message of the day length */ case 6: ret = afs_extract_data(call, true); if (ret < 0) @@ -1665,22 +1515,23 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_motd_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; - /* extract the message of the day */ + /* Fall through - and extract the message of the day */ case 7: _debug("extract motd"); ret = afs_extract_data(call, false); if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("motd '%s'", p); call->unmarshall++; + /* Fall through */ case 8: break; } @@ -1690,23 +1541,13 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) } /* - * Destroy a YFS.GetVolumeStatus call. - */ -static void yfs_get_volume_status_call_destructor(struct afs_call *call) -{ - kfree(call->reply[2]); - call->reply[2] = NULL; - afs_flat_call_destructor(call); -} - -/* * YFS.GetVolumeStatus operation type */ static const struct afs_call_type yfs_RXYFSGetVolumeStatus = { .name = "YFS.GetVolumeStatus", .op = yfs_FS_GetVolumeStatus, .deliver = yfs_deliver_fs_get_volume_status, - .destructor = yfs_get_volume_status_call_destructor, + .destructor = afs_flat_call_destructor, }; /* @@ -1719,28 +1560,21 @@ int yfs_fs_get_volume_status(struct afs_fs_cursor *fc, struct afs_call *call; struct afs_net *net = afs_v2net(vnode); __be32 *bp; - void *tmpbuf; _enter(""); - tmpbuf = kmalloc(AFSOPAQUEMAX, GFP_KERNEL); - if (!tmpbuf) - return -ENOMEM; - call = afs_alloc_flat_call(net, &yfs_RXYFSGetVolumeStatus, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_u64), - sizeof(struct yfs_xdr_YFSFetchVolumeStatus) + - sizeof(__be32)); - if (!call) { - kfree(tmpbuf); + max_t(size_t, + sizeof(struct yfs_xdr_YFSFetchVolumeStatus) + + sizeof(__be32), + AFSOPAQUEMAX + 1)); + if (!call) return -ENOMEM; - } call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = vs; - call->reply[2] = tmpbuf; + call->out_volstatus = vs; /* marshall the parameters */ bp = call->request; @@ -1751,34 +1585,9 @@ int yfs_fs_get_volume_status(struct afs_fs_cursor *fc, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); -} - -/* - * Deliver reply data to an YFS.SetLock, YFS.ExtendLock or YFS.ReleaseLock - */ -static int yfs_deliver_fs_xxxx_lock(struct afs_call *call) -{ - struct afs_vnode *vnode = call->reply[0]; - const __be32 *bp; - int ret; - - _enter("{%u}", call->unmarshall); - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, NULL); - - _leave(" = 0 [done]"); - return 0; + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1787,7 +1596,8 @@ static int yfs_deliver_fs_xxxx_lock(struct afs_call *call) static const struct afs_call_type yfs_RXYFSSetLock = { .name = "YFS.SetLock", .op = yfs_FS_SetLock, - .deliver = yfs_deliver_fs_xxxx_lock, + .deliver = yfs_deliver_status_and_volsync, + .done = afs_lock_op_done, .destructor = afs_flat_call_destructor, }; @@ -1797,7 +1607,8 @@ static const struct afs_call_type yfs_RXYFSSetLock = { static const struct afs_call_type yfs_RXYFSExtendLock = { .name = "YFS.ExtendLock", .op = yfs_FS_ExtendLock, - .deliver = yfs_deliver_fs_xxxx_lock, + .deliver = yfs_deliver_status_and_volsync, + .done = afs_lock_op_done, .destructor = afs_flat_call_destructor, }; @@ -1807,14 +1618,15 @@ static const struct afs_call_type yfs_RXYFSExtendLock = { static const struct afs_call_type yfs_RXYFSReleaseLock = { .name = "YFS.ReleaseLock", .op = yfs_FS_ReleaseLock, - .deliver = yfs_deliver_fs_xxxx_lock, + .deliver = yfs_deliver_status_and_volsync, .destructor = afs_flat_call_destructor, }; /* * Set a lock on a file */ -int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) +int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1833,7 +1645,8 @@ int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1844,14 +1657,16 @@ int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + trace_afs_make_fs_calli(call, &vnode->fid, type); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* * extend a lock on a file */ -int yfs_fs_extend_lock(struct afs_fs_cursor *fc) +int yfs_fs_extend_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1869,7 +1684,8 @@ int yfs_fs_extend_lock(struct afs_fs_cursor *fc) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1880,13 +1696,15 @@ int yfs_fs_extend_lock(struct afs_fs_cursor *fc) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* * release a lock on a file */ -int yfs_fs_release_lock(struct afs_fs_cursor *fc) +int yfs_fs_release_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1904,7 +1722,8 @@ int yfs_fs_release_lock(struct afs_fs_cursor *fc) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1915,38 +1734,9 @@ int yfs_fs_release_lock(struct afs_fs_cursor *fc) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); -} - -/* - * Deliver reply data to an FS.FetchStatus with no vnode. - */ -static int yfs_deliver_fs_fetch_status(struct afs_call *call) -{ - struct afs_file_status *status = call->reply[1]; - struct afs_callback *callback = call->reply[2]; - struct afs_volsync *volsync = call->reply[3]; - struct afs_vnode *vnode = call->reply[0]; - const __be32 *bp; - int ret; - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = yfs_decode_status(call, &bp, status, vnode, - &call->expected_version, NULL); - if (ret < 0) - return ret; - xdr_decode_YFSCallBack_raw(&bp, callback); - xdr_decode_YFSVolSync(&bp, volsync); - - _leave(" = 0 [done]"); - return 0; + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -1955,7 +1745,7 @@ static int yfs_deliver_fs_fetch_status(struct afs_call *call) static const struct afs_call_type yfs_RXYFSFetchStatus = { .name = "YFS.FetchStatus", .op = yfs_FS_FetchStatus, - .deliver = yfs_deliver_fs_fetch_status, + .deliver = yfs_deliver_fs_status_cb_and_volsync, .destructor = afs_flat_call_destructor, }; @@ -1965,8 +1755,7 @@ static const struct afs_call_type yfs_RXYFSFetchStatus = { int yfs_fs_fetch_status(struct afs_fs_cursor *fc, struct afs_net *net, struct afs_fid *fid, - struct afs_file_status *status, - struct afs_callback *callback, + struct afs_status_cb *scb, struct afs_volsync *volsync) { struct afs_call *call; @@ -1987,11 +1776,8 @@ int yfs_fs_fetch_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = NULL; /* vnode for fid[0] */ - call->reply[1] = status; - call->reply[2] = callback; - call->reply[3] = volsync; - call->expected_version = 1; /* vnode->status.data_version */ + call->out_scb = scb; + call->out_volsync = volsync; /* marshall the parameters */ bp = call->request; @@ -2000,10 +1786,11 @@ int yfs_fs_fetch_status(struct afs_fs_cursor *fc, bp = xdr_encode_YFSFid(bp, fid); yfs_check_req(call, bp); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, fid); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); } /* @@ -2011,9 +1798,7 @@ int yfs_fs_fetch_status(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) { - struct afs_file_status *statuses; - struct afs_callback *callbacks; - struct afs_vnode *vnode = call->reply[0]; + struct afs_status_cb *scb; const __be32 *bp; u32 tmp; int ret; @@ -2026,6 +1811,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; /* Extract the file status count and array in two steps */ + /* Fall through */ case 1: _debug("extract status count"); ret = afs_extract_data(call, true); @@ -2043,6 +1829,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) more_counts: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus)); + /* Fall through */ case 2: _debug("extract status array %u", call->count); ret = afs_extract_data(call, true); @@ -2050,10 +1837,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; bp = call->buffer; - statuses = call->reply[1]; - ret = yfs_decode_status(call, &bp, &statuses[call->count], - call->count == 0 ? vnode : NULL, - NULL, NULL); + scb = &call->out_scb[call->count]; + ret = xdr_decode_YFSFetchStatus(&bp, call, scb); if (ret < 0) return ret; @@ -2066,6 +1851,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_tmp(call); /* Extract the callback count and array in two steps */ + /* Fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -2082,6 +1868,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) more_cbs: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack)); + /* Fall through */ case 4: _debug("extract CB array"); ret = afs_extract_data(call, true); @@ -2090,13 +1877,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) _debug("unmarshall CB array"); bp = call->buffer; - callbacks = call->reply[2]; - xdr_decode_YFSCallBack_raw(&bp, &callbacks[call->count]); - statuses = call->reply[1]; - if (call->count == 0 && vnode && statuses[0].abort_code == 0) { - bp = call->buffer; - xdr_decode_YFSCallBack(call, vnode, &bp); - } + scb = &call->out_scb[call->count]; + xdr_decode_YFSCallBack(&bp, call, scb); call->count++; if (call->count < call->count2) goto more_cbs; @@ -2104,16 +1886,18 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; + /* Fall through */ case 5: ret = afs_extract_data(call, false); if (ret < 0) return ret; bp = call->buffer; - xdr_decode_YFSVolSync(&bp, call->reply[3]); + xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; + /* Fall through */ case 6: break; } @@ -2138,8 +1922,7 @@ static const struct afs_call_type yfs_RXYFSInlineBulkStatus = { int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, struct afs_net *net, struct afs_fid *fids, - struct afs_file_status *statuses, - struct afs_callback *callbacks, + struct afs_status_cb *statuses, unsigned int nr_fids, struct afs_volsync *volsync) { @@ -2162,10 +1945,8 @@ int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = NULL; /* vnode for fid[0] */ - call->reply[1] = statuses; - call->reply[2] = callbacks; - call->reply[3] = volsync; + call->out_scb = statuses; + call->out_volsync = volsync; call->count2 = nr_fids; /* marshall the parameters */ @@ -2177,8 +1958,234 @@ int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, bp = xdr_encode_YFSFid(bp, &fids[i]); yfs_check_req(call, bp); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &fids[0]); - return afs_make_call(&fc->ac, call, GFP_NOFS, false); + afs_set_fc_call(call, fc); + afs_make_call(&fc->ac, call, GFP_NOFS); + return afs_wait_for_call_to_complete(call, &fc->ac); +} + +/* + * Deliver reply data to an YFS.FetchOpaqueACL. + */ +static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) +{ + struct yfs_acl *yacl = call->out_yacl; + struct afs_acl *acl; + const __be32 *bp; + unsigned int size; + int ret; + + _enter("{%u}", call->unmarshall); + + switch (call->unmarshall) { + case 0: + afs_extract_to_tmp(call); + call->unmarshall++; + + /* Extract the file ACL length */ + case 1: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + size = call->count2 = ntohl(call->tmp); + size = round_up(size, 4); + + if (yacl->flags & YFS_ACL_WANT_ACL) { + acl = kmalloc(struct_size(acl, data, size), GFP_KERNEL); + if (!acl) + return -ENOMEM; + yacl->acl = acl; + acl->size = call->count2; + afs_extract_begin(call, acl->data, size); + } else { + iov_iter_discard(&call->iter, READ, size); + } + call->unmarshall++; + + /* Extract the file ACL */ + case 2: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + afs_extract_to_tmp(call); + call->unmarshall++; + + /* Extract the volume ACL length */ + case 3: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + size = call->count2 = ntohl(call->tmp); + size = round_up(size, 4); + + if (yacl->flags & YFS_ACL_WANT_VOL_ACL) { + acl = kmalloc(struct_size(acl, data, size), GFP_KERNEL); + if (!acl) + return -ENOMEM; + yacl->vol_acl = acl; + acl->size = call->count2; + afs_extract_begin(call, acl->data, size); + } else { + iov_iter_discard(&call->iter, READ, size); + } + call->unmarshall++; + + /* Extract the volume ACL */ + case 4: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + afs_extract_to_buf(call, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + call->unmarshall++; + + /* extract the metadata */ + case 5: + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; + + 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_YFSVolSync(&bp, call->out_volsync); + + call->unmarshall++; + + case 6: + break; + } + + _leave(" = 0 [done]"); + return 0; +} + +void yfs_free_opaque_acl(struct yfs_acl *yacl) +{ + if (yacl) { + kfree(yacl->acl); + kfree(yacl->vol_acl); + kfree(yacl); + } +} + +/* + * YFS.FetchOpaqueACL operation type + */ +static const struct afs_call_type yfs_RXYFSFetchOpaqueACL = { + .name = "YFS.FetchOpaqueACL", + .op = yfs_FS_FetchOpaqueACL, + .deliver = yfs_deliver_fs_fetch_opaque_acl, + .destructor = afs_flat_call_destructor, +}; + +/* + * Fetch the YFS advanced ACLs for a file. + */ +struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *fc, + struct yfs_acl *yacl, + struct afs_status_cb *scb) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + + call = afs_alloc_flat_call(net, &yfs_RXYFSFetchOpaqueACL, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid), + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) { + fc->ac.error = -ENOMEM; + return ERR_PTR(-ENOMEM); + } + + call->key = fc->key; + call->out_yacl = yacl; + call->out_scb = scb; + call->out_volsync = NULL; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSFETCHOPAQUEACL); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + afs_make_call(&fc->ac, call, GFP_KERNEL); + return (struct yfs_acl *)afs_wait_for_call_to_complete(call, &fc->ac); +} + +/* + * YFS.StoreOpaqueACL2 operation type + */ +static const struct afs_call_type yfs_RXYFSStoreOpaqueACL2 = { + .name = "YFS.StoreOpaqueACL2", + .op = yfs_FS_StoreOpaqueACL2, + .deliver = yfs_deliver_status_and_volsync, + .destructor = afs_flat_call_destructor, +}; + +/* + * Fetch the YFS ACL for a file. + */ +int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *fc, const struct afs_acl *acl, + struct afs_status_cb *scb) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + size_t size; + __be32 *bp; + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + + size = round_up(acl->size, 4); + call = afs_alloc_flat_call(net, &yfs_RXYFSStoreStatus, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid) + + sizeof(__be32) + size, + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) { + fc->ac.error = -ENOMEM; + return -ENOMEM; + } + + call->key = fc->key; + call->out_scb = scb; + call->out_volsync = NULL; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSSTOREOPAQUEACL2); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_u32(bp, acl->size); + memcpy(bp, acl->data, acl->size); + if (acl->size != size) + memset((void *)bp + acl->size, 0, size - acl->size); + yfs_check_req(call, bp); + + trace_afs_make_fs_call(call, &vnode->fid); + afs_make_call(&fc->ac, call, GFP_KERNEL); + return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -181,7 +181,7 @@ struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool woken; + bool done; bool cancelled; struct wait_queue_entry wait; struct work_struct work; @@ -204,8 +204,7 @@ struct aio_kiocb { struct kioctx *ki_ctx; kiocb_cancel_fn *ki_cancel; - struct iocb __user *ki_user_iocb; /* user's aiocb */ - __u64 ki_user_data; /* user's data for completion */ + struct io_event ki_res; struct list_head ki_list; /* the aio core uses this * for cancellation */ @@ -1022,6 +1021,9 @@ static bool get_reqs_available(struct kioctx *ctx) /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. + * + * The refcount is initialized to 2 - one for the async op completion, + * one for the synchronous code that does this. */ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { @@ -1031,10 +1033,15 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) if (unlikely(!req)) return NULL; + if (unlikely(!get_reqs_available(ctx))) { + kmem_cache_free(kiocb_cachep, req); + return NULL; + } + percpu_ref_get(&ctx->reqs); req->ki_ctx = ctx; INIT_LIST_HEAD(&req->ki_list); - refcount_set(&req->ki_refcnt, 0); + refcount_set(&req->ki_refcnt, 2); req->ki_eventfd = NULL; return req; } @@ -1067,30 +1074,20 @@ out: return ret; } -static inline void iocb_put(struct aio_kiocb *iocb) -{ - if (refcount_read(&iocb->ki_refcnt) == 0 || - refcount_dec_and_test(&iocb->ki_refcnt)) { - if (iocb->ki_filp) - fput(iocb->ki_filp); - percpu_ref_put(&iocb->ki_ctx->reqs); - kmem_cache_free(kiocb_cachep, iocb); - } -} - -static void aio_fill_event(struct io_event *ev, struct aio_kiocb *iocb, - long res, long res2) +static inline void iocb_destroy(struct aio_kiocb *iocb) { - ev->obj = (u64)(unsigned long)iocb->ki_user_iocb; - ev->data = iocb->ki_user_data; - ev->res = res; - ev->res2 = res2; + if (iocb->ki_eventfd) + eventfd_ctx_put(iocb->ki_eventfd); + if (iocb->ki_filp) + fput(iocb->ki_filp); + percpu_ref_put(&iocb->ki_ctx->reqs); + kmem_cache_free(kiocb_cachep, iocb); } /* aio_complete * Called when the io request on the given iocb is complete. */ -static void aio_complete(struct aio_kiocb *iocb, long res, long res2) +static void aio_complete(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; @@ -1114,14 +1111,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; - aio_fill_event(event, iocb, res, res2); + *event = iocb->ki_res; kunmap_atomic(ev_page); flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); - pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n", - ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data, - res, res2); + pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, + (void __user *)(unsigned long)iocb->ki_res.obj, + iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2); /* after flagging the request as done, we * must never even look at it again @@ -1148,10 +1145,8 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ - if (iocb->ki_eventfd) { + if (iocb->ki_eventfd) eventfd_signal(iocb->ki_eventfd, 1); - eventfd_ctx_put(iocb->ki_eventfd); - } /* * We have to order our ring_info tail store above and test @@ -1163,7 +1158,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); - iocb_put(iocb); +} + +static inline void iocb_put(struct aio_kiocb *iocb) +{ + if (refcount_dec_and_test(&iocb->ki_refcnt)) { + aio_complete(iocb); + iocb_destroy(iocb); + } } /* aio_read_events_ring @@ -1437,7 +1439,9 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) file_end_write(kiocb->ki_filp); } - aio_complete(iocb, res, res2); + iocb->ki_res.res = res; + iocb->ki_res.res2 = res2; + iocb_put(iocb); } static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) @@ -1514,13 +1518,13 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret) } } -static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, +static int aio_read(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; - ssize_t ret; + int ret; ret = aio_prep_rw(req, iocb); if (ret) @@ -1542,13 +1546,13 @@ static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, return ret; } -static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, +static int aio_write(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; - ssize_t ret; + int ret; ret = aio_prep_rw(req, iocb); if (ret) @@ -1585,11 +1589,10 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, static void aio_fsync_work(struct work_struct *work) { - struct fsync_iocb *req = container_of(work, struct fsync_iocb, work); - int ret; + struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work); - ret = vfs_fsync(req->file, req->datasync); - aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0); + iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); + iocb_put(iocb); } static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, @@ -1608,11 +1611,6 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, return 0; } -static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask) -{ - aio_complete(iocb, mangle_poll(mask), 0); -} - static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1638,9 +1636,11 @@ static void aio_poll_complete_work(struct work_struct *work) return; } list_del_init(&iocb->ki_list); + iocb->ki_res.res = mangle_poll(mask); + req->done = true; spin_unlock_irq(&ctx->ctx_lock); - aio_poll_complete(iocb, mask); + iocb_put(iocb); } /* assumes we are called with irqs disabled */ @@ -1668,31 +1668,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, __poll_t mask = key_to_poll(key); unsigned long flags; - req->woken = true; - /* for instances that support it check for an event match first: */ - if (mask) { - if (!(mask & req->events)) - return 0; + if (mask && !(mask & req->events)) + return 0; + + list_del_init(&req->wait.entry); + if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { /* * Try to complete the iocb inline if we can. Use * irqsave/irqrestore because not all filesystems (e.g. fuse) * call this function with IRQs disabled and because IRQs * have to be disabled before ctx_lock is obtained. */ - if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { - list_del(&iocb->ki_list); - spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); - - list_del_init(&req->wait.entry); - aio_poll_complete(iocb, mask); - return 1; - } + list_del(&iocb->ki_list); + iocb->ki_res.res = mangle_poll(mask); + req->done = true; + spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); + iocb_put(iocb); + } else { + schedule_work(&req->work); } - - list_del_init(&req->wait.entry); - schedule_work(&req->work); return 1; } @@ -1719,11 +1715,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, add_wait_queue(head, &pt->iocb->poll.wait); } -static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) +static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) { struct kioctx *ctx = aiocb->ki_ctx; struct poll_iocb *req = &aiocb->poll; struct aio_poll_table apt; + bool cancel = false; __poll_t mask; /* reject any unknown events outside the normal event mask. */ @@ -1737,7 +1734,7 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; - req->woken = false; + req->done = false; req->cancelled = false; apt.pt._qproc = aio_poll_queue_proc; @@ -1749,156 +1746,135 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) INIT_LIST_HEAD(&req->wait.entry); init_waitqueue_func_entry(&req->wait, aio_poll_wake); - /* one for removal from waitqueue, one for this function */ - refcount_set(&aiocb->ki_refcnt, 2); - mask = vfs_poll(req->file, &apt.pt) & req->events; - if (unlikely(!req->head)) { - /* we did not manage to set up a waitqueue, done */ - goto out; - } - spin_lock_irq(&ctx->ctx_lock); - spin_lock(&req->head->lock); - if (req->woken) { - /* wake_up context handles the rest */ - mask = 0; + if (likely(req->head)) { + spin_lock(&req->head->lock); + if (unlikely(list_empty(&req->wait.entry))) { + if (apt.error) + cancel = true; + apt.error = 0; + mask = 0; + } + if (mask || apt.error) { + list_del_init(&req->wait.entry); + } else if (cancel) { + WRITE_ONCE(req->cancelled, true); + } else if (!req->done) { /* actually waiting for an event */ + list_add_tail(&aiocb->ki_list, &ctx->active_reqs); + aiocb->ki_cancel = aio_poll_cancel; + } + spin_unlock(&req->head->lock); + } + if (mask) { /* no async, we'd stolen it */ + aiocb->ki_res.res = mangle_poll(mask); apt.error = 0; - } else if (mask || apt.error) { - /* if we get an error or a mask we are done */ - WARN_ON_ONCE(list_empty(&req->wait.entry)); - list_del_init(&req->wait.entry); - } else { - /* actually waiting for an event */ - list_add_tail(&aiocb->ki_list, &ctx->active_reqs); - aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); spin_unlock_irq(&ctx->ctx_lock); - -out: - if (unlikely(apt.error)) - return apt.error; - if (mask) - aio_poll_complete(aiocb, mask); - iocb_put(aiocb); - return 0; + iocb_put(aiocb); + return apt.error; } static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, - struct iocb __user *user_iocb, bool compat) + struct iocb __user *user_iocb, struct aio_kiocb *req, + bool compat) { - struct aio_kiocb *req; - ssize_t ret; - - /* enforce forwards compatibility on users */ - if (unlikely(iocb->aio_reserved2)) { - pr_debug("EINVAL: reserve field set\n"); - return -EINVAL; - } - - /* prevent overflows */ - if (unlikely( - (iocb->aio_buf != (unsigned long)iocb->aio_buf) || - (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) || - ((ssize_t)iocb->aio_nbytes < 0) - )) { - pr_debug("EINVAL: overflow check\n"); - return -EINVAL; - } - - if (!get_reqs_available(ctx)) - return -EAGAIN; - - ret = -EAGAIN; - req = aio_get_req(ctx); - if (unlikely(!req)) - goto out_put_reqs_available; - req->ki_filp = fget(iocb->aio_fildes); - ret = -EBADF; if (unlikely(!req->ki_filp)) - goto out_put_req; + return -EBADF; if (iocb->aio_flags & IOCB_FLAG_RESFD) { + struct eventfd_ctx *eventfd; /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an * instance of the file* now. The file descriptor must be * an eventfd() fd, and will be signaled for each completed * event using the eventfd_signal() function. */ - req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd); - if (IS_ERR(req->ki_eventfd)) { - ret = PTR_ERR(req->ki_eventfd); - req->ki_eventfd = NULL; - goto out_put_req; - } + eventfd = eventfd_ctx_fdget(iocb->aio_resfd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + req->ki_eventfd = eventfd; } - ret = put_user(KIOCB_KEY, &user_iocb->aio_key); - if (unlikely(ret)) { + if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) { pr_debug("EFAULT: aio_key\n"); - goto out_put_req; + return -EFAULT; } - req->ki_user_iocb = user_iocb; - req->ki_user_data = iocb->aio_data; + req->ki_res.obj = (u64)(unsigned long)user_iocb; + req->ki_res.data = iocb->aio_data; + req->ki_res.res = 0; + req->ki_res.res2 = 0; switch (iocb->aio_lio_opcode) { case IOCB_CMD_PREAD: - ret = aio_read(&req->rw, iocb, false, compat); - break; + return aio_read(&req->rw, iocb, false, compat); case IOCB_CMD_PWRITE: - ret = aio_write(&req->rw, iocb, false, compat); - break; + return aio_write(&req->rw, iocb, false, compat); case IOCB_CMD_PREADV: - ret = aio_read(&req->rw, iocb, true, compat); - break; + return aio_read(&req->rw, iocb, true, compat); case IOCB_CMD_PWRITEV: - ret = aio_write(&req->rw, iocb, true, compat); - break; + return aio_write(&req->rw, iocb, true, compat); case IOCB_CMD_FSYNC: - ret = aio_fsync(&req->fsync, iocb, false); - break; + return aio_fsync(&req->fsync, iocb, false); case IOCB_CMD_FDSYNC: - ret = aio_fsync(&req->fsync, iocb, true); - break; + return aio_fsync(&req->fsync, iocb, true); case IOCB_CMD_POLL: - ret = aio_poll(req, iocb); - break; + return aio_poll(req, iocb); default: pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode); - ret = -EINVAL; - break; + return -EINVAL; } - - /* - * If ret is 0, we'd either done aio_complete() ourselves or have - * arranged for that to be done asynchronously. Anything non-zero - * means that we need to destroy req ourselves. - */ - if (ret) - goto out_put_req; - return 0; -out_put_req: - if (req->ki_eventfd) - eventfd_ctx_put(req->ki_eventfd); - iocb_put(req); -out_put_reqs_available: - put_reqs_available(ctx, 1); - return ret; } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, bool compat) { + struct aio_kiocb *req; struct iocb iocb; + int err; if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb)))) return -EFAULT; - return __io_submit_one(ctx, &iocb, user_iocb, compat); + /* enforce forwards compatibility on users */ + if (unlikely(iocb.aio_reserved2)) { + pr_debug("EINVAL: reserve field set\n"); + return -EINVAL; + } + + /* prevent overflows */ + if (unlikely( + (iocb.aio_buf != (unsigned long)iocb.aio_buf) || + (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) || + ((ssize_t)iocb.aio_nbytes < 0) + )) { + pr_debug("EINVAL: overflow check\n"); + return -EINVAL; + } + + req = aio_get_req(ctx); + if (unlikely(!req)) + return -EAGAIN; + + err = __io_submit_one(ctx, &iocb, user_iocb, req, compat); + + /* Done with the synchronous reference */ + iocb_put(req); + + /* + * If err is 0, we'd either done aio_complete() ourselves or have + * arranged for that to be done asynchronously. Anything non-zero + * means that we need to destroy req ourselves. + */ + if (unlikely(err)) { + iocb_destroy(req); + put_reqs_available(ctx, 1); + } + return err; } /* sys_io_submit: @@ -1997,24 +1973,6 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, } #endif -/* lookup_kiocb - * Finds a given iocb for cancellation. - */ -static struct aio_kiocb * -lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb) -{ - struct aio_kiocb *kiocb; - - assert_spin_locked(&ctx->ctx_lock); - - /* TODO: use a hash or array, this sucks. */ - list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { - if (kiocb->ki_user_iocb == iocb) - return kiocb; - } - return NULL; -} - /* sys_io_cancel: * Attempts to cancel an iocb previously passed to io_submit. If * the operation is successfully cancelled, the resulting event is @@ -2032,6 +1990,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct aio_kiocb *kiocb; int ret = -EINVAL; u32 key; + u64 obj = (u64)(unsigned long)iocb; if (unlikely(get_user(key, &iocb->aio_key))) return -EFAULT; @@ -2043,10 +2002,13 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, return -EINVAL; spin_lock_irq(&ctx->ctx_lock); - kiocb = lookup_kiocb(ctx, iocb); - if (kiocb) { - ret = kiocb->ki_cancel(&kiocb->rw); - list_del_init(&kiocb->ki_list); + /* TODO: use a hash or array, this sucks. */ + list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { + if (kiocb->ki_res.obj == obj) { + ret = kiocb->ki_cancel(&kiocb->rw); + list_del_init(&kiocb->ki_list); + break; + } } spin_unlock_irq(&ctx->ctx_lock); diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index 70c132acdab1..e1091312abe1 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -71,6 +71,7 @@ struct autofs_info { kuid_t uid; kgid_t gid; + struct rcu_head rcu; }; #define AUTOFS_INF_EXPIRING (1<<0) /* dentry in the process of expiring */ diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 80597b88718b..fb0225f21c12 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -36,7 +36,7 @@ void autofs_clean_ino(struct autofs_info *ino) void autofs_free_ino(struct autofs_info *ino) { - kfree(ino); + kfree_rcu(ino, rcu); } void autofs_kill_sb(struct super_block *sb) diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 4700b4534439..e273850c95af 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -44,7 +44,7 @@ static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int); static struct inode *befs_iget(struct super_block *, unsigned long); static struct inode *befs_alloc_inode(struct super_block *sb); -static void befs_destroy_inode(struct inode *inode); +static void befs_free_inode(struct inode *inode); static void befs_destroy_inodecache(void); static int befs_symlink_readpage(struct file *, struct page *); static int befs_utf2nls(struct super_block *sb, const char *in, int in_len, @@ -64,7 +64,7 @@ static struct dentry *befs_get_parent(struct dentry *child); static const struct super_operations befs_sops = { .alloc_inode = befs_alloc_inode, /* allocate a new inode */ - .destroy_inode = befs_destroy_inode, /* deallocate an inode */ + .free_inode = befs_free_inode, /* deallocate an inode */ .put_super = befs_put_super, /* uninit super */ .statfs = befs_statfs, /* statfs */ .remount_fs = befs_remount, @@ -281,17 +281,11 @@ befs_alloc_inode(struct super_block *sb) return &bi->vfs_inode; } -static void befs_i_callback(struct rcu_head *head) +static void befs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(befs_inode_cachep, BEFS_I(inode)); } -static void befs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, befs_i_callback); -} - static void init_once(void *foo) { struct befs_inode_info *bi = (struct befs_inode_info *) foo; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index d136b2aaafb3..dc0cd2aa3d65 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -245,17 +245,11 @@ static struct inode *bfs_alloc_inode(struct super_block *sb) return &bi->vfs_inode; } -static void bfs_i_callback(struct rcu_head *head) +static void bfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(bfs_inode_cachep, BFS_I(inode)); } -static void bfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, bfs_i_callback); -} - static void init_once(void *foo) { struct bfs_inode_info *bi = foo; @@ -287,7 +281,7 @@ static void destroy_inodecache(void) static const struct super_operations bfs_sops = { .alloc_inode = bfs_alloc_inode, - .destroy_inode = bfs_destroy_inode, + .free_inode = bfs_free_inode, .write_inode = bfs_write_inode, .evict_inode = bfs_evict_inode, .put_super = bfs_put_super, diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 7d09d125f148..fa9e99a962e0 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -524,6 +524,19 @@ static inline int arch_check_elf(struct elfhdr *ehdr, bool has_interp, #endif /* !CONFIG_ARCH_BINFMT_ELF_STATE */ +static inline int make_prot(u32 p_flags) +{ + int prot = 0; + + if (p_flags & PF_R) + prot |= PROT_READ; + if (p_flags & PF_W) + prot |= PROT_WRITE; + if (p_flags & PF_X) + prot |= PROT_EXEC; + return prot; +} + /* This is much more generalized than the library routine read function, so we keep this separate. Technically the library read function is only provided so that we can read a.out libraries that have @@ -563,16 +576,10 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) { if (eppnt->p_type == PT_LOAD) { int elf_type = MAP_PRIVATE | MAP_DENYWRITE; - int elf_prot = 0; + int elf_prot = make_prot(eppnt->p_flags); unsigned long vaddr = 0; unsigned long k, map_addr; - if (eppnt->p_flags & PF_R) - elf_prot = PROT_READ; - if (eppnt->p_flags & PF_W) - elf_prot |= PROT_WRITE; - if (eppnt->p_flags & PF_X) - elf_prot |= PROT_EXEC; vaddr = eppnt->p_vaddr; if (interp_elf_ex->e_type == ET_EXEC || load_addr_set) elf_type |= MAP_FIXED_NOREPLACE; @@ -687,7 +694,6 @@ static int load_elf_binary(struct linux_binprm *bprm) struct file *interpreter = NULL; /* to shut gcc up */ unsigned long load_addr = 0, load_bias = 0; int load_addr_set = 0; - char * elf_interpreter = NULL; unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; unsigned long elf_bss, elf_brk; @@ -698,13 +704,12 @@ static int load_elf_binary(struct linux_binprm *bprm) unsigned long start_code, end_code, start_data, end_data; unsigned long reloc_func_desc __maybe_unused = 0; int executable_stack = EXSTACK_DEFAULT; - struct pt_regs *regs = current_pt_regs(); struct { struct elfhdr elf_ex; struct elfhdr interp_elf_ex; } *loc; struct arch_elf_state arch_state = INIT_ARCH_ELF_STATE; - loff_t pos; + struct pt_regs *regs; loc = kmalloc(sizeof(*loc), GFP_KERNEL); if (!loc) { @@ -734,69 +739,66 @@ static int load_elf_binary(struct linux_binprm *bprm) goto out; elf_ppnt = elf_phdata; - elf_bss = 0; - elf_brk = 0; + for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { + char *elf_interpreter; + loff_t pos; - start_code = ~0UL; - end_code = 0; - start_data = 0; - end_data = 0; + if (elf_ppnt->p_type != PT_INTERP) + continue; - for (i = 0; i < loc->elf_ex.e_phnum; i++) { - if (elf_ppnt->p_type == PT_INTERP) { - /* This is the program interpreter used for - * shared libraries - for now assume that this - * is an a.out format binary - */ - retval = -ENOEXEC; - if (elf_ppnt->p_filesz > PATH_MAX || - elf_ppnt->p_filesz < 2) - goto out_free_ph; - - retval = -ENOMEM; - elf_interpreter = kmalloc(elf_ppnt->p_filesz, - GFP_KERNEL); - if (!elf_interpreter) - goto out_free_ph; - - pos = elf_ppnt->p_offset; - retval = kernel_read(bprm->file, elf_interpreter, - elf_ppnt->p_filesz, &pos); - if (retval != elf_ppnt->p_filesz) { - if (retval >= 0) - retval = -EIO; - goto out_free_interp; - } - /* make sure path is NULL terminated */ - retval = -ENOEXEC; - if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0') - goto out_free_interp; + /* + * This is the program interpreter used for shared libraries - + * for now assume that this is an a.out format binary. + */ + retval = -ENOEXEC; + if (elf_ppnt->p_filesz > PATH_MAX || elf_ppnt->p_filesz < 2) + goto out_free_ph; - interpreter = open_exec(elf_interpreter); - retval = PTR_ERR(interpreter); - if (IS_ERR(interpreter)) - goto out_free_interp; + retval = -ENOMEM; + elf_interpreter = kmalloc(elf_ppnt->p_filesz, GFP_KERNEL); + if (!elf_interpreter) + goto out_free_ph; - /* - * If the binary is not readable then enforce - * mm->dumpable = 0 regardless of the interpreter's - * permissions. - */ - would_dump(bprm, interpreter); - - /* Get the exec headers */ - pos = 0; - retval = kernel_read(interpreter, &loc->interp_elf_ex, - sizeof(loc->interp_elf_ex), &pos); - if (retval != sizeof(loc->interp_elf_ex)) { - if (retval >= 0) - retval = -EIO; - goto out_free_dentry; - } + pos = elf_ppnt->p_offset; + retval = kernel_read(bprm->file, elf_interpreter, + elf_ppnt->p_filesz, &pos); + if (retval != elf_ppnt->p_filesz) { + if (retval >= 0) + retval = -EIO; + goto out_free_interp; + } + /* make sure path is NULL terminated */ + retval = -ENOEXEC; + if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0') + goto out_free_interp; - break; + interpreter = open_exec(elf_interpreter); + kfree(elf_interpreter); + retval = PTR_ERR(interpreter); + if (IS_ERR(interpreter)) + goto out_free_ph; + + /* + * If the binary is not readable then enforce mm->dumpable = 0 + * regardless of the interpreter's permissions. + */ + would_dump(bprm, interpreter); + + /* Get the exec headers */ + pos = 0; + retval = kernel_read(interpreter, &loc->interp_elf_ex, + sizeof(loc->interp_elf_ex), &pos); + if (retval != sizeof(loc->interp_elf_ex)) { + if (retval >= 0) + retval = -EIO; + goto out_free_dentry; } - elf_ppnt++; + + break; + +out_free_interp: + kfree(elf_interpreter); + goto out_free_ph; } elf_ppnt = elf_phdata; @@ -819,7 +821,7 @@ static int load_elf_binary(struct linux_binprm *bprm) } /* Some simple consistency checks for the interpreter */ - if (elf_interpreter) { + if (interpreter) { retval = -ELIBBAD; /* Not an ELF interpreter */ if (memcmp(loc->interp_elf_ex.e_ident, ELFMAG, SELFMAG) != 0) @@ -884,13 +886,19 @@ static int load_elf_binary(struct linux_binprm *bprm) if (retval < 0) goto out_free_dentry; - current->mm->start_stack = bprm->p; + elf_bss = 0; + elf_brk = 0; + + start_code = ~0UL; + end_code = 0; + start_data = 0; + end_data = 0; /* Now we do a little grungy work by mmapping the ELF image into the correct location in memory. */ for(i = 0, elf_ppnt = elf_phdata; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { - int elf_prot = 0, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE; + int elf_prot, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE; unsigned long k, vaddr; unsigned long total_size = 0; @@ -931,12 +939,7 @@ static int load_elf_binary(struct linux_binprm *bprm) elf_fixed = MAP_FIXED; } - if (elf_ppnt->p_flags & PF_R) - elf_prot |= PROT_READ; - if (elf_ppnt->p_flags & PF_W) - elf_prot |= PROT_WRITE; - if (elf_ppnt->p_flags & PF_X) - elf_prot |= PROT_EXEC; + elf_prot = make_prot(elf_ppnt->p_flags); elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE; @@ -978,7 +981,7 @@ static int load_elf_binary(struct linux_binprm *bprm) * independently randomized mmap region (0 load_bias * without MAP_FIXED). */ - if (elf_interpreter) { + if (interpreter) { load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); @@ -1076,7 +1079,7 @@ static int load_elf_binary(struct linux_binprm *bprm) goto out_free_dentry; } - if (elf_interpreter) { + if (interpreter) { unsigned long interp_map_addr = 0; elf_entry = load_elf_interp(&loc->interp_elf_ex, @@ -1100,7 +1103,6 @@ static int load_elf_binary(struct linux_binprm *bprm) allow_write_access(interpreter); fput(interpreter); - kfree(elf_interpreter); } else { elf_entry = loc->elf_ex.e_entry; if (BAD_ADDR(elf_entry)) { @@ -1115,7 +1117,7 @@ static int load_elf_binary(struct linux_binprm *bprm) set_binfmt(&elf_format); #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES - retval = arch_setup_additional_pages(bprm, !!elf_interpreter); + retval = arch_setup_additional_pages(bprm, !!interpreter); if (retval < 0) goto out; #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */ @@ -1132,6 +1134,17 @@ static int load_elf_binary(struct linux_binprm *bprm) current->mm->start_stack = bprm->p; if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) { + /* + * For architectures with ELF randomization, when executing + * a loader directly (i.e. no interpreter listed in ELF + * headers), move the brk area out of the mmap region + * (since it grows up, and may collide early with the stack + * growing down), and into the unused ELF_ET_DYN_BASE region. + */ + if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && !interpreter) + current->mm->brk = current->mm->start_brk = + ELF_ET_DYN_BASE; + current->mm->brk = current->mm->start_brk = arch_randomize_brk(current->mm); #ifdef compat_brk_randomized @@ -1148,6 +1161,7 @@ static int load_elf_binary(struct linux_binprm *bprm) MAP_FIXED | MAP_PRIVATE, 0); } + regs = current_pt_regs(); #ifdef ELF_PLAT_INIT /* * The ABI may specify that certain registers be set up in special @@ -1176,8 +1190,6 @@ out_free_dentry: allow_write_access(interpreter); if (interpreter) fput(interpreter); -out_free_interp: - kfree(elf_interpreter); out_free_ph: kfree(elf_phdata); goto out; @@ -1456,8 +1468,6 @@ static void fill_elf_header(struct elfhdr *elf, int segs, elf->e_ehsize = sizeof(struct elfhdr); elf->e_phentsize = sizeof(struct elf_phdr); elf->e_phnum = segs; - - return; } static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) @@ -1470,7 +1480,6 @@ static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) phdr->p_memsz = 0; phdr->p_flags = 0; phdr->p_align = 0; - return; } static void fill_note(struct memelfnote *note, const char *name, int type, @@ -1480,7 +1489,6 @@ static void fill_note(struct memelfnote *note, const char *name, int type, note->type = type; note->datasz = sz; note->data = data; - return; } /* diff --git a/fs/block_dev.c b/fs/block_dev.c index 78d3257435c0..0f7552a87d54 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -29,8 +29,6 @@ #include <linux/namei.h> #include <linux/log2.h> #include <linux/cleancache.h> -#include <linux/dax.h> -#include <linux/badblocks.h> #include <linux/task_io_accounting_ops.h> #include <linux/falloc.h> #include <linux/uaccess.h> @@ -210,7 +208,6 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, struct bio bio; ssize_t ret; blk_qc_t qc; - int i; struct bvec_iter_all iter_all; if ((pos | iov_iter_alignment(iter)) & @@ -261,10 +258,11 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, } __set_current_state(TASK_RUNNING); - bio_for_each_segment_all(bvec, &bio, i, iter_all) { + bio_for_each_segment_all(bvec, &bio, iter_all) { if (should_dirty && !PageCompound(bvec->bv_page)) set_page_dirty_lock(bvec->bv_page); - put_page(bvec->bv_page); + if (!bio_flagged(&bio, BIO_NO_PAGE_REF)) + put_page(bvec->bv_page); } if (unlikely(bio.bi_status)) @@ -307,10 +305,10 @@ static void blkdev_bio_end_io(struct bio *bio) struct blkdev_dio *dio = bio->bi_private; bool should_dirty = dio->should_dirty; - if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) { - if (bio->bi_status && !dio->bio.bi_status) - dio->bio.bi_status = bio->bi_status; - } else { + if (bio->bi_status && !dio->bio.bi_status) + dio->bio.bi_status = bio->bi_status; + + if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) { if (!dio->is_sync) { struct kiocb *iocb = dio->iocb; ssize_t ret; @@ -339,9 +337,8 @@ static void blkdev_bio_end_io(struct bio *bio) if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { struct bvec_iter_all iter_all; struct bio_vec *bvec; - int i; - bio_for_each_segment_all(bvec, bio, i, iter_all) + bio_for_each_segment_all(bvec, bio, iter_all) put_page(bvec->bv_page); } bio_put(bio); @@ -789,17 +786,9 @@ static struct inode *bdev_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void bdev_i_callback(struct rcu_head *head) -{ - struct inode *inode = container_of(head, struct inode, i_rcu); - struct bdev_inode *bdi = BDEV_I(inode); - - kmem_cache_free(bdev_cachep, bdi); -} - -static void bdev_destroy_inode(struct inode *inode) +static void bdev_free_inode(struct inode *inode) { - call_rcu(&inode->i_rcu, bdev_i_callback); + kmem_cache_free(bdev_cachep, BDEV_I(inode)); } static void init_once(void *foo) @@ -839,7 +828,7 @@ static void bdev_evict_inode(struct inode *inode) static const struct super_operations bdev_sops = { .statfs = simple_statfs, .alloc_inode = bdev_alloc_inode, - .destroy_inode = bdev_destroy_inode, + .free_inode = bdev_free_inode, .drop_inode = generic_delete_inode, .evict_inode = bdev_evict_inode, }; diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 5810463dc6d2..a0af1b952c4d 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -93,7 +93,11 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, goto out; } - ret = btrfs_setxattr(trans, inode, name, value, size, 0); + if (trans) + ret = btrfs_setxattr(trans, inode, name, value, size, 0); + else + ret = btrfs_setxattr_trans(inode, name, value, size, 0); + out: kfree(value); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 11459fe84a29..982152d3f920 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -791,7 +791,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, count = node->ref_mod * -1; break; default: - BUG_ON(1); + BUG(); } *total_refs += count; switch (node->type) { @@ -1460,8 +1460,8 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, * callers (such as fiemap) which want to know whether the extent is * shared but do not need a ref count. * - * This attempts to allocate a transaction in order to account for - * delayed refs, but continues on even when the alloc fails. + * This attempts to attach to the running transaction in order to account for + * delayed refs, but continues on even when no running transaction exists. * * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error. */ @@ -1484,13 +1484,16 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) tmp = ulist_alloc(GFP_NOFS); roots = ulist_alloc(GFP_NOFS); if (!tmp || !roots) { - ulist_free(tmp); - ulist_free(roots); - return -ENOMEM; + ret = -ENOMEM; + goto out; } - trans = btrfs_join_transaction(root); + trans = btrfs_attach_transaction(root); if (IS_ERR(trans)) { + if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) { + ret = PTR_ERR(trans); + goto out; + } trans = NULL; down_read(&fs_info->commit_root_sem); } else { @@ -1523,6 +1526,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) } else { up_read(&fs_info->commit_root_sem); } +out: ulist_free(tmp); ulist_free(roots); return ret; @@ -1747,7 +1751,7 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, else if (flags & BTRFS_EXTENT_FLAG_DATA) *flags_ret = BTRFS_EXTENT_FLAG_DATA; else - BUG_ON(1); + BUG(); return 0; } @@ -1912,13 +1916,19 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, extent_item_objectid); if (!search_commit_root) { - trans = btrfs_join_transaction(fs_info->extent_root); - if (IS_ERR(trans)) - return PTR_ERR(trans); + trans = btrfs_attach_transaction(fs_info->extent_root); + if (IS_ERR(trans)) { + if (PTR_ERR(trans) != -ENOENT && + PTR_ERR(trans) != -EROFS) + return PTR_ERR(trans); + trans = NULL; + } + } + + if (trans) btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem); - } else { + else down_read(&fs_info->commit_root_sem); - } ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid, tree_mod_seq_elem.seq, &refs, @@ -1951,7 +1961,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, free_leaf_list(refs); out: - if (!search_commit_root) { + if (trans) { btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem); btrfs_end_transaction(trans); } else { diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 6f5d07415dab..d5b438706b77 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -148,12 +148,6 @@ struct btrfs_inode { u64 last_unlink_trans; /* - * Track the transaction id of the last transaction used to create a - * hard link for the inode. This is used by the log tree (fsync). - */ - u64 last_link_trans; - - /* * Number of bytes outstanding that are going to need csums. This is * used in ENOSPC accounting. */ @@ -203,8 +197,6 @@ struct btrfs_inode { struct inode vfs_inode; }; -extern unsigned char btrfs_filetype_table[]; - static inline struct btrfs_inode *BTRFS_I(const struct inode *inode) { return container_of(inode, struct btrfs_inode, vfs_inode); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 4f2a8ae0aa42..daf7908d1e35 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -160,7 +160,6 @@ csum_failed: if (cb->errors) { bio_io_error(cb->orig_bio); } else { - int i; struct bio_vec *bvec; struct bvec_iter_all iter_all; @@ -169,7 +168,7 @@ csum_failed: * checked so the end_io handlers know about it */ ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, cb->orig_bio, i, iter_all) + bio_for_each_segment_all(bvec, cb->orig_bio, iter_all) SetPageChecked(bvec->bv_page); bio_endio(cb->orig_bio); @@ -251,7 +250,7 @@ static void end_compressed_bio_write(struct bio *bio) cb->compressed_pages[0]->mapping = cb->inode->i_mapping; btrfs_writepage_endio_finish_ordered(cb->compressed_pages[0], cb->start, cb->start + cb->len - 1, - bio->bi_status ? BLK_STS_OK : BLK_STS_NOTSUPP); + bio->bi_status == BLK_STS_OK); cb->compressed_pages[0]->mapping = NULL; end_compressed_writeback(inode, cb); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 324df36d28bf..5df76c17775a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -21,11 +21,9 @@ static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *ins_key, struct btrfs_path *path, int data_size, int extend); static int push_node_left(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct extent_buffer *dst, struct extent_buffer *src, int empty); static int balance_node_right(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct extent_buffer *dst_buf, struct extent_buffer *src_buf); static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, @@ -726,11 +724,11 @@ tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq) return __tree_mod_log_search(fs_info, start, min_seq, 0); } -static noinline int -tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, +static noinline int tree_mod_log_eb_copy(struct extent_buffer *dst, struct extent_buffer *src, unsigned long dst_offset, unsigned long src_offset, int nr_items) { + struct btrfs_fs_info *fs_info = dst->fs_info; int ret = 0; struct tree_mod_elem **tm_list = NULL; struct tree_mod_elem **tm_list_add, **tm_list_rem; @@ -950,7 +948,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if (new_flags != 0) { int level = btrfs_header_level(buf); - ret = btrfs_set_disk_extent_flags(trans, fs_info, + ret = btrfs_set_disk_extent_flags(trans, buf->start, buf->len, new_flags, level, 0); @@ -970,7 +968,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if (ret) return ret; } - clean_tree_block(fs_info, buf); + btrfs_clean_tree_block(buf); *last_ref = 1; } return 0; @@ -1792,9 +1790,8 @@ static void root_sub_used(struct btrfs_root *root, u32 size) /* given a node and slot number, this reads the blocks it points to. The * extent buffer is returned with a reference taken (but unlocked). */ -static noinline struct extent_buffer * -read_node_slot(struct btrfs_fs_info *fs_info, struct extent_buffer *parent, - int slot) +static noinline struct extent_buffer *read_node_slot( + struct extent_buffer *parent, int slot) { int level = btrfs_header_level(parent); struct extent_buffer *eb; @@ -1806,7 +1803,7 @@ read_node_slot(struct btrfs_fs_info *fs_info, struct extent_buffer *parent, BUG_ON(level == 0); btrfs_node_key_to_cpu(parent, &first_key, slot); - eb = read_tree_block(fs_info, btrfs_node_blockptr(parent, slot), + eb = read_tree_block(parent->fs_info, btrfs_node_blockptr(parent, slot), btrfs_node_ptr_generation(parent, slot), level - 1, &first_key); if (!IS_ERR(eb) && !extent_buffer_uptodate(eb)) { @@ -1863,7 +1860,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, return 0; /* promote the child to a root */ - child = read_node_slot(fs_info, mid, 0); + child = read_node_slot(mid, 0); if (IS_ERR(child)) { ret = PTR_ERR(child); btrfs_handle_fs_error(fs_info, ret, NULL); @@ -1888,7 +1885,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, path->locks[level] = 0; path->nodes[level] = NULL; - clean_tree_block(fs_info, mid); + btrfs_clean_tree_block(mid); btrfs_tree_unlock(mid); /* once for the path */ free_extent_buffer(mid); @@ -1903,7 +1900,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 4) return 0; - left = read_node_slot(fs_info, parent, pslot - 1); + left = read_node_slot(parent, pslot - 1); if (IS_ERR(left)) left = NULL; @@ -1918,7 +1915,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, } } - right = read_node_slot(fs_info, parent, pslot + 1); + right = read_node_slot(parent, pslot + 1); if (IS_ERR(right)) right = NULL; @@ -1936,7 +1933,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, /* first, try to make some room in the middle buffer */ if (left) { orig_slot += btrfs_header_nritems(left); - wret = push_node_left(trans, fs_info, left, mid, 1); + wret = push_node_left(trans, left, mid, 1); if (wret < 0) ret = wret; } @@ -1945,11 +1942,11 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, * then try to empty the right most buffer into the middle */ if (right) { - wret = push_node_left(trans, fs_info, mid, right, 1); + wret = push_node_left(trans, mid, right, 1); if (wret < 0 && wret != -ENOSPC) ret = wret; if (btrfs_header_nritems(right) == 0) { - clean_tree_block(fs_info, right); + btrfs_clean_tree_block(right); btrfs_tree_unlock(right); del_ptr(root, path, level + 1, pslot + 1); root_sub_used(root, right->len); @@ -1981,20 +1978,20 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_handle_fs_error(fs_info, ret, NULL); goto enospc; } - wret = balance_node_right(trans, fs_info, mid, left); + wret = balance_node_right(trans, mid, left); if (wret < 0) { ret = wret; goto enospc; } if (wret == 1) { - wret = push_node_left(trans, fs_info, left, mid, 1); + wret = push_node_left(trans, left, mid, 1); if (wret < 0) ret = wret; } BUG_ON(wret == 1); } if (btrfs_header_nritems(mid) == 0) { - clean_tree_block(fs_info, mid); + btrfs_clean_tree_block(mid); btrfs_tree_unlock(mid); del_ptr(root, path, level + 1, pslot); root_sub_used(root, mid->len); @@ -2078,7 +2075,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, if (!parent) return 1; - left = read_node_slot(fs_info, parent, pslot - 1); + left = read_node_slot(parent, pslot - 1); if (IS_ERR(left)) left = NULL; @@ -2098,8 +2095,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, if (ret) wret = 1; else { - wret = push_node_left(trans, fs_info, - left, mid, 0); + wret = push_node_left(trans, left, mid, 0); } } if (wret < 0) @@ -2131,7 +2127,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, btrfs_tree_unlock(left); free_extent_buffer(left); } - right = read_node_slot(fs_info, parent, pslot + 1); + right = read_node_slot(parent, pslot + 1); if (IS_ERR(right)) right = NULL; @@ -2154,8 +2150,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, if (ret) wret = 1; else { - wret = balance_node_right(trans, fs_info, - right, mid); + wret = balance_node_right(trans, right, mid); } } if (wret < 0) @@ -2416,6 +2411,16 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, if (tmp) { /* first we do an atomic uptodate check */ if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) { + /* + * Do extra check for first_key, eb can be stale due to + * being cached, read from scrub, or have multiple + * parents (shared tree blocks). + */ + if (btrfs_verify_level_key(tmp, + parent_level - 1, &first_key, gen)) { + free_extent_buffer(tmp); + return -EUCLEAN; + } *eb_ret = tmp; return 0; } @@ -2706,7 +2711,6 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, int ins_len, int cow) { - struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *b; int slot; int ret; @@ -2904,7 +2908,7 @@ cow_done: } else { p->slots[level] = slot; if (ins_len > 0 && - btrfs_leaf_free_space(fs_info, b) < ins_len) { + btrfs_leaf_free_space(b) < ins_len) { if (write_lock_level < 1) { write_lock_level = 1; btrfs_release_path(p); @@ -3181,11 +3185,31 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, slot = path->slots[0]; if (slot > 0) { btrfs_item_key(eb, &disk_key, slot - 1); - BUG_ON(comp_keys(&disk_key, new_key) >= 0); + if (unlikely(comp_keys(&disk_key, new_key) >= 0)) { + btrfs_crit(fs_info, + "slot %u key (%llu %u %llu) new key (%llu %u %llu)", + slot, btrfs_disk_key_objectid(&disk_key), + btrfs_disk_key_type(&disk_key), + btrfs_disk_key_offset(&disk_key), + new_key->objectid, new_key->type, + new_key->offset); + btrfs_print_leaf(eb); + BUG(); + } } if (slot < btrfs_header_nritems(eb) - 1) { btrfs_item_key(eb, &disk_key, slot + 1); - BUG_ON(comp_keys(&disk_key, new_key) <= 0); + if (unlikely(comp_keys(&disk_key, new_key) <= 0)) { + btrfs_crit(fs_info, + "slot %u key (%llu %u %llu) new key (%llu %u %llu)", + slot, btrfs_disk_key_objectid(&disk_key), + btrfs_disk_key_type(&disk_key), + btrfs_disk_key_offset(&disk_key), + new_key->objectid, new_key->type, + new_key->offset); + btrfs_print_leaf(eb); + BUG(); + } } btrfs_cpu_key_to_disk(&disk_key, new_key); @@ -3203,10 +3227,10 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, * error, and > 0 if there was no room in the left hand block. */ static int push_node_left(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct extent_buffer *dst, struct extent_buffer *src, int empty) { + struct btrfs_fs_info *fs_info = trans->fs_info; int push_items = 0; int src_nritems; int dst_nritems; @@ -3239,8 +3263,7 @@ static int push_node_left(struct btrfs_trans_handle *trans, } else push_items = min(src_nritems - 8, push_items); - ret = tree_mod_log_eb_copy(fs_info, dst, src, dst_nritems, 0, - push_items); + ret = tree_mod_log_eb_copy(dst, src, dst_nritems, 0, push_items); if (ret) { btrfs_abort_transaction(trans, ret); return ret; @@ -3278,10 +3301,10 @@ static int push_node_left(struct btrfs_trans_handle *trans, * this will only push up to 1/2 the contents of the left node over */ static int balance_node_right(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct extent_buffer *dst, struct extent_buffer *src) { + struct btrfs_fs_info *fs_info = trans->fs_info; int push_items = 0; int max_push; int src_nritems; @@ -3315,8 +3338,8 @@ static int balance_node_right(struct btrfs_trans_handle *trans, (dst_nritems) * sizeof(struct btrfs_key_ptr)); - ret = tree_mod_log_eb_copy(fs_info, dst, src, 0, - src_nritems - push_items, push_items); + ret = tree_mod_log_eb_copy(dst, src, 0, src_nritems - push_items, + push_items); if (ret) { btrfs_abort_transaction(trans, ret); return ret; @@ -3404,7 +3427,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, * blocknr is the block the key points to. */ static void insert_ptr(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct btrfs_path *path, + struct btrfs_path *path, struct btrfs_disk_key *key, u64 bytenr, int slot, int level) { @@ -3417,7 +3440,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, lower = path->nodes[level]; nritems = btrfs_header_nritems(lower); BUG_ON(slot > nritems); - BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(fs_info)); + BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(trans->fs_info)); if (slot != nritems) { if (level) { ret = tree_mod_log_insert_move(lower, slot + 1, slot, @@ -3501,7 +3524,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, root_add_used(root, fs_info->nodesize); ASSERT(btrfs_header_level(c) == level); - ret = tree_mod_log_eb_copy(fs_info, split, c, 0, mid, c_nritems - mid); + ret = tree_mod_log_eb_copy(split, c, 0, mid, c_nritems - mid); if (ret) { btrfs_abort_transaction(trans, ret); return ret; @@ -3517,7 +3540,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(c); btrfs_mark_buffer_dirty(split); - insert_ptr(trans, fs_info, path, &disk_key, split->start, + insert_ptr(trans, path, &disk_key, split->start, path->slots[level + 1] + 1, level + 1); if (path->slots[level] >= mid) { @@ -3565,9 +3588,9 @@ static int leaf_space_used(struct extent_buffer *l, int start, int nr) * the start of the leaf data. IOW, how much room * the leaf has left for both items and data */ -noinline int btrfs_leaf_free_space(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf) +noinline int btrfs_leaf_free_space(struct extent_buffer *leaf) { + struct btrfs_fs_info *fs_info = leaf->fs_info; int nritems = btrfs_header_nritems(leaf); int ret; @@ -3586,13 +3609,13 @@ noinline int btrfs_leaf_free_space(struct btrfs_fs_info *fs_info, * min slot controls the lowest index we're willing to push to the * right. We'll push up to and including min_slot, but no lower */ -static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, +static noinline int __push_leaf_right(struct btrfs_path *path, int data_size, int empty, struct extent_buffer *right, int free_space, u32 left_nritems, u32 min_slot) { + struct btrfs_fs_info *fs_info = right->fs_info; struct extent_buffer *left = path->nodes[0]; struct extent_buffer *upper = path->nodes[1]; struct btrfs_map_token token; @@ -3626,7 +3649,8 @@ static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, if (path->slots[0] > i) break; if (path->slots[0] == i) { - int space = btrfs_leaf_free_space(fs_info, left); + int space = btrfs_leaf_free_space(left); + if (space + push_space * 2 > free_space) break; } @@ -3655,10 +3679,10 @@ static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, right_nritems = btrfs_header_nritems(right); push_space = btrfs_item_end_nr(left, left_nritems - push_items); - push_space -= leaf_data_end(fs_info, left); + push_space -= leaf_data_end(left); /* make room in the right data area */ - data_end = leaf_data_end(fs_info, right); + data_end = leaf_data_end(right); memmove_extent_buffer(right, BTRFS_LEAF_DATA_OFFSET + data_end - push_space, BTRFS_LEAF_DATA_OFFSET + data_end, @@ -3667,7 +3691,7 @@ static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, /* copy from the left data area */ copy_extent_buffer(right, left, BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, - BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, left), + BTRFS_LEAF_DATA_OFFSET + leaf_data_end(left), push_space); memmove_extent_buffer(right, btrfs_item_nr_offset(push_items), @@ -3695,7 +3719,7 @@ static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, if (left_nritems) btrfs_mark_buffer_dirty(left); else - clean_tree_block(fs_info, left); + btrfs_clean_tree_block(left); btrfs_mark_buffer_dirty(right); @@ -3707,7 +3731,7 @@ static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, if (path->slots[0] >= left_nritems) { path->slots[0] -= left_nritems; if (btrfs_header_nritems(path->nodes[0]) == 0) - clean_tree_block(fs_info, path->nodes[0]); + btrfs_clean_tree_block(path->nodes[0]); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -3739,7 +3763,6 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root int min_data_size, int data_size, int empty, u32 min_slot) { - struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *left = path->nodes[0]; struct extent_buffer *right; struct extent_buffer *upper; @@ -3758,7 +3781,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root btrfs_assert_tree_locked(path->nodes[1]); - right = read_node_slot(fs_info, upper, slot + 1); + right = read_node_slot(upper, slot + 1); /* * slot + 1 is not valid or we fail to read the right node, * no big deal, just return. @@ -3769,7 +3792,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root btrfs_tree_lock(right); btrfs_set_lock_blocking_write(right); - free_space = btrfs_leaf_free_space(fs_info, right); + free_space = btrfs_leaf_free_space(right); if (free_space < data_size) goto out_unlock; @@ -3779,7 +3802,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root if (ret) goto out_unlock; - free_space = btrfs_leaf_free_space(fs_info, right); + free_space = btrfs_leaf_free_space(right); if (free_space < data_size) goto out_unlock; @@ -3800,7 +3823,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root return 0; } - return __push_leaf_right(fs_info, path, min_data_size, empty, + return __push_leaf_right(path, min_data_size, empty, right, free_space, left_nritems, min_slot); out_unlock: btrfs_tree_unlock(right); @@ -3816,12 +3839,12 @@ out_unlock: * item at 'max_slot' won't be touched. Use (u32)-1 to make us do all the * items */ -static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, int data_size, +static noinline int __push_leaf_left(struct btrfs_path *path, int data_size, int empty, struct extent_buffer *left, int free_space, u32 right_nritems, u32 max_slot) { + struct btrfs_fs_info *fs_info = left->fs_info; struct btrfs_disk_key disk_key; struct extent_buffer *right = path->nodes[0]; int i; @@ -3849,7 +3872,8 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, if (path->slots[0] < i) break; if (path->slots[0] == i) { - int space = btrfs_leaf_free_space(fs_info, right); + int space = btrfs_leaf_free_space(right); + if (space + push_space * 2 > free_space) break; } @@ -3882,7 +3906,7 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, btrfs_item_offset_nr(right, push_items - 1); copy_extent_buffer(left, right, BTRFS_LEAF_DATA_OFFSET + - leaf_data_end(fs_info, left) - push_space, + leaf_data_end(left) - push_space, BTRFS_LEAF_DATA_OFFSET + btrfs_item_offset_nr(right, push_items - 1), push_space); @@ -3909,11 +3933,11 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, if (push_items < right_nritems) { push_space = btrfs_item_offset_nr(right, push_items - 1) - - leaf_data_end(fs_info, right); + leaf_data_end(right); memmove_extent_buffer(right, BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, BTRFS_LEAF_DATA_OFFSET + - leaf_data_end(fs_info, right), push_space); + leaf_data_end(right), push_space); memmove_extent_buffer(right, btrfs_item_nr_offset(0), btrfs_item_nr_offset(push_items), @@ -3935,7 +3959,7 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, if (right_nritems) btrfs_mark_buffer_dirty(right); else - clean_tree_block(fs_info, right); + btrfs_clean_tree_block(right); btrfs_item_key(right, &disk_key, 0); fixup_low_keys(path, &disk_key, 1); @@ -3972,7 +3996,6 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int min_data_size, int data_size, int empty, u32 max_slot) { - struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *right = path->nodes[0]; struct extent_buffer *left; int slot; @@ -3992,7 +4015,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root btrfs_assert_tree_locked(path->nodes[1]); - left = read_node_slot(fs_info, path->nodes[1], slot - 1); + left = read_node_slot(path->nodes[1], slot - 1); /* * slot - 1 is not valid or we fail to read the left node, * no big deal, just return. @@ -4003,7 +4026,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root btrfs_tree_lock(left); btrfs_set_lock_blocking_write(left); - free_space = btrfs_leaf_free_space(fs_info, left); + free_space = btrfs_leaf_free_space(left); if (free_space < data_size) { ret = 1; goto out; @@ -4019,13 +4042,13 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root goto out; } - free_space = btrfs_leaf_free_space(fs_info, left); + free_space = btrfs_leaf_free_space(left); if (free_space < data_size) { ret = 1; goto out; } - return __push_leaf_left(fs_info, path, min_data_size, + return __push_leaf_left(path, min_data_size, empty, left, free_space, right_nritems, max_slot); out: @@ -4039,12 +4062,12 @@ out: * available for the resulting leaf level of the path. */ static noinline void copy_for_split(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct extent_buffer *l, struct extent_buffer *right, int slot, int mid, int nritems) { + struct btrfs_fs_info *fs_info = trans->fs_info; int data_copy_size; int rt_data_off; int i; @@ -4055,7 +4078,7 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, nritems = nritems - mid; btrfs_set_header_nritems(right, nritems); - data_copy_size = btrfs_item_end_nr(l, mid) - leaf_data_end(fs_info, l); + data_copy_size = btrfs_item_end_nr(l, mid) - leaf_data_end(l); copy_extent_buffer(right, l, btrfs_item_nr_offset(0), btrfs_item_nr_offset(mid), @@ -4064,7 +4087,7 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, copy_extent_buffer(right, l, BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - data_copy_size, BTRFS_LEAF_DATA_OFFSET + - leaf_data_end(fs_info, l), data_copy_size); + leaf_data_end(l), data_copy_size); rt_data_off = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_end_nr(l, mid); @@ -4079,8 +4102,7 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(l, mid); btrfs_item_key(right, &disk_key, 0); - insert_ptr(trans, fs_info, path, &disk_key, right->start, - path->slots[1] + 1, 1); + insert_ptr(trans, path, &disk_key, right->start, path->slots[1] + 1, 1); btrfs_mark_buffer_dirty(right); btrfs_mark_buffer_dirty(l); @@ -4115,7 +4137,6 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, struct btrfs_path *path, int data_size) { - struct btrfs_fs_info *fs_info = root->fs_info; int ret; int progress = 0; int slot; @@ -4124,7 +4145,7 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, slot = path->slots[0]; if (slot < btrfs_header_nritems(path->nodes[0])) - space_needed -= btrfs_leaf_free_space(fs_info, path->nodes[0]); + space_needed -= btrfs_leaf_free_space(path->nodes[0]); /* * try to push all the items after our slot into the @@ -4145,14 +4166,14 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, if (path->slots[0] == 0 || path->slots[0] == nritems) return 0; - if (btrfs_leaf_free_space(fs_info, path->nodes[0]) >= data_size) + if (btrfs_leaf_free_space(path->nodes[0]) >= data_size) return 0; /* try to push all the items before our slot into the next leaf */ slot = path->slots[0]; space_needed = data_size; if (slot > 0) - space_needed -= btrfs_leaf_free_space(fs_info, path->nodes[0]); + space_needed -= btrfs_leaf_free_space(path->nodes[0]); ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot); if (ret < 0) return ret; @@ -4201,7 +4222,7 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, int space_needed = data_size; if (slot < btrfs_header_nritems(l)) - space_needed -= btrfs_leaf_free_space(fs_info, l); + space_needed -= btrfs_leaf_free_space(l); wret = push_leaf_right(trans, root, path, space_needed, space_needed, 0, 0); @@ -4210,8 +4231,7 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, if (wret) { space_needed = data_size; if (slot > 0) - space_needed -= btrfs_leaf_free_space(fs_info, - l); + space_needed -= btrfs_leaf_free_space(l); wret = push_leaf_left(trans, root, path, space_needed, space_needed, 0, (u32)-1); if (wret < 0) @@ -4220,7 +4240,7 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, l = path->nodes[0]; /* did the pushes work? */ - if (btrfs_leaf_free_space(fs_info, l) >= data_size) + if (btrfs_leaf_free_space(l) >= data_size) return 0; } @@ -4288,7 +4308,7 @@ again: if (split == 0) { if (mid <= slot) { btrfs_set_header_nritems(right, 0); - insert_ptr(trans, fs_info, path, &disk_key, + insert_ptr(trans, path, &disk_key, right->start, path->slots[1] + 1, 1); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); @@ -4297,7 +4317,7 @@ again: path->slots[1] += 1; } else { btrfs_set_header_nritems(right, 0); - insert_ptr(trans, fs_info, path, &disk_key, + insert_ptr(trans, path, &disk_key, right->start, path->slots[1], 1); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); @@ -4314,7 +4334,7 @@ again: return ret; } - copy_for_split(trans, fs_info, path, l, right, slot, mid, nritems); + copy_for_split(trans, path, l, right, slot, mid, nritems); if (split == 2) { BUG_ON(num_doubles != 0); @@ -4327,7 +4347,7 @@ again: push_for_double: push_for_double_split(trans, root, path, data_size); tried_avoid_double = 1; - if (btrfs_leaf_free_space(fs_info, path->nodes[0]) >= data_size) + if (btrfs_leaf_free_space(path->nodes[0]) >= data_size) return 0; goto again; } @@ -4336,7 +4356,6 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int ins_len) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; @@ -4350,7 +4369,7 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, BUG_ON(key.type != BTRFS_EXTENT_DATA_KEY && key.type != BTRFS_EXTENT_CSUM_KEY); - if (btrfs_leaf_free_space(fs_info, leaf) >= ins_len) + if (btrfs_leaf_free_space(leaf) >= ins_len) return 0; item_size = btrfs_item_size_nr(leaf, path->slots[0]); @@ -4377,7 +4396,7 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, goto err; /* the leaf has changed, it now has room. return now */ - if (btrfs_leaf_free_space(fs_info, path->nodes[0]) >= ins_len) + if (btrfs_leaf_free_space(path->nodes[0]) >= ins_len) goto err; if (key.type == BTRFS_EXTENT_DATA_KEY) { @@ -4400,8 +4419,7 @@ err: return ret; } -static noinline int split_item(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, +static noinline int split_item(struct btrfs_path *path, const struct btrfs_key *new_key, unsigned long split_offset) { @@ -4416,7 +4434,7 @@ static noinline int split_item(struct btrfs_fs_info *fs_info, struct btrfs_disk_key disk_key; leaf = path->nodes[0]; - BUG_ON(btrfs_leaf_free_space(fs_info, leaf) < sizeof(struct btrfs_item)); + BUG_ON(btrfs_leaf_free_space(leaf) < sizeof(struct btrfs_item)); btrfs_set_path_blocking(path); @@ -4465,7 +4483,7 @@ static noinline int split_item(struct btrfs_fs_info *fs_info, item_size - split_offset); btrfs_mark_buffer_dirty(leaf); - BUG_ON(btrfs_leaf_free_space(fs_info, leaf) < 0); + BUG_ON(btrfs_leaf_free_space(leaf) < 0); kfree(buf); return 0; } @@ -4497,7 +4515,7 @@ int btrfs_split_item(struct btrfs_trans_handle *trans, if (ret) return ret; - ret = split_item(root->fs_info, path, new_key, split_offset); + ret = split_item(path, new_key, split_offset); return ret; } @@ -4543,8 +4561,7 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans, * off the end of the item or if we shift the item to chop bytes off * the front. */ -void btrfs_truncate_item(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, u32 new_size, int from_end) +void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end) { int slot; struct extent_buffer *leaf; @@ -4567,7 +4584,7 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, return; nritems = btrfs_header_nritems(leaf); - data_end = leaf_data_end(fs_info, leaf); + data_end = leaf_data_end(leaf); old_data_start = btrfs_item_offset_nr(leaf, slot); @@ -4633,7 +4650,7 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, btrfs_set_item_size(leaf, item, new_size); btrfs_mark_buffer_dirty(leaf); - if (btrfs_leaf_free_space(fs_info, leaf) < 0) { + if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); BUG(); } @@ -4642,8 +4659,7 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, /* * make the item pointed to by the path bigger, data_size is the added size. */ -void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - u32 data_size) +void btrfs_extend_item(struct btrfs_path *path, u32 data_size) { int slot; struct extent_buffer *leaf; @@ -4660,9 +4676,9 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); - data_end = leaf_data_end(fs_info, leaf); + data_end = leaf_data_end(leaf); - if (btrfs_leaf_free_space(fs_info, leaf) < data_size) { + if (btrfs_leaf_free_space(leaf) < data_size) { btrfs_print_leaf(leaf); BUG(); } @@ -4672,9 +4688,9 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, BUG_ON(slot < 0); if (slot >= nritems) { btrfs_print_leaf(leaf); - btrfs_crit(fs_info, "slot %d too large, nritems %d", + btrfs_crit(leaf->fs_info, "slot %d too large, nritems %d", slot, nritems); - BUG_ON(1); + BUG(); } /* @@ -4701,7 +4717,7 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, btrfs_set_item_size(leaf, item, old_size + data_size); btrfs_mark_buffer_dirty(leaf); - if (btrfs_leaf_free_space(fs_info, leaf) < 0) { + if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); BUG(); } @@ -4738,12 +4754,12 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, slot = path->slots[0]; nritems = btrfs_header_nritems(leaf); - data_end = leaf_data_end(fs_info, leaf); + data_end = leaf_data_end(leaf); - if (btrfs_leaf_free_space(fs_info, leaf) < total_size) { + if (btrfs_leaf_free_space(leaf) < total_size) { btrfs_print_leaf(leaf); btrfs_crit(fs_info, "not enough freespace need %u have %d", - total_size, btrfs_leaf_free_space(fs_info, leaf)); + total_size, btrfs_leaf_free_space(leaf)); BUG(); } @@ -4754,7 +4770,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, btrfs_print_leaf(leaf); btrfs_crit(fs_info, "slot %d old_data %d data_end %d", slot, old_data, data_end); - BUG_ON(1); + BUG(); } /* * item0..itemN ... dataN.offset..dataN.size .. data0.size @@ -4794,7 +4810,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, btrfs_set_header_nritems(leaf, nritems + nr); btrfs_mark_buffer_dirty(leaf); - if (btrfs_leaf_free_space(fs_info, leaf) < 0) { + if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); BUG(); } @@ -4966,7 +4982,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, nritems = btrfs_header_nritems(leaf); if (slot + nr != nritems) { - int data_end = leaf_data_end(fs_info, leaf); + int data_end = leaf_data_end(leaf); memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + data_end + dsize, @@ -4996,7 +5012,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_set_header_level(leaf, 0); } else { btrfs_set_path_blocking(path); - clean_tree_block(fs_info, leaf); + btrfs_clean_tree_block(leaf); btrfs_del_leaf(trans, root, path, leaf); } } else { @@ -5126,7 +5142,6 @@ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key, struct btrfs_path *path, u64 min_trans) { - struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *cur; struct btrfs_key found_key; int slot; @@ -5207,7 +5222,7 @@ find_next_key: goto out; } btrfs_set_path_blocking(path); - cur = read_node_slot(fs_info, cur, slot); + cur = read_node_slot(cur, slot); if (IS_ERR(cur)) { ret = PTR_ERR(cur); goto out; @@ -5229,14 +5244,12 @@ out: return ret; } -static int tree_move_down(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, - int *level) +static int tree_move_down(struct btrfs_path *path, int *level) { struct extent_buffer *eb; BUG_ON(*level == 0); - eb = read_node_slot(fs_info, path->nodes[*level], path->slots[*level]); + eb = read_node_slot(path->nodes[*level], path->slots[*level]); if (IS_ERR(eb)) return PTR_ERR(eb); @@ -5276,8 +5289,7 @@ static int tree_move_next_or_upnext(struct btrfs_path *path, * Returns 1 if it had to move up and next. 0 is returned if it moved only next * or down. */ -static int tree_advance(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, +static int tree_advance(struct btrfs_path *path, int *level, int root_level, int allow_down, struct btrfs_key *key) @@ -5287,7 +5299,7 @@ static int tree_advance(struct btrfs_fs_info *fs_info, if (*level == 0 || !allow_down) { ret = tree_move_next_or_upnext(path, level, root_level); } else { - ret = tree_move_down(fs_info, path, level); + ret = tree_move_down(path, level); } if (ret >= 0) { if (*level == 0) @@ -5464,7 +5476,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root, while (1) { if (advance_left && !left_end_reached) { - ret = tree_advance(fs_info, left_path, &left_level, + ret = tree_advance(left_path, &left_level, left_root_level, advance_left != ADVANCE_ONLY_NEXT, &left_key); @@ -5475,7 +5487,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root, advance_left = 0; } if (advance_right && !right_end_reached) { - ret = tree_advance(fs_info, right_path, &right_level, + ret = tree_advance(right_path, &right_level, right_root_level, advance_right != ADVANCE_ONLY_NEXT, &right_key); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b3642367a595..0a61dff27f57 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -41,6 +41,7 @@ extern struct kmem_cache *btrfs_bit_radix_cachep; extern struct kmem_cache *btrfs_path_cachep; extern struct kmem_cache *btrfs_free_space_cachep; struct btrfs_ordered_sum; +struct btrfs_ref; #define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */ @@ -1015,6 +1016,7 @@ struct btrfs_fs_info { /* used to keep from writing metadata until there is a nice batch */ struct percpu_counter dirty_metadata_bytes; struct percpu_counter delalloc_bytes; + struct percpu_counter dio_bytes; s32 dirty_metadata_batch; s32 delalloc_batch; @@ -1092,10 +1094,7 @@ struct btrfs_fs_info { /* holds configuration and tracking. Protected by qgroup_lock */ struct rb_root qgroup_tree; - struct rb_root qgroup_op_tree; spinlock_t qgroup_lock; - spinlock_t qgroup_op_lock; - atomic_t qgroup_op_seq; /* * used to avoid frequently calling ulist_alloc()/ulist_free() @@ -1152,12 +1151,6 @@ struct btrfs_fs_info { struct mutex unused_bg_unpin_mutex; struct mutex delete_unused_bgs_mutex; - /* - * Chunks that can't be freed yet (under a trim/discard operation) - * and will be latter freed. Protected by fs_info->chunk_mutex. - */ - struct list_head pinned_chunks; - /* Cached block sizes */ u32 nodesize; u32 sectorsize; @@ -1348,6 +1341,12 @@ struct btrfs_root { * manipulation with the read-only status via SUBVOL_SETFLAGS */ int send_in_progress; + /* + * Number of currently running deduplication operations that have a + * destination inode belonging to this root. Protected by the lock + * root_item_lock. + */ + int dedupe_in_progress; struct btrfs_subvolume_writers *subv_writers; atomic_t will_be_snapshotted; atomic_t snapshot_force_cow; @@ -1540,6 +1539,21 @@ do { \ #define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31) +#define BTRFS_INODE_FLAG_MASK \ + (BTRFS_INODE_NODATASUM | \ + BTRFS_INODE_NODATACOW | \ + BTRFS_INODE_READONLY | \ + BTRFS_INODE_NOCOMPRESS | \ + BTRFS_INODE_PREALLOC | \ + BTRFS_INODE_SYNC | \ + BTRFS_INODE_IMMUTABLE | \ + BTRFS_INODE_APPEND | \ + BTRFS_INODE_NODUMP | \ + BTRFS_INODE_NOATIME | \ + BTRFS_INODE_DIRSYNC | \ + BTRFS_INODE_COMPRESS | \ + BTRFS_INODE_ROOT_ITEM_INIT) + struct btrfs_map_token { const struct extent_buffer *eb; char *kaddr; @@ -2163,18 +2177,16 @@ static inline int btrfs_header_flag(const struct extent_buffer *eb, u64 flag) return (btrfs_header_flags(eb) & flag) == flag; } -static inline int btrfs_set_header_flag(struct extent_buffer *eb, u64 flag) +static inline void btrfs_set_header_flag(struct extent_buffer *eb, u64 flag) { u64 flags = btrfs_header_flags(eb); btrfs_set_header_flags(eb, flags | flag); - return (flags & flag) == flag; } -static inline int btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag) +static inline void btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag) { u64 flags = btrfs_header_flags(eb); btrfs_set_header_flags(eb, flags & ~flag); - return (flags & flag) == flag; } static inline int btrfs_header_backref_rev(const struct extent_buffer *eb) @@ -2445,13 +2457,12 @@ static inline int btrfs_super_csum_size(const struct btrfs_super_block *s) * this returns the address of the start of the last item, * which is the stop of the leaf data stack */ -static inline unsigned int leaf_data_end(const struct btrfs_fs_info *fs_info, - const struct extent_buffer *leaf) +static inline unsigned int leaf_data_end(const struct extent_buffer *leaf) { u32 nr = btrfs_header_nritems(leaf); if (nr == 0) - return BTRFS_LEAF_DATA_SIZE(fs_info); + return BTRFS_LEAF_DATA_SIZE(leaf->fs_info); return btrfs_item_offset_nr(leaf, nr - 1); } @@ -2698,8 +2709,6 @@ void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg); void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, unsigned long count); -int btrfs_async_run_delayed_refs(struct btrfs_fs_info *fs_info, - unsigned long count, u64 transid, int wait); void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head); @@ -2711,8 +2720,7 @@ int btrfs_pin_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num, int reserved); int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes); -int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb); +int btrfs_exclude_logged_extents(struct extent_buffer *eb); int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, u64 bytenr); struct btrfs_block_group_cache *btrfs_lookup_block_group( @@ -2745,13 +2753,9 @@ int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, int full_backref); int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 flags, int level, int is_data); -int btrfs_free_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, - u64 owner, u64 offset); +int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref); int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len, int delalloc); @@ -2760,15 +2764,11 @@ int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info, void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info); int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans); int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset); + struct btrfs_ref *generic_ref); int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans); -int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); -int btrfs_setup_space_cache(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); +int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans); +int btrfs_setup_space_cache(struct btrfs_trans_handle *trans); int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr); int btrfs_free_block_groups(struct btrfs_fs_info *info); int btrfs_read_block_groups(struct btrfs_fs_info *info); @@ -2936,10 +2936,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, struct extent_buffer **cow_ret, u64 new_root_objectid); int btrfs_block_can_be_shared(struct btrfs_root *root, struct extent_buffer *buf); -void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - u32 data_size); -void btrfs_truncate_item(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, u32 new_size, int from_end); +void btrfs_extend_item(struct btrfs_path *path, u32 data_size); +void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end); int btrfs_split_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, @@ -3015,8 +3013,7 @@ static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) { return btrfs_next_old_item(root, p, 0); } -int btrfs_leaf_free_space(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf); +int btrfs_leaf_free_space(struct extent_buffer *leaf); int __must_check btrfs_drop_snapshot(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, int update_ref, int for_reloc); @@ -3267,6 +3264,7 @@ void btrfs_evict_inode(struct inode *inode); int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc); struct inode *btrfs_alloc_inode(struct super_block *sb); void btrfs_destroy_inode(struct inode *inode); +void btrfs_free_inode(struct inode *inode); int btrfs_drop_inode(struct inode *inode); int __init btrfs_init_cachep(void); void __cold btrfs_destroy_cachep(void); @@ -3755,8 +3753,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, void btrfs_scrub_pause(struct btrfs_fs_info *fs_info); void btrfs_scrub_continue(struct btrfs_fs_info *fs_info); int btrfs_scrub_cancel(struct btrfs_fs_info *info); -int btrfs_scrub_cancel_dev(struct btrfs_fs_info *info, - struct btrfs_device *dev); +int btrfs_scrub_cancel_dev(struct btrfs_device *dev); int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid, struct btrfs_scrub_progress *progress); static inline void btrfs_init_full_stripe_locks_tree( @@ -3805,6 +3802,8 @@ static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info) return signal_pending(current); } +#define in_range(b, first, len) ((b) >= (first) && (b) < (first) + (len)) + /* Sanity test specific functions */ #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS void btrfs_test_inode_set_ops(struct inode *inode); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index c669f250d4a0..43fdb2992956 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -691,7 +691,6 @@ static int btrfs_batch_insert_items(struct btrfs_root *root, struct btrfs_path *path, struct btrfs_delayed_item *item) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_delayed_item *curr, *next; int free_space; int total_data_size = 0, total_size = 0; @@ -708,7 +707,7 @@ static int btrfs_batch_insert_items(struct btrfs_root *root, BUG_ON(!path->nodes[0]); leaf = path->nodes[0]; - free_space = btrfs_leaf_free_space(fs_info, leaf); + free_space = btrfs_leaf_free_space(leaf); INIT_LIST_HEAD(&head); next = item; @@ -1692,7 +1691,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, name = (char *)(di + 1); name_len = btrfs_stack_dir_name_len(di); - d_type = btrfs_filetype_table[di->type]; + d_type = fs_ftype_to_dtype(di->type); btrfs_disk_key_to_cpu(&location, &di->location); over = !dir_emit(ctx, name, name_len, diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 7d2a413df90d..a73fc23e2961 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -735,8 +735,7 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info, * transaction commits. */ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, - u64 bytenr, u64 num_bytes, u64 parent, - u64 ref_root, int level, int action, + struct btrfs_ref *generic_ref, struct btrfs_delayed_extent_op *extent_op, int *old_ref_mod, int *new_ref_mod) { @@ -746,10 +745,18 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; int qrecord_inserted; - bool is_system = (ref_root == BTRFS_CHUNK_TREE_OBJECTID); + bool is_system; + int action = generic_ref->action; + int level = generic_ref->tree_ref.level; int ret; + u64 bytenr = generic_ref->bytenr; + u64 num_bytes = generic_ref->len; + u64 parent = generic_ref->parent; u8 ref_type; + is_system = (generic_ref->real_root == BTRFS_CHUNK_TREE_OBJECTID); + + ASSERT(generic_ref->type == BTRFS_REF_METADATA && generic_ref->action); BUG_ON(extent_op && extent_op->is_data); ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS); if (!ref) @@ -762,7 +769,9 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, } if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) && - is_fstree(ref_root)) { + is_fstree(generic_ref->real_root) && + is_fstree(generic_ref->tree_ref.root) && + !generic_ref->skip_qgroup) { record = kzalloc(sizeof(*record), GFP_NOFS); if (!record) { kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref); @@ -777,13 +786,14 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, ref_type = BTRFS_TREE_BLOCK_REF_KEY; init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes, - ref_root, action, ref_type); - ref->root = ref_root; + generic_ref->tree_ref.root, action, ref_type); + ref->root = generic_ref->tree_ref.root; ref->parent = parent; ref->level = level; init_delayed_ref_head(head_ref, record, bytenr, num_bytes, - ref_root, 0, action, false, is_system); + generic_ref->tree_ref.root, 0, action, false, + is_system); head_ref->extent_op = extent_op; delayed_refs = &trans->transaction->delayed_refs; @@ -822,10 +832,9 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref. */ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, - u64 bytenr, u64 num_bytes, - u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action, - int *old_ref_mod, int *new_ref_mod) + struct btrfs_ref *generic_ref, + u64 reserved, int *old_ref_mod, + int *new_ref_mod) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_data_ref *ref; @@ -833,9 +842,17 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; int qrecord_inserted; + int action = generic_ref->action; int ret; + u64 bytenr = generic_ref->bytenr; + u64 num_bytes = generic_ref->len; + u64 parent = generic_ref->parent; + u64 ref_root = generic_ref->data_ref.ref_root; + u64 owner = generic_ref->data_ref.ino; + u64 offset = generic_ref->data_ref.offset; u8 ref_type; + ASSERT(generic_ref->type == BTRFS_REF_DATA && action); ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS); if (!ref) return -ENOMEM; @@ -859,7 +876,9 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, } if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) && - is_fstree(ref_root)) { + is_fstree(ref_root) && + is_fstree(generic_ref->real_root) && + !generic_ref->skip_qgroup) { record = kzalloc(sizeof(*record), GFP_NOFS); if (!record) { kmem_cache_free(btrfs_delayed_data_ref_cachep, ref); @@ -905,8 +924,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, return 0; } -int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, +int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op) { diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 70606da440aa..c18f93ea88ed 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -176,6 +176,83 @@ struct btrfs_delayed_ref_root { u64 qgroup_to_skip; }; +enum btrfs_ref_type { + BTRFS_REF_NOT_SET, + BTRFS_REF_DATA, + BTRFS_REF_METADATA, + BTRFS_REF_LAST, +}; + +struct btrfs_data_ref { + /* For EXTENT_DATA_REF */ + + /* Root which refers to this data extent */ + u64 ref_root; + + /* Inode which refers to this data extent */ + u64 ino; + + /* + * file_offset - extent_offset + * + * file_offset is the key.offset of the EXTENT_DATA key. + * extent_offset is btrfs_file_extent_offset() of the EXTENT_DATA data. + */ + u64 offset; +}; + +struct btrfs_tree_ref { + /* + * Level of this tree block + * + * Shared for skinny (TREE_BLOCK_REF) and normal tree ref. + */ + int level; + + /* + * Root which refers to this tree block. + * + * For TREE_BLOCK_REF (skinny metadata, either inline or keyed) + */ + u64 root; + + /* For non-skinny metadata, no special member needed */ +}; + +struct btrfs_ref { + enum btrfs_ref_type type; + int action; + + /* + * Whether this extent should go through qgroup record. + * + * Normally false, but for certain cases like delayed subtree scan, + * setting this flag can hugely reduce qgroup overhead. + */ + bool skip_qgroup; + + /* + * Optional. For which root is this modification. + * Mostly used for qgroup optimization. + * + * When unset, data/tree ref init code will populate it. + * In certain cases, we're modifying reference for a different root. + * E.g. COW fs tree blocks for balance. + * In that case, tree_ref::root will be fs tree, but we're doing this + * for reloc tree, then we should set @real_root to reloc tree. + */ + u64 real_root; + u64 bytenr; + u64 len; + + /* Bytenr of the parent tree block */ + u64 parent; + union { + struct btrfs_data_ref data_ref; + struct btrfs_tree_ref tree_ref; + }; +}; + extern struct kmem_cache *btrfs_delayed_ref_head_cachep; extern struct kmem_cache *btrfs_delayed_tree_ref_cachep; extern struct kmem_cache *btrfs_delayed_data_ref_cachep; @@ -184,6 +261,38 @@ extern struct kmem_cache *btrfs_delayed_extent_op_cachep; int __init btrfs_delayed_ref_init(void); void __cold btrfs_delayed_ref_exit(void); +static inline void btrfs_init_generic_ref(struct btrfs_ref *generic_ref, + int action, u64 bytenr, u64 len, u64 parent) +{ + generic_ref->action = action; + generic_ref->bytenr = bytenr; + generic_ref->len = len; + generic_ref->parent = parent; +} + +static inline void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, + int level, u64 root) +{ + /* If @real_root not set, use @root as fallback */ + if (!generic_ref->real_root) + generic_ref->real_root = root; + generic_ref->tree_ref.level = level; + generic_ref->tree_ref.root = root; + generic_ref->type = BTRFS_REF_METADATA; +} + +static inline void btrfs_init_data_ref(struct btrfs_ref *generic_ref, + u64 ref_root, u64 ino, u64 offset) +{ + /* If @real_root not set, use @root as fallback */ + if (!generic_ref->real_root) + generic_ref->real_root = ref_root; + generic_ref->data_ref.ref_root = ref_root; + generic_ref->data_ref.ino = ino; + generic_ref->data_ref.offset = offset; + generic_ref->type = BTRFS_REF_DATA; +} + static inline struct btrfs_delayed_extent_op * btrfs_alloc_delayed_extent_op(void) { @@ -224,17 +333,14 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea } int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, - u64 bytenr, u64 num_bytes, u64 parent, - u64 ref_root, int level, int action, + struct btrfs_ref *generic_ref, struct btrfs_delayed_extent_op *extent_op, int *old_ref_mod, int *new_ref_mod); int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, - u64 bytenr, u64 num_bytes, - u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action, - int *old_ref_mod, int *new_ref_mod); -int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, + struct btrfs_ref *generic_ref, + u64 reserved, int *old_ref_mod, + int *new_ref_mod); +int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index ee193c5222b2..55c15f31d00d 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -273,9 +273,9 @@ error: * called from commit_transaction. Writes changed device replace state to * disk. */ -int btrfs_run_dev_replace(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +int btrfs_run_dev_replace(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; int ret; struct btrfs_root *dev_root = fs_info->dev_root; struct btrfs_path *path; @@ -662,7 +662,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, btrfs_device_set_disk_total_bytes(tgt_device, src_device->disk_total_bytes); btrfs_device_set_bytes_used(tgt_device, src_device->bytes_used); - ASSERT(list_empty(&src_device->resized_list)); + ASSERT(list_empty(&src_device->post_commit_list)); tgt_device->commit_total_bytes = src_device->commit_total_bytes; tgt_device->commit_bytes_used = src_device->bytes_used; @@ -696,7 +696,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, /* replace the sysfs entry */ btrfs_sysfs_rm_device_link(fs_info->fs_devices, src_device); - btrfs_rm_dev_replace_free_srcdev(fs_info, src_device); + btrfs_rm_dev_replace_free_srcdev(src_device); /* write back the superblocks */ trans = btrfs_start_transaction(root, 0); diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h index 4aa40bacc6cc..78c5d8f1adda 100644 --- a/fs/btrfs/dev-replace.h +++ b/fs/btrfs/dev-replace.h @@ -9,8 +9,7 @@ struct btrfs_ioctl_dev_replace_args; int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info); -int btrfs_run_dev_replace(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); +int btrfs_run_dev_replace(struct btrfs_trans_handle *trans); int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args); void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 8de74d835dba..863367c2c620 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -36,7 +36,7 @@ static struct btrfs_dir_item *insert_with_overflow(struct btrfs_trans_handle di = btrfs_match_dir_item_name(fs_info, path, name, name_len); if (di) return ERR_PTR(-EEXIST); - btrfs_extend_item(fs_info, path, data_size); + btrfs_extend_item(path, data_size); } else if (ret < 0) return ERR_PTR(ret); WARN_ON(ret > 0); @@ -429,8 +429,7 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans, start = btrfs_item_ptr_offset(leaf, path->slots[0]); memmove_extent_buffer(leaf, ptr, ptr + sub_item_len, item_len - (ptr + sub_item_len - start)); - btrfs_truncate_item(root->fs_info, path, - item_len - sub_item_len, 1); + btrfs_truncate_item(path, item_len - sub_item_len, 1); } return ret; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 6fe9197f6ee4..deb74a8c191a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -260,15 +260,12 @@ void btrfs_csum_final(u32 crc, u8 *result) } /* - * compute the csum for a btree block, and either verify it or write it - * into the csum field of the block. + * Compute the csum of a btree block and store the result to provided buffer. + * + * Returns error if the extent buffer cannot be mapped. */ -static int csum_tree_block(struct btrfs_fs_info *fs_info, - struct extent_buffer *buf, - int verify) +static int csum_tree_block(struct extent_buffer *buf, u8 *result) { - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - char result[BTRFS_CSUM_SIZE]; unsigned long len; unsigned long cur_len; unsigned long offset = BTRFS_CSUM_SIZE; @@ -288,7 +285,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, */ err = map_private_extent_buffer(buf, offset, 32, &kaddr, &map_start, &map_len); - if (err) + if (WARN_ON(err)) return err; cur_len = min(len, map_len - (offset - map_start)); crc = btrfs_csum_data(kaddr + offset - map_start, @@ -300,23 +297,6 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, btrfs_csum_final(crc, result); - if (verify) { - if (memcmp_extent_buffer(buf, result, 0, csum_size)) { - u32 val; - u32 found = 0; - memcpy(&found, result, csum_size); - - read_extent_buffer(buf, &val, 0, csum_size); - btrfs_warn_rl(fs_info, - "%s checksum verify failed on %llu wanted %X found %X level %d", - fs_info->sb->s_id, buf->start, - val, found, btrfs_header_level(buf)); - return -EUCLEAN; - } - } else { - write_extent_buffer(buf, result, 0, csum_size); - } - return 0; } @@ -414,22 +394,21 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, return ret; } -static int verify_level_key(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int level, - struct btrfs_key *first_key, u64 parent_transid) +int btrfs_verify_level_key(struct extent_buffer *eb, int level, + struct btrfs_key *first_key, u64 parent_transid) { + struct btrfs_fs_info *fs_info = eb->fs_info; int found_level; struct btrfs_key found_key; int ret; found_level = btrfs_header_level(eb); if (found_level != level) { -#ifdef CONFIG_BTRFS_DEBUG - WARN_ON(1); + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: tree level check failed\n"); btrfs_err(fs_info, "tree level mismatch detected, bytenr=%llu level expected=%u has=%u", eb->start, level, found_level); -#endif return -EIO; } @@ -450,9 +429,9 @@ static int verify_level_key(struct btrfs_fs_info *fs_info, btrfs_item_key_to_cpu(eb, &found_key, 0); ret = btrfs_comp_cpu_keys(first_key, &found_key); -#ifdef CONFIG_BTRFS_DEBUG if (ret) { - WARN_ON(1); + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: tree first key check failed\n"); btrfs_err(fs_info, "tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)", eb->start, parent_transid, first_key->objectid, @@ -460,7 +439,6 @@ static int verify_level_key(struct btrfs_fs_info *fs_info, found_key.objectid, found_key.type, found_key.offset); } -#endif return ret; } @@ -472,11 +450,11 @@ static int verify_level_key(struct btrfs_fs_info *fs_info, * @level: expected level, mandatory check * @first_key: expected key of first slot, skip check if NULL */ -static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, +static int btree_read_extent_buffer_pages(struct extent_buffer *eb, u64 parent_transid, int level, struct btrfs_key *first_key) { + struct btrfs_fs_info *fs_info = eb->fs_info; struct extent_io_tree *io_tree; int failed = 0; int ret; @@ -487,14 +465,13 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; while (1) { clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); - ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE, - mirror_num); + ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num); if (!ret) { if (verify_parent_transid(io_tree, eb, parent_transid, 0)) ret = -EIO; - else if (verify_level_key(fs_info, eb, level, - first_key, parent_transid)) + else if (btrfs_verify_level_key(eb, level, + first_key, parent_transid)) ret = -EUCLEAN; else break; @@ -519,7 +496,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, } if (failed && !ret && failed_mirror) - repair_eb_io_failure(fs_info, eb, failed_mirror); + btrfs_repair_eb_io_failure(eb, failed_mirror); return ret; } @@ -533,7 +510,10 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) { u64 start = page_offset(page); u64 found_start; + u8 result[BTRFS_CSUM_SIZE]; + u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); struct extent_buffer *eb; + int ret; eb = (struct extent_buffer *)page->private; if (page != eb->pages[0]) @@ -552,12 +532,28 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid, btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0); - return csum_tree_block(fs_info, eb, 0); + if (csum_tree_block(eb, result)) + return -EINVAL; + + if (btrfs_header_level(eb)) + ret = btrfs_check_node(eb); + else + ret = btrfs_check_leaf_full(eb); + + if (ret < 0) { + btrfs_err(fs_info, + "block=%llu write time tree block corruption detected", + eb->start); + return ret; + } + write_extent_buffer(eb, result, 0, csum_size); + + return 0; } -static int check_tree_block_fsid(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb) +static int check_tree_block_fsid(struct extent_buffer *eb) { + struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; u8 fsid[BTRFS_FSID_SIZE]; int ret = 1; @@ -595,7 +591,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, struct extent_buffer *eb; struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; struct btrfs_fs_info *fs_info = root->fs_info; + u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int ret = 0; + u8 result[BTRFS_CSUM_SIZE]; int reads_done; if (!page->private) @@ -625,7 +623,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, ret = -EIO; goto err; } - if (check_tree_block_fsid(fs_info, eb)) { + if (check_tree_block_fsid(eb)) { btrfs_err_rl(fs_info, "bad fsid on block %llu", eb->start); ret = -EIO; @@ -642,25 +640,44 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, found_level); - ret = csum_tree_block(fs_info, eb, 1); + ret = csum_tree_block(eb, result); if (ret) goto err; + if (memcmp_extent_buffer(eb, result, 0, csum_size)) { + u32 val; + u32 found = 0; + + memcpy(&found, result, csum_size); + + 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", + fs_info->sb->s_id, eb->start, + val, found, btrfs_header_level(eb)); + ret = -EUCLEAN; + goto err; + } + /* * If this is a leaf block and it is corrupt, set the corrupt bit so * that we don't try and read the other copies of this block, just * return -EIO. */ - if (found_level == 0 && btrfs_check_leaf_full(fs_info, eb)) { + if (found_level == 0 && btrfs_check_leaf_full(eb)) { set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = -EIO; } - if (found_level > 0 && btrfs_check_node(fs_info, eb)) + if (found_level > 0 && btrfs_check_node(eb)) ret = -EIO; if (!ret) set_extent_buffer_uptodate(eb); + else + btrfs_err(fs_info, + "block=%llu read time tree block corruption detected", + eb->start); err: if (reads_done && test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) @@ -832,11 +849,11 @@ static blk_status_t btree_csum_one_bio(struct bio *bio) { struct bio_vec *bvec; struct btrfs_root *root; - int i, ret = 0; + int ret = 0; struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); if (ret) @@ -867,11 +884,10 @@ static int check_async_write(struct btrfs_inode *bi) return 1; } -static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, + int mirror_num, + unsigned long bio_flags) { - struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int async = check_async_write(BTRFS_I(inode)); blk_status_t ret; @@ -897,8 +913,7 @@ static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio, * checksumming can happen in parallel across all CPUs */ ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0, - bio_offset, private_data, - btree_submit_bio_start); + 0, inode, btree_submit_bio_start); } if (ret) @@ -1017,22 +1032,23 @@ static const struct address_space_operations btree_aops = { void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr) { struct extent_buffer *buf = NULL; - struct inode *btree_inode = fs_info->btree_inode; + int ret; buf = btrfs_find_create_tree_block(fs_info, bytenr); if (IS_ERR(buf)) return; - read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, - buf, WAIT_NONE, 0); - free_extent_buffer(buf); + + ret = read_extent_buffer_pages(buf, WAIT_NONE, 0); + if (ret < 0) + free_extent_buffer_stale(buf); + else + free_extent_buffer(buf); } int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, int mirror_num, struct extent_buffer **eb) { struct extent_buffer *buf = NULL; - struct inode *btree_inode = fs_info->btree_inode; - struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree; int ret; buf = btrfs_find_create_tree_block(fs_info, bytenr); @@ -1041,15 +1057,14 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags); - ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK, - mirror_num); + ret = read_extent_buffer_pages(buf, WAIT_PAGE_LOCK, mirror_num); if (ret) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return ret; } if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return -EIO; } else if (extent_buffer_uptodate(buf)) { *eb = buf; @@ -1068,19 +1083,6 @@ struct extent_buffer *btrfs_find_create_tree_block( return alloc_extent_buffer(fs_info, bytenr); } - -int btrfs_write_tree_block(struct extent_buffer *buf) -{ - return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start, - buf->start + buf->len - 1); -} - -void btrfs_wait_tree_block_writeback(struct extent_buffer *buf) -{ - filemap_fdatawait_range(buf->pages[0]->mapping, - buf->start, buf->start + buf->len - 1); -} - /* * Read tree block at logical address @bytenr and do variant basic but critical * verification. @@ -1100,19 +1102,19 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, if (IS_ERR(buf)) return buf; - ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid, + ret = btree_read_extent_buffer_pages(buf, parent_transid, level, first_key); if (ret) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return ERR_PTR(ret); } return buf; } -void clean_tree_block(struct btrfs_fs_info *fs_info, - struct extent_buffer *buf) +void btrfs_clean_tree_block(struct extent_buffer *buf) { + struct btrfs_fs_info *fs_info = buf->fs_info; if (btrfs_header_generation(buf) == fs_info->running_transaction->transid) { btrfs_assert_tree_locked(buf); @@ -1208,7 +1210,8 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->log_transid_committed = -1; root->last_log_commit = 0; if (!dummy) - extent_io_tree_init(&root->dirty_log_pages, NULL); + extent_io_tree_init(fs_info, &root->dirty_log_pages, + IO_TREE_ROOT_DIRTY_LOG_PAGES, NULL); memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); @@ -1255,9 +1258,9 @@ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info) #endif struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 objectid) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct extent_buffer *leaf; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *root; @@ -2138,8 +2141,9 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info) inode->i_mapping->a_ops = &btree_aops; RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node); - extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode); - BTRFS_I(inode)->io_tree.track_uptodate = 0; + extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree, + IO_TREE_INODE_IO, inode); + BTRFS_I(inode)->io_tree.track_uptodate = false; extent_map_tree_init(&BTRFS_I(inode)->extent_tree); BTRFS_I(inode)->io_tree.ops = &btree_extent_io_ops; @@ -2162,7 +2166,6 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) spin_lock_init(&fs_info->qgroup_lock); mutex_init(&fs_info->qgroup_ioctl_lock); fs_info->qgroup_tree = RB_ROOT; - fs_info->qgroup_op_tree = RB_ROOT; INIT_LIST_HEAD(&fs_info->dirty_qgroups); fs_info->qgroup_seq = 1; fs_info->qgroup_ulist = NULL; @@ -2630,11 +2633,17 @@ int open_ctree(struct super_block *sb, goto fail; } - ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); + ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL); if (ret) { err = ret; goto fail_srcu; } + + ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); + if (ret) { + err = ret; + goto fail_dio_bytes; + } fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); @@ -2667,7 +2676,6 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->tree_mod_seq_lock); spin_lock_init(&fs_info->super_lock); - spin_lock_init(&fs_info->qgroup_op_lock); spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); rwlock_init(&fs_info->tree_mod_log_lock); @@ -2694,7 +2702,6 @@ int open_ctree(struct super_block *sb, atomic_set(&fs_info->async_delalloc_pages, 0); atomic_set(&fs_info->defrag_running, 0); - atomic_set(&fs_info->qgroup_op_seq, 0); atomic_set(&fs_info->reada_works_cnt, 0); atomic_set(&fs_info->nr_delayed_iputs, 0); atomic64_set(&fs_info->tree_mod_seq, 0); @@ -2748,8 +2755,10 @@ int open_ctree(struct super_block *sb, fs_info->block_group_cache_tree = RB_ROOT; fs_info->first_logical_byte = (u64)-1; - extent_io_tree_init(&fs_info->freed_extents[0], NULL); - extent_io_tree_init(&fs_info->freed_extents[1], NULL); + extent_io_tree_init(fs_info, &fs_info->freed_extents[0], + IO_TREE_FS_INFO_FREED_EXTENTS0, NULL); + extent_io_tree_init(fs_info, &fs_info->freed_extents[1], + IO_TREE_FS_INFO_FREED_EXTENTS1, NULL); fs_info->pinned_extents = &fs_info->freed_extents[0]; set_bit(BTRFS_FS_BARRIER, &fs_info->flags); @@ -2776,8 +2785,6 @@ int open_ctree(struct super_block *sb, init_waitqueue_head(&fs_info->async_submit_wait); init_waitqueue_head(&fs_info->delayed_iputs_wait); - INIT_LIST_HEAD(&fs_info->pinned_chunks); - /* Usable values until the real ones are cached from the superblock */ fs_info->nodesize = 4096; fs_info->sectorsize = 4096; @@ -3335,6 +3342,8 @@ fail_delalloc_bytes: percpu_counter_destroy(&fs_info->delalloc_bytes); fail_dirty_metadata_bytes: percpu_counter_destroy(&fs_info->dirty_metadata_bytes); +fail_dio_bytes: + percpu_counter_destroy(&fs_info->dio_bytes); fail_srcu: cleanup_srcu_struct(&fs_info->subvol_srcu); fail: @@ -4016,6 +4025,10 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_sum(&fs_info->delalloc_bytes)); } + if (percpu_counter_sum(&fs_info->dio_bytes)) + btrfs_info(fs_info, "at unmount dio bytes count %lld", + percpu_counter_sum(&fs_info->dio_bytes)); + btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -4042,25 +4055,17 @@ void close_ctree(struct btrfs_fs_info *fs_info) btrfsic_unmount(fs_info->fs_devices); #endif - btrfs_close_devices(fs_info->fs_devices); btrfs_mapping_tree_free(&fs_info->mapping_tree); + btrfs_close_devices(fs_info->fs_devices); percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); + percpu_counter_destroy(&fs_info->dio_bytes); percpu_counter_destroy(&fs_info->dev_replace.bio_counter); cleanup_srcu_struct(&fs_info->subvol_srcu); btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); - - while (!list_empty(&fs_info->pinned_chunks)) { - struct extent_map *em; - - em = list_first_entry(&fs_info->pinned_chunks, - struct extent_map, list); - list_del_init(&em->list); - free_extent_map(em); - } } int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, @@ -4114,7 +4119,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) * So here we should only check item pointers, not item data. */ if (btrfs_header_level(buf) == 0 && - btrfs_check_leaf_relaxed(fs_info, buf)) { + btrfs_check_leaf_relaxed(buf)) { btrfs_print_leaf(buf); ASSERT(0); } @@ -4157,10 +4162,7 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info) int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, struct btrfs_key *first_key) { - struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root; - struct btrfs_fs_info *fs_info = root->fs_info; - - return btree_read_extent_buffer_pages(fs_info, buf, parent_transid, + return btree_read_extent_buffer_pages(buf, parent_transid, level, first_key); } @@ -4484,10 +4486,17 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_fs_info *fs_info) { + struct btrfs_device *dev, *tmp; + btrfs_cleanup_dirty_bgs(cur_trans, fs_info); ASSERT(list_empty(&cur_trans->dirty_bgs)); ASSERT(list_empty(&cur_trans->io_bgs)); + list_for_each_entry_safe(dev, tmp, &cur_trans->dev_update_list, + post_commit_list) { + list_del_init(&dev->post_commit_list); + } + btrfs_destroy_delayed_refs(cur_trans, fs_info); cur_trans->state = TRANS_STATE_COMMIT_START; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 987a64bc0c66..a0161aa1ea0b 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -39,6 +39,8 @@ static inline u64 btrfs_sb_offset(int mirror) struct btrfs_device; struct btrfs_fs_devices; +int btrfs_verify_level_key(struct extent_buffer *eb, int level, + struct btrfs_key *first_key, u64 parent_transid); struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, u64 parent_transid, int level, struct btrfs_key *first_key); @@ -48,7 +50,7 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, struct extent_buffer *btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, u64 bytenr); -void clean_tree_block(struct btrfs_fs_info *fs_info, struct extent_buffer *buf); +void btrfs_clean_tree_block(struct extent_buffer *buf); int open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options); @@ -123,8 +125,6 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, extent_submit_bio_start_t *submit_bio_start); blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio, int mirror_num); -int btrfs_write_tree_block(struct extent_buffer *buf); -void btrfs_wait_tree_block_writeback(struct extent_buffer *buf); int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_add_log_tree(struct btrfs_trans_handle *trans, @@ -134,7 +134,6 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *trans, void btrfs_cleanup_one_transaction(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 objectid); int btree_lock_page_hook(struct page *page, void *data, void (*flush_fn)(void *)); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c5880329ae37..f79e477a378e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -643,7 +643,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache, if (btrfs_test_opt(fs_info, SPACE_CACHE)) { mutex_lock(&caching_ctl->mutex); - ret = load_free_space_cache(fs_info, cache); + ret = load_free_space_cache(cache); spin_lock(&cache->lock); if (ret == 1) { @@ -756,14 +756,15 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info, return NULL; } -static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes, - bool metadata, u64 root_objectid) +static void add_pinned_bytes(struct btrfs_fs_info *fs_info, + struct btrfs_ref *ref) { struct btrfs_space_info *space_info; + s64 num_bytes = -ref->len; u64 flags; - if (metadata) { - if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID) + if (ref->type == BTRFS_REF_METADATA) { + if (ref->tree_ref.root == BTRFS_CHUNK_TREE_OBJECTID) flags = BTRFS_BLOCK_GROUP_SYSTEM; else flags = BTRFS_BLOCK_GROUP_METADATA; @@ -1704,7 +1705,7 @@ void setup_inline_extent_backref(struct btrfs_fs_info *fs_info, type = extent_ref_type(parent, owner); size = btrfs_extent_inline_ref_size(type); - btrfs_extend_item(fs_info, path, size); + btrfs_extend_item(path, size); ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); refs = btrfs_extent_refs(leaf, ei); @@ -1779,7 +1780,6 @@ void update_inline_extent_backref(struct btrfs_path *path, int *last_ref) { struct extent_buffer *leaf = path->nodes[0]; - struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_extent_item *ei; struct btrfs_extent_data_ref *dref = NULL; struct btrfs_shared_data_ref *sref = NULL; @@ -1834,7 +1834,7 @@ void update_inline_extent_backref(struct btrfs_path *path, memmove_extent_buffer(leaf, ptr, ptr + size, end - ptr - size); item_size -= size; - btrfs_truncate_item(fs_info, path, item_size, 1); + btrfs_truncate_item(path, item_size, 1); } btrfs_mark_buffer_dirty(leaf); } @@ -1905,7 +1905,6 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans, return ret; } -#define in_range(b, first, len) ((b) >= (first) && (b) < (first) + (len)) static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, u64 *discarded_bytes) { @@ -2043,39 +2042,28 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, /* Can return -ENOMEM */ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset) + struct btrfs_ref *generic_ref) { - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info = trans->fs_info; int old_ref_mod, new_ref_mod; int ret; - BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID && - root_objectid == BTRFS_TREE_LOG_OBJECTID); + ASSERT(generic_ref->type != BTRFS_REF_NOT_SET && + generic_ref->action); + BUG_ON(generic_ref->type == BTRFS_REF_METADATA && + generic_ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID); - btrfs_ref_tree_mod(root, bytenr, num_bytes, parent, root_objectid, - owner, offset, BTRFS_ADD_DELAYED_REF); - - if (owner < BTRFS_FIRST_FREE_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(trans, bytenr, - num_bytes, parent, - root_objectid, (int)owner, - BTRFS_ADD_DELAYED_REF, NULL, - &old_ref_mod, &new_ref_mod); - } else { - ret = btrfs_add_delayed_data_ref(trans, bytenr, - num_bytes, parent, - root_objectid, owner, offset, - 0, BTRFS_ADD_DELAYED_REF, + if (generic_ref->type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, generic_ref, + NULL, &old_ref_mod, &new_ref_mod); + else + ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0, &old_ref_mod, &new_ref_mod); - } - if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) { - bool metadata = owner < BTRFS_FIRST_FREE_OBJECTID; + btrfs_ref_tree_mod(fs_info, generic_ref); - add_pinned_bytes(fs_info, -num_bytes, metadata, root_objectid); - } + if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) + add_pinned_bytes(fs_info, generic_ref); return ret; } @@ -2877,97 +2865,6 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans) return btrfs_check_space_for_delayed_refs(trans->fs_info); } -struct async_delayed_refs { - struct btrfs_root *root; - u64 transid; - int count; - int error; - int sync; - struct completion wait; - struct btrfs_work work; -}; - -static inline struct async_delayed_refs * -to_async_delayed_refs(struct btrfs_work *work) -{ - return container_of(work, struct async_delayed_refs, work); -} - -static void delayed_ref_async_start(struct btrfs_work *work) -{ - struct async_delayed_refs *async = to_async_delayed_refs(work); - struct btrfs_trans_handle *trans; - struct btrfs_fs_info *fs_info = async->root->fs_info; - int ret; - - /* if the commit is already started, we don't need to wait here */ - if (btrfs_transaction_blocked(fs_info)) - goto done; - - trans = btrfs_join_transaction(async->root); - if (IS_ERR(trans)) { - async->error = PTR_ERR(trans); - goto done; - } - - /* - * trans->sync means that when we call end_transaction, we won't - * wait on delayed refs - */ - trans->sync = true; - - /* Don't bother flushing if we got into a different transaction */ - if (trans->transid > async->transid) - goto end; - - ret = btrfs_run_delayed_refs(trans, async->count); - if (ret) - async->error = ret; -end: - ret = btrfs_end_transaction(trans); - if (ret && !async->error) - async->error = ret; -done: - if (async->sync) - complete(&async->wait); - else - kfree(async); -} - -int btrfs_async_run_delayed_refs(struct btrfs_fs_info *fs_info, - unsigned long count, u64 transid, int wait) -{ - struct async_delayed_refs *async; - int ret; - - async = kmalloc(sizeof(*async), GFP_NOFS); - if (!async) - return -ENOMEM; - - async->root = fs_info->tree_root; - async->count = count; - async->error = 0; - async->transid = transid; - if (wait) - async->sync = 1; - else - async->sync = 0; - init_completion(&async->wait); - - btrfs_init_work(&async->work, btrfs_extent_refs_helper, - delayed_ref_async_start, NULL, NULL); - - btrfs_queue_work(fs_info->extent_workers, &async->work); - - if (wait) { - wait_for_completion(&async->wait); - ret = async->error; - kfree(async); - return ret; - } - return 0; -} - /* * this starts processing the delayed reference count updates and * extent insertions we have queued up so far. count can be @@ -3036,7 +2933,6 @@ out: } int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 flags, int level, int is_data) { @@ -3053,8 +2949,7 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, extent_op->is_data = is_data ? true : false; extent_op->level = level; - ret = btrfs_add_delayed_extent_op(fs_info, trans, bytenr, - num_bytes, extent_op); + ret = btrfs_add_delayed_extent_op(trans, bytenr, num_bytes, extent_op); if (ret) btrfs_free_delayed_extent_op(extent_op); return ret; @@ -3246,13 +3141,12 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, u32 nritems; struct btrfs_key key; struct btrfs_file_extent_item *fi; + struct btrfs_ref generic_ref = { 0 }; + bool for_reloc = btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC); int i; + int action; int level; int ret = 0; - int (*process_func)(struct btrfs_trans_handle *, - struct btrfs_root *, - u64, u64, u64, u64, u64, u64); - if (btrfs_is_testing(fs_info)) return 0; @@ -3264,15 +3158,14 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state) && level == 0) return 0; - if (inc) - process_func = btrfs_inc_extent_ref; - else - process_func = btrfs_free_extent; - if (full_backref) parent = buf->start; else parent = 0; + if (inc) + action = BTRFS_ADD_DELAYED_REF; + else + action = BTRFS_DROP_DELAYED_REF; for (i = 0; i < nritems; i++) { if (level == 0) { @@ -3290,16 +3183,30 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, num_bytes = btrfs_file_extent_disk_num_bytes(buf, fi); key.offset -= btrfs_file_extent_offset(buf, fi); - ret = process_func(trans, root, bytenr, num_bytes, - parent, ref_root, key.objectid, - key.offset); + btrfs_init_generic_ref(&generic_ref, action, bytenr, + num_bytes, parent); + generic_ref.real_root = root->root_key.objectid; + btrfs_init_data_ref(&generic_ref, ref_root, key.objectid, + key.offset); + generic_ref.skip_qgroup = for_reloc; + if (inc) + ret = btrfs_inc_extent_ref(trans, &generic_ref); + else + ret = btrfs_free_extent(trans, &generic_ref); if (ret) goto fail; } else { bytenr = btrfs_node_blockptr(buf, i); num_bytes = fs_info->nodesize; - ret = process_func(trans, root, bytenr, num_bytes, - parent, ref_root, level - 1, 0); + btrfs_init_generic_ref(&generic_ref, action, bytenr, + num_bytes, parent); + generic_ref.real_root = root->root_key.objectid; + btrfs_init_tree_ref(&generic_ref, level - 1, ref_root); + generic_ref.skip_qgroup = for_reloc; + if (inc) + ret = btrfs_inc_extent_ref(trans, &generic_ref); + else + ret = btrfs_free_extent(trans, &generic_ref); if (ret) goto fail; } @@ -3322,10 +3229,10 @@ int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, } static int write_one_cache_group(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_block_group_cache *cache) { + struct btrfs_fs_info *fs_info = trans->fs_info; int ret; struct btrfs_root *extent_root = fs_info->extent_root; unsigned long bi; @@ -3348,10 +3255,10 @@ fail: } -static struct btrfs_block_group_cache * -next_block_group(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache) +static struct btrfs_block_group_cache *next_block_group( + struct btrfs_block_group_cache *cache) { + struct btrfs_fs_info *fs_info = cache->fs_info; struct rb_node *node; spin_lock(&fs_info->block_group_cache_lock); @@ -3404,7 +3311,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group, if (trans->aborted) return 0; again: - inode = lookup_free_space_inode(fs_info, block_group, path); + inode = lookup_free_space_inode(block_group, path); if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) { ret = PTR_ERR(inode); btrfs_release_path(path); @@ -3418,8 +3325,7 @@ again: if (block_group->ro) goto out_free; - ret = create_free_space_inode(fs_info, trans, block_group, - path); + ret = create_free_space_inode(trans, block_group, path); if (ret) goto out_free; goto again; @@ -3538,9 +3444,9 @@ out: return ret; } -int btrfs_setup_space_cache(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +int btrfs_setup_space_cache(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group_cache *cache, *tmp; struct btrfs_transaction *cur_trans = trans->transaction; struct btrfs_path *path; @@ -3652,8 +3558,7 @@ again: if (cache->disk_cache_state == BTRFS_DC_SETUP) { cache->io_ctl.inode = NULL; - ret = btrfs_write_out_cache(fs_info, trans, - cache, path); + ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { num_started++; should_put = 0; @@ -3673,8 +3578,7 @@ again: } } if (!ret) { - ret = write_one_cache_group(trans, fs_info, - path, cache); + ret = write_one_cache_group(trans, path, cache); /* * Our block group might still be attached to the list * of new block groups in the transaction handle of some @@ -3744,9 +3648,9 @@ again: return ret; } -int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group_cache *cache; struct btrfs_transaction *cur_trans = trans->transaction; int ret = 0; @@ -3809,8 +3713,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, if (!ret && cache->disk_cache_state == BTRFS_DC_SETUP) { cache->io_ctl.inode = NULL; - ret = btrfs_write_out_cache(fs_info, trans, - cache, path); + ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { num_started++; should_put = 0; @@ -3824,8 +3727,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, } } if (!ret) { - ret = write_one_cache_group(trans, fs_info, - path, cache); + ret = write_one_cache_group(trans, path, cache); /* * One of the free space endio workers might have * created a new block group while updating a free space @@ -3842,8 +3744,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, if (ret == -ENOENT) { wait_event(cur_trans->writer_wait, atomic_read(&cur_trans->num_writers) == 1); - ret = write_one_cache_group(trans, fs_info, - path, cache); + ret = write_one_cache_group(trans, path, cache); } if (ret) btrfs_abort_transaction(trans, ret); @@ -4732,6 +4633,7 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim, struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; u64 delalloc_bytes; + u64 dio_bytes; u64 async_pages; u64 items; long time_left; @@ -4747,7 +4649,8 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim, delalloc_bytes = percpu_counter_sum_positive( &fs_info->delalloc_bytes); - if (delalloc_bytes == 0) { + dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes); + if (delalloc_bytes == 0 && dio_bytes == 0) { if (trans) return; if (wait_ordered) @@ -4755,8 +4658,16 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim, return; } + /* + * If we are doing more ordered than delalloc we need to just wait on + * ordered extents, otherwise we'll waste time trying to flush delalloc + * that likely won't give us the space back we need. + */ + if (dio_bytes > delalloc_bytes) + wait_ordered = true; + loops = 0; - while (delalloc_bytes && loops < 3) { + while ((delalloc_bytes || dio_bytes) && loops < 3) { nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT; /* @@ -4806,6 +4717,7 @@ skip_async: } delalloc_bytes = percpu_counter_sum_positive( &fs_info->delalloc_bytes); + dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes); } } @@ -5803,85 +5715,6 @@ int btrfs_block_rsv_refill(struct btrfs_root *root, return ret; } -static void calc_refill_bytes(struct btrfs_block_rsv *block_rsv, - u64 *metadata_bytes, u64 *qgroup_bytes) -{ - *metadata_bytes = 0; - *qgroup_bytes = 0; - - spin_lock(&block_rsv->lock); - if (block_rsv->reserved < block_rsv->size) - *metadata_bytes = block_rsv->size - block_rsv->reserved; - if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size) - *qgroup_bytes = block_rsv->qgroup_rsv_size - - block_rsv->qgroup_rsv_reserved; - spin_unlock(&block_rsv->lock); -} - -/** - * btrfs_inode_rsv_refill - refill the inode block rsv. - * @inode - the inode we are refilling. - * @flush - the flushing restriction. - * - * Essentially the same as btrfs_block_rsv_refill, except it uses the - * block_rsv->size as the minimum size. We'll either refill the missing amount - * or return if we already have enough space. This will also handle the reserve - * tracepoint for the reserved amount. - */ -static int btrfs_inode_rsv_refill(struct btrfs_inode *inode, - enum btrfs_reserve_flush_enum flush) -{ - struct btrfs_root *root = inode->root; - struct btrfs_block_rsv *block_rsv = &inode->block_rsv; - u64 num_bytes, last = 0; - u64 qgroup_num_bytes; - int ret = -ENOSPC; - - calc_refill_bytes(block_rsv, &num_bytes, &qgroup_num_bytes); - if (num_bytes == 0) - return 0; - - do { - ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, - true); - if (ret) - return ret; - ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush); - if (ret) { - btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes); - last = num_bytes; - /* - * If we are fragmented we can end up with a lot of - * outstanding extents which will make our size be much - * larger than our reserved amount. - * - * If the reservation happens here, it might be very - * big though not needed in the end, if the delalloc - * flushing happens. - * - * If this is the case try and do the reserve again. - */ - if (flush == BTRFS_RESERVE_FLUSH_ALL) - calc_refill_bytes(block_rsv, &num_bytes, - &qgroup_num_bytes); - if (num_bytes == 0) - return 0; - } - } while (ret && last != num_bytes); - - if (!ret) { - block_rsv_add_bytes(block_rsv, num_bytes, false); - trace_btrfs_space_reservation(root->fs_info, "delalloc", - btrfs_ino(inode), num_bytes, 1); - - /* Don't forget to increase qgroup_rsv_reserved */ - spin_lock(&block_rsv->lock); - block_rsv->qgroup_rsv_reserved += qgroup_num_bytes; - spin_unlock(&block_rsv->lock); - } - return ret; -} - static u64 __btrfs_block_rsv_release(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, u64 num_bytes, u64 *qgroup_to_release) @@ -6182,9 +6015,25 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, spin_unlock(&block_rsv->lock); } +static void calc_inode_reservations(struct btrfs_fs_info *fs_info, + u64 num_bytes, u64 *meta_reserve, + u64 *qgroup_reserve) +{ + u64 nr_extents = count_max_extents(num_bytes); + u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes); + + /* We add one for the inode update at finish ordered time */ + *meta_reserve = btrfs_calc_trans_metadata_size(fs_info, + nr_extents + csum_leaves + 1); + *qgroup_reserve = nr_extents * fs_info->nodesize; +} + int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_block_rsv *block_rsv = &inode->block_rsv; + u64 meta_reserve, qgroup_reserve; unsigned nr_extents; enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL; int ret = 0; @@ -6214,7 +6063,31 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) num_bytes = ALIGN(num_bytes, fs_info->sectorsize); - /* Add our new extents and calculate the new rsv size. */ + /* + * We always want to do it this way, every other way is wrong and ends + * in tears. Pre-reserving the amount we are going to add will always + * be the right way, because otherwise if we have enough parallelism we + * could end up with thousands of inodes all holding little bits of + * reservations they were able to make previously and the only way to + * reclaim that space is to ENOSPC out the operations and clear + * everything out and try again, which is bad. This way we just + * over-reserve slightly, and clean up the mess when we are done. + */ + calc_inode_reservations(fs_info, num_bytes, &meta_reserve, + &qgroup_reserve); + ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true); + if (ret) + goto out_fail; + ret = reserve_metadata_bytes(root, block_rsv, meta_reserve, flush); + if (ret) + goto out_qgroup; + + /* + * Now we need to update our outstanding extents and csum bytes _first_ + * and then add the reservation to the block_rsv. This keeps us from + * racing with an ordered completion or some such that would think it + * needs to free the reservation we just made. + */ spin_lock(&inode->lock); nr_extents = count_max_extents(num_bytes); btrfs_mod_outstanding_extents(inode, nr_extents); @@ -6222,22 +6095,21 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); - ret = btrfs_inode_rsv_refill(inode, flush); - if (unlikely(ret)) - goto out_fail; + /* Now we can safely add our space to our block rsv */ + block_rsv_add_bytes(block_rsv, meta_reserve, false); + trace_btrfs_space_reservation(root->fs_info, "delalloc", + btrfs_ino(inode), meta_reserve, 1); + + spin_lock(&block_rsv->lock); + block_rsv->qgroup_rsv_reserved += qgroup_reserve; + spin_unlock(&block_rsv->lock); if (delalloc_lock) mutex_unlock(&inode->delalloc_mutex); return 0; - +out_qgroup: + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve); out_fail: - spin_lock(&inode->lock); - nr_extents = count_max_extents(num_bytes); - btrfs_mod_outstanding_extents(inode, -nr_extents); - inode->csum_bytes -= num_bytes; - btrfs_calculate_inode_block_rsv_size(fs_info, inode); - spin_unlock(&inode->lock); - btrfs_inode_rsv_release(inode, true); if (delalloc_lock) mutex_unlock(&inode->delalloc_mutex); @@ -6361,9 +6233,9 @@ void btrfs_delalloc_release_space(struct inode *inode, } static int update_block_group(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *info, u64 bytenr, - u64 num_bytes, int alloc) + u64 bytenr, u64 num_bytes, int alloc) { + struct btrfs_fs_info *info = trans->fs_info; struct btrfs_block_group_cache *cache = NULL; u64 total = num_bytes; u64 old_val; @@ -6444,7 +6316,6 @@ static int update_block_group(struct btrfs_trans_handle *trans, if (list_empty(&cache->dirty_list)) { list_add_tail(&cache->dirty_list, &trans->transaction->dirty_bgs); - trans->transaction->num_dirty_bgs++; trans->delayed_ref_updates++; btrfs_get_block_group(cache); } @@ -6491,10 +6362,11 @@ static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start) return bytenr; } -static int pin_down_extent(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, +static int pin_down_extent(struct btrfs_block_group_cache *cache, u64 bytenr, u64 num_bytes, int reserved) { + struct btrfs_fs_info *fs_info = cache->fs_info; + spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); cache->pinned += num_bytes; @@ -6526,7 +6398,7 @@ int btrfs_pin_extent(struct btrfs_fs_info *fs_info, cache = btrfs_lookup_block_group(fs_info, bytenr); BUG_ON(!cache); /* Logic error */ - pin_down_extent(fs_info, cache, bytenr, num_bytes, reserved); + pin_down_extent(cache, bytenr, num_bytes, reserved); btrfs_put_block_group(cache); return 0; @@ -6553,7 +6425,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info, */ cache_block_group(cache, 1); - pin_down_extent(fs_info, cache, bytenr, num_bytes, 0); + pin_down_extent(cache, bytenr, num_bytes, 0); /* remove us from the free space cache (if we're there at all) */ ret = btrfs_remove_free_space(cache, bytenr, num_bytes); @@ -6607,9 +6479,9 @@ out_lock: return ret; } -int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb) +int btrfs_exclude_logged_extents(struct extent_buffer *eb) { + struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_file_extent_item *item; struct btrfs_key key; int found_type; @@ -7198,7 +7070,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, goto out; } - ret = update_block_group(trans, info, bytenr, num_bytes, 0); + ret = update_block_group(trans, bytenr, num_bytes, 0); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -7272,21 +7144,20 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, u64 parent, int last_ref) { struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_ref generic_ref = { 0 }; int pin = 1; int ret; + btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, + buf->start, buf->len, parent); + btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf), + root->root_key.objectid); + if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { int old_ref_mod, new_ref_mod; - btrfs_ref_tree_mod(root, buf->start, buf->len, parent, - root->root_key.objectid, - btrfs_header_level(buf), 0, - BTRFS_DROP_DELAYED_REF); - ret = btrfs_add_delayed_tree_ref(trans, buf->start, - buf->len, parent, - root->root_key.objectid, - btrfs_header_level(buf), - BTRFS_DROP_DELAYED_REF, NULL, + btrfs_ref_tree_mod(fs_info, &generic_ref); + ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL, &old_ref_mod, &new_ref_mod); BUG_ON(ret); /* -ENOMEM */ pin = old_ref_mod >= 0 && new_ref_mod < 0; @@ -7305,8 +7176,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, cache = btrfs_lookup_block_group(fs_info, buf->start); if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) { - pin_down_extent(fs_info, cache, buf->start, - buf->len, 1); + pin_down_extent(cache, buf->start, buf->len, 1); btrfs_put_block_group(cache); goto out; } @@ -7320,8 +7190,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, } out: if (pin) - add_pinned_bytes(fs_info, buf->len, true, - root->root_key.objectid); + add_pinned_bytes(fs_info, &generic_ref); if (last_ref) { /* @@ -7333,52 +7202,43 @@ out: } /* Can return -ENOMEM */ -int btrfs_free_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, - u64 owner, u64 offset) +int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) { - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info = trans->fs_info; int old_ref_mod, new_ref_mod; int ret; if (btrfs_is_testing(fs_info)) return 0; - if (root_objectid != BTRFS_TREE_LOG_OBJECTID) - btrfs_ref_tree_mod(root, bytenr, num_bytes, parent, - root_objectid, owner, offset, - BTRFS_DROP_DELAYED_REF); - /* * tree log blocks never actually go into the extent allocation * tree, just update pinning info and exit early. */ - if (root_objectid == BTRFS_TREE_LOG_OBJECTID) { - WARN_ON(owner >= BTRFS_FIRST_FREE_OBJECTID); + if ((ref->type == BTRFS_REF_METADATA && + ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID) || + (ref->type == BTRFS_REF_DATA && + ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID)) { /* unlocks the pinned mutex */ - btrfs_pin_extent(fs_info, bytenr, num_bytes, 1); + btrfs_pin_extent(fs_info, ref->bytenr, ref->len, 1); old_ref_mod = new_ref_mod = 0; ret = 0; - } else if (owner < BTRFS_FIRST_FREE_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(trans, bytenr, - num_bytes, parent, - root_objectid, (int)owner, - BTRFS_DROP_DELAYED_REF, NULL, + } else if (ref->type == BTRFS_REF_METADATA) { + ret = btrfs_add_delayed_tree_ref(trans, ref, NULL, &old_ref_mod, &new_ref_mod); } else { - ret = btrfs_add_delayed_data_ref(trans, bytenr, - num_bytes, parent, - root_objectid, owner, offset, - 0, BTRFS_DROP_DELAYED_REF, + ret = btrfs_add_delayed_data_ref(trans, ref, 0, &old_ref_mod, &new_ref_mod); } - if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) { - bool metadata = owner < BTRFS_FIRST_FREE_OBJECTID; + if (!((ref->type == BTRFS_REF_METADATA && + ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID) || + (ref->type == BTRFS_REF_DATA && + ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID))) + btrfs_ref_tree_mod(fs_info, ref); - add_pinned_bytes(fs_info, num_bytes, metadata, root_objectid); - } + if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) + add_pinned_bytes(fs_info, ref); return ret; } @@ -7569,7 +7429,6 @@ static int find_free_extent_clustered(struct btrfs_block_group_cache *bg, struct find_free_extent_ctl *ffe_ctl, struct btrfs_block_group_cache **cluster_bg_ret) { - struct btrfs_fs_info *fs_info = bg->fs_info; struct btrfs_block_group_cache *cluster_bg; u64 aligned_cluster; u64 offset; @@ -7629,9 +7488,8 @@ refill_cluster: aligned_cluster = max_t(u64, ffe_ctl->empty_cluster + ffe_ctl->empty_size, bg->full_stripe_len); - ret = btrfs_find_space_cluster(fs_info, bg, last_ptr, - ffe_ctl->search_start, ffe_ctl->num_bytes, - aligned_cluster); + ret = btrfs_find_space_cluster(bg, last_ptr, ffe_ctl->search_start, + ffe_ctl->num_bytes, aligned_cluster); if (ret == 0) { /* Now pull our allocation out of this cluster */ offset = btrfs_alloc_from_cluster(bg, last_ptr, @@ -8281,7 +8139,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, } if (pin) - pin_down_extent(fs_info, cache, start, len, 1); + pin_down_extent(cache, start, len, 1); else { if (btrfs_test_opt(fs_info, DISCARD)) ret = btrfs_discard_extent(fs_info, start, len, NULL); @@ -8370,7 +8228,7 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, if (ret) return ret; - ret = update_block_group(trans, fs_info, ins->objectid, ins->offset, 1); + ret = update_block_group(trans, ins->objectid, ins->offset, 1); if (ret) { /* -ENOENT, logic error */ btrfs_err(fs_info, "update block group failed for %llu %llu", ins->objectid, ins->offset); @@ -8460,7 +8318,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, if (ret) return ret; - ret = update_block_group(trans, fs_info, extent_key.objectid, + ret = update_block_group(trans, extent_key.objectid, fs_info->nodesize, 1); if (ret) { /* -ENOENT, logic error */ btrfs_err(fs_info, "update block group failed for %llu %llu", @@ -8478,19 +8336,17 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, u64 offset, u64 ram_bytes, struct btrfs_key *ins) { + struct btrfs_ref generic_ref = { 0 }; int ret; BUG_ON(root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); - btrfs_ref_tree_mod(root, ins->objectid, ins->offset, 0, - root->root_key.objectid, owner, offset, - BTRFS_ADD_DELAYED_EXTENT); - - ret = btrfs_add_delayed_data_ref(trans, ins->objectid, - ins->offset, 0, - root->root_key.objectid, owner, - offset, ram_bytes, - BTRFS_ADD_DELAYED_EXTENT, NULL, NULL); + btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT, + ins->objectid, ins->offset, 0); + btrfs_init_data_ref(&generic_ref, root->root_key.objectid, owner, offset); + btrfs_ref_tree_mod(root->fs_info, &generic_ref); + ret = btrfs_add_delayed_data_ref(trans, &generic_ref, + ram_bytes, NULL, NULL); return ret; } @@ -8563,7 +8419,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); btrfs_tree_lock(buf); - clean_tree_block(fs_info, buf); + btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); btrfs_set_lock_blocking_write(buf); @@ -8682,6 +8538,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_block_rsv *block_rsv; struct extent_buffer *buf; struct btrfs_delayed_extent_op *extent_op; + struct btrfs_ref generic_ref = { 0 }; u64 flags = 0; int ret; u32 blocksize = fs_info->nodesize; @@ -8736,13 +8593,12 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, extent_op->is_data = false; extent_op->level = level; - btrfs_ref_tree_mod(root, ins.objectid, ins.offset, parent, - root_objectid, level, 0, - BTRFS_ADD_DELAYED_EXTENT); - ret = btrfs_add_delayed_tree_ref(trans, ins.objectid, - ins.offset, parent, - root_objectid, level, - BTRFS_ADD_DELAYED_EXTENT, + btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT, + ins.objectid, ins.offset, parent); + generic_ref.real_root = root->root_key.objectid; + btrfs_init_tree_ref(&generic_ref, level, root_objectid); + btrfs_ref_tree_mod(fs_info, &generic_ref); + ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, extent_op, NULL, NULL); if (ret) goto out_free_delayed; @@ -8918,7 +8774,7 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans, BUG_ON(ret); /* -ENOMEM */ ret = btrfs_dec_ref(trans, root, eb, 0); BUG_ON(ret); /* -ENOMEM */ - ret = btrfs_set_disk_extent_flags(trans, fs_info, eb->start, + ret = btrfs_set_disk_extent_flags(trans, eb->start, eb->len, flag, btrfs_header_level(eb), 0); BUG_ON(ret); /* -ENOMEM */ @@ -8987,6 +8843,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, u64 parent; struct btrfs_key key; struct btrfs_key first_key; + struct btrfs_ref ref = { 0 }; struct extent_buffer *next; int level = wc->level; int reada = 0; @@ -9159,9 +9016,10 @@ skip: wc->drop_level = level; find_next_key(path, level, &wc->drop_progress); - ret = btrfs_free_extent(trans, root, bytenr, fs_info->nodesize, - parent, root->root_key.objectid, - level - 1, 0); + btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr, + fs_info->nodesize, parent); + btrfs_init_tree_ref(&ref, level - 1, root->root_key.objectid); + ret = btrfs_free_extent(trans, &ref); if (ret) goto out_unlock; } @@ -9251,21 +9109,23 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, else ret = btrfs_dec_ref(trans, root, eb, 0); BUG_ON(ret); /* -ENOMEM */ - ret = btrfs_qgroup_trace_leaf_items(trans, eb); - if (ret) { - btrfs_err_rl(fs_info, - "error %d accounting leaf items. Quota is out of sync, rescan required.", + if (is_fstree(root->root_key.objectid)) { + ret = btrfs_qgroup_trace_leaf_items(trans, eb); + if (ret) { + btrfs_err_rl(fs_info, + "error %d accounting leaf items, quota is out of sync, rescan required", ret); + } } } - /* make block locked assertion in clean_tree_block happy */ + /* make block locked assertion in btrfs_clean_tree_block happy */ if (!path->locks[level] && btrfs_header_generation(eb) == trans->transid) { btrfs_tree_lock(eb); btrfs_set_lock_blocking_write(eb); path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; } - clean_tree_block(fs_info, eb); + btrfs_clean_tree_block(eb); } if (eb == root->node) { @@ -9921,12 +9781,10 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache) */ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr) { - struct btrfs_root *root = fs_info->extent_root; struct btrfs_block_group_cache *block_group; struct btrfs_space_info *space_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; - struct btrfs_trans_handle *trans; u64 min_free; u64 dev_min = 1; u64 dev_nr = 0; @@ -10025,13 +9883,6 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr) min_free = div64_u64(min_free, dev_min); } - /* We need to do this so that we can look at pending chunks */ - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - goto out; - } - mutex_lock(&fs_info->chunk_mutex); list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { u64 dev_offset; @@ -10042,7 +9893,7 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr) */ if (device->total_bytes > device->bytes_used + min_free && !test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { - ret = find_free_dev_extent(trans, device, min_free, + ret = find_free_dev_extent(device, min_free, &dev_offset, NULL); if (!ret) dev_nr++; @@ -10058,7 +9909,6 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr) "no space to allocate a new chunk for block group %llu", block_group->key.objectid); mutex_unlock(&fs_info->chunk_mutex); - btrfs_end_transaction(trans); out: btrfs_put_block_group(block_group); return ret; @@ -10159,7 +10009,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) if (block_group->iref) break; spin_unlock(&block_group->lock); - block_group = next_block_group(info, block_group); + block_group = next_block_group(block_group); } if (!block_group) { if (last == 0) @@ -10660,7 +10510,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, struct btrfs_block_group_cache *cache; int ret; - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); cache = btrfs_create_block_group_cache(fs_info, chunk_offset, size); if (!cache) @@ -10808,7 +10658,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, * get the inode first so any iput calls done for the io_list * aren't the final iput (no unlinks allowed now) */ - inode = lookup_free_space_inode(fs_info, block_group, path); + inode = lookup_free_space_inode(block_group, path); mutex_lock(&trans->transaction->cache_write_mutex); /* @@ -10952,10 +10802,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, memcpy(&key, &block_group->key, sizeof(key)); mutex_lock(&fs_info->chunk_mutex); - if (!list_empty(&em->list)) { - /* We're in the transaction->pending_chunks list. */ - free_extent_map(em); - } spin_lock(&block_group->lock); block_group->removed = 1; /* @@ -10982,25 +10828,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, * the transaction commit has completed. */ remove_em = (atomic_read(&block_group->trimming) == 0); - /* - * Make sure a trimmer task always sees the em in the pinned_chunks list - * if it sees block_group->removed == 1 (needs to lock block_group->lock - * before checking block_group->removed). - */ - if (!remove_em) { - /* - * Our em might be in trans->transaction->pending_chunks which - * is protected by fs_info->chunk_mutex ([lock|unlock]_chunks), - * and so is the fs_info->pinned_chunks list. - * - * So at this point we must be holding the chunk_mutex to avoid - * any races with chunk allocation (more specifically at - * volumes.c:contains_pending_extent()), to ensure it always - * sees the em, either in the pending_chunks list or in the - * pinned_chunks list. - */ - list_move_tail(&em->list, &fs_info->pinned_chunks); - } spin_unlock(&block_group->lock); if (remove_em) { @@ -11008,11 +10835,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, em_tree = &fs_info->mapping_tree.map_tree; write_lock(&em_tree->lock); - /* - * The em might be in the pending_chunks list, so make sure the - * chunk mutex is locked, since remove_extent_mapping() will - * delete us from that list. - */ remove_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); /* once for the tree */ @@ -11315,11 +11137,12 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, * held back allocations. */ static int btrfs_trim_free_extents(struct btrfs_device *device, - u64 minlen, u64 *trimmed) + struct fstrim_range *range, u64 *trimmed) { - u64 start = 0, len = 0; + u64 start, len = 0, end = 0; int ret; + start = max_t(u64, range->start, SZ_1M); *trimmed = 0; /* Discard not supported = nothing to do. */ @@ -11338,43 +11161,52 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, while (1) { struct btrfs_fs_info *fs_info = device->fs_info; - struct btrfs_transaction *trans; u64 bytes; ret = mutex_lock_interruptible(&fs_info->chunk_mutex); if (ret) break; - ret = down_read_killable(&fs_info->commit_root_sem); - if (ret) { + find_first_clear_extent_bit(&device->alloc_state, start, + &start, &end, + CHUNK_TRIMMED | CHUNK_ALLOCATED); + /* + * If find_first_clear_extent_bit find a range that spans the + * end of the device it will set end to -1, in this case it's up + * to the caller to trim the value to the size of the device. + */ + end = min(end, device->total_bytes - 1); + len = end - start + 1; + + /* We didn't find any extents */ + if (!len) { mutex_unlock(&fs_info->chunk_mutex); + ret = 0; break; } - spin_lock(&fs_info->trans_lock); - trans = fs_info->running_transaction; - if (trans) - refcount_inc(&trans->use_count); - spin_unlock(&fs_info->trans_lock); - - if (!trans) - up_read(&fs_info->commit_root_sem); - - ret = find_free_dev_extent_start(trans, device, minlen, start, - &start, &len); - if (trans) { - up_read(&fs_info->commit_root_sem); - btrfs_put_transaction(trans); + /* Keep going until we satisfy minlen or reach end of space */ + if (len < range->minlen) { + mutex_unlock(&fs_info->chunk_mutex); + start += len; + continue; } - if (ret) { + /* If we are out of the passed range break */ + if (start > range->start + range->len - 1) { mutex_unlock(&fs_info->chunk_mutex); - if (ret == -ENOSPC) - ret = 0; break; } - ret = btrfs_issue_discard(device->bdev, start, len, &bytes); + start = max(range->start, start); + len = min(range->len, len); + + ret = btrfs_issue_discard(device->bdev, start, len, + &bytes); + if (!ret) + set_extent_bits(&device->alloc_state, start, + start + bytes - 1, + CHUNK_TRIMMED); mutex_unlock(&fs_info->chunk_mutex); if (ret) @@ -11383,6 +11215,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, start += len; *trimmed += bytes; + /* We've trimmed enough */ + if (*trimmed >= range->len) + break; + if (fatal_signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -11419,7 +11255,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) int ret = 0; cache = btrfs_lookup_first_block_group(fs_info, range->start); - for (; cache; cache = next_block_group(fs_info, cache)) { + for (; cache; cache = next_block_group(cache)) { if (cache->key.objectid >= (range->start + range->len)) { btrfs_put_block_group(cache); break; @@ -11466,8 +11302,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) mutex_lock(&fs_info->fs_devices->device_list_mutex); devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { - ret = btrfs_trim_free_extents(device, range->minlen, - &group_trimmed); + ret = btrfs_trim_free_extents(device, range, &group_trimmed); if (ret) { dev_failed++; dev_ret = ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index ca8b8e785cf3..db337e53aab3 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -109,8 +109,6 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller, #define btrfs_debug_check_extent_io_range(c, s, e) do {} while (0) #endif -#define BUFFER_LRU_MAX 64 - struct tree_entry { u64 start; u64 end; @@ -151,34 +149,51 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num, unsigned long bio_flags) { blk_status_t ret = 0; - struct bio_vec *bvec = bio_last_bvec_all(bio); - struct bio_vec bv; struct extent_io_tree *tree = bio->bi_private; - u64 start; - - mp_bvec_last_segment(bvec, &bv); - start = page_offset(bv.bv_page) + bv.bv_offset; bio->bi_private = NULL; if (tree->ops) ret = tree->ops->submit_bio_hook(tree->private_data, bio, - mirror_num, bio_flags, start); + mirror_num, bio_flags); else btrfsic_submit_bio(bio); return blk_status_to_errno(ret); } -static void flush_write_bio(struct extent_page_data *epd) +/* Cleanup unsubmitted bios */ +static void end_write_bio(struct extent_page_data *epd, int ret) { if (epd->bio) { - int ret; + epd->bio->bi_status = errno_to_blk_status(ret); + bio_endio(epd->bio); + epd->bio = NULL; + } +} +/* + * Submit bio from extent page data via submit_one_bio + * + * Return 0 if everything is OK. + * Return <0 for error. + */ +static int __must_check flush_write_bio(struct extent_page_data *epd) +{ + int ret = 0; + + if (epd->bio) { ret = submit_one_bio(epd->bio, 0, 0); - BUG_ON(ret < 0); /* -ENOMEM */ + /* + * Clean up of epd->bio is handled by its endio function. + * And endio is either triggered by successful bio execution + * or the error handler of submit bio hook. + * So at this point, no matter what happened, we don't need + * to clean up epd->bio. + */ epd->bio = NULL; } + return ret; } int __init extent_io_init(void) @@ -232,14 +247,46 @@ void __cold extent_io_exit(void) bioset_exit(&btrfs_bioset); } -void extent_io_tree_init(struct extent_io_tree *tree, +void extent_io_tree_init(struct btrfs_fs_info *fs_info, + struct extent_io_tree *tree, unsigned int owner, void *private_data) { + tree->fs_info = fs_info; tree->state = RB_ROOT; tree->ops = NULL; tree->dirty_bytes = 0; spin_lock_init(&tree->lock); tree->private_data = private_data; + tree->owner = owner; +} + +void extent_io_tree_release(struct extent_io_tree *tree) +{ + spin_lock(&tree->lock); + /* + * Do a single barrier for the waitqueue_active check here, the state + * of the waitqueue should not change once extent_io_tree_release is + * called. + */ + smp_mb(); + while (!RB_EMPTY_ROOT(&tree->state)) { + struct rb_node *node; + struct extent_state *state; + + node = rb_first(&tree->state); + state = rb_entry(node, struct extent_state, rb_node); + rb_erase(&state->rb_node, &tree->state); + RB_CLEAR_NODE(&state->rb_node); + /* + * btree io trees aren't supposed to have tasks waiting for + * changes in the flags of extent states ever. + */ + ASSERT(!waitqueue_active(&state->wq)); + free_extent_state(state); + + cond_resched_lock(&tree->lock); + } + spin_unlock(&tree->lock); } static struct extent_state *alloc_extent_state(gfp_t mask) @@ -400,7 +447,7 @@ static void merge_state(struct extent_io_tree *tree, struct extent_state *other; struct rb_node *other_node; - if (state->state & (EXTENT_IOBITS | EXTENT_BOUNDARY)) + if (state->state & (EXTENT_LOCKED | EXTENT_BOUNDARY)) return; other_node = rb_prev(&state->rb_node); @@ -611,6 +658,7 @@ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int clear = 0; btrfs_debug_check_extent_io_range(tree, start, end); + trace_btrfs_clear_extent_bit(tree, start, end - start + 1, bits); if (bits & EXTENT_DELALLOC) bits |= EXTENT_NORESERVE; @@ -618,7 +666,7 @@ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, if (delete) bits |= ~EXTENT_CTLBITS; - if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY)) + if (bits & (EXTENT_LOCKED | EXTENT_BOUNDARY)) clear = 1; again: if (!prealloc && gfpflags_allow_blocking(mask)) { @@ -850,7 +898,7 @@ static void cache_state(struct extent_state *state, struct extent_state **cached_ptr) { return cache_state_if_flags(state, cached_ptr, - EXTENT_IOBITS | EXTENT_BOUNDARY); + EXTENT_LOCKED | EXTENT_BOUNDARY); } /* @@ -880,6 +928,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u64 last_end; btrfs_debug_check_extent_io_range(tree, start, end); + trace_btrfs_set_extent_bit(tree, start, end - start + 1, bits); again: if (!prealloc && gfpflags_allow_blocking(mask)) { @@ -1112,6 +1161,8 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, bool first_iteration = true; btrfs_debug_check_extent_io_range(tree, start, end); + trace_btrfs_convert_extent_bit(tree, start, end - start + 1, bits, + clear_bits); again: if (!prealloc) { @@ -1311,6 +1362,13 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, changeset); } +int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits) +{ + return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, + GFP_NOWAIT, NULL); +} + int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, int wake, int delete, struct extent_state **cached) @@ -1478,6 +1536,79 @@ out: return ret; } +/** + * find_first_clear_extent_bit - finds the first range that has @bits not set + * and that starts after @start + * + * @tree - the tree to search + * @start - the offset at/after which the found extent should start + * @start_ret - records the beginning of the range + * @end_ret - records the end of the range (inclusive) + * @bits - the set of bits which must be unset + * + * Since unallocated range is also considered one which doesn't have the bits + * set it's possible that @end_ret contains -1, this happens in case the range + * spans (last_range_end, end of device]. In this case it's up to the caller to + * trim @end_ret to the appropriate size. + */ +void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start, + u64 *start_ret, u64 *end_ret, unsigned bits) +{ + struct extent_state *state; + struct rb_node *node, *prev = NULL, *next; + + spin_lock(&tree->lock); + + /* Find first extent with bits cleared */ + while (1) { + node = __etree_search(tree, start, &next, &prev, NULL, NULL); + if (!node) { + node = next; + if (!node) { + /* + * We are past the last allocated chunk, + * set start at the end of the last extent. The + * device alloc tree should never be empty so + * prev is always set. + */ + ASSERT(prev); + state = rb_entry(prev, struct extent_state, rb_node); + *start_ret = state->end + 1; + *end_ret = -1; + goto out; + } + } + state = rb_entry(node, struct extent_state, rb_node); + if (in_range(start, state->start, state->end - state->start + 1) && + (state->state & bits)) { + start = state->end + 1; + } else { + *start_ret = start; + break; + } + } + + /* + * Find the longest stretch from start until an entry which has the + * bits set + */ + while (1) { + state = rb_entry(node, struct extent_state, rb_node); + if (state->end >= start && !(state->state & bits)) { + *end_ret = state->end; + } else { + *end_ret = state->start - 1; + break; + } + + node = rb_next(node); + if (!node) + break; + } +out: + spin_unlock(&tree->lock); +} + /* * find a contiguous range of bytes in the file marked as delalloc, not * more than 'max_bytes'. start and end are used to return the range, @@ -2061,9 +2192,9 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, return 0; } -int repair_eb_io_failure(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int mirror_num) +int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num) { + struct btrfs_fs_info *fs_info = eb->fs_info; u64 start = eb->start; int i, num_pages = num_extent_pages(eb); int ret = 0; @@ -2409,7 +2540,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, read_mode, failrec->this_mirror, failrec->in_validation); status = tree->ops->submit_bio_hook(tree->private_data, bio, failrec->this_mirror, - failrec->bio_flags, 0); + failrec->bio_flags); if (status) { free_io_failure(failure_tree, tree, failrec); bio_put(bio); @@ -2451,11 +2582,10 @@ static void end_bio_extent_writepage(struct bio *bio) struct bio_vec *bvec; u64 start; u64 end; - int i; struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -2523,11 +2653,10 @@ static void end_bio_extent_readpage(struct bio *bio) u64 extent_len = 0; int mirror; int ret; - int i; struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -2607,8 +2736,6 @@ static void end_bio_extent_readpage(struct bio *bio) if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) btree_readahead_hook(eb, -EIO); - - ret = -EIO; } readpage_ok: if (likely(uptodate)) { @@ -3069,7 +3196,7 @@ out: return ret; } -static inline void __do_contiguous_readpages(struct extent_io_tree *tree, +static inline void contiguous_readpages(struct extent_io_tree *tree, struct page *pages[], int nr_pages, u64 start, u64 end, struct extent_map **em_cached, @@ -3100,46 +3227,6 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, } } -static void __extent_readpages(struct extent_io_tree *tree, - struct page *pages[], - int nr_pages, - struct extent_map **em_cached, - struct bio **bio, unsigned long *bio_flags, - u64 *prev_em_start) -{ - u64 start = 0; - u64 end = 0; - u64 page_start; - int index; - int first_index = 0; - - for (index = 0; index < nr_pages; index++) { - page_start = page_offset(pages[index]); - if (!end) { - start = page_start; - end = start + PAGE_SIZE - 1; - first_index = index; - } else if (end + 1 == page_start) { - end += PAGE_SIZE; - } else { - __do_contiguous_readpages(tree, &pages[first_index], - index - first_index, start, - end, em_cached, - bio, bio_flags, - prev_em_start); - start = page_start; - end = start + PAGE_SIZE - 1; - first_index = index; - } - } - - if (end) - __do_contiguous_readpages(tree, &pages[first_index], - index - first_index, start, - end, em_cached, bio, - bio_flags, prev_em_start); -} - static int __extent_read_full_page(struct extent_io_tree *tree, struct page *page, get_extent_t *get_extent, @@ -3419,6 +3506,9 @@ done: * records are inserted to lock ranges in the tree, and as dirty areas * are found, they are marked writeback. Then the lock bits are removed * and the end_io handler clears the writeback ranges + * + * Return 0 if everything goes well. + * Return <0 for error. */ static int __extent_writepage(struct page *page, struct writeback_control *wbc, struct extent_page_data *epd) @@ -3488,6 +3578,7 @@ done: end_extent_writepage(page, ret, start, page_end); } unlock_page(page); + ASSERT(ret <= 0); return ret; done_unlocked: @@ -3500,18 +3591,26 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb) TASK_UNINTERRUPTIBLE); } -static noinline_for_stack int -lock_extent_buffer_for_io(struct extent_buffer *eb, - struct btrfs_fs_info *fs_info, +/* + * Lock eb pages and flush the bio if we can't the locks + * + * Return 0 if nothing went wrong + * Return >0 is same as 0, except bio is not submitted + * Return <0 if something went wrong, no page is locked + */ +static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb, struct extent_page_data *epd) { - int i, num_pages; + struct btrfs_fs_info *fs_info = eb->fs_info; + int i, num_pages, failed_page_nr; int flush = 0; int ret = 0; if (!btrfs_try_tree_write_lock(eb)) { + ret = flush_write_bio(epd); + if (ret < 0) + return ret; flush = 1; - flush_write_bio(epd); btrfs_tree_lock(eb); } @@ -3520,7 +3619,9 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, if (!epd->sync_io) return 0; if (!flush) { - flush_write_bio(epd); + ret = flush_write_bio(epd); + if (ret < 0) + return ret; flush = 1; } while (1) { @@ -3561,7 +3662,11 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, if (!trylock_page(p)) { if (!flush) { - flush_write_bio(epd); + ret = flush_write_bio(epd); + if (ret < 0) { + failed_page_nr = i; + goto err_unlock; + } flush = 1; } lock_page(p); @@ -3569,6 +3674,11 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, } return ret; +err_unlock: + /* Unlock already locked pages */ + for (i = 0; i < failed_page_nr; i++) + unlock_page(eb->pages[i]); + return ret; } static void end_extent_buffer_writeback(struct extent_buffer *eb) @@ -3643,11 +3753,11 @@ static void end_bio_extent_buffer_writepage(struct bio *bio) { struct bio_vec *bvec; struct extent_buffer *eb; - int i, done; + int done; struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; eb = (struct extent_buffer *)page->private; @@ -3672,10 +3782,10 @@ static void end_bio_extent_buffer_writepage(struct bio *bio) } static noinline_for_stack int write_one_eb(struct extent_buffer *eb, - struct btrfs_fs_info *fs_info, struct writeback_control *wbc, struct extent_page_data *epd) { + struct btrfs_fs_info *fs_info = eb->fs_info; struct block_device *bdev = fs_info->fs_devices->latest_bdev; struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree; u64 offset = eb->start; @@ -3701,7 +3811,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, * header 0 1 2 .. N ... data_N .. data_2 data_1 data_0 */ start = btrfs_item_nr_offset(nritems); - end = BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, eb); + end = BTRFS_LEAF_DATA_OFFSET + leaf_data_end(eb); memzero_extent_buffer(eb, start, end - start); } @@ -3744,7 +3854,6 @@ int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc) { struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree; - struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info; struct extent_buffer *eb, *prev_eb = NULL; struct extent_page_data epd = { .bio = NULL, @@ -3819,13 +3928,13 @@ retry: continue; prev_eb = eb; - ret = lock_extent_buffer_for_io(eb, fs_info, &epd); + ret = lock_extent_buffer_for_io(eb, &epd); if (!ret) { free_extent_buffer(eb); continue; } - ret = write_one_eb(eb, fs_info, wbc, &epd); + ret = write_one_eb(eb, wbc, &epd); if (ret) { done = 1; free_extent_buffer(eb); @@ -3852,7 +3961,12 @@ retry: index = 0; goto retry; } - flush_write_bio(&epd); + ASSERT(ret <= 0); + if (ret < 0) { + end_write_bio(&epd, ret); + return ret; + } + ret = flush_write_bio(&epd); return ret; } @@ -3949,7 +4063,8 @@ retry: * tmpfs file mapping */ if (!trylock_page(page)) { - flush_write_bio(epd); + ret = flush_write_bio(epd); + BUG_ON(ret < 0); lock_page(page); } @@ -3959,8 +4074,10 @@ retry: } if (wbc->sync_mode != WB_SYNC_NONE) { - if (PageWriteback(page)) - flush_write_bio(epd); + if (PageWriteback(page)) { + ret = flush_write_bio(epd); + BUG_ON(ret < 0); + } wait_on_page_writeback(page); } @@ -3971,11 +4088,6 @@ retry: } ret = __extent_writepage(page, wbc, epd); - - if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) { - unlock_page(page); - ret = 0; - } if (ret < 0) { /* * done_index is set past this page, @@ -4029,8 +4141,14 @@ int extent_write_full_page(struct page *page, struct writeback_control *wbc) }; ret = __extent_writepage(page, wbc, &epd); + ASSERT(ret <= 0); + if (ret < 0) { + end_write_bio(&epd, ret); + return ret; + } - flush_write_bio(&epd); + ret = flush_write_bio(&epd); + ASSERT(ret <= 0); return ret; } @@ -4070,7 +4188,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end, start += PAGE_SIZE; } - flush_write_bio(&epd); + ASSERT(ret <= 0); + if (ret < 0) { + end_write_bio(&epd, ret); + return ret; + } + ret = flush_write_bio(&epd); return ret; } @@ -4086,7 +4209,12 @@ int extent_writepages(struct address_space *mapping, }; ret = extent_write_cache_pages(mapping, wbc, &epd); - flush_write_bio(&epd); + ASSERT(ret <= 0); + if (ret < 0) { + end_write_bio(&epd, ret); + return ret; + } + ret = flush_write_bio(&epd); return ret; } @@ -4102,6 +4230,8 @@ int extent_readpages(struct address_space *mapping, struct list_head *pages, u64 prev_em_start = (u64)-1; while (!list_empty(pages)) { + u64 contig_end = 0; + for (nr = 0; nr < ARRAY_SIZE(pagepool) && !list_empty(pages);) { struct page *page = lru_to_page(pages); @@ -4110,14 +4240,22 @@ int extent_readpages(struct address_space *mapping, struct list_head *pages, if (add_to_page_cache_lru(page, mapping, page->index, readahead_gfp_mask(mapping))) { put_page(page); - continue; + break; } pagepool[nr++] = page; + contig_end = page_offset(page) + PAGE_SIZE - 1; } - __extent_readpages(tree, pagepool, nr, &em_cached, &bio, - &bio_flags, &prev_em_start); + if (nr) { + u64 contig_start = page_offset(pagepool[0]); + + ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end); + + contiguous_readpages(tree, pagepool, nr, contig_start, + contig_end, &em_cached, &bio, &bio_flags, + &prev_em_start); + } } if (em_cached) @@ -4166,10 +4304,9 @@ static int try_release_extent_state(struct extent_io_tree *tree, u64 end = start + PAGE_SIZE - 1; int ret = 1; - if (test_range_bit(tree, start, end, - EXTENT_IOBITS, 0, NULL)) + if (test_range_bit(tree, start, end, EXTENT_LOCKED, 0, NULL)) { ret = 0; - else { + } else { /* * at this point we can safely clear everything except the * locked bit and the nodatasum bit @@ -4222,8 +4359,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) } if (!test_range_bit(tree, em->start, extent_map_end(em) - 1, - EXTENT_LOCKED | EXTENT_WRITEBACK, - 0, NULL)) { + EXTENT_LOCKED, 0, NULL)) { set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &btrfs_inode->runtime_flags); remove_extent_mapping(map, em); @@ -4372,8 +4508,7 @@ try_submit_last: * In this case, the first extent range will be cached but not emitted. * So we must emit it before ending extent_fiemap(). */ -static int emit_last_fiemap_cache(struct btrfs_fs_info *fs_info, - struct fiemap_extent_info *fieinfo, +static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo, struct fiemap_cache *cache) { int ret; @@ -4580,7 +4715,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } out_free: if (!ret) - ret = emit_last_fiemap_cache(root->fs_info, fieinfo, &cache); + ret = emit_last_fiemap_cache(fieinfo, &cache); free_extent_map(em); out: btrfs_free_path(path); @@ -4672,13 +4807,9 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, eb->fs_info = fs_info; eb->bflags = 0; rwlock_init(&eb->lock); - atomic_set(&eb->write_locks, 0); - atomic_set(&eb->read_locks, 0); atomic_set(&eb->blocking_readers, 0); atomic_set(&eb->blocking_writers, 0); - atomic_set(&eb->spinning_readers, 0); - atomic_set(&eb->spinning_writers, 0); - eb->lock_nested = 0; + eb->lock_nested = false; init_waitqueue_head(&eb->write_lock_wq); init_waitqueue_head(&eb->read_lock_wq); @@ -4695,6 +4826,13 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, > MAX_INLINE_EXTENT_BUFFER_SIZE); BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE); +#ifdef CONFIG_BTRFS_DEBUG + atomic_set(&eb->spinning_writers, 0); + atomic_set(&eb->spinning_readers, 0); + atomic_set(&eb->read_locks, 0); + atomic_set(&eb->write_locks, 0); +#endif + return eb; } @@ -5183,8 +5321,7 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb) } } -int read_extent_buffer_pages(struct extent_io_tree *tree, - struct extent_buffer *eb, int wait, int mirror_num) +int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) { int i; struct page *page; @@ -5196,6 +5333,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, unsigned long num_reads = 0; struct bio *bio = NULL; unsigned long bio_flags = 0; + struct extent_io_tree *tree = &BTRFS_I(eb->fs_info->btree_inode)->io_tree; if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; @@ -5746,13 +5884,13 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, btrfs_err(fs_info, "memmove bogus src_offset %lu move len %lu dst len %lu", src_offset, len, dst->len); - BUG_ON(1); + BUG(); } if (dst_offset + len > dst->len) { btrfs_err(fs_info, "memmove bogus dst_offset %lu move len %lu dst len %lu", dst_offset, len, dst->len); - BUG_ON(1); + BUG(); } while (len > 0) { @@ -5793,13 +5931,13 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, btrfs_err(fs_info, "memmove bogus src_offset %lu move len %lu len %lu", src_offset, len, dst->len); - BUG_ON(1); + BUG(); } if (dst_offset + len > dst->len) { btrfs_err(fs_info, "memmove bogus dst_offset %lu move len %lu len %lu", dst_offset, len, dst->len); - BUG_ON(1); + BUG(); } if (dst_offset < src_offset) { memcpy_extent_buffer(dst, dst_offset, src_offset, len); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 08749e0b9c32..aa18a16a6ed7 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -9,27 +9,34 @@ /* bits for the extent state */ #define EXTENT_DIRTY (1U << 0) -#define EXTENT_WRITEBACK (1U << 1) -#define EXTENT_UPTODATE (1U << 2) -#define EXTENT_LOCKED (1U << 3) -#define EXTENT_NEW (1U << 4) -#define EXTENT_DELALLOC (1U << 5) -#define EXTENT_DEFRAG (1U << 6) -#define EXTENT_BOUNDARY (1U << 9) -#define EXTENT_NODATASUM (1U << 10) -#define EXTENT_CLEAR_META_RESV (1U << 11) -#define EXTENT_NEED_WAIT (1U << 12) -#define EXTENT_DAMAGED (1U << 13) -#define EXTENT_NORESERVE (1U << 14) -#define EXTENT_QGROUP_RESERVED (1U << 15) -#define EXTENT_CLEAR_DATA_RESV (1U << 16) -#define EXTENT_DELALLOC_NEW (1U << 17) -#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) +#define EXTENT_UPTODATE (1U << 1) +#define EXTENT_LOCKED (1U << 2) +#define EXTENT_NEW (1U << 3) +#define EXTENT_DELALLOC (1U << 4) +#define EXTENT_DEFRAG (1U << 5) +#define EXTENT_BOUNDARY (1U << 6) +#define EXTENT_NODATASUM (1U << 7) +#define EXTENT_CLEAR_META_RESV (1U << 8) +#define EXTENT_NEED_WAIT (1U << 9) +#define EXTENT_DAMAGED (1U << 10) +#define EXTENT_NORESERVE (1U << 11) +#define EXTENT_QGROUP_RESERVED (1U << 12) +#define EXTENT_CLEAR_DATA_RESV (1U << 13) +#define EXTENT_DELALLOC_NEW (1U << 14) #define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \ EXTENT_CLEAR_DATA_RESV) #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING) /* + * Redefined bits above which are used only in the device allocation tree, + * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV + * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit + * manipulation functions + */ +#define CHUNK_ALLOCATED EXTENT_DIRTY +#define CHUNK_TRIMMED EXTENT_DEFRAG + +/* * flags for bio submission. The high bits indicate the compression * type for this bio */ @@ -88,9 +95,6 @@ struct btrfs_inode; struct btrfs_io_bio; struct io_failure_record; -typedef blk_status_t (extent_submit_bio_hook_t)(void *private_data, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset); typedef blk_status_t (extent_submit_bio_start_t)(void *private_data, struct bio *bio, u64 bio_offset); @@ -100,17 +104,34 @@ struct extent_io_ops { * The following callbacks must be always defined, the function * pointer will be called unconditionally. */ - extent_submit_bio_hook_t *submit_bio_hook; + blk_status_t (*submit_bio_hook)(struct inode *inode, struct bio *bio, + int mirror_num, unsigned long bio_flags); int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset, struct page *page, u64 start, u64 end, int mirror); }; +enum { + IO_TREE_FS_INFO_FREED_EXTENTS0, + IO_TREE_FS_INFO_FREED_EXTENTS1, + IO_TREE_INODE_IO, + IO_TREE_INODE_IO_FAILURE, + IO_TREE_RELOC_BLOCKS, + IO_TREE_TRANS_DIRTY_PAGES, + IO_TREE_ROOT_DIRTY_LOG_PAGES, + IO_TREE_SELFTEST, +}; + struct extent_io_tree { struct rb_root state; + struct btrfs_fs_info *fs_info; void *private_data; u64 dirty_bytes; - int track_uptodate; + bool track_uptodate; + + /* Who owns this io tree, should be one of IO_TREE_* */ + u8 owner; + spinlock_t lock; const struct extent_io_ops *ops; }; @@ -146,14 +167,9 @@ struct extent_buffer { struct rcu_head rcu_head; pid_t lock_owner; - /* count of read lock holders on the extent buffer */ - atomic_t write_locks; - atomic_t read_locks; atomic_t blocking_writers; atomic_t blocking_readers; - atomic_t spinning_readers; - atomic_t spinning_writers; - short lock_nested; + bool lock_nested; /* >= 0 if eb belongs to a log tree, -1 otherwise */ short log_index; @@ -171,6 +187,10 @@ struct extent_buffer { wait_queue_head_t read_lock_wq; struct page *pages[INLINE_EXTENT_BUFFER_PAGES]; #ifdef CONFIG_BTRFS_DEBUG + atomic_t spinning_writers; + atomic_t spinning_readers; + atomic_t read_locks; + atomic_t write_locks; struct list_head leak_list; #endif }; @@ -239,7 +259,10 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode, u64 start, u64 len, int create); -void extent_io_tree_init(struct extent_io_tree *tree, void *private_data); +void extent_io_tree_init(struct btrfs_fs_info *fs_info, + struct extent_io_tree *tree, unsigned int owner, + void *private_data); +void extent_io_tree_release(struct extent_io_tree *tree); int try_release_extent_mapping(struct page *page, gfp_t mask); int try_release_extent_buffer(struct page *page); int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, @@ -309,6 +332,8 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, u64 *failed_start, struct extent_state **cached_state, gfp_t mask); +int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits); static inline int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits) @@ -376,6 +401,8 @@ static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start, int find_first_extent_bit(struct extent_io_tree *tree, u64 start, u64 *start_ret, u64 *end_ret, unsigned bits, struct extent_state **cached_state); +void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start, + u64 *start_ret, u64 *end_ret, unsigned bits); int extent_invalidatepage(struct extent_io_tree *tree, struct page *page, unsigned long offset); int extent_write_full_page(struct page *page, struct writeback_control *wbc); @@ -405,8 +432,7 @@ void free_extent_buffer_stale(struct extent_buffer *eb); #define WAIT_NONE 0 #define WAIT_COMPLETE 1 #define WAIT_PAGE_LOCK 2 -int read_extent_buffer_pages(struct extent_io_tree *tree, - struct extent_buffer *eb, int wait, +int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num); void wait_on_extent_buffer_writeback(struct extent_buffer *eb); @@ -487,8 +513,7 @@ int clean_io_failure(struct btrfs_fs_info *fs_info, struct extent_io_tree *io_tree, u64 start, struct page *page, u64 ino, unsigned int pg_offset); void end_extent_writepage(struct page *page, int err, u64 start, u64 end); -int repair_eb_io_failure(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int mirror_num); +int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num); /* * When IO fails, either with EIO or csum verification fails, we diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 928f729c55ba..9558d79faf1e 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -4,6 +4,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include "ctree.h" +#include "volumes.h" #include "extent_map.h" #include "compression.h" @@ -337,6 +338,37 @@ static inline void setup_extent_mapping(struct extent_map_tree *tree, try_merge_map(tree, em); } +static void extent_map_device_set_bits(struct extent_map *em, unsigned bits) +{ + struct map_lookup *map = em->map_lookup; + u64 stripe_size = em->orig_block_len; + int i; + + for (i = 0; i < map->num_stripes; i++) { + struct btrfs_bio_stripe *stripe = &map->stripes[i]; + struct btrfs_device *device = stripe->dev; + + set_extent_bits_nowait(&device->alloc_state, stripe->physical, + stripe->physical + stripe_size - 1, bits); + } +} + +static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits) +{ + struct map_lookup *map = em->map_lookup; + u64 stripe_size = em->orig_block_len; + int i; + + for (i = 0; i < map->num_stripes; i++) { + struct btrfs_bio_stripe *stripe = &map->stripes[i]; + struct btrfs_device *device = stripe->dev; + + __clear_extent_bit(&device->alloc_state, stripe->physical, + stripe->physical + stripe_size - 1, bits, + 0, 0, NULL, GFP_NOWAIT, NULL); + } +} + /** * add_extent_mapping - add new extent map to the extent tree * @tree: tree to insert new map in @@ -357,6 +389,10 @@ int add_extent_mapping(struct extent_map_tree *tree, goto out; setup_extent_mapping(tree, em, modified); + if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags)) { + extent_map_device_set_bits(em, CHUNK_ALLOCATED); + extent_map_device_clear_bits(em, CHUNK_TRIMMED); + } out: return ret; } @@ -438,6 +474,8 @@ void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em) rb_erase_cached(&em->rb_node, &tree->map); if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags)) list_del_init(&em->list); + if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags)) + extent_map_device_clear_bits(em, CHUNK_ALLOCATED); RB_CLEAR_NODE(&em->rb_node); } diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 920bf3b4b0ef..d431ea8198e4 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -7,6 +7,7 @@ #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/highmem.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -412,6 +413,16 @@ fail: return ret; } +/* + * btrfs_csum_one_bio - Calculates checksums of the data contained inside a bio + * @inode: Owner of the data inside the bio + * @bio: Contains the data to be checksummed + * @file_start: offset in file this bio begins to describe + * @contig: Boolean. If true/1 means all bio vecs in this bio are + * contiguous and they begin at @file_start in the file. False/0 + * means this bio can contains potentially discontigous bio vecs + * so the logical offset of each should be calculated separately. + */ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, u64 file_start, int contig) { @@ -427,9 +438,13 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, unsigned long this_sum_bytes = 0; int i; u64 offset; + unsigned nofs_flag; + + nofs_flag = memalloc_nofs_save(); + sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), + GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); - sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), - GFP_NOFS); if (!sums) return BLK_STS_RESOURCE; @@ -453,8 +468,6 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, BUG_ON(!ordered); /* Logic error */ } - data = kmap_atomic(bvec.bv_page); - nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len + fs_info->sectorsize - 1); @@ -464,16 +477,17 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, offset < ordered->file_offset) { unsigned long bytes_left; - kunmap_atomic(data); sums->len = this_sum_bytes; this_sum_bytes = 0; - btrfs_add_ordered_sum(inode, ordered, sums); + btrfs_add_ordered_sum(ordered, sums); btrfs_put_ordered_extent(ordered); bytes_left = bio->bi_iter.bi_size - total_bytes; - sums = kzalloc(btrfs_ordered_sum_size(fs_info, bytes_left), - GFP_NOFS); + nofs_flag = memalloc_nofs_save(); + sums = kvzalloc(btrfs_ordered_sum_size(fs_info, + bytes_left), GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); BUG_ON(!sums); /* -ENOMEM */ sums->len = bytes_left; ordered = btrfs_lookup_ordered_extent(inode, @@ -482,16 +496,16 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) + total_bytes; index = 0; - - data = kmap_atomic(bvec.bv_page); } sums->sums[index] = ~(u32)0; + data = kmap_atomic(bvec.bv_page); sums->sums[index] = btrfs_csum_data(data + bvec.bv_offset + (i * fs_info->sectorsize), sums->sums[index], fs_info->sectorsize); + kunmap_atomic(data); btrfs_csum_final(sums->sums[index], (char *)(sums->sums + index)); index++; @@ -500,10 +514,9 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, total_bytes += fs_info->sectorsize; } - kunmap_atomic(data); } this_sum_bytes = 0; - btrfs_add_ordered_sum(inode, ordered, sums); + btrfs_add_ordered_sum(ordered, sums); btrfs_put_ordered_extent(ordered); return 0; } @@ -544,7 +557,7 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, */ u32 new_size = (bytenr - key->offset) >> blocksize_bits; new_size *= csum_size; - btrfs_truncate_item(fs_info, path, new_size, 1); + btrfs_truncate_item(path, new_size, 1); } else if (key->offset >= bytenr && csum_end > end_byte && end_byte > key->offset) { /* @@ -556,7 +569,7 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, u32 new_size = (csum_end - end_byte) >> blocksize_bits; new_size *= csum_size; - btrfs_truncate_item(fs_info, path, new_size, 0); + btrfs_truncate_item(path, new_size, 0); key->offset = end_byte; btrfs_set_item_key_safe(fs_info, path, key); @@ -825,11 +838,11 @@ again: u32 diff; u32 free_space; - if (btrfs_leaf_free_space(fs_info, leaf) < + if (btrfs_leaf_free_space(leaf) < sizeof(struct btrfs_item) + csum_size * 2) goto insert; - free_space = btrfs_leaf_free_space(fs_info, leaf) - + free_space = btrfs_leaf_free_space(leaf) - sizeof(struct btrfs_item) - csum_size; tmp = sums->len - total_bytes; tmp >>= fs_info->sb->s_blocksize_bits; @@ -845,7 +858,7 @@ again: diff /= csum_size; diff *= csum_size; - btrfs_extend_item(fs_info, path, diff); + btrfs_extend_item(path, diff); ret = 0; goto csum; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 34fe8a58b0e9..7e85dca0e6f2 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -754,6 +754,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; + struct btrfs_ref ref = { 0 }; struct btrfs_key key; struct btrfs_key new_key; u64 ino = btrfs_ino(BTRFS_I(inode)); @@ -909,11 +910,14 @@ next_slot: btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) { - ret = btrfs_inc_extent_ref(trans, root, - disk_bytenr, num_bytes, 0, + btrfs_init_generic_ref(&ref, + BTRFS_ADD_DELAYED_REF, + disk_bytenr, num_bytes, 0); + btrfs_init_data_ref(&ref, root->root_key.objectid, new_key.objectid, start - extent_offset); + ret = btrfs_inc_extent_ref(trans, &ref); BUG_ON(ret); /* -ENOMEM */ } key.offset = start; @@ -993,11 +997,14 @@ delete_extent_item: extent_end = ALIGN(extent_end, fs_info->sectorsize); } else if (update_refs && disk_bytenr > 0) { - ret = btrfs_free_extent(trans, root, - disk_bytenr, num_bytes, 0, + btrfs_init_generic_ref(&ref, + BTRFS_DROP_DELAYED_REF, + disk_bytenr, num_bytes, 0); + btrfs_init_data_ref(&ref, root->root_key.objectid, - key.objectid, key.offset - - extent_offset); + key.objectid, + key.offset - extent_offset); + ret = btrfs_free_extent(trans, &ref); BUG_ON(ret); /* -ENOMEM */ inode_sub_bytes(inode, extent_end - key.offset); @@ -1025,7 +1032,7 @@ delete_extent_item: continue; } - BUG_ON(1); + BUG(); } if (!ret && del_nr > 0) { @@ -1050,7 +1057,7 @@ delete_extent_item: if (!ret && replace_extent && leafs_visited == 1 && (path->locks[0] == BTRFS_WRITE_LOCK_BLOCKING || path->locks[0] == BTRFS_WRITE_LOCK) && - btrfs_leaf_free_space(fs_info, leaf) >= + btrfs_leaf_free_space(leaf) >= sizeof(struct btrfs_item) + extent_item_size) { key.objectid = ino; @@ -1142,6 +1149,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; struct btrfs_path *path; struct btrfs_file_extent_item *fi; + struct btrfs_ref ref = { 0 }; struct btrfs_key key; struct btrfs_key new_key; u64 bytenr; @@ -1287,9 +1295,11 @@ again: extent_end - split); btrfs_mark_buffer_dirty(leaf); - ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, - 0, root->root_key.objectid, - ino, orig_offset); + btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr, + num_bytes, 0); + btrfs_init_data_ref(&ref, root->root_key.objectid, ino, + orig_offset); + ret = btrfs_inc_extent_ref(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -1311,6 +1321,9 @@ again: other_start = end; other_end = 0; + btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr, + num_bytes, 0); + btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset); if (extent_mergeable(leaf, path->slots[0] + 1, ino, bytenr, orig_offset, &other_start, &other_end)) { @@ -1321,9 +1334,7 @@ again: extent_end = other_end; del_slot = path->slots[0] + 1; del_nr++; - ret = btrfs_free_extent(trans, root, bytenr, num_bytes, - 0, root->root_key.objectid, - ino, orig_offset); + ret = btrfs_free_extent(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -1341,9 +1352,7 @@ again: key.offset = other_start; del_slot = path->slots[0]; del_nr++; - ret = btrfs_free_extent(trans, root, bytenr, num_bytes, - 0, root->root_key.objectid, - ino, orig_offset); + ret = btrfs_free_extent(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -2165,7 +2174,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) inode_unlock(inode); goto out; } - trans->sync = true; ret = btrfs_log_dentry_safe(trans, dentry, start, end, &ctx); if (ret < 0) { @@ -3132,6 +3140,7 @@ static long btrfs_fallocate(struct file *file, int mode, ret = btrfs_qgroup_reserve_data(inode, &data_reserved, cur_offset, last_byte - cur_offset); if (ret < 0) { + cur_offset = last_byte; free_extent_map(em); break; } @@ -3181,7 +3190,7 @@ out: /* Let go of our reservation. */ if (ret != 0 && !(mode & FALLOC_FL_ZERO_RANGE)) btrfs_free_reserved_data_space(inode, data_reserved, - alloc_start, alloc_end - cur_offset); + cur_offset, alloc_end - cur_offset); extent_changeset_free(data_reserved); return ret; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 74aa552f4793..f74dc259307b 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -88,10 +88,11 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, return inode; } -struct inode *lookup_free_space_inode(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache - *block_group, struct btrfs_path *path) +struct inode *lookup_free_space_inode( + struct btrfs_block_group_cache *block_group, + struct btrfs_path *path) { + struct btrfs_fs_info *fs_info = block_group->fs_info; struct inode *inode = NULL; u32 flags = BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW; @@ -185,20 +186,19 @@ static int __create_free_space_inode(struct btrfs_root *root, return 0; } -int create_free_space_inode(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, +int create_free_space_inode(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path) { int ret; u64 ino; - ret = btrfs_find_free_objectid(fs_info->tree_root, &ino); + ret = btrfs_find_free_objectid(trans->fs_info->tree_root, &ino); if (ret < 0) return ret; - return __create_free_space_inode(fs_info->tree_root, trans, path, ino, - block_group->key.objectid); + return __create_free_space_inode(trans->fs_info->tree_root, trans, path, + ino, block_group->key.objectid); } int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, @@ -812,9 +812,9 @@ free_cache: goto out; } -int load_free_space_cache(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *block_group) +int load_free_space_cache(struct btrfs_block_group_cache *block_group) { + struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct inode *inode; struct btrfs_path *path; @@ -858,7 +858,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, * once created get their ->cached field set to BTRFS_CACHE_FINISHED so * we will never try to read their inode item while the fs is mounted. */ - inode = lookup_free_space_inode(fs_info, block_group, path); + inode = lookup_free_space_inode(block_group, path); if (IS_ERR(inode)) { btrfs_free_path(path); return 0; @@ -1039,8 +1039,7 @@ fail: return -1; } -static noinline_for_stack int -write_pinned_extent_entries(struct btrfs_fs_info *fs_info, +static noinline_for_stack int write_pinned_extent_entries( struct btrfs_block_group_cache *block_group, struct btrfs_io_ctl *io_ctl, int *entries) @@ -1059,7 +1058,7 @@ write_pinned_extent_entries(struct btrfs_fs_info *fs_info, * We shouldn't have switched the pinned extents yet so this is the * right one */ - unpin = fs_info->pinned_extents; + unpin = block_group->fs_info->pinned_extents; start = block_group->key.objectid; @@ -1235,7 +1234,6 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, struct btrfs_io_ctl *io_ctl, struct btrfs_trans_handle *trans) { - struct btrfs_fs_info *fs_info = root->fs_info; struct extent_state *cached_state = NULL; LIST_HEAD(bitmap_list); int entries = 0; @@ -1293,8 +1291,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, * If this changes while we are working we'll get added back to * the dirty list and redo it. No locking needed */ - ret = write_pinned_extent_entries(fs_info, block_group, - io_ctl, &entries); + ret = write_pinned_extent_entries(block_group, io_ctl, &entries); if (ret) goto out_nospc_locked; @@ -1370,11 +1367,11 @@ out_unlock: goto out; } -int btrfs_write_out_cache(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, +int btrfs_write_out_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct inode *inode; int ret = 0; @@ -1386,7 +1383,7 @@ int btrfs_write_out_cache(struct btrfs_fs_info *fs_info, } spin_unlock(&block_group->lock); - inode = lookup_free_space_inode(fs_info, block_group, path); + inode = lookup_free_space_inode(block_group, path); if (IS_ERR(inode)) return 0; @@ -3040,11 +3037,11 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group, * returns zero and sets up cluster if things worked out, otherwise * it returns -enospc */ -int btrfs_find_space_cluster(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *block_group, +int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 empty_size) { + struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry, *tmp; LIST_HEAD(bitmaps); @@ -3366,10 +3363,6 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group) em = lookup_extent_mapping(em_tree, block_group->key.objectid, 1); BUG_ON(!em); /* logic error, can't happen */ - /* - * remove_extent_mapping() will delete us from the pinned_chunks - * list, which is protected by the chunk mutex. - */ remove_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); mutex_unlock(&fs_info->chunk_mutex); diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 15e30b93db0d..8760acb55ffd 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -38,11 +38,10 @@ struct btrfs_free_space_op { struct btrfs_io_ctl; -struct inode *lookup_free_space_inode(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache - *block_group, struct btrfs_path *path); -int create_free_space_inode(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, +struct inode *lookup_free_space_inode( + struct btrfs_block_group_cache *block_group, + struct btrfs_path *path); +int create_free_space_inode(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path); @@ -51,13 +50,11 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct inode *inode); -int load_free_space_cache(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *block_group); +int load_free_space_cache(struct btrfs_block_group_cache *block_group); int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path); -int btrfs_write_out_cache(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, +int btrfs_write_out_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path); struct inode *lookup_free_ino_inode(struct btrfs_root *root, @@ -95,8 +92,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root); void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, u64 bytes); -int btrfs_find_space_cluster(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *block_group, +int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 empty_size); void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index e5089087eaa6..f5dc115ebba0 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -76,10 +76,11 @@ out: EXPORT_FOR_TESTS struct btrfs_free_space_info *search_free_space_info( - struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path, int cow) { + struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *root = fs_info->free_space_root; struct btrfs_key key; int ret; @@ -253,7 +254,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, btrfs_release_path(path); } - info = search_free_space_info(trans, fs_info, block_group, path, 1); + info = search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; @@ -398,7 +399,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, btrfs_release_path(path); } - info = search_free_space_info(trans, fs_info, block_group, path, 1); + info = search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; @@ -463,8 +464,7 @@ static int update_free_space_extent_count(struct btrfs_trans_handle *trans, if (new_extents == 0) return 0; - info = search_free_space_info(trans, trans->fs_info, block_group, path, - 1); + info = search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; @@ -793,8 +793,7 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans, return ret; } - info = search_free_space_info(NULL, trans->fs_info, block_group, path, - 0); + info = search_free_space_info(NULL, block_group, path, 0); if (IS_ERR(info)) return PTR_ERR(info); flags = btrfs_free_space_flags(path->nodes[0], info); @@ -977,7 +976,6 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path, u64 start, u64 size) { - struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_free_space_info *info; u32 flags; int ret; @@ -988,7 +986,7 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans, return ret; } - info = search_free_space_info(NULL, fs_info, block_group, path, 0); + info = search_free_space_info(NULL, block_group, path, 0); if (IS_ERR(info)) return PTR_ERR(info); flags = btrfs_free_space_flags(path->nodes[0], info); @@ -1150,7 +1148,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); - free_space_root = btrfs_create_tree(trans, fs_info, + free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { ret = PTR_ERR(free_space_root); @@ -1248,7 +1246,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) list_del(&free_space_root->dirty_list); btrfs_tree_lock(free_space_root->node); - clean_tree_block(fs_info, free_space_root->node); + btrfs_clean_tree_block(free_space_root->node); btrfs_tree_unlock(free_space_root->node); btrfs_free_tree_block(trans, free_space_root, free_space_root->node, 0, 1); @@ -1534,14 +1532,12 @@ out: int load_free_space_tree(struct btrfs_caching_control *caching_ctl) { struct btrfs_block_group_cache *block_group; - struct btrfs_fs_info *fs_info; struct btrfs_free_space_info *info; struct btrfs_path *path; u32 extent_count, flags; int ret; block_group = caching_ctl->block_group; - fs_info = block_group->fs_info; path = btrfs_alloc_path(); if (!path) @@ -1555,7 +1551,7 @@ int load_free_space_tree(struct btrfs_caching_control *caching_ctl) path->search_commit_root = 1; path->reada = READA_FORWARD; - info = search_free_space_info(NULL, fs_info, block_group, path, 0); + info = search_free_space_info(NULL, block_group, path, 0); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h index 3133651d7d70..22b7602bde25 100644 --- a/fs/btrfs/free-space-tree.h +++ b/fs/btrfs/free-space-tree.h @@ -30,7 +30,6 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans, #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct btrfs_free_space_info * search_free_space_info(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *block_group, struct btrfs_path *path, int cow); int __add_to_free_space_tree(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index a8956a3c9e05..30d62ef918b9 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -170,7 +170,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, memmove_extent_buffer(leaf, ptr, ptr + del_len, item_size - (ptr + del_len - item_start)); - btrfs_truncate_item(root->fs_info, path, item_size - del_len, 1); + btrfs_truncate_item(path, item_size - del_len, 1); out: btrfs_free_path(path); @@ -234,7 +234,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, item_start = btrfs_item_ptr_offset(leaf, path->slots[0]); memmove_extent_buffer(leaf, ptr, ptr + sub_item_len, item_size - (ptr + sub_item_len - item_start)); - btrfs_truncate_item(root->fs_info, path, item_size - sub_item_len, 1); + btrfs_truncate_item(path, item_size - sub_item_len, 1); out: btrfs_free_path(path); @@ -288,7 +288,7 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, name, name_len, NULL)) goto out; - btrfs_extend_item(root->fs_info, path, ins_len); + btrfs_extend_item(path, ins_len); ret = 0; } if (ret < 0) @@ -347,7 +347,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, goto out; old_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]); - btrfs_extend_item(fs_info, path, ins_len); + btrfs_extend_item(path, ins_len); ref = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_ref); ref = (struct btrfs_inode_ref *)((unsigned long)ref + old_size); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 82fdda8ff5ab..9aba9660efe5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -28,6 +28,7 @@ #include <linux/magic.h> #include <linux/iversion.h> #include <linux/swap.h> +#include <linux/sched/mm.h> #include <asm/unaligned.h> #include "ctree.h" #include "disk-io.h" @@ -73,17 +74,6 @@ struct kmem_cache *btrfs_trans_handle_cachep; struct kmem_cache *btrfs_path_cachep; struct kmem_cache *btrfs_free_space_cachep; -#define S_SHIFT 12 -static const unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = { - [S_IFREG >> S_SHIFT] = BTRFS_FT_REG_FILE, - [S_IFDIR >> S_SHIFT] = BTRFS_FT_DIR, - [S_IFCHR >> S_SHIFT] = BTRFS_FT_CHRDEV, - [S_IFBLK >> S_SHIFT] = BTRFS_FT_BLKDEV, - [S_IFIFO >> S_SHIFT] = BTRFS_FT_FIFO, - [S_IFSOCK >> S_SHIFT] = BTRFS_FT_SOCK, - [S_IFLNK >> S_SHIFT] = BTRFS_FT_SYMLINK, -}; - static int btrfs_setsize(struct inode *inode, struct iattr *attr); static int btrfs_truncate(struct inode *inode, bool skip_writeback); static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent); @@ -366,18 +356,24 @@ struct async_extent { struct list_head list; }; -struct async_cow { +struct async_chunk { struct inode *inode; - struct btrfs_fs_info *fs_info; struct page *locked_page; u64 start; u64 end; unsigned int write_flags; struct list_head extents; struct btrfs_work work; + atomic_t *pending; +}; + +struct async_cow { + /* Number of chunks in flight; must be first in the structure */ + atomic_t num_chunks; + struct async_chunk chunks[]; }; -static noinline int add_async_extent(struct async_cow *cow, +static noinline int add_async_extent(struct async_chunk *cow, u64 start, u64 ram_size, u64 compressed_size, struct page **pages, @@ -444,14 +440,14 @@ static inline void inode_should_defrag(struct btrfs_inode *inode, * are written in the same order that the flusher thread sent them * down. */ -static noinline void compress_file_range(struct inode *inode, - struct page *locked_page, - u64 start, u64 end, - struct async_cow *async_cow, - int *num_added) +static noinline void compress_file_range(struct async_chunk *async_chunk, + int *num_added) { + struct inode *inode = async_chunk->inode; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 blocksize = fs_info->sectorsize; + u64 start = async_chunk->start; + u64 end = async_chunk->end; u64 actual_end; int ret = 0; struct page **pages = NULL; @@ -630,7 +626,7 @@ cont: * allocation on disk for these compressed pages, and * will submit them to the elevator. */ - add_async_extent(async_cow, start, total_in, + add_async_extent(async_chunk, start, total_in, total_compressed, pages, nr_pages, compress_type); @@ -670,14 +666,14 @@ cleanup_and_bail_uncompressed: * to our extent and set things up for the async work queue to run * cow_file_range to do the normal delalloc dance. */ - if (page_offset(locked_page) >= start && - page_offset(locked_page) <= end) - __set_page_dirty_nobuffers(locked_page); + if (page_offset(async_chunk->locked_page) >= start && + page_offset(async_chunk->locked_page) <= end) + __set_page_dirty_nobuffers(async_chunk->locked_page); /* unlocked later on in the async handlers */ if (redirty) extent_range_redirty_for_io(inode, start, end); - add_async_extent(async_cow, start, end - start + 1, 0, NULL, 0, + add_async_extent(async_chunk, start, end - start + 1, 0, NULL, 0, BTRFS_COMPRESS_NONE); *num_added += 1; @@ -713,38 +709,34 @@ static void free_async_extent_pages(struct async_extent *async_extent) * queued. We walk all the async extents created by compress_file_range * and send them down to the disk. */ -static noinline void submit_compressed_extents(struct async_cow *async_cow) +static noinline void submit_compressed_extents(struct async_chunk *async_chunk) { - struct inode *inode = async_cow->inode; + struct inode *inode = async_chunk->inode; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct async_extent *async_extent; u64 alloc_hint = 0; struct btrfs_key ins; struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; - struct extent_io_tree *io_tree; + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; int ret = 0; again: - while (!list_empty(&async_cow->extents)) { - async_extent = list_entry(async_cow->extents.next, + while (!list_empty(&async_chunk->extents)) { + async_extent = list_entry(async_chunk->extents.next, struct async_extent, list); list_del(&async_extent->list); - io_tree = &BTRFS_I(inode)->io_tree; - retry: + lock_extent(io_tree, async_extent->start, + async_extent->start + async_extent->ram_size - 1); /* did the compression code fall back to uncompressed IO? */ if (!async_extent->pages) { int page_started = 0; unsigned long nr_written = 0; - lock_extent(io_tree, async_extent->start, - async_extent->start + - async_extent->ram_size - 1); - /* allocate blocks */ - ret = cow_file_range(inode, async_cow->locked_page, + ret = cow_file_range(inode, async_chunk->locked_page, async_extent->start, async_extent->start + async_extent->ram_size - 1, @@ -768,15 +760,12 @@ retry: async_extent->ram_size - 1, WB_SYNC_ALL); else if (ret) - unlock_page(async_cow->locked_page); + unlock_page(async_chunk->locked_page); kfree(async_extent); cond_resched(); continue; } - lock_extent(io_tree, async_extent->start, - async_extent->start + async_extent->ram_size - 1); - ret = btrfs_reserve_extent(root, async_extent->ram_size, async_extent->compressed_size, async_extent->compressed_size, @@ -855,7 +844,7 @@ retry: ins.objectid, ins.offset, async_extent->pages, async_extent->nr_pages, - async_cow->write_flags)) { + async_chunk->write_flags)) { struct page *p = async_extent->pages[0]; const u64 start = async_extent->start; const u64 end = start + async_extent->ram_size - 1; @@ -1132,16 +1121,15 @@ out_unlock: */ static noinline void async_cow_start(struct btrfs_work *work) { - struct async_cow *async_cow; + struct async_chunk *async_chunk; int num_added = 0; - async_cow = container_of(work, struct async_cow, work); - compress_file_range(async_cow->inode, async_cow->locked_page, - async_cow->start, async_cow->end, async_cow, - &num_added); + async_chunk = container_of(work, struct async_chunk, work); + + compress_file_range(async_chunk, &num_added); if (num_added == 0) { - btrfs_add_delayed_iput(async_cow->inode); - async_cow->inode = NULL; + btrfs_add_delayed_iput(async_chunk->inode); + async_chunk->inode = NULL; } } @@ -1150,14 +1138,12 @@ static noinline void async_cow_start(struct btrfs_work *work) */ static noinline void async_cow_submit(struct btrfs_work *work) { - struct btrfs_fs_info *fs_info; - struct async_cow *async_cow; + struct async_chunk *async_chunk = container_of(work, struct async_chunk, + work); + struct btrfs_fs_info *fs_info = btrfs_work_owner(work); unsigned long nr_pages; - async_cow = container_of(work, struct async_cow, work); - - fs_info = async_cow->fs_info; - nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >> + nr_pages = (async_chunk->end - async_chunk->start + PAGE_SIZE) >> PAGE_SHIFT; /* atomic_sub_return implies a barrier */ @@ -1166,22 +1152,28 @@ static noinline void async_cow_submit(struct btrfs_work *work) cond_wake_up_nomb(&fs_info->async_submit_wait); /* - * ->inode could be NULL if async_cow_start has failed to compress, + * ->inode could be NULL if async_chunk_start has failed to compress, * in which case we don't have anything to submit, yet we need to * always adjust ->async_delalloc_pages as its paired with the init * happening in cow_file_range_async */ - if (async_cow->inode) - submit_compressed_extents(async_cow); + if (async_chunk->inode) + submit_compressed_extents(async_chunk); } static noinline void async_cow_free(struct btrfs_work *work) { - struct async_cow *async_cow; - async_cow = container_of(work, struct async_cow, work); - if (async_cow->inode) - btrfs_add_delayed_iput(async_cow->inode); - kfree(async_cow); + struct async_chunk *async_chunk; + + async_chunk = container_of(work, struct async_chunk, work); + if (async_chunk->inode) + btrfs_add_delayed_iput(async_chunk->inode); + /* + * Since the pointer to 'pending' is at the beginning of the array of + * async_chunk's, freeing it ensures the whole array has been freed. + */ + if (atomic_dec_and_test(async_chunk->pending)) + kvfree(async_chunk->pending); } static int cow_file_range_async(struct inode *inode, struct page *locked_page, @@ -1190,45 +1182,73 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, unsigned int write_flags) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct async_cow *async_cow; + struct async_cow *ctx; + struct async_chunk *async_chunk; unsigned long nr_pages; u64 cur_end; + u64 num_chunks = DIV_ROUND_UP(end - start, SZ_512K); + int i; + bool should_compress; + unsigned nofs_flag; + + unlock_extent(&BTRFS_I(inode)->io_tree, start, end); + + if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS && + !btrfs_test_opt(fs_info, FORCE_COMPRESS)) { + num_chunks = 1; + should_compress = false; + } else { + should_compress = true; + } + + nofs_flag = memalloc_nofs_save(); + ctx = kvmalloc(struct_size(ctx, chunks, num_chunks), GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); + + if (!ctx) { + unsigned clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | + EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | + EXTENT_DO_ACCOUNTING; + unsigned long page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | + PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK | + PAGE_SET_ERROR; + + extent_clear_unlock_delalloc(inode, start, end, 0, locked_page, + clear_bits, page_ops); + return -ENOMEM; + } + + async_chunk = ctx->chunks; + atomic_set(&ctx->num_chunks, num_chunks); + + for (i = 0; i < num_chunks; i++) { + if (should_compress) + cur_end = min(end, start + SZ_512K - 1); + else + cur_end = end; - clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED, - 1, 0, NULL); - while (start < end) { - async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS); - BUG_ON(!async_cow); /* -ENOMEM */ /* * igrab is called higher up in the call chain, take only the * lightweight reference for the callback lifetime */ ihold(inode); - async_cow->inode = inode; - async_cow->fs_info = fs_info; - async_cow->locked_page = locked_page; - async_cow->start = start; - async_cow->write_flags = write_flags; - - if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS && - !btrfs_test_opt(fs_info, FORCE_COMPRESS)) - cur_end = end; - else - cur_end = min(end, start + SZ_512K - 1); - - async_cow->end = cur_end; - INIT_LIST_HEAD(&async_cow->extents); - - btrfs_init_work(&async_cow->work, + async_chunk[i].pending = &ctx->num_chunks; + async_chunk[i].inode = inode; + async_chunk[i].start = start; + async_chunk[i].end = cur_end; + async_chunk[i].locked_page = locked_page; + async_chunk[i].write_flags = write_flags; + INIT_LIST_HEAD(&async_chunk[i].extents); + + btrfs_init_work(&async_chunk[i].work, btrfs_delalloc_helper, async_cow_start, async_cow_submit, async_cow_free); - nr_pages = (cur_end - start + PAGE_SIZE) >> - PAGE_SHIFT; + nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE); atomic_add(nr_pages, &fs_info->async_delalloc_pages); - btrfs_queue_work(fs_info->delalloc_workers, &async_cow->work); + btrfs_queue_work(fs_info->delalloc_workers, &async_chunk[i].work); *nr_written += nr_pages; start = cur_end + 1; @@ -1451,7 +1471,7 @@ next_slot: extent_end = ALIGN(extent_end, fs_info->sectorsize); } else { - BUG_ON(1); + BUG(); } out_check: if (extent_end <= start) { @@ -1964,11 +1984,11 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio, * * c-3) otherwise: async submit */ -static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, + int mirror_num, + unsigned long bio_flags) + { - struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA; @@ -2003,8 +2023,7 @@ static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio, goto mapit; /* we're doing a write, do the async checksumming */ ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags, - bio_offset, inode, - btrfs_submit_bio_start); + 0, inode, btrfs_submit_bio_start); goto out; } else if (!skip_sum) { ret = btrfs_csum_one_bio(inode, bio, 0, 0); @@ -2531,6 +2550,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path, struct btrfs_file_extent_item *item; struct btrfs_ordered_extent *ordered; struct btrfs_trans_handle *trans; + struct btrfs_ref ref = { 0 }; struct btrfs_root *root; struct btrfs_key key; struct extent_buffer *leaf; @@ -2701,10 +2721,11 @@ again: inode_add_bytes(inode, len); btrfs_release_path(path); - ret = btrfs_inc_extent_ref(trans, root, new->bytenr, - new->disk_len, 0, - backref->root_id, backref->inum, - new->file_pos); /* start - extent_offset */ + btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new->bytenr, + new->disk_len, 0); + btrfs_init_data_ref(&ref, backref->root_id, backref->inum, + new->file_pos); /* start - extent_offset */ + ret = btrfs_inc_extent_ref(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); goto out_free_path; @@ -3699,21 +3720,6 @@ cache_index: * inode is not a directory, logging its parent unnecessarily. */ BTRFS_I(inode)->last_unlink_trans = BTRFS_I(inode)->last_trans; - /* - * Similar reasoning for last_link_trans, needs to be set otherwise - * for a case like the following: - * - * mkdir A - * touch foo - * ln foo A/bar - * echo 2 > /proc/sys/vm/drop_caches - * fsync foo - * <power failure> - * - * Would result in link bar and directory A not existing after the power - * failure. - */ - BTRFS_I(inode)->last_link_trans = BTRFS_I(inode)->last_trans; path->slots[0]++; if (inode->i_nlink != 1 || @@ -4679,7 +4685,7 @@ search_again: btrfs_set_file_extent_ram_bytes(leaf, fi, size); size = btrfs_file_extent_calc_inline_size(size); - btrfs_truncate_item(root->fs_info, path, size, 1); + btrfs_truncate_item(path, size, 1); } else if (!del_item) { /* * We have to bail so the last_size is set to @@ -4718,12 +4724,17 @@ delete: if (found_extent && (test_bit(BTRFS_ROOT_REF_COWS, &root->state) || root == fs_info->tree_root)) { + struct btrfs_ref ref = { 0 }; + btrfs_set_path_blocking(path); bytes_deleted += extent_num_bytes; - ret = btrfs_free_extent(trans, root, extent_start, - extent_num_bytes, 0, - btrfs_header_owner(leaf), - ino, extent_offset); + + btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, + extent_start, extent_num_bytes, 0); + ref.real_root = root->root_key.objectid; + btrfs_init_data_ref(&ref, btrfs_header_owner(leaf), + ino, extent_offset); + ret = btrfs_free_extent(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); break; @@ -5448,12 +5459,14 @@ no_delete: } /* - * this returns the key found in the dir entry in the location pointer. + * Return the key found in the dir entry in the location pointer, fill @type + * with BTRFS_FT_*, and return 0. + * * If no dir entries were found, returns -ENOENT. * If found a corrupted location in dir entry, returns -EUCLEAN. */ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, - struct btrfs_key *location) + struct btrfs_key *location, u8 *type) { const char *name = dentry->d_name.name; int namelen = dentry->d_name.len; @@ -5482,6 +5495,8 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, __func__, name, btrfs_ino(BTRFS_I(dir)), location->objectid, location->type, location->offset); } + if (!ret) + *type = btrfs_dir_type(path->nodes[0], di); out: btrfs_free_path(path); return ret; @@ -5719,6 +5734,24 @@ static struct inode *new_simple_dir(struct super_block *s, return inode; } +static inline u8 btrfs_inode_type(struct inode *inode) +{ + /* + * Compile-time asserts that generic FT_* types still match + * BTRFS_FT_* types + */ + BUILD_BUG_ON(BTRFS_FT_UNKNOWN != FT_UNKNOWN); + BUILD_BUG_ON(BTRFS_FT_REG_FILE != FT_REG_FILE); + BUILD_BUG_ON(BTRFS_FT_DIR != FT_DIR); + BUILD_BUG_ON(BTRFS_FT_CHRDEV != FT_CHRDEV); + BUILD_BUG_ON(BTRFS_FT_BLKDEV != FT_BLKDEV); + BUILD_BUG_ON(BTRFS_FT_FIFO != FT_FIFO); + BUILD_BUG_ON(BTRFS_FT_SOCK != FT_SOCK); + BUILD_BUG_ON(BTRFS_FT_SYMLINK != FT_SYMLINK); + + return fs_umode_to_ftype(inode->i_mode); +} + struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); @@ -5726,18 +5759,31 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_root *sub_root = root; struct btrfs_key location; + u8 di_type = 0; int index; int ret = 0; if (dentry->d_name.len > BTRFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - ret = btrfs_inode_by_name(dir, dentry, &location); + ret = btrfs_inode_by_name(dir, dentry, &location, &di_type); if (ret < 0) return ERR_PTR(ret); if (location.type == BTRFS_INODE_ITEM_KEY) { inode = btrfs_iget(dir->i_sb, &location, root, NULL); + if (IS_ERR(inode)) + return inode; + + /* Do extra check against inode mode with di_type */ + if (btrfs_inode_type(inode) != di_type) { + btrfs_crit(fs_info, +"inode mode mismatch with dir: inode mode=0%o btrfs type=%u dir type=%u", + inode->i_mode, btrfs_inode_type(inode), + di_type); + iput(inode); + return ERR_PTR(-EUCLEAN); + } return inode; } @@ -5797,10 +5843,6 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, return d_splice_alias(inode, dentry); } -unsigned char btrfs_filetype_table[] = { - DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK -}; - /* * All this infrastructure exists because dir_emit can fault, and we are holding * the tree lock when doing readdir. For now just allocate a buffer and copy @@ -5939,7 +5981,7 @@ again: name_ptr = (char *)(entry + 1); read_extent_buffer(leaf, name_ptr, (unsigned long)(di + 1), name_len); - put_unaligned(btrfs_filetype_table[btrfs_dir_type(leaf, di)], + put_unaligned(fs_ftype_to_dtype(btrfs_dir_type(leaf, di)), &entry->type); btrfs_dir_item_key_to_cpu(leaf, di, &location); put_unaligned(location.objectid, &entry->ino); @@ -6342,11 +6384,6 @@ fail: return ERR_PTR(ret); } -static inline u8 btrfs_inode_type(struct inode *inode) -{ - return btrfs_type_by_mode[(inode->i_mode & S_IFMT) >> S_SHIFT]; -} - /* * utility function to add 'inode' into 'parent_inode' with * a give name and a given sequence number. @@ -6634,7 +6671,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, if (err) goto fail; } - BTRFS_I(inode)->last_link_trans = trans->transid; d_instantiate(dentry, inode); ret = btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent, true, NULL); @@ -6783,7 +6819,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, u64 extent_start = 0; u64 extent_end = 0; u64 objectid = btrfs_ino(inode); - u8 extent_type; + int extent_type = -1; struct btrfs_path *path = NULL; struct btrfs_root *root = inode->root; struct btrfs_file_extent_item *item; @@ -6864,6 +6900,14 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, extent_start = found_key.offset; if (extent_type == BTRFS_FILE_EXTENT_REG || extent_type == BTRFS_FILE_EXTENT_PREALLOC) { + /* Only regular file could have regular/prealloc extent */ + if (!S_ISREG(inode->vfs_inode.i_mode)) { + ret = -EUCLEAN; + btrfs_crit(fs_info, + "regular/prealloc extent found for non-regular inode %llu", + btrfs_ino(inode)); + goto out; + } extent_end = extent_start + btrfs_file_extent_num_bytes(leaf, item); @@ -7828,7 +7872,6 @@ static void btrfs_retry_endio_nocsum(struct bio *bio) struct inode *inode = done->inode; struct bio_vec *bvec; struct extent_io_tree *io_tree, *failure_tree; - int i; struct bvec_iter_all iter_all; if (bio->bi_status) @@ -7841,7 +7884,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio) done->uptodate = 1; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, i, iter_all) + bio_for_each_segment_all(bvec, bio, iter_all) clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree, io_tree, done->start, bvec->bv_page, btrfs_ino(BTRFS_I(inode)), 0); @@ -7919,7 +7962,7 @@ static void btrfs_retry_endio(struct bio *bio) struct bio_vec *bvec; int uptodate; int ret; - int i; + int i = 0; struct bvec_iter_all iter_all; if (bio->bi_status) @@ -7934,7 +7977,7 @@ static void btrfs_retry_endio(struct bio *bio) failure_tree = &BTRFS_I(inode)->io_failure_tree; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page, bvec->bv_offset, done->start, bvec->bv_len); @@ -7946,6 +7989,7 @@ static void btrfs_retry_endio(struct bio *bio) bvec->bv_offset); else uptodate = 0; + i++; } done->uptodate = uptodate; @@ -9163,7 +9207,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->index_cnt = (u64)-1; ei->dir_index = 0; ei->last_unlink_trans = 0; - ei->last_link_trans = 0; ei->last_log_commit = 0; spin_lock_init(&ei->lock); @@ -9182,10 +9225,11 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) inode = &ei->vfs_inode; extent_map_tree_init(&ei->extent_tree); - extent_io_tree_init(&ei->io_tree, inode); - extent_io_tree_init(&ei->io_failure_tree, inode); - ei->io_tree.track_uptodate = 1; - ei->io_failure_tree.track_uptodate = 1; + extent_io_tree_init(fs_info, &ei->io_tree, IO_TREE_INODE_IO, inode); + extent_io_tree_init(fs_info, &ei->io_failure_tree, + IO_TREE_INODE_IO_FAILURE, inode); + ei->io_tree.track_uptodate = true; + ei->io_failure_tree.track_uptodate = true; atomic_set(&ei->sync_writers, 0); mutex_init(&ei->log_mutex); mutex_init(&ei->delalloc_mutex); @@ -9206,9 +9250,8 @@ void btrfs_test_destroy_inode(struct inode *inode) } #endif -static void btrfs_i_callback(struct rcu_head *head) +void btrfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode)); } @@ -9234,7 +9277,7 @@ void btrfs_destroy_inode(struct inode *inode) * created. */ if (!root) - goto free; + return; while (1) { ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1); @@ -9252,8 +9295,6 @@ void btrfs_destroy_inode(struct inode *inode) btrfs_qgroup_check_reserved_leak(inode); inode_tree_del(inode); btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0); -free: - call_rcu(&inode->i_rcu, btrfs_i_callback); } int btrfs_drop_inode(struct inode *inode) @@ -9430,7 +9471,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* Reference for the source. */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { /* force full log commit if subvolume involved. */ - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); } else { btrfs_pin_log_trans(root); root_log_pinned = true; @@ -9447,7 +9488,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* And now for the dest. */ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) { /* force full log commit if subvolume involved. */ - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); } else { btrfs_pin_log_trans(dest); dest_log_pinned = true; @@ -9583,7 +9624,7 @@ out_fail: btrfs_inode_in_log(BTRFS_I(old_inode), fs_info->generation) || (new_inode && btrfs_inode_in_log(BTRFS_I(new_inode), fs_info->generation))) - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); if (root_log_pinned) { btrfs_end_log_trans(root); @@ -9769,7 +9810,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, BTRFS_I(old_inode)->dir_index = 0ULL; if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) { /* force full log commit if subvolume involved. */ - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); } else { btrfs_pin_log_trans(root); log_pinned = true; @@ -9890,7 +9931,7 @@ out_fail: btrfs_inode_in_log(BTRFS_I(old_inode), fs_info->generation) || (new_inode && btrfs_inode_in_log(BTRFS_I(new_inode), fs_info->generation))) - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); btrfs_end_log_trans(root); log_pinned = false; @@ -10193,7 +10234,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, inode->i_op = &btrfs_symlink_inode_operations; inode_nohighmem(inode); - inode->i_mapping->a_ops = &btrfs_aops; inode_set_bytes(inode, name_len); btrfs_i_size_write(BTRFS_I(inode), name_len); err = btrfs_update_inode(trans, root, inode); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ec2d8919e7fb..6dafa857bbb9 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -187,11 +187,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) struct btrfs_inode *binode = BTRFS_I(inode); struct btrfs_root *root = binode->root; struct btrfs_trans_handle *trans; - unsigned int fsflags, old_fsflags; + unsigned int fsflags; int ret; - u64 old_flags; - unsigned int old_i_flags; - umode_t mode; + const char *comp = NULL; + u32 binode_flags = binode->flags; if (!inode_owner_or_capable(inode)) return -EPERM; @@ -212,13 +211,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) inode_lock(inode); - old_flags = binode->flags; - old_i_flags = inode->i_flags; - mode = inode->i_mode; - fsflags = btrfs_mask_fsflags_for_type(inode, fsflags); - old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags); - if ((fsflags ^ old_fsflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { + if ((fsflags ^ btrfs_inode_flags_to_fsflags(binode->flags)) & + (FS_APPEND_FL | FS_IMMUTABLE_FL)) { if (!capable(CAP_LINUX_IMMUTABLE)) { ret = -EPERM; goto out_unlock; @@ -226,52 +221,52 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) } if (fsflags & FS_SYNC_FL) - binode->flags |= BTRFS_INODE_SYNC; + binode_flags |= BTRFS_INODE_SYNC; else - binode->flags &= ~BTRFS_INODE_SYNC; + binode_flags &= ~BTRFS_INODE_SYNC; if (fsflags & FS_IMMUTABLE_FL) - binode->flags |= BTRFS_INODE_IMMUTABLE; + binode_flags |= BTRFS_INODE_IMMUTABLE; else - binode->flags &= ~BTRFS_INODE_IMMUTABLE; + binode_flags &= ~BTRFS_INODE_IMMUTABLE; if (fsflags & FS_APPEND_FL) - binode->flags |= BTRFS_INODE_APPEND; + binode_flags |= BTRFS_INODE_APPEND; else - binode->flags &= ~BTRFS_INODE_APPEND; + binode_flags &= ~BTRFS_INODE_APPEND; if (fsflags & FS_NODUMP_FL) - binode->flags |= BTRFS_INODE_NODUMP; + binode_flags |= BTRFS_INODE_NODUMP; else - binode->flags &= ~BTRFS_INODE_NODUMP; + binode_flags &= ~BTRFS_INODE_NODUMP; if (fsflags & FS_NOATIME_FL) - binode->flags |= BTRFS_INODE_NOATIME; + binode_flags |= BTRFS_INODE_NOATIME; else - binode->flags &= ~BTRFS_INODE_NOATIME; + binode_flags &= ~BTRFS_INODE_NOATIME; if (fsflags & FS_DIRSYNC_FL) - binode->flags |= BTRFS_INODE_DIRSYNC; + binode_flags |= BTRFS_INODE_DIRSYNC; else - binode->flags &= ~BTRFS_INODE_DIRSYNC; + binode_flags &= ~BTRFS_INODE_DIRSYNC; if (fsflags & FS_NOCOW_FL) { - if (S_ISREG(mode)) { + if (S_ISREG(inode->i_mode)) { /* * It's safe to turn csums off here, no extents exist. * Otherwise we want the flag to reflect the real COW * status of the file and will not set it. */ if (inode->i_size == 0) - binode->flags |= BTRFS_INODE_NODATACOW - | BTRFS_INODE_NODATASUM; + binode_flags |= BTRFS_INODE_NODATACOW | + BTRFS_INODE_NODATASUM; } else { - binode->flags |= BTRFS_INODE_NODATACOW; + binode_flags |= BTRFS_INODE_NODATACOW; } } else { /* * Revert back under same assumptions as above */ - if (S_ISREG(mode)) { + if (S_ISREG(inode->i_mode)) { if (inode->i_size == 0) - binode->flags &= ~(BTRFS_INODE_NODATACOW - | BTRFS_INODE_NODATASUM); + binode_flags &= ~(BTRFS_INODE_NODATACOW | + BTRFS_INODE_NODATASUM); } else { - binode->flags &= ~BTRFS_INODE_NODATACOW; + binode_flags &= ~BTRFS_INODE_NODATACOW; } } @@ -281,57 +276,61 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) * things smaller. */ if (fsflags & FS_NOCOMP_FL) { - binode->flags &= ~BTRFS_INODE_COMPRESS; - binode->flags |= BTRFS_INODE_NOCOMPRESS; - - ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0); - if (ret && ret != -ENODATA) - goto out_drop; + binode_flags &= ~BTRFS_INODE_COMPRESS; + binode_flags |= BTRFS_INODE_NOCOMPRESS; } else if (fsflags & FS_COMPR_FL) { - const char *comp; if (IS_SWAPFILE(inode)) { ret = -ETXTBSY; goto out_unlock; } - binode->flags |= BTRFS_INODE_COMPRESS; - binode->flags &= ~BTRFS_INODE_NOCOMPRESS; + binode_flags |= BTRFS_INODE_COMPRESS; + binode_flags &= ~BTRFS_INODE_NOCOMPRESS; comp = btrfs_compress_type2str(fs_info->compress_type); if (!comp || comp[0] == 0) comp = btrfs_compress_type2str(BTRFS_COMPRESS_ZLIB); - - ret = btrfs_set_prop(inode, "btrfs.compression", - comp, strlen(comp), 0); - if (ret) - goto out_drop; - } else { - ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0); - if (ret && ret != -ENODATA) - goto out_drop; - binode->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); + binode_flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } - trans = btrfs_start_transaction(root, 1); + /* + * 1 for inode item + * 2 for properties + */ + trans = btrfs_start_transaction(root, 3); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - goto out_drop; + goto out_unlock; } + if (comp) { + ret = btrfs_set_prop(trans, inode, "btrfs.compression", comp, + strlen(comp), 0); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_end_trans; + } + set_bit(BTRFS_INODE_COPY_EVERYTHING, + &BTRFS_I(inode)->runtime_flags); + } else { + ret = btrfs_set_prop(trans, inode, "btrfs.compression", NULL, + 0, 0); + if (ret && ret != -ENODATA) { + btrfs_abort_transaction(trans, ret); + goto out_end_trans; + } + } + + binode->flags = binode_flags; btrfs_sync_inode_flags_to_i_flags(inode); inode_inc_iversion(inode); inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, inode); + out_end_trans: btrfs_end_transaction(trans); - out_drop: - if (ret) { - binode->flags = old_flags; - inode->i_flags = old_i_flags; - } - out_unlock: inode_unlock(inode); mnt_drop_write_file(file); @@ -501,6 +500,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* + * If the fs is mounted with nologreplay, which requires it to be + * mounted in RO mode as well, we can not allow discard on free space + * inside block groups, because log trees refer to extents that are not + * pinned in a block group's free space cache (pinning the extents is + * precisely the first phase of replaying a log tree). + */ + if (btrfs_test_opt(fs_info, NOLOGREPLAY)) + return -EROFS; + rcu_read_lock(); list_for_each_entry_rcu(device, &fs_info->fs_devices->devices, dev_list) { @@ -3250,6 +3259,19 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, { int ret; u64 i, tail_len, chunk_count; + struct btrfs_root *root_dst = BTRFS_I(dst)->root; + + spin_lock(&root_dst->root_item_lock); + if (root_dst->send_in_progress) { + btrfs_warn_rl(root_dst->fs_info, +"cannot deduplicate to root %llu while send operations are using it (%d in progress)", + root_dst->root_key.objectid, + root_dst->send_in_progress); + spin_unlock(&root_dst->root_item_lock); + return -EAGAIN; + } + root_dst->dedupe_in_progress++; + spin_unlock(&root_dst->root_item_lock); tail_len = olen % BTRFS_MAX_DEDUPE_LEN; chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN); @@ -3258,7 +3280,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN, dst, dst_loff); if (ret) - return ret; + goto out; loff += BTRFS_MAX_DEDUPE_LEN; dst_loff += BTRFS_MAX_DEDUPE_LEN; @@ -3267,6 +3289,10 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, if (tail_len > 0) ret = btrfs_extent_same_range(src, loff, tail_len, dst, dst_loff); +out: + spin_lock(&root_dst->root_item_lock); + root_dst->dedupe_in_progress--; + spin_unlock(&root_dst->root_item_lock); return ret; } @@ -3725,13 +3751,16 @@ process_slot: datal); if (disko) { + struct btrfs_ref ref = { 0 }; inode_add_bytes(inode, datal); - ret = btrfs_inc_extent_ref(trans, - root, - disko, diskl, 0, - root->root_key.objectid, - btrfs_ino(BTRFS_I(inode)), - new_key.offset - datao); + btrfs_init_generic_ref(&ref, + BTRFS_ADD_DELAYED_REF, disko, + diskl, 0); + btrfs_init_data_ref(&ref, + root->root_key.objectid, + btrfs_ino(BTRFS_I(inode)), + new_key.offset - datao); + ret = btrfs_inc_extent_ref(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); @@ -3938,16 +3967,10 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, return -EXDEV; } - if (same_inode) - inode_lock(inode_in); - else - lock_two_nondirectories(inode_in, inode_out); - /* don't make the dst file partly checksummed */ if ((BTRFS_I(inode_in)->flags & BTRFS_INODE_NODATASUM) != (BTRFS_I(inode_out)->flags & BTRFS_INODE_NODATASUM)) { - ret = -EINVAL; - goto out_unlock; + return -EINVAL; } /* @@ -3981,26 +4004,14 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, ret = btrfs_wait_ordered_range(inode_in, ALIGN_DOWN(pos_in, bs), wb_len); if (ret < 0) - goto out_unlock; + return ret; ret = btrfs_wait_ordered_range(inode_out, ALIGN_DOWN(pos_out, bs), wb_len); if (ret < 0) - goto out_unlock; + return ret; - ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, + return generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, len, remap_flags); - if (ret < 0 || *len == 0) - goto out_unlock; - - return 0; - - out_unlock: - if (same_inode) - inode_unlock(inode_in); - else - unlock_two_nondirectories(inode_in, inode_out); - - return ret; } loff_t btrfs_remap_file_range(struct file *src_file, loff_t off, @@ -4015,16 +4026,22 @@ loff_t btrfs_remap_file_range(struct file *src_file, loff_t off, if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; + if (same_inode) + inode_lock(src_inode); + else + lock_two_nondirectories(src_inode, dst_inode); + ret = btrfs_remap_file_range_prep(src_file, off, dst_file, destoff, &len, remap_flags); if (ret < 0 || len == 0) - return ret; + goto out_unlock; if (remap_flags & REMAP_FILE_DEDUP) ret = btrfs_extent_same(src_inode, off, len, dst_inode, destoff); else ret = btrfs_clone_files(dst_file, src_file, off, len, destoff); +out_unlock: if (same_inode) inode_unlock(src_inode); else diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 82b84e4daad1..2f6c3c7851ed 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -12,10 +12,82 @@ #include "extent_io.h" #include "locking.h" -static void btrfs_assert_tree_read_locked(struct extent_buffer *eb); +#ifdef CONFIG_BTRFS_DEBUG +static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) +{ + WARN_ON(atomic_read(&eb->spinning_writers)); + atomic_inc(&eb->spinning_writers); +} + +static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) +{ + WARN_ON(atomic_read(&eb->spinning_writers) != 1); + atomic_dec(&eb->spinning_writers); +} + +static void btrfs_assert_no_spinning_writers(struct extent_buffer *eb) +{ + WARN_ON(atomic_read(&eb->spinning_writers)); +} + +static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) +{ + atomic_inc(&eb->spinning_readers); +} + +static void btrfs_assert_spinning_readers_put(struct extent_buffer *eb) +{ + WARN_ON(atomic_read(&eb->spinning_readers) == 0); + atomic_dec(&eb->spinning_readers); +} + +static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) +{ + atomic_inc(&eb->read_locks); +} + +static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) +{ + atomic_dec(&eb->read_locks); +} + +static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) +{ + BUG_ON(!atomic_read(&eb->read_locks)); +} + +static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) +{ + atomic_inc(&eb->write_locks); +} + +static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) +{ + atomic_dec(&eb->write_locks); +} + +void btrfs_assert_tree_locked(struct extent_buffer *eb) +{ + BUG_ON(!atomic_read(&eb->write_locks)); +} + +#else +static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) { } +static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) { } +static void btrfs_assert_no_spinning_writers(struct extent_buffer *eb) { } +static void btrfs_assert_spinning_readers_put(struct extent_buffer *eb) { } +static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) { } +static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { } +static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) { } +static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) { } +void btrfs_assert_tree_locked(struct extent_buffer *eb) { } +static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) { } +static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) { } +#endif void btrfs_set_lock_blocking_read(struct extent_buffer *eb) { + trace_btrfs_set_lock_blocking_read(eb); /* * No lock is required. The lock owner may change if we have a read * lock, but it won't change to or away from us. If we have the write @@ -25,13 +97,13 @@ void btrfs_set_lock_blocking_read(struct extent_buffer *eb) return; btrfs_assert_tree_read_locked(eb); atomic_inc(&eb->blocking_readers); - WARN_ON(atomic_read(&eb->spinning_readers) == 0); - atomic_dec(&eb->spinning_readers); + btrfs_assert_spinning_readers_put(eb); read_unlock(&eb->lock); } void btrfs_set_lock_blocking_write(struct extent_buffer *eb) { + trace_btrfs_set_lock_blocking_write(eb); /* * No lock is required. The lock owner may change if we have a read * lock, but it won't change to or away from us. If we have the write @@ -40,8 +112,7 @@ void btrfs_set_lock_blocking_write(struct extent_buffer *eb) if (eb->lock_nested && current->pid == eb->lock_owner) return; if (atomic_read(&eb->blocking_writers) == 0) { - WARN_ON(atomic_read(&eb->spinning_writers) != 1); - atomic_dec(&eb->spinning_writers); + btrfs_assert_spinning_writers_put(eb); btrfs_assert_tree_locked(eb); atomic_inc(&eb->blocking_writers); write_unlock(&eb->lock); @@ -50,6 +121,7 @@ void btrfs_set_lock_blocking_write(struct extent_buffer *eb) void btrfs_clear_lock_blocking_read(struct extent_buffer *eb) { + trace_btrfs_clear_lock_blocking_read(eb); /* * No lock is required. The lock owner may change if we have a read * lock, but it won't change to or away from us. If we have the write @@ -59,7 +131,7 @@ void btrfs_clear_lock_blocking_read(struct extent_buffer *eb) return; BUG_ON(atomic_read(&eb->blocking_readers) == 0); read_lock(&eb->lock); - atomic_inc(&eb->spinning_readers); + btrfs_assert_spinning_readers_get(eb); /* atomic_dec_and_test implies a barrier */ if (atomic_dec_and_test(&eb->blocking_readers)) cond_wake_up_nomb(&eb->read_lock_wq); @@ -67,6 +139,7 @@ void btrfs_clear_lock_blocking_read(struct extent_buffer *eb) void btrfs_clear_lock_blocking_write(struct extent_buffer *eb) { + trace_btrfs_clear_lock_blocking_write(eb); /* * no lock is required. The lock owner may change if * we have a read lock, but it won't change to or away @@ -77,8 +150,7 @@ void btrfs_clear_lock_blocking_write(struct extent_buffer *eb) return; BUG_ON(atomic_read(&eb->blocking_writers) != 1); write_lock(&eb->lock); - WARN_ON(atomic_read(&eb->spinning_writers)); - atomic_inc(&eb->spinning_writers); + btrfs_assert_spinning_writers_get(eb); /* atomic_dec_and_test implies a barrier */ if (atomic_dec_and_test(&eb->blocking_writers)) cond_wake_up_nomb(&eb->write_lock_wq); @@ -90,6 +162,10 @@ void btrfs_clear_lock_blocking_write(struct extent_buffer *eb) */ void btrfs_tree_read_lock(struct extent_buffer *eb) { + u64 start_ns = 0; + + if (trace_btrfs_tree_read_lock_enabled()) + start_ns = ktime_get_ns(); again: BUG_ON(!atomic_read(&eb->blocking_writers) && current->pid == eb->lock_owner); @@ -104,8 +180,9 @@ again: * called on a partly (write-)locked tree. */ BUG_ON(eb->lock_nested); - eb->lock_nested = 1; + eb->lock_nested = true; read_unlock(&eb->lock); + trace_btrfs_tree_read_lock(eb, start_ns); return; } if (atomic_read(&eb->blocking_writers)) { @@ -114,8 +191,9 @@ again: atomic_read(&eb->blocking_writers) == 0); goto again; } - atomic_inc(&eb->read_locks); - atomic_inc(&eb->spinning_readers); + btrfs_assert_tree_read_locks_get(eb); + btrfs_assert_spinning_readers_get(eb); + trace_btrfs_tree_read_lock(eb, start_ns); } /* @@ -133,8 +211,9 @@ int btrfs_tree_read_lock_atomic(struct extent_buffer *eb) read_unlock(&eb->lock); return 0; } - atomic_inc(&eb->read_locks); - atomic_inc(&eb->spinning_readers); + btrfs_assert_tree_read_locks_get(eb); + btrfs_assert_spinning_readers_get(eb); + trace_btrfs_tree_read_lock_atomic(eb); return 1; } @@ -154,8 +233,9 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb) read_unlock(&eb->lock); return 0; } - atomic_inc(&eb->read_locks); - atomic_inc(&eb->spinning_readers); + btrfs_assert_tree_read_locks_get(eb); + btrfs_assert_spinning_readers_get(eb); + trace_btrfs_try_tree_read_lock(eb); return 1; } @@ -175,9 +255,10 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb) write_unlock(&eb->lock); return 0; } - atomic_inc(&eb->write_locks); - atomic_inc(&eb->spinning_writers); + btrfs_assert_tree_write_locks_get(eb); + btrfs_assert_spinning_writers_get(eb); eb->lock_owner = current->pid; + trace_btrfs_try_tree_write_lock(eb); return 1; } @@ -186,6 +267,7 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb) */ void btrfs_tree_read_unlock(struct extent_buffer *eb) { + trace_btrfs_tree_read_unlock(eb); /* * if we're nested, we have the write lock. No new locking * is needed as long as we are the lock owner. @@ -193,13 +275,12 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb) * field only matters to the lock owner. */ if (eb->lock_nested && current->pid == eb->lock_owner) { - eb->lock_nested = 0; + eb->lock_nested = false; return; } btrfs_assert_tree_read_locked(eb); - WARN_ON(atomic_read(&eb->spinning_readers) == 0); - atomic_dec(&eb->spinning_readers); - atomic_dec(&eb->read_locks); + btrfs_assert_spinning_readers_put(eb); + btrfs_assert_tree_read_locks_put(eb); read_unlock(&eb->lock); } @@ -208,6 +289,7 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb) */ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) { + trace_btrfs_tree_read_unlock_blocking(eb); /* * if we're nested, we have the write lock. No new locking * is needed as long as we are the lock owner. @@ -215,7 +297,7 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) * field only matters to the lock owner. */ if (eb->lock_nested && current->pid == eb->lock_owner) { - eb->lock_nested = 0; + eb->lock_nested = false; return; } btrfs_assert_tree_read_locked(eb); @@ -223,7 +305,7 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) /* atomic_dec_and_test implies a barrier */ if (atomic_dec_and_test(&eb->blocking_readers)) cond_wake_up_nomb(&eb->read_lock_wq); - atomic_dec(&eb->read_locks); + btrfs_assert_tree_read_locks_put(eb); } /* @@ -232,6 +314,11 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) */ void btrfs_tree_lock(struct extent_buffer *eb) { + u64 start_ns = 0; + + if (trace_btrfs_tree_lock_enabled()) + start_ns = ktime_get_ns(); + WARN_ON(eb->lock_owner == current->pid); again: wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0); @@ -242,10 +329,10 @@ again: write_unlock(&eb->lock); goto again; } - WARN_ON(atomic_read(&eb->spinning_writers)); - atomic_inc(&eb->spinning_writers); - atomic_inc(&eb->write_locks); + btrfs_assert_spinning_writers_get(eb); + btrfs_assert_tree_write_locks_get(eb); eb->lock_owner = current->pid; + trace_btrfs_tree_lock(eb, start_ns); } /* @@ -258,28 +345,18 @@ void btrfs_tree_unlock(struct extent_buffer *eb) BUG_ON(blockers > 1); btrfs_assert_tree_locked(eb); + trace_btrfs_tree_unlock(eb); eb->lock_owner = 0; - atomic_dec(&eb->write_locks); + btrfs_assert_tree_write_locks_put(eb); if (blockers) { - WARN_ON(atomic_read(&eb->spinning_writers)); + btrfs_assert_no_spinning_writers(eb); atomic_dec(&eb->blocking_writers); /* Use the lighter barrier after atomic */ smp_mb__after_atomic(); cond_wake_up_nomb(&eb->write_lock_wq); } else { - WARN_ON(atomic_read(&eb->spinning_writers) != 1); - atomic_dec(&eb->spinning_writers); + btrfs_assert_spinning_writers_put(eb); write_unlock(&eb->lock); } } - -void btrfs_assert_tree_locked(struct extent_buffer *eb) -{ - BUG_ON(!atomic_read(&eb->write_locks)); -} - -static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) -{ - BUG_ON(!atomic_read(&eb->read_locks)); -} diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 6fde2b2741ef..52889da69113 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/writeback.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "transaction.h" #include "btrfs_inode.h" @@ -194,8 +195,11 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE) set_bit(type, &entry->flags); - if (dio) + if (dio) { + percpu_counter_add_batch(&fs_info->dio_bytes, len, + fs_info->delalloc_batch); set_bit(BTRFS_ORDERED_DIRECT, &entry->flags); + } /* one ref for the tree */ refcount_set(&entry->refs, 1); @@ -270,13 +274,12 @@ int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset, * when an ordered extent is finished. If the list covers more than one * ordered extent, it is split across multiples. */ -void btrfs_add_ordered_sum(struct inode *inode, - struct btrfs_ordered_extent *entry, +void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, struct btrfs_ordered_sum *sum) { struct btrfs_ordered_inode_tree *tree; - tree = &BTRFS_I(inode)->ordered_tree; + tree = &BTRFS_I(entry->inode)->ordered_tree; spin_lock_irq(&tree->lock); list_add_tail(&sum->list, &entry->list); spin_unlock_irq(&tree->lock); @@ -442,7 +445,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry) cur = entry->list.next; sum = list_entry(cur, struct btrfs_ordered_sum, list); list_del(&sum->list); - kfree(sum); + kvfree(sum); } kmem_cache_free(btrfs_ordered_extent_cache, entry); } @@ -468,6 +471,10 @@ void btrfs_remove_ordered_extent(struct inode *inode, if (root != fs_info->tree_root) btrfs_delalloc_release_metadata(btrfs_inode, entry->len, false); + if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags)) + percpu_counter_add_batch(&fs_info->dio_bytes, -entry->len, + fs_info->delalloc_batch); + tree = &btrfs_inode->ordered_tree; spin_lock_irq(&tree->lock); node = &entry->rb_node; diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index fb9a161f0215..4c5991c3de14 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -167,8 +167,7 @@ int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset, int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset, u64 start, u64 len, u64 disk_len, int type, int compress_type); -void btrfs_add_ordered_sum(struct inode *inode, - struct btrfs_ordered_extent *entry, +void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, struct btrfs_ordered_sum *sum); struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode, u64 file_offset); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index df49931ffe92..1141ca5fae6a 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -189,7 +189,7 @@ void btrfs_print_leaf(struct extent_buffer *l) btrfs_info(fs_info, "leaf %llu gen %llu total ptrs %d free space %d owner %llu", btrfs_header_bytenr(l), btrfs_header_generation(l), nr, - btrfs_leaf_free_space(fs_info, l), btrfs_header_owner(l)); + btrfs_leaf_free_space(l), btrfs_header_owner(l)); print_eb_refs_lock(l); for (i = 0 ; i < nr ; i++) { item = btrfs_item_nr(i); diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index dc6140013ae8..ca2716917e37 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -23,36 +23,6 @@ struct prop_handler { int inheritable; }; -static int prop_compression_validate(const char *value, size_t len); -static int prop_compression_apply(struct inode *inode, - const char *value, - size_t len); -static const char *prop_compression_extract(struct inode *inode); - -static struct prop_handler prop_handlers[] = { - { - .xattr_name = XATTR_BTRFS_PREFIX "compression", - .validate = prop_compression_validate, - .apply = prop_compression_apply, - .extract = prop_compression_extract, - .inheritable = 1 - }, -}; - -void __init btrfs_props_init(void) -{ - int i; - - hash_init(prop_handlers_ht); - - for (i = 0; i < ARRAY_SIZE(prop_handlers); i++) { - struct prop_handler *p = &prop_handlers[i]; - u64 h = btrfs_name_hash(p->xattr_name, strlen(p->xattr_name)); - - hash_add(prop_handlers_ht, &p->node, h); - } -} - static const struct hlist_head *find_prop_handlers_by_hash(const u64 hash) { struct hlist_head *h; @@ -85,15 +55,9 @@ find_prop_handler(const char *name, return NULL; } -static int __btrfs_set_prop(struct btrfs_trans_handle *trans, - struct inode *inode, - const char *name, - const char *value, - size_t value_len, - int flags) +int btrfs_validate_prop(const char *name, const char *value, size_t value_len) { const struct prop_handler *handler; - int ret; if (strlen(name) <= XATTR_BTRFS_PREFIX_LEN) return -EINVAL; @@ -102,9 +66,26 @@ static int __btrfs_set_prop(struct btrfs_trans_handle *trans, if (!handler) return -EINVAL; + if (value_len == 0) + return 0; + + return handler->validate(value, value_len); +} + +int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, + const char *name, const char *value, size_t value_len, + int flags) +{ + const struct prop_handler *handler; + int ret; + + handler = find_prop_handler(name, NULL); + if (!handler) + return -EINVAL; + if (value_len == 0) { ret = btrfs_setxattr(trans, inode, handler->xattr_name, - NULL, 0, flags); + NULL, 0, flags); if (ret) return ret; @@ -114,17 +95,14 @@ static int __btrfs_set_prop(struct btrfs_trans_handle *trans, return ret; } - ret = handler->validate(value, value_len); - if (ret) - return ret; - ret = btrfs_setxattr(trans, inode, handler->xattr_name, - value, value_len, flags); + ret = btrfs_setxattr(trans, inode, handler->xattr_name, value, + value_len, flags); if (ret) return ret; ret = handler->apply(inode, value, value_len); if (ret) { - btrfs_setxattr(trans, inode, handler->xattr_name, - NULL, 0, flags); + btrfs_setxattr(trans, inode, handler->xattr_name, NULL, + 0, flags); return ret; } @@ -133,15 +111,6 @@ static int __btrfs_set_prop(struct btrfs_trans_handle *trans, return 0; } -int btrfs_set_prop(struct inode *inode, - const char *name, - const char *value, - size_t value_len, - int flags) -{ - return __btrfs_set_prop(NULL, inode, name, value, value_len, flags); -} - static int iterate_object_props(struct btrfs_root *root, struct btrfs_path *path, u64 objectid, @@ -283,6 +252,78 @@ int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path) return ret; } +static int prop_compression_validate(const char *value, size_t len) +{ + if (!value) + return 0; + + if (!strncmp("lzo", value, 3)) + return 0; + else if (!strncmp("zlib", value, 4)) + return 0; + else if (!strncmp("zstd", value, 4)) + return 0; + + return -EINVAL; +} + +static int prop_compression_apply(struct inode *inode, const char *value, + size_t len) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + int type; + + if (len == 0) { + BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; + BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS; + BTRFS_I(inode)->prop_compress = BTRFS_COMPRESS_NONE; + + return 0; + } + + if (!strncmp("lzo", value, 3)) { + type = BTRFS_COMPRESS_LZO; + btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); + } else if (!strncmp("zlib", value, 4)) { + type = BTRFS_COMPRESS_ZLIB; + } else if (!strncmp("zstd", value, 4)) { + type = BTRFS_COMPRESS_ZSTD; + btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); + } else { + return -EINVAL; + } + + BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS; + BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS; + BTRFS_I(inode)->prop_compress = type; + + return 0; +} + +static const char *prop_compression_extract(struct inode *inode) +{ + switch (BTRFS_I(inode)->prop_compress) { + case BTRFS_COMPRESS_ZLIB: + case BTRFS_COMPRESS_LZO: + case BTRFS_COMPRESS_ZSTD: + return btrfs_compress_type2str(BTRFS_I(inode)->prop_compress); + default: + break; + } + + return NULL; +} + +static struct prop_handler prop_handlers[] = { + { + .xattr_name = XATTR_BTRFS_PREFIX "compression", + .validate = prop_compression_validate, + .apply = prop_compression_apply, + .extract = prop_compression_extract, + .inheritable = 1 + }, +}; + static int inherit_props(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *parent) @@ -308,20 +349,38 @@ static int inherit_props(struct btrfs_trans_handle *trans, if (!value) continue; + /* + * This is not strictly necessary as the property should be + * valid, but in case it isn't, don't propagate it futher. + */ + ret = h->validate(value, strlen(value)); + if (ret) + continue; + num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); ret = btrfs_block_rsv_add(root, trans->block_rsv, num_bytes, BTRFS_RESERVE_NO_FLUSH); if (ret) - goto out; - ret = __btrfs_set_prop(trans, inode, h->xattr_name, - value, strlen(value), 0); + return ret; + + ret = btrfs_setxattr(trans, inode, h->xattr_name, value, + strlen(value), 0); + if (!ret) { + ret = h->apply(inode, value, strlen(value)); + if (ret) + btrfs_setxattr(trans, inode, h->xattr_name, + NULL, 0, 0); + else + set_bit(BTRFS_INODE_HAS_PROPS, + &BTRFS_I(inode)->runtime_flags); + } + btrfs_block_rsv_release(fs_info, trans->block_rsv, num_bytes); if (ret) - goto out; + return ret; } - ret = 0; -out: - return ret; + + return 0; } int btrfs_inode_inherit_props(struct btrfs_trans_handle *trans, @@ -364,64 +423,17 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans, return ret; } -static int prop_compression_validate(const char *value, size_t len) -{ - if (!strncmp("lzo", value, len)) - return 0; - else if (!strncmp("zlib", value, len)) - return 0; - else if (!strncmp("zstd", value, len)) - return 0; - - return -EINVAL; -} - -static int prop_compression_apply(struct inode *inode, - const char *value, - size_t len) +void __init btrfs_props_init(void) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int type; - - if (len == 0) { - BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; - BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS; - BTRFS_I(inode)->prop_compress = BTRFS_COMPRESS_NONE; - - return 0; - } - - if (!strncmp("lzo", value, 3)) { - type = BTRFS_COMPRESS_LZO; - btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); - } else if (!strncmp("zlib", value, 4)) { - type = BTRFS_COMPRESS_ZLIB; - } else if (!strncmp("zstd", value, len)) { - type = BTRFS_COMPRESS_ZSTD; - btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); - } else { - return -EINVAL; - } + int i; - BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS; - BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS; - BTRFS_I(inode)->prop_compress = type; + hash_init(prop_handlers_ht); - return 0; -} + for (i = 0; i < ARRAY_SIZE(prop_handlers); i++) { + struct prop_handler *p = &prop_handlers[i]; + u64 h = btrfs_name_hash(p->xattr_name, strlen(p->xattr_name)); -static const char *prop_compression_extract(struct inode *inode) -{ - switch (BTRFS_I(inode)->prop_compress) { - case BTRFS_COMPRESS_ZLIB: - case BTRFS_COMPRESS_LZO: - case BTRFS_COMPRESS_ZSTD: - return btrfs_compress_type2str(BTRFS_I(inode)->prop_compress); - default: - break; + hash_add(prop_handlers_ht, &p->node, h); } - - return NULL; } - diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h index 618815b4f9d5..40b2c65b518c 100644 --- a/fs/btrfs/props.h +++ b/fs/btrfs/props.h @@ -10,11 +10,10 @@ void __init btrfs_props_init(void); -int btrfs_set_prop(struct inode *inode, - const char *name, - const char *value, - size_t value_len, +int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, + const char *name, const char *value, size_t value_len, int flags); +int btrfs_validate_prop(const char *name, const char *value, size_t value_len); int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index e659d9d61107..2f708f2c4e67 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -918,8 +918,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) /* * initially create the quota tree */ - quota_root = btrfs_create_tree(trans, fs_info, - BTRFS_QUOTA_TREE_OBJECTID); + quota_root = btrfs_create_tree(trans, BTRFS_QUOTA_TREE_OBJECTID); if (IS_ERR(quota_root)) { ret = PTR_ERR(quota_root); btrfs_abort_transaction(trans, ret); @@ -1101,7 +1100,7 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) list_del("a_root->dirty_list); btrfs_tree_lock(quota_root->node); - clean_tree_block(fs_info, quota_root->node); + btrfs_clean_tree_block(quota_root->node); btrfs_tree_unlock(quota_root->node); btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 67a6f7d47402..f3d0576dd327 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1442,12 +1442,11 @@ static int fail_bio_stripe(struct btrfs_raid_bio *rbio, static void set_bio_pages_uptodate(struct bio *bio) { struct bio_vec *bvec; - int i; struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, i, iter_all) + bio_for_each_segment_all(bvec, bio, iter_all) SetPageUptodate(bvec->bv_page); } diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index d09b6cdb785a..e87cbdad02a3 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -205,28 +205,17 @@ static struct root_entry *lookup_root_entry(struct rb_root *root, u64 objectid) #ifdef CONFIG_STACKTRACE static void __save_stack_trace(struct ref_action *ra) { - struct stack_trace stack_trace; - - stack_trace.max_entries = MAX_TRACE; - stack_trace.nr_entries = 0; - stack_trace.entries = ra->trace; - stack_trace.skip = 2; - save_stack_trace(&stack_trace); - ra->trace_len = stack_trace.nr_entries; + ra->trace_len = stack_trace_save(ra->trace, MAX_TRACE, 2); } static void __print_stack_trace(struct btrfs_fs_info *fs_info, struct ref_action *ra) { - struct stack_trace trace; - if (ra->trace_len == 0) { btrfs_err(fs_info, " ref-verify: no stacktrace"); return; } - trace.nr_entries = ra->trace_len; - trace.entries = ra->trace; - print_stack_trace(&trace, 2); + stack_trace_print(ra->trace, ra->trace_len, 2); } #else static void inline __save_stack_trace(struct ref_action *ra) @@ -520,6 +509,7 @@ static int process_leaf(struct btrfs_root *root, switch (key.type) { case BTRFS_EXTENT_ITEM_KEY: *num_bytes = key.offset; + /* fall through */ case BTRFS_METADATA_ITEM_KEY: *bytenr = key.objectid; ret = process_extent_item(fs_info, path, &key, i, @@ -670,36 +660,43 @@ static void dump_block_entry(struct btrfs_fs_info *fs_info, /* * btrfs_ref_tree_mod: called when we modify a ref for a bytenr - * @root: the root we are making this modification from. - * @bytenr: the bytenr we are modifying. - * @num_bytes: number of bytes. - * @parent: the parent bytenr. - * @ref_root: the original root owner of the bytenr. - * @owner: level in the case of metadata, inode in the case of data. - * @offset: 0 for metadata, file offset for data. - * @action: the action that we are doing, this is the same as the delayed ref - * action. * * This will add an action item to the given bytenr and do sanity checks to make * sure we haven't messed something up. If we are making a new allocation and * this block entry has history we will delete all previous actions as long as * our sanity checks pass as they are no longer needed. */ -int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, - u64 parent, u64 ref_root, u64 owner, u64 offset, - int action) +int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, + struct btrfs_ref *generic_ref) { - struct btrfs_fs_info *fs_info = root->fs_info; struct ref_entry *ref = NULL, *exist; struct ref_action *ra = NULL; struct block_entry *be = NULL; struct root_entry *re = NULL; + int action = generic_ref->action; int ret = 0; - bool metadata = owner < BTRFS_FIRST_FREE_OBJECTID; + bool metadata; + u64 bytenr = generic_ref->bytenr; + u64 num_bytes = generic_ref->len; + u64 parent = generic_ref->parent; + u64 ref_root; + u64 owner; + u64 offset; - if (!btrfs_test_opt(root->fs_info, REF_VERIFY)) + if (!btrfs_test_opt(fs_info, REF_VERIFY)) return 0; + if (generic_ref->type == BTRFS_REF_METADATA) { + ref_root = generic_ref->tree_ref.root; + owner = generic_ref->tree_ref.level; + offset = 0; + } else { + ref_root = generic_ref->data_ref.ref_root; + owner = generic_ref->data_ref.ino; + offset = generic_ref->data_ref.offset; + } + metadata = owner < BTRFS_FIRST_FREE_OBJECTID; + ref = kzalloc(sizeof(struct ref_entry), GFP_NOFS); ra = kmalloc(sizeof(struct ref_action), GFP_NOFS); if (!ra || !ref) { @@ -732,7 +729,7 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, INIT_LIST_HEAD(&ra->list); ra->action = action; - ra->root = root->root_key.objectid; + ra->root = generic_ref->real_root; /* * This is an allocation, preallocate the block_entry in case we haven't @@ -745,7 +742,7 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, * is and the new root objectid, so let's not treat the passed * in root as if it really has a ref for this bytenr. */ - be = add_block_entry(root->fs_info, bytenr, num_bytes, ref_root); + be = add_block_entry(fs_info, bytenr, num_bytes, ref_root); if (IS_ERR(be)) { kfree(ra); ret = PTR_ERR(be); @@ -787,13 +784,13 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, * one we want to lookup below when we modify the * re->num_refs. */ - ref_root = root->root_key.objectid; - re->root_objectid = root->root_key.objectid; + ref_root = generic_ref->real_root; + re->root_objectid = generic_ref->real_root; re->num_refs = 0; } - spin_lock(&root->fs_info->ref_verify_lock); - be = lookup_block_entry(&root->fs_info->block_tree, bytenr); + spin_lock(&fs_info->ref_verify_lock); + be = lookup_block_entry(&fs_info->block_tree, bytenr); if (!be) { btrfs_err(fs_info, "trying to do action %d to bytenr %llu num_bytes %llu but there is no existing entry!", @@ -862,7 +859,7 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, * didn't think of some other corner case. */ btrfs_err(fs_info, "failed to find root %llu for %llu", - root->root_key.objectid, be->bytenr); + generic_ref->real_root, be->bytenr); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); kfree(ra); @@ -881,7 +878,7 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, list_add_tail(&ra->list, &be->actions); ret = 0; out_unlock: - spin_unlock(&root->fs_info->ref_verify_lock); + spin_unlock(&fs_info->ref_verify_lock); out: if (ret) btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); diff --git a/fs/btrfs/ref-verify.h b/fs/btrfs/ref-verify.h index b7d2a4edfdb7..855de37719b5 100644 --- a/fs/btrfs/ref-verify.h +++ b/fs/btrfs/ref-verify.h @@ -9,9 +9,8 @@ #ifdef CONFIG_BTRFS_FS_REF_VERIFY int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info); void btrfs_free_ref_cache(struct btrfs_fs_info *fs_info); -int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, - u64 parent, u64 ref_root, u64 owner, u64 offset, - int action); +int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, + struct btrfs_ref *generic_ref); void btrfs_free_ref_tree_range(struct btrfs_fs_info *fs_info, u64 start, u64 len); @@ -30,9 +29,8 @@ static inline void btrfs_free_ref_cache(struct btrfs_fs_info *fs_info) { } -static inline int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, - u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, int action) +static inline int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, + struct btrfs_ref *generic_ref) { return 0; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index ddf028509931..a459ecddcce4 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1643,6 +1643,8 @@ int replace_file_extents(struct btrfs_trans_handle *trans, nritems = btrfs_header_nritems(leaf); for (i = 0; i < nritems; i++) { + struct btrfs_ref ref = { 0 }; + cond_resched(); btrfs_item_key_to_cpu(leaf, &key, i); if (key.type != BTRFS_EXTENT_DATA_KEY) @@ -1703,18 +1705,23 @@ int replace_file_extents(struct btrfs_trans_handle *trans, dirty = 1; key.offset -= btrfs_file_extent_offset(leaf, fi); - ret = btrfs_inc_extent_ref(trans, root, new_bytenr, - num_bytes, parent, - btrfs_header_owner(leaf), - key.objectid, key.offset); + btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr, + num_bytes, parent); + ref.real_root = root->root_key.objectid; + btrfs_init_data_ref(&ref, btrfs_header_owner(leaf), + key.objectid, key.offset); + ret = btrfs_inc_extent_ref(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); break; } - ret = btrfs_free_extent(trans, root, bytenr, num_bytes, - parent, btrfs_header_owner(leaf), - key.objectid, key.offset); + btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr, + num_bytes, parent); + ref.real_root = root->root_key.objectid; + btrfs_init_data_ref(&ref, btrfs_header_owner(leaf), + key.objectid, key.offset); + ret = btrfs_free_extent(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); break; @@ -1756,6 +1763,7 @@ int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc, struct btrfs_fs_info *fs_info = dest->fs_info; struct extent_buffer *eb; struct extent_buffer *parent; + struct btrfs_ref ref = { 0 }; struct btrfs_key key; u64 old_bytenr; u64 new_bytenr; @@ -1916,23 +1924,31 @@ again: path->slots[level], old_ptr_gen); btrfs_mark_buffer_dirty(path->nodes[level]); - ret = btrfs_inc_extent_ref(trans, src, old_bytenr, - blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0); + btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, old_bytenr, + blocksize, path->nodes[level]->start); + ref.skip_qgroup = true; + btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid); + ret = btrfs_inc_extent_ref(trans, &ref); BUG_ON(ret); - ret = btrfs_inc_extent_ref(trans, dest, new_bytenr, - blocksize, 0, dest->root_key.objectid, - level - 1, 0); + btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr, + blocksize, 0); + ref.skip_qgroup = true; + btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid); + ret = btrfs_inc_extent_ref(trans, &ref); BUG_ON(ret); - ret = btrfs_free_extent(trans, src, new_bytenr, blocksize, - path->nodes[level]->start, - src->root_key.objectid, level - 1, 0); + btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, new_bytenr, + blocksize, path->nodes[level]->start); + btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid); + ref.skip_qgroup = true; + ret = btrfs_free_extent(trans, &ref); BUG_ON(ret); - ret = btrfs_free_extent(trans, dest, old_bytenr, blocksize, - 0, dest->root_key.objectid, level - 1, - 0); + btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, old_bytenr, + blocksize, 0); + btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid); + ref.skip_qgroup = true; + ret = btrfs_free_extent(trans, &ref); BUG_ON(ret); btrfs_unlock_up_safe(path, 0); @@ -2721,6 +2737,7 @@ static int do_relocation(struct btrfs_trans_handle *trans, rc->backref_cache.path[node->level] = node; list_for_each_entry(edge, &node->upper, list[LOWER]) { struct btrfs_key first_key; + struct btrfs_ref ref = { 0 }; cond_resched(); @@ -2826,11 +2843,13 @@ static int do_relocation(struct btrfs_trans_handle *trans, trans->transid); btrfs_mark_buffer_dirty(upper->eb); - ret = btrfs_inc_extent_ref(trans, root, - node->eb->start, blocksize, - upper->eb->start, - btrfs_header_owner(upper->eb), - node->level, 0); + btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, + node->eb->start, blocksize, + upper->eb->start); + ref.real_root = root->root_key.objectid; + btrfs_init_tree_ref(&ref, node->level, + btrfs_header_owner(upper->eb)); + ret = btrfs_inc_extent_ref(trans, &ref); BUG_ON(ret); ret = btrfs_drop_subtree(trans, root, eb, upper->eb); @@ -4222,7 +4241,7 @@ out: return inode; } -static struct reloc_control *alloc_reloc_control(void) +static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info) { struct reloc_control *rc; @@ -4234,7 +4253,8 @@ static struct reloc_control *alloc_reloc_control(void) INIT_LIST_HEAD(&rc->dirty_subvol_roots); backref_cache_init(&rc->backref_cache); mapping_tree_init(&rc->reloc_root_tree); - extent_io_tree_init(&rc->processed_blocks, NULL); + extent_io_tree_init(fs_info, &rc->processed_blocks, + IO_TREE_RELOC_BLOCKS, NULL); return rc; } @@ -4276,7 +4296,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) return -ETXTBSY; } - rc = alloc_reloc_control(); + rc = alloc_reloc_control(fs_info); if (!rc) { btrfs_put_block_group(bg); return -ENOMEM; @@ -4298,7 +4318,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) goto out; } - inode = lookup_free_space_inode(fs_info, rc->block_group, path); + inode = lookup_free_space_inode(rc->block_group, path); btrfs_free_path(path); if (!IS_ERR(inode)) @@ -4330,27 +4350,36 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) mutex_lock(&fs_info->cleaner_mutex); ret = relocate_block_group(rc); mutex_unlock(&fs_info->cleaner_mutex); - if (ret < 0) { + if (ret < 0) err = ret; - goto out; - } - - if (rc->extents_found == 0) - break; - - btrfs_info(fs_info, "found %llu extents", rc->extents_found); + /* + * We may have gotten ENOSPC after we already dirtied some + * extents. If writeout happens while we're relocating a + * different block group we could end up hitting the + * BUG_ON(rc->stage == UPDATE_DATA_PTRS) in + * btrfs_reloc_cow_block. Make sure we write everything out + * properly so we don't trip over this problem, and then break + * out of the loop if we hit an error. + */ if (rc->stage == MOVE_DATA_EXTENTS && rc->found_file_extent) { ret = btrfs_wait_ordered_range(rc->data_inode, 0, (u64)-1); - if (ret) { + if (ret) err = ret; - goto out; - } invalidate_mapping_pages(rc->data_inode->i_mapping, 0, -1); rc->stage = UPDATE_DATA_PTRS; } + + if (err < 0) + goto out; + + if (rc->extents_found == 0) + break; + + btrfs_info(fs_info, "found %llu extents", rc->extents_found); + } WARN_ON(rc->block_group->pinned > 0); @@ -4472,7 +4501,7 @@ int btrfs_recover_relocation(struct btrfs_root *root) if (list_empty(&reloc_roots)) goto out; - rc = alloc_reloc_control(); + rc = alloc_reloc_control(fs_info); if (!rc) { err = -ENOMEM; goto out; @@ -4594,7 +4623,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len) new_bytenr = ordered->start + (sums->bytenr - disk_bytenr); sums->bytenr = new_bytenr; - btrfs_add_ordered_sum(inode, ordered, sums); + btrfs_add_ordered_sum(ordered, sums); } out: btrfs_put_ordered_extent(ordered); @@ -4667,14 +4696,12 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending, u64 *bytes_to_reserve) { - struct btrfs_root *root; - struct reloc_control *rc; + struct btrfs_root *root = pending->root; + struct reloc_control *rc = root->fs_info->reloc_ctl; - root = pending->root; - if (!root->reloc_root) + if (!root->reloc_root || !rc) return; - rc = root->fs_info->reloc_ctl; if (!rc->merge_reloc_tree) return; @@ -4703,10 +4730,10 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans, struct btrfs_root *root = pending->root; struct btrfs_root *reloc_root; struct btrfs_root *new_root; - struct reloc_control *rc; + struct reloc_control *rc = root->fs_info->reloc_ctl; int ret; - if (!root->reloc_root) + if (!root->reloc_root || !rc) return 0; rc = root->fs_info->reloc_ctl; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 893d12fbfda0..1b9a5d0de139 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -137,11 +137,14 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root goto out; } - if (ret != 0) { - btrfs_print_leaf(path->nodes[0]); - btrfs_crit(fs_info, "unable to update root key %llu %u %llu", - key->objectid, key->type, key->offset); - BUG_ON(1); + if (ret > 0) { + btrfs_crit(fs_info, + "unable to find root key (%llu %u %llu) in tree %llu", + key->objectid, key->type, key->offset, + root->root_key.objectid); + ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); + goto out; } l = path->nodes[0]; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index a99588536c79..f7b29f9db5e2 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3791,7 +3791,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, struct btrfs_workqueue *scrub_parity = NULL; if (btrfs_fs_closing(fs_info)) - return -EINVAL; + return -EAGAIN; if (fs_info->nodesize > BTRFS_STRIPE_LEN) { /* @@ -3999,9 +3999,9 @@ int btrfs_scrub_cancel(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_scrub_cancel_dev(struct btrfs_fs_info *fs_info, - struct btrfs_device *dev) +int btrfs_scrub_cancel_dev(struct btrfs_device *dev) { + struct btrfs_fs_info *fs_info = dev->fs_info; struct scrub_ctx *sctx; mutex_lock(&fs_info->scrub_lock); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7ea2d6b1f170..dd38dfe174df 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1160,7 +1160,6 @@ out: struct backref_ctx { struct send_ctx *sctx; - struct btrfs_path *path; /* number of total found references */ u64 found; @@ -1213,8 +1212,6 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_) { struct backref_ctx *bctx = ctx_; struct clone_root *found; - int ret; - u64 i_size; /* First check if the root is in the list of accepted clone sources */ found = bsearch((void *)(uintptr_t)root, bctx->sctx->clone_roots, @@ -1231,19 +1228,6 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_) } /* - * There are inodes that have extents that lie behind its i_size. Don't - * accept clones from these extents. - */ - ret = __get_inode_info(found->root, bctx->path, ino, &i_size, NULL, NULL, - NULL, NULL, NULL); - btrfs_release_path(bctx->path); - if (ret < 0) - return ret; - - if (offset + bctx->data_offset + bctx->extent_len > i_size) - return 0; - - /* * Make sure we don't consider clones from send_root that are * behind the current inode/offset. */ @@ -1319,8 +1303,6 @@ static int find_extent_clone(struct send_ctx *sctx, goto out; } - backref_ctx->path = tmp_path; - if (data_offset >= ino_size) { /* * There may be extents that lie behind the file's size. @@ -5082,6 +5064,7 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *path; struct btrfs_key key; int ret; + u64 clone_src_i_size; /* * Prevent cloning from a zero offset with a length matching the sector @@ -5107,6 +5090,16 @@ static int clone_range(struct send_ctx *sctx, return -ENOMEM; /* + * There are inodes that have extents that lie behind its i_size. Don't + * accept clones from these extents. + */ + ret = __get_inode_info(clone_root->root, path, clone_root->ino, + &clone_src_i_size, NULL, NULL, NULL, NULL, NULL); + btrfs_release_path(path); + if (ret < 0) + goto out; + + /* * We can't send a clone operation for the entire range if we find * extent items in the respective range in the source file that * refer to different extents or if we find holes. @@ -5148,6 +5141,7 @@ static int clone_range(struct send_ctx *sctx, u8 type; u64 ext_len; u64 clone_len; + u64 clone_data_offset; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(clone_root->root, path); @@ -5201,10 +5195,30 @@ static int clone_range(struct send_ctx *sctx, if (key.offset >= clone_root->offset + len) break; + if (key.offset >= clone_src_i_size) + break; + + if (key.offset + ext_len > clone_src_i_size) + ext_len = clone_src_i_size - key.offset; + + clone_data_offset = btrfs_file_extent_offset(leaf, ei); + if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte) { + clone_root->offset = key.offset; + if (clone_data_offset < data_offset && + clone_data_offset + ext_len > data_offset) { + u64 extent_offset; + + extent_offset = data_offset - clone_data_offset; + ext_len -= extent_offset; + clone_data_offset += extent_offset; + clone_root->offset += extent_offset; + } + } + clone_len = min_t(u64, ext_len, len); if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte && - btrfs_file_extent_offset(leaf, ei) == data_offset) + clone_data_offset == data_offset) ret = send_clone(sctx, offset, clone_len, clone_root); else ret = send_extent_data(sctx, offset, clone_len); @@ -6579,6 +6593,38 @@ commit_trans: return btrfs_commit_transaction(trans); } +/* + * Make sure any existing dellaloc is flushed for any root used by a send + * operation so that we do not miss any data and we do not race with writeback + * finishing and changing a tree while send is using the tree. This could + * happen if a subvolume is in RW mode, has delalloc, is turned to RO mode and + * a send operation then uses the subvolume. + * After flushing delalloc ensure_commit_roots_uptodate() must be called. + */ +static int flush_delalloc_roots(struct send_ctx *sctx) +{ + struct btrfs_root *root = sctx->parent_root; + int ret; + int i; + + if (root) { + ret = btrfs_start_delalloc_snapshot(root); + if (ret) + return ret; + btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); + } + + for (i = 0; i < sctx->clone_roots_cnt; i++) { + root = sctx->clone_roots[i].root; + ret = btrfs_start_delalloc_snapshot(root); + if (ret) + return ret; + btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); + } + + return 0; +} + static void btrfs_root_dec_send_in_progress(struct btrfs_root* root) { spin_lock(&root->root_item_lock); @@ -6594,6 +6640,13 @@ static void btrfs_root_dec_send_in_progress(struct btrfs_root* root) spin_unlock(&root->root_item_lock); } +static void dedupe_in_progress_warn(const struct btrfs_root *root) +{ + btrfs_warn_rl(root->fs_info, +"cannot use root %llu for send while deduplications on it are in progress (%d in progress)", + root->root_key.objectid, root->dedupe_in_progress); +} + long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) { int ret = 0; @@ -6617,6 +6670,11 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) * making it RW. This also protects against deletion. */ spin_lock(&send_root->root_item_lock); + if (btrfs_root_readonly(send_root) && send_root->dedupe_in_progress) { + dedupe_in_progress_warn(send_root); + spin_unlock(&send_root->root_item_lock); + return -EAGAIN; + } send_root->send_in_progress++; spin_unlock(&send_root->root_item_lock); @@ -6751,6 +6809,13 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) ret = -EPERM; goto out; } + if (clone_root->dedupe_in_progress) { + dedupe_in_progress_warn(clone_root); + spin_unlock(&clone_root->root_item_lock); + srcu_read_unlock(&fs_info->subvol_srcu, index); + ret = -EAGAIN; + goto out; + } clone_root->send_in_progress++; spin_unlock(&clone_root->root_item_lock); srcu_read_unlock(&fs_info->subvol_srcu, index); @@ -6785,6 +6850,13 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) ret = -EPERM; goto out; } + if (sctx->parent_root->dedupe_in_progress) { + dedupe_in_progress_warn(sctx->parent_root); + spin_unlock(&sctx->parent_root->root_item_lock); + srcu_read_unlock(&fs_info->subvol_srcu, index); + ret = -EAGAIN; + goto out; + } spin_unlock(&sctx->parent_root->root_item_lock); srcu_read_unlock(&fs_info->subvol_srcu, index); @@ -6803,6 +6875,10 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) NULL); sort_clone_roots = 1; + ret = flush_delalloc_roots(sctx); + if (ret) + goto out; + ret = ensure_commit_roots_uptodate(sctx); if (ret) goto out; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 120e4340792a..0645ec428b4f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1400,7 +1400,7 @@ static inline int is_subvolume_inode(struct inode *inode) } static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid, - const char *device_name, struct vfsmount *mnt) + struct vfsmount *mnt) { struct dentry *root; int ret; @@ -1649,7 +1649,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } /* mount_subvol() will free subvol_name and mnt_root */ - root = mount_subvol(subvol_name, subvol_objectid, device_name, mnt_root); + root = mount_subvol(subvol_name, subvol_objectid, mnt_root); out: return root; @@ -2298,6 +2298,7 @@ static const struct super_operations btrfs_super_ops = { .show_devname = btrfs_show_devname, .alloc_inode = btrfs_alloc_inode, .destroy_inode = btrfs_destroy_inode, + .free_inode = btrfs_free_inode, .statfs = btrfs_statfs, .remount_fs = btrfs_remount, .freeze_fs = btrfs_freeze, diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 8a59597f1883..9238fd4f1734 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -17,6 +17,16 @@ static struct vfsmount *test_mnt = NULL; +const char *test_error[] = { + [TEST_ALLOC_FS_INFO] = "cannot allocate fs_info", + [TEST_ALLOC_ROOT] = "cannot allocate root", + [TEST_ALLOC_EXTENT_BUFFER] = "cannot extent buffer", + [TEST_ALLOC_PATH] = "cannot allocate path", + [TEST_ALLOC_INODE] = "cannot allocate inode", + [TEST_ALLOC_BLOCK_GROUP] = "cannot allocate block group", + [TEST_ALLOC_EXTENT_MAP] = "cannot allocate extent map", +}; + static const struct super_operations btrfs_test_super_ops = { .alloc_inode = btrfs_alloc_inode, .destroy_inode = btrfs_test_destroy_inode, @@ -99,7 +109,6 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize) spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->qgroup_lock); - spin_lock_init(&fs_info->qgroup_op_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->tree_mod_seq_lock); @@ -115,8 +124,10 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize) INIT_LIST_HEAD(&fs_info->tree_mod_seq_list); INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC); INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); - extent_io_tree_init(&fs_info->freed_extents[0], NULL); - extent_io_tree_init(&fs_info->freed_extents[1], NULL); + extent_io_tree_init(fs_info, &fs_info->freed_extents[0], + IO_TREE_FS_INFO_FREED_EXTENTS0, NULL); + extent_io_tree_init(fs_info, &fs_info->freed_extents[1], + IO_TREE_FS_INFO_FREED_EXTENTS1, NULL); fs_info->pinned_extents = &fs_info->freed_extents[0]; set_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state); diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h index 70ff9f9d86a1..ee277bbd939b 100644 --- a/fs/btrfs/tests/btrfs-tests.h +++ b/fs/btrfs/tests/btrfs-tests.h @@ -10,7 +10,22 @@ int btrfs_run_sanity_tests(void); #define test_msg(fmt, ...) pr_info("BTRFS: selftest: " fmt "\n", ##__VA_ARGS__) -#define test_err(fmt, ...) pr_err("BTRFS: selftest: " fmt "\n", ##__VA_ARGS__) +#define test_err(fmt, ...) pr_err("BTRFS: selftest: %s:%d " fmt "\n", \ + __FILE__, __LINE__, ##__VA_ARGS__) + +#define test_std_err(index) test_err("%s", test_error[index]) + +enum { + TEST_ALLOC_FS_INFO, + TEST_ALLOC_ROOT, + TEST_ALLOC_EXTENT_BUFFER, + TEST_ALLOC_PATH, + TEST_ALLOC_INODE, + TEST_ALLOC_BLOCK_GROUP, + TEST_ALLOC_EXTENT_MAP, +}; + +extern const char *test_error[]; struct btrfs_root; struct btrfs_trans_handle; diff --git a/fs/btrfs/tests/extent-buffer-tests.c b/fs/btrfs/tests/extent-buffer-tests.c index 7d72eab6d32c..a1b9f9b5978e 100644 --- a/fs/btrfs/tests/extent-buffer-tests.c +++ b/fs/btrfs/tests/extent-buffer-tests.c @@ -30,27 +30,27 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize) fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { - test_err("could not allocate fs_info"); + test_std_err(TEST_ALLOC_FS_INFO); return -ENOMEM; } root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(root)) { - test_err("could not allocate root"); + test_std_err(TEST_ALLOC_ROOT); ret = PTR_ERR(root); goto out; } path = btrfs_alloc_path(); if (!path) { - test_err("could not allocate path"); + test_std_err(TEST_ALLOC_PATH); ret = -ENOMEM; goto out; } path->nodes[0] = eb = alloc_dummy_extent_buffer(fs_info, nodesize); if (!eb) { - test_err("could not allocate dummy buffer"); + test_std_err(TEST_ALLOC_EXTENT_BUFFER); ret = -ENOMEM; goto out; } diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 3c46d7f23456..7bf4d5734dbe 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -73,11 +73,15 @@ static int test_find_delalloc(u32 sectorsize) inode = btrfs_new_test_inode(); if (!inode) { - test_err("failed to allocate test inode"); + test_std_err(TEST_ALLOC_INODE); return -ENOMEM; } - extent_io_tree_init(&tmp, NULL); + /* + * Passing NULL as we don't have fs_info but tracepoints are not used + * at this point + */ + extent_io_tree_init(NULL, &tmp, IO_TREE_SELFTEST, NULL); /* * First go through and create and mark all of our pages dirty, we pin @@ -374,8 +378,8 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize) { struct btrfs_fs_info *fs_info; unsigned long len; - unsigned long *bitmap; - struct extent_buffer *eb; + unsigned long *bitmap = NULL; + struct extent_buffer *eb = NULL; int ret; test_msg("running extent buffer bitmap tests"); @@ -388,18 +392,23 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize) ? sectorsize * 4 : sectorsize; fs_info = btrfs_alloc_dummy_fs_info(len, len); + if (!fs_info) { + test_std_err(TEST_ALLOC_FS_INFO); + return -ENOMEM; + } bitmap = kmalloc(len, GFP_KERNEL); if (!bitmap) { test_err("couldn't allocate test bitmap"); - return -ENOMEM; + ret = -ENOMEM; + goto out; } eb = __alloc_dummy_extent_buffer(fs_info, 0, len); if (!eb) { - test_err("couldn't allocate test extent buffer"); - kfree(bitmap); - return -ENOMEM; + test_std_err(TEST_ALLOC_ROOT); + ret = -ENOMEM; + goto out; } ret = __test_eb_bitmaps(bitmap, eb, len); @@ -408,17 +417,18 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize) /* Do it over again with an extent buffer which isn't page-aligned. */ free_extent_buffer(eb); - eb = __alloc_dummy_extent_buffer(NULL, nodesize / 2, len); + eb = __alloc_dummy_extent_buffer(fs_info, nodesize / 2, len); if (!eb) { - test_err("couldn't allocate test extent buffer"); - kfree(bitmap); - return -ENOMEM; + test_std_err(TEST_ALLOC_ROOT); + ret = -ENOMEM; + goto out; } ret = __test_eb_bitmaps(bitmap, eb, len); out: free_extent_buffer(eb); kfree(bitmap); + btrfs_free_dummy_fs_info(fs_info); return ret; } @@ -434,6 +444,5 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize) ret = test_eb_bitmaps(sectorsize, nodesize); out: - test_msg("extent I/O tests finished"); return ret; } diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index bf15d3a7f20e..87aeabe9d610 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -47,7 +47,7 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree) * ->add_extent_mapping(0, 16K) * -> #handle -EEXIST */ -static void test_case_1(struct btrfs_fs_info *fs_info, +static int test_case_1(struct btrfs_fs_info *fs_info, struct extent_map_tree *em_tree) { struct extent_map *em; @@ -56,9 +56,10 @@ static void test_case_1(struct btrfs_fs_info *fs_info, int ret; em = alloc_extent_map(); - if (!em) - /* Skip the test on error. */ - return; + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + return -ENOMEM; + } /* Add [0, 16K) */ em->start = 0; @@ -66,25 +67,37 @@ static void test_case_1(struct btrfs_fs_info *fs_info, em->block_start = 0; em->block_len = SZ_16K; ret = add_extent_mapping(em_tree, em, 0); - ASSERT(ret == 0); + if (ret < 0) { + test_err("cannot add extent range [0, 16K)"); + goto out; + } free_extent_map(em); /* Add [16K, 20K) following [0, 16K) */ em = alloc_extent_map(); - if (!em) + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + ret = -ENOMEM; goto out; + } em->start = SZ_16K; em->len = SZ_4K; em->block_start = SZ_32K; /* avoid merging */ em->block_len = SZ_4K; ret = add_extent_mapping(em_tree, em, 0); - ASSERT(ret == 0); + if (ret < 0) { + test_err("cannot add extent range [16K, 20K)"); + goto out; + } free_extent_map(em); em = alloc_extent_map(); - if (!em) + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + ret = -ENOMEM; goto out; + } /* Add [0, 8K), should return [0, 16K) instead. */ em->start = start; @@ -92,19 +105,24 @@ static void test_case_1(struct btrfs_fs_info *fs_info, em->block_start = start; em->block_len = len; ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len); - if (ret) + if (ret) { test_err("case1 [%llu %llu]: ret %d", start, start + len, ret); + goto out; + } if (em && (em->start != 0 || extent_map_end(em) != SZ_16K || - em->block_start != 0 || em->block_len != SZ_16K)) + em->block_start != 0 || em->block_len != SZ_16K)) { test_err( "case1 [%llu %llu]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu", start, start + len, ret, em->start, em->len, em->block_start, em->block_len); + ret = -EINVAL; + } free_extent_map(em); out: - /* free memory */ free_extent_map_tree(em_tree); + + return ret; } /* @@ -113,16 +131,17 @@ out: * Reading the inline ending up with EEXIST, ie. read an inline * extent and discard page cache and read it again. */ -static void test_case_2(struct btrfs_fs_info *fs_info, +static int test_case_2(struct btrfs_fs_info *fs_info, struct extent_map_tree *em_tree) { struct extent_map *em; int ret; em = alloc_extent_map(); - if (!em) - /* Skip the test on error. */ - return; + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + return -ENOMEM; + } /* Add [0, 1K) */ em->start = 0; @@ -130,25 +149,37 @@ static void test_case_2(struct btrfs_fs_info *fs_info, em->block_start = EXTENT_MAP_INLINE; em->block_len = (u64)-1; ret = add_extent_mapping(em_tree, em, 0); - ASSERT(ret == 0); + if (ret < 0) { + test_err("cannot add extent range [0, 1K)"); + goto out; + } free_extent_map(em); - /* Add [4K, 4K) following [0, 1K) */ + /* Add [4K, 8K) following [0, 1K) */ em = alloc_extent_map(); - if (!em) + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + ret = -ENOMEM; goto out; + } em->start = SZ_4K; em->len = SZ_4K; em->block_start = SZ_4K; em->block_len = SZ_4K; ret = add_extent_mapping(em_tree, em, 0); - ASSERT(ret == 0); + if (ret < 0) { + test_err("cannot add extent range [4K, 8K)"); + goto out; + } free_extent_map(em); em = alloc_extent_map(); - if (!em) + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + ret = -ENOMEM; goto out; + } /* Add [0, 1K) */ em->start = 0; @@ -156,22 +187,27 @@ static void test_case_2(struct btrfs_fs_info *fs_info, em->block_start = EXTENT_MAP_INLINE; em->block_len = (u64)-1; ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len); - if (ret) + if (ret) { test_err("case2 [0 1K]: ret %d", ret); + goto out; + } if (em && (em->start != 0 || extent_map_end(em) != SZ_1K || - em->block_start != EXTENT_MAP_INLINE || em->block_len != (u64)-1)) + em->block_start != EXTENT_MAP_INLINE || em->block_len != (u64)-1)) { test_err( "case2 [0 1K]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu", ret, em->start, em->len, em->block_start, em->block_len); + ret = -EINVAL; + } free_extent_map(em); out: - /* free memory */ free_extent_map_tree(em_tree); + + return ret; } -static void __test_case_3(struct btrfs_fs_info *fs_info, +static int __test_case_3(struct btrfs_fs_info *fs_info, struct extent_map_tree *em_tree, u64 start) { struct extent_map *em; @@ -179,9 +215,10 @@ static void __test_case_3(struct btrfs_fs_info *fs_info, int ret; em = alloc_extent_map(); - if (!em) - /* Skip this test on error. */ - return; + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + return -ENOMEM; + } /* Add [4K, 8K) */ em->start = SZ_4K; @@ -189,12 +226,18 @@ static void __test_case_3(struct btrfs_fs_info *fs_info, em->block_start = SZ_4K; em->block_len = SZ_4K; ret = add_extent_mapping(em_tree, em, 0); - ASSERT(ret == 0); + if (ret < 0) { + test_err("cannot add extent range [4K, 8K)"); + goto out; + } free_extent_map(em); em = alloc_extent_map(); - if (!em) + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + ret = -ENOMEM; goto out; + } /* Add [0, 16K) */ em->start = 0; @@ -202,24 +245,29 @@ static void __test_case_3(struct btrfs_fs_info *fs_info, em->block_start = 0; em->block_len = SZ_16K; ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len); - if (ret) + if (ret) { test_err("case3 [0x%llx 0x%llx): ret %d", start, start + len, ret); + goto out; + } /* * Since bytes within em are contiguous, em->block_start is identical to * em->start. */ if (em && (start < em->start || start + len > extent_map_end(em) || - em->start != em->block_start || em->len != em->block_len)) + em->start != em->block_start || em->len != em->block_len)) { test_err( "case3 [0x%llx 0x%llx): ret %d em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)", start, start + len, ret, em->start, em->len, em->block_start, em->block_len); + ret = -EINVAL; + } free_extent_map(em); out: - /* free memory */ free_extent_map_tree(em_tree); + + return ret; } /* @@ -238,15 +286,23 @@ out: * -> add_extent_mapping() * -> add_extent_mapping() */ -static void test_case_3(struct btrfs_fs_info *fs_info, +static int test_case_3(struct btrfs_fs_info *fs_info, struct extent_map_tree *em_tree) { - __test_case_3(fs_info, em_tree, 0); - __test_case_3(fs_info, em_tree, SZ_8K); - __test_case_3(fs_info, em_tree, (12 * 1024ULL)); + int ret; + + ret = __test_case_3(fs_info, em_tree, 0); + if (ret) + return ret; + ret = __test_case_3(fs_info, em_tree, SZ_8K); + if (ret) + return ret; + ret = __test_case_3(fs_info, em_tree, (12 * SZ_1K)); + + return ret; } -static void __test_case_4(struct btrfs_fs_info *fs_info, +static int __test_case_4(struct btrfs_fs_info *fs_info, struct extent_map_tree *em_tree, u64 start) { struct extent_map *em; @@ -254,9 +310,10 @@ static void __test_case_4(struct btrfs_fs_info *fs_info, int ret; em = alloc_extent_map(); - if (!em) - /* Skip this test on error. */ - return; + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + return -ENOMEM; + } /* Add [0K, 8K) */ em->start = 0; @@ -264,44 +321,60 @@ static void __test_case_4(struct btrfs_fs_info *fs_info, em->block_start = 0; em->block_len = SZ_8K; ret = add_extent_mapping(em_tree, em, 0); - ASSERT(ret == 0); + if (ret < 0) { + test_err("cannot add extent range [0, 8K)"); + goto out; + } free_extent_map(em); em = alloc_extent_map(); - if (!em) + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + ret = -ENOMEM; goto out; + } - /* Add [8K, 24K) */ + /* Add [8K, 32K) */ em->start = SZ_8K; - em->len = 24 * 1024ULL; + em->len = 24 * SZ_1K; em->block_start = SZ_16K; /* avoid merging */ - em->block_len = 24 * 1024ULL; + em->block_len = 24 * SZ_1K; ret = add_extent_mapping(em_tree, em, 0); - ASSERT(ret == 0); + if (ret < 0) { + test_err("cannot add extent range [8K, 32K)"); + goto out; + } free_extent_map(em); em = alloc_extent_map(); - if (!em) + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + ret = -ENOMEM; goto out; + } /* Add [0K, 32K) */ em->start = 0; em->len = SZ_32K; em->block_start = 0; em->block_len = SZ_32K; ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len); - if (ret) + if (ret) { test_err("case4 [0x%llx 0x%llx): ret %d", start, len, ret); - if (em && - (start < em->start || start + len > extent_map_end(em))) + goto out; + } + if (em && (start < em->start || start + len > extent_map_end(em))) { test_err( "case4 [0x%llx 0x%llx): ret %d, added wrong em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)", start, len, ret, em->start, em->len, em->block_start, em->block_len); + ret = -EINVAL; + } free_extent_map(em); out: - /* free memory */ free_extent_map_tree(em_tree); + + return ret; } /* @@ -329,17 +402,24 @@ out: * # handle -EEXIST when adding * # [0, 32K) */ -static void test_case_4(struct btrfs_fs_info *fs_info, +static int test_case_4(struct btrfs_fs_info *fs_info, struct extent_map_tree *em_tree) { - __test_case_4(fs_info, em_tree, 0); - __test_case_4(fs_info, em_tree, SZ_4K); + int ret; + + ret = __test_case_4(fs_info, em_tree, 0); + if (ret) + return ret; + ret = __test_case_4(fs_info, em_tree, SZ_4K); + + return ret; } int btrfs_test_extent_map(void) { struct btrfs_fs_info *fs_info = NULL; struct extent_map_tree *em_tree; + int ret = 0; test_msg("running extent_map tests"); @@ -349,25 +429,32 @@ int btrfs_test_extent_map(void) */ fs_info = btrfs_alloc_dummy_fs_info(PAGE_SIZE, PAGE_SIZE); if (!fs_info) { - test_msg("Couldn't allocate dummy fs info"); + test_std_err(TEST_ALLOC_FS_INFO); return -ENOMEM; } em_tree = kzalloc(sizeof(*em_tree), GFP_KERNEL); - if (!em_tree) - /* Skip the test on error. */ + if (!em_tree) { + ret = -ENOMEM; goto out; + } extent_map_tree_init(em_tree); - test_case_1(fs_info, em_tree); - test_case_2(fs_info, em_tree); - test_case_3(fs_info, em_tree); - test_case_4(fs_info, em_tree); + ret = test_case_1(fs_info, em_tree); + if (ret) + goto out; + ret = test_case_2(fs_info, em_tree); + if (ret) + goto out; + ret = test_case_3(fs_info, em_tree); + if (ret) + goto out; + ret = test_case_4(fs_info, em_tree); - kfree(em_tree); out: + kfree(em_tree); btrfs_free_dummy_fs_info(fs_info); - return 0; + return ret; } diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c index 5c2f77e9439b..af89f66f9e63 100644 --- a/fs/btrfs/tests/free-space-tests.c +++ b/fs/btrfs/tests/free-space-tests.c @@ -404,7 +404,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache, }; const struct btrfs_free_space_op *orig_free_space_ops; - test_msg("running space stealing from bitmap to extent"); + test_msg("running space stealing from bitmap to extent tests"); /* * For this test, we want to ensure we end up with an extent entry @@ -834,9 +834,10 @@ int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize) test_msg("running btrfs free space cache tests"); fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); - if (!fs_info) + if (!fs_info) { + test_std_err(TEST_ALLOC_FS_INFO); return -ENOMEM; - + } /* * For ppc64 (with 64k page size), bytes per bitmap might be @@ -846,13 +847,14 @@ int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize) cache = btrfs_alloc_dummy_block_group(fs_info, BITS_PER_BITMAP * sectorsize + PAGE_SIZE); if (!cache) { - test_err("couldn't run the tests"); + test_std_err(TEST_ALLOC_BLOCK_GROUP); btrfs_free_dummy_fs_info(fs_info); return 0; } root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(root)) { + test_std_err(TEST_ALLOC_ROOT); ret = PTR_ERR(root); goto out; } @@ -874,6 +876,5 @@ out: btrfs_free_dummy_block_group(cache); btrfs_free_dummy_root(root); btrfs_free_dummy_fs_info(fs_info); - test_msg("free space cache tests finished"); return ret; } diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index 89346da890cf..a90dad166971 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -30,7 +30,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans, unsigned int i; int ret; - info = search_free_space_info(trans, fs_info, cache, path, 0); + info = search_free_space_info(trans, cache, path, 0); if (IS_ERR(info)) { test_err("could not find free space info"); ret = PTR_ERR(info); @@ -115,7 +115,7 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans, u32 flags; int ret; - info = search_free_space_info(trans, fs_info, cache, path, 0); + info = search_free_space_info(trans, cache, path, 0); if (IS_ERR(info)) { test_err("could not find free space info"); btrfs_release_path(path); @@ -444,14 +444,14 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { - test_err("couldn't allocate dummy fs info"); + test_std_err(TEST_ALLOC_FS_INFO); ret = -ENOMEM; goto out; } root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(root)) { - test_err("couldn't allocate dummy root"); + test_std_err(TEST_ALLOC_ROOT); ret = PTR_ERR(root); goto out; } @@ -463,7 +463,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, root->node = alloc_test_extent_buffer(root->fs_info, nodesize); if (!root->node) { - test_err("couldn't allocate dummy buffer"); + test_std_err(TEST_ALLOC_EXTENT_BUFFER); ret = -ENOMEM; goto out; } @@ -473,7 +473,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, cache = btrfs_alloc_dummy_block_group(fs_info, 8 * alignment); if (!cache) { - test_err("couldn't allocate dummy block group cache"); + test_std_err(TEST_ALLOC_BLOCK_GROUP); ret = -ENOMEM; goto out; } @@ -486,7 +486,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, path = btrfs_alloc_path(); if (!path) { - test_err("couldn't allocate path"); + test_std_err(TEST_ALLOC_ROOT); ret = -ENOMEM; goto out; } @@ -539,7 +539,7 @@ static int run_test_both_formats(test_func_t test_func, u32 sectorsize, ret = run_test(test_func, 0, sectorsize, nodesize, alignment); if (ret) { test_err( - "%pf failed with extents, sectorsize=%u, nodesize=%u, alignment=%u", + "%ps failed with extents, sectorsize=%u, nodesize=%u, alignment=%u", test_func, sectorsize, nodesize, alignment); test_ret = ret; } @@ -547,7 +547,7 @@ static int run_test_both_formats(test_func_t test_func, u32 sectorsize, ret = run_test(test_func, 1, sectorsize, nodesize, alignment); if (ret) { test_err( - "%pf failed with bitmaps, sectorsize=%u, nodesize=%u, alignment=%u", + "%ps failed with bitmaps, sectorsize=%u, nodesize=%u, alignment=%u", test_func, sectorsize, nodesize, alignment); test_ret = ret; } diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index af0c8e30d9e2..bc6dbd1b42fd 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -226,31 +226,34 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) u64 offset; int ret = -ENOMEM; + test_msg("running btrfs_get_extent tests"); + inode = btrfs_new_test_inode(); if (!inode) { - test_err("couldn't allocate inode"); + test_std_err(TEST_ALLOC_INODE); return ret; } + inode->i_mode = S_IFREG; BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; BTRFS_I(inode)->location.offset = 0; fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { - test_err("couldn't allocate dummy fs info"); + test_std_err(TEST_ALLOC_FS_INFO); goto out; } root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(root)) { - test_err("couldn't allocate root"); + test_std_err(TEST_ALLOC_ROOT); goto out; } root->node = alloc_dummy_extent_buffer(fs_info, nodesize); if (!root->node) { - test_err("couldn't allocate dummy buffer"); + test_std_err(TEST_ALLOC_ROOT); goto out; } @@ -827,9 +830,11 @@ static int test_hole_first(u32 sectorsize, u32 nodesize) struct extent_map *em = NULL; int ret = -ENOMEM; + test_msg("running hole first btrfs_get_extent test"); + inode = btrfs_new_test_inode(); if (!inode) { - test_err("couldn't allocate inode"); + test_std_err(TEST_ALLOC_INODE); return ret; } @@ -839,19 +844,19 @@ static int test_hole_first(u32 sectorsize, u32 nodesize) fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { - test_err("couldn't allocate dummy fs info"); + test_std_err(TEST_ALLOC_FS_INFO); goto out; } root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(root)) { - test_err("couldn't allocate root"); + test_std_err(TEST_ALLOC_ROOT); goto out; } root->node = alloc_dummy_extent_buffer(fs_info, nodesize); if (!root->node) { - test_err("couldn't allocate dummy buffer"); + test_std_err(TEST_ALLOC_ROOT); goto out; } @@ -927,21 +932,23 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) struct btrfs_root *root = NULL; int ret = -ENOMEM; + test_msg("running outstanding_extents tests"); + inode = btrfs_new_test_inode(); if (!inode) { - test_err("couldn't allocate inode"); + test_std_err(TEST_ALLOC_INODE); return ret; } fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { - test_err("couldn't allocate dummy fs info"); + test_std_err(TEST_ALLOC_FS_INFO); goto out; } root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(root)) { - test_err("couldn't allocate root"); + test_std_err(TEST_ALLOC_ROOT); goto out; } @@ -1110,17 +1117,16 @@ int btrfs_test_inodes(u32 sectorsize, u32 nodesize) { int ret; + test_msg("running inode tests"); + set_bit(EXTENT_FLAG_COMPRESSED, &compressed_only); set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only); - test_msg("running btrfs_get_extent tests"); ret = test_btrfs_get_extent(sectorsize, nodesize); if (ret) return ret; - test_msg("running hole first btrfs_get_extent test"); ret = test_hole_first(sectorsize, nodesize); if (ret) return ret; - test_msg("running outstanding_extents tests"); return test_extent_accounting(sectorsize, nodesize); } diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 412b910b04cc..09aaca1efd62 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -32,7 +32,7 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr, path = btrfs_alloc_path(); if (!path) { - test_err("couldn't allocate path"); + test_std_err(TEST_ALLOC_ROOT); return -ENOMEM; } @@ -82,7 +82,7 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes, path = btrfs_alloc_path(); if (!path) { - test_err("couldn't allocate path"); + test_std_err(TEST_ALLOC_ROOT); return -ENOMEM; } @@ -132,7 +132,7 @@ static int remove_extent_item(struct btrfs_root *root, u64 bytenr, path = btrfs_alloc_path(); if (!path) { - test_err("couldn't allocate path"); + test_std_err(TEST_ALLOC_ROOT); return -ENOMEM; } path->leave_spinning = 1; @@ -166,7 +166,7 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr, path = btrfs_alloc_path(); if (!path) { - test_err("couldn't allocate path"); + test_std_err(TEST_ALLOC_ROOT); return -ENOMEM; } @@ -215,7 +215,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root, btrfs_init_dummy_trans(&trans, fs_info); - test_msg("qgroup basic add"); + test_msg("running qgroup add/remove tests"); ret = btrfs_create_qgroup(&trans, BTRFS_FS_TREE_OBJECTID); if (ret) { test_err("couldn't create a qgroup %d", ret); @@ -316,7 +316,7 @@ static int test_multiple_refs(struct btrfs_root *root, btrfs_init_dummy_trans(&trans, fs_info); - test_msg("qgroup multiple refs test"); + test_msg("running qgroup multiple refs test"); /* * We have BTRFS_FS_TREE_OBJECTID created already from the @@ -457,13 +457,13 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { - test_err("couldn't allocate dummy fs info"); + test_std_err(TEST_ALLOC_FS_INFO); return -ENOMEM; } root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(root)) { - test_err("couldn't allocate root"); + test_std_err(TEST_ALLOC_ROOT); ret = PTR_ERR(root); goto out; } @@ -495,7 +495,7 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) tmp_root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(tmp_root)) { - test_err("couldn't allocate a fs root"); + test_std_err(TEST_ALLOC_ROOT); ret = PTR_ERR(tmp_root); goto out; } @@ -510,7 +510,7 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) tmp_root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(tmp_root)) { - test_err("couldn't allocate a fs root"); + test_std_err(TEST_ALLOC_ROOT); ret = PTR_ERR(tmp_root); goto out; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index e4e665f422fc..3f6811cdf803 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -50,14 +50,6 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) btrfs_err(transaction->fs_info, "pending csums is %llu", transaction->delayed_refs.pending_csums); - while (!list_empty(&transaction->pending_chunks)) { - struct extent_map *em; - - em = list_first_entry(&transaction->pending_chunks, - struct extent_map, list); - list_del_init(&em->list); - free_extent_map(em); - } /* * If any block groups are found in ->deleted_bgs then it's * because the transaction was aborted and a commit did not @@ -75,39 +67,11 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) btrfs_put_block_group_trimming(cache); btrfs_put_block_group(cache); } + WARN_ON(!list_empty(&transaction->dev_update_list)); kfree(transaction); } } -static void clear_btree_io_tree(struct extent_io_tree *tree) -{ - spin_lock(&tree->lock); - /* - * Do a single barrier for the waitqueue_active check here, the state - * of the waitqueue should not change once clear_btree_io_tree is - * called. - */ - smp_mb(); - while (!RB_EMPTY_ROOT(&tree->state)) { - struct rb_node *node; - struct extent_state *state; - - node = rb_first(&tree->state); - state = rb_entry(node, struct extent_state, rb_node); - rb_erase(&state->rb_node, &tree->state); - RB_CLEAR_NODE(&state->rb_node); - /* - * btree io trees aren't supposed to have tasks waiting for - * changes in the flags of extent states ever. - */ - ASSERT(!waitqueue_active(&state->wq)); - free_extent_state(state); - - cond_resched_lock(&tree->lock); - } - spin_unlock(&tree->lock); -} - static noinline void switch_commit_roots(struct btrfs_transaction *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -121,7 +85,7 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans) root->commit_root = btrfs_root_node(root); if (is_fstree(root->root_key.objectid)) btrfs_unpin_free_ino(root); - clear_btree_io_tree(&root->dirty_log_pages); + extent_io_tree_release(&root->dirty_log_pages); btrfs_qgroup_clean_swapped_blocks(root); } @@ -263,19 +227,18 @@ loop: spin_lock_init(&cur_trans->delayed_refs.lock); INIT_LIST_HEAD(&cur_trans->pending_snapshots); - INIT_LIST_HEAD(&cur_trans->pending_chunks); + INIT_LIST_HEAD(&cur_trans->dev_update_list); INIT_LIST_HEAD(&cur_trans->switch_commits); INIT_LIST_HEAD(&cur_trans->dirty_bgs); INIT_LIST_HEAD(&cur_trans->io_bgs); INIT_LIST_HEAD(&cur_trans->dropped_roots); mutex_init(&cur_trans->cache_write_mutex); - cur_trans->num_dirty_bgs = 0; spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); spin_lock_init(&cur_trans->dropped_roots_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); - extent_io_tree_init(&cur_trans->dirty_pages, - fs_info->btree_inode); + extent_io_tree_init(fs_info, &cur_trans->dirty_pages, + IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode); fs_info->generation++; cur_trans->transid = fs_info->generation; fs_info->running_transaction = cur_trans; @@ -928,7 +891,7 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info, * superblock that points to btree nodes/leafs for which * writeback hasn't finished yet (and without errors). * We cleanup any entries left in the io tree when committing - * the transaction (through clear_btree_io_tree()). + * the transaction (through extent_io_tree_release()). */ if (err == -ENOMEM) { err = 0; @@ -973,7 +936,7 @@ static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info, * left in the io tree. For a log commit, we don't remove them * after committing the log because the tree can be accessed * concurrently - we do it only at transaction commit time when - * it's safe to do it (through clear_btree_io_tree()). + * it's safe to do it (through extent_io_tree_release()). */ err = clear_extent_bit(dirty_pages, start, end, EXTENT_NEED_WAIT, 0, 0, &cached_state); @@ -1051,7 +1014,7 @@ static int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans) blk_finish_plug(&plug); ret2 = btrfs_wait_extents(fs_info, dirty_pages); - clear_btree_io_tree(&trans->transaction->dirty_pages); + extent_io_tree_release(&trans->transaction->dirty_pages); if (ret) return ret; @@ -1130,17 +1093,17 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans) if (ret) return ret; - ret = btrfs_run_dev_stats(trans, fs_info); + ret = btrfs_run_dev_stats(trans); if (ret) return ret; - ret = btrfs_run_dev_replace(trans, fs_info); + ret = btrfs_run_dev_replace(trans); if (ret) return ret; ret = btrfs_run_qgroups(trans); if (ret) return ret; - ret = btrfs_setup_space_cache(trans, fs_info); + ret = btrfs_setup_space_cache(trans); if (ret) return ret; @@ -1168,7 +1131,7 @@ again: } while (!list_empty(dirty_bgs) || !list_empty(io_bgs)) { - ret = btrfs_write_dirty_block_groups(trans, fs_info); + ret = btrfs_write_dirty_block_groups(trans); if (ret) return ret; ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); @@ -2241,8 +2204,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) memcpy(fs_info->super_for_commit, fs_info->super_copy, sizeof(*fs_info->super_copy)); - btrfs_update_commit_device_size(fs_info); - btrfs_update_commit_device_bytes_used(cur_trans); + btrfs_commit_device_sizes(cur_trans); clear_bit(BTRFS_FS_LOG1_ERR, &fs_info->flags); clear_bit(BTRFS_FS_LOG2_ERR, &fs_info->flags); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index f1ba78949d1b..78c446c222b7 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -51,7 +51,7 @@ struct btrfs_transaction { wait_queue_head_t writer_wait; wait_queue_head_t commit_wait; struct list_head pending_snapshots; - struct list_head pending_chunks; + struct list_head dev_update_list; struct list_head switch_commits; struct list_head dirty_bgs; @@ -80,7 +80,6 @@ struct btrfs_transaction { */ struct mutex cache_write_mutex; spinlock_t dirty_bgs_lock; - unsigned int num_dirty_bgs; /* Protected by spin lock fs_info->unused_bgs_lock. */ struct list_head deleted_bgs; spinlock_t dropped_roots_lock; @@ -120,7 +119,6 @@ struct btrfs_trans_handle { bool allocating_chunk; bool can_flush_pending_bgs; bool reloc_reserved; - bool sync; bool dirty; struct btrfs_root *root; struct btrfs_fs_info *fs_info; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index a62e1e837a89..748cd1598255 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -15,6 +15,9 @@ * carefully reviewed otherwise so it does not prevent mount of valid images. */ +#include <linux/types.h> +#include <linux/stddef.h> +#include <linux/error-injection.h> #include "ctree.h" #include "tree-checker.h" #include "disk-io.h" @@ -41,12 +44,12 @@ * Append generic "corrupt leaf/node root=%llu block=%llu slot=%d: " to @fmt. * Allows callers to customize the output. */ -__printf(4, 5) +__printf(3, 4) __cold -static void generic_err(const struct btrfs_fs_info *fs_info, - const struct extent_buffer *eb, int slot, +static void generic_err(const struct extent_buffer *eb, int slot, const char *fmt, ...) { + const struct btrfs_fs_info *fs_info = eb->fs_info; struct va_format vaf; va_list args; @@ -66,12 +69,12 @@ static void generic_err(const struct btrfs_fs_info *fs_info, * Customized reporter for extent data item, since its key objectid and * offset has its own meaning. */ -__printf(4, 5) +__printf(3, 4) __cold -static void file_extent_err(const struct btrfs_fs_info *fs_info, - const struct extent_buffer *eb, int slot, +static void file_extent_err(const struct extent_buffer *eb, int slot, const char *fmt, ...) { + const struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_key key; struct va_format vaf; va_list args; @@ -94,26 +97,26 @@ static void file_extent_err(const struct btrfs_fs_info *fs_info, * Return 0 if the btrfs_file_extent_##name is aligned to @alignment * Else return 1 */ -#define CHECK_FE_ALIGNED(fs_info, leaf, slot, fi, name, alignment) \ +#define CHECK_FE_ALIGNED(leaf, slot, fi, name, alignment) \ ({ \ if (!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), (alignment))) \ - file_extent_err((fs_info), (leaf), (slot), \ + file_extent_err((leaf), (slot), \ "invalid %s for file extent, have %llu, should be aligned to %u", \ (#name), btrfs_file_extent_##name((leaf), (fi)), \ (alignment)); \ (!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), (alignment))); \ }) -static int check_extent_data_item(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, +static int check_extent_data_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { + struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_file_extent_item *fi; u32 sectorsize = fs_info->sectorsize; u32 item_size = btrfs_item_size_nr(leaf, slot); if (!IS_ALIGNED(key->offset, sectorsize)) { - file_extent_err(fs_info, leaf, slot, + file_extent_err(leaf, slot, "unaligned file_offset for file extent, have %llu should be aligned to %u", key->offset, sectorsize); return -EUCLEAN; @@ -122,7 +125,7 @@ static int check_extent_data_item(struct btrfs_fs_info *fs_info, fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, fi) > BTRFS_FILE_EXTENT_TYPES) { - file_extent_err(fs_info, leaf, slot, + file_extent_err(leaf, slot, "invalid type for file extent, have %u expect range [0, %u]", btrfs_file_extent_type(leaf, fi), BTRFS_FILE_EXTENT_TYPES); @@ -134,14 +137,14 @@ static int check_extent_data_item(struct btrfs_fs_info *fs_info, * and must be caught in open_ctree(). */ if (btrfs_file_extent_compression(leaf, fi) > BTRFS_COMPRESS_TYPES) { - file_extent_err(fs_info, leaf, slot, + file_extent_err(leaf, slot, "invalid compression for file extent, have %u expect range [0, %u]", btrfs_file_extent_compression(leaf, fi), BTRFS_COMPRESS_TYPES); return -EUCLEAN; } if (btrfs_file_extent_encryption(leaf, fi)) { - file_extent_err(fs_info, leaf, slot, + file_extent_err(leaf, slot, "invalid encryption for file extent, have %u expect 0", btrfs_file_extent_encryption(leaf, fi)); return -EUCLEAN; @@ -149,7 +152,7 @@ static int check_extent_data_item(struct btrfs_fs_info *fs_info, if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) { /* Inline extent must have 0 as key offset */ if (key->offset) { - file_extent_err(fs_info, leaf, slot, + file_extent_err(leaf, slot, "invalid file_offset for inline file extent, have %llu expect 0", key->offset); return -EUCLEAN; @@ -163,7 +166,7 @@ static int check_extent_data_item(struct btrfs_fs_info *fs_info, /* Uncompressed inline extent size must match item size */ if (item_size != BTRFS_FILE_EXTENT_INLINE_DATA_START + btrfs_file_extent_ram_bytes(leaf, fi)) { - file_extent_err(fs_info, leaf, slot, + file_extent_err(leaf, slot, "invalid ram_bytes for uncompressed inline extent, have %u expect %llu", item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START + btrfs_file_extent_ram_bytes(leaf, fi)); @@ -174,41 +177,41 @@ static int check_extent_data_item(struct btrfs_fs_info *fs_info, /* Regular or preallocated extent has fixed item size */ if (item_size != sizeof(*fi)) { - file_extent_err(fs_info, leaf, slot, + file_extent_err(leaf, slot, "invalid item size for reg/prealloc file extent, have %u expect %zu", item_size, sizeof(*fi)); return -EUCLEAN; } - if (CHECK_FE_ALIGNED(fs_info, leaf, slot, fi, ram_bytes, sectorsize) || - CHECK_FE_ALIGNED(fs_info, leaf, slot, fi, disk_bytenr, sectorsize) || - CHECK_FE_ALIGNED(fs_info, leaf, slot, fi, disk_num_bytes, sectorsize) || - CHECK_FE_ALIGNED(fs_info, leaf, slot, fi, offset, sectorsize) || - CHECK_FE_ALIGNED(fs_info, leaf, slot, fi, num_bytes, sectorsize)) + if (CHECK_FE_ALIGNED(leaf, slot, fi, ram_bytes, sectorsize) || + CHECK_FE_ALIGNED(leaf, slot, fi, disk_bytenr, sectorsize) || + CHECK_FE_ALIGNED(leaf, slot, fi, disk_num_bytes, sectorsize) || + CHECK_FE_ALIGNED(leaf, slot, fi, offset, sectorsize) || + CHECK_FE_ALIGNED(leaf, slot, fi, num_bytes, sectorsize)) return -EUCLEAN; return 0; } -static int check_csum_item(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, struct btrfs_key *key, +static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { + struct btrfs_fs_info *fs_info = leaf->fs_info; u32 sectorsize = fs_info->sectorsize; u32 csumsize = btrfs_super_csum_size(fs_info->super_copy); if (key->objectid != BTRFS_EXTENT_CSUM_OBJECTID) { - generic_err(fs_info, leaf, slot, + generic_err(leaf, slot, "invalid key objectid for csum item, have %llu expect %llu", key->objectid, BTRFS_EXTENT_CSUM_OBJECTID); return -EUCLEAN; } if (!IS_ALIGNED(key->offset, sectorsize)) { - generic_err(fs_info, leaf, slot, + generic_err(leaf, slot, "unaligned key offset for csum item, have %llu should be aligned to %u", key->offset, sectorsize); return -EUCLEAN; } if (!IS_ALIGNED(btrfs_item_size_nr(leaf, slot), csumsize)) { - generic_err(fs_info, leaf, slot, + generic_err(leaf, slot, "unaligned item size for csum item, have %u should be aligned to %u", btrfs_item_size_nr(leaf, slot), csumsize); return -EUCLEAN; @@ -220,12 +223,12 @@ static int check_csum_item(struct btrfs_fs_info *fs_info, * Customized reported for dir_item, only important new info is key->objectid, * which represents inode number */ -__printf(4, 5) +__printf(3, 4) __cold -static void dir_item_err(const struct btrfs_fs_info *fs_info, - const struct extent_buffer *eb, int slot, +static void dir_item_err(const struct extent_buffer *eb, int slot, const char *fmt, ...) { + const struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_key key; struct va_format vaf; va_list args; @@ -244,10 +247,10 @@ static void dir_item_err(const struct btrfs_fs_info *fs_info, va_end(args); } -static int check_dir_item(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, +static int check_dir_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { + struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_dir_item *di; u32 item_size = btrfs_item_size_nr(leaf, slot); u32 cur = 0; @@ -263,7 +266,7 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, /* header itself should not cross item boundary */ if (cur + sizeof(*di) > item_size) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "dir item header crosses item boundary, have %zu boundary %u", cur + sizeof(*di), item_size); return -EUCLEAN; @@ -272,7 +275,7 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, /* dir type check */ dir_type = btrfs_dir_type(leaf, di); if (dir_type >= BTRFS_FT_MAX) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "invalid dir item type, have %u expect [0, %u)", dir_type, BTRFS_FT_MAX); return -EUCLEAN; @@ -280,14 +283,14 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, if (key->type == BTRFS_XATTR_ITEM_KEY && dir_type != BTRFS_FT_XATTR) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "invalid dir item type for XATTR key, have %u expect %u", dir_type, BTRFS_FT_XATTR); return -EUCLEAN; } if (dir_type == BTRFS_FT_XATTR && key->type != BTRFS_XATTR_ITEM_KEY) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "xattr dir type found for non-XATTR key"); return -EUCLEAN; } @@ -300,13 +303,13 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, name_len = btrfs_dir_name_len(leaf, di); data_len = btrfs_dir_data_len(leaf, di); if (name_len > max_name_len) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "dir item name len too long, have %u max %u", name_len, max_name_len); return -EUCLEAN; } if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(fs_info)) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "dir item name and data len too long, have %u max %u", name_len + data_len, BTRFS_MAX_XATTR_SIZE(fs_info)); @@ -314,7 +317,7 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, } if (data_len && dir_type != BTRFS_FT_XATTR) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "dir item with invalid data len, have %u expect 0", data_len); return -EUCLEAN; @@ -324,7 +327,7 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, /* header and name/data should not cross item boundary */ if (cur + total_size > item_size) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "dir item data crosses item boundary, have %u boundary %u", cur + total_size, item_size); return -EUCLEAN; @@ -342,7 +345,7 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, (unsigned long)(di + 1), name_len); name_hash = btrfs_name_hash(namebuf, name_len); if (key->offset != name_hash) { - dir_item_err(fs_info, leaf, slot, + dir_item_err(leaf, slot, "name hash mismatch with key, have 0x%016x expect 0x%016llx", name_hash, key->offset); return -EUCLEAN; @@ -354,12 +357,12 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, return 0; } -__printf(4, 5) +__printf(3, 4) __cold -static void block_group_err(const struct btrfs_fs_info *fs_info, - const struct extent_buffer *eb, int slot, +static void block_group_err(const struct extent_buffer *eb, int slot, const char *fmt, ...) { + const struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_key key; struct va_format vaf; va_list args; @@ -378,8 +381,7 @@ static void block_group_err(const struct btrfs_fs_info *fs_info, va_end(args); } -static int check_block_group_item(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, +static int check_block_group_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { struct btrfs_block_group_item bgi; @@ -392,13 +394,13 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, * handle it. We care more about the size. */ if (key->offset == 0) { - block_group_err(fs_info, leaf, slot, + block_group_err(leaf, slot, "invalid block group size 0"); return -EUCLEAN; } if (item_size != sizeof(bgi)) { - block_group_err(fs_info, leaf, slot, + block_group_err(leaf, slot, "invalid item size, have %u expect %zu", item_size, sizeof(bgi)); return -EUCLEAN; @@ -408,7 +410,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, sizeof(bgi)); if (btrfs_block_group_chunk_objectid(&bgi) != BTRFS_FIRST_CHUNK_TREE_OBJECTID) { - block_group_err(fs_info, leaf, slot, + block_group_err(leaf, slot, "invalid block group chunk objectid, have %llu expect %llu", btrfs_block_group_chunk_objectid(&bgi), BTRFS_FIRST_CHUNK_TREE_OBJECTID); @@ -416,7 +418,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, } if (btrfs_block_group_used(&bgi) > key->offset) { - block_group_err(fs_info, leaf, slot, + block_group_err(leaf, slot, "invalid block group used, have %llu expect [0, %llu)", btrfs_block_group_used(&bgi), key->offset); return -EUCLEAN; @@ -424,7 +426,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, flags = btrfs_block_group_flags(&bgi); if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) { - block_group_err(fs_info, leaf, slot, + block_group_err(leaf, slot, "invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set", flags & BTRFS_BLOCK_GROUP_PROFILE_MASK, hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK)); @@ -437,7 +439,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, type != BTRFS_BLOCK_GROUP_SYSTEM && type != (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA)) { - block_group_err(fs_info, leaf, slot, + block_group_err(leaf, slot, "invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx", type, hweight64(type), BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA, @@ -448,37 +450,367 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, return 0; } +__printf(4, 5) +__cold +static void chunk_err(const struct extent_buffer *leaf, + const struct btrfs_chunk *chunk, u64 logical, + const char *fmt, ...) +{ + const struct btrfs_fs_info *fs_info = leaf->fs_info; + bool is_sb; + struct va_format vaf; + va_list args; + int i; + int slot = -1; + + /* Only superblock eb is able to have such small offset */ + is_sb = (leaf->start == BTRFS_SUPER_INFO_OFFSET); + + if (!is_sb) { + /* + * Get the slot number by iterating through all slots, this + * would provide better readability. + */ + for (i = 0; i < btrfs_header_nritems(leaf); i++) { + if (btrfs_item_ptr_offset(leaf, i) == + (unsigned long)chunk) { + slot = i; + break; + } + } + } + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + + if (is_sb) + btrfs_crit(fs_info, + "corrupt superblock syschunk array: chunk_start=%llu, %pV", + logical, &vaf); + else + btrfs_crit(fs_info, + "corrupt leaf: root=%llu block=%llu slot=%d chunk_start=%llu, %pV", + BTRFS_CHUNK_TREE_OBJECTID, leaf->start, slot, + logical, &vaf); + va_end(args); +} + +/* + * The common chunk check which could also work on super block sys chunk array. + * + * Return -EUCLEAN if anything is corrupted. + * Return 0 if everything is OK. + */ +int btrfs_check_chunk_valid(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, u64 logical) +{ + struct btrfs_fs_info *fs_info = leaf->fs_info; + u64 length; + u64 stripe_len; + u16 num_stripes; + u16 sub_stripes; + u64 type; + u64 features; + bool mixed = false; + + length = btrfs_chunk_length(leaf, chunk); + stripe_len = btrfs_chunk_stripe_len(leaf, chunk); + num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); + type = btrfs_chunk_type(leaf, chunk); + + if (!num_stripes) { + chunk_err(leaf, chunk, logical, + "invalid chunk num_stripes, have %u", num_stripes); + return -EUCLEAN; + } + if (!IS_ALIGNED(logical, fs_info->sectorsize)) { + chunk_err(leaf, chunk, logical, + "invalid chunk logical, have %llu should aligned to %u", + logical, fs_info->sectorsize); + return -EUCLEAN; + } + if (btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize) { + chunk_err(leaf, chunk, logical, + "invalid chunk sectorsize, have %u expect %u", + btrfs_chunk_sector_size(leaf, chunk), + fs_info->sectorsize); + return -EUCLEAN; + } + if (!length || !IS_ALIGNED(length, fs_info->sectorsize)) { + chunk_err(leaf, chunk, logical, + "invalid chunk length, have %llu", length); + return -EUCLEAN; + } + if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) { + chunk_err(leaf, chunk, logical, + "invalid chunk stripe length: %llu", + stripe_len); + return -EUCLEAN; + } + if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) & + type) { + chunk_err(leaf, chunk, logical, + "unrecognized chunk type: 0x%llx", + ~(BTRFS_BLOCK_GROUP_TYPE_MASK | + BTRFS_BLOCK_GROUP_PROFILE_MASK) & + btrfs_chunk_type(leaf, chunk)); + return -EUCLEAN; + } + + if (!is_power_of_2(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && + (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) { + chunk_err(leaf, chunk, logical, + "invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set", + type & BTRFS_BLOCK_GROUP_PROFILE_MASK); + return -EUCLEAN; + } + if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) { + chunk_err(leaf, chunk, logical, + "missing chunk type flag, have 0x%llx one bit must be set in 0x%llx", + type, BTRFS_BLOCK_GROUP_TYPE_MASK); + return -EUCLEAN; + } + + if ((type & BTRFS_BLOCK_GROUP_SYSTEM) && + (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) { + chunk_err(leaf, chunk, logical, + "system chunk with data or metadata type: 0x%llx", + type); + return -EUCLEAN; + } + + features = btrfs_super_incompat_flags(fs_info->super_copy); + if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) + mixed = true; + + if (!mixed) { + if ((type & BTRFS_BLOCK_GROUP_METADATA) && + (type & BTRFS_BLOCK_GROUP_DATA)) { + chunk_err(leaf, chunk, logical, + "mixed chunk type in non-mixed mode: 0x%llx", type); + return -EUCLEAN; + } + } + + if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) || + (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) || + (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) || + (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) || + (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) || + ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && num_stripes != 1)) { + chunk_err(leaf, chunk, logical, + "invalid num_stripes:sub_stripes %u:%u for profile %llu", + num_stripes, sub_stripes, + type & BTRFS_BLOCK_GROUP_PROFILE_MASK); + return -EUCLEAN; + } + + return 0; +} + +__printf(3, 4) +__cold +static void dev_item_err(const struct extent_buffer *eb, int slot, + const char *fmt, ...) +{ + struct btrfs_key key; + struct va_format vaf; + va_list args; + + btrfs_item_key_to_cpu(eb, &key, slot); + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + btrfs_crit(eb->fs_info, + "corrupt %s: root=%llu block=%llu slot=%d devid=%llu %pV", + btrfs_header_level(eb) == 0 ? "leaf" : "node", + btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot, + key.objectid, &vaf); + va_end(args); +} + +static int check_dev_item(struct extent_buffer *leaf, + struct btrfs_key *key, int slot) +{ + struct btrfs_fs_info *fs_info = leaf->fs_info; + struct btrfs_dev_item *ditem; + u64 max_devid = max(BTRFS_MAX_DEVS(fs_info), BTRFS_MAX_DEVS_SYS_CHUNK); + + if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) { + dev_item_err(leaf, slot, + "invalid objectid: has=%llu expect=%llu", + key->objectid, BTRFS_DEV_ITEMS_OBJECTID); + return -EUCLEAN; + } + if (key->offset > max_devid) { + dev_item_err(leaf, slot, + "invalid devid: has=%llu expect=[0, %llu]", + key->offset, max_devid); + return -EUCLEAN; + } + ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); + if (btrfs_device_id(leaf, ditem) != key->offset) { + dev_item_err(leaf, slot, + "devid mismatch: key has=%llu item has=%llu", + key->offset, btrfs_device_id(leaf, ditem)); + return -EUCLEAN; + } + + /* + * For device total_bytes, we don't have reliable way to check it, as + * it can be 0 for device removal. Device size check can only be done + * by dev extents check. + */ + if (btrfs_device_bytes_used(leaf, ditem) > + btrfs_device_total_bytes(leaf, ditem)) { + dev_item_err(leaf, slot, + "invalid bytes used: have %llu expect [0, %llu]", + btrfs_device_bytes_used(leaf, ditem), + btrfs_device_total_bytes(leaf, ditem)); + return -EUCLEAN; + } + /* + * Remaining members like io_align/type/gen/dev_group aren't really + * utilized. Skip them to make later usage of them easier. + */ + return 0; +} + +/* Inode item error output has the same format as dir_item_err() */ +#define inode_item_err(fs_info, eb, slot, fmt, ...) \ + dir_item_err(eb, slot, fmt, __VA_ARGS__) + +static int check_inode_item(struct extent_buffer *leaf, + struct btrfs_key *key, int slot) +{ + struct btrfs_fs_info *fs_info = leaf->fs_info; + struct btrfs_inode_item *iitem; + u64 super_gen = btrfs_super_generation(fs_info->super_copy); + u32 valid_mask = (S_IFMT | S_ISUID | S_ISGID | S_ISVTX | 0777); + u32 mode; + + if ((key->objectid < BTRFS_FIRST_FREE_OBJECTID || + key->objectid > BTRFS_LAST_FREE_OBJECTID) && + key->objectid != BTRFS_ROOT_TREE_DIR_OBJECTID && + key->objectid != BTRFS_FREE_INO_OBJECTID) { + generic_err(leaf, slot, + "invalid key objectid: has %llu expect %llu or [%llu, %llu] or %llu", + key->objectid, BTRFS_ROOT_TREE_DIR_OBJECTID, + BTRFS_FIRST_FREE_OBJECTID, + BTRFS_LAST_FREE_OBJECTID, + BTRFS_FREE_INO_OBJECTID); + return -EUCLEAN; + } + if (key->offset != 0) { + inode_item_err(fs_info, leaf, slot, + "invalid key offset: has %llu expect 0", + key->offset); + return -EUCLEAN; + } + iitem = btrfs_item_ptr(leaf, slot, struct btrfs_inode_item); + + /* 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]", + btrfs_inode_generation(leaf, iitem), + super_gen + 1); + return -EUCLEAN; + } + /* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */ + if (btrfs_inode_transid(leaf, iitem) > super_gen + 1) { + inode_item_err(fs_info, leaf, slot, + "invalid inode generation: has %llu expect [0, %llu]", + btrfs_inode_transid(leaf, iitem), super_gen + 1); + return -EUCLEAN; + } + + /* + * For size and nbytes it's better not to be too strict, as for dir + * item its size/nbytes can easily get wrong, but doesn't affect + * anything in the fs. So here we skip the check. + */ + mode = btrfs_inode_mode(leaf, iitem); + if (mode & ~valid_mask) { + inode_item_err(fs_info, leaf, slot, + "unknown mode bit detected: 0x%x", + mode & ~valid_mask); + return -EUCLEAN; + } + + /* + * S_IFMT is not bit mapped so we can't completely rely on is_power_of_2, + * but is_power_of_2() can save us from checking FIFO/CHR/DIR/REG. + * Only needs to check BLK, LNK and SOCKS + */ + if (!is_power_of_2(mode & S_IFMT)) { + if (!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode)) { + inode_item_err(fs_info, leaf, slot, + "invalid mode: has 0%o expect valid S_IF* bit(s)", + mode & S_IFMT); + return -EUCLEAN; + } + } + if (S_ISDIR(mode) && btrfs_inode_nlink(leaf, iitem) > 1) { + inode_item_err(fs_info, leaf, slot, + "invalid nlink: has %u expect no more than 1 for dir", + btrfs_inode_nlink(leaf, iitem)); + return -EUCLEAN; + } + if (btrfs_inode_flags(leaf, iitem) & ~BTRFS_INODE_FLAG_MASK) { + inode_item_err(fs_info, leaf, slot, + "unknown flags detected: 0x%llx", + btrfs_inode_flags(leaf, iitem) & + ~BTRFS_INODE_FLAG_MASK); + return -EUCLEAN; + } + return 0; +} + /* * Common point to switch the item-specific validation. */ -static int check_leaf_item(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, +static int check_leaf_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { int ret = 0; + struct btrfs_chunk *chunk; switch (key->type) { case BTRFS_EXTENT_DATA_KEY: - ret = check_extent_data_item(fs_info, leaf, key, slot); + ret = check_extent_data_item(leaf, key, slot); break; case BTRFS_EXTENT_CSUM_KEY: - ret = check_csum_item(fs_info, leaf, key, slot); + ret = check_csum_item(leaf, key, slot); break; case BTRFS_DIR_ITEM_KEY: case BTRFS_DIR_INDEX_KEY: case BTRFS_XATTR_ITEM_KEY: - ret = check_dir_item(fs_info, leaf, key, slot); + ret = check_dir_item(leaf, key, slot); break; case BTRFS_BLOCK_GROUP_ITEM_KEY: - ret = check_block_group_item(fs_info, leaf, key, slot); + ret = check_block_group_item(leaf, key, slot); + break; + case BTRFS_CHUNK_ITEM_KEY: + chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + ret = btrfs_check_chunk_valid(leaf, chunk, key->offset); + break; + case BTRFS_DEV_ITEM_KEY: + ret = check_dev_item(leaf, key, slot); + break; + case BTRFS_INODE_ITEM_KEY: + ret = check_inode_item(leaf, key, slot); break; } return ret; } -static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, - bool check_item_data) +static int check_leaf(struct extent_buffer *leaf, bool check_item_data) { + struct btrfs_fs_info *fs_info = leaf->fs_info; /* No valid key type is 0, so all key should be larger than this key */ struct btrfs_key prev_key = {0, 0, 0}; struct btrfs_key key; @@ -486,7 +818,7 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, int slot; if (btrfs_header_level(leaf) != 0) { - generic_err(fs_info, leaf, 0, + generic_err(leaf, 0, "invalid level for leaf, have %d expect 0", btrfs_header_level(leaf)); return -EUCLEAN; @@ -502,7 +834,6 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, */ if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) { u64 owner = btrfs_header_owner(leaf); - struct btrfs_root *check_root; /* These trees must never be empty */ if (owner == BTRFS_ROOT_TREE_OBJECTID || @@ -511,34 +842,11 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, owner == BTRFS_DEV_TREE_OBJECTID || owner == BTRFS_FS_TREE_OBJECTID || owner == BTRFS_DATA_RELOC_TREE_OBJECTID) { - generic_err(fs_info, leaf, 0, + generic_err(leaf, 0, "invalid root, root %llu must never be empty", owner); return -EUCLEAN; } - key.objectid = owner; - key.type = BTRFS_ROOT_ITEM_KEY; - key.offset = (u64)-1; - - check_root = btrfs_get_fs_root(fs_info, &key, false); - /* - * The only reason we also check NULL here is that during - * open_ctree() some roots has not yet been set up. - */ - if (!IS_ERR_OR_NULL(check_root)) { - struct extent_buffer *eb; - - eb = btrfs_root_node(check_root); - /* if leaf is the root, then it's fine */ - if (leaf != eb) { - generic_err(fs_info, leaf, 0, - "invalid nritems, have %u should not be 0 for non-root leaf", - nritems); - free_extent_buffer(eb); - return -EUCLEAN; - } - free_extent_buffer(eb); - } return 0; } @@ -564,7 +872,7 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, /* Make sure the keys are in the right order */ if (btrfs_comp_cpu_keys(&prev_key, &key) >= 0) { - generic_err(fs_info, leaf, slot, + generic_err(leaf, slot, "bad key order, prev (%llu %u %llu) current (%llu %u %llu)", prev_key.objectid, prev_key.type, prev_key.offset, key.objectid, key.type, @@ -583,7 +891,7 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, item_end_expected = btrfs_item_offset_nr(leaf, slot - 1); if (btrfs_item_end_nr(leaf, slot) != item_end_expected) { - generic_err(fs_info, leaf, slot, + generic_err(leaf, slot, "unexpected item end, have %u expect %u", btrfs_item_end_nr(leaf, slot), item_end_expected); @@ -597,7 +905,7 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, */ if (btrfs_item_end_nr(leaf, slot) > BTRFS_LEAF_DATA_SIZE(fs_info)) { - generic_err(fs_info, leaf, slot, + generic_err(leaf, slot, "slot end outside of leaf, have %u expect range [0, %u]", btrfs_item_end_nr(leaf, slot), BTRFS_LEAF_DATA_SIZE(fs_info)); @@ -607,7 +915,7 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, /* Also check if the item pointer overlaps with btrfs item. */ if (btrfs_item_nr_offset(slot) + sizeof(struct btrfs_item) > btrfs_item_ptr_offset(leaf, slot)) { - generic_err(fs_info, leaf, slot, + generic_err(leaf, slot, "slot overlaps with its data, item end %lu data start %lu", btrfs_item_nr_offset(slot) + sizeof(struct btrfs_item), @@ -620,7 +928,7 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, * Check if the item size and content meet other * criteria */ - ret = check_leaf_item(fs_info, leaf, &key, slot); + ret = check_leaf_item(leaf, &key, slot); if (ret < 0) return ret; } @@ -633,20 +941,20 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, return 0; } -int btrfs_check_leaf_full(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf) +int btrfs_check_leaf_full(struct extent_buffer *leaf) { - return check_leaf(fs_info, leaf, true); + return check_leaf(leaf, true); } +ALLOW_ERROR_INJECTION(btrfs_check_leaf_full, ERRNO); -int btrfs_check_leaf_relaxed(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf) +int btrfs_check_leaf_relaxed(struct extent_buffer *leaf) { - return check_leaf(fs_info, leaf, false); + return check_leaf(leaf, false); } -int btrfs_check_node(struct btrfs_fs_info *fs_info, struct extent_buffer *node) +int btrfs_check_node(struct extent_buffer *node) { + struct btrfs_fs_info *fs_info = node->fs_info; unsigned long nr = btrfs_header_nritems(node); struct btrfs_key key, next_key; int slot; @@ -655,7 +963,7 @@ int btrfs_check_node(struct btrfs_fs_info *fs_info, struct extent_buffer *node) int ret = 0; if (level <= 0 || level >= BTRFS_MAX_LEVEL) { - generic_err(fs_info, node, 0, + generic_err(node, 0, "invalid level for node, have %d expect [1, %d]", level, BTRFS_MAX_LEVEL - 1); return -EUCLEAN; @@ -675,13 +983,13 @@ int btrfs_check_node(struct btrfs_fs_info *fs_info, struct extent_buffer *node) btrfs_node_key_to_cpu(node, &next_key, slot + 1); if (!bytenr) { - generic_err(fs_info, node, slot, + generic_err(node, slot, "invalid NULL node pointer"); ret = -EUCLEAN; goto out; } if (!IS_ALIGNED(bytenr, fs_info->sectorsize)) { - generic_err(fs_info, node, slot, + generic_err(node, slot, "unaligned pointer, have %llu should be aligned to %u", bytenr, fs_info->sectorsize); ret = -EUCLEAN; @@ -689,7 +997,7 @@ int btrfs_check_node(struct btrfs_fs_info *fs_info, struct extent_buffer *node) } if (btrfs_comp_cpu_keys(&key, &next_key) >= 0) { - generic_err(fs_info, node, slot, + generic_err(node, slot, "bad key order, current (%llu %u %llu) next (%llu %u %llu)", key.objectid, key.type, key.offset, next_key.objectid, next_key.type, @@ -701,3 +1009,4 @@ int btrfs_check_node(struct btrfs_fs_info *fs_info, struct extent_buffer *node) out: return ret; } +ALLOW_ERROR_INJECTION(btrfs_check_node, ERRNO); diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h index ff043275b784..32fecc9dc1dd 100644 --- a/fs/btrfs/tree-checker.h +++ b/fs/btrfs/tree-checker.h @@ -14,15 +14,16 @@ * Will check not only the item pointers, but also every possible member * in item data. */ -int btrfs_check_leaf_full(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf); +int btrfs_check_leaf_full(struct extent_buffer *leaf); /* * Less strict leaf checker. * Will only check item pointers, not reading item data. */ -int btrfs_check_leaf_relaxed(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf); -int btrfs_check_node(struct btrfs_fs_info *fs_info, struct extent_buffer *node); +int btrfs_check_leaf_relaxed(struct extent_buffer *leaf); +int btrfs_check_node(struct extent_buffer *node); + +int btrfs_check_chunk_valid(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, u64 logical); #endif diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 561884f60d35..6adcd8a2c5c7 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -139,7 +139,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans, mutex_lock(&root->log_mutex); if (root->log_root) { - if (btrfs_need_log_full_commit(fs_info, trans)) { + if (btrfs_need_log_full_commit(trans)) { ret = -EAGAIN; goto out; } @@ -225,6 +225,17 @@ void btrfs_end_log_trans(struct btrfs_root *root) } } +static int btrfs_write_tree_block(struct extent_buffer *buf) +{ + return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start, + buf->start + buf->len - 1); +} + +static void btrfs_wait_tree_block_writeback(struct extent_buffer *buf) +{ + filemap_fdatawait_range(buf->pages[0]->mapping, + buf->start, buf->start + buf->len - 1); +} /* * the walk control struct is used to pass state down the chain when @@ -304,7 +315,7 @@ static int process_one_buffer(struct btrfs_root *log, if (!ret && btrfs_buffer_uptodate(eb, gen, 0)) { if (wc->pin && btrfs_header_level(eb) == 0) - ret = btrfs_exclude_logged_extents(fs_info, eb); + ret = btrfs_exclude_logged_extents(eb); if (wc->write) btrfs_write_tree_block(eb); if (wc->wait) @@ -333,7 +344,6 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, struct extent_buffer *eb, int slot, struct btrfs_key *key) { - struct btrfs_fs_info *fs_info = root->fs_info; int ret; u32 item_size; u64 saved_i_size = 0; @@ -454,10 +464,9 @@ insert: found_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]); if (found_size > item_size) - btrfs_truncate_item(fs_info, path, item_size, 1); + btrfs_truncate_item(path, item_size, 1); else if (found_size < item_size) - btrfs_extend_item(fs_info, path, - item_size - found_size); + btrfs_extend_item(path, item_size - found_size); } else if (ret) { return ret; } @@ -694,9 +703,11 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, goto out; if (ins.objectid > 0) { + struct btrfs_ref ref = { 0 }; u64 csum_start; u64 csum_end; LIST_HEAD(ordered_sums); + /* * is this extent already allocated in the extent * allocation tree? If so, just add a reference @@ -704,10 +715,13 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ret = btrfs_lookup_data_extent(fs_info, ins.objectid, ins.offset); if (ret == 0) { - ret = btrfs_inc_extent_ref(trans, root, - ins.objectid, ins.offset, - 0, root->root_key.objectid, + btrfs_init_generic_ref(&ref, + BTRFS_ADD_DELAYED_REF, + ins.objectid, ins.offset, 0); + btrfs_init_data_ref(&ref, + root->root_key.objectid, key->objectid, offset); + ret = btrfs_inc_extent_ref(trans, &ref); if (ret) goto out; } else { @@ -2725,7 +2739,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking_write(next); - clean_tree_block(fs_info, next); + btrfs_clean_tree_block(next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } else { @@ -2809,7 +2823,7 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking_write(next); - clean_tree_block(fs_info, next); + btrfs_clean_tree_block(next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } else { @@ -2891,7 +2905,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking_write(next); - clean_tree_block(fs_info, next); + btrfs_clean_tree_block(next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } else { @@ -3066,7 +3080,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, } /* bail out if we need to do a full commit */ - if (btrfs_need_log_full_commit(fs_info, trans)) { + if (btrfs_need_log_full_commit(trans)) { ret = -EAGAIN; mutex_unlock(&root->log_mutex); goto out; @@ -3085,7 +3099,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (ret) { blk_finish_plug(&plug); btrfs_abort_transaction(trans, ret); - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); mutex_unlock(&root->log_mutex); goto out; } @@ -3127,7 +3141,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, list_del_init(&root_log_ctx.list); blk_finish_plug(&plug); - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); if (ret != -ENOSPC) { btrfs_abort_transaction(trans, ret); @@ -3173,7 +3187,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, * now that we've moved on to the tree of log tree roots, * check the full commit flag again */ - if (btrfs_need_log_full_commit(fs_info, trans)) { + if (btrfs_need_log_full_commit(trans)) { blk_finish_plug(&plug); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); @@ -3186,7 +3200,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, EXTENT_DIRTY | EXTENT_NEW); blk_finish_plug(&plug); if (ret) { - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; @@ -3196,7 +3210,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, ret = btrfs_wait_tree_log_extents(log_root_tree, EXTENT_NEW | EXTENT_DIRTY); if (ret) { - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } @@ -3218,7 +3232,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ ret = write_all_supers(fs_info, 1); if (ret) { - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); goto out_wake_log_root; } @@ -3422,7 +3436,7 @@ fail: out_unlock: mutex_unlock(&dir->log_mutex); if (ret == -ENOSPC) { - btrfs_set_log_full_commit(root->fs_info, trans); + btrfs_set_log_full_commit(trans); ret = 0; } else if (ret < 0) btrfs_abort_transaction(trans, ret); @@ -3438,7 +3452,6 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, const char *name, int name_len, struct btrfs_inode *inode, u64 dirid) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log; u64 index; int ret; @@ -3456,7 +3469,7 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, dirid, &index); mutex_unlock(&inode->log_mutex); if (ret == -ENOSPC) { - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); ret = 0; } else if (ret < 0 && ret != -ENOENT) btrfs_abort_transaction(trans, ret); @@ -5442,7 +5455,7 @@ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans, * Make sure any commits to the log are forced to be full * commits. */ - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); ret = true; } mutex_unlock(&inode->log_mutex); @@ -5819,6 +5832,190 @@ out: return ret; } +static int log_new_ancestors(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_path *path, + struct btrfs_log_ctx *ctx) +{ + struct btrfs_key found_key; + + btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); + + while (true) { + struct btrfs_fs_info *fs_info = root->fs_info; + const u64 last_committed = fs_info->last_trans_committed; + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + struct btrfs_key search_key; + struct inode *inode; + int ret = 0; + + btrfs_release_path(path); + + search_key.objectid = found_key.offset; + search_key.type = BTRFS_INODE_ITEM_KEY; + search_key.offset = 0; + inode = btrfs_iget(fs_info->sb, &search_key, root, NULL); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + if (BTRFS_I(inode)->generation > last_committed) + ret = btrfs_log_inode(trans, root, BTRFS_I(inode), + LOG_INODE_EXISTS, + 0, LLONG_MAX, ctx); + iput(inode); + if (ret) + return ret; + + if (search_key.objectid == BTRFS_FIRST_FREE_OBJECTID) + break; + + search_key.type = BTRFS_INODE_REF_KEY; + ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); + if (ret < 0) + return ret; + + leaf = path->nodes[0]; + slot = path->slots[0]; + if (slot >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + return ret; + else if (ret > 0) + return -ENOENT; + leaf = path->nodes[0]; + slot = path->slots[0]; + } + + btrfs_item_key_to_cpu(leaf, &found_key, slot); + if (found_key.objectid != search_key.objectid || + found_key.type != BTRFS_INODE_REF_KEY) + return -ENOENT; + } + return 0; +} + +static int log_new_ancestors_fast(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, + struct dentry *parent, + struct btrfs_log_ctx *ctx) +{ + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; + struct dentry *old_parent = NULL; + struct super_block *sb = inode->vfs_inode.i_sb; + int ret = 0; + + while (true) { + if (!parent || d_really_is_negative(parent) || + sb != parent->d_sb) + break; + + inode = BTRFS_I(d_inode(parent)); + if (root != inode->root) + break; + + if (inode->generation > fs_info->last_trans_committed) { + ret = btrfs_log_inode(trans, root, inode, + LOG_INODE_EXISTS, 0, LLONG_MAX, ctx); + if (ret) + break; + } + if (IS_ROOT(parent)) + break; + + parent = dget_parent(parent); + dput(old_parent); + old_parent = parent; + } + dput(old_parent); + + return ret; +} + +static int log_all_new_ancestors(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, + struct dentry *parent, + struct btrfs_log_ctx *ctx) +{ + struct btrfs_root *root = inode->root; + const u64 ino = btrfs_ino(inode); + struct btrfs_path *path; + struct btrfs_key search_key; + int ret; + + /* + * For a single hard link case, go through a fast path that does not + * need to iterate the fs/subvolume tree. + */ + if (inode->vfs_inode.i_nlink < 2) + return log_new_ancestors_fast(trans, inode, parent, ctx); + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + search_key.objectid = ino; + search_key.type = BTRFS_INODE_REF_KEY; + search_key.offset = 0; +again: + ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); + if (ret < 0) + goto out; + if (ret == 0) + path->slots[0]++; + + while (true) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + struct btrfs_key found_key; + + if (slot >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto out; + else if (ret > 0) + break; + continue; + } + + btrfs_item_key_to_cpu(leaf, &found_key, slot); + if (found_key.objectid != ino || + found_key.type > BTRFS_INODE_EXTREF_KEY) + break; + + /* + * Don't deal with extended references because they are rare + * cases and too complex to deal with (we would need to keep + * track of which subitem we are processing for each item in + * this loop, etc). So just return some error to fallback to + * a transaction commit. + */ + if (found_key.type == BTRFS_INODE_EXTREF_KEY) { + ret = -EMLINK; + goto out; + } + + /* + * Logging ancestors needs to do more searches on the fs/subvol + * tree, so it releases the path as needed to avoid deadlocks. + * Keep track of the last inode ref key and resume from that key + * after logging all new ancestors for the current hard link. + */ + memcpy(&search_key, &found_key, sizeof(search_key)); + + ret = log_new_ancestors(trans, root, path, ctx); + if (ret) + goto out; + btrfs_release_path(path); + goto again; + } + ret = 0; +out: + btrfs_free_path(path); + return ret; +} + /* * helper function around btrfs_log_inode to make sure newly created * parent directories also end up in the log. A minimal inode and backref @@ -5836,11 +6033,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct super_block *sb; - struct dentry *old_parent = NULL; int ret = 0; u64 last_committed = fs_info->last_trans_committed; bool log_dentries = false; - struct btrfs_inode *orig_inode = inode; sb = inode->vfs_inode.i_sb; @@ -5946,56 +6141,22 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, * and has a link count of 2. */ if (inode->last_unlink_trans > last_committed) { - ret = btrfs_log_all_parents(trans, orig_inode, ctx); + ret = btrfs_log_all_parents(trans, inode, ctx); if (ret) goto end_trans; } - /* - * If a new hard link was added to the inode in the current transaction - * and its link count is now greater than 1, we need to fallback to a - * transaction commit, otherwise we can end up not logging all its new - * parents for all the hard links. Here just from the dentry used to - * fsync, we can not visit the ancestor inodes for all the other hard - * links to figure out if any is new, so we fallback to a transaction - * commit (instead of adding a lot of complexity of scanning a btree, - * since this scenario is not a common use case). - */ - if (inode->vfs_inode.i_nlink > 1 && - inode->last_link_trans > last_committed) { - ret = -EMLINK; + ret = log_all_new_ancestors(trans, inode, parent, ctx); + if (ret) goto end_trans; - } - while (1) { - if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) - break; - - inode = BTRFS_I(d_inode(parent)); - if (root != inode->root) - break; - - if (inode->generation > last_committed) { - ret = btrfs_log_inode(trans, root, inode, - LOG_INODE_EXISTS, 0, LLONG_MAX, ctx); - if (ret) - goto end_trans; - } - if (IS_ROOT(parent)) - break; - - parent = dget_parent(parent); - dput(old_parent); - old_parent = parent; - } if (log_dentries) - ret = log_new_dir_dentries(trans, root, orig_inode, ctx); + ret = log_new_dir_dentries(trans, root, inode, ctx); else ret = 0; end_trans: - dput(old_parent); if (ret < 0) { - btrfs_set_log_full_commit(fs_info, trans); + btrfs_set_log_full_commit(trans); ret = 1; } diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index 0fab84a8f670..132e43d29034 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -30,16 +30,14 @@ static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, INIT_LIST_HEAD(&ctx->list); } -static inline void btrfs_set_log_full_commit(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans) +static inline void btrfs_set_log_full_commit(struct btrfs_trans_handle *trans) { - WRITE_ONCE(fs_info->last_trans_log_full_commit, trans->transid); + WRITE_ONCE(trans->fs_info->last_trans_log_full_commit, trans->transid); } -static inline int btrfs_need_log_full_commit(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans) +static inline int btrfs_need_log_full_commit(struct btrfs_trans_handle *trans) { - return READ_ONCE(fs_info->last_trans_log_full_commit) == + return READ_ONCE(trans->fs_info->last_trans_log_full_commit) == trans->transid; } diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index 3b2ae342e649..91caab63bdf5 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -121,12 +121,12 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, * An item with that type already exists. * Extend the item and store the new subid at the end. */ - btrfs_extend_item(fs_info, path, sizeof(subid_le)); + btrfs_extend_item(path, sizeof(subid_le)); eb = path->nodes[0]; slot = path->slots[0]; offset = btrfs_item_ptr_offset(eb, slot); offset += btrfs_item_size_nr(eb, slot) - sizeof(subid_le); - } else if (ret < 0) { + } else { btrfs_warn(fs_info, "insert uuid item failed %d (0x%016llx, 0x%016llx) type %u!", ret, (unsigned long long)key.objectid, @@ -219,7 +219,7 @@ int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, move_src = offset + sizeof(subid); move_len = item_size - (move_src - btrfs_item_ptr_offset(eb, slot)); memmove_extent_buffer(eb, move_dst, move_src, move_len); - btrfs_truncate_item(fs_info, path, item_size - sizeof(subid), 1); + btrfs_truncate_item(path, item_size - sizeof(subid), 1); out: btrfs_free_path(path); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index db934ceae9c1..1c2a6e4b39da 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -27,6 +27,7 @@ #include "math.h" #include "dev-replace.h" #include "sysfs.h" +#include "tree-checker.h" const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { [BTRFS_RAID_RAID10] = { @@ -184,8 +185,7 @@ void btrfs_describe_block_groups(u64 bg_flags, char *buf, u32 size_buf) out_overflow:; } -static int init_first_rw_device(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); +static int init_first_rw_device(struct btrfs_trans_handle *trans); static int btrfs_relocate_sys_chunks(struct btrfs_fs_info *fs_info); static void __btrfs_reset_dev_stats(struct btrfs_device *dev); static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev); @@ -318,7 +318,6 @@ static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid, mutex_init(&fs_devs->device_list_mutex); INIT_LIST_HEAD(&fs_devs->devices); - INIT_LIST_HEAD(&fs_devs->resized_devices); INIT_LIST_HEAD(&fs_devs->alloc_list); INIT_LIST_HEAD(&fs_devs->fs_list); if (fsid) @@ -334,7 +333,9 @@ static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid, void btrfs_free_device(struct btrfs_device *device) { + WARN_ON(!list_empty(&device->post_commit_list)); rcu_string_free(device->name); + extent_io_tree_release(&device->alloc_state); bio_put(device->flush_bio); kfree(device); } @@ -402,7 +403,7 @@ static struct btrfs_device *__alloc_device(void) INIT_LIST_HEAD(&dev->dev_list); INIT_LIST_HEAD(&dev->dev_alloc_list); - INIT_LIST_HEAD(&dev->resized_list); + INIT_LIST_HEAD(&dev->post_commit_list); spin_lock_init(&dev->io_lock); @@ -411,6 +412,7 @@ static struct btrfs_device *__alloc_device(void) btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); + extent_io_tree_init(NULL, &dev->alloc_state, 0, NULL); return dev; } @@ -1230,14 +1232,6 @@ again: mutex_unlock(&uuid_mutex); } -static void free_device_rcu(struct rcu_head *head) -{ - struct btrfs_device *device; - - device = container_of(head, struct btrfs_device, rcu); - btrfs_free_device(device); -} - static void btrfs_close_bdev(struct btrfs_device *device) { if (!device->bdev) @@ -1285,7 +1279,8 @@ static void btrfs_close_one_device(struct btrfs_device *device) list_replace_rcu(&device->dev_list, &new_device->dev_list); new_device->fs_devices = device->fs_devices; - call_rcu(&device->rcu, free_device_rcu); + synchronize_rcu(); + btrfs_free_device(device); } static int close_fs_devices(struct btrfs_fs_devices *fs_devices) @@ -1505,58 +1500,29 @@ error_bdev_put: return device; } -static int contains_pending_extent(struct btrfs_transaction *transaction, - struct btrfs_device *device, - u64 *start, u64 len) +/* + * Try to find a chunk that intersects [start, start + len] range and when one + * such is found, record the end of it in *start + */ +static bool contains_pending_extent(struct btrfs_device *device, u64 *start, + u64 len) { - struct btrfs_fs_info *fs_info = device->fs_info; - struct extent_map *em; - struct list_head *search_list = &fs_info->pinned_chunks; - int ret = 0; - u64 physical_start = *start; + u64 physical_start, physical_end; - if (transaction) - search_list = &transaction->pending_chunks; -again: - list_for_each_entry(em, search_list, list) { - struct map_lookup *map; - int i; + lockdep_assert_held(&device->fs_info->chunk_mutex); - map = em->map_lookup; - for (i = 0; i < map->num_stripes; i++) { - u64 end; + if (!find_first_extent_bit(&device->alloc_state, *start, + &physical_start, &physical_end, + CHUNK_ALLOCATED, NULL)) { - if (map->stripes[i].dev != device) - continue; - if (map->stripes[i].physical >= physical_start + len || - map->stripes[i].physical + em->orig_block_len <= - physical_start) - continue; - /* - * Make sure that while processing the pinned list we do - * not override our *start with a lower value, because - * we can have pinned chunks that fall within this - * device hole and that have lower physical addresses - * than the pending chunks we processed before. If we - * do not take this special care we can end up getting - * 2 pending chunks that start at the same physical - * device offsets because the end offset of a pinned - * chunk can be equal to the start offset of some - * pending chunk. - */ - end = map->stripes[i].physical + em->orig_block_len; - if (end > *start) { - *start = end; - ret = 1; - } + if (in_range(physical_start, *start, len) || + in_range(*start, physical_start, + physical_end - physical_start)) { + *start = physical_end + 1; + return true; } } - if (search_list != &fs_info->pinned_chunks) { - search_list = &fs_info->pinned_chunks; - goto again; - } - - return ret; + return false; } @@ -1581,8 +1547,7 @@ again: * But if we don't find suitable free space, it is used to store the size of * the max free space. */ -int find_free_dev_extent_start(struct btrfs_transaction *transaction, - struct btrfs_device *device, u64 num_bytes, +int find_free_dev_extent_start(struct btrfs_device *device, u64 num_bytes, u64 search_start, u64 *start, u64 *len) { struct btrfs_fs_info *fs_info = device->fs_info; @@ -1667,15 +1632,12 @@ again: * Have to check before we set max_hole_start, otherwise * we could end up sending back this offset anyway. */ - if (contains_pending_extent(transaction, device, - &search_start, + if (contains_pending_extent(device, &search_start, hole_size)) { - if (key.offset >= search_start) { + if (key.offset >= search_start) hole_size = key.offset - search_start; - } else { - WARN_ON_ONCE(1); + else hole_size = 0; - } } if (hole_size > max_hole_size) { @@ -1716,8 +1678,7 @@ next: if (search_end > search_start) { hole_size = search_end - search_start; - if (contains_pending_extent(transaction, device, &search_start, - hole_size)) { + if (contains_pending_extent(device, &search_start, hole_size)) { btrfs_release_path(path); goto again; } @@ -1742,13 +1703,11 @@ out: return ret; } -int find_free_dev_extent(struct btrfs_trans_handle *trans, - struct btrfs_device *device, u64 num_bytes, +int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *len) { /* FIXME use last free of some kind */ - return find_free_dev_extent_start(trans->transaction, device, - num_bytes, 0, start, len); + return find_free_dev_extent_start(device, num_bytes, 0, start, len); } static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans, @@ -1982,10 +1941,9 @@ static void update_dev_time(const char *path_name) filp_close(filp, NULL); } -static int btrfs_rm_dev_item(struct btrfs_fs_info *fs_info, - struct btrfs_device *device) +static int btrfs_rm_dev_item(struct btrfs_device *device) { - struct btrfs_root *root = fs_info->chunk_root; + struct btrfs_root *root = device->fs_info->chunk_root; int ret; struct btrfs_path *path; struct btrfs_key key; @@ -2186,12 +2144,12 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, * counter although write_all_supers() is not locked out. This * could give a filesystem state which requires a degraded mount. */ - ret = btrfs_rm_dev_item(fs_info, device); + ret = btrfs_rm_dev_item(device); if (ret) goto error_undo; clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); - btrfs_scrub_cancel_dev(fs_info, device); + btrfs_scrub_cancel_dev(device); /* * the device list mutex makes sure that we don't change @@ -2242,7 +2200,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, btrfs_scratch_superblocks(device->bdev, device->name->str); btrfs_close_bdev(device); - call_rcu(&device->rcu, free_device_rcu); + synchronize_rcu(); + btrfs_free_device(device); if (cur_devices->open_devices == 0) { while (fs_devices) { @@ -2299,9 +2258,9 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev) fs_devices->open_devices--; } -void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, - struct btrfs_device *srcdev) +void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev) { + struct btrfs_fs_info *fs_info = srcdev->fs_info; struct btrfs_fs_devices *fs_devices = srcdev->fs_devices; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &srcdev->dev_state)) { @@ -2310,7 +2269,8 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, } btrfs_close_bdev(srcdev); - call_rcu(&srcdev->rcu, free_device_rcu); + synchronize_rcu(); + btrfs_free_device(srcdev); /* if this is no devs we rather delete the fs_devices */ if (!fs_devices->num_devices) { @@ -2368,7 +2328,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev) btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str); btrfs_close_bdev(tgtdev); - call_rcu(&tgtdev->rcu, free_device_rcu); + synchronize_rcu(); + btrfs_free_device(tgtdev); } static struct btrfs_device *btrfs_find_device_by_path( @@ -2503,9 +2464,9 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info) /* * Store the expected generation for seed devices in device items. */ -static int btrfs_finish_sprout(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +static int btrfs_finish_sprout(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = fs_info->chunk_root; struct btrfs_path *path; struct extent_buffer *leaf; @@ -2705,7 +2666,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (seeding_dev) { mutex_lock(&fs_info->chunk_mutex); - ret = init_first_rw_device(trans, fs_info); + ret = init_first_rw_device(trans); mutex_unlock(&fs_info->chunk_mutex); if (ret) { btrfs_abort_transaction(trans, ret); @@ -2722,7 +2683,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (seeding_dev) { char fsid_buf[BTRFS_UUID_UNPARSED_SIZE]; - ret = btrfs_finish_sprout(trans, fs_info); + ret = btrfs_finish_sprout(trans); if (ret) { btrfs_abort_transaction(trans, ret); goto error_sysfs; @@ -2852,7 +2813,6 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = device->fs_info; struct btrfs_super_block *super_copy = fs_info->super_copy; - struct btrfs_fs_devices *fs_devices; u64 old_total; u64 diff; @@ -2871,8 +2831,6 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, return -EINVAL; } - fs_devices = fs_info->fs_devices; - btrfs_set_super_total_bytes(super_copy, round_down(old_total + diff, fs_info->sectorsize)); device->fs_devices->total_rw_bytes += diff; @@ -2880,9 +2838,9 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, btrfs_device_set_total_bytes(device, new_size); btrfs_device_set_disk_total_bytes(device, new_size); btrfs_clear_space_info_full(device->fs_info); - if (list_empty(&device->resized_list)) - list_add_tail(&device->resized_list, - &fs_devices->resized_devices); + if (list_empty(&device->post_commit_list)) + list_add_tail(&device->post_commit_list, + &trans->transaction->dev_update_list); mutex_unlock(&fs_info->chunk_mutex); return btrfs_update_device(trans, device); @@ -3601,10 +3559,10 @@ static int chunk_soft_convert_filter(u64 chunk_type, return 0; } -static int should_balance_chunk(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, +static int should_balance_chunk(struct extent_buffer *leaf, struct btrfs_chunk *chunk, u64 chunk_offset) { + struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_balance_control *bctl = fs_info->balance_ctl; struct btrfs_balance_args *bargs = NULL; u64 chunk_type = btrfs_chunk_type(leaf, chunk); @@ -3784,8 +3742,7 @@ again: spin_unlock(&fs_info->balance_lock); } - ret = should_balance_chunk(fs_info, leaf, chunk, - found_key.offset); + ret = should_balance_chunk(leaf, chunk, found_key.offset); btrfs_release_path(path); if (!ret) { @@ -4661,8 +4618,7 @@ int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info) if (IS_ERR(trans)) return PTR_ERR(trans); - uuid_root = btrfs_create_tree(trans, fs_info, - BTRFS_UUID_TREE_OBJECTID); + uuid_root = btrfs_create_tree(trans, BTRFS_UUID_TREE_OBJECTID); if (IS_ERR(uuid_root)) { ret = PTR_ERR(uuid_root); btrfs_abort_transaction(trans, ret); @@ -4722,15 +4678,16 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) int slot; int failed = 0; bool retried = false; - bool checked_pending_chunks = false; struct extent_buffer *l; struct btrfs_key key; struct btrfs_super_block *super_copy = fs_info->super_copy; u64 old_total = btrfs_super_total_bytes(super_copy); u64 old_size = btrfs_device_get_total_bytes(device); u64 diff; + u64 start; new_size = round_down(new_size, fs_info->sectorsize); + start = new_size; diff = round_down(old_size - new_size, fs_info->sectorsize); if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) @@ -4742,6 +4699,12 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) path->reada = READA_BACK; + trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + btrfs_free_path(path); + return PTR_ERR(trans); + } + mutex_lock(&fs_info->chunk_mutex); btrfs_device_set_total_bytes(device, new_size); @@ -4749,7 +4712,21 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) device->fs_devices->total_rw_bytes -= diff; atomic64_sub(diff, &fs_info->free_chunk_space); } - mutex_unlock(&fs_info->chunk_mutex); + + /* + * Once the device's size has been set to the new size, ensure all + * in-memory chunks are synced to disk so that the loop below sees them + * and relocates them accordingly. + */ + if (contains_pending_extent(device, &start, diff)) { + mutex_unlock(&fs_info->chunk_mutex); + ret = btrfs_commit_transaction(trans); + if (ret) + goto done; + } else { + mutex_unlock(&fs_info->chunk_mutex); + btrfs_end_transaction(trans); + } again: key.objectid = device->devid; @@ -4840,40 +4817,10 @@ again: } mutex_lock(&fs_info->chunk_mutex); - - /* - * We checked in the above loop all device extents that were already in - * the device tree. However before we have updated the device's - * total_bytes to the new size, we might have had chunk allocations that - * have not complete yet (new block groups attached to transaction - * handles), and therefore their device extents were not yet in the - * device tree and we missed them in the loop above. So if we have any - * pending chunk using a device extent that overlaps the device range - * that we can not use anymore, commit the current transaction and - * repeat the search on the device tree - this way we guarantee we will - * not have chunks using device extents that end beyond 'new_size'. - */ - if (!checked_pending_chunks) { - u64 start = new_size; - u64 len = old_size - new_size; - - if (contains_pending_extent(trans->transaction, device, - &start, len)) { - mutex_unlock(&fs_info->chunk_mutex); - checked_pending_chunks = true; - failed = 0; - retried = false; - ret = btrfs_commit_transaction(trans); - if (ret) - goto done; - goto again; - } - } - btrfs_device_set_disk_total_bytes(device, new_size); - if (list_empty(&device->resized_list)) - list_add_tail(&device->resized_list, - &fs_info->fs_devices->resized_devices); + if (list_empty(&device->post_commit_list)) + list_add_tail(&device->post_commit_list, + &trans->transaction->dev_update_list); WARN_ON(diff > old_total); btrfs_set_super_total_bytes(super_copy, @@ -4957,15 +4904,6 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type) btrfs_set_fs_incompat(info, RAID56); } -#define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info) \ - - sizeof(struct btrfs_chunk)) \ - / sizeof(struct btrfs_stripe) + 1) - -#define BTRFS_MAX_DEVS_SYS_CHUNK ((BTRFS_SYSTEM_CHUNK_ARRAY_SIZE \ - - 2 * sizeof(struct btrfs_disk_key) \ - - 2 * sizeof(struct btrfs_chunk)) \ - / sizeof(struct btrfs_stripe) + 1) - static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 start, u64 type) { @@ -5038,7 +4976,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, } else { btrfs_err(info, "invalid chunk type 0x%llx requested", type); - BUG_ON(1); + BUG(); } /* We don't want a chunk larger than 10% of writable space */ @@ -5079,7 +5017,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, if (total_avail == 0) continue; - ret = find_free_dev_extent(trans, device, + ret = find_free_dev_extent(device, max_stripe_size * dev_stripes, &dev_offset, &max_avail); if (ret && ret != -ENOSPC) @@ -5213,18 +5151,20 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, free_extent_map(em); goto error; } - - list_add_tail(&em->list, &trans->transaction->pending_chunks); - refcount_inc(&em->refs); write_unlock(&em_tree->lock); ret = btrfs_make_block_group(trans, 0, type, start, chunk_size); if (ret) goto error_del_extent; - for (i = 0; i < map->num_stripes; i++) - btrfs_device_set_bytes_used(map->stripes[i].dev, - map->stripes[i].dev->bytes_used + stripe_size); + for (i = 0; i < map->num_stripes; i++) { + struct btrfs_device *dev = map->stripes[i].dev; + + btrfs_device_set_bytes_used(dev, dev->bytes_used + stripe_size); + if (list_empty(&dev->post_commit_list)) + list_add_tail(&dev->post_commit_list, + &trans->transaction->dev_update_list); + } atomic64_sub(stripe_size * map->num_stripes, &info->free_chunk_space); @@ -5243,8 +5183,6 @@ error_del_extent: free_extent_map(em); /* One for the tree reference */ free_extent_map(em); - /* One for the pending_chunks list reference */ - free_extent_map(em); error: kfree(devices_info); return ret; @@ -5364,9 +5302,9 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type) return __btrfs_alloc_chunk(trans, chunk_offset, type); } -static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +static noinline int init_first_rw_device(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; u64 chunk_offset; u64 sys_chunk_offset; u64 alloc_profile; @@ -6714,99 +6652,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, return dev; } -/* Return -EIO if any error, otherwise return 0. */ -static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, - struct btrfs_chunk *chunk, u64 logical) -{ - u64 length; - u64 stripe_len; - u16 num_stripes; - u16 sub_stripes; - u64 type; - u64 features; - bool mixed = false; - - length = btrfs_chunk_length(leaf, chunk); - stripe_len = btrfs_chunk_stripe_len(leaf, chunk); - num_stripes = btrfs_chunk_num_stripes(leaf, chunk); - sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); - type = btrfs_chunk_type(leaf, chunk); - - if (!num_stripes) { - btrfs_err(fs_info, "invalid chunk num_stripes: %u", - num_stripes); - return -EIO; - } - if (!IS_ALIGNED(logical, fs_info->sectorsize)) { - btrfs_err(fs_info, "invalid chunk logical %llu", logical); - return -EIO; - } - if (btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize) { - btrfs_err(fs_info, "invalid chunk sectorsize %u", - btrfs_chunk_sector_size(leaf, chunk)); - return -EIO; - } - if (!length || !IS_ALIGNED(length, fs_info->sectorsize)) { - btrfs_err(fs_info, "invalid chunk length %llu", length); - return -EIO; - } - if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) { - btrfs_err(fs_info, "invalid chunk stripe length: %llu", - stripe_len); - return -EIO; - } - if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) & - type) { - btrfs_err(fs_info, "unrecognized chunk type: %llu", - ~(BTRFS_BLOCK_GROUP_TYPE_MASK | - BTRFS_BLOCK_GROUP_PROFILE_MASK) & - btrfs_chunk_type(leaf, chunk)); - return -EIO; - } - - if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) { - btrfs_err(fs_info, "missing chunk type flag: 0x%llx", type); - return -EIO; - } - - if ((type & BTRFS_BLOCK_GROUP_SYSTEM) && - (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) { - btrfs_err(fs_info, - "system chunk with data or metadata type: 0x%llx", type); - return -EIO; - } - - features = btrfs_super_incompat_flags(fs_info->super_copy); - if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) - mixed = true; - - if (!mixed) { - if ((type & BTRFS_BLOCK_GROUP_METADATA) && - (type & BTRFS_BLOCK_GROUP_DATA)) { - btrfs_err(fs_info, - "mixed chunk type in non-mixed mode: 0x%llx", type); - return -EIO; - } - } - - if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) || - (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) || - (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) || - (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) || - (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) || - ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && - num_stripes != 1)) { - btrfs_err(fs_info, - "invalid num_stripes:sub_stripes %u:%u for profile %llu", - num_stripes, sub_stripes, - type & BTRFS_BLOCK_GROUP_PROFILE_MASK); - return -EIO; - } - - return 0; -} - static void btrfs_report_missing_device(struct btrfs_fs_info *fs_info, u64 devid, u8 *uuid, bool error) { @@ -6818,10 +6663,30 @@ static void btrfs_report_missing_device(struct btrfs_fs_info *fs_info, devid, uuid); } -static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, - struct extent_buffer *leaf, +static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes) +{ + int index = btrfs_bg_flags_to_raid_index(type); + int ncopies = btrfs_raid_array[index].ncopies; + int data_stripes; + + switch (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + case BTRFS_BLOCK_GROUP_RAID5: + data_stripes = num_stripes - 1; + break; + case BTRFS_BLOCK_GROUP_RAID6: + data_stripes = num_stripes - 2; + break; + default: + data_stripes = num_stripes / ncopies; + break; + } + return div_u64(chunk_len, data_stripes); +} + +static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf, struct btrfs_chunk *chunk) { + struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree; struct map_lookup *map; struct extent_map *em; @@ -6837,9 +6702,15 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, length = btrfs_chunk_length(leaf, chunk); num_stripes = btrfs_chunk_num_stripes(leaf, chunk); - ret = btrfs_check_chunk_valid(fs_info, leaf, chunk, logical); - if (ret) - return ret; + /* + * Only need to verify chunk item if we're reading from sys chunk array, + * as chunk item in tree block is already verified by tree-checker. + */ + if (leaf->start == BTRFS_SUPER_INFO_OFFSET) { + ret = btrfs_check_chunk_valid(leaf, chunk, logical); + if (ret) + return ret; + } read_lock(&map_tree->map_tree.lock); em = lookup_extent_mapping(&map_tree->map_tree, logical, 1); @@ -6877,6 +6748,8 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, map->type = btrfs_chunk_type(leaf, chunk); map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); map->verified_stripes = 0; + em->orig_block_len = calc_stripe_length(map->type, em->len, + map->num_stripes); for (i = 0; i < num_stripes; i++) { map->stripes[i].physical = btrfs_stripe_offset_nr(leaf, chunk, i); @@ -7001,10 +6874,10 @@ out: return fs_devices; } -static int read_one_dev(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, +static int read_one_dev(struct extent_buffer *leaf, struct btrfs_dev_item *dev_item) { + struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; u64 devid; @@ -7193,7 +7066,7 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) if (cur_offset + len > array_size) goto out_short_read; - ret = read_one_chunk(fs_info, &key, sb, chunk); + ret = read_one_chunk(&key, sb, chunk); if (ret) break; } else { @@ -7334,14 +7207,14 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) struct btrfs_dev_item *dev_item; dev_item = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); - ret = read_one_dev(fs_info, leaf, dev_item); + ret = read_one_dev(leaf, dev_item); if (ret) goto error; total_dev++; } else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) { struct btrfs_chunk *chunk; chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); - ret = read_one_chunk(fs_info, &found_key, leaf, chunk); + ret = read_one_chunk(&found_key, leaf, chunk); if (ret) goto error; } @@ -7530,9 +7403,9 @@ out: /* * called from commit_transaction. Writes all changed device stats to disk. */ -int btrfs_run_dev_stats(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +int btrfs_run_dev_stats(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; int stats_cnt; @@ -7674,51 +7547,34 @@ void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_pat } /* - * Update the size of all devices, which is used for writing out the - * super blocks. + * Update the size and bytes used for each device where it changed. This is + * delayed since we would otherwise get errors while writing out the + * superblocks. + * + * Must be invoked during transaction commit. */ -void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info) +void btrfs_commit_device_sizes(struct btrfs_transaction *trans) { - struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *curr, *next; - if (list_empty(&fs_devices->resized_devices)) - return; - - mutex_lock(&fs_devices->device_list_mutex); - mutex_lock(&fs_info->chunk_mutex); - list_for_each_entry_safe(curr, next, &fs_devices->resized_devices, - resized_list) { - list_del_init(&curr->resized_list); - curr->commit_total_bytes = curr->disk_total_bytes; - } - mutex_unlock(&fs_info->chunk_mutex); - mutex_unlock(&fs_devices->device_list_mutex); -} + ASSERT(trans->state == TRANS_STATE_COMMIT_DOING); -/* Must be invoked during the transaction commit */ -void btrfs_update_commit_device_bytes_used(struct btrfs_transaction *trans) -{ - struct btrfs_fs_info *fs_info = trans->fs_info; - struct extent_map *em; - struct map_lookup *map; - struct btrfs_device *dev; - int i; - - if (list_empty(&trans->pending_chunks)) + if (list_empty(&trans->dev_update_list)) return; - /* In order to kick the device replace finish process */ - mutex_lock(&fs_info->chunk_mutex); - list_for_each_entry(em, &trans->pending_chunks, list) { - map = em->map_lookup; - - for (i = 0; i < map->num_stripes; i++) { - dev = map->stripes[i].dev; - dev->commit_bytes_used = dev->bytes_used; - } + /* + * We don't need the device_list_mutex here. This list is owned by the + * transaction and the transaction must complete before the device is + * released. + */ + mutex_lock(&trans->fs_info->chunk_mutex); + list_for_each_entry_safe(curr, next, &trans->dev_update_list, + post_commit_list) { + list_del_init(&curr->post_commit_list); + curr->commit_total_bytes = curr->disk_total_bytes; + curr->commit_bytes_used = curr->bytes_used; } - mutex_unlock(&fs_info->chunk_mutex); + mutex_unlock(&trans->fs_info->chunk_mutex); } void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info) @@ -7751,25 +7607,6 @@ int btrfs_bg_type_to_factor(u64 flags) } -static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes) -{ - int index = btrfs_bg_flags_to_raid_index(type); - int ncopies = btrfs_raid_array[index].ncopies; - int data_stripes; - - switch (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { - case BTRFS_BLOCK_GROUP_RAID5: - data_stripes = num_stripes - 1; - break; - case BTRFS_BLOCK_GROUP_RAID6: - data_stripes = num_stripes - 2; - break; - default: - data_stripes = num_stripes / ncopies; - break; - } - return div_u64(chunk_len, data_stripes); -} static int verify_one_dev_extent(struct btrfs_fs_info *fs_info, u64 chunk_offset, u64 devid, diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 3ad9d58d1b66..136a3eb64604 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -45,6 +45,7 @@ struct btrfs_pending_bios { struct btrfs_device { struct list_head dev_list; struct list_head dev_alloc_list; + struct list_head post_commit_list; /* chunk mutex */ struct btrfs_fs_devices *fs_devices; struct btrfs_fs_info *fs_info; @@ -102,18 +103,12 @@ struct btrfs_device { * size of the device on the current transaction * * This variant is update when committing the transaction, - * and protected by device_list_mutex + * and protected by chunk mutex */ u64 commit_total_bytes; /* bytes used on the current transaction */ u64 commit_bytes_used; - /* - * used to manage the device which is resized - * - * It is protected by chunk_lock. - */ - struct list_head resized_list; /* for sending down flush barriers */ struct bio *flush_bio; @@ -123,7 +118,6 @@ struct btrfs_device { struct scrub_ctx *scrub_ctx; struct btrfs_work work; - struct rcu_head rcu; /* readahead state */ atomic_t reada_in_flight; @@ -139,6 +133,8 @@ struct btrfs_device { /* Counter to record the change of device stats */ atomic_t dev_stats_ccnt; atomic_t dev_stat_values[BTRFS_DEV_STAT_VALUES_MAX]; + + struct extent_io_tree alloc_state; }; /* @@ -235,7 +231,6 @@ struct btrfs_fs_devices { struct mutex device_list_mutex; struct list_head devices; - struct list_head resized_devices; /* devices not currently being allocated */ struct list_head alloc_list; @@ -258,6 +253,15 @@ struct btrfs_fs_devices { #define BTRFS_BIO_INLINE_CSUM_SIZE 64 +#define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info) \ + - sizeof(struct btrfs_chunk)) \ + / sizeof(struct btrfs_stripe) + 1) + +#define BTRFS_MAX_DEVS_SYS_CHUNK ((BTRFS_SYSTEM_CHUNK_ARRAY_SIZE \ + - 2 * sizeof(struct btrfs_disk_key) \ + - 2 * sizeof(struct btrfs_chunk)) \ + / sizeof(struct btrfs_stripe) + 1) + /* * we need the mirror number and stripe index to be passed around * the call chain while we are processing end_io (especially errors). @@ -390,6 +394,7 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio) return BTRFS_MAP_WRITE; default: WARN_ON_ONCE(1); + /* fall through */ case REQ_OP_READ: return BTRFS_MAP_READ; } @@ -449,22 +454,18 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info); int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_fs_info *fs_info, u64 chunk_offset); -int find_free_dev_extent_start(struct btrfs_transaction *transaction, - struct btrfs_device *device, u64 num_bytes, - u64 search_start, u64 *start, u64 *max_avail); -int find_free_dev_extent(struct btrfs_trans_handle *trans, - struct btrfs_device *device, u64 num_bytes, +int find_free_dev_extent_start(struct btrfs_device *device, u64 num_bytes, + u64 search_start, u64 *start, u64 *max_avail); +int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *max_avail); void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index); int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_get_dev_stats *stats); void btrfs_init_devices_late(struct btrfs_fs_info *fs_info); int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info); -int btrfs_run_dev_stats(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); +int btrfs_run_dev_stats(struct btrfs_trans_handle *trans); void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev); -void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, - struct btrfs_device *srcdev); +void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev); void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev); void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path); int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, @@ -558,8 +559,7 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags) const char *get_raid_name(enum btrfs_raid_types type); -void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info); -void btrfs_update_commit_device_bytes_used(struct btrfs_transaction *trans); +void btrfs_commit_device_sizes(struct btrfs_transaction *trans); struct list_head *btrfs_get_fs_uuids(void); void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index f141b45ce349..78b6ba2029e8 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -76,9 +76,8 @@ out: return ret; } -static int do_setxattr(struct btrfs_trans_handle *trans, - struct inode *inode, const char *name, - const void *value, size_t size, int flags) +int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, + const char *name, const void *value, size_t size, int flags) { struct btrfs_dir_item *di = NULL; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -87,6 +86,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans, size_t name_len = strlen(name); int ret = 0; + ASSERT(trans); + if (name_len + size > BTRFS_MAX_XATTR_SIZE(root->fs_info)) return -ENOSPC; @@ -174,7 +175,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans, char *ptr; if (size > old_data_len) { - if (btrfs_leaf_free_space(fs_info, leaf) < + if (btrfs_leaf_free_space(leaf) < (size - old_data_len)) { ret = -ENOSPC; goto out; @@ -184,17 +185,15 @@ static int do_setxattr(struct btrfs_trans_handle *trans, if (old_data_len + name_len + sizeof(*di) == item_size) { /* No other xattrs packed in the same leaf item. */ if (size > old_data_len) - btrfs_extend_item(fs_info, path, - size - old_data_len); + btrfs_extend_item(path, size - old_data_len); else if (size < old_data_len) - btrfs_truncate_item(fs_info, path, - data_size, 1); + btrfs_truncate_item(path, data_size, 1); } else { /* There are other xattrs packed in the same item. */ ret = btrfs_delete_one_dir_name(trans, root, path, di); if (ret) goto out; - btrfs_extend_item(fs_info, path, data_size); + btrfs_extend_item(path, data_size); } item = btrfs_item_nr(slot); @@ -220,24 +219,18 @@ out: /* * @value: "" makes the attribute to empty, NULL removes it */ -int btrfs_setxattr(struct btrfs_trans_handle *trans, - struct inode *inode, const char *name, - const void *value, size_t size, int flags) +int btrfs_setxattr_trans(struct inode *inode, const char *name, + const void *value, size_t size, int flags) { struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_trans_handle *trans; int ret; - if (btrfs_root_readonly(root)) - return -EROFS; - - if (trans) - return do_setxattr(trans, inode, name, value, size, flags); - trans = btrfs_start_transaction(root, 2); if (IS_ERR(trans)) return PTR_ERR(trans); - ret = do_setxattr(trans, inode, name, value, size, flags); + ret = btrfs_setxattr(trans, inode, name, value, size, flags); if (ret) goto out; @@ -370,7 +363,7 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler, size_t size, int flags) { name = xattr_full_name(handler, name); - return btrfs_setxattr(NULL, inode, name, buffer, size, flags); + return btrfs_setxattr_trans(inode, name, buffer, size, flags); } static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, @@ -378,8 +371,32 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, const char *name, const void *value, size_t size, int flags) { + int ret; + struct btrfs_trans_handle *trans; + struct btrfs_root *root = BTRFS_I(inode)->root; + name = xattr_full_name(handler, name); - return btrfs_set_prop(inode, name, value, size, flags); + ret = btrfs_validate_prop(name, value, size); + if (ret) + return ret; + + trans = btrfs_start_transaction(root, 2); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + ret = btrfs_set_prop(trans, inode, name, value, size, flags); + if (!ret) { + inode_inc_iversion(inode); + inode->i_ctime = current_time(inode); + set_bit(BTRFS_INODE_COPY_EVERYTHING, + &BTRFS_I(inode)->runtime_flags); + ret = btrfs_update_inode(trans, root, inode); + BUG_ON(ret); + } + + btrfs_end_transaction(trans); + + return ret; } static const struct xattr_handler btrfs_security_xattr_handler = { @@ -419,10 +436,10 @@ const struct xattr_handler *btrfs_xattr_handlers[] = { }; static int btrfs_initxattrs(struct inode *inode, - const struct xattr *xattr_array, void *fs_info) + const struct xattr *xattr_array, void *fs_private) { + struct btrfs_trans_handle *trans = fs_private; const struct xattr *xattr; - struct btrfs_trans_handle *trans = fs_info; unsigned int nofs_flag; char *name; int err = 0; @@ -442,7 +459,7 @@ static int btrfs_initxattrs(struct inode *inode, strcpy(name, XATTR_SECURITY_PREFIX); strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name); err = btrfs_setxattr(trans, inode, name, xattr->value, - xattr->value_len, 0); + xattr->value_len, 0); kfree(name); if (err < 0) break; diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h index 471fcac6ff55..1cd3fc0a8f17 100644 --- a/fs/btrfs/xattr.h +++ b/fs/btrfs/xattr.h @@ -12,9 +12,10 @@ extern const struct xattr_handler *btrfs_xattr_handlers[]; int btrfs_getxattr(struct inode *inode, const char *name, void *buffer, size_t size); -int btrfs_setxattr(struct btrfs_trans_handle *trans, - struct inode *inode, const char *name, - const void *value, size_t size, int flags); +int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, + const char *name, const void *value, size_t size, int flags); +int btrfs_setxattr_trans(struct inode *inode, const char *name, + const void *value, size_t size, int flags); ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size); int btrfs_xattr_security_init(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index 6b9e29d050f3..a6ff07cf11d5 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -90,6 +90,9 @@ static inline struct workspace *list_to_workspace(struct list_head *list) return container_of(list, struct workspace, list); } +static void zstd_free_workspace(struct list_head *ws); +static struct list_head *zstd_alloc_workspace(unsigned int level); + /* * zstd_reclaim_timer_fn - reclaim timer * @t: timer @@ -124,7 +127,7 @@ static void zstd_reclaim_timer_fn(struct timer_list *timer) level = victim->level; list_del(&victim->lru_list); list_del(&victim->list); - wsm.ops->free_workspace(&victim->list); + zstd_free_workspace(&victim->list); if (list_empty(&wsm.idle_ws[level - 1])) clear_bit(level - 1, &wsm.active_map); @@ -180,7 +183,7 @@ static void zstd_init_workspace_manager(void) for (i = 0; i < ZSTD_BTRFS_MAX_LEVEL; i++) INIT_LIST_HEAD(&wsm.idle_ws[i]); - ws = wsm.ops->alloc_workspace(ZSTD_BTRFS_MAX_LEVEL); + ws = zstd_alloc_workspace(ZSTD_BTRFS_MAX_LEVEL); if (IS_ERR(ws)) { pr_warn( "BTRFS: cannot preallocate zstd compression workspace\n"); @@ -202,7 +205,7 @@ static void zstd_cleanup_workspace_manager(void) struct workspace, list); list_del(&workspace->list); list_del(&workspace->lru_list); - wsm.ops->free_workspace(&workspace->list); + zstd_free_workspace(&workspace->list); } } spin_unlock(&wsm.lock); @@ -272,7 +275,7 @@ again: return ws; nofs_flag = memalloc_nofs_save(); - ws = wsm.ops->alloc_workspace(level); + ws = zstd_alloc_workspace(level); memalloc_nofs_restore(nofs_flag); if (IS_ERR(ws)) { diff --git a/fs/buffer.c b/fs/buffer.c index ce357602f471..0faa41fb4c88 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2085,7 +2085,7 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, } EXPORT_SYMBOL(block_write_begin); -int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, +void __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, struct page *page) { loff_t old_size = inode->i_size; @@ -2104,7 +2104,6 @@ int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, } unlock_page(page); - put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); @@ -2116,7 +2115,6 @@ int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, */ if (i_size_changed) mark_inode_dirty(inode); - return copied; } int block_write_end(struct file *file, struct address_space *mapping, @@ -2160,7 +2158,9 @@ int generic_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); - return __generic_write_end(mapping->host, pos, copied, page); + __generic_write_end(mapping->host, pos, copied, page); + put_page(page); + return copied; } EXPORT_SYMBOL(generic_write_end); diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 1645fcfd9691..d27720cd3664 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -20,7 +20,6 @@ #include <linux/namei.h> #include <linux/security.h> #include <linux/slab.h> -#include <linux/xattr.h> #include "internal.h" #define CACHEFILES_KEYBUF_SIZE 512 diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 36a8dc699448..72f8e1311392 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -892,8 +892,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) int have = ci->i_snap_caps; if ((have & mask) == mask) { - dout("__ceph_caps_issued_mask %p snap issued %s" - " (mask %s)\n", &ci->vfs_inode, + dout("__ceph_caps_issued_mask ino 0x%lx snap issued %s" + " (mask %s)\n", ci->vfs_inode.i_ino, ceph_cap_string(have), ceph_cap_string(mask)); return 1; @@ -904,8 +904,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) if (!__cap_is_valid(cap)) continue; if ((cap->issued & mask) == mask) { - dout("__ceph_caps_issued_mask %p cap %p issued %s" - " (mask %s)\n", &ci->vfs_inode, cap, + dout("__ceph_caps_issued_mask ino 0x%lx cap %p issued %s" + " (mask %s)\n", ci->vfs_inode.i_ino, cap, ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) @@ -916,8 +916,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) /* does a combination of caps satisfy mask? */ have |= cap->issued; if ((have & mask) == mask) { - dout("__ceph_caps_issued_mask %p combo issued %s" - " (mask %s)\n", &ci->vfs_inode, + dout("__ceph_caps_issued_mask ino 0x%lx combo issued %s" + " (mask %s)\n", ci->vfs_inode.i_ino, ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) { @@ -2257,8 +2257,6 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) if (datasync) goto out; - inode_lock(inode); - dirty = try_flush_caps(inode, &flush_tid); dout("fsync dirty caps are %s\n", ceph_cap_string(dirty)); @@ -2273,7 +2271,6 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) ret = wait_event_interruptible(ci->i_cap_wq, caps_are_flushed(inode, flush_tid)); } - inode_unlock(inode); out: dout("fsync %p%s result=%d\n", inode, datasync ? " datasync" : "", ret); return ret; @@ -2528,9 +2525,14 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got, * to (when applicable), and check against max_size here as well. * Note that caller is responsible for ensuring max_size increases are * requested from the MDS. + * + * Returns 0 if caps were not able to be acquired (yet), a 1 if they were, + * or a negative error code. + * + * FIXME: how does a 0 return differ from -EAGAIN? */ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want, - loff_t endoff, bool nonblock, int *got, int *err) + loff_t endoff, bool nonblock, int *got) { struct inode *inode = &ci->vfs_inode; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; @@ -2550,8 +2552,7 @@ again: if ((file_wanted & need) != need) { dout("try_get_cap_refs need %s file_wanted %s, EBADF\n", ceph_cap_string(need), ceph_cap_string(file_wanted)); - *err = -EBADF; - ret = 1; + ret = -EBADF; goto out_unlock; } @@ -2572,10 +2573,8 @@ again: if (endoff >= 0 && endoff > (loff_t)ci->i_max_size) { dout("get_cap_refs %p endoff %llu > maxsize %llu\n", inode, endoff, ci->i_max_size); - if (endoff > ci->i_requested_max_size) { - *err = -EAGAIN; - ret = 1; - } + if (endoff > ci->i_requested_max_size) + ret = -EAGAIN; goto out_unlock; } /* @@ -2610,8 +2609,7 @@ again: * task isn't in TASK_RUNNING state */ if (nonblock) { - *err = -EAGAIN; - ret = 1; + ret = -EAGAIN; goto out_unlock; } @@ -2640,8 +2638,7 @@ again: if (session_readonly) { dout("get_cap_refs %p needed %s but mds%d readonly\n", inode, ceph_cap_string(need), ci->i_auth_cap->mds); - *err = -EROFS; - ret = 1; + ret = -EROFS; goto out_unlock; } @@ -2650,16 +2647,14 @@ again: if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) { dout("get_cap_refs %p forced umount\n", inode); - *err = -EIO; - ret = 1; + ret = -EIO; goto out_unlock; } mds_wanted = __ceph_caps_mds_wanted(ci, false); if (need & ~(mds_wanted & need)) { dout("get_cap_refs %p caps were dropped" " (session killed?)\n", inode); - *err = -ESTALE; - ret = 1; + ret = -ESTALE; goto out_unlock; } if (!(file_wanted & ~mds_wanted)) @@ -2710,7 +2705,7 @@ static void check_max_size(struct inode *inode, loff_t endoff) int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, bool nonblock, int *got) { - int ret, err = 0; + int ret; BUG_ON(need & ~CEPH_CAP_FILE_RD); BUG_ON(want & ~(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO|CEPH_CAP_FILE_SHARED)); @@ -2718,15 +2713,8 @@ int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, if (ret < 0) return ret; - ret = try_get_cap_refs(ci, need, want, 0, nonblock, got, &err); - if (ret) { - if (err == -EAGAIN) { - ret = 0; - } else if (err < 0) { - ret = err; - } - } - return ret; + ret = try_get_cap_refs(ci, need, want, 0, nonblock, got); + return ret == -EAGAIN ? 0 : ret; } /* @@ -2737,7 +2725,7 @@ int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, loff_t endoff, int *got, struct page **pinned_page) { - int _got, ret, err = 0; + int _got, ret; ret = ceph_pool_perm_check(ci, need); if (ret < 0) @@ -2747,21 +2735,19 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, if (endoff > 0) check_max_size(&ci->vfs_inode, endoff); - err = 0; _got = 0; ret = try_get_cap_refs(ci, need, want, endoff, - false, &_got, &err); - if (ret) { - if (err == -EAGAIN) - continue; - if (err < 0) - ret = err; - } else { + false, &_got); + if (ret == -EAGAIN) { + continue; + } else if (!ret) { + int err; + DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(&ci->i_cap_wq, &wait); - while (!try_get_cap_refs(ci, need, want, endoff, - true, &_got, &err)) { + while (!(err = try_get_cap_refs(ci, need, want, endoff, + true, &_got))) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -2770,19 +2756,14 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, } remove_wait_queue(&ci->i_cap_wq, &wait); - if (err == -EAGAIN) continue; - if (err < 0) - ret = err; } - if (ret < 0) { - if (err == -ESTALE) { - /* session was killed, try renew caps */ - ret = ceph_renew_caps(&ci->vfs_inode); - if (ret == 0) - continue; - } + if (ret == -ESTALE) { + /* session was killed, try renew caps */ + ret = ceph_renew_caps(&ci->vfs_inode); + if (ret == 0) + continue; return ret; } @@ -4099,7 +4080,7 @@ void ceph_put_fmode(struct ceph_inode_info *ci, int fmode) } /* - * For a soon-to-be unlinked file, drop the AUTH_RDCACHE caps. If it + * For a soon-to-be unlinked file, drop the LINK caps. If it * looks like the link count will hit 0, drop any other caps (other * than PIN) we don't specifically want (due to the file still being * open). diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 98365e74cb4a..b3fc5fe26a1a 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -37,7 +37,7 @@ static int mdsmap_show(struct seq_file *s, void *p) struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr; int state = mdsmap->m_info[i].state; seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, - ceph_pr_addr(&addr->in_addr), + ceph_pr_addr(addr), ceph_mds_state_name(state)); } return 0; @@ -88,7 +88,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_dentry, path ? path : ""); spin_unlock(&req->r_dentry->d_lock); - kfree(path); + ceph_mdsc_free_path(path, pathlen); } else if (req->r_path1) { seq_printf(s, " #%llx/%s", req->r_ino1.ino, req->r_path1); @@ -108,7 +108,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_old_dentry, path ? path : ""); spin_unlock(&req->r_old_dentry->d_lock); - kfree(path); + ceph_mdsc_free_path(path, pathlen); } else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) { if (req->r_ino2.ino) seq_printf(s, " #%llx/%s", req->r_ino2.ino, @@ -124,18 +124,48 @@ static int mdsc_show(struct seq_file *s, void *p) return 0; } +static int caps_show_cb(struct inode *inode, struct ceph_cap *cap, void *p) +{ + struct seq_file *s = p; + + seq_printf(s, "0x%-17lx%-17s%-17s\n", inode->i_ino, + ceph_cap_string(cap->issued), + ceph_cap_string(cap->implemented)); + return 0; +} + static int caps_show(struct seq_file *s, void *p) { struct ceph_fs_client *fsc = s->private; - int total, avail, used, reserved, min; + struct ceph_mds_client *mdsc = fsc->mdsc; + int total, avail, used, reserved, min, i; ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min); seq_printf(s, "total\t\t%d\n" "avail\t\t%d\n" "used\t\t%d\n" "reserved\t%d\n" - "min\t%d\n", + "min\t\t%d\n\n", total, avail, used, reserved, min); + seq_printf(s, "ino issued implemented\n"); + seq_printf(s, "-----------------------------------------------\n"); + + mutex_lock(&mdsc->mutex); + for (i = 0; i < mdsc->max_sessions; i++) { + struct ceph_mds_session *session; + + session = __ceph_lookup_mds_session(mdsc, i); + if (!session) + continue; + mutex_unlock(&mdsc->mutex); + mutex_lock(&session->s_mutex); + ceph_iterate_session_caps(session, caps_show_cb, s); + mutex_unlock(&session->s_mutex); + ceph_put_mds_session(session); + mutex_lock(&mdsc->mutex); + } + mutex_unlock(&mdsc->mutex); + return 0; } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index a8f429882249..0637149fb9f9 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1766,6 +1766,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size, unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) { struct ceph_inode_info *dci = ceph_inode(dir); + unsigned hash; switch (dci->i_dir_layout.dl_dir_hash) { case 0: /* for backward compat */ @@ -1773,8 +1774,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) return dn->d_name.hash; default: - return ceph_str_hash(dci->i_dir_layout.dl_dir_hash, + spin_lock(&dn->d_lock); + hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash, dn->d_name.name, dn->d_name.len); + spin_unlock(&dn->d_lock); + return hash; } } diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 3c59ad180ef0..d3ef7ee429ec 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -22,18 +22,77 @@ struct ceph_nfs_confh { u64 ino, parent_ino; } __attribute__ ((packed)); +/* + * fh for snapped inode + */ +struct ceph_nfs_snapfh { + u64 ino; + u64 snapid; + u64 parent_ino; + u32 hash; +} __attribute__ ((packed)); + +static int ceph_encode_snapfh(struct inode *inode, u32 *rawfh, int *max_len, + struct inode *parent_inode) +{ + const static int snap_handle_length = + sizeof(struct ceph_nfs_snapfh) >> 2; + struct ceph_nfs_snapfh *sfh = (void *)rawfh; + u64 snapid = ceph_snap(inode); + int ret; + bool no_parent = true; + + if (*max_len < snap_handle_length) { + *max_len = snap_handle_length; + ret = FILEID_INVALID; + goto out; + } + + ret = -EINVAL; + if (snapid != CEPH_SNAPDIR) { + struct inode *dir; + struct dentry *dentry = d_find_alias(inode); + if (!dentry) + goto out; + + rcu_read_lock(); + dir = d_inode_rcu(dentry->d_parent); + if (ceph_snap(dir) != CEPH_SNAPDIR) { + sfh->parent_ino = ceph_ino(dir); + sfh->hash = ceph_dentry_hash(dir, dentry); + no_parent = false; + } + rcu_read_unlock(); + dput(dentry); + } + + if (no_parent) { + if (!S_ISDIR(inode->i_mode)) + goto out; + sfh->parent_ino = sfh->ino; + sfh->hash = 0; + } + sfh->ino = ceph_ino(inode); + sfh->snapid = snapid; + + *max_len = snap_handle_length; + ret = FILEID_BTRFS_WITH_PARENT; +out: + dout("encode_snapfh %llx.%llx ret=%d\n", ceph_vinop(inode), ret); + return ret; +} + static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, struct inode *parent_inode) { + const static int handle_length = + sizeof(struct ceph_nfs_fh) >> 2; + const static int connected_handle_length = + sizeof(struct ceph_nfs_confh) >> 2; int type; - struct ceph_nfs_fh *fh = (void *)rawfh; - struct ceph_nfs_confh *cfh = (void *)rawfh; - int connected_handle_length = sizeof(*cfh)/4; - int handle_length = sizeof(*fh)/4; - /* don't re-export snaps */ if (ceph_snap(inode) != CEPH_NOSNAP) - return -EINVAL; + return ceph_encode_snapfh(inode, rawfh, max_len, parent_inode); if (parent_inode && (*max_len < connected_handle_length)) { *max_len = connected_handle_length; @@ -44,6 +103,7 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, } if (parent_inode) { + struct ceph_nfs_confh *cfh = (void *)rawfh; dout("encode_fh %llx with parent %llx\n", ceph_ino(inode), ceph_ino(parent_inode)); cfh->ino = ceph_ino(inode); @@ -51,6 +111,7 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, *max_len = connected_handle_length; type = FILEID_INO32_GEN_PARENT; } else { + struct ceph_nfs_fh *fh = (void *)rawfh; dout("encode_fh %llx\n", ceph_ino(inode)); fh->ino = ceph_ino(inode); *max_len = handle_length; @@ -59,7 +120,7 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, return type; } -static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) +static struct inode *__lookup_inode(struct super_block *sb, u64 ino) { struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc; struct inode *inode; @@ -81,7 +142,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) mask = CEPH_STAT_CAP_INODE; if (ceph_security_xattr_wanted(d_inode(sb->s_root))) mask |= CEPH_CAP_XATTR_SHARED; - req->r_args.getattr.mask = cpu_to_le32(mask); + req->r_args.lookupino.mask = cpu_to_le32(mask); req->r_ino1 = vino; req->r_num_caps = 1; @@ -91,16 +152,114 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) ihold(inode); ceph_mdsc_put_request(req); if (!inode) - return ERR_PTR(-ESTALE); - if (inode->i_nlink == 0) { - iput(inode); - return ERR_PTR(-ESTALE); - } + return err < 0 ? ERR_PTR(err) : ERR_PTR(-ESTALE); } + return inode; +} + +struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino) +{ + struct inode *inode = __lookup_inode(sb, ino); + if (IS_ERR(inode)) + return inode; + if (inode->i_nlink == 0) { + iput(inode); + return ERR_PTR(-ESTALE); + } + return inode; +} +static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) +{ + struct inode *inode = __lookup_inode(sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + if (inode->i_nlink == 0) { + iput(inode); + return ERR_PTR(-ESTALE); + } return d_obtain_alias(inode); } +static struct dentry *__snapfh_to_dentry(struct super_block *sb, + struct ceph_nfs_snapfh *sfh, + bool want_parent) +{ + struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc; + struct ceph_mds_request *req; + struct inode *inode; + struct ceph_vino vino; + int mask; + int err; + bool unlinked = false; + + if (want_parent) { + vino.ino = sfh->parent_ino; + if (sfh->snapid == CEPH_SNAPDIR) + vino.snap = CEPH_NOSNAP; + else if (sfh->ino == sfh->parent_ino) + vino.snap = CEPH_SNAPDIR; + else + vino.snap = sfh->snapid; + } else { + vino.ino = sfh->ino; + vino.snap = sfh->snapid; + } + inode = ceph_find_inode(sb, vino); + if (inode) + return d_obtain_alias(inode); + + req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO, + USE_ANY_MDS); + if (IS_ERR(req)) + return ERR_CAST(req); + + mask = CEPH_STAT_CAP_INODE; + if (ceph_security_xattr_wanted(d_inode(sb->s_root))) + mask |= CEPH_CAP_XATTR_SHARED; + req->r_args.lookupino.mask = cpu_to_le32(mask); + if (vino.snap < CEPH_NOSNAP) { + req->r_args.lookupino.snapid = cpu_to_le64(vino.snap); + if (!want_parent && sfh->ino != sfh->parent_ino) { + req->r_args.lookupino.parent = + cpu_to_le64(sfh->parent_ino); + req->r_args.lookupino.hash = + cpu_to_le32(sfh->hash); + } + } + + req->r_ino1 = vino; + req->r_num_caps = 1; + err = ceph_mdsc_do_request(mdsc, NULL, req); + inode = req->r_target_inode; + if (inode) { + if (vino.snap == CEPH_SNAPDIR) { + if (inode->i_nlink == 0) + unlinked = true; + inode = ceph_get_snapdir(inode); + } else if (ceph_snap(inode) == vino.snap) { + ihold(inode); + } else { + /* mds does not support lookup snapped inode */ + err = -EOPNOTSUPP; + inode = NULL; + } + } + ceph_mdsc_put_request(req); + + if (want_parent) { + dout("snapfh_to_parent %llx.%llx\n err=%d\n", + vino.ino, vino.snap, err); + } else { + dout("snapfh_to_dentry %llx.%llx parent %llx hash %x err=%d", + vino.ino, vino.snap, sfh->parent_ino, sfh->hash, err); + } + if (!inode) + return ERR_PTR(-ESTALE); + /* see comments in ceph_get_parent() */ + return unlinked ? d_obtain_root(inode) : d_obtain_alias(inode); +} + /* * convert regular fh to dentry */ @@ -110,6 +269,11 @@ static struct dentry *ceph_fh_to_dentry(struct super_block *sb, { struct ceph_nfs_fh *fh = (void *)fid->raw; + if (fh_type == FILEID_BTRFS_WITH_PARENT) { + struct ceph_nfs_snapfh *sfh = (void *)fid->raw; + return __snapfh_to_dentry(sb, sfh, false); + } + if (fh_type != FILEID_INO32_GEN && fh_type != FILEID_INO32_GEN_PARENT) return NULL; @@ -163,13 +327,49 @@ static struct dentry *__get_parent(struct super_block *sb, static struct dentry *ceph_get_parent(struct dentry *child) { - /* don't re-export snaps */ - if (ceph_snap(d_inode(child)) != CEPH_NOSNAP) - return ERR_PTR(-EINVAL); - - dout("get_parent %p ino %llx.%llx\n", - child, ceph_vinop(d_inode(child))); - return __get_parent(child->d_sb, child, 0); + struct inode *inode = d_inode(child); + struct dentry *dn; + + if (ceph_snap(inode) != CEPH_NOSNAP) { + struct inode* dir; + bool unlinked = false; + /* do not support non-directory */ + if (!d_is_dir(child)) { + dn = ERR_PTR(-EINVAL); + goto out; + } + dir = __lookup_inode(inode->i_sb, ceph_ino(inode)); + if (IS_ERR(dir)) { + dn = ERR_CAST(dir); + goto out; + } + /* There can be multiple paths to access snapped inode. + * For simplicity, treat snapdir of head inode as parent */ + if (ceph_snap(inode) != CEPH_SNAPDIR) { + struct inode *snapdir = ceph_get_snapdir(dir); + if (dir->i_nlink == 0) + unlinked = true; + iput(dir); + if (IS_ERR(snapdir)) { + dn = ERR_CAST(snapdir); + goto out; + } + dir = snapdir; + } + /* If directory has already been deleted, futher get_parent + * will fail. Do not mark snapdir dentry as disconnected, + * this prevent exportfs from doing futher get_parent. */ + if (unlinked) + dn = d_obtain_root(dir); + else + dn = d_obtain_alias(dir); + } else { + dn = __get_parent(child->d_sb, child, 0); + } +out: + dout("get_parent %p ino %llx.%llx err=%ld\n", + child, ceph_vinop(inode), (IS_ERR(dn) ? PTR_ERR(dn) : 0)); + return dn; } /* @@ -182,6 +382,11 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb, struct ceph_nfs_confh *cfh = (void *)fid->raw; struct dentry *dentry; + if (fh_type == FILEID_BTRFS_WITH_PARENT) { + struct ceph_nfs_snapfh *sfh = (void *)fid->raw; + return __snapfh_to_dentry(sb, sfh, true); + } + if (fh_type != FILEID_INO32_GEN_PARENT) return NULL; if (fh_len < sizeof(*cfh) / 4) @@ -194,14 +399,115 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb, return dentry; } +static int __get_snap_name(struct dentry *parent, char *name, + struct dentry *child) +{ + struct inode *inode = d_inode(child); + struct inode *dir = d_inode(parent); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_mds_request *req = NULL; + char *last_name = NULL; + unsigned next_offset = 2; + int err = -EINVAL; + + if (ceph_ino(inode) != ceph_ino(dir)) + goto out; + if (ceph_snap(inode) == CEPH_SNAPDIR) { + if (ceph_snap(dir) == CEPH_NOSNAP) { + strcpy(name, fsc->mount_options->snapdir_name); + err = 0; + } + goto out; + } + if (ceph_snap(dir) != CEPH_SNAPDIR) + goto out; + + while (1) { + struct ceph_mds_reply_info_parsed *rinfo; + struct ceph_mds_reply_dir_entry *rde; + int i; + + req = ceph_mdsc_create_request(fsc->mdsc, CEPH_MDS_OP_LSSNAP, + USE_AUTH_MDS); + if (IS_ERR(req)) { + err = PTR_ERR(req); + req = NULL; + goto out; + } + err = ceph_alloc_readdir_reply_buffer(req, inode); + if (err) + goto out; + + req->r_direct_mode = USE_AUTH_MDS; + req->r_readdir_offset = next_offset; + req->r_args.readdir.flags = + cpu_to_le16(CEPH_READDIR_REPLY_BITFLAGS); + if (last_name) { + req->r_path2 = last_name; + last_name = NULL; + } + + req->r_inode = dir; + ihold(dir); + req->r_dentry = dget(parent); + + inode_lock(dir); + err = ceph_mdsc_do_request(fsc->mdsc, NULL, req); + inode_unlock(dir); + + if (err < 0) + goto out; + + rinfo = &req->r_reply_info; + for (i = 0; i < rinfo->dir_nr; i++) { + rde = rinfo->dir_entries + i; + BUG_ON(!rde->inode.in); + if (ceph_snap(inode) == + le64_to_cpu(rde->inode.in->snapid)) { + memcpy(name, rde->name, rde->name_len); + name[rde->name_len] = '\0'; + err = 0; + goto out; + } + } + + if (rinfo->dir_end) + break; + + BUG_ON(rinfo->dir_nr <= 0); + rde = rinfo->dir_entries + (rinfo->dir_nr - 1); + next_offset += rinfo->dir_nr; + last_name = kstrndup(rde->name, rde->name_len, GFP_KERNEL); + if (!last_name) { + err = -ENOMEM; + goto out; + } + + ceph_mdsc_put_request(req); + req = NULL; + } + err = -ENOENT; +out: + if (req) + ceph_mdsc_put_request(req); + kfree(last_name); + dout("get_snap_name %p ino %llx.%llx err=%d\n", + child, ceph_vinop(inode), err); + return err; +} + static int ceph_get_name(struct dentry *parent, char *name, struct dentry *child) { struct ceph_mds_client *mdsc; struct ceph_mds_request *req; + struct inode *inode = d_inode(child); int err; - mdsc = ceph_inode_to_client(d_inode(child))->mdsc; + if (ceph_snap(inode) != CEPH_NOSNAP) + return __get_snap_name(parent, name, child); + + mdsc = ceph_inode_to_client(inode)->mdsc; req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME, USE_ANY_MDS); if (IS_ERR(req)) @@ -209,8 +515,8 @@ static int ceph_get_name(struct dentry *parent, char *name, inode_lock(d_inode(parent)); - req->r_inode = d_inode(child); - ihold(d_inode(child)); + req->r_inode = inode; + ihold(inode); req->r_ino2 = ceph_vino(d_inode(parent)); req->r_parent = d_inode(parent); set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); @@ -224,10 +530,10 @@ static int ceph_get_name(struct dentry *parent, char *name, memcpy(name, rinfo->dname, rinfo->dname_len); name[rinfo->dname_len] = 0; dout("get_name %p ino %llx.%llx name %s\n", - child, ceph_vinop(d_inode(child)), name); + child, ceph_vinop(inode), name); } else { dout("get_name %p ino %llx.%llx err %d\n", - child, ceph_vinop(d_inode(child)), err); + child, ceph_vinop(inode), err); } ceph_mdsc_put_request(req); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 9f53c3d99304..305daf043eb0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -247,6 +247,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) case S_IFREG: ceph_fscache_register_inode_cookie(inode); ceph_fscache_file_set_cookie(inode, file); + /* fall through */ case S_IFDIR: ret = ceph_init_file_info(inode, file, fmode, S_ISDIR(inode->i_mode)); @@ -928,7 +929,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, dout("sync_direct_%s on file %p %lld~%u snapc %p seq %lld\n", (write ? "write" : "read"), file, pos, (unsigned)count, - snapc, snapc->seq); + snapc, snapc ? snapc->seq : 0); ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count - 1); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 2d61ddda9bf5..f85355bf49c4 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -519,9 +519,8 @@ struct inode *ceph_alloc_inode(struct super_block *sb) return &ci->vfs_inode; } -static void ceph_i_callback(struct rcu_head *head) +void ceph_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); struct ceph_inode_info *ci = ceph_inode(inode); kfree(ci->i_symlink); @@ -581,8 +580,6 @@ void ceph_destroy_inode(struct inode *inode) ceph_buffer_put(ci->i_xattrs.prealloc_blob); ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns)); - - call_rcu(&inode->i_rcu, ceph_i_callback); } int ceph_drop_inode(struct inode *inode) @@ -1163,6 +1160,19 @@ static int splice_dentry(struct dentry **pdn, struct inode *in) return 0; } +static int d_name_cmp(struct dentry *dentry, const char *name, size_t len) +{ + int ret; + + /* take d_lock to ensure dentry->d_name stability */ + spin_lock(&dentry->d_lock); + ret = dentry->d_name.len - len; + if (!ret) + ret = memcmp(dentry->d_name.name, name, len); + spin_unlock(&dentry->d_lock); + return ret; +} + /* * Incorporate results into the local cache. This is either just * one inode, or a directory, dentry, and possibly linked-to inode (e.g., @@ -1412,7 +1422,8 @@ retry_lookup: err = splice_dentry(&req->r_dentry, in); if (err < 0) goto done; - } else if (rinfo->head->is_dentry) { + } else if (rinfo->head->is_dentry && + !d_name_cmp(req->r_dentry, rinfo->dname, rinfo->dname_len)) { struct ceph_vino *ptvino = NULL; if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) || @@ -2255,43 +2266,72 @@ int ceph_permission(struct inode *inode, int mask) return err; } +/* Craft a mask of needed caps given a set of requested statx attrs. */ +static int statx_to_caps(u32 want) +{ + int mask = 0; + + if (want & (STATX_MODE|STATX_UID|STATX_GID|STATX_CTIME)) + mask |= CEPH_CAP_AUTH_SHARED; + + if (want & (STATX_NLINK|STATX_CTIME)) + mask |= CEPH_CAP_LINK_SHARED; + + if (want & (STATX_ATIME|STATX_MTIME|STATX_CTIME|STATX_SIZE| + STATX_BLOCKS)) + mask |= CEPH_CAP_FILE_SHARED; + + if (want & (STATX_CTIME)) + mask |= CEPH_CAP_XATTR_SHARED; + + return mask; +} + /* - * Get all attributes. Hopefully somedata we'll have a statlite() - * and can limit the fields we require to be accurate. + * Get all the attributes. If we have sufficient caps for the requested attrs, + * then we can avoid talking to the MDS at all. */ int ceph_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); struct ceph_inode_info *ci = ceph_inode(inode); - int err; + int err = 0; - err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL, false); - if (!err) { - generic_fillattr(inode, stat); - stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino); - if (ceph_snap(inode) == CEPH_NOSNAP) - stat->dev = inode->i_sb->s_dev; + /* Skip the getattr altogether if we're asked not to sync */ + if (!(flags & AT_STATX_DONT_SYNC)) { + err = ceph_do_getattr(inode, statx_to_caps(request_mask), + flags & AT_STATX_FORCE_SYNC); + if (err) + return err; + } + + generic_fillattr(inode, stat); + stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino); + if (ceph_snap(inode) == CEPH_NOSNAP) + stat->dev = inode->i_sb->s_dev; + else + stat->dev = ci->i_snapid_map ? ci->i_snapid_map->dev : 0; + + if (S_ISDIR(inode->i_mode)) { + if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), + RBYTES)) + stat->size = ci->i_rbytes; else - stat->dev = ci->i_snapid_map ? ci->i_snapid_map->dev : 0; - - if (S_ISDIR(inode->i_mode)) { - if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), - RBYTES)) - stat->size = ci->i_rbytes; - else - stat->size = ci->i_files + ci->i_subdirs; - stat->blocks = 0; - stat->blksize = 65536; - /* - * Some applications rely on the number of st_nlink - * value on directories to be either 0 (if unlinked) - * or 2 + number of subdirectories. - */ - if (stat->nlink == 1) - /* '.' + '..' + subdirs */ - stat->nlink = 1 + 1 + ci->i_subdirs; - } + stat->size = ci->i_files + ci->i_subdirs; + stat->blocks = 0; + stat->blksize = 65536; + /* + * Some applications rely on the number of st_nlink + * value on directories to be either 0 (if unlinked) + * or 2 + number of subdirectories. + */ + if (stat->nlink == 1) + /* '.' + '..' + subdirs */ + stat->nlink = 1 + 1 + ci->i_subdirs; } + + /* Mask off any higher bits (e.g. btime) until we have support */ + stat->result_mask = request_mask & STATX_BASIC_STATS; return err; } diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 9dae2ec7e1fa..ac9b53b89365 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -237,15 +237,6 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) { err = -EIO; - } else if (op == CEPH_MDS_OP_SETFILELOCK) { - /* - * increasing i_filelock_ref closes race window between - * handling request reply and adding file_lock struct to - * inode. Otherwise, i_auth_cap may get trimmed in the - * window. Caller function will decrease the counter. - */ - fl->fl_ops = &ceph_fl_lock_ops; - atomic_inc(&ci->i_filelock_ref); } spin_unlock(&ci->i_ceph_lock); if (err < 0) { @@ -299,10 +290,6 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) { err = -EIO; - } else { - /* see comment in ceph_lock */ - fl->fl_ops = &ceph_fl_lock_ops; - atomic_inc(&ci->i_filelock_ref); } spin_unlock(&ci->i_ceph_lock); if (err < 0) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 21c33ed048ed..959b1bf7c327 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -550,15 +550,9 @@ void ceph_put_mds_session(struct ceph_mds_session *s) struct ceph_mds_session *__ceph_lookup_mds_session(struct ceph_mds_client *mdsc, int mds) { - struct ceph_mds_session *session; - if (mds >= mdsc->max_sessions || !mdsc->sessions[mds]) return NULL; - session = mdsc->sessions[mds]; - dout("lookup_mds_session %p %d\n", session, - refcount_read(&session->s_ref)); - get_session(session); - return session; + return get_session(mdsc->sessions[mds]); } static bool __have_session(struct ceph_mds_client *mdsc, int mds) @@ -1284,9 +1278,9 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc, * * Caller must hold session s_mutex. */ -static int iterate_session_caps(struct ceph_mds_session *session, - int (*cb)(struct inode *, struct ceph_cap *, - void *), void *arg) +int ceph_iterate_session_caps(struct ceph_mds_session *session, + int (*cb)(struct inode *, struct ceph_cap *, + void *), void *arg) { struct list_head *p; struct ceph_cap *cap; @@ -1414,6 +1408,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); ci->i_prealloc_cap_flush = NULL; } + + if (drop && + ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ceph_put_snap_context(ci->i_head_snapc); + ci->i_head_snapc = NULL; + } } spin_unlock(&ci->i_ceph_lock); while (!list_empty(&to_remove)) { @@ -1442,7 +1445,7 @@ static void remove_session_caps(struct ceph_mds_session *session) LIST_HEAD(dispose); dout("remove_session_caps on %p\n", session); - iterate_session_caps(session, remove_session_caps_cb, fsc); + ceph_iterate_session_caps(session, remove_session_caps_cb, fsc); wake_up_all(&fsc->mdsc->cap_flushing_wq); @@ -1525,8 +1528,8 @@ static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap, static void wake_up_session_caps(struct ceph_mds_session *session, int ev) { dout("wake_up_session_caps %p mds%d\n", session, session->s_mds); - iterate_session_caps(session, wake_up_session_cb, - (void *)(unsigned long)ev); + ceph_iterate_session_caps(session, wake_up_session_cb, + (void *)(unsigned long)ev); } /* @@ -1759,7 +1762,7 @@ int ceph_trim_caps(struct ceph_mds_client *mdsc, session->s_mds, session->s_nr_caps, max_caps, trim_caps); if (trim_caps > 0) { session->s_trim_caps = trim_caps; - iterate_session_caps(session, trim_caps_cb, session); + ceph_iterate_session_caps(session, trim_caps_cb, session); dout("trim_caps mds%d done: %d / %d, trimmed %d\n", session->s_mds, session->s_nr_caps, max_caps, trim_caps - session->s_trim_caps); @@ -1852,7 +1855,8 @@ again: num_cap_releases--; head = msg->front.iov_base; - le32_add_cpu(&head->num, 1); + put_unaligned_le32(get_unaligned_le32(&head->num) + 1, + &head->num); item = msg->front.iov_base + msg->front.iov_len; item->ino = cpu_to_le64(cap->cap_ino); item->cap_id = cpu_to_le64(cap->cap_id); @@ -2080,43 +2084,29 @@ static inline u64 __get_oldest_tid(struct ceph_mds_client *mdsc) * Encode hidden .snap dirs as a double /, i.e. * foo/.snap/bar -> foo//bar */ -char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base, +char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *pbase, int stop_on_nosnap) { struct dentry *temp; char *path; - int len, pos; + int pos; unsigned seq; + u64 base; if (!dentry) return ERR_PTR(-EINVAL); -retry: - len = 0; - seq = read_seqbegin(&rename_lock); - rcu_read_lock(); - for (temp = dentry; !IS_ROOT(temp);) { - struct inode *inode = d_inode(temp); - if (inode && ceph_snap(inode) == CEPH_SNAPDIR) - len++; /* slash only */ - else if (stop_on_nosnap && inode && - ceph_snap(inode) == CEPH_NOSNAP) - break; - else - len += 1 + temp->d_name.len; - temp = temp->d_parent; - } - rcu_read_unlock(); - if (len) - len--; /* no leading '/' */ - - path = kmalloc(len+1, GFP_NOFS); + path = __getname(); if (!path) return ERR_PTR(-ENOMEM); - pos = len; - path[pos] = 0; /* trailing null */ +retry: + pos = PATH_MAX - 1; + path[pos] = '\0'; + + seq = read_seqbegin(&rename_lock); rcu_read_lock(); - for (temp = dentry; !IS_ROOT(temp) && pos != 0; ) { + temp = dentry; + for (;;) { struct inode *inode; spin_lock(&temp->d_lock); @@ -2134,43 +2124,50 @@ retry: spin_unlock(&temp->d_lock); break; } - strncpy(path + pos, temp->d_name.name, - temp->d_name.len); + memcpy(path + pos, temp->d_name.name, temp->d_name.len); } spin_unlock(&temp->d_lock); - if (pos) - path[--pos] = '/'; temp = temp->d_parent; + + /* Are we at the root? */ + if (IS_ROOT(temp)) + break; + + /* Are we out of buffer? */ + if (--pos < 0) + break; + + path[pos] = '/'; } + base = ceph_ino(d_inode(temp)); rcu_read_unlock(); - if (pos != 0 || read_seqretry(&rename_lock, seq)) { + if (pos < 0 || read_seqretry(&rename_lock, seq)) { pr_err("build_path did not end path lookup where " - "expected, namelen is %d, pos is %d\n", len, pos); + "expected, pos is %d\n", pos); /* presumably this is only possible if racing with a rename of one of the parent directories (we can not lock the dentries above us to prevent this, but retrying should be harmless) */ - kfree(path); goto retry; } - *base = ceph_ino(d_inode(temp)); - *plen = len; + *pbase = base; + *plen = PATH_MAX - 1 - pos; dout("build_path on %p %d built %llx '%.*s'\n", - dentry, d_count(dentry), *base, len, path); - return path; + dentry, d_count(dentry), base, *plen, path + pos); + return path + pos; } static int build_dentry_path(struct dentry *dentry, struct inode *dir, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath, bool parent_locked) { char *path; rcu_read_lock(); if (!dir) dir = d_inode_rcu(dentry->d_parent); - if (dir && ceph_snap(dir) == CEPH_NOSNAP) { + if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP) { *pino = ceph_ino(dir); rcu_read_unlock(); *ppath = dentry->d_name.name; @@ -2182,13 +2179,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } static int build_inode_path(struct inode *inode, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath) { struct dentry *dentry; char *path; @@ -2204,7 +2201,7 @@ static int build_inode_path(struct inode *inode, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } @@ -2215,7 +2212,7 @@ static int build_inode_path(struct inode *inode, static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, struct inode *rdiri, const char *rpath, u64 rino, const char **ppath, int *pathlen, - u64 *ino, int *freepath) + u64 *ino, bool *freepath, bool parent_locked) { int r = 0; @@ -2225,7 +2222,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, ceph_snap(rinode)); } else if (rdentry) { r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino, - freepath); + freepath, parent_locked); dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath); } else if (rpath || rino) { @@ -2251,7 +2248,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, const char *path2 = NULL; u64 ino1 = 0, ino2 = 0; int pathlen1 = 0, pathlen2 = 0; - int freepath1 = 0, freepath2 = 0; + bool freepath1 = false, freepath2 = false; int len; u16 releases; void *p, *end; @@ -2259,16 +2256,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, ret = set_request_path_attr(req->r_inode, req->r_dentry, req->r_parent, req->r_path1, req->r_ino1.ino, - &path1, &pathlen1, &ino1, &freepath1); + &path1, &pathlen1, &ino1, &freepath1, + test_bit(CEPH_MDS_R_PARENT_LOCKED, + &req->r_req_flags)); if (ret < 0) { msg = ERR_PTR(ret); goto out; } + /* If r_old_dentry is set, then assume that its parent is locked */ ret = set_request_path_attr(NULL, req->r_old_dentry, req->r_old_dentry_dir, req->r_path2, req->r_ino2.ino, - &path2, &pathlen2, &ino2, &freepath2); + &path2, &pathlen2, &ino2, &freepath2, true); if (ret < 0) { msg = ERR_PTR(ret); goto out_free1; @@ -2283,9 +2283,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, (!!req->r_inode_drop + !!req->r_dentry_drop + !!req->r_old_inode_drop + !!req->r_old_dentry_drop); if (req->r_dentry_drop) - len += req->r_dentry->d_name.len; + len += pathlen1; if (req->r_old_dentry_drop) - len += req->r_old_dentry->d_name.len; + len += pathlen2; msg = ceph_msg_new2(CEPH_MSG_CLIENT_REQUEST, len, 1, GFP_NOFS, false); if (!msg) { @@ -2362,10 +2362,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, out_free2: if (freepath2) - kfree((char *)path2); + ceph_mdsc_free_path((char *)path2, pathlen2); out_free1: if (freepath1) - kfree((char *)path1); + ceph_mdsc_free_path((char *)path1, pathlen1); out: return msg; } @@ -2379,8 +2379,7 @@ static void complete_request(struct ceph_mds_client *mdsc, { if (req->r_callback) req->r_callback(mdsc, req); - else - complete_all(&req->r_completion); + complete_all(&req->r_completion); } /* @@ -2622,28 +2621,11 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds) } } -void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, +int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_mds_request *req) { - dout("submit_request on %p\n", req); - mutex_lock(&mdsc->mutex); - __register_request(mdsc, req, NULL); - __do_request(mdsc, req); - mutex_unlock(&mdsc->mutex); -} - -/* - * Synchrously perform an mds request. Take care of all of the - * session setup, forwarding, retry details. - */ -int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, - struct inode *dir, - struct ceph_mds_request *req) -{ int err; - dout("do_request on %p\n", req); - /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */ if (req->r_inode) ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN); @@ -2653,18 +2635,21 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); - /* issue */ + dout("submit_request on %p for inode %p\n", req, dir); mutex_lock(&mdsc->mutex); __register_request(mdsc, req, dir); __do_request(mdsc, req); + err = req->r_err; + mutex_unlock(&mdsc->mutex); + return err; +} - if (req->r_err) { - err = req->r_err; - goto out; - } +static int ceph_mdsc_wait_request(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req) +{ + int err; /* wait */ - mutex_unlock(&mdsc->mutex); dout("do_request waiting\n"); if (!req->r_timeout && req->r_wait_for_completion) { err = req->r_wait_for_completion(mdsc, req); @@ -2705,8 +2690,26 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, err = req->r_err; } -out: mutex_unlock(&mdsc->mutex); + return err; +} + +/* + * Synchrously perform an mds request. Take care of all of the + * session setup, forwarding, retry details. + */ +int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, + struct inode *dir, + struct ceph_mds_request *req) +{ + int err; + + dout("do_request on %p\n", req); + + /* issue */ + err = ceph_mdsc_submit_request(mdsc, dir, req); + if (!err) + err = ceph_mdsc_wait_request(mdsc, req); dout("do_request %p done, result %d\n", req, err); return err; } @@ -3437,7 +3440,7 @@ out_freeflocks: ceph_pagelist_encode_string(pagelist, path, pathlen); ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1)); out_freepath: - kfree(path); + ceph_mdsc_free_path(path, pathlen); } out_err: @@ -3594,7 +3597,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, recon_state.msg_version = 2; } /* trsaverse this session's caps */ - err = iterate_session_caps(session, encode_caps_cb, &recon_state); + err = ceph_iterate_session_caps(session, encode_caps_cb, &recon_state); spin_lock(&session->s_cap_lock); session->s_cap_reconnect = 0; @@ -4077,6 +4080,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) mdsc->max_sessions = 0; mdsc->stopping = 0; atomic64_set(&mdsc->quotarealms_count, 0); + mdsc->quotarealms_inodes = RB_ROOT; + mutex_init(&mdsc->quotarealms_inodes_mutex); mdsc->last_snap_seq = 0; init_rwsem(&mdsc->snap_rwsem); mdsc->snap_realms = RB_ROOT; @@ -4168,6 +4173,8 @@ void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) * their inode/dcache refs */ ceph_msgr_flush(); + + ceph_cleanup_quotarealms_inodes(mdsc); } /* diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 50385a481fdb..a83f28bc2387 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -326,6 +326,18 @@ struct ceph_snapid_map { }; /* + * node for list of quotarealm inodes that are not visible from the filesystem + * mountpoint, but required to handle, e.g. quotas. + */ +struct ceph_quotarealm_inode { + struct rb_node node; + u64 ino; + unsigned long timeout; /* last time a lookup failed for this inode */ + struct mutex mutex; + struct inode *inode; +}; + +/* * mds client state */ struct ceph_mds_client { @@ -344,6 +356,12 @@ struct ceph_mds_client { int stopping; /* true if shutting down */ atomic64_t quotarealms_count; /* # realms with quota */ + /* + * We keep a list of inodes we don't see in the mountpoint but that we + * need to track quota realms. + */ + struct rb_root quotarealms_inodes; + struct mutex quotarealms_inodes_mutex; /* * snap_rwsem will cover cap linkage into snaprealms, and @@ -447,8 +465,9 @@ extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, struct inode *dir); extern struct ceph_mds_request * ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode); -extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, - struct ceph_mds_request *req); +extern int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, + struct inode *dir, + struct ceph_mds_request *req); extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_mds_request *req); @@ -468,8 +487,18 @@ extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc); extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr); +extern int ceph_iterate_session_caps(struct ceph_mds_session *session, + int (*cb)(struct inode *, + struct ceph_cap *, void *), + void *arg); extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); +static inline void ceph_mdsc_free_path(char *path, int len) +{ + if (path) + __putname(path - (PATH_MAX - 1 - len)); +} + extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base, int stop_on_nosnap); diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 1a2c5d390f7f..701b4fb0fb5a 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -205,7 +205,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n", i+1, n, global_id, mds, inc, - ceph_pr_addr(&addr.in_addr), + ceph_pr_addr(&addr), ceph_mds_state_name(state)); if (mds < 0 || state <= 0) diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 9455d3aef0c3..c4522212872c 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -22,7 +22,16 @@ void ceph_adjust_quota_realms_count(struct inode *inode, bool inc) static inline bool ceph_has_realms_with_quotas(struct inode *inode) { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; - return atomic64_read(&mdsc->quotarealms_count) > 0; + struct super_block *sb = mdsc->fsc->sb; + + if (atomic64_read(&mdsc->quotarealms_count) > 0) + return true; + /* if root is the real CephFS root, we don't have quota realms */ + if (sb->s_root->d_inode && + (sb->s_root->d_inode->i_ino == CEPH_INO_ROOT)) + return false; + /* otherwise, we can't know for sure */ + return true; } void ceph_handle_quota(struct ceph_mds_client *mdsc, @@ -68,6 +77,108 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc, iput(inode); } +static struct ceph_quotarealm_inode * +find_quotarealm_inode(struct ceph_mds_client *mdsc, u64 ino) +{ + struct ceph_quotarealm_inode *qri = NULL; + struct rb_node **node, *parent = NULL; + + mutex_lock(&mdsc->quotarealms_inodes_mutex); + node = &(mdsc->quotarealms_inodes.rb_node); + while (*node) { + parent = *node; + qri = container_of(*node, struct ceph_quotarealm_inode, node); + + if (ino < qri->ino) + node = &((*node)->rb_left); + else if (ino > qri->ino) + node = &((*node)->rb_right); + else + break; + } + if (!qri || (qri->ino != ino)) { + /* Not found, create a new one and insert it */ + qri = kmalloc(sizeof(*qri), GFP_KERNEL); + if (qri) { + qri->ino = ino; + qri->inode = NULL; + qri->timeout = 0; + mutex_init(&qri->mutex); + rb_link_node(&qri->node, parent, node); + rb_insert_color(&qri->node, &mdsc->quotarealms_inodes); + } else + pr_warn("Failed to alloc quotarealms_inode\n"); + } + mutex_unlock(&mdsc->quotarealms_inodes_mutex); + + return qri; +} + +/* + * This function will try to lookup a realm inode which isn't visible in the + * filesystem mountpoint. A list of these kind of inodes (not visible) is + * maintained in the mdsc and freed only when the filesystem is umounted. + * + * Note that these inodes are kept in this list even if the lookup fails, which + * allows to prevent useless lookup requests. + */ +static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc, + struct super_block *sb, + struct ceph_snap_realm *realm) +{ + struct ceph_quotarealm_inode *qri; + struct inode *in; + + qri = find_quotarealm_inode(mdsc, realm->ino); + if (!qri) + return NULL; + + mutex_lock(&qri->mutex); + if (qri->inode) { + /* A request has already returned the inode */ + mutex_unlock(&qri->mutex); + return qri->inode; + } + /* Check if this inode lookup has failed recently */ + if (qri->timeout && + time_before_eq(jiffies, qri->timeout)) { + mutex_unlock(&qri->mutex); + return NULL; + } + in = ceph_lookup_inode(sb, realm->ino); + if (IS_ERR(in)) { + pr_warn("Can't lookup inode %llx (err: %ld)\n", + realm->ino, PTR_ERR(in)); + qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */ + } else { + qri->timeout = 0; + qri->inode = in; + } + mutex_unlock(&qri->mutex); + + return in; +} + +void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc) +{ + struct ceph_quotarealm_inode *qri; + struct rb_node *node; + + /* + * It should now be safe to clean quotarealms_inode tree without holding + * mdsc->quotarealms_inodes_mutex... + */ + mutex_lock(&mdsc->quotarealms_inodes_mutex); + while (!RB_EMPTY_ROOT(&mdsc->quotarealms_inodes)) { + node = rb_first(&mdsc->quotarealms_inodes); + qri = rb_entry(node, struct ceph_quotarealm_inode, node); + rb_erase(node, &mdsc->quotarealms_inodes); + iput(qri->inode); + kfree(qri); + } + mutex_unlock(&mdsc->quotarealms_inodes_mutex); +} + /* * This function walks through the snaprealm for an inode and returns the * ceph_snap_realm for the first snaprealm that has quotas set (either max_files @@ -76,9 +187,15 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc, * * Note that the caller is responsible for calling ceph_put_snap_realm() on the * returned realm. + * + * Callers of this function need to hold mdsc->snap_rwsem. However, if there's + * a need to do an inode lookup, this rwsem will be temporarily dropped. Hence + * the 'retry' argument: if rwsem needs to be dropped and 'retry' is 'false' + * this function will return -EAGAIN; otherwise, the snaprealms walk-through + * will be restarted. */ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, - struct inode *inode) + struct inode *inode, bool retry) { struct ceph_inode_info *ci = NULL; struct ceph_snap_realm *realm, *next; @@ -88,6 +205,7 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, if (ceph_snap(inode) != CEPH_NOSNAP) return NULL; +restart: realm = ceph_inode(inode)->i_snap_realm; if (realm) ceph_get_snap_realm(mdsc, realm); @@ -95,11 +213,25 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, pr_err_ratelimited("get_quota_realm: ino (%llx.%llx) " "null i_snap_realm\n", ceph_vinop(inode)); while (realm) { + bool has_inode; + spin_lock(&realm->inodes_with_caps_lock); - in = realm->inode ? igrab(realm->inode) : NULL; + has_inode = realm->inode; + in = has_inode ? igrab(realm->inode) : NULL; spin_unlock(&realm->inodes_with_caps_lock); - if (!in) + if (has_inode && !in) break; + if (!in) { + up_read(&mdsc->snap_rwsem); + in = lookup_quotarealm_inode(mdsc, inode->i_sb, realm); + down_read(&mdsc->snap_rwsem); + if (IS_ERR_OR_NULL(in)) + break; + ceph_put_snap_realm(mdsc, realm); + if (!retry) + return ERR_PTR(-EAGAIN); + goto restart; + } ci = ceph_inode(in); has_quota = __ceph_has_any_quota(ci); @@ -125,9 +257,22 @@ bool ceph_quota_is_same_realm(struct inode *old, struct inode *new) struct ceph_snap_realm *old_realm, *new_realm; bool is_same; +restart: + /* + * We need to lookup 2 quota realms atomically, i.e. with snap_rwsem. + * However, get_quota_realm may drop it temporarily. By setting the + * 'retry' parameter to 'false', we'll get -EAGAIN if the rwsem was + * dropped and we can then restart the whole operation. + */ down_read(&mdsc->snap_rwsem); - old_realm = get_quota_realm(mdsc, old); - new_realm = get_quota_realm(mdsc, new); + old_realm = get_quota_realm(mdsc, old, true); + new_realm = get_quota_realm(mdsc, new, false); + if (PTR_ERR(new_realm) == -EAGAIN) { + up_read(&mdsc->snap_rwsem); + if (old_realm) + ceph_put_snap_realm(mdsc, old_realm); + goto restart; + } is_same = (old_realm == new_realm); up_read(&mdsc->snap_rwsem); @@ -166,6 +311,7 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, return false; down_read(&mdsc->snap_rwsem); +restart: realm = ceph_inode(inode)->i_snap_realm; if (realm) ceph_get_snap_realm(mdsc, realm); @@ -173,12 +319,23 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, pr_err_ratelimited("check_quota_exceeded: ino (%llx.%llx) " "null i_snap_realm\n", ceph_vinop(inode)); while (realm) { + bool has_inode; + spin_lock(&realm->inodes_with_caps_lock); - in = realm->inode ? igrab(realm->inode) : NULL; + has_inode = realm->inode; + in = has_inode ? igrab(realm->inode) : NULL; spin_unlock(&realm->inodes_with_caps_lock); - if (!in) + if (has_inode && !in) break; - + if (!in) { + up_read(&mdsc->snap_rwsem); + in = lookup_quotarealm_inode(mdsc, inode->i_sb, realm); + down_read(&mdsc->snap_rwsem); + if (IS_ERR_OR_NULL(in)) + break; + ceph_put_snap_realm(mdsc, realm); + goto restart; + } ci = ceph_inode(in); spin_lock(&ci->i_ceph_lock); if (op == QUOTA_CHECK_MAX_FILES_OP) { @@ -314,7 +471,7 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf) bool is_updated = false; down_read(&mdsc->snap_rwsem); - realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root)); + realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root), true); up_read(&mdsc->snap_rwsem); if (!realm) return false; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 89aa37fa0f84..b26e12cd8ec3 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -572,7 +572,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) old_snapc = NULL; update_snapc: - if (ci->i_head_snapc) { + if (ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ci->i_head_snapc = NULL; + } else { ci->i_head_snapc = ceph_get_snap_context(new_snapc); dout(" new snapc is %p\n", new_snapc); } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 6d5bb2f74612..c864b44c8341 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -845,13 +845,21 @@ static void ceph_umount_begin(struct super_block *sb) return; } +static int ceph_remount(struct super_block *sb, int *flags, char *data) +{ + sync_filesystem(sb); + return 0; +} + static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .destroy_inode = ceph_destroy_inode, + .free_inode = ceph_free_inode, .write_inode = ceph_write_inode, .drop_inode = ceph_drop_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, + .remount_fs = ceph_remount, .show_options = ceph_show_options, .statfs = ceph_statfs, .umount_begin = ceph_umount_begin, diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 16c03188578e..6edab9a750f8 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -874,6 +874,7 @@ extern const struct inode_operations ceph_file_iops; extern struct inode *ceph_alloc_inode(struct super_block *sb); extern void ceph_destroy_inode(struct inode *inode); +extern void ceph_free_inode(struct inode *inode); extern int ceph_drop_inode(struct inode *inode); extern struct inode *ceph_get_inode(struct super_block *sb, @@ -1082,6 +1083,7 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg); /* export.c */ extern const struct export_operations ceph_export_ops; +struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino); /* locks.c */ extern __init void ceph_flock_init(void); @@ -1132,5 +1134,6 @@ extern bool ceph_quota_is_max_bytes_approaching(struct inode *inode, loff_t newlen); extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf); +extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc); #endif /* _FS_CEPH_SUPER_H */ diff --git a/fs/char_dev.c b/fs/char_dev.c index a279c58fe360..d18cad28c1c3 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -88,22 +88,31 @@ static int find_dynamic_major(void) /* * Register a single major with a specified minor range. * - * If major == 0 this functions will dynamically allocate a major and return - * its number. - * - * If major > 0 this function will attempt to reserve the passed range of - * minors and will return zero on success. + * If major == 0 this function will dynamically allocate an unused major. + * If major > 0 this function will attempt to reserve the range of minors + * with given major. * - * Returns a -ve errno on failure. */ static struct char_device_struct * __register_chrdev_region(unsigned int major, unsigned int baseminor, int minorct, const char *name) { - struct char_device_struct *cd, **cp; - int ret = 0; + struct char_device_struct *cd, *curr, *prev = NULL; + int ret = -EBUSY; int i; + if (major >= CHRDEV_MAJOR_MAX) { + pr_err("CHRDEV \"%s\" major requested (%u) is greater than the maximum (%u)\n", + name, major, CHRDEV_MAJOR_MAX-1); + return ERR_PTR(-EINVAL); + } + + if (minorct > MINORMASK + 1 - baseminor) { + pr_err("CHRDEV \"%s\" minor range requested (%u-%u) is out of range of maximum range (%u-%u) for a single major\n", + name, baseminor, baseminor + minorct - 1, 0, MINORMASK); + return ERR_PTR(-EINVAL); + } + cd = kzalloc(sizeof(struct char_device_struct), GFP_KERNEL); if (cd == NULL) return ERR_PTR(-ENOMEM); @@ -120,10 +129,20 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, major = ret; } - if (major >= CHRDEV_MAJOR_MAX) { - pr_err("CHRDEV \"%s\" major requested (%u) is greater than the maximum (%u)\n", - name, major, CHRDEV_MAJOR_MAX-1); - ret = -EINVAL; + i = major_to_index(major); + for (curr = chrdevs[i]; curr; prev = curr, curr = curr->next) { + if (curr->major < major) + continue; + + if (curr->major > major) + break; + + if (curr->baseminor + curr->minorct <= baseminor) + continue; + + if (curr->baseminor >= baseminor + minorct) + break; + goto out; } @@ -132,37 +151,14 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, cd->minorct = minorct; strlcpy(cd->name, name, sizeof(cd->name)); - i = major_to_index(major); - - for (cp = &chrdevs[i]; *cp; cp = &(*cp)->next) - if ((*cp)->major > major || - ((*cp)->major == major && - (((*cp)->baseminor >= baseminor) || - ((*cp)->baseminor + (*cp)->minorct > baseminor)))) - break; - - /* Check for overlapping minor ranges. */ - if (*cp && (*cp)->major == major) { - int old_min = (*cp)->baseminor; - int old_max = (*cp)->baseminor + (*cp)->minorct - 1; - int new_min = baseminor; - int new_max = baseminor + minorct - 1; - - /* New driver overlaps from the left. */ - if (new_max >= old_min && new_max <= old_max) { - ret = -EBUSY; - goto out; - } - - /* New driver overlaps from the right. */ - if (new_min <= old_max && new_min >= old_min) { - ret = -EBUSY; - goto out; - } + if (!prev) { + cd->next = curr; + chrdevs[i] = cd; + } else { + cd->next = prev->next; + prev->next = cd; } - cd->next = *cp; - *cp = cd; mutex_unlock(&chrdevs_lock); return cd; out: diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 13c1288b04a7..45e74da40f3a 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -312,12 +312,10 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) atomic_read(&server->smbd_conn->send_credits), atomic_read(&server->smbd_conn->receive_credits), server->smbd_conn->receive_credit_target); - seq_printf(m, "\nPending send_pending: %x send_payload_pending:" - " %x smbd_send_pending: %x smbd_recv_pending: %x", + seq_printf(m, "\nPending send_pending: %x " + "send_payload_pending: %x", atomic_read(&server->smbd_conn->send_pending), - atomic_read(&server->smbd_conn->send_payload_pending), - server->smbd_conn->smbd_send_pending, - server->smbd_conn->smbd_recv_pending); + atomic_read(&server->smbd_conn->send_payload_pending)); seq_printf(m, "\nReceive buffers count_receive_queue: %x " "count_empty_packet_queue: %x", server->smbd_conn->count_receive_queue, @@ -334,6 +332,12 @@ skip_rdma: #endif seq_printf(m, "\nNumber of credits: %d Dialect 0x%x", server->credits, server->dialect); + if (server->compress_algorithm == SMB3_COMPRESS_LZNT1) + seq_printf(m, " COMPRESS_LZNT1"); + else if (server->compress_algorithm == SMB3_COMPRESS_LZ77) + seq_printf(m, " COMPRESS_LZ77"); + else if (server->compress_algorithm == SMB3_COMPRESS_LZ77_HUFF) + seq_printf(m, " COMPRESS_LZ77_HUFF"); if (server->sign) seq_printf(m, " signed"); if (server->posix_ext_supported) @@ -376,6 +380,8 @@ skip_rdma: atomic_read(&server->in_send), atomic_read(&server->num_waiters)); #endif + /* dump session id helpful for use with network trace */ + seq_printf(m, " SessionId: 0x%llx", ses->Suid); if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) seq_puts(m, " encrypted"); if (ses->sign) @@ -462,8 +468,13 @@ static ssize_t cifs_stats_proc_write(struct file *file, server = list_entry(tmp1, struct TCP_Server_Info, tcp_ses_list); #ifdef CONFIG_CIFS_STATS2 - for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++) + for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++) { + atomic_set(&server->num_cmds[i], 0); atomic_set(&server->smb2slowcmd[i], 0); + server->time_per_cmd[i] = 0; + server->slowest_cmd[i] = 0; + server->fastest_cmd[0] = 0; + } #endif /* CONFIG_CIFS_STATS2 */ list_for_each(tmp2, &server->smb_ses_list) { ses = list_entry(tmp2, struct cifs_ses, @@ -531,9 +542,19 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) server = list_entry(tmp1, struct TCP_Server_Info, tcp_ses_list); #ifdef CONFIG_CIFS_STATS2 + seq_puts(m, "\nTotal time spent processing by command. Time "); + seq_printf(m, "units are jiffies (%d per second)\n", HZ); + seq_puts(m, " SMB3 CMD\tNumber\tTotal Time\tFastest\tSlowest\n"); + seq_puts(m, " --------\t------\t----------\t-------\t-------\n"); + for (j = 0; j < NUMBER_OF_SMB2_COMMANDS; j++) + seq_printf(m, " %d\t\t%d\t%llu\t\t%u\t%u\n", j, + atomic_read(&server->num_cmds[j]), + server->time_per_cmd[j], + server->fastest_cmd[j], + server->slowest_cmd[j]); for (j = 0; j < NUMBER_OF_SMB2_COMMANDS; j++) if (atomic_read(&server->smb2slowcmd[j])) - seq_printf(m, "%d slow responses from %s for command %d\n", + seq_printf(m, " %d slow responses from %s for command %d\n", atomic_read(&server->smb2slowcmd[j]), server->hostname, j); #endif /* STATS2 */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f9b71c12cc9f..f5fcd6360056 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -315,16 +315,10 @@ cifs_alloc_inode(struct super_block *sb) return &cifs_inode->vfs_inode; } -static void cifs_i_callback(struct rcu_head *head) -{ - struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(cifs_inode_cachep, CIFS_I(inode)); -} - static void -cifs_destroy_inode(struct inode *inode) +cifs_free_inode(struct inode *inode) { - call_rcu(&inode->i_rcu, cifs_i_callback); + kmem_cache_free(cifs_inode_cachep, CIFS_I(inode)); } static void @@ -489,6 +483,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",seal"); if (tcon->nocase) seq_puts(s, ",nocase"); + if (tcon->local_lease) + seq_puts(s, ",locallease"); if (tcon->retry) seq_puts(s, ",hard"); else @@ -559,6 +555,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) tcon->ses->server->echo_interval / HZ); if (tcon->snapshot_time) seq_printf(s, ",snapshot=%llu", tcon->snapshot_time); + if (tcon->handle_timeout) + seq_printf(s, ",handletimeout=%u", tcon->handle_timeout); /* convert actimeo and display it in seconds */ seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ); @@ -628,7 +626,7 @@ static int cifs_drop_inode(struct inode *inode) static const struct super_operations cifs_super_ops = { .statfs = cifs_statfs, .alloc_inode = cifs_alloc_inode, - .destroy_inode = cifs_destroy_inode, + .free_inode = cifs_free_inode, .drop_inode = cifs_drop_inode, .evict_inode = cifs_evict_inode, /* .delete_inode = cifs_delete_inode, */ /* Do not need above @@ -880,6 +878,9 @@ out: static loff_t cifs_llseek(struct file *file, loff_t offset, int whence) { + struct cifsFileInfo *cfile = file->private_data; + struct cifs_tcon *tcon; + /* * whence == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate * the cached file length @@ -911,6 +912,12 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence) if (rc < 0) return (loff_t)rc; } + if (cfile && cfile->tlink) { + tcon = tlink_tcon(cfile->tlink); + if (tcon->ses->server->ops->llseek) + return tcon->ses->server->ops->llseek(file, tcon, + offset, whence); + } return generic_file_llseek(file, offset, whence); } @@ -988,6 +995,7 @@ const struct inode_operations cifs_file_inode_ops = { .getattr = cifs_getattr, .permission = cifs_permission, .listxattr = cifs_listxattr, + .fiemap = cifs_fiemap, }; const struct inode_operations cifs_symlink_inode_ops = { @@ -1071,11 +1079,6 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, cifs_dbg(FYI, "copychunk range\n"); - if (src_inode == target_inode) { - rc = -EINVAL; - goto out; - } - if (!src_file->private_data || !dst_file->private_data) { rc = -EBADF; cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 5c0298b9998f..aea005703785 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -84,6 +84,8 @@ extern int cifs_revalidate_mapping(struct inode *inode); extern int cifs_zap_mapping(struct inode *inode); extern int cifs_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int cifs_setattr(struct dentry *, struct iattr *); +extern int cifs_fiemap(struct inode *, struct fiemap_extent_info *, u64 start, + u64 len); extern const struct inode_operations cifs_file_inode_ops; extern const struct inode_operations cifs_symlink_inode_ops; @@ -150,5 +152,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.19" +#define CIFS_VERSION "2.20" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 38feae812b47..334ff5f9c3f3 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -60,6 +60,12 @@ #define CIFS_MAX_ACTIMEO (1 << 30) /* + * Max persistent and resilient handle timeout (milliseconds). + * Windows durable max was 960000 (16 minutes) + */ +#define SMB3_MAX_HANDLE_TIMEOUT 960000 + +/* * MAX_REQ is the maximum number of requests that WE will send * on one socket concurrently. */ @@ -349,7 +355,8 @@ struct smb_version_operations { struct cifs_sb_info *); /* query symlink target */ int (*query_symlink)(const unsigned int, struct cifs_tcon *, - const char *, char **, struct cifs_sb_info *); + struct cifs_sb_info *, const char *, + char **, bool); /* open a file for non-posix mounts */ int (*open)(const unsigned int, struct cifs_open_parms *, __u32 *, FILE_ALL_INFO *); @@ -487,6 +494,11 @@ struct smb_version_operations { char *full_path, umode_t mode, dev_t device_number); + /* version specific fiemap implementation */ + int (*fiemap)(struct cifs_tcon *tcon, struct cifsFileInfo *, + struct fiemap_extent_info *, u64, u64); + /* version specific llseek implementation */ + loff_t (*llseek)(struct file *, struct cifs_tcon *, loff_t, int); }; struct smb_version_values { @@ -586,9 +598,14 @@ struct smb_vol { struct nls_table *local_nls; unsigned int echo_interval; /* echo interval in secs */ __u64 snapshot_time; /* needed for timewarp tokens */ + __u32 handle_timeout; /* persistent and durable handle timeout in ms */ unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */ }; +/** + * CIFS superblock mount flags (mnt_cifs_flags) to consider when + * trying to reuse existing superblock for a new mount + */ #define CIFS_MOUNT_MASK (CIFS_MOUNT_NO_PERM | CIFS_MOUNT_SET_UID | \ CIFS_MOUNT_SERVER_INUM | CIFS_MOUNT_DIRECT_IO | \ CIFS_MOUNT_NO_XATTR | CIFS_MOUNT_MAP_SPECIAL_CHR | \ @@ -599,8 +616,13 @@ struct smb_vol { CIFS_MOUNT_NOPOSIXBRL | CIFS_MOUNT_NOSSYNC | \ CIFS_MOUNT_FSCACHE | CIFS_MOUNT_MF_SYMLINKS | \ CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_STRICT_IO | \ - CIFS_MOUNT_CIFS_BACKUPUID | CIFS_MOUNT_CIFS_BACKUPGID) + CIFS_MOUNT_CIFS_BACKUPUID | CIFS_MOUNT_CIFS_BACKUPGID | \ + CIFS_MOUNT_NO_DFS) +/** + * Generic VFS superblock mount flags (s_flags) to consider when + * trying to reuse existing superblock for a new mount + */ #define CIFS_MS_MASK (SB_RDONLY | SB_MANDLOCK | SB_NOEXEC | SB_NOSUID | \ SB_NODEV | SB_SYNCHRONOUS) @@ -707,10 +729,15 @@ struct TCP_Server_Info { #ifdef CONFIG_CIFS_STATS2 atomic_t in_send; /* requests trying to send */ atomic_t num_waiters; /* blocked waiting to get in sendrecv */ + atomic_t num_cmds[NUMBER_OF_SMB2_COMMANDS]; /* total requests by cmd */ atomic_t smb2slowcmd[NUMBER_OF_SMB2_COMMANDS]; /* count resps > 1 sec */ + __u64 time_per_cmd[NUMBER_OF_SMB2_COMMANDS]; /* total time per cmd */ + __u32 slowest_cmd[NUMBER_OF_SMB2_COMMANDS]; + __u32 fastest_cmd[NUMBER_OF_SMB2_COMMANDS]; #endif /* STATS2 */ unsigned int max_read; unsigned int max_write; + __le16 compress_algorithm; __le16 cipher_type; /* save initital negprot hash */ __u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; @@ -1058,6 +1085,7 @@ struct cifs_tcon { __u32 vol_serial_number; __le64 vol_create_time; __u64 snapshot_time; /* for timewarp tokens - timestamp of snapshot */ + __u32 handle_timeout; /* persistent and durable handle timeout in ms */ __u32 ss_flags; /* sector size flags */ __u32 perf_sector_size; /* best sector size for perf */ __u32 max_chunks; @@ -1325,6 +1353,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) } struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); #define CIFS_CACHE_READ_FLG 1 @@ -1664,11 +1693,11 @@ static inline bool is_retryable_error(int error) /* Type of Request to SendReceive2 */ #define CIFS_BLOCKING_OP 1 /* operation can block */ -#define CIFS_ASYNC_OP 2 /* do not wait for response */ +#define CIFS_NON_BLOCKING 2 /* do not block waiting for credits */ #define CIFS_TIMEOUT_MASK 0x003 /* only one of above set in req */ #define CIFS_LOG_ERROR 0x010 /* log NT STATUS if non-zero */ #define CIFS_LARGE_BUF_OP 0x020 /* large request buffer */ -#define CIFS_NO_RESP 0x040 /* no response buffer required */ +#define CIFS_NO_RSP_BUF 0x040 /* no response buffer required */ /* Type of request operation */ #define CIFS_ECHO_OP 0x080 /* echo request */ @@ -1678,6 +1707,7 @@ static inline bool is_retryable_error(int error) #define CIFS_HAS_CREDITS 0x0400 /* already has credits */ #define CIFS_TRANSFORM_REQ 0x0800 /* transform request before sending */ +#define CIFS_NO_SRV_RSP 0x1000 /* there is no server response */ /* Security Flags: indicate type of session setup needed */ #define CIFSSEC_MAY_SIGN 0x00001 @@ -1847,6 +1877,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; #endif /* CONFIG_CIFS_ACL */ void cifs_oplock_break(struct work_struct *work); +void cifs_queue_oplock_break(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 4f96b3b00a7a..e23234207fc2 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -526,12 +526,21 @@ extern int E_md4hash(const unsigned char *passwd, unsigned char *p16, const struct nls_table *codepage); extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8, unsigned char *p24); + +extern int +cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, + const char *devname, bool is_smb3); extern void cifs_cleanup_volume_info_contents(struct smb_vol *volume_info); extern struct TCP_Server_Info * cifs_find_tcp_session(struct smb_vol *vol); +extern void cifs_put_smb_ses(struct cifs_ses *ses); + +extern struct cifs_ses * +cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info); + void cifs_readdata_release(struct kref *refcount); int cifs_async_readv(struct cifs_readdata *rdata); int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index f43747c062a7..1fbd92843a73 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -860,7 +860,7 @@ CIFSSMBEcho(struct TCP_Server_Info *server) iov[1].iov_base = (char *)smb + 4; rc = cifs_call_async(server, &rqst, NULL, cifs_echo_callback, NULL, - server, CIFS_ASYNC_OP | CIFS_ECHO_OP, NULL); + server, CIFS_NON_BLOCKING | CIFS_ECHO_OP, NULL); if (rc) cifs_dbg(FYI, "Echo request failed: %d\n", rc); @@ -2508,8 +2508,8 @@ int cifs_lockv(const unsigned int xid, struct cifs_tcon *tcon, iov[1].iov_len = (num_unlock + num_lock) * sizeof(LOCKING_ANDX_RANGE); cifs_stats_inc(&tcon->stats.cifs_stats.num_locks); - rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, CIFS_NO_RESP, - &rsp_iov); + rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, + CIFS_NO_RSP_BUF, &rsp_iov); cifs_small_buf_release(pSMB); if (rc) cifs_dbg(FYI, "Send error in cifs_lockv = %d\n", rc); @@ -2540,7 +2540,7 @@ CIFSSMBLock(const unsigned int xid, struct cifs_tcon *tcon, if (lockType == LOCKING_ANDX_OPLOCK_RELEASE) { /* no response expected */ - flags = CIFS_ASYNC_OP | CIFS_OBREAK_OP; + flags = CIFS_NO_SRV_RSP | CIFS_NON_BLOCKING | CIFS_OBREAK_OP; pSMB->Timeout = 0; } else if (waitFlag) { flags = CIFS_BLOCKING_OP; /* blocking operation, no timeout */ @@ -6567,93 +6567,3 @@ SetEARetry: return rc; } #endif - -#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* BB unused temporarily */ -/* - * Years ago the kernel added a "dnotify" function for Samba server, - * to allow network clients (such as Windows) to display updated - * lists of files in directory listings automatically when - * files are added by one user when another user has the - * same directory open on their desktop. The Linux cifs kernel - * client hooked into the kernel side of this interface for - * the same reason, but ironically when the VFS moved from - * "dnotify" to "inotify" it became harder to plug in Linux - * network file system clients (the most obvious use case - * for notify interfaces is when multiple users can update - * the contents of the same directory - exactly what network - * file systems can do) although the server (Samba) could - * still use it. For the short term we leave the worker - * function ifdeffed out (below) until inotify is fixed - * in the VFS to make it easier to plug in network file - * system clients. If inotify turns out to be permanently - * incompatible for network fs clients, we could instead simply - * expose this config flag by adding a future cifs (and smb2) notify ioctl. - */ -int CIFSSMBNotify(const unsigned int xid, struct cifs_tcon *tcon, - const int notify_subdirs, const __u16 netfid, - __u32 filter, struct file *pfile, int multishot, - const struct nls_table *nls_codepage) -{ - int rc = 0; - struct smb_com_transaction_change_notify_req *pSMB = NULL; - struct smb_com_ntransaction_change_notify_rsp *pSMBr = NULL; - struct dir_notify_req *dnotify_req; - int bytes_returned; - - cifs_dbg(FYI, "In CIFSSMBNotify for file handle %d\n", (int)netfid); - rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, (void **) &pSMB, - (void **) &pSMBr); - if (rc) - return rc; - - pSMB->TotalParameterCount = 0 ; - pSMB->TotalDataCount = 0; - pSMB->MaxParameterCount = cpu_to_le32(2); - pSMB->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00); - pSMB->MaxSetupCount = 4; - pSMB->Reserved = 0; - pSMB->ParameterOffset = 0; - pSMB->DataCount = 0; - pSMB->DataOffset = 0; - pSMB->SetupCount = 4; /* single byte does not need le conversion */ - pSMB->SubCommand = cpu_to_le16(NT_TRANSACT_NOTIFY_CHANGE); - pSMB->ParameterCount = pSMB->TotalParameterCount; - if (notify_subdirs) - pSMB->WatchTree = 1; /* one byte - no le conversion needed */ - pSMB->Reserved2 = 0; - pSMB->CompletionFilter = cpu_to_le32(filter); - pSMB->Fid = netfid; /* file handle always le */ - pSMB->ByteCount = 0; - - rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *)pSMBr, &bytes_returned, - CIFS_ASYNC_OP); - if (rc) { - cifs_dbg(FYI, "Error in Notify = %d\n", rc); - } else { - /* Add file to outstanding requests */ - /* BB change to kmem cache alloc */ - dnotify_req = kmalloc( - sizeof(struct dir_notify_req), - GFP_KERNEL); - if (dnotify_req) { - dnotify_req->Pid = pSMB->hdr.Pid; - dnotify_req->PidHigh = pSMB->hdr.PidHigh; - dnotify_req->Mid = pSMB->hdr.Mid; - dnotify_req->Tid = pSMB->hdr.Tid; - dnotify_req->Uid = pSMB->hdr.Uid; - dnotify_req->netfid = netfid; - dnotify_req->pfile = pfile; - dnotify_req->filter = filter; - dnotify_req->multishot = multishot; - spin_lock(&GlobalMid_Lock); - list_add_tail(&dnotify_req->lhead, - &GlobalDnotifyReqList); - spin_unlock(&GlobalMid_Lock); - } else - rc = -ENOMEM; - } - cifs_buf_release(pSMB); - return rc; -} -#endif /* was needed for dnotify, and will be needed for inotify when VFS fix */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a8e9738db691..8c4121da624e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -103,7 +103,7 @@ enum { Opt_cruid, Opt_gid, Opt_file_mode, Opt_dirmode, Opt_port, Opt_blocksize, Opt_rsize, Opt_wsize, Opt_actimeo, - Opt_echo_interval, Opt_max_credits, + Opt_echo_interval, Opt_max_credits, Opt_handletimeout, Opt_snapshot, /* Mount options which take string value */ @@ -208,6 +208,7 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_rsize, "rsize=%s" }, { Opt_wsize, "wsize=%s" }, { Opt_actimeo, "actimeo=%s" }, + { Opt_handletimeout, "handletimeout=%s" }, { Opt_echo_interval, "echo_interval=%s" }, { Opt_max_credits, "max_credits=%s" }, { Opt_snapshot, "snapshot=%s" }, @@ -322,8 +323,6 @@ static int ip_connect(struct TCP_Server_Info *server); static int generic_ip_connect(struct TCP_Server_Info *server); static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink); static void cifs_prune_tlinks(struct work_struct *work); -static int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, - const char *devname, bool is_smb3); static char *extract_hostname(const char *unc); /* @@ -565,6 +564,12 @@ cifs_reconnect(struct TCP_Server_Info *server) mid_entry->callback(mid_entry); } + if (cifs_rdma_enabled(server)) { + mutex_lock(&server->srv_mutex); + smbd_destroy(server); + mutex_unlock(&server->srv_mutex); + } + do { try_to_freeze(); @@ -930,10 +935,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) wake_up_all(&server->request_q); /* give those requests time to exit */ msleep(125); - if (cifs_rdma_enabled(server) && server->smbd_conn) { - smbd_destroy(server->smbd_conn); - server->smbd_conn = NULL; - } + if (cifs_rdma_enabled(server)) + smbd_destroy(server); if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; @@ -1619,6 +1622,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->actimeo = CIFS_DEF_ACTIMEO; + /* Most clients set timeout to 0, allows server to use its default */ + vol->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */ + /* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */ vol->ops = &smb30_operations; vol->vals = &smbdefault_values; @@ -2017,6 +2023,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, goto cifs_parse_mount_err; } break; + case Opt_handletimeout: + if (get_option_ul(args, &option)) { + cifs_dbg(VFS, "%s: Invalid handletimeout value\n", + __func__); + goto cifs_parse_mount_err; + } + vol->handle_timeout = option; + if (vol->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) { + cifs_dbg(VFS, "Invalid handle cache timeout, longer than 16 minutes\n"); + goto cifs_parse_mount_err; + } + break; case Opt_echo_interval: if (get_option_ul(args, &option)) { cifs_dbg(VFS, "%s: Invalid echo interval value\n", @@ -2428,6 +2446,10 @@ match_port(struct TCP_Server_Info *server, struct sockaddr *addr) { __be16 port, *sport; + /* SMBDirect manages its own ports, don't match it here */ + if (server->rdma) + return true; + switch (addr->sa_family) { case AF_INET: sport = &((struct sockaddr_in *) &server->dstaddr)->sin_port; @@ -2888,8 +2910,7 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb_vol *vol) return NULL; } -static void -cifs_put_smb_ses(struct cifs_ses *ses) +void cifs_put_smb_ses(struct cifs_ses *ses) { unsigned int rc, xid; struct TCP_Server_Info *server = ses->server; @@ -3066,7 +3087,7 @@ cifs_set_cifscreds(struct smb_vol *vol __attribute__((unused)), * already got a server reference (server refcount +1). See * cifs_get_tcon() for refcount explanations. */ -static struct cifs_ses * +struct cifs_ses * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) { int rc = -ENOMEM; @@ -3183,6 +3204,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb_vol *volume_info) return 0; if (tcon->snapshot_time != volume_info->snapshot_time) return 0; + if (tcon->handle_timeout != volume_info->handle_timeout) + return 0; return 1; } @@ -3297,6 +3320,16 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) tcon->snapshot_time = volume_info->snapshot_time; } + if (volume_info->handle_timeout) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "Use SMB2.1 or later for handle timeout option\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } else + tcon->handle_timeout = volume_info->handle_timeout; + } + tcon->ses = ses; if (volume_info->password) { tcon->password = kstrdup(volume_info->password, GFP_KERNEL); @@ -4361,7 +4394,7 @@ static int mount_do_dfs_failover(const char *path, } #endif -static int +int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, const char *devname, bool is_smb3) { @@ -4515,7 +4548,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) struct cifs_tcon *tcon = NULL; struct TCP_Server_Info *server; char *root_path = NULL, *full_path = NULL; - char *old_mountdata; + char *old_mountdata, *origin_mountdata = NULL; int count; rc = mount_get_conns(vol, cifs_sb, &xid, &server, &ses, &tcon); @@ -4574,6 +4607,14 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) goto error; } + /* Save DFS root volume information for DFS refresh worker */ + origin_mountdata = kstrndup(cifs_sb->mountdata, + strlen(cifs_sb->mountdata), GFP_KERNEL); + if (!origin_mountdata) { + rc = -ENOMEM; + goto error; + } + if (cifs_sb->mountdata != old_mountdata) { /* If we were redirected, reconnect to new target server */ mount_put_conns(cifs_sb, xid, server, ses, tcon); @@ -4682,7 +4723,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) } spin_unlock(&cifs_tcp_ses_lock); - rc = dfs_cache_add_vol(vol, cifs_sb->origin_fullpath); + rc = dfs_cache_add_vol(origin_mountdata, vol, cifs_sb->origin_fullpath); if (rc) { kfree(cifs_sb->origin_fullpath); goto error; @@ -4700,6 +4741,7 @@ out: error: kfree(full_path); kfree(root_path); + kfree(origin_mountdata); mount_put_conns(cifs_sb, xid, server, ses, tcon); return rc; } diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 09b7d0d4f6e4..85dc89d3a203 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -2,7 +2,7 @@ /* * DFS referral cache routines * - * Copyright (c) 2018 Paulo Alcantara <palcantara@suse.de> + * Copyright (c) 2018-2019 Paulo Alcantara <palcantara@suse.de> */ #include <linux/rcupdate.h> @@ -52,6 +52,7 @@ static struct kmem_cache *dfs_cache_slab __read_mostly; struct dfs_cache_vol_info { char *vi_fullpath; struct smb_vol vi_vol; + char *vi_mntdata; struct list_head vi_list; }; @@ -529,6 +530,7 @@ static inline void free_vol(struct dfs_cache_vol_info *vi) { list_del(&vi->vi_list); kfree(vi->vi_fullpath); + kfree(vi->vi_mntdata); cifs_cleanup_volume_info_contents(&vi->vi_vol); kfree(vi); } @@ -1139,17 +1141,18 @@ err_free_username: * dfs_cache_add_vol - add a cifs volume during mount() that will be handled by * DFS cache refresh worker. * + * @mntdata: mount data. * @vol: cifs volume. * @fullpath: origin full path. * * Return zero if volume was set up correctly, otherwise non-zero. */ -int dfs_cache_add_vol(struct smb_vol *vol, const char *fullpath) +int dfs_cache_add_vol(char *mntdata, struct smb_vol *vol, const char *fullpath) { int rc; struct dfs_cache_vol_info *vi; - if (!vol || !fullpath) + if (!vol || !fullpath || !mntdata) return -EINVAL; cifs_dbg(FYI, "%s: fullpath: %s\n", __func__, fullpath); @@ -1168,6 +1171,8 @@ int dfs_cache_add_vol(struct smb_vol *vol, const char *fullpath) if (rc) goto err_free_fullpath; + vi->vi_mntdata = mntdata; + mutex_lock(&dfs_cache.dc_lock); list_add_tail(&vi->vi_list, &dfs_cache.dc_vol_list); mutex_unlock(&dfs_cache.dc_lock); @@ -1275,8 +1280,102 @@ static void get_tcons(struct TCP_Server_Info *server, struct list_head *head) spin_unlock(&cifs_tcp_ses_lock); } +static inline bool is_dfs_link(const char *path) +{ + char *s; + + s = strchr(path + 1, '\\'); + if (!s) + return false; + return !!strchr(s + 1, '\\'); +} + +static inline char *get_dfs_root(const char *path) +{ + char *s, *npath; + + s = strchr(path + 1, '\\'); + if (!s) + return ERR_PTR(-EINVAL); + + s = strchr(s + 1, '\\'); + if (!s) + return ERR_PTR(-EINVAL); + + npath = kstrndup(path, s - path, GFP_KERNEL); + if (!npath) + return ERR_PTR(-ENOMEM); + + return npath; +} + +/* Find root SMB session out of a DFS link path */ +static struct cifs_ses *find_root_ses(struct dfs_cache_vol_info *vi, + struct cifs_tcon *tcon, const char *path) +{ + char *rpath; + int rc; + struct dfs_info3_param ref = {0}; + char *mdata = NULL, *devname = NULL; + bool is_smb3 = tcon->ses->server->vals->header_preamble_size == 0; + struct TCP_Server_Info *server; + struct cifs_ses *ses; + struct smb_vol vol; + + rpath = get_dfs_root(path); + if (IS_ERR(rpath)) + return ERR_CAST(rpath); + + memset(&vol, 0, sizeof(vol)); + + rc = dfs_cache_noreq_find(rpath, &ref, NULL); + if (rc) { + ses = ERR_PTR(rc); + goto out; + } + + mdata = cifs_compose_mount_options(vi->vi_mntdata, rpath, &ref, + &devname); + free_dfs_info_param(&ref); + + if (IS_ERR(mdata)) { + ses = ERR_CAST(mdata); + mdata = NULL; + goto out; + } + + rc = cifs_setup_volume_info(&vol, mdata, devname, is_smb3); + kfree(devname); + + if (rc) { + ses = ERR_PTR(rc); + goto out; + } + + server = cifs_find_tcp_session(&vol); + if (IS_ERR_OR_NULL(server)) { + ses = ERR_PTR(-EHOSTDOWN); + goto out; + } + if (server->tcpStatus != CifsGood) { + cifs_put_tcp_session(server, 0); + ses = ERR_PTR(-EHOSTDOWN); + goto out; + } + + ses = cifs_get_smb_ses(server, &vol); + +out: + cifs_cleanup_volume_info_contents(&vol); + kfree(mdata); + kfree(rpath); + + return ses; +} + /* Refresh DFS cache entry from a given tcon */ -static void do_refresh_tcon(struct dfs_cache *dc, struct cifs_tcon *tcon) +static void do_refresh_tcon(struct dfs_cache *dc, struct dfs_cache_vol_info *vi, + struct cifs_tcon *tcon) { int rc = 0; unsigned int xid; @@ -1285,6 +1384,7 @@ static void do_refresh_tcon(struct dfs_cache *dc, struct cifs_tcon *tcon) struct dfs_cache_entry *ce; struct dfs_info3_param *refs = NULL; int numrefs = 0; + struct cifs_ses *root_ses = NULL, *ses; xid = get_xid(); @@ -1306,13 +1406,24 @@ static void do_refresh_tcon(struct dfs_cache *dc, struct cifs_tcon *tcon) if (!cache_entry_expired(ce)) goto out; - if (unlikely(!tcon->ses->server->ops->get_dfs_refer)) { + /* If it's a DFS Link, then use root SMB session for refreshing it */ + if (is_dfs_link(npath)) { + ses = root_ses = find_root_ses(vi, tcon, npath); + if (IS_ERR(ses)) { + rc = PTR_ERR(ses); + root_ses = NULL; + goto out; + } + } else { + ses = tcon->ses; + } + + if (unlikely(!ses->server->ops->get_dfs_refer)) { rc = -EOPNOTSUPP; } else { - rc = tcon->ses->server->ops->get_dfs_refer(xid, tcon->ses, path, - &refs, &numrefs, - dc->dc_nlsc, - tcon->remap); + rc = ses->server->ops->get_dfs_refer(xid, ses, path, &refs, + &numrefs, dc->dc_nlsc, + tcon->remap); if (!rc) { mutex_lock(&dfs_cache_list_lock); ce = __update_cache_entry(npath, refs, numrefs); @@ -1323,9 +1434,11 @@ static void do_refresh_tcon(struct dfs_cache *dc, struct cifs_tcon *tcon) rc = PTR_ERR(ce); } } - if (rc) - cifs_dbg(FYI, "%s: failed to update expired entry\n", __func__); + out: + if (root_ses) + cifs_put_smb_ses(root_ses); + free_xid(xid); free_normalized_path(path, npath); } @@ -1333,9 +1446,6 @@ out: /* * Worker that will refresh DFS cache based on lowest TTL value from a DFS * referral. - * - * FIXME: ensure that all requests are sent to DFS root for refreshing the - * cache. */ static void refresh_cache_worker(struct work_struct *work) { @@ -1356,7 +1466,7 @@ static void refresh_cache_worker(struct work_struct *work) goto next; get_tcons(server, &list); list_for_each_entry_safe(tcon, ntcon, &list, ulist) { - do_refresh_tcon(dc, tcon); + do_refresh_tcon(dc, vi, tcon); list_del_init(&tcon->ulist); cifs_put_tcon(tcon); } diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h index 22f366514f3a..76c732943f5f 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -2,7 +2,7 @@ /* * DFS referral cache routines * - * Copyright (c) 2018 Paulo Alcantara <palcantara@suse.de> + * Copyright (c) 2018-2019 Paulo Alcantara <palcantara@suse.de> */ #ifndef _CIFS_DFS_CACHE_H @@ -43,7 +43,8 @@ dfs_cache_noreq_update_tgthint(const char *path, extern int dfs_cache_get_tgt_referral(const char *path, const struct dfs_cache_tgt_iterator *it, struct dfs_info3_param *ref); -extern int dfs_cache_add_vol(struct smb_vol *vol, const char *fullpath); +extern int dfs_cache_add_vol(char *mntdata, struct smb_vol *vol, + const char *fullpath); extern int dfs_cache_update_vol(const char *fullpath, struct TCP_Server_Info *server); extern void dfs_cache_del_vol(const char *fullpath); diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 7ede7306599f..1e21b2528cfb 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -77,7 +77,7 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) goto name_is_IP_address; /* Perform the upcall */ - rc = dns_query(NULL, hostname, len, NULL, ip_addr, NULL); + rc = dns_query(NULL, hostname, len, NULL, ip_addr, NULL, false); if (rc < 0) cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n", __func__, len, len, hostname); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 89006e044973..ce9a5be11df5 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -360,13 +360,31 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; } -/* - * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. Must be called without holding - * tcon->open_file_lock and cifs_file->file_info_lock. +/** + * cifsFileInfo_put - release a reference of file priv data + * + * Always potentially wait for oplock handler. See _cifsFileInfo_put(). */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { + _cifsFileInfo_put(cifs_file, true); +} + +/** + * _cifsFileInfo_put - release a reference of file priv data + * + * This may involve closing the filehandle @cifs_file out on the + * server. Must be called without holding tcon->open_file_lock and + * cifs_file->file_info_lock. + * + * If @wait_for_oplock_handler is true and we are releasing the last + * reference, wait for any running oplock break handler of the file + * and cancel any pending one. If calling this function from the + * oplock break handler, you need to pass false. + * + */ +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) +{ struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); struct TCP_Server_Info *server = tcon->ses->server; @@ -414,7 +432,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) spin_unlock(&tcon->open_file_lock); - oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = wait_oplock_handler ? + cancel_work_sync(&cifs_file->oplock_break) : false; if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -2424,7 +2443,6 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, rc = file_write_and_wait_range(file, start, end); if (rc) return rc; - inode_lock(inode); xid = get_xid(); @@ -2449,7 +2467,6 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, } free_xid(xid); - inode_unlock(inode); return rc; } @@ -2461,12 +2478,10 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct TCP_Server_Info *server; struct cifsFileInfo *smbfile = file->private_data; struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); - struct inode *inode = file->f_mapping->host; rc = file_write_and_wait_range(file, start, end); if (rc) return rc; - inode_lock(inode); xid = get_xid(); @@ -2483,7 +2498,6 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) } free_xid(xid); - inode_unlock(inode); return rc; } @@ -2858,7 +2872,6 @@ static void collect_uncached_write_data(struct cifs_aio_ctx *ctx) struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb; struct dentry *dentry = ctx->cfile->dentry; - unsigned int i; int rc; tcon = tlink_tcon(ctx->cfile->tlink); @@ -2922,10 +2935,6 @@ restart_loop: kref_put(&wdata->refcount, cifs_uncached_writedata_release); } - if (!ctx->direct_io) - for (i = 0; i < ctx->npages; i++) - put_page(ctx->bv[i].bv_page); - cifs_stats_bytes_written(tcon, ctx->total_len); set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags); @@ -3563,7 +3572,6 @@ collect_uncached_read_data(struct cifs_aio_ctx *ctx) struct iov_iter *to = &ctx->iter; struct cifs_sb_info *cifs_sb; struct cifs_tcon *tcon; - unsigned int i; int rc; tcon = tlink_tcon(ctx->cfile->tlink); @@ -3647,15 +3655,8 @@ again: kref_put(&rdata->refcount, cifs_uncached_readdata_release); } - if (!ctx->direct_io) { - for (i = 0; i < ctx->npages; i++) { - if (ctx->should_dirty) - set_page_dirty(ctx->bv[i].bv_page); - put_page(ctx->bv[i].bv_page); - } - + if (!ctx->direct_io) ctx->total_len = ctx->len - iov_iter_count(to); - } /* mask nodata case */ if (rc == -ENODATA) @@ -4603,6 +4604,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + _cifsFileInfo_put(cfile, false /* do not wait for ourself */); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 53fdb5df0d2e..d7cc62252634 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1735,6 +1735,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (rc == 0 || rc != -EBUSY) goto do_rename_exit; + /* Don't fall back to using SMB on SMB 2+ mount */ + if (server->vals->protocol_id != 0) + goto do_rename_exit; + /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; @@ -2112,6 +2116,43 @@ int cifs_getattr(const struct path *path, struct kstat *stat, return rc; } +int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start, + u64 len) +{ + struct cifsInodeInfo *cifs_i = CIFS_I(inode); + struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_i->vfs_inode.i_sb); + struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + struct TCP_Server_Info *server = tcon->ses->server; + struct cifsFileInfo *cfile; + int rc; + + /* + * We need to be sure that all dirty pages are written as they + * might fill holes on the server. + */ + if (!CIFS_CACHE_READ(CIFS_I(inode)) && inode->i_mapping && + inode->i_mapping->nrpages != 0) { + rc = filemap_fdatawait(inode->i_mapping); + if (rc) { + mapping_set_error(inode->i_mapping, rc); + return rc; + } + } + + cfile = find_readable_file(cifs_i, false); + if (cfile == NULL) + return -EINVAL; + + if (server->ops->fiemap) { + rc = server->ops->fiemap(tcon, cfile, fei, start, len); + cifsFileInfo_put(cfile); + return rc; + } + + cifsFileInfo_put(cfile); + return -ENOTSUPP; +} + static int cifs_truncate_page(struct address_space *mapping, loff_t from) { pgoff_t index = from >> PAGE_SHIFT; diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 62216dc8f9f5..b736acd3917b 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -648,9 +648,16 @@ cifs_get_link(struct dentry *direntry, struct inode *inode, rc = query_mf_symlink(xid, tcon, cifs_sb, full_path, &target_path); - if (rc != 0 && server->ops->query_symlink) - rc = server->ops->query_symlink(xid, tcon, full_path, - &target_path, cifs_sb); + if (rc != 0 && server->ops->query_symlink) { + struct cifsInodeInfo *cifsi = CIFS_I(inode); + bool reparse_point = false; + + if (cifsi->cifsAttrs & ATTR_REPARSE) + reparse_point = true; + + rc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, + &target_path, reparse_point); + } kfree(full_path); free_xid(xid); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index bee203055b30..b1a696a73f7c 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -501,8 +501,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &pCifsInode->flags); - queue_work(cifsoplockd_wq, - &netfile->oplock_break); + cifs_queue_oplock_break(netfile); netfile->oplock_break_cancelled = false; spin_unlock(&tcon->open_file_lock); @@ -607,6 +606,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) spin_unlock(&cinode->writers_lock); } +/** + * cifs_queue_oplock_break - queue the oplock break handler for cfile + * + * This function is called from the demultiplex thread when it + * receives an oplock break for @cfile. + * + * Assumes the tcon->open_file_lock is held. + * Assumes cfile->file_info_lock is NOT held. + */ +void cifs_queue_oplock_break(struct cifsFileInfo *cfile) +{ + /* + * Bump the handle refcount now while we hold the + * open_file_lock to enforce the validity of it for the oplock + * break handler. The matching put is done at the end of the + * handler. + */ + cifsFileInfo_get(cfile); + + queue_work(cifsoplockd_wq, &cfile->oplock_break); +} + void cifs_done_oplock_break(struct cifsInodeInfo *cinode) { clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); @@ -768,6 +789,11 @@ cifs_aio_ctx_alloc(void) { struct cifs_aio_ctx *ctx; + /* + * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io + * to false so that we know when we have to unreference pages within + * cifs_aio_ctx_release() + */ ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL); if (!ctx) return NULL; @@ -786,7 +812,23 @@ cifs_aio_ctx_release(struct kref *refcount) struct cifs_aio_ctx, refcount); cifsFileInfo_put(ctx->cfile); - kvfree(ctx->bv); + + /* + * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly + * which means that iov_iter_get_pages() was a success and thus that + * we have taken reference on pages. + */ + if (ctx->bv) { + unsigned i; + + for (i = 0; i < ctx->npages; i++) { + if (ctx->should_dirty) + set_page_dirty(ctx->bv[i].bv_page); + put_page(ctx->bv[i].bv_page); + } + kvfree(ctx->bv); + } + kfree(ctx); } @@ -917,7 +959,6 @@ cifs_alloc_hash(const char *name, } (*sdesc)->shash.tfm = *shash; - (*sdesc)->shash.flags = 0x0; return 0; } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index c711f1f39bf2..c4e75afa3258 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -950,8 +950,8 @@ cifs_unix_dfs_readlink(const unsigned int xid, struct cifs_tcon *tcon, static int cifs_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, - const char *full_path, char **target_path, - struct cifs_sb_info *cifs_sb) + struct cifs_sb_info *cifs_sb, const char *full_path, + char **target_path, bool is_reparse_point) { int rc; int oplock = 0; @@ -960,6 +960,11 @@ cifs_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); + if (is_reparse_point) { + cifs_dbg(VFS, "reparse points not handled for SMB1 symlinks\n"); + return -EOPNOTSUPP; + } + /* Check for unix extensions */ if (cap_unix(tcon->ses)) { rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path, diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index b204e84b87fb..54bffb2a1786 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -68,13 +68,15 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, if (oparms->tcon->use_resilient) { - nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */ + /* default timeout is 0, servers pick default (120 seconds) */ + nr_ioctl_req.Timeout = + cpu_to_le32(oparms->tcon->handle_timeout); nr_ioctl_req.Reserved = 0; rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, true /* is_fsctl */, (char *)&nr_ioctl_req, sizeof(nr_ioctl_req), - NULL, NULL /* no return info */); + CIFSMaxBufSize, NULL, NULL /* no return info */); if (rc == -EOPNOTSUPP) { cifs_dbg(VFS, "resiliency not supported by server, disabling\n"); diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 0e3570e40ff8..e311f58dc1c8 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -555,7 +555,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); - queue_work(cifsoplockd_wq, &cfile->oplock_break); + cifs_queue_oplock_break(cfile); kfree(lw); return true; } @@ -712,8 +712,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); spin_unlock(&cfile->file_info_lock); - queue_work(cifsoplockd_wq, - &cfile->oplock_break); + + cifs_queue_oplock_break(cfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 1022a3771e14..e921e6511728 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * SMB2 version specific operations * @@ -282,7 +283,7 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) __u64 wire_mid = le64_to_cpu(shdr->MessageId); if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) { - cifs_dbg(VFS, "encrypted frame parsing not supported yet"); + cifs_dbg(VFS, "Encrypted frame parsing not supported yet\n"); return NULL; } @@ -324,6 +325,7 @@ static int smb2_negotiate(const unsigned int xid, struct cifs_ses *ses) { int rc; + ses->server->CurrentMid = 0; rc = SMB2_negotiate(xid, ses); /* BB we probably don't need to retry with modern servers */ @@ -581,7 +583,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */, NULL /* no data input */, 0 /* no data input */, - (char **)&out_buf, &ret_data_len); + CIFSMaxBufSize, (char **)&out_buf, &ret_data_len); if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "server does not support query network interfaces\n"); @@ -717,32 +719,28 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId); #endif /* CIFS_DEBUG2 */ - if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) - oplock = smb2_parse_lease_state(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key); - else - goto oshr_exit; - - memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid)); tcon->crfid.tcon = tcon; tcon->crfid.is_valid = true; kref_init(&tcon->crfid.refcount); - kref_get(&tcon->crfid.refcount); + if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { + kref_get(&tcon->crfid.refcount); + oplock = smb2_parse_lease_state(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key); + } else + goto oshr_exit; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) goto oshr_exit; - rc = smb2_validate_and_copy_iov( + if (!smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), sizeof(struct smb2_file_all_info), &rsp_iov[1], sizeof(struct smb2_file_all_info), - (char *)&tcon->crfid.file_all_info); - if (rc) - goto oshr_exit; - tcon->crfid.file_all_info_is_valid = 1; + (char *)&tcon->crfid.file_all_info)) + tcon->crfid.file_all_info_is_valid = 1; oshr_exit: mutex_unlock(&tcon->crfid.fid_mutex); @@ -793,8 +791,6 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); else close_shroot(&tcon->crfid); - - return; } static void @@ -822,7 +818,6 @@ smb2_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid, FS_DEVICE_INFORMATION); SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); - return; } static int @@ -910,9 +905,8 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, value = &src->ea_data[src->ea_name_length + 1]; value_len = (size_t)le16_to_cpu(src->ea_value_length); - if (name_len == 0) { + if (name_len == 0) break; - } if (src_size < 8 + name_len + 1 + value_len) { cifs_dbg(FYI, "EA entry goes beyond length of list\n"); @@ -1165,6 +1159,7 @@ static void smb2_clear_stats(struct cifs_tcon *tcon) { int i; + for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++) { atomic_set(&tcon->stats.smb2_stats.smb2_com_sent[i], 0); atomic_set(&tcon->stats.smb2_stats.smb2_com_failed[i], 0); @@ -1299,7 +1294,7 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */, - NULL, 0 /* no input */, + NULL, 0 /* no input */, CIFSMaxBufSize, (char **)&res_key, &ret_data_len); if (rc) { @@ -1386,6 +1381,26 @@ smb2_ioctl_query_info(const unsigned int xid, oparms.fid = &fid; oparms.reconnect = false; + /* + * FSCTL codes encode the special access they need in the fsctl code. + */ + if (qi.flags & PASSTHRU_FSCTL) { + switch (qi.info_type & FSCTL_DEVICE_ACCESS_MASK) { + case FSCTL_DEVICE_ACCESS_FILE_READ_WRITE_ACCESS: + oparms.desired_access = FILE_READ_DATA | FILE_WRITE_DATA | FILE_READ_ATTRIBUTES | SYNCHRONIZE; + break; + case FSCTL_DEVICE_ACCESS_FILE_ANY_ACCESS: + oparms.desired_access = GENERIC_ALL; + break; + case FSCTL_DEVICE_ACCESS_FILE_READ_ACCESS: + oparms.desired_access = GENERIC_READ; + break; + case FSCTL_DEVICE_ACCESS_FILE_WRITE_ACCESS: + oparms.desired_access = GENERIC_WRITE; + break; + } + } + rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, path); if (rc) goto iqinf_exit; @@ -1403,8 +1418,9 @@ smb2_ioctl_query_info(const unsigned int xid, rc = SMB2_ioctl_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID, - qi.info_type, true, NULL, - 0); + qi.info_type, true, buffer, + qi.output_buffer_length, + CIFSMaxBufSize); } } else if (qi.flags == PASSTHRU_QUERY_INFO) { memset(&qi_iov, 0, sizeof(qi_iov)); @@ -1445,12 +1461,19 @@ smb2_ioctl_query_info(const unsigned int xid, io_rsp = (struct smb2_ioctl_rsp *)rsp_iov[1].iov_base; 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; } - if (copy_to_user(pqi + 1, &io_rsp[1], qi.input_buffer_length)) { + 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; } @@ -1505,7 +1528,7 @@ smb2_copychunk_range(const unsigned int xid, if (pcchunk == NULL) return -ENOMEM; - cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n"); + cifs_dbg(FYI, "%s: about to call request res key\n", __func__); /* Request a key from the server to identify the source of the copy */ rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink), srcfile->fid.persistent_fid, @@ -1532,8 +1555,8 @@ smb2_copychunk_range(const unsigned int xid, rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, true /* is_fsctl */, (char *)pcchunk, - sizeof(struct copychunk_ioctl), (char **)&retbuf, - &ret_data_len); + sizeof(struct copychunk_ioctl), CIFSMaxBufSize, + (char **)&retbuf, &ret_data_len); if (rc == 0) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) { @@ -1625,6 +1648,7 @@ static unsigned int smb2_read_data_offset(char *buf) { struct smb2_read_rsp *rsp = (struct smb2_read_rsp *)buf; + return rsp->DataOffset; } @@ -1693,7 +1717,7 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_SPARSE, true /* is_fctl */, - &setsparse, 1, NULL, NULL); + &setsparse, 1, CIFSMaxBufSize, NULL, NULL); if (rc) { tcon->broken_sparse_sup = true; cifs_dbg(FYI, "set sparse rc = %d\n", rc); @@ -1753,7 +1777,7 @@ smb2_duplicate_extents(const unsigned int xid, dup_ext_buf.SourceFileOffset = cpu_to_le64(src_off); dup_ext_buf.TargetFileOffset = cpu_to_le64(dest_off); dup_ext_buf.ByteCount = cpu_to_le64(len); - cifs_dbg(FYI, "duplicate extents: src off %lld dst off %lld len %lld", + cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n", src_off, dest_off, len); rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); @@ -1766,11 +1790,11 @@ smb2_duplicate_extents(const unsigned int xid, true /* is_fsctl */, (char *)&dup_ext_buf, sizeof(struct duplicate_extents_to_file), - NULL, + CIFSMaxBufSize, NULL, &ret_data_len); if (ret_data_len > 0) - cifs_dbg(FYI, "non-zero response length in duplicate extents"); + cifs_dbg(FYI, "Non-zero response length in duplicate extents\n"); duplicate_extents_out: return rc; @@ -1801,7 +1825,7 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, true /* is_fsctl */, (char *)&integr_info, sizeof(struct fsctl_set_integrity_information_req), - NULL, + CIFSMaxBufSize, NULL, &ret_data_len); } @@ -1809,6 +1833,8 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, /* GMT Token is @GMT-YYYY.MM.DD-HH.MM.SS Unicode which is 48 bytes + null */ #define GMT_TOKEN_SIZE 50 +#define MIN_SNAPSHOT_ARRAY_SIZE 16 /* See MS-SMB2 section 3.3.5.15.1 */ + /* * Input buffer contains (empty) struct smb_snapshot array with size filled in * For output see struct SRV_SNAPSHOT_ARRAY in MS-SMB2 section 2.2.32.2 @@ -1820,13 +1846,37 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, char *retbuf = NULL; unsigned int ret_data_len = 0; int rc; + u32 max_response_size; struct smb_snapshot_array snapshot_in; + /* + * On the first query to enumerate the list of snapshots available + * for this volume the buffer begins with 0 (number of snapshots + * which can be returned is zero since at that point we do not know + * how big the buffer needs to be). On the second query, + * it (ret_data_len) is set to number of snapshots so we can + * know to set the maximum response size larger (see below). + */ + if (get_user(ret_data_len, (unsigned int __user *)ioc_buf)) + return -EFAULT; + + /* + * Note that for snapshot queries that servers like Azure expect that + * the first query be minimal size (and just used to get the number/size + * of previous versions) so response size must be specified as EXACTLY + * sizeof(struct snapshot_array) which is 16 when rounded up to multiple + * of eight bytes. + */ + if (ret_data_len == 0) + max_response_size = MIN_SNAPSHOT_ARRAY_SIZE; + else + max_response_size = CIFSMaxBufSize; + rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SRV_ENUMERATE_SNAPSHOTS, true /* is_fsctl */, - NULL, 0 /* no input data */, + NULL, 0 /* no input data */, max_response_size, (char **)&retbuf, &ret_data_len); cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n", @@ -1933,9 +1983,9 @@ smb2_close_dir(const unsigned int xid, struct cifs_tcon *tcon, } /* -* If we negotiate SMB2 protocol and get STATUS_PENDING - update -* the number of credits and return true. Otherwise - return false. -*/ + * If we negotiate SMB2 protocol and get STATUS_PENDING - update + * the number of credits and return true. Otherwise - return false. + */ static bool smb2_is_status_pending(char *buf, struct TCP_Server_Info *server) { @@ -2256,7 +2306,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, struct get_dfs_referral_rsp *dfs_rsp = NULL; u32 dfs_req_size = 0, dfs_rsp_size = 0; - cifs_dbg(FYI, "smb2_get_dfs_refer path <%s>\n", search_name); + cifs_dbg(FYI, "%s: path: %s\n", __func__, search_name); /* * Try to use the IPC tcon, otherwise just use any @@ -2304,13 +2354,13 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_DFS_GET_REFERRALS, true /* is_fsctl */, - (char *)dfs_req, dfs_req_size, + (char *)dfs_req, dfs_req_size, CIFSMaxBufSize, (char **)&dfs_rsp, &dfs_rsp_size); } while (rc == -EAGAIN); if (rc) { if ((rc != -ENOENT) && (rc != -EOPNOTSUPP)) - cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc); + cifs_dbg(VFS, "ioctl error in %s rc=%d\n", __func__, rc); goto out; } @@ -2319,7 +2369,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, nls_codepage, remap, search_name, true /* is_unicode */); if (rc) { - cifs_dbg(VFS, "parse error in smb2_get_dfs_refer rc=%d\n", rc); + cifs_dbg(VFS, "parse error in %s rc=%d\n", __func__, rc); goto out; } @@ -2340,44 +2390,129 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, static int smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, - const char *full_path, char **target_path, - struct cifs_sb_info *cifs_sb) + struct cifs_sb_info *cifs_sb, const char *full_path, + char **target_path, bool is_reparse_point) { int rc; - __le16 *utf16_path; + __le16 *utf16_path = NULL; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct cifs_open_parms oparms; struct cifs_fid fid; struct kvec err_iov = {NULL, 0}; struct smb2_err_rsp *err_buf = NULL; - int resp_buftype; struct smb2_symlink_err_rsp *symlink; unsigned int sub_len; unsigned int sub_offset; unsigned int print_len; unsigned int print_offset; + int flags = 0; + struct smb_rqst rqst[3]; + int resp_buftype[3]; + struct kvec rsp_iov[3]; + struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; + struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; + struct kvec close_iov[1]; + struct smb2_create_rsp *create_rsp; + struct smb2_ioctl_rsp *ioctl_rsp; + char *ioctl_buf; + u32 plen; cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); + if (smb3_encryption_required(tcon)) + flags |= CIFS_TRANSFORM_REQ; + + memset(rqst, 0, sizeof(rqst)); + resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; + memset(rsp_iov, 0, sizeof(rsp_iov)); + utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb); if (!utf16_path) return -ENOMEM; + /* Open */ + memset(&open_iov, 0, sizeof(open_iov)); + rqst[0].rq_iov = open_iov; + rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; + + memset(&oparms, 0, sizeof(oparms)); oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; + if (backup_cred(cifs_sb)) oparms.create_options = CREATE_OPEN_BACKUP_INTENT; else oparms.create_options = 0; + if (is_reparse_point) + oparms.create_options = OPEN_REPARSE_POINT; + oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov, - &resp_buftype); + rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, utf16_path); + if (rc) + goto querty_exit; + smb2_set_next_command(tcon, &rqst[0]); + + + /* IOCTL */ + memset(&io_iov, 0, sizeof(io_iov)); + rqst[1].rq_iov = io_iov; + rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; + + rc = SMB2_ioctl_init(tcon, &rqst[1], fid.persistent_fid, + fid.volatile_fid, FSCTL_GET_REPARSE_POINT, + true /* is_fctl */, NULL, 0, CIFSMaxBufSize); + if (rc) + goto querty_exit; + + smb2_set_next_command(tcon, &rqst[1]); + smb2_set_related(&rqst[1]); + + + /* Close */ + memset(&close_iov, 0, sizeof(close_iov)); + rqst[2].rq_iov = close_iov; + rqst[2].rq_nvec = 1; + + rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID); + if (rc) + goto querty_exit; + + smb2_set_related(&rqst[2]); + + rc = compound_send_recv(xid, tcon->ses, flags, 3, rqst, + resp_buftype, rsp_iov); + + create_rsp = rsp_iov[0].iov_base; + if (create_rsp && create_rsp->sync_hdr.Status) + err_iov = rsp_iov[0]; + ioctl_rsp = rsp_iov[1].iov_base; + + /* + * Open was successful and we got an ioctl response. + */ + if ((rc == 0) && (is_reparse_point)) { + /* See MS-FSCC 2.3.23 */ + + ioctl_buf = (char *)ioctl_rsp + le32_to_cpu(ioctl_rsp->OutputOffset); + plen = le32_to_cpu(ioctl_rsp->OutputCount); + + if (plen + le32_to_cpu(ioctl_rsp->OutputOffset) > + rsp_iov[1].iov_len) { + cifs_dbg(VFS, "srv returned invalid ioctl length: %d\n", plen); + rc = -EIO; + goto querty_exit; + } + + /* Do stuff with ioctl_buf/plen */ + goto querty_exit; + } + if (!rc || !err_iov.iov_base) { rc = -ENOENT; - goto free_path; + goto querty_exit; } err_buf = err_iov.iov_base; @@ -2417,9 +2552,14 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); querty_exit: - free_rsp_buf(resp_buftype, err_buf); - free_path: + cifs_dbg(FYI, "query symlink rc %d\n", rc); kfree(utf16_path); + SMB2_open_free(&rqst[0]); + SMB2_ioctl_free(&rqst[1]); + SMB2_close_free(&rqst[2]); + free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); return rc; } @@ -2596,16 +2736,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, struct cifsInodeInfo *cifsi; struct cifsFileInfo *cfile = file->private_data; struct file_zero_data_information fsctl_buf; - struct smb_rqst rqst[2]; - int resp_buftype[2]; - struct kvec rsp_iov[2]; - struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; - struct kvec si_iov[1]; - unsigned int size[1]; - void *data[1]; long rc; unsigned int xid; - int num = 0, flags = 0; __le64 eof; xid = get_xid(); @@ -2613,7 +2745,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, inode = d_inode(cfile->dentry); cifsi = CIFS_I(inode); - trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, + trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); @@ -2627,38 +2759,16 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, return rc; } - /* - * Must check if file sparse since fallocate -z (zero range) assumes - * non-sparse allocation - */ - if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)) { - rc = -EOPNOTSUPP; - trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, - ses->Suid, offset, len, rc); - free_xid(xid); - return rc; - } - - cifs_dbg(FYI, "offset %lld len %lld", offset, len); + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); fsctl_buf.FileOffset = cpu_to_le64(offset); fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); - if (smb3_encryption_required(tcon)) - flags |= CIFS_TRANSFORM_REQ; - - memset(rqst, 0, sizeof(rqst)); - resp_buftype[0] = resp_buftype[1] = CIFS_NO_BUFFER; - memset(rsp_iov, 0, sizeof(rsp_iov)); - - - memset(&io_iov, 0, sizeof(io_iov)); - rqst[num].rq_iov = io_iov; - rqst[num].rq_nvec = SMB2_IOCTL_IOV_SIZE; - rc = SMB2_ioctl_init(tcon, &rqst[num++], cfile->fid.persistent_fid, - cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, - true /* is_fctl */, (char *)&fsctl_buf, - sizeof(struct file_zero_data_information)); + rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true, + (char *)&fsctl_buf, + sizeof(struct file_zero_data_information), + 0, NULL, NULL); if (rc) goto zero_range_exit; @@ -2666,33 +2776,12 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, * do we also need to change the size of the file? */ if (keep_size == false && i_size_read(inode) < offset + len) { - smb2_set_next_command(tcon, &rqst[0]); - - memset(&si_iov, 0, sizeof(si_iov)); - rqst[num].rq_iov = si_iov; - rqst[num].rq_nvec = 1; - eof = cpu_to_le64(offset + len); - size[0] = 8; /* sizeof __le64 */ - data[0] = &eof; - - rc = SMB2_set_info_init(tcon, &rqst[num++], - cfile->fid.persistent_fid, - cfile->fid.persistent_fid, - current->tgid, - FILE_END_OF_FILE_INFORMATION, - SMB2_O_INFO_FILE, 0, data, size); - smb2_set_related(&rqst[1]); + rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, cfile->pid, &eof); } - rc = compound_send_recv(xid, ses, flags, num, rqst, - resp_buftype, rsp_iov); - zero_range_exit: - SMB2_ioctl_free(&rqst[0]); - SMB2_set_info_free(&rqst[1]); - free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); - free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -2727,7 +2816,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, return rc; } - cifs_dbg(FYI, "offset %lld len %lld", offset, len); + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); fsctl_buf.FileOffset = cpu_to_le64(offset); fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); @@ -2735,7 +2824,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true /* is_fctl */, (char *)&fsctl_buf, - sizeof(struct file_zero_data_information), NULL, NULL); + sizeof(struct file_zero_data_information), + CIFSMaxBufSize, NULL, NULL); free_xid(xid); return rc; } @@ -2832,6 +2922,163 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, return rc; } +static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offset, int whence) +{ + struct cifsFileInfo *wrcfile, *cfile = file->private_data; + struct cifsInodeInfo *cifsi; + struct inode *inode; + int rc = 0; + struct file_allocated_range_buffer in_data, *out_data = NULL; + u32 out_data_len; + unsigned int xid; + + if (whence != SEEK_HOLE && whence != SEEK_DATA) + return generic_file_llseek(file, offset, whence); + + inode = d_inode(cfile->dentry); + cifsi = CIFS_I(inode); + + if (offset < 0 || offset >= i_size_read(inode)) + return -ENXIO; + + xid = get_xid(); + /* + * We need to be sure that all dirty pages are written as they + * might fill holes on the server. + * Note that we also MUST flush any written pages since at least + * some servers (Windows2016) will not reflect recent writes in + * QUERY_ALLOCATED_RANGES until SMB2_flush is called. + */ + wrcfile = find_writable_file(cifsi, false); + if (wrcfile) { + filemap_write_and_wait(inode->i_mapping); + smb2_flush_file(xid, tcon, &wrcfile->fid); + cifsFileInfo_put(wrcfile); + } + + if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)) { + if (whence == SEEK_HOLE) + offset = i_size_read(inode); + goto lseek_exit; + } + + in_data.file_offset = cpu_to_le64(offset); + in_data.length = cpu_to_le64(i_size_read(inode)); + + rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + FSCTL_QUERY_ALLOCATED_RANGES, true, + (char *)&in_data, sizeof(in_data), + sizeof(struct file_allocated_range_buffer), + (char **)&out_data, &out_data_len); + if (rc == -E2BIG) + rc = 0; + if (rc) + goto lseek_exit; + + if (whence == SEEK_HOLE && out_data_len == 0) + goto lseek_exit; + + if (whence == SEEK_DATA && out_data_len == 0) { + rc = -ENXIO; + goto lseek_exit; + } + + if (out_data_len < sizeof(struct file_allocated_range_buffer)) { + rc = -EINVAL; + goto lseek_exit; + } + if (whence == SEEK_DATA) { + offset = le64_to_cpu(out_data->file_offset); + goto lseek_exit; + } + if (offset < le64_to_cpu(out_data->file_offset)) + goto lseek_exit; + + offset = le64_to_cpu(out_data->file_offset) + le64_to_cpu(out_data->length); + + lseek_exit: + free_xid(xid); + kfree(out_data); + if (!rc) + return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); + else + return rc; +} + +static int smb3_fiemap(struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, + struct fiemap_extent_info *fei, u64 start, u64 len) +{ + unsigned int xid; + struct file_allocated_range_buffer in_data, *out_data; + u32 out_data_len; + int i, num, rc, flags, last_blob; + u64 next; + + if (fiemap_check_flags(fei, FIEMAP_FLAG_SYNC)) + return -EBADR; + + xid = get_xid(); + again: + in_data.file_offset = cpu_to_le64(start); + in_data.length = cpu_to_le64(len); + + rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + FSCTL_QUERY_ALLOCATED_RANGES, true, + (char *)&in_data, sizeof(in_data), + 1024 * sizeof(struct file_allocated_range_buffer), + (char **)&out_data, &out_data_len); + if (rc == -E2BIG) { + last_blob = 0; + rc = 0; + } else + last_blob = 1; + if (rc) + goto out; + + if (out_data_len < sizeof(struct file_allocated_range_buffer)) { + rc = -EINVAL; + goto out; + } + if (out_data_len % sizeof(struct file_allocated_range_buffer)) { + rc = -EINVAL; + goto out; + } + + num = out_data_len / sizeof(struct file_allocated_range_buffer); + for (i = 0; i < num; i++) { + flags = 0; + if (i == num - 1 && last_blob) + flags |= FIEMAP_EXTENT_LAST; + + rc = fiemap_fill_next_extent(fei, + le64_to_cpu(out_data[i].file_offset), + le64_to_cpu(out_data[i].file_offset), + le64_to_cpu(out_data[i].length), + flags); + if (rc < 0) + goto out; + if (rc == 1) { + rc = 0; + goto out; + } + } + + if (!last_blob) { + next = le64_to_cpu(out_data[num - 1].file_offset) + + le64_to_cpu(out_data[num - 1].length); + len = len - (next - start); + start = next; + goto again; + } + + out: + free_xid(xid); + kfree(out_data); + return rc; +} static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode, loff_t off, loff_t len) @@ -2899,26 +3146,28 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, unsigned int epoch, bool *purge_cache) { char message[5] = {0}; + unsigned int new_oplock = 0; oplock &= 0xFF; if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) return; - cinode->oplock = 0; if (oplock & SMB2_LEASE_READ_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_READ_FLG; + new_oplock |= CIFS_CACHE_READ_FLG; strcat(message, "R"); } if (oplock & SMB2_LEASE_HANDLE_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_HANDLE_FLG; + new_oplock |= CIFS_CACHE_HANDLE_FLG; strcat(message, "H"); } if (oplock & SMB2_LEASE_WRITE_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_WRITE_FLG; + new_oplock |= CIFS_CACHE_WRITE_FLG; strcat(message, "W"); } - if (!cinode->oplock) - strcat(message, "None"); + if (!new_oplock) + strncpy(message, "None", sizeof(message)); + + cinode->oplock = new_oplock; cifs_dbg(FYI, "%s Lease granted on inode %p\n", message, &cinode->vfs_inode); } @@ -3219,7 +3468,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, req = aead_request_alloc(tfm, GFP_KERNEL); if (!req) { - cifs_dbg(VFS, "%s: Failed to alloc aead request", __func__); + cifs_dbg(VFS, "%s: Failed to alloc aead request\n", __func__); return -ENOMEM; } @@ -3230,7 +3479,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, sg = init_sg(num_rqst, rqst, sign); if (!sg) { - cifs_dbg(VFS, "%s: Failed to init sg", __func__); + cifs_dbg(VFS, "%s: Failed to init sg\n", __func__); rc = -ENOMEM; goto free_req; } @@ -3238,7 +3487,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, iv_len = crypto_aead_ivsize(tfm); iv = kzalloc(iv_len, GFP_KERNEL); if (!iv) { - cifs_dbg(VFS, "%s: Failed to alloc IV", __func__); + cifs_dbg(VFS, "%s: Failed to alloc iv\n", __func__); rc = -ENOMEM; goto free_sg; } @@ -3346,7 +3595,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst, fill_transform_hdr(tr_hdr, orig_len, old_rq); rc = crypt_message(server, num_rqst, new_rq, 1); - cifs_dbg(FYI, "encrypt message returned %d", rc); + cifs_dbg(FYI, "Encrypt message returned %d\n", rc); if (rc) goto err_free; @@ -3387,7 +3636,7 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, rqst.rq_tailsz = (page_data_size % PAGE_SIZE) ? : PAGE_SIZE; rc = crypt_message(server, 1, &rqst, 0); - cifs_dbg(FYI, "decrypt message returned %d\n", rc); + cifs_dbg(FYI, "Decrypt message returned %d\n", rc); if (rc) return rc; @@ -4000,6 +4249,8 @@ struct smb_version_operations smb20_operations = { .next_header = smb2_next_header, .ioctl_query_info = smb2_ioctl_query_info, .make_node = smb2_make_node, + .fiemap = smb3_fiemap, + .llseek = smb3_llseek, }; struct smb_version_operations smb21_operations = { @@ -4099,6 +4350,8 @@ struct smb_version_operations smb21_operations = { .next_header = smb2_next_header, .ioctl_query_info = smb2_ioctl_query_info, .make_node = smb2_make_node, + .fiemap = smb3_fiemap, + .llseek = smb3_llseek, }; struct smb_version_operations smb30_operations = { @@ -4207,6 +4460,8 @@ struct smb_version_operations smb30_operations = { .next_header = smb2_next_header, .ioctl_query_info = smb2_ioctl_query_info, .make_node = smb2_make_node, + .fiemap = smb3_fiemap, + .llseek = smb3_llseek, }; struct smb_version_operations smb311_operations = { @@ -4316,6 +4571,8 @@ struct smb_version_operations smb311_operations = { .next_header = smb2_next_header, .ioctl_query_info = smb2_ioctl_query_info, .make_node = smb2_make_node, + .fiemap = smb3_fiemap, + .llseek = smb3_llseek, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 21ac19ff19cb..710ceb875161 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -459,10 +459,7 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, return rc; } - -#define SMB2_PREAUTH_INTEGRITY_CAPABILITIES cpu_to_le16(1) -#define SMB2_ENCRYPTION_CAPABILITIES cpu_to_le16(2) -#define SMB2_POSIX_EXTENSIONS_AVAILABLE cpu_to_le16(0x100) +/* For explanation of negotiate contexts see MS-SMB2 section 2.2.3.1 */ static void build_preauth_ctxt(struct smb2_preauth_neg_context *pneg_ctxt) @@ -476,6 +473,19 @@ build_preauth_ctxt(struct smb2_preauth_neg_context *pneg_ctxt) } static void +build_compression_ctxt(struct smb2_compression_capabilities_context *pneg_ctxt) +{ + pneg_ctxt->ContextType = SMB2_COMPRESSION_CAPABILITIES; + pneg_ctxt->DataLength = + cpu_to_le16(sizeof(struct smb2_compression_capabilities_context) + - sizeof(struct smb2_neg_context)); + pneg_ctxt->CompressionAlgorithmCount = cpu_to_le16(3); + pneg_ctxt->CompressionAlgorithms[0] = SMB3_COMPRESS_LZ77; + pneg_ctxt->CompressionAlgorithms[1] = SMB3_COMPRESS_LZ77_HUFF; + pneg_ctxt->CompressionAlgorithms[2] = SMB3_COMPRESS_LZNT1; +} + +static void build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt) { pneg_ctxt->ContextType = SMB2_ENCRYPTION_CAPABILITIES; @@ -541,10 +551,17 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, *total_len += ctxt_len; pneg_ctxt += ctxt_len; + build_compression_ctxt((struct smb2_compression_capabilities_context *) + pneg_ctxt); + ctxt_len = DIV_ROUND_UP( + sizeof(struct smb2_compression_capabilities_context), 8) * 8; + *total_len += ctxt_len; + pneg_ctxt += ctxt_len; + build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt); *total_len += sizeof(struct smb2_posix_neg_context); - req->NegotiateContextCount = cpu_to_le16(3); + req->NegotiateContextCount = cpu_to_le16(4); } static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt) @@ -562,6 +579,27 @@ static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt) printk_once(KERN_WARNING "unknown SMB3 hash algorithm\n"); } +static void decode_compress_ctx(struct TCP_Server_Info *server, + struct smb2_compression_capabilities_context *ctxt) +{ + unsigned int len = le16_to_cpu(ctxt->DataLength); + + /* sizeof compress context is a one element compression capbility struct */ + if (len < 10) { + printk_once(KERN_WARNING "server sent bad compression cntxt\n"); + return; + } + if (le16_to_cpu(ctxt->CompressionAlgorithmCount) != 1) { + printk_once(KERN_WARNING "illegal SMB3 compress algorithm count\n"); + return; + } + if (le16_to_cpu(ctxt->CompressionAlgorithms[0]) > 3) { + printk_once(KERN_WARNING "unknown compression algorithm\n"); + return; + } + server->compress_algorithm = ctxt->CompressionAlgorithms[0]; +} + static int decode_encrypt_ctx(struct TCP_Server_Info *server, struct smb2_encryption_neg_context *ctxt) { @@ -626,6 +664,9 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES) rc = decode_encrypt_ctx(server, (struct smb2_encryption_neg_context *)pctx); + else if (pctx->ContextType == SMB2_COMPRESSION_CAPABILITIES) + decode_compress_ctx(server, + (struct smb2_compression_capabilities_context *)pctx); else if (pctx->ContextType == SMB2_POSIX_EXTENSIONS_AVAILABLE) server->posix_ext_supported = true; else @@ -832,8 +873,11 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { /* ops set to 3.0 by default for default so update */ ses->server->ops = &smb21_operations; - } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) + ses->server->vals = &smb21_values; + } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) { ses->server->ops = &smb311_operations; + ses->server->vals = &smb311_values; + } } else if (le16_to_cpu(rsp->DialectRevision) != ses->server->vals->protocol_id) { /* if requested single dialect ensure returned dialect matched */ @@ -1002,7 +1046,8 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, - (char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen); + (char *)pneg_inbuf, inbuflen, CIFSMaxBufSize, + (char **)&pneg_rsp, &rsplen); if (rc == -EOPNOTSUPP) { /* * Old Windows versions or Netapp SMB server can return @@ -1537,7 +1582,7 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) else if (server->sign) req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED; - flags |= CIFS_NO_RESP; + flags |= CIFS_NO_RSP_BUF; iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; @@ -1738,7 +1783,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - flags |= CIFS_NO_RESP; + flags |= CIFS_NO_RSP_BUF; iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; @@ -1858,8 +1903,9 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, } static struct create_durable_v2 * -create_durable_v2_buf(struct cifs_fid *pfid) +create_durable_v2_buf(struct cifs_open_parms *oparms) { + struct cifs_fid *pfid = oparms->fid; struct create_durable_v2 *buf; buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL); @@ -1873,7 +1919,14 @@ create_durable_v2_buf(struct cifs_fid *pfid) (struct create_durable_v2, Name)); buf->ccontext.NameLength = cpu_to_le16(4); - buf->dcontext.Timeout = 0; /* Should this be configurable by workload */ + /* + * NB: Handle timeout defaults to 0, which allows server to choose + * (most servers default to 120 seconds) and most clients default to 0. + * This can be overridden at mount ("handletimeout=") if the user wants + * a different persistent (or resilient) handle timeout for all opens + * opens on a particular SMB3 mount. + */ + buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout); buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); generate_random_uuid(buf->dcontext.CreateGuid); memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16); @@ -1926,7 +1979,7 @@ add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec, struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; - iov[num].iov_base = create_durable_v2_buf(oparms->fid); + iov[num].iov_base = create_durable_v2_buf(oparms); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable_v2); @@ -2478,17 +2531,32 @@ creat_exit: int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen) + bool is_fsctl, char *in_data, u32 indatalen, + __u32 max_response_size) { struct smb2_ioctl_req *req; struct kvec *iov = rqst->rq_iov; unsigned int total_len; int rc; + char *in_data_buf; rc = smb2_plain_req_init(SMB2_IOCTL, tcon, (void **) &req, &total_len); if (rc) return rc; + if (indatalen) { + /* + * indatalen is usually small at a couple of bytes max, so + * just allocate through generic pool + */ + in_data_buf = kmalloc(indatalen, GFP_NOFS); + if (!in_data_buf) { + cifs_small_buf_release(req); + return -ENOMEM; + } + memcpy(in_data_buf, in_data, indatalen); + } + req->CtlCode = cpu_to_le32(opcode); req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; @@ -2509,7 +2577,7 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, cpu_to_le32(offsetof(struct smb2_ioctl_req, Buffer)); rqst->rq_nvec = 2; iov[0].iov_len = total_len - 1; - iov[1].iov_base = in_data; + iov[1].iov_base = in_data_buf; iov[1].iov_len = indatalen; } else { rqst->rq_nvec = 1; @@ -2520,16 +2588,21 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, req->OutputCount = 0; /* MBZ */ /* - * Could increase MaxOutputResponse, but that would require more - * than one credit. Windows typically sets this smaller, but for some + * In most cases max_response_size is set to 16K (CIFSMaxBufSize) + * We Could increase default MaxOutputResponse, but that could require + * more credits. Windows typically sets this smaller, but for some * ioctls it may be useful to allow server to send more. No point * limiting what the server can send as long as fits in one credit - * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE - * (by default, note that it can be overridden to make max larger) - * in responses (except for read responses which can be bigger. - * We may want to bump this limit up + * We can not handle more than CIFS_MAX_BUF_SIZE yet but may want + * to increase this limit up in the future. + * Note that for snapshot queries that servers like Azure expect that + * the first query be minimal size (and just used to get the number/size + * of previous versions) so response size must be specified as EXACTLY + * sizeof(struct snapshot_array) which is 16 when rounded up to multiple + * of eight bytes. Currently that is the only case where we set max + * response size smaller. */ - req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize); + req->MaxOutputResponse = cpu_to_le32(max_response_size); if (is_fsctl) req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); @@ -2546,17 +2619,21 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, void SMB2_ioctl_free(struct smb_rqst *rqst) { - if (rqst && rqst->rq_iov) + if (rqst && rqst->rq_iov) { cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */ + if (rqst->rq_iov[1].iov_len) + kfree(rqst->rq_iov[1].iov_base); + } } + /* * SMB2 IOCTL is used for both IOCTLs and FSCTLs */ int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, - char *in_data, u32 indatalen, + char *in_data, u32 indatalen, u32 max_out_data_len, char **out_data, u32 *plen /* returned data len */) { struct smb_rqst rqst; @@ -2593,8 +2670,8 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rqst.rq_iov = iov; rqst.rq_nvec = SMB2_IOCTL_IOV_SIZE; - rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, - opcode, is_fsctl, in_data, indatalen); + rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, opcode, + is_fsctl, in_data, indatalen, max_out_data_len); if (rc) goto ioctl_exit; @@ -2606,7 +2683,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, trace_smb3_fsctl_err(xid, persistent_fid, tcon->tid, ses->Suid, 0, opcode, rc); - if ((rc != 0) && (rc != -EINVAL)) { + if ((rc != 0) && (rc != -EINVAL) && (rc != -E2BIG)) { cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); goto ioctl_exit; } else if (rc == -EINVAL) { @@ -2615,6 +2692,11 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); goto ioctl_exit; } + } else if (rc == -E2BIG) { + if (opcode != FSCTL_QUERY_ALLOCATED_RANGES) { + cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); + goto ioctl_exit; + } } /* check if caller wants to look at return data or just return rc */ @@ -2672,7 +2754,8 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, FSCTL_SET_COMPRESSION, true /* is_fsctl */, (char *)&fsctl_input /* data input */, - 2 /* in data len */, &ret_data /* out data */, NULL); + 2 /* in data len */, CIFSMaxBufSize /* max out data */, + &ret_data /* out data */, NULL); cifs_dbg(FYI, "set compression rc %d\n", rc); @@ -3203,7 +3286,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len, rdata->nr_pages, rdata->page_offset, rdata->tailsz, true, need_invalidate); if (!rdata->mr) - return -ENOBUFS; + return -EAGAIN; req->Channel = SMB2_CHANNEL_RDMA_V1_INVALIDATE; if (need_invalidate) @@ -3431,8 +3514,6 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, rqst.rq_nvec = 1; rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); - rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; if (rc) { @@ -3448,12 +3529,15 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->tcon->tid, ses->Suid, io_parms->offset, 0); free_rsp_buf(resp_buftype, rsp_iov.iov_base); + cifs_small_buf_release(req); return rc == -ENODATA ? 0 : rc; } else trace_smb3_read_done(xid, req->PersistentFileId, io_parms->tcon->tid, ses->Suid, io_parms->offset, io_parms->length); + cifs_small_buf_release(req); + *nbytes = le32_to_cpu(rsp->DataLength); if ((*nbytes > CIFS_MAX_MSGSIZE) || (*nbytes > io_parms->length)) { @@ -3607,7 +3691,7 @@ smb2_async_writev(struct cifs_writedata *wdata, wdata->nr_pages, wdata->page_offset, wdata->tailsz, false, need_invalidate); if (!wdata->mr) { - rc = -ENOBUFS; + rc = -EAGAIN; goto async_writev_out; } req->Length = 0; @@ -3752,7 +3836,6 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); rsp = (struct smb2_write_rsp *)rsp_iov.iov_base; if (rc) { @@ -3770,6 +3853,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->offset, *nbytes); } + cifs_small_buf_release(req); free_rsp_buf(resp_buftype, rsp); return rc; } @@ -4143,7 +4227,7 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, req->OplockLevel = oplock_level; req->sync_hdr.CreditRequest = cpu_to_le16(1); - flags |= CIFS_NO_RESP; + flags |= CIFS_NO_RSP_BUF; iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; @@ -4417,7 +4501,7 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon, struct kvec rsp_iov; int resp_buf_type; unsigned int count; - int flags = CIFS_NO_RESP; + int flags = CIFS_NO_RSP_BUF; unsigned int total_len; cifs_dbg(FYI, "smb2_lockv num lock %d\n", num_lock); @@ -4510,7 +4594,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, memcpy(req->LeaseKey, lease_key, 16); req->LeaseState = lease_state; - flags |= CIFS_NO_RESP; + flags |= CIFS_NO_RSP_BUF; iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index ee8977688e21..c7d5813bebd8 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -251,6 +251,14 @@ struct smb2_negotiate_req { #define SMB2_NT_FIND 0x00100000 #define SMB2_LARGE_FILES 0x00200000 + +/* Negotiate Contexts - ContextTypes. See MS-SMB2 section 2.2.3.1 for details */ +#define SMB2_PREAUTH_INTEGRITY_CAPABILITIES cpu_to_le16(1) +#define SMB2_ENCRYPTION_CAPABILITIES cpu_to_le16(2) +#define SMB2_COMPRESSION_CAPABILITIES cpu_to_le16(3) +#define SMB2_NETNAME_NEGOTIATE_CONTEXT_ID cpu_to_le16(5) +#define SMB2_POSIX_EXTENSIONS_AVAILABLE cpu_to_le16(0x100) + struct smb2_neg_context { __le16 ContextType; __le16 DataLength; @@ -288,6 +296,27 @@ struct smb2_encryption_neg_context { __le16 Ciphers[1]; /* Ciphers[0] since only one used now */ } __packed; +/* See MS-SMB2 2.2.3.1.3 */ +#define SMB3_COMPRESS_NONE cpu_to_le16(0x0000) +#define SMB3_COMPRESS_LZNT1 cpu_to_le16(0x0001) +#define SMB3_COMPRESS_LZ77 cpu_to_le16(0x0002) +#define SMB3_COMPRESS_LZ77_HUFF cpu_to_le16(0x0003) + +struct smb2_compression_capabilities_context { + __le16 ContextType; /* 3 */ + __le16 DataLength; + __u32 Reserved; + __le16 CompressionAlgorithmCount; + __u16 Padding; + __u32 Reserved1; + __le16 CompressionAlgorithms[3]; +} __packed; + +/* + * For smb2_netname_negotiate_context_id See MS-SMB2 2.2.3.1.4. + * Its struct simply contains NetName, an array of Unicode characters + */ + #define POSIX_CTXT_DATA_LEN 16 struct smb2_posix_neg_context { __le16 ContextType; /* 0x100 */ @@ -842,6 +871,11 @@ struct fsctl_get_integrity_information_rsp { __le32 ClusterSizeInBytes; } __packed; +struct file_allocated_range_buffer { + __le64 file_offset; + __le64 length; +} __packed; + /* Integrity ChecksumAlgorithm choices for above */ #define CHECKSUM_TYPE_NONE 0x0000 #define CHECKSUM_TYPE_CRC64 0x0002 @@ -1047,6 +1081,7 @@ struct smb2_flush_rsp { /* For read request Flags field below, following flag is defined for SMB3.02 */ #define SMB2_READFLAG_READ_UNBUFFERED 0x01 +#define SMB2_READFLAG_REQUEST_COMPRESSED 0x02 /* See MS-SMB2 2.2.19 */ /* Channel field for read and write: exactly one of following flags can be set*/ #define SMB2_CHANNEL_NONE cpu_to_le32(0x00000000) @@ -1113,6 +1148,42 @@ struct smb2_write_rsp { __u8 Buffer[1]; } __packed; +/* notify flags */ +#define SMB2_WATCH_TREE 0x0001 + +/* notify completion filter flags. See MS-FSCC 2.6 and MS-SMB2 2.2.35 */ +#define FILE_NOTIFY_CHANGE_FILE_NAME 0x00000001 +#define FILE_NOTIFY_CHANGE_DIR_NAME 0x00000002 +#define FILE_NOTIFY_CHANGE_ATTRIBUTES 0x00000004 +#define FILE_NOTIFY_CHANGE_SIZE 0x00000008 +#define FILE_NOTIFY_CHANGE_LAST_WRITE 0x00000010 +#define FILE_NOTIFY_CHANGE_LAST_ACCESS 0x00000020 +#define FILE_NOTIFY_CHANGE_CREATION 0x00000040 +#define FILE_NOTIFY_CHANGE_EA 0x00000080 +#define FILE_NOTIFY_CHANGE_SECURITY 0x00000100 +#define FILE_NOTIFY_CHANGE_STREAM_NAME 0x00000200 +#define FILE_NOTIFY_CHANGE_STREAM_SIZE 0x00000400 +#define FILE_NOTIFY_CHANGE_STREAM_WRITE 0x00000800 + +struct smb2_change_notify_req { + struct smb2_sync_hdr sync_hdr; + __le16 StructureSize; + __le16 Flags; + __le32 OutputBufferLength; + __u64 PersistentFileId; /* opaque endianness */ + __u64 VolatileFileId; /* opaque endianness */ + __le32 CompletionFilter; + __u32 Reserved; +} __packed; + +struct smb2_change_notify_rsp { + struct smb2_sync_hdr sync_hdr; + __le16 StructureSize; /* Must be 9 */ + __le16 OutputBufferOffset; + __le32 OutputBufferLength; + __u8 Buffer[1]; /* array of file notify structs */ +} __packed; + #define SMB2_LOCKFLAG_SHARED_LOCK 0x0001 #define SMB2_LOCKFLAG_EXCLUSIVE_LOCK 0x0002 #define SMB2_LOCKFLAG_UNLOCK 0x0004 diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 3c32d0cfea69..52df125e9189 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -142,11 +142,12 @@ extern int SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, extern void SMB2_open_free(struct smb_rqst *rqst); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen, char **out_data, u32 *plen /* returned data len */); extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen); + bool is_fsctl, char *in_data, u32 indatalen, + __u32 max_response_size); extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); diff --git a/fs/cifs/smb2status.h b/fs/cifs/smb2status.h index 447c0c6e4c64..7505056e9580 100644 --- a/fs/cifs/smb2status.h +++ b/fs/cifs/smb2status.h @@ -40,1743 +40,1743 @@ struct ntstatus { __le32 Code; }; -#define STATUS_SUCCESS __constant_cpu_to_le32(0x00000000) -#define STATUS_WAIT_0 __constant_cpu_to_le32(0x00000000) -#define STATUS_WAIT_1 __constant_cpu_to_le32(0x00000001) -#define STATUS_WAIT_2 __constant_cpu_to_le32(0x00000002) -#define STATUS_WAIT_3 __constant_cpu_to_le32(0x00000003) -#define STATUS_WAIT_63 __constant_cpu_to_le32(0x0000003F) -#define STATUS_ABANDONED __constant_cpu_to_le32(0x00000080) -#define STATUS_ABANDONED_WAIT_0 __constant_cpu_to_le32(0x00000080) -#define STATUS_ABANDONED_WAIT_63 __constant_cpu_to_le32(0x000000BF) -#define STATUS_USER_APC __constant_cpu_to_le32(0x000000C0) -#define STATUS_KERNEL_APC __constant_cpu_to_le32(0x00000100) -#define STATUS_ALERTED __constant_cpu_to_le32(0x00000101) -#define STATUS_TIMEOUT __constant_cpu_to_le32(0x00000102) -#define STATUS_PENDING __constant_cpu_to_le32(0x00000103) -#define STATUS_REPARSE __constant_cpu_to_le32(0x00000104) -#define STATUS_MORE_ENTRIES __constant_cpu_to_le32(0x00000105) -#define STATUS_NOT_ALL_ASSIGNED __constant_cpu_to_le32(0x00000106) -#define STATUS_SOME_NOT_MAPPED __constant_cpu_to_le32(0x00000107) -#define STATUS_OPLOCK_BREAK_IN_PROGRESS __constant_cpu_to_le32(0x00000108) -#define STATUS_VOLUME_MOUNTED __constant_cpu_to_le32(0x00000109) -#define STATUS_RXACT_COMMITTED __constant_cpu_to_le32(0x0000010A) -#define STATUS_NOTIFY_CLEANUP __constant_cpu_to_le32(0x0000010B) -#define STATUS_NOTIFY_ENUM_DIR __constant_cpu_to_le32(0x0000010C) -#define STATUS_NO_QUOTAS_FOR_ACCOUNT __constant_cpu_to_le32(0x0000010D) -#define STATUS_PRIMARY_TRANSPORT_CONNECT_FAILED __constant_cpu_to_le32(0x0000010E) -#define STATUS_PAGE_FAULT_TRANSITION __constant_cpu_to_le32(0x00000110) -#define STATUS_PAGE_FAULT_DEMAND_ZERO __constant_cpu_to_le32(0x00000111) -#define STATUS_PAGE_FAULT_COPY_ON_WRITE __constant_cpu_to_le32(0x00000112) -#define STATUS_PAGE_FAULT_GUARD_PAGE __constant_cpu_to_le32(0x00000113) -#define STATUS_PAGE_FAULT_PAGING_FILE __constant_cpu_to_le32(0x00000114) -#define STATUS_CACHE_PAGE_LOCKED __constant_cpu_to_le32(0x00000115) -#define STATUS_CRASH_DUMP __constant_cpu_to_le32(0x00000116) -#define STATUS_BUFFER_ALL_ZEROS __constant_cpu_to_le32(0x00000117) -#define STATUS_REPARSE_OBJECT __constant_cpu_to_le32(0x00000118) -#define STATUS_RESOURCE_REQUIREMENTS_CHANGED __constant_cpu_to_le32(0x00000119) -#define STATUS_TRANSLATION_COMPLETE __constant_cpu_to_le32(0x00000120) -#define STATUS_DS_MEMBERSHIP_EVALUATED_LOCALLY __constant_cpu_to_le32(0x00000121) -#define STATUS_NOTHING_TO_TERMINATE __constant_cpu_to_le32(0x00000122) -#define STATUS_PROCESS_NOT_IN_JOB __constant_cpu_to_le32(0x00000123) -#define STATUS_PROCESS_IN_JOB __constant_cpu_to_le32(0x00000124) -#define STATUS_VOLSNAP_HIBERNATE_READY __constant_cpu_to_le32(0x00000125) -#define STATUS_FSFILTER_OP_COMPLETED_SUCCESSFULLY __constant_cpu_to_le32(0x00000126) -#define STATUS_INTERRUPT_VECTOR_ALREADY_CONNECTED __constant_cpu_to_le32(0x00000127) -#define STATUS_INTERRUPT_STILL_CONNECTED __constant_cpu_to_le32(0x00000128) -#define STATUS_PROCESS_CLONED __constant_cpu_to_le32(0x00000129) -#define STATUS_FILE_LOCKED_WITH_ONLY_READERS __constant_cpu_to_le32(0x0000012A) -#define STATUS_FILE_LOCKED_WITH_WRITERS __constant_cpu_to_le32(0x0000012B) -#define STATUS_RESOURCEMANAGER_READ_ONLY __constant_cpu_to_le32(0x00000202) -#define STATUS_WAIT_FOR_OPLOCK __constant_cpu_to_le32(0x00000367) -#define DBG_EXCEPTION_HANDLED __constant_cpu_to_le32(0x00010001) -#define DBG_CONTINUE __constant_cpu_to_le32(0x00010002) -#define STATUS_FLT_IO_COMPLETE __constant_cpu_to_le32(0x001C0001) -#define STATUS_OBJECT_NAME_EXISTS __constant_cpu_to_le32(0x40000000) -#define STATUS_THREAD_WAS_SUSPENDED __constant_cpu_to_le32(0x40000001) -#define STATUS_WORKING_SET_LIMIT_RANGE __constant_cpu_to_le32(0x40000002) -#define STATUS_IMAGE_NOT_AT_BASE __constant_cpu_to_le32(0x40000003) -#define STATUS_RXACT_STATE_CREATED __constant_cpu_to_le32(0x40000004) -#define STATUS_SEGMENT_NOTIFICATION __constant_cpu_to_le32(0x40000005) -#define STATUS_LOCAL_USER_SESSION_KEY __constant_cpu_to_le32(0x40000006) -#define STATUS_BAD_CURRENT_DIRECTORY __constant_cpu_to_le32(0x40000007) -#define STATUS_SERIAL_MORE_WRITES __constant_cpu_to_le32(0x40000008) -#define STATUS_REGISTRY_RECOVERED __constant_cpu_to_le32(0x40000009) -#define STATUS_FT_READ_RECOVERY_FROM_BACKUP __constant_cpu_to_le32(0x4000000A) -#define STATUS_FT_WRITE_RECOVERY __constant_cpu_to_le32(0x4000000B) -#define STATUS_SERIAL_COUNTER_TIMEOUT __constant_cpu_to_le32(0x4000000C) -#define STATUS_NULL_LM_PASSWORD __constant_cpu_to_le32(0x4000000D) -#define STATUS_IMAGE_MACHINE_TYPE_MISMATCH __constant_cpu_to_le32(0x4000000E) -#define STATUS_RECEIVE_PARTIAL __constant_cpu_to_le32(0x4000000F) -#define STATUS_RECEIVE_EXPEDITED __constant_cpu_to_le32(0x40000010) -#define STATUS_RECEIVE_PARTIAL_EXPEDITED __constant_cpu_to_le32(0x40000011) -#define STATUS_EVENT_DONE __constant_cpu_to_le32(0x40000012) -#define STATUS_EVENT_PENDING __constant_cpu_to_le32(0x40000013) -#define STATUS_CHECKING_FILE_SYSTEM __constant_cpu_to_le32(0x40000014) -#define STATUS_FATAL_APP_EXIT __constant_cpu_to_le32(0x40000015) -#define STATUS_PREDEFINED_HANDLE __constant_cpu_to_le32(0x40000016) -#define STATUS_WAS_UNLOCKED __constant_cpu_to_le32(0x40000017) -#define STATUS_SERVICE_NOTIFICATION __constant_cpu_to_le32(0x40000018) -#define STATUS_WAS_LOCKED __constant_cpu_to_le32(0x40000019) -#define STATUS_LOG_HARD_ERROR __constant_cpu_to_le32(0x4000001A) -#define STATUS_ALREADY_WIN32 __constant_cpu_to_le32(0x4000001B) -#define STATUS_WX86_UNSIMULATE __constant_cpu_to_le32(0x4000001C) -#define STATUS_WX86_CONTINUE __constant_cpu_to_le32(0x4000001D) -#define STATUS_WX86_SINGLE_STEP __constant_cpu_to_le32(0x4000001E) -#define STATUS_WX86_BREAKPOINT __constant_cpu_to_le32(0x4000001F) -#define STATUS_WX86_EXCEPTION_CONTINUE __constant_cpu_to_le32(0x40000020) -#define STATUS_WX86_EXCEPTION_LASTCHANCE __constant_cpu_to_le32(0x40000021) -#define STATUS_WX86_EXCEPTION_CHAIN __constant_cpu_to_le32(0x40000022) -#define STATUS_IMAGE_MACHINE_TYPE_MISMATCH_EXE __constant_cpu_to_le32(0x40000023) -#define STATUS_NO_YIELD_PERFORMED __constant_cpu_to_le32(0x40000024) -#define STATUS_TIMER_RESUME_IGNORED __constant_cpu_to_le32(0x40000025) -#define STATUS_ARBITRATION_UNHANDLED __constant_cpu_to_le32(0x40000026) -#define STATUS_CARDBUS_NOT_SUPPORTED __constant_cpu_to_le32(0x40000027) -#define STATUS_WX86_CREATEWX86TIB __constant_cpu_to_le32(0x40000028) -#define STATUS_MP_PROCESSOR_MISMATCH __constant_cpu_to_le32(0x40000029) -#define STATUS_HIBERNATED __constant_cpu_to_le32(0x4000002A) -#define STATUS_RESUME_HIBERNATION __constant_cpu_to_le32(0x4000002B) -#define STATUS_FIRMWARE_UPDATED __constant_cpu_to_le32(0x4000002C) -#define STATUS_DRIVERS_LEAKING_LOCKED_PAGES __constant_cpu_to_le32(0x4000002D) -#define STATUS_MESSAGE_RETRIEVED __constant_cpu_to_le32(0x4000002E) -#define STATUS_SYSTEM_POWERSTATE_TRANSITION __constant_cpu_to_le32(0x4000002F) -#define STATUS_ALPC_CHECK_COMPLETION_LIST __constant_cpu_to_le32(0x40000030) -#define STATUS_SYSTEM_POWERSTATE_COMPLEX_TRANSITION __constant_cpu_to_le32(0x40000031) -#define STATUS_ACCESS_AUDIT_BY_POLICY __constant_cpu_to_le32(0x40000032) -#define STATUS_ABANDON_HIBERFILE __constant_cpu_to_le32(0x40000033) -#define STATUS_BIZRULES_NOT_ENABLED __constant_cpu_to_le32(0x40000034) -#define STATUS_WAKE_SYSTEM __constant_cpu_to_le32(0x40000294) -#define STATUS_DS_SHUTTING_DOWN __constant_cpu_to_le32(0x40000370) -#define DBG_REPLY_LATER __constant_cpu_to_le32(0x40010001) -#define DBG_UNABLE_TO_PROVIDE_HANDLE __constant_cpu_to_le32(0x40010002) -#define DBG_TERMINATE_THREAD __constant_cpu_to_le32(0x40010003) -#define DBG_TERMINATE_PROCESS __constant_cpu_to_le32(0x40010004) -#define DBG_CONTROL_C __constant_cpu_to_le32(0x40010005) -#define DBG_PRINTEXCEPTION_C __constant_cpu_to_le32(0x40010006) -#define DBG_RIPEXCEPTION __constant_cpu_to_le32(0x40010007) -#define DBG_CONTROL_BREAK __constant_cpu_to_le32(0x40010008) -#define DBG_COMMAND_EXCEPTION __constant_cpu_to_le32(0x40010009) -#define RPC_NT_UUID_LOCAL_ONLY __constant_cpu_to_le32(0x40020056) -#define RPC_NT_SEND_INCOMPLETE __constant_cpu_to_le32(0x400200AF) -#define STATUS_CTX_CDM_CONNECT __constant_cpu_to_le32(0x400A0004) -#define STATUS_CTX_CDM_DISCONNECT __constant_cpu_to_le32(0x400A0005) -#define STATUS_SXS_RELEASE_ACTIVATION_CONTEXT __constant_cpu_to_le32(0x4015000D) -#define STATUS_RECOVERY_NOT_NEEDED __constant_cpu_to_le32(0x40190034) -#define STATUS_RM_ALREADY_STARTED __constant_cpu_to_le32(0x40190035) -#define STATUS_LOG_NO_RESTART __constant_cpu_to_le32(0x401A000C) -#define STATUS_VIDEO_DRIVER_DEBUG_REPORT_REQUEST __constant_cpu_to_le32(0x401B00EC) -#define STATUS_GRAPHICS_PARTIAL_DATA_POPULATED __constant_cpu_to_le32(0x401E000A) -#define STATUS_GRAPHICS_DRIVER_MISMATCH __constant_cpu_to_le32(0x401E0117) -#define STATUS_GRAPHICS_MODE_NOT_PINNED __constant_cpu_to_le32(0x401E0307) -#define STATUS_GRAPHICS_NO_PREFERRED_MODE __constant_cpu_to_le32(0x401E031E) -#define STATUS_GRAPHICS_DATASET_IS_EMPTY __constant_cpu_to_le32(0x401E034B) -#define STATUS_GRAPHICS_NO_MORE_ELEMENTS_IN_DATASET __constant_cpu_to_le32(0x401E034C) -#define STATUS_GRAPHICS_PATH_CONTENT_GEOMETRY_TRANSFORMATION_NOT_PINNED __constant_cpu_to_le32(0x401E0351) -#define STATUS_GRAPHICS_UNKNOWN_CHILD_STATUS __constant_cpu_to_le32(0x401E042F) -#define STATUS_GRAPHICS_LEADLINK_START_DEFERRED __constant_cpu_to_le32(0x401E0437) -#define STATUS_GRAPHICS_POLLING_TOO_FREQUENTLY __constant_cpu_to_le32(0x401E0439) -#define STATUS_GRAPHICS_START_DEFERRED __constant_cpu_to_le32(0x401E043A) -#define STATUS_NDIS_INDICATION_REQUIRED __constant_cpu_to_le32(0x40230001) -#define STATUS_GUARD_PAGE_VIOLATION __constant_cpu_to_le32(0x80000001) -#define STATUS_DATATYPE_MISALIGNMENT __constant_cpu_to_le32(0x80000002) -#define STATUS_BREAKPOINT __constant_cpu_to_le32(0x80000003) -#define STATUS_SINGLE_STEP __constant_cpu_to_le32(0x80000004) -#define STATUS_BUFFER_OVERFLOW __constant_cpu_to_le32(0x80000005) -#define STATUS_NO_MORE_FILES __constant_cpu_to_le32(0x80000006) -#define STATUS_WAKE_SYSTEM_DEBUGGER __constant_cpu_to_le32(0x80000007) -#define STATUS_HANDLES_CLOSED __constant_cpu_to_le32(0x8000000A) -#define STATUS_NO_INHERITANCE __constant_cpu_to_le32(0x8000000B) -#define STATUS_GUID_SUBSTITUTION_MADE __constant_cpu_to_le32(0x8000000C) -#define STATUS_PARTIAL_COPY __constant_cpu_to_le32(0x8000000D) -#define STATUS_DEVICE_PAPER_EMPTY __constant_cpu_to_le32(0x8000000E) -#define STATUS_DEVICE_POWERED_OFF __constant_cpu_to_le32(0x8000000F) -#define STATUS_DEVICE_OFF_LINE __constant_cpu_to_le32(0x80000010) -#define STATUS_DEVICE_BUSY __constant_cpu_to_le32(0x80000011) -#define STATUS_NO_MORE_EAS __constant_cpu_to_le32(0x80000012) -#define STATUS_INVALID_EA_NAME __constant_cpu_to_le32(0x80000013) -#define STATUS_EA_LIST_INCONSISTENT __constant_cpu_to_le32(0x80000014) -#define STATUS_INVALID_EA_FLAG __constant_cpu_to_le32(0x80000015) -#define STATUS_VERIFY_REQUIRED __constant_cpu_to_le32(0x80000016) -#define STATUS_EXTRANEOUS_INFORMATION __constant_cpu_to_le32(0x80000017) -#define STATUS_RXACT_COMMIT_NECESSARY __constant_cpu_to_le32(0x80000018) -#define STATUS_NO_MORE_ENTRIES __constant_cpu_to_le32(0x8000001A) -#define STATUS_FILEMARK_DETECTED __constant_cpu_to_le32(0x8000001B) -#define STATUS_MEDIA_CHANGED __constant_cpu_to_le32(0x8000001C) -#define STATUS_BUS_RESET __constant_cpu_to_le32(0x8000001D) -#define STATUS_END_OF_MEDIA __constant_cpu_to_le32(0x8000001E) -#define STATUS_BEGINNING_OF_MEDIA __constant_cpu_to_le32(0x8000001F) -#define STATUS_MEDIA_CHECK __constant_cpu_to_le32(0x80000020) -#define STATUS_SETMARK_DETECTED __constant_cpu_to_le32(0x80000021) -#define STATUS_NO_DATA_DETECTED __constant_cpu_to_le32(0x80000022) -#define STATUS_REDIRECTOR_HAS_OPEN_HANDLES __constant_cpu_to_le32(0x80000023) -#define STATUS_SERVER_HAS_OPEN_HANDLES __constant_cpu_to_le32(0x80000024) -#define STATUS_ALREADY_DISCONNECTED __constant_cpu_to_le32(0x80000025) -#define STATUS_LONGJUMP __constant_cpu_to_le32(0x80000026) -#define STATUS_CLEANER_CARTRIDGE_INSTALLED __constant_cpu_to_le32(0x80000027) -#define STATUS_PLUGPLAY_QUERY_VETOED __constant_cpu_to_le32(0x80000028) -#define STATUS_UNWIND_CONSOLIDATE __constant_cpu_to_le32(0x80000029) -#define STATUS_REGISTRY_HIVE_RECOVERED __constant_cpu_to_le32(0x8000002A) -#define STATUS_DLL_MIGHT_BE_INSECURE __constant_cpu_to_le32(0x8000002B) -#define STATUS_DLL_MIGHT_BE_INCOMPATIBLE __constant_cpu_to_le32(0x8000002C) -#define STATUS_STOPPED_ON_SYMLINK __constant_cpu_to_le32(0x8000002D) -#define STATUS_DEVICE_REQUIRES_CLEANING __constant_cpu_to_le32(0x80000288) -#define STATUS_DEVICE_DOOR_OPEN __constant_cpu_to_le32(0x80000289) -#define STATUS_DATA_LOST_REPAIR __constant_cpu_to_le32(0x80000803) -#define DBG_EXCEPTION_NOT_HANDLED __constant_cpu_to_le32(0x80010001) -#define STATUS_CLUSTER_NODE_ALREADY_UP __constant_cpu_to_le32(0x80130001) -#define STATUS_CLUSTER_NODE_ALREADY_DOWN __constant_cpu_to_le32(0x80130002) -#define STATUS_CLUSTER_NETWORK_ALREADY_ONLINE __constant_cpu_to_le32(0x80130003) -#define STATUS_CLUSTER_NETWORK_ALREADY_OFFLINE __constant_cpu_to_le32(0x80130004) -#define STATUS_CLUSTER_NODE_ALREADY_MEMBER __constant_cpu_to_le32(0x80130005) -#define STATUS_COULD_NOT_RESIZE_LOG __constant_cpu_to_le32(0x80190009) -#define STATUS_NO_TXF_METADATA __constant_cpu_to_le32(0x80190029) -#define STATUS_CANT_RECOVER_WITH_HANDLE_OPEN __constant_cpu_to_le32(0x80190031) -#define STATUS_TXF_METADATA_ALREADY_PRESENT __constant_cpu_to_le32(0x80190041) -#define STATUS_TRANSACTION_SCOPE_CALLBACKS_NOT_SET __constant_cpu_to_le32(0x80190042) -#define STATUS_VIDEO_HUNG_DISPLAY_DRIVER_THREAD_RECOVERED __constant_cpu_to_le32(0x801B00EB) -#define STATUS_FLT_BUFFER_TOO_SMALL __constant_cpu_to_le32(0x801C0001) -#define STATUS_FVE_PARTIAL_METADATA __constant_cpu_to_le32(0x80210001) -#define STATUS_UNSUCCESSFUL __constant_cpu_to_le32(0xC0000001) -#define STATUS_NOT_IMPLEMENTED __constant_cpu_to_le32(0xC0000002) -#define STATUS_INVALID_INFO_CLASS __constant_cpu_to_le32(0xC0000003) -#define STATUS_INFO_LENGTH_MISMATCH __constant_cpu_to_le32(0xC0000004) -#define STATUS_ACCESS_VIOLATION __constant_cpu_to_le32(0xC0000005) -#define STATUS_IN_PAGE_ERROR __constant_cpu_to_le32(0xC0000006) -#define STATUS_PAGEFILE_QUOTA __constant_cpu_to_le32(0xC0000007) -#define STATUS_INVALID_HANDLE __constant_cpu_to_le32(0xC0000008) -#define STATUS_BAD_INITIAL_STACK __constant_cpu_to_le32(0xC0000009) -#define STATUS_BAD_INITIAL_PC __constant_cpu_to_le32(0xC000000A) -#define STATUS_INVALID_CID __constant_cpu_to_le32(0xC000000B) -#define STATUS_TIMER_NOT_CANCELED __constant_cpu_to_le32(0xC000000C) -#define STATUS_INVALID_PARAMETER __constant_cpu_to_le32(0xC000000D) -#define STATUS_NO_SUCH_DEVICE __constant_cpu_to_le32(0xC000000E) -#define STATUS_NO_SUCH_FILE __constant_cpu_to_le32(0xC000000F) -#define STATUS_INVALID_DEVICE_REQUEST __constant_cpu_to_le32(0xC0000010) -#define STATUS_END_OF_FILE __constant_cpu_to_le32(0xC0000011) -#define STATUS_WRONG_VOLUME __constant_cpu_to_le32(0xC0000012) -#define STATUS_NO_MEDIA_IN_DEVICE __constant_cpu_to_le32(0xC0000013) -#define STATUS_UNRECOGNIZED_MEDIA __constant_cpu_to_le32(0xC0000014) -#define STATUS_NONEXISTENT_SECTOR __constant_cpu_to_le32(0xC0000015) -#define STATUS_MORE_PROCESSING_REQUIRED __constant_cpu_to_le32(0xC0000016) -#define STATUS_NO_MEMORY __constant_cpu_to_le32(0xC0000017) -#define STATUS_CONFLICTING_ADDRESSES __constant_cpu_to_le32(0xC0000018) -#define STATUS_NOT_MAPPED_VIEW __constant_cpu_to_le32(0xC0000019) -#define STATUS_UNABLE_TO_FREE_VM __constant_cpu_to_le32(0xC000001A) -#define STATUS_UNABLE_TO_DELETE_SECTION __constant_cpu_to_le32(0xC000001B) -#define STATUS_INVALID_SYSTEM_SERVICE __constant_cpu_to_le32(0xC000001C) -#define STATUS_ILLEGAL_INSTRUCTION __constant_cpu_to_le32(0xC000001D) -#define STATUS_INVALID_LOCK_SEQUENCE __constant_cpu_to_le32(0xC000001E) -#define STATUS_INVALID_VIEW_SIZE __constant_cpu_to_le32(0xC000001F) -#define STATUS_INVALID_FILE_FOR_SECTION __constant_cpu_to_le32(0xC0000020) -#define STATUS_ALREADY_COMMITTED __constant_cpu_to_le32(0xC0000021) -#define STATUS_ACCESS_DENIED __constant_cpu_to_le32(0xC0000022) -#define STATUS_BUFFER_TOO_SMALL __constant_cpu_to_le32(0xC0000023) -#define STATUS_OBJECT_TYPE_MISMATCH __constant_cpu_to_le32(0xC0000024) -#define STATUS_NONCONTINUABLE_EXCEPTION __constant_cpu_to_le32(0xC0000025) -#define STATUS_INVALID_DISPOSITION __constant_cpu_to_le32(0xC0000026) -#define STATUS_UNWIND __constant_cpu_to_le32(0xC0000027) -#define STATUS_BAD_STACK __constant_cpu_to_le32(0xC0000028) -#define STATUS_INVALID_UNWIND_TARGET __constant_cpu_to_le32(0xC0000029) -#define STATUS_NOT_LOCKED __constant_cpu_to_le32(0xC000002A) -#define STATUS_PARITY_ERROR __constant_cpu_to_le32(0xC000002B) -#define STATUS_UNABLE_TO_DECOMMIT_VM __constant_cpu_to_le32(0xC000002C) -#define STATUS_NOT_COMMITTED __constant_cpu_to_le32(0xC000002D) -#define STATUS_INVALID_PORT_ATTRIBUTES __constant_cpu_to_le32(0xC000002E) -#define STATUS_PORT_MESSAGE_TOO_LONG __constant_cpu_to_le32(0xC000002F) -#define STATUS_INVALID_PARAMETER_MIX __constant_cpu_to_le32(0xC0000030) -#define STATUS_INVALID_QUOTA_LOWER __constant_cpu_to_le32(0xC0000031) -#define STATUS_DISK_CORRUPT_ERROR __constant_cpu_to_le32(0xC0000032) -#define STATUS_OBJECT_NAME_INVALID __constant_cpu_to_le32(0xC0000033) -#define STATUS_OBJECT_NAME_NOT_FOUND __constant_cpu_to_le32(0xC0000034) -#define STATUS_OBJECT_NAME_COLLISION __constant_cpu_to_le32(0xC0000035) -#define STATUS_PORT_DISCONNECTED __constant_cpu_to_le32(0xC0000037) -#define STATUS_DEVICE_ALREADY_ATTACHED __constant_cpu_to_le32(0xC0000038) -#define STATUS_OBJECT_PATH_INVALID __constant_cpu_to_le32(0xC0000039) -#define STATUS_OBJECT_PATH_NOT_FOUND __constant_cpu_to_le32(0xC000003A) -#define STATUS_OBJECT_PATH_SYNTAX_BAD __constant_cpu_to_le32(0xC000003B) -#define STATUS_DATA_OVERRUN __constant_cpu_to_le32(0xC000003C) -#define STATUS_DATA_LATE_ERROR __constant_cpu_to_le32(0xC000003D) -#define STATUS_DATA_ERROR __constant_cpu_to_le32(0xC000003E) -#define STATUS_CRC_ERROR __constant_cpu_to_le32(0xC000003F) -#define STATUS_SECTION_TOO_BIG __constant_cpu_to_le32(0xC0000040) -#define STATUS_PORT_CONNECTION_REFUSED __constant_cpu_to_le32(0xC0000041) -#define STATUS_INVALID_PORT_HANDLE __constant_cpu_to_le32(0xC0000042) -#define STATUS_SHARING_VIOLATION __constant_cpu_to_le32(0xC0000043) -#define STATUS_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC0000044) -#define STATUS_INVALID_PAGE_PROTECTION __constant_cpu_to_le32(0xC0000045) -#define STATUS_MUTANT_NOT_OWNED __constant_cpu_to_le32(0xC0000046) -#define STATUS_SEMAPHORE_LIMIT_EXCEEDED __constant_cpu_to_le32(0xC0000047) -#define STATUS_PORT_ALREADY_SET __constant_cpu_to_le32(0xC0000048) -#define STATUS_SECTION_NOT_IMAGE __constant_cpu_to_le32(0xC0000049) -#define STATUS_SUSPEND_COUNT_EXCEEDED __constant_cpu_to_le32(0xC000004A) -#define STATUS_THREAD_IS_TERMINATING __constant_cpu_to_le32(0xC000004B) -#define STATUS_BAD_WORKING_SET_LIMIT __constant_cpu_to_le32(0xC000004C) -#define STATUS_INCOMPATIBLE_FILE_MAP __constant_cpu_to_le32(0xC000004D) -#define STATUS_SECTION_PROTECTION __constant_cpu_to_le32(0xC000004E) -#define STATUS_EAS_NOT_SUPPORTED __constant_cpu_to_le32(0xC000004F) -#define STATUS_EA_TOO_LARGE __constant_cpu_to_le32(0xC0000050) -#define STATUS_NONEXISTENT_EA_ENTRY __constant_cpu_to_le32(0xC0000051) -#define STATUS_NO_EAS_ON_FILE __constant_cpu_to_le32(0xC0000052) -#define STATUS_EA_CORRUPT_ERROR __constant_cpu_to_le32(0xC0000053) -#define STATUS_FILE_LOCK_CONFLICT __constant_cpu_to_le32(0xC0000054) -#define STATUS_LOCK_NOT_GRANTED __constant_cpu_to_le32(0xC0000055) -#define STATUS_DELETE_PENDING __constant_cpu_to_le32(0xC0000056) -#define STATUS_CTL_FILE_NOT_SUPPORTED __constant_cpu_to_le32(0xC0000057) -#define STATUS_UNKNOWN_REVISION __constant_cpu_to_le32(0xC0000058) -#define STATUS_REVISION_MISMATCH __constant_cpu_to_le32(0xC0000059) -#define STATUS_INVALID_OWNER __constant_cpu_to_le32(0xC000005A) -#define STATUS_INVALID_PRIMARY_GROUP __constant_cpu_to_le32(0xC000005B) -#define STATUS_NO_IMPERSONATION_TOKEN __constant_cpu_to_le32(0xC000005C) -#define STATUS_CANT_DISABLE_MANDATORY __constant_cpu_to_le32(0xC000005D) -#define STATUS_NO_LOGON_SERVERS __constant_cpu_to_le32(0xC000005E) -#define STATUS_NO_SUCH_LOGON_SESSION __constant_cpu_to_le32(0xC000005F) -#define STATUS_NO_SUCH_PRIVILEGE __constant_cpu_to_le32(0xC0000060) -#define STATUS_PRIVILEGE_NOT_HELD __constant_cpu_to_le32(0xC0000061) -#define STATUS_INVALID_ACCOUNT_NAME __constant_cpu_to_le32(0xC0000062) -#define STATUS_USER_EXISTS __constant_cpu_to_le32(0xC0000063) -#define STATUS_NO_SUCH_USER __constant_cpu_to_le32(0xC0000064) -#define STATUS_GROUP_EXISTS __constant_cpu_to_le32(0xC0000065) -#define STATUS_NO_SUCH_GROUP __constant_cpu_to_le32(0xC0000066) -#define STATUS_MEMBER_IN_GROUP __constant_cpu_to_le32(0xC0000067) -#define STATUS_MEMBER_NOT_IN_GROUP __constant_cpu_to_le32(0xC0000068) -#define STATUS_LAST_ADMIN __constant_cpu_to_le32(0xC0000069) -#define STATUS_WRONG_PASSWORD __constant_cpu_to_le32(0xC000006A) -#define STATUS_ILL_FORMED_PASSWORD __constant_cpu_to_le32(0xC000006B) -#define STATUS_PASSWORD_RESTRICTION __constant_cpu_to_le32(0xC000006C) -#define STATUS_LOGON_FAILURE __constant_cpu_to_le32(0xC000006D) -#define STATUS_ACCOUNT_RESTRICTION __constant_cpu_to_le32(0xC000006E) -#define STATUS_INVALID_LOGON_HOURS __constant_cpu_to_le32(0xC000006F) -#define STATUS_INVALID_WORKSTATION __constant_cpu_to_le32(0xC0000070) -#define STATUS_PASSWORD_EXPIRED __constant_cpu_to_le32(0xC0000071) -#define STATUS_ACCOUNT_DISABLED __constant_cpu_to_le32(0xC0000072) -#define STATUS_NONE_MAPPED __constant_cpu_to_le32(0xC0000073) -#define STATUS_TOO_MANY_LUIDS_REQUESTED __constant_cpu_to_le32(0xC0000074) -#define STATUS_LUIDS_EXHAUSTED __constant_cpu_to_le32(0xC0000075) -#define STATUS_INVALID_SUB_AUTHORITY __constant_cpu_to_le32(0xC0000076) -#define STATUS_INVALID_ACL __constant_cpu_to_le32(0xC0000077) -#define STATUS_INVALID_SID __constant_cpu_to_le32(0xC0000078) -#define STATUS_INVALID_SECURITY_DESCR __constant_cpu_to_le32(0xC0000079) -#define STATUS_PROCEDURE_NOT_FOUND __constant_cpu_to_le32(0xC000007A) -#define STATUS_INVALID_IMAGE_FORMAT __constant_cpu_to_le32(0xC000007B) -#define STATUS_NO_TOKEN __constant_cpu_to_le32(0xC000007C) -#define STATUS_BAD_INHERITANCE_ACL __constant_cpu_to_le32(0xC000007D) -#define STATUS_RANGE_NOT_LOCKED __constant_cpu_to_le32(0xC000007E) -#define STATUS_DISK_FULL __constant_cpu_to_le32(0xC000007F) -#define STATUS_SERVER_DISABLED __constant_cpu_to_le32(0xC0000080) -#define STATUS_SERVER_NOT_DISABLED __constant_cpu_to_le32(0xC0000081) -#define STATUS_TOO_MANY_GUIDS_REQUESTED __constant_cpu_to_le32(0xC0000082) -#define STATUS_GUIDS_EXHAUSTED __constant_cpu_to_le32(0xC0000083) -#define STATUS_INVALID_ID_AUTHORITY __constant_cpu_to_le32(0xC0000084) -#define STATUS_AGENTS_EXHAUSTED __constant_cpu_to_le32(0xC0000085) -#define STATUS_INVALID_VOLUME_LABEL __constant_cpu_to_le32(0xC0000086) -#define STATUS_SECTION_NOT_EXTENDED __constant_cpu_to_le32(0xC0000087) -#define STATUS_NOT_MAPPED_DATA __constant_cpu_to_le32(0xC0000088) -#define STATUS_RESOURCE_DATA_NOT_FOUND __constant_cpu_to_le32(0xC0000089) -#define STATUS_RESOURCE_TYPE_NOT_FOUND __constant_cpu_to_le32(0xC000008A) -#define STATUS_RESOURCE_NAME_NOT_FOUND __constant_cpu_to_le32(0xC000008B) -#define STATUS_ARRAY_BOUNDS_EXCEEDED __constant_cpu_to_le32(0xC000008C) -#define STATUS_FLOAT_DENORMAL_OPERAND __constant_cpu_to_le32(0xC000008D) -#define STATUS_FLOAT_DIVIDE_BY_ZERO __constant_cpu_to_le32(0xC000008E) -#define STATUS_FLOAT_INEXACT_RESULT __constant_cpu_to_le32(0xC000008F) -#define STATUS_FLOAT_INVALID_OPERATION __constant_cpu_to_le32(0xC0000090) -#define STATUS_FLOAT_OVERFLOW __constant_cpu_to_le32(0xC0000091) -#define STATUS_FLOAT_STACK_CHECK __constant_cpu_to_le32(0xC0000092) -#define STATUS_FLOAT_UNDERFLOW __constant_cpu_to_le32(0xC0000093) -#define STATUS_INTEGER_DIVIDE_BY_ZERO __constant_cpu_to_le32(0xC0000094) -#define STATUS_INTEGER_OVERFLOW __constant_cpu_to_le32(0xC0000095) -#define STATUS_PRIVILEGED_INSTRUCTION __constant_cpu_to_le32(0xC0000096) -#define STATUS_TOO_MANY_PAGING_FILES __constant_cpu_to_le32(0xC0000097) -#define STATUS_FILE_INVALID __constant_cpu_to_le32(0xC0000098) -#define STATUS_ALLOTTED_SPACE_EXCEEDED __constant_cpu_to_le32(0xC0000099) -#define STATUS_INSUFFICIENT_RESOURCES __constant_cpu_to_le32(0xC000009A) -#define STATUS_DFS_EXIT_PATH_FOUND __constant_cpu_to_le32(0xC000009B) -#define STATUS_DEVICE_DATA_ERROR __constant_cpu_to_le32(0xC000009C) -#define STATUS_DEVICE_NOT_CONNECTED __constant_cpu_to_le32(0xC000009D) -#define STATUS_DEVICE_POWER_FAILURE __constant_cpu_to_le32(0xC000009E) -#define STATUS_FREE_VM_NOT_AT_BASE __constant_cpu_to_le32(0xC000009F) -#define STATUS_MEMORY_NOT_ALLOCATED __constant_cpu_to_le32(0xC00000A0) -#define STATUS_WORKING_SET_QUOTA __constant_cpu_to_le32(0xC00000A1) -#define STATUS_MEDIA_WRITE_PROTECTED __constant_cpu_to_le32(0xC00000A2) -#define STATUS_DEVICE_NOT_READY __constant_cpu_to_le32(0xC00000A3) -#define STATUS_INVALID_GROUP_ATTRIBUTES __constant_cpu_to_le32(0xC00000A4) -#define STATUS_BAD_IMPERSONATION_LEVEL __constant_cpu_to_le32(0xC00000A5) -#define STATUS_CANT_OPEN_ANONYMOUS __constant_cpu_to_le32(0xC00000A6) -#define STATUS_BAD_VALIDATION_CLASS __constant_cpu_to_le32(0xC00000A7) -#define STATUS_BAD_TOKEN_TYPE __constant_cpu_to_le32(0xC00000A8) -#define STATUS_BAD_MASTER_BOOT_RECORD __constant_cpu_to_le32(0xC00000A9) -#define STATUS_INSTRUCTION_MISALIGNMENT __constant_cpu_to_le32(0xC00000AA) -#define STATUS_INSTANCE_NOT_AVAILABLE __constant_cpu_to_le32(0xC00000AB) -#define STATUS_PIPE_NOT_AVAILABLE __constant_cpu_to_le32(0xC00000AC) -#define STATUS_INVALID_PIPE_STATE __constant_cpu_to_le32(0xC00000AD) -#define STATUS_PIPE_BUSY __constant_cpu_to_le32(0xC00000AE) -#define STATUS_ILLEGAL_FUNCTION __constant_cpu_to_le32(0xC00000AF) -#define STATUS_PIPE_DISCONNECTED __constant_cpu_to_le32(0xC00000B0) -#define STATUS_PIPE_CLOSING __constant_cpu_to_le32(0xC00000B1) -#define STATUS_PIPE_CONNECTED __constant_cpu_to_le32(0xC00000B2) -#define STATUS_PIPE_LISTENING __constant_cpu_to_le32(0xC00000B3) -#define STATUS_INVALID_READ_MODE __constant_cpu_to_le32(0xC00000B4) -#define STATUS_IO_TIMEOUT __constant_cpu_to_le32(0xC00000B5) -#define STATUS_FILE_FORCED_CLOSED __constant_cpu_to_le32(0xC00000B6) -#define STATUS_PROFILING_NOT_STARTED __constant_cpu_to_le32(0xC00000B7) -#define STATUS_PROFILING_NOT_STOPPED __constant_cpu_to_le32(0xC00000B8) -#define STATUS_COULD_NOT_INTERPRET __constant_cpu_to_le32(0xC00000B9) -#define STATUS_FILE_IS_A_DIRECTORY __constant_cpu_to_le32(0xC00000BA) -#define STATUS_NOT_SUPPORTED __constant_cpu_to_le32(0xC00000BB) -#define STATUS_REMOTE_NOT_LISTENING __constant_cpu_to_le32(0xC00000BC) -#define STATUS_DUPLICATE_NAME __constant_cpu_to_le32(0xC00000BD) -#define STATUS_BAD_NETWORK_PATH __constant_cpu_to_le32(0xC00000BE) -#define STATUS_NETWORK_BUSY __constant_cpu_to_le32(0xC00000BF) -#define STATUS_DEVICE_DOES_NOT_EXIST __constant_cpu_to_le32(0xC00000C0) -#define STATUS_TOO_MANY_COMMANDS __constant_cpu_to_le32(0xC00000C1) -#define STATUS_ADAPTER_HARDWARE_ERROR __constant_cpu_to_le32(0xC00000C2) -#define STATUS_INVALID_NETWORK_RESPONSE __constant_cpu_to_le32(0xC00000C3) -#define STATUS_UNEXPECTED_NETWORK_ERROR __constant_cpu_to_le32(0xC00000C4) -#define STATUS_BAD_REMOTE_ADAPTER __constant_cpu_to_le32(0xC00000C5) -#define STATUS_PRINT_QUEUE_FULL __constant_cpu_to_le32(0xC00000C6) -#define STATUS_NO_SPOOL_SPACE __constant_cpu_to_le32(0xC00000C7) -#define STATUS_PRINT_CANCELLED __constant_cpu_to_le32(0xC00000C8) -#define STATUS_NETWORK_NAME_DELETED __constant_cpu_to_le32(0xC00000C9) -#define STATUS_NETWORK_ACCESS_DENIED __constant_cpu_to_le32(0xC00000CA) -#define STATUS_BAD_DEVICE_TYPE __constant_cpu_to_le32(0xC00000CB) -#define STATUS_BAD_NETWORK_NAME __constant_cpu_to_le32(0xC00000CC) -#define STATUS_TOO_MANY_NAMES __constant_cpu_to_le32(0xC00000CD) -#define STATUS_TOO_MANY_SESSIONS __constant_cpu_to_le32(0xC00000CE) -#define STATUS_SHARING_PAUSED __constant_cpu_to_le32(0xC00000CF) -#define STATUS_REQUEST_NOT_ACCEPTED __constant_cpu_to_le32(0xC00000D0) -#define STATUS_REDIRECTOR_PAUSED __constant_cpu_to_le32(0xC00000D1) -#define STATUS_NET_WRITE_FAULT __constant_cpu_to_le32(0xC00000D2) -#define STATUS_PROFILING_AT_LIMIT __constant_cpu_to_le32(0xC00000D3) -#define STATUS_NOT_SAME_DEVICE __constant_cpu_to_le32(0xC00000D4) -#define STATUS_FILE_RENAMED __constant_cpu_to_le32(0xC00000D5) -#define STATUS_VIRTUAL_CIRCUIT_CLOSED __constant_cpu_to_le32(0xC00000D6) -#define STATUS_NO_SECURITY_ON_OBJECT __constant_cpu_to_le32(0xC00000D7) -#define STATUS_CANT_WAIT __constant_cpu_to_le32(0xC00000D8) -#define STATUS_PIPE_EMPTY __constant_cpu_to_le32(0xC00000D9) -#define STATUS_CANT_ACCESS_DOMAIN_INFO __constant_cpu_to_le32(0xC00000DA) -#define STATUS_CANT_TERMINATE_SELF __constant_cpu_to_le32(0xC00000DB) -#define STATUS_INVALID_SERVER_STATE __constant_cpu_to_le32(0xC00000DC) -#define STATUS_INVALID_DOMAIN_STATE __constant_cpu_to_le32(0xC00000DD) -#define STATUS_INVALID_DOMAIN_ROLE __constant_cpu_to_le32(0xC00000DE) -#define STATUS_NO_SUCH_DOMAIN __constant_cpu_to_le32(0xC00000DF) -#define STATUS_DOMAIN_EXISTS __constant_cpu_to_le32(0xC00000E0) -#define STATUS_DOMAIN_LIMIT_EXCEEDED __constant_cpu_to_le32(0xC00000E1) -#define STATUS_OPLOCK_NOT_GRANTED __constant_cpu_to_le32(0xC00000E2) -#define STATUS_INVALID_OPLOCK_PROTOCOL __constant_cpu_to_le32(0xC00000E3) -#define STATUS_INTERNAL_DB_CORRUPTION __constant_cpu_to_le32(0xC00000E4) -#define STATUS_INTERNAL_ERROR __constant_cpu_to_le32(0xC00000E5) -#define STATUS_GENERIC_NOT_MAPPED __constant_cpu_to_le32(0xC00000E6) -#define STATUS_BAD_DESCRIPTOR_FORMAT __constant_cpu_to_le32(0xC00000E7) -#define STATUS_INVALID_USER_BUFFER __constant_cpu_to_le32(0xC00000E8) -#define STATUS_UNEXPECTED_IO_ERROR __constant_cpu_to_le32(0xC00000E9) -#define STATUS_UNEXPECTED_MM_CREATE_ERR __constant_cpu_to_le32(0xC00000EA) -#define STATUS_UNEXPECTED_MM_MAP_ERROR __constant_cpu_to_le32(0xC00000EB) -#define STATUS_UNEXPECTED_MM_EXTEND_ERR __constant_cpu_to_le32(0xC00000EC) -#define STATUS_NOT_LOGON_PROCESS __constant_cpu_to_le32(0xC00000ED) -#define STATUS_LOGON_SESSION_EXISTS __constant_cpu_to_le32(0xC00000EE) -#define STATUS_INVALID_PARAMETER_1 __constant_cpu_to_le32(0xC00000EF) -#define STATUS_INVALID_PARAMETER_2 __constant_cpu_to_le32(0xC00000F0) -#define STATUS_INVALID_PARAMETER_3 __constant_cpu_to_le32(0xC00000F1) -#define STATUS_INVALID_PARAMETER_4 __constant_cpu_to_le32(0xC00000F2) -#define STATUS_INVALID_PARAMETER_5 __constant_cpu_to_le32(0xC00000F3) -#define STATUS_INVALID_PARAMETER_6 __constant_cpu_to_le32(0xC00000F4) -#define STATUS_INVALID_PARAMETER_7 __constant_cpu_to_le32(0xC00000F5) -#define STATUS_INVALID_PARAMETER_8 __constant_cpu_to_le32(0xC00000F6) -#define STATUS_INVALID_PARAMETER_9 __constant_cpu_to_le32(0xC00000F7) -#define STATUS_INVALID_PARAMETER_10 __constant_cpu_to_le32(0xC00000F8) -#define STATUS_INVALID_PARAMETER_11 __constant_cpu_to_le32(0xC00000F9) -#define STATUS_INVALID_PARAMETER_12 __constant_cpu_to_le32(0xC00000FA) -#define STATUS_REDIRECTOR_NOT_STARTED __constant_cpu_to_le32(0xC00000FB) -#define STATUS_REDIRECTOR_STARTED __constant_cpu_to_le32(0xC00000FC) -#define STATUS_STACK_OVERFLOW __constant_cpu_to_le32(0xC00000FD) -#define STATUS_NO_SUCH_PACKAGE __constant_cpu_to_le32(0xC00000FE) -#define STATUS_BAD_FUNCTION_TABLE __constant_cpu_to_le32(0xC00000FF) -#define STATUS_VARIABLE_NOT_FOUND __constant_cpu_to_le32(0xC0000100) -#define STATUS_DIRECTORY_NOT_EMPTY __constant_cpu_to_le32(0xC0000101) -#define STATUS_FILE_CORRUPT_ERROR __constant_cpu_to_le32(0xC0000102) -#define STATUS_NOT_A_DIRECTORY __constant_cpu_to_le32(0xC0000103) -#define STATUS_BAD_LOGON_SESSION_STATE __constant_cpu_to_le32(0xC0000104) -#define STATUS_LOGON_SESSION_COLLISION __constant_cpu_to_le32(0xC0000105) -#define STATUS_NAME_TOO_LONG __constant_cpu_to_le32(0xC0000106) -#define STATUS_FILES_OPEN __constant_cpu_to_le32(0xC0000107) -#define STATUS_CONNECTION_IN_USE __constant_cpu_to_le32(0xC0000108) -#define STATUS_MESSAGE_NOT_FOUND __constant_cpu_to_le32(0xC0000109) -#define STATUS_PROCESS_IS_TERMINATING __constant_cpu_to_le32(0xC000010A) -#define STATUS_INVALID_LOGON_TYPE __constant_cpu_to_le32(0xC000010B) -#define STATUS_NO_GUID_TRANSLATION __constant_cpu_to_le32(0xC000010C) -#define STATUS_CANNOT_IMPERSONATE __constant_cpu_to_le32(0xC000010D) -#define STATUS_IMAGE_ALREADY_LOADED __constant_cpu_to_le32(0xC000010E) -#define STATUS_ABIOS_NOT_PRESENT __constant_cpu_to_le32(0xC000010F) -#define STATUS_ABIOS_LID_NOT_EXIST __constant_cpu_to_le32(0xC0000110) -#define STATUS_ABIOS_LID_ALREADY_OWNED __constant_cpu_to_le32(0xC0000111) -#define STATUS_ABIOS_NOT_LID_OWNER __constant_cpu_to_le32(0xC0000112) -#define STATUS_ABIOS_INVALID_COMMAND __constant_cpu_to_le32(0xC0000113) -#define STATUS_ABIOS_INVALID_LID __constant_cpu_to_le32(0xC0000114) -#define STATUS_ABIOS_SELECTOR_NOT_AVAILABLE __constant_cpu_to_le32(0xC0000115) -#define STATUS_ABIOS_INVALID_SELECTOR __constant_cpu_to_le32(0xC0000116) -#define STATUS_NO_LDT __constant_cpu_to_le32(0xC0000117) -#define STATUS_INVALID_LDT_SIZE __constant_cpu_to_le32(0xC0000118) -#define STATUS_INVALID_LDT_OFFSET __constant_cpu_to_le32(0xC0000119) -#define STATUS_INVALID_LDT_DESCRIPTOR __constant_cpu_to_le32(0xC000011A) -#define STATUS_INVALID_IMAGE_NE_FORMAT __constant_cpu_to_le32(0xC000011B) -#define STATUS_RXACT_INVALID_STATE __constant_cpu_to_le32(0xC000011C) -#define STATUS_RXACT_COMMIT_FAILURE __constant_cpu_to_le32(0xC000011D) -#define STATUS_MAPPED_FILE_SIZE_ZERO __constant_cpu_to_le32(0xC000011E) -#define STATUS_TOO_MANY_OPENED_FILES __constant_cpu_to_le32(0xC000011F) -#define STATUS_CANCELLED __constant_cpu_to_le32(0xC0000120) -#define STATUS_CANNOT_DELETE __constant_cpu_to_le32(0xC0000121) -#define STATUS_INVALID_COMPUTER_NAME __constant_cpu_to_le32(0xC0000122) -#define STATUS_FILE_DELETED __constant_cpu_to_le32(0xC0000123) -#define STATUS_SPECIAL_ACCOUNT __constant_cpu_to_le32(0xC0000124) -#define STATUS_SPECIAL_GROUP __constant_cpu_to_le32(0xC0000125) -#define STATUS_SPECIAL_USER __constant_cpu_to_le32(0xC0000126) -#define STATUS_MEMBERS_PRIMARY_GROUP __constant_cpu_to_le32(0xC0000127) -#define STATUS_FILE_CLOSED __constant_cpu_to_le32(0xC0000128) -#define STATUS_TOO_MANY_THREADS __constant_cpu_to_le32(0xC0000129) -#define STATUS_THREAD_NOT_IN_PROCESS __constant_cpu_to_le32(0xC000012A) -#define STATUS_TOKEN_ALREADY_IN_USE __constant_cpu_to_le32(0xC000012B) -#define STATUS_PAGEFILE_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC000012C) -#define STATUS_COMMITMENT_LIMIT __constant_cpu_to_le32(0xC000012D) -#define STATUS_INVALID_IMAGE_LE_FORMAT __constant_cpu_to_le32(0xC000012E) -#define STATUS_INVALID_IMAGE_NOT_MZ __constant_cpu_to_le32(0xC000012F) -#define STATUS_INVALID_IMAGE_PROTECT __constant_cpu_to_le32(0xC0000130) -#define STATUS_INVALID_IMAGE_WIN_16 __constant_cpu_to_le32(0xC0000131) -#define STATUS_LOGON_SERVER_CONFLICT __constant_cpu_to_le32(0xC0000132) -#define STATUS_TIME_DIFFERENCE_AT_DC __constant_cpu_to_le32(0xC0000133) -#define STATUS_SYNCHRONIZATION_REQUIRED __constant_cpu_to_le32(0xC0000134) -#define STATUS_DLL_NOT_FOUND __constant_cpu_to_le32(0xC0000135) -#define STATUS_OPEN_FAILED __constant_cpu_to_le32(0xC0000136) -#define STATUS_IO_PRIVILEGE_FAILED __constant_cpu_to_le32(0xC0000137) -#define STATUS_ORDINAL_NOT_FOUND __constant_cpu_to_le32(0xC0000138) -#define STATUS_ENTRYPOINT_NOT_FOUND __constant_cpu_to_le32(0xC0000139) -#define STATUS_CONTROL_C_EXIT __constant_cpu_to_le32(0xC000013A) -#define STATUS_LOCAL_DISCONNECT __constant_cpu_to_le32(0xC000013B) -#define STATUS_REMOTE_DISCONNECT __constant_cpu_to_le32(0xC000013C) -#define STATUS_REMOTE_RESOURCES __constant_cpu_to_le32(0xC000013D) -#define STATUS_LINK_FAILED __constant_cpu_to_le32(0xC000013E) -#define STATUS_LINK_TIMEOUT __constant_cpu_to_le32(0xC000013F) -#define STATUS_INVALID_CONNECTION __constant_cpu_to_le32(0xC0000140) -#define STATUS_INVALID_ADDRESS __constant_cpu_to_le32(0xC0000141) -#define STATUS_DLL_INIT_FAILED __constant_cpu_to_le32(0xC0000142) -#define STATUS_MISSING_SYSTEMFILE __constant_cpu_to_le32(0xC0000143) -#define STATUS_UNHANDLED_EXCEPTION __constant_cpu_to_le32(0xC0000144) -#define STATUS_APP_INIT_FAILURE __constant_cpu_to_le32(0xC0000145) -#define STATUS_PAGEFILE_CREATE_FAILED __constant_cpu_to_le32(0xC0000146) -#define STATUS_NO_PAGEFILE __constant_cpu_to_le32(0xC0000147) -#define STATUS_INVALID_LEVEL __constant_cpu_to_le32(0xC0000148) -#define STATUS_WRONG_PASSWORD_CORE __constant_cpu_to_le32(0xC0000149) -#define STATUS_ILLEGAL_FLOAT_CONTEXT __constant_cpu_to_le32(0xC000014A) -#define STATUS_PIPE_BROKEN __constant_cpu_to_le32(0xC000014B) -#define STATUS_REGISTRY_CORRUPT __constant_cpu_to_le32(0xC000014C) -#define STATUS_REGISTRY_IO_FAILED __constant_cpu_to_le32(0xC000014D) -#define STATUS_NO_EVENT_PAIR __constant_cpu_to_le32(0xC000014E) -#define STATUS_UNRECOGNIZED_VOLUME __constant_cpu_to_le32(0xC000014F) -#define STATUS_SERIAL_NO_DEVICE_INITED __constant_cpu_to_le32(0xC0000150) -#define STATUS_NO_SUCH_ALIAS __constant_cpu_to_le32(0xC0000151) -#define STATUS_MEMBER_NOT_IN_ALIAS __constant_cpu_to_le32(0xC0000152) -#define STATUS_MEMBER_IN_ALIAS __constant_cpu_to_le32(0xC0000153) -#define STATUS_ALIAS_EXISTS __constant_cpu_to_le32(0xC0000154) -#define STATUS_LOGON_NOT_GRANTED __constant_cpu_to_le32(0xC0000155) -#define STATUS_TOO_MANY_SECRETS __constant_cpu_to_le32(0xC0000156) -#define STATUS_SECRET_TOO_LONG __constant_cpu_to_le32(0xC0000157) -#define STATUS_INTERNAL_DB_ERROR __constant_cpu_to_le32(0xC0000158) -#define STATUS_FULLSCREEN_MODE __constant_cpu_to_le32(0xC0000159) -#define STATUS_TOO_MANY_CONTEXT_IDS __constant_cpu_to_le32(0xC000015A) -#define STATUS_LOGON_TYPE_NOT_GRANTED __constant_cpu_to_le32(0xC000015B) -#define STATUS_NOT_REGISTRY_FILE __constant_cpu_to_le32(0xC000015C) -#define STATUS_NT_CROSS_ENCRYPTION_REQUIRED __constant_cpu_to_le32(0xC000015D) -#define STATUS_DOMAIN_CTRLR_CONFIG_ERROR __constant_cpu_to_le32(0xC000015E) -#define STATUS_FT_MISSING_MEMBER __constant_cpu_to_le32(0xC000015F) -#define STATUS_ILL_FORMED_SERVICE_ENTRY __constant_cpu_to_le32(0xC0000160) -#define STATUS_ILLEGAL_CHARACTER __constant_cpu_to_le32(0xC0000161) -#define STATUS_UNMAPPABLE_CHARACTER __constant_cpu_to_le32(0xC0000162) -#define STATUS_UNDEFINED_CHARACTER __constant_cpu_to_le32(0xC0000163) -#define STATUS_FLOPPY_VOLUME __constant_cpu_to_le32(0xC0000164) -#define STATUS_FLOPPY_ID_MARK_NOT_FOUND __constant_cpu_to_le32(0xC0000165) -#define STATUS_FLOPPY_WRONG_CYLINDER __constant_cpu_to_le32(0xC0000166) -#define STATUS_FLOPPY_UNKNOWN_ERROR __constant_cpu_to_le32(0xC0000167) -#define STATUS_FLOPPY_BAD_REGISTERS __constant_cpu_to_le32(0xC0000168) -#define STATUS_DISK_RECALIBRATE_FAILED __constant_cpu_to_le32(0xC0000169) -#define STATUS_DISK_OPERATION_FAILED __constant_cpu_to_le32(0xC000016A) -#define STATUS_DISK_RESET_FAILED __constant_cpu_to_le32(0xC000016B) -#define STATUS_SHARED_IRQ_BUSY __constant_cpu_to_le32(0xC000016C) -#define STATUS_FT_ORPHANING __constant_cpu_to_le32(0xC000016D) -#define STATUS_BIOS_FAILED_TO_CONNECT_INTERRUPT __constant_cpu_to_le32(0xC000016E) -#define STATUS_PARTITION_FAILURE __constant_cpu_to_le32(0xC0000172) -#define STATUS_INVALID_BLOCK_LENGTH __constant_cpu_to_le32(0xC0000173) -#define STATUS_DEVICE_NOT_PARTITIONED __constant_cpu_to_le32(0xC0000174) -#define STATUS_UNABLE_TO_LOCK_MEDIA __constant_cpu_to_le32(0xC0000175) -#define STATUS_UNABLE_TO_UNLOAD_MEDIA __constant_cpu_to_le32(0xC0000176) -#define STATUS_EOM_OVERFLOW __constant_cpu_to_le32(0xC0000177) -#define STATUS_NO_MEDIA __constant_cpu_to_le32(0xC0000178) -#define STATUS_NO_SUCH_MEMBER __constant_cpu_to_le32(0xC000017A) -#define STATUS_INVALID_MEMBER __constant_cpu_to_le32(0xC000017B) -#define STATUS_KEY_DELETED __constant_cpu_to_le32(0xC000017C) -#define STATUS_NO_LOG_SPACE __constant_cpu_to_le32(0xC000017D) -#define STATUS_TOO_MANY_SIDS __constant_cpu_to_le32(0xC000017E) -#define STATUS_LM_CROSS_ENCRYPTION_REQUIRED __constant_cpu_to_le32(0xC000017F) -#define STATUS_KEY_HAS_CHILDREN __constant_cpu_to_le32(0xC0000180) -#define STATUS_CHILD_MUST_BE_VOLATILE __constant_cpu_to_le32(0xC0000181) -#define STATUS_DEVICE_CONFIGURATION_ERROR __constant_cpu_to_le32(0xC0000182) -#define STATUS_DRIVER_INTERNAL_ERROR __constant_cpu_to_le32(0xC0000183) -#define STATUS_INVALID_DEVICE_STATE __constant_cpu_to_le32(0xC0000184) -#define STATUS_IO_DEVICE_ERROR __constant_cpu_to_le32(0xC0000185) -#define STATUS_DEVICE_PROTOCOL_ERROR __constant_cpu_to_le32(0xC0000186) -#define STATUS_BACKUP_CONTROLLER __constant_cpu_to_le32(0xC0000187) -#define STATUS_LOG_FILE_FULL __constant_cpu_to_le32(0xC0000188) -#define STATUS_TOO_LATE __constant_cpu_to_le32(0xC0000189) -#define STATUS_NO_TRUST_LSA_SECRET __constant_cpu_to_le32(0xC000018A) -#define STATUS_NO_TRUST_SAM_ACCOUNT __constant_cpu_to_le32(0xC000018B) -#define STATUS_TRUSTED_DOMAIN_FAILURE __constant_cpu_to_le32(0xC000018C) -#define STATUS_TRUSTED_RELATIONSHIP_FAILURE __constant_cpu_to_le32(0xC000018D) -#define STATUS_EVENTLOG_FILE_CORRUPT __constant_cpu_to_le32(0xC000018E) -#define STATUS_EVENTLOG_CANT_START __constant_cpu_to_le32(0xC000018F) -#define STATUS_TRUST_FAILURE __constant_cpu_to_le32(0xC0000190) -#define STATUS_MUTANT_LIMIT_EXCEEDED __constant_cpu_to_le32(0xC0000191) -#define STATUS_NETLOGON_NOT_STARTED __constant_cpu_to_le32(0xC0000192) -#define STATUS_ACCOUNT_EXPIRED __constant_cpu_to_le32(0xC0000193) -#define STATUS_POSSIBLE_DEADLOCK __constant_cpu_to_le32(0xC0000194) -#define STATUS_NETWORK_CREDENTIAL_CONFLICT __constant_cpu_to_le32(0xC0000195) -#define STATUS_REMOTE_SESSION_LIMIT __constant_cpu_to_le32(0xC0000196) -#define STATUS_EVENTLOG_FILE_CHANGED __constant_cpu_to_le32(0xC0000197) -#define STATUS_NOLOGON_INTERDOMAIN_TRUST_ACCOUNT __constant_cpu_to_le32(0xC0000198) -#define STATUS_NOLOGON_WORKSTATION_TRUST_ACCOUNT __constant_cpu_to_le32(0xC0000199) -#define STATUS_NOLOGON_SERVER_TRUST_ACCOUNT __constant_cpu_to_le32(0xC000019A) -#define STATUS_DOMAIN_TRUST_INCONSISTENT __constant_cpu_to_le32(0xC000019B) -#define STATUS_FS_DRIVER_REQUIRED __constant_cpu_to_le32(0xC000019C) -#define STATUS_IMAGE_ALREADY_LOADED_AS_DLL __constant_cpu_to_le32(0xC000019D) -#define STATUS_NETWORK_OPEN_RESTRICTION __constant_cpu_to_le32(0xC0000201) -#define STATUS_NO_USER_SESSION_KEY __constant_cpu_to_le32(0xC0000202) -#define STATUS_USER_SESSION_DELETED __constant_cpu_to_le32(0xC0000203) -#define STATUS_RESOURCE_LANG_NOT_FOUND __constant_cpu_to_le32(0xC0000204) -#define STATUS_INSUFF_SERVER_RESOURCES __constant_cpu_to_le32(0xC0000205) -#define STATUS_INVALID_BUFFER_SIZE __constant_cpu_to_le32(0xC0000206) -#define STATUS_INVALID_ADDRESS_COMPONENT __constant_cpu_to_le32(0xC0000207) -#define STATUS_INVALID_ADDRESS_WILDCARD __constant_cpu_to_le32(0xC0000208) -#define STATUS_TOO_MANY_ADDRESSES __constant_cpu_to_le32(0xC0000209) -#define STATUS_ADDRESS_ALREADY_EXISTS __constant_cpu_to_le32(0xC000020A) -#define STATUS_ADDRESS_CLOSED __constant_cpu_to_le32(0xC000020B) -#define STATUS_CONNECTION_DISCONNECTED __constant_cpu_to_le32(0xC000020C) -#define STATUS_CONNECTION_RESET __constant_cpu_to_le32(0xC000020D) -#define STATUS_TOO_MANY_NODES __constant_cpu_to_le32(0xC000020E) -#define STATUS_TRANSACTION_ABORTED __constant_cpu_to_le32(0xC000020F) -#define STATUS_TRANSACTION_TIMED_OUT __constant_cpu_to_le32(0xC0000210) -#define STATUS_TRANSACTION_NO_RELEASE __constant_cpu_to_le32(0xC0000211) -#define STATUS_TRANSACTION_NO_MATCH __constant_cpu_to_le32(0xC0000212) -#define STATUS_TRANSACTION_RESPONDED __constant_cpu_to_le32(0xC0000213) -#define STATUS_TRANSACTION_INVALID_ID __constant_cpu_to_le32(0xC0000214) -#define STATUS_TRANSACTION_INVALID_TYPE __constant_cpu_to_le32(0xC0000215) -#define STATUS_NOT_SERVER_SESSION __constant_cpu_to_le32(0xC0000216) -#define STATUS_NOT_CLIENT_SESSION __constant_cpu_to_le32(0xC0000217) -#define STATUS_CANNOT_LOAD_REGISTRY_FILE __constant_cpu_to_le32(0xC0000218) -#define STATUS_DEBUG_ATTACH_FAILED __constant_cpu_to_le32(0xC0000219) -#define STATUS_SYSTEM_PROCESS_TERMINATED __constant_cpu_to_le32(0xC000021A) -#define STATUS_DATA_NOT_ACCEPTED __constant_cpu_to_le32(0xC000021B) -#define STATUS_NO_BROWSER_SERVERS_FOUND __constant_cpu_to_le32(0xC000021C) -#define STATUS_VDM_HARD_ERROR __constant_cpu_to_le32(0xC000021D) -#define STATUS_DRIVER_CANCEL_TIMEOUT __constant_cpu_to_le32(0xC000021E) -#define STATUS_REPLY_MESSAGE_MISMATCH __constant_cpu_to_le32(0xC000021F) -#define STATUS_MAPPED_ALIGNMENT __constant_cpu_to_le32(0xC0000220) -#define STATUS_IMAGE_CHECKSUM_MISMATCH __constant_cpu_to_le32(0xC0000221) -#define STATUS_LOST_WRITEBEHIND_DATA __constant_cpu_to_le32(0xC0000222) -#define STATUS_CLIENT_SERVER_PARAMETERS_INVALID __constant_cpu_to_le32(0xC0000223) -#define STATUS_PASSWORD_MUST_CHANGE __constant_cpu_to_le32(0xC0000224) -#define STATUS_NOT_FOUND __constant_cpu_to_le32(0xC0000225) -#define STATUS_NOT_TINY_STREAM __constant_cpu_to_le32(0xC0000226) -#define STATUS_RECOVERY_FAILURE __constant_cpu_to_le32(0xC0000227) -#define STATUS_STACK_OVERFLOW_READ __constant_cpu_to_le32(0xC0000228) -#define STATUS_FAIL_CHECK __constant_cpu_to_le32(0xC0000229) -#define STATUS_DUPLICATE_OBJECTID __constant_cpu_to_le32(0xC000022A) -#define STATUS_OBJECTID_EXISTS __constant_cpu_to_le32(0xC000022B) -#define STATUS_CONVERT_TO_LARGE __constant_cpu_to_le32(0xC000022C) -#define STATUS_RETRY __constant_cpu_to_le32(0xC000022D) -#define STATUS_FOUND_OUT_OF_SCOPE __constant_cpu_to_le32(0xC000022E) -#define STATUS_ALLOCATE_BUCKET __constant_cpu_to_le32(0xC000022F) -#define STATUS_PROPSET_NOT_FOUND __constant_cpu_to_le32(0xC0000230) -#define STATUS_MARSHALL_OVERFLOW __constant_cpu_to_le32(0xC0000231) -#define STATUS_INVALID_VARIANT __constant_cpu_to_le32(0xC0000232) -#define STATUS_DOMAIN_CONTROLLER_NOT_FOUND __constant_cpu_to_le32(0xC0000233) -#define STATUS_ACCOUNT_LOCKED_OUT __constant_cpu_to_le32(0xC0000234) -#define STATUS_HANDLE_NOT_CLOSABLE __constant_cpu_to_le32(0xC0000235) -#define STATUS_CONNECTION_REFUSED __constant_cpu_to_le32(0xC0000236) -#define STATUS_GRACEFUL_DISCONNECT __constant_cpu_to_le32(0xC0000237) -#define STATUS_ADDRESS_ALREADY_ASSOCIATED __constant_cpu_to_le32(0xC0000238) -#define STATUS_ADDRESS_NOT_ASSOCIATED __constant_cpu_to_le32(0xC0000239) -#define STATUS_CONNECTION_INVALID __constant_cpu_to_le32(0xC000023A) -#define STATUS_CONNECTION_ACTIVE __constant_cpu_to_le32(0xC000023B) -#define STATUS_NETWORK_UNREACHABLE __constant_cpu_to_le32(0xC000023C) -#define STATUS_HOST_UNREACHABLE __constant_cpu_to_le32(0xC000023D) -#define STATUS_PROTOCOL_UNREACHABLE __constant_cpu_to_le32(0xC000023E) -#define STATUS_PORT_UNREACHABLE __constant_cpu_to_le32(0xC000023F) -#define STATUS_REQUEST_ABORTED __constant_cpu_to_le32(0xC0000240) -#define STATUS_CONNECTION_ABORTED __constant_cpu_to_le32(0xC0000241) -#define STATUS_BAD_COMPRESSION_BUFFER __constant_cpu_to_le32(0xC0000242) -#define STATUS_USER_MAPPED_FILE __constant_cpu_to_le32(0xC0000243) -#define STATUS_AUDIT_FAILED __constant_cpu_to_le32(0xC0000244) -#define STATUS_TIMER_RESOLUTION_NOT_SET __constant_cpu_to_le32(0xC0000245) -#define STATUS_CONNECTION_COUNT_LIMIT __constant_cpu_to_le32(0xC0000246) -#define STATUS_LOGIN_TIME_RESTRICTION __constant_cpu_to_le32(0xC0000247) -#define STATUS_LOGIN_WKSTA_RESTRICTION __constant_cpu_to_le32(0xC0000248) -#define STATUS_IMAGE_MP_UP_MISMATCH __constant_cpu_to_le32(0xC0000249) -#define STATUS_INSUFFICIENT_LOGON_INFO __constant_cpu_to_le32(0xC0000250) -#define STATUS_BAD_DLL_ENTRYPOINT __constant_cpu_to_le32(0xC0000251) -#define STATUS_BAD_SERVICE_ENTRYPOINT __constant_cpu_to_le32(0xC0000252) -#define STATUS_LPC_REPLY_LOST __constant_cpu_to_le32(0xC0000253) -#define STATUS_IP_ADDRESS_CONFLICT1 __constant_cpu_to_le32(0xC0000254) -#define STATUS_IP_ADDRESS_CONFLICT2 __constant_cpu_to_le32(0xC0000255) -#define STATUS_REGISTRY_QUOTA_LIMIT __constant_cpu_to_le32(0xC0000256) -#define STATUS_PATH_NOT_COVERED __constant_cpu_to_le32(0xC0000257) -#define STATUS_NO_CALLBACK_ACTIVE __constant_cpu_to_le32(0xC0000258) -#define STATUS_LICENSE_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC0000259) -#define STATUS_PWD_TOO_SHORT __constant_cpu_to_le32(0xC000025A) -#define STATUS_PWD_TOO_RECENT __constant_cpu_to_le32(0xC000025B) -#define STATUS_PWD_HISTORY_CONFLICT __constant_cpu_to_le32(0xC000025C) -#define STATUS_PLUGPLAY_NO_DEVICE __constant_cpu_to_le32(0xC000025E) -#define STATUS_UNSUPPORTED_COMPRESSION __constant_cpu_to_le32(0xC000025F) -#define STATUS_INVALID_HW_PROFILE __constant_cpu_to_le32(0xC0000260) -#define STATUS_INVALID_PLUGPLAY_DEVICE_PATH __constant_cpu_to_le32(0xC0000261) -#define STATUS_DRIVER_ORDINAL_NOT_FOUND __constant_cpu_to_le32(0xC0000262) -#define STATUS_DRIVER_ENTRYPOINT_NOT_FOUND __constant_cpu_to_le32(0xC0000263) -#define STATUS_RESOURCE_NOT_OWNED __constant_cpu_to_le32(0xC0000264) -#define STATUS_TOO_MANY_LINKS __constant_cpu_to_le32(0xC0000265) -#define STATUS_QUOTA_LIST_INCONSISTENT __constant_cpu_to_le32(0xC0000266) -#define STATUS_FILE_IS_OFFLINE __constant_cpu_to_le32(0xC0000267) -#define STATUS_EVALUATION_EXPIRATION __constant_cpu_to_le32(0xC0000268) -#define STATUS_ILLEGAL_DLL_RELOCATION __constant_cpu_to_le32(0xC0000269) -#define STATUS_LICENSE_VIOLATION __constant_cpu_to_le32(0xC000026A) -#define STATUS_DLL_INIT_FAILED_LOGOFF __constant_cpu_to_le32(0xC000026B) -#define STATUS_DRIVER_UNABLE_TO_LOAD __constant_cpu_to_le32(0xC000026C) -#define STATUS_DFS_UNAVAILABLE __constant_cpu_to_le32(0xC000026D) -#define STATUS_VOLUME_DISMOUNTED __constant_cpu_to_le32(0xC000026E) -#define STATUS_WX86_INTERNAL_ERROR __constant_cpu_to_le32(0xC000026F) -#define STATUS_WX86_FLOAT_STACK_CHECK __constant_cpu_to_le32(0xC0000270) -#define STATUS_VALIDATE_CONTINUE __constant_cpu_to_le32(0xC0000271) -#define STATUS_NO_MATCH __constant_cpu_to_le32(0xC0000272) -#define STATUS_NO_MORE_MATCHES __constant_cpu_to_le32(0xC0000273) -#define STATUS_NOT_A_REPARSE_POINT __constant_cpu_to_le32(0xC0000275) -#define STATUS_IO_REPARSE_TAG_INVALID __constant_cpu_to_le32(0xC0000276) -#define STATUS_IO_REPARSE_TAG_MISMATCH __constant_cpu_to_le32(0xC0000277) -#define STATUS_IO_REPARSE_DATA_INVALID __constant_cpu_to_le32(0xC0000278) -#define STATUS_IO_REPARSE_TAG_NOT_HANDLED __constant_cpu_to_le32(0xC0000279) -#define STATUS_REPARSE_POINT_NOT_RESOLVED __constant_cpu_to_le32(0xC0000280) -#define STATUS_DIRECTORY_IS_A_REPARSE_POINT __constant_cpu_to_le32(0xC0000281) -#define STATUS_RANGE_LIST_CONFLICT __constant_cpu_to_le32(0xC0000282) -#define STATUS_SOURCE_ELEMENT_EMPTY __constant_cpu_to_le32(0xC0000283) -#define STATUS_DESTINATION_ELEMENT_FULL __constant_cpu_to_le32(0xC0000284) -#define STATUS_ILLEGAL_ELEMENT_ADDRESS __constant_cpu_to_le32(0xC0000285) -#define STATUS_MAGAZINE_NOT_PRESENT __constant_cpu_to_le32(0xC0000286) -#define STATUS_REINITIALIZATION_NEEDED __constant_cpu_to_le32(0xC0000287) -#define STATUS_ENCRYPTION_FAILED __constant_cpu_to_le32(0xC000028A) -#define STATUS_DECRYPTION_FAILED __constant_cpu_to_le32(0xC000028B) -#define STATUS_RANGE_NOT_FOUND __constant_cpu_to_le32(0xC000028C) -#define STATUS_NO_RECOVERY_POLICY __constant_cpu_to_le32(0xC000028D) -#define STATUS_NO_EFS __constant_cpu_to_le32(0xC000028E) -#define STATUS_WRONG_EFS __constant_cpu_to_le32(0xC000028F) -#define STATUS_NO_USER_KEYS __constant_cpu_to_le32(0xC0000290) -#define STATUS_FILE_NOT_ENCRYPTED __constant_cpu_to_le32(0xC0000291) -#define STATUS_NOT_EXPORT_FORMAT __constant_cpu_to_le32(0xC0000292) -#define STATUS_FILE_ENCRYPTED __constant_cpu_to_le32(0xC0000293) -#define STATUS_WMI_GUID_NOT_FOUND __constant_cpu_to_le32(0xC0000295) -#define STATUS_WMI_INSTANCE_NOT_FOUND __constant_cpu_to_le32(0xC0000296) -#define STATUS_WMI_ITEMID_NOT_FOUND __constant_cpu_to_le32(0xC0000297) -#define STATUS_WMI_TRY_AGAIN __constant_cpu_to_le32(0xC0000298) -#define STATUS_SHARED_POLICY __constant_cpu_to_le32(0xC0000299) -#define STATUS_POLICY_OBJECT_NOT_FOUND __constant_cpu_to_le32(0xC000029A) -#define STATUS_POLICY_ONLY_IN_DS __constant_cpu_to_le32(0xC000029B) -#define STATUS_VOLUME_NOT_UPGRADED __constant_cpu_to_le32(0xC000029C) -#define STATUS_REMOTE_STORAGE_NOT_ACTIVE __constant_cpu_to_le32(0xC000029D) -#define STATUS_REMOTE_STORAGE_MEDIA_ERROR __constant_cpu_to_le32(0xC000029E) -#define STATUS_NO_TRACKING_SERVICE __constant_cpu_to_le32(0xC000029F) -#define STATUS_SERVER_SID_MISMATCH __constant_cpu_to_le32(0xC00002A0) -#define STATUS_DS_NO_ATTRIBUTE_OR_VALUE __constant_cpu_to_le32(0xC00002A1) -#define STATUS_DS_INVALID_ATTRIBUTE_SYNTAX __constant_cpu_to_le32(0xC00002A2) -#define STATUS_DS_ATTRIBUTE_TYPE_UNDEFINED __constant_cpu_to_le32(0xC00002A3) -#define STATUS_DS_ATTRIBUTE_OR_VALUE_EXISTS __constant_cpu_to_le32(0xC00002A4) -#define STATUS_DS_BUSY __constant_cpu_to_le32(0xC00002A5) -#define STATUS_DS_UNAVAILABLE __constant_cpu_to_le32(0xC00002A6) -#define STATUS_DS_NO_RIDS_ALLOCATED __constant_cpu_to_le32(0xC00002A7) -#define STATUS_DS_NO_MORE_RIDS __constant_cpu_to_le32(0xC00002A8) -#define STATUS_DS_INCORRECT_ROLE_OWNER __constant_cpu_to_le32(0xC00002A9) -#define STATUS_DS_RIDMGR_INIT_ERROR __constant_cpu_to_le32(0xC00002AA) -#define STATUS_DS_OBJ_CLASS_VIOLATION __constant_cpu_to_le32(0xC00002AB) -#define STATUS_DS_CANT_ON_NON_LEAF __constant_cpu_to_le32(0xC00002AC) -#define STATUS_DS_CANT_ON_RDN __constant_cpu_to_le32(0xC00002AD) -#define STATUS_DS_CANT_MOD_OBJ_CLASS __constant_cpu_to_le32(0xC00002AE) -#define STATUS_DS_CROSS_DOM_MOVE_FAILED __constant_cpu_to_le32(0xC00002AF) -#define STATUS_DS_GC_NOT_AVAILABLE __constant_cpu_to_le32(0xC00002B0) -#define STATUS_DIRECTORY_SERVICE_REQUIRED __constant_cpu_to_le32(0xC00002B1) -#define STATUS_REPARSE_ATTRIBUTE_CONFLICT __constant_cpu_to_le32(0xC00002B2) -#define STATUS_CANT_ENABLE_DENY_ONLY __constant_cpu_to_le32(0xC00002B3) -#define STATUS_FLOAT_MULTIPLE_FAULTS __constant_cpu_to_le32(0xC00002B4) -#define STATUS_FLOAT_MULTIPLE_TRAPS __constant_cpu_to_le32(0xC00002B5) -#define STATUS_DEVICE_REMOVED __constant_cpu_to_le32(0xC00002B6) -#define STATUS_JOURNAL_DELETE_IN_PROGRESS __constant_cpu_to_le32(0xC00002B7) -#define STATUS_JOURNAL_NOT_ACTIVE __constant_cpu_to_le32(0xC00002B8) -#define STATUS_NOINTERFACE __constant_cpu_to_le32(0xC00002B9) -#define STATUS_DS_ADMIN_LIMIT_EXCEEDED __constant_cpu_to_le32(0xC00002C1) -#define STATUS_DRIVER_FAILED_SLEEP __constant_cpu_to_le32(0xC00002C2) -#define STATUS_MUTUAL_AUTHENTICATION_FAILED __constant_cpu_to_le32(0xC00002C3) -#define STATUS_CORRUPT_SYSTEM_FILE __constant_cpu_to_le32(0xC00002C4) -#define STATUS_DATATYPE_MISALIGNMENT_ERROR __constant_cpu_to_le32(0xC00002C5) -#define STATUS_WMI_READ_ONLY __constant_cpu_to_le32(0xC00002C6) -#define STATUS_WMI_SET_FAILURE __constant_cpu_to_le32(0xC00002C7) -#define STATUS_COMMITMENT_MINIMUM __constant_cpu_to_le32(0xC00002C8) -#define STATUS_REG_NAT_CONSUMPTION __constant_cpu_to_le32(0xC00002C9) -#define STATUS_TRANSPORT_FULL __constant_cpu_to_le32(0xC00002CA) -#define STATUS_DS_SAM_INIT_FAILURE __constant_cpu_to_le32(0xC00002CB) -#define STATUS_ONLY_IF_CONNECTED __constant_cpu_to_le32(0xC00002CC) -#define STATUS_DS_SENSITIVE_GROUP_VIOLATION __constant_cpu_to_le32(0xC00002CD) -#define STATUS_PNP_RESTART_ENUMERATION __constant_cpu_to_le32(0xC00002CE) -#define STATUS_JOURNAL_ENTRY_DELETED __constant_cpu_to_le32(0xC00002CF) -#define STATUS_DS_CANT_MOD_PRIMARYGROUPID __constant_cpu_to_le32(0xC00002D0) -#define STATUS_SYSTEM_IMAGE_BAD_SIGNATURE __constant_cpu_to_le32(0xC00002D1) -#define STATUS_PNP_REBOOT_REQUIRED __constant_cpu_to_le32(0xC00002D2) -#define STATUS_POWER_STATE_INVALID __constant_cpu_to_le32(0xC00002D3) -#define STATUS_DS_INVALID_GROUP_TYPE __constant_cpu_to_le32(0xC00002D4) -#define STATUS_DS_NO_NEST_GLOBALGROUP_IN_MIXEDDOMAIN __constant_cpu_to_le32(0xC00002D5) -#define STATUS_DS_NO_NEST_LOCALGROUP_IN_MIXEDDOMAIN __constant_cpu_to_le32(0xC00002D6) -#define STATUS_DS_GLOBAL_CANT_HAVE_LOCAL_MEMBER __constant_cpu_to_le32(0xC00002D7) -#define STATUS_DS_GLOBAL_CANT_HAVE_UNIVERSAL_MEMBER __constant_cpu_to_le32(0xC00002D8) -#define STATUS_DS_UNIVERSAL_CANT_HAVE_LOCAL_MEMBER __constant_cpu_to_le32(0xC00002D9) -#define STATUS_DS_GLOBAL_CANT_HAVE_CROSSDOMAIN_MEMBER __constant_cpu_to_le32(0xC00002DA) -#define STATUS_DS_LOCAL_CANT_HAVE_CROSSDOMAIN_LOCAL_MEMBER __constant_cpu_to_le32(0xC00002DB) -#define STATUS_DS_HAVE_PRIMARY_MEMBERS __constant_cpu_to_le32(0xC00002DC) -#define STATUS_WMI_NOT_SUPPORTED __constant_cpu_to_le32(0xC00002DD) -#define STATUS_INSUFFICIENT_POWER __constant_cpu_to_le32(0xC00002DE) -#define STATUS_SAM_NEED_BOOTKEY_PASSWORD __constant_cpu_to_le32(0xC00002DF) -#define STATUS_SAM_NEED_BOOTKEY_FLOPPY __constant_cpu_to_le32(0xC00002E0) -#define STATUS_DS_CANT_START __constant_cpu_to_le32(0xC00002E1) -#define STATUS_DS_INIT_FAILURE __constant_cpu_to_le32(0xC00002E2) -#define STATUS_SAM_INIT_FAILURE __constant_cpu_to_le32(0xC00002E3) -#define STATUS_DS_GC_REQUIRED __constant_cpu_to_le32(0xC00002E4) -#define STATUS_DS_LOCAL_MEMBER_OF_LOCAL_ONLY __constant_cpu_to_le32(0xC00002E5) -#define STATUS_DS_NO_FPO_IN_UNIVERSAL_GROUPS __constant_cpu_to_le32(0xC00002E6) -#define STATUS_DS_MACHINE_ACCOUNT_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC00002E7) -#define STATUS_MULTIPLE_FAULT_VIOLATION __constant_cpu_to_le32(0xC00002E8) -#define STATUS_CURRENT_DOMAIN_NOT_ALLOWED __constant_cpu_to_le32(0xC00002E9) -#define STATUS_CANNOT_MAKE __constant_cpu_to_le32(0xC00002EA) -#define STATUS_SYSTEM_SHUTDOWN __constant_cpu_to_le32(0xC00002EB) -#define STATUS_DS_INIT_FAILURE_CONSOLE __constant_cpu_to_le32(0xC00002EC) -#define STATUS_DS_SAM_INIT_FAILURE_CONSOLE __constant_cpu_to_le32(0xC00002ED) -#define STATUS_UNFINISHED_CONTEXT_DELETED __constant_cpu_to_le32(0xC00002EE) -#define STATUS_NO_TGT_REPLY __constant_cpu_to_le32(0xC00002EF) -#define STATUS_OBJECTID_NOT_FOUND __constant_cpu_to_le32(0xC00002F0) -#define STATUS_NO_IP_ADDRESSES __constant_cpu_to_le32(0xC00002F1) -#define STATUS_WRONG_CREDENTIAL_HANDLE __constant_cpu_to_le32(0xC00002F2) -#define STATUS_CRYPTO_SYSTEM_INVALID __constant_cpu_to_le32(0xC00002F3) -#define STATUS_MAX_REFERRALS_EXCEEDED __constant_cpu_to_le32(0xC00002F4) -#define STATUS_MUST_BE_KDC __constant_cpu_to_le32(0xC00002F5) -#define STATUS_STRONG_CRYPTO_NOT_SUPPORTED __constant_cpu_to_le32(0xC00002F6) -#define STATUS_TOO_MANY_PRINCIPALS __constant_cpu_to_le32(0xC00002F7) -#define STATUS_NO_PA_DATA __constant_cpu_to_le32(0xC00002F8) -#define STATUS_PKINIT_NAME_MISMATCH __constant_cpu_to_le32(0xC00002F9) -#define STATUS_SMARTCARD_LOGON_REQUIRED __constant_cpu_to_le32(0xC00002FA) -#define STATUS_KDC_INVALID_REQUEST __constant_cpu_to_le32(0xC00002FB) -#define STATUS_KDC_UNABLE_TO_REFER __constant_cpu_to_le32(0xC00002FC) -#define STATUS_KDC_UNKNOWN_ETYPE __constant_cpu_to_le32(0xC00002FD) -#define STATUS_SHUTDOWN_IN_PROGRESS __constant_cpu_to_le32(0xC00002FE) -#define STATUS_SERVER_SHUTDOWN_IN_PROGRESS __constant_cpu_to_le32(0xC00002FF) -#define STATUS_NOT_SUPPORTED_ON_SBS __constant_cpu_to_le32(0xC0000300) -#define STATUS_WMI_GUID_DISCONNECTED __constant_cpu_to_le32(0xC0000301) -#define STATUS_WMI_ALREADY_DISABLED __constant_cpu_to_le32(0xC0000302) -#define STATUS_WMI_ALREADY_ENABLED __constant_cpu_to_le32(0xC0000303) -#define STATUS_MFT_TOO_FRAGMENTED __constant_cpu_to_le32(0xC0000304) -#define STATUS_COPY_PROTECTION_FAILURE __constant_cpu_to_le32(0xC0000305) -#define STATUS_CSS_AUTHENTICATION_FAILURE __constant_cpu_to_le32(0xC0000306) -#define STATUS_CSS_KEY_NOT_PRESENT __constant_cpu_to_le32(0xC0000307) -#define STATUS_CSS_KEY_NOT_ESTABLISHED __constant_cpu_to_le32(0xC0000308) -#define STATUS_CSS_SCRAMBLED_SECTOR __constant_cpu_to_le32(0xC0000309) -#define STATUS_CSS_REGION_MISMATCH __constant_cpu_to_le32(0xC000030A) -#define STATUS_CSS_RESETS_EXHAUSTED __constant_cpu_to_le32(0xC000030B) -#define STATUS_PKINIT_FAILURE __constant_cpu_to_le32(0xC0000320) -#define STATUS_SMARTCARD_SUBSYSTEM_FAILURE __constant_cpu_to_le32(0xC0000321) -#define STATUS_NO_KERB_KEY __constant_cpu_to_le32(0xC0000322) -#define STATUS_HOST_DOWN __constant_cpu_to_le32(0xC0000350) -#define STATUS_UNSUPPORTED_PREAUTH __constant_cpu_to_le32(0xC0000351) -#define STATUS_EFS_ALG_BLOB_TOO_BIG __constant_cpu_to_le32(0xC0000352) -#define STATUS_PORT_NOT_SET __constant_cpu_to_le32(0xC0000353) -#define STATUS_DEBUGGER_INACTIVE __constant_cpu_to_le32(0xC0000354) -#define STATUS_DS_VERSION_CHECK_FAILURE __constant_cpu_to_le32(0xC0000355) -#define STATUS_AUDITING_DISABLED __constant_cpu_to_le32(0xC0000356) -#define STATUS_PRENT4_MACHINE_ACCOUNT __constant_cpu_to_le32(0xC0000357) -#define STATUS_DS_AG_CANT_HAVE_UNIVERSAL_MEMBER __constant_cpu_to_le32(0xC0000358) -#define STATUS_INVALID_IMAGE_WIN_32 __constant_cpu_to_le32(0xC0000359) -#define STATUS_INVALID_IMAGE_WIN_64 __constant_cpu_to_le32(0xC000035A) -#define STATUS_BAD_BINDINGS __constant_cpu_to_le32(0xC000035B) -#define STATUS_NETWORK_SESSION_EXPIRED __constant_cpu_to_le32(0xC000035C) -#define STATUS_APPHELP_BLOCK __constant_cpu_to_le32(0xC000035D) -#define STATUS_ALL_SIDS_FILTERED __constant_cpu_to_le32(0xC000035E) -#define STATUS_NOT_SAFE_MODE_DRIVER __constant_cpu_to_le32(0xC000035F) -#define STATUS_ACCESS_DISABLED_BY_POLICY_DEFAULT __constant_cpu_to_le32(0xC0000361) -#define STATUS_ACCESS_DISABLED_BY_POLICY_PATH __constant_cpu_to_le32(0xC0000362) -#define STATUS_ACCESS_DISABLED_BY_POLICY_PUBLISHER __constant_cpu_to_le32(0xC0000363) -#define STATUS_ACCESS_DISABLED_BY_POLICY_OTHER __constant_cpu_to_le32(0xC0000364) -#define STATUS_FAILED_DRIVER_ENTRY __constant_cpu_to_le32(0xC0000365) -#define STATUS_DEVICE_ENUMERATION_ERROR __constant_cpu_to_le32(0xC0000366) -#define STATUS_MOUNT_POINT_NOT_RESOLVED __constant_cpu_to_le32(0xC0000368) -#define STATUS_INVALID_DEVICE_OBJECT_PARAMETER __constant_cpu_to_le32(0xC0000369) -#define STATUS_MCA_OCCURED __constant_cpu_to_le32(0xC000036A) -#define STATUS_DRIVER_BLOCKED_CRITICAL __constant_cpu_to_le32(0xC000036B) -#define STATUS_DRIVER_BLOCKED __constant_cpu_to_le32(0xC000036C) -#define STATUS_DRIVER_DATABASE_ERROR __constant_cpu_to_le32(0xC000036D) -#define STATUS_SYSTEM_HIVE_TOO_LARGE __constant_cpu_to_le32(0xC000036E) -#define STATUS_INVALID_IMPORT_OF_NON_DLL __constant_cpu_to_le32(0xC000036F) -#define STATUS_NO_SECRETS __constant_cpu_to_le32(0xC0000371) -#define STATUS_ACCESS_DISABLED_NO_SAFER_UI_BY_POLICY __constant_cpu_to_le32(0xC0000372) -#define STATUS_FAILED_STACK_SWITCH __constant_cpu_to_le32(0xC0000373) -#define STATUS_HEAP_CORRUPTION __constant_cpu_to_le32(0xC0000374) -#define STATUS_SMARTCARD_WRONG_PIN __constant_cpu_to_le32(0xC0000380) -#define STATUS_SMARTCARD_CARD_BLOCKED __constant_cpu_to_le32(0xC0000381) -#define STATUS_SMARTCARD_CARD_NOT_AUTHENTICATED __constant_cpu_to_le32(0xC0000382) -#define STATUS_SMARTCARD_NO_CARD __constant_cpu_to_le32(0xC0000383) -#define STATUS_SMARTCARD_NO_KEY_CONTAINER __constant_cpu_to_le32(0xC0000384) -#define STATUS_SMARTCARD_NO_CERTIFICATE __constant_cpu_to_le32(0xC0000385) -#define STATUS_SMARTCARD_NO_KEYSET __constant_cpu_to_le32(0xC0000386) -#define STATUS_SMARTCARD_IO_ERROR __constant_cpu_to_le32(0xC0000387) -#define STATUS_DOWNGRADE_DETECTED __constant_cpu_to_le32(0xC0000388) -#define STATUS_SMARTCARD_CERT_REVOKED __constant_cpu_to_le32(0xC0000389) -#define STATUS_ISSUING_CA_UNTRUSTED __constant_cpu_to_le32(0xC000038A) -#define STATUS_REVOCATION_OFFLINE_C __constant_cpu_to_le32(0xC000038B) -#define STATUS_PKINIT_CLIENT_FAILURE __constant_cpu_to_le32(0xC000038C) -#define STATUS_SMARTCARD_CERT_EXPIRED __constant_cpu_to_le32(0xC000038D) -#define STATUS_DRIVER_FAILED_PRIOR_UNLOAD __constant_cpu_to_le32(0xC000038E) -#define STATUS_SMARTCARD_SILENT_CONTEXT __constant_cpu_to_le32(0xC000038F) -#define STATUS_PER_USER_TRUST_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC0000401) -#define STATUS_ALL_USER_TRUST_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC0000402) -#define STATUS_USER_DELETE_TRUST_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC0000403) -#define STATUS_DS_NAME_NOT_UNIQUE __constant_cpu_to_le32(0xC0000404) -#define STATUS_DS_DUPLICATE_ID_FOUND __constant_cpu_to_le32(0xC0000405) -#define STATUS_DS_GROUP_CONVERSION_ERROR __constant_cpu_to_le32(0xC0000406) -#define STATUS_VOLSNAP_PREPARE_HIBERNATE __constant_cpu_to_le32(0xC0000407) -#define STATUS_USER2USER_REQUIRED __constant_cpu_to_le32(0xC0000408) -#define STATUS_STACK_BUFFER_OVERRUN __constant_cpu_to_le32(0xC0000409) -#define STATUS_NO_S4U_PROT_SUPPORT __constant_cpu_to_le32(0xC000040A) -#define STATUS_CROSSREALM_DELEGATION_FAILURE __constant_cpu_to_le32(0xC000040B) -#define STATUS_REVOCATION_OFFLINE_KDC __constant_cpu_to_le32(0xC000040C) -#define STATUS_ISSUING_CA_UNTRUSTED_KDC __constant_cpu_to_le32(0xC000040D) -#define STATUS_KDC_CERT_EXPIRED __constant_cpu_to_le32(0xC000040E) -#define STATUS_KDC_CERT_REVOKED __constant_cpu_to_le32(0xC000040F) -#define STATUS_PARAMETER_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC0000410) -#define STATUS_HIBERNATION_FAILURE __constant_cpu_to_le32(0xC0000411) -#define STATUS_DELAY_LOAD_FAILED __constant_cpu_to_le32(0xC0000412) -#define STATUS_AUTHENTICATION_FIREWALL_FAILED __constant_cpu_to_le32(0xC0000413) -#define STATUS_VDM_DISALLOWED __constant_cpu_to_le32(0xC0000414) -#define STATUS_HUNG_DISPLAY_DRIVER_THREAD __constant_cpu_to_le32(0xC0000415) -#define STATUS_INSUFFICIENT_RESOURCE_FOR_SPECIFIED_SHARED_SECTION_SIZE __constant_cpu_to_le32(0xC0000416) -#define STATUS_INVALID_CRUNTIME_PARAMETER __constant_cpu_to_le32(0xC0000417) -#define STATUS_NTLM_BLOCKED __constant_cpu_to_le32(0xC0000418) -#define STATUS_ASSERTION_FAILURE __constant_cpu_to_le32(0xC0000420) -#define STATUS_VERIFIER_STOP __constant_cpu_to_le32(0xC0000421) -#define STATUS_CALLBACK_POP_STACK __constant_cpu_to_le32(0xC0000423) -#define STATUS_INCOMPATIBLE_DRIVER_BLOCKED __constant_cpu_to_le32(0xC0000424) -#define STATUS_HIVE_UNLOADED __constant_cpu_to_le32(0xC0000425) -#define STATUS_COMPRESSION_DISABLED __constant_cpu_to_le32(0xC0000426) -#define STATUS_FILE_SYSTEM_LIMITATION __constant_cpu_to_le32(0xC0000427) -#define STATUS_INVALID_IMAGE_HASH __constant_cpu_to_le32(0xC0000428) -#define STATUS_NOT_CAPABLE __constant_cpu_to_le32(0xC0000429) -#define STATUS_REQUEST_OUT_OF_SEQUENCE __constant_cpu_to_le32(0xC000042A) -#define STATUS_IMPLEMENTATION_LIMIT __constant_cpu_to_le32(0xC000042B) -#define STATUS_ELEVATION_REQUIRED __constant_cpu_to_le32(0xC000042C) -#define STATUS_BEYOND_VDL __constant_cpu_to_le32(0xC0000432) -#define STATUS_ENCOUNTERED_WRITE_IN_PROGRESS __constant_cpu_to_le32(0xC0000433) -#define STATUS_PTE_CHANGED __constant_cpu_to_le32(0xC0000434) -#define STATUS_PURGE_FAILED __constant_cpu_to_le32(0xC0000435) -#define STATUS_CRED_REQUIRES_CONFIRMATION __constant_cpu_to_le32(0xC0000440) -#define STATUS_CS_ENCRYPTION_INVALID_SERVER_RESPONSE __constant_cpu_to_le32(0xC0000441) -#define STATUS_CS_ENCRYPTION_UNSUPPORTED_SERVER __constant_cpu_to_le32(0xC0000442) -#define STATUS_CS_ENCRYPTION_EXISTING_ENCRYPTED_FILE __constant_cpu_to_le32(0xC0000443) -#define STATUS_CS_ENCRYPTION_NEW_ENCRYPTED_FILE __constant_cpu_to_le32(0xC0000444) -#define STATUS_CS_ENCRYPTION_FILE_NOT_CSE __constant_cpu_to_le32(0xC0000445) -#define STATUS_INVALID_LABEL __constant_cpu_to_le32(0xC0000446) -#define STATUS_DRIVER_PROCESS_TERMINATED __constant_cpu_to_le32(0xC0000450) -#define STATUS_AMBIGUOUS_SYSTEM_DEVICE __constant_cpu_to_le32(0xC0000451) -#define STATUS_SYSTEM_DEVICE_NOT_FOUND __constant_cpu_to_le32(0xC0000452) -#define STATUS_RESTART_BOOT_APPLICATION __constant_cpu_to_le32(0xC0000453) -#define STATUS_INVALID_TASK_NAME __constant_cpu_to_le32(0xC0000500) -#define STATUS_INVALID_TASK_INDEX __constant_cpu_to_le32(0xC0000501) -#define STATUS_THREAD_ALREADY_IN_TASK __constant_cpu_to_le32(0xC0000502) -#define STATUS_CALLBACK_BYPASS __constant_cpu_to_le32(0xC0000503) -#define STATUS_PORT_CLOSED __constant_cpu_to_le32(0xC0000700) -#define STATUS_MESSAGE_LOST __constant_cpu_to_le32(0xC0000701) -#define STATUS_INVALID_MESSAGE __constant_cpu_to_le32(0xC0000702) -#define STATUS_REQUEST_CANCELED __constant_cpu_to_le32(0xC0000703) -#define STATUS_RECURSIVE_DISPATCH __constant_cpu_to_le32(0xC0000704) -#define STATUS_LPC_RECEIVE_BUFFER_EXPECTED __constant_cpu_to_le32(0xC0000705) -#define STATUS_LPC_INVALID_CONNECTION_USAGE __constant_cpu_to_le32(0xC0000706) -#define STATUS_LPC_REQUESTS_NOT_ALLOWED __constant_cpu_to_le32(0xC0000707) -#define STATUS_RESOURCE_IN_USE __constant_cpu_to_le32(0xC0000708) -#define STATUS_HARDWARE_MEMORY_ERROR __constant_cpu_to_le32(0xC0000709) -#define STATUS_THREADPOOL_HANDLE_EXCEPTION __constant_cpu_to_le32(0xC000070A) -#define STATUS_THREADPOOL_SET_EVENT_ON_COMPLETION_FAILED __constant_cpu_to_le32(0xC000070B) -#define STATUS_THREADPOOL_RELEASE_SEMAPHORE_ON_COMPLETION_FAILED __constant_cpu_to_le32(0xC000070C) -#define STATUS_THREADPOOL_RELEASE_MUTEX_ON_COMPLETION_FAILED __constant_cpu_to_le32(0xC000070D) -#define STATUS_THREADPOOL_FREE_LIBRARY_ON_COMPLETION_FAILED __constant_cpu_to_le32(0xC000070E) -#define STATUS_THREADPOOL_RELEASED_DURING_OPERATION __constant_cpu_to_le32(0xC000070F) -#define STATUS_CALLBACK_RETURNED_WHILE_IMPERSONATING __constant_cpu_to_le32(0xC0000710) -#define STATUS_APC_RETURNED_WHILE_IMPERSONATING __constant_cpu_to_le32(0xC0000711) -#define STATUS_PROCESS_IS_PROTECTED __constant_cpu_to_le32(0xC0000712) -#define STATUS_MCA_EXCEPTION __constant_cpu_to_le32(0xC0000713) -#define STATUS_CERTIFICATE_MAPPING_NOT_UNIQUE __constant_cpu_to_le32(0xC0000714) -#define STATUS_SYMLINK_CLASS_DISABLED __constant_cpu_to_le32(0xC0000715) -#define STATUS_INVALID_IDN_NORMALIZATION __constant_cpu_to_le32(0xC0000716) -#define STATUS_NO_UNICODE_TRANSLATION __constant_cpu_to_le32(0xC0000717) -#define STATUS_ALREADY_REGISTERED __constant_cpu_to_le32(0xC0000718) -#define STATUS_CONTEXT_MISMATCH __constant_cpu_to_le32(0xC0000719) -#define STATUS_PORT_ALREADY_HAS_COMPLETION_LIST __constant_cpu_to_le32(0xC000071A) -#define STATUS_CALLBACK_RETURNED_THREAD_PRIORITY __constant_cpu_to_le32(0xC000071B) -#define STATUS_INVALID_THREAD __constant_cpu_to_le32(0xC000071C) -#define STATUS_CALLBACK_RETURNED_TRANSACTION __constant_cpu_to_le32(0xC000071D) -#define STATUS_CALLBACK_RETURNED_LDR_LOCK __constant_cpu_to_le32(0xC000071E) -#define STATUS_CALLBACK_RETURNED_LANG __constant_cpu_to_le32(0xC000071F) -#define STATUS_CALLBACK_RETURNED_PRI_BACK __constant_cpu_to_le32(0xC0000720) -#define STATUS_CALLBACK_RETURNED_THREAD_AFFINITY __constant_cpu_to_le32(0xC0000721) -#define STATUS_DISK_REPAIR_DISABLED __constant_cpu_to_le32(0xC0000800) -#define STATUS_DS_DOMAIN_RENAME_IN_PROGRESS __constant_cpu_to_le32(0xC0000801) -#define STATUS_DISK_QUOTA_EXCEEDED __constant_cpu_to_le32(0xC0000802) -#define STATUS_CONTENT_BLOCKED __constant_cpu_to_le32(0xC0000804) -#define STATUS_BAD_CLUSTERS __constant_cpu_to_le32(0xC0000805) -#define STATUS_VOLUME_DIRTY __constant_cpu_to_le32(0xC0000806) -#define STATUS_FILE_CHECKED_OUT __constant_cpu_to_le32(0xC0000901) -#define STATUS_CHECKOUT_REQUIRED __constant_cpu_to_le32(0xC0000902) -#define STATUS_BAD_FILE_TYPE __constant_cpu_to_le32(0xC0000903) -#define STATUS_FILE_TOO_LARGE __constant_cpu_to_le32(0xC0000904) -#define STATUS_FORMS_AUTH_REQUIRED __constant_cpu_to_le32(0xC0000905) -#define STATUS_VIRUS_INFECTED __constant_cpu_to_le32(0xC0000906) -#define STATUS_VIRUS_DELETED __constant_cpu_to_le32(0xC0000907) -#define STATUS_BAD_MCFG_TABLE __constant_cpu_to_le32(0xC0000908) -#define STATUS_WOW_ASSERTION __constant_cpu_to_le32(0xC0009898) -#define STATUS_INVALID_SIGNATURE __constant_cpu_to_le32(0xC000A000) -#define STATUS_HMAC_NOT_SUPPORTED __constant_cpu_to_le32(0xC000A001) -#define STATUS_IPSEC_QUEUE_OVERFLOW __constant_cpu_to_le32(0xC000A010) -#define STATUS_ND_QUEUE_OVERFLOW __constant_cpu_to_le32(0xC000A011) -#define STATUS_HOPLIMIT_EXCEEDED __constant_cpu_to_le32(0xC000A012) -#define STATUS_PROTOCOL_NOT_SUPPORTED __constant_cpu_to_le32(0xC000A013) -#define STATUS_LOST_WRITEBEHIND_DATA_NETWORK_DISCONNECTED __constant_cpu_to_le32(0xC000A080) -#define STATUS_LOST_WRITEBEHIND_DATA_NETWORK_SERVER_ERROR __constant_cpu_to_le32(0xC000A081) -#define STATUS_LOST_WRITEBEHIND_DATA_LOCAL_DISK_ERROR __constant_cpu_to_le32(0xC000A082) -#define STATUS_XML_PARSE_ERROR __constant_cpu_to_le32(0xC000A083) -#define STATUS_XMLDSIG_ERROR __constant_cpu_to_le32(0xC000A084) -#define STATUS_WRONG_COMPARTMENT __constant_cpu_to_le32(0xC000A085) -#define STATUS_AUTHIP_FAILURE __constant_cpu_to_le32(0xC000A086) -#define DBG_NO_STATE_CHANGE __constant_cpu_to_le32(0xC0010001) -#define DBG_APP_NOT_IDLE __constant_cpu_to_le32(0xC0010002) -#define RPC_NT_INVALID_STRING_BINDING __constant_cpu_to_le32(0xC0020001) -#define RPC_NT_WRONG_KIND_OF_BINDING __constant_cpu_to_le32(0xC0020002) -#define RPC_NT_INVALID_BINDING __constant_cpu_to_le32(0xC0020003) -#define RPC_NT_PROTSEQ_NOT_SUPPORTED __constant_cpu_to_le32(0xC0020004) -#define RPC_NT_INVALID_RPC_PROTSEQ __constant_cpu_to_le32(0xC0020005) -#define RPC_NT_INVALID_STRING_UUID __constant_cpu_to_le32(0xC0020006) -#define RPC_NT_INVALID_ENDPOINT_FORMAT __constant_cpu_to_le32(0xC0020007) -#define RPC_NT_INVALID_NET_ADDR __constant_cpu_to_le32(0xC0020008) -#define RPC_NT_NO_ENDPOINT_FOUND __constant_cpu_to_le32(0xC0020009) -#define RPC_NT_INVALID_TIMEOUT __constant_cpu_to_le32(0xC002000A) -#define RPC_NT_OBJECT_NOT_FOUND __constant_cpu_to_le32(0xC002000B) -#define RPC_NT_ALREADY_REGISTERED __constant_cpu_to_le32(0xC002000C) -#define RPC_NT_TYPE_ALREADY_REGISTERED __constant_cpu_to_le32(0xC002000D) -#define RPC_NT_ALREADY_LISTENING __constant_cpu_to_le32(0xC002000E) -#define RPC_NT_NO_PROTSEQS_REGISTERED __constant_cpu_to_le32(0xC002000F) -#define RPC_NT_NOT_LISTENING __constant_cpu_to_le32(0xC0020010) -#define RPC_NT_UNKNOWN_MGR_TYPE __constant_cpu_to_le32(0xC0020011) -#define RPC_NT_UNKNOWN_IF __constant_cpu_to_le32(0xC0020012) -#define RPC_NT_NO_BINDINGS __constant_cpu_to_le32(0xC0020013) -#define RPC_NT_NO_PROTSEQS __constant_cpu_to_le32(0xC0020014) -#define RPC_NT_CANT_CREATE_ENDPOINT __constant_cpu_to_le32(0xC0020015) -#define RPC_NT_OUT_OF_RESOURCES __constant_cpu_to_le32(0xC0020016) -#define RPC_NT_SERVER_UNAVAILABLE __constant_cpu_to_le32(0xC0020017) -#define RPC_NT_SERVER_TOO_BUSY __constant_cpu_to_le32(0xC0020018) -#define RPC_NT_INVALID_NETWORK_OPTIONS __constant_cpu_to_le32(0xC0020019) -#define RPC_NT_NO_CALL_ACTIVE __constant_cpu_to_le32(0xC002001A) -#define RPC_NT_CALL_FAILED __constant_cpu_to_le32(0xC002001B) -#define RPC_NT_CALL_FAILED_DNE __constant_cpu_to_le32(0xC002001C) -#define RPC_NT_PROTOCOL_ERROR __constant_cpu_to_le32(0xC002001D) -#define RPC_NT_UNSUPPORTED_TRANS_SYN __constant_cpu_to_le32(0xC002001F) -#define RPC_NT_UNSUPPORTED_TYPE __constant_cpu_to_le32(0xC0020021) -#define RPC_NT_INVALID_TAG __constant_cpu_to_le32(0xC0020022) -#define RPC_NT_INVALID_BOUND __constant_cpu_to_le32(0xC0020023) -#define RPC_NT_NO_ENTRY_NAME __constant_cpu_to_le32(0xC0020024) -#define RPC_NT_INVALID_NAME_SYNTAX __constant_cpu_to_le32(0xC0020025) -#define RPC_NT_UNSUPPORTED_NAME_SYNTAX __constant_cpu_to_le32(0xC0020026) -#define RPC_NT_UUID_NO_ADDRESS __constant_cpu_to_le32(0xC0020028) -#define RPC_NT_DUPLICATE_ENDPOINT __constant_cpu_to_le32(0xC0020029) -#define RPC_NT_UNKNOWN_AUTHN_TYPE __constant_cpu_to_le32(0xC002002A) -#define RPC_NT_MAX_CALLS_TOO_SMALL __constant_cpu_to_le32(0xC002002B) -#define RPC_NT_STRING_TOO_LONG __constant_cpu_to_le32(0xC002002C) -#define RPC_NT_PROTSEQ_NOT_FOUND __constant_cpu_to_le32(0xC002002D) -#define RPC_NT_PROCNUM_OUT_OF_RANGE __constant_cpu_to_le32(0xC002002E) -#define RPC_NT_BINDING_HAS_NO_AUTH __constant_cpu_to_le32(0xC002002F) -#define RPC_NT_UNKNOWN_AUTHN_SERVICE __constant_cpu_to_le32(0xC0020030) -#define RPC_NT_UNKNOWN_AUTHN_LEVEL __constant_cpu_to_le32(0xC0020031) -#define RPC_NT_INVALID_AUTH_IDENTITY __constant_cpu_to_le32(0xC0020032) -#define RPC_NT_UNKNOWN_AUTHZ_SERVICE __constant_cpu_to_le32(0xC0020033) -#define EPT_NT_INVALID_ENTRY __constant_cpu_to_le32(0xC0020034) -#define EPT_NT_CANT_PERFORM_OP __constant_cpu_to_le32(0xC0020035) -#define EPT_NT_NOT_REGISTERED __constant_cpu_to_le32(0xC0020036) -#define RPC_NT_NOTHING_TO_EXPORT __constant_cpu_to_le32(0xC0020037) -#define RPC_NT_INCOMPLETE_NAME __constant_cpu_to_le32(0xC0020038) -#define RPC_NT_INVALID_VERS_OPTION __constant_cpu_to_le32(0xC0020039) -#define RPC_NT_NO_MORE_MEMBERS __constant_cpu_to_le32(0xC002003A) -#define RPC_NT_NOT_ALL_OBJS_UNEXPORTED __constant_cpu_to_le32(0xC002003B) -#define RPC_NT_INTERFACE_NOT_FOUND __constant_cpu_to_le32(0xC002003C) -#define RPC_NT_ENTRY_ALREADY_EXISTS __constant_cpu_to_le32(0xC002003D) -#define RPC_NT_ENTRY_NOT_FOUND __constant_cpu_to_le32(0xC002003E) -#define RPC_NT_NAME_SERVICE_UNAVAILABLE __constant_cpu_to_le32(0xC002003F) -#define RPC_NT_INVALID_NAF_ID __constant_cpu_to_le32(0xC0020040) -#define RPC_NT_CANNOT_SUPPORT __constant_cpu_to_le32(0xC0020041) -#define RPC_NT_NO_CONTEXT_AVAILABLE __constant_cpu_to_le32(0xC0020042) -#define RPC_NT_INTERNAL_ERROR __constant_cpu_to_le32(0xC0020043) -#define RPC_NT_ZERO_DIVIDE __constant_cpu_to_le32(0xC0020044) -#define RPC_NT_ADDRESS_ERROR __constant_cpu_to_le32(0xC0020045) -#define RPC_NT_FP_DIV_ZERO __constant_cpu_to_le32(0xC0020046) -#define RPC_NT_FP_UNDERFLOW __constant_cpu_to_le32(0xC0020047) -#define RPC_NT_FP_OVERFLOW __constant_cpu_to_le32(0xC0020048) -#define RPC_NT_CALL_IN_PROGRESS __constant_cpu_to_le32(0xC0020049) -#define RPC_NT_NO_MORE_BINDINGS __constant_cpu_to_le32(0xC002004A) -#define RPC_NT_GROUP_MEMBER_NOT_FOUND __constant_cpu_to_le32(0xC002004B) -#define EPT_NT_CANT_CREATE __constant_cpu_to_le32(0xC002004C) -#define RPC_NT_INVALID_OBJECT __constant_cpu_to_le32(0xC002004D) -#define RPC_NT_NO_INTERFACES __constant_cpu_to_le32(0xC002004F) -#define RPC_NT_CALL_CANCELLED __constant_cpu_to_le32(0xC0020050) -#define RPC_NT_BINDING_INCOMPLETE __constant_cpu_to_le32(0xC0020051) -#define RPC_NT_COMM_FAILURE __constant_cpu_to_le32(0xC0020052) -#define RPC_NT_UNSUPPORTED_AUTHN_LEVEL __constant_cpu_to_le32(0xC0020053) -#define RPC_NT_NO_PRINC_NAME __constant_cpu_to_le32(0xC0020054) -#define RPC_NT_NOT_RPC_ERROR __constant_cpu_to_le32(0xC0020055) -#define RPC_NT_SEC_PKG_ERROR __constant_cpu_to_le32(0xC0020057) -#define RPC_NT_NOT_CANCELLED __constant_cpu_to_le32(0xC0020058) -#define RPC_NT_INVALID_ASYNC_HANDLE __constant_cpu_to_le32(0xC0020062) -#define RPC_NT_INVALID_ASYNC_CALL __constant_cpu_to_le32(0xC0020063) -#define RPC_NT_PROXY_ACCESS_DENIED __constant_cpu_to_le32(0xC0020064) -#define RPC_NT_NO_MORE_ENTRIES __constant_cpu_to_le32(0xC0030001) -#define RPC_NT_SS_CHAR_TRANS_OPEN_FAIL __constant_cpu_to_le32(0xC0030002) -#define RPC_NT_SS_CHAR_TRANS_SHORT_FILE __constant_cpu_to_le32(0xC0030003) -#define RPC_NT_SS_IN_NULL_CONTEXT __constant_cpu_to_le32(0xC0030004) -#define RPC_NT_SS_CONTEXT_MISMATCH __constant_cpu_to_le32(0xC0030005) -#define RPC_NT_SS_CONTEXT_DAMAGED __constant_cpu_to_le32(0xC0030006) -#define RPC_NT_SS_HANDLES_MISMATCH __constant_cpu_to_le32(0xC0030007) -#define RPC_NT_SS_CANNOT_GET_CALL_HANDLE __constant_cpu_to_le32(0xC0030008) -#define RPC_NT_NULL_REF_POINTER __constant_cpu_to_le32(0xC0030009) -#define RPC_NT_ENUM_VALUE_OUT_OF_RANGE __constant_cpu_to_le32(0xC003000A) -#define RPC_NT_BYTE_COUNT_TOO_SMALL __constant_cpu_to_le32(0xC003000B) -#define RPC_NT_BAD_STUB_DATA __constant_cpu_to_le32(0xC003000C) -#define RPC_NT_INVALID_ES_ACTION __constant_cpu_to_le32(0xC0030059) -#define RPC_NT_WRONG_ES_VERSION __constant_cpu_to_le32(0xC003005A) -#define RPC_NT_WRONG_STUB_VERSION __constant_cpu_to_le32(0xC003005B) -#define RPC_NT_INVALID_PIPE_OBJECT __constant_cpu_to_le32(0xC003005C) -#define RPC_NT_INVALID_PIPE_OPERATION __constant_cpu_to_le32(0xC003005D) -#define RPC_NT_WRONG_PIPE_VERSION __constant_cpu_to_le32(0xC003005E) -#define RPC_NT_PIPE_CLOSED __constant_cpu_to_le32(0xC003005F) -#define RPC_NT_PIPE_DISCIPLINE_ERROR __constant_cpu_to_le32(0xC0030060) -#define RPC_NT_PIPE_EMPTY __constant_cpu_to_le32(0xC0030061) -#define STATUS_PNP_BAD_MPS_TABLE __constant_cpu_to_le32(0xC0040035) -#define STATUS_PNP_TRANSLATION_FAILED __constant_cpu_to_le32(0xC0040036) -#define STATUS_PNP_IRQ_TRANSLATION_FAILED __constant_cpu_to_le32(0xC0040037) -#define STATUS_PNP_INVALID_ID __constant_cpu_to_le32(0xC0040038) -#define STATUS_IO_REISSUE_AS_CACHED __constant_cpu_to_le32(0xC0040039) -#define STATUS_CTX_WINSTATION_NAME_INVALID __constant_cpu_to_le32(0xC00A0001) -#define STATUS_CTX_INVALID_PD __constant_cpu_to_le32(0xC00A0002) -#define STATUS_CTX_PD_NOT_FOUND __constant_cpu_to_le32(0xC00A0003) -#define STATUS_CTX_CLOSE_PENDING __constant_cpu_to_le32(0xC00A0006) -#define STATUS_CTX_NO_OUTBUF __constant_cpu_to_le32(0xC00A0007) -#define STATUS_CTX_MODEM_INF_NOT_FOUND __constant_cpu_to_le32(0xC00A0008) -#define STATUS_CTX_INVALID_MODEMNAME __constant_cpu_to_le32(0xC00A0009) -#define STATUS_CTX_RESPONSE_ERROR __constant_cpu_to_le32(0xC00A000A) -#define STATUS_CTX_MODEM_RESPONSE_TIMEOUT __constant_cpu_to_le32(0xC00A000B) -#define STATUS_CTX_MODEM_RESPONSE_NO_CARRIER __constant_cpu_to_le32(0xC00A000C) -#define STATUS_CTX_MODEM_RESPONSE_NO_DIALTONE __constant_cpu_to_le32(0xC00A000D) -#define STATUS_CTX_MODEM_RESPONSE_BUSY __constant_cpu_to_le32(0xC00A000E) -#define STATUS_CTX_MODEM_RESPONSE_VOICE __constant_cpu_to_le32(0xC00A000F) -#define STATUS_CTX_TD_ERROR __constant_cpu_to_le32(0xC00A0010) -#define STATUS_CTX_LICENSE_CLIENT_INVALID __constant_cpu_to_le32(0xC00A0012) -#define STATUS_CTX_LICENSE_NOT_AVAILABLE __constant_cpu_to_le32(0xC00A0013) -#define STATUS_CTX_LICENSE_EXPIRED __constant_cpu_to_le32(0xC00A0014) -#define STATUS_CTX_WINSTATION_NOT_FOUND __constant_cpu_to_le32(0xC00A0015) -#define STATUS_CTX_WINSTATION_NAME_COLLISION __constant_cpu_to_le32(0xC00A0016) -#define STATUS_CTX_WINSTATION_BUSY __constant_cpu_to_le32(0xC00A0017) -#define STATUS_CTX_BAD_VIDEO_MODE __constant_cpu_to_le32(0xC00A0018) -#define STATUS_CTX_GRAPHICS_INVALID __constant_cpu_to_le32(0xC00A0022) -#define STATUS_CTX_NOT_CONSOLE __constant_cpu_to_le32(0xC00A0024) -#define STATUS_CTX_CLIENT_QUERY_TIMEOUT __constant_cpu_to_le32(0xC00A0026) -#define STATUS_CTX_CONSOLE_DISCONNECT __constant_cpu_to_le32(0xC00A0027) -#define STATUS_CTX_CONSOLE_CONNECT __constant_cpu_to_le32(0xC00A0028) -#define STATUS_CTX_SHADOW_DENIED __constant_cpu_to_le32(0xC00A002A) -#define STATUS_CTX_WINSTATION_ACCESS_DENIED __constant_cpu_to_le32(0xC00A002B) -#define STATUS_CTX_INVALID_WD __constant_cpu_to_le32(0xC00A002E) -#define STATUS_CTX_WD_NOT_FOUND __constant_cpu_to_le32(0xC00A002F) -#define STATUS_CTX_SHADOW_INVALID __constant_cpu_to_le32(0xC00A0030) -#define STATUS_CTX_SHADOW_DISABLED __constant_cpu_to_le32(0xC00A0031) -#define STATUS_RDP_PROTOCOL_ERROR __constant_cpu_to_le32(0xC00A0032) -#define STATUS_CTX_CLIENT_LICENSE_NOT_SET __constant_cpu_to_le32(0xC00A0033) -#define STATUS_CTX_CLIENT_LICENSE_IN_USE __constant_cpu_to_le32(0xC00A0034) -#define STATUS_CTX_SHADOW_ENDED_BY_MODE_CHANGE __constant_cpu_to_le32(0xC00A0035) -#define STATUS_CTX_SHADOW_NOT_RUNNING __constant_cpu_to_le32(0xC00A0036) -#define STATUS_CTX_LOGON_DISABLED __constant_cpu_to_le32(0xC00A0037) -#define STATUS_CTX_SECURITY_LAYER_ERROR __constant_cpu_to_le32(0xC00A0038) -#define STATUS_TS_INCOMPATIBLE_SESSIONS __constant_cpu_to_le32(0xC00A0039) -#define STATUS_MUI_FILE_NOT_FOUND __constant_cpu_to_le32(0xC00B0001) -#define STATUS_MUI_INVALID_FILE __constant_cpu_to_le32(0xC00B0002) -#define STATUS_MUI_INVALID_RC_CONFIG __constant_cpu_to_le32(0xC00B0003) -#define STATUS_MUI_INVALID_LOCALE_NAME __constant_cpu_to_le32(0xC00B0004) -#define STATUS_MUI_INVALID_ULTIMATEFALLBACK_NAME __constant_cpu_to_le32(0xC00B0005) -#define STATUS_MUI_FILE_NOT_LOADED __constant_cpu_to_le32(0xC00B0006) -#define STATUS_RESOURCE_ENUM_USER_STOP __constant_cpu_to_le32(0xC00B0007) -#define STATUS_CLUSTER_INVALID_NODE __constant_cpu_to_le32(0xC0130001) -#define STATUS_CLUSTER_NODE_EXISTS __constant_cpu_to_le32(0xC0130002) -#define STATUS_CLUSTER_JOIN_IN_PROGRESS __constant_cpu_to_le32(0xC0130003) -#define STATUS_CLUSTER_NODE_NOT_FOUND __constant_cpu_to_le32(0xC0130004) -#define STATUS_CLUSTER_LOCAL_NODE_NOT_FOUND __constant_cpu_to_le32(0xC0130005) -#define STATUS_CLUSTER_NETWORK_EXISTS __constant_cpu_to_le32(0xC0130006) -#define STATUS_CLUSTER_NETWORK_NOT_FOUND __constant_cpu_to_le32(0xC0130007) -#define STATUS_CLUSTER_NETINTERFACE_EXISTS __constant_cpu_to_le32(0xC0130008) -#define STATUS_CLUSTER_NETINTERFACE_NOT_FOUND __constant_cpu_to_le32(0xC0130009) -#define STATUS_CLUSTER_INVALID_REQUEST __constant_cpu_to_le32(0xC013000A) -#define STATUS_CLUSTER_INVALID_NETWORK_PROVIDER __constant_cpu_to_le32(0xC013000B) -#define STATUS_CLUSTER_NODE_DOWN __constant_cpu_to_le32(0xC013000C) -#define STATUS_CLUSTER_NODE_UNREACHABLE __constant_cpu_to_le32(0xC013000D) -#define STATUS_CLUSTER_NODE_NOT_MEMBER __constant_cpu_to_le32(0xC013000E) -#define STATUS_CLUSTER_JOIN_NOT_IN_PROGRESS __constant_cpu_to_le32(0xC013000F) -#define STATUS_CLUSTER_INVALID_NETWORK __constant_cpu_to_le32(0xC0130010) -#define STATUS_CLUSTER_NO_NET_ADAPTERS __constant_cpu_to_le32(0xC0130011) -#define STATUS_CLUSTER_NODE_UP __constant_cpu_to_le32(0xC0130012) -#define STATUS_CLUSTER_NODE_PAUSED __constant_cpu_to_le32(0xC0130013) -#define STATUS_CLUSTER_NODE_NOT_PAUSED __constant_cpu_to_le32(0xC0130014) -#define STATUS_CLUSTER_NO_SECURITY_CONTEXT __constant_cpu_to_le32(0xC0130015) -#define STATUS_CLUSTER_NETWORK_NOT_INTERNAL __constant_cpu_to_le32(0xC0130016) -#define STATUS_CLUSTER_POISONED __constant_cpu_to_le32(0xC0130017) -#define STATUS_ACPI_INVALID_OPCODE __constant_cpu_to_le32(0xC0140001) -#define STATUS_ACPI_STACK_OVERFLOW __constant_cpu_to_le32(0xC0140002) -#define STATUS_ACPI_ASSERT_FAILED __constant_cpu_to_le32(0xC0140003) -#define STATUS_ACPI_INVALID_INDEX __constant_cpu_to_le32(0xC0140004) -#define STATUS_ACPI_INVALID_ARGUMENT __constant_cpu_to_le32(0xC0140005) -#define STATUS_ACPI_FATAL __constant_cpu_to_le32(0xC0140006) -#define STATUS_ACPI_INVALID_SUPERNAME __constant_cpu_to_le32(0xC0140007) -#define STATUS_ACPI_INVALID_ARGTYPE __constant_cpu_to_le32(0xC0140008) -#define STATUS_ACPI_INVALID_OBJTYPE __constant_cpu_to_le32(0xC0140009) -#define STATUS_ACPI_INVALID_TARGETTYPE __constant_cpu_to_le32(0xC014000A) -#define STATUS_ACPI_INCORRECT_ARGUMENT_COUNT __constant_cpu_to_le32(0xC014000B) -#define STATUS_ACPI_ADDRESS_NOT_MAPPED __constant_cpu_to_le32(0xC014000C) -#define STATUS_ACPI_INVALID_EVENTTYPE __constant_cpu_to_le32(0xC014000D) -#define STATUS_ACPI_HANDLER_COLLISION __constant_cpu_to_le32(0xC014000E) -#define STATUS_ACPI_INVALID_DATA __constant_cpu_to_le32(0xC014000F) -#define STATUS_ACPI_INVALID_REGION __constant_cpu_to_le32(0xC0140010) -#define STATUS_ACPI_INVALID_ACCESS_SIZE __constant_cpu_to_le32(0xC0140011) -#define STATUS_ACPI_ACQUIRE_GLOBAL_LOCK __constant_cpu_to_le32(0xC0140012) -#define STATUS_ACPI_ALREADY_INITIALIZED __constant_cpu_to_le32(0xC0140013) -#define STATUS_ACPI_NOT_INITIALIZED __constant_cpu_to_le32(0xC0140014) -#define STATUS_ACPI_INVALID_MUTEX_LEVEL __constant_cpu_to_le32(0xC0140015) -#define STATUS_ACPI_MUTEX_NOT_OWNED __constant_cpu_to_le32(0xC0140016) -#define STATUS_ACPI_MUTEX_NOT_OWNER __constant_cpu_to_le32(0xC0140017) -#define STATUS_ACPI_RS_ACCESS __constant_cpu_to_le32(0xC0140018) -#define STATUS_ACPI_INVALID_TABLE __constant_cpu_to_le32(0xC0140019) -#define STATUS_ACPI_REG_HANDLER_FAILED __constant_cpu_to_le32(0xC0140020) -#define STATUS_ACPI_POWER_REQUEST_FAILED __constant_cpu_to_le32(0xC0140021) -#define STATUS_SXS_SECTION_NOT_FOUND __constant_cpu_to_le32(0xC0150001) -#define STATUS_SXS_CANT_GEN_ACTCTX __constant_cpu_to_le32(0xC0150002) -#define STATUS_SXS_INVALID_ACTCTXDATA_FORMAT __constant_cpu_to_le32(0xC0150003) -#define STATUS_SXS_ASSEMBLY_NOT_FOUND __constant_cpu_to_le32(0xC0150004) -#define STATUS_SXS_MANIFEST_FORMAT_ERROR __constant_cpu_to_le32(0xC0150005) -#define STATUS_SXS_MANIFEST_PARSE_ERROR __constant_cpu_to_le32(0xC0150006) -#define STATUS_SXS_ACTIVATION_CONTEXT_DISABLED __constant_cpu_to_le32(0xC0150007) -#define STATUS_SXS_KEY_NOT_FOUND __constant_cpu_to_le32(0xC0150008) -#define STATUS_SXS_VERSION_CONFLICT __constant_cpu_to_le32(0xC0150009) -#define STATUS_SXS_WRONG_SECTION_TYPE __constant_cpu_to_le32(0xC015000A) -#define STATUS_SXS_THREAD_QUERIES_DISABLED __constant_cpu_to_le32(0xC015000B) -#define STATUS_SXS_ASSEMBLY_MISSING __constant_cpu_to_le32(0xC015000C) -#define STATUS_SXS_PROCESS_DEFAULT_ALREADY_SET __constant_cpu_to_le32(0xC015000E) -#define STATUS_SXS_EARLY_DEACTIVATION __constant_cpu_to_le32(0xC015000F) -#define STATUS_SXS_INVALID_DEACTIVATION __constant_cpu_to_le32(0xC0150010) -#define STATUS_SXS_MULTIPLE_DEACTIVATION __constant_cpu_to_le32(0xC0150011) -#define STATUS_SXS_SYSTEM_DEFAULT_ACTIVATION_CONTEXT_EMPTY __constant_cpu_to_le32(0xC0150012) -#define STATUS_SXS_PROCESS_TERMINATION_REQUESTED __constant_cpu_to_le32(0xC0150013) -#define STATUS_SXS_CORRUPT_ACTIVATION_STACK __constant_cpu_to_le32(0xC0150014) -#define STATUS_SXS_CORRUPTION __constant_cpu_to_le32(0xC0150015) -#define STATUS_SXS_INVALID_IDENTITY_ATTRIBUTE_VALUE __constant_cpu_to_le32(0xC0150016) -#define STATUS_SXS_INVALID_IDENTITY_ATTRIBUTE_NAME __constant_cpu_to_le32(0xC0150017) -#define STATUS_SXS_IDENTITY_DUPLICATE_ATTRIBUTE __constant_cpu_to_le32(0xC0150018) -#define STATUS_SXS_IDENTITY_PARSE_ERROR __constant_cpu_to_le32(0xC0150019) -#define STATUS_SXS_COMPONENT_STORE_CORRUPT __constant_cpu_to_le32(0xC015001A) -#define STATUS_SXS_FILE_HASH_MISMATCH __constant_cpu_to_le32(0xC015001B) -#define STATUS_SXS_MANIFEST_IDENTITY_SAME_BUT_CONTENTS_DIFFERENT __constant_cpu_to_le32(0xC015001C) -#define STATUS_SXS_IDENTITIES_DIFFERENT __constant_cpu_to_le32(0xC015001D) -#define STATUS_SXS_ASSEMBLY_IS_NOT_A_DEPLOYMENT __constant_cpu_to_le32(0xC015001E) -#define STATUS_SXS_FILE_NOT_PART_OF_ASSEMBLY __constant_cpu_to_le32(0xC015001F) -#define STATUS_ADVANCED_INSTALLER_FAILED __constant_cpu_to_le32(0xC0150020) -#define STATUS_XML_ENCODING_MISMATCH __constant_cpu_to_le32(0xC0150021) -#define STATUS_SXS_MANIFEST_TOO_BIG __constant_cpu_to_le32(0xC0150022) -#define STATUS_SXS_SETTING_NOT_REGISTERED __constant_cpu_to_le32(0xC0150023) -#define STATUS_SXS_TRANSACTION_CLOSURE_INCOMPLETE __constant_cpu_to_le32(0xC0150024) -#define STATUS_SMI_PRIMITIVE_INSTALLER_FAILED __constant_cpu_to_le32(0xC0150025) -#define STATUS_GENERIC_COMMAND_FAILED __constant_cpu_to_le32(0xC0150026) -#define STATUS_SXS_FILE_HASH_MISSING __constant_cpu_to_le32(0xC0150027) -#define STATUS_TRANSACTIONAL_CONFLICT __constant_cpu_to_le32(0xC0190001) -#define STATUS_INVALID_TRANSACTION __constant_cpu_to_le32(0xC0190002) -#define STATUS_TRANSACTION_NOT_ACTIVE __constant_cpu_to_le32(0xC0190003) -#define STATUS_TM_INITIALIZATION_FAILED __constant_cpu_to_le32(0xC0190004) -#define STATUS_RM_NOT_ACTIVE __constant_cpu_to_le32(0xC0190005) -#define STATUS_RM_METADATA_CORRUPT __constant_cpu_to_le32(0xC0190006) -#define STATUS_TRANSACTION_NOT_JOINED __constant_cpu_to_le32(0xC0190007) -#define STATUS_DIRECTORY_NOT_RM __constant_cpu_to_le32(0xC0190008) -#define STATUS_TRANSACTIONS_UNSUPPORTED_REMOTE __constant_cpu_to_le32(0xC019000A) -#define STATUS_LOG_RESIZE_INVALID_SIZE __constant_cpu_to_le32(0xC019000B) -#define STATUS_REMOTE_FILE_VERSION_MISMATCH __constant_cpu_to_le32(0xC019000C) -#define STATUS_CRM_PROTOCOL_ALREADY_EXISTS __constant_cpu_to_le32(0xC019000F) -#define STATUS_TRANSACTION_PROPAGATION_FAILED __constant_cpu_to_le32(0xC0190010) -#define STATUS_CRM_PROTOCOL_NOT_FOUND __constant_cpu_to_le32(0xC0190011) -#define STATUS_TRANSACTION_SUPERIOR_EXISTS __constant_cpu_to_le32(0xC0190012) -#define STATUS_TRANSACTION_REQUEST_NOT_VALID __constant_cpu_to_le32(0xC0190013) -#define STATUS_TRANSACTION_NOT_REQUESTED __constant_cpu_to_le32(0xC0190014) -#define STATUS_TRANSACTION_ALREADY_ABORTED __constant_cpu_to_le32(0xC0190015) -#define STATUS_TRANSACTION_ALREADY_COMMITTED __constant_cpu_to_le32(0xC0190016) -#define STATUS_TRANSACTION_INVALID_MARSHALL_BUFFER __constant_cpu_to_le32(0xC0190017) -#define STATUS_CURRENT_TRANSACTION_NOT_VALID __constant_cpu_to_le32(0xC0190018) -#define STATUS_LOG_GROWTH_FAILED __constant_cpu_to_le32(0xC0190019) -#define STATUS_OBJECT_NO_LONGER_EXISTS __constant_cpu_to_le32(0xC0190021) -#define STATUS_STREAM_MINIVERSION_NOT_FOUND __constant_cpu_to_le32(0xC0190022) -#define STATUS_STREAM_MINIVERSION_NOT_VALID __constant_cpu_to_le32(0xC0190023) -#define STATUS_MINIVERSION_INACCESSIBLE_FROM_SPECIFIED_TRANSACTION __constant_cpu_to_le32(0xC0190024) -#define STATUS_CANT_OPEN_MINIVERSION_WITH_MODIFY_INTENT __constant_cpu_to_le32(0xC0190025) -#define STATUS_CANT_CREATE_MORE_STREAM_MINIVERSIONS __constant_cpu_to_le32(0xC0190026) -#define STATUS_HANDLE_NO_LONGER_VALID __constant_cpu_to_le32(0xC0190028) -#define STATUS_LOG_CORRUPTION_DETECTED __constant_cpu_to_le32(0xC0190030) -#define STATUS_RM_DISCONNECTED __constant_cpu_to_le32(0xC0190032) -#define STATUS_ENLISTMENT_NOT_SUPERIOR __constant_cpu_to_le32(0xC0190033) -#define STATUS_FILE_IDENTITY_NOT_PERSISTENT __constant_cpu_to_le32(0xC0190036) -#define STATUS_CANT_BREAK_TRANSACTIONAL_DEPENDENCY __constant_cpu_to_le32(0xC0190037) -#define STATUS_CANT_CROSS_RM_BOUNDARY __constant_cpu_to_le32(0xC0190038) -#define STATUS_TXF_DIR_NOT_EMPTY __constant_cpu_to_le32(0xC0190039) -#define STATUS_INDOUBT_TRANSACTIONS_EXIST __constant_cpu_to_le32(0xC019003A) -#define STATUS_TM_VOLATILE __constant_cpu_to_le32(0xC019003B) -#define STATUS_ROLLBACK_TIMER_EXPIRED __constant_cpu_to_le32(0xC019003C) -#define STATUS_TXF_ATTRIBUTE_CORRUPT __constant_cpu_to_le32(0xC019003D) -#define STATUS_EFS_NOT_ALLOWED_IN_TRANSACTION __constant_cpu_to_le32(0xC019003E) -#define STATUS_TRANSACTIONAL_OPEN_NOT_ALLOWED __constant_cpu_to_le32(0xC019003F) -#define STATUS_TRANSACTED_MAPPING_UNSUPPORTED_REMOTE __constant_cpu_to_le32(0xC0190040) -#define STATUS_TRANSACTION_REQUIRED_PROMOTION __constant_cpu_to_le32(0xC0190043) -#define STATUS_CANNOT_EXECUTE_FILE_IN_TRANSACTION __constant_cpu_to_le32(0xC0190044) -#define STATUS_TRANSACTIONS_NOT_FROZEN __constant_cpu_to_le32(0xC0190045) -#define STATUS_TRANSACTION_FREEZE_IN_PROGRESS __constant_cpu_to_le32(0xC0190046) -#define STATUS_NOT_SNAPSHOT_VOLUME __constant_cpu_to_le32(0xC0190047) -#define STATUS_NO_SAVEPOINT_WITH_OPEN_FILES __constant_cpu_to_le32(0xC0190048) -#define STATUS_SPARSE_NOT_ALLOWED_IN_TRANSACTION __constant_cpu_to_le32(0xC0190049) -#define STATUS_TM_IDENTITY_MISMATCH __constant_cpu_to_le32(0xC019004A) -#define STATUS_FLOATED_SECTION __constant_cpu_to_le32(0xC019004B) -#define STATUS_CANNOT_ACCEPT_TRANSACTED_WORK __constant_cpu_to_le32(0xC019004C) -#define STATUS_CANNOT_ABORT_TRANSACTIONS __constant_cpu_to_le32(0xC019004D) -#define STATUS_TRANSACTION_NOT_FOUND __constant_cpu_to_le32(0xC019004E) -#define STATUS_RESOURCEMANAGER_NOT_FOUND __constant_cpu_to_le32(0xC019004F) -#define STATUS_ENLISTMENT_NOT_FOUND __constant_cpu_to_le32(0xC0190050) -#define STATUS_TRANSACTIONMANAGER_NOT_FOUND __constant_cpu_to_le32(0xC0190051) -#define STATUS_TRANSACTIONMANAGER_NOT_ONLINE __constant_cpu_to_le32(0xC0190052) -#define STATUS_TRANSACTIONMANAGER_RECOVERY_NAME_COLLISION __constant_cpu_to_le32(0xC0190053) -#define STATUS_TRANSACTION_NOT_ROOT __constant_cpu_to_le32(0xC0190054) -#define STATUS_TRANSACTION_OBJECT_EXPIRED __constant_cpu_to_le32(0xC0190055) -#define STATUS_COMPRESSION_NOT_ALLOWED_IN_TRANSACTION __constant_cpu_to_le32(0xC0190056) -#define STATUS_TRANSACTION_RESPONSE_NOT_ENLISTED __constant_cpu_to_le32(0xC0190057) -#define STATUS_TRANSACTION_RECORD_TOO_LONG __constant_cpu_to_le32(0xC0190058) -#define STATUS_NO_LINK_TRACKING_IN_TRANSACTION __constant_cpu_to_le32(0xC0190059) -#define STATUS_OPERATION_NOT_SUPPORTED_IN_TRANSACTION __constant_cpu_to_le32(0xC019005A) -#define STATUS_TRANSACTION_INTEGRITY_VIOLATED __constant_cpu_to_le32(0xC019005B) -#define STATUS_LOG_SECTOR_INVALID __constant_cpu_to_le32(0xC01A0001) -#define STATUS_LOG_SECTOR_PARITY_INVALID __constant_cpu_to_le32(0xC01A0002) -#define STATUS_LOG_SECTOR_REMAPPED __constant_cpu_to_le32(0xC01A0003) -#define STATUS_LOG_BLOCK_INCOMPLETE __constant_cpu_to_le32(0xC01A0004) -#define STATUS_LOG_INVALID_RANGE __constant_cpu_to_le32(0xC01A0005) -#define STATUS_LOG_BLOCKS_EXHAUSTED __constant_cpu_to_le32(0xC01A0006) -#define STATUS_LOG_READ_CONTEXT_INVALID __constant_cpu_to_le32(0xC01A0007) -#define STATUS_LOG_RESTART_INVALID __constant_cpu_to_le32(0xC01A0008) -#define STATUS_LOG_BLOCK_VERSION __constant_cpu_to_le32(0xC01A0009) -#define STATUS_LOG_BLOCK_INVALID __constant_cpu_to_le32(0xC01A000A) -#define STATUS_LOG_READ_MODE_INVALID __constant_cpu_to_le32(0xC01A000B) -#define STATUS_LOG_METADATA_CORRUPT __constant_cpu_to_le32(0xC01A000D) -#define STATUS_LOG_METADATA_INVALID __constant_cpu_to_le32(0xC01A000E) -#define STATUS_LOG_METADATA_INCONSISTENT __constant_cpu_to_le32(0xC01A000F) -#define STATUS_LOG_RESERVATION_INVALID __constant_cpu_to_le32(0xC01A0010) -#define STATUS_LOG_CANT_DELETE __constant_cpu_to_le32(0xC01A0011) -#define STATUS_LOG_CONTAINER_LIMIT_EXCEEDED __constant_cpu_to_le32(0xC01A0012) -#define STATUS_LOG_START_OF_LOG __constant_cpu_to_le32(0xC01A0013) -#define STATUS_LOG_POLICY_ALREADY_INSTALLED __constant_cpu_to_le32(0xC01A0014) -#define STATUS_LOG_POLICY_NOT_INSTALLED __constant_cpu_to_le32(0xC01A0015) -#define STATUS_LOG_POLICY_INVALID __constant_cpu_to_le32(0xC01A0016) -#define STATUS_LOG_POLICY_CONFLICT __constant_cpu_to_le32(0xC01A0017) -#define STATUS_LOG_PINNED_ARCHIVE_TAIL __constant_cpu_to_le32(0xC01A0018) -#define STATUS_LOG_RECORD_NONEXISTENT __constant_cpu_to_le32(0xC01A0019) -#define STATUS_LOG_RECORDS_RESERVED_INVALID __constant_cpu_to_le32(0xC01A001A) -#define STATUS_LOG_SPACE_RESERVED_INVALID __constant_cpu_to_le32(0xC01A001B) -#define STATUS_LOG_TAIL_INVALID __constant_cpu_to_le32(0xC01A001C) -#define STATUS_LOG_FULL __constant_cpu_to_le32(0xC01A001D) -#define STATUS_LOG_MULTIPLEXED __constant_cpu_to_le32(0xC01A001E) -#define STATUS_LOG_DEDICATED __constant_cpu_to_le32(0xC01A001F) -#define STATUS_LOG_ARCHIVE_NOT_IN_PROGRESS __constant_cpu_to_le32(0xC01A0020) -#define STATUS_LOG_ARCHIVE_IN_PROGRESS __constant_cpu_to_le32(0xC01A0021) -#define STATUS_LOG_EPHEMERAL __constant_cpu_to_le32(0xC01A0022) -#define STATUS_LOG_NOT_ENOUGH_CONTAINERS __constant_cpu_to_le32(0xC01A0023) -#define STATUS_LOG_CLIENT_ALREADY_REGISTERED __constant_cpu_to_le32(0xC01A0024) -#define STATUS_LOG_CLIENT_NOT_REGISTERED __constant_cpu_to_le32(0xC01A0025) -#define STATUS_LOG_FULL_HANDLER_IN_PROGRESS __constant_cpu_to_le32(0xC01A0026) -#define STATUS_LOG_CONTAINER_READ_FAILED __constant_cpu_to_le32(0xC01A0027) -#define STATUS_LOG_CONTAINER_WRITE_FAILED __constant_cpu_to_le32(0xC01A0028) -#define STATUS_LOG_CONTAINER_OPEN_FAILED __constant_cpu_to_le32(0xC01A0029) -#define STATUS_LOG_CONTAINER_STATE_INVALID __constant_cpu_to_le32(0xC01A002A) -#define STATUS_LOG_STATE_INVALID __constant_cpu_to_le32(0xC01A002B) -#define STATUS_LOG_PINNED __constant_cpu_to_le32(0xC01A002C) -#define STATUS_LOG_METADATA_FLUSH_FAILED __constant_cpu_to_le32(0xC01A002D) -#define STATUS_LOG_INCONSISTENT_SECURITY __constant_cpu_to_le32(0xC01A002E) -#define STATUS_LOG_APPENDED_FLUSH_FAILED __constant_cpu_to_le32(0xC01A002F) -#define STATUS_LOG_PINNED_RESERVATION __constant_cpu_to_le32(0xC01A0030) -#define STATUS_VIDEO_HUNG_DISPLAY_DRIVER_THREAD __constant_cpu_to_le32(0xC01B00EA) -#define STATUS_FLT_NO_HANDLER_DEFINED __constant_cpu_to_le32(0xC01C0001) -#define STATUS_FLT_CONTEXT_ALREADY_DEFINED __constant_cpu_to_le32(0xC01C0002) -#define STATUS_FLT_INVALID_ASYNCHRONOUS_REQUEST __constant_cpu_to_le32(0xC01C0003) -#define STATUS_FLT_DISALLOW_FAST_IO __constant_cpu_to_le32(0xC01C0004) -#define STATUS_FLT_INVALID_NAME_REQUEST __constant_cpu_to_le32(0xC01C0005) -#define STATUS_FLT_NOT_SAFE_TO_POST_OPERATION __constant_cpu_to_le32(0xC01C0006) -#define STATUS_FLT_NOT_INITIALIZED __constant_cpu_to_le32(0xC01C0007) -#define STATUS_FLT_FILTER_NOT_READY __constant_cpu_to_le32(0xC01C0008) -#define STATUS_FLT_POST_OPERATION_CLEANUP __constant_cpu_to_le32(0xC01C0009) -#define STATUS_FLT_INTERNAL_ERROR __constant_cpu_to_le32(0xC01C000A) -#define STATUS_FLT_DELETING_OBJECT __constant_cpu_to_le32(0xC01C000B) -#define STATUS_FLT_MUST_BE_NONPAGED_POOL __constant_cpu_to_le32(0xC01C000C) -#define STATUS_FLT_DUPLICATE_ENTRY __constant_cpu_to_le32(0xC01C000D) -#define STATUS_FLT_CBDQ_DISABLED __constant_cpu_to_le32(0xC01C000E) -#define STATUS_FLT_DO_NOT_ATTACH __constant_cpu_to_le32(0xC01C000F) -#define STATUS_FLT_DO_NOT_DETACH __constant_cpu_to_le32(0xC01C0010) -#define STATUS_FLT_INSTANCE_ALTITUDE_COLLISION __constant_cpu_to_le32(0xC01C0011) -#define STATUS_FLT_INSTANCE_NAME_COLLISION __constant_cpu_to_le32(0xC01C0012) -#define STATUS_FLT_FILTER_NOT_FOUND __constant_cpu_to_le32(0xC01C0013) -#define STATUS_FLT_VOLUME_NOT_FOUND __constant_cpu_to_le32(0xC01C0014) -#define STATUS_FLT_INSTANCE_NOT_FOUND __constant_cpu_to_le32(0xC01C0015) -#define STATUS_FLT_CONTEXT_ALLOCATION_NOT_FOUND __constant_cpu_to_le32(0xC01C0016) -#define STATUS_FLT_INVALID_CONTEXT_REGISTRATION __constant_cpu_to_le32(0xC01C0017) -#define STATUS_FLT_NAME_CACHE_MISS __constant_cpu_to_le32(0xC01C0018) -#define STATUS_FLT_NO_DEVICE_OBJECT __constant_cpu_to_le32(0xC01C0019) -#define STATUS_FLT_VOLUME_ALREADY_MOUNTED __constant_cpu_to_le32(0xC01C001A) -#define STATUS_FLT_ALREADY_ENLISTED __constant_cpu_to_le32(0xC01C001B) -#define STATUS_FLT_CONTEXT_ALREADY_LINKED __constant_cpu_to_le32(0xC01C001C) -#define STATUS_FLT_NO_WAITER_FOR_REPLY __constant_cpu_to_le32(0xC01C0020) -#define STATUS_MONITOR_NO_DESCRIPTOR __constant_cpu_to_le32(0xC01D0001) -#define STATUS_MONITOR_UNKNOWN_DESCRIPTOR_FORMAT __constant_cpu_to_le32(0xC01D0002) -#define STATUS_MONITOR_INVALID_DESCRIPTOR_CHECKSUM __constant_cpu_to_le32(0xC01D0003) -#define STATUS_MONITOR_INVALID_STANDARD_TIMING_BLOCK __constant_cpu_to_le32(0xC01D0004) -#define STATUS_MONITOR_WMI_DATABLOCK_REGISTRATION_FAILED __constant_cpu_to_le32(0xC01D0005) -#define STATUS_MONITOR_INVALID_SERIAL_NUMBER_MONDSC_BLOCK __constant_cpu_to_le32(0xC01D0006) -#define STATUS_MONITOR_INVALID_USER_FRIENDLY_MONDSC_BLOCK __constant_cpu_to_le32(0xC01D0007) -#define STATUS_MONITOR_NO_MORE_DESCRIPTOR_DATA __constant_cpu_to_le32(0xC01D0008) -#define STATUS_MONITOR_INVALID_DETAILED_TIMING_BLOCK __constant_cpu_to_le32(0xC01D0009) -#define STATUS_GRAPHICS_NOT_EXCLUSIVE_MODE_OWNER __constant_cpu_to_le32(0xC01E0000) -#define STATUS_GRAPHICS_INSUFFICIENT_DMA_BUFFER __constant_cpu_to_le32(0xC01E0001) -#define STATUS_GRAPHICS_INVALID_DISPLAY_ADAPTER __constant_cpu_to_le32(0xC01E0002) -#define STATUS_GRAPHICS_ADAPTER_WAS_RESET __constant_cpu_to_le32(0xC01E0003) -#define STATUS_GRAPHICS_INVALID_DRIVER_MODEL __constant_cpu_to_le32(0xC01E0004) -#define STATUS_GRAPHICS_PRESENT_MODE_CHANGED __constant_cpu_to_le32(0xC01E0005) -#define STATUS_GRAPHICS_PRESENT_OCCLUDED __constant_cpu_to_le32(0xC01E0006) -#define STATUS_GRAPHICS_PRESENT_DENIED __constant_cpu_to_le32(0xC01E0007) -#define STATUS_GRAPHICS_CANNOTCOLORCONVERT __constant_cpu_to_le32(0xC01E0008) -#define STATUS_GRAPHICS_NO_VIDEO_MEMORY __constant_cpu_to_le32(0xC01E0100) -#define STATUS_GRAPHICS_CANT_LOCK_MEMORY __constant_cpu_to_le32(0xC01E0101) -#define STATUS_GRAPHICS_ALLOCATION_BUSY __constant_cpu_to_le32(0xC01E0102) -#define STATUS_GRAPHICS_TOO_MANY_REFERENCES __constant_cpu_to_le32(0xC01E0103) -#define STATUS_GRAPHICS_TRY_AGAIN_LATER __constant_cpu_to_le32(0xC01E0104) -#define STATUS_GRAPHICS_TRY_AGAIN_NOW __constant_cpu_to_le32(0xC01E0105) -#define STATUS_GRAPHICS_ALLOCATION_INVALID __constant_cpu_to_le32(0xC01E0106) -#define STATUS_GRAPHICS_UNSWIZZLING_APERTURE_UNAVAILABLE __constant_cpu_to_le32(0xC01E0107) -#define STATUS_GRAPHICS_UNSWIZZLING_APERTURE_UNSUPPORTED __constant_cpu_to_le32(0xC01E0108) -#define STATUS_GRAPHICS_CANT_EVICT_PINNED_ALLOCATION __constant_cpu_to_le32(0xC01E0109) -#define STATUS_GRAPHICS_INVALID_ALLOCATION_USAGE __constant_cpu_to_le32(0xC01E0110) -#define STATUS_GRAPHICS_CANT_RENDER_LOCKED_ALLOCATION __constant_cpu_to_le32(0xC01E0111) -#define STATUS_GRAPHICS_ALLOCATION_CLOSED __constant_cpu_to_le32(0xC01E0112) -#define STATUS_GRAPHICS_INVALID_ALLOCATION_INSTANCE __constant_cpu_to_le32(0xC01E0113) -#define STATUS_GRAPHICS_INVALID_ALLOCATION_HANDLE __constant_cpu_to_le32(0xC01E0114) -#define STATUS_GRAPHICS_WRONG_ALLOCATION_DEVICE __constant_cpu_to_le32(0xC01E0115) -#define STATUS_GRAPHICS_ALLOCATION_CONTENT_LOST __constant_cpu_to_le32(0xC01E0116) -#define STATUS_GRAPHICS_GPU_EXCEPTION_ON_DEVICE __constant_cpu_to_le32(0xC01E0200) -#define STATUS_GRAPHICS_INVALID_VIDPN_TOPOLOGY __constant_cpu_to_le32(0xC01E0300) -#define STATUS_GRAPHICS_VIDPN_TOPOLOGY_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0301) -#define STATUS_GRAPHICS_VIDPN_TOPOLOGY_CURRENTLY_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0302) -#define STATUS_GRAPHICS_INVALID_VIDPN __constant_cpu_to_le32(0xC01E0303) -#define STATUS_GRAPHICS_INVALID_VIDEO_PRESENT_SOURCE __constant_cpu_to_le32(0xC01E0304) -#define STATUS_GRAPHICS_INVALID_VIDEO_PRESENT_TARGET __constant_cpu_to_le32(0xC01E0305) -#define STATUS_GRAPHICS_VIDPN_MODALITY_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0306) -#define STATUS_GRAPHICS_INVALID_VIDPN_SOURCEMODESET __constant_cpu_to_le32(0xC01E0308) -#define STATUS_GRAPHICS_INVALID_VIDPN_TARGETMODESET __constant_cpu_to_le32(0xC01E0309) -#define STATUS_GRAPHICS_INVALID_FREQUENCY __constant_cpu_to_le32(0xC01E030A) -#define STATUS_GRAPHICS_INVALID_ACTIVE_REGION __constant_cpu_to_le32(0xC01E030B) -#define STATUS_GRAPHICS_INVALID_TOTAL_REGION __constant_cpu_to_le32(0xC01E030C) -#define STATUS_GRAPHICS_INVALID_VIDEO_PRESENT_SOURCE_MODE __constant_cpu_to_le32(0xC01E0310) -#define STATUS_GRAPHICS_INVALID_VIDEO_PRESENT_TARGET_MODE __constant_cpu_to_le32(0xC01E0311) -#define STATUS_GRAPHICS_PINNED_MODE_MUST_REMAIN_IN_SET __constant_cpu_to_le32(0xC01E0312) -#define STATUS_GRAPHICS_PATH_ALREADY_IN_TOPOLOGY __constant_cpu_to_le32(0xC01E0313) -#define STATUS_GRAPHICS_MODE_ALREADY_IN_MODESET __constant_cpu_to_le32(0xC01E0314) -#define STATUS_GRAPHICS_INVALID_VIDEOPRESENTSOURCESET __constant_cpu_to_le32(0xC01E0315) -#define STATUS_GRAPHICS_INVALID_VIDEOPRESENTTARGETSET __constant_cpu_to_le32(0xC01E0316) -#define STATUS_GRAPHICS_SOURCE_ALREADY_IN_SET __constant_cpu_to_le32(0xC01E0317) -#define STATUS_GRAPHICS_TARGET_ALREADY_IN_SET __constant_cpu_to_le32(0xC01E0318) -#define STATUS_GRAPHICS_INVALID_VIDPN_PRESENT_PATH __constant_cpu_to_le32(0xC01E0319) -#define STATUS_GRAPHICS_NO_RECOMMENDED_VIDPN_TOPOLOGY __constant_cpu_to_le32(0xC01E031A) -#define STATUS_GRAPHICS_INVALID_MONITOR_FREQUENCYRANGESET __constant_cpu_to_le32(0xC01E031B) -#define STATUS_GRAPHICS_INVALID_MONITOR_FREQUENCYRANGE __constant_cpu_to_le32(0xC01E031C) -#define STATUS_GRAPHICS_FREQUENCYRANGE_NOT_IN_SET __constant_cpu_to_le32(0xC01E031D) -#define STATUS_GRAPHICS_FREQUENCYRANGE_ALREADY_IN_SET __constant_cpu_to_le32(0xC01E031F) -#define STATUS_GRAPHICS_STALE_MODESET __constant_cpu_to_le32(0xC01E0320) -#define STATUS_GRAPHICS_INVALID_MONITOR_SOURCEMODESET __constant_cpu_to_le32(0xC01E0321) -#define STATUS_GRAPHICS_INVALID_MONITOR_SOURCE_MODE __constant_cpu_to_le32(0xC01E0322) -#define STATUS_GRAPHICS_NO_RECOMMENDED_FUNCTIONAL_VIDPN __constant_cpu_to_le32(0xC01E0323) -#define STATUS_GRAPHICS_MODE_ID_MUST_BE_UNIQUE __constant_cpu_to_le32(0xC01E0324) -#define STATUS_GRAPHICS_EMPTY_ADAPTER_MONITOR_MODE_SUPPORT_INTERSECTION __constant_cpu_to_le32(0xC01E0325) -#define STATUS_GRAPHICS_VIDEO_PRESENT_TARGETS_LESS_THAN_SOURCES __constant_cpu_to_le32(0xC01E0326) -#define STATUS_GRAPHICS_PATH_NOT_IN_TOPOLOGY __constant_cpu_to_le32(0xC01E0327) -#define STATUS_GRAPHICS_ADAPTER_MUST_HAVE_AT_LEAST_ONE_SOURCE __constant_cpu_to_le32(0xC01E0328) -#define STATUS_GRAPHICS_ADAPTER_MUST_HAVE_AT_LEAST_ONE_TARGET __constant_cpu_to_le32(0xC01E0329) -#define STATUS_GRAPHICS_INVALID_MONITORDESCRIPTORSET __constant_cpu_to_le32(0xC01E032A) -#define STATUS_GRAPHICS_INVALID_MONITORDESCRIPTOR __constant_cpu_to_le32(0xC01E032B) -#define STATUS_GRAPHICS_MONITORDESCRIPTOR_NOT_IN_SET __constant_cpu_to_le32(0xC01E032C) -#define STATUS_GRAPHICS_MONITORDESCRIPTOR_ALREADY_IN_SET __constant_cpu_to_le32(0xC01E032D) -#define STATUS_GRAPHICS_MONITORDESCRIPTOR_ID_MUST_BE_UNIQUE __constant_cpu_to_le32(0xC01E032E) -#define STATUS_GRAPHICS_INVALID_VIDPN_TARGET_SUBSET_TYPE __constant_cpu_to_le32(0xC01E032F) -#define STATUS_GRAPHICS_RESOURCES_NOT_RELATED __constant_cpu_to_le32(0xC01E0330) -#define STATUS_GRAPHICS_SOURCE_ID_MUST_BE_UNIQUE __constant_cpu_to_le32(0xC01E0331) -#define STATUS_GRAPHICS_TARGET_ID_MUST_BE_UNIQUE __constant_cpu_to_le32(0xC01E0332) -#define STATUS_GRAPHICS_NO_AVAILABLE_VIDPN_TARGET __constant_cpu_to_le32(0xC01E0333) -#define STATUS_GRAPHICS_MONITOR_COULD_NOT_BE_ASSOCIATED_WITH_ADAPTER __constant_cpu_to_le32(0xC01E0334) -#define STATUS_GRAPHICS_NO_VIDPNMGR __constant_cpu_to_le32(0xC01E0335) -#define STATUS_GRAPHICS_NO_ACTIVE_VIDPN __constant_cpu_to_le32(0xC01E0336) -#define STATUS_GRAPHICS_STALE_VIDPN_TOPOLOGY __constant_cpu_to_le32(0xC01E0337) -#define STATUS_GRAPHICS_MONITOR_NOT_CONNECTED __constant_cpu_to_le32(0xC01E0338) -#define STATUS_GRAPHICS_SOURCE_NOT_IN_TOPOLOGY __constant_cpu_to_le32(0xC01E0339) -#define STATUS_GRAPHICS_INVALID_PRIMARYSURFACE_SIZE __constant_cpu_to_le32(0xC01E033A) -#define STATUS_GRAPHICS_INVALID_VISIBLEREGION_SIZE __constant_cpu_to_le32(0xC01E033B) -#define STATUS_GRAPHICS_INVALID_STRIDE __constant_cpu_to_le32(0xC01E033C) -#define STATUS_GRAPHICS_INVALID_PIXELFORMAT __constant_cpu_to_le32(0xC01E033D) -#define STATUS_GRAPHICS_INVALID_COLORBASIS __constant_cpu_to_le32(0xC01E033E) -#define STATUS_GRAPHICS_INVALID_PIXELVALUEACCESSMODE __constant_cpu_to_le32(0xC01E033F) -#define STATUS_GRAPHICS_TARGET_NOT_IN_TOPOLOGY __constant_cpu_to_le32(0xC01E0340) -#define STATUS_GRAPHICS_NO_DISPLAY_MODE_MANAGEMENT_SUPPORT __constant_cpu_to_le32(0xC01E0341) -#define STATUS_GRAPHICS_VIDPN_SOURCE_IN_USE __constant_cpu_to_le32(0xC01E0342) -#define STATUS_GRAPHICS_CANT_ACCESS_ACTIVE_VIDPN __constant_cpu_to_le32(0xC01E0343) -#define STATUS_GRAPHICS_INVALID_PATH_IMPORTANCE_ORDINAL __constant_cpu_to_le32(0xC01E0344) -#define STATUS_GRAPHICS_INVALID_PATH_CONTENT_GEOMETRY_TRANSFORMATION __constant_cpu_to_le32(0xC01E0345) -#define STATUS_GRAPHICS_PATH_CONTENT_GEOMETRY_TRANSFORMATION_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0346) -#define STATUS_GRAPHICS_INVALID_GAMMA_RAMP __constant_cpu_to_le32(0xC01E0347) -#define STATUS_GRAPHICS_GAMMA_RAMP_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0348) -#define STATUS_GRAPHICS_MULTISAMPLING_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0349) -#define STATUS_GRAPHICS_MODE_NOT_IN_MODESET __constant_cpu_to_le32(0xC01E034A) -#define STATUS_GRAPHICS_INVALID_VIDPN_TOPOLOGY_RECOMMENDATION_REASON __constant_cpu_to_le32(0xC01E034D) -#define STATUS_GRAPHICS_INVALID_PATH_CONTENT_TYPE __constant_cpu_to_le32(0xC01E034E) -#define STATUS_GRAPHICS_INVALID_COPYPROTECTION_TYPE __constant_cpu_to_le32(0xC01E034F) -#define STATUS_GRAPHICS_UNASSIGNED_MODESET_ALREADY_EXISTS __constant_cpu_to_le32(0xC01E0350) -#define STATUS_GRAPHICS_INVALID_SCANLINE_ORDERING __constant_cpu_to_le32(0xC01E0352) -#define STATUS_GRAPHICS_TOPOLOGY_CHANGES_NOT_ALLOWED __constant_cpu_to_le32(0xC01E0353) -#define STATUS_GRAPHICS_NO_AVAILABLE_IMPORTANCE_ORDINALS __constant_cpu_to_le32(0xC01E0354) -#define STATUS_GRAPHICS_INCOMPATIBLE_PRIVATE_FORMAT __constant_cpu_to_le32(0xC01E0355) -#define STATUS_GRAPHICS_INVALID_MODE_PRUNING_ALGORITHM __constant_cpu_to_le32(0xC01E0356) -#define STATUS_GRAPHICS_INVALID_MONITOR_CAPABILITY_ORIGIN __constant_cpu_to_le32(0xC01E0357) -#define STATUS_GRAPHICS_INVALID_MONITOR_FREQUENCYRANGE_CONSTRAINT __constant_cpu_to_le32(0xC01E0358) -#define STATUS_GRAPHICS_MAX_NUM_PATHS_REACHED __constant_cpu_to_le32(0xC01E0359) -#define STATUS_GRAPHICS_CANCEL_VIDPN_TOPOLOGY_AUGMENTATION __constant_cpu_to_le32(0xC01E035A) -#define STATUS_GRAPHICS_INVALID_CLIENT_TYPE __constant_cpu_to_le32(0xC01E035B) -#define STATUS_GRAPHICS_CLIENTVIDPN_NOT_SET __constant_cpu_to_le32(0xC01E035C) -#define STATUS_GRAPHICS_SPECIFIED_CHILD_ALREADY_CONNECTED __constant_cpu_to_le32(0xC01E0400) -#define STATUS_GRAPHICS_CHILD_DESCRIPTOR_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0401) -#define STATUS_GRAPHICS_NOT_A_LINKED_ADAPTER __constant_cpu_to_le32(0xC01E0430) -#define STATUS_GRAPHICS_LEADLINK_NOT_ENUMERATED __constant_cpu_to_le32(0xC01E0431) -#define STATUS_GRAPHICS_CHAINLINKS_NOT_ENUMERATED __constant_cpu_to_le32(0xC01E0432) -#define STATUS_GRAPHICS_ADAPTER_CHAIN_NOT_READY __constant_cpu_to_le32(0xC01E0433) -#define STATUS_GRAPHICS_CHAINLINKS_NOT_STARTED __constant_cpu_to_le32(0xC01E0434) -#define STATUS_GRAPHICS_CHAINLINKS_NOT_POWERED_ON __constant_cpu_to_le32(0xC01E0435) -#define STATUS_GRAPHICS_INCONSISTENT_DEVICE_LINK_STATE __constant_cpu_to_le32(0xC01E0436) -#define STATUS_GRAPHICS_NOT_POST_DEVICE_DRIVER __constant_cpu_to_le32(0xC01E0438) -#define STATUS_GRAPHICS_ADAPTER_ACCESS_NOT_EXCLUDED __constant_cpu_to_le32(0xC01E043B) -#define STATUS_GRAPHICS_OPM_PROTECTED_OUTPUT_DOES_NOT_HAVE_COPP_SEMANTICS __constant_cpu_to_le32(0xC01E051C) -#define STATUS_GRAPHICS_OPM_INVALID_INFORMATION_REQUEST __constant_cpu_to_le32(0xC01E051D) -#define STATUS_GRAPHICS_OPM_DRIVER_INTERNAL_ERROR __constant_cpu_to_le32(0xC01E051E) -#define STATUS_GRAPHICS_OPM_PROTECTED_OUTPUT_DOES_NOT_HAVE_OPM_SEMANTICS __constant_cpu_to_le32(0xC01E051F) -#define STATUS_GRAPHICS_OPM_SIGNALING_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0520) -#define STATUS_GRAPHICS_OPM_INVALID_CONFIGURATION_REQUEST __constant_cpu_to_le32(0xC01E0521) -#define STATUS_GRAPHICS_OPM_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0500) -#define STATUS_GRAPHICS_COPP_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0501) -#define STATUS_GRAPHICS_UAB_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0502) -#define STATUS_GRAPHICS_OPM_INVALID_ENCRYPTED_PARAMETERS __constant_cpu_to_le32(0xC01E0503) -#define STATUS_GRAPHICS_OPM_PARAMETER_ARRAY_TOO_SMALL __constant_cpu_to_le32(0xC01E0504) -#define STATUS_GRAPHICS_OPM_NO_PROTECTED_OUTPUTS_EXIST __constant_cpu_to_le32(0xC01E0505) -#define STATUS_GRAPHICS_PVP_NO_DISPLAY_DEVICE_CORRESPONDS_TO_NAME __constant_cpu_to_le32(0xC01E0506) -#define STATUS_GRAPHICS_PVP_DISPLAY_DEVICE_NOT_ATTACHED_TO_DESKTOP __constant_cpu_to_le32(0xC01E0507) -#define STATUS_GRAPHICS_PVP_MIRRORING_DEVICES_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0508) -#define STATUS_GRAPHICS_OPM_INVALID_POINTER __constant_cpu_to_le32(0xC01E050A) -#define STATUS_GRAPHICS_OPM_INTERNAL_ERROR __constant_cpu_to_le32(0xC01E050B) -#define STATUS_GRAPHICS_OPM_INVALID_HANDLE __constant_cpu_to_le32(0xC01E050C) -#define STATUS_GRAPHICS_PVP_NO_MONITORS_CORRESPOND_TO_DISPLAY_DEVICE __constant_cpu_to_le32(0xC01E050D) -#define STATUS_GRAPHICS_PVP_INVALID_CERTIFICATE_LENGTH __constant_cpu_to_le32(0xC01E050E) -#define STATUS_GRAPHICS_OPM_SPANNING_MODE_ENABLED __constant_cpu_to_le32(0xC01E050F) -#define STATUS_GRAPHICS_OPM_THEATER_MODE_ENABLED __constant_cpu_to_le32(0xC01E0510) -#define STATUS_GRAPHICS_PVP_HFS_FAILED __constant_cpu_to_le32(0xC01E0511) -#define STATUS_GRAPHICS_OPM_INVALID_SRM __constant_cpu_to_le32(0xC01E0512) -#define STATUS_GRAPHICS_OPM_OUTPUT_DOES_NOT_SUPPORT_HDCP __constant_cpu_to_le32(0xC01E0513) -#define STATUS_GRAPHICS_OPM_OUTPUT_DOES_NOT_SUPPORT_ACP __constant_cpu_to_le32(0xC01E0514) -#define STATUS_GRAPHICS_OPM_OUTPUT_DOES_NOT_SUPPORT_CGMSA __constant_cpu_to_le32(0xC01E0515) -#define STATUS_GRAPHICS_OPM_HDCP_SRM_NEVER_SET __constant_cpu_to_le32(0xC01E0516) -#define STATUS_GRAPHICS_OPM_RESOLUTION_TOO_HIGH __constant_cpu_to_le32(0xC01E0517) -#define STATUS_GRAPHICS_OPM_ALL_HDCP_HARDWARE_ALREADY_IN_USE __constant_cpu_to_le32(0xC01E0518) -#define STATUS_GRAPHICS_OPM_PROTECTED_OUTPUT_NO_LONGER_EXISTS __constant_cpu_to_le32(0xC01E051A) -#define STATUS_GRAPHICS_OPM_SESSION_TYPE_CHANGE_IN_PROGRESS __constant_cpu_to_le32(0xC01E051B) -#define STATUS_GRAPHICS_I2C_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0580) -#define STATUS_GRAPHICS_I2C_DEVICE_DOES_NOT_EXIST __constant_cpu_to_le32(0xC01E0581) -#define STATUS_GRAPHICS_I2C_ERROR_TRANSMITTING_DATA __constant_cpu_to_le32(0xC01E0582) -#define STATUS_GRAPHICS_I2C_ERROR_RECEIVING_DATA __constant_cpu_to_le32(0xC01E0583) -#define STATUS_GRAPHICS_DDCCI_VCP_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E0584) -#define STATUS_GRAPHICS_DDCCI_INVALID_DATA __constant_cpu_to_le32(0xC01E0585) -#define STATUS_GRAPHICS_DDCCI_MONITOR_RETURNED_INVALID_TIMING_STATUS_BYTE __constant_cpu_to_le32(0xC01E0586) -#define STATUS_GRAPHICS_DDCCI_INVALID_CAPABILITIES_STRING __constant_cpu_to_le32(0xC01E0587) -#define STATUS_GRAPHICS_MCA_INTERNAL_ERROR __constant_cpu_to_le32(0xC01E0588) -#define STATUS_GRAPHICS_DDCCI_INVALID_MESSAGE_COMMAND __constant_cpu_to_le32(0xC01E0589) -#define STATUS_GRAPHICS_DDCCI_INVALID_MESSAGE_LENGTH __constant_cpu_to_le32(0xC01E058A) -#define STATUS_GRAPHICS_DDCCI_INVALID_MESSAGE_CHECKSUM __constant_cpu_to_le32(0xC01E058B) -#define STATUS_GRAPHICS_INVALID_PHYSICAL_MONITOR_HANDLE __constant_cpu_to_le32(0xC01E058C) -#define STATUS_GRAPHICS_MONITOR_NO_LONGER_EXISTS __constant_cpu_to_le32(0xC01E058D) -#define STATUS_GRAPHICS_ONLY_CONSOLE_SESSION_SUPPORTED __constant_cpu_to_le32(0xC01E05E0) -#define STATUS_GRAPHICS_NO_DISPLAY_DEVICE_CORRESPONDS_TO_NAME __constant_cpu_to_le32(0xC01E05E1) -#define STATUS_GRAPHICS_DISPLAY_DEVICE_NOT_ATTACHED_TO_DESKTOP __constant_cpu_to_le32(0xC01E05E2) -#define STATUS_GRAPHICS_MIRRORING_DEVICES_NOT_SUPPORTED __constant_cpu_to_le32(0xC01E05E3) -#define STATUS_GRAPHICS_INVALID_POINTER __constant_cpu_to_le32(0xC01E05E4) -#define STATUS_GRAPHICS_NO_MONITORS_CORRESPOND_TO_DISPLAY_DEVICE __constant_cpu_to_le32(0xC01E05E5) -#define STATUS_GRAPHICS_PARAMETER_ARRAY_TOO_SMALL __constant_cpu_to_le32(0xC01E05E6) -#define STATUS_GRAPHICS_INTERNAL_ERROR __constant_cpu_to_le32(0xC01E05E7) -#define STATUS_GRAPHICS_SESSION_TYPE_CHANGE_IN_PROGRESS __constant_cpu_to_le32(0xC01E05E8) -#define STATUS_FVE_LOCKED_VOLUME __constant_cpu_to_le32(0xC0210000) -#define STATUS_FVE_NOT_ENCRYPTED __constant_cpu_to_le32(0xC0210001) -#define STATUS_FVE_BAD_INFORMATION __constant_cpu_to_le32(0xC0210002) -#define STATUS_FVE_TOO_SMALL __constant_cpu_to_le32(0xC0210003) -#define STATUS_FVE_FAILED_WRONG_FS __constant_cpu_to_le32(0xC0210004) -#define STATUS_FVE_FAILED_BAD_FS __constant_cpu_to_le32(0xC0210005) -#define STATUS_FVE_FS_NOT_EXTENDED __constant_cpu_to_le32(0xC0210006) -#define STATUS_FVE_FS_MOUNTED __constant_cpu_to_le32(0xC0210007) -#define STATUS_FVE_NO_LICENSE __constant_cpu_to_le32(0xC0210008) -#define STATUS_FVE_ACTION_NOT_ALLOWED __constant_cpu_to_le32(0xC0210009) -#define STATUS_FVE_BAD_DATA __constant_cpu_to_le32(0xC021000A) -#define STATUS_FVE_VOLUME_NOT_BOUND __constant_cpu_to_le32(0xC021000B) -#define STATUS_FVE_NOT_DATA_VOLUME __constant_cpu_to_le32(0xC021000C) -#define STATUS_FVE_CONV_READ_ERROR __constant_cpu_to_le32(0xC021000D) -#define STATUS_FVE_CONV_WRITE_ERROR __constant_cpu_to_le32(0xC021000E) -#define STATUS_FVE_OVERLAPPED_UPDATE __constant_cpu_to_le32(0xC021000F) -#define STATUS_FVE_FAILED_SECTOR_SIZE __constant_cpu_to_le32(0xC0210010) -#define STATUS_FVE_FAILED_AUTHENTICATION __constant_cpu_to_le32(0xC0210011) -#define STATUS_FVE_NOT_OS_VOLUME __constant_cpu_to_le32(0xC0210012) -#define STATUS_FVE_KEYFILE_NOT_FOUND __constant_cpu_to_le32(0xC0210013) -#define STATUS_FVE_KEYFILE_INVALID __constant_cpu_to_le32(0xC0210014) -#define STATUS_FVE_KEYFILE_NO_VMK __constant_cpu_to_le32(0xC0210015) -#define STATUS_FVE_TPM_DISABLED __constant_cpu_to_le32(0xC0210016) -#define STATUS_FVE_TPM_SRK_AUTH_NOT_ZERO __constant_cpu_to_le32(0xC0210017) -#define STATUS_FVE_TPM_INVALID_PCR __constant_cpu_to_le32(0xC0210018) -#define STATUS_FVE_TPM_NO_VMK __constant_cpu_to_le32(0xC0210019) -#define STATUS_FVE_PIN_INVALID __constant_cpu_to_le32(0xC021001A) -#define STATUS_FVE_AUTH_INVALID_APPLICATION __constant_cpu_to_le32(0xC021001B) -#define STATUS_FVE_AUTH_INVALID_CONFIG __constant_cpu_to_le32(0xC021001C) -#define STATUS_FVE_DEBUGGER_ENABLED __constant_cpu_to_le32(0xC021001D) -#define STATUS_FVE_DRY_RUN_FAILED __constant_cpu_to_le32(0xC021001E) -#define STATUS_FVE_BAD_METADATA_POINTER __constant_cpu_to_le32(0xC021001F) -#define STATUS_FVE_OLD_METADATA_COPY __constant_cpu_to_le32(0xC0210020) -#define STATUS_FVE_REBOOT_REQUIRED __constant_cpu_to_le32(0xC0210021) -#define STATUS_FVE_RAW_ACCESS __constant_cpu_to_le32(0xC0210022) -#define STATUS_FVE_RAW_BLOCKED __constant_cpu_to_le32(0xC0210023) -#define STATUS_FWP_CALLOUT_NOT_FOUND __constant_cpu_to_le32(0xC0220001) -#define STATUS_FWP_CONDITION_NOT_FOUND __constant_cpu_to_le32(0xC0220002) -#define STATUS_FWP_FILTER_NOT_FOUND __constant_cpu_to_le32(0xC0220003) -#define STATUS_FWP_LAYER_NOT_FOUND __constant_cpu_to_le32(0xC0220004) -#define STATUS_FWP_PROVIDER_NOT_FOUND __constant_cpu_to_le32(0xC0220005) -#define STATUS_FWP_PROVIDER_CONTEXT_NOT_FOUND __constant_cpu_to_le32(0xC0220006) -#define STATUS_FWP_SUBLAYER_NOT_FOUND __constant_cpu_to_le32(0xC0220007) -#define STATUS_FWP_NOT_FOUND __constant_cpu_to_le32(0xC0220008) -#define STATUS_FWP_ALREADY_EXISTS __constant_cpu_to_le32(0xC0220009) -#define STATUS_FWP_IN_USE __constant_cpu_to_le32(0xC022000A) -#define STATUS_FWP_DYNAMIC_SESSION_IN_PROGRESS __constant_cpu_to_le32(0xC022000B) -#define STATUS_FWP_WRONG_SESSION __constant_cpu_to_le32(0xC022000C) -#define STATUS_FWP_NO_TXN_IN_PROGRESS __constant_cpu_to_le32(0xC022000D) -#define STATUS_FWP_TXN_IN_PROGRESS __constant_cpu_to_le32(0xC022000E) -#define STATUS_FWP_TXN_ABORTED __constant_cpu_to_le32(0xC022000F) -#define STATUS_FWP_SESSION_ABORTED __constant_cpu_to_le32(0xC0220010) -#define STATUS_FWP_INCOMPATIBLE_TXN __constant_cpu_to_le32(0xC0220011) -#define STATUS_FWP_TIMEOUT __constant_cpu_to_le32(0xC0220012) -#define STATUS_FWP_NET_EVENTS_DISABLED __constant_cpu_to_le32(0xC0220013) -#define STATUS_FWP_INCOMPATIBLE_LAYER __constant_cpu_to_le32(0xC0220014) -#define STATUS_FWP_KM_CLIENTS_ONLY __constant_cpu_to_le32(0xC0220015) -#define STATUS_FWP_LIFETIME_MISMATCH __constant_cpu_to_le32(0xC0220016) -#define STATUS_FWP_BUILTIN_OBJECT __constant_cpu_to_le32(0xC0220017) -#define STATUS_FWP_TOO_MANY_BOOTTIME_FILTERS __constant_cpu_to_le32(0xC0220018) -#define STATUS_FWP_TOO_MANY_CALLOUTS __constant_cpu_to_le32(0xC0220018) -#define STATUS_FWP_NOTIFICATION_DROPPED __constant_cpu_to_le32(0xC0220019) -#define STATUS_FWP_TRAFFIC_MISMATCH __constant_cpu_to_le32(0xC022001A) -#define STATUS_FWP_INCOMPATIBLE_SA_STATE __constant_cpu_to_le32(0xC022001B) -#define STATUS_FWP_NULL_POINTER __constant_cpu_to_le32(0xC022001C) -#define STATUS_FWP_INVALID_ENUMERATOR __constant_cpu_to_le32(0xC022001D) -#define STATUS_FWP_INVALID_FLAGS __constant_cpu_to_le32(0xC022001E) -#define STATUS_FWP_INVALID_NET_MASK __constant_cpu_to_le32(0xC022001F) -#define STATUS_FWP_INVALID_RANGE __constant_cpu_to_le32(0xC0220020) -#define STATUS_FWP_INVALID_INTERVAL __constant_cpu_to_le32(0xC0220021) -#define STATUS_FWP_ZERO_LENGTH_ARRAY __constant_cpu_to_le32(0xC0220022) -#define STATUS_FWP_NULL_DISPLAY_NAME __constant_cpu_to_le32(0xC0220023) -#define STATUS_FWP_INVALID_ACTION_TYPE __constant_cpu_to_le32(0xC0220024) -#define STATUS_FWP_INVALID_WEIGHT __constant_cpu_to_le32(0xC0220025) -#define STATUS_FWP_MATCH_TYPE_MISMATCH __constant_cpu_to_le32(0xC0220026) -#define STATUS_FWP_TYPE_MISMATCH __constant_cpu_to_le32(0xC0220027) -#define STATUS_FWP_OUT_OF_BOUNDS __constant_cpu_to_le32(0xC0220028) -#define STATUS_FWP_RESERVED __constant_cpu_to_le32(0xC0220029) -#define STATUS_FWP_DUPLICATE_CONDITION __constant_cpu_to_le32(0xC022002A) -#define STATUS_FWP_DUPLICATE_KEYMOD __constant_cpu_to_le32(0xC022002B) -#define STATUS_FWP_ACTION_INCOMPATIBLE_WITH_LAYER __constant_cpu_to_le32(0xC022002C) -#define STATUS_FWP_ACTION_INCOMPATIBLE_WITH_SUBLAYER __constant_cpu_to_le32(0xC022002D) -#define STATUS_FWP_CONTEXT_INCOMPATIBLE_WITH_LAYER __constant_cpu_to_le32(0xC022002E) -#define STATUS_FWP_CONTEXT_INCOMPATIBLE_WITH_CALLOUT __constant_cpu_to_le32(0xC022002F) -#define STATUS_FWP_INCOMPATIBLE_AUTH_METHOD __constant_cpu_to_le32(0xC0220030) -#define STATUS_FWP_INCOMPATIBLE_DH_GROUP __constant_cpu_to_le32(0xC0220031) -#define STATUS_FWP_EM_NOT_SUPPORTED __constant_cpu_to_le32(0xC0220032) -#define STATUS_FWP_NEVER_MATCH __constant_cpu_to_le32(0xC0220033) -#define STATUS_FWP_PROVIDER_CONTEXT_MISMATCH __constant_cpu_to_le32(0xC0220034) -#define STATUS_FWP_INVALID_PARAMETER __constant_cpu_to_le32(0xC0220035) -#define STATUS_FWP_TOO_MANY_SUBLAYERS __constant_cpu_to_le32(0xC0220036) -#define STATUS_FWP_CALLOUT_NOTIFICATION_FAILED __constant_cpu_to_le32(0xC0220037) -#define STATUS_FWP_INCOMPATIBLE_AUTH_CONFIG __constant_cpu_to_le32(0xC0220038) -#define STATUS_FWP_INCOMPATIBLE_CIPHER_CONFIG __constant_cpu_to_le32(0xC0220039) -#define STATUS_FWP_TCPIP_NOT_READY __constant_cpu_to_le32(0xC0220100) -#define STATUS_FWP_INJECT_HANDLE_CLOSING __constant_cpu_to_le32(0xC0220101) -#define STATUS_FWP_INJECT_HANDLE_STALE __constant_cpu_to_le32(0xC0220102) -#define STATUS_FWP_CANNOT_PEND __constant_cpu_to_le32(0xC0220103) -#define STATUS_NDIS_CLOSING __constant_cpu_to_le32(0xC0230002) -#define STATUS_NDIS_BAD_VERSION __constant_cpu_to_le32(0xC0230004) -#define STATUS_NDIS_BAD_CHARACTERISTICS __constant_cpu_to_le32(0xC0230005) -#define STATUS_NDIS_ADAPTER_NOT_FOUND __constant_cpu_to_le32(0xC0230006) -#define STATUS_NDIS_OPEN_FAILED __constant_cpu_to_le32(0xC0230007) -#define STATUS_NDIS_DEVICE_FAILED __constant_cpu_to_le32(0xC0230008) -#define STATUS_NDIS_MULTICAST_FULL __constant_cpu_to_le32(0xC0230009) -#define STATUS_NDIS_MULTICAST_EXISTS __constant_cpu_to_le32(0xC023000A) -#define STATUS_NDIS_MULTICAST_NOT_FOUND __constant_cpu_to_le32(0xC023000B) -#define STATUS_NDIS_REQUEST_ABORTED __constant_cpu_to_le32(0xC023000C) -#define STATUS_NDIS_RESET_IN_PROGRESS __constant_cpu_to_le32(0xC023000D) -#define STATUS_NDIS_INVALID_PACKET __constant_cpu_to_le32(0xC023000F) -#define STATUS_NDIS_INVALID_DEVICE_REQUEST __constant_cpu_to_le32(0xC0230010) -#define STATUS_NDIS_ADAPTER_NOT_READY __constant_cpu_to_le32(0xC0230011) -#define STATUS_NDIS_INVALID_LENGTH __constant_cpu_to_le32(0xC0230014) -#define STATUS_NDIS_INVALID_DATA __constant_cpu_to_le32(0xC0230015) -#define STATUS_NDIS_BUFFER_TOO_SHORT __constant_cpu_to_le32(0xC0230016) -#define STATUS_NDIS_INVALID_OID __constant_cpu_to_le32(0xC0230017) -#define STATUS_NDIS_ADAPTER_REMOVED __constant_cpu_to_le32(0xC0230018) -#define STATUS_NDIS_UNSUPPORTED_MEDIA __constant_cpu_to_le32(0xC0230019) -#define STATUS_NDIS_GROUP_ADDRESS_IN_USE __constant_cpu_to_le32(0xC023001A) -#define STATUS_NDIS_FILE_NOT_FOUND __constant_cpu_to_le32(0xC023001B) -#define STATUS_NDIS_ERROR_READING_FILE __constant_cpu_to_le32(0xC023001C) -#define STATUS_NDIS_ALREADY_MAPPED __constant_cpu_to_le32(0xC023001D) -#define STATUS_NDIS_RESOURCE_CONFLICT __constant_cpu_to_le32(0xC023001E) -#define STATUS_NDIS_MEDIA_DISCONNECTED __constant_cpu_to_le32(0xC023001F) -#define STATUS_NDIS_INVALID_ADDRESS __constant_cpu_to_le32(0xC0230022) -#define STATUS_NDIS_PAUSED __constant_cpu_to_le32(0xC023002A) -#define STATUS_NDIS_INTERFACE_NOT_FOUND __constant_cpu_to_le32(0xC023002B) -#define STATUS_NDIS_UNSUPPORTED_REVISION __constant_cpu_to_le32(0xC023002C) -#define STATUS_NDIS_INVALID_PORT __constant_cpu_to_le32(0xC023002D) -#define STATUS_NDIS_INVALID_PORT_STATE __constant_cpu_to_le32(0xC023002E) -#define STATUS_NDIS_LOW_POWER_STATE __constant_cpu_to_le32(0xC023002F) -#define STATUS_NDIS_NOT_SUPPORTED __constant_cpu_to_le32(0xC02300BB) -#define STATUS_NDIS_DOT11_AUTO_CONFIG_ENABLED __constant_cpu_to_le32(0xC0232000) -#define STATUS_NDIS_DOT11_MEDIA_IN_USE __constant_cpu_to_le32(0xC0232001) -#define STATUS_NDIS_DOT11_POWER_STATE_INVALID __constant_cpu_to_le32(0xC0232002) -#define STATUS_IPSEC_BAD_SPI __constant_cpu_to_le32(0xC0360001) -#define STATUS_IPSEC_SA_LIFETIME_EXPIRED __constant_cpu_to_le32(0xC0360002) -#define STATUS_IPSEC_WRONG_SA __constant_cpu_to_le32(0xC0360003) -#define STATUS_IPSEC_REPLAY_CHECK_FAILED __constant_cpu_to_le32(0xC0360004) -#define STATUS_IPSEC_INVALID_PACKET __constant_cpu_to_le32(0xC0360005) -#define STATUS_IPSEC_INTEGRITY_CHECK_FAILED __constant_cpu_to_le32(0xC0360006) -#define STATUS_IPSEC_CLEAR_TEXT_DROP __constant_cpu_to_le32(0xC0360007) +#define STATUS_SUCCESS cpu_to_le32(0x00000000) +#define STATUS_WAIT_0 cpu_to_le32(0x00000000) +#define STATUS_WAIT_1 cpu_to_le32(0x00000001) +#define STATUS_WAIT_2 cpu_to_le32(0x00000002) +#define STATUS_WAIT_3 cpu_to_le32(0x00000003) +#define STATUS_WAIT_63 cpu_to_le32(0x0000003F) +#define STATUS_ABANDONED cpu_to_le32(0x00000080) +#define STATUS_ABANDONED_WAIT_0 cpu_to_le32(0x00000080) +#define STATUS_ABANDONED_WAIT_63 cpu_to_le32(0x000000BF) +#define STATUS_USER_APC cpu_to_le32(0x000000C0) +#define STATUS_KERNEL_APC cpu_to_le32(0x00000100) +#define STATUS_ALERTED cpu_to_le32(0x00000101) +#define STATUS_TIMEOUT cpu_to_le32(0x00000102) +#define STATUS_PENDING cpu_to_le32(0x00000103) +#define STATUS_REPARSE cpu_to_le32(0x00000104) +#define STATUS_MORE_ENTRIES cpu_to_le32(0x00000105) +#define STATUS_NOT_ALL_ASSIGNED cpu_to_le32(0x00000106) +#define STATUS_SOME_NOT_MAPPED cpu_to_le32(0x00000107) +#define STATUS_OPLOCK_BREAK_IN_PROGRESS cpu_to_le32(0x00000108) +#define STATUS_VOLUME_MOUNTED cpu_to_le32(0x00000109) +#define STATUS_RXACT_COMMITTED cpu_to_le32(0x0000010A) +#define STATUS_NOTIFY_CLEANUP cpu_to_le32(0x0000010B) +#define STATUS_NOTIFY_ENUM_DIR cpu_to_le32(0x0000010C) +#define STATUS_NO_QUOTAS_FOR_ACCOUNT cpu_to_le32(0x0000010D) +#define STATUS_PRIMARY_TRANSPORT_CONNECT_FAILED cpu_to_le32(0x0000010E) +#define STATUS_PAGE_FAULT_TRANSITION cpu_to_le32(0x00000110) +#define STATUS_PAGE_FAULT_DEMAND_ZERO cpu_to_le32(0x00000111) +#define STATUS_PAGE_FAULT_COPY_ON_WRITE cpu_to_le32(0x00000112) +#define STATUS_PAGE_FAULT_GUARD_PAGE cpu_to_le32(0x00000113) +#define STATUS_PAGE_FAULT_PAGING_FILE cpu_to_le32(0x00000114) +#define STATUS_CACHE_PAGE_LOCKED cpu_to_le32(0x00000115) +#define STATUS_CRASH_DUMP cpu_to_le32(0x00000116) +#define STATUS_BUFFER_ALL_ZEROS cpu_to_le32(0x00000117) +#define STATUS_REPARSE_OBJECT cpu_to_le32(0x00000118) +#define STATUS_RESOURCE_REQUIREMENTS_CHANGED cpu_to_le32(0x00000119) +#define STATUS_TRANSLATION_COMPLETE cpu_to_le32(0x00000120) +#define STATUS_DS_MEMBERSHIP_EVALUATED_LOCALLY cpu_to_le32(0x00000121) +#define STATUS_NOTHING_TO_TERMINATE cpu_to_le32(0x00000122) +#define STATUS_PROCESS_NOT_IN_JOB cpu_to_le32(0x00000123) +#define STATUS_PROCESS_IN_JOB cpu_to_le32(0x00000124) +#define STATUS_VOLSNAP_HIBERNATE_READY cpu_to_le32(0x00000125) +#define STATUS_FSFILTER_OP_COMPLETED_SUCCESSFULLY cpu_to_le32(0x00000126) +#define STATUS_INTERRUPT_VECTOR_ALREADY_CONNECTED cpu_to_le32(0x00000127) +#define STATUS_INTERRUPT_STILL_CONNECTED cpu_to_le32(0x00000128) +#define STATUS_PROCESS_CLONED cpu_to_le32(0x00000129) +#define STATUS_FILE_LOCKED_WITH_ONLY_READERS cpu_to_le32(0x0000012A) +#define STATUS_FILE_LOCKED_WITH_WRITERS cpu_to_le32(0x0000012B) +#define STATUS_RESOURCEMANAGER_READ_ONLY cpu_to_le32(0x00000202) +#define STATUS_WAIT_FOR_OPLOCK cpu_to_le32(0x00000367) +#define DBG_EXCEPTION_HANDLED cpu_to_le32(0x00010001) +#define DBG_CONTINUE cpu_to_le32(0x00010002) +#define STATUS_FLT_IO_COMPLETE cpu_to_le32(0x001C0001) +#define STATUS_OBJECT_NAME_EXISTS cpu_to_le32(0x40000000) +#define STATUS_THREAD_WAS_SUSPENDED cpu_to_le32(0x40000001) +#define STATUS_WORKING_SET_LIMIT_RANGE cpu_to_le32(0x40000002) +#define STATUS_IMAGE_NOT_AT_BASE cpu_to_le32(0x40000003) +#define STATUS_RXACT_STATE_CREATED cpu_to_le32(0x40000004) +#define STATUS_SEGMENT_NOTIFICATION cpu_to_le32(0x40000005) +#define STATUS_LOCAL_USER_SESSION_KEY cpu_to_le32(0x40000006) +#define STATUS_BAD_CURRENT_DIRECTORY cpu_to_le32(0x40000007) +#define STATUS_SERIAL_MORE_WRITES cpu_to_le32(0x40000008) +#define STATUS_REGISTRY_RECOVERED cpu_to_le32(0x40000009) +#define STATUS_FT_READ_RECOVERY_FROM_BACKUP cpu_to_le32(0x4000000A) +#define STATUS_FT_WRITE_RECOVERY cpu_to_le32(0x4000000B) +#define STATUS_SERIAL_COUNTER_TIMEOUT cpu_to_le32(0x4000000C) +#define STATUS_NULL_LM_PASSWORD cpu_to_le32(0x4000000D) +#define STATUS_IMAGE_MACHINE_TYPE_MISMATCH cpu_to_le32(0x4000000E) +#define STATUS_RECEIVE_PARTIAL cpu_to_le32(0x4000000F) +#define STATUS_RECEIVE_EXPEDITED cpu_to_le32(0x40000010) +#define STATUS_RECEIVE_PARTIAL_EXPEDITED cpu_to_le32(0x40000011) +#define STATUS_EVENT_DONE cpu_to_le32(0x40000012) +#define STATUS_EVENT_PENDING cpu_to_le32(0x40000013) +#define STATUS_CHECKING_FILE_SYSTEM cpu_to_le32(0x40000014) +#define STATUS_FATAL_APP_EXIT cpu_to_le32(0x40000015) +#define STATUS_PREDEFINED_HANDLE cpu_to_le32(0x40000016) +#define STATUS_WAS_UNLOCKED cpu_to_le32(0x40000017) +#define STATUS_SERVICE_NOTIFICATION cpu_to_le32(0x40000018) +#define STATUS_WAS_LOCKED cpu_to_le32(0x40000019) +#define STATUS_LOG_HARD_ERROR cpu_to_le32(0x4000001A) +#define STATUS_ALREADY_WIN32 cpu_to_le32(0x4000001B) +#define STATUS_WX86_UNSIMULATE cpu_to_le32(0x4000001C) +#define STATUS_WX86_CONTINUE cpu_to_le32(0x4000001D) +#define STATUS_WX86_SINGLE_STEP cpu_to_le32(0x4000001E) +#define STATUS_WX86_BREAKPOINT cpu_to_le32(0x4000001F) +#define STATUS_WX86_EXCEPTION_CONTINUE cpu_to_le32(0x40000020) +#define STATUS_WX86_EXCEPTION_LASTCHANCE cpu_to_le32(0x40000021) +#define STATUS_WX86_EXCEPTION_CHAIN cpu_to_le32(0x40000022) +#define STATUS_IMAGE_MACHINE_TYPE_MISMATCH_EXE cpu_to_le32(0x40000023) +#define STATUS_NO_YIELD_PERFORMED cpu_to_le32(0x40000024) +#define STATUS_TIMER_RESUME_IGNORED cpu_to_le32(0x40000025) +#define STATUS_ARBITRATION_UNHANDLED cpu_to_le32(0x40000026) +#define STATUS_CARDBUS_NOT_SUPPORTED cpu_to_le32(0x40000027) +#define STATUS_WX86_CREATEWX86TIB cpu_to_le32(0x40000028) +#define STATUS_MP_PROCESSOR_MISMATCH cpu_to_le32(0x40000029) +#define STATUS_HIBERNATED cpu_to_le32(0x4000002A) +#define STATUS_RESUME_HIBERNATION cpu_to_le32(0x4000002B) +#define STATUS_FIRMWARE_UPDATED cpu_to_le32(0x4000002C) +#define STATUS_DRIVERS_LEAKING_LOCKED_PAGES cpu_to_le32(0x4000002D) +#define STATUS_MESSAGE_RETRIEVED cpu_to_le32(0x4000002E) +#define STATUS_SYSTEM_POWERSTATE_TRANSITION cpu_to_le32(0x4000002F) +#define STATUS_ALPC_CHECK_COMPLETION_LIST cpu_to_le32(0x40000030) +#define STATUS_SYSTEM_POWERSTATE_COMPLEX_TRANSITION cpu_to_le32(0x40000031) +#define STATUS_ACCESS_AUDIT_BY_POLICY cpu_to_le32(0x40000032) +#define STATUS_ABANDON_HIBERFILE cpu_to_le32(0x40000033) +#define STATUS_BIZRULES_NOT_ENABLED cpu_to_le32(0x40000034) +#define STATUS_WAKE_SYSTEM cpu_to_le32(0x40000294) +#define STATUS_DS_SHUTTING_DOWN cpu_to_le32(0x40000370) +#define DBG_REPLY_LATER cpu_to_le32(0x40010001) +#define DBG_UNABLE_TO_PROVIDE_HANDLE cpu_to_le32(0x40010002) +#define DBG_TERMINATE_THREAD cpu_to_le32(0x40010003) +#define DBG_TERMINATE_PROCESS cpu_to_le32(0x40010004) +#define DBG_CONTROL_C cpu_to_le32(0x40010005) +#define DBG_PRINTEXCEPTION_C cpu_to_le32(0x40010006) +#define DBG_RIPEXCEPTION cpu_to_le32(0x40010007) +#define DBG_CONTROL_BREAK cpu_to_le32(0x40010008) +#define DBG_COMMAND_EXCEPTION cpu_to_le32(0x40010009) +#define RPC_NT_UUID_LOCAL_ONLY cpu_to_le32(0x40020056) +#define RPC_NT_SEND_INCOMPLETE cpu_to_le32(0x400200AF) +#define STATUS_CTX_CDM_CONNECT cpu_to_le32(0x400A0004) +#define STATUS_CTX_CDM_DISCONNECT cpu_to_le32(0x400A0005) +#define STATUS_SXS_RELEASE_ACTIVATION_CONTEXT cpu_to_le32(0x4015000D) +#define STATUS_RECOVERY_NOT_NEEDED cpu_to_le32(0x40190034) +#define STATUS_RM_ALREADY_STARTED cpu_to_le32(0x40190035) +#define STATUS_LOG_NO_RESTART cpu_to_le32(0x401A000C) +#define STATUS_VIDEO_DRIVER_DEBUG_REPORT_REQUEST cpu_to_le32(0x401B00EC) +#define STATUS_GRAPHICS_PARTIAL_DATA_POPULATED cpu_to_le32(0x401E000A) +#define STATUS_GRAPHICS_DRIVER_MISMATCH cpu_to_le32(0x401E0117) +#define STATUS_GRAPHICS_MODE_NOT_PINNED cpu_to_le32(0x401E0307) +#define STATUS_GRAPHICS_NO_PREFERRED_MODE cpu_to_le32(0x401E031E) +#define STATUS_GRAPHICS_DATASET_IS_EMPTY cpu_to_le32(0x401E034B) +#define STATUS_GRAPHICS_NO_MORE_ELEMENTS_IN_DATASET cpu_to_le32(0x401E034C) +#define STATUS_GRAPHICS_PATH_CONTENT_GEOMETRY_TRANSFORMATION_NOT_PINNED cpu_to_le32(0x401E0351) +#define STATUS_GRAPHICS_UNKNOWN_CHILD_STATUS cpu_to_le32(0x401E042F) +#define STATUS_GRAPHICS_LEADLINK_START_DEFERRED cpu_to_le32(0x401E0437) +#define STATUS_GRAPHICS_POLLING_TOO_FREQUENTLY cpu_to_le32(0x401E0439) +#define STATUS_GRAPHICS_START_DEFERRED cpu_to_le32(0x401E043A) +#define STATUS_NDIS_INDICATION_REQUIRED cpu_to_le32(0x40230001) +#define STATUS_GUARD_PAGE_VIOLATION cpu_to_le32(0x80000001) +#define STATUS_DATATYPE_MISALIGNMENT cpu_to_le32(0x80000002) +#define STATUS_BREAKPOINT cpu_to_le32(0x80000003) +#define STATUS_SINGLE_STEP cpu_to_le32(0x80000004) +#define STATUS_BUFFER_OVERFLOW cpu_to_le32(0x80000005) +#define STATUS_NO_MORE_FILES cpu_to_le32(0x80000006) +#define STATUS_WAKE_SYSTEM_DEBUGGER cpu_to_le32(0x80000007) +#define STATUS_HANDLES_CLOSED cpu_to_le32(0x8000000A) +#define STATUS_NO_INHERITANCE cpu_to_le32(0x8000000B) +#define STATUS_GUID_SUBSTITUTION_MADE cpu_to_le32(0x8000000C) +#define STATUS_PARTIAL_COPY cpu_to_le32(0x8000000D) +#define STATUS_DEVICE_PAPER_EMPTY cpu_to_le32(0x8000000E) +#define STATUS_DEVICE_POWERED_OFF cpu_to_le32(0x8000000F) +#define STATUS_DEVICE_OFF_LINE cpu_to_le32(0x80000010) +#define STATUS_DEVICE_BUSY cpu_to_le32(0x80000011) +#define STATUS_NO_MORE_EAS cpu_to_le32(0x80000012) +#define STATUS_INVALID_EA_NAME cpu_to_le32(0x80000013) +#define STATUS_EA_LIST_INCONSISTENT cpu_to_le32(0x80000014) +#define STATUS_INVALID_EA_FLAG cpu_to_le32(0x80000015) +#define STATUS_VERIFY_REQUIRED cpu_to_le32(0x80000016) +#define STATUS_EXTRANEOUS_INFORMATION cpu_to_le32(0x80000017) +#define STATUS_RXACT_COMMIT_NECESSARY cpu_to_le32(0x80000018) +#define STATUS_NO_MORE_ENTRIES cpu_to_le32(0x8000001A) +#define STATUS_FILEMARK_DETECTED cpu_to_le32(0x8000001B) +#define STATUS_MEDIA_CHANGED cpu_to_le32(0x8000001C) +#define STATUS_BUS_RESET cpu_to_le32(0x8000001D) +#define STATUS_END_OF_MEDIA cpu_to_le32(0x8000001E) +#define STATUS_BEGINNING_OF_MEDIA cpu_to_le32(0x8000001F) +#define STATUS_MEDIA_CHECK cpu_to_le32(0x80000020) +#define STATUS_SETMARK_DETECTED cpu_to_le32(0x80000021) +#define STATUS_NO_DATA_DETECTED cpu_to_le32(0x80000022) +#define STATUS_REDIRECTOR_HAS_OPEN_HANDLES cpu_to_le32(0x80000023) +#define STATUS_SERVER_HAS_OPEN_HANDLES cpu_to_le32(0x80000024) +#define STATUS_ALREADY_DISCONNECTED cpu_to_le32(0x80000025) +#define STATUS_LONGJUMP cpu_to_le32(0x80000026) +#define STATUS_CLEANER_CARTRIDGE_INSTALLED cpu_to_le32(0x80000027) +#define STATUS_PLUGPLAY_QUERY_VETOED cpu_to_le32(0x80000028) +#define STATUS_UNWIND_CONSOLIDATE cpu_to_le32(0x80000029) +#define STATUS_REGISTRY_HIVE_RECOVERED cpu_to_le32(0x8000002A) +#define STATUS_DLL_MIGHT_BE_INSECURE cpu_to_le32(0x8000002B) +#define STATUS_DLL_MIGHT_BE_INCOMPATIBLE cpu_to_le32(0x8000002C) +#define STATUS_STOPPED_ON_SYMLINK cpu_to_le32(0x8000002D) +#define STATUS_DEVICE_REQUIRES_CLEANING cpu_to_le32(0x80000288) +#define STATUS_DEVICE_DOOR_OPEN cpu_to_le32(0x80000289) +#define STATUS_DATA_LOST_REPAIR cpu_to_le32(0x80000803) +#define DBG_EXCEPTION_NOT_HANDLED cpu_to_le32(0x80010001) +#define STATUS_CLUSTER_NODE_ALREADY_UP cpu_to_le32(0x80130001) +#define STATUS_CLUSTER_NODE_ALREADY_DOWN cpu_to_le32(0x80130002) +#define STATUS_CLUSTER_NETWORK_ALREADY_ONLINE cpu_to_le32(0x80130003) +#define STATUS_CLUSTER_NETWORK_ALREADY_OFFLINE cpu_to_le32(0x80130004) +#define STATUS_CLUSTER_NODE_ALREADY_MEMBER cpu_to_le32(0x80130005) +#define STATUS_COULD_NOT_RESIZE_LOG cpu_to_le32(0x80190009) +#define STATUS_NO_TXF_METADATA cpu_to_le32(0x80190029) +#define STATUS_CANT_RECOVER_WITH_HANDLE_OPEN cpu_to_le32(0x80190031) +#define STATUS_TXF_METADATA_ALREADY_PRESENT cpu_to_le32(0x80190041) +#define STATUS_TRANSACTION_SCOPE_CALLBACKS_NOT_SET cpu_to_le32(0x80190042) +#define STATUS_VIDEO_HUNG_DISPLAY_DRIVER_THREAD_RECOVERED cpu_to_le32(0x801B00EB) +#define STATUS_FLT_BUFFER_TOO_SMALL cpu_to_le32(0x801C0001) +#define STATUS_FVE_PARTIAL_METADATA cpu_to_le32(0x80210001) +#define STATUS_UNSUCCESSFUL cpu_to_le32(0xC0000001) +#define STATUS_NOT_IMPLEMENTED cpu_to_le32(0xC0000002) +#define STATUS_INVALID_INFO_CLASS cpu_to_le32(0xC0000003) +#define STATUS_INFO_LENGTH_MISMATCH cpu_to_le32(0xC0000004) +#define STATUS_ACCESS_VIOLATION cpu_to_le32(0xC0000005) +#define STATUS_IN_PAGE_ERROR cpu_to_le32(0xC0000006) +#define STATUS_PAGEFILE_QUOTA cpu_to_le32(0xC0000007) +#define STATUS_INVALID_HANDLE cpu_to_le32(0xC0000008) +#define STATUS_BAD_INITIAL_STACK cpu_to_le32(0xC0000009) +#define STATUS_BAD_INITIAL_PC cpu_to_le32(0xC000000A) +#define STATUS_INVALID_CID cpu_to_le32(0xC000000B) +#define STATUS_TIMER_NOT_CANCELED cpu_to_le32(0xC000000C) +#define STATUS_INVALID_PARAMETER cpu_to_le32(0xC000000D) +#define STATUS_NO_SUCH_DEVICE cpu_to_le32(0xC000000E) +#define STATUS_NO_SUCH_FILE cpu_to_le32(0xC000000F) +#define STATUS_INVALID_DEVICE_REQUEST cpu_to_le32(0xC0000010) +#define STATUS_END_OF_FILE cpu_to_le32(0xC0000011) +#define STATUS_WRONG_VOLUME cpu_to_le32(0xC0000012) +#define STATUS_NO_MEDIA_IN_DEVICE cpu_to_le32(0xC0000013) +#define STATUS_UNRECOGNIZED_MEDIA cpu_to_le32(0xC0000014) +#define STATUS_NONEXISTENT_SECTOR cpu_to_le32(0xC0000015) +#define STATUS_MORE_PROCESSING_REQUIRED cpu_to_le32(0xC0000016) +#define STATUS_NO_MEMORY cpu_to_le32(0xC0000017) +#define STATUS_CONFLICTING_ADDRESSES cpu_to_le32(0xC0000018) +#define STATUS_NOT_MAPPED_VIEW cpu_to_le32(0xC0000019) +#define STATUS_UNABLE_TO_FREE_VM cpu_to_le32(0xC000001A) +#define STATUS_UNABLE_TO_DELETE_SECTION cpu_to_le32(0xC000001B) +#define STATUS_INVALID_SYSTEM_SERVICE cpu_to_le32(0xC000001C) +#define STATUS_ILLEGAL_INSTRUCTION cpu_to_le32(0xC000001D) +#define STATUS_INVALID_LOCK_SEQUENCE cpu_to_le32(0xC000001E) +#define STATUS_INVALID_VIEW_SIZE cpu_to_le32(0xC000001F) +#define STATUS_INVALID_FILE_FOR_SECTION cpu_to_le32(0xC0000020) +#define STATUS_ALREADY_COMMITTED cpu_to_le32(0xC0000021) +#define STATUS_ACCESS_DENIED cpu_to_le32(0xC0000022) +#define STATUS_BUFFER_TOO_SMALL cpu_to_le32(0xC0000023) +#define STATUS_OBJECT_TYPE_MISMATCH cpu_to_le32(0xC0000024) +#define STATUS_NONCONTINUABLE_EXCEPTION cpu_to_le32(0xC0000025) +#define STATUS_INVALID_DISPOSITION cpu_to_le32(0xC0000026) +#define STATUS_UNWIND cpu_to_le32(0xC0000027) +#define STATUS_BAD_STACK cpu_to_le32(0xC0000028) +#define STATUS_INVALID_UNWIND_TARGET cpu_to_le32(0xC0000029) +#define STATUS_NOT_LOCKED cpu_to_le32(0xC000002A) +#define STATUS_PARITY_ERROR cpu_to_le32(0xC000002B) +#define STATUS_UNABLE_TO_DECOMMIT_VM cpu_to_le32(0xC000002C) +#define STATUS_NOT_COMMITTED cpu_to_le32(0xC000002D) +#define STATUS_INVALID_PORT_ATTRIBUTES cpu_to_le32(0xC000002E) +#define STATUS_PORT_MESSAGE_TOO_LONG cpu_to_le32(0xC000002F) +#define STATUS_INVALID_PARAMETER_MIX cpu_to_le32(0xC0000030) +#define STATUS_INVALID_QUOTA_LOWER cpu_to_le32(0xC0000031) +#define STATUS_DISK_CORRUPT_ERROR cpu_to_le32(0xC0000032) +#define STATUS_OBJECT_NAME_INVALID cpu_to_le32(0xC0000033) +#define STATUS_OBJECT_NAME_NOT_FOUND cpu_to_le32(0xC0000034) +#define STATUS_OBJECT_NAME_COLLISION cpu_to_le32(0xC0000035) +#define STATUS_PORT_DISCONNECTED cpu_to_le32(0xC0000037) +#define STATUS_DEVICE_ALREADY_ATTACHED cpu_to_le32(0xC0000038) +#define STATUS_OBJECT_PATH_INVALID cpu_to_le32(0xC0000039) +#define STATUS_OBJECT_PATH_NOT_FOUND cpu_to_le32(0xC000003A) +#define STATUS_OBJECT_PATH_SYNTAX_BAD cpu_to_le32(0xC000003B) +#define STATUS_DATA_OVERRUN cpu_to_le32(0xC000003C) +#define STATUS_DATA_LATE_ERROR cpu_to_le32(0xC000003D) +#define STATUS_DATA_ERROR cpu_to_le32(0xC000003E) +#define STATUS_CRC_ERROR cpu_to_le32(0xC000003F) +#define STATUS_SECTION_TOO_BIG cpu_to_le32(0xC0000040) +#define STATUS_PORT_CONNECTION_REFUSED cpu_to_le32(0xC0000041) +#define STATUS_INVALID_PORT_HANDLE cpu_to_le32(0xC0000042) +#define STATUS_SHARING_VIOLATION cpu_to_le32(0xC0000043) +#define STATUS_QUOTA_EXCEEDED cpu_to_le32(0xC0000044) +#define STATUS_INVALID_PAGE_PROTECTION cpu_to_le32(0xC0000045) +#define STATUS_MUTANT_NOT_OWNED cpu_to_le32(0xC0000046) +#define STATUS_SEMAPHORE_LIMIT_EXCEEDED cpu_to_le32(0xC0000047) +#define STATUS_PORT_ALREADY_SET cpu_to_le32(0xC0000048) +#define STATUS_SECTION_NOT_IMAGE cpu_to_le32(0xC0000049) +#define STATUS_SUSPEND_COUNT_EXCEEDED cpu_to_le32(0xC000004A) +#define STATUS_THREAD_IS_TERMINATING cpu_to_le32(0xC000004B) +#define STATUS_BAD_WORKING_SET_LIMIT cpu_to_le32(0xC000004C) +#define STATUS_INCOMPATIBLE_FILE_MAP cpu_to_le32(0xC000004D) +#define STATUS_SECTION_PROTECTION cpu_to_le32(0xC000004E) +#define STATUS_EAS_NOT_SUPPORTED cpu_to_le32(0xC000004F) +#define STATUS_EA_TOO_LARGE cpu_to_le32(0xC0000050) +#define STATUS_NONEXISTENT_EA_ENTRY cpu_to_le32(0xC0000051) +#define STATUS_NO_EAS_ON_FILE cpu_to_le32(0xC0000052) +#define STATUS_EA_CORRUPT_ERROR cpu_to_le32(0xC0000053) +#define STATUS_FILE_LOCK_CONFLICT cpu_to_le32(0xC0000054) +#define STATUS_LOCK_NOT_GRANTED cpu_to_le32(0xC0000055) +#define STATUS_DELETE_PENDING cpu_to_le32(0xC0000056) +#define STATUS_CTL_FILE_NOT_SUPPORTED cpu_to_le32(0xC0000057) +#define STATUS_UNKNOWN_REVISION cpu_to_le32(0xC0000058) +#define STATUS_REVISION_MISMATCH cpu_to_le32(0xC0000059) +#define STATUS_INVALID_OWNER cpu_to_le32(0xC000005A) +#define STATUS_INVALID_PRIMARY_GROUP cpu_to_le32(0xC000005B) +#define STATUS_NO_IMPERSONATION_TOKEN cpu_to_le32(0xC000005C) +#define STATUS_CANT_DISABLE_MANDATORY cpu_to_le32(0xC000005D) +#define STATUS_NO_LOGON_SERVERS cpu_to_le32(0xC000005E) +#define STATUS_NO_SUCH_LOGON_SESSION cpu_to_le32(0xC000005F) +#define STATUS_NO_SUCH_PRIVILEGE cpu_to_le32(0xC0000060) +#define STATUS_PRIVILEGE_NOT_HELD cpu_to_le32(0xC0000061) +#define STATUS_INVALID_ACCOUNT_NAME cpu_to_le32(0xC0000062) +#define STATUS_USER_EXISTS cpu_to_le32(0xC0000063) +#define STATUS_NO_SUCH_USER cpu_to_le32(0xC0000064) +#define STATUS_GROUP_EXISTS cpu_to_le32(0xC0000065) +#define STATUS_NO_SUCH_GROUP cpu_to_le32(0xC0000066) +#define STATUS_MEMBER_IN_GROUP cpu_to_le32(0xC0000067) +#define STATUS_MEMBER_NOT_IN_GROUP cpu_to_le32(0xC0000068) +#define STATUS_LAST_ADMIN cpu_to_le32(0xC0000069) +#define STATUS_WRONG_PASSWORD cpu_to_le32(0xC000006A) +#define STATUS_ILL_FORMED_PASSWORD cpu_to_le32(0xC000006B) +#define STATUS_PASSWORD_RESTRICTION cpu_to_le32(0xC000006C) +#define STATUS_LOGON_FAILURE cpu_to_le32(0xC000006D) +#define STATUS_ACCOUNT_RESTRICTION cpu_to_le32(0xC000006E) +#define STATUS_INVALID_LOGON_HOURS cpu_to_le32(0xC000006F) +#define STATUS_INVALID_WORKSTATION cpu_to_le32(0xC0000070) +#define STATUS_PASSWORD_EXPIRED cpu_to_le32(0xC0000071) +#define STATUS_ACCOUNT_DISABLED cpu_to_le32(0xC0000072) +#define STATUS_NONE_MAPPED cpu_to_le32(0xC0000073) +#define STATUS_TOO_MANY_LUIDS_REQUESTED cpu_to_le32(0xC0000074) +#define STATUS_LUIDS_EXHAUSTED cpu_to_le32(0xC0000075) +#define STATUS_INVALID_SUB_AUTHORITY cpu_to_le32(0xC0000076) +#define STATUS_INVALID_ACL cpu_to_le32(0xC0000077) +#define STATUS_INVALID_SID cpu_to_le32(0xC0000078) +#define STATUS_INVALID_SECURITY_DESCR cpu_to_le32(0xC0000079) +#define STATUS_PROCEDURE_NOT_FOUND cpu_to_le32(0xC000007A) +#define STATUS_INVALID_IMAGE_FORMAT cpu_to_le32(0xC000007B) +#define STATUS_NO_TOKEN cpu_to_le32(0xC000007C) +#define STATUS_BAD_INHERITANCE_ACL cpu_to_le32(0xC000007D) +#define STATUS_RANGE_NOT_LOCKED cpu_to_le32(0xC000007E) +#define STATUS_DISK_FULL cpu_to_le32(0xC000007F) +#define STATUS_SERVER_DISABLED cpu_to_le32(0xC0000080) +#define STATUS_SERVER_NOT_DISABLED cpu_to_le32(0xC0000081) +#define STATUS_TOO_MANY_GUIDS_REQUESTED cpu_to_le32(0xC0000082) +#define STATUS_GUIDS_EXHAUSTED cpu_to_le32(0xC0000083) +#define STATUS_INVALID_ID_AUTHORITY cpu_to_le32(0xC0000084) +#define STATUS_AGENTS_EXHAUSTED cpu_to_le32(0xC0000085) +#define STATUS_INVALID_VOLUME_LABEL cpu_to_le32(0xC0000086) +#define STATUS_SECTION_NOT_EXTENDED cpu_to_le32(0xC0000087) +#define STATUS_NOT_MAPPED_DATA cpu_to_le32(0xC0000088) +#define STATUS_RESOURCE_DATA_NOT_FOUND cpu_to_le32(0xC0000089) +#define STATUS_RESOURCE_TYPE_NOT_FOUND cpu_to_le32(0xC000008A) +#define STATUS_RESOURCE_NAME_NOT_FOUND cpu_to_le32(0xC000008B) +#define STATUS_ARRAY_BOUNDS_EXCEEDED cpu_to_le32(0xC000008C) +#define STATUS_FLOAT_DENORMAL_OPERAND cpu_to_le32(0xC000008D) +#define STATUS_FLOAT_DIVIDE_BY_ZERO cpu_to_le32(0xC000008E) +#define STATUS_FLOAT_INEXACT_RESULT cpu_to_le32(0xC000008F) +#define STATUS_FLOAT_INVALID_OPERATION cpu_to_le32(0xC0000090) +#define STATUS_FLOAT_OVERFLOW cpu_to_le32(0xC0000091) +#define STATUS_FLOAT_STACK_CHECK cpu_to_le32(0xC0000092) +#define STATUS_FLOAT_UNDERFLOW cpu_to_le32(0xC0000093) +#define STATUS_INTEGER_DIVIDE_BY_ZERO cpu_to_le32(0xC0000094) +#define STATUS_INTEGER_OVERFLOW cpu_to_le32(0xC0000095) +#define STATUS_PRIVILEGED_INSTRUCTION cpu_to_le32(0xC0000096) +#define STATUS_TOO_MANY_PAGING_FILES cpu_to_le32(0xC0000097) +#define STATUS_FILE_INVALID cpu_to_le32(0xC0000098) +#define STATUS_ALLOTTED_SPACE_EXCEEDED cpu_to_le32(0xC0000099) +#define STATUS_INSUFFICIENT_RESOURCES cpu_to_le32(0xC000009A) +#define STATUS_DFS_EXIT_PATH_FOUND cpu_to_le32(0xC000009B) +#define STATUS_DEVICE_DATA_ERROR cpu_to_le32(0xC000009C) +#define STATUS_DEVICE_NOT_CONNECTED cpu_to_le32(0xC000009D) +#define STATUS_DEVICE_POWER_FAILURE cpu_to_le32(0xC000009E) +#define STATUS_FREE_VM_NOT_AT_BASE cpu_to_le32(0xC000009F) +#define STATUS_MEMORY_NOT_ALLOCATED cpu_to_le32(0xC00000A0) +#define STATUS_WORKING_SET_QUOTA cpu_to_le32(0xC00000A1) +#define STATUS_MEDIA_WRITE_PROTECTED cpu_to_le32(0xC00000A2) +#define STATUS_DEVICE_NOT_READY cpu_to_le32(0xC00000A3) +#define STATUS_INVALID_GROUP_ATTRIBUTES cpu_to_le32(0xC00000A4) +#define STATUS_BAD_IMPERSONATION_LEVEL cpu_to_le32(0xC00000A5) +#define STATUS_CANT_OPEN_ANONYMOUS cpu_to_le32(0xC00000A6) +#define STATUS_BAD_VALIDATION_CLASS cpu_to_le32(0xC00000A7) +#define STATUS_BAD_TOKEN_TYPE cpu_to_le32(0xC00000A8) +#define STATUS_BAD_MASTER_BOOT_RECORD cpu_to_le32(0xC00000A9) +#define STATUS_INSTRUCTION_MISALIGNMENT cpu_to_le32(0xC00000AA) +#define STATUS_INSTANCE_NOT_AVAILABLE cpu_to_le32(0xC00000AB) +#define STATUS_PIPE_NOT_AVAILABLE cpu_to_le32(0xC00000AC) +#define STATUS_INVALID_PIPE_STATE cpu_to_le32(0xC00000AD) +#define STATUS_PIPE_BUSY cpu_to_le32(0xC00000AE) +#define STATUS_ILLEGAL_FUNCTION cpu_to_le32(0xC00000AF) +#define STATUS_PIPE_DISCONNECTED cpu_to_le32(0xC00000B0) +#define STATUS_PIPE_CLOSING cpu_to_le32(0xC00000B1) +#define STATUS_PIPE_CONNECTED cpu_to_le32(0xC00000B2) +#define STATUS_PIPE_LISTENING cpu_to_le32(0xC00000B3) +#define STATUS_INVALID_READ_MODE cpu_to_le32(0xC00000B4) +#define STATUS_IO_TIMEOUT cpu_to_le32(0xC00000B5) +#define STATUS_FILE_FORCED_CLOSED cpu_to_le32(0xC00000B6) +#define STATUS_PROFILING_NOT_STARTED cpu_to_le32(0xC00000B7) +#define STATUS_PROFILING_NOT_STOPPED cpu_to_le32(0xC00000B8) +#define STATUS_COULD_NOT_INTERPRET cpu_to_le32(0xC00000B9) +#define STATUS_FILE_IS_A_DIRECTORY cpu_to_le32(0xC00000BA) +#define STATUS_NOT_SUPPORTED cpu_to_le32(0xC00000BB) +#define STATUS_REMOTE_NOT_LISTENING cpu_to_le32(0xC00000BC) +#define STATUS_DUPLICATE_NAME cpu_to_le32(0xC00000BD) +#define STATUS_BAD_NETWORK_PATH cpu_to_le32(0xC00000BE) +#define STATUS_NETWORK_BUSY cpu_to_le32(0xC00000BF) +#define STATUS_DEVICE_DOES_NOT_EXIST cpu_to_le32(0xC00000C0) +#define STATUS_TOO_MANY_COMMANDS cpu_to_le32(0xC00000C1) +#define STATUS_ADAPTER_HARDWARE_ERROR cpu_to_le32(0xC00000C2) +#define STATUS_INVALID_NETWORK_RESPONSE cpu_to_le32(0xC00000C3) +#define STATUS_UNEXPECTED_NETWORK_ERROR cpu_to_le32(0xC00000C4) +#define STATUS_BAD_REMOTE_ADAPTER cpu_to_le32(0xC00000C5) +#define STATUS_PRINT_QUEUE_FULL cpu_to_le32(0xC00000C6) +#define STATUS_NO_SPOOL_SPACE cpu_to_le32(0xC00000C7) +#define STATUS_PRINT_CANCELLED cpu_to_le32(0xC00000C8) +#define STATUS_NETWORK_NAME_DELETED cpu_to_le32(0xC00000C9) +#define STATUS_NETWORK_ACCESS_DENIED cpu_to_le32(0xC00000CA) +#define STATUS_BAD_DEVICE_TYPE cpu_to_le32(0xC00000CB) +#define STATUS_BAD_NETWORK_NAME cpu_to_le32(0xC00000CC) +#define STATUS_TOO_MANY_NAMES cpu_to_le32(0xC00000CD) +#define STATUS_TOO_MANY_SESSIONS cpu_to_le32(0xC00000CE) +#define STATUS_SHARING_PAUSED cpu_to_le32(0xC00000CF) +#define STATUS_REQUEST_NOT_ACCEPTED cpu_to_le32(0xC00000D0) +#define STATUS_REDIRECTOR_PAUSED cpu_to_le32(0xC00000D1) +#define STATUS_NET_WRITE_FAULT cpu_to_le32(0xC00000D2) +#define STATUS_PROFILING_AT_LIMIT cpu_to_le32(0xC00000D3) +#define STATUS_NOT_SAME_DEVICE cpu_to_le32(0xC00000D4) +#define STATUS_FILE_RENAMED cpu_to_le32(0xC00000D5) +#define STATUS_VIRTUAL_CIRCUIT_CLOSED cpu_to_le32(0xC00000D6) +#define STATUS_NO_SECURITY_ON_OBJECT cpu_to_le32(0xC00000D7) +#define STATUS_CANT_WAIT cpu_to_le32(0xC00000D8) +#define STATUS_PIPE_EMPTY cpu_to_le32(0xC00000D9) +#define STATUS_CANT_ACCESS_DOMAIN_INFO cpu_to_le32(0xC00000DA) +#define STATUS_CANT_TERMINATE_SELF cpu_to_le32(0xC00000DB) +#define STATUS_INVALID_SERVER_STATE cpu_to_le32(0xC00000DC) +#define STATUS_INVALID_DOMAIN_STATE cpu_to_le32(0xC00000DD) +#define STATUS_INVALID_DOMAIN_ROLE cpu_to_le32(0xC00000DE) +#define STATUS_NO_SUCH_DOMAIN cpu_to_le32(0xC00000DF) +#define STATUS_DOMAIN_EXISTS cpu_to_le32(0xC00000E0) +#define STATUS_DOMAIN_LIMIT_EXCEEDED cpu_to_le32(0xC00000E1) +#define STATUS_OPLOCK_NOT_GRANTED cpu_to_le32(0xC00000E2) +#define STATUS_INVALID_OPLOCK_PROTOCOL cpu_to_le32(0xC00000E3) +#define STATUS_INTERNAL_DB_CORRUPTION cpu_to_le32(0xC00000E4) +#define STATUS_INTERNAL_ERROR cpu_to_le32(0xC00000E5) +#define STATUS_GENERIC_NOT_MAPPED cpu_to_le32(0xC00000E6) +#define STATUS_BAD_DESCRIPTOR_FORMAT cpu_to_le32(0xC00000E7) +#define STATUS_INVALID_USER_BUFFER cpu_to_le32(0xC00000E8) +#define STATUS_UNEXPECTED_IO_ERROR cpu_to_le32(0xC00000E9) +#define STATUS_UNEXPECTED_MM_CREATE_ERR cpu_to_le32(0xC00000EA) +#define STATUS_UNEXPECTED_MM_MAP_ERROR cpu_to_le32(0xC00000EB) +#define STATUS_UNEXPECTED_MM_EXTEND_ERR cpu_to_le32(0xC00000EC) +#define STATUS_NOT_LOGON_PROCESS cpu_to_le32(0xC00000ED) +#define STATUS_LOGON_SESSION_EXISTS cpu_to_le32(0xC00000EE) +#define STATUS_INVALID_PARAMETER_1 cpu_to_le32(0xC00000EF) +#define STATUS_INVALID_PARAMETER_2 cpu_to_le32(0xC00000F0) +#define STATUS_INVALID_PARAMETER_3 cpu_to_le32(0xC00000F1) +#define STATUS_INVALID_PARAMETER_4 cpu_to_le32(0xC00000F2) +#define STATUS_INVALID_PARAMETER_5 cpu_to_le32(0xC00000F3) +#define STATUS_INVALID_PARAMETER_6 cpu_to_le32(0xC00000F4) +#define STATUS_INVALID_PARAMETER_7 cpu_to_le32(0xC00000F5) +#define STATUS_INVALID_PARAMETER_8 cpu_to_le32(0xC00000F6) +#define STATUS_INVALID_PARAMETER_9 cpu_to_le32(0xC00000F7) +#define STATUS_INVALID_PARAMETER_10 cpu_to_le32(0xC00000F8) +#define STATUS_INVALID_PARAMETER_11 cpu_to_le32(0xC00000F9) +#define STATUS_INVALID_PARAMETER_12 cpu_to_le32(0xC00000FA) +#define STATUS_REDIRECTOR_NOT_STARTED cpu_to_le32(0xC00000FB) +#define STATUS_REDIRECTOR_STARTED cpu_to_le32(0xC00000FC) +#define STATUS_STACK_OVERFLOW cpu_to_le32(0xC00000FD) +#define STATUS_NO_SUCH_PACKAGE cpu_to_le32(0xC00000FE) +#define STATUS_BAD_FUNCTION_TABLE cpu_to_le32(0xC00000FF) +#define STATUS_VARIABLE_NOT_FOUND cpu_to_le32(0xC0000100) +#define STATUS_DIRECTORY_NOT_EMPTY cpu_to_le32(0xC0000101) +#define STATUS_FILE_CORRUPT_ERROR cpu_to_le32(0xC0000102) +#define STATUS_NOT_A_DIRECTORY cpu_to_le32(0xC0000103) +#define STATUS_BAD_LOGON_SESSION_STATE cpu_to_le32(0xC0000104) +#define STATUS_LOGON_SESSION_COLLISION cpu_to_le32(0xC0000105) +#define STATUS_NAME_TOO_LONG cpu_to_le32(0xC0000106) +#define STATUS_FILES_OPEN cpu_to_le32(0xC0000107) +#define STATUS_CONNECTION_IN_USE cpu_to_le32(0xC0000108) +#define STATUS_MESSAGE_NOT_FOUND cpu_to_le32(0xC0000109) +#define STATUS_PROCESS_IS_TERMINATING cpu_to_le32(0xC000010A) +#define STATUS_INVALID_LOGON_TYPE cpu_to_le32(0xC000010B) +#define STATUS_NO_GUID_TRANSLATION cpu_to_le32(0xC000010C) +#define STATUS_CANNOT_IMPERSONATE cpu_to_le32(0xC000010D) +#define STATUS_IMAGE_ALREADY_LOADED cpu_to_le32(0xC000010E) +#define STATUS_ABIOS_NOT_PRESENT cpu_to_le32(0xC000010F) +#define STATUS_ABIOS_LID_NOT_EXIST cpu_to_le32(0xC0000110) +#define STATUS_ABIOS_LID_ALREADY_OWNED cpu_to_le32(0xC0000111) +#define STATUS_ABIOS_NOT_LID_OWNER cpu_to_le32(0xC0000112) +#define STATUS_ABIOS_INVALID_COMMAND cpu_to_le32(0xC0000113) +#define STATUS_ABIOS_INVALID_LID cpu_to_le32(0xC0000114) +#define STATUS_ABIOS_SELECTOR_NOT_AVAILABLE cpu_to_le32(0xC0000115) +#define STATUS_ABIOS_INVALID_SELECTOR cpu_to_le32(0xC0000116) +#define STATUS_NO_LDT cpu_to_le32(0xC0000117) +#define STATUS_INVALID_LDT_SIZE cpu_to_le32(0xC0000118) +#define STATUS_INVALID_LDT_OFFSET cpu_to_le32(0xC0000119) +#define STATUS_INVALID_LDT_DESCRIPTOR cpu_to_le32(0xC000011A) +#define STATUS_INVALID_IMAGE_NE_FORMAT cpu_to_le32(0xC000011B) +#define STATUS_RXACT_INVALID_STATE cpu_to_le32(0xC000011C) +#define STATUS_RXACT_COMMIT_FAILURE cpu_to_le32(0xC000011D) +#define STATUS_MAPPED_FILE_SIZE_ZERO cpu_to_le32(0xC000011E) +#define STATUS_TOO_MANY_OPENED_FILES cpu_to_le32(0xC000011F) +#define STATUS_CANCELLED cpu_to_le32(0xC0000120) +#define STATUS_CANNOT_DELETE cpu_to_le32(0xC0000121) +#define STATUS_INVALID_COMPUTER_NAME cpu_to_le32(0xC0000122) +#define STATUS_FILE_DELETED cpu_to_le32(0xC0000123) +#define STATUS_SPECIAL_ACCOUNT cpu_to_le32(0xC0000124) +#define STATUS_SPECIAL_GROUP cpu_to_le32(0xC0000125) +#define STATUS_SPECIAL_USER cpu_to_le32(0xC0000126) +#define STATUS_MEMBERS_PRIMARY_GROUP cpu_to_le32(0xC0000127) +#define STATUS_FILE_CLOSED cpu_to_le32(0xC0000128) +#define STATUS_TOO_MANY_THREADS cpu_to_le32(0xC0000129) +#define STATUS_THREAD_NOT_IN_PROCESS cpu_to_le32(0xC000012A) +#define STATUS_TOKEN_ALREADY_IN_USE cpu_to_le32(0xC000012B) +#define STATUS_PAGEFILE_QUOTA_EXCEEDED cpu_to_le32(0xC000012C) +#define STATUS_COMMITMENT_LIMIT cpu_to_le32(0xC000012D) +#define STATUS_INVALID_IMAGE_LE_FORMAT cpu_to_le32(0xC000012E) +#define STATUS_INVALID_IMAGE_NOT_MZ cpu_to_le32(0xC000012F) +#define STATUS_INVALID_IMAGE_PROTECT cpu_to_le32(0xC0000130) +#define STATUS_INVALID_IMAGE_WIN_16 cpu_to_le32(0xC0000131) +#define STATUS_LOGON_SERVER_CONFLICT cpu_to_le32(0xC0000132) +#define STATUS_TIME_DIFFERENCE_AT_DC cpu_to_le32(0xC0000133) +#define STATUS_SYNCHRONIZATION_REQUIRED cpu_to_le32(0xC0000134) +#define STATUS_DLL_NOT_FOUND cpu_to_le32(0xC0000135) +#define STATUS_OPEN_FAILED cpu_to_le32(0xC0000136) +#define STATUS_IO_PRIVILEGE_FAILED cpu_to_le32(0xC0000137) +#define STATUS_ORDINAL_NOT_FOUND cpu_to_le32(0xC0000138) +#define STATUS_ENTRYPOINT_NOT_FOUND cpu_to_le32(0xC0000139) +#define STATUS_CONTROL_C_EXIT cpu_to_le32(0xC000013A) +#define STATUS_LOCAL_DISCONNECT cpu_to_le32(0xC000013B) +#define STATUS_REMOTE_DISCONNECT cpu_to_le32(0xC000013C) +#define STATUS_REMOTE_RESOURCES cpu_to_le32(0xC000013D) +#define STATUS_LINK_FAILED cpu_to_le32(0xC000013E) +#define STATUS_LINK_TIMEOUT cpu_to_le32(0xC000013F) +#define STATUS_INVALID_CONNECTION cpu_to_le32(0xC0000140) +#define STATUS_INVALID_ADDRESS cpu_to_le32(0xC0000141) +#define STATUS_DLL_INIT_FAILED cpu_to_le32(0xC0000142) +#define STATUS_MISSING_SYSTEMFILE cpu_to_le32(0xC0000143) +#define STATUS_UNHANDLED_EXCEPTION cpu_to_le32(0xC0000144) +#define STATUS_APP_INIT_FAILURE cpu_to_le32(0xC0000145) +#define STATUS_PAGEFILE_CREATE_FAILED cpu_to_le32(0xC0000146) +#define STATUS_NO_PAGEFILE cpu_to_le32(0xC0000147) +#define STATUS_INVALID_LEVEL cpu_to_le32(0xC0000148) +#define STATUS_WRONG_PASSWORD_CORE cpu_to_le32(0xC0000149) +#define STATUS_ILLEGAL_FLOAT_CONTEXT cpu_to_le32(0xC000014A) +#define STATUS_PIPE_BROKEN cpu_to_le32(0xC000014B) +#define STATUS_REGISTRY_CORRUPT cpu_to_le32(0xC000014C) +#define STATUS_REGISTRY_IO_FAILED cpu_to_le32(0xC000014D) +#define STATUS_NO_EVENT_PAIR cpu_to_le32(0xC000014E) +#define STATUS_UNRECOGNIZED_VOLUME cpu_to_le32(0xC000014F) +#define STATUS_SERIAL_NO_DEVICE_INITED cpu_to_le32(0xC0000150) +#define STATUS_NO_SUCH_ALIAS cpu_to_le32(0xC0000151) +#define STATUS_MEMBER_NOT_IN_ALIAS cpu_to_le32(0xC0000152) +#define STATUS_MEMBER_IN_ALIAS cpu_to_le32(0xC0000153) +#define STATUS_ALIAS_EXISTS cpu_to_le32(0xC0000154) +#define STATUS_LOGON_NOT_GRANTED cpu_to_le32(0xC0000155) +#define STATUS_TOO_MANY_SECRETS cpu_to_le32(0xC0000156) +#define STATUS_SECRET_TOO_LONG cpu_to_le32(0xC0000157) +#define STATUS_INTERNAL_DB_ERROR cpu_to_le32(0xC0000158) +#define STATUS_FULLSCREEN_MODE cpu_to_le32(0xC0000159) +#define STATUS_TOO_MANY_CONTEXT_IDS cpu_to_le32(0xC000015A) +#define STATUS_LOGON_TYPE_NOT_GRANTED cpu_to_le32(0xC000015B) +#define STATUS_NOT_REGISTRY_FILE cpu_to_le32(0xC000015C) +#define STATUS_NT_CROSS_ENCRYPTION_REQUIRED cpu_to_le32(0xC000015D) +#define STATUS_DOMAIN_CTRLR_CONFIG_ERROR cpu_to_le32(0xC000015E) +#define STATUS_FT_MISSING_MEMBER cpu_to_le32(0xC000015F) +#define STATUS_ILL_FORMED_SERVICE_ENTRY cpu_to_le32(0xC0000160) +#define STATUS_ILLEGAL_CHARACTER cpu_to_le32(0xC0000161) +#define STATUS_UNMAPPABLE_CHARACTER cpu_to_le32(0xC0000162) +#define STATUS_UNDEFINED_CHARACTER cpu_to_le32(0xC0000163) +#define STATUS_FLOPPY_VOLUME cpu_to_le32(0xC0000164) +#define STATUS_FLOPPY_ID_MARK_NOT_FOUND cpu_to_le32(0xC0000165) +#define STATUS_FLOPPY_WRONG_CYLINDER cpu_to_le32(0xC0000166) +#define STATUS_FLOPPY_UNKNOWN_ERROR cpu_to_le32(0xC0000167) +#define STATUS_FLOPPY_BAD_REGISTERS cpu_to_le32(0xC0000168) +#define STATUS_DISK_RECALIBRATE_FAILED cpu_to_le32(0xC0000169) +#define STATUS_DISK_OPERATION_FAILED cpu_to_le32(0xC000016A) +#define STATUS_DISK_RESET_FAILED cpu_to_le32(0xC000016B) +#define STATUS_SHARED_IRQ_BUSY cpu_to_le32(0xC000016C) +#define STATUS_FT_ORPHANING cpu_to_le32(0xC000016D) +#define STATUS_BIOS_FAILED_TO_CONNECT_INTERRUPT cpu_to_le32(0xC000016E) +#define STATUS_PARTITION_FAILURE cpu_to_le32(0xC0000172) +#define STATUS_INVALID_BLOCK_LENGTH cpu_to_le32(0xC0000173) +#define STATUS_DEVICE_NOT_PARTITIONED cpu_to_le32(0xC0000174) +#define STATUS_UNABLE_TO_LOCK_MEDIA cpu_to_le32(0xC0000175) +#define STATUS_UNABLE_TO_UNLOAD_MEDIA cpu_to_le32(0xC0000176) +#define STATUS_EOM_OVERFLOW cpu_to_le32(0xC0000177) +#define STATUS_NO_MEDIA cpu_to_le32(0xC0000178) +#define STATUS_NO_SUCH_MEMBER cpu_to_le32(0xC000017A) +#define STATUS_INVALID_MEMBER cpu_to_le32(0xC000017B) +#define STATUS_KEY_DELETED cpu_to_le32(0xC000017C) +#define STATUS_NO_LOG_SPACE cpu_to_le32(0xC000017D) +#define STATUS_TOO_MANY_SIDS cpu_to_le32(0xC000017E) +#define STATUS_LM_CROSS_ENCRYPTION_REQUIRED cpu_to_le32(0xC000017F) +#define STATUS_KEY_HAS_CHILDREN cpu_to_le32(0xC0000180) +#define STATUS_CHILD_MUST_BE_VOLATILE cpu_to_le32(0xC0000181) +#define STATUS_DEVICE_CONFIGURATION_ERROR cpu_to_le32(0xC0000182) +#define STATUS_DRIVER_INTERNAL_ERROR cpu_to_le32(0xC0000183) +#define STATUS_INVALID_DEVICE_STATE cpu_to_le32(0xC0000184) +#define STATUS_IO_DEVICE_ERROR cpu_to_le32(0xC0000185) +#define STATUS_DEVICE_PROTOCOL_ERROR cpu_to_le32(0xC0000186) +#define STATUS_BACKUP_CONTROLLER cpu_to_le32(0xC0000187) +#define STATUS_LOG_FILE_FULL cpu_to_le32(0xC0000188) +#define STATUS_TOO_LATE cpu_to_le32(0xC0000189) +#define STATUS_NO_TRUST_LSA_SECRET cpu_to_le32(0xC000018A) +#define STATUS_NO_TRUST_SAM_ACCOUNT cpu_to_le32(0xC000018B) +#define STATUS_TRUSTED_DOMAIN_FAILURE cpu_to_le32(0xC000018C) +#define STATUS_TRUSTED_RELATIONSHIP_FAILURE cpu_to_le32(0xC000018D) +#define STATUS_EVENTLOG_FILE_CORRUPT cpu_to_le32(0xC000018E) +#define STATUS_EVENTLOG_CANT_START cpu_to_le32(0xC000018F) +#define STATUS_TRUST_FAILURE cpu_to_le32(0xC0000190) +#define STATUS_MUTANT_LIMIT_EXCEEDED cpu_to_le32(0xC0000191) +#define STATUS_NETLOGON_NOT_STARTED cpu_to_le32(0xC0000192) +#define STATUS_ACCOUNT_EXPIRED cpu_to_le32(0xC0000193) +#define STATUS_POSSIBLE_DEADLOCK cpu_to_le32(0xC0000194) +#define STATUS_NETWORK_CREDENTIAL_CONFLICT cpu_to_le32(0xC0000195) +#define STATUS_REMOTE_SESSION_LIMIT cpu_to_le32(0xC0000196) +#define STATUS_EVENTLOG_FILE_CHANGED cpu_to_le32(0xC0000197) +#define STATUS_NOLOGON_INTERDOMAIN_TRUST_ACCOUNT cpu_to_le32(0xC0000198) +#define STATUS_NOLOGON_WORKSTATION_TRUST_ACCOUNT cpu_to_le32(0xC0000199) +#define STATUS_NOLOGON_SERVER_TRUST_ACCOUNT cpu_to_le32(0xC000019A) +#define STATUS_DOMAIN_TRUST_INCONSISTENT cpu_to_le32(0xC000019B) +#define STATUS_FS_DRIVER_REQUIRED cpu_to_le32(0xC000019C) +#define STATUS_IMAGE_ALREADY_LOADED_AS_DLL cpu_to_le32(0xC000019D) +#define STATUS_NETWORK_OPEN_RESTRICTION cpu_to_le32(0xC0000201) +#define STATUS_NO_USER_SESSION_KEY cpu_to_le32(0xC0000202) +#define STATUS_USER_SESSION_DELETED cpu_to_le32(0xC0000203) +#define STATUS_RESOURCE_LANG_NOT_FOUND cpu_to_le32(0xC0000204) +#define STATUS_INSUFF_SERVER_RESOURCES cpu_to_le32(0xC0000205) +#define STATUS_INVALID_BUFFER_SIZE cpu_to_le32(0xC0000206) +#define STATUS_INVALID_ADDRESS_COMPONENT cpu_to_le32(0xC0000207) +#define STATUS_INVALID_ADDRESS_WILDCARD cpu_to_le32(0xC0000208) +#define STATUS_TOO_MANY_ADDRESSES cpu_to_le32(0xC0000209) +#define STATUS_ADDRESS_ALREADY_EXISTS cpu_to_le32(0xC000020A) +#define STATUS_ADDRESS_CLOSED cpu_to_le32(0xC000020B) +#define STATUS_CONNECTION_DISCONNECTED cpu_to_le32(0xC000020C) +#define STATUS_CONNECTION_RESET cpu_to_le32(0xC000020D) +#define STATUS_TOO_MANY_NODES cpu_to_le32(0xC000020E) +#define STATUS_TRANSACTION_ABORTED cpu_to_le32(0xC000020F) +#define STATUS_TRANSACTION_TIMED_OUT cpu_to_le32(0xC0000210) +#define STATUS_TRANSACTION_NO_RELEASE cpu_to_le32(0xC0000211) +#define STATUS_TRANSACTION_NO_MATCH cpu_to_le32(0xC0000212) +#define STATUS_TRANSACTION_RESPONDED cpu_to_le32(0xC0000213) +#define STATUS_TRANSACTION_INVALID_ID cpu_to_le32(0xC0000214) +#define STATUS_TRANSACTION_INVALID_TYPE cpu_to_le32(0xC0000215) +#define STATUS_NOT_SERVER_SESSION cpu_to_le32(0xC0000216) +#define STATUS_NOT_CLIENT_SESSION cpu_to_le32(0xC0000217) +#define STATUS_CANNOT_LOAD_REGISTRY_FILE cpu_to_le32(0xC0000218) +#define STATUS_DEBUG_ATTACH_FAILED cpu_to_le32(0xC0000219) +#define STATUS_SYSTEM_PROCESS_TERMINATED cpu_to_le32(0xC000021A) +#define STATUS_DATA_NOT_ACCEPTED cpu_to_le32(0xC000021B) +#define STATUS_NO_BROWSER_SERVERS_FOUND cpu_to_le32(0xC000021C) +#define STATUS_VDM_HARD_ERROR cpu_to_le32(0xC000021D) +#define STATUS_DRIVER_CANCEL_TIMEOUT cpu_to_le32(0xC000021E) +#define STATUS_REPLY_MESSAGE_MISMATCH cpu_to_le32(0xC000021F) +#define STATUS_MAPPED_ALIGNMENT cpu_to_le32(0xC0000220) +#define STATUS_IMAGE_CHECKSUM_MISMATCH cpu_to_le32(0xC0000221) +#define STATUS_LOST_WRITEBEHIND_DATA cpu_to_le32(0xC0000222) +#define STATUS_CLIENT_SERVER_PARAMETERS_INVALID cpu_to_le32(0xC0000223) +#define STATUS_PASSWORD_MUST_CHANGE cpu_to_le32(0xC0000224) +#define STATUS_NOT_FOUND cpu_to_le32(0xC0000225) +#define STATUS_NOT_TINY_STREAM cpu_to_le32(0xC0000226) +#define STATUS_RECOVERY_FAILURE cpu_to_le32(0xC0000227) +#define STATUS_STACK_OVERFLOW_READ cpu_to_le32(0xC0000228) +#define STATUS_FAIL_CHECK cpu_to_le32(0xC0000229) +#define STATUS_DUPLICATE_OBJECTID cpu_to_le32(0xC000022A) +#define STATUS_OBJECTID_EXISTS cpu_to_le32(0xC000022B) +#define STATUS_CONVERT_TO_LARGE cpu_to_le32(0xC000022C) +#define STATUS_RETRY cpu_to_le32(0xC000022D) +#define STATUS_FOUND_OUT_OF_SCOPE cpu_to_le32(0xC000022E) +#define STATUS_ALLOCATE_BUCKET cpu_to_le32(0xC000022F) +#define STATUS_PROPSET_NOT_FOUND cpu_to_le32(0xC0000230) +#define STATUS_MARSHALL_OVERFLOW cpu_to_le32(0xC0000231) +#define STATUS_INVALID_VARIANT cpu_to_le32(0xC0000232) +#define STATUS_DOMAIN_CONTROLLER_NOT_FOUND cpu_to_le32(0xC0000233) +#define STATUS_ACCOUNT_LOCKED_OUT cpu_to_le32(0xC0000234) +#define STATUS_HANDLE_NOT_CLOSABLE cpu_to_le32(0xC0000235) +#define STATUS_CONNECTION_REFUSED cpu_to_le32(0xC0000236) +#define STATUS_GRACEFUL_DISCONNECT cpu_to_le32(0xC0000237) +#define STATUS_ADDRESS_ALREADY_ASSOCIATED cpu_to_le32(0xC0000238) +#define STATUS_ADDRESS_NOT_ASSOCIATED cpu_to_le32(0xC0000239) +#define STATUS_CONNECTION_INVALID cpu_to_le32(0xC000023A) +#define STATUS_CONNECTION_ACTIVE cpu_to_le32(0xC000023B) +#define STATUS_NETWORK_UNREACHABLE cpu_to_le32(0xC000023C) +#define STATUS_HOST_UNREACHABLE cpu_to_le32(0xC000023D) +#define STATUS_PROTOCOL_UNREACHABLE cpu_to_le32(0xC000023E) +#define STATUS_PORT_UNREACHABLE cpu_to_le32(0xC000023F) +#define STATUS_REQUEST_ABORTED cpu_to_le32(0xC0000240) +#define STATUS_CONNECTION_ABORTED cpu_to_le32(0xC0000241) +#define STATUS_BAD_COMPRESSION_BUFFER cpu_to_le32(0xC0000242) +#define STATUS_USER_MAPPED_FILE cpu_to_le32(0xC0000243) +#define STATUS_AUDIT_FAILED cpu_to_le32(0xC0000244) +#define STATUS_TIMER_RESOLUTION_NOT_SET cpu_to_le32(0xC0000245) +#define STATUS_CONNECTION_COUNT_LIMIT cpu_to_le32(0xC0000246) +#define STATUS_LOGIN_TIME_RESTRICTION cpu_to_le32(0xC0000247) +#define STATUS_LOGIN_WKSTA_RESTRICTION cpu_to_le32(0xC0000248) +#define STATUS_IMAGE_MP_UP_MISMATCH cpu_to_le32(0xC0000249) +#define STATUS_INSUFFICIENT_LOGON_INFO cpu_to_le32(0xC0000250) +#define STATUS_BAD_DLL_ENTRYPOINT cpu_to_le32(0xC0000251) +#define STATUS_BAD_SERVICE_ENTRYPOINT cpu_to_le32(0xC0000252) +#define STATUS_LPC_REPLY_LOST cpu_to_le32(0xC0000253) +#define STATUS_IP_ADDRESS_CONFLICT1 cpu_to_le32(0xC0000254) +#define STATUS_IP_ADDRESS_CONFLICT2 cpu_to_le32(0xC0000255) +#define STATUS_REGISTRY_QUOTA_LIMIT cpu_to_le32(0xC0000256) +#define STATUS_PATH_NOT_COVERED cpu_to_le32(0xC0000257) +#define STATUS_NO_CALLBACK_ACTIVE cpu_to_le32(0xC0000258) +#define STATUS_LICENSE_QUOTA_EXCEEDED cpu_to_le32(0xC0000259) +#define STATUS_PWD_TOO_SHORT cpu_to_le32(0xC000025A) +#define STATUS_PWD_TOO_RECENT cpu_to_le32(0xC000025B) +#define STATUS_PWD_HISTORY_CONFLICT cpu_to_le32(0xC000025C) +#define STATUS_PLUGPLAY_NO_DEVICE cpu_to_le32(0xC000025E) +#define STATUS_UNSUPPORTED_COMPRESSION cpu_to_le32(0xC000025F) +#define STATUS_INVALID_HW_PROFILE cpu_to_le32(0xC0000260) +#define STATUS_INVALID_PLUGPLAY_DEVICE_PATH cpu_to_le32(0xC0000261) +#define STATUS_DRIVER_ORDINAL_NOT_FOUND cpu_to_le32(0xC0000262) +#define STATUS_DRIVER_ENTRYPOINT_NOT_FOUND cpu_to_le32(0xC0000263) +#define STATUS_RESOURCE_NOT_OWNED cpu_to_le32(0xC0000264) +#define STATUS_TOO_MANY_LINKS cpu_to_le32(0xC0000265) +#define STATUS_QUOTA_LIST_INCONSISTENT cpu_to_le32(0xC0000266) +#define STATUS_FILE_IS_OFFLINE cpu_to_le32(0xC0000267) +#define STATUS_EVALUATION_EXPIRATION cpu_to_le32(0xC0000268) +#define STATUS_ILLEGAL_DLL_RELOCATION cpu_to_le32(0xC0000269) +#define STATUS_LICENSE_VIOLATION cpu_to_le32(0xC000026A) +#define STATUS_DLL_INIT_FAILED_LOGOFF cpu_to_le32(0xC000026B) +#define STATUS_DRIVER_UNABLE_TO_LOAD cpu_to_le32(0xC000026C) +#define STATUS_DFS_UNAVAILABLE cpu_to_le32(0xC000026D) +#define STATUS_VOLUME_DISMOUNTED cpu_to_le32(0xC000026E) +#define STATUS_WX86_INTERNAL_ERROR cpu_to_le32(0xC000026F) +#define STATUS_WX86_FLOAT_STACK_CHECK cpu_to_le32(0xC0000270) +#define STATUS_VALIDATE_CONTINUE cpu_to_le32(0xC0000271) +#define STATUS_NO_MATCH cpu_to_le32(0xC0000272) +#define STATUS_NO_MORE_MATCHES cpu_to_le32(0xC0000273) +#define STATUS_NOT_A_REPARSE_POINT cpu_to_le32(0xC0000275) +#define STATUS_IO_REPARSE_TAG_INVALID cpu_to_le32(0xC0000276) +#define STATUS_IO_REPARSE_TAG_MISMATCH cpu_to_le32(0xC0000277) +#define STATUS_IO_REPARSE_DATA_INVALID cpu_to_le32(0xC0000278) +#define STATUS_IO_REPARSE_TAG_NOT_HANDLED cpu_to_le32(0xC0000279) +#define STATUS_REPARSE_POINT_NOT_RESOLVED cpu_to_le32(0xC0000280) +#define STATUS_DIRECTORY_IS_A_REPARSE_POINT cpu_to_le32(0xC0000281) +#define STATUS_RANGE_LIST_CONFLICT cpu_to_le32(0xC0000282) +#define STATUS_SOURCE_ELEMENT_EMPTY cpu_to_le32(0xC0000283) +#define STATUS_DESTINATION_ELEMENT_FULL cpu_to_le32(0xC0000284) +#define STATUS_ILLEGAL_ELEMENT_ADDRESS cpu_to_le32(0xC0000285) +#define STATUS_MAGAZINE_NOT_PRESENT cpu_to_le32(0xC0000286) +#define STATUS_REINITIALIZATION_NEEDED cpu_to_le32(0xC0000287) +#define STATUS_ENCRYPTION_FAILED cpu_to_le32(0xC000028A) +#define STATUS_DECRYPTION_FAILED cpu_to_le32(0xC000028B) +#define STATUS_RANGE_NOT_FOUND cpu_to_le32(0xC000028C) +#define STATUS_NO_RECOVERY_POLICY cpu_to_le32(0xC000028D) +#define STATUS_NO_EFS cpu_to_le32(0xC000028E) +#define STATUS_WRONG_EFS cpu_to_le32(0xC000028F) +#define STATUS_NO_USER_KEYS cpu_to_le32(0xC0000290) +#define STATUS_FILE_NOT_ENCRYPTED cpu_to_le32(0xC0000291) +#define STATUS_NOT_EXPORT_FORMAT cpu_to_le32(0xC0000292) +#define STATUS_FILE_ENCRYPTED cpu_to_le32(0xC0000293) +#define STATUS_WMI_GUID_NOT_FOUND cpu_to_le32(0xC0000295) +#define STATUS_WMI_INSTANCE_NOT_FOUND cpu_to_le32(0xC0000296) +#define STATUS_WMI_ITEMID_NOT_FOUND cpu_to_le32(0xC0000297) +#define STATUS_WMI_TRY_AGAIN cpu_to_le32(0xC0000298) +#define STATUS_SHARED_POLICY cpu_to_le32(0xC0000299) +#define STATUS_POLICY_OBJECT_NOT_FOUND cpu_to_le32(0xC000029A) +#define STATUS_POLICY_ONLY_IN_DS cpu_to_le32(0xC000029B) +#define STATUS_VOLUME_NOT_UPGRADED cpu_to_le32(0xC000029C) +#define STATUS_REMOTE_STORAGE_NOT_ACTIVE cpu_to_le32(0xC000029D) +#define STATUS_REMOTE_STORAGE_MEDIA_ERROR cpu_to_le32(0xC000029E) +#define STATUS_NO_TRACKING_SERVICE cpu_to_le32(0xC000029F) +#define STATUS_SERVER_SID_MISMATCH cpu_to_le32(0xC00002A0) +#define STATUS_DS_NO_ATTRIBUTE_OR_VALUE cpu_to_le32(0xC00002A1) +#define STATUS_DS_INVALID_ATTRIBUTE_SYNTAX cpu_to_le32(0xC00002A2) +#define STATUS_DS_ATTRIBUTE_TYPE_UNDEFINED cpu_to_le32(0xC00002A3) +#define STATUS_DS_ATTRIBUTE_OR_VALUE_EXISTS cpu_to_le32(0xC00002A4) +#define STATUS_DS_BUSY cpu_to_le32(0xC00002A5) +#define STATUS_DS_UNAVAILABLE cpu_to_le32(0xC00002A6) +#define STATUS_DS_NO_RIDS_ALLOCATED cpu_to_le32(0xC00002A7) +#define STATUS_DS_NO_MORE_RIDS cpu_to_le32(0xC00002A8) +#define STATUS_DS_INCORRECT_ROLE_OWNER cpu_to_le32(0xC00002A9) +#define STATUS_DS_RIDMGR_INIT_ERROR cpu_to_le32(0xC00002AA) +#define STATUS_DS_OBJ_CLASS_VIOLATION cpu_to_le32(0xC00002AB) +#define STATUS_DS_CANT_ON_NON_LEAF cpu_to_le32(0xC00002AC) +#define STATUS_DS_CANT_ON_RDN cpu_to_le32(0xC00002AD) +#define STATUS_DS_CANT_MOD_OBJ_CLASS cpu_to_le32(0xC00002AE) +#define STATUS_DS_CROSS_DOM_MOVE_FAILED cpu_to_le32(0xC00002AF) +#define STATUS_DS_GC_NOT_AVAILABLE cpu_to_le32(0xC00002B0) +#define STATUS_DIRECTORY_SERVICE_REQUIRED cpu_to_le32(0xC00002B1) +#define STATUS_REPARSE_ATTRIBUTE_CONFLICT cpu_to_le32(0xC00002B2) +#define STATUS_CANT_ENABLE_DENY_ONLY cpu_to_le32(0xC00002B3) +#define STATUS_FLOAT_MULTIPLE_FAULTS cpu_to_le32(0xC00002B4) +#define STATUS_FLOAT_MULTIPLE_TRAPS cpu_to_le32(0xC00002B5) +#define STATUS_DEVICE_REMOVED cpu_to_le32(0xC00002B6) +#define STATUS_JOURNAL_DELETE_IN_PROGRESS cpu_to_le32(0xC00002B7) +#define STATUS_JOURNAL_NOT_ACTIVE cpu_to_le32(0xC00002B8) +#define STATUS_NOINTERFACE cpu_to_le32(0xC00002B9) +#define STATUS_DS_ADMIN_LIMIT_EXCEEDED cpu_to_le32(0xC00002C1) +#define STATUS_DRIVER_FAILED_SLEEP cpu_to_le32(0xC00002C2) +#define STATUS_MUTUAL_AUTHENTICATION_FAILED cpu_to_le32(0xC00002C3) +#define STATUS_CORRUPT_SYSTEM_FILE cpu_to_le32(0xC00002C4) +#define STATUS_DATATYPE_MISALIGNMENT_ERROR cpu_to_le32(0xC00002C5) +#define STATUS_WMI_READ_ONLY cpu_to_le32(0xC00002C6) +#define STATUS_WMI_SET_FAILURE cpu_to_le32(0xC00002C7) +#define STATUS_COMMITMENT_MINIMUM cpu_to_le32(0xC00002C8) +#define STATUS_REG_NAT_CONSUMPTION cpu_to_le32(0xC00002C9) +#define STATUS_TRANSPORT_FULL cpu_to_le32(0xC00002CA) +#define STATUS_DS_SAM_INIT_FAILURE cpu_to_le32(0xC00002CB) +#define STATUS_ONLY_IF_CONNECTED cpu_to_le32(0xC00002CC) +#define STATUS_DS_SENSITIVE_GROUP_VIOLATION cpu_to_le32(0xC00002CD) +#define STATUS_PNP_RESTART_ENUMERATION cpu_to_le32(0xC00002CE) +#define STATUS_JOURNAL_ENTRY_DELETED cpu_to_le32(0xC00002CF) +#define STATUS_DS_CANT_MOD_PRIMARYGROUPID cpu_to_le32(0xC00002D0) +#define STATUS_SYSTEM_IMAGE_BAD_SIGNATURE cpu_to_le32(0xC00002D1) +#define STATUS_PNP_REBOOT_REQUIRED cpu_to_le32(0xC00002D2) +#define STATUS_POWER_STATE_INVALID cpu_to_le32(0xC00002D3) +#define STATUS_DS_INVALID_GROUP_TYPE cpu_to_le32(0xC00002D4) +#define STATUS_DS_NO_NEST_GLOBALGROUP_IN_MIXEDDOMAIN cpu_to_le32(0xC00002D5) +#define STATUS_DS_NO_NEST_LOCALGROUP_IN_MIXEDDOMAIN cpu_to_le32(0xC00002D6) +#define STATUS_DS_GLOBAL_CANT_HAVE_LOCAL_MEMBER cpu_to_le32(0xC00002D7) +#define STATUS_DS_GLOBAL_CANT_HAVE_UNIVERSAL_MEMBER cpu_to_le32(0xC00002D8) +#define STATUS_DS_UNIVERSAL_CANT_HAVE_LOCAL_MEMBER cpu_to_le32(0xC00002D9) +#define STATUS_DS_GLOBAL_CANT_HAVE_CROSSDOMAIN_MEMBER cpu_to_le32(0xC00002DA) +#define STATUS_DS_LOCAL_CANT_HAVE_CROSSDOMAIN_LOCAL_MEMBER cpu_to_le32(0xC00002DB) +#define STATUS_DS_HAVE_PRIMARY_MEMBERS cpu_to_le32(0xC00002DC) +#define STATUS_WMI_NOT_SUPPORTED cpu_to_le32(0xC00002DD) +#define STATUS_INSUFFICIENT_POWER cpu_to_le32(0xC00002DE) +#define STATUS_SAM_NEED_BOOTKEY_PASSWORD cpu_to_le32(0xC00002DF) +#define STATUS_SAM_NEED_BOOTKEY_FLOPPY cpu_to_le32(0xC00002E0) +#define STATUS_DS_CANT_START cpu_to_le32(0xC00002E1) +#define STATUS_DS_INIT_FAILURE cpu_to_le32(0xC00002E2) +#define STATUS_SAM_INIT_FAILURE cpu_to_le32(0xC00002E3) +#define STATUS_DS_GC_REQUIRED cpu_to_le32(0xC00002E4) +#define STATUS_DS_LOCAL_MEMBER_OF_LOCAL_ONLY cpu_to_le32(0xC00002E5) +#define STATUS_DS_NO_FPO_IN_UNIVERSAL_GROUPS cpu_to_le32(0xC00002E6) +#define STATUS_DS_MACHINE_ACCOUNT_QUOTA_EXCEEDED cpu_to_le32(0xC00002E7) +#define STATUS_MULTIPLE_FAULT_VIOLATION cpu_to_le32(0xC00002E8) +#define STATUS_CURRENT_DOMAIN_NOT_ALLOWED cpu_to_le32(0xC00002E9) +#define STATUS_CANNOT_MAKE cpu_to_le32(0xC00002EA) +#define STATUS_SYSTEM_SHUTDOWN cpu_to_le32(0xC00002EB) +#define STATUS_DS_INIT_FAILURE_CONSOLE cpu_to_le32(0xC00002EC) +#define STATUS_DS_SAM_INIT_FAILURE_CONSOLE cpu_to_le32(0xC00002ED) +#define STATUS_UNFINISHED_CONTEXT_DELETED cpu_to_le32(0xC00002EE) +#define STATUS_NO_TGT_REPLY cpu_to_le32(0xC00002EF) +#define STATUS_OBJECTID_NOT_FOUND cpu_to_le32(0xC00002F0) +#define STATUS_NO_IP_ADDRESSES cpu_to_le32(0xC00002F1) +#define STATUS_WRONG_CREDENTIAL_HANDLE cpu_to_le32(0xC00002F2) +#define STATUS_CRYPTO_SYSTEM_INVALID cpu_to_le32(0xC00002F3) +#define STATUS_MAX_REFERRALS_EXCEEDED cpu_to_le32(0xC00002F4) +#define STATUS_MUST_BE_KDC cpu_to_le32(0xC00002F5) +#define STATUS_STRONG_CRYPTO_NOT_SUPPORTED cpu_to_le32(0xC00002F6) +#define STATUS_TOO_MANY_PRINCIPALS cpu_to_le32(0xC00002F7) +#define STATUS_NO_PA_DATA cpu_to_le32(0xC00002F8) +#define STATUS_PKINIT_NAME_MISMATCH cpu_to_le32(0xC00002F9) +#define STATUS_SMARTCARD_LOGON_REQUIRED cpu_to_le32(0xC00002FA) +#define STATUS_KDC_INVALID_REQUEST cpu_to_le32(0xC00002FB) +#define STATUS_KDC_UNABLE_TO_REFER cpu_to_le32(0xC00002FC) +#define STATUS_KDC_UNKNOWN_ETYPE cpu_to_le32(0xC00002FD) +#define STATUS_SHUTDOWN_IN_PROGRESS cpu_to_le32(0xC00002FE) +#define STATUS_SERVER_SHUTDOWN_IN_PROGRESS cpu_to_le32(0xC00002FF) +#define STATUS_NOT_SUPPORTED_ON_SBS cpu_to_le32(0xC0000300) +#define STATUS_WMI_GUID_DISCONNECTED cpu_to_le32(0xC0000301) +#define STATUS_WMI_ALREADY_DISABLED cpu_to_le32(0xC0000302) +#define STATUS_WMI_ALREADY_ENABLED cpu_to_le32(0xC0000303) +#define STATUS_MFT_TOO_FRAGMENTED cpu_to_le32(0xC0000304) +#define STATUS_COPY_PROTECTION_FAILURE cpu_to_le32(0xC0000305) +#define STATUS_CSS_AUTHENTICATION_FAILURE cpu_to_le32(0xC0000306) +#define STATUS_CSS_KEY_NOT_PRESENT cpu_to_le32(0xC0000307) +#define STATUS_CSS_KEY_NOT_ESTABLISHED cpu_to_le32(0xC0000308) +#define STATUS_CSS_SCRAMBLED_SECTOR cpu_to_le32(0xC0000309) +#define STATUS_CSS_REGION_MISMATCH cpu_to_le32(0xC000030A) +#define STATUS_CSS_RESETS_EXHAUSTED cpu_to_le32(0xC000030B) +#define STATUS_PKINIT_FAILURE cpu_to_le32(0xC0000320) +#define STATUS_SMARTCARD_SUBSYSTEM_FAILURE cpu_to_le32(0xC0000321) +#define STATUS_NO_KERB_KEY cpu_to_le32(0xC0000322) +#define STATUS_HOST_DOWN cpu_to_le32(0xC0000350) +#define STATUS_UNSUPPORTED_PREAUTH cpu_to_le32(0xC0000351) +#define STATUS_EFS_ALG_BLOB_TOO_BIG cpu_to_le32(0xC0000352) +#define STATUS_PORT_NOT_SET cpu_to_le32(0xC0000353) +#define STATUS_DEBUGGER_INACTIVE cpu_to_le32(0xC0000354) +#define STATUS_DS_VERSION_CHECK_FAILURE cpu_to_le32(0xC0000355) +#define STATUS_AUDITING_DISABLED cpu_to_le32(0xC0000356) +#define STATUS_PRENT4_MACHINE_ACCOUNT cpu_to_le32(0xC0000357) +#define STATUS_DS_AG_CANT_HAVE_UNIVERSAL_MEMBER cpu_to_le32(0xC0000358) +#define STATUS_INVALID_IMAGE_WIN_32 cpu_to_le32(0xC0000359) +#define STATUS_INVALID_IMAGE_WIN_64 cpu_to_le32(0xC000035A) +#define STATUS_BAD_BINDINGS cpu_to_le32(0xC000035B) +#define STATUS_NETWORK_SESSION_EXPIRED cpu_to_le32(0xC000035C) +#define STATUS_APPHELP_BLOCK cpu_to_le32(0xC000035D) +#define STATUS_ALL_SIDS_FILTERED cpu_to_le32(0xC000035E) +#define STATUS_NOT_SAFE_MODE_DRIVER cpu_to_le32(0xC000035F) +#define STATUS_ACCESS_DISABLED_BY_POLICY_DEFAULT cpu_to_le32(0xC0000361) +#define STATUS_ACCESS_DISABLED_BY_POLICY_PATH cpu_to_le32(0xC0000362) +#define STATUS_ACCESS_DISABLED_BY_POLICY_PUBLISHER cpu_to_le32(0xC0000363) +#define STATUS_ACCESS_DISABLED_BY_POLICY_OTHER cpu_to_le32(0xC0000364) +#define STATUS_FAILED_DRIVER_ENTRY cpu_to_le32(0xC0000365) +#define STATUS_DEVICE_ENUMERATION_ERROR cpu_to_le32(0xC0000366) +#define STATUS_MOUNT_POINT_NOT_RESOLVED cpu_to_le32(0xC0000368) +#define STATUS_INVALID_DEVICE_OBJECT_PARAMETER cpu_to_le32(0xC0000369) +#define STATUS_MCA_OCCURED cpu_to_le32(0xC000036A) +#define STATUS_DRIVER_BLOCKED_CRITICAL cpu_to_le32(0xC000036B) +#define STATUS_DRIVER_BLOCKED cpu_to_le32(0xC000036C) +#define STATUS_DRIVER_DATABASE_ERROR cpu_to_le32(0xC000036D) +#define STATUS_SYSTEM_HIVE_TOO_LARGE cpu_to_le32(0xC000036E) +#define STATUS_INVALID_IMPORT_OF_NON_DLL cpu_to_le32(0xC000036F) +#define STATUS_NO_SECRETS cpu_to_le32(0xC0000371) +#define STATUS_ACCESS_DISABLED_NO_SAFER_UI_BY_POLICY cpu_to_le32(0xC0000372) +#define STATUS_FAILED_STACK_SWITCH cpu_to_le32(0xC0000373) +#define STATUS_HEAP_CORRUPTION cpu_to_le32(0xC0000374) +#define STATUS_SMARTCARD_WRONG_PIN cpu_to_le32(0xC0000380) +#define STATUS_SMARTCARD_CARD_BLOCKED cpu_to_le32(0xC0000381) +#define STATUS_SMARTCARD_CARD_NOT_AUTHENTICATED cpu_to_le32(0xC0000382) +#define STATUS_SMARTCARD_NO_CARD cpu_to_le32(0xC0000383) +#define STATUS_SMARTCARD_NO_KEY_CONTAINER cpu_to_le32(0xC0000384) +#define STATUS_SMARTCARD_NO_CERTIFICATE cpu_to_le32(0xC0000385) +#define STATUS_SMARTCARD_NO_KEYSET cpu_to_le32(0xC0000386) +#define STATUS_SMARTCARD_IO_ERROR cpu_to_le32(0xC0000387) +#define STATUS_DOWNGRADE_DETECTED cpu_to_le32(0xC0000388) +#define STATUS_SMARTCARD_CERT_REVOKED cpu_to_le32(0xC0000389) +#define STATUS_ISSUING_CA_UNTRUSTED cpu_to_le32(0xC000038A) +#define STATUS_REVOCATION_OFFLINE_C cpu_to_le32(0xC000038B) +#define STATUS_PKINIT_CLIENT_FAILURE cpu_to_le32(0xC000038C) +#define STATUS_SMARTCARD_CERT_EXPIRED cpu_to_le32(0xC000038D) +#define STATUS_DRIVER_FAILED_PRIOR_UNLOAD cpu_to_le32(0xC000038E) +#define STATUS_SMARTCARD_SILENT_CONTEXT cpu_to_le32(0xC000038F) +#define STATUS_PER_USER_TRUST_QUOTA_EXCEEDED cpu_to_le32(0xC0000401) +#define STATUS_ALL_USER_TRUST_QUOTA_EXCEEDED cpu_to_le32(0xC0000402) +#define STATUS_USER_DELETE_TRUST_QUOTA_EXCEEDED cpu_to_le32(0xC0000403) +#define STATUS_DS_NAME_NOT_UNIQUE cpu_to_le32(0xC0000404) +#define STATUS_DS_DUPLICATE_ID_FOUND cpu_to_le32(0xC0000405) +#define STATUS_DS_GROUP_CONVERSION_ERROR cpu_to_le32(0xC0000406) +#define STATUS_VOLSNAP_PREPARE_HIBERNATE cpu_to_le32(0xC0000407) +#define STATUS_USER2USER_REQUIRED cpu_to_le32(0xC0000408) +#define STATUS_STACK_BUFFER_OVERRUN cpu_to_le32(0xC0000409) +#define STATUS_NO_S4U_PROT_SUPPORT cpu_to_le32(0xC000040A) +#define STATUS_CROSSREALM_DELEGATION_FAILURE cpu_to_le32(0xC000040B) +#define STATUS_REVOCATION_OFFLINE_KDC cpu_to_le32(0xC000040C) +#define STATUS_ISSUING_CA_UNTRUSTED_KDC cpu_to_le32(0xC000040D) +#define STATUS_KDC_CERT_EXPIRED cpu_to_le32(0xC000040E) +#define STATUS_KDC_CERT_REVOKED cpu_to_le32(0xC000040F) +#define STATUS_PARAMETER_QUOTA_EXCEEDED cpu_to_le32(0xC0000410) +#define STATUS_HIBERNATION_FAILURE cpu_to_le32(0xC0000411) +#define STATUS_DELAY_LOAD_FAILED cpu_to_le32(0xC0000412) +#define STATUS_AUTHENTICATION_FIREWALL_FAILED cpu_to_le32(0xC0000413) +#define STATUS_VDM_DISALLOWED cpu_to_le32(0xC0000414) +#define STATUS_HUNG_DISPLAY_DRIVER_THREAD cpu_to_le32(0xC0000415) +#define STATUS_INSUFFICIENT_RESOURCE_FOR_SPECIFIED_SHARED_SECTION_SIZE cpu_to_le32(0xC0000416) +#define STATUS_INVALID_CRUNTIME_PARAMETER cpu_to_le32(0xC0000417) +#define STATUS_NTLM_BLOCKED cpu_to_le32(0xC0000418) +#define STATUS_ASSERTION_FAILURE cpu_to_le32(0xC0000420) +#define STATUS_VERIFIER_STOP cpu_to_le32(0xC0000421) +#define STATUS_CALLBACK_POP_STACK cpu_to_le32(0xC0000423) +#define STATUS_INCOMPATIBLE_DRIVER_BLOCKED cpu_to_le32(0xC0000424) +#define STATUS_HIVE_UNLOADED cpu_to_le32(0xC0000425) +#define STATUS_COMPRESSION_DISABLED cpu_to_le32(0xC0000426) +#define STATUS_FILE_SYSTEM_LIMITATION cpu_to_le32(0xC0000427) +#define STATUS_INVALID_IMAGE_HASH cpu_to_le32(0xC0000428) +#define STATUS_NOT_CAPABLE cpu_to_le32(0xC0000429) +#define STATUS_REQUEST_OUT_OF_SEQUENCE cpu_to_le32(0xC000042A) +#define STATUS_IMPLEMENTATION_LIMIT cpu_to_le32(0xC000042B) +#define STATUS_ELEVATION_REQUIRED cpu_to_le32(0xC000042C) +#define STATUS_BEYOND_VDL cpu_to_le32(0xC0000432) +#define STATUS_ENCOUNTERED_WRITE_IN_PROGRESS cpu_to_le32(0xC0000433) +#define STATUS_PTE_CHANGED cpu_to_le32(0xC0000434) +#define STATUS_PURGE_FAILED cpu_to_le32(0xC0000435) +#define STATUS_CRED_REQUIRES_CONFIRMATION cpu_to_le32(0xC0000440) +#define STATUS_CS_ENCRYPTION_INVALID_SERVER_RESPONSE cpu_to_le32(0xC0000441) +#define STATUS_CS_ENCRYPTION_UNSUPPORTED_SERVER cpu_to_le32(0xC0000442) +#define STATUS_CS_ENCRYPTION_EXISTING_ENCRYPTED_FILE cpu_to_le32(0xC0000443) +#define STATUS_CS_ENCRYPTION_NEW_ENCRYPTED_FILE cpu_to_le32(0xC0000444) +#define STATUS_CS_ENCRYPTION_FILE_NOT_CSE cpu_to_le32(0xC0000445) +#define STATUS_INVALID_LABEL cpu_to_le32(0xC0000446) +#define STATUS_DRIVER_PROCESS_TERMINATED cpu_to_le32(0xC0000450) +#define STATUS_AMBIGUOUS_SYSTEM_DEVICE cpu_to_le32(0xC0000451) +#define STATUS_SYSTEM_DEVICE_NOT_FOUND cpu_to_le32(0xC0000452) +#define STATUS_RESTART_BOOT_APPLICATION cpu_to_le32(0xC0000453) +#define STATUS_INVALID_TASK_NAME cpu_to_le32(0xC0000500) +#define STATUS_INVALID_TASK_INDEX cpu_to_le32(0xC0000501) +#define STATUS_THREAD_ALREADY_IN_TASK cpu_to_le32(0xC0000502) +#define STATUS_CALLBACK_BYPASS cpu_to_le32(0xC0000503) +#define STATUS_PORT_CLOSED cpu_to_le32(0xC0000700) +#define STATUS_MESSAGE_LOST cpu_to_le32(0xC0000701) +#define STATUS_INVALID_MESSAGE cpu_to_le32(0xC0000702) +#define STATUS_REQUEST_CANCELED cpu_to_le32(0xC0000703) +#define STATUS_RECURSIVE_DISPATCH cpu_to_le32(0xC0000704) +#define STATUS_LPC_RECEIVE_BUFFER_EXPECTED cpu_to_le32(0xC0000705) +#define STATUS_LPC_INVALID_CONNECTION_USAGE cpu_to_le32(0xC0000706) +#define STATUS_LPC_REQUESTS_NOT_ALLOWED cpu_to_le32(0xC0000707) +#define STATUS_RESOURCE_IN_USE cpu_to_le32(0xC0000708) +#define STATUS_HARDWARE_MEMORY_ERROR cpu_to_le32(0xC0000709) +#define STATUS_THREADPOOL_HANDLE_EXCEPTION cpu_to_le32(0xC000070A) +#define STATUS_THREADPOOL_SET_EVENT_ON_COMPLETION_FAILED cpu_to_le32(0xC000070B) +#define STATUS_THREADPOOL_RELEASE_SEMAPHORE_ON_COMPLETION_FAILED cpu_to_le32(0xC000070C) +#define STATUS_THREADPOOL_RELEASE_MUTEX_ON_COMPLETION_FAILED cpu_to_le32(0xC000070D) +#define STATUS_THREADPOOL_FREE_LIBRARY_ON_COMPLETION_FAILED cpu_to_le32(0xC000070E) +#define STATUS_THREADPOOL_RELEASED_DURING_OPERATION cpu_to_le32(0xC000070F) +#define STATUS_CALLBACK_RETURNED_WHILE_IMPERSONATING cpu_to_le32(0xC0000710) +#define STATUS_APC_RETURNED_WHILE_IMPERSONATING cpu_to_le32(0xC0000711) +#define STATUS_PROCESS_IS_PROTECTED cpu_to_le32(0xC0000712) +#define STATUS_MCA_EXCEPTION cpu_to_le32(0xC0000713) +#define STATUS_CERTIFICATE_MAPPING_NOT_UNIQUE cpu_to_le32(0xC0000714) +#define STATUS_SYMLINK_CLASS_DISABLED cpu_to_le32(0xC0000715) +#define STATUS_INVALID_IDN_NORMALIZATION cpu_to_le32(0xC0000716) +#define STATUS_NO_UNICODE_TRANSLATION cpu_to_le32(0xC0000717) +#define STATUS_ALREADY_REGISTERED cpu_to_le32(0xC0000718) +#define STATUS_CONTEXT_MISMATCH cpu_to_le32(0xC0000719) +#define STATUS_PORT_ALREADY_HAS_COMPLETION_LIST cpu_to_le32(0xC000071A) +#define STATUS_CALLBACK_RETURNED_THREAD_PRIORITY cpu_to_le32(0xC000071B) +#define STATUS_INVALID_THREAD cpu_to_le32(0xC000071C) +#define STATUS_CALLBACK_RETURNED_TRANSACTION cpu_to_le32(0xC000071D) +#define STATUS_CALLBACK_RETURNED_LDR_LOCK cpu_to_le32(0xC000071E) +#define STATUS_CALLBACK_RETURNED_LANG cpu_to_le32(0xC000071F) +#define STATUS_CALLBACK_RETURNED_PRI_BACK cpu_to_le32(0xC0000720) +#define STATUS_CALLBACK_RETURNED_THREAD_AFFINITY cpu_to_le32(0xC0000721) +#define STATUS_DISK_REPAIR_DISABLED cpu_to_le32(0xC0000800) +#define STATUS_DS_DOMAIN_RENAME_IN_PROGRESS cpu_to_le32(0xC0000801) +#define STATUS_DISK_QUOTA_EXCEEDED cpu_to_le32(0xC0000802) +#define STATUS_CONTENT_BLOCKED cpu_to_le32(0xC0000804) +#define STATUS_BAD_CLUSTERS cpu_to_le32(0xC0000805) +#define STATUS_VOLUME_DIRTY cpu_to_le32(0xC0000806) +#define STATUS_FILE_CHECKED_OUT cpu_to_le32(0xC0000901) +#define STATUS_CHECKOUT_REQUIRED cpu_to_le32(0xC0000902) +#define STATUS_BAD_FILE_TYPE cpu_to_le32(0xC0000903) +#define STATUS_FILE_TOO_LARGE cpu_to_le32(0xC0000904) +#define STATUS_FORMS_AUTH_REQUIRED cpu_to_le32(0xC0000905) +#define STATUS_VIRUS_INFECTED cpu_to_le32(0xC0000906) +#define STATUS_VIRUS_DELETED cpu_to_le32(0xC0000907) +#define STATUS_BAD_MCFG_TABLE cpu_to_le32(0xC0000908) +#define STATUS_WOW_ASSERTION cpu_to_le32(0xC0009898) +#define STATUS_INVALID_SIGNATURE cpu_to_le32(0xC000A000) +#define STATUS_HMAC_NOT_SUPPORTED cpu_to_le32(0xC000A001) +#define STATUS_IPSEC_QUEUE_OVERFLOW cpu_to_le32(0xC000A010) +#define STATUS_ND_QUEUE_OVERFLOW cpu_to_le32(0xC000A011) +#define STATUS_HOPLIMIT_EXCEEDED cpu_to_le32(0xC000A012) +#define STATUS_PROTOCOL_NOT_SUPPORTED cpu_to_le32(0xC000A013) +#define STATUS_LOST_WRITEBEHIND_DATA_NETWORK_DISCONNECTED cpu_to_le32(0xC000A080) +#define STATUS_LOST_WRITEBEHIND_DATA_NETWORK_SERVER_ERROR cpu_to_le32(0xC000A081) +#define STATUS_LOST_WRITEBEHIND_DATA_LOCAL_DISK_ERROR cpu_to_le32(0xC000A082) +#define STATUS_XML_PARSE_ERROR cpu_to_le32(0xC000A083) +#define STATUS_XMLDSIG_ERROR cpu_to_le32(0xC000A084) +#define STATUS_WRONG_COMPARTMENT cpu_to_le32(0xC000A085) +#define STATUS_AUTHIP_FAILURE cpu_to_le32(0xC000A086) +#define DBG_NO_STATE_CHANGE cpu_to_le32(0xC0010001) +#define DBG_APP_NOT_IDLE cpu_to_le32(0xC0010002) +#define RPC_NT_INVALID_STRING_BINDING cpu_to_le32(0xC0020001) +#define RPC_NT_WRONG_KIND_OF_BINDING cpu_to_le32(0xC0020002) +#define RPC_NT_INVALID_BINDING cpu_to_le32(0xC0020003) +#define RPC_NT_PROTSEQ_NOT_SUPPORTED cpu_to_le32(0xC0020004) +#define RPC_NT_INVALID_RPC_PROTSEQ cpu_to_le32(0xC0020005) +#define RPC_NT_INVALID_STRING_UUID cpu_to_le32(0xC0020006) +#define RPC_NT_INVALID_ENDPOINT_FORMAT cpu_to_le32(0xC0020007) +#define RPC_NT_INVALID_NET_ADDR cpu_to_le32(0xC0020008) +#define RPC_NT_NO_ENDPOINT_FOUND cpu_to_le32(0xC0020009) +#define RPC_NT_INVALID_TIMEOUT cpu_to_le32(0xC002000A) +#define RPC_NT_OBJECT_NOT_FOUND cpu_to_le32(0xC002000B) +#define RPC_NT_ALREADY_REGISTERED cpu_to_le32(0xC002000C) +#define RPC_NT_TYPE_ALREADY_REGISTERED cpu_to_le32(0xC002000D) +#define RPC_NT_ALREADY_LISTENING cpu_to_le32(0xC002000E) +#define RPC_NT_NO_PROTSEQS_REGISTERED cpu_to_le32(0xC002000F) +#define RPC_NT_NOT_LISTENING cpu_to_le32(0xC0020010) +#define RPC_NT_UNKNOWN_MGR_TYPE cpu_to_le32(0xC0020011) +#define RPC_NT_UNKNOWN_IF cpu_to_le32(0xC0020012) +#define RPC_NT_NO_BINDINGS cpu_to_le32(0xC0020013) +#define RPC_NT_NO_PROTSEQS cpu_to_le32(0xC0020014) +#define RPC_NT_CANT_CREATE_ENDPOINT cpu_to_le32(0xC0020015) +#define RPC_NT_OUT_OF_RESOURCES cpu_to_le32(0xC0020016) +#define RPC_NT_SERVER_UNAVAILABLE cpu_to_le32(0xC0020017) +#define RPC_NT_SERVER_TOO_BUSY cpu_to_le32(0xC0020018) +#define RPC_NT_INVALID_NETWORK_OPTIONS cpu_to_le32(0xC0020019) +#define RPC_NT_NO_CALL_ACTIVE cpu_to_le32(0xC002001A) +#define RPC_NT_CALL_FAILED cpu_to_le32(0xC002001B) +#define RPC_NT_CALL_FAILED_DNE cpu_to_le32(0xC002001C) +#define RPC_NT_PROTOCOL_ERROR cpu_to_le32(0xC002001D) +#define RPC_NT_UNSUPPORTED_TRANS_SYN cpu_to_le32(0xC002001F) +#define RPC_NT_UNSUPPORTED_TYPE cpu_to_le32(0xC0020021) +#define RPC_NT_INVALID_TAG cpu_to_le32(0xC0020022) +#define RPC_NT_INVALID_BOUND cpu_to_le32(0xC0020023) +#define RPC_NT_NO_ENTRY_NAME cpu_to_le32(0xC0020024) +#define RPC_NT_INVALID_NAME_SYNTAX cpu_to_le32(0xC0020025) +#define RPC_NT_UNSUPPORTED_NAME_SYNTAX cpu_to_le32(0xC0020026) +#define RPC_NT_UUID_NO_ADDRESS cpu_to_le32(0xC0020028) +#define RPC_NT_DUPLICATE_ENDPOINT cpu_to_le32(0xC0020029) +#define RPC_NT_UNKNOWN_AUTHN_TYPE cpu_to_le32(0xC002002A) +#define RPC_NT_MAX_CALLS_TOO_SMALL cpu_to_le32(0xC002002B) +#define RPC_NT_STRING_TOO_LONG cpu_to_le32(0xC002002C) +#define RPC_NT_PROTSEQ_NOT_FOUND cpu_to_le32(0xC002002D) +#define RPC_NT_PROCNUM_OUT_OF_RANGE cpu_to_le32(0xC002002E) +#define RPC_NT_BINDING_HAS_NO_AUTH cpu_to_le32(0xC002002F) +#define RPC_NT_UNKNOWN_AUTHN_SERVICE cpu_to_le32(0xC0020030) +#define RPC_NT_UNKNOWN_AUTHN_LEVEL cpu_to_le32(0xC0020031) +#define RPC_NT_INVALID_AUTH_IDENTITY cpu_to_le32(0xC0020032) +#define RPC_NT_UNKNOWN_AUTHZ_SERVICE cpu_to_le32(0xC0020033) +#define EPT_NT_INVALID_ENTRY cpu_to_le32(0xC0020034) +#define EPT_NT_CANT_PERFORM_OP cpu_to_le32(0xC0020035) +#define EPT_NT_NOT_REGISTERED cpu_to_le32(0xC0020036) +#define RPC_NT_NOTHING_TO_EXPORT cpu_to_le32(0xC0020037) +#define RPC_NT_INCOMPLETE_NAME cpu_to_le32(0xC0020038) +#define RPC_NT_INVALID_VERS_OPTION cpu_to_le32(0xC0020039) +#define RPC_NT_NO_MORE_MEMBERS cpu_to_le32(0xC002003A) +#define RPC_NT_NOT_ALL_OBJS_UNEXPORTED cpu_to_le32(0xC002003B) +#define RPC_NT_INTERFACE_NOT_FOUND cpu_to_le32(0xC002003C) +#define RPC_NT_ENTRY_ALREADY_EXISTS cpu_to_le32(0xC002003D) +#define RPC_NT_ENTRY_NOT_FOUND cpu_to_le32(0xC002003E) +#define RPC_NT_NAME_SERVICE_UNAVAILABLE cpu_to_le32(0xC002003F) +#define RPC_NT_INVALID_NAF_ID cpu_to_le32(0xC0020040) +#define RPC_NT_CANNOT_SUPPORT cpu_to_le32(0xC0020041) +#define RPC_NT_NO_CONTEXT_AVAILABLE cpu_to_le32(0xC0020042) +#define RPC_NT_INTERNAL_ERROR cpu_to_le32(0xC0020043) +#define RPC_NT_ZERO_DIVIDE cpu_to_le32(0xC0020044) +#define RPC_NT_ADDRESS_ERROR cpu_to_le32(0xC0020045) +#define RPC_NT_FP_DIV_ZERO cpu_to_le32(0xC0020046) +#define RPC_NT_FP_UNDERFLOW cpu_to_le32(0xC0020047) +#define RPC_NT_FP_OVERFLOW cpu_to_le32(0xC0020048) +#define RPC_NT_CALL_IN_PROGRESS cpu_to_le32(0xC0020049) +#define RPC_NT_NO_MORE_BINDINGS cpu_to_le32(0xC002004A) +#define RPC_NT_GROUP_MEMBER_NOT_FOUND cpu_to_le32(0xC002004B) +#define EPT_NT_CANT_CREATE cpu_to_le32(0xC002004C) +#define RPC_NT_INVALID_OBJECT cpu_to_le32(0xC002004D) +#define RPC_NT_NO_INTERFACES cpu_to_le32(0xC002004F) +#define RPC_NT_CALL_CANCELLED cpu_to_le32(0xC0020050) +#define RPC_NT_BINDING_INCOMPLETE cpu_to_le32(0xC0020051) +#define RPC_NT_COMM_FAILURE cpu_to_le32(0xC0020052) +#define RPC_NT_UNSUPPORTED_AUTHN_LEVEL cpu_to_le32(0xC0020053) +#define RPC_NT_NO_PRINC_NAME cpu_to_le32(0xC0020054) +#define RPC_NT_NOT_RPC_ERROR cpu_to_le32(0xC0020055) +#define RPC_NT_SEC_PKG_ERROR cpu_to_le32(0xC0020057) +#define RPC_NT_NOT_CANCELLED cpu_to_le32(0xC0020058) +#define RPC_NT_INVALID_ASYNC_HANDLE cpu_to_le32(0xC0020062) +#define RPC_NT_INVALID_ASYNC_CALL cpu_to_le32(0xC0020063) +#define RPC_NT_PROXY_ACCESS_DENIED cpu_to_le32(0xC0020064) +#define RPC_NT_NO_MORE_ENTRIES cpu_to_le32(0xC0030001) +#define RPC_NT_SS_CHAR_TRANS_OPEN_FAIL cpu_to_le32(0xC0030002) +#define RPC_NT_SS_CHAR_TRANS_SHORT_FILE cpu_to_le32(0xC0030003) +#define RPC_NT_SS_IN_NULL_CONTEXT cpu_to_le32(0xC0030004) +#define RPC_NT_SS_CONTEXT_MISMATCH cpu_to_le32(0xC0030005) +#define RPC_NT_SS_CONTEXT_DAMAGED cpu_to_le32(0xC0030006) +#define RPC_NT_SS_HANDLES_MISMATCH cpu_to_le32(0xC0030007) +#define RPC_NT_SS_CANNOT_GET_CALL_HANDLE cpu_to_le32(0xC0030008) +#define RPC_NT_NULL_REF_POINTER cpu_to_le32(0xC0030009) +#define RPC_NT_ENUM_VALUE_OUT_OF_RANGE cpu_to_le32(0xC003000A) +#define RPC_NT_BYTE_COUNT_TOO_SMALL cpu_to_le32(0xC003000B) +#define RPC_NT_BAD_STUB_DATA cpu_to_le32(0xC003000C) +#define RPC_NT_INVALID_ES_ACTION cpu_to_le32(0xC0030059) +#define RPC_NT_WRONG_ES_VERSION cpu_to_le32(0xC003005A) +#define RPC_NT_WRONG_STUB_VERSION cpu_to_le32(0xC003005B) +#define RPC_NT_INVALID_PIPE_OBJECT cpu_to_le32(0xC003005C) +#define RPC_NT_INVALID_PIPE_OPERATION cpu_to_le32(0xC003005D) +#define RPC_NT_WRONG_PIPE_VERSION cpu_to_le32(0xC003005E) +#define RPC_NT_PIPE_CLOSED cpu_to_le32(0xC003005F) +#define RPC_NT_PIPE_DISCIPLINE_ERROR cpu_to_le32(0xC0030060) +#define RPC_NT_PIPE_EMPTY cpu_to_le32(0xC0030061) +#define STATUS_PNP_BAD_MPS_TABLE cpu_to_le32(0xC0040035) +#define STATUS_PNP_TRANSLATION_FAILED cpu_to_le32(0xC0040036) +#define STATUS_PNP_IRQ_TRANSLATION_FAILED cpu_to_le32(0xC0040037) +#define STATUS_PNP_INVALID_ID cpu_to_le32(0xC0040038) +#define STATUS_IO_REISSUE_AS_CACHED cpu_to_le32(0xC0040039) +#define STATUS_CTX_WINSTATION_NAME_INVALID cpu_to_le32(0xC00A0001) +#define STATUS_CTX_INVALID_PD cpu_to_le32(0xC00A0002) +#define STATUS_CTX_PD_NOT_FOUND cpu_to_le32(0xC00A0003) +#define STATUS_CTX_CLOSE_PENDING cpu_to_le32(0xC00A0006) +#define STATUS_CTX_NO_OUTBUF cpu_to_le32(0xC00A0007) +#define STATUS_CTX_MODEM_INF_NOT_FOUND cpu_to_le32(0xC00A0008) +#define STATUS_CTX_INVALID_MODEMNAME cpu_to_le32(0xC00A0009) +#define STATUS_CTX_RESPONSE_ERROR cpu_to_le32(0xC00A000A) +#define STATUS_CTX_MODEM_RESPONSE_TIMEOUT cpu_to_le32(0xC00A000B) +#define STATUS_CTX_MODEM_RESPONSE_NO_CARRIER cpu_to_le32(0xC00A000C) +#define STATUS_CTX_MODEM_RESPONSE_NO_DIALTONE cpu_to_le32(0xC00A000D) +#define STATUS_CTX_MODEM_RESPONSE_BUSY cpu_to_le32(0xC00A000E) +#define STATUS_CTX_MODEM_RESPONSE_VOICE cpu_to_le32(0xC00A000F) +#define STATUS_CTX_TD_ERROR cpu_to_le32(0xC00A0010) +#define STATUS_CTX_LICENSE_CLIENT_INVALID cpu_to_le32(0xC00A0012) +#define STATUS_CTX_LICENSE_NOT_AVAILABLE cpu_to_le32(0xC00A0013) +#define STATUS_CTX_LICENSE_EXPIRED cpu_to_le32(0xC00A0014) +#define STATUS_CTX_WINSTATION_NOT_FOUND cpu_to_le32(0xC00A0015) +#define STATUS_CTX_WINSTATION_NAME_COLLISION cpu_to_le32(0xC00A0016) +#define STATUS_CTX_WINSTATION_BUSY cpu_to_le32(0xC00A0017) +#define STATUS_CTX_BAD_VIDEO_MODE cpu_to_le32(0xC00A0018) +#define STATUS_CTX_GRAPHICS_INVALID cpu_to_le32(0xC00A0022) +#define STATUS_CTX_NOT_CONSOLE cpu_to_le32(0xC00A0024) +#define STATUS_CTX_CLIENT_QUERY_TIMEOUT cpu_to_le32(0xC00A0026) +#define STATUS_CTX_CONSOLE_DISCONNECT cpu_to_le32(0xC00A0027) +#define STATUS_CTX_CONSOLE_CONNECT cpu_to_le32(0xC00A0028) +#define STATUS_CTX_SHADOW_DENIED cpu_to_le32(0xC00A002A) +#define STATUS_CTX_WINSTATION_ACCESS_DENIED cpu_to_le32(0xC00A002B) +#define STATUS_CTX_INVALID_WD cpu_to_le32(0xC00A002E) +#define STATUS_CTX_WD_NOT_FOUND cpu_to_le32(0xC00A002F) +#define STATUS_CTX_SHADOW_INVALID cpu_to_le32(0xC00A0030) +#define STATUS_CTX_SHADOW_DISABLED cpu_to_le32(0xC00A0031) +#define STATUS_RDP_PROTOCOL_ERROR cpu_to_le32(0xC00A0032) +#define STATUS_CTX_CLIENT_LICENSE_NOT_SET cpu_to_le32(0xC00A0033) +#define STATUS_CTX_CLIENT_LICENSE_IN_USE cpu_to_le32(0xC00A0034) +#define STATUS_CTX_SHADOW_ENDED_BY_MODE_CHANGE cpu_to_le32(0xC00A0035) +#define STATUS_CTX_SHADOW_NOT_RUNNING cpu_to_le32(0xC00A0036) +#define STATUS_CTX_LOGON_DISABLED cpu_to_le32(0xC00A0037) +#define STATUS_CTX_SECURITY_LAYER_ERROR cpu_to_le32(0xC00A0038) +#define STATUS_TS_INCOMPATIBLE_SESSIONS cpu_to_le32(0xC00A0039) +#define STATUS_MUI_FILE_NOT_FOUND cpu_to_le32(0xC00B0001) +#define STATUS_MUI_INVALID_FILE cpu_to_le32(0xC00B0002) +#define STATUS_MUI_INVALID_RC_CONFIG cpu_to_le32(0xC00B0003) +#define STATUS_MUI_INVALID_LOCALE_NAME cpu_to_le32(0xC00B0004) +#define STATUS_MUI_INVALID_ULTIMATEFALLBACK_NAME cpu_to_le32(0xC00B0005) +#define STATUS_MUI_FILE_NOT_LOADED cpu_to_le32(0xC00B0006) +#define STATUS_RESOURCE_ENUM_USER_STOP cpu_to_le32(0xC00B0007) +#define STATUS_CLUSTER_INVALID_NODE cpu_to_le32(0xC0130001) +#define STATUS_CLUSTER_NODE_EXISTS cpu_to_le32(0xC0130002) +#define STATUS_CLUSTER_JOIN_IN_PROGRESS cpu_to_le32(0xC0130003) +#define STATUS_CLUSTER_NODE_NOT_FOUND cpu_to_le32(0xC0130004) +#define STATUS_CLUSTER_LOCAL_NODE_NOT_FOUND cpu_to_le32(0xC0130005) +#define STATUS_CLUSTER_NETWORK_EXISTS cpu_to_le32(0xC0130006) +#define STATUS_CLUSTER_NETWORK_NOT_FOUND cpu_to_le32(0xC0130007) +#define STATUS_CLUSTER_NETINTERFACE_EXISTS cpu_to_le32(0xC0130008) +#define STATUS_CLUSTER_NETINTERFACE_NOT_FOUND cpu_to_le32(0xC0130009) +#define STATUS_CLUSTER_INVALID_REQUEST cpu_to_le32(0xC013000A) +#define STATUS_CLUSTER_INVALID_NETWORK_PROVIDER cpu_to_le32(0xC013000B) +#define STATUS_CLUSTER_NODE_DOWN cpu_to_le32(0xC013000C) +#define STATUS_CLUSTER_NODE_UNREACHABLE cpu_to_le32(0xC013000D) +#define STATUS_CLUSTER_NODE_NOT_MEMBER cpu_to_le32(0xC013000E) +#define STATUS_CLUSTER_JOIN_NOT_IN_PROGRESS cpu_to_le32(0xC013000F) +#define STATUS_CLUSTER_INVALID_NETWORK cpu_to_le32(0xC0130010) +#define STATUS_CLUSTER_NO_NET_ADAPTERS cpu_to_le32(0xC0130011) +#define STATUS_CLUSTER_NODE_UP cpu_to_le32(0xC0130012) +#define STATUS_CLUSTER_NODE_PAUSED cpu_to_le32(0xC0130013) +#define STATUS_CLUSTER_NODE_NOT_PAUSED cpu_to_le32(0xC0130014) +#define STATUS_CLUSTER_NO_SECURITY_CONTEXT cpu_to_le32(0xC0130015) +#define STATUS_CLUSTER_NETWORK_NOT_INTERNAL cpu_to_le32(0xC0130016) +#define STATUS_CLUSTER_POISONED cpu_to_le32(0xC0130017) +#define STATUS_ACPI_INVALID_OPCODE cpu_to_le32(0xC0140001) +#define STATUS_ACPI_STACK_OVERFLOW cpu_to_le32(0xC0140002) +#define STATUS_ACPI_ASSERT_FAILED cpu_to_le32(0xC0140003) +#define STATUS_ACPI_INVALID_INDEX cpu_to_le32(0xC0140004) +#define STATUS_ACPI_INVALID_ARGUMENT cpu_to_le32(0xC0140005) +#define STATUS_ACPI_FATAL cpu_to_le32(0xC0140006) +#define STATUS_ACPI_INVALID_SUPERNAME cpu_to_le32(0xC0140007) +#define STATUS_ACPI_INVALID_ARGTYPE cpu_to_le32(0xC0140008) +#define STATUS_ACPI_INVALID_OBJTYPE cpu_to_le32(0xC0140009) +#define STATUS_ACPI_INVALID_TARGETTYPE cpu_to_le32(0xC014000A) +#define STATUS_ACPI_INCORRECT_ARGUMENT_COUNT cpu_to_le32(0xC014000B) +#define STATUS_ACPI_ADDRESS_NOT_MAPPED cpu_to_le32(0xC014000C) +#define STATUS_ACPI_INVALID_EVENTTYPE cpu_to_le32(0xC014000D) +#define STATUS_ACPI_HANDLER_COLLISION cpu_to_le32(0xC014000E) +#define STATUS_ACPI_INVALID_DATA cpu_to_le32(0xC014000F) +#define STATUS_ACPI_INVALID_REGION cpu_to_le32(0xC0140010) +#define STATUS_ACPI_INVALID_ACCESS_SIZE cpu_to_le32(0xC0140011) +#define STATUS_ACPI_ACQUIRE_GLOBAL_LOCK cpu_to_le32(0xC0140012) +#define STATUS_ACPI_ALREADY_INITIALIZED cpu_to_le32(0xC0140013) +#define STATUS_ACPI_NOT_INITIALIZED cpu_to_le32(0xC0140014) +#define STATUS_ACPI_INVALID_MUTEX_LEVEL cpu_to_le32(0xC0140015) +#define STATUS_ACPI_MUTEX_NOT_OWNED cpu_to_le32(0xC0140016) +#define STATUS_ACPI_MUTEX_NOT_OWNER cpu_to_le32(0xC0140017) +#define STATUS_ACPI_RS_ACCESS cpu_to_le32(0xC0140018) +#define STATUS_ACPI_INVALID_TABLE cpu_to_le32(0xC0140019) +#define STATUS_ACPI_REG_HANDLER_FAILED cpu_to_le32(0xC0140020) +#define STATUS_ACPI_POWER_REQUEST_FAILED cpu_to_le32(0xC0140021) +#define STATUS_SXS_SECTION_NOT_FOUND cpu_to_le32(0xC0150001) +#define STATUS_SXS_CANT_GEN_ACTCTX cpu_to_le32(0xC0150002) +#define STATUS_SXS_INVALID_ACTCTXDATA_FORMAT cpu_to_le32(0xC0150003) +#define STATUS_SXS_ASSEMBLY_NOT_FOUND cpu_to_le32(0xC0150004) +#define STATUS_SXS_MANIFEST_FORMAT_ERROR cpu_to_le32(0xC0150005) +#define STATUS_SXS_MANIFEST_PARSE_ERROR cpu_to_le32(0xC0150006) +#define STATUS_SXS_ACTIVATION_CONTEXT_DISABLED cpu_to_le32(0xC0150007) +#define STATUS_SXS_KEY_NOT_FOUND cpu_to_le32(0xC0150008) +#define STATUS_SXS_VERSION_CONFLICT cpu_to_le32(0xC0150009) +#define STATUS_SXS_WRONG_SECTION_TYPE cpu_to_le32(0xC015000A) +#define STATUS_SXS_THREAD_QUERIES_DISABLED cpu_to_le32(0xC015000B) +#define STATUS_SXS_ASSEMBLY_MISSING cpu_to_le32(0xC015000C) +#define STATUS_SXS_PROCESS_DEFAULT_ALREADY_SET cpu_to_le32(0xC015000E) +#define STATUS_SXS_EARLY_DEACTIVATION cpu_to_le32(0xC015000F) +#define STATUS_SXS_INVALID_DEACTIVATION cpu_to_le32(0xC0150010) +#define STATUS_SXS_MULTIPLE_DEACTIVATION cpu_to_le32(0xC0150011) +#define STATUS_SXS_SYSTEM_DEFAULT_ACTIVATION_CONTEXT_EMPTY cpu_to_le32(0xC0150012) +#define STATUS_SXS_PROCESS_TERMINATION_REQUESTED cpu_to_le32(0xC0150013) +#define STATUS_SXS_CORRUPT_ACTIVATION_STACK cpu_to_le32(0xC0150014) +#define STATUS_SXS_CORRUPTION cpu_to_le32(0xC0150015) +#define STATUS_SXS_INVALID_IDENTITY_ATTRIBUTE_VALUE cpu_to_le32(0xC0150016) +#define STATUS_SXS_INVALID_IDENTITY_ATTRIBUTE_NAME cpu_to_le32(0xC0150017) +#define STATUS_SXS_IDENTITY_DUPLICATE_ATTRIBUTE cpu_to_le32(0xC0150018) +#define STATUS_SXS_IDENTITY_PARSE_ERROR cpu_to_le32(0xC0150019) +#define STATUS_SXS_COMPONENT_STORE_CORRUPT cpu_to_le32(0xC015001A) +#define STATUS_SXS_FILE_HASH_MISMATCH cpu_to_le32(0xC015001B) +#define STATUS_SXS_MANIFEST_IDENTITY_SAME_BUT_CONTENTS_DIFFERENT cpu_to_le32(0xC015001C) +#define STATUS_SXS_IDENTITIES_DIFFERENT cpu_to_le32(0xC015001D) +#define STATUS_SXS_ASSEMBLY_IS_NOT_A_DEPLOYMENT cpu_to_le32(0xC015001E) +#define STATUS_SXS_FILE_NOT_PART_OF_ASSEMBLY cpu_to_le32(0xC015001F) +#define STATUS_ADVANCED_INSTALLER_FAILED cpu_to_le32(0xC0150020) +#define STATUS_XML_ENCODING_MISMATCH cpu_to_le32(0xC0150021) +#define STATUS_SXS_MANIFEST_TOO_BIG cpu_to_le32(0xC0150022) +#define STATUS_SXS_SETTING_NOT_REGISTERED cpu_to_le32(0xC0150023) +#define STATUS_SXS_TRANSACTION_CLOSURE_INCOMPLETE cpu_to_le32(0xC0150024) +#define STATUS_SMI_PRIMITIVE_INSTALLER_FAILED cpu_to_le32(0xC0150025) +#define STATUS_GENERIC_COMMAND_FAILED cpu_to_le32(0xC0150026) +#define STATUS_SXS_FILE_HASH_MISSING cpu_to_le32(0xC0150027) +#define STATUS_TRANSACTIONAL_CONFLICT cpu_to_le32(0xC0190001) +#define STATUS_INVALID_TRANSACTION cpu_to_le32(0xC0190002) +#define STATUS_TRANSACTION_NOT_ACTIVE cpu_to_le32(0xC0190003) +#define STATUS_TM_INITIALIZATION_FAILED cpu_to_le32(0xC0190004) +#define STATUS_RM_NOT_ACTIVE cpu_to_le32(0xC0190005) +#define STATUS_RM_METADATA_CORRUPT cpu_to_le32(0xC0190006) +#define STATUS_TRANSACTION_NOT_JOINED cpu_to_le32(0xC0190007) +#define STATUS_DIRECTORY_NOT_RM cpu_to_le32(0xC0190008) +#define STATUS_TRANSACTIONS_UNSUPPORTED_REMOTE cpu_to_le32(0xC019000A) +#define STATUS_LOG_RESIZE_INVALID_SIZE cpu_to_le32(0xC019000B) +#define STATUS_REMOTE_FILE_VERSION_MISMATCH cpu_to_le32(0xC019000C) +#define STATUS_CRM_PROTOCOL_ALREADY_EXISTS cpu_to_le32(0xC019000F) +#define STATUS_TRANSACTION_PROPAGATION_FAILED cpu_to_le32(0xC0190010) +#define STATUS_CRM_PROTOCOL_NOT_FOUND cpu_to_le32(0xC0190011) +#define STATUS_TRANSACTION_SUPERIOR_EXISTS cpu_to_le32(0xC0190012) +#define STATUS_TRANSACTION_REQUEST_NOT_VALID cpu_to_le32(0xC0190013) +#define STATUS_TRANSACTION_NOT_REQUESTED cpu_to_le32(0xC0190014) +#define STATUS_TRANSACTION_ALREADY_ABORTED cpu_to_le32(0xC0190015) +#define STATUS_TRANSACTION_ALREADY_COMMITTED cpu_to_le32(0xC0190016) +#define STATUS_TRANSACTION_INVALID_MARSHALL_BUFFER cpu_to_le32(0xC0190017) +#define STATUS_CURRENT_TRANSACTION_NOT_VALID cpu_to_le32(0xC0190018) +#define STATUS_LOG_GROWTH_FAILED cpu_to_le32(0xC0190019) +#define STATUS_OBJECT_NO_LONGER_EXISTS cpu_to_le32(0xC0190021) +#define STATUS_STREAM_MINIVERSION_NOT_FOUND cpu_to_le32(0xC0190022) +#define STATUS_STREAM_MINIVERSION_NOT_VALID cpu_to_le32(0xC0190023) +#define STATUS_MINIVERSION_INACCESSIBLE_FROM_SPECIFIED_TRANSACTION cpu_to_le32(0xC0190024) +#define STATUS_CANT_OPEN_MINIVERSION_WITH_MODIFY_INTENT cpu_to_le32(0xC0190025) +#define STATUS_CANT_CREATE_MORE_STREAM_MINIVERSIONS cpu_to_le32(0xC0190026) +#define STATUS_HANDLE_NO_LONGER_VALID cpu_to_le32(0xC0190028) +#define STATUS_LOG_CORRUPTION_DETECTED cpu_to_le32(0xC0190030) +#define STATUS_RM_DISCONNECTED cpu_to_le32(0xC0190032) +#define STATUS_ENLISTMENT_NOT_SUPERIOR cpu_to_le32(0xC0190033) +#define STATUS_FILE_IDENTITY_NOT_PERSISTENT cpu_to_le32(0xC0190036) +#define STATUS_CANT_BREAK_TRANSACTIONAL_DEPENDENCY cpu_to_le32(0xC0190037) +#define STATUS_CANT_CROSS_RM_BOUNDARY cpu_to_le32(0xC0190038) +#define STATUS_TXF_DIR_NOT_EMPTY cpu_to_le32(0xC0190039) +#define STATUS_INDOUBT_TRANSACTIONS_EXIST cpu_to_le32(0xC019003A) +#define STATUS_TM_VOLATILE cpu_to_le32(0xC019003B) +#define STATUS_ROLLBACK_TIMER_EXPIRED cpu_to_le32(0xC019003C) +#define STATUS_TXF_ATTRIBUTE_CORRUPT cpu_to_le32(0xC019003D) +#define STATUS_EFS_NOT_ALLOWED_IN_TRANSACTION cpu_to_le32(0xC019003E) +#define STATUS_TRANSACTIONAL_OPEN_NOT_ALLOWED cpu_to_le32(0xC019003F) +#define STATUS_TRANSACTED_MAPPING_UNSUPPORTED_REMOTE cpu_to_le32(0xC0190040) +#define STATUS_TRANSACTION_REQUIRED_PROMOTION cpu_to_le32(0xC0190043) +#define STATUS_CANNOT_EXECUTE_FILE_IN_TRANSACTION cpu_to_le32(0xC0190044) +#define STATUS_TRANSACTIONS_NOT_FROZEN cpu_to_le32(0xC0190045) +#define STATUS_TRANSACTION_FREEZE_IN_PROGRESS cpu_to_le32(0xC0190046) +#define STATUS_NOT_SNAPSHOT_VOLUME cpu_to_le32(0xC0190047) +#define STATUS_NO_SAVEPOINT_WITH_OPEN_FILES cpu_to_le32(0xC0190048) +#define STATUS_SPARSE_NOT_ALLOWED_IN_TRANSACTION cpu_to_le32(0xC0190049) +#define STATUS_TM_IDENTITY_MISMATCH cpu_to_le32(0xC019004A) +#define STATUS_FLOATED_SECTION cpu_to_le32(0xC019004B) +#define STATUS_CANNOT_ACCEPT_TRANSACTED_WORK cpu_to_le32(0xC019004C) +#define STATUS_CANNOT_ABORT_TRANSACTIONS cpu_to_le32(0xC019004D) +#define STATUS_TRANSACTION_NOT_FOUND cpu_to_le32(0xC019004E) +#define STATUS_RESOURCEMANAGER_NOT_FOUND cpu_to_le32(0xC019004F) +#define STATUS_ENLISTMENT_NOT_FOUND cpu_to_le32(0xC0190050) +#define STATUS_TRANSACTIONMANAGER_NOT_FOUND cpu_to_le32(0xC0190051) +#define STATUS_TRANSACTIONMANAGER_NOT_ONLINE cpu_to_le32(0xC0190052) +#define STATUS_TRANSACTIONMANAGER_RECOVERY_NAME_COLLISION cpu_to_le32(0xC0190053) +#define STATUS_TRANSACTION_NOT_ROOT cpu_to_le32(0xC0190054) +#define STATUS_TRANSACTION_OBJECT_EXPIRED cpu_to_le32(0xC0190055) +#define STATUS_COMPRESSION_NOT_ALLOWED_IN_TRANSACTION cpu_to_le32(0xC0190056) +#define STATUS_TRANSACTION_RESPONSE_NOT_ENLISTED cpu_to_le32(0xC0190057) +#define STATUS_TRANSACTION_RECORD_TOO_LONG cpu_to_le32(0xC0190058) +#define STATUS_NO_LINK_TRACKING_IN_TRANSACTION cpu_to_le32(0xC0190059) +#define STATUS_OPERATION_NOT_SUPPORTED_IN_TRANSACTION cpu_to_le32(0xC019005A) +#define STATUS_TRANSACTION_INTEGRITY_VIOLATED cpu_to_le32(0xC019005B) +#define STATUS_LOG_SECTOR_INVALID cpu_to_le32(0xC01A0001) +#define STATUS_LOG_SECTOR_PARITY_INVALID cpu_to_le32(0xC01A0002) +#define STATUS_LOG_SECTOR_REMAPPED cpu_to_le32(0xC01A0003) +#define STATUS_LOG_BLOCK_INCOMPLETE cpu_to_le32(0xC01A0004) +#define STATUS_LOG_INVALID_RANGE cpu_to_le32(0xC01A0005) +#define STATUS_LOG_BLOCKS_EXHAUSTED cpu_to_le32(0xC01A0006) +#define STATUS_LOG_READ_CONTEXT_INVALID cpu_to_le32(0xC01A0007) +#define STATUS_LOG_RESTART_INVALID cpu_to_le32(0xC01A0008) +#define STATUS_LOG_BLOCK_VERSION cpu_to_le32(0xC01A0009) +#define STATUS_LOG_BLOCK_INVALID cpu_to_le32(0xC01A000A) +#define STATUS_LOG_READ_MODE_INVALID cpu_to_le32(0xC01A000B) +#define STATUS_LOG_METADATA_CORRUPT cpu_to_le32(0xC01A000D) +#define STATUS_LOG_METADATA_INVALID cpu_to_le32(0xC01A000E) +#define STATUS_LOG_METADATA_INCONSISTENT cpu_to_le32(0xC01A000F) +#define STATUS_LOG_RESERVATION_INVALID cpu_to_le32(0xC01A0010) +#define STATUS_LOG_CANT_DELETE cpu_to_le32(0xC01A0011) +#define STATUS_LOG_CONTAINER_LIMIT_EXCEEDED cpu_to_le32(0xC01A0012) +#define STATUS_LOG_START_OF_LOG cpu_to_le32(0xC01A0013) +#define STATUS_LOG_POLICY_ALREADY_INSTALLED cpu_to_le32(0xC01A0014) +#define STATUS_LOG_POLICY_NOT_INSTALLED cpu_to_le32(0xC01A0015) +#define STATUS_LOG_POLICY_INVALID cpu_to_le32(0xC01A0016) +#define STATUS_LOG_POLICY_CONFLICT cpu_to_le32(0xC01A0017) +#define STATUS_LOG_PINNED_ARCHIVE_TAIL cpu_to_le32(0xC01A0018) +#define STATUS_LOG_RECORD_NONEXISTENT cpu_to_le32(0xC01A0019) +#define STATUS_LOG_RECORDS_RESERVED_INVALID cpu_to_le32(0xC01A001A) +#define STATUS_LOG_SPACE_RESERVED_INVALID cpu_to_le32(0xC01A001B) +#define STATUS_LOG_TAIL_INVALID cpu_to_le32(0xC01A001C) +#define STATUS_LOG_FULL cpu_to_le32(0xC01A001D) +#define STATUS_LOG_MULTIPLEXED cpu_to_le32(0xC01A001E) +#define STATUS_LOG_DEDICATED cpu_to_le32(0xC01A001F) +#define STATUS_LOG_ARCHIVE_NOT_IN_PROGRESS cpu_to_le32(0xC01A0020) +#define STATUS_LOG_ARCHIVE_IN_PROGRESS cpu_to_le32(0xC01A0021) +#define STATUS_LOG_EPHEMERAL cpu_to_le32(0xC01A0022) +#define STATUS_LOG_NOT_ENOUGH_CONTAINERS cpu_to_le32(0xC01A0023) +#define STATUS_LOG_CLIENT_ALREADY_REGISTERED cpu_to_le32(0xC01A0024) +#define STATUS_LOG_CLIENT_NOT_REGISTERED cpu_to_le32(0xC01A0025) +#define STATUS_LOG_FULL_HANDLER_IN_PROGRESS cpu_to_le32(0xC01A0026) +#define STATUS_LOG_CONTAINER_READ_FAILED cpu_to_le32(0xC01A0027) +#define STATUS_LOG_CONTAINER_WRITE_FAILED cpu_to_le32(0xC01A0028) +#define STATUS_LOG_CONTAINER_OPEN_FAILED cpu_to_le32(0xC01A0029) +#define STATUS_LOG_CONTAINER_STATE_INVALID cpu_to_le32(0xC01A002A) +#define STATUS_LOG_STATE_INVALID cpu_to_le32(0xC01A002B) +#define STATUS_LOG_PINNED cpu_to_le32(0xC01A002C) +#define STATUS_LOG_METADATA_FLUSH_FAILED cpu_to_le32(0xC01A002D) +#define STATUS_LOG_INCONSISTENT_SECURITY cpu_to_le32(0xC01A002E) +#define STATUS_LOG_APPENDED_FLUSH_FAILED cpu_to_le32(0xC01A002F) +#define STATUS_LOG_PINNED_RESERVATION cpu_to_le32(0xC01A0030) +#define STATUS_VIDEO_HUNG_DISPLAY_DRIVER_THREAD cpu_to_le32(0xC01B00EA) +#define STATUS_FLT_NO_HANDLER_DEFINED cpu_to_le32(0xC01C0001) +#define STATUS_FLT_CONTEXT_ALREADY_DEFINED cpu_to_le32(0xC01C0002) +#define STATUS_FLT_INVALID_ASYNCHRONOUS_REQUEST cpu_to_le32(0xC01C0003) +#define STATUS_FLT_DISALLOW_FAST_IO cpu_to_le32(0xC01C0004) +#define STATUS_FLT_INVALID_NAME_REQUEST cpu_to_le32(0xC01C0005) +#define STATUS_FLT_NOT_SAFE_TO_POST_OPERATION cpu_to_le32(0xC01C0006) +#define STATUS_FLT_NOT_INITIALIZED cpu_to_le32(0xC01C0007) +#define STATUS_FLT_FILTER_NOT_READY cpu_to_le32(0xC01C0008) +#define STATUS_FLT_POST_OPERATION_CLEANUP cpu_to_le32(0xC01C0009) +#define STATUS_FLT_INTERNAL_ERROR cpu_to_le32(0xC01C000A) +#define STATUS_FLT_DELETING_OBJECT cpu_to_le32(0xC01C000B) +#define STATUS_FLT_MUST_BE_NONPAGED_POOL cpu_to_le32(0xC01C000C) +#define STATUS_FLT_DUPLICATE_ENTRY cpu_to_le32(0xC01C000D) +#define STATUS_FLT_CBDQ_DISABLED cpu_to_le32(0xC01C000E) +#define STATUS_FLT_DO_NOT_ATTACH cpu_to_le32(0xC01C000F) +#define STATUS_FLT_DO_NOT_DETACH cpu_to_le32(0xC01C0010) +#define STATUS_FLT_INSTANCE_ALTITUDE_COLLISION cpu_to_le32(0xC01C0011) +#define STATUS_FLT_INSTANCE_NAME_COLLISION cpu_to_le32(0xC01C0012) +#define STATUS_FLT_FILTER_NOT_FOUND cpu_to_le32(0xC01C0013) +#define STATUS_FLT_VOLUME_NOT_FOUND cpu_to_le32(0xC01C0014) +#define STATUS_FLT_INSTANCE_NOT_FOUND cpu_to_le32(0xC01C0015) +#define STATUS_FLT_CONTEXT_ALLOCATION_NOT_FOUND cpu_to_le32(0xC01C0016) +#define STATUS_FLT_INVALID_CONTEXT_REGISTRATION cpu_to_le32(0xC01C0017) +#define STATUS_FLT_NAME_CACHE_MISS cpu_to_le32(0xC01C0018) +#define STATUS_FLT_NO_DEVICE_OBJECT cpu_to_le32(0xC01C0019) +#define STATUS_FLT_VOLUME_ALREADY_MOUNTED cpu_to_le32(0xC01C001A) +#define STATUS_FLT_ALREADY_ENLISTED cpu_to_le32(0xC01C001B) +#define STATUS_FLT_CONTEXT_ALREADY_LINKED cpu_to_le32(0xC01C001C) +#define STATUS_FLT_NO_WAITER_FOR_REPLY cpu_to_le32(0xC01C0020) +#define STATUS_MONITOR_NO_DESCRIPTOR cpu_to_le32(0xC01D0001) +#define STATUS_MONITOR_UNKNOWN_DESCRIPTOR_FORMAT cpu_to_le32(0xC01D0002) +#define STATUS_MONITOR_INVALID_DESCRIPTOR_CHECKSUM cpu_to_le32(0xC01D0003) +#define STATUS_MONITOR_INVALID_STANDARD_TIMING_BLOCK cpu_to_le32(0xC01D0004) +#define STATUS_MONITOR_WMI_DATABLOCK_REGISTRATION_FAILED cpu_to_le32(0xC01D0005) +#define STATUS_MONITOR_INVALID_SERIAL_NUMBER_MONDSC_BLOCK cpu_to_le32(0xC01D0006) +#define STATUS_MONITOR_INVALID_USER_FRIENDLY_MONDSC_BLOCK cpu_to_le32(0xC01D0007) +#define STATUS_MONITOR_NO_MORE_DESCRIPTOR_DATA cpu_to_le32(0xC01D0008) +#define STATUS_MONITOR_INVALID_DETAILED_TIMING_BLOCK cpu_to_le32(0xC01D0009) +#define STATUS_GRAPHICS_NOT_EXCLUSIVE_MODE_OWNER cpu_to_le32(0xC01E0000) +#define STATUS_GRAPHICS_INSUFFICIENT_DMA_BUFFER cpu_to_le32(0xC01E0001) +#define STATUS_GRAPHICS_INVALID_DISPLAY_ADAPTER cpu_to_le32(0xC01E0002) +#define STATUS_GRAPHICS_ADAPTER_WAS_RESET cpu_to_le32(0xC01E0003) +#define STATUS_GRAPHICS_INVALID_DRIVER_MODEL cpu_to_le32(0xC01E0004) +#define STATUS_GRAPHICS_PRESENT_MODE_CHANGED cpu_to_le32(0xC01E0005) +#define STATUS_GRAPHICS_PRESENT_OCCLUDED cpu_to_le32(0xC01E0006) +#define STATUS_GRAPHICS_PRESENT_DENIED cpu_to_le32(0xC01E0007) +#define STATUS_GRAPHICS_CANNOTCOLORCONVERT cpu_to_le32(0xC01E0008) +#define STATUS_GRAPHICS_NO_VIDEO_MEMORY cpu_to_le32(0xC01E0100) +#define STATUS_GRAPHICS_CANT_LOCK_MEMORY cpu_to_le32(0xC01E0101) +#define STATUS_GRAPHICS_ALLOCATION_BUSY cpu_to_le32(0xC01E0102) +#define STATUS_GRAPHICS_TOO_MANY_REFERENCES cpu_to_le32(0xC01E0103) +#define STATUS_GRAPHICS_TRY_AGAIN_LATER cpu_to_le32(0xC01E0104) +#define STATUS_GRAPHICS_TRY_AGAIN_NOW cpu_to_le32(0xC01E0105) +#define STATUS_GRAPHICS_ALLOCATION_INVALID cpu_to_le32(0xC01E0106) +#define STATUS_GRAPHICS_UNSWIZZLING_APERTURE_UNAVAILABLE cpu_to_le32(0xC01E0107) +#define STATUS_GRAPHICS_UNSWIZZLING_APERTURE_UNSUPPORTED cpu_to_le32(0xC01E0108) +#define STATUS_GRAPHICS_CANT_EVICT_PINNED_ALLOCATION cpu_to_le32(0xC01E0109) +#define STATUS_GRAPHICS_INVALID_ALLOCATION_USAGE cpu_to_le32(0xC01E0110) +#define STATUS_GRAPHICS_CANT_RENDER_LOCKED_ALLOCATION cpu_to_le32(0xC01E0111) +#define STATUS_GRAPHICS_ALLOCATION_CLOSED cpu_to_le32(0xC01E0112) +#define STATUS_GRAPHICS_INVALID_ALLOCATION_INSTANCE cpu_to_le32(0xC01E0113) +#define STATUS_GRAPHICS_INVALID_ALLOCATION_HANDLE cpu_to_le32(0xC01E0114) +#define STATUS_GRAPHICS_WRONG_ALLOCATION_DEVICE cpu_to_le32(0xC01E0115) +#define STATUS_GRAPHICS_ALLOCATION_CONTENT_LOST cpu_to_le32(0xC01E0116) +#define STATUS_GRAPHICS_GPU_EXCEPTION_ON_DEVICE cpu_to_le32(0xC01E0200) +#define STATUS_GRAPHICS_INVALID_VIDPN_TOPOLOGY cpu_to_le32(0xC01E0300) +#define STATUS_GRAPHICS_VIDPN_TOPOLOGY_NOT_SUPPORTED cpu_to_le32(0xC01E0301) +#define STATUS_GRAPHICS_VIDPN_TOPOLOGY_CURRENTLY_NOT_SUPPORTED cpu_to_le32(0xC01E0302) +#define STATUS_GRAPHICS_INVALID_VIDPN cpu_to_le32(0xC01E0303) +#define STATUS_GRAPHICS_INVALID_VIDEO_PRESENT_SOURCE cpu_to_le32(0xC01E0304) +#define STATUS_GRAPHICS_INVALID_VIDEO_PRESENT_TARGET cpu_to_le32(0xC01E0305) +#define STATUS_GRAPHICS_VIDPN_MODALITY_NOT_SUPPORTED cpu_to_le32(0xC01E0306) +#define STATUS_GRAPHICS_INVALID_VIDPN_SOURCEMODESET cpu_to_le32(0xC01E0308) +#define STATUS_GRAPHICS_INVALID_VIDPN_TARGETMODESET cpu_to_le32(0xC01E0309) +#define STATUS_GRAPHICS_INVALID_FREQUENCY cpu_to_le32(0xC01E030A) +#define STATUS_GRAPHICS_INVALID_ACTIVE_REGION cpu_to_le32(0xC01E030B) +#define STATUS_GRAPHICS_INVALID_TOTAL_REGION cpu_to_le32(0xC01E030C) +#define STATUS_GRAPHICS_INVALID_VIDEO_PRESENT_SOURCE_MODE cpu_to_le32(0xC01E0310) +#define STATUS_GRAPHICS_INVALID_VIDEO_PRESENT_TARGET_MODE cpu_to_le32(0xC01E0311) +#define STATUS_GRAPHICS_PINNED_MODE_MUST_REMAIN_IN_SET cpu_to_le32(0xC01E0312) +#define STATUS_GRAPHICS_PATH_ALREADY_IN_TOPOLOGY cpu_to_le32(0xC01E0313) +#define STATUS_GRAPHICS_MODE_ALREADY_IN_MODESET cpu_to_le32(0xC01E0314) +#define STATUS_GRAPHICS_INVALID_VIDEOPRESENTSOURCESET cpu_to_le32(0xC01E0315) +#define STATUS_GRAPHICS_INVALID_VIDEOPRESENTTARGETSET cpu_to_le32(0xC01E0316) +#define STATUS_GRAPHICS_SOURCE_ALREADY_IN_SET cpu_to_le32(0xC01E0317) +#define STATUS_GRAPHICS_TARGET_ALREADY_IN_SET cpu_to_le32(0xC01E0318) +#define STATUS_GRAPHICS_INVALID_VIDPN_PRESENT_PATH cpu_to_le32(0xC01E0319) +#define STATUS_GRAPHICS_NO_RECOMMENDED_VIDPN_TOPOLOGY cpu_to_le32(0xC01E031A) +#define STATUS_GRAPHICS_INVALID_MONITOR_FREQUENCYRANGESET cpu_to_le32(0xC01E031B) +#define STATUS_GRAPHICS_INVALID_MONITOR_FREQUENCYRANGE cpu_to_le32(0xC01E031C) +#define STATUS_GRAPHICS_FREQUENCYRANGE_NOT_IN_SET cpu_to_le32(0xC01E031D) +#define STATUS_GRAPHICS_FREQUENCYRANGE_ALREADY_IN_SET cpu_to_le32(0xC01E031F) +#define STATUS_GRAPHICS_STALE_MODESET cpu_to_le32(0xC01E0320) +#define STATUS_GRAPHICS_INVALID_MONITOR_SOURCEMODESET cpu_to_le32(0xC01E0321) +#define STATUS_GRAPHICS_INVALID_MONITOR_SOURCE_MODE cpu_to_le32(0xC01E0322) +#define STATUS_GRAPHICS_NO_RECOMMENDED_FUNCTIONAL_VIDPN cpu_to_le32(0xC01E0323) +#define STATUS_GRAPHICS_MODE_ID_MUST_BE_UNIQUE cpu_to_le32(0xC01E0324) +#define STATUS_GRAPHICS_EMPTY_ADAPTER_MONITOR_MODE_SUPPORT_INTERSECTION cpu_to_le32(0xC01E0325) +#define STATUS_GRAPHICS_VIDEO_PRESENT_TARGETS_LESS_THAN_SOURCES cpu_to_le32(0xC01E0326) +#define STATUS_GRAPHICS_PATH_NOT_IN_TOPOLOGY cpu_to_le32(0xC01E0327) +#define STATUS_GRAPHICS_ADAPTER_MUST_HAVE_AT_LEAST_ONE_SOURCE cpu_to_le32(0xC01E0328) +#define STATUS_GRAPHICS_ADAPTER_MUST_HAVE_AT_LEAST_ONE_TARGET cpu_to_le32(0xC01E0329) +#define STATUS_GRAPHICS_INVALID_MONITORDESCRIPTORSET cpu_to_le32(0xC01E032A) +#define STATUS_GRAPHICS_INVALID_MONITORDESCRIPTOR cpu_to_le32(0xC01E032B) +#define STATUS_GRAPHICS_MONITORDESCRIPTOR_NOT_IN_SET cpu_to_le32(0xC01E032C) +#define STATUS_GRAPHICS_MONITORDESCRIPTOR_ALREADY_IN_SET cpu_to_le32(0xC01E032D) +#define STATUS_GRAPHICS_MONITORDESCRIPTOR_ID_MUST_BE_UNIQUE cpu_to_le32(0xC01E032E) +#define STATUS_GRAPHICS_INVALID_VIDPN_TARGET_SUBSET_TYPE cpu_to_le32(0xC01E032F) +#define STATUS_GRAPHICS_RESOURCES_NOT_RELATED cpu_to_le32(0xC01E0330) +#define STATUS_GRAPHICS_SOURCE_ID_MUST_BE_UNIQUE cpu_to_le32(0xC01E0331) +#define STATUS_GRAPHICS_TARGET_ID_MUST_BE_UNIQUE cpu_to_le32(0xC01E0332) +#define STATUS_GRAPHICS_NO_AVAILABLE_VIDPN_TARGET cpu_to_le32(0xC01E0333) +#define STATUS_GRAPHICS_MONITOR_COULD_NOT_BE_ASSOCIATED_WITH_ADAPTER cpu_to_le32(0xC01E0334) +#define STATUS_GRAPHICS_NO_VIDPNMGR cpu_to_le32(0xC01E0335) +#define STATUS_GRAPHICS_NO_ACTIVE_VIDPN cpu_to_le32(0xC01E0336) +#define STATUS_GRAPHICS_STALE_VIDPN_TOPOLOGY cpu_to_le32(0xC01E0337) +#define STATUS_GRAPHICS_MONITOR_NOT_CONNECTED cpu_to_le32(0xC01E0338) +#define STATUS_GRAPHICS_SOURCE_NOT_IN_TOPOLOGY cpu_to_le32(0xC01E0339) +#define STATUS_GRAPHICS_INVALID_PRIMARYSURFACE_SIZE cpu_to_le32(0xC01E033A) +#define STATUS_GRAPHICS_INVALID_VISIBLEREGION_SIZE cpu_to_le32(0xC01E033B) +#define STATUS_GRAPHICS_INVALID_STRIDE cpu_to_le32(0xC01E033C) +#define STATUS_GRAPHICS_INVALID_PIXELFORMAT cpu_to_le32(0xC01E033D) +#define STATUS_GRAPHICS_INVALID_COLORBASIS cpu_to_le32(0xC01E033E) +#define STATUS_GRAPHICS_INVALID_PIXELVALUEACCESSMODE cpu_to_le32(0xC01E033F) +#define STATUS_GRAPHICS_TARGET_NOT_IN_TOPOLOGY cpu_to_le32(0xC01E0340) +#define STATUS_GRAPHICS_NO_DISPLAY_MODE_MANAGEMENT_SUPPORT cpu_to_le32(0xC01E0341) +#define STATUS_GRAPHICS_VIDPN_SOURCE_IN_USE cpu_to_le32(0xC01E0342) +#define STATUS_GRAPHICS_CANT_ACCESS_ACTIVE_VIDPN cpu_to_le32(0xC01E0343) +#define STATUS_GRAPHICS_INVALID_PATH_IMPORTANCE_ORDINAL cpu_to_le32(0xC01E0344) +#define STATUS_GRAPHICS_INVALID_PATH_CONTENT_GEOMETRY_TRANSFORMATION cpu_to_le32(0xC01E0345) +#define STATUS_GRAPHICS_PATH_CONTENT_GEOMETRY_TRANSFORMATION_NOT_SUPPORTED cpu_to_le32(0xC01E0346) +#define STATUS_GRAPHICS_INVALID_GAMMA_RAMP cpu_to_le32(0xC01E0347) +#define STATUS_GRAPHICS_GAMMA_RAMP_NOT_SUPPORTED cpu_to_le32(0xC01E0348) +#define STATUS_GRAPHICS_MULTISAMPLING_NOT_SUPPORTED cpu_to_le32(0xC01E0349) +#define STATUS_GRAPHICS_MODE_NOT_IN_MODESET cpu_to_le32(0xC01E034A) +#define STATUS_GRAPHICS_INVALID_VIDPN_TOPOLOGY_RECOMMENDATION_REASON cpu_to_le32(0xC01E034D) +#define STATUS_GRAPHICS_INVALID_PATH_CONTENT_TYPE cpu_to_le32(0xC01E034E) +#define STATUS_GRAPHICS_INVALID_COPYPROTECTION_TYPE cpu_to_le32(0xC01E034F) +#define STATUS_GRAPHICS_UNASSIGNED_MODESET_ALREADY_EXISTS cpu_to_le32(0xC01E0350) +#define STATUS_GRAPHICS_INVALID_SCANLINE_ORDERING cpu_to_le32(0xC01E0352) +#define STATUS_GRAPHICS_TOPOLOGY_CHANGES_NOT_ALLOWED cpu_to_le32(0xC01E0353) +#define STATUS_GRAPHICS_NO_AVAILABLE_IMPORTANCE_ORDINALS cpu_to_le32(0xC01E0354) +#define STATUS_GRAPHICS_INCOMPATIBLE_PRIVATE_FORMAT cpu_to_le32(0xC01E0355) +#define STATUS_GRAPHICS_INVALID_MODE_PRUNING_ALGORITHM cpu_to_le32(0xC01E0356) +#define STATUS_GRAPHICS_INVALID_MONITOR_CAPABILITY_ORIGIN cpu_to_le32(0xC01E0357) +#define STATUS_GRAPHICS_INVALID_MONITOR_FREQUENCYRANGE_CONSTRAINT cpu_to_le32(0xC01E0358) +#define STATUS_GRAPHICS_MAX_NUM_PATHS_REACHED cpu_to_le32(0xC01E0359) +#define STATUS_GRAPHICS_CANCEL_VIDPN_TOPOLOGY_AUGMENTATION cpu_to_le32(0xC01E035A) +#define STATUS_GRAPHICS_INVALID_CLIENT_TYPE cpu_to_le32(0xC01E035B) +#define STATUS_GRAPHICS_CLIENTVIDPN_NOT_SET cpu_to_le32(0xC01E035C) +#define STATUS_GRAPHICS_SPECIFIED_CHILD_ALREADY_CONNECTED cpu_to_le32(0xC01E0400) +#define STATUS_GRAPHICS_CHILD_DESCRIPTOR_NOT_SUPPORTED cpu_to_le32(0xC01E0401) +#define STATUS_GRAPHICS_NOT_A_LINKED_ADAPTER cpu_to_le32(0xC01E0430) +#define STATUS_GRAPHICS_LEADLINK_NOT_ENUMERATED cpu_to_le32(0xC01E0431) +#define STATUS_GRAPHICS_CHAINLINKS_NOT_ENUMERATED cpu_to_le32(0xC01E0432) +#define STATUS_GRAPHICS_ADAPTER_CHAIN_NOT_READY cpu_to_le32(0xC01E0433) +#define STATUS_GRAPHICS_CHAINLINKS_NOT_STARTED cpu_to_le32(0xC01E0434) +#define STATUS_GRAPHICS_CHAINLINKS_NOT_POWERED_ON cpu_to_le32(0xC01E0435) +#define STATUS_GRAPHICS_INCONSISTENT_DEVICE_LINK_STATE cpu_to_le32(0xC01E0436) +#define STATUS_GRAPHICS_NOT_POST_DEVICE_DRIVER cpu_to_le32(0xC01E0438) +#define STATUS_GRAPHICS_ADAPTER_ACCESS_NOT_EXCLUDED cpu_to_le32(0xC01E043B) +#define STATUS_GRAPHICS_OPM_PROTECTED_OUTPUT_DOES_NOT_HAVE_COPP_SEMANTICS cpu_to_le32(0xC01E051C) +#define STATUS_GRAPHICS_OPM_INVALID_INFORMATION_REQUEST cpu_to_le32(0xC01E051D) +#define STATUS_GRAPHICS_OPM_DRIVER_INTERNAL_ERROR cpu_to_le32(0xC01E051E) +#define STATUS_GRAPHICS_OPM_PROTECTED_OUTPUT_DOES_NOT_HAVE_OPM_SEMANTICS cpu_to_le32(0xC01E051F) +#define STATUS_GRAPHICS_OPM_SIGNALING_NOT_SUPPORTED cpu_to_le32(0xC01E0520) +#define STATUS_GRAPHICS_OPM_INVALID_CONFIGURATION_REQUEST cpu_to_le32(0xC01E0521) +#define STATUS_GRAPHICS_OPM_NOT_SUPPORTED cpu_to_le32(0xC01E0500) +#define STATUS_GRAPHICS_COPP_NOT_SUPPORTED cpu_to_le32(0xC01E0501) +#define STATUS_GRAPHICS_UAB_NOT_SUPPORTED cpu_to_le32(0xC01E0502) +#define STATUS_GRAPHICS_OPM_INVALID_ENCRYPTED_PARAMETERS cpu_to_le32(0xC01E0503) +#define STATUS_GRAPHICS_OPM_PARAMETER_ARRAY_TOO_SMALL cpu_to_le32(0xC01E0504) +#define STATUS_GRAPHICS_OPM_NO_PROTECTED_OUTPUTS_EXIST cpu_to_le32(0xC01E0505) +#define STATUS_GRAPHICS_PVP_NO_DISPLAY_DEVICE_CORRESPONDS_TO_NAME cpu_to_le32(0xC01E0506) +#define STATUS_GRAPHICS_PVP_DISPLAY_DEVICE_NOT_ATTACHED_TO_DESKTOP cpu_to_le32(0xC01E0507) +#define STATUS_GRAPHICS_PVP_MIRRORING_DEVICES_NOT_SUPPORTED cpu_to_le32(0xC01E0508) +#define STATUS_GRAPHICS_OPM_INVALID_POINTER cpu_to_le32(0xC01E050A) +#define STATUS_GRAPHICS_OPM_INTERNAL_ERROR cpu_to_le32(0xC01E050B) +#define STATUS_GRAPHICS_OPM_INVALID_HANDLE cpu_to_le32(0xC01E050C) +#define STATUS_GRAPHICS_PVP_NO_MONITORS_CORRESPOND_TO_DISPLAY_DEVICE cpu_to_le32(0xC01E050D) +#define STATUS_GRAPHICS_PVP_INVALID_CERTIFICATE_LENGTH cpu_to_le32(0xC01E050E) +#define STATUS_GRAPHICS_OPM_SPANNING_MODE_ENABLED cpu_to_le32(0xC01E050F) +#define STATUS_GRAPHICS_OPM_THEATER_MODE_ENABLED cpu_to_le32(0xC01E0510) +#define STATUS_GRAPHICS_PVP_HFS_FAILED cpu_to_le32(0xC01E0511) +#define STATUS_GRAPHICS_OPM_INVALID_SRM cpu_to_le32(0xC01E0512) +#define STATUS_GRAPHICS_OPM_OUTPUT_DOES_NOT_SUPPORT_HDCP cpu_to_le32(0xC01E0513) +#define STATUS_GRAPHICS_OPM_OUTPUT_DOES_NOT_SUPPORT_ACP cpu_to_le32(0xC01E0514) +#define STATUS_GRAPHICS_OPM_OUTPUT_DOES_NOT_SUPPORT_CGMSA cpu_to_le32(0xC01E0515) +#define STATUS_GRAPHICS_OPM_HDCP_SRM_NEVER_SET cpu_to_le32(0xC01E0516) +#define STATUS_GRAPHICS_OPM_RESOLUTION_TOO_HIGH cpu_to_le32(0xC01E0517) +#define STATUS_GRAPHICS_OPM_ALL_HDCP_HARDWARE_ALREADY_IN_USE cpu_to_le32(0xC01E0518) +#define STATUS_GRAPHICS_OPM_PROTECTED_OUTPUT_NO_LONGER_EXISTS cpu_to_le32(0xC01E051A) +#define STATUS_GRAPHICS_OPM_SESSION_TYPE_CHANGE_IN_PROGRESS cpu_to_le32(0xC01E051B) +#define STATUS_GRAPHICS_I2C_NOT_SUPPORTED cpu_to_le32(0xC01E0580) +#define STATUS_GRAPHICS_I2C_DEVICE_DOES_NOT_EXIST cpu_to_le32(0xC01E0581) +#define STATUS_GRAPHICS_I2C_ERROR_TRANSMITTING_DATA cpu_to_le32(0xC01E0582) +#define STATUS_GRAPHICS_I2C_ERROR_RECEIVING_DATA cpu_to_le32(0xC01E0583) +#define STATUS_GRAPHICS_DDCCI_VCP_NOT_SUPPORTED cpu_to_le32(0xC01E0584) +#define STATUS_GRAPHICS_DDCCI_INVALID_DATA cpu_to_le32(0xC01E0585) +#define STATUS_GRAPHICS_DDCCI_MONITOR_RETURNED_INVALID_TIMING_STATUS_BYTE cpu_to_le32(0xC01E0586) +#define STATUS_GRAPHICS_DDCCI_INVALID_CAPABILITIES_STRING cpu_to_le32(0xC01E0587) +#define STATUS_GRAPHICS_MCA_INTERNAL_ERROR cpu_to_le32(0xC01E0588) +#define STATUS_GRAPHICS_DDCCI_INVALID_MESSAGE_COMMAND cpu_to_le32(0xC01E0589) +#define STATUS_GRAPHICS_DDCCI_INVALID_MESSAGE_LENGTH cpu_to_le32(0xC01E058A) +#define STATUS_GRAPHICS_DDCCI_INVALID_MESSAGE_CHECKSUM cpu_to_le32(0xC01E058B) +#define STATUS_GRAPHICS_INVALID_PHYSICAL_MONITOR_HANDLE cpu_to_le32(0xC01E058C) +#define STATUS_GRAPHICS_MONITOR_NO_LONGER_EXISTS cpu_to_le32(0xC01E058D) +#define STATUS_GRAPHICS_ONLY_CONSOLE_SESSION_SUPPORTED cpu_to_le32(0xC01E05E0) +#define STATUS_GRAPHICS_NO_DISPLAY_DEVICE_CORRESPONDS_TO_NAME cpu_to_le32(0xC01E05E1) +#define STATUS_GRAPHICS_DISPLAY_DEVICE_NOT_ATTACHED_TO_DESKTOP cpu_to_le32(0xC01E05E2) +#define STATUS_GRAPHICS_MIRRORING_DEVICES_NOT_SUPPORTED cpu_to_le32(0xC01E05E3) +#define STATUS_GRAPHICS_INVALID_POINTER cpu_to_le32(0xC01E05E4) +#define STATUS_GRAPHICS_NO_MONITORS_CORRESPOND_TO_DISPLAY_DEVICE cpu_to_le32(0xC01E05E5) +#define STATUS_GRAPHICS_PARAMETER_ARRAY_TOO_SMALL cpu_to_le32(0xC01E05E6) +#define STATUS_GRAPHICS_INTERNAL_ERROR cpu_to_le32(0xC01E05E7) +#define STATUS_GRAPHICS_SESSION_TYPE_CHANGE_IN_PROGRESS cpu_to_le32(0xC01E05E8) +#define STATUS_FVE_LOCKED_VOLUME cpu_to_le32(0xC0210000) +#define STATUS_FVE_NOT_ENCRYPTED cpu_to_le32(0xC0210001) +#define STATUS_FVE_BAD_INFORMATION cpu_to_le32(0xC0210002) +#define STATUS_FVE_TOO_SMALL cpu_to_le32(0xC0210003) +#define STATUS_FVE_FAILED_WRONG_FS cpu_to_le32(0xC0210004) +#define STATUS_FVE_FAILED_BAD_FS cpu_to_le32(0xC0210005) +#define STATUS_FVE_FS_NOT_EXTENDED cpu_to_le32(0xC0210006) +#define STATUS_FVE_FS_MOUNTED cpu_to_le32(0xC0210007) +#define STATUS_FVE_NO_LICENSE cpu_to_le32(0xC0210008) +#define STATUS_FVE_ACTION_NOT_ALLOWED cpu_to_le32(0xC0210009) +#define STATUS_FVE_BAD_DATA cpu_to_le32(0xC021000A) +#define STATUS_FVE_VOLUME_NOT_BOUND cpu_to_le32(0xC021000B) +#define STATUS_FVE_NOT_DATA_VOLUME cpu_to_le32(0xC021000C) +#define STATUS_FVE_CONV_READ_ERROR cpu_to_le32(0xC021000D) +#define STATUS_FVE_CONV_WRITE_ERROR cpu_to_le32(0xC021000E) +#define STATUS_FVE_OVERLAPPED_UPDATE cpu_to_le32(0xC021000F) +#define STATUS_FVE_FAILED_SECTOR_SIZE cpu_to_le32(0xC0210010) +#define STATUS_FVE_FAILED_AUTHENTICATION cpu_to_le32(0xC0210011) +#define STATUS_FVE_NOT_OS_VOLUME cpu_to_le32(0xC0210012) +#define STATUS_FVE_KEYFILE_NOT_FOUND cpu_to_le32(0xC0210013) +#define STATUS_FVE_KEYFILE_INVALID cpu_to_le32(0xC0210014) +#define STATUS_FVE_KEYFILE_NO_VMK cpu_to_le32(0xC0210015) +#define STATUS_FVE_TPM_DISABLED cpu_to_le32(0xC0210016) +#define STATUS_FVE_TPM_SRK_AUTH_NOT_ZERO cpu_to_le32(0xC0210017) +#define STATUS_FVE_TPM_INVALID_PCR cpu_to_le32(0xC0210018) +#define STATUS_FVE_TPM_NO_VMK cpu_to_le32(0xC0210019) +#define STATUS_FVE_PIN_INVALID cpu_to_le32(0xC021001A) +#define STATUS_FVE_AUTH_INVALID_APPLICATION cpu_to_le32(0xC021001B) +#define STATUS_FVE_AUTH_INVALID_CONFIG cpu_to_le32(0xC021001C) +#define STATUS_FVE_DEBUGGER_ENABLED cpu_to_le32(0xC021001D) +#define STATUS_FVE_DRY_RUN_FAILED cpu_to_le32(0xC021001E) +#define STATUS_FVE_BAD_METADATA_POINTER cpu_to_le32(0xC021001F) +#define STATUS_FVE_OLD_METADATA_COPY cpu_to_le32(0xC0210020) +#define STATUS_FVE_REBOOT_REQUIRED cpu_to_le32(0xC0210021) +#define STATUS_FVE_RAW_ACCESS cpu_to_le32(0xC0210022) +#define STATUS_FVE_RAW_BLOCKED cpu_to_le32(0xC0210023) +#define STATUS_FWP_CALLOUT_NOT_FOUND cpu_to_le32(0xC0220001) +#define STATUS_FWP_CONDITION_NOT_FOUND cpu_to_le32(0xC0220002) +#define STATUS_FWP_FILTER_NOT_FOUND cpu_to_le32(0xC0220003) +#define STATUS_FWP_LAYER_NOT_FOUND cpu_to_le32(0xC0220004) +#define STATUS_FWP_PROVIDER_NOT_FOUND cpu_to_le32(0xC0220005) +#define STATUS_FWP_PROVIDER_CONTEXT_NOT_FOUND cpu_to_le32(0xC0220006) +#define STATUS_FWP_SUBLAYER_NOT_FOUND cpu_to_le32(0xC0220007) +#define STATUS_FWP_NOT_FOUND cpu_to_le32(0xC0220008) +#define STATUS_FWP_ALREADY_EXISTS cpu_to_le32(0xC0220009) +#define STATUS_FWP_IN_USE cpu_to_le32(0xC022000A) +#define STATUS_FWP_DYNAMIC_SESSION_IN_PROGRESS cpu_to_le32(0xC022000B) +#define STATUS_FWP_WRONG_SESSION cpu_to_le32(0xC022000C) +#define STATUS_FWP_NO_TXN_IN_PROGRESS cpu_to_le32(0xC022000D) +#define STATUS_FWP_TXN_IN_PROGRESS cpu_to_le32(0xC022000E) +#define STATUS_FWP_TXN_ABORTED cpu_to_le32(0xC022000F) +#define STATUS_FWP_SESSION_ABORTED cpu_to_le32(0xC0220010) +#define STATUS_FWP_INCOMPATIBLE_TXN cpu_to_le32(0xC0220011) +#define STATUS_FWP_TIMEOUT cpu_to_le32(0xC0220012) +#define STATUS_FWP_NET_EVENTS_DISABLED cpu_to_le32(0xC0220013) +#define STATUS_FWP_INCOMPATIBLE_LAYER cpu_to_le32(0xC0220014) +#define STATUS_FWP_KM_CLIENTS_ONLY cpu_to_le32(0xC0220015) +#define STATUS_FWP_LIFETIME_MISMATCH cpu_to_le32(0xC0220016) +#define STATUS_FWP_BUILTIN_OBJECT cpu_to_le32(0xC0220017) +#define STATUS_FWP_TOO_MANY_BOOTTIME_FILTERS cpu_to_le32(0xC0220018) +#define STATUS_FWP_TOO_MANY_CALLOUTS cpu_to_le32(0xC0220018) +#define STATUS_FWP_NOTIFICATION_DROPPED cpu_to_le32(0xC0220019) +#define STATUS_FWP_TRAFFIC_MISMATCH cpu_to_le32(0xC022001A) +#define STATUS_FWP_INCOMPATIBLE_SA_STATE cpu_to_le32(0xC022001B) +#define STATUS_FWP_NULL_POINTER cpu_to_le32(0xC022001C) +#define STATUS_FWP_INVALID_ENUMERATOR cpu_to_le32(0xC022001D) +#define STATUS_FWP_INVALID_FLAGS cpu_to_le32(0xC022001E) +#define STATUS_FWP_INVALID_NET_MASK cpu_to_le32(0xC022001F) +#define STATUS_FWP_INVALID_RANGE cpu_to_le32(0xC0220020) +#define STATUS_FWP_INVALID_INTERVAL cpu_to_le32(0xC0220021) +#define STATUS_FWP_ZERO_LENGTH_ARRAY cpu_to_le32(0xC0220022) +#define STATUS_FWP_NULL_DISPLAY_NAME cpu_to_le32(0xC0220023) +#define STATUS_FWP_INVALID_ACTION_TYPE cpu_to_le32(0xC0220024) +#define STATUS_FWP_INVALID_WEIGHT cpu_to_le32(0xC0220025) +#define STATUS_FWP_MATCH_TYPE_MISMATCH cpu_to_le32(0xC0220026) +#define STATUS_FWP_TYPE_MISMATCH cpu_to_le32(0xC0220027) +#define STATUS_FWP_OUT_OF_BOUNDS cpu_to_le32(0xC0220028) +#define STATUS_FWP_RESERVED cpu_to_le32(0xC0220029) +#define STATUS_FWP_DUPLICATE_CONDITION cpu_to_le32(0xC022002A) +#define STATUS_FWP_DUPLICATE_KEYMOD cpu_to_le32(0xC022002B) +#define STATUS_FWP_ACTION_INCOMPATIBLE_WITH_LAYER cpu_to_le32(0xC022002C) +#define STATUS_FWP_ACTION_INCOMPATIBLE_WITH_SUBLAYER cpu_to_le32(0xC022002D) +#define STATUS_FWP_CONTEXT_INCOMPATIBLE_WITH_LAYER cpu_to_le32(0xC022002E) +#define STATUS_FWP_CONTEXT_INCOMPATIBLE_WITH_CALLOUT cpu_to_le32(0xC022002F) +#define STATUS_FWP_INCOMPATIBLE_AUTH_METHOD cpu_to_le32(0xC0220030) +#define STATUS_FWP_INCOMPATIBLE_DH_GROUP cpu_to_le32(0xC0220031) +#define STATUS_FWP_EM_NOT_SUPPORTED cpu_to_le32(0xC0220032) +#define STATUS_FWP_NEVER_MATCH cpu_to_le32(0xC0220033) +#define STATUS_FWP_PROVIDER_CONTEXT_MISMATCH cpu_to_le32(0xC0220034) +#define STATUS_FWP_INVALID_PARAMETER cpu_to_le32(0xC0220035) +#define STATUS_FWP_TOO_MANY_SUBLAYERS cpu_to_le32(0xC0220036) +#define STATUS_FWP_CALLOUT_NOTIFICATION_FAILED cpu_to_le32(0xC0220037) +#define STATUS_FWP_INCOMPATIBLE_AUTH_CONFIG cpu_to_le32(0xC0220038) +#define STATUS_FWP_INCOMPATIBLE_CIPHER_CONFIG cpu_to_le32(0xC0220039) +#define STATUS_FWP_TCPIP_NOT_READY cpu_to_le32(0xC0220100) +#define STATUS_FWP_INJECT_HANDLE_CLOSING cpu_to_le32(0xC0220101) +#define STATUS_FWP_INJECT_HANDLE_STALE cpu_to_le32(0xC0220102) +#define STATUS_FWP_CANNOT_PEND cpu_to_le32(0xC0220103) +#define STATUS_NDIS_CLOSING cpu_to_le32(0xC0230002) +#define STATUS_NDIS_BAD_VERSION cpu_to_le32(0xC0230004) +#define STATUS_NDIS_BAD_CHARACTERISTICS cpu_to_le32(0xC0230005) +#define STATUS_NDIS_ADAPTER_NOT_FOUND cpu_to_le32(0xC0230006) +#define STATUS_NDIS_OPEN_FAILED cpu_to_le32(0xC0230007) +#define STATUS_NDIS_DEVICE_FAILED cpu_to_le32(0xC0230008) +#define STATUS_NDIS_MULTICAST_FULL cpu_to_le32(0xC0230009) +#define STATUS_NDIS_MULTICAST_EXISTS cpu_to_le32(0xC023000A) +#define STATUS_NDIS_MULTICAST_NOT_FOUND cpu_to_le32(0xC023000B) +#define STATUS_NDIS_REQUEST_ABORTED cpu_to_le32(0xC023000C) +#define STATUS_NDIS_RESET_IN_PROGRESS cpu_to_le32(0xC023000D) +#define STATUS_NDIS_INVALID_PACKET cpu_to_le32(0xC023000F) +#define STATUS_NDIS_INVALID_DEVICE_REQUEST cpu_to_le32(0xC0230010) +#define STATUS_NDIS_ADAPTER_NOT_READY cpu_to_le32(0xC0230011) +#define STATUS_NDIS_INVALID_LENGTH cpu_to_le32(0xC0230014) +#define STATUS_NDIS_INVALID_DATA cpu_to_le32(0xC0230015) +#define STATUS_NDIS_BUFFER_TOO_SHORT cpu_to_le32(0xC0230016) +#define STATUS_NDIS_INVALID_OID cpu_to_le32(0xC0230017) +#define STATUS_NDIS_ADAPTER_REMOVED cpu_to_le32(0xC0230018) +#define STATUS_NDIS_UNSUPPORTED_MEDIA cpu_to_le32(0xC0230019) +#define STATUS_NDIS_GROUP_ADDRESS_IN_USE cpu_to_le32(0xC023001A) +#define STATUS_NDIS_FILE_NOT_FOUND cpu_to_le32(0xC023001B) +#define STATUS_NDIS_ERROR_READING_FILE cpu_to_le32(0xC023001C) +#define STATUS_NDIS_ALREADY_MAPPED cpu_to_le32(0xC023001D) +#define STATUS_NDIS_RESOURCE_CONFLICT cpu_to_le32(0xC023001E) +#define STATUS_NDIS_MEDIA_DISCONNECTED cpu_to_le32(0xC023001F) +#define STATUS_NDIS_INVALID_ADDRESS cpu_to_le32(0xC0230022) +#define STATUS_NDIS_PAUSED cpu_to_le32(0xC023002A) +#define STATUS_NDIS_INTERFACE_NOT_FOUND cpu_to_le32(0xC023002B) +#define STATUS_NDIS_UNSUPPORTED_REVISION cpu_to_le32(0xC023002C) +#define STATUS_NDIS_INVALID_PORT cpu_to_le32(0xC023002D) +#define STATUS_NDIS_INVALID_PORT_STATE cpu_to_le32(0xC023002E) +#define STATUS_NDIS_LOW_POWER_STATE cpu_to_le32(0xC023002F) +#define STATUS_NDIS_NOT_SUPPORTED cpu_to_le32(0xC02300BB) +#define STATUS_NDIS_DOT11_AUTO_CONFIG_ENABLED cpu_to_le32(0xC0232000) +#define STATUS_NDIS_DOT11_MEDIA_IN_USE cpu_to_le32(0xC0232001) +#define STATUS_NDIS_DOT11_POWER_STATE_INVALID cpu_to_le32(0xC0232002) +#define STATUS_IPSEC_BAD_SPI cpu_to_le32(0xC0360001) +#define STATUS_IPSEC_SA_LIFETIME_EXPIRED cpu_to_le32(0xC0360002) +#define STATUS_IPSEC_WRONG_SA cpu_to_le32(0xC0360003) +#define STATUS_IPSEC_REPLAY_CHECK_FAILED cpu_to_le32(0xC0360004) +#define STATUS_IPSEC_INVALID_PACKET cpu_to_le32(0xC0360005) +#define STATUS_IPSEC_INTEGRITY_CHECK_FAILED cpu_to_le32(0xC0360006) +#define STATUS_IPSEC_CLEAR_TEXT_DROP cpu_to_le32(0xC0360007) diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index b943b74cd246..caac37b1de8c 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -164,95 +164,6 @@ do { \ #define log_rdma_mr(level, fmt, args...) \ log_rdma(level, LOG_RDMA_MR, fmt, ##args) -/* - * Destroy the transport and related RDMA and memory resources - * Need to go through all the pending counters and make sure on one is using - * the transport while it is destroyed - */ -static void smbd_destroy_rdma_work(struct work_struct *work) -{ - struct smbd_response *response; - struct smbd_connection *info = - container_of(work, struct smbd_connection, destroy_work); - unsigned long flags; - - log_rdma_event(INFO, "destroying qp\n"); - ib_drain_qp(info->id->qp); - rdma_destroy_qp(info->id); - - /* Unblock all I/O waiting on the send queue */ - wake_up_interruptible_all(&info->wait_send_queue); - - log_rdma_event(INFO, "cancelling idle timer\n"); - cancel_delayed_work_sync(&info->idle_timer_work); - log_rdma_event(INFO, "cancelling send immediate work\n"); - cancel_delayed_work_sync(&info->send_immediate_work); - - log_rdma_event(INFO, "wait for all send to finish\n"); - wait_event(info->wait_smbd_send_pending, - info->smbd_send_pending == 0); - - log_rdma_event(INFO, "wait for all recv to finish\n"); - wake_up_interruptible(&info->wait_reassembly_queue); - wait_event(info->wait_smbd_recv_pending, - info->smbd_recv_pending == 0); - - log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); - wait_event(info->wait_send_pending, - atomic_read(&info->send_pending) == 0); - wait_event(info->wait_send_payload_pending, - atomic_read(&info->send_payload_pending) == 0); - - log_rdma_event(INFO, "freeing mr list\n"); - wake_up_interruptible_all(&info->wait_mr); - wait_event(info->wait_for_mr_cleanup, - atomic_read(&info->mr_used_count) == 0); - destroy_mr_list(info); - - /* It's not posssible for upper layer to get to reassembly */ - log_rdma_event(INFO, "drain the reassembly queue\n"); - do { - spin_lock_irqsave(&info->reassembly_queue_lock, flags); - response = _get_first_reassembly(info); - if (response) { - list_del(&response->list); - spin_unlock_irqrestore( - &info->reassembly_queue_lock, flags); - put_receive_buffer(info, response); - } else - spin_unlock_irqrestore(&info->reassembly_queue_lock, flags); - } while (response); - - info->reassembly_data_length = 0; - - log_rdma_event(INFO, "free receive buffers\n"); - wait_event(info->wait_receive_queues, - info->count_receive_queue + info->count_empty_packet_queue - == info->receive_credit_max); - destroy_receive_buffers(info); - - ib_free_cq(info->send_cq); - ib_free_cq(info->recv_cq); - ib_dealloc_pd(info->pd); - rdma_destroy_id(info->id); - - /* free mempools */ - mempool_destroy(info->request_mempool); - kmem_cache_destroy(info->request_cache); - - mempool_destroy(info->response_mempool); - kmem_cache_destroy(info->response_cache); - - info->transport_status = SMBD_DESTROYED; - wake_up_all(&info->wait_destroy); -} - -static int smbd_process_disconnected(struct smbd_connection *info) -{ - schedule_work(&info->destroy_work); - return 0; -} - static void smbd_disconnect_rdma_work(struct work_struct *work) { struct smbd_connection *info = @@ -319,7 +230,9 @@ static int smbd_conn_upcall( } info->transport_status = SMBD_DISCONNECTED; - smbd_process_disconnected(info); + wake_up_interruptible(&info->disconn_wait); + wake_up_interruptible(&info->wait_reassembly_queue); + wake_up_interruptible_all(&info->wait_send_queue); break; default: @@ -940,7 +853,7 @@ static int smbd_create_header(struct smbd_connection *info, if (info->transport_status != SMBD_CONNECTED) { log_outgoing(ERR, "disconnected not sending\n"); - return -ENOENT; + return -EAGAIN; } atomic_dec(&info->send_credits); @@ -990,7 +903,7 @@ static int smbd_create_header(struct smbd_connection *info, request->sge[0].addr = ib_dma_map_single(info->id->device, (void *)packet, header_length, - DMA_BIDIRECTIONAL); + DMA_TO_DEVICE); if (ib_dma_mapping_error(info->id->device, request->sge[0].addr)) { mempool_free(request, info->request_mempool); rc = -EIO; @@ -1066,6 +979,7 @@ static int smbd_post_send(struct smbd_connection *info, wake_up(&info->wait_send_pending); } smbd_disconnect_rdma_connection(info); + rc = -EAGAIN; } else /* Reset timer for idle connection after packet is sent */ mod_delayed_work(info->workqueue, &info->idle_timer_work, @@ -1091,7 +1005,7 @@ static int smbd_post_send_sgl(struct smbd_connection *info, for_each_sg(sgl, sg, num_sgs, i) { request->sge[i+1].addr = ib_dma_map_page(info->id->device, sg_page(sg), - sg->offset, sg->length, DMA_BIDIRECTIONAL); + sg->offset, sg->length, DMA_TO_DEVICE); if (ib_dma_mapping_error( info->id->device, request->sge[i+1].addr)) { rc = -EIO; @@ -1478,17 +1392,97 @@ static void idle_connection_timer(struct work_struct *work) info->keep_alive_interval*HZ); } -/* Destroy this SMBD connection, called from upper layer */ -void smbd_destroy(struct smbd_connection *info) +/* + * Destroy the transport and related RDMA and memory resources + * Need to go through all the pending counters and make sure on one is using + * the transport while it is destroyed + */ +void smbd_destroy(struct TCP_Server_Info *server) { + struct smbd_connection *info = server->smbd_conn; + struct smbd_response *response; + unsigned long flags; + + if (!info) { + log_rdma_event(INFO, "rdma session already destroyed\n"); + return; + } + log_rdma_event(INFO, "destroying rdma session\n"); + if (info->transport_status != SMBD_DISCONNECTED) { + rdma_disconnect(server->smbd_conn->id); + log_rdma_event(INFO, "wait for transport being disconnected\n"); + wait_event_interruptible( + info->disconn_wait, + info->transport_status == SMBD_DISCONNECTED); + } - /* Kick off the disconnection process */ - smbd_disconnect_rdma_connection(info); + log_rdma_event(INFO, "destroying qp\n"); + ib_drain_qp(info->id->qp); + rdma_destroy_qp(info->id); + + log_rdma_event(INFO, "cancelling idle timer\n"); + cancel_delayed_work_sync(&info->idle_timer_work); + log_rdma_event(INFO, "cancelling send immediate work\n"); + cancel_delayed_work_sync(&info->send_immediate_work); + + log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); + wait_event(info->wait_send_pending, + atomic_read(&info->send_pending) == 0); + wait_event(info->wait_send_payload_pending, + atomic_read(&info->send_payload_pending) == 0); + + /* It's not posssible for upper layer to get to reassembly */ + log_rdma_event(INFO, "drain the reassembly queue\n"); + do { + spin_lock_irqsave(&info->reassembly_queue_lock, flags); + response = _get_first_reassembly(info); + if (response) { + list_del(&response->list); + spin_unlock_irqrestore( + &info->reassembly_queue_lock, flags); + put_receive_buffer(info, response); + } else + spin_unlock_irqrestore( + &info->reassembly_queue_lock, flags); + } while (response); + info->reassembly_data_length = 0; + + log_rdma_event(INFO, "free receive buffers\n"); + wait_event(info->wait_receive_queues, + info->count_receive_queue + info->count_empty_packet_queue + == info->receive_credit_max); + destroy_receive_buffers(info); + + /* + * For performance reasons, memory registration and deregistration + * are not locked by srv_mutex. It is possible some processes are + * blocked on transport srv_mutex while holding memory registration. + * Release the transport srv_mutex to allow them to hit the failure + * path when sending data, and then release memory registartions. + */ + log_rdma_event(INFO, "freeing mr list\n"); + wake_up_interruptible_all(&info->wait_mr); + while (atomic_read(&info->mr_used_count)) { + mutex_unlock(&server->srv_mutex); + msleep(1000); + mutex_lock(&server->srv_mutex); + } + destroy_mr_list(info); + + ib_free_cq(info->send_cq); + ib_free_cq(info->recv_cq); + ib_dealloc_pd(info->pd); + rdma_destroy_id(info->id); + + /* free mempools */ + mempool_destroy(info->request_mempool); + kmem_cache_destroy(info->request_cache); - log_rdma_event(INFO, "wait for transport being destroyed\n"); - wait_event(info->wait_destroy, - info->transport_status == SMBD_DESTROYED); + mempool_destroy(info->response_mempool); + kmem_cache_destroy(info->response_cache); + + info->transport_status = SMBD_DESTROYED; destroy_workqueue(info->workqueue); kfree(info); @@ -1513,17 +1507,9 @@ int smbd_reconnect(struct TCP_Server_Info *server) */ if (server->smbd_conn->transport_status == SMBD_CONNECTED) { log_rdma_event(INFO, "disconnecting transport\n"); - smbd_disconnect_rdma_connection(server->smbd_conn); + smbd_destroy(server); } - /* wait until the transport is destroyed */ - if (!wait_event_timeout(server->smbd_conn->wait_destroy, - server->smbd_conn->transport_status == SMBD_DESTROYED, 5*HZ)) - return -EAGAIN; - - destroy_workqueue(server->smbd_conn->workqueue); - kfree(server->smbd_conn); - create_conn: log_rdma_event(INFO, "creating rdma session\n"); server->smbd_conn = smbd_get_connection( @@ -1739,12 +1725,13 @@ static struct smbd_connection *_smbd_get_connection( conn_param.retry_count = SMBD_CM_RETRY; conn_param.rnr_retry_count = SMBD_CM_RNR_RETRY; conn_param.flow_control = 0; - init_waitqueue_head(&info->wait_destroy); log_rdma_event(INFO, "connecting to IP %pI4 port %d\n", &addr_in->sin_addr, port); init_waitqueue_head(&info->conn_wait); + init_waitqueue_head(&info->disconn_wait); + init_waitqueue_head(&info->wait_reassembly_queue); rc = rdma_connect(info->id, &conn_param); if (rc) { log_rdma_event(ERR, "rdma_connect() failed with %i\n", rc); @@ -1768,19 +1755,11 @@ static struct smbd_connection *_smbd_get_connection( } init_waitqueue_head(&info->wait_send_queue); - init_waitqueue_head(&info->wait_reassembly_queue); - INIT_DELAYED_WORK(&info->idle_timer_work, idle_connection_timer); INIT_DELAYED_WORK(&info->send_immediate_work, send_immediate_work); queue_delayed_work(info->workqueue, &info->idle_timer_work, info->keep_alive_interval*HZ); - init_waitqueue_head(&info->wait_smbd_send_pending); - info->smbd_send_pending = 0; - - init_waitqueue_head(&info->wait_smbd_recv_pending); - info->smbd_recv_pending = 0; - init_waitqueue_head(&info->wait_send_pending); atomic_set(&info->send_pending, 0); @@ -1788,7 +1767,6 @@ static struct smbd_connection *_smbd_get_connection( atomic_set(&info->send_payload_pending, 0); INIT_WORK(&info->disconnect_work, smbd_disconnect_rdma_work); - INIT_WORK(&info->destroy_work, smbd_destroy_rdma_work); INIT_WORK(&info->recv_done_work, smbd_recv_done_work); INIT_WORK(&info->post_send_credits_work, smbd_post_send_credits); info->new_credits_offered = 0; @@ -1810,7 +1788,7 @@ static struct smbd_connection *_smbd_get_connection( allocate_mr_failed: /* At this point, need to a full transport shutdown */ - smbd_destroy(info); + smbd_destroy(server); return NULL; negotiation_failed: @@ -1882,11 +1860,6 @@ static int smbd_recv_buf(struct smbd_connection *info, char *buf, int rc; again: - if (info->transport_status != SMBD_CONNECTED) { - log_read(ERR, "disconnected\n"); - return -ENODEV; - } - /* * No need to hold the reassembly queue lock all the time as we are * the only one reading from the front of the queue. The transport @@ -2000,7 +1973,12 @@ read_rfc1002_done: info->transport_status != SMBD_CONNECTED); /* Don't return any data if interrupted */ if (rc) - return -ENODEV; + return rc; + + if (info->transport_status != SMBD_CONNECTED) { + log_read(ERR, "disconnected\n"); + return 0; + } goto again; } @@ -2052,8 +2030,6 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) unsigned int to_read, page_offset; int rc; - info->smbd_recv_pending++; - if (iov_iter_rw(&msg->msg_iter) == WRITE) { /* It's a bug in upper layer to get there */ cifs_dbg(VFS, "CIFS: invalid msg iter dir %u\n", @@ -2084,9 +2060,6 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) } out: - info->smbd_recv_pending--; - wake_up(&info->wait_smbd_recv_pending); - /* SMBDirect will read it all or nothing */ if (rc > 0) msg->msg_iter.count = 0; @@ -2099,7 +2072,8 @@ out: * rqst: the data to write * return value: 0 if successfully write, otherwise error code */ -int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) +int smbd_send(struct TCP_Server_Info *server, + int num_rqst, struct smb_rqst *rqst_array) { struct smbd_connection *info = server->smbd_conn; struct kvec vec; @@ -2111,54 +2085,51 @@ int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) info->max_send_size - sizeof(struct smbd_data_transfer); struct kvec *iov; int rc; + struct smb_rqst *rqst; + int rqst_idx; - info->smbd_send_pending++; if (info->transport_status != SMBD_CONNECTED) { - rc = -ENODEV; + rc = -EAGAIN; goto done; } /* - * Skip the RFC1002 length defined in MS-SMB2 section 2.1 - * It is used only for TCP transport in the iov[0] - * In future we may want to add a transport layer under protocol - * layer so this will only be issued to TCP transport - */ - - if (rqst->rq_iov[0].iov_len != 4) { - log_write(ERR, "expected the pdu length in 1st iov, but got %zu\n", rqst->rq_iov[0].iov_len); - return -EINVAL; - } - - /* * Add in the page array if there is one. The caller needs to set * rq_tailsz to PAGE_SIZE when the buffer has multiple pages and * ends at page boundary */ - buflen = smb_rqst_len(server, rqst); + remaining_data_length = 0; + for (i = 0; i < num_rqst; i++) + remaining_data_length += smb_rqst_len(server, &rqst_array[i]); - if (buflen + sizeof(struct smbd_data_transfer) > + if (remaining_data_length + sizeof(struct smbd_data_transfer) > info->max_fragmented_send_size) { log_write(ERR, "payload size %d > max size %d\n", - buflen, info->max_fragmented_send_size); + remaining_data_length, info->max_fragmented_send_size); rc = -EINVAL; goto done; } - iov = &rqst->rq_iov[1]; + log_write(INFO, "num_rqst=%d total length=%u\n", + num_rqst, remaining_data_length); + + rqst_idx = 0; +next_rqst: + rqst = &rqst_array[rqst_idx]; + iov = rqst->rq_iov; - cifs_dbg(FYI, "Sending smb (RDMA): smb_len=%u\n", buflen); - for (i = 0; i < rqst->rq_nvec-1; i++) + cifs_dbg(FYI, "Sending smb (RDMA): idx=%d smb_len=%lu\n", + rqst_idx, smb_rqst_len(server, rqst)); + for (i = 0; i < rqst->rq_nvec; i++) dump_smb(iov[i].iov_base, iov[i].iov_len); - remaining_data_length = buflen; - log_write(INFO, "rqst->rq_nvec=%d rqst->rq_npages=%d rq_pagesz=%d " - "rq_tailsz=%d buflen=%d\n", - rqst->rq_nvec, rqst->rq_npages, rqst->rq_pagesz, - rqst->rq_tailsz, buflen); + log_write(INFO, "rqst_idx=%d nvec=%d rqst->rq_npages=%d rq_pagesz=%d " + "rq_tailsz=%d buflen=%lu\n", + rqst_idx, rqst->rq_nvec, rqst->rq_npages, rqst->rq_pagesz, + rqst->rq_tailsz, smb_rqst_len(server, rqst)); - start = i = iov[0].iov_len ? 0 : 1; + start = i = 0; buflen = 0; while (true) { buflen += iov[i].iov_len; @@ -2206,14 +2177,14 @@ int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) goto done; } i++; - if (i == rqst->rq_nvec-1) + if (i == rqst->rq_nvec) break; } start = i; buflen = 0; } else { i++; - if (i == rqst->rq_nvec-1) { + if (i == rqst->rq_nvec) { /* send out all remaining vecs */ remaining_data_length -= buflen; log_write(INFO, @@ -2257,6 +2228,10 @@ int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) } } + rqst_idx++; + if (rqst_idx < num_rqst) + goto next_rqst; + done: /* * As an optimization, we don't wait for individual I/O to finish @@ -2268,9 +2243,6 @@ done: wait_event(info->wait_send_payload_pending, atomic_read(&info->send_payload_pending) == 0); - info->smbd_send_pending--; - wake_up(&info->wait_smbd_send_pending); - return rc; } diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index a11096254f29..f6241b8bce5f 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -70,12 +70,11 @@ struct smbd_connection { int ri_rc; struct completion ri_done; wait_queue_head_t conn_wait; - wait_queue_head_t wait_destroy; + wait_queue_head_t disconn_wait; struct completion negotiate_completion; bool negotiate_done; - struct work_struct destroy_work; struct work_struct disconnect_work; struct work_struct recv_done_work; struct work_struct post_send_credits_work; @@ -123,13 +122,6 @@ struct smbd_connection { wait_queue_head_t wait_for_mr_cleanup; /* Activity accoutning */ - /* Pending reqeusts issued from upper layer */ - int smbd_send_pending; - wait_queue_head_t wait_smbd_send_pending; - - int smbd_recv_pending; - wait_queue_head_t wait_smbd_recv_pending; - atomic_t send_pending; wait_queue_head_t wait_send_pending; atomic_t send_payload_pending; @@ -288,11 +280,12 @@ struct smbd_connection *smbd_get_connection( /* Reconnect SMBDirect session */ int smbd_reconnect(struct TCP_Server_Info *server); /* Destroy SMBDirect session */ -void smbd_destroy(struct smbd_connection *info); +void smbd_destroy(struct TCP_Server_Info *server); /* Interface for carrying upper layer I/O through send/recv */ int smbd_recv(struct smbd_connection *info, struct msghdr *msg); -int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst); +int smbd_send(struct TCP_Server_Info *server, + int num_rqst, struct smb_rqst *rqst); enum mr_state { MR_READY, @@ -330,9 +323,9 @@ struct smbd_connection {}; static inline void *smbd_get_connection( struct TCP_Server_Info *server, struct sockaddr *dstaddr) {return NULL;} static inline int smbd_reconnect(struct TCP_Server_Info *server) {return -1; } -static inline void smbd_destroy(struct smbd_connection *info) {} +static inline void smbd_destroy(struct TCP_Server_Info *server) {} static inline int smbd_recv(struct smbd_connection *info, struct msghdr *msg) {return -1; } -static inline int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) {return -1; } +static inline int smbd_send(struct TCP_Server_Info *server, int num_rqst, struct smb_rqst *rqst) {return -1; } #endif #endif diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h index f996daeea271..08628e6a42ac 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/cifs/smbfsctl.h @@ -35,6 +35,33 @@ * below). Additional detail on less common ones can be found in MS-FSCC * section 2.3. */ + +/* + * FSCTL values are 32 bits and are constructed as + * <device 16bits> <access 2bits> <function 12bits> <method 2bits> + */ +/* Device */ +#define FSCTL_DEVICE_DFS (0x0006 << 16) +#define FSCTL_DEVICE_FILE_SYSTEM (0x0009 << 16) +#define FSCTL_DEVICE_NAMED_PIPE (0x0011 << 16) +#define FSCTL_DEVICE_NETWORK_FILE_SYSTEM (0x0014 << 16) +#define FSCTL_DEVICE_MASK 0xffff0000 +/* Access */ +#define FSCTL_DEVICE_ACCESS_FILE_ANY_ACCESS (0x00 << 14) +#define FSCTL_DEVICE_ACCESS_FILE_READ_ACCESS (0x01 << 14) +#define FSCTL_DEVICE_ACCESS_FILE_WRITE_ACCESS (0x02 << 14) +#define FSCTL_DEVICE_ACCESS_FILE_READ_WRITE_ACCESS (0x03 << 14) +#define FSCTL_DEVICE_ACCESS_MASK 0x0000c000 +/* Function */ +#define FSCTL_DEVICE_FUNCTION_MASK 0x00003ffc +/* Method */ +#define FSCTL_DEVICE_METHOD_BUFFERED 0x00 +#define FSCTL_DEVICE_METHOD_IN_DIRECT 0x01 +#define FSCTL_DEVICE_METHOD_OUT_DIRECT 0x02 +#define FSCTL_DEVICE_METHOD_NEITHER 0x03 +#define FSCTL_DEVICE_METHOD_MASK 0x00000003 + + #define FSCTL_DFS_GET_REFERRALS 0x00060194 #define FSCTL_DFS_GET_REFERRALS_EX 0x000601B0 #define FSCTL_REQUEST_OPLOCK_LEVEL_1 0x00090000 @@ -76,7 +103,7 @@ #define FSCTL_SET_ZERO_ON_DEALLOC 0x00090194 /* BB add struct */ #define FSCTL_SET_SHORT_NAME_BEHAVIOR 0x000901B4 /* BB add struct */ #define FSCTL_GET_INTEGRITY_INFORMATION 0x0009027C -#define FSCTL_QUERY_ALLOCATED_RANGES 0x000940CF /* BB add struct */ +#define FSCTL_QUERY_ALLOCATED_RANGES 0x000940CF #define FSCTL_SET_DEFECT_MANAGEMENT 0x00098134 /* BB add struct */ #define FSCTL_FILE_LEVEL_TRIM 0x00098208 /* BB add struct */ #define FSCTL_DUPLICATE_EXTENTS_TO_FILE 0x00098344 diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 1de8e996e566..60661b3f983a 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -33,7 +33,7 @@ #include <linux/uaccess.h> #include <asm/processor.h> #include <linux/mempool.h> -#include <linux/signal.h> +#include <linux/sched/signal.h> #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" @@ -104,7 +104,10 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) { #ifdef CONFIG_CIFS_STATS2 __le16 command = midEntry->server->vals->lock_cmd; + __u16 smb_cmd = le16_to_cpu(midEntry->command); unsigned long now; + unsigned long roundtrip_time; + struct TCP_Server_Info *server = midEntry->server; #endif midEntry->mid_state = MID_FREE; atomic_dec(&midCount); @@ -114,6 +117,23 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) cifs_small_buf_release(midEntry->resp_buf); #ifdef CONFIG_CIFS_STATS2 now = jiffies; + if (now < midEntry->when_alloc) + cifs_dbg(VFS, "invalid mid allocation time\n"); + roundtrip_time = now - midEntry->when_alloc; + + if (smb_cmd < NUMBER_OF_SMB2_COMMANDS) { + if (atomic_read(&server->num_cmds[smb_cmd]) == 0) { + server->slowest_cmd[smb_cmd] = roundtrip_time; + server->fastest_cmd[smb_cmd] = roundtrip_time; + } else { + if (server->slowest_cmd[smb_cmd] < roundtrip_time) + server->slowest_cmd[smb_cmd] = roundtrip_time; + else if (server->fastest_cmd[smb_cmd] > roundtrip_time) + server->fastest_cmd[smb_cmd] = roundtrip_time; + } + cifs_stats_inc(&server->num_cmds[smb_cmd]); + server->time_per_cmd[smb_cmd] += roundtrip_time; + } /* * commands taking longer than one second (default) can be indications * that something is wrong, unless it is quite a slow link or a very @@ -131,11 +151,10 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) * smb2slowcmd[NUMBER_OF_SMB2_COMMANDS] counts by command * NB: le16_to_cpu returns unsigned so can not be negative below */ - if (le16_to_cpu(midEntry->command) < NUMBER_OF_SMB2_COMMANDS) - cifs_stats_inc(&midEntry->server->smb2slowcmd[le16_to_cpu(midEntry->command)]); + if (smb_cmd < NUMBER_OF_SMB2_COMMANDS) + cifs_stats_inc(&server->smb2slowcmd[smb_cmd]); - trace_smb3_slow_rsp(le16_to_cpu(midEntry->command), - midEntry->mid, midEntry->pid, + trace_smb3_slow_rsp(smb_cmd, midEntry->mid, midEntry->pid, midEntry->when_sent, midEntry->when_received); if (cifsFYI & CIFS_TIMER) { pr_debug(" CIFS slow rsp: cmd %d mid %llu", @@ -300,7 +319,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, __be32 rfc1002_marker; if (cifs_rdma_enabled(server) && server->smbd_conn) { - rc = smbd_send(server, rqst); + rc = smbd_send(server, num_rqst, rqst); goto smbd_done; } @@ -510,7 +529,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, return -EAGAIN; spin_lock(&server->req_lock); - if ((flags & CIFS_TIMEOUT_MASK) == CIFS_ASYNC_OP) { + if ((flags & CIFS_TIMEOUT_MASK) == CIFS_NON_BLOCKING) { /* oplock breaks must not be held up */ server->in_flight++; *credits -= 1; @@ -819,7 +838,7 @@ SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses, iov[0].iov_base = in_buf; iov[0].iov_len = get_rfc1002_length(in_buf) + 4; - flags |= CIFS_NO_RESP; + flags |= CIFS_NO_RSP_BUF; rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov); cifs_dbg(NOISY, "SendRcvNoRsp flags %d rc %d\n", flags, rc); @@ -1054,8 +1073,11 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, mutex_unlock(&ses->server->srv_mutex); - if (rc < 0) { - /* Sending failed for some reason - return credits back */ + /* + * If sending failed for some reason or it is an oplock break that we + * will not receive a response to - return credits back + */ + if (rc < 0 || (flags & CIFS_NO_SRV_RSP)) { for (i = 0; i < num_rqst; i++) add_credits(ses->server, &credits[i], optype); goto out; @@ -1076,9 +1098,6 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, smb311_update_preauth_hash(ses, rqst[0].rq_iov, rqst[0].rq_nvec); - if ((flags & CIFS_TIMEOUT_MASK) == CIFS_ASYNC_OP) - goto out; - for (i = 0; i < num_rqst; i++) { rc = wait_for_response(ses->server, midQ[i]); if (rc != 0) @@ -1132,7 +1151,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, flags & CIFS_LOG_ERROR); /* mark it so buf will not be freed by cifs_delete_mid */ - if ((flags & CIFS_NO_RESP) == 0) + if ((flags & CIFS_NO_RSP_BUF) == 0) midQ[i]->resp_buf = NULL; } @@ -1283,9 +1302,6 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, if (rc < 0) goto out; - if ((flags & CIFS_TIMEOUT_MASK) == CIFS_ASYNC_OP) - goto out; - rc = wait_for_response(ses->server, midQ); if (rc != 0) { send_cancel(ses->server, &rqst, midQ); diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 97424cf206c0..23f6ebd08e80 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -54,17 +54,11 @@ static struct inode *coda_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void coda_i_callback(struct rcu_head *head) +static void coda_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(coda_inode_cachep, ITOC(inode)); } -static void coda_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, coda_i_callback); -} - static void init_once(void *foo) { struct coda_inode_info *ei = (struct coda_inode_info *) foo; @@ -104,7 +98,7 @@ static int coda_remount(struct super_block *sb, int *flags, char *data) static const struct super_operations coda_super_operations = { .alloc_inode = coda_alloc_inode, - .destroy_inode = coda_destroy_inode, + .free_inode = coda_free_inode, .evict_inode = coda_evict_inode, .put_super = coda_put_super, .statfs = coda_statfs, diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index c5234c21b539..f2bb7985d21c 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -39,7 +39,6 @@ #include <linux/device.h> #include <linux/pid_namespace.h> #include <asm/io.h> -#include <linux/poll.h> #include <linux/uaccess.h> #include <linux/coda.h> diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 39843fa7e11b..5e7932d668ab 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1690,9 +1690,11 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence) switch (whence) { case 1: offset += file->f_pos; + /* fall through */ case 0: if (offset >= 0) break; + /* fall through */ default: return -EINVAL; } @@ -1755,12 +1757,19 @@ int configfs_register_group(struct config_group *parent_group, inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); ret = create_default_group(parent_group, group); - if (!ret) { - spin_lock(&configfs_dirent_lock); - configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); - spin_unlock(&configfs_dirent_lock); - } + if (ret) + goto err_out; + + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + inode_unlock(d_inode(parent)); + return 0; +err_out: inode_unlock(d_inode(parent)); + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); return ret; } EXPORT_SYMBOL(configfs_register_group); diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index 5759bcd018cd..b46021ebde85 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -29,20 +29,17 @@ static void __fscrypt_decrypt_bio(struct bio *bio, bool done) { struct bio_vec *bv; - int i; struct bvec_iter_all iter_all; - bio_for_each_segment_all(bv, bio, i, iter_all) { + bio_for_each_segment_all(bv, bio, iter_all) { struct page *page = bv->bv_page; int ret = fscrypt_decrypt_page(page->mapping->host, page, PAGE_SIZE, 0, page->index); - if (ret) { - WARN_ON_ONCE(1); + if (ret) SetPageError(page); - } else if (done) { + else if (done) SetPageUptodate(page); - } if (done) unlock_page(page); } @@ -104,7 +101,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE); - ctx = fscrypt_get_ctx(inode, GFP_NOFS); + ctx = fscrypt_get_ctx(GFP_NOFS); if (IS_ERR(ctx)) return PTR_ERR(ctx); diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 4dc788e3bc96..68e2ca4c4af6 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -87,23 +87,17 @@ EXPORT_SYMBOL(fscrypt_release_ctx); /** * fscrypt_get_ctx() - Gets an encryption context - * @inode: The inode for which we are doing the crypto * @gfp_flags: The gfp flag for memory allocation * * Allocates and initializes an encryption context. * - * Return: An allocated and initialized encryption context on success; error - * value or NULL otherwise. + * Return: A new encryption context on success; an ERR_PTR() otherwise. */ -struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags) +struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) { - struct fscrypt_ctx *ctx = NULL; - struct fscrypt_info *ci = inode->i_crypt_info; + struct fscrypt_ctx *ctx; unsigned long flags; - if (ci == NULL) - return ERR_PTR(-ENOKEY); - /* * We first try getting the ctx from a free list because in * the common case the ctx will have an allocated and @@ -258,9 +252,9 @@ struct page *fscrypt_encrypt_page(const struct inode *inode, BUG_ON(!PageLocked(page)); - ctx = fscrypt_get_ctx(inode, gfp_flags); + ctx = fscrypt_get_ctx(gfp_flags); if (IS_ERR(ctx)) - return (struct page *)ctx; + return ERR_CAST(ctx); /* The encryption operation will require a bounce page. */ ciphertext_page = fscrypt_alloc_bounce_page(ctx, gfp_flags); @@ -313,45 +307,47 @@ int fscrypt_decrypt_page(const struct inode *inode, struct page *page, EXPORT_SYMBOL(fscrypt_decrypt_page); /* - * Validate dentries for encrypted directories to make sure we aren't - * potentially caching stale data after a key has been added or - * removed. + * Validate dentries in encrypted directories to make sure we aren't potentially + * caching stale dentries after a key has been added. */ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *dir; - int dir_has_key, cached_with_key; + int err; + int valid; + + /* + * Plaintext names are always valid, since fscrypt doesn't support + * reverting to ciphertext names without evicting the directory's inode + * -- which implies eviction of the dentries in the directory. + */ + if (!(dentry->d_flags & DCACHE_ENCRYPTED_NAME)) + return 1; + + /* + * Ciphertext name; valid if the directory's key is still unavailable. + * + * Although fscrypt forbids rename() on ciphertext names, we still must + * use dget_parent() here rather than use ->d_parent directly. That's + * because a corrupted fs image may contain directory hard links, which + * the VFS handles by moving the directory's dentry tree in the dcache + * each time ->lookup() finds the directory and it already has a dentry + * elsewhere. Thus ->d_parent can be changing, and we must safely grab + * a reference to some ->d_parent to prevent it from being freed. + */ if (flags & LOOKUP_RCU) return -ECHILD; dir = dget_parent(dentry); - if (!IS_ENCRYPTED(d_inode(dir))) { - dput(dir); - return 0; - } - - spin_lock(&dentry->d_lock); - cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY; - spin_unlock(&dentry->d_lock); - dir_has_key = (d_inode(dir)->i_crypt_info != NULL); + err = fscrypt_get_encryption_info(d_inode(dir)); + valid = !fscrypt_has_encryption_key(d_inode(dir)); dput(dir); - /* - * If the dentry was cached without the key, and it is a - * negative dentry, it might be a valid name. We can't check - * if the key has since been made available due to locking - * reasons, so we fail the validation so ext4_lookup() can do - * this check. - * - * We also fail the validation if the dentry was created with - * the key present, but we no longer have the key, or vice versa. - */ - if ((!cached_with_key && d_is_negative(dentry)) || - (!cached_with_key && dir_has_key) || - (cached_with_key && !dir_has_key)) - return 0; - return 1; + if (err < 0) + return err; + + return valid; } const struct dentry_operations fscrypt_d_ops = { diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 7ff40a73dbec..eccea3d8f923 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -269,7 +269,7 @@ int fscrypt_fname_disk_to_usr(struct inode *inode, if (iname->len < FS_CRYPTO_BLOCK_SIZE) return -EUCLEAN; - if (inode->i_crypt_info) + if (fscrypt_has_encryption_key(inode)) return fname_decrypt(inode, iname, oname); if (iname->len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) { @@ -336,7 +336,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, if (ret) return ret; - if (dir->i_crypt_info) { + if (fscrypt_has_encryption_key(dir)) { if (!fscrypt_fname_encrypted_size(dir, iname->len, dir->i_sb->s_cop->max_namelen, &fname->crypto_buf.len)) @@ -356,6 +356,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, } if (!lookup) return -ENOKEY; + fname->is_ciphertext_name = true; /* * We don't have the key and we are doing a lookup; decode the diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 56debb1fcf5e..2dc22549d724 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -49,7 +49,8 @@ int fscrypt_file_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL_GPL(fscrypt_file_open); -int __fscrypt_prepare_link(struct inode *inode, struct inode *dir) +int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, + struct dentry *dentry) { int err; @@ -57,6 +58,10 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir) if (err) return err; + /* ... in case we looked up ciphertext name before key was added */ + if (dentry->d_flags & DCACHE_ENCRYPTED_NAME) + return -ENOKEY; + if (!fscrypt_has_permitted_context(dir, inode)) return -EXDEV; @@ -78,6 +83,11 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) return err; + /* ... in case we looked up ciphertext name(s) before key was added */ + if ((old_dentry->d_flags | new_dentry->d_flags) & + DCACHE_ENCRYPTED_NAME) + return -ENOKEY; + if (old_dir != new_dir) { if (IS_ENCRYPTED(new_dir) && !fscrypt_has_permitted_context(new_dir, @@ -94,21 +104,21 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, } EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename); -int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry) +int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct fscrypt_name *fname) { - int err = fscrypt_get_encryption_info(dir); + int err = fscrypt_setup_filename(dir, &dentry->d_name, 1, fname); - if (err) + if (err && err != -ENOENT) return err; - if (fscrypt_has_encryption_key(dir)) { + if (fname->is_ciphertext_name) { spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; + dentry->d_flags |= DCACHE_ENCRYPTED_NAME; spin_unlock(&dentry->d_lock); + d_set_d_op(dentry, &fscrypt_d_ops); } - - d_set_d_op(dentry, &fscrypt_d_ops); - return 0; + return err; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); @@ -179,11 +189,9 @@ int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, sd->len = cpu_to_le16(ciphertext_len); err = fname_encrypt(inode, &iname, sd->encrypted_path, ciphertext_len); - if (err) { - if (!disk_link->name) - kfree(sd); - return err; - } + if (err) + goto err_free_sd; + /* * Null-terminating the ciphertext doesn't make sense, but we still * count the null terminator in the length, so we might as well @@ -191,9 +199,20 @@ int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, */ sd->encrypted_path[ciphertext_len] = '\0'; + /* Cache the plaintext symlink target for later use by get_link() */ + err = -ENOMEM; + inode->i_link = kmemdup(target, len + 1, GFP_NOFS); + if (!inode->i_link) + goto err_free_sd; + if (!disk_link->name) disk_link->name = (unsigned char *)sd; return 0; + +err_free_sd: + if (!disk_link->name) + kfree(sd); + return err; } EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink); @@ -202,7 +221,7 @@ EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink); * @inode: the symlink inode * @caddr: the on-disk contents of the symlink * @max_size: size of @caddr buffer - * @done: if successful, will be set up to free the returned target + * @done: if successful, will be set up to free the returned target if needed * * If the symlink's encryption key is available, we decrypt its target. * Otherwise, we encode its target for presentation. @@ -217,12 +236,18 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, { const struct fscrypt_symlink_data *sd; struct fscrypt_str cstr, pstr; + bool has_key; int err; /* This is for encrypted symlinks only */ if (WARN_ON(!IS_ENCRYPTED(inode))) return ERR_PTR(-EINVAL); + /* If the decrypted target is already cached, just return it. */ + pstr.name = READ_ONCE(inode->i_link); + if (pstr.name) + return pstr.name; + /* * Try to set up the symlink's encryption key, but we can continue * regardless of whether the key is available or not. @@ -230,6 +255,7 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, err = fscrypt_get_encryption_info(inode); if (err) return ERR_PTR(err); + has_key = fscrypt_has_encryption_key(inode); /* * For historical reasons, encrypted symlink targets are prefixed with @@ -261,7 +287,17 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, goto err_kfree; pstr.name[pstr.len] = '\0'; - set_delayed_call(done, kfree_link, pstr.name); + + /* + * Cache decrypted symlink targets in i_link for later use. Don't cache + * symlink targets encoded without the key, since those become outdated + * once the key is added. This pairs with the READ_ONCE() above and in + * the VFS path lookup code. + */ + if (!has_key || + cmpxchg_release(&inode->i_link, NULL, pstr.name) != NULL) + set_delayed_call(done, kfree_link, pstr.name); + return pstr.name; err_kfree: diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 322ce9686bdb..dcd91a3fbe49 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -402,7 +402,6 @@ static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt) { SHASH_DESC_ON_STACK(desc, tfm); desc->tfm = tfm; - desc->flags = 0; return crypto_shash_digest(desc, key, keysize, salt); } @@ -509,7 +508,7 @@ int fscrypt_get_encryption_info(struct inode *inode) u8 *raw_key = NULL; int res; - if (inode->i_crypt_info) + if (fscrypt_has_encryption_key(inode)) return 0; res = fscrypt_initialize(inode->i_sb->s_cop->flags); @@ -573,7 +572,7 @@ int fscrypt_get_encryption_info(struct inode *inode) if (res) goto out; - if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL) + if (cmpxchg_release(&inode->i_crypt_info, NULL, crypt_info) == NULL) crypt_info = NULL; out: if (res == -ENOKEY) @@ -584,9 +583,30 @@ out: } EXPORT_SYMBOL(fscrypt_get_encryption_info); +/** + * fscrypt_put_encryption_info - free most of an inode's fscrypt data + * + * Free the inode's fscrypt_info. Filesystems must call this when the inode is + * being evicted. An RCU grace period need not have elapsed yet. + */ void fscrypt_put_encryption_info(struct inode *inode) { put_crypt_info(inode->i_crypt_info); inode->i_crypt_info = NULL; } EXPORT_SYMBOL(fscrypt_put_encryption_info); + +/** + * fscrypt_free_inode - free an inode's fscrypt data requiring RCU delay + * + * Free the inode's cached decrypted symlink target, if any. Filesystems must + * call this after an RCU grace period, just before they free the inode. + */ +void fscrypt_free_inode(struct inode *inode) +{ + if (IS_ENCRYPTED(inode) && S_ISLNK(inode->i_mode)) { + kfree(inode->i_link); + inode->i_link = NULL; + } +} +EXPORT_SYMBOL(fscrypt_free_inode); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index bd7eaf9b3f00..d536889ac31b 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -194,8 +194,8 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) res = fscrypt_get_encryption_info(child); if (res) return 0; - parent_ci = parent->i_crypt_info; - child_ci = child->i_crypt_info; + parent_ci = READ_ONCE(parent->i_crypt_info); + child_ci = READ_ONCE(child->i_crypt_info); if (parent_ci && child_ci) { return memcmp(parent_ci->ci_master_key_descriptor, @@ -246,7 +246,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child, if (res < 0) return res; - ci = parent->i_crypt_info; + ci = READ_ONCE(parent->i_crypt_info); if (ci == NULL) return -ENOKEY; @@ -33,6 +33,7 @@ #include <linux/sizes.h> #include <linux/mmu_notifier.h> #include <linux/iomap.h> +#include <asm/pgalloc.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -813,7 +814,7 @@ static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index, goto unlock_pmd; flush_cache_page(vma, address, pfn); - pmd = pmdp_huge_clear_flush(vma, address, pmdp); + pmd = pmdp_invalidate(vma, address, pmdp); pmd = pmd_wrprotect(pmd); pmd = pmd_mkclean(pmd); set_pmd_at(vma->vm_mm, address, pmdp, pmd); @@ -1407,7 +1408,9 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; + struct vm_area_struct *vma = vmf->vma; struct inode *inode = mapping->host; + pgtable_t pgtable = NULL; struct page *zero_page; spinlock_t *ptl; pmd_t pmd_entry; @@ -1422,12 +1425,22 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, DAX_PMD | DAX_ZERO_PAGE, false); + if (arch_needs_pgtable_deposit()) { + pgtable = pte_alloc_one(vma->vm_mm); + if (!pgtable) + return VM_FAULT_OOM; + } + ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { spin_unlock(ptl); goto fallback; } + if (pgtable) { + pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); + mm_inc_nr_ptes(vma->vm_mm); + } pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot); pmd_entry = pmd_mkhuge(pmd_entry); set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry); @@ -1436,6 +1449,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, return VM_FAULT_NOPAGE; fallback: + if (pgtable) + pte_free(vma->vm_mm, pgtable); trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry); return VM_FAULT_FALLBACK; } @@ -1560,8 +1575,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, } trace_dax_pmd_insert_mapping(inode, vmf, PMD_SIZE, pfn, entry); - result = vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn, - write); + result = vmf_insert_pfn_pmd(vmf, pfn, write); break; case IOMAP_UNWRITTEN: case IOMAP_HOLE: @@ -1671,8 +1685,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order) ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn); #ifdef CONFIG_FS_DAX_PMD else if (order == PMD_ORDER) - ret = vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, - pfn, true); + ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE); #endif else ret = VM_FAULT_FALLBACK; diff --git a/fs/dcache.c b/fs/dcache.c index aac41adf4743..8136bda27a1f 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -18,6 +18,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> +#include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> @@ -284,25 +285,23 @@ static inline int dname_external(const struct dentry *dentry) void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { spin_lock(&dentry->d_lock); + name->name = dentry->d_name; if (unlikely(dname_external(dentry))) { - struct external_name *p = external_name(dentry); - atomic_inc(&p->u.count); - spin_unlock(&dentry->d_lock); - name->name = p->name; + atomic_inc(&external_name(dentry)->u.count); } else { memcpy(name->inline_name, dentry->d_iname, dentry->d_name.len + 1); - spin_unlock(&dentry->d_lock); - name->name = name->inline_name; + name->name.name = name->inline_name; } + spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { - if (unlikely(name->name != name->inline_name)) { + if (unlikely(name->name.name != name->inline_name)) { struct external_name *p; - p = container_of(name->name, struct external_name, name[0]); + p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) kfree_rcu(p, u.head); } @@ -344,7 +343,7 @@ static void dentry_free(struct dentry *dentry) } } /* if dentry was never visible to RCU, immediate free is OK */ - if (!(dentry->d_flags & DCACHE_RCUACCESS)) + if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); @@ -1701,7 +1700,6 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; - dentry->d_flags |= DCACHE_RCUACCESS; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject @@ -1726,7 +1724,7 @@ struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { - dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR; + dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; @@ -1739,12 +1737,21 @@ struct dentry *d_alloc_cursor(struct dentry * parent) * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. + * This is used for pipes, sockets et.al. - the stuff that should + * never be anyone's children or parents. Unlike all other + * dentries, these will not have RCU delay between dropping the + * last reference and freeing them. + * + * The only user is alloc_file_pseudo() and that's what should + * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { - return __d_alloc(sb, name); + struct dentry *dentry = __d_alloc(sb, name); + if (likely(dentry)) + dentry->d_flags |= DCACHE_NORCU; + return dentry; } -EXPORT_SYMBOL(d_alloc_pseudo); struct dentry *d_alloc_name(struct dentry *parent, const char *name) { @@ -1911,12 +1918,10 @@ struct dentry *d_make_root(struct inode *root_inode) if (root_inode) { res = d_alloc_anon(root_inode->i_sb); - if (res) { - res->d_flags |= DCACHE_RCUACCESS; + if (res) d_instantiate(res, root_inode); - } else { + else iput(root_inode); - } } return res; } @@ -2781,9 +2786,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; - if (dentry == old_parent) - dentry->d_flags |= DCACHE_RCUACCESS; - else + if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; @@ -2795,6 +2798,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); __d_rehash(dentry); fsnotify_update_flags(dentry); + fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 4fce1da7db23..ddd708b09fa1 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -394,12 +394,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n"); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * - * If debugfs is not enabled in the kernel, the value -%ENODEV will be - * returned. It is not wise to check for this value, but rather, check for - * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling - * code. + * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will + * be returned. */ struct dentry *debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value) @@ -440,12 +439,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n"); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * - * If debugfs is not enabled in the kernel, the value -%ENODEV will be - * returned. It is not wise to check for this value, but rather, check for - * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling - * code. + * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will + * be returned. */ struct dentry *debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value) @@ -486,12 +484,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n"); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * - * If debugfs is not enabled in the kernel, the value -%ENODEV will be - * returned. It is not wise to check for this value, but rather, check for - * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling - * code. + * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will + * be returned. */ struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value) @@ -533,12 +530,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * - * If debugfs is not enabled in the kernel, the value -%ENODEV will be - * returned. It is not wise to check for this value, but rather, check for - * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling - * code. + * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will + * be returned. */ struct dentry *debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value) @@ -582,12 +578,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n"); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * - * If debugfs is not enabled in the kernel, the value -%ENODEV will be - * returned. It is not wise to check for this value, but rather, check for - * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling - * code. + * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will + * be returned. */ struct dentry *debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, unsigned long *value) @@ -850,12 +845,11 @@ static const struct file_operations fops_bool_wo = { * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * - * If debugfs is not enabled in the kernel, the value -%ENODEV will be - * returned. It is not wise to check for this value, but rather, check for - * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling - * code. + * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will + * be returned. */ struct dentry *debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, bool *value) @@ -904,12 +898,11 @@ static const struct file_operations fops_blob = { * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * - * If debugfs is not enabled in the kernel, the value -%ENODEV will be - * returned. It is not wise to check for this value, but rather, check for - * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling - * code. + * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will + * be returned. */ struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, @@ -1005,8 +998,9 @@ static const struct file_operations u32_array_fops = { * Writing is not supported. Seek within the file is also not supported. * Once array is created its size can not be changed. * - * The function returns a pointer to dentry on success. If debugfs is not - * enabled in the kernel, the value -%ENODEV will be returned. + * The function returns a pointer to dentry on success. If an error occurs, + * %ERR_PTR(-ERROR) or NULL will be returned. If debugfs is not enabled in + * the kernel, the value %ERR_PTR(-ENODEV) will be returned. */ struct dentry *debugfs_create_u32_array(const char *name, umode_t mode, struct dentry *parent, @@ -1102,12 +1096,11 @@ static const struct file_operations fops_regset32 = { * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * - * If debugfs is not enabled in the kernel, the value -%ENODEV will be - * returned. It is not wise to check for this value, but rather, check for - * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling - * code. + * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will + * be returned. */ struct dentry *debugfs_create_regset32(const char *name, umode_t mode, struct dentry *parent, diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 95b5e78c22b1..acef14ad53db 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -163,19 +163,18 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } -static void debugfs_evict_inode(struct inode *inode) +static void debugfs_free_inode(struct inode *inode) { - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); + free_inode_nonrcu(inode); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, - .evict_inode = debugfs_evict_inode, + .free_inode = debugfs_free_inode, }; static void debugfs_release_dentry(struct dentry *dentry) @@ -819,7 +818,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, goto exit; } d_move(old_dentry, dentry); - fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name, + fsnotify_move(d_inode(old_dir), d_inode(new_dir), &old_name.name, d_is_dir(old_dentry), NULL, old_dentry); release_dentry_name_snapshot(&old_name); diff --git a/fs/direct-io.c b/fs/direct-io.c index 9bb015bc4a83..fbe885d68035 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -538,7 +538,6 @@ static struct bio *dio_await_one(struct dio *dio) static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) { struct bio_vec *bvec; - unsigned i; blk_status_t err = bio->bi_status; if (err) { @@ -553,7 +552,7 @@ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) } else { struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; if (dio->op == REQ_OP_READ && !PageCompound(page) && diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index 43a96c330570..d8e27defa89f 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -68,6 +68,7 @@ static int user_cmd(struct sk_buff *skb, struct genl_info *info) static const struct genl_ops dlm_nl_ops[] = { { .cmd = DLM_CMD_HELLO, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = user_cmd, }, }; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index f664da55234e..491cf5baa8c2 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -68,7 +68,6 @@ static int ecryptfs_hash_digest(struct crypto_shash *tfm, int err; desc->tfm = tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; err = crypto_shash_digest(desc, src, len, dst); shash_desc_zero(desc); return err; diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index e74fe84d0886..90fbac5d485b 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -769,7 +769,6 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes, } s->hash_desc->tfm = s->hash_tfm; - s->hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; rc = crypto_shash_digest(s->hash_desc, (u8 *)s->auth_tok->token.password.session_key_encryption_key, diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index 85411ceb0508..c3e511f2b6c0 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -67,9 +67,8 @@ out: return inode; } -static void ecryptfs_i_callback(struct rcu_head *head) +static void ecryptfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); struct ecryptfs_inode_info *inode_info; inode_info = ecryptfs_inode_to_private(inode); @@ -92,7 +91,6 @@ static void ecryptfs_destroy_inode(struct inode *inode) inode_info = ecryptfs_inode_to_private(inode); BUG_ON(inode_info->lower_file); ecryptfs_destroy_crypt_stat(&inode_info->crypt_stat); - call_rcu(&inode->i_rcu, ecryptfs_i_callback); } /** @@ -186,6 +184,7 @@ static int ecryptfs_show_options(struct seq_file *m, struct dentry *root) const struct super_operations ecryptfs_sops = { .alloc_inode = ecryptfs_alloc_inode, .destroy_inode = ecryptfs_destroy_inode, + .free_inode = ecryptfs_free_inode, .statfs = ecryptfs_statfs, .remount_fs = NULL, .evict_inode = ecryptfs_evict_inode, diff --git a/fs/efs/super.c b/fs/efs/super.c index 6ffb7ba1547a..867fc24dee20 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -74,17 +74,11 @@ static struct inode *efs_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void efs_i_callback(struct rcu_head *head) +static void efs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(efs_inode_cachep, INODE_INFO(inode)); } -static void efs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, efs_i_callback); -} - static void init_once(void *foo) { struct efs_inode_info *ei = (struct efs_inode_info *) foo; @@ -122,7 +116,7 @@ static int efs_remount(struct super_block *sb, int *flags, char *data) static const struct super_operations efs_superblock_operations = { .alloc_inode = efs_alloc_inode, - .destroy_inode = efs_destroy_inode, + .free_inode = efs_free_inode, .statfs = efs_statfs, .remount_fs = efs_remount, }; diff --git a/fs/eventfd.c b/fs/eventfd.c index 08d3bd602f73..93b1fa7bb298 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -21,6 +21,9 @@ #include <linux/eventfd.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/idr.h> + +static DEFINE_IDA(eventfd_ida); struct eventfd_ctx { struct kref kref; @@ -35,6 +38,7 @@ struct eventfd_ctx { */ __u64 count; unsigned int flags; + int id; }; /** @@ -69,6 +73,8 @@ EXPORT_SYMBOL_GPL(eventfd_signal); static void eventfd_free_ctx(struct eventfd_ctx *ctx) { + if (ctx->id >= 0) + ida_simple_remove(&eventfd_ida, ctx->id); kfree(ctx); } @@ -297,6 +303,7 @@ static void eventfd_show_fdinfo(struct seq_file *m, struct file *f) seq_printf(m, "eventfd-count: %16llx\n", (unsigned long long)ctx->count); spin_unlock_irq(&ctx->wqh.lock); + seq_printf(m, "eventfd-id: %d\n", ctx->id); } #endif @@ -400,6 +407,7 @@ static int do_eventfd(unsigned int count, int flags) init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; + ctx->id = ida_simple_get(&eventfd_ida, 0, 0, GFP_KERNEL); fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx, O_RDWR | (flags & EFD_SHARED_FCNTL_FLAGS)); diff --git a/fs/exec.c b/fs/exec.c index 2e0033348d8e..d88584ebf07f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1652,11 +1652,13 @@ int search_binary_handler(struct linux_binprm *bprm) if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); + bprm->recursion_depth++; retval = fmt->load_binary(bprm); + bprm->recursion_depth--; + read_lock(&binfmt_lock); put_binfmt(fmt); - bprm->recursion_depth--; if (retval < 0 && !bprm->mm) { /* we got to flush_old_exec() and failed after it */ read_unlock(&binfmt_lock); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index c27c27300d95..e474127dd255 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -451,7 +451,9 @@ failed_out: /** * ext2_alloc_branch - allocate and set up a chain of blocks. * @inode: owner - * @num: depth of the chain (number of blocks to allocate) + * @indirect_blks: depth of the chain (number of blocks to allocate) + * @blks: number of allocated direct blocks + * @goal: preferred place for allocation * @offsets: offsets (in the blocks) to store the pointers to next. * @branch: place to store the chain in. * diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 0128010a0874..3988633789cb 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -192,17 +192,11 @@ static struct inode *ext2_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void ext2_i_callback(struct rcu_head *head) +static void ext2_free_in_core_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(ext2_inode_cachep, EXT2_I(inode)); } -static void ext2_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, ext2_i_callback); -} - static void init_once(void *foo) { struct ext2_inode_info *ei = (struct ext2_inode_info *) foo; @@ -351,7 +345,7 @@ static const struct quotactl_ops ext2_quotactl_ops = { static const struct super_operations ext2_sops = { .alloc_inode = ext2_alloc_inode, - .destroy_inode = ext2_destroy_inode, + .free_inode = ext2_free_in_core_inode, .write_inode = ext2_write_inode, .evict_inode = ext2_evict_inode, .put_super = ext2_put_super, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c18ab748d20d..1cb67859e051 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2041,7 +2041,6 @@ static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); desc.shash.tfm = sbi->s_chksum_driver; - desc.shash.flags = 0; *(u32 *)desc.ctx = crc; BUG_ON(crypto_shash_update(&desc.shash, address, length)); @@ -2304,23 +2303,47 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); #ifdef CONFIG_FS_ENCRYPTION +static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, + const struct fscrypt_name *src) +{ + memset(dst, 0, sizeof(*dst)); + + dst->usr_fname = src->usr_fname; + dst->disk_name = src->disk_name; + dst->hinfo.hash = src->hash; + dst->hinfo.minor_hash = src->minor_hash; + dst->crypto_buf = src->crypto_buf; +} + static inline int ext4_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct ext4_filename *fname) + const struct qstr *iname, + int lookup, + struct ext4_filename *fname) { struct fscrypt_name name; int err; - memset(fname, 0, sizeof(struct ext4_filename)); - err = fscrypt_setup_filename(dir, iname, lookup, &name); + if (err) + return err; - fname->usr_fname = name.usr_fname; - fname->disk_name = name.disk_name; - fname->hinfo.hash = name.hash; - fname->hinfo.minor_hash = name.minor_hash; - fname->crypto_buf = name.crypto_buf; - return err; + ext4_fname_from_fscrypt_name(fname, &name); + return 0; +} + +static inline int ext4_fname_prepare_lookup(struct inode *dir, + struct dentry *dentry, + struct ext4_filename *fname) +{ + struct fscrypt_name name; + int err; + + err = fscrypt_prepare_lookup(dir, dentry, &name); + if (err) + return err; + + ext4_fname_from_fscrypt_name(fname, &name); + return 0; } static inline void ext4_fname_free_filename(struct ext4_filename *fname) @@ -2334,19 +2357,27 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->usr_fname = NULL; fname->disk_name.name = NULL; } -#else +#else /* !CONFIG_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct ext4_filename *fname) + const struct qstr *iname, + int lookup, + struct ext4_filename *fname) { fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; return 0; } -static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } -#endif +static inline int ext4_fname_prepare_lookup(struct inode *dir, + struct dentry *dentry, + struct ext4_filename *fname) +{ + return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname); +} + +static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } +#endif /* !CONFIG_FS_ENCRYPTION */ /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ac7457fef9e6..cd01c4a67ffb 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1374,7 +1374,7 @@ static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, } /* - * ext4_find_entry() + * __ext4_find_entry() * * finds an entry in the specified directory with the wanted name. It * returns the cache buffer in which the entry was found, and the entry @@ -1384,39 +1384,32 @@ static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, * The returned buffer_head has ->b_count elevated. The caller is expected * to brelse() it when appropriate. */ -static struct buffer_head * ext4_find_entry (struct inode *dir, - const struct qstr *d_name, - struct ext4_dir_entry_2 **res_dir, - int *inlined) +static struct buffer_head *__ext4_find_entry(struct inode *dir, + struct ext4_filename *fname, + struct ext4_dir_entry_2 **res_dir, + int *inlined) { struct super_block *sb; struct buffer_head *bh_use[NAMEI_RA_SIZE]; struct buffer_head *bh, *ret = NULL; ext4_lblk_t start, block; - const u8 *name = d_name->name; + const u8 *name = fname->usr_fname->name; size_t ra_max = 0; /* Number of bh's in the readahead buffer, bh_use[] */ size_t ra_ptr = 0; /* Current index into readahead buffer */ ext4_lblk_t nblocks; int i, namelen, retval; - struct ext4_filename fname; *res_dir = NULL; sb = dir->i_sb; - namelen = d_name->len; + namelen = fname->usr_fname->len; if (namelen > EXT4_NAME_LEN) return NULL; - retval = ext4_fname_setup_filename(dir, d_name, 1, &fname); - if (retval == -ENOENT) - return NULL; - if (retval) - return ERR_PTR(retval); - if (ext4_has_inline_data(dir)) { int has_inline_data = 1; - ret = ext4_find_inline_entry(dir, &fname, res_dir, + ret = ext4_find_inline_entry(dir, fname, res_dir, &has_inline_data); if (has_inline_data) { if (inlined) @@ -1436,7 +1429,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, goto restart; } if (is_dx(dir)) { - ret = ext4_dx_find_entry(dir, &fname, res_dir); + ret = ext4_dx_find_entry(dir, fname, res_dir); /* * On success, or if the error was file not found, * return. Otherwise, fall back to doing a search the @@ -1500,7 +1493,7 @@ restart: goto cleanup_and_exit; } set_buffer_verified(bh); - i = search_dirblock(bh, dir, &fname, + i = search_dirblock(bh, dir, fname, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); if (i == 1) { EXT4_I(dir)->i_dir_start_lookup = block; @@ -1531,10 +1524,50 @@ cleanup_and_exit: /* Clean up the read-ahead blocks */ for (; ra_ptr < ra_max; ra_ptr++) brelse(bh_use[ra_ptr]); - ext4_fname_free_filename(&fname); return ret; } +static struct buffer_head *ext4_find_entry(struct inode *dir, + const struct qstr *d_name, + struct ext4_dir_entry_2 **res_dir, + int *inlined) +{ + int err; + struct ext4_filename fname; + struct buffer_head *bh; + + err = ext4_fname_setup_filename(dir, d_name, 1, &fname); + if (err == -ENOENT) + return NULL; + if (err) + return ERR_PTR(err); + + bh = __ext4_find_entry(dir, &fname, res_dir, inlined); + + ext4_fname_free_filename(&fname); + return bh; +} + +static struct buffer_head *ext4_lookup_entry(struct inode *dir, + struct dentry *dentry, + struct ext4_dir_entry_2 **res_dir) +{ + int err; + struct ext4_filename fname; + struct buffer_head *bh; + + err = ext4_fname_prepare_lookup(dir, dentry, &fname); + if (err == -ENOENT) + return NULL; + if (err) + return ERR_PTR(err); + + bh = __ext4_find_entry(dir, &fname, res_dir, NULL); + + ext4_fname_free_filename(&fname); + return bh; +} + static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir) @@ -1593,16 +1626,11 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi struct inode *inode; struct ext4_dir_entry_2 *de; struct buffer_head *bh; - int err; - - err = fscrypt_prepare_lookup(dir, dentry, flags); - if (err) - return ERR_PTR(err); if (dentry->d_name.len > EXT4_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); + bh = ext4_lookup_entry(dir, dentry, &de); if (IS_ERR(bh)) return ERR_CAST(bh); inode = NULL; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 3e9298e6a705..4690618a92e9 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -61,11 +61,10 @@ static void buffer_io_error(struct buffer_head *bh) static void ext4_finish_bio(struct bio *bio) { - int i; struct bio_vec *bvec; struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; #ifdef CONFIG_FS_ENCRYPTION struct page *data_page = NULL; diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 9386b0446afb..c916017db334 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -71,7 +71,6 @@ static inline bool ext4_bio_encrypted(struct bio *bio) static void mpage_end_io(struct bio *bio) { struct bio_vec *bv; - int i; struct bvec_iter_all iter_all; if (ext4_bio_encrypted(bio)) { @@ -82,7 +81,7 @@ static void mpage_end_io(struct bio *bio) return; } } - bio_for_each_segment_all(bv, bio, i, iter_all) { + bio_for_each_segment_all(bv, bio, iter_all) { struct page *page = bv->bv_page; if (!bio->bi_status) { @@ -245,7 +244,7 @@ int ext4_mpage_readpages(struct address_space *mapping, struct fscrypt_ctx *ctx = NULL; if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) { - ctx = fscrypt_get_ctx(inode, GFP_NOFS); + ctx = fscrypt_get_ctx(GFP_NOFS); if (IS_ERR(ctx)) goto set_error_page; } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 4d5c0fc9d23a..c0e9aef376a7 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1761,8 +1761,6 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, ext4_msg(sb, KERN_ERR, "filesystem too large to resize to %llu blocks safely", n_blocks_count); - if (sizeof(sector_t) < 8) - ext4_warning(sb, "CONFIG_LBDAF not enabled"); return -EINVAL; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 272e1881b5f8..4079605d437a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1111,9 +1111,9 @@ static int ext4_drop_inode(struct inode *inode) return drop; } -static void ext4_i_callback(struct rcu_head *head) +static void ext4_free_in_core_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); + fscrypt_free_inode(inode); kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } @@ -1128,7 +1128,6 @@ static void ext4_destroy_inode(struct inode *inode) true); dump_stack(); } - call_rcu(&inode->i_rcu, ext4_i_callback); } static void init_once(void *foo) @@ -1406,6 +1405,7 @@ static const struct quotactl_ops ext4_qctl_operations = { static const struct super_operations ext4_sops = { .alloc_inode = ext4_alloc_inode, + .free_inode = ext4_free_in_core_inode, .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, @@ -2740,13 +2740,9 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) loff_t res; loff_t upper_limit = MAX_LFS_FILESIZE; - /* small i_blocks in vfs inode? */ - if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) { - /* - * CONFIG_LBDAF is not enabled implies the inode - * i_block represent total blocks in 512 bytes - * 32 == size of vfs inode i_blocks * 8 - */ + BUILD_BUG_ON(sizeof(blkcnt_t) < sizeof(u64)); + + if (!has_huge_files) { upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ @@ -2787,11 +2783,11 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) * number of 512-byte sectors of the file. */ - if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) { + if (!has_huge_files) { /* - * !has_huge_files or CONFIG_LBDAF not enabled implies that - * the inode i_block field represents total file blocks in - * 2^32 512-byte sectors == size of vfs inode i_blocks * 8 + * !has_huge_files or implies that the inode i_block field + * represents total file blocks in 2^32 512-byte sectors == + * size of vfs inode i_blocks * 8 */ upper_limit = (1LL << 32) - 1; @@ -2940,18 +2936,6 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) ~EXT4_FEATURE_RO_COMPAT_SUPP)); return 0; } - /* - * Large file size enabled file system can only be mounted - * read-write on 32-bit systems if kernel is built with CONFIG_LBDAF - */ - if (ext4_has_feature_huge_file(sb)) { - if (sizeof(blkcnt_t) < sizeof(u64)) { - ext4_msg(sb, KERN_ERR, "Filesystem with huge files " - "cannot be mounted RDWR without " - "CONFIG_LBDAF"); - return 0; - } - } if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) { ext4_msg(sb, KERN_ERR, "Can't support bigalloc feature without " @@ -4168,8 +4152,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); - if (sizeof(sector_t) < 8) - ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); goto failed_mount; } diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 63e599524085..217b290ae3a5 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -285,7 +285,7 @@ static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { - switch(pa->e_tag) { + switch (pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; @@ -326,7 +326,7 @@ static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; - return not_equiv; + return not_equiv; } static int f2fs_acl_create(struct inode *dir, umode_t *mode, diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index a98e1b02279e..ed70b68b2b38 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -66,7 +66,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, .old_blkaddr = index, .new_blkaddr = index, .encrypted_page = NULL, - .is_meta = is_meta, + .is_por = !is_meta, }; int err; @@ -130,6 +130,30 @@ struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) return __get_meta_page(sbi, index, false); } +static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr, + int type) +{ + struct seg_entry *se; + unsigned int segno, offset; + bool exist; + + if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ) + return true; + + segno = GET_SEGNO(sbi, blkaddr); + offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + se = get_seg_entry(sbi, segno); + + exist = f2fs_test_bit(offset, se->cur_valid_map); + if (!exist && type == DATA_GENERIC_ENHANCE) { + f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " + "blkaddr:%u, sit bitmap:%d", blkaddr, exist); + set_sbi_flag(sbi, SBI_NEED_FSCK); + WARN_ON(1); + } + return exist; +} + bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { @@ -151,15 +175,22 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, return false; break; case META_POR: + if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || + blkaddr < MAIN_BLKADDR(sbi))) + return false; + break; case DATA_GENERIC: + case DATA_GENERIC_ENHANCE: + case DATA_GENERIC_ENHANCE_READ: if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || - blkaddr < MAIN_BLKADDR(sbi))) { - if (type == DATA_GENERIC) { - f2fs_msg(sbi->sb, KERN_WARNING, - "access invalid blkaddr:%u", blkaddr); - WARN_ON(1); - } + blkaddr < MAIN_BLKADDR(sbi))) { + f2fs_msg(sbi->sb, KERN_WARNING, + "access invalid blkaddr:%u", blkaddr); + set_sbi_flag(sbi, SBI_NEED_FSCK); + WARN_ON(1); return false; + } else { + return __is_bitmap_valid(sbi, blkaddr, type); } break; case META_GENERIC: @@ -189,7 +220,7 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, .op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD, .encrypted_page = NULL, .in_list = false, - .is_meta = (type != META_POR), + .is_por = (type == META_POR), }; struct blk_plug plug; @@ -644,6 +675,12 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return 0; + if (bdev_read_only(sbi->sb->s_bdev)) { + f2fs_msg(sbi->sb, KERN_INFO, "write access " + "unavailable, skipping orphan cleanup"); + return 0; + } + if (s_flags & SB_RDONLY) { f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); sbi->sb->s_flags &= ~SB_RDONLY; @@ -758,13 +795,27 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) } } +static __u32 f2fs_checkpoint_chksum(struct f2fs_sb_info *sbi, + struct f2fs_checkpoint *ckpt) +{ + unsigned int chksum_ofs = le32_to_cpu(ckpt->checksum_offset); + __u32 chksum; + + chksum = f2fs_crc32(sbi, ckpt, chksum_ofs); + if (chksum_ofs < CP_CHKSUM_OFFSET) { + chksum_ofs += sizeof(chksum); + chksum = f2fs_chksum(sbi, chksum, (__u8 *)ckpt + chksum_ofs, + F2FS_BLKSIZE - chksum_ofs); + } + return chksum; +} + static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, struct f2fs_checkpoint **cp_block, struct page **cp_page, unsigned long long *version) { - unsigned long blk_size = sbi->blocksize; size_t crc_offset = 0; - __u32 crc = 0; + __u32 crc; *cp_page = f2fs_get_meta_page(sbi, cp_addr); if (IS_ERR(*cp_page)) @@ -773,15 +824,27 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, *cp_block = (struct f2fs_checkpoint *)page_address(*cp_page); crc_offset = le32_to_cpu((*cp_block)->checksum_offset); - if (crc_offset > (blk_size - sizeof(__le32))) { + if (crc_offset < CP_MIN_CHKSUM_OFFSET || + crc_offset > CP_CHKSUM_OFFSET) { f2fs_put_page(*cp_page, 1); f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc_offset: %zu", crc_offset); return -EINVAL; } - crc = cur_cp_crc(*cp_block); - if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) { + if (__is_set_ckpt_flags(*cp_block, CP_LARGE_NAT_BITMAP_FLAG)) { + if (crc_offset != CP_MIN_CHKSUM_OFFSET) { + f2fs_put_page(*cp_page, 1); + f2fs_msg(sbi->sb, KERN_WARNING, + "layout of large_nat_bitmap is deprecated, " + "run fsck to repair, chksum_offset: %zu", + crc_offset); + return -EINVAL; + } + } + + crc = f2fs_checkpoint_chksum(sbi, *cp_block); + if (crc != cur_cp_crc(*cp_block)) { f2fs_put_page(*cp_page, 1); f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value"); return -EINVAL; @@ -1009,13 +1072,11 @@ retry: if (inode) { unsigned long cur_ino = inode->i_ino; - if (is_dir) - F2FS_I(inode)->cp_task = current; + F2FS_I(inode)->cp_task = current; filemap_fdatawrite(inode->i_mapping); - if (is_dir) - F2FS_I(inode)->cp_task = NULL; + F2FS_I(inode)->cp_task = NULL; iput(inode); /* We need to give cpu to another writers. */ @@ -1391,7 +1452,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP)); get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP)); - crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset)); + crc32 = f2fs_checkpoint_chksum(sbi, ckpt); *((__le32 *)((unsigned char *)ckpt + le32_to_cpu(ckpt->checksum_offset))) = cpu_to_le32(crc32); @@ -1475,7 +1536,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) clear_sbi_flag(sbi, SBI_IS_DIRTY); clear_sbi_flag(sbi, SBI_NEED_CP); clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + + spin_lock(&sbi->stat_lock); sbi->unusable_block_count = 0; + spin_unlock(&sbi->stat_lock); + __set_cp_next_pack(sbi); /* @@ -1500,6 +1565,9 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned long long ckpt_ver; int err = 0; + if (f2fs_readonly(sbi->sb) || f2fs_hw_is_readonly(sbi)) + return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { if (cpc->reason != CP_PAUSE) return 0; @@ -1516,10 +1584,6 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) err = -EIO; goto out; } - if (f2fs_readonly(sbi->sb)) { - err = -EROFS; - goto out; - } trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops"); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9727944139f2..eda4181d2092 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -86,10 +86,9 @@ static void __read_end_io(struct bio *bio) { struct page *page; struct bio_vec *bv; - int i; struct bvec_iter_all iter_all; - bio_for_each_segment_all(bv, bio, i, iter_all) { + bio_for_each_segment_all(bv, bio, iter_all) { page = bv->bv_page; /* PG_error was set if any post_read step failed */ @@ -164,7 +163,6 @@ static void f2fs_write_end_io(struct bio *bio) { struct f2fs_sb_info *sbi = bio->bi_private; struct bio_vec *bvec; - int i; struct bvec_iter_all iter_all; if (time_to_inject(sbi, FAULT_WRITE_IO)) { @@ -172,7 +170,7 @@ static void f2fs_write_end_io(struct bio *bio) bio->bi_status = BLK_STS_IOERR; } - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; enum count_type type = WB_DATA_TYPE(page); @@ -220,12 +218,14 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, struct block_device *bdev = sbi->sb->s_bdev; int i; - for (i = 0; i < sbi->s_ndevs; i++) { - if (FDEV(i).start_blk <= blk_addr && - FDEV(i).end_blk >= blk_addr) { - blk_addr -= FDEV(i).start_blk; - bdev = FDEV(i).bdev; - break; + if (f2fs_is_multi_device(sbi)) { + for (i = 0; i < sbi->s_ndevs; i++) { + if (FDEV(i).start_blk <= blk_addr && + FDEV(i).end_blk >= blk_addr) { + blk_addr -= FDEV(i).start_blk; + bdev = FDEV(i).bdev; + break; + } } } if (bio) { @@ -239,6 +239,9 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) { int i; + if (!f2fs_is_multi_device(sbi)) + return 0; + for (i = 0; i < sbi->s_ndevs; i++) if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr) return i; @@ -349,7 +352,6 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode, { struct bio_vec *bvec; struct page *target; - int i; struct bvec_iter_all iter_all; if (!io->bio) @@ -358,7 +360,7 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode, if (!inode && !page && !ino) return true; - bio_for_each_segment_all(bvec, io->bio, i, iter_all) { + bio_for_each_segment_all(bvec, io->bio, iter_all) { if (bvec->bv_page->mapping) target = bvec->bv_page; @@ -423,7 +425,7 @@ static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type) { - __submit_merged_write_cond(sbi, NULL, 0, 0, type, true); + __submit_merged_write_cond(sbi, NULL, NULL, 0, type, true); } void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, @@ -451,7 +453,8 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) fio->encrypted_page : fio->page; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, - __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) + fio->is_por ? META_POR : (__is_meta_io(fio) ? + META_GENERIC : DATA_GENERIC_ENHANCE))) return -EFAULT; trace_f2fs_submit_page_bio(page, fio); @@ -501,9 +504,7 @@ next: spin_unlock(&io->io_lock); } - if (__is_valid_data_blkaddr(fio->old_blkaddr)) - verify_block_addr(fio, fio->old_blkaddr); - verify_block_addr(fio, fio->new_blkaddr); + verify_fio_blkaddr(fio); bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; @@ -560,9 +561,6 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, struct bio_post_read_ctx *ctx; unsigned int post_read_steps = 0; - if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) - return ERR_PTR(-EFAULT); - bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false); if (!bio) return ERR_PTR(-ENOMEM); @@ -590,8 +588,10 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, static int f2fs_submit_page_read(struct inode *inode, struct page *page, block_t blkaddr) { - struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct bio *bio; + bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0); if (IS_ERR(bio)) return PTR_ERR(bio); @@ -603,8 +603,8 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, return -EFAULT; } ClearPageError(page); - inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); - __submit_bio(F2FS_I_SB(inode), bio, DATA); + inc_page_count(sbi, F2FS_RD_DATA); + __submit_bio(sbi, bio, DATA); return 0; } @@ -732,6 +732,11 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, if (f2fs_lookup_extent_cache(inode, index, &ei)) { dn.data_blkaddr = ei.blk + index - ei.fofs; + if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr, + DATA_GENERIC_ENHANCE_READ)) { + err = -EFAULT; + goto put_err; + } goto got_it; } @@ -745,6 +750,13 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, err = -ENOENT; goto put_err; } + if (dn.data_blkaddr != NEW_ADDR && + !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), + dn.data_blkaddr, + DATA_GENERIC_ENHANCE)) { + err = -EFAULT; + goto put_err; + } got_it: if (PageUptodate(page)) { unlock_page(page); @@ -1087,12 +1099,12 @@ next_block: blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); if (__is_valid_data_blkaddr(blkaddr) && - !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) { + !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) { err = -EFAULT; goto sync_out; } - if (is_valid_data_blkaddr(sbi, blkaddr)) { + if (__is_valid_data_blkaddr(blkaddr)) { /* use out-place-update for driect IO under LFS mode */ if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO && map->m_may_create) { @@ -1502,6 +1514,118 @@ out: return ret; } +static int f2fs_read_single_page(struct inode *inode, struct page *page, + unsigned nr_pages, + struct f2fs_map_blocks *map, + struct bio **bio_ret, + sector_t *last_block_in_bio, + bool is_readahead) +{ + struct bio *bio = *bio_ret; + const unsigned blkbits = inode->i_blkbits; + const unsigned blocksize = 1 << blkbits; + sector_t block_in_file; + sector_t last_block; + sector_t last_block_in_file; + sector_t block_nr; + int ret = 0; + + block_in_file = (sector_t)page->index; + last_block = block_in_file + nr_pages; + last_block_in_file = (i_size_read(inode) + blocksize - 1) >> + blkbits; + if (last_block > last_block_in_file) + last_block = last_block_in_file; + + /* just zeroing out page which is beyond EOF */ + if (block_in_file >= last_block) + goto zero_out; + /* + * Map blocks using the previous result first. + */ + if ((map->m_flags & F2FS_MAP_MAPPED) && + block_in_file > map->m_lblk && + block_in_file < (map->m_lblk + map->m_len)) + goto got_it; + + /* + * Then do more f2fs_map_blocks() calls until we are + * done with this page. + */ + map->m_lblk = block_in_file; + map->m_len = last_block - block_in_file; + + ret = f2fs_map_blocks(inode, map, 0, F2FS_GET_BLOCK_DEFAULT); + if (ret) + goto out; +got_it: + if ((map->m_flags & F2FS_MAP_MAPPED)) { + block_nr = map->m_pblk + block_in_file - map->m_lblk; + SetPageMappedToDisk(page); + + if (!PageUptodate(page) && !cleancache_get_page(page)) { + SetPageUptodate(page); + goto confused; + } + + if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, + DATA_GENERIC_ENHANCE_READ)) { + ret = -EFAULT; + goto out; + } + } else { +zero_out: + zero_user_segment(page, 0, PAGE_SIZE); + if (!PageUptodate(page)) + SetPageUptodate(page); + unlock_page(page); + goto out; + } + + /* + * This page will go to BIO. Do we need to send this + * BIO off first? + */ + if (bio && (*last_block_in_bio != block_nr - 1 || + !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) { +submit_and_realloc: + __submit_bio(F2FS_I_SB(inode), bio, DATA); + bio = NULL; + } + if (bio == NULL) { + bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, + is_readahead ? REQ_RAHEAD : 0); + if (IS_ERR(bio)) { + ret = PTR_ERR(bio); + bio = NULL; + goto out; + } + } + + /* + * If the page is under writeback, we need to wait for + * its completion to see the correct decrypted data. + */ + f2fs_wait_on_block_writeback(inode, block_nr); + + if (bio_add_page(bio, page, blocksize, 0) < blocksize) + goto submit_and_realloc; + + inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); + ClearPageError(page); + *last_block_in_bio = block_nr; + goto out; +confused: + if (bio) { + __submit_bio(F2FS_I_SB(inode), bio, DATA); + bio = NULL; + } + unlock_page(page); +out: + *bio_ret = bio; + return ret; +} + /* * This function was originally taken from fs/mpage.c, and customized for f2fs. * Major change was from block_size == page_size in f2fs by default. @@ -1518,13 +1642,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping, struct bio *bio = NULL; sector_t last_block_in_bio = 0; struct inode *inode = mapping->host; - const unsigned blkbits = inode->i_blkbits; - const unsigned blocksize = 1 << blkbits; - sector_t block_in_file; - sector_t last_block; - sector_t last_block_in_file; - sector_t block_nr; struct f2fs_map_blocks map; + int ret = 0; map.m_pblk = 0; map.m_lblk = 0; @@ -1547,98 +1666,13 @@ static int f2fs_mpage_readpages(struct address_space *mapping, goto next_page; } - block_in_file = (sector_t)page->index; - last_block = block_in_file + nr_pages; - last_block_in_file = (i_size_read(inode) + blocksize - 1) >> - blkbits; - if (last_block > last_block_in_file) - last_block = last_block_in_file; - - /* just zeroing out page which is beyond EOF */ - if (block_in_file >= last_block) - goto zero_out; - /* - * Map blocks using the previous result first. - */ - if ((map.m_flags & F2FS_MAP_MAPPED) && - block_in_file > map.m_lblk && - block_in_file < (map.m_lblk + map.m_len)) - goto got_it; - - /* - * Then do more f2fs_map_blocks() calls until we are - * done with this page. - */ - map.m_lblk = block_in_file; - map.m_len = last_block - block_in_file; - - if (f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT)) - goto set_error_page; -got_it: - if ((map.m_flags & F2FS_MAP_MAPPED)) { - block_nr = map.m_pblk + block_in_file - map.m_lblk; - SetPageMappedToDisk(page); - - if (!PageUptodate(page) && !cleancache_get_page(page)) { - SetPageUptodate(page); - goto confused; - } - - if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, - DATA_GENERIC)) - goto set_error_page; - } else { -zero_out: + ret = f2fs_read_single_page(inode, page, nr_pages, &map, &bio, + &last_block_in_bio, is_readahead); + if (ret) { + SetPageError(page); zero_user_segment(page, 0, PAGE_SIZE); - if (!PageUptodate(page)) - SetPageUptodate(page); unlock_page(page); - goto next_page; - } - - /* - * This page will go to BIO. Do we need to send this - * BIO off first? - */ - if (bio && (last_block_in_bio != block_nr - 1 || - !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) { -submit_and_realloc: - __submit_bio(F2FS_I_SB(inode), bio, DATA); - bio = NULL; - } - if (bio == NULL) { - bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, - is_readahead ? REQ_RAHEAD : 0); - if (IS_ERR(bio)) { - bio = NULL; - goto set_error_page; - } - } - - /* - * If the page is under writeback, we need to wait for - * its completion to see the correct decrypted data. - */ - f2fs_wait_on_block_writeback(inode, block_nr); - - if (bio_add_page(bio, page, blocksize, 0) < blocksize) - goto submit_and_realloc; - - inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); - ClearPageError(page); - last_block_in_bio = block_nr; - goto next_page; -set_error_page: - SetPageError(page); - zero_user_segment(page, 0, PAGE_SIZE); - unlock_page(page); - goto next_page; -confused: - if (bio) { - __submit_bio(F2FS_I_SB(inode), bio, DATA); - bio = NULL; } - unlock_page(page); next_page: if (pages) put_page(page); @@ -1646,7 +1680,7 @@ next_page: BUG_ON(pages && !list_empty(pages)); if (bio) __submit_bio(F2FS_I_SB(inode), bio, DATA); - return 0; + return pages ? 0 : ret; } static int f2fs_read_data_page(struct file *file, struct page *page) @@ -1816,7 +1850,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) fio->old_blkaddr = ei.blk + page->index - ei.fofs; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, - DATA_GENERIC)) + DATA_GENERIC_ENHANCE)) return -EFAULT; ipu_force = true; @@ -1843,7 +1877,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) got_it: if (__is_valid_data_blkaddr(fio->old_blkaddr) && !f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, - DATA_GENERIC)) { + DATA_GENERIC_ENHANCE)) { err = -EFAULT; goto out_writepage; } @@ -1851,7 +1885,8 @@ got_it: * If current allocation needs SSR, * it had better in-place writes for updated data. */ - if (ipu_force || (is_valid_data_blkaddr(fio->sbi, fio->old_blkaddr) && + if (ipu_force || + (__is_valid_data_blkaddr(fio->old_blkaddr) && need_inplace_update(fio))) { err = encrypt_one_page(fio); if (err) @@ -1869,9 +1904,10 @@ got_it: true); if (PageWriteback(page)) end_page_writeback(page); + } else { + set_inode_flag(inode, FI_UPDATE_WRITE); } trace_f2fs_do_write_data_page(fio->page, IPU); - set_inode_flag(inode, FI_UPDATE_WRITE); return err; } @@ -2033,7 +2069,8 @@ out: } unlock_page(page); - if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode)) + if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) && + !F2FS_I(inode)->cp_task) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { @@ -2494,6 +2531,11 @@ repeat: zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); } else { + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE_READ)) { + err = -EFAULT; + goto fail; + } err = f2fs_submit_page_read(inode, page, blkaddr); if (err) goto fail; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 87f75ebd2fd6..06b89a9862ab 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -210,7 +210,14 @@ enum { META_SSA, META_MAX, META_POR, - DATA_GENERIC, + DATA_GENERIC, /* check range only */ + DATA_GENERIC_ENHANCE, /* strong check on range and segment bitmap */ + DATA_GENERIC_ENHANCE_READ, /* + * strong check on range and segment + * bitmap but no warning due to race + * condition of read on truncated area + * by extent_cache + */ META_GENERIC, }; @@ -1041,7 +1048,7 @@ struct f2fs_io_info { bool submitted; /* indicate IO submission */ int need_lock; /* indicate we need to lock cp_rwsem */ bool in_list; /* indicate fio is in io_list */ - bool is_meta; /* indicate borrow meta inode mapping or not */ + bool is_por; /* indicate IO is from recovery or not */ bool retry; /* need to reallocate block address */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ @@ -1068,8 +1075,8 @@ struct f2fs_dev_info { block_t start_blk; block_t end_blk; #ifdef CONFIG_BLK_DEV_ZONED - unsigned int nr_blkz; /* Total number of zones */ - u8 *blkz_type; /* Array of zones type */ + unsigned int nr_blkz; /* Total number of zones */ + unsigned long *blkz_seq; /* Bitmap indicating sequential zones */ #endif }; @@ -1338,7 +1345,7 @@ struct f2fs_private_dio { #ifdef CONFIG_F2FS_FAULT_INJECTION #define f2fs_show_injection_info(type) \ - printk_ratelimited("%sF2FS-fs : inject %s in %s of %pF\n", \ + printk_ratelimited("%sF2FS-fs : inject %s in %s of %pS\n", \ KERN_INFO, f2fs_fault_name[type], \ __func__, __builtin_return_address(0)) static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) @@ -1366,6 +1373,17 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) } #endif +/* + * Test if the mounted volume is a multi-device volume. + * - For a single regular disk volume, sbi->s_ndevs is 0. + * - For a single zoned disk volume, sbi->s_ndevs is 1. + * - For a multi-device volume, sbi->s_ndevs is always 2 or more. + */ +static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) +{ + return sbi->s_ndevs > 1; +} + /* For write statistics. Suppose sector size is 512 bytes, * and the return value is in kbytes. s is of struct f2fs_sb_info. */ @@ -1422,7 +1440,6 @@ static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc, BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx)); desc.shash.tfm = sbi->s_chksum_driver; - desc.shash.flags = 0; *(u32 *)desc.ctx = crc; err = crypto_shash_update(&desc.shash, address, length); @@ -1778,6 +1795,7 @@ enospc: return -ENOSPC; } +void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, block_t count) @@ -1786,13 +1804,21 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); - f2fs_bug_on(sbi, inode->i_blocks < sectors); sbi->total_valid_block_count -= (block_t)count; if (sbi->reserved_blocks && sbi->current_reserved_blocks < sbi->reserved_blocks) sbi->current_reserved_blocks = min(sbi->reserved_blocks, sbi->current_reserved_blocks + count); spin_unlock(&sbi->stat_lock); + if (unlikely(inode->i_blocks < sectors)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu", + inode->i_ino, + (unsigned long long)inode->i_blocks, + (unsigned long long)sectors); + set_sbi_flag(sbi, SBI_NEED_FSCK); + return; + } f2fs_i_blocks_write(inode, count, false, true); } @@ -1890,7 +1916,11 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) { offset = (flag == SIT_BITMAP) ? le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0; - return &ckpt->sit_nat_version_bitmap + offset; + /* + * if large_nat_bitmap feature is enabled, leave checksum + * protection for all nat/sit bitmaps. + */ + return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32); } if (__cp_payload(sbi) > 0) { @@ -2009,7 +2039,6 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, !sbi->total_valid_block_count); f2fs_bug_on(sbi, !sbi->total_valid_node_count); - f2fs_bug_on(sbi, !is_inode && !inode->i_blocks); sbi->total_valid_node_count--; sbi->total_valid_block_count--; @@ -2019,10 +2048,19 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, spin_unlock(&sbi->stat_lock); - if (is_inode) + if (is_inode) { dquot_free_inode(inode); - else + } else { + if (unlikely(inode->i_blocks == 0)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent i_blocks, ino:%lu, iblocks:%llu", + inode->i_ino, + (unsigned long long)inode->i_blocks); + set_sbi_flag(sbi, SBI_NEED_FSCK); + return; + } f2fs_i_blocks_write(inode, 1, false, true); + } } static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi) @@ -2546,7 +2584,14 @@ static inline int f2fs_has_inline_xattr(struct inode *inode) static inline unsigned int addrs_per_inode(struct inode *inode) { - return CUR_ADDRS_PER_INODE(inode) - get_inline_xattr_addrs(inode); + unsigned int addrs = CUR_ADDRS_PER_INODE(inode) - + get_inline_xattr_addrs(inode); + return ALIGN_DOWN(addrs, 1); +} + +static inline unsigned int addrs_per_block(struct inode *inode) +{ + return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, 1); } static inline void *inline_xattr_addr(struct inode *inode, struct page *page) @@ -2559,7 +2604,9 @@ static inline void *inline_xattr_addr(struct inode *inode, struct page *page) static inline int inline_xattr_size(struct inode *inode) { - return get_inline_xattr_addrs(inode) * sizeof(__le32); + if (f2fs_has_inline_xattr(inode)) + return get_inline_xattr_addrs(inode) * sizeof(__le32); + return 0; } static inline int f2fs_has_inline_data(struct inode *inode) @@ -2801,12 +2848,10 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, #define __is_large_section(sbi) ((sbi)->segs_per_sec > 1) -#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META && \ - (!is_read_io((fio)->op) || (fio)->is_meta)) +#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META) bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); -void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); static inline void verify_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { @@ -2825,15 +2870,6 @@ static inline bool __is_valid_data_blkaddr(block_t blkaddr) return true; } -static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, - block_t blkaddr) -{ - if (!__is_valid_data_blkaddr(blkaddr)) - return false; - verify_blkaddr(sbi, blkaddr, DATA_GENERIC); - return true; -} - static inline void f2fs_set_page_private(struct page *page, unsigned long data) { @@ -3531,16 +3567,12 @@ F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); #ifdef CONFIG_BLK_DEV_ZONED -static inline int get_blkz_type(struct f2fs_sb_info *sbi, - struct block_device *bdev, block_t blkaddr) +static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi, + block_t blkaddr) { unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz; - int i; - for (i = 0; i < sbi->s_ndevs; i++) - if (FDEV(i).bdev == bdev) - return FDEV(i).blkz_type[zno]; - return -EINVAL; + return test_bit(zno, FDEV(devi).blkz_seq); } #endif @@ -3549,9 +3581,23 @@ static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) return f2fs_sb_has_blkzoned(sbi); } +static inline bool f2fs_bdev_support_discard(struct block_device *bdev) +{ + return blk_queue_discard(bdev_get_queue(bdev)) || + bdev_is_zoned(bdev); +} + static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) { - return blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev)); + int i; + + if (!f2fs_is_multi_device(sbi)) + return f2fs_bdev_support_discard(sbi->sb->s_bdev); + + for (i = 0; i < sbi->s_ndevs; i++) + if (f2fs_bdev_support_discard(FDEV(i).bdev)) + return true; + return false; } static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) @@ -3560,6 +3606,20 @@ static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) f2fs_hw_should_discard(sbi); } +static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi) +{ + int i; + + if (!f2fs_is_multi_device(sbi)) + return bdev_read_only(sbi->sb->s_bdev); + + for (i = 0; i < sbi->s_ndevs; i++) + if (bdev_read_only(FDEV(i).bdev)) + return true; + return false; +} + + static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) { clear_opt(sbi, ADAPTIVE); @@ -3615,7 +3675,7 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, if (f2fs_post_read_required(inode)) return true; - if (sbi->s_ndevs) + if (f2fs_is_multi_device(sbi)) return true; /* * for blkzoned device, fallback direct IO to buffered IO, so @@ -3652,4 +3712,4 @@ static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) return false; } -#endif +#endif /* _LINUX_F2FS_H */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5742ab8b57dc..45b45f37d347 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -39,6 +39,8 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) ret = filemap_fault(vmf); up_read(&F2FS_I(inode)->i_mmap_sem); + trace_f2fs_filemap_fault(inode, vmf->pgoff, (unsigned long)ret); + return ret; } @@ -356,7 +358,7 @@ static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr, switch (whence) { case SEEK_DATA: if ((blkaddr == NEW_ADDR && dirty == pgofs) || - is_valid_data_blkaddr(sbi, blkaddr)) + __is_valid_data_blkaddr(blkaddr)) return true; break; case SEEK_HOLE: @@ -422,7 +424,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), - blkaddr, DATA_GENERIC)) { + blkaddr, DATA_GENERIC_ENHANCE)) { f2fs_put_dnode(&dn); goto fail; } @@ -523,7 +525,8 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) f2fs_set_data_blkaddr(dn); if (__is_valid_data_blkaddr(blkaddr) && - !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) + !f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE)) continue; f2fs_invalidate_blocks(sbi, blkaddr); @@ -552,7 +555,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) void f2fs_truncate_data_blocks(struct dnode_of_data *dn) { - f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); + f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode)); } static int truncate_partial_data_page(struct inode *inode, u64 from, @@ -1006,7 +1009,8 @@ next_dnode: } else if (ret == -ENOENT) { if (dn.max_level == 0) return -ENOENT; - done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len); + done = min((pgoff_t)ADDRS_PER_BLOCK(inode) - dn.ofs_in_node, + len); blkaddr += done; do_replace += done; goto next; @@ -1017,6 +1021,14 @@ next_dnode: for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { *blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); + + if (__is_valid_data_blkaddr(*blkaddr) && + !f2fs_is_valid_blkaddr(sbi, *blkaddr, + DATA_GENERIC_ENHANCE)) { + f2fs_put_dnode(&dn); + return -EFAULT; + } + if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) { if (test_opt(sbi, LFS)) { @@ -1157,7 +1169,7 @@ static int __exchange_data_block(struct inode *src_inode, int ret; while (len) { - olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len); + olen = min((pgoff_t)4 * ADDRS_PER_BLOCK(src_inode), len); src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode), array_size(olen, sizeof(block_t)), @@ -2573,10 +2585,10 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) sizeof(range))) return -EFAULT; - if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num || + if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || __is_large_section(sbi)) { f2fs_msg(sbi->sb, KERN_WARNING, - "Can't flush %u in %d for segs_per_sec %u != 1\n", + "Can't flush %u in %d for segs_per_sec %u != 1", range.dev_num, sbi->s_ndevs, sbi->segs_per_sec); return -EINVAL; @@ -2858,7 +2870,7 @@ int f2fs_pin_file_control(struct inode *inode, bool inc) if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) { f2fs_msg(sbi->sb, KERN_WARNING, - "%s: Enable GC = ino %lx after %x GC trials\n", + "%s: Enable GC = ino %lx after %x GC trials", __func__, inode->i_ino, fi->i_gc_failures[GC_FAILURE_PIN]); clear_inode_flag(inode, FI_PIN_FILE); @@ -3035,15 +3047,21 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(file); ssize_t ret; - if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) - return -EIO; + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { + ret = -EIO; + goto out; + } - if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) - return -EINVAL; + if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) { + ret = -EINVAL; + goto out; + } if (!inode_trylock(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) - return -EAGAIN; + if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; + } inode_lock(inode); } @@ -3056,19 +3074,16 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iov_iter_fault_in_readable(from, iov_iter_count(from))) set_inode_flag(inode, FI_NO_PREALLOC); - if ((iocb->ki_flags & IOCB_NOWAIT) && - (iocb->ki_flags & IOCB_DIRECT)) { - if (!f2fs_overwrite_io(inode, iocb->ki_pos, + if ((iocb->ki_flags & IOCB_NOWAIT)) { + if (!f2fs_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)) || - f2fs_has_inline_data(inode) || - f2fs_force_buffered_io(inode, - iocb, from)) { - clear_inode_flag(inode, - FI_NO_PREALLOC); - inode_unlock(inode); - return -EAGAIN; - } - + f2fs_has_inline_data(inode) || + f2fs_force_buffered_io(inode, iocb, from)) { + clear_inode_flag(inode, FI_NO_PREALLOC); + inode_unlock(inode); + ret = -EAGAIN; + goto out; + } } else { preallocated = true; target_size = iocb->ki_pos + iov_iter_count(from); @@ -3077,7 +3092,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (err) { clear_inode_flag(inode, FI_NO_PREALLOC); inode_unlock(inode); - return err; + ret = err; + goto out; } } ret = __generic_file_write_iter(iocb, from); @@ -3091,7 +3107,9 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret); } inode_unlock(inode); - +out: + trace_f2fs_file_write_iter(inode, iocb->ki_pos, + iov_iter_count(from), ret); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 195cf0f9d9ef..963fb4571fd9 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -591,7 +591,7 @@ block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode) int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1); bidx = node_ofs - 5 - dec; } - return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode); + return bidx * ADDRS_PER_BLOCK(inode) + ADDRS_PER_INODE(inode); } static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, @@ -656,6 +656,11 @@ static int ra_data_block(struct inode *inode, pgoff_t index) if (f2fs_lookup_extent_cache(inode, index, &ei)) { dn.data_blkaddr = ei.blk + index - ei.fofs; + if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, + DATA_GENERIC_ENHANCE_READ))) { + err = -EFAULT; + goto put_page; + } goto got_it; } @@ -665,8 +670,12 @@ static int ra_data_block(struct inode *inode, pgoff_t index) goto put_page; f2fs_put_dnode(&dn); + if (!__is_valid_data_blkaddr(dn.data_blkaddr)) { + err = -ENOENT; + goto put_page; + } if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, - DATA_GENERIC))) { + DATA_GENERIC_ENHANCE))) { err = -EFAULT; goto put_page; } @@ -1175,6 +1184,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, "type [%d, %d] in SSA and SIT", segno, type, GET_SUM_TYPE((&sum->footer))); set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_stop_checkpoint(sbi, false); goto skip; } @@ -1346,7 +1356,7 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES; /* give warm/cold data area from slower device */ - if (sbi->s_ndevs && !__is_large_section(sbi)) + if (f2fs_is_multi_device(sbi) && !__is_large_section(sbi)) SIT_I(sbi)->last_victim[ALLOC_NEXT] = GET_SEGNO(sbi, FDEV(0).end_blk) + 1; } diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index bb6a152310ef..404d2462a0fe 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -420,6 +420,14 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); + /* + * should retrieve reserved space which was used to keep + * inline_dentry's structure for backward compatibility. + */ + if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) && + !f2fs_has_inline_xattr(dir)) + F2FS_I(dir)->i_inline_xattr_size = 0; + f2fs_i_depth_write(dir, 1); if (i_size_read(dir) < PAGE_SIZE) f2fs_i_size_write(dir, PAGE_SIZE); @@ -501,6 +509,15 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); + + /* + * should retrieve reserved space which was used to keep + * inline_dentry's structure for backward compatibility. + */ + if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) && + !f2fs_has_inline_xattr(dir)) + F2FS_I(dir)->i_inline_xattr_size = 0; + kvfree(backup_dentry); return 0; recover: diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index e7f2e8759315..ccb02226dd2c 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -73,7 +73,7 @@ static int __written_first_block(struct f2fs_sb_info *sbi, if (!__is_valid_data_blkaddr(addr)) return 1; - if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC)) + if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE)) return -EFAULT; return 0; } @@ -177,8 +177,8 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page) if (provided != calculated) f2fs_msg(sbi->sb, KERN_WARNING, - "checksum invalid, ino = %x, %x vs. %x", - ino_of_node(page), provided, calculated); + "checksum invalid, nid = %lu, ino_of_node = %x, %x vs. %x", + page->index, ino_of_node(page), provided, calculated); return provided == calculated; } @@ -267,9 +267,10 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest; if (ei->len && - (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC) || + (!f2fs_is_valid_blkaddr(sbi, ei->blk, + DATA_GENERIC_ENHANCE) || !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1, - DATA_GENERIC))) { + DATA_GENERIC_ENHANCE))) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_msg(sbi->sb, KERN_WARNING, "%s: inode (ino=%lx) extent info [%u, %u, %u] " @@ -488,6 +489,7 @@ make_now: return inode; bad_inode: + f2fs_inode_synced(inode); iget_failed(inode); trace_f2fs_iget_exit(inode, ret); return ERR_PTR(ret); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index f5e34e467003..0f77f9242751 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -143,7 +143,7 @@ fail_drop: return ERR_PTR(err); } -static int is_extension_exist(const unsigned char *s, const char *sub) +static inline int is_extension_exist(const unsigned char *s, const char *sub) { size_t slen = strlen(s); size_t sublen = strlen(sub); @@ -436,19 +436,23 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, nid_t ino = -1; int err = 0; unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir)); + struct fscrypt_name fname; trace_f2fs_lookup_start(dir, dentry, flags); - err = fscrypt_prepare_lookup(dir, dentry, flags); - if (err) - goto out; - if (dentry->d_name.len > F2FS_NAME_LEN) { err = -ENAMETOOLONG; goto out; } - de = f2fs_find_entry(dir, &dentry->d_name, &page); + err = fscrypt_prepare_lookup(dir, dentry, &fname); + if (err == -ENOENT) + goto out_splice; + if (err) + goto out; + de = __f2fs_find_entry(dir, &fname, &page); + fscrypt_free_filename(&fname); + if (!de) { if (IS_ERR(page)) { err = PTR_ERR(page); @@ -488,8 +492,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, } out_splice: new = d_splice_alias(inode, dentry); - if (IS_ERR(new)) - err = PTR_ERR(new); + err = PTR_ERR_OR_ZERO(new); trace_f2fs_lookup_end(dir, dentry, ino, err); return new; out_iput: diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3f99ab288695..18a038a2a9fa 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -454,7 +454,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, new_blkaddr == NULL_ADDR); f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR && new_blkaddr == NEW_ADDR); - f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) && + f2fs_bug_on(sbi, __is_valid_data_blkaddr(nat_get_blkaddr(e)) && new_blkaddr == NEW_ADDR); /* increment version no as node is removed */ @@ -465,7 +465,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, /* change address */ nat_set_blkaddr(e, new_blkaddr); - if (!is_valid_data_blkaddr(sbi, new_blkaddr)) + if (!__is_valid_data_blkaddr(new_blkaddr)) set_nat_flag(e, IS_CHECKPOINTED, false); __set_nat_cache_dirty(nm_i, e); @@ -526,6 +526,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct f2fs_nat_entry ne; struct nat_entry *e; pgoff_t index; + block_t blkaddr; int i; ni->nid = nid; @@ -569,6 +570,11 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: + blkaddr = le32_to_cpu(ne.block_addr); + if (__is_valid_data_blkaddr(blkaddr) && + !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) + return -EFAULT; + /* cache nat entry */ cache_nat_entry(sbi, nid, &ne); return 0; @@ -600,9 +606,9 @@ static void f2fs_ra_node_pages(struct page *parent, int start, int n) pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) { const long direct_index = ADDRS_PER_INODE(dn->inode); - const long direct_blks = ADDRS_PER_BLOCK; - const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; - unsigned int skipped_unit = ADDRS_PER_BLOCK; + const long direct_blks = ADDRS_PER_BLOCK(dn->inode); + const long indirect_blks = ADDRS_PER_BLOCK(dn->inode) * NIDS_PER_BLOCK; + unsigned int skipped_unit = ADDRS_PER_BLOCK(dn->inode); int cur_level = dn->cur_level; int max_level = dn->max_level; pgoff_t base = 0; @@ -616,8 +622,10 @@ pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) switch (dn->max_level) { case 3: base += 2 * indirect_blks; + /* fall through */ case 2: base += 2 * direct_blks; + /* fall through */ case 1: base += direct_index; break; @@ -636,9 +644,9 @@ static int get_node_path(struct inode *inode, long block, int offset[4], unsigned int noffset[4]) { const long direct_index = ADDRS_PER_INODE(inode); - const long direct_blks = ADDRS_PER_BLOCK; + const long direct_blks = ADDRS_PER_BLOCK(inode); const long dptrs_per_blk = NIDS_PER_BLOCK; - const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; + const long indirect_blks = ADDRS_PER_BLOCK(inode) * NIDS_PER_BLOCK; const long dindirect_blks = indirect_blks * NIDS_PER_BLOCK; int n = 0; int level = 0; @@ -1179,8 +1187,14 @@ int f2fs_remove_inode_page(struct inode *inode) f2fs_put_dnode(&dn); return -EIO; } - f2fs_bug_on(F2FS_I_SB(inode), - inode->i_blocks != 0 && inode->i_blocks != 8); + + if (unlikely(inode->i_blocks != 0 && inode->i_blocks != 8)) { + f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, + "Inconsistent i_blocks, ino:%lu, iblocks:%llu", + inode->i_ino, + (unsigned long long)inode->i_blocks); + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); + } /* will put inode & node pages */ err = truncate_node(&dn); @@ -1275,9 +1289,10 @@ static int read_node_page(struct page *page, int op_flags) int err; if (PageUptodate(page)) { -#ifdef CONFIG_F2FS_CHECK_FS - f2fs_bug_on(sbi, !f2fs_inode_chksum_verify(sbi, page)); -#endif + if (!f2fs_inode_chksum_verify(sbi, page)) { + ClearPageUptodate(page); + return -EBADMSG; + } return LOCKED_PAGE; } @@ -1541,7 +1556,8 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, } if (__is_valid_data_blkaddr(ni.blk_addr) && - !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) { + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, + DATA_GENERIC_ENHANCE)) { up_read(&sbi->node_write); goto redirty_out; } @@ -2076,6 +2092,9 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, if (unlikely(nid == 0)) return false; + if (unlikely(f2fs_check_nid_range(sbi, nid))) + return false; + i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); i->nid = nid; i->state = FREE_NID; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index e3883db868d8..e04f82b3f4fc 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -325,8 +325,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, break; } - if (!is_recoverable_dnode(page)) + if (!is_recoverable_dnode(page)) { + f2fs_put_page(page, 1); break; + } if (!is_fsync_dnode(page)) goto next; @@ -338,8 +340,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, if (!check_only && IS_INODE(page) && is_dent_dnode(page)) { err = f2fs_recover_inode_page(sbi, page); - if (err) + if (err) { + f2fs_put_page(page, 1); break; + } quota_inode = true; } @@ -355,6 +359,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, err = 0; goto next; } + f2fs_put_page(page, 1); break; } } @@ -370,6 +375,7 @@ next: "%s: detect looped node chain, " "blkaddr:%u, next:%u", __func__, blkaddr, next_blkaddr_of_node(page)); + f2fs_put_page(page, 1); err = -EINVAL; break; } @@ -380,7 +386,6 @@ next: f2fs_ra_meta_pages_cond(sbi, blkaddr); } - f2fs_put_page(page, 1); return err; } @@ -546,7 +551,15 @@ retry_dn: goto err; f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); - f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page)); + + if (ofs_of_node(dn.node_page) != ofs_of_node(page)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u", + inode->i_ino, ofs_of_node(dn.node_page), + ofs_of_node(page)); + err = -EFAULT; + goto err; + } for (; start < end; start++, dn.ofs_in_node++) { block_t src, dest; @@ -554,6 +567,18 @@ retry_dn: src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); dest = datablock_addr(dn.inode, page, dn.ofs_in_node); + if (__is_valid_data_blkaddr(src) && + !f2fs_is_valid_blkaddr(sbi, src, META_POR)) { + err = -EFAULT; + goto err; + } + + if (__is_valid_data_blkaddr(dest) && + !f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { + err = -EFAULT; + goto err; + } + /* skip recovering if dest is the same as src */ if (src == dest) continue; @@ -666,8 +691,10 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, */ if (IS_INODE(page)) { err = recover_inode(entry->inode, page); - if (err) + if (err) { + f2fs_put_page(page, 1); break; + } } if (entry->last_dentry == blkaddr) { err = recover_dentry(entry->inode, page, dir_list); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index aa7fe79b62b2..8dee063c833f 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -580,7 +580,7 @@ static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) int ret = 0; int i; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return __submit_flush_wait(sbi, sbi->sb->s_bdev); for (i = 0; i < sbi->s_ndevs; i++) { @@ -648,7 +648,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino) return ret; } - if (atomic_inc_return(&fcc->queued_flush) == 1 || sbi->s_ndevs > 1) { + if (atomic_inc_return(&fcc->queued_flush) == 1 || + f2fs_is_multi_device(sbi)) { ret = submit_flush_wait(sbi, ino); atomic_dec(&fcc->queued_flush); @@ -754,7 +755,7 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi) { int ret = 0, i; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return 0; for (i = 1; i < sbi->s_ndevs; i++) { @@ -1367,9 +1368,12 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, { block_t lblkstart = blkstart; + if (!f2fs_bdev_support_discard(bdev)) + return 0; + trace_f2fs_queue_discard(bdev, blkstart, blklen); - if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { int devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; @@ -1732,42 +1736,36 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, block_t lblkstart = blkstart; int devi = 0; - if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { devi = f2fs_target_device_index(sbi, blkstart); + if (blkstart < FDEV(devi).start_blk || + blkstart > FDEV(devi).end_blk) { + f2fs_msg(sbi->sb, KERN_ERR, "Invalid block %x", + blkstart); + return -EIO; + } blkstart -= FDEV(devi).start_blk; } - /* - * We need to know the type of the zone: for conventional zones, - * use regular discard if the drive supports it. For sequential - * zones, reset the zone write pointer. - */ - switch (get_blkz_type(sbi, bdev, blkstart)) { - - case BLK_ZONE_TYPE_CONVENTIONAL: - if (!blk_queue_discard(bdev_get_queue(bdev))) - return 0; - return __queue_discard_cmd(sbi, bdev, lblkstart, blklen); - case BLK_ZONE_TYPE_SEQWRITE_REQ: - case BLK_ZONE_TYPE_SEQWRITE_PREF: + /* For sequential zones, reset the zone write pointer */ + if (f2fs_blkz_is_seq(sbi, devi, blkstart)) { sector = SECTOR_FROM_BLOCK(blkstart); nr_sects = SECTOR_FROM_BLOCK(blklen); if (sector & (bdev_zone_sectors(bdev) - 1) || nr_sects != bdev_zone_sectors(bdev)) { - f2fs_msg(sbi->sb, KERN_INFO, - "(%d) %s: Unaligned discard attempted (block %x + %x)", + f2fs_msg(sbi->sb, KERN_ERR, + "(%d) %s: Unaligned zone reset attempted (block %x + %x)", devi, sbi->s_ndevs ? FDEV(devi).path: "", blkstart, blklen); return -EIO; } trace_f2fs_issue_reset_zone(bdev, blkstart); - return blkdev_reset_zones(bdev, sector, - nr_sects, GFP_NOFS); - default: - /* Unknown zone type: broken device ? */ - return -EIO; + return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS); } + + /* For conventional zones, use regular discard if supported */ + return __queue_discard_cmd(sbi, bdev, lblkstart, blklen); } #endif @@ -1775,8 +1773,7 @@ static int __issue_discard_async(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { #ifdef CONFIG_BLK_DEV_ZONED - if (f2fs_sb_has_blkzoned(sbi) && - bdev_zoned_model(bdev) != BLK_ZONED_NONE) + if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev)) return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen); #endif return __queue_discard_cmd(sbi, bdev, blkstart, blklen); @@ -2172,8 +2169,11 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) * before, we must track that to know how much space we * really have. */ - if (f2fs_test_bit(offset, se->ckpt_valid_map)) + if (f2fs_test_bit(offset, se->ckpt_valid_map)) { + spin_lock(&sbi->stat_lock); sbi->unusable_block_count++; + spin_unlock(&sbi->stat_lock); + } } if (f2fs_test_and_clear_bit(offset, se->discard_map)) @@ -2220,7 +2220,7 @@ bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) struct seg_entry *se; bool is_cp = false; - if (!is_valid_data_blkaddr(sbi, blkaddr)) + if (!__is_valid_data_blkaddr(blkaddr)) return true; down_read(&sit_i->sentry_lock); @@ -3089,7 +3089,7 @@ static void update_device_state(struct f2fs_io_info *fio) struct f2fs_sb_info *sbi = fio->sbi; unsigned int devidx; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return; devidx = f2fs_target_device_index(sbi, fio->new_blkaddr); @@ -3187,13 +3187,18 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) { int err; struct f2fs_sb_info *sbi = fio->sbi; + unsigned int segno; fio->new_blkaddr = fio->old_blkaddr; /* i/o temperature is needed for passing down write hints */ __get_segment_type(fio); - f2fs_bug_on(sbi, !IS_DATASEG(get_seg_entry(sbi, - GET_SEGNO(sbi, fio->new_blkaddr))->type)); + segno = GET_SEGNO(sbi, fio->new_blkaddr); + + if (!IS_DATASEG(get_seg_entry(sbi, segno)->type)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + return -EFAULT; + } stat_inc_inplace_blocks(fio->sbi); @@ -3336,7 +3341,7 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) if (!f2fs_post_read_required(inode)) return; - if (!is_valid_data_blkaddr(sbi, blkaddr)) + if (!__is_valid_data_blkaddr(blkaddr)) return; cpage = find_lock_page(META_MAPPING(sbi), blkaddr); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 5c7ed0442d6e..429007b8036e 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -82,7 +82,7 @@ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1)) #define GET_SEGNO(sbi, blk_addr) \ - ((!is_valid_data_blkaddr(sbi, blk_addr)) ? \ + ((!__is_valid_data_blkaddr(blk_addr)) ? \ NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \ GET_SEGNO_FROM_SEG0(sbi, blk_addr))) #define BLKS_PER_SEC(sbi) \ @@ -656,14 +656,15 @@ static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1); } -static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr) +static inline void verify_fio_blkaddr(struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; - if (__is_meta_io(fio)) - verify_blkaddr(sbi, blk_addr, META_GENERIC); - else - verify_blkaddr(sbi, blk_addr, DATA_GENERIC); + if (__is_valid_data_blkaddr(fio->old_blkaddr)) + verify_blkaddr(sbi, fio->old_blkaddr, __is_meta_io(fio) ? + META_GENERIC : DATA_GENERIC); + verify_blkaddr(sbi, fio->new_blkaddr, __is_meta_io(fio) ? + META_GENERIC : DATA_GENERIC_ENHANCE); } /* @@ -672,7 +673,6 @@ static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr) static inline int check_block_count(struct f2fs_sb_info *sbi, int segno, struct f2fs_sit_entry *raw_sit) { -#ifdef CONFIG_F2FS_CHECK_FS bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false; int valid_blocks = 0; int cur_pos = 0, next_pos; @@ -699,7 +699,7 @@ static inline int check_block_count(struct f2fs_sb_info *sbi, set_sbi_flag(sbi, SBI_NEED_FSCK); return -EINVAL; } -#endif + /* check segment usage, and check boundary of a given segment number */ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg || segno > TOTAL_SEGS(sbi) - 1)) { diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f2aaa2cc6b3e..6b959bbb336a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1000,17 +1000,12 @@ static void f2fs_dirty_inode(struct inode *inode, int flags) f2fs_inode_dirtied(inode, false); } -static void f2fs_i_callback(struct rcu_head *head) +static void f2fs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); + fscrypt_free_inode(inode); kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode)); } -static void f2fs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, f2fs_i_callback); -} - static void destroy_percpu_info(struct f2fs_sb_info *sbi) { percpu_counter_destroy(&sbi->alloc_valid_block_count); @@ -1024,7 +1019,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) for (i = 0; i < sbi->s_ndevs; i++) { blkdev_put(FDEV(i).bdev, FMODE_EXCL); #ifdef CONFIG_BLK_DEV_ZONED - kvfree(FDEV(i).blkz_type); + kvfree(FDEV(i).blkz_seq); #endif } kvfree(sbi->devs); @@ -1226,10 +1221,13 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = total_count - start_count; buf->f_bfree = user_block_count - valid_user_blocks(sbi) - sbi->current_reserved_blocks; + + spin_lock(&sbi->stat_lock); if (unlikely(buf->f_bfree <= sbi->unusable_block_count)) buf->f_bfree = 0; else buf->f_bfree -= sbi->unusable_block_count; + spin_unlock(&sbi->stat_lock); if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks) buf->f_bavail = buf->f_bfree - @@ -1504,9 +1502,15 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) mutex_lock(&sbi->gc_mutex); cpc.reason = CP_PAUSE; set_sbi_flag(sbi, SBI_CP_DISABLED); - f2fs_write_checkpoint(sbi, &cpc); + err = f2fs_write_checkpoint(sbi, &cpc); + if (err) + goto out_unlock; + spin_lock(&sbi->stat_lock); sbi->unusable_block_count = 0; + spin_unlock(&sbi->stat_lock); + +out_unlock: mutex_unlock(&sbi->gc_mutex); restore_flag: sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ @@ -2166,8 +2170,8 @@ void f2fs_quota_off_umount(struct super_block *sb) static const struct super_operations f2fs_sops = { .alloc_inode = f2fs_alloc_inode, + .free_inode = f2fs_free_inode, .drop_inode = f2fs_drop_inode, - .destroy_inode = f2fs_destroy_inode, .write_inode = f2fs_write_inode, .dirty_inode = f2fs_dirty_inode, .show_options = f2fs_show_options, @@ -2276,7 +2280,7 @@ static const struct export_operations f2fs_export_ops = { static loff_t max_file_blocks(void) { loff_t result = 0; - loff_t leaf_count = ADDRS_PER_BLOCK; + loff_t leaf_count = DEF_ADDRS_PER_BLOCK; /* * note: previously, result is equal to (DEF_ADDRS_PER_INODE - @@ -2454,7 +2458,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, /* Currently, support only 4KB page cache size */ if (F2FS_BLKSIZE != PAGE_SIZE) { f2fs_msg(sb, KERN_INFO, - "Invalid page_cache_size (%lu), supports only 4KB\n", + "Invalid page_cache_size (%lu), supports only 4KB", PAGE_SIZE); return 1; } @@ -2463,7 +2467,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, blocksize = 1 << le32_to_cpu(raw_super->log_blocksize); if (blocksize != F2FS_BLKSIZE) { f2fs_msg(sb, KERN_INFO, - "Invalid blocksize (%u), supports only 4KB\n", + "Invalid blocksize (%u), supports only 4KB", blocksize); return 1; } @@ -2471,7 +2475,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, /* check log blocks per segment */ if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { f2fs_msg(sb, KERN_INFO, - "Invalid log blocks per segment (%u)\n", + "Invalid log blocks per segment (%u)", le32_to_cpu(raw_super->log_blocks_per_seg)); return 1; } @@ -2592,7 +2596,8 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int log_blocks_per_seg; unsigned int segment_count_main; unsigned int cp_pack_start_sum, cp_payload; - block_t user_block_count; + block_t user_block_count, valid_user_blocks; + block_t avail_node_count, valid_node_count; int i, j; total = le32_to_cpu(raw_super->segment_count); @@ -2627,6 +2632,24 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) return 1; } + valid_user_blocks = le64_to_cpu(ckpt->valid_block_count); + if (valid_user_blocks > user_block_count) { + f2fs_msg(sbi->sb, KERN_ERR, + "Wrong valid_user_blocks: %u, user_block_count: %u", + valid_user_blocks, user_block_count); + return 1; + } + + valid_node_count = le32_to_cpu(ckpt->valid_node_count); + avail_node_count = sbi->total_node_count - sbi->nquota_files - + F2FS_RESERVED_NODE_NUM; + if (valid_node_count > avail_node_count) { + f2fs_msg(sbi->sb, KERN_ERR, + "Wrong valid_node_count: %u, avail_node_count: %u", + valid_node_count, avail_node_count); + return 1; + } + main_segs = le32_to_cpu(raw_super->segment_count_main); blocks_per_seg = sbi->blocks_per_seg; @@ -2798,9 +2821,11 @@ 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_type = f2fs_kmalloc(sbi, FDEV(devi).nr_blkz, - GFP_KERNEL); - if (!FDEV(devi).blkz_type) + FDEV(devi).blkz_seq = f2fs_kzalloc(sbi, + BITS_TO_LONGS(FDEV(devi).nr_blkz) + * sizeof(unsigned long), + GFP_KERNEL); + if (!FDEV(devi).blkz_seq) return -ENOMEM; #define F2FS_REPORT_NR_ZONES 4096 @@ -2827,7 +2852,8 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) } for (i = 0; i < nr_zones; i++) { - FDEV(devi).blkz_type[n] = zones[i].type; + if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(n, FDEV(devi).blkz_seq); sector += zones[i].len; n++; } @@ -3110,7 +3136,7 @@ try_onemore: #ifndef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi)) { f2fs_msg(sb, KERN_ERR, - "Zoned block device support is not enabled\n"); + "Zoned block device support is not enabled"); err = -EOPNOTSUPP; goto free_sb_buf; } @@ -3355,10 +3381,17 @@ try_onemore: * mount should be failed, when device has readonly mode, and * previous checkpoint was not done by clean system shutdown. */ - if (bdev_read_only(sb->s_bdev) && - !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { - err = -EROFS; - goto free_meta; + if (f2fs_hw_is_readonly(sbi)) { + if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { + err = -EROFS; + f2fs_msg(sb, KERN_ERR, + "Need to recover fsync data, but " + "write access unavailable"); + goto free_meta; + } + f2fs_msg(sbi->sb, KERN_INFO, "write access " + "unavailable, skipping recovery"); + goto reset_checkpoint; } if (need_fsck) diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 848a785abe25..e791741d193b 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -202,12 +202,17 @@ static inline const struct xattr_handler *f2fs_xattr_handler(int index) return handler; } -static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index, - size_t len, const char *name) +static struct f2fs_xattr_entry *__find_xattr(void *base_addr, + void *last_base_addr, int index, + size_t len, const char *name) { struct f2fs_xattr_entry *entry; list_for_each_xattr(entry, base_addr) { + if ((void *)(entry) + sizeof(__u32) > last_base_addr || + (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) + return NULL; + if (entry->e_name_index != index) continue; if (entry->e_name_len != len) @@ -297,20 +302,22 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, const char *name, struct f2fs_xattr_entry **xe, void **base_addr, int *base_size) { - void *cur_addr, *txattr_addr, *last_addr = NULL; + void *cur_addr, *txattr_addr, *last_txattr_addr; + void *last_addr = NULL; nid_t xnid = F2FS_I(inode)->i_xattr_nid; - unsigned int size = xnid ? VALID_XATTR_BLOCK_SIZE : 0; unsigned int inline_size = inline_xattr_size(inode); int err = 0; - if (!size && !inline_size) + if (!xnid && !inline_size) return -ENODATA; - *base_size = inline_size + size + XATTR_PADDING_SIZE; + *base_size = XATTR_SIZE(xnid, inode) + XATTR_PADDING_SIZE; txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode), *base_size, GFP_NOFS); if (!txattr_addr) return -ENOMEM; + last_txattr_addr = (void *)txattr_addr + XATTR_SIZE(xnid, inode); + /* read from inline xattr */ if (inline_size) { err = read_inline_xattr(inode, ipage, txattr_addr); @@ -337,7 +344,11 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, else cur_addr = txattr_addr; - *xe = __find_xattr(cur_addr, index, len, name); + *xe = __find_xattr(cur_addr, last_txattr_addr, index, len, name); + if (!*xe) { + err = -EFAULT; + goto out; + } check: if (IS_XATTR_LAST_ENTRY(*xe)) { err = -ENODATA; @@ -581,7 +592,8 @@ static int __f2fs_setxattr(struct inode *inode, int index, struct page *ipage, int flags) { struct f2fs_xattr_entry *here, *last; - void *base_addr; + void *base_addr, *last_base_addr; + nid_t xnid = F2FS_I(inode)->i_xattr_nid; int found, newsize; size_t len; __u32 new_hsize; @@ -605,8 +617,14 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (error) return error; + last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode); + /* find entry with wanted name. */ - here = __find_xattr(base_addr, index, len, name); + here = __find_xattr(base_addr, last_base_addr, index, len, name); + if (!here) { + error = -EFAULT; + goto exit; + } found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1; diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 9172ee082ca8..a90920e2f949 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -71,6 +71,8 @@ struct f2fs_xattr_entry { entry = XATTR_NEXT_ENTRY(entry)) #define VALID_XATTR_BLOCK_SIZE (PAGE_SIZE - sizeof(struct node_footer)) #define XATTR_PADDING_SIZE (sizeof(__u32)) +#define XATTR_SIZE(x,i) (((x) ? VALID_XATTR_BLOCK_SIZE : 0) + \ + (inline_xattr_size(i))) #define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + \ VALID_XATTR_BLOCK_SIZE) diff --git a/fs/fat/file.c b/fs/fat/file.c index b3bed32946b1..0e3ed79fcc3f 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -193,12 +193,17 @@ static int fat_file_release(struct inode *inode, struct file *filp) int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { struct inode *inode = filp->f_mapping->host; - int res, err; + int err; + + err = __generic_file_fsync(filp, start, end, datasync); + if (err) + return err; - res = generic_file_fsync(filp, start, end, datasync); err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); + if (err) + return err; - return res ? res : err; + return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); } diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 79bb0e73a65f..ba93d1373306 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -746,17 +746,11 @@ static struct inode *fat_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void fat_i_callback(struct rcu_head *head) +static void fat_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); } -static void fat_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, fat_i_callback); -} - static void init_once(void *foo) { struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; @@ -920,7 +914,7 @@ EXPORT_SYMBOL_GPL(fat_sync_inode); static int fat_show_options(struct seq_file *m, struct dentry *root); static const struct super_operations fat_sops = { .alloc_inode = fat_alloc_inode, - .destroy_inode = fat_destroy_inode, + .free_inode = fat_free_inode, .write_inode = fat_write_inode, .evict_inode = fat_evict_inode, .put_super = fat_put_super, diff --git a/fs/fcntl.c b/fs/fcntl.c index 083185174c6d..3d40771e8e7c 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -769,7 +769,7 @@ static void send_sigio_to_task(struct task_struct *p, si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; - /* fall-through: fall back on the old plain SIGIO signal */ + /* fall-through - fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } diff --git a/fs/file_table.c b/fs/file_table.c index 155d7514a094..3f9c1b452c1d 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -255,6 +255,7 @@ static void __fput(struct file *file) struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; + fmode_t mode = file->f_mode; if (unlikely(!(file->f_mode & FMODE_OPENED))) goto out; @@ -277,18 +278,20 @@ static void __fput(struct file *file) if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && - !(file->f_mode & FMODE_PATH))) { + !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); } fops_put(file->f_op); put_pid(file->f_owner.pid); - if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) + if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_dec(inode); - if (file->f_mode & FMODE_WRITER) { + if (mode & FMODE_WRITER) { put_write_access(inode); __mnt_drop_write(mnt); } dput(dentry); + if (unlikely(mode & FMODE_NEED_UNMOUNT)) + dissolve_on_fput(mnt); mntput(mnt); out: file_free(file); diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c index 48b24bb50d02..a89f68c3cbed 100644 --- a/fs/freevxfs/vxfs_super.c +++ b/fs/freevxfs/vxfs_super.c @@ -131,21 +131,14 @@ static struct inode *vxfs_alloc_inode(struct super_block *sb) return &vi->vfs_inode; } -static void vxfs_i_callback(struct rcu_head *head) +static void vxfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(vxfs_inode_cachep, VXFS_INO(inode)); } -static void vxfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, vxfs_i_callback); -} - static const struct super_operations vxfs_super_ops = { .alloc_inode = vxfs_alloc_inode, - .destroy_inode = vxfs_destroy_inode, + .free_inode = vxfs_free_inode, .evict_inode = vxfs_evict_inode, .put_super = vxfs_put_super, .statfs = vxfs_statfs, diff --git a/fs/fs_context.c b/fs/fs_context.c index 87e3546b9a52..a47ccd5a4a78 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -11,6 +11,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/fs.h> @@ -23,6 +24,7 @@ #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> +#include <asm/sections.h> #include "mount.h" #include "internal.h" @@ -271,6 +273,8 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, fc->cred = get_current_cred(); fc->net_ns = get_net(current->nsproxy->net_ns); + mutex_init(&fc->uapi_mutex); + switch (purpose) { case FS_CONTEXT_FOR_MOUNT: fc->user_ns = get_user_ns(fc->cred->user_ns); @@ -353,6 +357,8 @@ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc) if (!fc) return ERR_PTR(-ENOMEM); + mutex_init(&fc->uapi_mutex); + fc->fs_private = NULL; fc->s_fs_info = NULL; fc->source = NULL; @@ -361,6 +367,8 @@ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc) get_net(fc->net_ns); get_user_ns(fc->user_ns); get_cred(fc->cred); + if (fc->log) + refcount_inc(&fc->log->usage); /* Can't call put until we've called ->dup */ ret = fc->ops->dup(fc, src_fc); @@ -378,7 +386,6 @@ err_fc: } EXPORT_SYMBOL(vfs_dup_fs_context); -#ifdef CONFIG_PRINTK /** * logfc - Log a message to a filesystem context * @fc: The filesystem context to log to. @@ -386,27 +393,100 @@ EXPORT_SYMBOL(vfs_dup_fs_context); */ void logfc(struct fs_context *fc, const char *fmt, ...) { + static const char store_failure[] = "OOM: Can't store error string"; + struct fc_log *log = fc ? fc->log : NULL; + const char *p; va_list va; + char *q; + u8 freeable; va_start(va, fmt); - - switch (fmt[0]) { - case 'w': - vprintk_emit(0, LOGLEVEL_WARNING, NULL, 0, fmt, va); - break; - case 'e': - vprintk_emit(0, LOGLEVEL_ERR, NULL, 0, fmt, va); - break; - default: - vprintk_emit(0, LOGLEVEL_NOTICE, NULL, 0, fmt, va); - break; + if (!strchr(fmt, '%')) { + p = fmt; + goto unformatted_string; + } + if (strcmp(fmt, "%s") == 0) { + p = va_arg(va, const char *); + goto unformatted_string; } - pr_cont("\n"); + q = kvasprintf(GFP_KERNEL, fmt, va); +copied_string: + if (!q) + goto store_failure; + freeable = 1; + goto store_string; + +unformatted_string: + if ((unsigned long)p >= (unsigned long)__start_rodata && + (unsigned long)p < (unsigned long)__end_rodata) + goto const_string; + if (log && within_module_core((unsigned long)p, log->owner)) + goto const_string; + q = kstrdup(p, GFP_KERNEL); + goto copied_string; + +store_failure: + p = store_failure; +const_string: + q = (char *)p; + freeable = 0; +store_string: + if (!log) { + switch (fmt[0]) { + case 'w': + printk(KERN_WARNING "%s\n", q + 2); + break; + case 'e': + printk(KERN_ERR "%s\n", q + 2); + break; + default: + printk(KERN_NOTICE "%s\n", q + 2); + break; + } + if (freeable) + kfree(q); + } else { + unsigned int logsize = ARRAY_SIZE(log->buffer); + u8 index; + + index = log->head & (logsize - 1); + BUILD_BUG_ON(sizeof(log->head) != sizeof(u8) || + sizeof(log->tail) != sizeof(u8)); + if ((u8)(log->head - log->tail) == logsize) { + /* The buffer is full, discard the oldest message */ + if (log->need_free & (1 << index)) + kfree(log->buffer[index]); + log->tail++; + } + + log->buffer[index] = q; + log->need_free &= ~(1 << index); + log->need_free |= freeable << index; + log->head++; + } va_end(va); } EXPORT_SYMBOL(logfc); -#endif + +/* + * Free a logging structure. + */ +static void put_fc_log(struct fs_context *fc) +{ + struct fc_log *log = fc->log; + int i; + + if (log) { + if (refcount_dec_and_test(&log->usage)) { + fc->log = NULL; + for (i = 0; i <= 7; i++) + if (log->need_free & (1 << i)) + kfree(log->buffer[i]); + kfree(log); + } + } +} /** * put_fs_context - Dispose of a superblock configuration context. @@ -431,6 +511,7 @@ void put_fs_context(struct fs_context *fc) put_user_ns(fc->user_ns); put_cred(fc->cred); kfree(fc->subtype); + put_fc_log(fc); put_filesystem(fc->fs_type); kfree(fc->source); kfree(fc); @@ -640,3 +721,54 @@ int parse_monolithic_mount_data(struct fs_context *fc, void *data) return monolithic_mount_data(fc, data); } + +/* + * Clean up a context after performing an action on it and put it into a state + * from where it can be used to reconfigure a superblock. + * + * Note that here we do only the parts that can't fail; the rest is in + * finish_clean_context() below and in between those fs_context is marked + * FS_CONTEXT_AWAITING_RECONF. The reason for splitup is that after + * successful mount or remount we need to report success to userland. + * Trying to do full reinit (for the sake of possible subsequent remount) + * and failing to allocate memory would've put us into a nasty situation. + * So here we only discard the old state and reinitialization is left + * until we actually try to reconfigure. + */ +void vfs_clean_context(struct fs_context *fc) +{ + if (fc->need_free && fc->ops && fc->ops->free) + fc->ops->free(fc); + fc->need_free = false; + fc->fs_private = NULL; + fc->s_fs_info = NULL; + fc->sb_flags = 0; + security_free_mnt_opts(&fc->security); + kfree(fc->subtype); + fc->subtype = NULL; + kfree(fc->source); + fc->source = NULL; + + fc->purpose = FS_CONTEXT_FOR_RECONFIGURE; + fc->phase = FS_CONTEXT_AWAITING_RECONF; +} + +int finish_clean_context(struct fs_context *fc) +{ + int error; + + if (fc->phase != FS_CONTEXT_AWAITING_RECONF) + return 0; + + if (fc->fs_type->init_fs_context) + error = fc->fs_type->init_fs_context(fc); + else + error = legacy_init_fs_context(fc); + if (unlikely(error)) { + fc->phase = FS_CONTEXT_FAILED; + return error; + } + fc->need_free = true; + fc->phase = FS_CONTEXT_RECONF_PARAMS; + return 0; +} diff --git a/fs/fsopen.c b/fs/fsopen.c new file mode 100644 index 000000000000..c2891e933ef1 --- /dev/null +++ b/fs/fsopen.c @@ -0,0 +1,477 @@ +/* Filesystem access-by-fd. + * + * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/fs_context.h> +#include <linux/fs_parser.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/syscalls.h> +#include <linux/security.h> +#include <linux/anon_inodes.h> +#include <linux/namei.h> +#include <linux/file.h> +#include <uapi/linux/mount.h> +#include "internal.h" +#include "mount.h" + +/* + * Allow the user to read back any error, warning or informational messages. + */ +static ssize_t fscontext_read(struct file *file, + char __user *_buf, size_t len, loff_t *pos) +{ + struct fs_context *fc = file->private_data; + struct fc_log *log = fc->log; + unsigned int logsize = ARRAY_SIZE(log->buffer); + ssize_t ret; + char *p; + bool need_free; + int index, n; + + ret = mutex_lock_interruptible(&fc->uapi_mutex); + if (ret < 0) + return ret; + + if (log->head == log->tail) { + mutex_unlock(&fc->uapi_mutex); + return -ENODATA; + } + + index = log->tail & (logsize - 1); + p = log->buffer[index]; + need_free = log->need_free & (1 << index); + log->buffer[index] = NULL; + log->need_free &= ~(1 << index); + log->tail++; + mutex_unlock(&fc->uapi_mutex); + + ret = -EMSGSIZE; + n = strlen(p); + if (n > len) + goto err_free; + ret = -EFAULT; + if (copy_to_user(_buf, p, n) != 0) + goto err_free; + ret = n; + +err_free: + if (need_free) + kfree(p); + return ret; +} + +static int fscontext_release(struct inode *inode, struct file *file) +{ + struct fs_context *fc = file->private_data; + + if (fc) { + file->private_data = NULL; + put_fs_context(fc); + } + return 0; +} + +const struct file_operations fscontext_fops = { + .read = fscontext_read, + .release = fscontext_release, + .llseek = no_llseek, +}; + +/* + * Attach a filesystem context to a file and an fd. + */ +static int fscontext_create_fd(struct fs_context *fc, unsigned int o_flags) +{ + int fd; + + fd = anon_inode_getfd("[fscontext]", &fscontext_fops, fc, + O_RDWR | o_flags); + if (fd < 0) + put_fs_context(fc); + return fd; +} + +static int fscontext_alloc_log(struct fs_context *fc) +{ + fc->log = kzalloc(sizeof(*fc->log), GFP_KERNEL); + if (!fc->log) + return -ENOMEM; + refcount_set(&fc->log->usage, 1); + fc->log->owner = fc->fs_type->owner; + return 0; +} + +/* + * Open a filesystem by name so that it can be configured for mounting. + * + * We are allowed to specify a container in which the filesystem will be + * opened, thereby indicating which namespaces will be used (notably, which + * network namespace will be used for network filesystems). + */ +SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags) +{ + struct file_system_type *fs_type; + struct fs_context *fc; + const char *fs_name; + int ret; + + if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + if (flags & ~FSOPEN_CLOEXEC) + return -EINVAL; + + fs_name = strndup_user(_fs_name, PAGE_SIZE); + if (IS_ERR(fs_name)) + return PTR_ERR(fs_name); + + fs_type = get_fs_type(fs_name); + kfree(fs_name); + if (!fs_type) + return -ENODEV; + + fc = fs_context_for_mount(fs_type, 0); + put_filesystem(fs_type); + if (IS_ERR(fc)) + return PTR_ERR(fc); + + fc->phase = FS_CONTEXT_CREATE_PARAMS; + + ret = fscontext_alloc_log(fc); + if (ret < 0) + goto err_fc; + + return fscontext_create_fd(fc, flags & FSOPEN_CLOEXEC ? O_CLOEXEC : 0); + +err_fc: + put_fs_context(fc); + return ret; +} + +/* + * Pick a superblock into a context for reconfiguration. + */ +SYSCALL_DEFINE3(fspick, int, dfd, const char __user *, path, unsigned int, flags) +{ + struct fs_context *fc; + struct path target; + unsigned int lookup_flags; + int ret; + + if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + if ((flags & ~(FSPICK_CLOEXEC | + FSPICK_SYMLINK_NOFOLLOW | + FSPICK_NO_AUTOMOUNT | + FSPICK_EMPTY_PATH)) != 0) + return -EINVAL; + + lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT; + if (flags & FSPICK_SYMLINK_NOFOLLOW) + lookup_flags &= ~LOOKUP_FOLLOW; + if (flags & FSPICK_NO_AUTOMOUNT) + lookup_flags &= ~LOOKUP_AUTOMOUNT; + if (flags & FSPICK_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; + ret = user_path_at(dfd, path, lookup_flags, &target); + if (ret < 0) + goto err; + + ret = -EINVAL; + if (target.mnt->mnt_root != target.dentry) + goto err_path; + + fc = fs_context_for_reconfigure(target.dentry, 0, 0); + if (IS_ERR(fc)) { + ret = PTR_ERR(fc); + goto err_path; + } + + fc->phase = FS_CONTEXT_RECONF_PARAMS; + + ret = fscontext_alloc_log(fc); + if (ret < 0) + goto err_fc; + + path_put(&target); + return fscontext_create_fd(fc, flags & FSPICK_CLOEXEC ? O_CLOEXEC : 0); + +err_fc: + put_fs_context(fc); +err_path: + path_put(&target); +err: + return ret; +} + +/* + * Check the state and apply the configuration. Note that this function is + * allowed to 'steal' the value by setting param->xxx to NULL before returning. + */ +static int vfs_fsconfig_locked(struct fs_context *fc, int cmd, + struct fs_parameter *param) +{ + struct super_block *sb; + int ret; + + ret = finish_clean_context(fc); + if (ret) + return ret; + switch (cmd) { + case FSCONFIG_CMD_CREATE: + if (fc->phase != FS_CONTEXT_CREATE_PARAMS) + return -EBUSY; + fc->phase = FS_CONTEXT_CREATING; + ret = vfs_get_tree(fc); + if (ret) + break; + sb = fc->root->d_sb; + ret = security_sb_kern_mount(sb); + if (unlikely(ret)) { + fc_drop_locked(fc); + break; + } + up_write(&sb->s_umount); + fc->phase = FS_CONTEXT_AWAITING_MOUNT; + return 0; + case FSCONFIG_CMD_RECONFIGURE: + if (fc->phase != FS_CONTEXT_RECONF_PARAMS) + return -EBUSY; + fc->phase = FS_CONTEXT_RECONFIGURING; + sb = fc->root->d_sb; + if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { + ret = -EPERM; + break; + } + down_write(&sb->s_umount); + ret = reconfigure_super(fc); + up_write(&sb->s_umount); + if (ret) + break; + vfs_clean_context(fc); + return 0; + default: + if (fc->phase != FS_CONTEXT_CREATE_PARAMS && + fc->phase != FS_CONTEXT_RECONF_PARAMS) + return -EBUSY; + + return vfs_parse_fs_param(fc, param); + } + fc->phase = FS_CONTEXT_FAILED; + return ret; +} + +/** + * sys_fsconfig - Set parameters and trigger actions on a context + * @fd: The filesystem context to act upon + * @cmd: The action to take + * @_key: Where appropriate, the parameter key to set + * @_value: Where appropriate, the parameter value to set + * @aux: Additional information for the value + * + * This system call is used to set parameters on a context, including + * superblock settings, data source and security labelling. + * + * Actions include triggering the creation of a superblock and the + * reconfiguration of the superblock attached to the specified context. + * + * When setting a parameter, @cmd indicates the type of value being proposed + * and @_key indicates the parameter to be altered. + * + * @_value and @aux are used to specify the value, should a value be required: + * + * (*) fsconfig_set_flag: No value is specified. The parameter must be boolean + * in nature. The key may be prefixed with "no" to invert the + * setting. @_value must be NULL and @aux must be 0. + * + * (*) fsconfig_set_string: A string value is specified. The parameter can be + * expecting boolean, integer, string or take a path. A conversion to an + * appropriate type will be attempted (which may include looking up as a + * path). @_value points to a NUL-terminated string and @aux must be 0. + * + * (*) fsconfig_set_binary: A binary blob is specified. @_value points to the + * blob and @aux indicates its size. The parameter must be expecting a + * blob. + * + * (*) fsconfig_set_path: A non-empty path is specified. The parameter must be + * expecting a path object. @_value points to a NUL-terminated string that + * is the path and @aux is a file descriptor at which to start a relative + * lookup or AT_FDCWD. + * + * (*) fsconfig_set_path_empty: As fsconfig_set_path, but with AT_EMPTY_PATH + * implied. + * + * (*) fsconfig_set_fd: An open file descriptor is specified. @_value must be + * NULL and @aux indicates the file descriptor. + */ +SYSCALL_DEFINE5(fsconfig, + int, fd, + unsigned int, cmd, + const char __user *, _key, + const void __user *, _value, + int, aux) +{ + struct fs_context *fc; + struct fd f; + int ret; + + struct fs_parameter param = { + .type = fs_value_is_undefined, + }; + + if (fd < 0) + return -EINVAL; + + switch (cmd) { + case FSCONFIG_SET_FLAG: + if (!_key || _value || aux) + return -EINVAL; + break; + case FSCONFIG_SET_STRING: + if (!_key || !_value || aux) + return -EINVAL; + break; + case FSCONFIG_SET_BINARY: + if (!_key || !_value || aux <= 0 || aux > 1024 * 1024) + return -EINVAL; + break; + case FSCONFIG_SET_PATH: + case FSCONFIG_SET_PATH_EMPTY: + if (!_key || !_value || (aux != AT_FDCWD && aux < 0)) + return -EINVAL; + break; + case FSCONFIG_SET_FD: + if (!_key || _value || aux < 0) + return -EINVAL; + break; + case FSCONFIG_CMD_CREATE: + case FSCONFIG_CMD_RECONFIGURE: + if (_key || _value || aux) + return -EINVAL; + break; + default: + return -EOPNOTSUPP; + } + + f = fdget(fd); + if (!f.file) + return -EBADF; + ret = -EINVAL; + if (f.file->f_op != &fscontext_fops) + goto out_f; + + fc = f.file->private_data; + if (fc->ops == &legacy_fs_context_ops) { + switch (cmd) { + case FSCONFIG_SET_BINARY: + case FSCONFIG_SET_PATH: + case FSCONFIG_SET_PATH_EMPTY: + case FSCONFIG_SET_FD: + ret = -EOPNOTSUPP; + goto out_f; + } + } + + if (_key) { + param.key = strndup_user(_key, 256); + if (IS_ERR(param.key)) { + ret = PTR_ERR(param.key); + goto out_f; + } + } + + switch (cmd) { + case FSCONFIG_SET_FLAG: + param.type = fs_value_is_flag; + break; + case FSCONFIG_SET_STRING: + param.type = fs_value_is_string; + param.string = strndup_user(_value, 256); + if (IS_ERR(param.string)) { + ret = PTR_ERR(param.string); + goto out_key; + } + param.size = strlen(param.string); + break; + case FSCONFIG_SET_BINARY: + param.type = fs_value_is_blob; + param.size = aux; + param.blob = memdup_user_nul(_value, aux); + if (IS_ERR(param.blob)) { + ret = PTR_ERR(param.blob); + goto out_key; + } + break; + case FSCONFIG_SET_PATH: + param.type = fs_value_is_filename; + param.name = getname_flags(_value, 0, NULL); + if (IS_ERR(param.name)) { + ret = PTR_ERR(param.name); + goto out_key; + } + param.dirfd = aux; + param.size = strlen(param.name->name); + break; + case FSCONFIG_SET_PATH_EMPTY: + param.type = fs_value_is_filename_empty; + param.name = getname_flags(_value, LOOKUP_EMPTY, NULL); + if (IS_ERR(param.name)) { + ret = PTR_ERR(param.name); + goto out_key; + } + param.dirfd = aux; + param.size = strlen(param.name->name); + break; + case FSCONFIG_SET_FD: + param.type = fs_value_is_file; + ret = -EBADF; + param.file = fget(aux); + if (!param.file) + goto out_key; + break; + default: + break; + } + + ret = mutex_lock_interruptible(&fc->uapi_mutex); + if (ret == 0) { + ret = vfs_fsconfig_locked(fc, cmd, ¶m); + mutex_unlock(&fc->uapi_mutex); + } + + /* Clean up the our record of any value that we obtained from + * userspace. Note that the value may have been stolen by the LSM or + * filesystem, in which case the value pointer will have been cleared. + */ + switch (cmd) { + case FSCONFIG_SET_STRING: + case FSCONFIG_SET_BINARY: + kfree(param.string); + break; + case FSCONFIG_SET_PATH: + case FSCONFIG_SET_PATH_EMPTY: + if (param.name) + putname(param.name); + break; + case FSCONFIG_SET_FD: + if (param.file) + fput(param.file); + break; + default: + break; + } +out_key: + kfree(param.key); +out_f: + fdput(f); + return ret; +} diff --git a/fs/fuse/control.c b/fs/fuse/control.c index fe80bea4ad89..14ce1e47f980 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/module.h> +#include <linux/fs_context.h> #define FUSE_CTL_SUPER_MAGIC 0x65735543 @@ -317,7 +318,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc) drop_nlink(d_inode(fuse_control_sb->s_root)); } -static int fuse_ctl_fill_super(struct super_block *sb, void *data, int silent) +static int fuse_ctl_fill_super(struct super_block *sb, struct fs_context *fctx) { static const struct tree_descr empty_descr = {""}; struct fuse_conn *fc; @@ -343,10 +344,19 @@ static int fuse_ctl_fill_super(struct super_block *sb, void *data, int silent) return 0; } -static struct dentry *fuse_ctl_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data) +static int fuse_ctl_get_tree(struct fs_context *fc) { - return mount_single(fs_type, flags, raw_data, fuse_ctl_fill_super); + return vfs_get_super(fc, vfs_get_single_super, fuse_ctl_fill_super); +} + +static const struct fs_context_operations fuse_ctl_context_ops = { + .get_tree = fuse_ctl_get_tree, +}; + +static int fuse_ctl_init_fs_context(struct fs_context *fc) +{ + fc->ops = &fuse_ctl_context_ops; + return 0; } static void fuse_ctl_kill_sb(struct super_block *sb) @@ -365,7 +375,7 @@ static void fuse_ctl_kill_sb(struct super_block *sb) static struct file_system_type fuse_ctl_fs_type = { .owner = THIS_MODULE, .name = "fusectl", - .mount = fuse_ctl_mount, + .init_fs_context = fuse_ctl_init_fs_context, .kill_sb = fuse_ctl_kill_sb, }; MODULE_ALIAS_FS("fusectl"); diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 55a26f351467..4b41df1d4642 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -33,6 +33,8 @@ * closed. */ +#define pr_fmt(fmt) "CUSE: " fmt + #include <linux/fuse.h> #include <linux/cdev.h> #include <linux/device.h> @@ -225,7 +227,7 @@ static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp) return 0; if (end[-1] != '\0') { - printk(KERN_ERR "CUSE: info not properly terminated\n"); + pr_err("info not properly terminated\n"); return -EINVAL; } @@ -242,7 +244,7 @@ static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp) key = strstrip(key); if (!strlen(key)) { - printk(KERN_ERR "CUSE: zero length info key specified\n"); + pr_err("zero length info key specified\n"); return -EINVAL; } @@ -282,12 +284,11 @@ static int cuse_parse_devinfo(char *p, size_t len, struct cuse_devinfo *devinfo) if (strcmp(key, "DEVNAME") == 0) devinfo->name = val; else - printk(KERN_WARNING "CUSE: unknown device info \"%s\"\n", - key); + pr_warn("unknown device info \"%s\"\n", key); } if (!devinfo->name || !strlen(devinfo->name)) { - printk(KERN_ERR "CUSE: DEVNAME unspecified\n"); + pr_err("DEVNAME unspecified\n"); return -EINVAL; } @@ -341,7 +342,7 @@ static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req) else rc = register_chrdev_region(devt, 1, devinfo.name); if (rc) { - printk(KERN_ERR "CUSE: failed to register chrdev region\n"); + pr_err("failed to register chrdev region\n"); goto err; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 8a63e52785e9..24ea19cfe07e 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -906,8 +906,8 @@ static int fuse_check_page(struct page *page) 1 << PG_lru | 1 << PG_active | 1 << PG_reclaim))) { - printk(KERN_WARNING "fuse: trying to steal weird page\n"); - printk(KERN_WARNING " 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); + 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; } return 0; @@ -1317,6 +1317,16 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, unsigned reqsize; unsigned int hash; + /* + * Require sane minimum read buffer - that has capacity for fixed part + * of any request header + negotated max_write room for data. If the + * requirement is not satisfied return EINVAL to the filesystem server + * to indicate that it is not following FUSE server/client contract. + * Don't dequeue / abort any request. + */ + if (nbytes < max_t(size_t, FUSE_MIN_READ_BUFFER, 4096 + fc->max_write)) + return -EINVAL; + restart: spin_lock(&fiq->waitq.lock); err = -EAGAIN; @@ -1749,7 +1759,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, offset = outarg->offset & ~PAGE_MASK; file_size = i_size_read(inode); - num = outarg->size; + num = min(outarg->size, fc->max_write); if (outarg->offset > file_size) num = 0; else if (outarg->offset + num > file_size) @@ -2056,10 +2066,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -2077,7 +2085,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2100,11 +2110,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); pipe_unlock(pipe); -out: kvfree(bufs); return ret; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 06096b60f1df..3959f08279e6 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -178,7 +178,9 @@ void fuse_finish_open(struct inode *inode, struct file *file) if (!(ff->open_flags & FOPEN_KEEP_CACHE)) invalidate_inode_pages2(inode->i_mapping); - if (ff->open_flags & FOPEN_NONSEEKABLE) + if (ff->open_flags & FOPEN_STREAM) + stream_open(inode, file); + else if (ff->open_flags & FOPEN_NONSEEKABLE) nonseekable_open(inode, file); if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -462,7 +464,7 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, memset(&inarg, 0, sizeof(inarg)); inarg.fh = ff->fh; - inarg.fsync_flags = datasync ? 1 : 0; + inarg.fsync_flags = datasync ? FUSE_FSYNC_FDATASYNC : 0; args.in.h.opcode = opcode; args.in.h.nodeid = get_node_id(inode); args.in.numargs = 1; @@ -1586,7 +1588,7 @@ __acquires(fi->lock) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); - size_t crop = i_size_read(inode); + loff_t crop = i_size_read(inode); struct fuse_req *req; while (fi->writectr >= 0 && !list_empty(&fi->queued_writes)) { @@ -2576,8 +2578,13 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, #if BITS_PER_LONG == 32 inarg.flags |= FUSE_IOCTL_32BIT; #else - if (flags & FUSE_IOCTL_COMPAT) + if (flags & FUSE_IOCTL_COMPAT) { inarg.flags |= FUSE_IOCTL_32BIT; +#ifdef CONFIG_X86_X32 + if (in_x32_syscall()) + inarg.flags |= FUSE_IOCTL_COMPAT_X32; +#endif + } #endif /* assume all the iovs returned by client always fits in a page */ @@ -3044,6 +3051,13 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, } } + if (!(mode & FALLOC_FL_KEEP_SIZE) && + offset + length > i_size_read(inode)) { + err = inode_newsize_ok(inode, offset + length); + if (err) + return err; + } + if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 0920c0c032a0..24dbca777775 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -9,6 +9,10 @@ #ifndef _FS_FUSE_I_H #define _FS_FUSE_I_H +#ifndef pr_fmt +# define pr_fmt(fmt) "fuse: " fmt +#endif + #include <linux/fuse.h> #include <linux/fs.h> #include <linux/mount.h> @@ -690,6 +694,9 @@ struct fuse_conn { /** Use enhanced/automatic page cache invalidation. */ unsigned auto_inval_data:1; + /** Filesystem is fully reponsible for page cache invalidation. */ + unsigned explicit_inval_data:1; + /** Does the filesystem support readdirplus? */ unsigned do_readdirplus:1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ec5d9953dfb6..4bb885b0f032 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -81,14 +81,12 @@ struct fuse_forget_link *fuse_alloc_forget(void) static struct inode *fuse_alloc_inode(struct super_block *sb) { - struct inode *inode; struct fuse_inode *fi; - inode = kmem_cache_alloc(fuse_inode_cachep, GFP_KERNEL); - if (!inode) + fi = kmem_cache_alloc(fuse_inode_cachep, GFP_KERNEL); + if (!fi) return NULL; - fi = get_fuse_inode(inode); fi->i_time = 0; fi->inval_mask = 0; fi->nodeid = 0; @@ -100,41 +98,37 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) spin_lock_init(&fi->lock); fi->forget = fuse_alloc_forget(); if (!fi->forget) { - kmem_cache_free(fuse_inode_cachep, inode); + kmem_cache_free(fuse_inode_cachep, fi); return NULL; } - return inode; -} - -static void fuse_i_callback(struct rcu_head *head) -{ - struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(fuse_inode_cachep, inode); + return &fi->inode; } -static void fuse_destroy_inode(struct inode *inode) +static void fuse_free_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); - if (S_ISREG(inode->i_mode) && !is_bad_inode(inode)) { - WARN_ON(!list_empty(&fi->write_files)); - WARN_ON(!list_empty(&fi->queued_writes)); - } + mutex_destroy(&fi->mutex); kfree(fi->forget); - call_rcu(&inode->i_rcu, fuse_i_callback); + kmem_cache_free(fuse_inode_cachep, fi); } static void fuse_evict_inode(struct inode *inode) { + struct fuse_inode *fi = get_fuse_inode(inode); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_sb->s_flags & SB_ACTIVE) { struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_inode *fi = get_fuse_inode(inode); fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup); fi->forget = NULL; } + if (S_ISREG(inode->i_mode) && !is_bad_inode(inode)) { + WARN_ON(!list_empty(&fi->write_files)); + WARN_ON(!list_empty(&fi->queued_writes)); + } } static int fuse_remount_fs(struct super_block *sb, int *flags, char *data) @@ -237,7 +231,8 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, if (oldsize != attr->size) { truncate_pagecache(inode, attr->size); - inval = true; + if (!fc->explicit_inval_data) + inval = true; } else if (fc->auto_inval_data) { struct timespec64 new_mtime = { .tv_sec = attr->mtime, @@ -814,7 +809,7 @@ static const struct export_operations fuse_export_operations = { static const struct super_operations fuse_super_operations = { .alloc_inode = fuse_alloc_inode, - .destroy_inode = fuse_destroy_inode, + .free_inode = fuse_free_inode, .evict_inode = fuse_evict_inode, .write_inode = fuse_write_inode, .drop_inode = generic_delete_inode, @@ -912,6 +907,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->dont_mask = 1; if (arg->flags & FUSE_AUTO_INVAL_DATA) fc->auto_inval_data = 1; + else if (arg->flags & FUSE_EXPLICIT_INVAL_DATA) + fc->explicit_inval_data = 1; if (arg->flags & FUSE_DO_READDIRPLUS) { fc->do_readdirplus = 1; if (arg->flags & FUSE_READDIRPLUS_AUTO) @@ -973,7 +970,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL | FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS | - FUSE_NO_OPENDIR_SUPPORT; + FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); @@ -1397,8 +1394,8 @@ static int __init fuse_init(void) { int res; - printk(KERN_INFO "fuse init (API version %i.%i)\n", - FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION); + pr_info("init (API version %i.%i)\n", + FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION); INIT_LIST_HEAD(&fuse_conn_list); res = fuse_fs_init(); @@ -1434,7 +1431,7 @@ static int __init fuse_init(void) static void __exit fuse_exit(void) { - printk(KERN_DEBUG "fuse exit\n"); + pr_debug("exit\n"); fuse_ctl_cleanup(); fuse_sysfs_cleanup(); diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index 3ed2b088dcfd..6a1e499543f5 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -1,6 +1,5 @@ config GFS2_FS tristate "GFS2 file system support" - depends on (64BIT || LBDAF) select FS_POSIX_ACL select CRC32 select LIBCRC32C diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 05dd78f4b2b3..6210d4429d84 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -649,7 +649,7 @@ out_uninit: */ void adjust_fs_space(struct inode *inode) { - struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; + struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode); struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; @@ -657,10 +657,13 @@ void adjust_fs_space(struct inode *inode) struct buffer_head *m_bh, *l_bh; u64 fs_total, new_free; + if (gfs2_trans_begin(sdp, 2 * RES_STATFS, 0) != 0) + return; + /* Total up the file system space, according to the latest rindex. */ fs_total = gfs2_ri_total(sdp); if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0) - return; + goto out; spin_lock(&sdp->sd_statfs_spin); gfs2_statfs_change_in(m_sc, m_bh->b_data + @@ -675,11 +678,14 @@ void adjust_fs_space(struct inode *inode) gfs2_statfs_change(sdp, new_free, new_free, 0); if (gfs2_meta_inode_buffer(l_ip, &l_bh) != 0) - goto out; + goto out2; update_statfs(sdp, m_bh, l_bh); brelse(l_bh); -out: +out2: brelse(m_bh); +out: + sdp->sd_rindex_uptodate = 0; + gfs2_trans_end(sdp); } /** diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 02b2646d84b3..f42718dd292f 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -142,7 +142,7 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page) if (error) goto out_brelse; if (isdir) { - gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1); + gfs2_trans_remove_revoke(GFS2_SB(&ip->i_inode), block, 1); error = gfs2_dir_get_new_buffer(ip, block, &bh); if (error) goto out_brelse; @@ -676,7 +676,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap, goto out; alloced += n; if (state != ALLOC_DATA || gfs2_is_jdata(ip)) - gfs2_trans_add_unrevoke(sdp, bn, n); + gfs2_trans_remove_revoke(sdp, bn, n); switch (state) { /* Growing height of tree */ case ALLOC_GROW_HEIGHT: @@ -710,7 +710,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap, } if (n == 0) break; - /* Branching from existing tree */ + /* fall through - To branching from existing tree */ case ALLOC_GROW_DEPTH: if (i > 1 && i < mp->mp_fheight) gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]); @@ -721,7 +721,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap, state = ALLOC_DATA; if (n == 0) break; - /* Tree complete, adding data blocks */ + /* fall through - To tree complete, adding data blocks */ case ALLOC_DATA: BUG_ON(n > dblks); BUG_ON(mp->mp_bh[end_of_metadata] == NULL); @@ -925,6 +925,32 @@ do_alloc: goto out; } +/** + * gfs2_lblk_to_dblk - convert logical block to disk block + * @inode: the inode of the file we're mapping + * @lblock: the block relative to the start of the file + * @dblock: the returned dblock, if no error + * + * This function maps a single block from a file logical block (relative to + * the start of the file) to a file system absolute block using iomap. + * + * Returns: the absolute file system block, or an error + */ +int gfs2_lblk_to_dblk(struct inode *inode, u32 lblock, u64 *dblock) +{ + struct iomap iomap = { }; + struct metapath mp = { .mp_aheight = 1, }; + loff_t pos = (loff_t)lblock << inode->i_blkbits; + int ret; + + ret = gfs2_iomap_get(inode, pos, i_blocksize(inode), 0, &iomap, &mp); + release_metapath(&mp); + if (ret == 0) + *dblock = iomap.addr >> inode->i_blkbits; + + return ret; +} + static int gfs2_write_lock(struct inode *inode) { struct gfs2_inode *ip = GFS2_I(inode); @@ -965,15 +991,31 @@ static void gfs2_write_unlock(struct inode *inode) gfs2_glock_dq_uninit(&ip->i_gh); } -static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos, - unsigned copied, struct page *page, - struct iomap *iomap) +static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, + unsigned len, struct iomap *iomap) +{ + struct gfs2_sbd *sdp = GFS2_SB(inode); + + return gfs2_trans_begin(sdp, RES_DINODE + (len >> inode->i_blkbits), 0); +} + +static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, + unsigned copied, struct page *page, + struct iomap *iomap) { struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); - gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + if (page && !gfs2_is_stuffed(ip)) + gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + gfs2_trans_end(sdp); } +static const struct iomap_page_ops gfs2_iomap_page_ops = { + .page_prepare = gfs2_iomap_page_prepare, + .page_done = gfs2_iomap_page_done, +}; + static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, loff_t length, unsigned flags, struct iomap *iomap, @@ -1026,32 +1068,46 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, if (alloc_required) rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks); - ret = gfs2_trans_begin(sdp, rblocks, iomap->length >> inode->i_blkbits); - if (ret) - goto out_trans_fail; + if (unstuff || iomap->type == IOMAP_HOLE) { + struct gfs2_trans *tr; - if (unstuff) { - ret = gfs2_unstuff_dinode(ip, NULL); - if (ret) - goto out_trans_end; - release_metapath(mp); - ret = gfs2_iomap_get(inode, iomap->offset, iomap->length, - flags, iomap, mp); + ret = gfs2_trans_begin(sdp, rblocks, + iomap->length >> inode->i_blkbits); if (ret) - goto out_trans_end; - } + goto out_trans_fail; - if (iomap->type == IOMAP_HOLE) { - ret = gfs2_iomap_alloc(inode, iomap, flags, mp); - if (ret) { - gfs2_trans_end(sdp); - gfs2_inplace_release(ip); - punch_hole(ip, iomap->offset, iomap->length); - goto out_qunlock; + if (unstuff) { + ret = gfs2_unstuff_dinode(ip, NULL); + if (ret) + goto out_trans_end; + release_metapath(mp); + ret = gfs2_iomap_get(inode, iomap->offset, + iomap->length, flags, iomap, mp); + if (ret) + goto out_trans_end; + } + + if (iomap->type == IOMAP_HOLE) { + ret = gfs2_iomap_alloc(inode, iomap, flags, mp); + if (ret) { + gfs2_trans_end(sdp); + gfs2_inplace_release(ip); + punch_hole(ip, iomap->offset, iomap->length); + goto out_qunlock; + } } + + tr = current->journal_info; + if (tr->tr_num_buf_new) + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + else + gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]); + + gfs2_trans_end(sdp); } - if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip)) - iomap->page_done = gfs2_iomap_journaled_page_done; + + if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip)) + iomap->page_ops = &gfs2_iomap_page_ops; return 0; out_trans_end: @@ -1090,10 +1146,6 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->type != IOMAP_MAPPED) ret = -ENOTBLK; } - if (!ret) { - get_bh(mp.mp_bh[0]); - iomap->private = mp.mp_bh[0]; - } release_metapath(&mp); trace_gfs2_iomap_end(ip, iomap, ret); return ret; @@ -1104,27 +1156,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); - struct gfs2_trans *tr = current->journal_info; - struct buffer_head *dibh = iomap->private; if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) != IOMAP_WRITE) goto out; - if (iomap->type != IOMAP_INLINE) { + if (!gfs2_is_stuffed(ip)) gfs2_ordered_add_inode(ip); - if (tr->tr_num_buf_new) - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - else - gfs2_trans_add_meta(ip->i_gl, dibh); - } - - if (inode == sdp->sd_rindex) { + if (inode == sdp->sd_rindex) adjust_fs_space(inode); - sdp->sd_rindex_uptodate = 0; - } - gfs2_trans_end(sdp); gfs2_inplace_release(ip); if (length != written && (iomap->flags & IOMAP_F_NEW)) { @@ -1144,8 +1185,6 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, gfs2_write_unlock(inode); out: - if (dibh) - brelse(dibh); return 0; } diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h index 6b18fb323f0a..19a1fd772c61 100644 --- a/fs/gfs2/bmap.h +++ b/fs/gfs2/bmap.h @@ -64,5 +64,6 @@ extern int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset, extern int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd); extern void gfs2_free_journal_extents(struct gfs2_jdesc *jd); extern int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length); +extern int gfs2_lblk_to_dblk(struct inode *inode, u32 lblock, u64 *dblock); #endif /* __BMAP_DOT_H__ */ diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index daa14ab4e31b..db9a05244a35 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -883,7 +883,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, if (!bh) return NULL; - gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1); + gfs2_trans_remove_revoke(GFS2_SB(inode), bn, 1); gfs2_trans_add_meta(ip->i_gl, bh); gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF); leaf = (struct gfs2_leaf *)bh->b_data; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index d32964cd1117..15c605cfcfc8 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -140,6 +140,7 @@ void gfs2_glock_free(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + BUG_ON(test_bit(GLF_REVOKES, &gl->gl_flags)); rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms); smp_mb(); wake_up_glock(gl); @@ -183,15 +184,19 @@ static int demote_ok(const struct gfs2_glock *gl) void gfs2_glock_add_to_lru(struct gfs2_glock *gl) { + if (!(gl->gl_ops->go_flags & GLOF_LRU)) + return; + spin_lock(&lru_lock); - if (!list_empty(&gl->gl_lru)) - list_del_init(&gl->gl_lru); - else + list_del(&gl->gl_lru); + list_add_tail(&gl->gl_lru, &lru_list); + + if (!test_bit(GLF_LRU, &gl->gl_flags)) { + set_bit(GLF_LRU, &gl->gl_flags); atomic_inc(&lru_count); + } - list_add_tail(&gl->gl_lru, &lru_list); - set_bit(GLF_LRU, &gl->gl_flags); spin_unlock(&lru_lock); } @@ -201,7 +206,7 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) return; spin_lock(&lru_lock); - if (!list_empty(&gl->gl_lru)) { + if (test_bit(GLF_LRU, &gl->gl_flags)) { list_del_init(&gl->gl_lru); atomic_dec(&lru_count); clear_bit(GLF_LRU, &gl->gl_flags); @@ -1159,8 +1164,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) !test_bit(GLF_DEMOTE, &gl->gl_flags)) fast_path = 1; } - if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl) && - (glops->go_flags & GLOF_LRU)) + if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl)) gfs2_glock_add_to_lru(gl); trace_gfs2_glock_queue(gh, 0); @@ -1456,6 +1460,7 @@ __acquires(&lru_lock) if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); + set_bit(GLF_LRU, &gl->gl_flags); atomic_inc(&lru_count); continue; } @@ -1463,7 +1468,6 @@ add_back_to_lru: spin_unlock(&gl->gl_lockref.lock); goto add_back_to_lru; } - clear_bit(GLF_LRU, &gl->gl_flags); gl->gl_lockref.count++; if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1498,6 +1502,7 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); + clear_bit(GLF_LRU, &gl->gl_flags); freed++; continue; } @@ -1796,7 +1801,7 @@ void gfs2_dump_glock(struct seq_file *seq, struct gfs2_glock *gl) state2str(gl->gl_target), state2str(gl->gl_demote_state), dtime, atomic_read(&gl->gl_ail_count), - atomic_read(&gl->gl_revokes), + test_bit(GLF_REVOKES, &gl->gl_flags) ? 1 : 0, (int)gl->gl_lockref.count, gl->gl_hold_time); list_for_each_entry(gh, &gl->gl_holders, gh_list) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 78510ab91835..24ada3ccc525 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -28,6 +28,7 @@ #include "util.h" #include "trans.h" #include "dir.h" +#include "lops.h" struct workqueue_struct *gfs2_freeze_wq; @@ -531,7 +532,7 @@ static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh) if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { j_gl->gl_ops->go_inval(j_gl, DIO_METADATA); - error = gfs2_find_jhead(sdp->sd_jdesc, &head); + error = gfs2_find_jhead(sdp->sd_jdesc, &head, false); if (error) gfs2_consist(sdp); if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index cdf07b408f54..b15755068593 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -345,6 +345,7 @@ enum { GLF_OBJECT = 14, /* Used only for tracing */ GLF_BLOCKING = 15, GLF_INODE_CREATING = 16, /* Inode creation occurring */ + GLF_REVOKES = 17, /* Glock has revokes in queue */ }; struct gfs2_glock { @@ -374,7 +375,6 @@ struct gfs2_glock { struct list_head gl_lru; struct list_head gl_ail_list; atomic_t gl_ail_count; - atomic_t gl_revokes; struct delayed_work gl_work; union { /* For inode and iopen glocks only */ @@ -535,7 +535,7 @@ struct gfs2_jdesc { unsigned long jd_flags; #define JDF_RECOVERY 1 unsigned int jd_jid; - unsigned int jd_blocks; + u32 jd_blocks; int jd_recover_error; /* Replay stuff */ @@ -621,6 +621,7 @@ enum { SDF_SKIP_DLM_UNLOCK = 8, SDF_FORCE_AIL_FLUSH = 9, SDF_AIL1_IO_ERROR = 10, + SDF_FS_FROZEN = 11, }; enum gfs2_freeze_state { @@ -809,8 +810,8 @@ struct gfs2_sbd { atomic_t sd_log_pinned; unsigned int sd_log_num_revoke; - struct list_head sd_log_le_revoke; - struct list_head sd_log_le_ordered; + struct list_head sd_log_revokes; + struct list_head sd_log_ordered; spinlock_t sd_ordered_lock; atomic_t sd_log_thresh1; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index b8830fda51e8..a2e1df488df0 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -551,9 +551,9 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) LIST_HEAD(written); spin_lock(&sdp->sd_ordered_lock); - list_sort(NULL, &sdp->sd_log_le_ordered, &ip_cmp); - while (!list_empty(&sdp->sd_log_le_ordered)) { - ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered); + list_sort(NULL, &sdp->sd_log_ordered, &ip_cmp); + while (!list_empty(&sdp->sd_log_ordered)) { + ip = list_entry(sdp->sd_log_ordered.next, struct gfs2_inode, i_ordered); if (ip->i_inode.i_mapping->nrpages == 0) { test_and_clear_bit(GIF_ORDERED, &ip->i_flags); list_del(&ip->i_ordered); @@ -564,7 +564,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) filemap_fdatawrite(ip->i_inode.i_mapping); spin_lock(&sdp->sd_ordered_lock); } - list_splice(&written, &sdp->sd_log_le_ordered); + list_splice(&written, &sdp->sd_log_ordered); spin_unlock(&sdp->sd_ordered_lock); } @@ -573,8 +573,8 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) struct gfs2_inode *ip; spin_lock(&sdp->sd_ordered_lock); - while (!list_empty(&sdp->sd_log_le_ordered)) { - ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered); + while (!list_empty(&sdp->sd_log_ordered)) { + ip = list_entry(sdp->sd_log_ordered.next, struct gfs2_inode, i_ordered); list_del(&ip->i_ordered); WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags)); if (ip->i_inode.i_mapping->nrpages == 0) @@ -606,9 +606,12 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) gfs2_remove_from_ail(bd); /* drops ref on bh */ bd->bd_bh = NULL; sdp->sd_log_num_revoke++; - atomic_inc(&gl->gl_revokes); + if (!test_bit(GLF_REVOKES, &gl->gl_flags)) { + set_bit(GLF_REVOKES, &gl->gl_flags); + gfs2_glock_hold(gl); + } set_bit(GLF_LFLUSH, &gl->gl_flags); - list_add(&bd->bd_list, &sdp->sd_log_le_revoke); + list_add(&bd->bd_list, &sdp->sd_log_revokes); } void gfs2_write_revokes(struct gfs2_sbd *sdp) @@ -666,11 +669,12 @@ out_of_blocks: } /** - * write_log_header - Write a journal log header buffer at sd_log_flush_head + * gfs2_write_log_header - Write a journal log header buffer at lblock * @sdp: The GFS2 superblock * @jd: journal descriptor of the journal to which we are writing * @seq: sequence number * @tail: tail of the log + * @lblock: value for lh_blkno (block number relative to start of journal) * @flags: log header flags GFS2_LOG_HEAD_* * @op_flags: flags to pass to the bio * @@ -678,7 +682,8 @@ out_of_blocks: */ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, - u64 seq, u32 tail, u32 flags, int op_flags) + u64 seq, u32 tail, u32 lblock, u32 flags, + int op_flags) { struct gfs2_log_header *lh; u32 hash, crc; @@ -686,7 +691,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; struct timespec64 tv; struct super_block *sb = sdp->sd_vfs; - u64 addr; + u64 dblock; lh = page_address(page); clear_page(lh); @@ -699,15 +704,21 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, lh->lh_sequence = cpu_to_be64(seq); lh->lh_flags = cpu_to_be32(flags); lh->lh_tail = cpu_to_be32(tail); - lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head); + lh->lh_blkno = cpu_to_be32(lblock); hash = ~crc32(~0, lh, LH_V1_SIZE); lh->lh_hash = cpu_to_be32(hash); ktime_get_coarse_real_ts64(&tv); lh->lh_nsec = cpu_to_be32(tv.tv_nsec); lh->lh_sec = cpu_to_be64(tv.tv_sec); - addr = gfs2_log_bmap(sdp); - lh->lh_addr = cpu_to_be64(addr); + if (!list_empty(&jd->extent_list)) + dblock = gfs2_log_bmap(sdp); + else { + int ret = gfs2_lblk_to_dblk(jd->jd_inode, lblock, &dblock); + if (gfs2_assert_withdraw(sdp, ret == 0)) + return; + } + lh->lh_addr = cpu_to_be64(dblock); lh->lh_jinode = cpu_to_be64(GFS2_I(jd->jd_inode)->i_no_addr); /* We may only write local statfs, quota, etc., when writing to our @@ -732,8 +743,8 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, sb->s_blocksize - LH_V1_SIZE - 4); lh->lh_crc = cpu_to_be32(crc); - gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags); + gfs2_log_write(sdp, page, sb->s_blocksize, 0, dblock); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags); log_flush_wait(sdp); } @@ -761,7 +772,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags) } sdp->sd_log_idle = (tail == sdp->sd_log_flush_head); gfs2_write_log_header(sdp, sdp->sd_jdesc, sdp->sd_log_sequence++, tail, - flags, op_flags); + sdp->sd_log_flush_head, flags, op_flags); if (sdp->sd_log_tail != tail) log_pull_tail(sdp, tail); @@ -810,7 +821,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) gfs2_ordered_write(sdp); lops_before_commit(sdp, tr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, 0); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE); if (sdp->sd_log_head != sdp->sd_log_flush_head) { log_flush_wait(sdp); diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index 1bc9bd444b28..7a34a3234266 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -59,7 +59,7 @@ static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip) if (!test_bit(GIF_ORDERED, &ip->i_flags)) { spin_lock(&sdp->sd_ordered_lock); if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags)) - list_add(&ip->i_ordered, &sdp->sd_log_le_ordered); + list_add(&ip->i_ordered, &sdp->sd_log_ordered); spin_unlock(&sdp->sd_ordered_lock); } } @@ -70,7 +70,8 @@ extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct, extern void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks); extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks); extern void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, - u64 seq, u32 tail, u32 flags, int op_flags); + u64 seq, u32 tail, u32 lblock, u32 flags, + int op_flags); extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 type); extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 8722c60b11fe..33ab662c9aac 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -17,7 +17,9 @@ #include <linux/bio.h> #include <linux/fs.h> #include <linux/list_sort.h> +#include <linux/blkdev.h> +#include "bmap.h" #include "dir.h" #include "gfs2.h" #include "incore.h" @@ -194,7 +196,6 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, /** * gfs2_end_log_write - end of i/o to the log * @bio: The bio - * @error: Status of i/o request * * Each bio_vec contains either data from the pagecache or data * relating to the log itself. Here we iterate over the bio_vec @@ -207,7 +208,6 @@ static void gfs2_end_log_write(struct bio *bio) struct gfs2_sbd *sdp = bio->bi_private; struct bio_vec *bvec; struct page *page; - int i; struct bvec_iter_all iter_all; if (bio->bi_status) { @@ -216,7 +216,7 @@ static void gfs2_end_log_write(struct bio *bio) wake_up(&sdp->sd_logd_waitq); } - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { page = bvec->bv_page; if (page_has_buffers(page)) gfs2_end_log_write_bh(sdp, bvec, bio->bi_status); @@ -232,20 +232,19 @@ static void gfs2_end_log_write(struct bio *bio) /** * gfs2_log_submit_bio - Submit any pending log bio * @biop: Address of the bio pointer - * @op: REQ_OP - * @op_flags: req_flag_bits + * @opf: REQ_OP | op_flags * * Submit any pending part-built or full bio to the block device. If * there is no pending bio, then this is a no-op. */ -void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags) +void gfs2_log_submit_bio(struct bio **biop, int opf) { struct bio *bio = *biop; if (bio) { struct gfs2_sbd *sdp = bio->bi_private; atomic_inc(&sdp->sd_log_in_flight); - bio_set_op_attrs(bio, op, op_flags); + bio->bi_opf = opf; submit_bio(bio); *biop = NULL; } @@ -306,7 +305,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno, nblk >>= sdp->sd_fsb2bb_shift; if (blkno == nblk && !flush) return bio; - gfs2_log_submit_bio(biop, op, 0); + gfs2_log_submit_bio(biop, op); } *biop = gfs2_log_alloc_bio(sdp, blkno, end_io); @@ -377,6 +376,205 @@ void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) gfs2_log_bmap(sdp)); } +/** + * gfs2_end_log_read - end I/O callback for reads from the log + * @bio: The bio + * + * Simply unlock the pages in the bio. The main thread will wait on them and + * process them in order as necessary. + */ + +static void gfs2_end_log_read(struct bio *bio) +{ + struct page *page; + struct bio_vec *bvec; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bvec, bio, iter_all) { + page = bvec->bv_page; + if (bio->bi_status) { + int err = blk_status_to_errno(bio->bi_status); + + SetPageError(page); + mapping_set_error(page->mapping, err); + } + unlock_page(page); + } + + bio_put(bio); +} + +/** + * gfs2_jhead_pg_srch - Look for the journal head in a given page. + * @jd: The journal descriptor + * @page: The page to look in + * + * Returns: 1 if found, 0 otherwise. + */ + +static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, + struct gfs2_log_header_host *head, + struct page *page) +{ + struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); + struct gfs2_log_header_host uninitialized_var(lh); + void *kaddr = kmap_atomic(page); + unsigned int offset; + bool ret = false; + + for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { + if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { + if (lh.lh_sequence > head->lh_sequence) + *head = lh; + else { + ret = true; + break; + } + } + } + kunmap_atomic(kaddr); + return ret; +} + +/** + * gfs2_jhead_process_page - Search/cleanup a page + * @jd: The journal descriptor + * @index: Index of the page to look into + * @done: If set, perform only cleanup, else search and set if found. + * + * Find the page with 'index' in the journal's mapping. Search the page for + * the journal head if requested (cleanup == false). Release refs on the + * page so the page cache can reclaim it (put_page() twice). We grabbed a + * reference on this page two times, first when we did a find_or_create_page() + * to obtain the page to add it to the bio and second when we do a + * find_get_page() here to get the page to wait on while I/O on it is being + * completed. + * This function is also used to free up a page we might've grabbed but not + * used. Maybe we added it to a bio, but not submitted it for I/O. Or we + * submitted the I/O, but we already found the jhead so we only need to drop + * our references to the page. + */ + +static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index, + struct gfs2_log_header_host *head, + bool *done) +{ + struct page *page; + + page = find_get_page(jd->jd_inode->i_mapping, index); + wait_on_page_locked(page); + + if (PageError(page)) + *done = true; + + if (!*done) + *done = gfs2_jhead_pg_srch(jd, head, page); + + put_page(page); /* Once for find_get_page */ + put_page(page); /* Once more for find_or_create_page */ +} + +/** + * gfs2_find_jhead - find the head of a log + * @jd: The journal descriptor + * @head: The log descriptor for the head of the log is returned here + * + * Do a search of a journal by reading it in large chunks using bios and find + * the valid log entry with the highest sequence number. (i.e. the log head) + * + * Returns: 0 on success, errno otherwise + */ +int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, + bool keep_cache) +{ + struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); + struct address_space *mapping = jd->jd_inode->i_mapping; + unsigned int block = 0, blocks_submitted = 0, blocks_read = 0; + unsigned int bsize = sdp->sd_sb.sb_bsize; + unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift; + unsigned int shift = PAGE_SHIFT - bsize_shift; + unsigned int readhead_blocks = BIO_MAX_PAGES << shift; + struct gfs2_journal_extent *je; + int sz, ret = 0; + struct bio *bio = NULL; + struct page *page = NULL; + bool done = false; + errseq_t since; + + memset(head, 0, sizeof(*head)); + if (list_empty(&jd->extent_list)) + gfs2_map_journal_extents(sdp, jd); + + since = filemap_sample_wb_err(mapping); + list_for_each_entry(je, &jd->extent_list, list) { + for (; block < je->lblock + je->blocks; block++) { + u64 dblock; + + if (!page) { + page = find_or_create_page(mapping, + block >> shift, GFP_NOFS); + if (!page) { + ret = -ENOMEM; + done = true; + goto out; + } + } + + if (bio) { + unsigned int off; + + off = (block << bsize_shift) & ~PAGE_MASK; + sz = bio_add_page(bio, page, bsize, off); + if (sz == bsize) { /* block added */ + if (off + bsize == PAGE_SIZE) { + page = NULL; + goto page_added; + } + continue; + } + blocks_submitted = block + 1; + submit_bio(bio); + bio = NULL; + } + + dblock = je->dblock + (block - je->lblock); + bio = gfs2_log_alloc_bio(sdp, dblock, gfs2_end_log_read); + bio->bi_opf = REQ_OP_READ; + sz = bio_add_page(bio, page, bsize, 0); + gfs2_assert_warn(sdp, sz == bsize); + if (bsize == PAGE_SIZE) + page = NULL; + +page_added: + if (blocks_submitted < blocks_read + readhead_blocks) { + /* Keep at least one bio in flight */ + continue; + } + + gfs2_jhead_process_page(jd, blocks_read >> shift, head, &done); + blocks_read += PAGE_SIZE >> bsize_shift; + if (done) + goto out; /* found */ + } + } + +out: + if (bio) + submit_bio(bio); + while (blocks_read < block) { + gfs2_jhead_process_page(jd, blocks_read >> shift, head, &done); + blocks_read += PAGE_SIZE >> bsize_shift; + } + + if (!ret) + ret = filemap_check_wb_err(mapping, since); + + if (!keep_cache) + truncate_inode_pages(mapping, 0); + + return ret; +} + static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, u32 ld_length, u32 ld_data1) { @@ -530,7 +728,7 @@ static void buf_lo_before_scan(struct gfs2_jdesc *jd, jd->jd_replayed_blocks = 0; } -static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start, +static int buf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start, struct gfs2_log_descriptor *ld, __be64 *ptr, int pass) { @@ -623,7 +821,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { struct gfs2_meta_header *mh; unsigned int offset; - struct list_head *head = &sdp->sd_log_le_revoke; + struct list_head *head = &sdp->sd_log_revokes; struct gfs2_bufdata *bd; struct page *page; unsigned int length; @@ -661,18 +859,35 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { - struct list_head *head = &sdp->sd_log_le_revoke; - struct gfs2_bufdata *bd; - struct gfs2_glock *gl; + struct list_head *head = &sdp->sd_log_revokes; + struct gfs2_bufdata *bd, *tmp; - while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_list); - list_del_init(&bd->bd_list); - gl = bd->bd_gl; - atomic_dec(&gl->gl_revokes); - clear_bit(GLF_LFLUSH, &gl->gl_flags); + /* + * Glocks can be referenced repeatedly on the revoke list, but the list + * only holds one reference. All glocks on the list will have the + * GLF_REVOKES flag set initially. + */ + + list_for_each_entry_safe(bd, tmp, head, bd_list) { + struct gfs2_glock *gl = bd->bd_gl; + + if (test_bit(GLF_REVOKES, &gl->gl_flags)) { + /* Keep each glock on the list exactly once. */ + clear_bit(GLF_REVOKES, &gl->gl_flags); + continue; + } + list_del(&bd->bd_list); kmem_cache_free(gfs2_bufdata_cachep, bd); } + list_for_each_entry_safe(bd, tmp, head, bd_list) { + struct gfs2_glock *gl = bd->bd_gl; + + list_del(&bd->bd_list); + kmem_cache_free(gfs2_bufdata_cachep, bd); + clear_bit(GLF_LFLUSH, &gl->gl_flags); + gfs2_glock_queue_put(gl); + } + /* the list is empty now */ } static void revoke_lo_before_scan(struct gfs2_jdesc *jd, @@ -685,7 +900,7 @@ static void revoke_lo_before_scan(struct gfs2_jdesc *jd, jd->jd_replay_tail = head->lh_tail; } -static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start, +static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, u32 start, struct gfs2_log_descriptor *ld, __be64 *ptr, int pass) { @@ -767,7 +982,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr gfs2_before_commit(sdp, limit, nbuf, &tr->tr_databuf, 1); } -static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start, +static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start, struct gfs2_log_descriptor *ld, __be64 *ptr, int pass) { @@ -853,7 +1068,7 @@ static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) } -const struct gfs2_log_operations gfs2_buf_lops = { +static const struct gfs2_log_operations gfs2_buf_lops = { .lo_before_commit = buf_lo_before_commit, .lo_after_commit = buf_lo_after_commit, .lo_before_scan = buf_lo_before_scan, @@ -862,7 +1077,7 @@ const struct gfs2_log_operations gfs2_buf_lops = { .lo_name = "buf", }; -const struct gfs2_log_operations gfs2_revoke_lops = { +static const struct gfs2_log_operations gfs2_revoke_lops = { .lo_before_commit = revoke_lo_before_commit, .lo_after_commit = revoke_lo_after_commit, .lo_before_scan = revoke_lo_before_scan, @@ -871,7 +1086,7 @@ const struct gfs2_log_operations gfs2_revoke_lops = { .lo_name = "revoke", }; -const struct gfs2_log_operations gfs2_databuf_lops = { +static const struct gfs2_log_operations gfs2_databuf_lops = { .lo_before_commit = databuf_lo_before_commit, .lo_after_commit = databuf_lo_after_commit, .lo_scan_elements = databuf_lo_scan_elements, diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 711c4d89c063..f195ffb435ac 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -20,18 +20,15 @@ ((sizeof(struct gfs2_log_descriptor) + (2 * sizeof(__be64) - 1)) & \ ~(2 * sizeof(__be64) - 1)) -extern const struct gfs2_log_operations gfs2_glock_lops; -extern const struct gfs2_log_operations gfs2_buf_lops; -extern const struct gfs2_log_operations gfs2_revoke_lops; -extern const struct gfs2_log_operations gfs2_databuf_lops; - extern const struct gfs2_log_operations *gfs2_log_ops[]; extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp); extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, unsigned size, unsigned offset, u64 blkno); extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); -extern void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags); +extern void gfs2_log_submit_bio(struct bio **biop, int opf); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); +extern int gfs2_find_jhead(struct gfs2_jdesc *jd, + struct gfs2_log_header_host *head, bool keep_cache); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { @@ -77,7 +74,7 @@ static inline void lops_before_scan(struct gfs2_jdesc *jd, gfs2_log_ops[x]->lo_before_scan(jd, head, pass); } -static inline int lops_scan_elements(struct gfs2_jdesc *jd, unsigned int start, +static inline int lops_scan_elements(struct gfs2_jdesc *jd, u32 start, struct gfs2_log_descriptor *ld, __be64 *ptr, unsigned int pass) diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 136484ef35d3..c700738de1f7 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -59,7 +59,6 @@ static void gfs2_init_glock_once(void *foo) INIT_LIST_HEAD(&gl->gl_lru); INIT_LIST_HEAD(&gl->gl_ail_list); atomic_set(&gl->gl_ail_count, 0); - atomic_set(&gl->gl_revokes, 0); } static void gfs2_init_gl_aspace_once(void *foo) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 3201342404a7..ff86e1d4f8ff 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -189,10 +189,9 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno) static void gfs2_meta_read_endio(struct bio *bio) { struct bio_vec *bvec; - int i; struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; struct buffer_head *bh = page_buffers(page); unsigned int len = bvec->bv_len; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index b041cb8ae383..46f6615eaf12 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -41,6 +41,7 @@ #include "dir.h" #include "meta_io.h" #include "trace_gfs2.h" +#include "lops.h" #define DO 0 #define UNDO 1 @@ -117,8 +118,8 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) spin_lock_init(&sdp->sd_log_lock); atomic_set(&sdp->sd_log_pinned, 0); - INIT_LIST_HEAD(&sdp->sd_log_le_revoke); - INIT_LIST_HEAD(&sdp->sd_log_le_ordered); + INIT_LIST_HEAD(&sdp->sd_log_revokes); + INIT_LIST_HEAD(&sdp->sd_log_ordered); spin_lock_init(&sdp->sd_ordered_lock); init_waitqueue_head(&sdp->sd_log_waitq); @@ -616,7 +617,7 @@ static int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd) fs_err(sdp, "Error checking journal for spectator mount.\n"); goto out_unlock; } - error = gfs2_find_jhead(jd, &head); + error = gfs2_find_jhead(jd, &head, false); if (error) { fs_err(sdp, "Error parsing journal for spectator mount.\n"); goto out_unlock; diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 2dac43065382..389b3ef77e20 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -182,129 +182,6 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk, } /** - * find_good_lh - find a good log header - * @jd: the journal - * @blk: the segment to start searching from - * @lh: the log header to fill in - * @forward: if true search forward in the log, else search backward - * - * Call get_log_header() to get a log header for a segment, but if the - * segment is bad, either scan forward or backward until we find a good one. - * - * Returns: errno - */ - -static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk, - struct gfs2_log_header_host *head) -{ - unsigned int orig_blk = *blk; - int error; - - for (;;) { - error = get_log_header(jd, *blk, head); - if (error <= 0) - return error; - - if (++*blk == jd->jd_blocks) - *blk = 0; - - if (*blk == orig_blk) { - gfs2_consist_inode(GFS2_I(jd->jd_inode)); - return -EIO; - } - } -} - -/** - * jhead_scan - make sure we've found the head of the log - * @jd: the journal - * @head: this is filled in with the log descriptor of the head - * - * At this point, seg and lh should be either the head of the log or just - * before. Scan forward until we find the head. - * - * Returns: errno - */ - -static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) -{ - unsigned int blk = head->lh_blkno; - struct gfs2_log_header_host lh; - int error; - - for (;;) { - if (++blk == jd->jd_blocks) - blk = 0; - - error = get_log_header(jd, blk, &lh); - if (error < 0) - return error; - if (error == 1) - continue; - - if (lh.lh_sequence == head->lh_sequence) { - gfs2_consist_inode(GFS2_I(jd->jd_inode)); - return -EIO; - } - if (lh.lh_sequence < head->lh_sequence) - break; - - *head = lh; - } - - return 0; -} - -/** - * gfs2_find_jhead - find the head of a log - * @jd: the journal - * @head: the log descriptor for the head of the log is returned here - * - * Do a binary search of a journal and find the valid log entry with the - * highest sequence number. (i.e. the log head) - * - * Returns: errno - */ - -int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) -{ - struct gfs2_log_header_host lh_1, lh_m; - u32 blk_1, blk_2, blk_m; - int error; - - blk_1 = 0; - blk_2 = jd->jd_blocks - 1; - - for (;;) { - blk_m = (blk_1 + blk_2) / 2; - - error = find_good_lh(jd, &blk_1, &lh_1); - if (error) - return error; - - error = find_good_lh(jd, &blk_m, &lh_m); - if (error) - return error; - - if (blk_1 == blk_m || blk_m == blk_2) - break; - - if (lh_1.lh_sequence <= lh_m.lh_sequence) - blk_1 = blk_m; - else - blk_2 = blk_m; - } - - error = jhead_scan(jd, &lh_1); - if (error) - return error; - - *head = lh_1; - - return error; -} - -/** * foreach_descriptor - go through the active part of the log * @jd: the journal * @start: the first log header in the active region @@ -316,7 +193,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) * Returns: errno */ -static int foreach_descriptor(struct gfs2_jdesc *jd, unsigned int start, +static int foreach_descriptor(struct gfs2_jdesc *jd, u32 start, unsigned int end, int pass) { struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); @@ -386,10 +263,12 @@ static void clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) { struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); + u32 lblock = head->lh_blkno; - sdp->sd_log_flush_head = head->lh_blkno; - gfs2_replay_incr_blk(jd, &sdp->sd_log_flush_head); - gfs2_write_log_header(sdp, jd, head->lh_sequence + 1, 0, + gfs2_replay_incr_blk(jd, &lblock); + if (jd->jd_jid == sdp->sd_lockstruct.ls_jid) + sdp->sd_log_flush_head = lblock; + gfs2_write_log_header(sdp, jd, head->lh_sequence + 1, 0, lblock, GFS2_LOG_HEAD_UNMOUNT | GFS2_LOG_HEAD_RECOVERY, REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC); } @@ -467,7 +346,7 @@ void gfs2_recover_func(struct work_struct *work) if (error) goto fail_gunlock_ji; - error = gfs2_find_jhead(jd, &head); + error = gfs2_find_jhead(jd, &head, true); if (error) goto fail_gunlock_ji; t_jhd = ktime_get(); diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 11d81248be85..1831a1974c8c 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -14,7 +14,7 @@ extern struct workqueue_struct *gfs_recovery_wq; -static inline void gfs2_replay_incr_blk(struct gfs2_jdesc *jd, unsigned int *blk) +static inline void gfs2_replay_incr_blk(struct gfs2_jdesc *jd, u32 *blk) { if (++*blk == jd->jd_blocks) *blk = 0; @@ -27,8 +27,6 @@ extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where); extern void gfs2_revoke_clean(struct gfs2_jdesc *jd); -extern int gfs2_find_jhead(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait); extern void gfs2_recover_func(struct work_struct *work); extern int __get_log_header(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 17a8d3b43990..15d6e32de55f 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1729,25 +1729,22 @@ fail: static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext, const struct gfs2_inode *ip, bool nowrap) { + bool scan_from_start = rbm->bii == 0 && rbm->offset == 0; struct buffer_head *bh; - int initial_bii; - u32 initial_offset; - int first_bii = rbm->bii; - u32 first_offset = rbm->offset; + int last_bii; u32 offset; u8 *buffer; - int n = 0; - int iters = rbm->rgd->rd_length; + bool wrapped = false; int ret; struct gfs2_bitmap *bi; struct gfs2_extent maxext = { .rbm.rgd = rbm->rgd, }; - /* If we are not starting at the beginning of a bitmap, then we - * need to add one to the bitmap count to ensure that we search - * the starting bitmap twice. + /* + * Determine the last bitmap to search. If we're not starting at the + * beginning of a bitmap, we need to search that bitmap twice to scan + * the entire resource group. */ - if (rbm->offset != 0) - iters++; + last_bii = rbm->bii - (rbm->offset == 0); while(1) { bi = rbm_bi(rbm); @@ -1761,47 +1758,46 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext, WARN_ON(!buffer_uptodate(bh)); if (state != GFS2_BLKST_UNLINKED && bi->bi_clone) buffer = bi->bi_clone + bi->bi_offset; - initial_offset = rbm->offset; offset = gfs2_bitfit(buffer, bi->bi_bytes, rbm->offset, state); - if (offset == BFITNOENT) - goto bitmap_full; + if (offset == BFITNOENT) { + if (state == GFS2_BLKST_FREE && rbm->offset == 0) + set_bit(GBF_FULL, &bi->bi_flags); + goto next_bitmap; + } rbm->offset = offset; if (ip == NULL) return 0; - initial_bii = rbm->bii; ret = gfs2_reservation_check_and_update(rbm, ip, minext ? *minext : 0, &maxext); if (ret == 0) return 0; - if (ret > 0) { - n += (rbm->bii - initial_bii); + if (ret > 0) goto next_iter; - } if (ret == -E2BIG) { rbm->bii = 0; rbm->offset = 0; - n += (rbm->bii - initial_bii); goto res_covered_end_of_rgrp; } return ret; -bitmap_full: /* Mark bitmap as full and fall through */ - if ((state == GFS2_BLKST_FREE) && initial_offset == 0) - set_bit(GBF_FULL, &bi->bi_flags); - next_bitmap: /* Find next bitmap in the rgrp */ rbm->offset = 0; rbm->bii++; if (rbm->bii == rbm->rgd->rd_length) rbm->bii = 0; res_covered_end_of_rgrp: - if ((rbm->bii == 0) && nowrap) - break; - n++; + if (rbm->bii == 0) { + if (wrapped) + break; + wrapped = true; + if (nowrap) + break; + } next_iter: - if (n >= iters) + /* Have we scanned the entire resource group? */ + if (wrapped && rbm->bii > last_bii) break; } @@ -1811,8 +1807,8 @@ next_iter: /* If the extent was too small, and it's smaller than the smallest to have failed before, remember for future reference that it's useless to search this rgrp again for this amount or more. */ - if ((first_offset == 0) && (first_bii == 0) && - (*minext < rbm->rgd->rd_extfail_pt)) + if (wrapped && (scan_from_start || rbm->bii > last_bii) && + *minext < rbm->rgd->rd_extfail_pt) rbm->rgd->rd_extfail_pt = *minext; /* If the maximum extent we found is big enough to fulfill the @@ -2444,7 +2440,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, gfs2_statfs_change(sdp, 0, -(s64)*nblocks, dinode ? 1 : 0); if (dinode) - gfs2_trans_add_unrevoke(sdp, block, *nblocks); + gfs2_trans_remove_revoke(sdp, block, *nblocks); gfs2_quota_change(ip, *nblocks, ip->i_inode.i_uid, ip->i_inode.i_gid); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index ca71163ff7cf..fbf6b1fd330b 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -45,6 +45,7 @@ #include "util.h" #include "sys.h" #include "xattr.h" +#include "lops.h" #define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) @@ -425,7 +426,7 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) j_gl->gl_ops->go_inval(j_gl, DIO_METADATA); - error = gfs2_find_jhead(sdp->sd_jdesc, &head); + error = gfs2_find_jhead(sdp->sd_jdesc, &head, false); if (error) goto fail; @@ -680,7 +681,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp, error = gfs2_jdesc_check(jd); if (error) break; - error = gfs2_find_jhead(jd, &lh); + error = gfs2_find_jhead(jd, &lh, false); if (error) break; if (!(lh.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) { @@ -973,8 +974,7 @@ void gfs2_freeze_func(struct work_struct *work) if (error) { printk(KERN_INFO "GFS2: couldn't get freeze lock : %d\n", error); gfs2_assert_withdraw(sdp, 0); - } - else { + } else { atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); error = thaw_super(sb); if (error) { @@ -987,6 +987,8 @@ void gfs2_freeze_func(struct work_struct *work) gfs2_glock_dq_uninit(&freeze_gh); } deactivate_super(sb); + clear_bit_unlock(SDF_FS_FROZEN, &sdp->sd_flags); + wake_up_bit(&sdp->sd_flags, SDF_FS_FROZEN); return; } @@ -1029,6 +1031,7 @@ static int gfs2_freeze(struct super_block *sb) msleep(1000); } error = 0; + set_bit(SDF_FS_FROZEN, &sdp->sd_flags); out: mutex_unlock(&sdp->sd_freeze_mutex); return error; @@ -1053,7 +1056,7 @@ static int gfs2_unfreeze(struct super_block *sb) gfs2_glock_dq_uninit(&sdp->sd_freeze_gh); mutex_unlock(&sdp->sd_freeze_mutex); - return 0; + return wait_on_bit(&sdp->sd_flags, SDF_FS_FROZEN, TASK_INTERRUPTIBLE); } /** @@ -1474,7 +1477,7 @@ static void gfs2_final_release_pages(struct gfs2_inode *ip) truncate_inode_pages(gfs2_glock2aspace(ip->i_gl), 0); truncate_inode_pages(&inode->i_data, 0); - if (atomic_read(&gl->gl_revokes) == 0) { + if (!test_bit(GLF_REVOKES, &gl->gl_flags)) { clear_bit(GLF_LFLUSH, &gl->gl_flags); clear_bit(GLF_DIRTY, &gl->gl_flags); } @@ -1630,8 +1633,6 @@ alloc_failed: goto out_truncate; } - /* Case 1 starts here */ - if (S_ISDIR(inode->i_mode) && (ip->i_diskflags & GFS2_DIF_EXHASH)) { error = gfs2_dir_exhash_dealloc(ip); @@ -1670,7 +1671,6 @@ out_truncate: write_inode_now(inode, 1); gfs2_ail_flush(ip->i_gl, 0); - /* Case 2 starts here */ error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); if (error) goto out_unlock; @@ -1680,7 +1680,6 @@ out_truncate: gfs2_trans_end(sdp); out_unlock: - /* Error path for case 1 */ if (gfs2_rs_active(&ip->i_res)) gfs2_rs_deltree(&ip->i_res); @@ -1699,7 +1698,6 @@ out_unlock: if (error && error != GLR_TRYFAILED && error != -EROFS) fs_warn(sdp, "gfs2_evict_inode: %d\n", error); out: - /* Case 3 starts here */ truncate_inode_pages_final(&inode->i_data); gfs2_rsqa_delete(ip, NULL); gfs2_ordered_del_inode(ip); @@ -1736,20 +1734,14 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb) return &ip->i_inode; } -static void gfs2_i_callback(struct rcu_head *head) -{ - struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(gfs2_inode_cachep, inode); -} - -static void gfs2_destroy_inode(struct inode *inode) +static void gfs2_free_inode(struct inode *inode) { - call_rcu(&inode->i_rcu, gfs2_i_callback); + kmem_cache_free(gfs2_inode_cachep, GFS2_I(inode)); } const struct super_operations gfs2_super_ops = { .alloc_inode = gfs2_alloc_inode, - .destroy_inode = gfs2_destroy_inode, + .free_inode = gfs2_free_inode, .write_inode = gfs2_write_inode, .dirty_inode = gfs2_dirty_inode, .evict_inode = gfs2_evict_inode, diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 1787d295834e..08e4996adc23 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -650,7 +650,6 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) char ro[20]; char spectator[20]; char *envp[] = { ro, spectator, NULL }; - int sysfs_frees_sdp = 0; sprintf(ro, "RDONLY=%d", sb_rdonly(sb)); sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0); @@ -661,8 +660,6 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) if (error) goto fail_reg; - sysfs_frees_sdp = 1; /* Freeing sdp is now done by sysfs calling - function gfs2_sbd_release. */ error = sysfs_create_group(&sdp->sd_kobj, &tune_group); if (error) goto fail_reg; @@ -687,10 +684,7 @@ fail_tune: fail_reg: free_percpu(sdp->sd_lkstats); fs_err(sdp, "error %d adding sysfs files\n", error); - if (sysfs_frees_sdp) - kobject_put(&sdp->sd_kobj); - else - kfree(sdp); + kobject_put(&sdp->sd_kobj); sb->s_fs_info = NULL; return error; } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index cd9a94a6b5bb..d328da7cde36 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -253,14 +253,14 @@ void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) tr->tr_num_revoke++; } -void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) +void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) { struct gfs2_bufdata *bd, *tmp; struct gfs2_trans *tr = current->journal_info; unsigned int n = len; gfs2_log_lock(sdp); - list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_list) { + list_for_each_entry_safe(bd, tmp, &sdp->sd_log_revokes, bd_list) { if ((bd->bd_blkno >= blkno) && (bd->bd_blkno < (blkno + len))) { list_del_init(&bd->bd_list); gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke); diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h index ad70087d0597..1e39f056ccb7 100644 --- a/fs/gfs2/trans.h +++ b/fs/gfs2/trans.h @@ -44,6 +44,6 @@ extern void gfs2_trans_end(struct gfs2_sbd *sdp); extern void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh); extern void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh); extern void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd); -extern void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len); +extern void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len); #endif /* __TRANS_DOT_H__ */ diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 996c915a9c97..675e704830df 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -631,7 +631,7 @@ static int ea_alloc_blk(struct gfs2_inode *ip, struct buffer_head **bhp) error = gfs2_alloc_blocks(ip, &block, &n, 0, NULL); if (error) return error; - gfs2_trans_add_unrevoke(sdp, block, 1); + gfs2_trans_remove_revoke(sdp, block, 1); *bhp = gfs2_meta_new(ip->i_gl, block); gfs2_trans_add_meta(ip->i_gl, *bhp); gfs2_metatype_set(*bhp, GFS2_METATYPE_EA, GFS2_FORMAT_EA); @@ -693,7 +693,7 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea, error = gfs2_alloc_blocks(ip, &block, &n, 0, NULL); if (error) return error; - gfs2_trans_add_unrevoke(sdp, block, 1); + gfs2_trans_remove_revoke(sdp, block, 1); bh = gfs2_meta_new(ip->i_gl, block); gfs2_trans_add_meta(ip->i_gl, bh); gfs2_metatype_set(bh, GFS2_METATYPE_ED, GFS2_FORMAT_ED); @@ -997,7 +997,7 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er, error = gfs2_alloc_blocks(ip, &blk, &n, 0, NULL); if (error) return error; - gfs2_trans_add_unrevoke(sdp, blk, 1); + gfs2_trans_remove_revoke(sdp, blk, 1); indbh = gfs2_meta_new(ip->i_gl, blk); gfs2_trans_add_meta(ip->i_gl, indbh); gfs2_metatype_set(indbh, GFS2_METATYPE_IN, GFS2_FORMAT_IN); diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 173876782f73..c33324686d89 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -167,20 +167,14 @@ static struct inode *hfs_alloc_inode(struct super_block *sb) return i ? &i->vfs_inode : NULL; } -static void hfs_i_callback(struct rcu_head *head) +static void hfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(hfs_inode_cachep, HFS_I(inode)); } -static void hfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, hfs_i_callback); -} - static const struct super_operations hfs_super_operations = { .alloc_inode = hfs_alloc_inode, - .destroy_inode = hfs_destroy_inode, + .free_inode = hfs_free_inode, .write_inode = hfs_write_inode, .evict_inode = hfs_evict_inode, .put_super = hfs_put_super, diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index eb4535eba95d..0cc5feff76cd 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -18,7 +18,7 @@ #include <linux/nls.h> static struct inode *hfsplus_alloc_inode(struct super_block *sb); -static void hfsplus_destroy_inode(struct inode *inode); +static void hfsplus_free_inode(struct inode *inode); #include "hfsplus_fs.h" #include "xattr.h" @@ -361,7 +361,7 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data) static const struct super_operations hfsplus_sops = { .alloc_inode = hfsplus_alloc_inode, - .destroy_inode = hfsplus_destroy_inode, + .free_inode = hfsplus_free_inode, .write_inode = hfsplus_write_inode, .evict_inode = hfsplus_evict_inode, .put_super = hfsplus_put_super, @@ -628,18 +628,11 @@ static struct inode *hfsplus_alloc_inode(struct super_block *sb) return i ? &i->vfs_inode : NULL; } -static void hfsplus_i_callback(struct rcu_head *head) +static void hfsplus_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(hfsplus_inode_cachep, HFSPLUS_I(inode)); } -static void hfsplus_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, hfsplus_i_callback); -} - #define HFSPLUS_INODE_SIZE sizeof(struct hfsplus_inode_info) static struct dentry *hfsplus_mount(struct file_system_type *fs_type, diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h index 33b8423ef0c9..f4295aa19350 100644 --- a/fs/hostfs/hostfs.h +++ b/fs/hostfs/hostfs.h @@ -87,7 +87,7 @@ extern int do_mkdir(const char *file, int mode); extern int hostfs_do_rmdir(const char *file); extern int do_mknod(const char *file, int mode, unsigned int major, unsigned int minor); -extern int link_file(const char *from, const char *to); +extern int link_file(const char *to, const char *from); extern int hostfs_do_readlink(char *file, char *buf, int size); extern int rename_file(char *from, char *to); extern int rename2_file(char *from, char *to, unsigned int flags); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 444c7b170359..5a7eb0c79839 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -243,17 +243,11 @@ static void hostfs_evict_inode(struct inode *inode) } } -static void hostfs_i_callback(struct rcu_head *head) +static void hostfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kfree(HOSTFS_I(inode)); } -static void hostfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, hostfs_i_callback); -} - static int hostfs_show_options(struct seq_file *seq, struct dentry *root) { const char *root_path = root->d_sb->s_fs_info; @@ -270,7 +264,7 @@ static int hostfs_show_options(struct seq_file *seq, struct dentry *root) static const struct super_operations hostfs_sbops = { .alloc_inode = hostfs_alloc_inode, - .destroy_inode = hostfs_destroy_inode, + .free_inode = hostfs_free_inode, .evict_inode = hostfs_evict_inode, .statfs = hostfs_statfs, .show_options = hostfs_show_options, diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index f2c3ebcd309c..ed4264bca790 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -238,17 +238,11 @@ static struct inode *hpfs_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void hpfs_i_callback(struct rcu_head *head) +static void hpfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(hpfs_inode_cachep, hpfs_i(inode)); } -static void hpfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, hpfs_i_callback); -} - static void init_once(void *foo) { struct hpfs_inode_info *ei = (struct hpfs_inode_info *) foo; @@ -532,7 +526,7 @@ static int hpfs_show_options(struct seq_file *seq, struct dentry *root) static const struct super_operations hpfs_sops = { .alloc_inode = hpfs_alloc_inode, - .destroy_inode = hpfs_destroy_inode, + .free_inode = hpfs_free_inode, .evict_inode = hpfs_evict_inode, .put_super = hpfs_put_super, .statfs = hpfs_statfs, diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index ec32fece5e1e..1dcc57189382 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -440,9 +440,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, u32 hash; index = page->index; - hash = hugetlb_fault_mutex_hash(h, current->mm, - &pseudo_vma, - mapping, index, 0); + hash = hugetlb_fault_mutex_hash(h, mapping, index, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -499,8 +497,15 @@ static void hugetlbfs_evict_inode(struct inode *inode) struct resv_map *resv_map; remove_inode_hugepages(inode, 0, LLONG_MAX); - resv_map = (struct resv_map *)inode->i_mapping->private_data; - /* root inode doesn't have the resv_map, so we should check it */ + + /* + * Get the resv_map from the address space embedded in the inode. + * This is the address space which points to any resv_map allocated + * at inode creation time. If this is a device special inode, + * i_mapping may not point to the original address space. + */ + resv_map = (struct resv_map *)(&inode->i_data)->private_data; + /* Only regular and link inodes have associated reserve maps */ if (resv_map) resv_map_release(&resv_map->refs); clear_inode(inode); @@ -639,8 +644,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ - hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping, - index, addr); + hash = hugetlb_fault_mutex_hash(h, mapping, index, addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ @@ -755,11 +759,17 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev) { struct inode *inode; - struct resv_map *resv_map; + struct resv_map *resv_map = NULL; - resv_map = resv_map_alloc(); - if (!resv_map) - return NULL; + /* + * Reserve maps are only needed for inodes that can have associated + * page allocations. + */ + if (S_ISREG(mode) || S_ISLNK(mode)) { + resv_map = resv_map_alloc(); + if (!resv_map) + return NULL; + } inode = new_inode(sb); if (inode) { @@ -794,8 +804,10 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; } lockdep_annotate_inode_mutex_key(inode); - } else - kref_put(&resv_map->refs, resv_map_release); + } else { + if (resv_map) + kref_put(&resv_map->refs, resv_map_release); + } return inode; } @@ -1043,9 +1055,8 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) return &p->vfs_inode; } -static void hugetlbfs_i_callback(struct rcu_head *head) +static void hugetlbfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode)); } @@ -1053,7 +1064,6 @@ static void hugetlbfs_destroy_inode(struct inode *inode) { hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb)); mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy); - call_rcu(&inode->i_rcu, hugetlbfs_i_callback); } static const struct address_space_operations hugetlbfs_aops = { @@ -1100,6 +1110,7 @@ static const struct inode_operations hugetlbfs_inode_operations = { static const struct super_operations hugetlbfs_ops = { .alloc_inode = hugetlbfs_alloc_inode, + .free_inode = hugetlbfs_free_inode, .destroy_inode = hugetlbfs_destroy_inode, .evict_inode = hugetlbfs_evict_inode, .statfs = hugetlbfs_statfs, diff --git a/fs/inode.c b/fs/inode.c index e9d97add2b36..e9d18b2c3f91 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -202,12 +202,28 @@ out: } EXPORT_SYMBOL(inode_init_always); +void free_inode_nonrcu(struct inode *inode) +{ + kmem_cache_free(inode_cachep, inode); +} +EXPORT_SYMBOL(free_inode_nonrcu); + +static void i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + if (inode->free_inode) + inode->free_inode(inode); + else + free_inode_nonrcu(inode); +} + static struct inode *alloc_inode(struct super_block *sb) { + const struct super_operations *ops = sb->s_op; struct inode *inode; - if (sb->s_op->alloc_inode) - inode = sb->s_op->alloc_inode(sb); + if (ops->alloc_inode) + inode = ops->alloc_inode(sb); else inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL); @@ -215,22 +231,19 @@ static struct inode *alloc_inode(struct super_block *sb) return NULL; if (unlikely(inode_init_always(sb, inode))) { - if (inode->i_sb->s_op->destroy_inode) - inode->i_sb->s_op->destroy_inode(inode); - else - kmem_cache_free(inode_cachep, inode); + if (ops->destroy_inode) { + ops->destroy_inode(inode); + if (!ops->free_inode) + return NULL; + } + inode->free_inode = ops->free_inode; + i_callback(&inode->i_rcu); return NULL; } return inode; } -void free_inode_nonrcu(struct inode *inode) -{ - kmem_cache_free(inode_cachep, inode); -} -EXPORT_SYMBOL(free_inode_nonrcu); - void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); @@ -253,20 +266,19 @@ void __destroy_inode(struct inode *inode) } EXPORT_SYMBOL(__destroy_inode); -static void i_callback(struct rcu_head *head) -{ - struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(inode_cachep, inode); -} - static void destroy_inode(struct inode *inode) { + const struct super_operations *ops = inode->i_sb->s_op; + BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); - if (inode->i_sb->s_op->destroy_inode) - inode->i_sb->s_op->destroy_inode(inode); - else - call_rcu(&inode->i_rcu, i_callback); + if (ops->destroy_inode) { + ops->destroy_inode(inode); + if (!ops->free_inode) + return; + } + inode->free_inode = ops->free_inode; + call_rcu(&inode->i_rcu, i_callback); } /** @@ -1601,7 +1613,7 @@ EXPORT_SYMBOL(bmap); * passed since the last atime update. */ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, - struct timespec now) + struct timespec64 now) { if (!(mnt->mnt_flags & MNT_RELATIME)) @@ -1702,7 +1714,7 @@ bool atime_needs_update(const struct path *path, struct inode *inode) now = current_time(inode); - if (!relatime_need_update(mnt, inode, timespec64_to_timespec(now))) + if (!relatime_need_update(mnt, inode, now)) return false; if (timespec64_equal(&inode->i_atime, &now)) @@ -1817,8 +1829,13 @@ int file_remove_privs(struct file *file) int kill; int error = 0; - /* Fast path for nothing security related */ - if (IS_NOSEC(inode)) + /* + * Fast path for nothing security related. + * As well for non-regular files, e.g. blkdev inodes. + * For example, blkdev_write_iter() might get here + * trying to remove privs which it is not allowed to. + */ + if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); diff --git a/fs/internal.h b/fs/internal.h index 6a8b71643af4..0010889f2e85 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -44,7 +44,7 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait) extern void guard_bio_eod(int rw, struct bio *bio); extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len, get_block_t *get_block, struct iomap *iomap); -int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, +void __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, struct page *page); /* @@ -55,8 +55,11 @@ extern void __init chrdev_init(void); /* * fs_context.c */ +extern const struct fs_context_operations legacy_fs_context_ops; extern int parse_monolithic_mount_data(struct fs_context *, void *); extern void fc_drop_locked(struct fs_context *); +extern void vfs_clean_context(struct fs_context *fc); +extern int finish_clean_context(struct fs_context *fc); /* * namei.c @@ -89,11 +92,10 @@ extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); -extern int __mnt_want_write(struct vfsmount *); extern int __mnt_want_write_file(struct file *); -extern void __mnt_drop_write(struct vfsmount *); extern void __mnt_drop_write_file(struct file *); +extern void dissolve_on_fput(struct vfsmount *); /* * fs_struct.c */ @@ -157,6 +159,7 @@ extern struct dentry *__d_alloc(struct super_block *, const struct qstr *); extern int d_set_mounted(struct dentry *dentry); extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc); extern struct dentry *d_alloc_cursor(struct dentry *); +extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); /* * read_write.c diff --git a/fs/io_uring.c b/fs/io_uring.c index bbdbd56cf2ac..310f8d17c53e 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4,15 +4,28 @@ * supporting fast/efficient IO. * * A note on the read/write ordering memory barriers that are matched between - * the application and kernel side. When the application reads the CQ ring - * tail, it must use an appropriate smp_rmb() to order with the smp_wmb() - * the kernel uses after writing the tail. Failure to do so could cause a - * delay in when the application notices that completion events available. - * This isn't a fatal condition. Likewise, the application must use an - * appropriate smp_wmb() both before writing the SQ tail, and after writing - * the SQ tail. The first one orders the sqe writes with the tail write, and - * the latter is paired with the smp_rmb() the kernel will issue before - * reading the SQ tail on submission. + * the application and kernel side. + * + * After the application reads the CQ ring tail, it must use an + * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses + * before writing the tail (using smp_load_acquire to read the tail will + * do). It also needs a smp_mb() before updating CQ head (ordering the + * entry load(s) with the head store), pairing with an implicit barrier + * through a control-dependency in io_get_cqring (smp_store_release to + * store head will do). Failure to do so could lead to reading invalid + * CQ entries. + * + * Likewise, the application must use an appropriate smp_wmb() before + * writing the SQ tail (ordering SQ entry stores with the tail store), + * which pairs with smp_load_acquire in io_get_sqring (smp_store_release + * to store the tail will do). And it needs a barrier ordering the SQ + * head load before writing new SQ entries (smp_load_acquire to read + * head will do). + * + * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application + * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after* + * updating the SQ tail; a full memory barrier smp_mb() is needed + * between. * * Also see the examples in the liburing library: * @@ -70,20 +83,108 @@ struct io_uring { u32 tail ____cacheline_aligned_in_smp; }; +/* + * This data is shared with the application through the mmap at offset + * IORING_OFF_SQ_RING. + * + * The offsets to the member fields are published through struct + * io_sqring_offsets when calling io_uring_setup. + */ struct io_sq_ring { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The kernel controls head and the application controls tail. + */ struct io_uring r; + /* + * Bitmask to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ u32 ring_mask; + /* Ring size (constant, power of 2) */ u32 ring_entries; + /* + * Number of invalid entries dropped by the kernel due to + * invalid index stored in array + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * After a new SQ head value was read by the application this + * counter includes all submissions that were dropped reaching + * the new SQ head (and possibly more). + */ u32 dropped; + /* + * Runtime flags + * + * Written by the kernel, shouldn't be modified by the + * application. + * + * The application needs a full memory barrier before checking + * for IORING_SQ_NEED_WAKEUP after updating the sq tail. + */ u32 flags; + /* + * Ring buffer of indices into array of io_uring_sqe, which is + * mmapped by the application using the IORING_OFF_SQES offset. + * + * This indirection could e.g. be used to assign fixed + * io_uring_sqe entries to operations and only submit them to + * the queue when needed. + * + * The kernel modifies neither the indices array nor the entries + * array. + */ u32 array[]; }; +/* + * This data is shared with the application through the mmap at offset + * IORING_OFF_CQ_RING. + * + * The offsets to the member fields are published through struct + * io_cqring_offsets when calling io_uring_setup. + */ struct io_cq_ring { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The application controls head and the kernel tail. + */ struct io_uring r; + /* + * Bitmask to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ u32 ring_mask; + /* Ring size (constant, power of 2) */ u32 ring_entries; + /* + * Number of completion events lost because the queue was full; + * this should be avoided by the application by making sure + * there are not more requests pending thatn there is space in + * the completion queue. + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * As completion events come in out of order this counter is not + * ordered with any other data. + */ u32 overflow; + /* + * Ring buffer of completion events. + * + * The kernel writes completion events fresh every time they are + * produced, so the application is allowed to modify pending + * entries. + */ struct io_uring_cqe cqes[]; }; @@ -121,6 +222,8 @@ struct io_ring_ctx { unsigned sq_mask; unsigned sq_thread_idle; struct io_uring_sqe *sq_sqes; + + struct list_head defer_list; } ____cacheline_aligned_in_smp; /* IO offload */ @@ -128,7 +231,6 @@ struct io_ring_ctx { struct task_struct *sqo_thread; /* if using sq thread polling */ struct mm_struct *sqo_mm; wait_queue_head_t sqo_wait; - unsigned sqo_stop; struct { /* CQ ring */ @@ -138,6 +240,7 @@ struct io_ring_ctx { unsigned cq_mask; struct wait_queue_head cq_wait; struct fasync_struct *cq_fasync; + struct eventfd_ctx *cq_ev_fd; } ____cacheline_aligned_in_smp; /* @@ -221,13 +324,15 @@ struct io_kiocb { struct list_head list; unsigned int flags; refcount_t refs; -#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */ +#define REQ_F_NOWAIT 1 /* must not punt to workers */ #define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */ #define REQ_F_FIXED_FILE 4 /* ctx owns file */ #define REQ_F_SEQ_PREV 8 /* sequential with previous */ -#define REQ_F_PREPPED 16 /* prep already done */ +#define REQ_F_IO_DRAIN 16 /* drain existing IO first */ +#define REQ_F_IO_DRAINED 32 /* drain done */ u64 user_data; - u64 error; + u32 error; /* iopoll result from callback */ + u32 sequence; struct work_struct work; }; @@ -255,6 +360,8 @@ struct io_submit_state { unsigned int ios_left; }; +static void io_sq_wq_submit_work(struct work_struct *work); + static struct kmem_cache *req_cachep; static const struct file_operations io_uring_fops; @@ -306,10 +413,36 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) spin_lock_init(&ctx->completion_lock); INIT_LIST_HEAD(&ctx->poll_list); INIT_LIST_HEAD(&ctx->cancel_list); + INIT_LIST_HEAD(&ctx->defer_list); return ctx; } -static void io_commit_cqring(struct io_ring_ctx *ctx) +static inline bool io_sequence_defer(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) + return false; + + return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped; +} + +static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) +{ + struct io_kiocb *req; + + if (list_empty(&ctx->defer_list)) + return NULL; + + req = list_first_entry(&ctx->defer_list, struct io_kiocb, list); + if (!io_sequence_defer(ctx, req)) { + list_del_init(&req->list); + return req; + } + + return NULL; +} + +static void __io_commit_cqring(struct io_ring_ctx *ctx) { struct io_cq_ring *ring = ctx->cq_ring; @@ -317,12 +450,6 @@ static void io_commit_cqring(struct io_ring_ctx *ctx) /* order cqe stores with ring update */ smp_store_release(&ring->r.tail, ctx->cached_cq_tail); - /* - * Write sider barrier of tail update, app has read side. See - * comment at the top of this file. - */ - smp_wmb(); - if (wq_has_sleeper(&ctx->cq_wait)) { wake_up_interruptible(&ctx->cq_wait); kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); @@ -330,15 +457,30 @@ static void io_commit_cqring(struct io_ring_ctx *ctx) } } +static void io_commit_cqring(struct io_ring_ctx *ctx) +{ + struct io_kiocb *req; + + __io_commit_cqring(ctx); + + while ((req = io_get_deferred_req(ctx)) != NULL) { + req->flags |= REQ_F_IO_DRAINED; + queue_work(ctx->sqo_wq, &req->work); + } +} + static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) { struct io_cq_ring *ring = ctx->cq_ring; unsigned tail; tail = ctx->cached_cq_tail; - /* See comment at the top of the file */ - smp_rmb(); - if (tail + 1 == READ_ONCE(ring->r.head)) + /* + * writes to the cq entry need to come after reading head; the + * control dependency is enough as we're using WRITE_ONCE to + * fill the cq entry + */ + if (tail - READ_ONCE(ring->r.head) == ring->ring_entries) return NULL; ctx->cached_cq_tail++; @@ -346,7 +488,7 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) } static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, - long res, unsigned ev_flags) + long res) { struct io_uring_cqe *cqe; @@ -359,7 +501,7 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, if (cqe) { WRITE_ONCE(cqe->user_data, ki_user_data); WRITE_ONCE(cqe->res, res); - WRITE_ONCE(cqe->flags, ev_flags); + WRITE_ONCE(cqe->flags, 0); } else { unsigned overflow = READ_ONCE(ctx->cq_ring->overflow); @@ -373,15 +515,17 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) wake_up(&ctx->wait); if (waitqueue_active(&ctx->sqo_wait)) wake_up(&ctx->sqo_wait); + if (ctx->cq_ev_fd) + eventfd_signal(ctx->cq_ev_fd, 1); } static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data, - long res, unsigned ev_flags) + long res) { unsigned long flags; spin_lock_irqsave(&ctx->completion_lock, flags); - io_cqring_fill_event(ctx, user_data, res, ev_flags); + io_cqring_fill_event(ctx, user_data, res); io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); @@ -483,7 +627,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, list); list_del(&req->list); - io_cqring_fill_event(ctx, req->user_data, req->error, 0); + io_cqring_fill_event(ctx, req->user_data, req->error); (*nr_events)++; if (refcount_dec_and_test(&req->refs)) { @@ -631,7 +775,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) kiocb_end_write(kiocb); - io_cqring_add_event(req->ctx, req->user_data, res, 0); + io_cqring_add_event(req->ctx, req->user_data, res); io_put_req(req); } @@ -682,11 +826,9 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_add_tail(&req->list, &ctx->poll_list); } -static void io_file_put(struct io_submit_state *state, struct file *file) +static void io_file_put(struct io_submit_state *state) { - if (!state) { - fput(file); - } else if (state->file) { + if (state->file) { int diff = state->has_refs - state->used_refs; if (diff) @@ -711,7 +853,7 @@ static struct file *io_file_get(struct io_submit_state *state, int fd) state->ios_left--; return state->file; } - io_file_put(state, NULL); + io_file_put(state); } state->file = fget_many(fd, state->ios_left); if (!state->file) @@ -742,7 +884,7 @@ static bool io_file_supports_async(struct file *file) } static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) + bool force_nonblock) { const struct io_uring_sqe *sqe = s->sqe; struct io_ring_ctx *ctx = req->ctx; @@ -752,9 +894,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, if (!req->file) return -EBADF; - /* For -EAGAIN retry, everything is already prepped */ - if (req->flags & REQ_F_PREPPED) - return 0; if (force_nonblock && !io_file_supports_async(req->file)) force_nonblock = false; @@ -776,10 +915,14 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); if (unlikely(ret)) return ret; - if (force_nonblock) { + + /* don't allow async punt if RWF_NOWAIT was requested */ + if (kiocb->ki_flags & IOCB_NOWAIT) + req->flags |= REQ_F_NOWAIT; + + if (force_nonblock) kiocb->ki_flags |= IOCB_NOWAIT; - req->flags |= REQ_F_FORCE_NONBLOCK; - } + if (ctx->flags & IORING_SETUP_IOPOLL) { if (!(kiocb->ki_flags & IOCB_DIRECT) || !kiocb->ki_filp->f_op->iopoll) @@ -793,7 +936,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, return -EINVAL; kiocb->ki_complete = io_complete_rw; } - req->flags |= REQ_F_PREPPED; return 0; } @@ -940,7 +1082,7 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) } static int io_read(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) + bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw; @@ -949,7 +1091,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, size_t iov_count; int ret; - ret = io_prep_rw(req, s, force_nonblock, state); + ret = io_prep_rw(req, s, force_nonblock); if (ret) return ret; file = kiocb->ki_filp; @@ -987,7 +1129,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, } static int io_write(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) + bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw; @@ -996,7 +1138,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, size_t iov_count; int ret; - ret = io_prep_rw(req, s, force_nonblock, state); + ret = io_prep_rw(req, s, force_nonblock); if (ret) return ret; @@ -1068,7 +1210,7 @@ static int io_nop(struct io_kiocb *req, u64 user_data) if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - io_cqring_add_event(ctx, user_data, err, 0); + io_cqring_add_event(ctx, user_data, err); io_put_req(req); return 0; } @@ -1079,16 +1221,12 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (!req->file) return -EBADF; - /* Prep already done (EAGAIN retry) */ - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; - req->flags |= REQ_F_PREPPED; return 0; } @@ -1117,7 +1255,51 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, end > 0 ? end : LLONG_MAX, fsync_flags & IORING_FSYNC_DATASYNC); - io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); + io_cqring_add_event(req->ctx, sqe->user_data, ret); + io_put_req(req); + return 0; +} + +static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret = 0; + + if (!req->file) + return -EBADF; + + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) + return -EINVAL; + + return ret; +} + +static int io_sync_file_range(struct io_kiocb *req, + const struct io_uring_sqe *sqe, + bool force_nonblock) +{ + loff_t sqe_off; + loff_t sqe_len; + unsigned flags; + int ret; + + ret = io_prep_sfr(req, sqe); + if (ret) + return ret; + + /* sync_file_range always requires a blocking context */ + if (force_nonblock) + return -EAGAIN; + + sqe_off = READ_ONCE(sqe->off); + sqe_len = READ_ONCE(sqe->len); + flags = READ_ONCE(sqe->sync_range_flags); + + ret = sync_file_range(req->rw.ki_filp, sqe_off, sqe_len, flags); + + io_cqring_add_event(req->ctx, sqe->user_data, ret); io_put_req(req); return 0; } @@ -1175,7 +1357,7 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) } spin_unlock_irq(&ctx->completion_lock); - io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); + io_cqring_add_event(req->ctx, sqe->user_data, ret); io_put_req(req); return 0; } @@ -1184,7 +1366,7 @@ static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req, __poll_t mask) { req->poll.done = true; - io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask), 0); + io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask)); io_commit_cqring(ctx); } @@ -1324,7 +1506,6 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) spin_unlock(&poll->head->lock); } if (mask) { /* no async, we'd stolen it */ - req->error = mangle_poll(mask); ipt.error = 0; io_poll_complete(ctx, req, mask); } @@ -1337,9 +1518,36 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) return ipt.error; } +static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_uring_sqe *sqe_copy; + + if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) + return 0; + + sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL); + if (!sqe_copy) + return -EAGAIN; + + spin_lock_irq(&ctx->completion_lock); + if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) { + spin_unlock_irq(&ctx->completion_lock); + kfree(sqe_copy); + return 0; + } + + memcpy(sqe_copy, sqe, sizeof(*sqe_copy)); + req->submit.sqe = sqe_copy; + + INIT_WORK(&req->work, io_sq_wq_submit_work); + list_add_tail(&req->list, &ctx->defer_list); + spin_unlock_irq(&ctx->completion_lock); + return -EIOCBQUEUED; +} + static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct sqe_submit *s, bool force_nonblock, - struct io_submit_state *state) + const struct sqe_submit *s, bool force_nonblock) { int ret, opcode; @@ -1355,18 +1563,18 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, case IORING_OP_READV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_read(req, s, force_nonblock, state); + ret = io_read(req, s, force_nonblock); break; case IORING_OP_WRITEV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_write(req, s, force_nonblock, state); + ret = io_write(req, s, force_nonblock); break; case IORING_OP_READ_FIXED: - ret = io_read(req, s, force_nonblock, state); + ret = io_read(req, s, force_nonblock); break; case IORING_OP_WRITE_FIXED: - ret = io_write(req, s, force_nonblock, state); + ret = io_write(req, s, force_nonblock); break; case IORING_OP_FSYNC: ret = io_fsync(req, s->sqe, force_nonblock); @@ -1377,6 +1585,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, case IORING_OP_POLL_REMOVE: ret = io_poll_remove(req, s->sqe); break; + case IORING_OP_SYNC_FILE_RANGE: + ret = io_sync_file_range(req, s->sqe, force_nonblock); + break; default: ret = -EINVAL; break; @@ -1439,8 +1650,7 @@ restart: struct sqe_submit *s = &req->submit; const struct io_uring_sqe *sqe = s->sqe; - /* Ensure we clear previously set forced non-block flag */ - req->flags &= ~REQ_F_FORCE_NONBLOCK; + /* Ensure we clear previously set non-block flag */ req->rw.ki_flags &= ~IOCB_NOWAIT; ret = 0; @@ -1459,7 +1669,7 @@ restart: s->has_user = cur_mm != NULL; s->needs_lock = true; do { - ret = __io_submit_sqe(ctx, req, s, false, NULL); + ret = __io_submit_sqe(ctx, req, s, false); /* * We can get EAGAIN for polled IO even though * we're forcing a sync submission from here, @@ -1470,12 +1680,13 @@ restart: break; cond_resched(); } while (1); - - /* drop submission reference */ - io_put_req(req); } + + /* drop submission reference */ + io_put_req(req); + if (ret) { - io_cqring_add_event(ctx, sqe->user_data, ret, 0); + io_cqring_add_event(ctx, sqe->user_data, ret); io_put_req(req); } @@ -1585,6 +1796,11 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, flags = READ_ONCE(s->sqe->flags); fd = READ_ONCE(s->sqe->fd); + if (flags & IOSQE_IO_DRAIN) { + req->flags |= REQ_F_IO_DRAIN; + req->sequence = ctx->cached_sq_head - 1; + } + if (!io_op_needs_file(s->sqe)) { req->file = NULL; return 0; @@ -1614,7 +1830,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, int ret; /* enforce forwards compatibility on users */ - if (unlikely(s->sqe->flags & ~IOSQE_FIXED_FILE)) + if (unlikely(s->sqe->flags & ~(IOSQE_FIXED_FILE | IOSQE_IO_DRAIN))) return -EINVAL; req = io_get_req(ctx, state); @@ -1625,8 +1841,15 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, if (unlikely(ret)) goto out; - ret = __io_submit_sqe(ctx, req, s, true, state); - if (ret == -EAGAIN) { + ret = io_req_defer(ctx, req, s->sqe); + if (ret) { + if (ret == -EIOCBQUEUED) + ret = 0; + return ret; + } + + ret = __io_submit_sqe(ctx, req, s, true); + if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { struct io_uring_sqe *sqe_copy; sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL); @@ -1671,7 +1894,7 @@ out: static void io_submit_state_end(struct io_submit_state *state) { blk_finish_plug(&state->plug); - io_file_put(state, NULL); + io_file_put(state); if (state->free_reqs) kmem_cache_free_bulk(req_cachep, state->free_reqs, &state->reqs[state->cur_req]); @@ -1700,24 +1923,10 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) * write new data to them. */ smp_store_release(&ring->r.head, ctx->cached_sq_head); - - /* - * write side barrier of head update, app has read side. See - * comment at the top of this file - */ - smp_wmb(); } } /* - * Undo last io_get_sqring() - */ -static void io_drop_sqring(struct io_ring_ctx *ctx) -{ - ctx->cached_sq_head--; -} - -/* * Fetch an sqe, if one is available. Note that s->sqe will point to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always @@ -1739,9 +1948,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) * though the application is the one updating it. */ head = ctx->cached_sq_head; - /* See comment at the top of this file */ - smp_rmb(); - if (head == READ_ONCE(ring->r.tail)) + /* make sure SQ entry isn't read before tail */ + if (head == smp_load_acquire(&ring->r.tail)) return false; head = READ_ONCE(ring->array[head & ctx->sq_mask]); @@ -1755,8 +1963,6 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) /* drop invalid entries */ ctx->cached_sq_head++; ring->dropped++; - /* See comment at the top of this file */ - smp_wmb(); return false; } @@ -1785,7 +1991,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, continue; } - io_cqring_add_event(ctx, sqes[i].sqe->user_data, ret, 0); + io_cqring_add_event(ctx, sqes[i].sqe->user_data, ret); } if (statep) @@ -1808,7 +2014,7 @@ static int io_sq_thread(void *data) set_fs(USER_DS); timeout = inflight = 0; - while (!kthread_should_stop() && !ctx->sqo_stop) { + while (!kthread_should_park()) { bool all_fixed, mm_fault = false; int i; @@ -1866,10 +2072,11 @@ static int io_sq_thread(void *data) /* Tell userspace we may need a wakeup call */ ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP; - smp_wmb(); + /* make sure to read SQ tail after writing flags */ + smp_mb(); if (!io_get_sqring(ctx, &sqes[0])) { - if (kthread_should_stop()) { + if (kthread_should_park()) { finish_wait(&ctx->sqo_wait, &wait); break; } @@ -1879,13 +2086,11 @@ static int io_sq_thread(void *data) finish_wait(&ctx->sqo_wait, &wait); ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP; - smp_wmb(); continue; } finish_wait(&ctx->sqo_wait, &wait); ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP; - smp_wmb(); } i = 0; @@ -1920,13 +2125,16 @@ static int io_sq_thread(void *data) unuse_mm(cur_mm); mmput(cur_mm); } + + kthread_parkme(); + return 0; } static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) { struct io_submit_state state, *statep = NULL; - int i, ret = 0, submit = 0; + int i, submit = 0; if (to_submit > IO_PLUG_THRESHOLD) { io_submit_state_start(&state, ctx, to_submit); @@ -1935,6 +2143,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) for (i = 0; i < to_submit; i++) { struct sqe_submit s; + int ret; if (!io_get_sqring(ctx, &s)) break; @@ -1942,25 +2151,24 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) s.has_user = true; s.needs_lock = false; s.needs_fixed_file = false; + submit++; ret = io_submit_sqe(ctx, &s, statep); - if (ret) { - io_drop_sqring(ctx); - break; - } - - submit++; + if (ret) + io_cqring_add_event(ctx, s.sqe->user_data, ret); } io_commit_sqring(ctx); if (statep) io_submit_state_end(statep); - return submit ? submit : ret; + return submit; } static unsigned io_cqring_events(struct io_cq_ring *ring) { + /* See comment at the top of this file */ + smp_rmb(); return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head); } @@ -1973,11 +2181,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, { struct io_cq_ring *ring = ctx->cq_ring; sigset_t ksigmask, sigsaved; - DEFINE_WAIT(wait); int ret; - /* See comment at the top of this file */ - smp_rmb(); if (io_cqring_events(ring) >= min_events) return 0; @@ -1995,23 +2200,9 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } - do { - prepare_to_wait(&ctx->wait, &wait, TASK_INTERRUPTIBLE); - - ret = 0; - /* See comment at the top of this file */ - smp_rmb(); - if (io_cqring_events(ring) >= min_events) - break; - - schedule(); - + ret = wait_event_interruptible(ctx->wait, io_cqring_events(ring) >= min_events); + if (ret == -ERESTARTSYS) ret = -EINTR; - if (signal_pending(current)) - break; - } while (1); - - finish_wait(&ctx->wait, &wait); if (sig) restore_user_sigmask(sig, &sigsaved); @@ -2052,8 +2243,12 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) static void io_sq_thread_stop(struct io_ring_ctx *ctx) { if (ctx->sqo_thread) { - ctx->sqo_stop = 1; - mb(); + /* + * The park is a bit of a work-around, without it we get + * warning spews on shutdown with SQPOLL set and affinity + * set to a single CPU. + */ + kthread_park(ctx->sqo_thread); kthread_stop(ctx->sqo_thread); ctx->sqo_thread = NULL; } @@ -2141,7 +2336,6 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) left = ctx->nr_user_files; while (left) { unsigned this_files = min_t(unsigned, left, SCM_MAX_FD); - int ret; ret = __io_sqe_files_scm(ctx, this_files, total); if (ret) @@ -2215,6 +2409,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, fput(ctx->user_files[i]); kfree(ctx->user_files); + ctx->user_files = NULL; ctx->nr_user_files = 0; return ret; } @@ -2235,19 +2430,24 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, mmgrab(current->mm); ctx->sqo_mm = current->mm; - ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); - if (!ctx->sq_thread_idle) - ctx->sq_thread_idle = HZ; + if (ctx->flags & IORING_SETUP_SQPOLL) { + ret = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto err; - ret = -EINVAL; - if (!cpu_possible(p->sq_thread_cpu)) - goto err; + ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); + if (!ctx->sq_thread_idle) + ctx->sq_thread_idle = HZ; - if (ctx->flags & IORING_SETUP_SQPOLL) { if (p->flags & IORING_SETUP_SQ_AFF) { - int cpu; + int cpu = p->sq_thread_cpu; + + ret = -EINVAL; + if (cpu >= nr_cpu_ids) + goto err; + if (!cpu_online(cpu)) + goto err; - cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS); ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread, ctx, cpu, "io_uring-sq"); @@ -2308,8 +2508,12 @@ static int io_account_mem(struct user_struct *user, unsigned long nr_pages) static void io_mem_free(void *ptr) { - struct page *page = virt_to_head_page(ptr); + struct page *page; + if (!ptr) + return; + + page = virt_to_head_page(ptr); if (put_page_testzero(page)) free_compound_page(page); } @@ -2350,7 +2554,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) if (ctx->account_mem) io_unaccount_mem(ctx->user, imu->nr_bvecs); - kfree(imu->bvec); + kvfree(imu->bvec); imu->nr_bvecs = 0; } @@ -2442,9 +2646,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, if (!pages || nr_pages > got_pages) { kfree(vmas); kfree(pages); - pages = kmalloc_array(nr_pages, sizeof(struct page *), + pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); - vmas = kmalloc_array(nr_pages, + vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), GFP_KERNEL); if (!pages || !vmas) { @@ -2456,7 +2660,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, got_pages = nr_pages; } - imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec), + imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec), GFP_KERNEL); ret = -ENOMEM; if (!imu->bvec) { @@ -2467,8 +2671,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, ret = 0; down_read(¤t->mm->mmap_sem); - pret = get_user_pages_longterm(ubuf, nr_pages, FOLL_WRITE, - pages, vmas); + pret = get_user_pages(ubuf, nr_pages, + FOLL_WRITE | FOLL_LONGTERM, + pages, vmas); if (pret == nr_pages) { /* don't support file backed memory */ for (j = 0; j < nr_pages; j++) { @@ -2495,6 +2700,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, } if (ctx->account_mem) io_unaccount_mem(ctx->user, nr_pages); + kvfree(imu->bvec); goto err; } @@ -2517,16 +2723,48 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, ctx->nr_user_bufs++; } - kfree(pages); - kfree(vmas); + kvfree(pages); + kvfree(vmas); return 0; err: - kfree(pages); - kfree(vmas); + kvfree(pages); + kvfree(vmas); io_sqe_buffer_unregister(ctx); return ret; } +static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg) +{ + __s32 __user *fds = arg; + int fd; + + if (ctx->cq_ev_fd) + return -EBUSY; + + if (copy_from_user(&fd, fds, sizeof(*fds))) + return -EFAULT; + + ctx->cq_ev_fd = eventfd_ctx_fdget(fd); + if (IS_ERR(ctx->cq_ev_fd)) { + int ret = PTR_ERR(ctx->cq_ev_fd); + ctx->cq_ev_fd = NULL; + return ret; + } + + return 0; +} + +static int io_eventfd_unregister(struct io_ring_ctx *ctx) +{ + if (ctx->cq_ev_fd) { + eventfd_ctx_put(ctx->cq_ev_fd); + ctx->cq_ev_fd = NULL; + return 0; + } + + return -ENXIO; +} + static void io_ring_ctx_free(struct io_ring_ctx *ctx) { io_finish_async(ctx); @@ -2536,6 +2774,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_iopoll_reap_events(ctx); io_sqe_buffer_unregister(ctx); io_sqe_files_unregister(ctx); + io_eventfd_unregister(ctx); #if defined(CONFIG_UNIX) if (ctx->ring_sock) @@ -2560,9 +2799,13 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) __poll_t mask = 0; poll_wait(file, &ctx->cq_wait, wait); - /* See comment at the top of this file */ + /* + * synchronizes with barrier from wq_has_sleeper call in + * io_commit_cqring + */ smp_rmb(); - if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head) + if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head != + ctx->sq_ring->ring_entries) mask |= EPOLLOUT | EPOLLWRNORM; if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail) mask |= EPOLLIN | EPOLLRDNORM; @@ -2673,24 +2916,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, mutex_lock(&ctx->uring_lock); submitted = io_ring_submit(ctx, to_submit); mutex_unlock(&ctx->uring_lock); - - if (submitted < 0) - goto out_ctx; } if (flags & IORING_ENTER_GETEVENTS) { unsigned nr_events = 0; min_complete = min(min_complete, ctx->cq_entries); - /* - * The application could have included the 'to_submit' count - * in how many events it wanted to wait for. If we failed to - * submit the desired count, we may need to adjust the number - * of events to poll/wait for. - */ - if (submitted < to_submit) - min_complete = min_t(unsigned, submitted, min_complete); - if (ctx->flags & IORING_SETUP_IOPOLL) { mutex_lock(&ctx->uring_lock); ret = io_iopoll_check(ctx, &nr_events, min_complete); @@ -2736,17 +2967,12 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, return -EOVERFLOW; ctx->sq_sqes = io_mem_alloc(size); - if (!ctx->sq_sqes) { - io_mem_free(ctx->sq_ring); + if (!ctx->sq_sqes) return -ENOMEM; - } cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries)); - if (!cq_ring) { - io_mem_free(ctx->sq_ring); - io_mem_free(ctx->sq_sqes); + if (!cq_ring) return -ENOMEM; - } ctx->cq_ring = cq_ring; cq_ring->ring_mask = p->cq_entries - 1; @@ -2917,11 +3143,31 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries, static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) + __releases(ctx->uring_lock) + __acquires(ctx->uring_lock) { int ret; + /* + * We're inside the ring mutex, if the ref is already dying, then + * someone else killed the ctx or is already going through + * io_uring_register(). + */ + if (percpu_ref_is_dying(&ctx->refs)) + return -ENXIO; + percpu_ref_kill(&ctx->refs); + + /* + * Drop uring mutex before waiting for references to exit. If another + * thread is currently inside io_uring_enter() it might need to grab + * the uring_lock to make progress. If we hold it here across the drain + * wait, then we can deadlock. It's safe to drop the mutex here, since + * no new references will come in after we've killed the percpu ref. + */ + mutex_unlock(&ctx->uring_lock); wait_for_completion(&ctx->ctx_done); + mutex_lock(&ctx->uring_lock); switch (opcode) { case IORING_REGISTER_BUFFERS: @@ -2942,6 +3188,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_sqe_files_unregister(ctx); break; + case IORING_REGISTER_EVENTFD: + ret = -EINVAL; + if (nr_args != 1) + break; + ret = io_eventfd_register(ctx, arg); + break; + case IORING_UNREGISTER_EVENTFD: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_eventfd_unregister(ctx); + break; default: ret = -EINVAL; break; diff --git a/fs/iomap.c b/fs/iomap.c index abdd18e404f8..23ef63fd1669 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. * Copyright (c) 2016-2018 Christoph Hellwig. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #include <linux/module.h> #include <linux/compiler.h> @@ -249,6 +241,26 @@ iomap_read_page_end_io(struct bio_vec *bvec, int error) } static void +iomap_read_end_io(struct bio *bio) +{ + int error = blk_status_to_errno(bio->bi_status); + struct bio_vec *bvec; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bvec, bio, iter_all) + iomap_read_page_end_io(bvec, error); + bio_put(bio); +} + +struct iomap_readpage_ctx { + struct page *cur_page; + bool cur_page_in_bio; + bool is_readahead; + struct bio *bio; + struct list_head *pages; +}; + +static void iomap_read_inline_data(struct inode *inode, struct page *page, struct iomap *iomap) { @@ -268,27 +280,6 @@ iomap_read_inline_data(struct inode *inode, struct page *page, SetPageUptodate(page); } -static void -iomap_read_end_io(struct bio *bio) -{ - int error = blk_status_to_errno(bio->bi_status); - struct bio_vec *bvec; - int i; - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bvec, bio, i, iter_all) - iomap_read_page_end_io(bvec, error); - bio_put(bio); -} - -struct iomap_readpage_ctx { - struct page *cur_page; - bool cur_page_in_bio; - bool is_readahead; - struct bio *bio; - struct list_head *pages; -}; - static loff_t iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap) @@ -665,6 +656,7 @@ static int iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, struct page **pagep, struct iomap *iomap) { + const struct iomap_page_ops *page_ops = iomap->page_ops; pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status = 0; @@ -674,9 +666,17 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, if (fatal_signal_pending(current)) return -EINTR; + if (page_ops && page_ops->page_prepare) { + status = page_ops->page_prepare(inode, pos, len, iomap); + if (status) + return status; + } + page = grab_cache_page_write_begin(inode->i_mapping, index, flags); - if (!page) - return -ENOMEM; + if (!page) { + status = -ENOMEM; + goto out_no_page; + } if (iomap->type == IOMAP_INLINE) iomap_read_inline_data(inode, page, iomap); @@ -684,15 +684,21 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, status = __block_write_begin_int(page, pos, len, NULL, iomap); else status = __iomap_write_begin(inode, pos, len, page, iomap); - if (unlikely(status)) { - unlock_page(page); - put_page(page); - page = NULL; - iomap_write_failed(inode, pos, len); - } + if (unlikely(status)) + goto out_unlock; *pagep = page; + return 0; + +out_unlock: + unlock_page(page); + put_page(page); + iomap_write_failed(inode, pos, len); + +out_no_page: + if (page_ops && page_ops->page_done) + page_ops->page_done(inode, pos, 0, NULL, iomap); return status; } @@ -738,13 +744,11 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len, * uptodate page as a zero-length write, and force the caller to redo * the whole thing. */ - if (unlikely(copied < len && !PageUptodate(page))) { - copied = 0; - } else { - iomap_set_range_uptodate(page, offset_in_page(pos), len); - iomap_set_page_dirty(page); - } - return __generic_write_end(inode, pos, copied, page); + if (unlikely(copied < len && !PageUptodate(page))) + return 0; + iomap_set_range_uptodate(page, offset_in_page(pos), len); + iomap_set_page_dirty(page); + return copied; } static int @@ -761,7 +765,6 @@ iomap_write_end_inline(struct inode *inode, struct page *page, kunmap_atomic(addr); mark_inode_dirty(inode); - __generic_write_end(inode, pos, copied, page); return copied; } @@ -769,19 +772,22 @@ static int iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page, struct iomap *iomap) { + const struct iomap_page_ops *page_ops = iomap->page_ops; int ret; if (iomap->type == IOMAP_INLINE) { ret = iomap_write_end_inline(inode, page, iomap, pos, copied); } else if (iomap->flags & IOMAP_F_BUFFER_HEAD) { - ret = generic_write_end(NULL, inode->i_mapping, pos, len, - copied, page, NULL); + ret = block_write_end(NULL, inode->i_mapping, pos, len, copied, + page, NULL); } else { ret = __iomap_write_end(inode, pos, len, copied, page, iomap); } - if (iomap->page_done) - iomap->page_done(inode, pos, copied, page, iomap); + __generic_write_end(inode, pos, ret, page); + if (page_ops && page_ops->page_done) + page_ops->page_done(inode, pos, copied, page, iomap); + put_page(page); if (ret < len) iomap_write_failed(inode, pos, len); @@ -1592,9 +1598,8 @@ static void iomap_dio_bio_end_io(struct bio *bio) if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { struct bvec_iter_all iter_all; struct bio_vec *bvec; - int i; - bio_for_each_segment_all(bvec, bio, i, iter_all) + bio_for_each_segment_all(bvec, bio, iter_all) put_page(bvec->bv_page); } bio_put(bio); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 488a9e7f8f66..603b052a3c94 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -72,17 +72,11 @@ static struct inode *isofs_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void isofs_i_callback(struct rcu_head *head) +static void isofs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(isofs_inode_cachep, ISOFS_I(inode)); } -static void isofs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, isofs_i_callback); -} - static void init_once(void *foo) { struct iso_inode_info *ei = foo; @@ -122,7 +116,7 @@ static int isofs_remount(struct super_block *sb, int *flags, char *data) static const struct super_operations isofs_sops = { .alloc_inode = isofs_alloc_inode, - .destroy_inode = isofs_destroy_inode, + .free_inode = isofs_free_inode, .put_super = isofs_put_super, .statfs = isofs_statfs, .remount_fs = isofs_remount, diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index eab04eca95a3..112d85849db1 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -340,6 +340,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino) rdev = old_decode_dev(je16_to_cpu(jdev.old_id)); else rdev = new_decode_dev(je32_to_cpu(jdev.new_id)); + /* fall through */ case S_IFSOCK: case S_IFIFO: diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 389ea53ea487..bccfc40b3a74 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1414,11 +1414,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f) jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL); - if (f->target) { - kfree(f->target); - f->target = NULL; - } - fds = f->dents; while(fds) { fd = fds; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index bb6ae387469f..af4aa6599473 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -44,15 +44,12 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb) return &f->vfs_inode; } -static void jffs2_i_callback(struct rcu_head *head) +static void jffs2_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode)); -} + struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); -static void jffs2_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, jffs2_i_callback); + kfree(f->target); + kmem_cache_free(jffs2_inode_cachep, f); } static void jffs2_i_init_once(void *foo) @@ -255,7 +252,7 @@ static int jffs2_remount_fs(struct super_block *sb, int *flags, char *data) static const struct super_operations jffs2_super_operations = { .alloc_inode = jffs2_alloc_inode, - .destroy_inode =jffs2_destroy_inode, + .free_inode = jffs2_free_inode, .put_super = jffs2_put_super, .statfs = jffs2_statfs, .remount_fs = jffs2_remount_fs, diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 8c06a6ea862d..ebb299003a5b 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -117,7 +117,8 @@ int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) rc = posix_acl_update_mode(inode, &mode, &acl); if (rc) goto end_tx; - update_mode = 1; + if (mode != inode->i_mode) + update_mode = 1; } rc = __jfs_set_acl(tid, inode, type, acl); if (!rc) { diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 805ae9e8944a..f2b92b292abe 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -31,6 +31,7 @@ #include "jfs_extent.h" #include "jfs_unicode.h" #include "jfs_debug.h" +#include "jfs_dmap.h" struct inode *jfs_iget(struct super_block *sb, unsigned long ino) @@ -150,6 +151,8 @@ int jfs_write_inode(struct inode *inode, struct writeback_control *wbc) void jfs_evict_inode(struct inode *inode) { + struct jfs_inode_info *ji = JFS_IP(inode); + jfs_info("In jfs_evict_inode, inode = 0x%p", inode); if (!inode->i_nlink && !is_bad_inode(inode)) { @@ -173,6 +176,16 @@ void jfs_evict_inode(struct inode *inode) } clear_inode(inode); dquot_drop(inode); + + BUG_ON(!list_empty(&ji->anon_inode_list)); + + spin_lock_irq(&ji->ag_lock); + if (ji->active_ag != -1) { + struct bmap *bmap = JFS_SBI(inode->i_sb)->bmap; + atomic_dec(&bmap->db_active[ji->active_ag]); + ji->active_ag = -1; + } + spin_unlock_irq(&ji->ag_lock); } void jfs_dirty_inode(struct inode *inode, int flags) diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 912a3af2393e..340eb8e4f716 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -23,6 +23,8 @@ #include <linux/rwsem.h> #include <linux/slab.h> #include <linux/bitops.h> +#include <linux/uuid.h> + #include "jfs_types.h" #include "jfs_xtree.h" #include "jfs_dtree.h" @@ -178,8 +180,8 @@ struct jfs_sb_info { pxd_t logpxd; /* pxd describing log */ pxd_t fsckpxd; /* pxd describing fsck wkspc */ pxd_t ait2; /* pxd describing AIT copy */ - char uuid[16]; /* 128-bit uuid for volume */ - char loguuid[16]; /* 128-bit uuid for log */ + uuid_t uuid; /* 128-bit uuid for volume */ + uuid_t loguuid; /* 128-bit uuid for log */ /* * commit_state is used for synchronization of the jfs_commit * threads. It is protected by LAZY_LOCK(). diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 6b68df395892..4c77b808020b 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1092,8 +1092,7 @@ int lmLogOpen(struct super_block *sb) mutex_lock(&jfs_log_mutex); list_for_each_entry(log, &jfs_external_logs, journal_list) { if (log->bdev->bd_dev == sbi->logdev) { - if (memcmp(log->uuid, sbi->loguuid, - sizeof(log->uuid))) { + if (!uuid_equal(&log->uuid, &sbi->loguuid)) { jfs_warn("wrong uuid on JFS journal"); mutex_unlock(&jfs_log_mutex); return -EINVAL; @@ -1130,7 +1129,7 @@ int lmLogOpen(struct super_block *sb) } log->bdev = bdev; - memcpy(log->uuid, sbi->loguuid, sizeof(log->uuid)); + uuid_copy(&log->uuid, &sbi->loguuid); /* * initialize log: @@ -1336,7 +1335,7 @@ int lmLogInit(struct jfs_log * log) jfs_info("lmLogInit: inline log:0x%p base:0x%Lx size:0x%x", log, (unsigned long long)log->base, log->size); } else { - if (memcmp(logsuper->uuid, log->uuid, 16)) { + if (!uuid_equal(&logsuper->uuid, &log->uuid)) { jfs_warn("wrong uuid on JFS log device"); goto errout20; } @@ -1732,7 +1731,7 @@ static int lmLogFileSystem(struct jfs_log * log, struct jfs_sb_info *sbi, int i; struct logsuper *logsuper; struct lbuf *bpsuper; - char *uuid = sbi->uuid; + uuid_t *uuid = &sbi->uuid; /* * insert/remove file system device to log active file system list. @@ -1743,8 +1742,8 @@ static int lmLogFileSystem(struct jfs_log * log, struct jfs_sb_info *sbi, logsuper = (struct logsuper *) bpsuper->l_ldata; if (activate) { for (i = 0; i < MAX_ACTIVE; i++) - if (!memcmp(logsuper->active[i].uuid, NULL_UUID, 16)) { - memcpy(logsuper->active[i].uuid, uuid, 16); + if (uuid_is_null(&logsuper->active[i].uuid)) { + uuid_copy(&logsuper->active[i].uuid, uuid); sbi->aggregate = i; break; } @@ -1755,8 +1754,9 @@ static int lmLogFileSystem(struct jfs_log * log, struct jfs_sb_info *sbi, } } else { for (i = 0; i < MAX_ACTIVE; i++) - if (!memcmp(logsuper->active[i].uuid, uuid, 16)) { - memcpy(logsuper->active[i].uuid, NULL_UUID, 16); + if (uuid_equal(&logsuper->active[i].uuid, uuid)) { + uuid_copy(&logsuper->active[i].uuid, + &uuid_null); break; } if (i == MAX_ACTIVE) { diff --git a/fs/jfs/jfs_logmgr.h b/fs/jfs/jfs_logmgr.h index e38c21598850..870fc22360e7 100644 --- a/fs/jfs/jfs_logmgr.h +++ b/fs/jfs/jfs_logmgr.h @@ -19,6 +19,8 @@ #ifndef _H_JFS_LOGMGR #define _H_JFS_LOGMGR +#include <linux/uuid.h> + #include "jfs_filsys.h" #include "jfs_lock.h" @@ -73,15 +75,13 @@ struct logsuper { __le32 state; /* 4: state - see below */ __le32 end; /* 4: addr of last log record set by logredo */ - char uuid[16]; /* 16: 128-bit journal uuid */ + uuid_t uuid; /* 16: 128-bit journal uuid */ char label[16]; /* 16: journal label */ struct { - char uuid[16]; + uuid_t uuid; } active[MAX_ACTIVE]; /* 2048: active file systems list */ }; -#define NULL_UUID "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0" - /* log flag: commit option (see jfs_filsys.h) */ /* log state */ @@ -410,7 +410,7 @@ struct jfs_log { spinlock_t synclock; /* 4: synclist lock */ struct lbuf *wqueue; /* 4: log pageout queue */ int count; /* 4: count */ - char uuid[16]; /* 16: 128-bit uuid of log device */ + uuid_t uuid; /* 16: 128-bit uuid of log device */ int no_integrity; /* 3: flag to disable journaling to disk */ }; diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index d8658607bf46..c9c1f16b93df 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -389,8 +389,8 @@ static int chkSuper(struct super_block *sb) sbi->logpxd = j_sb->s_logpxd; else { sbi->logdev = new_decode_dev(le32_to_cpu(j_sb->s_logdev)); - memcpy(sbi->uuid, j_sb->s_uuid, sizeof(sbi->uuid)); - memcpy(sbi->loguuid, j_sb->s_loguuid, sizeof(sbi->uuid)); + uuid_copy(&sbi->uuid, &j_sb->s_uuid); + uuid_copy(&sbi->loguuid, &j_sb->s_loguuid); } sbi->fsckpxd = j_sb->s_fsckpxd; sbi->ait2 = j_sb->s_ait2; diff --git a/fs/jfs/jfs_superblock.h b/fs/jfs/jfs_superblock.h index 04847b8d3070..eb03de7fa925 100644 --- a/fs/jfs/jfs_superblock.h +++ b/fs/jfs/jfs_superblock.h @@ -18,6 +18,8 @@ #ifndef _H_JFS_SUPERBLOCK #define _H_JFS_SUPERBLOCK +#include <linux/uuid.h> + /* * make the magic number something a human could read */ @@ -98,11 +100,9 @@ struct jfs_superblock { __le64 s_xsize; /* 8: extendfs s_size */ pxd_t s_xfsckpxd; /* 8: extendfs fsckpxd */ pxd_t s_xlogpxd; /* 8: extendfs logpxd */ - /* - 128 byte boundary - */ - - char s_uuid[16]; /* 16: 128-bit uuid for volume */ + uuid_t s_uuid; /* 16: 128-bit uuid for volume */ char s_label[16]; /* 16: volume label */ - char s_loguuid[16]; /* 16: 128-bit uuid for log device */ + uuid_t s_loguuid; /* 16: 128-bit uuid for log device */ }; diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index a5663cb621d8..78789c5ed36b 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1928,8 +1928,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, * header ? */ if (tlck->type & tlckTRUNCATE) { - /* This odd declaration suppresses a bogus gcc warning */ - pxd_t pxd = pxd; /* truncated extent of xad */ + pxd_t pxd; /* truncated extent of xad */ int twm; /* diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 14528c0ffe63..fa719a1553b6 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -203,7 +203,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode, * RETURN: Errors from subroutines * * note: - * EACCESS: user needs search+write permission on the parent directory + * EACCES: user needs search+write permission on the parent directory */ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode) { diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 65d8fc87ab11..8f78fa374242 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -124,27 +124,9 @@ static struct inode *jfs_alloc_inode(struct super_block *sb) return &jfs_inode->vfs_inode; } -static void jfs_i_callback(struct rcu_head *head) +static void jfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); - struct jfs_inode_info *ji = JFS_IP(inode); - kmem_cache_free(jfs_inode_cachep, ji); -} - -static void jfs_destroy_inode(struct inode *inode) -{ - struct jfs_inode_info *ji = JFS_IP(inode); - - BUG_ON(!list_empty(&ji->anon_inode_list)); - - spin_lock_irq(&ji->ag_lock); - if (ji->active_ag != -1) { - struct bmap *bmap = JFS_SBI(inode->i_sb)->bmap; - atomic_dec(&bmap->db_active[ji->active_ag]); - ji->active_ag = -1; - } - spin_unlock_irq(&ji->ag_lock); - call_rcu(&inode->i_rcu, jfs_i_callback); + kmem_cache_free(jfs_inode_cachep, JFS_IP(inode)); } static int jfs_statfs(struct dentry *dentry, struct kstatfs *buf) @@ -174,9 +156,11 @@ static int jfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_files = maxinodes; buf->f_ffree = maxinodes - (atomic_read(&imap->im_numinos) - atomic_read(&imap->im_numfree)); - buf->f_fsid.val[0] = (u32)crc32_le(0, sbi->uuid, sizeof(sbi->uuid)/2); - buf->f_fsid.val[1] = (u32)crc32_le(0, sbi->uuid + sizeof(sbi->uuid)/2, - sizeof(sbi->uuid)/2); + buf->f_fsid.val[0] = crc32_le(0, (char *)&sbi->uuid, + sizeof(sbi->uuid)/2); + buf->f_fsid.val[1] = crc32_le(0, + (char *)&sbi->uuid + sizeof(sbi->uuid)/2, + sizeof(sbi->uuid)/2); buf->f_namelen = JFS_NAME_MAX; return 0; @@ -912,7 +896,7 @@ out: static const struct super_operations jfs_super_operations = { .alloc_inode = jfs_alloc_inode, - .destroy_inode = jfs_destroy_inode, + .free_inode = jfs_free_inode, .dirty_inode = jfs_dirty_inode, .write_inode = jfs_write_inode, .evict_inode = jfs_evict_inode, diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index b84d635567d3..016ba88f7335 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -532,9 +532,6 @@ void kernfs_put(struct kernfs_node *kn) kfree_const(kn->name); if (kn->iattr) { - if (kn->iattr->ia_secdata) - security_release_secctx(kn->iattr->ia_secdata, - kn->iattr->ia_secdata_len); simple_xattrs_free(&kn->iattr->xattrs); kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } @@ -618,6 +615,7 @@ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) } static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, + struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) @@ -650,11 +648,10 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, kn->id.generation = gen; /* - * set ino first. This barrier is paired with atomic_inc_not_zero in + * set ino first. This RELEASE is paired with atomic_inc_not_zero in * kernfs_find_and_get_node_by_ino */ - smp_mb__before_atomic(); - atomic_set(&kn->count, 1); + atomic_set_release(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); @@ -674,6 +671,12 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, goto err_out3; } + if (parent) { + ret = security_kernfs_init_security(parent, kn); + if (ret) + goto err_out3; + } + return kn; err_out3: @@ -692,7 +695,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, { struct kernfs_node *kn; - kn = __kernfs_new_node(kernfs_root(parent), + kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); @@ -795,9 +798,8 @@ int kernfs_add_one(struct kernfs_node *kn) /* Update timestamps on the parent */ ps_iattr = parent->iattr; if (ps_iattr) { - struct iattr *ps_iattrs = &ps_iattr->ia_iattr; - ktime_get_real_ts64(&ps_iattrs->ia_ctime); - ps_iattrs->ia_mtime = ps_iattrs->ia_ctime; + ktime_get_real_ts64(&ps_iattr->ia_ctime); + ps_iattr->ia_mtime = ps_iattr->ia_ctime; } mutex_unlock(&kernfs_mutex); @@ -962,7 +964,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, INIT_LIST_HEAD(&root->supers); root->next_generation = 1; - kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO, + kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) { @@ -1329,9 +1331,8 @@ static void __kernfs_remove(struct kernfs_node *kn) /* update timestamps on the parent */ if (ps_iattr) { - ktime_get_real_ts64(&ps_iattr->ia_iattr.ia_ctime); - ps_iattr->ia_iattr.ia_mtime = - ps_iattr->ia_iattr.ia_ctime; + ktime_get_real_ts64(&ps_iattr->ia_ctime); + ps_iattr->ia_mtime = ps_iattr->ia_ctime; } kernfs_put(pos); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index ae948aaa4c53..553ce0a92b05 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -885,6 +885,7 @@ repeat: list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *inode; + struct qstr name; /* * We want fsnotify_modify() on @kn but as the @@ -896,6 +897,7 @@ repeat: if (!inode) continue; + name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name)); parent = kernfs_get_parent(kn); if (parent) { struct inode *p_inode; @@ -903,7 +905,7 @@ repeat: p_inode = ilookup(info->sb, parent->id.ino); if (p_inode) { fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD, - inode, FSNOTIFY_EVENT_INODE, kn->name, 0); + inode, FSNOTIFY_EVENT_INODE, &name, 0); iput(p_inode); } @@ -911,7 +913,7 @@ repeat: } fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, - kn->name, 0); + &name, 0); iput(inode); } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 0c1fd945ce42..f89a0f13840e 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -31,30 +31,27 @@ static const struct inode_operations kernfs_iops = { .listxattr = kernfs_iop_listxattr, }; -static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) +static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, int alloc) { static DEFINE_MUTEX(iattr_mutex); struct kernfs_iattrs *ret; - struct iattr *iattrs; mutex_lock(&iattr_mutex); - if (kn->iattr) + if (kn->iattr || !alloc) goto out_unlock; kn->iattr = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL); if (!kn->iattr) goto out_unlock; - iattrs = &kn->iattr->ia_iattr; /* assign default attributes */ - iattrs->ia_mode = kn->mode; - iattrs->ia_uid = GLOBAL_ROOT_UID; - iattrs->ia_gid = GLOBAL_ROOT_GID; + kn->iattr->ia_uid = GLOBAL_ROOT_UID; + kn->iattr->ia_gid = GLOBAL_ROOT_GID; - ktime_get_real_ts64(&iattrs->ia_atime); - iattrs->ia_mtime = iattrs->ia_atime; - iattrs->ia_ctime = iattrs->ia_atime; + ktime_get_real_ts64(&kn->iattr->ia_atime); + kn->iattr->ia_mtime = kn->iattr->ia_atime; + kn->iattr->ia_ctime = kn->iattr->ia_atime; simple_xattrs_init(&kn->iattr->xattrs); out_unlock: @@ -63,32 +60,37 @@ out_unlock: return ret; } +static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) +{ + return __kernfs_iattrs(kn, 1); +} + +static struct kernfs_iattrs *kernfs_iattrs_noalloc(struct kernfs_node *kn) +{ + return __kernfs_iattrs(kn, 0); +} + int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { struct kernfs_iattrs *attrs; - struct iattr *iattrs; unsigned int ia_valid = iattr->ia_valid; attrs = kernfs_iattrs(kn); if (!attrs) return -ENOMEM; - iattrs = &attrs->ia_iattr; - if (ia_valid & ATTR_UID) - iattrs->ia_uid = iattr->ia_uid; + attrs->ia_uid = iattr->ia_uid; if (ia_valid & ATTR_GID) - iattrs->ia_gid = iattr->ia_gid; + attrs->ia_gid = iattr->ia_gid; if (ia_valid & ATTR_ATIME) - iattrs->ia_atime = iattr->ia_atime; + attrs->ia_atime = iattr->ia_atime; if (ia_valid & ATTR_MTIME) - iattrs->ia_mtime = iattr->ia_mtime; + attrs->ia_mtime = iattr->ia_mtime; if (ia_valid & ATTR_CTIME) - iattrs->ia_ctime = iattr->ia_ctime; - if (ia_valid & ATTR_MODE) { - umode_t mode = iattr->ia_mode; - iattrs->ia_mode = kn->mode = mode; - } + attrs->ia_ctime = iattr->ia_ctime; + if (ia_valid & ATTR_MODE) + kn->mode = iattr->ia_mode; return 0; } @@ -135,23 +137,6 @@ out: return error; } -static int kernfs_node_setsecdata(struct kernfs_iattrs *attrs, void **secdata, - u32 *secdata_len) -{ - void *old_secdata; - size_t old_secdata_len; - - old_secdata = attrs->ia_secdata; - old_secdata_len = attrs->ia_secdata_len; - - attrs->ia_secdata = *secdata; - attrs->ia_secdata_len = *secdata_len; - - *secdata = old_secdata; - *secdata_len = old_secdata_len; - return 0; -} - ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) { struct kernfs_node *kn = kernfs_dentry_node(dentry); @@ -171,14 +156,15 @@ static inline void set_default_inode_attr(struct inode *inode, umode_t mode) inode->i_ctime = current_time(inode); } -static inline void set_inode_attr(struct inode *inode, struct iattr *iattr) +static inline void set_inode_attr(struct inode *inode, + struct kernfs_iattrs *attrs) { struct super_block *sb = inode->i_sb; - inode->i_uid = iattr->ia_uid; - inode->i_gid = iattr->ia_gid; - inode->i_atime = timespec64_trunc(iattr->ia_atime, sb->s_time_gran); - inode->i_mtime = timespec64_trunc(iattr->ia_mtime, sb->s_time_gran); - inode->i_ctime = timespec64_trunc(iattr->ia_ctime, sb->s_time_gran); + inode->i_uid = attrs->ia_uid; + inode->i_gid = attrs->ia_gid; + inode->i_atime = timespec64_trunc(attrs->ia_atime, sb->s_time_gran); + inode->i_mtime = timespec64_trunc(attrs->ia_mtime, sb->s_time_gran); + inode->i_ctime = timespec64_trunc(attrs->ia_ctime, sb->s_time_gran); } static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) @@ -186,15 +172,12 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) struct kernfs_iattrs *attrs = kn->iattr; inode->i_mode = kn->mode; - if (attrs) { + if (attrs) /* * kernfs_node has non-default attributes get them from * persistent copy in kernfs_node. */ - set_inode_attr(inode, &attrs->ia_iattr); - security_inode_notifysecctx(inode, attrs->ia_secdata, - attrs->ia_secdata_len); - } + set_inode_attr(inode, attrs); if (kernfs_type(kn) == KERNFS_DIR) set_nlink(inode, kn->dir.subdirs + 2); @@ -305,78 +288,57 @@ int kernfs_iop_permission(struct inode *inode, int mask) return generic_permission(inode, mask); } -static int kernfs_xattr_get(const struct xattr_handler *handler, - struct dentry *unused, struct inode *inode, - const char *suffix, void *value, size_t size) +int kernfs_xattr_get(struct kernfs_node *kn, const char *name, + void *value, size_t size) { - const char *name = xattr_full_name(handler, suffix); - struct kernfs_node *kn = inode->i_private; - struct kernfs_iattrs *attrs; - - attrs = kernfs_iattrs(kn); + struct kernfs_iattrs *attrs = kernfs_iattrs_noalloc(kn); if (!attrs) - return -ENOMEM; + return -ENODATA; return simple_xattr_get(&attrs->xattrs, name, value, size); } -static int kernfs_xattr_set(const struct xattr_handler *handler, - struct dentry *unused, struct inode *inode, - const char *suffix, const void *value, - size_t size, int flags) +int kernfs_xattr_set(struct kernfs_node *kn, const char *name, + const void *value, size_t size, int flags) { - const char *name = xattr_full_name(handler, suffix); - struct kernfs_node *kn = inode->i_private; - struct kernfs_iattrs *attrs; - - attrs = kernfs_iattrs(kn); + struct kernfs_iattrs *attrs = kernfs_iattrs(kn); if (!attrs) return -ENOMEM; return simple_xattr_set(&attrs->xattrs, name, value, size, flags); } -static const struct xattr_handler kernfs_trusted_xattr_handler = { - .prefix = XATTR_TRUSTED_PREFIX, - .get = kernfs_xattr_get, - .set = kernfs_xattr_set, -}; - -static int kernfs_security_xattr_set(const struct xattr_handler *handler, - struct dentry *unused, struct inode *inode, - const char *suffix, const void *value, - size_t size, int flags) +static int kernfs_vfs_xattr_get(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *suffix, void *value, size_t size) { + const char *name = xattr_full_name(handler, suffix); struct kernfs_node *kn = inode->i_private; - struct kernfs_iattrs *attrs; - void *secdata; - u32 secdata_len = 0; - int error; - - attrs = kernfs_iattrs(kn); - if (!attrs) - return -ENOMEM; - error = security_inode_setsecurity(inode, suffix, value, size, flags); - if (error) - return error; - error = security_inode_getsecctx(inode, &secdata, &secdata_len); - if (error) - return error; + return kernfs_xattr_get(kn, name, value, size); +} - mutex_lock(&kernfs_mutex); - error = kernfs_node_setsecdata(attrs, &secdata, &secdata_len); - mutex_unlock(&kernfs_mutex); +static int kernfs_vfs_xattr_set(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *suffix, const void *value, + size_t size, int flags) +{ + const char *name = xattr_full_name(handler, suffix); + struct kernfs_node *kn = inode->i_private; - if (secdata) - security_release_secctx(secdata, secdata_len); - return error; + return kernfs_xattr_set(kn, name, value, size, flags); } +static const struct xattr_handler kernfs_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = kernfs_vfs_xattr_get, + .set = kernfs_vfs_xattr_set, +}; + static const struct xattr_handler kernfs_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, - .get = kernfs_xattr_get, - .set = kernfs_security_xattr_set, + .get = kernfs_vfs_xattr_get, + .set = kernfs_vfs_xattr_set, }; const struct xattr_handler *kernfs_xattr_handlers[] = { diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 0b7d197a904c..3c437990f39a 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -20,9 +20,11 @@ #include <linux/fs_context.h> struct kernfs_iattrs { - struct iattr ia_iattr; - void *ia_secdata; - u32 ia_secdata_len; + kuid_t ia_uid; + kgid_t ia_gid; + struct timespec64 ia_atime; + struct timespec64 ia_mtime; + struct timespec64 ia_ctime; struct simple_xattrs xattrs; }; diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 162f43b80c84..eb46c3a16e2f 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -33,8 +33,8 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, kgid_t gid = GLOBAL_ROOT_GID; if (target->iattr) { - uid = target->iattr->ia_iattr.ia_uid; - gid = target->iattr->ia_iattr.ia_gid; + uid = target->iattr->ia_uid; + gid = target->iattr->ia_gid; } kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, uid, gid, diff --git a/fs/libfs.c b/fs/libfs.c index 0fb590d79f30..4b59b1816efb 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -146,9 +146,11 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) switch (whence) { case 1: offset += file->f_pos; + /* fall through */ case 0: if (offset >= 0) break; + /* fall through */ default: return -EINVAL; } @@ -1167,6 +1169,20 @@ simple_nosetlease(struct file *filp, long arg, struct file_lock **flp, } EXPORT_SYMBOL(simple_nosetlease); +/** + * simple_get_link - generic helper to get the target of "fast" symlinks + * @dentry: not used here + * @inode: the symlink inode + * @done: not used here + * + * Generic helper for filesystems to use for symlink inodes where a pointer to + * the symlink target is stored in ->i_link. NOTE: this isn't normally called, + * since as an optimization the path lookup code uses any non-NULL ->i_link + * directly, without calling ->get_link(). But ->get_link() still must be set, + * to mark the inode_operations as being for a symlink. + * + * Return: the symlink target + */ const char *simple_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index c2a128678e6e..5fb4f8910aab 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -56,14 +56,14 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init) u32 nlm_version = (nlm_init->nfs_version == 2) ? 1 : 4; int status; - status = lockd_up(nlm_init->net); + status = lockd_up(nlm_init->net, nlm_init->cred); if (status < 0) return ERR_PTR(status); host = nlmclnt_lookup_host(nlm_init->address, nlm_init->addrlen, nlm_init->protocol, nlm_version, nlm_init->hostname, nlm_init->noresvport, - nlm_init->net); + nlm_init->net, nlm_init->cred); if (host == NULL) goto out_nohost; if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL) @@ -241,7 +241,7 @@ reclaimer(void *ptr) allow_signal(SIGKILL); down_write(&host->h_rwsem); - lockd_up(net); /* note: this cannot fail as lockd is already running */ + lockd_up(net, NULL); /* note: this cannot fail as lockd is already running */ dprintk("lockd: reclaiming locks for host %s\n", host->h_name); diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index e8a004097d18..d9c32d1a20c0 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -715,7 +715,7 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, void *data) struct nlm_rqst *req = data; u32 status = ntohl(req->a_res.status); - if (RPC_ASSASSINATED(task)) + if (RPC_SIGNALLED(task)) goto die; if (task->tk_status < 0) { @@ -783,7 +783,7 @@ static void nlmclnt_cancel_callback(struct rpc_task *task, void *data) struct nlm_rqst *req = data; u32 status = ntohl(req->a_res.status); - if (RPC_ASSASSINATED(task)) + if (RPC_SIGNALLED(task)) goto die; if (task->tk_status < 0) { diff --git a/fs/lockd/host.c b/fs/lockd/host.c index f0b5c987d6ae..7d46fafdbbe5 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -60,6 +60,7 @@ struct nlm_lookup_host_info { const size_t hostname_len; /* it's length */ const int noresvport; /* use non-priv port */ struct net *net; /* network namespace to bind */ + const struct cred *cred; }; /* @@ -162,6 +163,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni, host->h_nsmhandle = nsm; host->h_addrbuf = nsm->sm_addrbuf; host->net = ni->net; + host->h_cred = get_cred(ni->cred), strlcpy(host->nodename, utsname()->nodename, sizeof(host->nodename)); out: @@ -188,6 +190,7 @@ static void nlm_destroy_host_locked(struct nlm_host *host) clnt = host->h_rpcclnt; if (clnt != NULL) rpc_shutdown_client(clnt); + put_cred(host->h_cred); kfree(host); ln->nrhosts--; @@ -202,6 +205,8 @@ static void nlm_destroy_host_locked(struct nlm_host *host) * @version: NLM protocol version * @hostname: '\0'-terminated hostname of server * @noresvport: 1 if non-privileged port should be used + * @net: pointer to net namespace + * @cred: pointer to cred * * Returns an nlm_host structure that matches the passed-in * [server address, transport protocol, NLM version, server hostname]. @@ -214,7 +219,8 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, const u32 version, const char *hostname, int noresvport, - struct net *net) + struct net *net, + const struct cred *cred) { struct nlm_lookup_host_info ni = { .server = 0, @@ -226,6 +232,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, .hostname_len = strlen(hostname), .noresvport = noresvport, .net = net, + .cred = cred, }; struct hlist_head *chain; struct nlm_host *host; @@ -458,6 +465,7 @@ nlm_bind_host(struct nlm_host *host) .authflavor = RPC_AUTH_UNIX, .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_AUTOBIND), + .cred = host->h_cred, }; /* diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 654594ef4f94..1eabd91870e6 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -82,6 +82,7 @@ static struct rpc_clnt *nsm_create(struct net *net, const char *nodename) .version = NSM_VERSION, .authflavor = RPC_AUTH_NULL, .flags = RPC_CLNT_CREATE_NOPING, + .cred = current_cred(), }; return rpc_create(&args); diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 346ed161756d..3056f3a0c270 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -188,28 +188,31 @@ lockd(void *vrqstp) static int create_lockd_listener(struct svc_serv *serv, const char *name, struct net *net, const int family, - const unsigned short port) + const unsigned short port, + const struct cred *cred) { struct svc_xprt *xprt; xprt = svc_find_xprt(serv, name, net, family, 0); if (xprt == NULL) return svc_create_xprt(serv, name, net, family, port, - SVC_SOCK_DEFAULTS); + SVC_SOCK_DEFAULTS, cred); svc_xprt_put(xprt); return 0; } static int create_lockd_family(struct svc_serv *serv, struct net *net, - const int family) + const int family, const struct cred *cred) { int err; - err = create_lockd_listener(serv, "udp", net, family, nlm_udpport); + err = create_lockd_listener(serv, "udp", net, family, nlm_udpport, + cred); if (err < 0) return err; - return create_lockd_listener(serv, "tcp", net, family, nlm_tcpport); + return create_lockd_listener(serv, "tcp", net, family, nlm_tcpport, + cred); } /* @@ -222,16 +225,17 @@ static int create_lockd_family(struct svc_serv *serv, struct net *net, * Returns zero if all listeners are available; otherwise a * negative errno value is returned. */ -static int make_socks(struct svc_serv *serv, struct net *net) +static int make_socks(struct svc_serv *serv, struct net *net, + const struct cred *cred) { static int warned; int err; - err = create_lockd_family(serv, net, PF_INET); + err = create_lockd_family(serv, net, PF_INET, cred); if (err < 0) goto out_err; - err = create_lockd_family(serv, net, PF_INET6); + err = create_lockd_family(serv, net, PF_INET6, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_err; @@ -246,7 +250,8 @@ out_err: return err; } -static int lockd_up_net(struct svc_serv *serv, struct net *net) +static int lockd_up_net(struct svc_serv *serv, struct net *net, + const struct cred *cred) { struct lockd_net *ln = net_generic(net, lockd_net_id); int error; @@ -258,7 +263,7 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net) if (error) goto err_bind; - error = make_socks(serv, net); + error = make_socks(serv, net, cred); if (error < 0) goto err_bind; set_grace_period(net); @@ -461,7 +466,7 @@ static struct svc_serv *lockd_create_svc(void) /* * Bring up the lockd process if it's not already up. */ -int lockd_up(struct net *net) +int lockd_up(struct net *net, const struct cred *cred) { struct svc_serv *serv; int error; @@ -474,7 +479,7 @@ int lockd_up(struct net *net) goto err_create; } - error = lockd_up_net(serv, net); + error = lockd_up_net(serv, net, cred); if (error < 0) { lockd_unregister_notifiers(); goto err_put; @@ -807,5 +812,7 @@ static struct svc_program nlmsvc_program = { .pg_name = "lockd", /* service name */ .pg_class = "nfsd", /* share authentication with nfsd */ .pg_stats = &nlmsvc_stats, /* stats table */ - .pg_authenticate = &lockd_authenticate /* export authentication */ + .pg_authenticate = &lockd_authenticate, /* export authentication */ + .pg_init_request = svc_generic_init_request, + .pg_rpcbind_set = svc_generic_rpcbind_set, }; diff --git a/fs/locks.c b/fs/locks.c index 71d0c6c2aac5..8af49f89ac2f 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -352,6 +352,12 @@ EXPORT_SYMBOL_GPL(locks_alloc_lock); void locks_release_private(struct file_lock *fl) { + BUG_ON(waitqueue_active(&fl->fl_wait)); + BUG_ON(!list_empty(&fl->fl_list)); + BUG_ON(!list_empty(&fl->fl_blocked_requests)); + BUG_ON(!list_empty(&fl->fl_blocked_member)); + BUG_ON(!hlist_unhashed(&fl->fl_link)); + if (fl->fl_ops) { if (fl->fl_ops->fl_release_private) fl->fl_ops->fl_release_private(fl); @@ -371,12 +377,6 @@ EXPORT_SYMBOL_GPL(locks_release_private); /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { - BUG_ON(waitqueue_active(&fl->fl_wait)); - BUG_ON(!list_empty(&fl->fl_list)); - BUG_ON(!list_empty(&fl->fl_blocked_requests)); - BUG_ON(!list_empty(&fl->fl_blocked_member)); - BUG_ON(!hlist_unhashed(&fl->fl_link)); - locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } @@ -1476,7 +1476,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg) switch (arg) { case F_UNLCK: fl->fl_flags &= ~FL_UNLOCK_PENDING; - /* fall through: */ + /* fall through */ case F_RDLCK: fl->fl_flags &= ~FL_DOWNGRADE_PENDING; } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 72e308c3e66b..101200761f61 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -68,17 +68,11 @@ static struct inode *minix_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void minix_i_callback(struct rcu_head *head) +static void minix_free_in_core_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(minix_inode_cachep, minix_i(inode)); } -static void minix_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, minix_i_callback); -} - static void init_once(void *foo) { struct minix_inode_info *ei = (struct minix_inode_info *) foo; @@ -110,7 +104,7 @@ static void destroy_inodecache(void) static const struct super_operations minix_sops = { .alloc_inode = minix_alloc_inode, - .destroy_inode = minix_destroy_inode, + .free_inode = minix_free_in_core_inode, .write_inode = minix_write_inode, .evict_inode = minix_evict_inode, .put_super = minix_put_super, diff --git a/fs/mpage.c b/fs/mpage.c index 3f19da75178b..436a85260394 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -47,10 +47,9 @@ static void mpage_end_io(struct bio *bio) { struct bio_vec *bv; - int i; struct bvec_iter_all iter_all; - bio_for_each_segment_all(bv, bio, i, iter_all) { + bio_for_each_segment_all(bv, bio, iter_all) { struct page *page = bv->bv_page; page_endio(page, bio_op(bio), blk_status_to_errno(bio->bi_status)); diff --git a/fs/namei.c b/fs/namei.c index dede0147b3f6..20831c2fbb34 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1066,7 +1066,7 @@ const char *get_link(struct nameidata *nd) return ERR_PTR(error); nd->last_type = LAST_BIND; - res = inode->i_link; + res = READ_ONCE(inode->i_link); if (!res) { const char * (*get)(struct dentry *, struct inode *, struct delayed_call *); @@ -4498,10 +4498,10 @@ out: inode_unlock(target); dput(new_dentry); if (!error) { - fsnotify_move(old_dir, new_dir, old_name.name, is_dir, + fsnotify_move(old_dir, new_dir, &old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { - fsnotify_move(new_dir, old_dir, old_dentry->d_name.name, + fsnotify_move(new_dir, old_dir, &old_dentry->d_name, new_is_dir, NULL, new_dentry); } } @@ -4729,7 +4729,7 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) spin_unlock(&inode->i_lock); } - link = inode->i_link; + link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) diff --git a/fs/namespace.c b/fs/namespace.c index c9cab307fa77..ffb13f0562b0 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -20,6 +20,7 @@ #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ +#include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> @@ -1832,6 +1833,27 @@ struct vfsmount *collect_mounts(const struct path *path) return &tree->mnt; } +static void free_mnt_ns(struct mnt_namespace *); +static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); + +void dissolve_on_fput(struct vfsmount *mnt) +{ + struct mnt_namespace *ns; + namespace_lock(); + lock_mount_hash(); + ns = real_mount(mnt)->mnt_ns; + if (ns) { + if (is_anon_ns(ns)) + umount_tree(real_mount(mnt), UMOUNT_CONNECTED); + else + ns = NULL; + } + unlock_mount_hash(); + namespace_unlock(); + if (ns) + free_mnt_ns(ns); +} + void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); @@ -2065,6 +2087,10 @@ static int attach_recursive_mnt(struct mount *source_mnt, attach_mnt(source_mnt, dest_mnt, dest_mp); touch_mnt_namespace(source_mnt->mnt_ns); } else { + if (source_mnt->mnt_ns) { + /* move from anon - the caller will destroy */ + list_del_init(&source_mnt->mnt_ns->list); + } mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } @@ -2222,6 +2248,30 @@ static bool has_locked_children(struct mount *mnt, struct dentry *dentry) return false; } +static struct mount *__do_loopback(struct path *old_path, int recurse) +{ + struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); + + if (IS_MNT_UNBINDABLE(old)) + return mnt; + + if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) + return mnt; + + if (!recurse && has_locked_children(old, old_path->dentry)) + return mnt; + + if (recurse) + mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); + else + mnt = clone_mnt(old, old_path->dentry, 0); + + if (!IS_ERR(mnt)) + mnt->mnt.mnt_flags &= ~MNT_LOCKED; + + return mnt; +} + /* * do loopback mount. */ @@ -2229,7 +2279,7 @@ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; - struct mount *mnt = NULL, *old, *parent; + struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) @@ -2243,38 +2293,21 @@ static int do_loopback(struct path *path, const char *old_name, goto out; mp = lock_mount(path); - err = PTR_ERR(mp); - if (IS_ERR(mp)) + if (IS_ERR(mp)) { + err = PTR_ERR(mp); goto out; + } - old = real_mount(old_path.mnt); parent = real_mount(path->mnt); - - err = -EINVAL; - if (IS_MNT_UNBINDABLE(old)) - goto out2; - if (!check_mnt(parent)) goto out2; - if (!check_mnt(old) && old_path.dentry->d_op != &ns_dentry_operations) - goto out2; - - if (!recurse && has_locked_children(old, old_path.dentry)) - goto out2; - - if (recurse) - mnt = copy_tree(old, old_path.dentry, CL_COPY_MNT_NS_FILE); - else - mnt = clone_mnt(old, old_path.dentry, 0); - + mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } - mnt->mnt.mnt_flags &= ~MNT_LOCKED; - err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); @@ -2288,6 +2321,96 @@ out: return err; } +static struct file *open_detached_copy(struct path *path, bool recursive) +{ + struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; + struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); + struct mount *mnt, *p; + struct file *file; + + if (IS_ERR(ns)) + return ERR_CAST(ns); + + namespace_lock(); + mnt = __do_loopback(path, recursive); + if (IS_ERR(mnt)) { + namespace_unlock(); + free_mnt_ns(ns); + return ERR_CAST(mnt); + } + + lock_mount_hash(); + for (p = mnt; p; p = next_mnt(p, mnt)) { + p->mnt_ns = ns; + ns->mounts++; + } + ns->root = mnt; + list_add_tail(&ns->list, &mnt->mnt_list); + mntget(&mnt->mnt); + unlock_mount_hash(); + namespace_unlock(); + + mntput(path->mnt); + path->mnt = &mnt->mnt; + file = dentry_open(path, O_PATH, current_cred()); + if (IS_ERR(file)) + dissolve_on_fput(path->mnt); + else + file->f_mode |= FMODE_NEED_UNMOUNT; + return file; +} + +SYSCALL_DEFINE3(open_tree, int, dfd, const char *, filename, unsigned, flags) +{ + struct file *file; + struct path path; + int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; + bool detached = flags & OPEN_TREE_CLONE; + int error; + int fd; + + BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); + + if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | + AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | + OPEN_TREE_CLOEXEC)) + return -EINVAL; + + if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) + return -EINVAL; + + if (flags & AT_NO_AUTOMOUNT) + lookup_flags &= ~LOOKUP_AUTOMOUNT; + if (flags & AT_SYMLINK_NOFOLLOW) + lookup_flags &= ~LOOKUP_FOLLOW; + if (flags & AT_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; + + if (detached && !may_mount()) + return -EPERM; + + fd = get_unused_fd_flags(flags & O_CLOEXEC); + if (fd < 0) + return fd; + + error = user_path_at(dfd, filename, lookup_flags, &path); + if (unlikely(error)) { + file = ERR_PTR(error); + } else { + if (detached) + file = open_detached_copy(&path, flags & AT_RECURSIVE); + else + file = dentry_open(&path, O_PATH, current_cred()); + path_put(&path); + } + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); + } + fd_install(fd, file); + return fd; +} + /* * Don't allow locked mount flags to be cleared. * @@ -2426,72 +2549,117 @@ static inline int tree_contains_unbindable(struct mount *mnt) return 0; } -static int do_move_mount(struct path *path, const char *old_name) +/* + * Check that there aren't references to earlier/same mount namespaces in the + * specified subtree. Such references can act as pins for mount namespaces + * that aren't checked by the mount-cycle checking code, thereby allowing + * cycles to be made. + */ +static bool check_for_nsfs_mounts(struct mount *subtree) { - struct path old_path, parent_path; + struct mount *p; + bool ret = false; + + lock_mount_hash(); + for (p = subtree; p; p = next_mnt(p, subtree)) + if (mnt_ns_loop(p->mnt.mnt_root)) + goto out; + + ret = true; +out: + unlock_mount_hash(); + return ret; +} + +static int do_move_mount(struct path *old_path, struct path *new_path) +{ + struct path parent_path = {.mnt = NULL, .dentry = NULL}; + struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mountpoint *mp; int err; - if (!old_name || !*old_name) - return -EINVAL; - err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); - if (err) - return err; + bool attached; - mp = lock_mount(path); - err = PTR_ERR(mp); + mp = lock_mount(new_path); if (IS_ERR(mp)) - goto out; + return PTR_ERR(mp); - old = real_mount(old_path.mnt); - p = real_mount(path->mnt); + old = real_mount(old_path->mnt); + p = real_mount(new_path->mnt); + attached = mnt_has_parent(old); + ns = old->mnt_ns; err = -EINVAL; - if (!check_mnt(p) || !check_mnt(old)) - goto out1; + /* The mountpoint must be in our namespace. */ + if (!check_mnt(p)) + goto out; - if (old->mnt.mnt_flags & MNT_LOCKED) - goto out1; + /* The thing moved should be either ours or completely unattached. */ + if (attached && !check_mnt(old)) + goto out; - err = -EINVAL; - if (old_path.dentry != old_path.mnt->mnt_root) - goto out1; + if (!attached && !(ns && is_anon_ns(ns))) + goto out; - if (!mnt_has_parent(old)) - goto out1; + if (old->mnt.mnt_flags & MNT_LOCKED) + goto out; - if (d_is_dir(path->dentry) != - d_is_dir(old_path.dentry)) - goto out1; + if (old_path->dentry != old_path->mnt->mnt_root) + goto out; + + if (d_is_dir(new_path->dentry) != + d_is_dir(old_path->dentry)) + goto out; /* * Don't move a mount residing in a shared parent. */ - if (IS_MNT_SHARED(old->mnt_parent)) - goto out1; + if (attached && IS_MNT_SHARED(old->mnt_parent)) + goto out; /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) - goto out1; + goto out; err = -ELOOP; + if (!check_for_nsfs_mounts(old)) + goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) - goto out1; + goto out; - err = attach_recursive_mnt(old, real_mount(path->mnt), mp, &parent_path); + err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, + attached ? &parent_path : NULL); if (err) - goto out1; + goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); -out1: - unlock_mount(mp); out: - if (!err) + unlock_mount(mp); + if (!err) { path_put(&parent_path); + if (!attached) + free_mnt_ns(ns); + } + return err; +} + +static int do_move_mount_old(struct path *path, const char *old_name) +{ + struct path old_path; + int err; + + if (!old_name || !*old_name) + return -EINVAL; + + err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); + if (err) + return err; + + err = do_move_mount(&old_path, path); path_put(&old_path); return err; } @@ -2937,7 +3105,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) retval = do_change_type(&path, flags); else if (flags & MS_MOVE) - retval = do_move_mount(&path, dev_name); + retval = do_move_mount_old(&path, dev_name); else retval = do_new_mount(&path, type_page, sb_flags, mnt_flags, dev_name, data_page); @@ -3166,6 +3334,203 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, } /* + * Create a kernel mount representation for a new, prepared superblock + * (specified by fs_fd) and attach to an open_tree-like file descriptor. + */ +SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, + unsigned int, attr_flags) +{ + struct mnt_namespace *ns; + struct fs_context *fc; + struct file *file; + struct path newmount; + struct mount *mnt; + struct fd f; + unsigned int mnt_flags = 0; + long ret; + + if (!may_mount()) + return -EPERM; + + if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) + return -EINVAL; + + if (attr_flags & ~(MOUNT_ATTR_RDONLY | + MOUNT_ATTR_NOSUID | + MOUNT_ATTR_NODEV | + MOUNT_ATTR_NOEXEC | + MOUNT_ATTR__ATIME | + MOUNT_ATTR_NODIRATIME)) + return -EINVAL; + + if (attr_flags & MOUNT_ATTR_RDONLY) + mnt_flags |= MNT_READONLY; + if (attr_flags & MOUNT_ATTR_NOSUID) + mnt_flags |= MNT_NOSUID; + if (attr_flags & MOUNT_ATTR_NODEV) + mnt_flags |= MNT_NODEV; + if (attr_flags & MOUNT_ATTR_NOEXEC) + mnt_flags |= MNT_NOEXEC; + if (attr_flags & MOUNT_ATTR_NODIRATIME) + mnt_flags |= MNT_NODIRATIME; + + switch (attr_flags & MOUNT_ATTR__ATIME) { + case MOUNT_ATTR_STRICTATIME: + break; + case MOUNT_ATTR_NOATIME: + mnt_flags |= MNT_NOATIME; + break; + case MOUNT_ATTR_RELATIME: + mnt_flags |= MNT_RELATIME; + break; + default: + return -EINVAL; + } + + f = fdget(fs_fd); + if (!f.file) + return -EBADF; + + ret = -EINVAL; + if (f.file->f_op != &fscontext_fops) + goto err_fsfd; + + fc = f.file->private_data; + + ret = mutex_lock_interruptible(&fc->uapi_mutex); + if (ret < 0) + goto err_fsfd; + + /* There must be a valid superblock or we can't mount it */ + ret = -EINVAL; + if (!fc->root) + goto err_unlock; + + ret = -EPERM; + if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { + pr_warn("VFS: Mount too revealing\n"); + goto err_unlock; + } + + ret = -EBUSY; + if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) + goto err_unlock; + + ret = -EPERM; + if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock()) + goto err_unlock; + + newmount.mnt = vfs_create_mount(fc); + if (IS_ERR(newmount.mnt)) { + ret = PTR_ERR(newmount.mnt); + goto err_unlock; + } + newmount.dentry = dget(fc->root); + newmount.mnt->mnt_flags = mnt_flags; + + /* We've done the mount bit - now move the file context into more or + * less the same state as if we'd done an fspick(). We don't want to + * do any memory allocation or anything like that at this point as we + * don't want to have to handle any errors incurred. + */ + vfs_clean_context(fc); + + ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); + if (IS_ERR(ns)) { + ret = PTR_ERR(ns); + goto err_path; + } + mnt = real_mount(newmount.mnt); + mnt->mnt_ns = ns; + ns->root = mnt; + ns->mounts = 1; + list_add(&mnt->mnt_list, &ns->list); + + /* Attach to an apparent O_PATH fd with a note that we need to unmount + * it, not just simply put it. + */ + file = dentry_open(&newmount, O_PATH, fc->cred); + if (IS_ERR(file)) { + dissolve_on_fput(newmount.mnt); + ret = PTR_ERR(file); + goto err_path; + } + file->f_mode |= FMODE_NEED_UNMOUNT; + + ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); + if (ret >= 0) + fd_install(ret, file); + else + fput(file); + +err_path: + path_put(&newmount); +err_unlock: + mutex_unlock(&fc->uapi_mutex); +err_fsfd: + fdput(f); + return ret; +} + +/* + * Move a mount from one place to another. In combination with + * fsopen()/fsmount() this is used to install a new mount and in combination + * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy + * a mount subtree. + * + * Note the flags value is a combination of MOVE_MOUNT_* flags. + */ +SYSCALL_DEFINE5(move_mount, + int, from_dfd, const char *, from_pathname, + int, to_dfd, const char *, to_pathname, + unsigned int, flags) +{ + struct path from_path, to_path; + unsigned int lflags; + int ret = 0; + + if (!may_mount()) + return -EPERM; + + if (flags & ~MOVE_MOUNT__MASK) + return -EINVAL; + + /* If someone gives a pathname, they aren't permitted to move + * from an fd that requires unmount as we can't get at the flag + * to clear it afterwards. + */ + lflags = 0; + if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; + if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; + if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; + + ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); + if (ret < 0) + return ret; + + lflags = 0; + if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; + if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; + if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; + + ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); + if (ret < 0) + goto out_from; + + ret = security_move_mount(&from_path, &to_path); + if (ret < 0) + goto out_to; + + ret = do_move_mount(&from_path, &to_path); + +out_to: + path_put(&to_path); +out_from: + path_put(&from_path); + return ret; +} + +/* * Return true if path is reachable from root * * namespace_sem or mount_lock is held diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 5f93cfacb3d1..69d02cf8cf37 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -121,7 +121,6 @@ config PNFS_FILE_LAYOUT config PNFS_BLOCK tristate depends on NFS_V4_1 && BLK_DEV_DM - depends on 64BIT || LBDAF default NFS_V4 config PNFS_FLEXFILE_LAYOUT diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 0b602a39dd71..7817ad94a6ba 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -41,11 +41,13 @@ static struct svc_program nfs4_callback_program; static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net) { + const struct cred *cred = current_cred(); int ret; struct nfs_net *nn = net_generic(net, nfs_net_id); ret = svc_create_xprt(serv, "tcp", net, PF_INET, - nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, + cred); if (ret <= 0) goto out_err; nn->nfs_callback_tcpport = ret; @@ -53,7 +55,8 @@ static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net) nn->nfs_callback_tcpport, PF_INET, net->ns.inum); ret = svc_create_xprt(serv, "tcp", net, PF_INET6, - nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, + cred); if (ret > 0) { nn->nfs_callback_tcpport6 = ret; dprintk("NFS: Callback listener port = %u (af %u, net %x)\n", @@ -457,4 +460,6 @@ static struct svc_program nfs4_callback_program = { .pg_class = "nfs", /* authentication class */ .pg_stats = &nfs4_callback_stats, .pg_authenticate = nfs_callback_authenticate, + .pg_init_request = svc_generic_init_request, + .pg_rpcbind_set = svc_generic_rpcbind_set, }; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 06233bfa6d73..73a5a5ea2976 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -983,7 +983,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) out_invalidcred: pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n"); - return rpc_autherr_badcred; + return svc_return_autherr(rqstp, rpc_autherr_badcred); } /* diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 90d71fda65ce..3d04cb0b839e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -284,6 +284,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat struct nfs_client *clp; const struct sockaddr *sap = data->addr; struct nfs_net *nn = net_generic(data->net, nfs_net_id); + int error; again: list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { @@ -296,9 +297,11 @@ again: if (clp->cl_cons_state > NFS_CS_READY) { refcount_inc(&clp->cl_count); spin_unlock(&nn->nfs_client_lock); - nfs_wait_client_init_complete(clp); + error = nfs_wait_client_init_complete(clp); nfs_put_client(clp); spin_lock(&nn->nfs_client_lock); + if (error < 0) + return ERR_PTR(error); goto again; } @@ -407,6 +410,8 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) clp = nfs_match_client(cl_init); if (clp) { spin_unlock(&nn->nfs_client_lock); + if (IS_ERR(clp)) + return clp; if (new) new->rpc_ops->free_client(new); return nfs_found_client(cl_init, clp); @@ -500,6 +505,7 @@ int nfs_create_rpc_client(struct nfs_client *clp, .program = &nfs_program, .version = clp->rpc_ops->version, .authflavor = flavor, + .cred = cl_init->cred, }; if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) @@ -552,6 +558,7 @@ static int nfs_start_lockd(struct nfs_server *server) 1 : 0, .net = clp->cl_net, .nlmclnt_ops = clp->cl_nfs_mod->rpc_ops->nlmclnt_ops, + .cred = current_cred(), }; if (nlm_init.nfs_version > 3) @@ -598,6 +605,8 @@ int nfs_init_server_rpcclient(struct nfs_server *server, sizeof(server->client->cl_timeout_default)); server->client->cl_timeout = &server->client->cl_timeout_default; server->client->cl_softrtry = 0; + if (server->flags & NFS_MOUNT_SOFTERR) + server->client->cl_softerr = 1; if (server->flags & NFS_MOUNT_SOFT) server->client->cl_softrtry = 1; @@ -652,6 +661,7 @@ static int nfs_init_server(struct nfs_server *server, .proto = data->nfs_server.protocol, .net = data->net, .timeparms = &timeparms, + .cred = server->cred, }; struct nfs_client *clp; int error; @@ -920,6 +930,7 @@ void nfs_free_server(struct nfs_server *server) ida_destroy(&server->lockowner_id); ida_destroy(&server->openowner_id); nfs_free_iostats(server->io_stats); + put_cred(server->cred); kfree(server); nfs_release_automount_timer(); } @@ -940,6 +951,8 @@ struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info, if (!server) return ERR_PTR(-ENOMEM); + server->cred = get_cred(current_cred()); + error = -ENOMEM; fattr = nfs_alloc_fattr(); if (fattr == NULL) @@ -1006,6 +1019,8 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source, if (!server) return ERR_PTR(-ENOMEM); + server->cred = get_cred(source->cred); + error = -ENOMEM; fattr_fsinfo = nfs_alloc_fattr(); if (fattr_fsinfo == NULL) diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 2f6b447cdd82..8b78274e3e56 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -1034,6 +1034,18 @@ void nfs_mark_test_expired_all_delegations(struct nfs_client *clp) } /** + * nfs_test_expired_all_delegations - test all delegations for a client + * @clp: nfs_client to process + * + * Helper for handling "recallable state revoked" status from server. + */ +void nfs_test_expired_all_delegations(struct nfs_client *clp) +{ + nfs_mark_test_expired_all_delegations(clp); + nfs4_schedule_state_manager(clp); +} + +/** * nfs_reap_expired_delegations - reap expired delegations * @clp: nfs_client to process * diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 35b4b02c1ae0..5799777df5ec 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -58,6 +58,7 @@ void nfs_delegation_mark_reclaim(struct nfs_client *clp); void nfs_delegation_reap_unclaimed(struct nfs_client *clp); void nfs_mark_test_expired_all_delegations(struct nfs_client *clp); +void nfs_test_expired_all_delegations(struct nfs_client *clp); void nfs_reap_expired_delegations(struct nfs_client *clp); /* NFSv4 delegation-related procedures */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index a71d0b42d160..47d445bec8c9 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -714,8 +714,9 @@ out: * We only need to convert from xdr once so future lookups are much simpler */ static -int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) +int nfs_readdir_filler(void *data, struct page* page) { + nfs_readdir_descriptor_t *desc = data; struct inode *inode = file_inode(desc->file); int ret; @@ -762,8 +763,8 @@ void cache_page_release(nfs_readdir_descriptor_t *desc) static struct page *get_cache_page(nfs_readdir_descriptor_t *desc) { - return read_cache_page(desc->file->f_mapping, - desc->page_index, (filler_t *)nfs_readdir_filler, desc); + return read_cache_page(desc->file->f_mapping, desc->page_index, + nfs_readdir_filler, desc); } /* diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 0fd811ac08b5..2436bd92bc00 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -492,7 +492,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, struct nfs_page *req; unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); /* XXX do we need to do the eof zeroing found in async_filler? */ - req = nfs_create_request(dreq->ctx, pagevec[i], NULL, + req = nfs_create_request(dreq->ctx, pagevec[i], pgbase, req_len); if (IS_ERR(req)) { result = PTR_ERR(req); @@ -663,6 +663,8 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) } list_for_each_entry_safe(req, tmp, &reqs, wb_list) { + /* Bump the transmission count */ + req->wb_nio++; if (!nfs_pageio_add_request(&desc, req)) { nfs_list_move_request(req, &failed); spin_lock(&cinfo.inode->i_lock); @@ -703,6 +705,11 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) req = nfs_list_entry(data->pages.next); nfs_list_remove_request(req); if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) { + /* + * Despite the reboot, the write was successful, + * so reset wb_nio. + */ + req->wb_nio = 0; /* Note the rewrite will go through mds */ nfs_mark_request_commit(req, NULL, &cinfo, 0); } else @@ -899,7 +906,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, struct nfs_page *req; unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); - req = nfs_create_request(dreq->ctx, pagevec[i], NULL, + req = nfs_create_request(dreq->ctx, pagevec[i], pgbase, req_len); if (IS_ERR(req)) { result = PTR_ERR(req); diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index a7d3df85736d..e6a700f01452 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -22,7 +22,7 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, char *ip_addr = NULL; int ip_len; - ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL); + ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL, false); if (ip_len > 0) ret = rpc_pton(net, ip_addr, ip_len, sa, salen); else diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 4899b85f9b3c..144e183250c3 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -147,7 +147,7 @@ nfs_file_flush(struct file *file, fl_owner_t id) return 0; /* Flush writes to the server and return any errors */ - return vfs_fsync(file, 0); + return nfs_wb_all(inode); } ssize_t @@ -199,13 +199,6 @@ EXPORT_SYMBOL_GPL(nfs_file_mmap); * Flush any dirty pages for this process, and check for write errors. * The return status from this call provides a reliable indication of * whether any write errors occurred for this process. - * - * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to - * disk, but it retrieves and clears ctx->error after synching, despite - * the two being set at the same time in nfs_context_set_write_error(). - * This is because the former is used to notify the _next_ call to - * nfs_file_write() that a write error occurred, and hence cause it to - * fall back to doing a synchronous write. */ static int nfs_file_fsync_commit(struct file *file, int datasync) @@ -220,11 +213,8 @@ nfs_file_fsync_commit(struct file *file, int datasync) nfs_inc_stats(inode, NFSIOS_VFSFSYNC); do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); status = nfs_commit_inode(inode, FLUSH_SYNC); - if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) { - ret = xchg(&ctx->error, 0); - if (ret) - goto out; - } + if (status == 0) + status = file_check_and_advance_wb_err(file); if (status < 0) { ret = status; goto out; @@ -245,13 +235,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) trace_nfs_fsync_enter(inode); do { - struct nfs_open_context *ctx = nfs_file_open_context(file); - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); - if (test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) { - int ret2 = xchg(&ctx->error, 0); - if (ret2) - ret = ret2; - } + ret = file_write_and_wait_range(file, start, end); if (ret != 0) break; ret = nfs_file_fsync_commit(file, datasync); @@ -600,8 +584,7 @@ static int nfs_need_check_write(struct file *filp, struct inode *inode) struct nfs_open_context *ctx; ctx = nfs_file_open_context(filp); - if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) || - nfs_ctx_key_to_expire(ctx, inode)) + if (nfs_ctx_key_to_expire(ctx, inode)) return 1; return 0; } @@ -655,7 +638,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) /* Return error values */ if (nfs_need_check_write(file, inode)) { - int err = vfs_fsync(file, 0); + int err = nfs_wb_all(inode); if (err < 0) result = err; } @@ -709,7 +692,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) * Flush all pending writes before doing anything * with locks.. */ - vfs_fsync(filp, 0); + nfs_wb_all(inode); l_ctx = nfs_get_lock_context(nfs_file_open_context(filp)); if (!IS_ERR(l_ctx)) { diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 61f46facb39c..3cb073c50fa6 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -904,7 +904,7 @@ fl_pnfs_update_layout(struct inode *ino, status = filelayout_check_deviceid(lo, fl, gfp_flags); if (status) { pnfs_put_lseg(lseg); - lseg = ERR_PTR(status); + lseg = NULL; } out: return lseg; @@ -917,7 +917,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, pnfs_generic_pg_check_layout(pgio); if (!pgio->pg_lseg) { pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode, - req->wb_context, + nfs_req_openctx(req), 0, NFS4_MAX_UINT64, IOMODE_READ, @@ -944,7 +944,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, pnfs_generic_pg_check_layout(pgio); if (!pgio->pg_lseg) { pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode, - req->wb_context, + nfs_req_openctx(req), 0, NFS4_MAX_UINT64, IOMODE_RW, diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 6673d4ff5a2a..9920c52bd0cd 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -28,6 +28,8 @@ #define FF_LAYOUT_POLL_RETRY_MAX (15*HZ) #define FF_LAYOUTRETURN_MAXERR 20 +static unsigned short io_maxretrans; + static void ff_layout_read_record_layoutstats_done(struct rpc_task *task, struct nfs_pgio_header *hdr); static int ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, @@ -871,7 +873,7 @@ ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio, { pnfs_put_lseg(pgio->pg_lseg); pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, + nfs_req_openctx(req), 0, NFS4_MAX_UINT64, IOMODE_READ, @@ -925,6 +927,7 @@ retry: pgm = &pgio->pg_mirrors[0]; pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; + pgio->pg_maxretrans = io_maxretrans; return; out_nolseg: if (pgio->pg_error < 0) @@ -950,7 +953,7 @@ retry: pnfs_generic_pg_check_layout(pgio); if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, + nfs_req_openctx(req), 0, NFS4_MAX_UINT64, IOMODE_RW, @@ -992,6 +995,7 @@ retry: pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize; } + pgio->pg_maxretrans = io_maxretrans; return; out_mds: @@ -1006,7 +1010,7 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, { if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, + nfs_req_openctx(req), 0, NFS4_MAX_UINT64, IOMODE_RW, @@ -2515,3 +2519,7 @@ MODULE_DESCRIPTION("The NFSv4 flexfile layout driver"); module_init(nfs4flexfilelayout_init); module_exit(nfs4flexfilelayout_exit); + +module_param(io_maxretrans, ushort, 0644); +MODULE_PARM_DESC(io_maxretrans, "The number of times the NFSv4.1 client " + "retries an I/O request before returning an error. "); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 414a90d48493..3bc2550cfe4e 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -885,10 +885,14 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) spin_lock(&inode->i_lock); res = __nfs_find_lock_context(ctx); if (res == NULL) { - list_add_tail_rcu(&new->list, &ctx->lock_context.list); - new->open_context = ctx; - res = new; - new = NULL; + new->open_context = get_nfs_open_context(ctx); + if (new->open_context) { + list_add_tail_rcu(&new->list, + &ctx->lock_context.list); + res = new; + new = NULL; + } else + res = ERR_PTR(-EBADF); } spin_unlock(&inode->i_lock); kfree(new); @@ -906,6 +910,7 @@ void nfs_put_lock_context(struct nfs_lock_context *l_ctx) return; list_del_rcu(&l_ctx->list); spin_unlock(&inode->i_lock); + put_nfs_open_context(ctx); kfree_rcu(l_ctx, rcu_head); } EXPORT_SYMBOL_GPL(nfs_put_lock_context); @@ -2055,17 +2060,11 @@ struct inode *nfs_alloc_inode(struct super_block *sb) } EXPORT_SYMBOL_GPL(nfs_alloc_inode); -static void nfs_i_callback(struct rcu_head *head) +void nfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(nfs_inode_cachep, NFS_I(inode)); } - -void nfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, nfs_i_callback); -} -EXPORT_SYMBOL_GPL(nfs_destroy_inode); +EXPORT_SYMBOL_GPL(nfs_free_inode); static inline void nfs4_init_once(struct nfs_inode *nfsi) { diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index c7cf23ae6597..498fab72f70b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -84,6 +84,7 @@ struct nfs_client_initdata { u32 minorversion; struct net *net; const struct rpc_timeout *timeparms; + const struct cred *cred; }; /* @@ -381,7 +382,7 @@ int nfs_check_flags(int); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); -extern void nfs_destroy_inode(struct inode *); +extern void nfs_free_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); @@ -766,15 +767,10 @@ static inline bool nfs_error_is_fatal(int err) case -ESTALE: case -E2BIG: case -ENOMEM: + case -ETIMEDOUT: return true; default: return false; } } -static inline void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) -{ - ctx->error = error; - smp_wmb(); - set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); -} diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index d979ff4fee7e..cb7c10e9721e 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -163,6 +163,7 @@ int nfs_mount(struct nfs_mount_request *info) .program = &mnt_program, .version = info->version, .authflavor = RPC_AUTH_UNIX, + .cred = current_cred(), }; struct rpc_clnt *mnt_clnt; int status; @@ -249,6 +250,7 @@ void nfs_umount(const struct nfs_mount_request *info) .version = info->version, .authflavor = RPC_AUTH_UNIX, .flags = RPC_CLNT_CREATE_NOPING, + .cred = current_cred(), }; struct rpc_message msg = { .rpc_argp = info->dirpath, diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index a7ed29de0a40..572794dab4b1 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -76,6 +76,20 @@ static int nfs_stat_to_errno(enum nfs_stat); * or decoded inline. */ +static struct user_namespace *rpc_userns(const struct rpc_clnt *clnt) +{ + if (clnt && clnt->cl_cred) + return clnt->cl_cred->user_ns; + return &init_user_ns; +} + +static struct user_namespace *rpc_rqst_userns(const struct rpc_rqst *rqstp) +{ + if (rqstp->rq_task) + return rpc_userns(rqstp->rq_task->tk_client); + return &init_user_ns; +} + /* * typedef opaque nfsdata<>; */ @@ -248,7 +262,8 @@ static __be32 *xdr_decode_time(__be32 *p, struct timespec *timep) * }; * */ -static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr) +static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, + struct user_namespace *userns) { u32 rdev, type; __be32 *p; @@ -263,10 +278,10 @@ static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr) fattr->mode = be32_to_cpup(p++); fattr->nlink = be32_to_cpup(p++); - fattr->uid = make_kuid(&init_user_ns, be32_to_cpup(p++)); + fattr->uid = make_kuid(userns, be32_to_cpup(p++)); if (!uid_valid(fattr->uid)) goto out_uid; - fattr->gid = make_kgid(&init_user_ns, be32_to_cpup(p++)); + fattr->gid = make_kgid(userns, be32_to_cpup(p++)); if (!gid_valid(fattr->gid)) goto out_gid; @@ -321,7 +336,8 @@ static __be32 *xdr_time_not_set(__be32 *p) return p; } -static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr) +static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr, + struct user_namespace *userns) { struct timespec ts; __be32 *p; @@ -333,11 +349,11 @@ static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr) else *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); if (attr->ia_valid & ATTR_UID) - *p++ = cpu_to_be32(from_kuid(&init_user_ns, attr->ia_uid)); + *p++ = cpu_to_be32(from_kuid_munged(userns, attr->ia_uid)); else *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); if (attr->ia_valid & ATTR_GID) - *p++ = cpu_to_be32(from_kgid(&init_user_ns, attr->ia_gid)); + *p++ = cpu_to_be32(from_kgid_munged(userns, attr->ia_gid)); else *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); if (attr->ia_valid & ATTR_SIZE) @@ -451,7 +467,8 @@ out_cheating: * }; */ static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result, - __u32 *op_status) + __u32 *op_status, + struct user_namespace *userns) { enum nfs_stat status; int error; @@ -463,7 +480,7 @@ static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result, *op_status = status; if (status != NFS_OK) goto out_default; - error = decode_fattr(xdr, result); + error = decode_fattr(xdr, result, userns); out: return error; out_default: @@ -498,19 +515,21 @@ static void encode_diropargs(struct xdr_stream *xdr, const struct nfs_fh *fh, * void; * }; */ -static int decode_diropok(struct xdr_stream *xdr, struct nfs_diropok *result) +static int decode_diropok(struct xdr_stream *xdr, struct nfs_diropok *result, + struct user_namespace *userns) { int error; error = decode_fhandle(xdr, result->fh); if (unlikely(error)) goto out; - error = decode_fattr(xdr, result->fattr); + error = decode_fattr(xdr, result->fattr, userns); out: return error; } -static int decode_diropres(struct xdr_stream *xdr, struct nfs_diropok *result) +static int decode_diropres(struct xdr_stream *xdr, struct nfs_diropok *result, + struct user_namespace *userns) { enum nfs_stat status; int error; @@ -520,7 +539,7 @@ static int decode_diropres(struct xdr_stream *xdr, struct nfs_diropok *result) goto out; if (status != NFS_OK) goto out_default; - error = decode_diropok(xdr, result); + error = decode_diropok(xdr, result, userns); out: return error; out_default: @@ -559,7 +578,7 @@ static void nfs2_xdr_enc_sattrargs(struct rpc_rqst *req, const struct nfs_sattrargs *args = data; encode_fhandle(xdr, args->fh); - encode_sattr(xdr, args->sattr); + encode_sattr(xdr, args->sattr, rpc_rqst_userns(req)); } static void nfs2_xdr_enc_diropargs(struct rpc_rqst *req, @@ -674,7 +693,7 @@ static void nfs2_xdr_enc_createargs(struct rpc_rqst *req, const struct nfs_createargs *args = data; encode_diropargs(xdr, args->fh, args->name, args->len); - encode_sattr(xdr, args->sattr); + encode_sattr(xdr, args->sattr, rpc_rqst_userns(req)); } static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req, @@ -741,7 +760,7 @@ static void nfs2_xdr_enc_symlinkargs(struct rpc_rqst *req, encode_diropargs(xdr, args->fromfh, args->fromname, args->fromlen); encode_path(xdr, args->pages, args->pathlen); - encode_sattr(xdr, args->sattr); + encode_sattr(xdr, args->sattr, rpc_rqst_userns(req)); } /* @@ -803,13 +822,13 @@ out_default: static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr, void *result) { - return decode_attrstat(xdr, result, NULL); + return decode_attrstat(xdr, result, NULL, rpc_rqst_userns(req)); } static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr, void *result) { - return decode_diropres(xdr, result); + return decode_diropres(xdr, result, rpc_rqst_userns(req)); } /* @@ -864,7 +883,7 @@ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr, result->op_status = status; if (status != NFS_OK) goto out_default; - error = decode_fattr(xdr, result->fattr); + error = decode_fattr(xdr, result->fattr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; error = decode_nfsdata(xdr, result); @@ -881,7 +900,8 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, /* All NFSv2 writes are "file sync" writes */ result->verf->committed = NFS_FILE_SYNC; - return decode_attrstat(xdr, result->fattr, &result->op_status); + return decode_attrstat(xdr, result->fattr, &result->op_status, + rpc_rqst_userns(req)); } /** diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 7879f2a0fcfd..1afdb0f7473f 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -91,6 +91,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, .proto = ds_proto, .net = mds_clp->cl_net, .timeparms = &ds_timeout, + .cred = mds_srv->cred, }; struct nfs_client *clp; char buf[INET6_ADDRSTRLEN + 1]; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 110358f4986d..abbbdde97e31 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -104,6 +104,20 @@ static const umode_t nfs_type2fmt[] = { [NF3FIFO] = S_IFIFO, }; +static struct user_namespace *rpc_userns(const struct rpc_clnt *clnt) +{ + if (clnt && clnt->cl_cred) + return clnt->cl_cred->user_ns; + return &init_user_ns; +} + +static struct user_namespace *rpc_rqst_userns(const struct rpc_rqst *rqstp) +{ + if (rqstp->rq_task) + return rpc_userns(rqstp->rq_task->tk_client); + return &init_user_ns; +} + /* * Encode/decode NFSv3 basic data types * @@ -516,7 +530,8 @@ static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec *timep) * set_mtime mtime; * }; */ -static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr) +static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr, + struct user_namespace *userns) { struct timespec ts; u32 nbytes; @@ -551,13 +566,13 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr) if (attr->ia_valid & ATTR_UID) { *p++ = xdr_one; - *p++ = cpu_to_be32(from_kuid(&init_user_ns, attr->ia_uid)); + *p++ = cpu_to_be32(from_kuid_munged(userns, attr->ia_uid)); } else *p++ = xdr_zero; if (attr->ia_valid & ATTR_GID) { *p++ = xdr_one; - *p++ = cpu_to_be32(from_kgid(&init_user_ns, attr->ia_gid)); + *p++ = cpu_to_be32(from_kgid_munged(userns, attr->ia_gid)); } else *p++ = xdr_zero; @@ -606,7 +621,8 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr) * nfstime3 ctime; * }; */ -static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr) +static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr, + struct user_namespace *userns) { umode_t fmode; __be32 *p; @@ -619,10 +635,10 @@ static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr) fattr->mode = (be32_to_cpup(p++) & ~S_IFMT) | fmode; fattr->nlink = be32_to_cpup(p++); - fattr->uid = make_kuid(&init_user_ns, be32_to_cpup(p++)); + fattr->uid = make_kuid(userns, be32_to_cpup(p++)); if (!uid_valid(fattr->uid)) goto out_uid; - fattr->gid = make_kgid(&init_user_ns, be32_to_cpup(p++)); + fattr->gid = make_kgid(userns, be32_to_cpup(p++)); if (!gid_valid(fattr->gid)) goto out_gid; @@ -659,7 +675,8 @@ out_gid: * void; * }; */ -static int decode_post_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) +static int decode_post_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr, + struct user_namespace *userns) { __be32 *p; @@ -667,7 +684,7 @@ static int decode_post_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) if (unlikely(!p)) return -EIO; if (*p != xdr_zero) - return decode_fattr3(xdr, fattr); + return decode_fattr3(xdr, fattr, userns); return 0; } @@ -728,14 +745,15 @@ static int decode_pre_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) return 0; } -static int decode_wcc_data(struct xdr_stream *xdr, struct nfs_fattr *fattr) +static int decode_wcc_data(struct xdr_stream *xdr, struct nfs_fattr *fattr, + struct user_namespace *userns) { int error; error = decode_pre_op_attr(xdr, fattr); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, fattr); + error = decode_post_op_attr(xdr, fattr, userns); out: return error; } @@ -837,7 +855,7 @@ static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req, { const struct nfs3_sattrargs *args = data; encode_nfs_fh3(xdr, args->fh); - encode_sattr3(xdr, args->sattr); + encode_sattr3(xdr, args->sattr, rpc_rqst_userns(req)); encode_sattrguard3(xdr, args); } @@ -998,13 +1016,14 @@ static void nfs3_xdr_enc_write3args(struct rpc_rqst *req, * }; */ static void encode_createhow3(struct xdr_stream *xdr, - const struct nfs3_createargs *args) + const struct nfs3_createargs *args, + struct user_namespace *userns) { encode_uint32(xdr, args->createmode); switch (args->createmode) { case NFS3_CREATE_UNCHECKED: case NFS3_CREATE_GUARDED: - encode_sattr3(xdr, args->sattr); + encode_sattr3(xdr, args->sattr, userns); break; case NFS3_CREATE_EXCLUSIVE: encode_createverf3(xdr, args->verifier); @@ -1021,7 +1040,7 @@ static void nfs3_xdr_enc_create3args(struct rpc_rqst *req, const struct nfs3_createargs *args = data; encode_diropargs3(xdr, args->fh, args->name, args->len); - encode_createhow3(xdr, args); + encode_createhow3(xdr, args, rpc_rqst_userns(req)); } /* @@ -1039,7 +1058,7 @@ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, const struct nfs3_mkdirargs *args = data; encode_diropargs3(xdr, args->fh, args->name, args->len); - encode_sattr3(xdr, args->sattr); + encode_sattr3(xdr, args->sattr, rpc_rqst_userns(req)); } /* @@ -1056,11 +1075,12 @@ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, * }; */ static void encode_symlinkdata3(struct xdr_stream *xdr, - const void *data) + const void *data, + struct user_namespace *userns) { const struct nfs3_symlinkargs *args = data; - encode_sattr3(xdr, args->sattr); + encode_sattr3(xdr, args->sattr, userns); encode_nfspath3(xdr, args->pages, args->pathlen); } @@ -1071,7 +1091,7 @@ static void nfs3_xdr_enc_symlink3args(struct rpc_rqst *req, const struct nfs3_symlinkargs *args = data; encode_diropargs3(xdr, args->fromfh, args->fromname, args->fromlen); - encode_symlinkdata3(xdr, args); + encode_symlinkdata3(xdr, args, rpc_rqst_userns(req)); xdr->buf->flags |= XDRBUF_WRITE; } @@ -1100,24 +1120,26 @@ static void nfs3_xdr_enc_symlink3args(struct rpc_rqst *req, * }; */ static void encode_devicedata3(struct xdr_stream *xdr, - const struct nfs3_mknodargs *args) + const struct nfs3_mknodargs *args, + struct user_namespace *userns) { - encode_sattr3(xdr, args->sattr); + encode_sattr3(xdr, args->sattr, userns); encode_specdata3(xdr, args->rdev); } static void encode_mknoddata3(struct xdr_stream *xdr, - const struct nfs3_mknodargs *args) + const struct nfs3_mknodargs *args, + struct user_namespace *userns) { encode_ftype3(xdr, args->type); switch (args->type) { case NF3CHR: case NF3BLK: - encode_devicedata3(xdr, args); + encode_devicedata3(xdr, args, userns); break; case NF3SOCK: case NF3FIFO: - encode_sattr3(xdr, args->sattr); + encode_sattr3(xdr, args->sattr, userns); break; case NF3REG: case NF3DIR: @@ -1134,7 +1156,7 @@ static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req, const struct nfs3_mknodargs *args = data; encode_diropargs3(xdr, args->fh, args->name, args->len); - encode_mknoddata3(xdr, args); + encode_mknoddata3(xdr, args, rpc_rqst_userns(req)); } /* @@ -1379,7 +1401,7 @@ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req, goto out; if (status != NFS3_OK) goto out_default; - error = decode_fattr3(xdr, result); + error = decode_fattr3(xdr, result, rpc_rqst_userns(req)); out: return error; out_default: @@ -1414,7 +1436,7 @@ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_wcc_data(xdr, result); + error = decode_wcc_data(xdr, result, rpc_rqst_userns(req)); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -1449,6 +1471,7 @@ static int nfs3_xdr_dec_lookup3res(struct rpc_rqst *req, struct xdr_stream *xdr, void *data) { + struct user_namespace *userns = rpc_rqst_userns(req); struct nfs3_diropres *result = data; enum nfs_stat status; int error; @@ -1461,14 +1484,14 @@ static int nfs3_xdr_dec_lookup3res(struct rpc_rqst *req, error = decode_nfs_fh3(xdr, result->fh); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, userns); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->dir_attr); + error = decode_post_op_attr(xdr, result->dir_attr, userns); out: return error; out_default: - error = decode_post_op_attr(xdr, result->dir_attr); + error = decode_post_op_attr(xdr, result->dir_attr, userns); if (unlikely(error)) goto out; return nfs3_stat_to_errno(status); @@ -1504,7 +1527,7 @@ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -1545,7 +1568,7 @@ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result); + error = decode_post_op_attr(xdr, result, rpc_rqst_userns(req)); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -1623,7 +1646,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; result->op_status = status; @@ -1694,7 +1717,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_wcc_data(xdr, result->fattr); + error = decode_wcc_data(xdr, result->fattr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; result->op_status = status; @@ -1728,14 +1751,15 @@ out_status: * }; */ static int decode_create3resok(struct xdr_stream *xdr, - struct nfs3_diropres *result) + struct nfs3_diropres *result, + struct user_namespace *userns) { int error; error = decode_post_op_fh3(xdr, result->fh); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, userns); if (unlikely(error)) goto out; /* The server isn't required to return a file handle. @@ -1744,7 +1768,7 @@ static int decode_create3resok(struct xdr_stream *xdr, * values for the new object. */ if (result->fh->size == 0) result->fattr->valid = 0; - error = decode_wcc_data(xdr, result->dir_attr); + error = decode_wcc_data(xdr, result->dir_attr, userns); out: return error; } @@ -1753,6 +1777,7 @@ static int nfs3_xdr_dec_create3res(struct rpc_rqst *req, struct xdr_stream *xdr, void *data) { + struct user_namespace *userns = rpc_rqst_userns(req); struct nfs3_diropres *result = data; enum nfs_stat status; int error; @@ -1762,11 +1787,11 @@ static int nfs3_xdr_dec_create3res(struct rpc_rqst *req, goto out; if (status != NFS3_OK) goto out_default; - error = decode_create3resok(xdr, result); + error = decode_create3resok(xdr, result, userns); out: return error; out_default: - error = decode_wcc_data(xdr, result->dir_attr); + error = decode_wcc_data(xdr, result->dir_attr, userns); if (unlikely(error)) goto out; return nfs3_stat_to_errno(status); @@ -1801,7 +1826,7 @@ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_wcc_data(xdr, result->dir_attr); + error = decode_wcc_data(xdr, result->dir_attr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -1836,6 +1861,7 @@ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, struct xdr_stream *xdr, void *data) { + struct user_namespace *userns = rpc_rqst_userns(req); struct nfs_renameres *result = data; enum nfs_stat status; int error; @@ -1843,10 +1869,10 @@ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_wcc_data(xdr, result->old_fattr); + error = decode_wcc_data(xdr, result->old_fattr, userns); if (unlikely(error)) goto out; - error = decode_wcc_data(xdr, result->new_fattr); + error = decode_wcc_data(xdr, result->new_fattr, userns); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -1880,6 +1906,7 @@ out_status: static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, void *data) { + struct user_namespace *userns = rpc_rqst_userns(req); struct nfs3_linkres *result = data; enum nfs_stat status; int error; @@ -1887,10 +1914,10 @@ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, userns); if (unlikely(error)) goto out; - error = decode_wcc_data(xdr, result->dir_attr); + error = decode_wcc_data(xdr, result->dir_attr, userns); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -1939,6 +1966,7 @@ out_status: int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, bool plus) { + struct user_namespace *userns = rpc_userns(entry->server->client); struct nfs_entry old = *entry; __be32 *p; int error; @@ -1973,7 +2001,7 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, if (plus) { entry->fattr->valid = 0; - error = decode_post_op_attr(xdr, entry->fattr); + error = decode_post_op_attr(xdr, entry->fattr, userns); if (unlikely(error)) return error; if (entry->fattr->valid & NFS_ATTR_FATTR_V3) @@ -2045,11 +2073,12 @@ static int decode_dirlist3(struct xdr_stream *xdr) } static int decode_readdir3resok(struct xdr_stream *xdr, - struct nfs3_readdirres *result) + struct nfs3_readdirres *result, + struct user_namespace *userns) { int error; - error = decode_post_op_attr(xdr, result->dir_attr); + error = decode_post_op_attr(xdr, result->dir_attr, userns); if (unlikely(error)) goto out; /* XXX: do we need to check if result->verf != NULL ? */ @@ -2074,11 +2103,11 @@ static int nfs3_xdr_dec_readdir3res(struct rpc_rqst *req, goto out; if (status != NFS3_OK) goto out_default; - error = decode_readdir3resok(xdr, result); + error = decode_readdir3resok(xdr, result, rpc_rqst_userns(req)); out: return error; out_default: - error = decode_post_op_attr(xdr, result->dir_attr); + error = decode_post_op_attr(xdr, result->dir_attr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; return nfs3_stat_to_errno(status); @@ -2138,7 +2167,7 @@ static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -2212,7 +2241,7 @@ static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -2273,7 +2302,7 @@ static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; if (status != NFS3_OK) @@ -2315,7 +2344,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; - error = decode_wcc_data(xdr, result->fattr); + error = decode_wcc_data(xdr, result->fattr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; result->op_status = status; @@ -2331,14 +2360,15 @@ out_status: #ifdef CONFIG_NFS_V3_ACL static inline int decode_getacl3resok(struct xdr_stream *xdr, - struct nfs3_getaclres *result) + struct nfs3_getaclres *result, + struct user_namespace *userns) { struct posix_acl **acl; unsigned int *aclcnt; size_t hdrlen; int error; - error = decode_post_op_attr(xdr, result->fattr); + error = decode_post_op_attr(xdr, result->fattr, userns); if (unlikely(error)) goto out; error = decode_uint32(xdr, &result->mask); @@ -2386,7 +2416,7 @@ static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req, goto out; if (status != NFS3_OK) goto out_default; - error = decode_getacl3resok(xdr, result); + error = decode_getacl3resok(xdr, result, rpc_rqst_userns(req)); out: return error; out_default: @@ -2405,7 +2435,7 @@ static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, goto out; if (status != NFS3_OK) goto out_default; - error = decode_post_op_attr(xdr, result); + error = decode_post_op_attr(xdr, result, rpc_rqst_userns(req)); out: return error; out_default: diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index ff6f85fb676b..5196bfa7894d 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -329,9 +329,6 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, }; ssize_t err, err2; - if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY)) - return -EOPNOTSUPP; - src_lock = nfs_get_lock_context(nfs_file_open_context(src)); if (IS_ERR(src_lock)) return PTR_ERR(src_lock); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 06ac3d9ac7c6..8a38a254f516 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -206,6 +206,7 @@ struct nfs4_exception { unsigned char delay : 1, recovering : 1, retry : 1; + bool interruptible; }; struct nfs4_state_recovery_ops { diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 1339ede979af..3ce246346f02 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -870,6 +870,7 @@ static int nfs4_set_client(struct nfs_server *server, .minorversion = minorversion, .net = net, .timeparms = timeparms, + .cred = server->cred, }; struct nfs_client *clp; @@ -931,6 +932,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, .minorversion = minor_version, .net = mds_clp->cl_net, .timeparms = &ds_timeout, + .cred = mds_srv->cred, }; char buf[INET6_ADDRSTRLEN + 1]; @@ -1107,6 +1109,8 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, if (!server) return ERR_PTR(-ENOMEM); + server->cred = get_cred(current_cred()); + auth_probe = mount_info->parsed->auth_info.flavor_len < 1; /* set up the general RPC client */ @@ -1143,6 +1147,8 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, parent_server = NFS_SB(data->sb); parent_client = parent_server->nfs_client; + server->cred = get_cred(parent_server->cred); + /* Initialise the client representation from the parent server */ nfs_server_copy_userdata(server, parent_server); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 45b2322e092d..cf42a8b939e3 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -125,7 +125,7 @@ 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 vfs_fsync(file, 0); + return nfs_wb_all(inode); } #ifdef CONFIG_NFS_V4_2 @@ -133,8 +133,10 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t count, unsigned int flags) { + if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY)) + return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) - return -EINVAL; + return -EOPNOTSUPP; return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); } @@ -185,7 +187,7 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off, bool same_inode = false; int ret; - if (remap_flags & ~REMAP_FILE_ADVISORY) + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; /* check alignment w.r.t. clone_blksize */ diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index bf34ddaa2ad7..4884fdae28fb 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -69,8 +69,16 @@ struct idmap { struct rpc_pipe *idmap_pipe; struct idmap_legacy_upcalldata *idmap_upcall_data; struct mutex idmap_mutex; + const struct cred *cred; }; +static struct user_namespace *idmap_userns(const struct idmap *idmap) +{ + if (idmap && idmap->cred) + return idmap->cred->user_ns; + return &init_user_ns; +} + /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields * @fattr: fully initialised struct nfs_fattr @@ -271,14 +279,15 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen, const char *type, struct idmap *idmap) { char *desc; - struct key *rkey; + struct key *rkey = ERR_PTR(-EAGAIN); ssize_t ret; ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc); if (ret < 0) return ERR_PTR(ret); - rkey = request_key(&key_type_id_resolver, desc, ""); + if (!idmap->cred || idmap->cred->user_ns == &init_user_ns) + rkey = request_key(&key_type_id_resolver, desc, ""); if (IS_ERR(rkey)) { mutex_lock(&idmap->idmap_mutex); rkey = request_key_with_auxdata(&key_type_id_resolver_legacy, @@ -452,6 +461,9 @@ nfs_idmap_new(struct nfs_client *clp) if (idmap == NULL) return -ENOMEM; + mutex_init(&idmap->idmap_mutex); + idmap->cred = get_cred(clp->cl_rpcclient->cl_cred); + rpc_init_pipe_dir_object(&idmap->idmap_pdo, &nfs_idmap_pipe_dir_object_ops, idmap); @@ -462,7 +474,6 @@ nfs_idmap_new(struct nfs_client *clp) goto err; } idmap->idmap_pipe = pipe; - mutex_init(&idmap->idmap_mutex); error = rpc_add_pipe_dir_object(clp->cl_net, &clp->cl_rpcclient->cl_pipedir_objects, @@ -475,6 +486,7 @@ nfs_idmap_new(struct nfs_client *clp) err_destroy_pipe: rpc_destroy_pipe_data(idmap->idmap_pipe); err: + put_cred(idmap->cred); kfree(idmap); return error; } @@ -491,6 +503,7 @@ nfs_idmap_delete(struct nfs_client *clp) &clp->cl_rpcclient->cl_pipedir_objects, &idmap->idmap_pdo); rpc_destroy_pipe_data(idmap->idmap_pipe); + put_cred(idmap->cred); kfree(idmap); } @@ -735,7 +748,7 @@ int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_ if (!nfs_map_string_to_numeric(name, namelen, &id)) ret = nfs_idmap_lookup_id(name, namelen, "uid", &id, idmap); if (ret == 0) { - *uid = make_kuid(&init_user_ns, id); + *uid = make_kuid(idmap_userns(idmap), id); if (!uid_valid(*uid)) ret = -ERANGE; } @@ -752,7 +765,7 @@ int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size if (!nfs_map_string_to_numeric(name, namelen, &id)) ret = nfs_idmap_lookup_id(name, namelen, "gid", &id, idmap); if (ret == 0) { - *gid = make_kgid(&init_user_ns, id); + *gid = make_kgid(idmap_userns(idmap), id); if (!gid_valid(*gid)) ret = -ERANGE; } @@ -766,7 +779,7 @@ int nfs_map_uid_to_name(const struct nfs_server *server, kuid_t uid, char *buf, int ret = -EINVAL; __u32 id; - id = from_kuid(&init_user_ns, uid); + id = from_kuid_munged(idmap_userns(idmap), uid); if (!(server->caps & NFS_CAP_UIDGID_NOMAP)) ret = nfs_idmap_lookup_name(id, "user", buf, buflen, idmap); if (ret < 0) @@ -780,7 +793,7 @@ int nfs_map_gid_to_group(const struct nfs_server *server, kgid_t gid, char *buf, int ret = -EINVAL; __u32 id; - id = from_kgid(&init_user_ns, gid); + id = from_kgid_munged(idmap_userns(idmap), gid); if (!(server->caps & NFS_CAP_UIDGID_NOMAP)) ret = nfs_idmap_lookup_name(id, "group", buf, buflen, idmap); if (ret < 0) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 741ff8c9c6ed..c29cbef6b53f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -400,17 +400,32 @@ static long nfs4_update_delay(long *timeout) return ret; } -static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) +static int nfs4_delay_killable(long *timeout) { - int res = 0; - might_sleep(); freezable_schedule_timeout_killable_unsafe( nfs4_update_delay(timeout)); - if (fatal_signal_pending(current)) - res = -ERESTARTSYS; - return res; + if (!__fatal_signal_pending(current)) + return 0; + return -EINTR; +} + +static int nfs4_delay_interruptible(long *timeout) +{ + might_sleep(); + + freezable_schedule_timeout_interruptible(nfs4_update_delay(timeout)); + if (!signal_pending(current)) + return 0; + return __fatal_signal_pending(current) ? -EINTR :-ERESTARTSYS; +} + +static int nfs4_delay(long *timeout, bool interruptible) +{ + if (interruptible) + return nfs4_delay_interruptible(timeout); + return nfs4_delay_killable(timeout); } /* This is the error handling routine for processes that are allowed @@ -546,7 +561,8 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ ret = nfs4_do_handle_exception(server, errorcode, exception); if (exception->delay) { - ret = nfs4_delay(server->client, &exception->timeout); + ret = nfs4_delay(&exception->timeout, + exception->interruptible); goto out_retry; } if (exception->recovering) { @@ -978,10 +994,8 @@ int nfs4_setup_sequence(struct nfs_client *client, if (res->sr_slot != NULL) goto out_start; - if (session) { + if (session) tbl = &session->fc_slot_table; - task->tk_timeout = 0; - } spin_lock(&tbl->slot_tbl_lock); /* The state manager will wait until the slot table is empty */ @@ -990,9 +1004,8 @@ int nfs4_setup_sequence(struct nfs_client *client, slot = nfs4_alloc_slot(tbl); if (IS_ERR(slot)) { - /* Try again in 1/4 second */ if (slot == ERR_PTR(-ENOMEM)) - task->tk_timeout = HZ >> 2; + goto out_sleep_timeout; goto out_sleep; } spin_unlock(&tbl->slot_tbl_lock); @@ -1004,11 +1017,20 @@ out_start: nfs41_sequence_res_init(res); rpc_call_start(task); return 0; - +out_sleep_timeout: + /* Try again in 1/4 second */ + if (args->sa_privileged) + rpc_sleep_on_priority_timeout(&tbl->slot_tbl_waitq, task, + jiffies + (HZ >> 2), RPC_PRIORITY_PRIVILEGED); + else + rpc_sleep_on_timeout(&tbl->slot_tbl_waitq, task, + NULL, jiffies + (HZ >> 2)); + spin_unlock(&tbl->slot_tbl_lock); + return -EAGAIN; out_sleep: if (args->sa_privileged) rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task, - NULL, RPC_PRIORITY_PRIVILEGED); + RPC_PRIORITY_PRIVILEGED); else rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL); spin_unlock(&tbl->slot_tbl_lock); @@ -3060,7 +3082,9 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, int *opened) { struct nfs_server *server = NFS_SERVER(dir); - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; struct nfs4_state *res; struct nfs4_open_createattrs c = { .label = label, @@ -3673,7 +3697,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = nfs4_handle_exception(server, @@ -3715,7 +3741,9 @@ static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = _nfs4_lookup_root(server, fhandle, info); @@ -3942,7 +3970,9 @@ static int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label, struct inode *inode) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = _nfs4_proc_getattr(server, fhandle, fattr, label, inode); @@ -4065,7 +4095,9 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; struct rpc_clnt *client = *clnt; int err; do { @@ -4169,7 +4201,9 @@ static int _nfs4_proc_lookupp(struct inode *inode, static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = _nfs4_proc_lookupp(inode, fhandle, fattr, label); @@ -4216,7 +4250,9 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = _nfs4_proc_access(inode, entry); @@ -4271,7 +4307,9 @@ static int _nfs4_proc_readlink(struct inode *inode, struct page *page, static int nfs4_proc_readlink(struct inode *inode, struct page *page, unsigned int pgbase, unsigned int pglen) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = _nfs4_proc_readlink(inode, page, pgbase, pglen); @@ -4347,7 +4385,9 @@ _nfs4_proc_remove(struct inode *dir, const struct qstr *name, u32 ftype) static int nfs4_proc_remove(struct inode *dir, struct dentry *dentry) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; struct inode *inode = d_inode(dentry); int err; @@ -4368,7 +4408,9 @@ static int nfs4_proc_remove(struct inode *dir, struct dentry *dentry) static int nfs4_proc_rmdir(struct inode *dir, const struct qstr *name) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { @@ -4527,7 +4569,9 @@ out: static int nfs4_proc_link(struct inode *inode, struct inode *dir, const struct qstr *name) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = nfs4_handle_exception(NFS_SERVER(inode), @@ -4634,7 +4678,9 @@ out: static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page, unsigned int len, struct iattr *sattr) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; struct nfs4_label l, *label = NULL; int err; @@ -4673,7 +4719,9 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) { struct nfs_server *server = NFS_SERVER(dir); - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; struct nfs4_label l, *label = NULL; int err; @@ -4733,7 +4781,9 @@ static int _nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred, static int nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred, u64 cookie, struct page **pages, unsigned int count, bool plus) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = _nfs4_proc_readdir(dentry, cred, cookie, @@ -4784,7 +4834,9 @@ static int nfs4_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, dev_t rdev) { struct nfs_server *server = NFS_SERVER(dir); - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; struct nfs4_label l, *label = NULL; int err; @@ -4826,7 +4878,9 @@ static int _nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsstat *fsstat) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = nfs4_handle_exception(server, @@ -4857,7 +4911,9 @@ static int _nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; unsigned long now = jiffies; int err; @@ -4919,7 +4975,9 @@ static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_pathconf *pathconf) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { @@ -5488,7 +5546,9 @@ out_free: static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; ssize_t ret; do { ret = __nfs4_get_acl_uncached(inode, buf, buflen); @@ -5622,7 +5682,9 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, static int nfs4_get_security_label(struct inode *inode, void *buf, size_t buflen) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) @@ -6263,7 +6325,9 @@ out: static int nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock *request) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { @@ -6827,6 +6891,7 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock * struct nfs4_exception exception = { .state = state, .inode = state->inode, + .interruptible = true, }; int err; @@ -7240,7 +7305,9 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, struct nfs4_fs_locations *fs_locations, struct page *page) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = _nfs4_proc_fs_locations(client, dir, name, @@ -7383,7 +7450,9 @@ int nfs4_proc_get_locations(struct inode *inode, struct nfs_client *clp = server->nfs_client; const struct nfs4_mig_recovery_ops *ops = clp->cl_mvops->mig_recovery_ops; - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int status; dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__, @@ -7507,7 +7576,9 @@ int nfs4_proc_fsid_present(struct inode *inode, const struct cred *cred) struct nfs_client *clp = server->nfs_client; const struct nfs4_mig_recovery_ops *ops = clp->cl_mvops->mig_recovery_ops; - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int status; dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__, @@ -7573,7 +7644,9 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = -NFS4ERR_WRONGSEC; @@ -9263,7 +9336,9 @@ static int nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { /* first try using integrity protection */ @@ -9430,7 +9505,9 @@ static int nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid, const struct cred *cred) { - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .interruptible = true, + }; int err; do { err = _nfs41_test_stateid(server, stateid, cred); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 3de36479ed7a..e2e3c4f04d3e 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -159,6 +159,10 @@ int nfs40_discover_server_trunking(struct nfs_client *clp, /* Sustain the lease, even if it's empty. If the clientid4 * goes stale it's of no use for trunking discovery. */ nfs4_schedule_state_renewal(*result); + + /* If the client state need to recover, do it. */ + if (clp->cl_state) + nfs4_schedule_state_manager(clp); } out: return status; @@ -2346,8 +2350,7 @@ static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp) { /* FIXME: For now, we destroy all layouts. */ pnfs_destroy_all_layouts(clp); - /* FIXME: For now, we test all delegations+open state+locks. */ - nfs41_handle_some_state_revoked(clp); + nfs_test_expired_all_delegations(clp); dprintk("%s: Recallable state revoked on server %s!\n", __func__, clp->cl_hostname); } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 6fb7cb6b3f4b..689977e148cb 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -50,7 +50,7 @@ struct file_system_type nfs4_referral_fs_type = { static const struct super_operations nfs4_sops = { .alloc_inode = nfs_alloc_inode, - .destroy_inode = nfs_destroy_inode, + .free_inode = nfs_free_inode, .write_inode = nfs4_write_inode, .drop_inode = nfs_drop_inode, .statfs = nfs_statfs, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index cfcabc33e24d..602446158bfb 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2589,7 +2589,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, ARRAY_SIZE(nfs4_acl_bitmap), &hdr); rpc_prepare_reply_pages(req, args->acl_pages, 0, - args->acl_len, replen); + args->acl_len, replen + 1); encode_nops(&hdr); } @@ -2811,7 +2811,7 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, } rpc_prepare_reply_pages(req, (struct page **)&args->page, 0, - PAGE_SIZE, replen); + PAGE_SIZE, replen + 1); encode_nops(&hdr); } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index e9f39fa5964b..6ec30014a439 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -16,8 +16,8 @@ #include <linux/nfs.h> #include <linux/nfs3.h> #include <linux/nfs4.h> -#include <linux/nfs_page.h> #include <linux/nfs_fs.h> +#include <linux/nfs_page.h> #include <linux/nfs_mount.h> #include <linux/export.h> @@ -47,7 +47,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->req = nfs_list_entry(mirror->pg_list.next); hdr->inode = desc->pg_inode; - hdr->cred = hdr->req->wb_context->cred; + hdr->cred = nfs_req_openctx(hdr->req)->cred; hdr->io_start = req_offset(hdr->req); hdr->good_bytes = mirror->pg_count; hdr->io_completion = desc->pg_io_completion; @@ -295,25 +295,13 @@ out: nfs_release_request(head); } -/** - * nfs_create_request - Create an NFS read/write request. - * @ctx: open context to use - * @page: page to write - * @last: last nfs request created for this page group or NULL if head - * @offset: starting offset within the page for the write - * @count: number of bytes to read/write - * - * The page must be locked by the caller. This makes sure we never - * create two different requests for the same page. - * User should ensure it is safe to sleep in this function. - */ -struct nfs_page * -nfs_create_request(struct nfs_open_context *ctx, struct page *page, - struct nfs_page *last, unsigned int offset, +static struct nfs_page * +__nfs_create_request(struct nfs_lock_context *l_ctx, struct page *page, + unsigned int pgbase, unsigned int offset, unsigned int count) { struct nfs_page *req; - struct nfs_lock_context *l_ctx; + struct nfs_open_context *ctx = l_ctx->open_context; if (test_bit(NFS_CONTEXT_BAD, &ctx->flags)) return ERR_PTR(-EBADF); @@ -322,13 +310,8 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, if (req == NULL) return ERR_PTR(-ENOMEM); - /* get lock context early so we can deal with alloc failures */ - l_ctx = nfs_get_lock_context(ctx); - if (IS_ERR(l_ctx)) { - nfs_page_free(req); - return ERR_CAST(l_ctx); - } req->wb_lock_context = l_ctx; + refcount_inc(&l_ctx->count); atomic_inc(&l_ctx->io_count); /* Initialize the request struct. Initially, we assume a @@ -340,15 +323,59 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, get_page(page); } req->wb_offset = offset; - req->wb_pgbase = offset; + req->wb_pgbase = pgbase; req->wb_bytes = count; - req->wb_context = get_nfs_open_context(ctx); kref_init(&req->wb_kref); - nfs_page_group_init(req, last); + req->wb_nio = 0; return req; } /** + * nfs_create_request - Create an NFS read/write request. + * @ctx: open context to use + * @page: page to write + * @offset: starting offset within the page for the write + * @count: number of bytes to read/write + * + * The page must be locked by the caller. This makes sure we never + * create two different requests for the same page. + * User should ensure it is safe to sleep in this function. + */ +struct nfs_page * +nfs_create_request(struct nfs_open_context *ctx, struct page *page, + unsigned int offset, unsigned int count) +{ + struct nfs_lock_context *l_ctx = nfs_get_lock_context(ctx); + struct nfs_page *ret; + + if (IS_ERR(l_ctx)) + return ERR_CAST(l_ctx); + ret = __nfs_create_request(l_ctx, page, offset, offset, count); + if (!IS_ERR(ret)) + nfs_page_group_init(ret, NULL); + nfs_put_lock_context(l_ctx); + return ret; +} + +static struct nfs_page * +nfs_create_subreq(struct nfs_page *req, struct nfs_page *last, + unsigned int pgbase, unsigned int offset, + unsigned int count) +{ + struct nfs_page *ret; + + ret = __nfs_create_request(req->wb_lock_context, req->wb_page, + pgbase, offset, count); + if (!IS_ERR(ret)) { + nfs_lock_request(ret); + ret->wb_index = req->wb_index; + nfs_page_group_init(ret, last); + ret->wb_nio = req->wb_nio; + } + return ret; +} + +/** * nfs_unlock_request - Unlock request and wake up sleepers. * @req: pointer to request */ @@ -386,8 +413,8 @@ void nfs_unlock_and_release_request(struct nfs_page *req) static void nfs_clear_request(struct nfs_page *req) { struct page *page = req->wb_page; - struct nfs_open_context *ctx = req->wb_context; struct nfs_lock_context *l_ctx = req->wb_lock_context; + struct nfs_open_context *ctx; if (page != NULL) { put_page(page); @@ -396,16 +423,13 @@ static void nfs_clear_request(struct nfs_page *req) if (l_ctx != NULL) { if (atomic_dec_and_test(&l_ctx->io_count)) { wake_up_var(&l_ctx->io_count); + ctx = l_ctx->open_context; if (test_bit(NFS_CONTEXT_UNLOCK, &ctx->flags)) rpc_wake_up(&NFS_SERVER(d_inode(ctx->dentry))->uoc_rpcwaitq); } nfs_put_lock_context(l_ctx); req->wb_lock_context = NULL; } - if (ctx != NULL) { - put_nfs_open_context(ctx); - req->wb_context = NULL; - } } /** @@ -550,7 +574,7 @@ static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr, hdr->args.pgbase = req->wb_pgbase; hdr->args.pages = hdr->page_array.pagevec; hdr->args.count = count; - hdr->args.context = get_nfs_open_context(req->wb_context); + hdr->args.context = get_nfs_open_context(nfs_req_openctx(req)); hdr->args.lock_context = req->wb_lock_context; hdr->args.stable = NFS_UNSTABLE; switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) { @@ -698,6 +722,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_mirrors_dynamic = NULL; desc->pg_mirrors = desc->pg_mirrors_static; nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize); + desc->pg_maxretrans = 0; } /** @@ -906,9 +931,9 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, struct file_lock_context *flctx; if (prev) { - if (!nfs_match_open_context(req->wb_context, prev->wb_context)) + if (!nfs_match_open_context(nfs_req_openctx(req), nfs_req_openctx(prev))) return false; - flctx = d_inode(req->wb_context->dentry)->i_flctx; + flctx = d_inode(nfs_req_openctx(req)->dentry)->i_flctx; if (flctx != NULL && !(list_empty_careful(&flctx->flc_posix) && list_empty_careful(&flctx->flc_flock)) && @@ -957,6 +982,15 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, return 0; mirror->pg_base = req->wb_pgbase; } + + if (desc->pg_maxretrans && req->wb_nio > desc->pg_maxretrans) { + if (NFS_SERVER(desc->pg_inode)->flags & NFS_MOUNT_SOFTERR) + desc->pg_error = -ETIMEDOUT; + else + desc->pg_error = -EIO; + return 0; + } + if (!nfs_can_coalesce_requests(prev, req, desc)) return 0; nfs_list_move_request(req, &mirror->pg_list); @@ -1049,14 +1083,10 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, pgbase += subreq->wb_bytes; if (bytes_left) { - subreq = nfs_create_request(req->wb_context, - req->wb_page, - subreq, pgbase, bytes_left); + subreq = nfs_create_subreq(req, subreq, pgbase, + offset, bytes_left); if (IS_ERR(subreq)) goto err_ptr; - nfs_lock_request(subreq); - subreq->wb_offset = offset; - subreq->wb_index = req->wb_index; } } while (bytes_left > 0); @@ -1158,19 +1188,14 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, lastreq = lastreq->wb_this_page) ; - dupreq = nfs_create_request(req->wb_context, - req->wb_page, lastreq, pgbase, bytes); + dupreq = nfs_create_subreq(req, lastreq, + pgbase, offset, bytes); + nfs_page_group_unlock(req); if (IS_ERR(dupreq)) { - nfs_page_group_unlock(req); desc->pg_error = PTR_ERR(dupreq); goto out_failed; } - - nfs_lock_request(dupreq); - nfs_page_group_unlock(req); - dupreq->wb_offset = offset; - dupreq->wb_index = req->wb_index; } else dupreq = req; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 7066cd7c7aff..83722e936b4a 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2436,7 +2436,7 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r rd_size = nfs_dreq_bytes_left(pgio->pg_dreq); pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, + nfs_req_openctx(req), req_offset(req), rd_size, IOMODE_READ, @@ -2463,7 +2463,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, pnfs_generic_pg_check_range(pgio, req); if (pgio->pg_lseg == NULL) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, + nfs_req_openctx(req), req_offset(req), wb_size, IOMODE_RW, diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index c0420b979d88..f15609c003d8 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -459,7 +459,7 @@ static inline bool pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx) { - struct inode *inode = d_inode(req->wb_context->dentry); + struct inode *inode = d_inode(nfs_req_openctx(req)->dentry); struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (lseg == NULL || ld->mark_request_commit == NULL) @@ -471,7 +471,7 @@ pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, static inline bool pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { - struct inode *inode = d_inode(req->wb_context->dentry); + struct inode *inode = d_inode(nfs_req_openctx(req)->dentry); struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (ld == NULL || ld->clear_request_commit == NULL) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 1d95a60b2586..c799e540ed1e 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -92,7 +92,7 @@ EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); static void nfs_readpage_release(struct nfs_page *req) { - struct inode *inode = d_inode(req->wb_context->dentry); + struct inode *inode = d_inode(nfs_req_openctx(req)->dentry); dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), req->wb_bytes, @@ -118,7 +118,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, len = nfs_page_length(page); if (len == 0) return nfs_return_empty_page(page); - new = nfs_create_request(ctx, page, NULL, 0, len); + new = nfs_create_request(ctx, page, 0, len); if (IS_ERR(new)) { unlock_page(page); return PTR_ERR(new); @@ -363,7 +363,7 @@ readpage_async_filler(void *data, struct page *page) if (len == 0) return nfs_return_empty_page(page); - new = nfs_create_request(desc->ctx, page, NULL, 0, len); + new = nfs_create_request(desc->ctx, page, 0, len); if (IS_ERR(new)) goto out_error; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 23790c7b2289..d6c687419a81 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -78,7 +78,7 @@ enum { /* Mount options that take no arguments */ - Opt_soft, Opt_hard, + Opt_soft, Opt_softerr, Opt_hard, Opt_posix, Opt_noposix, Opt_cto, Opt_nocto, Opt_ac, Opt_noac, @@ -125,6 +125,7 @@ static const match_table_t nfs_mount_option_tokens = { { Opt_sloppy, "sloppy" }, { Opt_soft, "soft" }, + { Opt_softerr, "softerr" }, { Opt_hard, "hard" }, { Opt_deprecated, "intr" }, { Opt_deprecated, "nointr" }, @@ -309,7 +310,7 @@ struct file_system_type nfs_xdev_fs_type = { const struct super_operations nfs_sops = { .alloc_inode = nfs_alloc_inode, - .destroy_inode = nfs_destroy_inode, + .free_inode = nfs_free_inode, .write_inode = nfs_write_inode, .drop_inode = nfs_drop_inode, .statfs = nfs_statfs, @@ -628,7 +629,8 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, const char *str; const char *nostr; } nfs_info[] = { - { NFS_MOUNT_SOFT, ",soft", ",hard" }, + { NFS_MOUNT_SOFT, ",soft", "" }, + { NFS_MOUNT_SOFTERR, ",softerr", "" }, { NFS_MOUNT_POSIX, ",posix", "" }, { NFS_MOUNT_NOCTO, ",nocto", "" }, { NFS_MOUNT_NOAC, ",noac", "" }, @@ -658,6 +660,8 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, seq_printf(m, ",acdirmin=%u", nfss->acdirmin/HZ); if (nfss->acdirmax != NFS_DEF_ACDIRMAX*HZ || showdefaults) seq_printf(m, ",acdirmax=%u", nfss->acdirmax/HZ); + if (!(nfss->flags & (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))) + seq_puts(m, ",hard"); for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) { if (nfss->flags & nfs_infop->flag) seq_puts(m, nfs_infop->str); @@ -1239,10 +1243,15 @@ static int nfs_parse_mount_options(char *raw, */ case Opt_soft: mnt->flags |= NFS_MOUNT_SOFT; + mnt->flags &= ~NFS_MOUNT_SOFTERR; break; - case Opt_hard: + case Opt_softerr: + mnt->flags |= NFS_MOUNT_SOFTERR; mnt->flags &= ~NFS_MOUNT_SOFT; break; + case Opt_hard: + mnt->flags &= ~(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR); + break; case Opt_posix: mnt->flags |= NFS_MOUNT_POSIX; break; @@ -2041,7 +2050,8 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); args->nfs_server.port = ntohs(data->addr.sin_port); - if (!nfs_verify_server_address(sap)) + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) @@ -2475,6 +2485,21 @@ static int nfs_compare_super_address(struct nfs_server *server1, return 1; } +static int nfs_compare_userns(const struct nfs_server *old, + const struct nfs_server *new) +{ + const struct user_namespace *oldns = &init_user_ns; + const struct user_namespace *newns = &init_user_ns; + + if (old->client && old->client->cl_cred) + oldns = old->client->cl_cred->user_ns; + if (new->client && new->client->cl_cred) + newns = new->client->cl_cred->user_ns; + if (oldns != newns) + return 0; + return 1; +} + static int nfs_compare_super(struct super_block *sb, void *data) { struct nfs_sb_mountdata *sb_mntdata = data; @@ -2488,6 +2513,8 @@ static int nfs_compare_super(struct super_block *sb, void *data) return 0; if (memcmp(&old->fsid, &server->fsid, sizeof(old->fsid)) != 0) return 0; + if (!nfs_compare_userns(old, server)) + return 0; return nfs_compare_mount_options(sb, server, mntflags); } diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index 06eb44b47885..25ba299fdac2 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -26,8 +26,9 @@ * and straight-forward than readdir caching. */ -static int nfs_symlink_filler(struct inode *inode, struct page *page) +static int nfs_symlink_filler(void *data, struct page *page) { + struct inode *inode = data; int error; error = NFS_PROTO(inode)->readlink(inode, page, 0, PAGE_SIZE); @@ -65,8 +66,8 @@ static const char *nfs_get_link(struct dentry *dentry, err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); if (err) return err; - page = read_cache_page(&inode->i_data, 0, - (filler_t *)nfs_symlink_filler, inode); + page = read_cache_page(&inode->i_data, 0, nfs_symlink_filler, + inode); if (IS_ERR(page)) return ERR_CAST(page); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f3ebabaa291d..bc5bb9323412 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -244,6 +244,12 @@ static void nfs_set_pageerror(struct address_space *mapping) nfs_zap_mapping(mapping->host, mapping); } +static void nfs_mapping_set_error(struct page *page, int error) +{ + SetPageError(page); + mapping_set_error(page_file_mapping(page), error); +} + /* * nfs_page_group_search_locked * @head - head request of page group @@ -582,11 +588,10 @@ release_request: return ERR_PTR(ret); } -static void nfs_write_error_remove_page(struct nfs_page *req) +static void nfs_write_error(struct nfs_page *req, int error) { + nfs_mapping_set_error(req->wb_page, error); nfs_end_page_writeback(req); - generic_error_remove_page(page_file_mapping(req->wb_page), - req->wb_page); nfs_release_request(req); } @@ -609,6 +614,7 @@ nfs_error_is_fatal_on_server(int err) static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, struct page *page) { + struct address_space *mapping; struct nfs_page *req; int ret = 0; @@ -622,19 +628,19 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, nfs_set_page_writeback(page); WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags)); - ret = req->wb_context->error; /* If there is a fatal error that covers this write, just exit */ - if (nfs_error_is_fatal_on_server(ret)) + ret = 0; + mapping = page_file_mapping(page); + if (test_bit(AS_ENOSPC, &mapping->flags) || + test_bit(AS_EIO, &mapping->flags)) goto out_launder; - ret = 0; if (!nfs_pageio_add_request(pgio, req)) { ret = pgio->pg_error; /* * Remove the problematic req upon fatal errors on the server */ if (nfs_error_is_fatal(ret)) { - nfs_context_set_write_error(req->wb_context, ret); if (nfs_error_is_fatal_on_server(ret)) goto out_launder; } else @@ -646,8 +652,8 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, out: return ret; out_launder: - nfs_write_error_remove_page(req); - return ret; + nfs_write_error(req, ret); + return 0; } static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, @@ -958,7 +964,8 @@ static void nfs_clear_request_commit(struct nfs_page *req) { if (test_bit(PG_CLEAN, &req->wb_flags)) { - struct inode *inode = d_inode(req->wb_context->dentry); + struct nfs_open_context *ctx = nfs_req_openctx(req); + struct inode *inode = d_inode(ctx->dentry); struct nfs_commit_info cinfo; nfs_init_cinfo_from_inode(&cinfo, inode); @@ -999,10 +1006,12 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { nfs_set_pageerror(page_file_mapping(req->wb_page)); - nfs_context_set_write_error(req->wb_context, hdr->error); + nfs_mapping_set_error(req->wb_page, hdr->error); goto remove_req; } if (nfs_write_need_commit(hdr)) { + /* Reset wb_nio, since the write was successful. */ + req->wb_nio = 0; memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf)); nfs_mark_request_commit(req, hdr->lseg, &cinfo, hdr->pgio_mirror_idx); @@ -1136,6 +1145,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, req->wb_bytes = end - req->wb_offset; else req->wb_bytes = rqend - req->wb_offset; + req->wb_nio = 0; return req; out_flushme: /* @@ -1165,7 +1175,7 @@ static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx, req = nfs_try_to_update_request(inode, page, offset, bytes); if (req != NULL) goto out; - req = nfs_create_request(ctx, page, NULL, offset, bytes); + req = nfs_create_request(ctx, page, offset, bytes); if (IS_ERR(req)) goto out; nfs_inode_add_request(inode, req); @@ -1210,7 +1220,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) return 0; l_ctx = req->wb_lock_context; do_flush = req->wb_page != page || - !nfs_match_open_context(req->wb_context, ctx); + !nfs_match_open_context(nfs_req_openctx(req), ctx); if (l_ctx && flctx && !(list_empty_careful(&flctx->flc_posix) && list_empty_careful(&flctx->flc_flock))) { @@ -1410,8 +1420,10 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, */ static void nfs_redirty_request(struct nfs_page *req) { + /* Bump the transmission count */ + req->wb_nio++; nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags); + set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1423,14 +1435,10 @@ static void nfs_async_write_error(struct list_head *head, int error) while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - if (nfs_error_is_fatal(error)) { - nfs_context_set_write_error(req->wb_context, error); - if (nfs_error_is_fatal_on_server(error)) { - nfs_write_error_remove_page(req); - continue; - } - } - nfs_redirty_request(req); + if (nfs_error_is_fatal(error)) + nfs_write_error(req, error); + else + nfs_redirty_request(req); } } @@ -1735,7 +1743,8 @@ void nfs_init_commit(struct nfs_commit_data *data, struct nfs_commit_info *cinfo) { struct nfs_page *first = nfs_list_entry(head->next); - struct inode *inode = d_inode(first->wb_context->dentry); + struct nfs_open_context *ctx = nfs_req_openctx(first); + struct inode *inode = d_inode(ctx->dentry); /* Set up the RPC argument and reply structs * NB: take care not to mess about with data->commit et al. */ @@ -1743,7 +1752,7 @@ void nfs_init_commit(struct nfs_commit_data *data, list_splice_init(head, &data->pages); data->inode = inode; - data->cred = first->wb_context->cred; + data->cred = ctx->cred; data->lseg = lseg; /* reference transferred */ /* only set lwb for pnfs commit */ if (lseg) @@ -1756,7 +1765,7 @@ void nfs_init_commit(struct nfs_commit_data *data, /* Note: we always request a commit of the entire inode */ data->args.offset = 0; data->args.count = 0; - data->context = get_nfs_open_context(first->wb_context); + data->context = get_nfs_open_context(ctx); data->res.fattr = &data->fattr; data->res.verf = &data->verf; nfs_fattr_init(&data->fattr); @@ -1839,14 +1848,15 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) nfs_clear_page_commit(req->wb_page); dprintk("NFS: commit (%s/%llu %d@%lld)", - req->wb_context->dentry->d_sb->s_id, - (unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)), + nfs_req_openctx(req)->dentry->d_sb->s_id, + (unsigned long long)NFS_FILEID(d_inode(nfs_req_openctx(req)->dentry)), req->wb_bytes, (long long)req_offset(req)); if (status < 0) { - nfs_context_set_write_error(req->wb_context, status); - if (req->wb_page) + if (req->wb_page) { + nfs_mapping_set_error(req->wb_page, status); nfs_inode_remove_request(req); + } dprintk_cont(", error = %d\n", status); goto next; } @@ -1863,7 +1873,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) /* We have a mismatch. Write the page again */ dprintk_cont(" mismatch\n"); nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags); + set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); next: nfs_unlock_and_release_request(req); /* Latency breaker */ diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 802993d8912f..baa01956a5b3 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -570,13 +570,13 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) err = get_int(&mesg, &an_int); if (err) goto out3; - exp.ex_anon_uid= make_kuid(&init_user_ns, an_int); + exp.ex_anon_uid= make_kuid(current_user_ns(), an_int); /* anon gid */ err = get_int(&mesg, &an_int); if (err) goto out3; - exp.ex_anon_gid= make_kgid(&init_user_ns, an_int); + exp.ex_anon_gid= make_kgid(current_user_ns(), an_int); /* fsid */ err = get_int(&mesg, &an_int); @@ -1170,15 +1170,17 @@ static void show_secinfo(struct seq_file *m, struct svc_export *exp) static void exp_flags(struct seq_file *m, int flag, int fsid, kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fsloc) { + struct user_namespace *userns = m->file->f_cred->user_ns; + show_expflags(m, flag, NFSEXP_ALLFLAGS); if (flag & NFSEXP_FSID) seq_printf(m, ",fsid=%d", fsid); - if (!uid_eq(anonu, make_kuid(&init_user_ns, (uid_t)-2)) && - !uid_eq(anonu, make_kuid(&init_user_ns, 0x10000-2))) - seq_printf(m, ",anonuid=%u", from_kuid(&init_user_ns, anonu)); - if (!gid_eq(anong, make_kgid(&init_user_ns, (gid_t)-2)) && - !gid_eq(anong, make_kgid(&init_user_ns, 0x10000-2))) - seq_printf(m, ",anongid=%u", from_kgid(&init_user_ns, anong)); + if (!uid_eq(anonu, make_kuid(userns, (uid_t)-2)) && + !uid_eq(anonu, make_kuid(userns, 0x10000-2))) + seq_printf(m, ",anonuid=%u", from_kuid_munged(userns, anonu)); + if (!gid_eq(anong, make_kgid(userns, (gid_t)-2)) && + !gid_eq(anong, make_kgid(userns, 0x10000-2))) + seq_printf(m, ",anongid=%u", from_kgid_munged(userns, anong)); if (fsloc && fsloc->locations_count > 0) { char *loctype = (fsloc->migrated) ? "refer" : "replicas"; int i; diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 32cb8c027483..789abc4dd1d2 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -104,6 +104,9 @@ struct nfsd_net { time_t nfsd4_grace; bool somebody_reclaimed; + bool track_reclaim_completes; + atomic_t nr_reclaim_complete; + bool nfsd_net_up; bool lockd_up; @@ -131,10 +134,18 @@ struct nfsd_net { u32 s2s_cp_cl_id; struct idr s2s_cp_stateids; spinlock_t s2s_cp_lock; + + /* + * Version information + */ + bool *nfsd_versions; + bool *nfsd4_minorversions; }; /* Simple check to find out if a given net was properly initialized */ #define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl) +extern void nfsd_netns_free_versions(struct nfsd_net *nn); + extern unsigned int nfsd_net_id; #endif /* __NFSD_NETNS_H__ */ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 8f933e84cec1..9bc32af4e2da 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -442,7 +442,9 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) struct nfsd3_readdirargs *argp = rqstp->rq_argp; struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; - int count; + int count = 0; + struct page **p; + caddr_t page_addr = NULL; dprintk("nfsd: READDIR(3) %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), @@ -462,7 +464,18 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) nfserr = nfsd_readdir(rqstp, &resp->fh, (loff_t*) &argp->cookie, &resp->common, nfs3svc_encode_entry); memcpy(resp->verf, argp->verf, 8); - resp->count = resp->buffer - argp->buffer; + count = 0; + for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) { + page_addr = page_address(*p); + + if (((caddr_t)resp->buffer >= page_addr) && + ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) { + count += (caddr_t)resp->buffer - page_addr; + break; + } + count += PAGE_SIZE; + } + resp->count = count >> 2; if (resp->offset) { loff_t offset = argp->cookie; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 93fea246f676..fcf31822c74c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -96,7 +96,7 @@ decode_filename(__be32 *p, char **namp, unsigned int *lenp) } static __be32 * -decode_sattr3(__be32 *p, struct iattr *iap) +decode_sattr3(__be32 *p, struct iattr *iap, struct user_namespace *userns) { u32 tmp; @@ -107,12 +107,12 @@ decode_sattr3(__be32 *p, struct iattr *iap) iap->ia_mode = ntohl(*p++); } if (*p++) { - iap->ia_uid = make_kuid(&init_user_ns, ntohl(*p++)); + iap->ia_uid = make_kuid(userns, ntohl(*p++)); if (uid_valid(iap->ia_uid)) iap->ia_valid |= ATTR_UID; } if (*p++) { - iap->ia_gid = make_kgid(&init_user_ns, ntohl(*p++)); + iap->ia_gid = make_kgid(userns, ntohl(*p++)); if (gid_valid(iap->ia_gid)) iap->ia_valid |= ATTR_GID; } @@ -165,12 +165,13 @@ static __be32 * encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat) { + struct user_namespace *userns = nfsd_user_namespace(rqstp); struct timespec ts; *p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]); *p++ = htonl((u32) (stat->mode & S_IALLUGO)); *p++ = htonl((u32) stat->nlink); - *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid)); - *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid)); + *p++ = htonl((u32) from_kuid_munged(userns, stat->uid)); + *p++ = htonl((u32) from_kgid_munged(userns, stat->gid)); if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN) { p = xdr_encode_hyper(p, (u64) NFS3_MAXPATHLEN); } else { @@ -325,7 +326,7 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) p = decode_fh(p, &args->fh); if (!p) return 0; - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); if ((args->check_guard = ntohl(*p++)) != 0) { struct timespec time; @@ -455,7 +456,7 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) switch (args->createmode = ntohl(*p++)) { case NFS3_CREATE_UNCHECKED: case NFS3_CREATE_GUARDED: - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); break; case NFS3_CREATE_EXCLUSIVE: args->verf = p; @@ -476,7 +477,7 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); return xdr_argsize_check(rqstp, p); } @@ -491,7 +492,7 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen))) return 0; - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); args->tlen = ntohl(*p++); @@ -519,7 +520,7 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) if (args->ftype == NF3BLK || args->ftype == NF3CHR || args->ftype == NF3SOCK || args->ftype == NF3FIFO) - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); if (args->ftype == NF3BLK || args->ftype == NF3CHR) { args->major = ntohl(*p++); @@ -573,6 +574,7 @@ int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_readdirargs *args = rqstp->rq_argp; + int len; u32 max_blocksize = svc_max_payload(rqstp); p = decode_fh(p, &args->fh); @@ -582,8 +584,14 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) args->verf = p; p += 2; args->dircount = ~0; args->count = ntohl(*p++); - args->count = min_t(u32, args->count, max_blocksize); - args->buffer = page_address(*(rqstp->rq_next_page++)); + len = args->count = min_t(u32, args->count, max_blocksize); + + while (len > 0) { + struct page *p = *(rqstp->rq_next_page++); + if (!args->buffer) + args->buffer = page_address(p); + len -= PAGE_SIZE; + } return xdr_argsize_check(rqstp, p); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index d219159b98af..397eb7820929 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -868,6 +868,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c .program = &cb_program, .version = 1, .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), + .cred = current_cred(), }; struct rpc_clnt *client; const struct cred *cred; @@ -1010,8 +1011,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -1032,12 +1034,15 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback * the submission code will error out, so we don't need to * handle that case here. */ - if (task->tk_flags & RPC_TASK_KILLED) + if (RPC_SIGNALLED(task)) goto need_restart; return true; } + if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -1076,12 +1081,13 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback cb->cb_seq_status); } + cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, clp->cl_cb_session->se_cb_seq_nr); - if (task->tk_flags & RPC_TASK_KILLED) + if (RPC_SIGNALLED(task)) goto need_restart; out: return ret; @@ -1117,10 +1123,11 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) rpc_restart_call_prepare(task); return; case 1: - break; - case -1: - /* Network partition? */ - nfsd4_mark_cb_down(clp, task->tk_status); + switch (task->tk_status) { + case -EIO: + case -ETIMEDOUT: + nfsd4_mark_cb_down(clp, task->tk_status); + } break; default: BUG(); @@ -1283,6 +1290,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; } void nfsd4_run_cb(struct nfsd4_callback *cb) diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index bf137fec33ff..2961016097ac 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -634,7 +634,7 @@ nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen, return nfserr_inval; status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id); - *uid = make_kuid(&init_user_ns, id); + *uid = make_kuid(nfsd_user_namespace(rqstp), id); if (!uid_valid(*uid)) status = nfserr_badowner; return status; @@ -651,7 +651,7 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen, return nfserr_inval; status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id); - *gid = make_kgid(&init_user_ns, id); + *gid = make_kgid(nfsd_user_namespace(rqstp), id); if (!gid_valid(*gid)) status = nfserr_badowner; return status; @@ -660,13 +660,13 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen, __be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp, kuid_t uid) { - u32 id = from_kuid(&init_user_ns, uid); + u32 id = from_kuid_munged(nfsd_user_namespace(rqstp), uid); return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id); } __be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp, kgid_t gid) { - u32 id = from_kgid(&init_user_ns, gid); + u32 id = from_kgid_munged(nfsd_user_namespace(rqstp), gid); return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id); } diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 44517fb5c0de..a79e24b79095 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -693,7 +693,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) ops->fence_client(ls); else nfsd4_cb_layout_fail(ls); - return -1; + return 1; case -NFS4ERR_NOMATCHING_LAYOUT: trace_nfsd_layout_recall_done(&ls->ls_stid.sc_stateid); task->tk_status = 0; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 0cfd257ffdaf..8beda999e134 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -427,6 +427,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; reclaim = true; + /* fall through */ case NFS4_OPEN_CLAIM_FH: case NFS4_OPEN_CLAIM_DELEG_CUR_FH: status = do_open_fhandle(rqstp, cstate, open); @@ -1926,6 +1927,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) struct nfsd4_compound_state *cstate = &resp->cstate; struct svc_fh *current_fh = &cstate->current_fh; struct svc_fh *save_fh = &cstate->save_fh; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); __be32 status; svcxdr_init_encode(rqstp, resp); @@ -1948,7 +1950,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) * According to RFC3010, this takes precedence over all other errors. */ status = nfserr_minor_vers_mismatch; - if (nfsd_minorversion(args->minorversion, NFSD_TEST) <= 0) + if (nfsd_minorversion(nn, args->minorversion, NFSD_TEST) <= 0) goto out; status = nfserr_resource; if (args->opcnt > NFSD_MAX_OPS_PER_COMPOUND) diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 5188f9f70c78..87679557d0d6 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -126,7 +126,6 @@ nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname) SHASH_DESC_ON_STACK(desc, tfm); desc->tfm = tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; status = crypto_shash_digest(desc, clname->data, clname->len, cksum.data); @@ -170,12 +169,33 @@ legacy_recdir_name_error(struct nfs4_client *clp, int error) } static void +__nfsd4_create_reclaim_record_grace(struct nfs4_client *clp, + const char *dname, int len, struct nfsd_net *nn) +{ + struct xdr_netobj name; + struct nfs4_client_reclaim *crp; + + name.data = kmemdup(dname, len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return; + } + name.len = len; + crp = nfs4_client_to_reclaim(name, nn); + if (!crp) { + kfree(name.data); + return; + } + crp->cr_clp = clp; +} + +static void nfsd4_create_clid_dir(struct nfs4_client *clp) { const struct cred *original_cred; char dname[HEXDIR_LEN]; struct dentry *dir, *dentry; - struct nfs4_client_reclaim *crp; int status; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); @@ -221,11 +241,9 @@ out_put: out_unlock: inode_unlock(d_inode(dir)); if (status == 0) { - if (nn->in_grace) { - crp = nfs4_client_to_reclaim(dname, nn); - if (crp) - crp->cr_clp = clp; - } + if (nn->in_grace) + __nfsd4_create_reclaim_record_grace(clp, dname, + HEXDIR_LEN, nn); vfs_fsync(nn->rec_file, 0); } else { printk(KERN_ERR "NFSD: failed to write recovery record" @@ -346,10 +364,29 @@ out_unlock: } static void +__nfsd4_remove_reclaim_record_grace(const char *dname, int len, + struct nfsd_net *nn) +{ + struct xdr_netobj name; + struct nfs4_client_reclaim *crp; + + name.data = kmemdup(dname, len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return; + } + name.len = len; + crp = nfsd4_find_reclaim_client(name, nn); + kfree(name.data); + if (crp) + nfs4_remove_reclaim_record(crp, nn); +} + +static void nfsd4_remove_clid_dir(struct nfs4_client *clp) { const struct cred *original_cred; - struct nfs4_client_reclaim *crp; char dname[HEXDIR_LEN]; int status; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); @@ -374,12 +411,9 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) nfs4_reset_creds(original_cred); if (status == 0) { vfs_fsync(nn->rec_file, 0); - if (nn->in_grace) { - /* remove reclaim record */ - crp = nfsd4_find_reclaim_client(dname, nn); - if (crp) - nfs4_remove_reclaim_record(crp, nn); - } + if (nn->in_grace) + __nfsd4_remove_reclaim_record_grace(dname, + HEXDIR_LEN, nn); } out_drop_write: mnt_drop_write_file(nn->rec_file); @@ -393,14 +427,31 @@ static int purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) { int status; + struct xdr_netobj name; - if (nfs4_has_reclaimed_state(child->d_name.name, nn)) + if (child->d_name.len != HEXDIR_LEN - 1) { + printk("%s: illegal name %pd in recovery directory\n", + __func__, child); + /* Keep trying; maybe the others are OK: */ return 0; + } + name.data = kmemdup_nul(child->d_name.name, child->d_name.len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + goto out; + } + name.len = HEXDIR_LEN; + if (nfs4_has_reclaimed_state(name, nn)) + goto out_free; status = vfs_rmdir(d_inode(parent), child); if (status) printk("failed to remove client recovery directory %pd\n", child); +out_free: + kfree(name.data); +out: /* Keep trying, success or failure: */ return 0; } @@ -430,13 +481,24 @@ out: static int load_recdir(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) { + struct xdr_netobj name; + if (child->d_name.len != HEXDIR_LEN - 1) { - printk("nfsd4: illegal name %pd in recovery directory\n", - child); + printk("%s: illegal name %pd in recovery directory\n", + __func__, child); /* Keep trying; maybe the others are OK: */ return 0; } - nfs4_client_to_reclaim(child->d_name.name, nn); + name.data = kmemdup_nul(child->d_name.name, child->d_name.len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + goto out; + } + name.len = HEXDIR_LEN; + if (!nfs4_client_to_reclaim(name, nn)) + kfree(name.data); +out: return 0; } @@ -565,6 +627,7 @@ nfsd4_legacy_tracking_init(struct net *net) status = nfsd4_load_reboot_recovery_data(net); if (status) goto err; + printk("NFSD: Using legacy client tracking operations.\n"); return 0; err: @@ -616,6 +679,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp) char dname[HEXDIR_LEN]; struct nfs4_client_reclaim *crp; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + struct xdr_netobj name; /* did we already find that this client is stable? */ if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) @@ -628,13 +692,22 @@ nfsd4_check_legacy_client(struct nfs4_client *clp) } /* look for it in the reclaim hashtable otherwise */ - crp = nfsd4_find_reclaim_client(dname, nn); + name.data = kmemdup(dname, HEXDIR_LEN, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + goto out_enoent; + } + name.len = HEXDIR_LEN; + crp = nfsd4_find_reclaim_client(name, nn); + kfree(name.data); if (crp) { set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); crp->cr_clp = clp; return 0; } +out_enoent: return -ENOENT; } @@ -657,6 +730,7 @@ struct cld_net { spinlock_t cn_lock; struct list_head cn_list; unsigned int cn_xid; + bool cn_has_legacy; }; struct cld_upcall { @@ -707,6 +781,40 @@ cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg) } static ssize_t +__cld_pipe_inprogress_downcall(const struct cld_msg __user *cmsg, + struct nfsd_net *nn) +{ + uint8_t cmd; + struct xdr_netobj name; + uint16_t namelen; + struct cld_net *cn = nn->cld_net; + + if (get_user(cmd, &cmsg->cm_cmd)) { + dprintk("%s: error when copying cmd from userspace", __func__); + return -EFAULT; + } + if (cmd == Cld_GraceStart) { + if (get_user(namelen, &cmsg->cm_u.cm_name.cn_len)) + return -EFAULT; + name.data = memdup_user(&cmsg->cm_u.cm_name.cn_id, namelen); + if (IS_ERR_OR_NULL(name.data)) + return -EFAULT; + name.len = namelen; + if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) { + name.len = name.len - 5; + memmove(name.data, name.data + 5, name.len); + cn->cn_has_legacy = true; + } + if (!nfs4_client_to_reclaim(name, nn)) { + kfree(name.data); + return -EFAULT; + } + return sizeof(*cmsg); + } + return -EFAULT; +} + +static ssize_t cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { struct cld_upcall *tmp, *cup; @@ -715,6 +823,7 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) struct nfsd_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info, nfsd_net_id); struct cld_net *cn = nn->cld_net; + int16_t status; if (mlen != sizeof(*cmsg)) { dprintk("%s: got %zu bytes, expected %zu\n", __func__, mlen, @@ -728,13 +837,24 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) return -EFAULT; } + /* + * copy the status so we know whether to remove the upcall from the + * list (for -EINPROGRESS, we just want to make sure the xid is + * valid, not remove the upcall from the list) + */ + if (get_user(status, &cmsg->cm_status)) { + dprintk("%s: error when copying status from userspace", __func__); + return -EFAULT; + } + /* walk the list and find corresponding xid */ cup = NULL; spin_lock(&cn->cn_lock); list_for_each_entry(tmp, &cn->cn_list, cu_list) { if (get_unaligned(&tmp->cu_msg.cm_xid) == xid) { cup = tmp; - list_del_init(&cup->cu_list); + if (status != -EINPROGRESS) + list_del_init(&cup->cu_list); break; } } @@ -746,6 +866,9 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) return -EINVAL; } + if (status == -EINPROGRESS) + return __cld_pipe_inprogress_downcall(cmsg, nn); + if (copy_from_user(&cup->cu_msg, src, mlen) != 0) return -EFAULT; @@ -821,7 +944,7 @@ nfsd4_cld_unregister_net(struct net *net, struct rpc_pipe *pipe) /* Initialize rpc_pipefs pipe for communication with client tracking daemon */ static int -nfsd4_init_cld_pipe(struct net *net) +__nfsd4_init_cld_pipe(struct net *net) { int ret; struct dentry *dentry; @@ -852,6 +975,7 @@ nfsd4_init_cld_pipe(struct net *net) } cn->cn_pipe->dentry = dentry; + cn->cn_has_legacy = false; nn->cld_net = cn; return 0; @@ -864,6 +988,17 @@ err: return ret; } +static int +nfsd4_init_cld_pipe(struct net *net) +{ + int status; + + status = __nfsd4_init_cld_pipe(net); + if (!status) + printk("NFSD: Using old nfsdcld client tracking operations.\n"); + return status; +} + static void nfsd4_remove_cld_pipe(struct net *net) { @@ -992,9 +1127,14 @@ out_err: "record from stable storage: %d\n", ret); } -/* Check for presence of a record, and update its timestamp */ +/* + * For older nfsdcld's that do not allow us to "slurp" the clients + * from the tracking database during startup. + * + * Check for presence of a record, and update its timestamp + */ static int -nfsd4_cld_check(struct nfs4_client *clp) +nfsd4_cld_check_v0(struct nfs4_client *clp) { int ret; struct cld_upcall *cup; @@ -1027,8 +1167,84 @@ nfsd4_cld_check(struct nfs4_client *clp) return ret; } +/* + * For newer nfsdcld's that allow us to "slurp" the clients + * from the tracking database during startup. + * + * Check for presence of a record in the reclaim_str_hashtbl + */ +static int +nfsd4_cld_check(struct nfs4_client *clp) +{ + struct nfs4_client_reclaim *crp; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + struct cld_net *cn = nn->cld_net; + int status; + char dname[HEXDIR_LEN]; + struct xdr_netobj name; + + /* did we already find that this client is stable? */ + if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) + return 0; + + /* look for it in the reclaim hashtable otherwise */ + crp = nfsd4_find_reclaim_client(clp->cl_name, nn); + if (crp) + goto found; + + if (cn->cn_has_legacy) { + status = nfs4_make_rec_clidname(dname, &clp->cl_name); + if (status) + return -ENOENT; + + name.data = kmemdup(dname, HEXDIR_LEN, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return -ENOENT; + } + name.len = HEXDIR_LEN; + crp = nfsd4_find_reclaim_client(name, nn); + kfree(name.data); + if (crp) + goto found; + + } + return -ENOENT; +found: + crp->cr_clp = clp; + return 0; +} + +static int +nfsd4_cld_grace_start(struct nfsd_net *nn) +{ + int ret; + struct cld_upcall *cup; + struct cld_net *cn = nn->cld_net; + + cup = alloc_cld_upcall(cn); + if (!cup) { + ret = -ENOMEM; + goto out_err; + } + + cup->cu_msg.cm_cmd = Cld_GraceStart; + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg); + if (!ret) + ret = cup->cu_msg.cm_status; + + free_cld_upcall(cup); +out_err: + if (ret) + dprintk("%s: Unable to get clients from userspace: %d\n", + __func__, ret); + return ret; +} + +/* For older nfsdcld's that need cm_gracetime */ static void -nfsd4_cld_grace_done(struct nfsd_net *nn) +nfsd4_cld_grace_done_v0(struct nfsd_net *nn) { int ret; struct cld_upcall *cup; @@ -1052,11 +1268,149 @@ out_err: printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret); } -static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = { +/* + * For newer nfsdcld's that do not need cm_gracetime. We also need to call + * nfs4_release_reclaim() to clear out the reclaim_str_hashtbl. + */ +static void +nfsd4_cld_grace_done(struct nfsd_net *nn) +{ + int ret; + struct cld_upcall *cup; + struct cld_net *cn = nn->cld_net; + + cup = alloc_cld_upcall(cn); + if (!cup) { + ret = -ENOMEM; + goto out_err; + } + + cup->cu_msg.cm_cmd = Cld_GraceDone; + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg); + if (!ret) + ret = cup->cu_msg.cm_status; + + free_cld_upcall(cup); +out_err: + nfs4_release_reclaim(nn); + if (ret) + printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret); +} + +static int +nfs4_cld_state_init(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + int i; + + nn->reclaim_str_hashtbl = kmalloc_array(CLIENT_HASH_SIZE, + sizeof(struct list_head), + GFP_KERNEL); + if (!nn->reclaim_str_hashtbl) + return -ENOMEM; + + for (i = 0; i < CLIENT_HASH_SIZE; i++) + INIT_LIST_HEAD(&nn->reclaim_str_hashtbl[i]); + nn->reclaim_str_hashtbl_size = 0; + nn->track_reclaim_completes = true; + atomic_set(&nn->nr_reclaim_complete, 0); + + return 0; +} + +static void +nfs4_cld_state_shutdown(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nn->track_reclaim_completes = false; + kfree(nn->reclaim_str_hashtbl); +} + +static bool +cld_running(struct nfsd_net *nn) +{ + struct cld_net *cn = nn->cld_net; + struct rpc_pipe *pipe = cn->cn_pipe; + + return pipe->nreaders || pipe->nwriters; +} + +static int +nfsd4_cld_tracking_init(struct net *net) +{ + int status; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + bool running; + int retries = 10; + + status = nfs4_cld_state_init(net); + if (status) + return status; + + status = __nfsd4_init_cld_pipe(net); + if (status) + goto err_shutdown; + + /* + * rpc pipe upcalls take 30 seconds to time out, so we don't want to + * queue an upcall unless we know that nfsdcld is running (because we + * want this to fail fast so that nfsd4_client_tracking_init() can try + * the next client tracking method). nfsdcld should already be running + * before nfsd is started, so the wait here is for nfsdcld to open the + * pipefs file we just created. + */ + while (!(running = cld_running(nn)) && retries--) + msleep(100); + + if (!running) { + status = -ETIMEDOUT; + goto err_remove; + } + + status = nfsd4_cld_grace_start(nn); + if (status) { + if (status == -EOPNOTSUPP) + printk(KERN_WARNING "NFSD: Please upgrade nfsdcld.\n"); + nfs4_release_reclaim(nn); + goto err_remove; + } else + printk("NFSD: Using nfsdcld client tracking operations.\n"); + return 0; + +err_remove: + nfsd4_remove_cld_pipe(net); +err_shutdown: + nfs4_cld_state_shutdown(net); + return status; +} + +static void +nfsd4_cld_tracking_exit(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs4_release_reclaim(nn); + nfsd4_remove_cld_pipe(net); + nfs4_cld_state_shutdown(net); +} + +/* For older nfsdcld's */ +static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v0 = { .init = nfsd4_init_cld_pipe, .exit = nfsd4_remove_cld_pipe, .create = nfsd4_cld_create, .remove = nfsd4_cld_remove, + .check = nfsd4_cld_check_v0, + .grace_done = nfsd4_cld_grace_done_v0, +}; + +/* For newer nfsdcld's */ +static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = { + .init = nfsd4_cld_tracking_init, + .exit = nfsd4_cld_tracking_exit, + .create = nfsd4_cld_create, + .remove = nfsd4_cld_remove, .check = nfsd4_cld_check, .grace_done = nfsd4_cld_grace_done, }; @@ -1268,6 +1622,8 @@ nfsd4_umh_cltrack_init(struct net *net) ret = nfsd4_umh_cltrack_upcall("init", NULL, grace_start, NULL); kfree(grace_start); + if (!ret) + printk("NFSD: Using UMH upcall client tracking operations.\n"); return ret; } @@ -1417,9 +1773,20 @@ nfsd4_client_tracking_init(struct net *net) if (nn->client_tracking_ops) goto do_init; + /* First, try to use nfsdcld */ + nn->client_tracking_ops = &nfsd4_cld_tracking_ops; + status = nn->client_tracking_ops->init(net); + if (!status) + return status; + if (status != -ETIMEDOUT) { + nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0; + status = nn->client_tracking_ops->init(net); + if (!status) + return status; + } + /* - * First, try a UMH upcall. It should succeed or fail quickly, so - * there's little harm in trying that first. + * Next, try the UMH upcall. */ nn->client_tracking_ops = &nfsd4_umh_tracking_ops; status = nn->client_tracking_ops->init(net); @@ -1427,25 +1794,23 @@ nfsd4_client_tracking_init(struct net *net) return status; /* - * See if the recoverydir exists and is a directory. If it is, - * then use the legacy ops. + * Finally, See if the recoverydir exists and is a directory. + * If it is, then use the legacy ops. */ nn->client_tracking_ops = &nfsd4_legacy_tracking_ops; status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path); if (!status) { status = d_is_dir(path.dentry); path_put(&path); - if (status) - goto do_init; + if (!status) { + status = -EINVAL; + goto out; + } } - /* Finally, try to use nfsdcld */ - nn->client_tracking_ops = &nfsd4_cld_tracking_ops; - printk(KERN_WARNING "NFSD: the nfsdcld client tracking upcall will be " - "removed in 3.10. Please transition to using " - "nfsdcltrack.\n"); do_init: status = nn->client_tracking_ops->init(net); +out: if (status) { printk(KERN_WARNING "NFSD: Unable to initialize client " "recovery tracking! (%d)\n", status); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6a45fb00c5fc..618e66078ee5 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -77,6 +77,7 @@ static u64 current_sessionid = 1; /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); +void nfsd4_end_grace(struct nfsd_net *nn); /* Locking: */ @@ -265,6 +266,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { + locks_delete_block(&nbl->nbl_lock); locks_release_private(&nbl->nbl_lock); kfree(nbl); } @@ -293,11 +295,18 @@ remove_blocked_locks(struct nfs4_lockowner *lo) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } } +static void +nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) +{ + struct nfsd4_blocked_lock *nbl = container_of(cb, + struct nfsd4_blocked_lock, nbl_cb); + locks_delete_block(&nbl->nbl_lock); +} + static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -325,6 +334,7 @@ nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb) } static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { + .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, }; @@ -1058,9 +1068,9 @@ static unsigned int clientid_hashval(u32 id) return id & CLIENT_HASH_MASK; } -static unsigned int clientstr_hashval(const char *name) +static unsigned int clientstr_hashval(struct xdr_netobj name) { - return opaque_hashval(name, 8) & CLIENT_HASH_MASK; + return opaque_hashval(name.data, 8) & CLIENT_HASH_MASK; } /* @@ -1988,6 +1998,22 @@ destroy_client(struct nfs4_client *clp) __destroy_client(clp); } +static void inc_reclaim_complete(struct nfs4_client *clp) +{ + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + if (!nn->track_reclaim_completes) + return; + if (!nfsd4_find_reclaim_client(clp->cl_name, nn)) + return; + if (atomic_inc_return(&nn->nr_reclaim_complete) == + nn->reclaim_str_hashtbl_size) { + printk(KERN_INFO "NFSD: all clients done reclaiming, ending NFSv4 grace period (net %x)\n", + clp->net->ns.inum); + nfsd4_end_grace(nn); + } +} + static void expire_client(struct nfs4_client *clp) { unhash_client(clp); @@ -2039,11 +2065,6 @@ compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) return memcmp(o1->data, o2->data, o1->len); } -static int same_name(const char *n1, const char *n2) -{ - return 0 == memcmp(n1, n2, HEXDIR_LEN); -} - static int same_verf(nfs4_verifier *v1, nfs4_verifier *v2) { @@ -2576,6 +2597,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, break; default: /* checked by xdr code */ WARN_ON_ONCE(1); + /* fall through */ case SP4_SSV: status = nfserr_encr_alg_unsupp; goto out_nolock; @@ -3344,6 +3366,7 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, status = nfs_ok; nfsd4_client_record_create(cstate->session->se_client); + inc_reclaim_complete(cstate->session->se_client); out: return status; } @@ -3948,6 +3971,9 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, switch (task->tk_status) { case 0: return 1; + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; case -EBADHANDLE: case -NFS4ERR_BAD_STATEID: /* @@ -3960,7 +3986,7 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, } /*FALLTHRU*/ default: - return -1; + return 1; } } @@ -4703,7 +4729,6 @@ nfsd4_end_grace(struct nfsd_net *nn) if (nn->grace_ended) return; - dprintk("NFSD: end of grace period\n"); nn->grace_ended = true; /* * If the server goes down again right now, an NFSv4 @@ -4739,6 +4764,10 @@ static bool clients_still_reclaiming(struct nfsd_net *nn) unsigned long double_grace_period_end = nn->boot_time + 2 * nn->nfsd4_lease; + if (nn->track_reclaim_completes && + atomic_read(&nn->nr_reclaim_complete) == + nn->reclaim_str_hashtbl_size) + return false; if (!nn->somebody_reclaimed) return false; nn->somebody_reclaimed = false; @@ -4769,6 +4798,7 @@ nfs4_laundromat(struct nfsd_net *nn) new_timeo = 0; goto out; } + dprintk("NFSD: end of grace period\n"); nfsd4_end_grace(nn); INIT_LIST_HEAD(&reaplist); spin_lock(&nn->client_lock); @@ -4863,7 +4893,6 @@ nfs4_laundromat(struct nfsd_net *nn) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } out: @@ -6449,7 +6478,7 @@ alloc_reclaim(void) } bool -nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn) +nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client_reclaim *crp; @@ -6459,20 +6488,24 @@ nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn) /* * failure => all reset bets are off, nfserr_no_grace... + * + * The caller is responsible for freeing name.data if NULL is returned (it + * will be freed in nfs4_remove_reclaim_record in the normal case). */ struct nfs4_client_reclaim * -nfs4_client_to_reclaim(const char *name, struct nfsd_net *nn) +nfs4_client_to_reclaim(struct xdr_netobj name, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp; - dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", HEXDIR_LEN, name); + dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", name.len, name.data); crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); INIT_LIST_HEAD(&crp->cr_strhash); list_add(&crp->cr_strhash, &nn->reclaim_str_hashtbl[strhashval]); - memcpy(crp->cr_recdir, name, HEXDIR_LEN); + crp->cr_name.data = name.data; + crp->cr_name.len = name.len; crp->cr_clp = NULL; nn->reclaim_str_hashtbl_size++; } @@ -6483,6 +6516,7 @@ void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *crp, struct nfsd_net *nn) { list_del(&crp->cr_strhash); + kfree(crp->cr_name.data); kfree(crp); nn->reclaim_str_hashtbl_size--; } @@ -6506,16 +6540,16 @@ nfs4_release_reclaim(struct nfsd_net *nn) /* * called from OPEN, CLAIM_PREVIOUS with a new clientid. */ struct nfs4_client_reclaim * -nfsd4_find_reclaim_client(const char *recdir, struct nfsd_net *nn) +nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; - dprintk("NFSD: nfs4_find_reclaim_client for recdir %s\n", recdir); + dprintk("NFSD: nfs4_find_reclaim_client for name %.*s\n", name.len, name.data); - strhashval = clientstr_hashval(recdir); + strhashval = clientstr_hashval(name); list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) { - if (same_name(crp->cr_recdir, recdir)) { + if (compare_blob(&crp->cr_name, &name) == 0) { return crp; } } @@ -7253,10 +7287,19 @@ nfs4_state_start_net(struct net *net) 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) + goto skip_grace; printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); return 0; + +skip_grace: + printk(KERN_INFO "NFSD: no clients to reclaim, skipping NFSv4 grace period (net %x)\n", + net->ns.inum); + queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_lease * HZ); + nfsd4_end_grace(nn); + return 0; } /* initialization to perform when the nfsd service is started: */ diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 3de42a729093..52c4f6daa649 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -521,6 +521,7 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs) { DECODE_HEAD; + struct user_namespace *userns = nfsd_user_namespace(argp->rqstp); u32 dummy, uid, gid; char *machine_name; int i; @@ -563,8 +564,8 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); if (cbs->flavor == (u32)(-1)) { - kuid_t kuid = make_kuid(&init_user_ns, uid); - kgid_t kgid = make_kgid(&init_user_ns, gid); + kuid_t kuid = make_kuid(userns, uid); + kgid_t kgid = make_kgid(userns, gid); if (uid_valid(kuid) && gid_valid(kgid)) { cbs->uid = kuid; cbs->gid = kgid; @@ -2420,8 +2421,10 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, __be32 status; int err; struct nfs4_acl *acl = NULL; +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL void *context = NULL; int contextlen; +#endif bool contextsupport = false; struct nfsd4_compoundres *resp = rqstp->rq_resp; u32 minorversion = resp->cstate.minorversion; @@ -2906,12 +2909,14 @@ out_acl: *p++ = cpu_to_be32(NFS4_CHANGE_TYPE_IS_TIME_METADATA); } +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { status = nfsd4_encode_security_label(xdr, rqstp, context, contextlen); if (status) goto out; } +#endif attrlen = htonl(xdr->buf->len - attrlen_offset - 4); write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index f2feb2d11bae..90972e1fd785 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -439,7 +439,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return rv; if (newthreads < 0) return -EINVAL; - rv = nfsd_svc(newthreads, net); + rv = nfsd_svc(newthreads, net, file->f_cred); if (rv < 0) return rv; } else @@ -537,14 +537,14 @@ out_free: } static ssize_t -nfsd_print_version_support(char *buf, int remaining, const char *sep, - unsigned vers, int minor) +nfsd_print_version_support(struct nfsd_net *nn, char *buf, int remaining, + const char *sep, unsigned vers, int minor) { const char *format = minor < 0 ? "%s%c%u" : "%s%c%u.%u"; - bool supported = !!nfsd_vers(vers, NFSD_TEST); + bool supported = !!nfsd_vers(nn, vers, NFSD_TEST); if (vers == 4 && minor >= 0 && - !nfsd_minorversion(minor, NFSD_TEST)) + !nfsd_minorversion(nn, minor, NFSD_TEST)) supported = false; if (minor == 0 && supported) /* @@ -599,20 +599,20 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) switch(num) { case 2: case 3: - nfsd_vers(num, cmd); + nfsd_vers(nn, num, cmd); break; case 4: if (*minorp == '.') { - if (nfsd_minorversion(minor, cmd) < 0) + if (nfsd_minorversion(nn, minor, cmd) < 0) return -EINVAL; - } else if ((cmd == NFSD_SET) != nfsd_vers(num, NFSD_TEST)) { + } else if ((cmd == NFSD_SET) != nfsd_vers(nn, num, NFSD_TEST)) { /* * Either we have +4 and no minors are enabled, * or we have -4 and at least one minor is enabled. * In either case, propagate 'cmd' to all minors. */ minor = 0; - while (nfsd_minorversion(minor, cmd) >= 0) + while (nfsd_minorversion(nn, minor, cmd) >= 0) minor++; } break; @@ -624,7 +624,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) /* If all get turned off, turn them back on, as * having no versions is BAD */ - nfsd_reset_versions(); + nfsd_reset_versions(nn); } /* Now write current state into reply buffer */ @@ -633,12 +633,12 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) remaining = SIMPLE_TRANSACTION_LIMIT; for (num=2 ; num <= 4 ; num++) { int minor; - if (!nfsd_vers(num, NFSD_AVAIL)) + if (!nfsd_vers(nn, num, NFSD_AVAIL)) continue; minor = -1; do { - len = nfsd_print_version_support(buf, remaining, + len = nfsd_print_version_support(nn, buf, remaining, sep, num, minor); if (len >= remaining) goto out; @@ -717,7 +717,7 @@ static ssize_t __write_ports_names(char *buf, struct net *net) * a socket of a supported family/protocol, and we use it as an * nfsd listener. */ -static ssize_t __write_ports_addfd(char *buf, struct net *net) +static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred *cred) { char *mesg = buf; int fd, err; @@ -736,7 +736,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net) if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT); + err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); if (err < 0) { nfsd_destroy(net); return err; @@ -751,7 +751,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net) * A transport listener is added by writing it's transport name and * a port number. */ -static ssize_t __write_ports_addxprt(char *buf, struct net *net) +static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cred *cred) { char transport[16]; struct svc_xprt *xprt; @@ -769,12 +769,12 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net) return err; err = svc_create_xprt(nn->nfsd_serv, transport, net, - PF_INET, port, SVC_SOCK_ANONYMOUS); + PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; err = svc_create_xprt(nn->nfsd_serv, transport, net, - PF_INET6, port, SVC_SOCK_ANONYMOUS); + PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; @@ -799,10 +799,10 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size, return __write_ports_names(buf, net); if (isdigit(buf[0])) - return __write_ports_addfd(buf, net); + return __write_ports_addfd(buf, net, file->f_cred); if (isalpha(buf[0])) - return __write_ports_addxprt(buf, net); + return __write_ports_addxprt(buf, net, file->f_cred); return -EINVAL; } @@ -1239,9 +1239,12 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; + nn->nfsd_versions = NULL; + nn->nfsd4_minorversions = NULL; nn->nfsd4_lease = 90; /* default lease time */ nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; + nn->track_reclaim_completes = false; nn->clverifier_counter = prandom_u32(); nn->clientid_counter = prandom_u32(); nn->s2s_cp_cl_id = nn->clientid_counter++; @@ -1260,6 +1263,7 @@ static __net_exit void nfsd_exit_net(struct net *net) { nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); + nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); } static struct pernet_operations nfsd_net_ops = { diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 066899929863..24187b5dd638 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -17,6 +17,7 @@ #include <linux/nfs3.h> #include <linux/nfs4.h> #include <linux/sunrpc/svc.h> +#include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/msg_prot.h> #include <uapi/linux/nfsd/debug.h> @@ -73,7 +74,7 @@ extern const struct seq_operations nfs_exports_op; /* * Function prototypes. */ -int nfsd_svc(int nrservs, struct net *net); +int nfsd_svc(int nrservs, struct net *net, const struct cred *cred); int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); int nfsd_nrthreads(struct net *); @@ -98,10 +99,12 @@ extern const struct svc_version nfsd_acl_version3; #endif #endif +struct nfsd_net; + enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; -int nfsd_vers(int vers, enum vers_op change); -int nfsd_minorversion(u32 minorversion, enum vers_op change); -void nfsd_reset_versions(void); +int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change); +int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change); +void nfsd_reset_versions(struct nfsd_net *nn); int nfsd_create_serv(struct net *net); extern int nfsd_max_blksize; @@ -110,6 +113,12 @@ static inline int nfsd_v4client(struct svc_rqst *rq) { return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4; } +static inline struct user_namespace * +nfsd_user_namespace(const struct svc_rqst *rqstp) +{ + const struct cred *cred = rqstp->rq_xprt->xpt_cred; + return cred ? cred->user_ns : &init_user_ns; +} /* * NFSv4 State diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 89cb484f1cfb..18d94ea984ba 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -32,6 +32,24 @@ extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) +static int nfsd_acl_rpcbind_set(struct net *, + const struct svc_program *, + u32, int, + unsigned short, + unsigned short); +static __be32 nfsd_acl_init_request(struct svc_rqst *, + const struct svc_program *, + struct svc_process_info *); +#endif +static int nfsd_rpcbind_set(struct net *, + const struct svc_program *, + u32, int, + unsigned short, + unsigned short); +static __be32 nfsd_init_request(struct svc_rqst *, + const struct svc_program *, + struct svc_process_info *); /* * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members @@ -86,6 +104,8 @@ static struct svc_program nfsd_acl_program = { .pg_class = "nfsd", .pg_stats = &nfsd_acl_svcstats, .pg_authenticate = &svc_set_client, + .pg_init_request = nfsd_acl_init_request, + .pg_rpcbind_set = nfsd_acl_rpcbind_set, }; static struct svc_stat nfsd_acl_svcstats = { @@ -105,7 +125,6 @@ static const struct svc_version *nfsd_version[] = { #define NFSD_MINVERS 2 #define NFSD_NRVERS ARRAY_SIZE(nfsd_version) -static const struct svc_version *nfsd_versions[NFSD_NRVERS]; struct svc_program nfsd_program = { #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) @@ -113,77 +132,136 @@ struct svc_program nfsd_program = { #endif .pg_prog = NFS_PROGRAM, /* program number */ .pg_nvers = NFSD_NRVERS, /* nr of entries in nfsd_version */ - .pg_vers = nfsd_versions, /* version table */ + .pg_vers = nfsd_version, /* version table */ .pg_name = "nfsd", /* program name */ .pg_class = "nfsd", /* authentication class */ .pg_stats = &nfsd_svcstats, /* version table */ .pg_authenticate = &svc_set_client, /* export authentication */ - + .pg_init_request = nfsd_init_request, + .pg_rpcbind_set = nfsd_rpcbind_set, }; -static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = { - [0] = 1, - [1] = 1, - [2] = 1, -}; +static bool +nfsd_support_version(int vers) +{ + if (vers >= NFSD_MINVERS && vers < NFSD_NRVERS) + return nfsd_version[vers] != NULL; + return false; +} + +static bool * +nfsd_alloc_versions(void) +{ + bool *vers = kmalloc_array(NFSD_NRVERS, sizeof(bool), GFP_KERNEL); + unsigned i; + + if (vers) { + /* All compiled versions are enabled by default */ + for (i = 0; i < NFSD_NRVERS; i++) + vers[i] = nfsd_support_version(i); + } + return vers; +} + +static bool * +nfsd_alloc_minorversions(void) +{ + bool *vers = kmalloc_array(NFSD_SUPPORTED_MINOR_VERSION + 1, + sizeof(bool), GFP_KERNEL); + unsigned i; + + if (vers) { + /* All minor versions are enabled by default */ + for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) + vers[i] = nfsd_support_version(4); + } + return vers; +} -int nfsd_vers(int vers, enum vers_op change) +void +nfsd_netns_free_versions(struct nfsd_net *nn) +{ + kfree(nn->nfsd_versions); + kfree(nn->nfsd4_minorversions); + nn->nfsd_versions = NULL; + nn->nfsd4_minorversions = NULL; +} + +static void +nfsd_netns_init_versions(struct nfsd_net *nn) +{ + if (!nn->nfsd_versions) { + nn->nfsd_versions = nfsd_alloc_versions(); + nn->nfsd4_minorversions = nfsd_alloc_minorversions(); + if (!nn->nfsd_versions || !nn->nfsd4_minorversions) + nfsd_netns_free_versions(nn); + } +} + +int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change) { if (vers < NFSD_MINVERS || vers >= NFSD_NRVERS) return 0; switch(change) { case NFSD_SET: - nfsd_versions[vers] = nfsd_version[vers]; -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - if (vers < NFSD_ACL_NRVERS) - nfsd_acl_versions[vers] = nfsd_acl_version[vers]; -#endif + if (nn->nfsd_versions) + nn->nfsd_versions[vers] = nfsd_support_version(vers); break; case NFSD_CLEAR: - nfsd_versions[vers] = NULL; -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - if (vers < NFSD_ACL_NRVERS) - nfsd_acl_versions[vers] = NULL; -#endif + nfsd_netns_init_versions(nn); + if (nn->nfsd_versions) + nn->nfsd_versions[vers] = false; break; case NFSD_TEST: - return nfsd_versions[vers] != NULL; + if (nn->nfsd_versions) + return nn->nfsd_versions[vers]; + /* Fallthrough */ case NFSD_AVAIL: - return nfsd_version[vers] != NULL; + return nfsd_support_version(vers); } return 0; } static void -nfsd_adjust_nfsd_versions4(void) +nfsd_adjust_nfsd_versions4(struct nfsd_net *nn) { unsigned i; for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) { - if (nfsd_supported_minorversions[i]) + if (nn->nfsd4_minorversions[i]) return; } - nfsd_vers(4, NFSD_CLEAR); + nfsd_vers(nn, 4, NFSD_CLEAR); } -int nfsd_minorversion(u32 minorversion, enum vers_op change) +int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change) { if (minorversion > NFSD_SUPPORTED_MINOR_VERSION && change != NFSD_AVAIL) return -1; + switch(change) { case NFSD_SET: - nfsd_supported_minorversions[minorversion] = true; - nfsd_vers(4, NFSD_SET); + if (nn->nfsd4_minorversions) { + nfsd_vers(nn, 4, NFSD_SET); + nn->nfsd4_minorversions[minorversion] = + nfsd_vers(nn, 4, NFSD_TEST); + } break; case NFSD_CLEAR: - nfsd_supported_minorversions[minorversion] = false; - nfsd_adjust_nfsd_versions4(); + nfsd_netns_init_versions(nn); + if (nn->nfsd4_minorversions) { + nn->nfsd4_minorversions[minorversion] = false; + nfsd_adjust_nfsd_versions4(nn); + } break; case NFSD_TEST: - return nfsd_supported_minorversions[minorversion]; + if (nn->nfsd4_minorversions) + return nn->nfsd4_minorversions[minorversion]; + return nfsd_vers(nn, 4, NFSD_TEST); case NFSD_AVAIL: - return minorversion <= NFSD_SUPPORTED_MINOR_VERSION; + return minorversion <= NFSD_SUPPORTED_MINOR_VERSION && + nfsd_vers(nn, 4, NFSD_AVAIL); } return 0; } @@ -205,7 +283,7 @@ int nfsd_nrthreads(struct net *net) return rv; } -static int nfsd_init_socks(struct net *net) +static int nfsd_init_socks(struct net *net, const struct cred *cred) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -214,12 +292,12 @@ static int nfsd_init_socks(struct net *net) return 0; error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS); + SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS); + SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; @@ -265,16 +343,12 @@ static void nfsd_shutdown_generic(void) nfsd_racache_shutdown(); } -static bool nfsd_needs_lockd(void) +static bool nfsd_needs_lockd(struct nfsd_net *nn) { -#if defined(CONFIG_NFSD_V3) - return (nfsd_versions[2] != NULL) || (nfsd_versions[3] != NULL); -#else - return (nfsd_versions[2] != NULL); -#endif + return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST); } -static int nfsd_startup_net(int nrservs, struct net *net) +static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cred) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; @@ -285,12 +359,12 @@ static int nfsd_startup_net(int nrservs, struct net *net) ret = nfsd_startup_generic(nrservs); if (ret) return ret; - ret = nfsd_init_socks(net); + ret = nfsd_init_socks(net, cred); if (ret) goto out_socks; - if (nfsd_needs_lockd() && !nn->lockd_up) { - ret = lockd_up(net); + if (nfsd_needs_lockd(nn) && !nn->lockd_up) { + ret = lockd_up(net, cred); if (ret) goto out_socks; nn->lockd_up = 1; @@ -422,20 +496,20 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) nfsd_export_flush(net); } -void nfsd_reset_versions(void) +void nfsd_reset_versions(struct nfsd_net *nn) { int i; for (i = 0; i < NFSD_NRVERS; i++) - if (nfsd_vers(i, NFSD_TEST)) + if (nfsd_vers(nn, i, NFSD_TEST)) return; for (i = 0; i < NFSD_NRVERS; i++) if (i != 4) - nfsd_vers(i, NFSD_SET); + nfsd_vers(nn, i, NFSD_SET); else { int minor = 0; - while (nfsd_minorversion(minor, NFSD_SET) >= 0) + while (nfsd_minorversion(nn, minor, NFSD_SET) >= 0) minor++; } } @@ -503,7 +577,7 @@ int nfsd_create_serv(struct net *net) } if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); - nfsd_reset_versions(); + nfsd_reset_versions(nn); nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, &nfsd_thread_sv_ops); if (nn->nfsd_serv == NULL) @@ -623,7 +697,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) * this is the first time nrservs is nonzero. */ int -nfsd_svc(int nrservs, struct net *net) +nfsd_svc(int nrservs, struct net *net, const struct cred *cred) { int error; bool nfsd_up_before; @@ -645,7 +719,7 @@ nfsd_svc(int nrservs, struct net *net) nfsd_up_before = nn->nfsd_net_up; - error = nfsd_startup_net(nrservs, net); + error = nfsd_startup_net(nrservs, net, cred); if (error) goto out_destroy; error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, @@ -667,6 +741,101 @@ out: return error; } +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) +static bool +nfsd_support_acl_version(int vers) +{ + if (vers >= NFSD_ACL_MINVERS && vers < NFSD_ACL_NRVERS) + return nfsd_acl_version[vers] != NULL; + return false; +} + +static int +nfsd_acl_rpcbind_set(struct net *net, const struct svc_program *progp, + u32 version, int family, unsigned short proto, + unsigned short port) +{ + if (!nfsd_support_acl_version(version) || + !nfsd_vers(net_generic(net, nfsd_net_id), version, NFSD_TEST)) + return 0; + return svc_generic_rpcbind_set(net, progp, version, family, + proto, port); +} + +static __be32 +nfsd_acl_init_request(struct svc_rqst *rqstp, + const struct svc_program *progp, + struct svc_process_info *ret) +{ + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + int i; + + if (likely(nfsd_support_acl_version(rqstp->rq_vers) && + nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) + return svc_generic_init_request(rqstp, progp, ret); + + ret->mismatch.lovers = NFSD_ACL_NRVERS; + for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) { + if (nfsd_support_acl_version(rqstp->rq_vers) && + nfsd_vers(nn, i, NFSD_TEST)) { + ret->mismatch.lovers = i; + break; + } + } + if (ret->mismatch.lovers == NFSD_ACL_NRVERS) + return rpc_prog_unavail; + ret->mismatch.hivers = NFSD_ACL_MINVERS; + for (i = NFSD_ACL_NRVERS - 1; i >= NFSD_ACL_MINVERS; i--) { + if (nfsd_support_acl_version(rqstp->rq_vers) && + nfsd_vers(nn, i, NFSD_TEST)) { + ret->mismatch.hivers = i; + break; + } + } + return rpc_prog_mismatch; +} +#endif + +static int +nfsd_rpcbind_set(struct net *net, const struct svc_program *progp, + u32 version, int family, unsigned short proto, + unsigned short port) +{ + if (!nfsd_vers(net_generic(net, nfsd_net_id), version, NFSD_TEST)) + return 0; + return svc_generic_rpcbind_set(net, progp, version, family, + proto, port); +} + +static __be32 +nfsd_init_request(struct svc_rqst *rqstp, + const struct svc_program *progp, + struct svc_process_info *ret) +{ + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + int i; + + if (likely(nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) + return svc_generic_init_request(rqstp, progp, ret); + + ret->mismatch.lovers = NFSD_NRVERS; + for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) { + if (nfsd_vers(nn, i, NFSD_TEST)) { + ret->mismatch.lovers = i; + break; + } + } + if (ret->mismatch.lovers == NFSD_NRVERS) + return rpc_prog_unavail; + ret->mismatch.hivers = NFSD_MINVERS; + for (i = NFSD_NRVERS - 1; i >= NFSD_MINVERS; i--) { + if (nfsd_vers(nn, i, NFSD_TEST)) { + ret->mismatch.hivers = i; + break; + } + } + return rpc_prog_mismatch; +} /* * This is the NFS server kernel thread diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 6b2e8b73d36e..b51fe515f06f 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -71,7 +71,7 @@ decode_filename(__be32 *p, char **namp, unsigned int *lenp) } static __be32 * -decode_sattr(__be32 *p, struct iattr *iap) +decode_sattr(__be32 *p, struct iattr *iap, struct user_namespace *userns) { u32 tmp, tmp1; @@ -86,12 +86,12 @@ decode_sattr(__be32 *p, struct iattr *iap) iap->ia_mode = tmp; } if ((tmp = ntohl(*p++)) != (u32)-1) { - iap->ia_uid = make_kuid(&init_user_ns, tmp); + iap->ia_uid = make_kuid(userns, tmp); if (uid_valid(iap->ia_uid)) iap->ia_valid |= ATTR_UID; } if ((tmp = ntohl(*p++)) != (u32)-1) { - iap->ia_gid = make_kgid(&init_user_ns, tmp); + iap->ia_gid = make_kgid(userns, tmp); if (gid_valid(iap->ia_gid)) iap->ia_valid |= ATTR_GID; } @@ -129,6 +129,7 @@ static __be32 * encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat) { + struct user_namespace *userns = nfsd_user_namespace(rqstp); struct dentry *dentry = fhp->fh_dentry; int type; struct timespec64 time; @@ -139,8 +140,8 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, *p++ = htonl(nfs_ftypes[type >> 12]); *p++ = htonl((u32) stat->mode); *p++ = htonl((u32) stat->nlink); - *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid)); - *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid)); + *p++ = htonl((u32) from_kuid_munged(userns, stat->uid)); + *p++ = htonl((u32) from_kgid_munged(userns, stat->gid)); if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) { *p++ = htonl(NFS_MAXPATHLEN); @@ -216,7 +217,7 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) p = decode_fh(p, &args->fh); if (!p) return 0; - p = decode_sattr(p, &args->attrs); + p = decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); return xdr_argsize_check(rqstp, p); } @@ -319,7 +320,7 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) if ( !(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; - p = decode_sattr(p, &args->attrs); + p = decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); return xdr_argsize_check(rqstp, p); } @@ -398,7 +399,7 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) return 0; p += xdrlen; } - decode_sattr(p, &args->attrs); + decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); return 1; } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 396c76755b03..0b74d371ed67 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -70,6 +70,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; }; struct nfsd4_callback_ops { @@ -367,7 +368,7 @@ struct nfs4_client { struct nfs4_client_reclaim { struct list_head cr_strhash; /* hash by cr_name */ struct nfs4_client *cr_clp; /* pointer to associated clp */ - char cr_recdir[HEXDIR_LEN]; /* recover dir */ + struct xdr_netobj cr_name; /* recovery dir name */ }; /* A reasonable value for REPLAY_ISIZE was estimated as follows: @@ -619,7 +620,7 @@ void nfs4_put_stid(struct nfs4_stid *s); void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); extern void nfs4_release_reclaim(struct nfsd_net *); -extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, +extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn); extern __be32 nfs4_check_open_reclaim(clientid_t *clid, struct nfsd4_compound_state *cstate, struct nfsd_net *nn); @@ -634,9 +635,9 @@ extern void nfsd4_destroy_callback_queue(void); extern void nfsd4_shutdown_callback(struct nfs4_client *); extern void nfsd4_shutdown_copy(struct nfs4_client *clp); extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp); -extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name, +extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name, struct nfsd_net *nn); -extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn); +extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn); struct nfs4_file *find_file(struct knfsd_fh *fh); void put_nfs4_file(struct nfs4_file *fi); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 7dc98e14655d..fc24ee47eab5 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1786,12 +1786,12 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, rdentry = lookup_one_len(fname, dentry, flen); host_err = PTR_ERR(rdentry); if (IS_ERR(rdentry)) - goto out_nfserr; + goto out_drop_write; if (d_really_is_negative(rdentry)) { dput(rdentry); - err = nfserr_noent; - goto out; + host_err = -ENOENT; + goto out_drop_write; } if (!type) @@ -1805,6 +1805,8 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, host_err = commit_metadata(fhp); dput(rdentry); +out_drop_write: + fh_drop_write(fhp); out_nfserr: err = nfserrno(host_err); out: diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index a7e107309f76..db351247892d 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -120,8 +120,11 @@ void nfsd_put_raparams(struct file *file, struct raparms *ra); static inline int fh_want_write(struct svc_fh *fh) { - int ret = mnt_want_write(fh->fh_export->ex_path.mnt); + int ret; + if (fh->fh_want_write) + return 0; + ret = mnt_want_write(fh->fh_export->ex_path.mnt); if (!ret) fh->fh_want_write = true; return ret; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index a2f247b6a209..42395ba52da6 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -252,7 +252,6 @@ int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *, struct nilfs_argv *, void nilfs_inode_add_blocks(struct inode *inode, int n); void nilfs_inode_sub_blocks(struct inode *inode, int n); extern struct inode *nilfs_new_inode(struct inode *, umode_t); -extern void nilfs_free_inode(struct inode *); extern int nilfs_get_block(struct inode *, sector_t, struct buffer_head *, int); extern void nilfs_set_inode_flags(struct inode *); extern int nilfs_read_inode_common(struct inode *, struct nilfs_inode *); @@ -289,7 +288,6 @@ static inline int nilfs_mark_inode_dirty_sync(struct inode *inode) /* super.c */ extern struct inode *nilfs_alloc_inode(struct super_block *); -extern void nilfs_destroy_inode(struct inode *); extern __printf(3, 4) void __nilfs_msg(struct super_block *sb, const char *level, diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 26290aa1023f..5729ee86da9a 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -155,21 +155,14 @@ struct inode *nilfs_alloc_inode(struct super_block *sb) return &ii->vfs_inode; } -static void nilfs_i_callback(struct rcu_head *head) +static void nilfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); - if (nilfs_is_metadata_file_inode(inode)) nilfs_mdt_destroy(inode); kmem_cache_free(nilfs_inode_cachep, NILFS_I(inode)); } -void nilfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, nilfs_i_callback); -} - static int nilfs_sync_super(struct super_block *sb, int flag) { struct the_nilfs *nilfs = sb->s_fs_info; @@ -686,7 +679,7 @@ static int nilfs_show_options(struct seq_file *seq, struct dentry *dentry) static const struct super_operations nilfs_sops = { .alloc_inode = nilfs_alloc_inode, - .destroy_inode = nilfs_destroy_inode, + .free_inode = nilfs_free_inode, .dirty_inode = nilfs_dirty_inode, .evict_inode = nilfs_evict_inode, .put_super = nilfs_put_super, diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 58d77dc696eb..250369d6901d 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -81,7 +81,7 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) static int dnotify_handle_event(struct fsnotify_group *group, struct inode *inode, u32 mask, const void *data, int data_type, - const unsigned char *file_name, u32 cookie, + const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig index 735bfb2e9190..521dc91d2cb5 100644 --- a/fs/notify/fanotify/Kconfig +++ b/fs/notify/fanotify/Kconfig @@ -1,7 +1,6 @@ config FANOTIFY bool "Filesystem wide access notification" select FSNOTIFY - select ANON_INODES select EXPORTFS default n ---help--- diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 6b9c27548997..e6fde1a5c072 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -346,10 +346,16 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info) __kernel_fsid_t fsid = {}; fsnotify_foreach_obj_type(type) { + struct fsnotify_mark_connector *conn; + if (!fsnotify_iter_should_report_type(iter_info, type)) continue; - fsid = iter_info->marks[type]->connector->fsid; + conn = READ_ONCE(iter_info->marks[type]->connector); + /* Mark is just getting destroyed or created? */ + if (!conn) + continue; + fsid = conn->fsid; if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1])) continue; return fsid; @@ -361,7 +367,7 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info) static int fanotify_handle_event(struct fsnotify_group *group, struct inode *inode, u32 mask, const void *data, int data_type, - const unsigned char *file_name, u32 cookie, + const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { int ret = 0; @@ -408,8 +414,12 @@ static int fanotify_handle_event(struct fsnotify_group *group, return 0; } - if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { fsid = fanotify_get_fsid(iter_info); + /* Racing with mark destruction or creation? */ + if (!fsid.val[0] && !fsid.val[1]) + return 0; + } event = fanotify_alloc_event(group, inode, mask, data, data_type, &fsid); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index df06f3da166c..8c7cbac7183c 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -108,6 +108,47 @@ void fsnotify_sb_delete(struct super_block *sb) } /* + * fsnotify_nameremove - a filename was removed from a directory + * + * This is mostly called under parent vfs inode lock so name and + * dentry->d_parent should be stable. However there are some corner cases where + * inode lock is not held. So to be on the safe side and be reselient to future + * callers and out of tree users of d_delete(), we do not assume that d_parent + * and d_name are stable and we use dget_parent() and + * take_dentry_name_snapshot() to grab stable references. + */ +void fsnotify_nameremove(struct dentry *dentry, int isdir) +{ + struct dentry *parent; + struct name_snapshot name; + __u32 mask = FS_DELETE; + + /* d_delete() of pseudo inode? (e.g. __ns_get_path() playing tricks) */ + if (IS_ROOT(dentry)) + return; + + if (isdir) + mask |= FS_ISDIR; + + parent = dget_parent(dentry); + /* Avoid unneeded take_dentry_name_snapshot() */ + if (!(d_inode(parent)->i_fsnotify_mask & FS_DELETE) && + !(dentry->d_sb->s_fsnotify_mask & FS_DELETE)) + goto out_dput; + + take_dentry_name_snapshot(&name, dentry); + + fsnotify(d_inode(parent), mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, + &name.name, 0); + + release_dentry_name_snapshot(&name); + +out_dput: + dput(parent); +} +EXPORT_SYMBOL(fsnotify_nameremove); + +/* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the @@ -179,10 +220,10 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask take_dentry_name_snapshot(&name, dentry); if (path) ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH, - name.name, 0); + &name.name, 0); else ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE, - name.name, 0); + &name.name, 0); release_dentry_name_snapshot(&name); } @@ -195,7 +236,7 @@ EXPORT_SYMBOL_GPL(__fsnotify_parent); static int send_to_group(struct inode *to_tell, __u32 mask, const void *data, int data_is, u32 cookie, - const unsigned char *file_name, + const struct qstr *file_name, struct fsnotify_iter_info *iter_info) { struct fsnotify_group *group = NULL; @@ -325,7 +366,7 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) * notification event in whatever means they feel necessary. */ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, - const unsigned char *file_name, u32 cookie) + const struct qstr *file_name, u32 cookie) { struct fsnotify_iter_info iter_info = {}; struct super_block *sb = to_tell->i_sb; diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig index b981fc0c8379..0161c74e76e2 100644 --- a/fs/notify/inotify/Kconfig +++ b/fs/notify/inotify/Kconfig @@ -1,6 +1,5 @@ config INOTIFY_USER bool "Inotify support for userspace" - select ANON_INODES select FSNOTIFY default y ---help--- diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index 74ae60305189..3f246f7b8a92 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -27,7 +27,7 @@ extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, extern int inotify_handle_event(struct fsnotify_group *group, struct inode *inode, u32 mask, const void *data, int data_type, - const unsigned char *file_name, u32 cookie, + const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); extern const struct fsnotify_ops inotify_fsnotify_ops; diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index ff30abd6a49b..7e8b131029f8 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -67,7 +67,7 @@ static int inotify_merge(struct list_head *list, int inotify_handle_event(struct fsnotify_group *group, struct inode *inode, u32 mask, const void *data, int data_type, - const unsigned char *file_name, u32 cookie, + const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); @@ -89,7 +89,7 @@ int inotify_handle_event(struct fsnotify_group *group, return 0; } if (file_name) { - len = strlen(file_name); + len = file_name->len; alloc_len += len + 1; } @@ -129,7 +129,7 @@ int inotify_handle_event(struct fsnotify_group *group, event->sync_cookie = cookie; event->name_len = len; if (len) - strcpy(event->name, file_name); + strcpy(event->name, file_name->name); ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { diff --git a/fs/notify/mark.c b/fs/notify/mark.c index d593d4269561..b251105f646f 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -239,13 +239,13 @@ static void fsnotify_drop_object(unsigned int type, void *objp) void fsnotify_put_mark(struct fsnotify_mark *mark) { - struct fsnotify_mark_connector *conn; + struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ - if (!mark->connector) { + if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; @@ -255,10 +255,9 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ - if (!refcount_dec_and_lock(&mark->refcnt, &mark->connector->lock)) + if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; - conn = mark->connector; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); @@ -266,7 +265,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) } else { __fsnotify_recalc_mask(conn); } - mark->connector = NULL; + WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); @@ -620,7 +619,12 @@ restart: /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: - mark->connector = conn; + /* + * Since connector is attached to object using cmpxchg() we are + * guaranteed that connector initialization is fully visible by anyone + * seeing mark->connector set. + */ + WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); @@ -808,6 +812,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; + WRITE_ONCE(mark->connector, NULL); } /* diff --git a/fs/nsfs.c b/fs/nsfs.c index 60702d677bd4..e3bf08c5af41 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -85,13 +85,12 @@ slow: inode->i_fop = &ns_file_operations; inode->i_private = ns; - dentry = d_alloc_pseudo(mnt->mnt_sb, &empty_name); + dentry = d_alloc_anon(mnt->mnt_sb); if (!dentry) { iput(inode); return ERR_PTR(-ENOMEM); } d_instantiate(dentry, inode); - dentry->d_flags |= DCACHE_RCUACCESS; dentry->d_fsdata = (void *)ns->ops; d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry); if (d) { @@ -106,17 +105,16 @@ slow: void *ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb, void *private_data) { - struct ns_common *ns; void *ret; -again: - ns = ns_get_cb(private_data); - if (!ns) - return ERR_PTR(-ENOENT); + do { + struct ns_common *ns = ns_get_cb(private_data); + if (!ns) + return ERR_PTR(-ENOENT); + + ret = __ns_get_path(path, ns); + } while (ret == ERR_PTR(-EAGAIN)); - ret = __ns_get_path(path, ns); - if (IS_ERR(ret) && PTR_ERR(ret) == -EAGAIN) - goto again; return ret; } @@ -155,7 +153,7 @@ int open_related_ns(struct ns_common *ns, if (fd < 0) return fd; - while (1) { + do { struct ns_common *relative; relative = get_ns(ns); @@ -165,10 +163,8 @@ int open_related_ns(struct ns_common *ns, } err = __ns_get_path(&path, relative); - if (IS_ERR(err) && PTR_ERR(err) == -EAGAIN) - continue; - break; - } + } while (err == ERR_PTR(-EAGAIN)); + if (IS_ERR(err)) { put_unused_fd(fd); return PTR_ERR(err); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index bd3221cbdd95..fb1a2b49a5da 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -332,23 +332,11 @@ struct inode *ntfs_alloc_big_inode(struct super_block *sb) return NULL; } -static void ntfs_i_callback(struct rcu_head *head) +void ntfs_free_big_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(ntfs_big_inode_cache, NTFS_I(inode)); } -void ntfs_destroy_big_inode(struct inode *inode) -{ - ntfs_inode *ni = NTFS_I(inode); - - ntfs_debug("Entering."); - BUG_ON(ni->page); - if (!atomic_dec_and_test(&ni->count)) - BUG(); - call_rcu(&inode->i_rcu, ntfs_i_callback); -} - static inline ntfs_inode *ntfs_alloc_extent_inode(void) { ntfs_inode *ni; @@ -2287,6 +2275,9 @@ void ntfs_evict_big_inode(struct inode *vi) ni->ext.base_ntfs_ino = NULL; } } + BUG_ON(ni->page); + if (!atomic_dec_and_test(&ni->count)) + BUG(); return; } diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h index b3c3469de6cb..58c8fd2948d3 100644 --- a/fs/ntfs/inode.h +++ b/fs/ntfs/inode.h @@ -278,7 +278,7 @@ extern struct inode *ntfs_index_iget(struct inode *base_vi, ntfschar *name, u32 name_len); extern struct inode *ntfs_alloc_big_inode(struct super_block *sb); -extern void ntfs_destroy_big_inode(struct inode *inode); +extern void ntfs_free_big_inode(struct inode *inode); extern void ntfs_evict_big_inode(struct inode *vi); extern void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni); diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index bb7159f697f2..887ea8b3b000 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2676,7 +2676,7 @@ static int ntfs_write_inode(struct inode *vi, struct writeback_control *wbc) */ static const struct super_operations ntfs_sops = { .alloc_inode = ntfs_alloc_big_inode, /* VFS: Allocate new inode. */ - .destroy_inode = ntfs_destroy_big_inode, /* VFS: Deallocate inode. */ + .free_inode = ntfs_free_big_inode, /* VFS: Deallocate inode. */ #ifdef NTFS_RW .write_inode = ntfs_write_inode, /* VFS: Write dirty inode to disk. */ diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index af2e7473956e..67dcee65fe50 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -81,6 +81,7 @@ static void o2quo_fence_self(void) default: WARN_ON(o2nm_single_cluster->cl_fence_method >= O2NM_FENCE_METHODS); + /* fall through */ case O2NM_FENCE_RESET: printk(KERN_ERR "*** ocfs2 is very sorry to be fencing this " "system by restarting ***\n"); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index c121abbdfc7d..85f21caaa6ec 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -69,10 +69,6 @@ #define NAMEI_RA_BLOCKS 4 #define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS) -static unsigned char ocfs2_filetype_table[] = { - DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK -}; - static int ocfs2_do_extend_dir(struct super_block *sb, handle_t *handle, struct inode *dir, @@ -1718,7 +1714,7 @@ int __ocfs2_add_entry(handle_t *handle, de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len)); de = de1; } - de->file_type = OCFS2_FT_UNKNOWN; + de->file_type = FT_UNKNOWN; if (blkno) { de->inode = cpu_to_le64(blkno); ocfs2_set_de_type(de, inode->i_mode); @@ -1803,13 +1799,9 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode, } offset += le16_to_cpu(de->rec_len); if (le64_to_cpu(de->inode)) { - unsigned char d_type = DT_UNKNOWN; - - if (de->file_type < OCFS2_FT_MAX) - d_type = ocfs2_filetype_table[de->file_type]; - if (!dir_emit(ctx, de->name, de->name_len, - le64_to_cpu(de->inode), d_type)) + le64_to_cpu(de->inode), + fs_ftype_to_dtype(de->file_type))) goto out; } ctx->pos += le16_to_cpu(de->rec_len); @@ -1900,14 +1892,10 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, break; } if (le64_to_cpu(de->inode)) { - unsigned char d_type = DT_UNKNOWN; - - if (de->file_type < OCFS2_FT_MAX) - d_type = ocfs2_filetype_table[de->file_type]; if (!dir_emit(ctx, de->name, de->name_len, le64_to_cpu(de->inode), - d_type)) { + fs_ftype_to_dtype(de->file_type))) { brelse(bh); return 0; } diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 8decbe95dcec..98885181e1fe 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -349,17 +349,11 @@ static struct inode *dlmfs_alloc_inode(struct super_block *sb) return &ip->ip_vfs_inode; } -static void dlmfs_i_callback(struct rcu_head *head) +static void dlmfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(dlmfs_inode_cache, DLMFS_I(inode)); } -static void dlmfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, dlmfs_i_callback); -} - static void dlmfs_evict_inode(struct inode *inode) { int status; @@ -605,7 +599,7 @@ static const struct inode_operations dlmfs_root_inode_operations = { static const struct super_operations dlmfs_ops = { .statfs = simple_statfs, .alloc_inode = dlmfs_alloc_inode, - .destroy_inode = dlmfs_destroy_inode, + .free_inode = dlmfs_free_inode, .evict_inode = dlmfs_evict_inode, .drop_inode = generic_delete_inode, }; diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 4bf8d5854b27..af2888d23de3 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -148,16 +148,24 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) u64 blkno; struct dentry *parent; struct inode *dir = d_inode(child); + int set; trace_ocfs2_get_parent(child, child->d_name.len, child->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno); + status = ocfs2_nfs_sync_lock(OCFS2_SB(dir->i_sb), 1); + if (status < 0) { + mlog(ML_ERROR, "getting nfs sync lock(EX) failed %d\n", status); + parent = ERR_PTR(status); + goto bail; + } + status = ocfs2_inode_lock(dir, NULL, 0); if (status < 0) { if (status != -ENOENT) mlog_errno(status); parent = ERR_PTR(status); - goto bail; + goto unlock_nfs_sync; } status = ocfs2_lookup_ino_from_name(dir, "..", 2, &blkno); @@ -166,11 +174,31 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) goto bail_unlock; } + status = ocfs2_test_inode_bit(OCFS2_SB(dir->i_sb), blkno, &set); + if (status < 0) { + if (status == -EINVAL) { + status = -ESTALE; + } else + mlog(ML_ERROR, "test inode bit failed %d\n", status); + parent = ERR_PTR(status); + goto bail_unlock; + } + + trace_ocfs2_get_dentry_test_bit(status, set); + if (!set) { + status = -ESTALE; + parent = ERR_PTR(status); + goto bail_unlock; + } + parent = d_obtain_alias(ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0)); bail_unlock: ocfs2_inode_unlock(dir, 0); +unlock_nfs_sync: + ocfs2_nfs_sync_unlock(OCFS2_SB(dir->i_sb), 1); + bail: trace_ocfs2_get_parent_end(parent); diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 7071ad0dec90..b86bf5e74348 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -392,21 +392,6 @@ static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = { #define OCFS2_HB_GLOBAL "heartbeat=global" /* - * OCFS2 directory file types. Only the low 3 bits are used. The - * other bits are reserved for now. - */ -#define OCFS2_FT_UNKNOWN 0 -#define OCFS2_FT_REG_FILE 1 -#define OCFS2_FT_DIR 2 -#define OCFS2_FT_CHRDEV 3 -#define OCFS2_FT_BLKDEV 4 -#define OCFS2_FT_FIFO 5 -#define OCFS2_FT_SOCK 6 -#define OCFS2_FT_SYMLINK 7 - -#define OCFS2_FT_MAX 8 - -/* * OCFS2_DIR_PAD defines the directory entries boundaries * * NOTE: It must be a multiple of 4 @@ -424,17 +409,6 @@ static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = { #define OCFS2_LINKS_HI_SHIFT 16 #define OCFS2_DX_ENTRIES_MAX (0xffffffffU) -#define S_SHIFT 12 -static unsigned char ocfs2_type_by_mode[S_IFMT >> S_SHIFT] = { - [S_IFREG >> S_SHIFT] = OCFS2_FT_REG_FILE, - [S_IFDIR >> S_SHIFT] = OCFS2_FT_DIR, - [S_IFCHR >> S_SHIFT] = OCFS2_FT_CHRDEV, - [S_IFBLK >> S_SHIFT] = OCFS2_FT_BLKDEV, - [S_IFIFO >> S_SHIFT] = OCFS2_FT_FIFO, - [S_IFSOCK >> S_SHIFT] = OCFS2_FT_SOCK, - [S_IFLNK >> S_SHIFT] = OCFS2_FT_SYMLINK, -}; - /* * Convenience casts @@ -1629,7 +1603,7 @@ static inline int ocfs2_sprintf_system_inode_name(char *buf, int len, static inline void ocfs2_set_de_type(struct ocfs2_dir_entry *de, umode_t mode) { - de->file_type = ocfs2_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; + de->file_type = fs_umode_to_ftype(mode); } static inline int ocfs2_gd_is_discontig(struct ocfs2_group_desc *gd) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 96ae7cedd487..8821bc7b9c72 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -134,7 +134,7 @@ static int ocfs2_get_sector(struct super_block *sb, int block, int sect_size); static struct inode *ocfs2_alloc_inode(struct super_block *sb); -static void ocfs2_destroy_inode(struct inode *inode); +static void ocfs2_free_inode(struct inode *inode); static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend); static int ocfs2_enable_quotas(struct ocfs2_super *osb); static void ocfs2_disable_quotas(struct ocfs2_super *osb); @@ -147,7 +147,7 @@ static struct dquot **ocfs2_get_dquots(struct inode *inode) static const struct super_operations ocfs2_sops = { .statfs = ocfs2_statfs, .alloc_inode = ocfs2_alloc_inode, - .destroy_inode = ocfs2_destroy_inode, + .free_inode = ocfs2_free_inode, .drop_inode = ocfs2_drop_inode, .evict_inode = ocfs2_evict_inode, .sync_fs = ocfs2_sync_fs, @@ -575,17 +575,11 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb) return &oi->vfs_inode; } -static void ocfs2_i_callback(struct rcu_head *head) +static void ocfs2_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(ocfs2_inode_cachep, OCFS2_I(inode)); } -static void ocfs2_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, ocfs2_i_callback); -} - static unsigned long long ocfs2_max_file_offset(unsigned int bbits, unsigned int cbits) { @@ -600,7 +594,6 @@ static unsigned long long ocfs2_max_file_offset(unsigned int bbits, */ #if BITS_PER_LONG == 32 -# if defined(CONFIG_LBDAF) BUILD_BUG_ON(sizeof(sector_t) != 8); /* * We might be limited by page cache size. @@ -614,15 +607,6 @@ static unsigned long long ocfs2_max_file_offset(unsigned int bbits, */ bitshift = 31; } -# else - /* - * We are limited by the size of sector_t. Use block size, as - * that's what we expose to the VFS. - */ - bytes = 1 << bbits; - trim = 1; - bitshift = 31; -# endif #endif /* diff --git a/fs/open.c b/fs/open.c index f1c2f855fd43..9c7d724a6f67 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1215,3 +1215,22 @@ int nonseekable_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(nonseekable_open); + +/* + * stream_open is used by subsystems that want stream-like file descriptors. + * Such file descriptors are not seekable and don't have notion of position + * (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL). + * Contrary to file descriptors of other regular files, .read() and .write() + * can run simultaneously. + * + * stream_open never fails and is marked to return int so that it could be + * directly used as file_operations.open . + */ +int stream_open(struct inode *inode, struct file *filp) +{ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode |= FMODE_STREAM; + return 0; +} + +EXPORT_SYMBOL(stream_open); diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 1b2d0d2fe2ee..46655e454c55 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -336,17 +336,11 @@ static struct inode *openprom_alloc_inode(struct super_block *sb) return &oi->vfs_inode; } -static void openprom_i_callback(struct rcu_head *head) +static void openprom_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(op_inode_cachep, OP_I(inode)); } -static void openprom_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, openprom_i_callback); -} - static struct inode *openprom_iget(struct super_block *sb, ino_t ino) { struct inode *inode; @@ -375,7 +369,7 @@ static int openprom_remount(struct super_block *sb, int *flags, char *data) static const struct super_operations openprom_sops = { .alloc_inode = openprom_alloc_inode, - .destroy_inode = openprom_destroy_inode, + .free_inode = openprom_free_inode, .statfs = simple_statfs, .remount_fs = openprom_remount, }; diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index 72d2ff17d27b..eced272a3c57 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -142,7 +142,7 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) rc = __orangefs_set_acl(inode, acl, type); } else { iattr.ia_valid = ATTR_MODE; - rc = orangefs_inode_setattr(inode, &iattr); + rc = __orangefs_setattr(inode, &iattr); } return rc; @@ -185,7 +185,7 @@ int orangefs_init_acl(struct inode *inode, struct inode *dir) inode->i_mode = mode; iattr.ia_mode = mode; iattr.ia_valid |= ATTR_MODE; - orangefs_inode_setattr(inode, &iattr); + __orangefs_setattr(inode, &iattr); } return error; diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index b094d3d79354..a35c17017210 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * (C) 2001 Clemson University and The University of Chicago + * Copyright 2018 Omnibond Systems, L.L.C. * * See COPYING in top-level directory. */ @@ -44,15 +45,16 @@ static int flush_racache(struct inode *inode) /* * Post and wait for the I/O upcall to finish */ -static ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode, - loff_t *offset, struct iov_iter *iter, - size_t total_size, loff_t readahead_size) +ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode, + loff_t *offset, struct iov_iter *iter, size_t total_size, + loff_t readahead_size, struct orangefs_write_range *wr, int *index_return) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); struct orangefs_khandle *handle = &orangefs_inode->refn.khandle; struct orangefs_kernel_op_s *new_op = NULL; int buffer_index = -1; ssize_t ret; + size_t copy_amount; new_op = op_alloc(ORANGEFS_VFS_OP_FILE_IO); if (!new_op) @@ -84,6 +86,10 @@ populate_shared_memory: new_op->upcall.req.io.buf_index = buffer_index; new_op->upcall.req.io.count = total_size; new_op->upcall.req.io.offset = *offset; + if (type == ORANGEFS_IO_WRITE && wr) { + new_op->upcall.uid = from_kuid(&init_user_ns, wr->uid); + new_op->upcall.gid = from_kgid(&init_user_ns, wr->gid); + } gossip_debug(GOSSIP_FILE_DEBUG, "%s(%pU): offset: %llu total_size: %zd\n", @@ -168,7 +174,10 @@ populate_shared_memory: * trigger the write. */ case OP_VFS_STATE_INPROGR: - ret = total_size; + if (type == ORANGEFS_IO_READ) + ret = -EINTR; + else + ret = total_size; break; default: gossip_err("%s: unexpected op state :%d:.\n", @@ -204,8 +213,25 @@ populate_shared_memory: * can futher be kernel-space or user-space addresses. * or it can pointers to struct page's */ + + /* + * When reading, readahead_size will only be zero when + * we're doing O_DIRECT, otherwise we got here from + * orangefs_readpage. + * + * If we got here from orangefs_readpage we want to + * copy either a page or the whole file into the io + * vector, whichever is smaller. + */ + if (readahead_size) + copy_amount = + min(new_op->downcall.resp.io.amt_complete, + (__s64)PAGE_SIZE); + else + copy_amount = new_op->downcall.resp.io.amt_complete; + ret = orangefs_bufmap_copy_to_iovec(iter, buffer_index, - new_op->downcall.resp.io.amt_complete); + copy_amount); if (ret < 0) { gossip_err("%s: Failed to copy-out buffers. Please make sure that the pvfs2-client is running (%ld)\n", __func__, (long)ret); @@ -223,246 +249,112 @@ populate_shared_memory: out: if (buffer_index >= 0) { - orangefs_bufmap_put(buffer_index); - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU): PUT buffer_index %d\n", - __func__, handle, buffer_index); + if ((readahead_size) && (type == ORANGEFS_IO_READ)) { + /* readpage */ + *index_return = buffer_index; + gossip_debug(GOSSIP_FILE_DEBUG, + "%s: hold on to buffer_index :%d:\n", + __func__, buffer_index); + } else { + /* O_DIRECT */ + orangefs_bufmap_put(buffer_index); + gossip_debug(GOSSIP_FILE_DEBUG, + "%s(%pU): PUT buffer_index %d\n", + __func__, handle, buffer_index); + } buffer_index = -1; } op_release(new_op); return ret; } -/* - * Common entry point for read/write/readv/writev - * This function will dispatch it to either the direct I/O - * or buffered I/O path depending on the mount options and/or - * augmented/extended metadata attached to the file. - * Note: File extended attributes override any mount options. - */ -static ssize_t do_readv_writev(enum ORANGEFS_io_type type, struct file *file, - loff_t *offset, struct iov_iter *iter) +int orangefs_revalidate_mapping(struct inode *inode) { - struct inode *inode = file->f_mapping->host; struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); - struct orangefs_khandle *handle = &orangefs_inode->refn.khandle; - size_t count = iov_iter_count(iter); - ssize_t total_count = 0; - ssize_t ret = -EINVAL; - - gossip_debug(GOSSIP_FILE_DEBUG, - "%s-BEGIN(%pU): count(%d) after estimate_max_iovecs.\n", - __func__, - handle, - (int)count); - - if (type == ORANGEFS_IO_WRITE) { - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU): proceeding with offset : %llu, " - "size %d\n", - __func__, - handle, - llu(*offset), - (int)count); - } + struct address_space *mapping = inode->i_mapping; + unsigned long *bitlock = &orangefs_inode->bitlock; + int ret; - if (count == 0) { - ret = 0; - goto out; + while (1) { + ret = wait_on_bit(bitlock, 1, TASK_KILLABLE); + if (ret) + return ret; + spin_lock(&inode->i_lock); + if (test_bit(1, bitlock)) { + spin_unlock(&inode->i_lock); + continue; + } + if (!time_before(jiffies, orangefs_inode->mapping_time)) + break; + spin_unlock(&inode->i_lock); + return 0; } - while (iov_iter_count(iter)) { - size_t each_count = iov_iter_count(iter); - size_t amt_complete; - - /* how much to transfer in this loop iteration */ - if (each_count > orangefs_bufmap_size_query()) - each_count = orangefs_bufmap_size_query(); + set_bit(1, bitlock); + smp_wmb(); + spin_unlock(&inode->i_lock); - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU): size of each_count(%d)\n", - __func__, - handle, - (int)each_count); - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU): BEFORE wait_for_io: offset is %d\n", - __func__, - handle, - (int)*offset); - - ret = wait_for_direct_io(type, inode, offset, iter, - each_count, 0); - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU): return from wait_for_io:%d\n", - __func__, - handle, - (int)ret); + unmap_mapping_range(mapping, 0, 0, 0); + ret = filemap_write_and_wait(mapping); + if (!ret) + ret = invalidate_inode_pages2(mapping); - if (ret < 0) - goto out; - - *offset += ret; - total_count += ret; - amt_complete = ret; + orangefs_inode->mapping_time = jiffies + + orangefs_cache_timeout_msecs*HZ/1000; - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU): AFTER wait_for_io: offset is %d\n", - __func__, - handle, - (int)*offset); - - /* - * if we got a short I/O operations, - * fall out and return what we got so far - */ - if (amt_complete < each_count) - break; - } /*end while */ - -out: - if (total_count > 0) - ret = total_count; - if (ret > 0) { - if (type == ORANGEFS_IO_READ) { - file_accessed(file); - } else { - file_update_time(file); - /* - * Must invalidate to ensure write loop doesn't - * prevent kernel from reading updated - * attribute. Size probably changed because of - * the write, and other clients could update - * any other attribute. - */ - orangefs_inode->getattr_time = jiffies - 1; - } - } - - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU): Value(%d) returned.\n", - __func__, - handle, - (int)ret); + clear_bit(1, bitlock); + smp_mb__after_atomic(); + wake_up_bit(bitlock, 1); return ret; } -/* - * Read data from a specified offset in a file (referenced by inode). - * Data may be placed either in a user or kernel buffer. - */ -ssize_t orangefs_inode_read(struct inode *inode, - struct iov_iter *iter, - loff_t *offset, - loff_t readahead_size) +static ssize_t orangefs_file_read_iter(struct kiocb *iocb, + struct iov_iter *iter) { - struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); - size_t count = iov_iter_count(iter); - size_t bufmap_size; - ssize_t ret = -EINVAL; + int ret; + struct orangefs_read_options *ro; orangefs_stats.reads++; - bufmap_size = orangefs_bufmap_size_query(); - if (count > bufmap_size) { - gossip_debug(GOSSIP_FILE_DEBUG, - "%s: count is too large (%zd/%zd)!\n", - __func__, count, bufmap_size); - return -EINVAL; + /* + * 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; } - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU) %zd@%llu\n", - __func__, - &orangefs_inode->refn.khandle, - count, - llu(*offset)); - - ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, offset, iter, - count, readahead_size); - if (ret > 0) - *offset += ret; - - gossip_debug(GOSSIP_FILE_DEBUG, - "%s(%pU): Value(%zd) returned.\n", - __func__, - &orangefs_inode->refn.khandle, - ret); + down_read(&file_inode(iocb->ki_filp)->i_rwsem); + ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp)); + if (ret) + goto out; + ret = generic_file_read_iter(iocb, iter); +out: + up_read(&file_inode(iocb->ki_filp)->i_rwsem); return ret; } -static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) +static ssize_t orangefs_file_write_iter(struct kiocb *iocb, + struct iov_iter *iter) { - struct file *file = iocb->ki_filp; - loff_t pos = iocb->ki_pos; - ssize_t rc = 0; - - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n"); - - orangefs_stats.reads++; - - rc = do_readv_writev(ORANGEFS_IO_READ, file, &pos, iter); - iocb->ki_pos = pos; - - return rc; -} - -static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *iter) -{ - struct file *file = iocb->ki_filp; - loff_t pos; - ssize_t rc; - - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n"); - - inode_lock(file->f_mapping->host); - - /* Make sure generic_write_checks sees an up to date inode size. */ - if (file->f_flags & O_APPEND) { - rc = orangefs_inode_getattr(file->f_mapping->host, 0, 1, - STATX_SIZE); - if (rc == -ESTALE) - rc = -EIO; - if (rc) { - gossip_err("%s: orangefs_inode_getattr failed, " - "rc:%zd:.\n", __func__, rc); - goto out; - } - } - - rc = generic_write_checks(iocb, iter); - - if (rc <= 0) { - gossip_err("%s: generic_write_checks failed, rc:%zd:.\n", - __func__, rc); - goto out; - } - - /* - * if we are appending, generic_write_checks would have updated - * pos to the end of the file, so we will wait till now to set - * pos... - */ - pos = iocb->ki_pos; - - rc = do_readv_writev(ORANGEFS_IO_WRITE, - file, - &pos, - iter); - if (rc < 0) { - gossip_err("%s: do_readv_writev failed, rc:%zd:.\n", - __func__, rc); - goto out; - } - - iocb->ki_pos = pos; + int ret; orangefs_stats.writes++; -out: + if (iocb->ki_pos > i_size_read(file_inode(iocb->ki_filp))) { + ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp)); + if (ret) + return ret; + } - inode_unlock(file->f_mapping->host); - return rc; + ret = generic_file_write_iter(iocb, iter); + return ret; } /* @@ -528,14 +420,13 @@ static vm_fault_t orangefs_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; int ret; - - ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1, - STATX_SIZE); + ret = orangefs_inode_getattr(file->f_mapping->host, + ORANGEFS_GETATTR_SIZE); if (ret == -ESTALE) ret = -EIO; if (ret) { - gossip_err("%s: orangefs_inode_getattr failed, ret:%d:.\n", - __func__, ret); + gossip_err("%s: orangefs_inode_getattr failed, " + "ret:%d:.\n", __func__, ret); return VM_FAULT_SIGBUS; } return filemap_fault(vmf); @@ -544,7 +435,7 @@ static vm_fault_t orangefs_fault(struct vm_fault *vmf) static const struct vm_operations_struct orangefs_file_vm_ops = { .fault = orangefs_fault, .map_pages = filemap_map_pages, - .page_mkwrite = filemap_page_mkwrite, + .page_mkwrite = orangefs_page_mkwrite, }; /* @@ -552,15 +443,18 @@ static const struct vm_operations_struct orangefs_file_vm_ops = { */ static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma) { + int ret; + + ret = orangefs_revalidate_mapping(file_inode(file)); + if (ret) + return ret; + gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_mmap: called on %s\n", (file ? (char *)file->f_path.dentry->d_name.name : (char *)"Unknown")); - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) - return -EINVAL; - /* set the sequential readahead hint */ vma->vm_flags |= VM_SEQ_READ; vma->vm_flags &= ~VM_RAND_READ; @@ -600,8 +494,7 @@ static int orangefs_file_release(struct inode *inode, struct file *file) gossip_debug(GOSSIP_INODE_DEBUG, "flush_racache finished\n"); } - truncate_inode_pages(file_inode(file)->i_mapping, - 0); + } return 0; } @@ -619,6 +512,11 @@ static int orangefs_fsync(struct file *file, ORANGEFS_I(file_inode(file)); struct orangefs_kernel_op_s *new_op = NULL; + ret = filemap_write_and_wait_range(file_inode(file)->i_mapping, + start, end); + if (ret < 0) + return ret; + new_op = op_alloc(ORANGEFS_VFS_OP_FSYNC); if (!new_op) return -ENOMEM; @@ -656,8 +554,8 @@ static loff_t orangefs_file_llseek(struct file *file, loff_t offset, int origin) * NOTE: We are only interested in file size here, * so we set mask accordingly. */ - ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1, - STATX_SIZE); + ret = orangefs_inode_getattr(file->f_mapping->host, + ORANGEFS_GETATTR_SIZE); if (ret == -ESTALE) ret = -EIO; if (ret) { @@ -700,6 +598,42 @@ 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) +{ + /* + * This is vfs_fsync_range(file, 0, LLONG_MAX, 0) without the + * service_operation in orangefs_fsync. + * + * Do not send fsync to OrangeFS server on a close. Do send fsync + * on an explicit fsync call. This duplicates historical OrangeFS + * behavior. + */ + 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; + spin_unlock(&inode->i_lock); + mark_inode_dirty_sync(inode); + } + + r = filemap_write_and_wait_range(file->f_mapping, 0, LLONG_MAX); + if (r > 0) + return 0; + else + return r; +} + /** ORANGEFS implementation of VFS file operations */ const struct file_operations orangefs_file_operations = { .llseek = orangefs_file_llseek, @@ -708,7 +642,8 @@ const struct file_operations orangefs_file_operations = { .lock = orangefs_lock, .unlocked_ioctl = orangefs_ioctl, .mmap = orangefs_file_mmap, - .open = generic_file_open, + .open = orangefs_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 c3334eca18c7..0c337d8bdaab 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * (C) 2001 Clemson University and The University of Chicago + * Copyright 2018 Omnibond Systems, L.L.C. * * See COPYING in top-level directory. */ @@ -14,40 +15,312 @@ #include "orangefs-kernel.h" #include "orangefs-bufmap.h" -static int read_one_page(struct page *page) +static int orangefs_writepage_locked(struct page *page, + struct writeback_control *wbc) { - int ret; - int max_block; - ssize_t bytes_read = 0; struct inode *inode = page->mapping->host; - const __u32 blocksize = PAGE_SIZE; - const __u32 blockbits = PAGE_SHIFT; - struct iov_iter to; - struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE}; + struct orangefs_write_range *wr = NULL; + struct iov_iter iter; + struct bio_vec bv; + size_t len, wlen; + ssize_t ret; + loff_t off; + + set_page_writeback(page); + + len = i_size_read(inode); + if (PagePrivate(page)) { + wr = (struct orangefs_write_range *)page_private(page); + WARN_ON(wr->pos >= len); + off = wr->pos; + if (off + wr->len > len) + wlen = len - off; + else + wlen = wr->len; + } else { + WARN_ON(1); + off = page_offset(page); + if (off + PAGE_SIZE > len) + wlen = len - off; + else + wlen = PAGE_SIZE; + } + /* Should've been handled in orangefs_invalidatepage. */ + WARN_ON(off == len || off + wlen > len); + + bv.bv_page = page; + bv.bv_len = wlen; + bv.bv_offset = off % PAGE_SIZE; + WARN_ON(wlen == 0); + iov_iter_bvec(&iter, WRITE, &bv, 1, wlen); + + ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, wlen, + len, wr, NULL); + if (ret < 0) { + SetPageError(page); + mapping_set_error(page->mapping, ret); + } else { + ret = 0; + } + if (wr) { + kfree(wr); + set_page_private(page, 0); + ClearPagePrivate(page); + put_page(page); + } + return ret; +} + +static int orangefs_writepage(struct page *page, struct writeback_control *wbc) +{ + int ret; + ret = orangefs_writepage_locked(page, wbc); + unlock_page(page); + end_page_writeback(page); + return ret; +} - iov_iter_bvec(&to, READ, &bv, 1, PAGE_SIZE); +struct orangefs_writepages { + loff_t off; + size_t len; + kuid_t uid; + kgid_t gid; + int maxpages; + int npages; + struct page **pages; + struct bio_vec *bv; +}; - gossip_debug(GOSSIP_INODE_DEBUG, - "orangefs_readpage called with page %p\n", - page); +static int orangefs_writepages_work(struct orangefs_writepages *ow, + struct writeback_control *wbc) +{ + struct inode *inode = ow->pages[0]->mapping->host; + struct orangefs_write_range *wrp, wr; + struct iov_iter iter; + ssize_t ret; + size_t len; + loff_t off; + int i; + + len = i_size_read(inode); + + for (i = 0; i < ow->npages; i++) { + set_page_writeback(ow->pages[i]); + ow->bv[i].bv_page = ow->pages[i]; + ow->bv[i].bv_len = min(page_offset(ow->pages[i]) + PAGE_SIZE, + ow->off + ow->len) - + max(ow->off, page_offset(ow->pages[i])); + if (i == 0) + ow->bv[i].bv_offset = ow->off - + page_offset(ow->pages[i]); + else + ow->bv[i].bv_offset = 0; + } + iov_iter_bvec(&iter, WRITE, ow->bv, ow->npages, ow->len); + + WARN_ON(ow->off >= len); + if (ow->off + ow->len > len) + ow->len = len - ow->off; + + off = ow->off; + wr.uid = ow->uid; + wr.gid = ow->gid; + ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, ow->len, + 0, &wr, NULL); + if (ret < 0) { + for (i = 0; i < ow->npages; i++) { + SetPageError(ow->pages[i]); + mapping_set_error(ow->pages[i]->mapping, ret); + if (PagePrivate(ow->pages[i])) { + wrp = (struct orangefs_write_range *) + page_private(ow->pages[i]); + ClearPagePrivate(ow->pages[i]); + put_page(ow->pages[i]); + kfree(wrp); + } + end_page_writeback(ow->pages[i]); + unlock_page(ow->pages[i]); + } + } else { + ret = 0; + for (i = 0; i < ow->npages; i++) { + if (PagePrivate(ow->pages[i])) { + wrp = (struct orangefs_write_range *) + page_private(ow->pages[i]); + ClearPagePrivate(ow->pages[i]); + put_page(ow->pages[i]); + kfree(wrp); + } + end_page_writeback(ow->pages[i]); + unlock_page(ow->pages[i]); + } + } + return ret; +} + +static int orangefs_writepages_callback(struct page *page, + struct writeback_control *wbc, void *data) +{ + struct orangefs_writepages *ow = data; + struct orangefs_write_range *wr; + int ret; + + if (!PagePrivate(page)) { + unlock_page(page); + /* It's not private so there's nothing to write, right? */ + printk("writepages_callback not private!\n"); + BUG(); + return 0; + } + wr = (struct orangefs_write_range *)page_private(page); + + ret = -1; + if (ow->npages == 0) { + ow->off = wr->pos; + ow->len = wr->len; + ow->uid = wr->uid; + ow->gid = wr->gid; + ow->pages[ow->npages++] = page; + ret = 0; + goto done; + } + if (!uid_eq(ow->uid, wr->uid) || !gid_eq(ow->gid, wr->gid)) { + orangefs_writepages_work(ow, wbc); + ow->npages = 0; + ret = -1; + goto done; + } + if (ow->off + ow->len == wr->pos) { + ow->len += wr->len; + ow->pages[ow->npages++] = page; + ret = 0; + goto done; + } +done: + if (ret == -1) { + if (ow->npages) { + orangefs_writepages_work(ow, wbc); + ow->npages = 0; + } + ret = orangefs_writepage_locked(page, wbc); + mapping_set_error(page->mapping, ret); + unlock_page(page); + end_page_writeback(page); + } else { + if (ow->npages == ow->maxpages) { + orangefs_writepages_work(ow, wbc); + ow->npages = 0; + } + } + return ret; +} + +static int orangefs_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct orangefs_writepages *ow; + struct blk_plug plug; + int ret; + ow = kzalloc(sizeof(struct orangefs_writepages), GFP_KERNEL); + if (!ow) + return -ENOMEM; + ow->maxpages = orangefs_bufmap_size_query()/PAGE_SIZE; + ow->pages = kcalloc(ow->maxpages, sizeof(struct page *), GFP_KERNEL); + if (!ow->pages) { + kfree(ow); + return -ENOMEM; + } + ow->bv = kcalloc(ow->maxpages, sizeof(struct bio_vec), GFP_KERNEL); + if (!ow->bv) { + kfree(ow->pages); + kfree(ow); + return -ENOMEM; + } + blk_start_plug(&plug); + ret = write_cache_pages(mapping, wbc, orangefs_writepages_callback, ow); + if (ow->npages) + ret = orangefs_writepages_work(ow, wbc); + blk_finish_plug(&plug); + kfree(ow->pages); + kfree(ow->bv); + kfree(ow); + return ret; +} - max_block = ((inode->i_size / blocksize) + 1); +static int orangefs_launder_page(struct page *); - if (page->index < max_block) { - loff_t blockptr_offset = (((loff_t) page->index) << blockbits); +static int orangefs_readpage(struct file *file, struct page *page) +{ + struct inode *inode = page->mapping->host; + struct iov_iter iter; + struct bio_vec bv; + ssize_t ret; + loff_t off; /* offset into this 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; - bytes_read = orangefs_inode_read(inode, - &to, - &blockptr_offset, - inode->i_size); + /* + * 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. + */ + 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; + + if (PageDirty(page)) + orangefs_launder_page(page); + + off = page_offset(page); + index = off >> PAGE_SHIFT; + bv.bv_page = page; + bv.bv_len = PAGE_SIZE; + bv.bv_offset = 0; + iov_iter_bvec(&iter, READ, &bv, 1, PAGE_SIZE); + + ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, &off, &iter, + read_size, inode->i_size, NULL, &buffer_index); + remaining = ret; /* this will only zero remaining unread portions of the page data */ - iov_iter_zero(~0U, &to); + iov_iter_zero(~0U, &iter); /* takes care of potential aliasing */ flush_dcache_page(page); - if (bytes_read < 0) { - ret = bytes_read; + if (ret < 0) { SetPageError(page); + unlock_page(page); + goto out; } else { SetPageUptodate(page); if (PageError(page)) @@ -56,96 +329,469 @@ static int read_one_page(struct page *page) } /* unlock the page after the ->readpage() routine completes */ unlock_page(page); + + if (remaining > PAGE_SIZE) { + slot_index = 0; + while ((remaining - PAGE_SIZE) >= PAGE_SIZE) { + remaining -= PAGE_SIZE; + /* + * It is an optimization to try and fill more than one + * page... by now we've already gotten the single + * page we were after, if stuff doesn't seem to + * be going our way at this point just return + * and hope for the best. + * + * If we look for pages and they're already there is + * one reason to give up, and if they're not there + * and we can't create them is another reason. + */ + + index++; + slot_index++; + next_page = find_get_page(inode->i_mapping, index); + if (next_page) { + gossip_debug(GOSSIP_FILE_DEBUG, + "%s: found next page, quitting\n", + __func__); + put_page(next_page); + goto out; + } + next_page = find_or_create_page(inode->i_mapping, + index, + GFP_KERNEL); + /* + * I've never hit this, leave it as a printk for + * now so it will be obvious. + */ + if (!next_page) { + printk("%s: can't create next page, quitting\n", + __func__); + goto out; + } + kaddr = kmap_atomic(next_page); + orangefs_bufmap_page_fill(kaddr, + buffer_index, + slot_index); + kunmap_atomic(kaddr); + SetPageUptodate(next_page); + unlock_page(next_page); + put_page(next_page); + } + } + +out: + if (buffer_index != -1) + orangefs_bufmap_put(buffer_index); return ret; } -static int orangefs_readpage(struct file *file, struct page *page) +static int orangefs_write_begin(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, struct page **pagep, + void **fsdata) { - return read_one_page(page); + struct orangefs_write_range *wr; + struct page *page; + pgoff_t index; + int ret; + + index = pos >> PAGE_SHIFT; + + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) + return -ENOMEM; + + *pagep = page; + + if (PageDirty(page) && !PagePrivate(page)) { + /* + * Should be impossible. If it happens, launder the page + * since we don't know what's dirty. This will WARN in + * orangefs_writepage_locked. + */ + ret = orangefs_launder_page(page); + if (ret) + return ret; + } + if (PagePrivate(page)) { + struct orangefs_write_range *wr; + wr = (struct orangefs_write_range *)page_private(page); + if (wr->pos + wr->len == pos && + uid_eq(wr->uid, current_fsuid()) && + gid_eq(wr->gid, current_fsgid())) { + wr->len += len; + goto okay; + } else { + ret = orangefs_launder_page(page); + if (ret) + return ret; + } + } + + wr = kmalloc(sizeof *wr, GFP_KERNEL); + if (!wr) + return -ENOMEM; + + wr->pos = pos; + wr->len = len; + wr->uid = current_fsuid(); + wr->gid = current_fsgid(); + SetPagePrivate(page); + set_page_private(page, (unsigned long)wr); + get_page(page); +okay: + return 0; } -static int orangefs_readpages(struct file *file, - struct address_space *mapping, - struct list_head *pages, - unsigned nr_pages) +static int orangefs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { - int page_idx; - int ret; + struct inode *inode = page->mapping->host; + loff_t last_pos = pos + copied; - gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpages called\n"); - - for (page_idx = 0; page_idx < nr_pages; page_idx++) { - struct page *page; - - page = lru_to_page(pages); - list_del(&page->lru); - if (!add_to_page_cache(page, - mapping, - page->index, - readahead_gfp_mask(mapping))) { - ret = read_one_page(page); - gossip_debug(GOSSIP_INODE_DEBUG, - "failure adding page to cache, read_one_page returned: %d\n", - ret); - } else { - put_page(page); - } - } - BUG_ON(!list_empty(pages)); - return 0; + /* + * No need to use i_size_read() here, the i_size + * cannot change under us because we hold the i_mutex. + */ + if (last_pos > inode->i_size) + i_size_write(inode, last_pos); + + /* zero the stale part of the page if we did a short copy */ + if (!PageUptodate(page)) { + unsigned from = pos & (PAGE_SIZE - 1); + if (copied < len) { + zero_user(page, from + copied, len - copied); + } + /* Set fully written pages uptodate. */ + if (pos == page_offset(page) && + (len == PAGE_SIZE || pos + len == inode->i_size)) { + zero_user_segment(page, from + copied, PAGE_SIZE); + SetPageUptodate(page); + } + } + + set_page_dirty(page); + unlock_page(page); + put_page(page); + + mark_inode_dirty_sync(file_inode(file)); + return copied; } static void orangefs_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { - gossip_debug(GOSSIP_INODE_DEBUG, - "orangefs_invalidatepage called on page %p " - "(offset is %u)\n", - page, - offset); + struct orangefs_write_range *wr; + wr = (struct orangefs_write_range *)page_private(page); + + if (offset == 0 && length == PAGE_SIZE) { + kfree((struct orangefs_write_range *)page_private(page)); + set_page_private(page, 0); + ClearPagePrivate(page); + put_page(page); + return; + /* write range entirely within invalidate range (or equal) */ + } else if (page_offset(page) + offset <= wr->pos && + wr->pos + wr->len <= page_offset(page) + offset + length) { + kfree((struct orangefs_write_range *)page_private(page)); + set_page_private(page, 0); + ClearPagePrivate(page); + put_page(page); + /* XXX is this right? only caller in fs */ + cancel_dirty_page(page); + return; + /* invalidate range chops off end of write range */ + } else if (wr->pos < page_offset(page) + offset && + wr->pos + wr->len <= page_offset(page) + offset + length && + page_offset(page) + offset < wr->pos + wr->len) { + size_t x; + x = wr->pos + wr->len - (page_offset(page) + offset); + WARN_ON(x > wr->len); + wr->len -= x; + wr->uid = current_fsuid(); + wr->gid = current_fsgid(); + /* invalidate range chops off beginning of write range */ + } else if (page_offset(page) + offset <= wr->pos && + page_offset(page) + offset + length < wr->pos + wr->len && + wr->pos < page_offset(page) + offset + length) { + size_t x; + x = page_offset(page) + offset + length - wr->pos; + WARN_ON(x > wr->len); + wr->pos += x; + wr->len -= x; + wr->uid = current_fsuid(); + wr->gid = current_fsgid(); + /* invalidate range entirely within write range (punch hole) */ + } else if (wr->pos < page_offset(page) + offset && + page_offset(page) + offset + length < wr->pos + wr->len) { + /* XXX what do we do here... should not WARN_ON */ + WARN_ON(1); + /* punch hole */ + /* + * should we just ignore this and write it out anyway? + * it hardly makes sense + */ + return; + /* non-overlapping ranges */ + } else { + /* WARN if they do overlap */ + if (!((page_offset(page) + offset + length <= wr->pos) ^ + (wr->pos + wr->len <= page_offset(page) + offset))) { + WARN_ON(1); + printk("invalidate range offset %llu length %u\n", + page_offset(page) + offset, length); + printk("write range offset %llu length %zu\n", + wr->pos, wr->len); + } + return; + } - ClearPageUptodate(page); - ClearPageMappedToDisk(page); - return; + /* + * Above there are returns where wr is freed or where we WARN. + * Thus the following runs if wr was modified above. + */ + orangefs_launder_page(page); } static int orangefs_releasepage(struct page *page, gfp_t foo) { - gossip_debug(GOSSIP_INODE_DEBUG, - "orangefs_releasepage called on page %p\n", - page); - return 0; + return !PagePrivate(page); } -/* - * Having a direct_IO entry point in the address_space_operations - * struct causes the kernel to allows us to use O_DIRECT on - * open. Nothing will ever call this thing, but in the future we - * will need to be able to use O_DIRECT on open in order to support - * AIO. Modeled after NFS, they do this too. - */ +static void orangefs_freepage(struct page *page) +{ + if (PagePrivate(page)) { + kfree((struct orangefs_write_range *)page_private(page)); + set_page_private(page, 0); + ClearPagePrivate(page); + put_page(page); + } +} + +static int orangefs_launder_page(struct page *page) +{ + int r = 0; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + }; + wait_on_page_writeback(page); + if (clear_page_dirty_for_io(page)) { + r = orangefs_writepage_locked(page, &wbc); + end_page_writeback(page); + } + return r; +} static ssize_t orangefs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { - gossip_debug(GOSSIP_INODE_DEBUG, - "orangefs_direct_IO: %pD\n", - iocb->ki_filp); + /* + * Comment from original do_readv_writev: + * Common entry point for read/write/readv/writev + * This function will dispatch it to either the direct I/O + * or buffered I/O path depending on the mount options and/or + * augmented/extended metadata attached to the file. + * Note: File extended attributes override any mount options. + */ + struct file *file = iocb->ki_filp; + loff_t pos = iocb->ki_pos; + enum ORANGEFS_io_type type = iov_iter_rw(iter) == WRITE ? + ORANGEFS_IO_WRITE : ORANGEFS_IO_READ; + loff_t *offset = &pos; + struct inode *inode = file->f_mapping->host; + struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); + struct orangefs_khandle *handle = &orangefs_inode->refn.khandle; + size_t count = iov_iter_count(iter); + ssize_t total_count = 0; + ssize_t ret = -EINVAL; + int i = 0; + + gossip_debug(GOSSIP_FILE_DEBUG, + "%s-BEGIN(%pU): count(%d) after estimate_max_iovecs.\n", + __func__, + handle, + (int)count); + + if (type == ORANGEFS_IO_WRITE) { + gossip_debug(GOSSIP_FILE_DEBUG, + "%s(%pU): proceeding with offset : %llu, " + "size %d\n", + __func__, + handle, + llu(*offset), + (int)count); + } + + if (count == 0) { + ret = 0; + goto out; + } - return -EINVAL; + while (iov_iter_count(iter)) { + size_t each_count = iov_iter_count(iter); + size_t amt_complete; + i++; + + /* how much to transfer in this loop iteration */ + if (each_count > orangefs_bufmap_size_query()) + each_count = orangefs_bufmap_size_query(); + + gossip_debug(GOSSIP_FILE_DEBUG, + "%s(%pU): size of each_count(%d)\n", + __func__, + handle, + (int)each_count); + gossip_debug(GOSSIP_FILE_DEBUG, + "%s(%pU): BEFORE wait_for_io: offset is %d\n", + __func__, + handle, + (int)*offset); + + ret = wait_for_direct_io(type, inode, offset, iter, + each_count, 0, NULL, NULL); + gossip_debug(GOSSIP_FILE_DEBUG, + "%s(%pU): return from wait_for_io:%d\n", + __func__, + handle, + (int)ret); + + if (ret < 0) + goto out; + + *offset += ret; + total_count += ret; + amt_complete = ret; + + gossip_debug(GOSSIP_FILE_DEBUG, + "%s(%pU): AFTER wait_for_io: offset is %d\n", + __func__, + handle, + (int)*offset); + + /* + * if we got a short I/O operations, + * fall out and return what we got so far + */ + if (amt_complete < each_count) + break; + } /*end while */ + +out: + if (total_count > 0) + ret = total_count; + if (ret > 0) { + if (type == ORANGEFS_IO_READ) { + file_accessed(file); + } else { + file_update_time(file); + if (*offset > i_size_read(inode)) + i_size_write(inode, *offset); + } + } + + gossip_debug(GOSSIP_FILE_DEBUG, + "%s(%pU): Value(%d) returned.\n", + __func__, + handle, + (int)ret); + + return ret; } /** ORANGEFS2 implementation of address space operations */ static const struct address_space_operations orangefs_address_operations = { + .writepage = orangefs_writepage, .readpage = orangefs_readpage, - .readpages = orangefs_readpages, + .writepages = orangefs_writepages, + .set_page_dirty = __set_page_dirty_nobuffers, + .write_begin = orangefs_write_begin, + .write_end = orangefs_write_end, .invalidatepage = orangefs_invalidatepage, .releasepage = orangefs_releasepage, + .freepage = orangefs_freepage, + .launder_page = orangefs_launder_page, .direct_IO = orangefs_direct_IO, }; +vm_fault_t orangefs_page_mkwrite(struct vm_fault *vmf) +{ + struct page *page = vmf->page; + struct inode *inode = file_inode(vmf->vma->vm_file); + struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); + unsigned long *bitlock = &orangefs_inode->bitlock; + vm_fault_t ret; + struct orangefs_write_range *wr; + + sb_start_pagefault(inode->i_sb); + + if (wait_on_bit(bitlock, 1, TASK_KILLABLE)) { + ret = VM_FAULT_RETRY; + goto out; + } + + lock_page(page); + if (PageDirty(page) && !PagePrivate(page)) { + /* + * Should be impossible. If it happens, launder the page + * since we don't know what's dirty. This will WARN in + * orangefs_writepage_locked. + */ + if (orangefs_launder_page(page)) { + ret = VM_FAULT_LOCKED|VM_FAULT_RETRY; + goto out; + } + } + if (PagePrivate(page)) { + wr = (struct orangefs_write_range *)page_private(page); + if (uid_eq(wr->uid, current_fsuid()) && + gid_eq(wr->gid, current_fsgid())) { + wr->pos = page_offset(page); + wr->len = PAGE_SIZE; + goto okay; + } else { + if (orangefs_launder_page(page)) { + ret = VM_FAULT_LOCKED|VM_FAULT_RETRY; + goto out; + } + } + } + wr = kmalloc(sizeof *wr, GFP_KERNEL); + if (!wr) { + ret = VM_FAULT_LOCKED|VM_FAULT_RETRY; + goto out; + } + wr->pos = page_offset(page); + wr->len = PAGE_SIZE; + wr->uid = current_fsuid(); + wr->gid = current_fsgid(); + SetPagePrivate(page); + set_page_private(page, (unsigned long)wr); + get_page(page); +okay: + + file_update_time(vmf->vma->vm_file); + if (page->mapping != inode->i_mapping) { + unlock_page(page); + ret = VM_FAULT_LOCKED|VM_FAULT_NOPAGE; + goto out; + } + + /* + * We mark the page dirty already here so that when freeze is in + * progress, we are guaranteed that writeback during freezing will + * see the dirty page and writeprotect it again. + */ + set_page_dirty(page); + wait_for_stable_page(page); + ret = VM_FAULT_LOCKED; +out: + sb_end_pagefault(inode->i_sb); + return ret; +} + static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); @@ -162,7 +808,7 @@ static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr) iattr->ia_size); /* Ensure that we have a up to date size, so we know if it changed. */ - ret = orangefs_inode_getattr(inode, 0, 1, STATX_SIZE); + ret = orangefs_inode_getattr(inode, ORANGEFS_GETATTR_SIZE); if (ret == -ESTALE) ret = -EIO; if (ret) { @@ -172,7 +818,11 @@ static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr) } orig_size = i_size_read(inode); - truncate_setsize(inode, iattr->ia_size); + /* This is truncate_setsize in a different order. */ + truncate_pagecache(inode, iattr->ia_size); + i_size_write(inode, iattr->ia_size); + if (iattr->ia_size > orig_size) + pagecache_isize_extended(inode, orig_size, iattr->ia_size); new_op = op_alloc(ORANGEFS_VFS_OP_TRUNCATE); if (!new_op) @@ -202,22 +852,33 @@ static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr) return ret; } -/* - * Change attributes of an object referenced by dentry. - */ -int orangefs_setattr(struct dentry *dentry, struct iattr *iattr) +int __orangefs_setattr(struct inode *inode, struct iattr *iattr) { - int ret = -EINVAL; - struct inode *inode = dentry->d_inode; - - gossip_debug(GOSSIP_INODE_DEBUG, - "%s: called on %pd\n", - __func__, - dentry); + int ret; - ret = setattr_prepare(dentry, iattr); - if (ret) - goto out; + if (iattr->ia_valid & ATTR_MODE) { + if (iattr->ia_mode & (S_ISVTX)) { + if (is_root_handle(inode)) { + /* + * allow sticky bit to be set on root (since + * it shows up that way by default anyhow), + * but don't show it to the server + */ + iattr->ia_mode -= S_ISVTX; + } else { + gossip_debug(GOSSIP_UTILS_DEBUG, + "User attempted to set sticky bit on non-root directory; returning EINVAL.\n"); + ret = -EINVAL; + goto out; + } + } + if (iattr->ia_mode & (S_ISUID)) { + gossip_debug(GOSSIP_UTILS_DEBUG, + "Attempting to set setuid bit (not supported); returning EINVAL.\n"); + ret = -EINVAL; + goto out; + } + } if (iattr->ia_valid & ATTR_SIZE) { ret = orangefs_setattr_size(inode, iattr); @@ -225,21 +886,51 @@ int orangefs_setattr(struct dentry *dentry, struct iattr *iattr) goto out; } +again: + spin_lock(&inode->i_lock); + if (ORANGEFS_I(inode)->attr_valid) { + if (uid_eq(ORANGEFS_I(inode)->attr_uid, current_fsuid()) && + gid_eq(ORANGEFS_I(inode)->attr_gid, current_fsgid())) { + ORANGEFS_I(inode)->attr_valid = iattr->ia_valid; + } else { + spin_unlock(&inode->i_lock); + write_inode_now(inode, 1); + goto again; + } + } else { + ORANGEFS_I(inode)->attr_valid = iattr->ia_valid; + ORANGEFS_I(inode)->attr_uid = current_fsuid(); + ORANGEFS_I(inode)->attr_gid = current_fsgid(); + } setattr_copy(inode, iattr); + spin_unlock(&inode->i_lock); mark_inode_dirty(inode); - ret = orangefs_inode_setattr(inode, iattr); - gossip_debug(GOSSIP_INODE_DEBUG, - "%s: orangefs_inode_setattr returned %d\n", - __func__, - ret); - - if (!ret && (iattr->ia_valid & ATTR_MODE)) + if (iattr->ia_valid & ATTR_MODE) /* change mod on a file that has ACLs */ ret = posix_acl_chmod(inode, inode->i_mode); + ret = 0; out: - gossip_debug(GOSSIP_INODE_DEBUG, "%s: ret:%d:\n", __func__, ret); + return ret; +} + +/* + * Change attributes of an object referenced by dentry. + */ +int orangefs_setattr(struct dentry *dentry, struct iattr *iattr) +{ + int ret; + gossip_debug(GOSSIP_INODE_DEBUG, "__orangefs_setattr: called on %pd\n", + dentry); + ret = setattr_prepare(dentry, iattr); + if (ret) + goto out; + ret = __orangefs_setattr(d_inode(dentry), iattr); + sync_inode_metadata(d_inode(dentry), 1); +out: + gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_setattr: returning %d\n", + ret); return ret; } @@ -253,10 +944,11 @@ int orangefs_getattr(const struct path *path, struct kstat *stat, struct inode *inode = path->dentry->d_inode; gossip_debug(GOSSIP_INODE_DEBUG, - "orangefs_getattr: called on %pd\n", - path->dentry); + "orangefs_getattr: called on %pd mask %u\n", + path->dentry, request_mask); - ret = orangefs_inode_getattr(inode, 0, 0, request_mask); + ret = orangefs_inode_getattr(inode, + request_mask & STATX_SIZE ? ORANGEFS_GETATTR_SIZE : 0); if (ret == 0) { generic_fillattr(inode, stat); @@ -284,7 +976,7 @@ int orangefs_permission(struct inode *inode, int mask) gossip_debug(GOSSIP_INODE_DEBUG, "%s: refreshing\n", __func__); /* Make sure the permission (and other common attrs) are up to date. */ - ret = orangefs_inode_getattr(inode, 0, 0, STATX_MODE); + ret = orangefs_inode_getattr(inode, 0); if (ret < 0) return ret; @@ -304,7 +996,7 @@ int orangefs_update_time(struct inode *inode, struct timespec64 *time, int flags iattr.ia_valid |= ATTR_CTIME; if (flags & S_MTIME) iattr.ia_valid |= ATTR_MTIME; - return orangefs_inode_setattr(inode, &iattr); + return __orangefs_setattr(inode, &iattr); } /* ORANGEFS2 implementation of VFS inode operations for files */ @@ -364,6 +1056,10 @@ static int orangefs_set_inode(struct inode *inode, void *data) struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data; ORANGEFS_I(inode)->refn.fs_id = ref->fs_id; ORANGEFS_I(inode)->refn.khandle = ref->khandle; + ORANGEFS_I(inode)->attr_valid = 0; + hash_init(ORANGEFS_I(inode)->xattr_cache); + ORANGEFS_I(inode)->mapping_time = jiffies - 1; + ORANGEFS_I(inode)->bitlock = 0; return 0; } @@ -409,7 +1105,7 @@ struct inode *orangefs_iget(struct super_block *sb, if (!(inode->i_state & I_NEW)) return inode; - error = orangefs_inode_getattr(inode, 1, 1, STATX_ALL); + error = orangefs_inode_getattr(inode, ORANGEFS_GETATTR_NEW); if (error) { iget_failed(inode); return ERR_PTR(error); @@ -454,17 +1150,11 @@ struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir, orangefs_set_inode(inode, ref); inode->i_ino = hash; /* needed for stat etc */ - error = orangefs_inode_getattr(inode, 1, 1, STATX_ALL); + error = orangefs_inode_getattr(inode, ORANGEFS_GETATTR_NEW); if (error) goto out_iput; orangefs_init_iops(inode); - - inode->i_mode = mode; - inode->i_uid = current_fsuid(); - inode->i_gid = current_fsgid(); - inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); - inode->i_size = PAGE_SIZE; inode->i_rdev = dev; error = insert_inode_locked4(inode, hash, orangefs_test_inode, ref); diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index c8676c996249..1dd710e5f376 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -76,19 +76,16 @@ static int orangefs_create(struct inode *dir, d_instantiate_new(dentry, inode); orangefs_set_timeout(dentry); - ORANGEFS_I(inode)->getattr_time = jiffies - 1; - ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS; gossip_debug(GOSSIP_NAME_DEBUG, "%s: dentry instantiated for %pd\n", __func__, dentry); - dir->i_mtime = dir->i_ctime = current_time(dir); memset(&iattr, 0, sizeof iattr); - iattr.ia_valid |= ATTR_MTIME; - orangefs_inode_setattr(dir, &iattr); - mark_inode_dirty_sync(dir); + iattr.ia_valid |= ATTR_MTIME | ATTR_CTIME; + iattr.ia_mtime = iattr.ia_ctime = current_time(dir); + __orangefs_setattr(dir, &iattr); ret = 0; out: op_release(new_op); @@ -210,11 +207,10 @@ static int orangefs_unlink(struct inode *dir, struct dentry *dentry) if (!ret) { drop_nlink(inode); - dir->i_mtime = dir->i_ctime = current_time(dir); memset(&iattr, 0, sizeof iattr); - iattr.ia_valid |= ATTR_MTIME; - orangefs_inode_setattr(dir, &iattr); - mark_inode_dirty_sync(dir); + iattr.ia_valid |= ATTR_MTIME | ATTR_CTIME; + iattr.ia_mtime = iattr.ia_ctime = current_time(dir); + __orangefs_setattr(dir, &iattr); } return ret; } @@ -291,19 +287,16 @@ static int orangefs_symlink(struct inode *dir, d_instantiate_new(dentry, inode); orangefs_set_timeout(dentry); - ORANGEFS_I(inode)->getattr_time = jiffies - 1; - ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS; gossip_debug(GOSSIP_NAME_DEBUG, "Inode (Symlink) %pU -> %pd\n", get_khandle_from_ino(inode), dentry); - dir->i_mtime = dir->i_ctime = current_time(dir); memset(&iattr, 0, sizeof iattr); - iattr.ia_valid |= ATTR_MTIME; - orangefs_inode_setattr(dir, &iattr); - mark_inode_dirty_sync(dir); + iattr.ia_valid |= ATTR_MTIME | ATTR_CTIME; + iattr.ia_mtime = iattr.ia_ctime = current_time(dir); + __orangefs_setattr(dir, &iattr); ret = 0; out: op_release(new_op); @@ -360,8 +353,6 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode d_instantiate_new(dentry, inode); orangefs_set_timeout(dentry); - ORANGEFS_I(inode)->getattr_time = jiffies - 1; - ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS; gossip_debug(GOSSIP_NAME_DEBUG, "Inode (Directory) %pU -> %pd\n", @@ -372,11 +363,10 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode * NOTE: we have no good way to keep nlink consistent for directories * across clients; keep constant at 1. */ - dir->i_mtime = dir->i_ctime = current_time(dir); memset(&iattr, 0, sizeof iattr); - iattr.ia_valid |= ATTR_MTIME; - orangefs_inode_setattr(dir, &iattr); - mark_inode_dirty_sync(dir); + iattr.ia_valid |= ATTR_MTIME | ATTR_CTIME; + iattr.ia_mtime = iattr.ia_ctime = current_time(dir); + __orangefs_setattr(dir, &iattr); out: op_release(new_op); return ret; @@ -389,6 +379,7 @@ static int orangefs_rename(struct inode *old_dir, unsigned int flags) { struct orangefs_kernel_op_s *new_op; + struct iattr iattr; int ret; if (flags) @@ -398,7 +389,10 @@ static int orangefs_rename(struct inode *old_dir, "orangefs_rename: called (%pd2 => %pd2) ct=%d\n", old_dentry, new_dentry, d_count(new_dentry)); - ORANGEFS_I(new_dentry->d_parent->d_inode)->getattr_time = jiffies - 1; + memset(&iattr, 0, sizeof iattr); + iattr.ia_valid |= ATTR_MTIME | ATTR_CTIME; + iattr.ia_mtime = iattr.ia_ctime = current_time(new_dir); + __orangefs_setattr(new_dir, &iattr); new_op = op_alloc(ORANGEFS_VFS_OP_RENAME); if (!new_op) diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 443bcd8c3c19..2bb916d68576 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -269,7 +269,7 @@ orangefs_bufmap_map(struct orangefs_bufmap *bufmap, /* map the pages */ ret = get_user_pages_fast((unsigned long)user_desc->ptr, - bufmap->page_count, 1, bufmap->page_array); + bufmap->page_count, FOLL_WRITE, bufmap->page_array); if (ret < 0) return ret; @@ -538,3 +538,16 @@ int orangefs_bufmap_copy_to_iovec(struct iov_iter *iter, } return 0; } + +void orangefs_bufmap_page_fill(void *page_to, + int buffer_index, + int slot_index) +{ + struct orangefs_bufmap_desc *from; + void *page_from; + + from = &__orangefs_bufmap->desc_array[buffer_index]; + page_from = kmap_atomic(from->page_array[slot_index]); + memcpy(page_to, page_from, PAGE_SIZE); + kunmap_atomic(page_from); +} diff --git a/fs/orangefs/orangefs-bufmap.h b/fs/orangefs/orangefs-bufmap.h index c2c3c5a0eeab..75b2d2833af1 100644 --- a/fs/orangefs/orangefs-bufmap.h +++ b/fs/orangefs/orangefs-bufmap.h @@ -34,4 +34,6 @@ int orangefs_bufmap_copy_to_iovec(struct iov_iter *iter, int buffer_index, size_t size); +void orangefs_bufmap_page_fill(void *kaddr, int buffer_index, int slot_index); + #endif /* __ORANGEFS_BUFMAP_H */ diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 0732cb08173e..87b1a6fce628 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -963,7 +963,7 @@ int orangefs_debugfs_new_client_mask(void __user *arg) return ret; } -int orangefs_debugfs_new_client_string(void __user *arg) +int orangefs_debugfs_new_client_string(void __user *arg) { int ret; @@ -1016,7 +1016,7 @@ int orangefs_debugfs_new_client_string(void __user *arg) return 0; } -int orangefs_debugfs_new_debug(void __user *arg) +int orangefs_debugfs_new_debug(void __user *arg) { struct dev_mask_info_s mask_info = {0}; int ret; diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 17b24ad6b264..572dd29fbd54 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -51,6 +51,7 @@ #include <linux/rwsem.h> #include <linux/xattr.h> #include <linux/exportfs.h> +#include <linux/hashtable.h> #include <asm/unaligned.h> @@ -192,7 +193,13 @@ struct orangefs_inode_s { sector_t last_failed_block_index_read; unsigned long getattr_time; - u32 getattr_mask; + unsigned long mapping_time; + int attr_valid; + kuid_t attr_uid; + kgid_t attr_gid; + unsigned long bitlock; + + DECLARE_HASHTABLE(xattr_cache, 4); }; /* per superblock private orangefs info */ @@ -217,6 +224,25 @@ struct orangefs_stats { unsigned long writes; }; +struct orangefs_cached_xattr { + struct hlist_node node; + char key[ORANGEFS_MAX_XATTR_NAMELEN]; + char val[ORANGEFS_MAX_XATTR_VALUELEN]; + ssize_t length; + unsigned long timeout; +}; + +struct orangefs_write_range { + loff_t pos; + size_t len; + kuid_t uid; + kgid_t gid; +}; + +struct orangefs_read_options { + ssize_t blksiz; +}; + extern struct orangefs_stats orangefs_stats; /* @@ -329,13 +355,15 @@ void fsid_key_table_finalize(void); /* * defined in inode.c */ +vm_fault_t orangefs_page_mkwrite(struct vm_fault *); struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir, int mode, dev_t dev, struct orangefs_object_kref *ref); -int orangefs_setattr(struct dentry *dentry, struct iattr *iattr); +int __orangefs_setattr(struct inode *, struct iattr *); +int orangefs_setattr(struct dentry *, struct iattr *); int orangefs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); @@ -355,11 +383,6 @@ ssize_t orangefs_listxattr(struct dentry *dentry, char *buffer, size_t size); struct inode *orangefs_iget(struct super_block *sb, struct orangefs_object_kref *ref); -ssize_t orangefs_inode_read(struct inode *inode, - struct iov_iter *iter, - loff_t *offset, - loff_t readahead_size); - /* * defined in devorangefs-req.c */ @@ -371,6 +394,15 @@ int is_daemon_in_service(void); bool __is_daemon_in_service(void); /* + * defined in file.c + */ +int orangefs_revalidate_mapping(struct inode *); +ssize_t wait_for_direct_io(enum ORANGEFS_io_type, struct inode *, loff_t *, + struct iov_iter *, size_t, loff_t, struct orangefs_write_range *, int *); +ssize_t do_readv_writev(enum ORANGEFS_io_type, struct file *, loff_t *, + struct iov_iter *); + +/* * defined in orangefs-utils.c */ __s32 fsid_of_op(struct orangefs_kernel_op_s *op); @@ -386,12 +418,14 @@ int orangefs_inode_setxattr(struct inode *inode, size_t size, int flags); -int orangefs_inode_getattr(struct inode *inode, int new, int bypass, - u32 request_mask); +#define ORANGEFS_GETATTR_NEW 1 +#define ORANGEFS_GETATTR_SIZE 2 + +int orangefs_inode_getattr(struct inode *, int); int orangefs_inode_check_changed(struct inode *inode); -int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr); +int orangefs_inode_setattr(struct inode *inode); bool orangefs_cancel_op_in_progress(struct orangefs_kernel_op_s *op); @@ -400,6 +434,7 @@ int orangefs_normalize_to_errno(__s32 error_code); extern struct mutex orangefs_request_mutex; extern int op_timeout_secs; extern int slot_timeout_secs; +extern int orangefs_cache_timeout_msecs; extern int orangefs_dcache_timeout_msecs; extern int orangefs_getattr_timeout_msecs; extern struct list_head orangefs_superblocks; @@ -426,6 +461,7 @@ extern const struct dentry_operations orangefs_dentry_operations; #define ORANGEFS_OP_CANCELLATION 4 /* this is a cancellation */ #define ORANGEFS_OP_NO_MUTEX 8 /* don't acquire request_mutex */ #define ORANGEFS_OP_ASYNC 16 /* Queue it, but don't wait */ +#define ORANGEFS_OP_WRITEBACK 32 int service_operation(struct orangefs_kernel_op_s *op, const char *op_name, diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 85ef87245a87..82cf8b3e568b 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -30,6 +30,7 @@ static ulong module_parm_debug_mask; __u64 orangefs_gossip_debug_mask; int op_timeout_secs = ORANGEFS_DEFAULT_OP_TIMEOUT_SECS; int slot_timeout_secs = ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS; +int orangefs_cache_timeout_msecs = 50; int orangefs_dcache_timeout_msecs = 50; int orangefs_getattr_timeout_msecs = 50; diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c index 19739aaee675..3627ea946402 100644 --- a/fs/orangefs/orangefs-sysfs.c +++ b/fs/orangefs/orangefs-sysfs.c @@ -62,6 +62,14 @@ * Slots are requested and waited for, * the wait times out after slot_timeout_secs. * + * What: /sys/fs/orangefs/cache_timeout_msecs + * Date: Mar 2018 + * Contact: Martin Brandenburg <martin@omnibond.com> + * Description: + * Time in milliseconds between which + * orangefs_revalidate_mapping will invalidate the page + * cache. + * * What: /sys/fs/orangefs/dcache_timeout_msecs * Date: Jul 2016 * Contact: Martin Brandenburg <martin@omnibond.com> @@ -222,6 +230,13 @@ static ssize_t sysfs_int_show(struct kobject *kobj, slot_timeout_secs); goto out; } else if (!strcmp(attr->attr.name, + "cache_timeout_msecs")) { + rc = scnprintf(buf, + PAGE_SIZE, + "%d\n", + orangefs_cache_timeout_msecs); + goto out; + } else if (!strcmp(attr->attr.name, "dcache_timeout_msecs")) { rc = scnprintf(buf, PAGE_SIZE, @@ -277,6 +292,9 @@ static ssize_t sysfs_int_store(struct kobject *kobj, } else if (!strcmp(attr->attr.name, "slot_timeout_secs")) { rc = kstrtoint(buf, 0, &slot_timeout_secs); goto out; + } else if (!strcmp(attr->attr.name, "cache_timeout_msecs")) { + rc = kstrtoint(buf, 0, &orangefs_cache_timeout_msecs); + goto out; } else if (!strcmp(attr->attr.name, "dcache_timeout_msecs")) { rc = kstrtoint(buf, 0, &orangefs_dcache_timeout_msecs); goto out; @@ -818,6 +836,9 @@ static struct orangefs_attribute op_timeout_secs_attribute = static struct orangefs_attribute slot_timeout_secs_attribute = __ATTR(slot_timeout_secs, 0664, sysfs_int_show, sysfs_int_store); +static struct orangefs_attribute cache_timeout_msecs_attribute = + __ATTR(cache_timeout_msecs, 0664, sysfs_int_show, sysfs_int_store); + static struct orangefs_attribute dcache_timeout_msecs_attribute = __ATTR(dcache_timeout_msecs, 0664, sysfs_int_show, sysfs_int_store); @@ -861,6 +882,7 @@ static struct orangefs_attribute perf_time_interval_secs_attribute = static struct attribute *orangefs_default_attrs[] = { &op_timeout_secs_attribute.attr, &slot_timeout_secs_attribute.attr, + &cache_timeout_msecs_attribute.attr, &dcache_timeout_msecs_attribute.attr, &getattr_timeout_msecs_attribute.attr, &readahead_count_attribute.attr, diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c index 804c8a261e4b..d4b7ae763186 100644 --- a/fs/orangefs/orangefs-utils.c +++ b/fs/orangefs/orangefs-utils.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * (C) 2001 Clemson University and The University of Chicago + * Copyright 2018 Omnibond Systems, L.L.C. * * See COPYING in top-level directory. */ @@ -135,51 +136,37 @@ static int orangefs_inode_perms(struct ORANGEFS_sys_attr_s *attrs) * NOTE: in kernel land, we never use the sys_attr->link_target for * anything, so don't bother copying it into the sys_attr object here. */ -static inline int copy_attributes_from_inode(struct inode *inode, - struct ORANGEFS_sys_attr_s *attrs, - struct iattr *iattr) +static inline void copy_attributes_from_inode(struct inode *inode, + struct ORANGEFS_sys_attr_s *attrs) { - umode_t tmp_mode; - - if (!iattr || !inode || !attrs) { - gossip_err("NULL iattr (%p), inode (%p), attrs (%p) " - "in copy_attributes_from_inode!\n", - iattr, - inode, - attrs); - return -EINVAL; - } - /* - * We need to be careful to only copy the attributes out of the - * iattr object that we know are valid. - */ + struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); attrs->mask = 0; - if (iattr->ia_valid & ATTR_UID) { - attrs->owner = from_kuid(&init_user_ns, iattr->ia_uid); + if (orangefs_inode->attr_valid & ATTR_UID) { + attrs->owner = from_kuid(&init_user_ns, inode->i_uid); attrs->mask |= ORANGEFS_ATTR_SYS_UID; gossip_debug(GOSSIP_UTILS_DEBUG, "(UID) %d\n", attrs->owner); } - if (iattr->ia_valid & ATTR_GID) { - attrs->group = from_kgid(&init_user_ns, iattr->ia_gid); + if (orangefs_inode->attr_valid & ATTR_GID) { + attrs->group = from_kgid(&init_user_ns, inode->i_gid); attrs->mask |= ORANGEFS_ATTR_SYS_GID; gossip_debug(GOSSIP_UTILS_DEBUG, "(GID) %d\n", attrs->group); } - if (iattr->ia_valid & ATTR_ATIME) { + if (orangefs_inode->attr_valid & ATTR_ATIME) { attrs->mask |= ORANGEFS_ATTR_SYS_ATIME; - if (iattr->ia_valid & ATTR_ATIME_SET) { - attrs->atime = (time64_t)iattr->ia_atime.tv_sec; + if (orangefs_inode->attr_valid & ATTR_ATIME_SET) { + attrs->atime = (time64_t)inode->i_atime.tv_sec; attrs->mask |= ORANGEFS_ATTR_SYS_ATIME_SET; } } - if (iattr->ia_valid & ATTR_MTIME) { + if (orangefs_inode->attr_valid & ATTR_MTIME) { attrs->mask |= ORANGEFS_ATTR_SYS_MTIME; - if (iattr->ia_valid & ATTR_MTIME_SET) { - attrs->mtime = (time64_t)iattr->ia_mtime.tv_sec; + if (orangefs_inode->attr_valid & ATTR_MTIME_SET) { + attrs->mtime = (time64_t)inode->i_mtime.tv_sec; attrs->mask |= ORANGEFS_ATTR_SYS_MTIME_SET; } } - if (iattr->ia_valid & ATTR_CTIME) + if (orangefs_inode->attr_valid & ATTR_CTIME) attrs->mask |= ORANGEFS_ATTR_SYS_CTIME; /* @@ -188,36 +175,10 @@ static inline int copy_attributes_from_inode(struct inode *inode, * worry about ATTR_SIZE */ - if (iattr->ia_valid & ATTR_MODE) { - tmp_mode = iattr->ia_mode; - if (tmp_mode & (S_ISVTX)) { - if (is_root_handle(inode)) { - /* - * allow sticky bit to be set on root (since - * it shows up that way by default anyhow), - * but don't show it to the server - */ - tmp_mode -= S_ISVTX; - } else { - gossip_debug(GOSSIP_UTILS_DEBUG, - "%s: setting sticky bit not supported.\n", - __func__); - return -EINVAL; - } - } - - if (tmp_mode & (S_ISUID)) { - gossip_debug(GOSSIP_UTILS_DEBUG, - "%s: setting setuid bit not supported.\n", - __func__); - return -EINVAL; - } - - attrs->perms = ORANGEFS_util_translate_mode(tmp_mode); + if (orangefs_inode->attr_valid & ATTR_MODE) { + attrs->perms = ORANGEFS_util_translate_mode(inode->i_mode); attrs->mask |= ORANGEFS_ATTR_SYS_PERM; } - - return 0; } static int orangefs_inode_type(enum orangefs_ds_type objtype) @@ -272,27 +233,30 @@ static int orangefs_inode_is_stale(struct inode *inode, return 0; } -int orangefs_inode_getattr(struct inode *inode, int new, int bypass, - u32 request_mask) +int orangefs_inode_getattr(struct inode *inode, int flags) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); struct orangefs_kernel_op_s *new_op; loff_t inode_size; int ret, type; - gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__, - get_khandle_from_ino(inode)); + gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU flags %d\n", + __func__, get_khandle_from_ino(inode), flags); - if (!new && !bypass) { - /* - * Must have all the attributes in the mask and be within cache - * time. - */ - if ((request_mask & orangefs_inode->getattr_mask) == - request_mask && - time_before(jiffies, orangefs_inode->getattr_time)) - return 0; +again: + spin_lock(&inode->i_lock); + /* Must have all the attributes in the mask and be within cache time. */ + if ((!flags && time_before(jiffies, orangefs_inode->getattr_time)) || + orangefs_inode->attr_valid || inode->i_state & I_DIRTY_PAGES) { + if (orangefs_inode->attr_valid) { + spin_unlock(&inode->i_lock); + write_inode_now(inode, 1); + goto again; + } + spin_unlock(&inode->i_lock); + return 0; } + spin_unlock(&inode->i_lock); new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR); if (!new_op) @@ -302,7 +266,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass, * Size is the hardest attribute to get. The incremental cost of any * other attribute is essentially zero. */ - if (request_mask & STATX_SIZE || new) + if (flags) new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_ALL_NOHINT; else new_op->upcall.req.getattr.mask = @@ -313,13 +277,33 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass, if (ret != 0) goto out; - if (!new) { +again2: + spin_lock(&inode->i_lock); + /* Must have all the attributes in the mask and be within cache time. */ + if ((!flags && time_before(jiffies, orangefs_inode->getattr_time)) || + orangefs_inode->attr_valid || inode->i_state & I_DIRTY_PAGES) { + if (orangefs_inode->attr_valid) { + spin_unlock(&inode->i_lock); + write_inode_now(inode, 1); + goto again2; + } + if (inode->i_state & I_DIRTY_PAGES) { + ret = 0; + goto out_unlock; + } + gossip_debug(GOSSIP_UTILS_DEBUG, "%s: in cache or dirty\n", + __func__); + ret = 0; + goto out_unlock; + } + + if (!(flags & ORANGEFS_GETATTR_NEW)) { ret = orangefs_inode_is_stale(inode, &new_op->downcall.resp.getattr.attributes, new_op->downcall.resp.getattr.link_target); if (ret) { ret = -ESTALE; - goto out; + goto out_unlock; } } @@ -329,30 +313,26 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass, case S_IFREG: inode->i_flags = orangefs_inode_flags(&new_op-> downcall.resp.getattr.attributes); - if (request_mask & STATX_SIZE || new) { + if (flags) { inode_size = (loff_t)new_op-> downcall.resp.getattr.attributes.size; inode->i_size = inode_size; inode->i_blkbits = ffs(new_op->downcall.resp.getattr. attributes.blksize); - spin_lock(&inode->i_lock); inode->i_bytes = inode_size; inode->i_blocks = (inode_size + 512 - inode_size % 512)/512; - spin_unlock(&inode->i_lock); } break; case S_IFDIR: - if (request_mask & STATX_SIZE || new) { + if (flags) { inode->i_size = PAGE_SIZE; - spin_lock(&inode->i_lock); inode_set_bytes(inode, inode->i_size); - spin_unlock(&inode->i_lock); } set_nlink(inode, 1); break; case S_IFLNK: - if (new) { + if (flags & ORANGEFS_GETATTR_NEW) { inode->i_size = (loff_t)strlen(new_op-> downcall.resp.getattr.link_target); ret = strscpy(orangefs_inode->link_target, @@ -360,7 +340,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass, ORANGEFS_NAME_MAX); if (ret == -E2BIG) { ret = -EIO; - goto out; + goto out_unlock; } inode->i_link = orangefs_inode->link_target; } @@ -370,7 +350,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass, /* XXX: ESTALE? This is what is done if it is not new. */ orangefs_make_bad_inode(inode); ret = -ESTALE; - goto out; + goto out_unlock; } inode->i_uid = make_kuid(&init_user_ns, new_op-> @@ -393,11 +373,9 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass, orangefs_inode->getattr_time = jiffies + orangefs_getattr_timeout_msecs*HZ/1000; - if (request_mask & STATX_SIZE || new) - orangefs_inode->getattr_mask = STATX_BASIC_STATS; - else - orangefs_inode->getattr_mask = STATX_BASIC_STATS & ~STATX_SIZE; ret = 0; +out_unlock: + spin_unlock(&inode->i_lock); out: op_release(new_op); return ret; @@ -436,7 +414,7 @@ out: * issues a orangefs setattr request to make sure the new attribute values * take effect if successful. returns 0 on success; -errno otherwise */ -int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr) +int orangefs_inode_setattr(struct inode *inode) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); struct orangefs_kernel_op_s *new_op; @@ -446,24 +424,31 @@ int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr) if (!new_op) return -ENOMEM; + spin_lock(&inode->i_lock); + new_op->upcall.uid = from_kuid(&init_user_ns, orangefs_inode->attr_uid); + new_op->upcall.gid = from_kgid(&init_user_ns, orangefs_inode->attr_gid); new_op->upcall.req.setattr.refn = orangefs_inode->refn; - ret = copy_attributes_from_inode(inode, - &new_op->upcall.req.setattr.attributes, - iattr); - if (ret >= 0) { - ret = service_operation(new_op, __func__, - get_interruptible_flag(inode)); - - gossip_debug(GOSSIP_UTILS_DEBUG, - "orangefs_inode_setattr: returning %d\n", - ret); + copy_attributes_from_inode(inode, + &new_op->upcall.req.setattr.attributes); + orangefs_inode->attr_valid = 0; + if (!new_op->upcall.req.setattr.attributes.mask) { + spin_unlock(&inode->i_lock); + op_release(new_op); + return 0; } + spin_unlock(&inode->i_lock); + + ret = service_operation(new_op, __func__, + get_interruptible_flag(inode) | ORANGEFS_OP_WRITEBACK); + gossip_debug(GOSSIP_UTILS_DEBUG, + "orangefs_inode_setattr: returning %d\n", ret); + if (ret) + orangefs_make_bad_inode(inode); op_release(new_op); if (ret == 0) orangefs_inode->getattr_time = jiffies - 1; - return ret; } diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index dfaee90d30bd..ee5efdc35cc1 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -10,6 +10,7 @@ #include "orangefs-bufmap.h" #include <linux/parser.h> +#include <linux/hashtable.h> /* a cache for orangefs-inode objects (i.e. orangefs inode private data) */ static struct kmem_cache *orangefs_inode_cache; @@ -124,10 +125,18 @@ static struct inode *orangefs_alloc_inode(struct super_block *sb) return &orangefs_inode->vfs_inode; } -static void orangefs_i_callback(struct rcu_head *head) +static void orangefs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); + struct orangefs_cached_xattr *cx; + struct hlist_node *tmp; + int i; + + hash_for_each_safe(orangefs_inode->xattr_cache, i, tmp, cx, node) { + hlist_del(&cx->node); + kfree(cx); + } + kmem_cache_free(orangefs_inode_cache, orangefs_inode); } @@ -138,8 +147,13 @@ static void orangefs_destroy_inode(struct inode *inode) gossip_debug(GOSSIP_SUPER_DEBUG, "%s: deallocated %p destroying inode %pU\n", __func__, orangefs_inode, get_khandle_from_ino(inode)); +} - call_rcu(&inode->i_rcu, orangefs_i_callback); +static int orangefs_write_inode(struct inode *inode, + struct writeback_control *wbc) +{ + gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_write_inode\n"); + return orangefs_inode_setattr(inode); } /* @@ -299,7 +313,9 @@ void fsid_key_table_finalize(void) static const struct super_operations orangefs_s_ops = { .alloc_inode = orangefs_alloc_inode, + .free_inode = orangefs_free_inode, .destroy_inode = orangefs_destroy_inode, + .write_inode = orangefs_write_inode, .drop_inode = generic_delete_inode, .statfs = orangefs_statfs, .remount_fs = orangefs_remount_fs, @@ -397,15 +413,11 @@ static int orangefs_fill_sb(struct super_block *sb, struct orangefs_fs_mount_response *fs_mount, void *data, int silent) { - int ret = -EINVAL; - struct inode *root = NULL; - struct dentry *root_dentry = NULL; + int ret; + struct inode *root; + struct dentry *root_dentry; struct orangefs_object_kref root_object; - /* alloc and init our private orangefs sb info */ - sb->s_fs_info = kzalloc(sizeof(struct orangefs_sb_info_s), GFP_KERNEL); - if (!ORANGEFS_SB(sb)) - return -ENOMEM; ORANGEFS_SB(sb)->sb = sb; ORANGEFS_SB(sb)->root_khandle = fs_mount->root_khandle; @@ -428,6 +440,10 @@ static int orangefs_fill_sb(struct super_block *sb, sb->s_blocksize_bits = PAGE_SHIFT; sb->s_maxbytes = MAX_LFS_FILESIZE; + ret = super_setup_bdi(sb); + if (ret) + return ret; + root_object.khandle = ORANGEFS_SB(sb)->root_khandle; root_object.fs_id = ORANGEFS_SB(sb)->fs_id; gossip_debug(GOSSIP_SUPER_DEBUG, @@ -506,6 +522,13 @@ struct dentry *orangefs_mount(struct file_system_type *fst, goto free_op; } + /* alloc and init our private orangefs sb info */ + sb->s_fs_info = kzalloc(sizeof(struct orangefs_sb_info_s), GFP_KERNEL); + if (!ORANGEFS_SB(sb)) { + d = ERR_PTR(-ENOMEM); + goto free_op; + } + ret = orangefs_fill_sb(sb, &new_op->downcall.resp.fs_mount, data, flags & SB_SILENT ? 1 : 0); diff --git a/fs/orangefs/waitqueue.c b/fs/orangefs/waitqueue.c index 0729d2645d6a..beafc33d57be 100644 --- a/fs/orangefs/waitqueue.c +++ b/fs/orangefs/waitqueue.c @@ -19,7 +19,7 @@ static int wait_for_matching_downcall(struct orangefs_kernel_op_s *op, long timeout, - bool interruptible) + int flags) __acquires(op->lock); static void orangefs_clean_up_interrupted_operation(struct orangefs_kernel_op_s *op) __releases(op->lock); @@ -143,9 +143,7 @@ retry_servicing: if (!(flags & ORANGEFS_OP_NO_MUTEX)) mutex_unlock(&orangefs_request_mutex); - ret = wait_for_matching_downcall(op, timeout, - flags & ORANGEFS_OP_INTERRUPTIBLE); - + ret = wait_for_matching_downcall(op, timeout, flags); gossip_debug(GOSSIP_WAIT_DEBUG, "%s: wait_for_matching_downcall returned %d for %p\n", __func__, @@ -319,10 +317,12 @@ static void */ static int wait_for_matching_downcall(struct orangefs_kernel_op_s *op, long timeout, - bool interruptible) + int flags) __acquires(op->lock) { long n; + int writeback = flags & ORANGEFS_OP_WRITEBACK, + interruptible = flags & ORANGEFS_OP_INTERRUPTIBLE; /* * There's a "schedule_timeout" inside of these wait @@ -330,10 +330,12 @@ static int wait_for_matching_downcall(struct orangefs_kernel_op_s *op, * user process that needs something done and is being * manipulated by the client-core process. */ - if (interruptible) + if (writeback) + n = wait_for_completion_io_timeout(&op->waitq, timeout); + else if (!writeback && interruptible) n = wait_for_completion_interruptible_timeout(&op->waitq, - timeout); - else + timeout); + else /* !writeback && !interruptible but compiler complains */ n = wait_for_completion_killable_timeout(&op->waitq, timeout); spin_lock(&op->lock); diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index 03bcb871544d..bdc285aea360 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * (C) 2001 Clemson University and The University of Chicago + * Copyright 2018 Omnibond Systems, L.L.C. * * See COPYING in top-level directory. */ @@ -14,7 +15,7 @@ #include "orangefs-bufmap.h" #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> - +#include <linux/hashtable.h> #define SYSTEM_ORANGEFS_KEY "system.pvfs2." #define SYSTEM_ORANGEFS_KEY_LEN 13 @@ -50,6 +51,35 @@ static inline int convert_to_internal_xattr_flags(int setxattr_flags) return internal_flag; } +static unsigned int xattr_key(const char *key) +{ + unsigned int i = 0; + while (key) + i += *key++; + return i % 16; +} + +static struct orangefs_cached_xattr *find_cached_xattr(struct inode *inode, + const char *key) +{ + struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); + struct orangefs_cached_xattr *cx; + struct hlist_head *h; + struct hlist_node *tmp; + h = &orangefs_inode->xattr_cache[xattr_key(key)]; + if (hlist_empty(h)) + return NULL; + hlist_for_each_entry_safe(cx, tmp, h, node) { +/* if (!time_before(jiffies, cx->timeout)) { + hlist_del(&cx->node); + kfree(cx); + continue; + }*/ + if (!strcmp(cx->key, key)) + return cx; + } + return NULL; +} /* * Tries to get a specified key's attributes of a given @@ -65,6 +95,7 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name, { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); struct orangefs_kernel_op_s *new_op = NULL; + struct orangefs_cached_xattr *cx; ssize_t ret = -ENOMEM; ssize_t length = 0; int fsuid; @@ -93,6 +124,27 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name, down_read(&orangefs_inode->xattr_sem); + cx = find_cached_xattr(inode, name); + if (cx && time_before(jiffies, cx->timeout)) { + if (cx->length == -1) { + ret = -ENODATA; + goto out_unlock; + } else { + if (size == 0) { + ret = cx->length; + goto out_unlock; + } + if (cx->length > size) { + ret = -ERANGE; + goto out_unlock; + } + memcpy(buffer, cx->val, cx->length); + memset(buffer + cx->length, 0, size - cx->length); + ret = cx->length; + goto out_unlock; + } + } + new_op = op_alloc(ORANGEFS_VFS_OP_GETXATTR); if (!new_op) goto out_unlock; @@ -117,6 +169,15 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name, " does not exist!\n", get_khandle_from_ino(inode), (char *)new_op->upcall.req.getxattr.key); + cx = kmalloc(sizeof *cx, GFP_KERNEL); + if (cx) { + strcpy(cx->key, name); + cx->length = -1; + cx->timeout = jiffies + + orangefs_getattr_timeout_msecs*HZ/1000; + hash_add(orangefs_inode->xattr_cache, &cx->node, + xattr_key(cx->key)); + } } goto out_release_op; } @@ -156,6 +217,23 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name, ret = length; + if (cx) { + strcpy(cx->key, name); + memcpy(cx->val, buffer, length); + cx->length = length; + cx->timeout = jiffies + HZ; + } else { + cx = kmalloc(sizeof *cx, GFP_KERNEL); + if (cx) { + strcpy(cx->key, name); + memcpy(cx->val, buffer, length); + cx->length = length; + cx->timeout = jiffies + HZ; + hash_add(orangefs_inode->xattr_cache, &cx->node, + xattr_key(cx->key)); + } + } + out_release_op: op_release(new_op); out_unlock: @@ -168,6 +246,9 @@ static int orangefs_inode_removexattr(struct inode *inode, const char *name, { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); struct orangefs_kernel_op_s *new_op = NULL; + struct orangefs_cached_xattr *cx; + struct hlist_head *h; + struct hlist_node *tmp; int ret = -ENOMEM; if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) @@ -209,6 +290,16 @@ static int orangefs_inode_removexattr(struct inode *inode, const char *name, "orangefs_inode_removexattr: returning %d\n", ret); op_release(new_op); + + h = &orangefs_inode->xattr_cache[xattr_key(name)]; + hlist_for_each_entry_safe(cx, tmp, h, node) { + if (!strcmp(cx->key, name)) { + hlist_del(&cx->node); + kfree(cx); + break; + } + } + out_unlock: up_write(&orangefs_inode->xattr_sem); return ret; @@ -226,6 +317,9 @@ int orangefs_inode_setxattr(struct inode *inode, const char *name, struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); struct orangefs_kernel_op_s *new_op; int internal_flag = 0; + struct orangefs_cached_xattr *cx; + struct hlist_head *h; + struct hlist_node *tmp; int ret = -ENOMEM; gossip_debug(GOSSIP_XATTR_DEBUG, @@ -287,6 +381,16 @@ int orangefs_inode_setxattr(struct inode *inode, const char *name, /* when request is serviced properly, free req op struct */ op_release(new_op); + + h = &orangefs_inode->xattr_cache[xattr_key(name)]; + hlist_for_each_entry_safe(cx, tmp, h, node) { + if (!strcmp(cx->key, name)) { + hlist_del(&cx->node); + kfree(cx); + break; + } + } + out_unlock: up_write(&orangefs_inode->xattr_sem); return ret; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 68b3303e4b46..56feaa739979 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -909,14 +909,14 @@ static bool ovl_open_need_copy_up(struct dentry *dentry, int flags) return true; } -int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags) +int ovl_maybe_copy_up(struct dentry *dentry, int flags) { int err = 0; - if (ovl_open_need_copy_up(dentry, file_flags)) { + if (ovl_open_need_copy_up(dentry, flags)) { err = ovl_want_write(dentry); if (!err) { - err = ovl_copy_up_flags(dentry, file_flags); + err = ovl_copy_up_flags(dentry, flags); ovl_drop_write(dentry); } } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 82c129bfe58d..93872bb50230 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -260,7 +260,7 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, * hashed directory inode aliases. */ inode = ovl_get_inode(dentry->d_sb, &oip); - if (WARN_ON(IS_ERR(inode))) + if (IS_ERR(inode)) return PTR_ERR(inode); } else { WARN_ON(ovl_inode_real(inode) != d_inode(newdentry)); diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 54e5d17d7f3e..cc1c9e5606ba 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -398,7 +398,7 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected, * pointer because we hold no lock on the real dentry. */ take_dentry_name_snapshot(&name, real); - this = lookup_one_len(name.name, connected, strlen(name.name)); + this = lookup_one_len(name.name.name, connected, name.name.len); err = PTR_ERR(this); if (IS_ERR(this)) { goto fail; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 84dd957efa24..540a8b845145 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -11,6 +11,7 @@ #include <linux/mount.h> #include <linux/xattr.h> #include <linux/uio.h> +#include <linux/uaccess.h> #include "overlayfs.h" static char ovl_whatisit(struct inode *inode, struct inode *realinode) @@ -29,10 +30,11 @@ static struct file *ovl_open_realfile(const struct file *file, struct inode *inode = file_inode(file); struct file *realfile; const struct cred *old_cred; + int flags = file->f_flags | O_NOATIME | FMODE_NONOTIFY; old_cred = ovl_override_creds(inode->i_sb); - realfile = open_with_fake_path(&file->f_path, file->f_flags | O_NOATIME, - realinode, current_cred()); + realfile = open_with_fake_path(&file->f_path, flags, realinode, + current_cred()); revert_creds(old_cred); pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n", @@ -50,7 +52,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags) int err; /* No atime modificaton on underlying */ - flags |= O_NOATIME; + flags |= O_NOATIME | FMODE_NONOTIFY; /* If some flag changed that cannot be changed then something's amiss */ if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK)) @@ -116,11 +118,10 @@ static int ovl_real_fdget(const struct file *file, struct fd *real) static int ovl_open(struct inode *inode, struct file *file) { - struct dentry *dentry = file_dentry(file); struct file *realfile; int err; - err = ovl_open_maybe_copy_up(dentry, file->f_flags); + err = ovl_maybe_copy_up(file_dentry(file), file->f_flags); if (err) return err; @@ -145,11 +146,47 @@ static int ovl_release(struct inode *inode, struct file *file) static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) { - struct inode *realinode = ovl_inode_real(file_inode(file)); + struct inode *inode = file_inode(file); + struct fd real; + const struct cred *old_cred; + ssize_t ret; + + /* + * The two special cases below do not need to involve real fs, + * so we can optimizing concurrent callers. + */ + if (offset == 0) { + if (whence == SEEK_CUR) + return file->f_pos; + + if (whence == SEEK_SET) + return vfs_setpos(file, 0, 0); + } + + ret = ovl_real_fdget(file, &real); + if (ret) + return ret; + + /* + * Overlay file f_pos is the master copy that is preserved + * through copy up and modified on read/write, but only real + * fs knows how to SEEK_HOLE/SEEK_DATA and real fs may impose + * limitations that are more strict than ->s_maxbytes for specific + * files, so we use the real file to perform seeks. + */ + inode_lock(inode); + real.file->f_pos = file->f_pos; + + old_cred = ovl_override_creds(inode->i_sb); + ret = vfs_llseek(real.file, offset, whence); + revert_creds(old_cred); + + file->f_pos = real.file->f_pos; + inode_unlock(inode); + + fdput(real); - return generic_file_llseek_size(file, offset, whence, - realinode->i_sb->s_maxbytes, - i_size_read(realinode)); + return ret; } static void ovl_file_accessed(struct file *file) @@ -372,10 +409,68 @@ static long ovl_real_ioctl(struct file *file, unsigned int cmd, return ret; } -static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static unsigned int ovl_get_inode_flags(struct inode *inode) +{ + unsigned int flags = READ_ONCE(inode->i_flags); + unsigned int ovl_iflags = 0; + + if (flags & S_SYNC) + ovl_iflags |= FS_SYNC_FL; + if (flags & S_APPEND) + ovl_iflags |= FS_APPEND_FL; + if (flags & S_IMMUTABLE) + ovl_iflags |= FS_IMMUTABLE_FL; + if (flags & S_NOATIME) + ovl_iflags |= FS_NOATIME_FL; + + return ovl_iflags; +} + +static long ovl_ioctl_set_flags(struct file *file, unsigned long arg) { long ret; struct inode *inode = file_inode(file); + unsigned int flags; + unsigned int old_flags; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (get_user(flags, (int __user *) arg)) + return -EFAULT; + + ret = mnt_want_write_file(file); + if (ret) + return ret; + + inode_lock(inode); + + /* Check the capability before cred override */ + ret = -EPERM; + old_flags = ovl_get_inode_flags(inode); + if (((flags ^ old_flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) && + !capable(CAP_LINUX_IMMUTABLE)) + goto unlock; + + ret = ovl_maybe_copy_up(file_dentry(file), O_WRONLY); + if (ret) + goto unlock; + + ret = ovl_real_ioctl(file, FS_IOC_SETFLAGS, arg); + + ovl_copyflags(ovl_inode_real(inode), inode); +unlock: + inode_unlock(inode); + + mnt_drop_write_file(file); + + return ret; + +} + +static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long ret; switch (cmd) { case FS_IOC_GETFLAGS: @@ -383,23 +478,7 @@ static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; case FS_IOC_SETFLAGS: - if (!inode_owner_or_capable(inode)) - return -EACCES; - - ret = mnt_want_write_file(file); - if (ret) - return ret; - - ret = ovl_copy_up_with_data(file_dentry(file)); - if (!ret) { - ret = ovl_real_ioctl(file, cmd, arg); - - inode_lock(inode); - ovl_copyflags(ovl_inode_real(inode), inode); - inode_unlock(inode); - } - - mnt_drop_write_file(file); + ret = ovl_ioctl_set_flags(file, arg); break; default: diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 3b7ed5d2279c..b48273e846ad 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -832,7 +832,7 @@ struct inode *ovl_get_inode(struct super_block *sb, int fsid = bylower ? oip->lowerpath->layer->fsid : 0; bool is_dir, metacopy = false; unsigned long ino = 0; - int err = -ENOMEM; + int err = oip->newinode ? -EEXIST : -ENOMEM; if (!realinode) realinode = d_inode(lowerdentry); @@ -917,6 +917,7 @@ out: return inode; out_err: + pr_warn_ratelimited("overlayfs: failed to get inode (%i)\n", err); inode = ERR_PTR(err); goto out; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 9c6018287d57..d26efed9f80a 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -421,7 +421,7 @@ extern const struct file_operations ovl_file_operations; int ovl_copy_up(struct dentry *dentry); int ovl_copy_up_with_data(struct dentry *dentry); int ovl_copy_up_flags(struct dentry *dentry, int flags); -int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags); +int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct dentry *old, struct dentry *new); int ovl_set_attr(struct dentry *upper, struct kstat *stat); struct ovl_fh *ovl_encode_real_fh(struct dentry *real, bool is_upper); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 0116735cc321..5ec4fc2f5d7e 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -190,11 +190,13 @@ static struct inode *ovl_alloc_inode(struct super_block *sb) return &oi->vfs_inode; } -static void ovl_i_callback(struct rcu_head *head) +static void ovl_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); + struct ovl_inode *oi = OVL_I(inode); - kmem_cache_free(ovl_inode_cachep, OVL_I(inode)); + kfree(oi->redirect); + mutex_destroy(&oi->lock); + kmem_cache_free(ovl_inode_cachep, oi); } static void ovl_destroy_inode(struct inode *inode) @@ -207,10 +209,6 @@ static void ovl_destroy_inode(struct inode *inode) ovl_dir_cache_free(inode); else iput(oi->lowerdata); - kfree(oi->redirect); - mutex_destroy(&oi->lock); - - call_rcu(&inode->i_rcu, ovl_i_callback); } static void ovl_free_fs(struct ovl_fs *ofs) @@ -377,6 +375,7 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data) static const struct super_operations ovl_super_operations = { .alloc_inode = ovl_alloc_inode, + .free_inode = ovl_free_inode, .destroy_inode = ovl_destroy_inode, .drop_inode = generic_delete_inode, .put_super = ovl_put_super, diff --git a/fs/pipe.c b/fs/pipe.c index 070aad543382..41065901106b 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -188,9 +188,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/fs/proc/base.c b/fs/proc/base.c index ddef482f1334..9c8ca6cd3ce4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -407,7 +407,6 @@ static void unlock_trace(struct task_struct *task) static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - struct stack_trace trace; unsigned long *entries; int err; @@ -430,20 +429,17 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, if (!entries) return -ENOMEM; - trace.nr_entries = 0; - trace.max_entries = MAX_STACK_TRACE_DEPTH; - trace.entries = entries; - trace.skip = 0; - err = lock_trace(task); if (!err) { - unsigned int i; + unsigned int i, nr_entries; - save_stack_trace_tsk(task, &trace); + nr_entries = stack_trace_save_tsk(task, entries, + MAX_STACK_TRACE_DEPTH, 0); - for (i = 0; i < trace.nr_entries; i++) { + for (i = 0; i < nr_entries; i++) { seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } + unlock_trace(task); } kfree(entries); @@ -489,10 +485,9 @@ static int lstats_show_proc(struct seq_file *m, void *v) lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long bt = lr->backtrace[q]; + if (!bt) break; - if (bt == ULONG_MAX) - break; seq_printf(m, " %ps", (void *)bt); } seq_putc(m, '\n'); @@ -515,7 +510,7 @@ static ssize_t lstats_write(struct file *file, const char __user *buf, if (!task) return -ESRCH; - clear_all_latency_tracing(task); + clear_tsk_latency_tracing(task); put_task_struct(task); return count; @@ -616,24 +611,25 @@ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - long nr; - unsigned long args[6], sp, pc; + struct syscall_info info; + u64 *args = &info.data.args[0]; int res; res = lock_trace(task); if (res) return res; - if (task_current_syscall(task, &nr, args, 6, &sp, &pc)) + if (task_current_syscall(task, &info)) seq_puts(m, "running\n"); - else if (nr < 0) - seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc); + else if (info.data.nr < 0) + seq_printf(m, "%d 0x%llx 0x%llx\n", + info.data.nr, info.sp, info.data.instruction_pointer); else seq_printf(m, - "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", - nr, + "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n", + info.data.nr, args[0], args[1], args[2], args[3], args[4], args[5], - sp, pc); + info.sp, info.data.instruction_pointer); unlock_trace(task); return 0; @@ -2539,6 +2535,11 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, rcu_read_unlock(); return -EACCES; } + /* Prevent changes to overridden credentials. */ + if (current_cred() != current_real_cred()) { + rcu_read_unlock(); + return -EBUSY; + } rcu_read_unlock(); if (count > PAGE_SIZE) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index fc7e38def174..5f8d215b3fd0 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -72,17 +72,11 @@ static struct inode *proc_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void proc_i_callback(struct rcu_head *head) +static void proc_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(proc_inode_cachep, PROC_I(inode)); } -static void proc_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, proc_i_callback); -} - static void init_once(void *foo) { struct proc_inode *ei = (struct proc_inode *) foo; @@ -123,7 +117,7 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root) const struct super_operations proc_sops = { .alloc_inode = proc_alloc_inode, - .destroy_inode = proc_destroy_inode, + .free_inode = proc_free_inode, .drop_inode = generic_delete_inode, .evict_inode = proc_evict_inode, .statfs = simple_statfs, diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d65390727541..c74570736b24 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -13,6 +13,7 @@ #include <linux/namei.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/bpf-cgroup.h> #include "internal.h" static const struct dentry_operations proc_sys_dentry_operations; @@ -569,8 +570,8 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, struct inode *inode = file_inode(filp); struct ctl_table_header *head = grab_header(inode); struct ctl_table *table = PROC_I(inode)->sysctl_entry; + void *new_buf = NULL; ssize_t error; - size_t res; if (IS_ERR(head)) return PTR_ERR(head); @@ -588,11 +589,27 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, if (!table->proc_handler) goto out; + error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count, + ppos, &new_buf); + if (error) + goto out; + /* careful: calling conventions are nasty here */ - res = count; - error = table->proc_handler(table, write, buf, &res, ppos); + if (new_buf) { + mm_segment_t old_fs; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + error = table->proc_handler(table, write, (void __user *)new_buf, + &count, ppos); + set_fs(old_fs); + kfree(new_buf); + } else { + error = table->proc_handler(table, write, buf, &count, ppos); + } + if (!error) - error = res; + error = count; out: sysctl_head_finish(head); @@ -1626,9 +1643,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - if (parent) + if (parent) { put_links(header); - start_unregistering(header); + start_unregistering(header); + } + if (!--header->count) kfree_rcu(header, rcu); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 92a91e7816d8..01d4eb0e6bd1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); @@ -1151,7 +1169,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, break; } - mmu_notifier_range_init(&range, mm, 0, -1UL); + mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY, + 0, NULL, mm, 0, -1UL); mmu_notifier_invalidate_range_start(&range); } walk_page_range(0, mm->highest_vm_end, &clear_refs_walk); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index c60ee46f3e39..29e94e0b6d73 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -115,7 +115,7 @@ static int pstore_ftrace_seq_show(struct seq_file *s, void *v) rec = (struct pstore_ftrace_record *)(ps->record->buf + data->off); - seq_printf(s, "CPU:%d ts:%llu %08lx %08lx %pf <- %pF\n", + seq_printf(s, "CPU:%d ts:%llu %08lx %08lx %ps <- %pS\n", pstore_ftrace_decode_cpu(rec), pstore_ftrace_read_timestamp(rec), rec->ip, rec->parent_ip, (void *)rec->ip, diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 3d46fe302fcb..48c70aa4a3ec 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -28,14 +28,14 @@ static const struct super_operations qnx4_sops; static struct inode *qnx4_alloc_inode(struct super_block *sb); -static void qnx4_destroy_inode(struct inode *inode); +static void qnx4_free_inode(struct inode *inode); static int qnx4_remount(struct super_block *sb, int *flags, char *data); static int qnx4_statfs(struct dentry *, struct kstatfs *); static const struct super_operations qnx4_sops = { .alloc_inode = qnx4_alloc_inode, - .destroy_inode = qnx4_destroy_inode, + .free_inode = qnx4_free_inode, .statfs = qnx4_statfs, .remount_fs = qnx4_remount, }; @@ -342,17 +342,11 @@ static struct inode *qnx4_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void qnx4_i_callback(struct rcu_head *head) +static void qnx4_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(qnx4_inode_cachep, qnx4_i(inode)); } -static void qnx4_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, qnx4_i_callback); -} - static void init_once(void *foo) { struct qnx4_inode_info *ei = (struct qnx4_inode_info *) foo; diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 4aeb26bcb4d0..59cf45f6be49 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -29,14 +29,14 @@ static const struct super_operations qnx6_sops; static void qnx6_put_super(struct super_block *sb); static struct inode *qnx6_alloc_inode(struct super_block *sb); -static void qnx6_destroy_inode(struct inode *inode); +static void qnx6_free_inode(struct inode *inode); static int qnx6_remount(struct super_block *sb, int *flags, char *data); static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf); static int qnx6_show_options(struct seq_file *seq, struct dentry *root); static const struct super_operations qnx6_sops = { .alloc_inode = qnx6_alloc_inode, - .destroy_inode = qnx6_destroy_inode, + .free_inode = qnx6_free_inode, .put_super = qnx6_put_super, .statfs = qnx6_statfs, .remount_fs = qnx6_remount, @@ -602,17 +602,11 @@ static struct inode *qnx6_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void qnx6_i_callback(struct rcu_head *head) +static void qnx6_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(qnx6_inode_cachep, QNX6_I(inode)); } -static void qnx6_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, qnx6_i_callback); -} - static void init_once(void *foo) { struct qnx6_inode_info *ei = (struct qnx6_inode_info *) foo; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index fc20e06c56ba..9ad72ea7f71f 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -9,7 +9,7 @@ * on the Melbourne quota system as used on BSD derived systems. The internal * implementation is based on one of the several variants of the LINUX * inode-subsystem with added complexity of the diskquota system. - * + * * Author: Marco van Wieringen <mvw@planets.elm.net> * * Fixes: Dmitry Gorodchanin <pgmdsg@ibi.com>, 11 Feb 96 @@ -51,7 +51,7 @@ * Added journalled quota support, fix lock inversion problems * Jan Kara, <jack@suse.cz>, 2003,2004 * - * (C) Copyright 1994 - 1997 Marco van Wieringen + * (C) Copyright 1994 - 1997 Marco van Wieringen */ #include <linux/errno.h> @@ -197,7 +197,7 @@ static struct quota_format_type *find_quota_format(int id) int qm; spin_unlock(&dq_list_lock); - + for (qm = 0; module_names[qm].qm_fmt_id && module_names[qm].qm_fmt_id != id; qm++) ; @@ -424,10 +424,11 @@ int dquot_acquire(struct dquot *dquot) struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); mutex_lock(&dquot->dq_lock); - if (!test_bit(DQ_READ_B, &dquot->dq_flags)) + if (!test_bit(DQ_READ_B, &dquot->dq_flags)) { ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot); - if (ret < 0) - goto out_iolock; + if (ret < 0) + goto out_iolock; + } /* Make sure flags update is visible after dquot has been filled */ smp_mb__before_atomic(); set_bit(DQ_READ_B, &dquot->dq_flags); @@ -1049,7 +1050,9 @@ static void remove_dquot_ref(struct super_block *sb, int type, struct list_head *tofree_head) { struct inode *inode; +#ifdef CONFIG_QUOTA_DEBUG int reserved = 0; +#endif spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { @@ -1061,8 +1064,10 @@ static void remove_dquot_ref(struct super_block *sb, int type, */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { +#ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; +#endif remove_inode_dquot_ref(inode, type, tofree_head); } spin_unlock(&dq_data_lock); @@ -1663,7 +1668,7 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (!dquots[cnt]) continue; - if (flags & DQUOT_SPACE_RESERVE) { + if (reserve) { ret = dquot_add_space(dquots[cnt], 0, number, flags, &warn[cnt]); } else { @@ -1676,13 +1681,11 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) if (!dquots[cnt]) continue; spin_lock(&dquots[cnt]->dq_dqb_lock); - if (flags & DQUOT_SPACE_RESERVE) { - dquots[cnt]->dq_dqb.dqb_rsvspace -= - number; - } else { - dquots[cnt]->dq_dqb.dqb_curspace -= - number; - } + if (reserve) + dquot_free_reserved_space(dquots[cnt], + number); + else + dquot_decr_space(dquots[cnt], number); spin_unlock(&dquots[cnt]->dq_dqb_lock); } spin_unlock(&inode->i_lock); @@ -1733,7 +1736,7 @@ int dquot_alloc_inode(struct inode *inode) continue; /* Back out changes we already did */ spin_lock(&dquots[cnt]->dq_dqb_lock); - dquots[cnt]->dq_dqb.dqb_curinodes--; + dquot_decr_inodes(dquots[cnt], 1); spin_unlock(&dquots[cnt]->dq_dqb_lock); } goto warn_put_all; @@ -2397,7 +2400,7 @@ out_file_flags: out_fmt: put_quota_format(fmt); - return error; + return error; } /* Reenable quotas on remount RW */ @@ -2775,7 +2778,7 @@ int dquot_get_state(struct super_block *sb, struct qc_state *state) struct qc_type_state *tstate; struct quota_info *dqopt = sb_dqopt(sb); int type; - + memset(state, 0, sizeof(*state)); for (type = 0; type < MAXQUOTAS; type++) { if (!sb_has_quota_active(sb, type)) diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c index 7ac5298aba70..9f2b2573b83c 100644 --- a/fs/quota/quota_v1.c +++ b/fs/quota/quota_v1.c @@ -127,7 +127,7 @@ static int v1_check_quota_file(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; ulong blocks; - size_t off; + size_t off; struct v2_disk_dqheader dqhead; ssize_t size; loff_t isize; diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index a73e5b34db41..3c30034e733f 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -78,7 +78,7 @@ static int v2_check_quota_file(struct super_block *sb, int type) struct v2_disk_dqheader dqhead; static const uint quota_magics[] = V2_INITQMAGICS; static const uint quota_versions[] = V2_INITQVERSIONS; - + if (v2_read_header(sb, type, &dqhead)) return 0; if (le32_to_cpu(dqhead.dqh_magic) != quota_magics[type] || diff --git a/fs/read_write.c b/fs/read_write.c index 177ccc3d405a..c543d965e288 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -365,29 +365,37 @@ out_putf: int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { struct inode *inode; - loff_t pos; int retval = -EINVAL; inode = file_inode(file); if (unlikely((ssize_t) count < 0)) return retval; - pos = *ppos; - if (unlikely(pos < 0)) { - if (!unsigned_offsets(file)) - return retval; - if (count >= -pos) /* both values are in 0..LLONG_MAX */ - return -EOVERFLOW; - } else if (unlikely((loff_t) (pos + count) < 0)) { - if (!unsigned_offsets(file)) - return retval; - } - if (unlikely(inode->i_flctx && mandatory_lock(inode))) { - retval = locks_mandatory_area(inode, file, pos, pos + count - 1, - read_write == READ ? F_RDLCK : F_WRLCK); - if (retval < 0) - return retval; + /* + * ranged mandatory locking does not apply to streams - it makes sense + * only for files where position has a meaning. + */ + if (ppos) { + loff_t pos = *ppos; + + if (unlikely(pos < 0)) { + if (!unsigned_offsets(file)) + return retval; + if (count >= -pos) /* both values are in 0..LLONG_MAX */ + return -EOVERFLOW; + } else if (unlikely((loff_t) (pos + count) < 0)) { + if (!unsigned_offsets(file)) + return retval; + } + + if (unlikely(inode->i_flctx && mandatory_lock(inode))) { + retval = locks_mandatory_area(inode, file, pos, pos + count - 1, + read_write == READ ? F_RDLCK : F_WRLCK); + if (retval < 0) + return retval; + } } + return security_file_permission(file, read_write == READ ? MAY_READ : MAY_WRITE); } @@ -400,12 +408,13 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo ssize_t ret; init_sync_kiocb(&kiocb, filp); - kiocb.ki_pos = *ppos; + kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_init(&iter, READ, &iov, 1, len); ret = call_read_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); - *ppos = kiocb.ki_pos; + if (ppos) + *ppos = kiocb.ki_pos; return ret; } @@ -468,12 +477,12 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t ssize_t ret; init_sync_kiocb(&kiocb, filp); - kiocb.ki_pos = *ppos; + kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_init(&iter, WRITE, &iov, 1, len); ret = call_write_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); - if (ret > 0) + if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } @@ -558,14 +567,10 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return ret; } -static inline loff_t file_pos_read(struct file *file) -{ - return file->f_pos; -} - -static inline void file_pos_write(struct file *file, loff_t pos) +/* file_ppos returns &file->f_pos or NULL if file is stream */ +static inline loff_t *file_ppos(struct file *file) { - file->f_pos = pos; + return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) @@ -574,10 +579,14 @@ ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) ssize_t ret = -EBADF; if (f.file) { - loff_t pos = file_pos_read(f.file); - ret = vfs_read(f.file, buf, count, &pos); - if (ret >= 0) - file_pos_write(f.file, pos); + loff_t pos, *ppos = file_ppos(f.file); + if (ppos) { + pos = *ppos; + ppos = &pos; + } + ret = vfs_read(f.file, buf, count, ppos); + if (ret >= 0 && ppos) + f.file->f_pos = pos; fdput_pos(f); } return ret; @@ -594,10 +603,14 @@ ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) ssize_t ret = -EBADF; if (f.file) { - loff_t pos = file_pos_read(f.file); - ret = vfs_write(f.file, buf, count, &pos); - if (ret >= 0) - file_pos_write(f.file, pos); + loff_t pos, *ppos = file_ppos(f.file); + if (ppos) { + pos = *ppos; + ppos = &pos; + } + ret = vfs_write(f.file, buf, count, ppos); + if (ret >= 0 && ppos) + f.file->f_pos = pos; fdput_pos(f); } @@ -672,14 +685,15 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, ret = kiocb_set_rw_flags(&kiocb, flags); if (ret) return ret; - kiocb.ki_pos = *ppos; + kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = call_read_iter(filp, &kiocb, iter); else ret = call_write_iter(filp, &kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); - *ppos = kiocb.ki_pos; + if (ppos) + *ppos = kiocb.ki_pos; return ret; } @@ -1012,10 +1026,14 @@ static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, ssize_t ret = -EBADF; if (f.file) { - loff_t pos = file_pos_read(f.file); - ret = vfs_readv(f.file, vec, vlen, &pos, flags); - if (ret >= 0) - file_pos_write(f.file, pos); + loff_t pos, *ppos = file_ppos(f.file); + if (ppos) { + pos = *ppos; + ppos = &pos; + } + ret = vfs_readv(f.file, vec, vlen, ppos, flags); + if (ret >= 0 && ppos) + f.file->f_pos = pos; fdput_pos(f); } @@ -1032,10 +1050,14 @@ static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, ssize_t ret = -EBADF; if (f.file) { - loff_t pos = file_pos_read(f.file); - ret = vfs_writev(f.file, vec, vlen, &pos, flags); - if (ret >= 0) - file_pos_write(f.file, pos); + loff_t pos, *ppos = file_ppos(f.file); + if (ppos) { + pos = *ppos; + ppos = &pos; + } + ret = vfs_writev(f.file, vec, vlen, ppos, flags); + if (ret >= 0 && ppos) + f.file->f_pos = pos; fdput_pos(f); } diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 8a76f9d14bc6..36346dc4cec0 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -1844,7 +1844,7 @@ static int flush_used_journal_lists(struct super_block *s, * removes any nodes in table with name block and dev as bh. * only touchs the hnext and hprev pointers. */ -void remove_journal_hash(struct super_block *sb, +static void remove_journal_hash(struct super_block *sb, struct reiserfs_journal_cnode **table, struct reiserfs_journal_list *jl, unsigned long block, int remove_freed) diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 1fc934d24459..ab028ea0e561 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -650,17 +650,11 @@ static struct inode *reiserfs_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void reiserfs_i_callback(struct rcu_head *head) +static void reiserfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(reiserfs_inode_cachep, REISERFS_I(inode)); } -static void reiserfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, reiserfs_i_callback); -} - static void init_once(void *foo) { struct reiserfs_inode_info *ei = (struct reiserfs_inode_info *)foo; @@ -815,7 +809,7 @@ static struct dquot **reiserfs_get_dquots(struct inode *inode) static const struct super_operations reiserfs_sops = { .alloc_inode = reiserfs_alloc_inode, - .destroy_inode = reiserfs_destroy_inode, + .free_inode = reiserfs_free_inode, .write_inode = reiserfs_write_inode, .dirty_inode = reiserfs_dirty_inode, .evict_inode = reiserfs_evict_inode, diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 32d8986c26fb..b5b26d8a192c 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -450,6 +450,15 @@ fail: static inline __u32 xattr_hash(const char *msg, int len) { + /* + * csum_partial() gives different results for little-endian and + * big endian hosts. Images created on little-endian hosts and + * mounted on big-endian hosts(and vice versa) will see csum mismatches + * when trying to fetch xattrs. Treating the hash as __wsum_t would + * lower the frequency of mismatch. This is an endianness bug in + * reiserfs. The return statement would result in a sparse warning. Do + * not fix the sparse warning so as to not hide a reminder of the bug. + */ return csum_partial(msg, len, 0); } diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 6ccb51993a76..7d580f7c3f1d 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -381,18 +381,11 @@ static struct inode *romfs_alloc_inode(struct super_block *sb) /* * return a spent inode to the slab cache */ -static void romfs_i_callback(struct rcu_head *head) +static void romfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode)); } -static void romfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, romfs_i_callback); -} - /* * get filesystem statistics */ @@ -439,7 +432,7 @@ static int romfs_remount(struct super_block *sb, int *flags, char *data) static const struct super_operations romfs_super_ops = { .alloc_inode = romfs_alloc_inode, - .destroy_inode = romfs_destroy_inode, + .free_inode = romfs_free_inode, .statfs = romfs_statfs, .remount_fs = romfs_remount, }; diff --git a/fs/seq_file.c b/fs/seq_file.c index 1dea7a8a5255..abe27ec43176 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -317,6 +317,7 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence) switch (whence) { case SEEK_CUR: offset += file->f_pos; + /* fall through */ case SEEK_SET: if (offset < 0) break; diff --git a/fs/signalfd.c b/fs/signalfd.c index 757afc7c5895..44b6845b071c 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -176,6 +176,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info if (!nonblock) break; ret = -EAGAIN; + /* fall through */ default: spin_unlock_irq(¤t->sighand->siglock); return ret; diff --git a/fs/splice.c b/fs/splice.c index 3ee7e82df48f..25212dcca2df 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -330,8 +330,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = { .get = generic_pipe_buf_get, }; -static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { return 1; } @@ -1593,7 +1593,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1667,7 +1671,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 40e657386fa5..767046d9f65d 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -473,18 +473,11 @@ static struct inode *squashfs_alloc_inode(struct super_block *sb) } -static void squashfs_i_callback(struct rcu_head *head) +static void squashfs_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(squashfs_inode_cachep, squashfs_i(inode)); } -static void squashfs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, squashfs_i_callback); -} - - static struct file_system_type squashfs_fs_type = { .owner = THIS_MODULE, .name = "squashfs", @@ -496,7 +489,7 @@ MODULE_ALIAS_FS("squashfs"); static const struct super_operations squashfs_super_ops = { .alloc_inode = squashfs_alloc_inode, - .destroy_inode = squashfs_destroy_inode, + .free_inode = squashfs_free_inode, .statfs = squashfs_statfs, .put_super = squashfs_put_super, .remount_fs = squashfs_remount diff --git a/fs/stack.c b/fs/stack.c index a54e33ed10f1..664ed35558bd 100644 --- a/fs/stack.c +++ b/fs/stack.c @@ -21,11 +21,10 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src) i_size = i_size_read(src); /* - * But if CONFIG_LBDAF (on 32-bit), we ought to make an effort to - * keep the two halves of i_blocks in sync despite SMP or PREEMPT - - * though stat's generic_fillattr() doesn't bother, and we won't be - * applying quotas (where i_blocks does become important) at the - * upper level. + * But on 32-bit, we ought to make an effort to keep the two halves of + * i_blocks in sync despite SMP or PREEMPT - though stat's + * generic_fillattr() doesn't bother, and we won't be applying quotas + * (where i_blocks does become important) at the upper level. * * We don't actually know what locking is used at the lower level; * but if it's a filesystem that supports quotas, it will be using @@ -44,9 +43,9 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src) * include/linux/fs.h). We don't necessarily hold i_mutex when this * is called, so take i_lock for that case. * - * And if CONFIG_LBDAF (on 32-bit), continue our effort to keep the - * two halves of i_blocks in sync despite SMP or PREEMPT: use i_lock - * for that case too, and do both at once by combining the tests. + * And if on 32-bit, continue our effort to keep the two halves of + * i_blocks in sync despite SMP or PREEMPT: use i_lock for that case + * too, and do both at once by combining the tests. * * There is none of this locking overhead in the 64-bit case. */ diff --git a/fs/super.c b/fs/super.c index 583a0124bc39..2739f57515f8 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1467,11 +1467,6 @@ int vfs_get_tree(struct fs_context *fc) struct super_block *sb; int error; - if (fc->fs_type->fs_flags & FS_REQUIRES_DEV && !fc->source) { - errorf(fc, "Filesystem requires source device"); - return -ENOENT; - } - if (fc->root) return -EBUSY; diff --git a/fs/sync.c b/fs/sync.c index b54e0541ad89..4d1ff010bc5a 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -234,58 +234,10 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd) return do_fsync(fd, 1); } -/* - * sys_sync_file_range() permits finely controlled syncing over a segment of - * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is - * zero then sys_sync_file_range() will operate from offset out to EOF. - * - * The flag bits are: - * - * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range - * before performing the write. - * - * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the - * range which are not presently under writeback. Note that this may block for - * significant periods due to exhaustion of disk request structures. - * - * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range - * after performing the write. - * - * Useful combinations of the flag bits are: - * - * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages - * in the range which were dirty on entry to sys_sync_file_range() are placed - * under writeout. This is a start-write-for-data-integrity operation. - * - * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which - * are not presently under writeout. This is an asynchronous flush-to-disk - * operation. Not suitable for data integrity operations. - * - * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for - * completion of writeout of all pages in the range. This will be used after an - * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait - * for that operation to complete and to return the result. - * - * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER: - * a traditional sync() operation. This is a write-for-data-integrity operation - * which will ensure that all pages in the range which were dirty on entry to - * sys_sync_file_range() are committed to disk. - * - * - * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any - * I/O errors or ENOSPC conditions and will return those to the caller, after - * clearing the EIO and ENOSPC flags in the address_space. - * - * It should be noted that none of these operations write out the file's - * metadata. So unless the application is strictly performing overwrites of - * already-instantiated disk blocks, there are no guarantees here that the data - * will be available after a crash. - */ -int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, - unsigned int flags) +int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, + unsigned int flags) { int ret; - struct fd f; struct address_space *mapping; loff_t endbyte; /* inclusive */ umode_t i_mode; @@ -325,41 +277,105 @@ int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, else endbyte--; /* inclusive */ - ret = -EBADF; - f = fdget(fd); - if (!f.file) - goto out; - - i_mode = file_inode(f.file)->i_mode; + i_mode = file_inode(file)->i_mode; ret = -ESPIPE; if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) && !S_ISLNK(i_mode)) - goto out_put; + goto out; - mapping = f.file->f_mapping; + mapping = file->f_mapping; ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) { - ret = file_fdatawait_range(f.file, offset, endbyte); + ret = file_fdatawait_range(file, offset, endbyte); if (ret < 0) - goto out_put; + goto out; } if (flags & SYNC_FILE_RANGE_WRITE) { + int sync_mode = WB_SYNC_NONE; + + if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) == + SYNC_FILE_RANGE_WRITE_AND_WAIT) + sync_mode = WB_SYNC_ALL; + ret = __filemap_fdatawrite_range(mapping, offset, endbyte, - WB_SYNC_NONE); + sync_mode); if (ret < 0) - goto out_put; + goto out; } if (flags & SYNC_FILE_RANGE_WAIT_AFTER) - ret = file_fdatawait_range(f.file, offset, endbyte); + ret = file_fdatawait_range(file, offset, endbyte); -out_put: - fdput(f); out: return ret; } +/* + * ksys_sync_file_range() permits finely controlled syncing over a segment of + * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is + * zero then ksys_sync_file_range() will operate from offset out to EOF. + * + * The flag bits are: + * + * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range + * before performing the write. + * + * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the + * range which are not presently under writeback. Note that this may block for + * significant periods due to exhaustion of disk request structures. + * + * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range + * after performing the write. + * + * Useful combinations of the flag bits are: + * + * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages + * in the range which were dirty on entry to ksys_sync_file_range() are placed + * under writeout. This is a start-write-for-data-integrity operation. + * + * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which + * are not presently under writeout. This is an asynchronous flush-to-disk + * operation. Not suitable for data integrity operations. + * + * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for + * completion of writeout of all pages in the range. This will be used after an + * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait + * for that operation to complete and to return the result. + * + * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER + * (a.k.a. SYNC_FILE_RANGE_WRITE_AND_WAIT): + * a traditional sync() operation. This is a write-for-data-integrity operation + * which will ensure that all pages in the range which were dirty on entry to + * ksys_sync_file_range() are written to disk. It should be noted that disk + * caches are not flushed by this call, so there are no guarantees here that the + * data will be available on disk after a crash. + * + * + * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any + * I/O errors or ENOSPC conditions and will return those to the caller, after + * clearing the EIO and ENOSPC flags in the address_space. + * + * It should be noted that none of these operations write out the file's + * metadata. So unless the application is strictly performing overwrites of + * already-instantiated disk blocks, there are no guarantees here that the data + * will be available after a crash. + */ +int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, + unsigned int flags) +{ + int ret; + struct fd f; + + ret = -EBADF; + f = fdget(fd); + if (f.file) + ret = sync_file_range(f.file, offset, nbytes, flags); + + fdput(f); + return ret; +} + SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, unsigned int, flags) { diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 273736f41be3..02b1d9d0c182 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -313,17 +313,11 @@ static struct inode *sysv_alloc_inode(struct super_block *sb) return &si->vfs_inode; } -static void sysv_i_callback(struct rcu_head *head) +static void sysv_free_in_core_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(sysv_inode_cachep, SYSV_I(inode)); } -static void sysv_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, sysv_i_callback); -} - static void init_once(void *p) { struct sysv_inode_info *si = (struct sysv_inode_info *)p; @@ -333,7 +327,7 @@ static void init_once(void *p) const struct super_operations sysv_sops = { .alloc_inode = sysv_alloc_inode, - .destroy_inode = sysv_destroy_inode, + .free_inode = sysv_free_in_core_inode, .write_inode = sysv_write_inode, .evict_inode = sysv_evict_inode, .put_super = sysv_put_super, diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index 4d5d20491ffd..ea2414b385ec 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -28,21 +28,6 @@ static int add_nondir(struct dentry *dentry, struct inode *inode) return err; } -static int sysv_hash(const struct dentry *dentry, struct qstr *qstr) -{ - /* Truncate the name in place, avoids having to define a compare - function. */ - if (qstr->len > SYSV_NAMELEN) { - qstr->len = SYSV_NAMELEN; - qstr->hash = full_name_hash(dentry, qstr->name, qstr->len); - } - return 0; -} - -const struct dentry_operations sysv_dentry_operations = { - .d_hash = sysv_hash, -}; - static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { struct inode * inode = NULL; diff --git a/fs/sysv/super.c b/fs/sysv/super.c index 89765ddfb738..d3b2f54d6449 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -312,7 +312,6 @@ static int complete_read_super(struct super_block *sb, int silent, int size) flavour_setup[sbi->s_type](sbi, &sb->s_max_links); - sbi->s_truncate = 1; sbi->s_ndatazones = sbi->s_nzones - sbi->s_firstdatazone; sbi->s_inodes_per_block = bsize >> 6; sbi->s_inodes_per_block_1 = (bsize >> 6)-1; @@ -334,8 +333,6 @@ static int complete_read_super(struct super_block *sb, int silent, int size) sb->s_op = &sysv_sops; if (sbi->s_forced_ro) sb->s_flags |= SB_RDONLY; - if (sbi->s_truncate) - sb->s_d_op = &sysv_dentry_operations; root_inode = sysv_iget(sb, SYSV_ROOT_INO); if (IS_ERR(root_inode)) { printk("SysV FS: get root inode failed\n"); diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h index e913698779c0..1cff585526b1 100644 --- a/fs/sysv/sysv.h +++ b/fs/sysv/sysv.h @@ -23,8 +23,6 @@ struct sysv_sb_info { struct super_block *s_sb; /* VFS superblock */ int s_type; /* file system type: FSTYPE_{XENIX|SYSV|COH} */ char s_bytesex; /* bytesex (le/be/pdp) */ - char s_truncate; /* if 1: names > SYSV_NAMELEN chars are truncated */ - /* if 0: they are disallowed (ENAMETOOLONG) */ unsigned int s_inodes_per_block; /* number of inodes per block */ unsigned int s_inodes_per_block_1; /* inodes_per_block - 1 */ unsigned int s_inodes_per_block_bits; /* log2(inodes_per_block) */ @@ -166,7 +164,6 @@ extern const struct file_operations sysv_file_operations; extern const struct file_operations sysv_dir_operations; extern const struct address_space_operations sysv_aops; extern const struct super_operations sysv_sops; -extern const struct dentry_operations sysv_dentry_operations; enum { diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c index 5bf5fd08879e..60f43b93d06e 100644 --- a/fs/ubifs/auth.c +++ b/fs/ubifs/auth.c @@ -33,7 +33,6 @@ int __ubifs_node_calc_hash(const struct ubifs_info *c, const void *node, int err; shash->tfm = c->hash_tfm; - shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP; err = crypto_shash_digest(shash, node, le32_to_cpu(ch->len), hash); if (err < 0) @@ -56,7 +55,6 @@ static int ubifs_hash_calc_hmac(const struct ubifs_info *c, const u8 *hash, int err; shash->tfm = c->hmac_tfm; - shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP; err = crypto_shash_digest(shash, hash, c->hash_len, hmac); if (err < 0) @@ -78,7 +76,6 @@ static int ubifs_hash_calc_hmac(const struct ubifs_info *c, const u8 *hash, int ubifs_prepare_auth_node(struct ubifs_info *c, void *node, struct shash_desc *inhash) { - SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm); struct ubifs_auth_node *auth = node; u8 *hash; int err; @@ -87,13 +84,16 @@ int ubifs_prepare_auth_node(struct ubifs_info *c, void *node, if (!hash) return -ENOMEM; - hash_desc->tfm = c->hash_tfm; - hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - ubifs_shash_copy_state(c, inhash, hash_desc); + { + SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm); - err = crypto_shash_final(hash_desc, hash); - if (err) - goto out; + hash_desc->tfm = c->hash_tfm; + ubifs_shash_copy_state(c, inhash, hash_desc); + + err = crypto_shash_final(hash_desc, hash); + if (err) + goto out; + } err = ubifs_hash_calc_hmac(c, hash, auth->hmac); if (err) @@ -123,7 +123,6 @@ static struct shash_desc *ubifs_get_desc(const struct ubifs_info *c, return ERR_PTR(-ENOMEM); desc->tfm = tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; err = crypto_shash_init(desc); if (err) { @@ -147,24 +146,6 @@ struct shash_desc *__ubifs_hash_get_desc(const struct ubifs_info *c) } /** - * __ubifs_shash_final - finalize shash - * @c: UBIFS file-system description object - * @desc: the descriptor - * @out: the output hash - * - * Simple wrapper around crypto_shash_final(), safe to be called with - * disabled authentication. - */ -int __ubifs_shash_final(const struct ubifs_info *c, struct shash_desc *desc, - u8 *out) -{ - if (ubifs_authenticated(c)) - return crypto_shash_final(desc, out); - - return 0; -} - -/** * ubifs_bad_hash - Report hash mismatches * @c: UBIFS file-system description object * @node: the node @@ -364,7 +345,6 @@ static int ubifs_node_calc_hmac(const struct ubifs_info *c, const void *node, ubifs_assert(c, ofs_hmac + hmac_len < len); shash->tfm = c->hmac_tfm; - shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP; err = crypto_shash_init(shash); if (err) @@ -483,7 +463,6 @@ int ubifs_hmac_wkm(struct ubifs_info *c, u8 *hmac) return 0; shash->tfm = c->hmac_tfm; - shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP; err = crypto_shash_init(shash); if (err) diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index c49ff50fdceb..3a2613038e88 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -1603,7 +1603,6 @@ int dbg_walk_index(struct ubifs_info *c, dbg_leaf_callback leaf_cb, err = PTR_ERR(child); goto out_unlock; } - zbr->znode = child; } znode = child; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 5767b373a8ff..1a379b596b0d 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -220,11 +220,9 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino); - err = fscrypt_prepare_lookup(dir, dentry, flags); - if (err) - return ERR_PTR(err); - - err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &nm); + err = fscrypt_prepare_lookup(dir, dentry, &nm); + if (err == -ENOENT) + return d_splice_alias(NULL, dentry); if (err) return ERR_PTR(err); @@ -792,16 +790,14 @@ static int ubifs_unlink(struct inode *dir, struct dentry *dentry) dentry, inode->i_ino, inode->i_nlink, dir->i_ino); - if (ubifs_crypt_is_encrypted(dir)) { - err = fscrypt_get_encryption_info(dir); - if (err && err != -ENOKEY) - return err; - } - err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &nm); if (err) return err; + err = ubifs_purge_xattrs(inode); + if (err) + return err; + sz_change = CALC_DENT_SIZE(fname_len(&nm)); ubifs_assert(c, inode_is_locked(dir)); @@ -902,16 +898,14 @@ static int ubifs_rmdir(struct inode *dir, struct dentry *dentry) if (err) return err; - if (ubifs_crypt_is_encrypted(dir)) { - err = fscrypt_get_encryption_info(dir); - if (err && err != -ENOKEY) - return err; - } - err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &nm); if (err) return err; + err = ubifs_purge_xattrs(inode); + if (err) + return err; + sz_change = CALC_DENT_SIZE(fname_len(&nm)); err = ubifs_budget_space(c, &req); @@ -1294,9 +1288,14 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, old_dentry, old_inode->i_ino, old_dir->i_ino, new_dentry, new_dir->i_ino, flags); - if (unlink) + if (unlink) { ubifs_assert(c, inode_is_locked(new_inode)); + err = ubifs_purge_xattrs(new_inode); + if (err) + return err; + } + if (unlink && is_dir) { err = ubifs_check_dir_empty(new_inode); if (err) @@ -1652,9 +1651,7 @@ const struct inode_operations ubifs_dir_inode_operations = { #ifdef CONFIG_UBIFS_FS_XATTR .listxattr = ubifs_listxattr, #endif -#ifdef CONFIG_UBIFS_ATIME_SUPPORT .update_time = ubifs_update_time, -#endif .tmpfile = ubifs_tmpfile, }; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 5d2ffb1a45fc..512e7d9c60cd 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1375,7 +1375,6 @@ static inline int mctime_update_needed(const struct inode *inode, return 0; } -#ifdef CONFIG_UBIFS_ATIME_SUPPORT /** * ubifs_update_time - update time of inode. * @inode: inode to update @@ -1392,6 +1391,9 @@ int ubifs_update_time(struct inode *inode, struct timespec64 *time, int iflags = I_DIRTY_TIME; int err, release; + if (!IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT)) + return generic_update_time(inode, time, flags); + err = ubifs_budget_space(c, &req); if (err) return err; @@ -1414,7 +1416,6 @@ int ubifs_update_time(struct inode *inode, struct timespec64 *time, ubifs_release_budget(c, &req); return 0; } -#endif /** * update_mctime - update mtime and ctime of an inode. @@ -1623,9 +1624,10 @@ static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) if (err) return err; vma->vm_ops = &ubifs_file_vm_ops; -#ifdef CONFIG_UBIFS_ATIME_SUPPORT - file_accessed(file); -#endif + + if (IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT)) + file_accessed(file); + return 0; } @@ -1663,9 +1665,7 @@ const struct inode_operations ubifs_file_inode_operations = { #ifdef CONFIG_UBIFS_FS_XATTR .listxattr = ubifs_listxattr, #endif -#ifdef CONFIG_UBIFS_ATIME_SUPPORT .update_time = ubifs_update_time, -#endif }; const struct inode_operations ubifs_symlink_inode_operations = { @@ -1675,9 +1675,7 @@ const struct inode_operations ubifs_symlink_inode_operations = { #ifdef CONFIG_UBIFS_FS_XATTR .listxattr = ubifs_listxattr, #endif -#ifdef CONFIG_UBIFS_ATIME_SUPPORT .update_time = ubifs_update_time, -#endif }; const struct file_operations ubifs_file_operations = { diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index f9646835b026..5deaae7fcead 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -747,12 +747,6 @@ static int cmp_dirty_idx(const struct ubifs_lprops **a, return lpa->dirty + lpa->free - lpb->dirty - lpb->free; } -static void swap_dirty_idx(struct ubifs_lprops **a, struct ubifs_lprops **b, - int size) -{ - swap(*a, *b); -} - /** * ubifs_save_dirty_idx_lnums - save an array of the most dirty index LEB nos. * @c: the UBIFS file-system description object @@ -772,8 +766,7 @@ int ubifs_save_dirty_idx_lnums(struct ubifs_info *c) sizeof(void *) * c->dirty_idx.cnt); /* Sort it so that the dirtiest is now at the end */ sort(c->dirty_idx.arr, c->dirty_idx.cnt, sizeof(void *), - (int (*)(const void *, const void *))cmp_dirty_idx, - (void (*)(void *, void *, int))swap_dirty_idx); + (int (*)(const void *, const void *))cmp_dirty_idx, NULL); dbg_find("found %d dirty index LEBs", c->dirty_idx.cnt); if (c->dirty_idx.cnt) dbg_find("dirtiest index LEB is %d with dirty %d and free %d", diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 82e4e6a30b04..6b05b3ec500e 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -193,7 +193,6 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return err; } case FS_IOC_SET_ENCRYPTION_POLICY: { -#ifdef CONFIG_FS_ENCRYPTION struct ubifs_info *c = inode->i_sb->s_fs_info; err = ubifs_enable_encryption(c); @@ -201,17 +200,9 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return err; return fscrypt_ioctl_set_policy(file, (const void __user *)arg); -#else - return -EOPNOTSUPP; -#endif } - case FS_IOC_GET_ENCRYPTION_POLICY: { -#ifdef CONFIG_FS_ENCRYPTION + case FS_IOC_GET_ENCRYPTION_POLICY: return fscrypt_ioctl_get_policy(file, (void __user *)arg); -#else - return -EOPNOTSUPP; -#endif - } default: return -ENOTTY; diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 729dc76c83df..74a7306978d0 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -852,10 +852,11 @@ out_free: int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) { int err, lnum, offs; - struct ubifs_ino_node *ino; + struct ubifs_ino_node *ino, *ino_start; struct ubifs_inode *ui = ubifs_inode(inode); - int sync = 0, write_len, ilen = UBIFS_INO_NODE_SZ; + int sync = 0, write_len = 0, ilen = UBIFS_INO_NODE_SZ; int last_reference = !inode->i_nlink; + int kill_xattrs = ui->xattr_cnt && last_reference; u8 hash[UBIFS_HASH_ARR_SZ]; dbg_jnl("ino %lu, nlink %u", inode->i_ino, inode->i_nlink); @@ -867,14 +868,16 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) if (!last_reference) { ilen += ui->data_len; sync = IS_SYNC(inode); + } else if (kill_xattrs) { + write_len += UBIFS_INO_NODE_SZ * ui->xattr_cnt; } if (ubifs_authenticated(c)) - write_len = ALIGN(ilen, 8) + ubifs_auth_node_sz(c); + write_len += ALIGN(ilen, 8) + ubifs_auth_node_sz(c); else - write_len = ilen; + write_len += ilen; - ino = kmalloc(write_len, GFP_NOFS); + ino_start = ino = kmalloc(write_len, GFP_NOFS); if (!ino) return -ENOMEM; @@ -883,12 +886,59 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) if (err) goto out_free; + if (kill_xattrs) { + union ubifs_key key; + struct fscrypt_name nm = {0}; + struct inode *xino; + struct ubifs_dent_node *xent, *pxent = NULL; + + if (ui->xattr_cnt >= ubifs_xattr_max_cnt(c)) { + ubifs_err(c, "Cannot delete inode, it has too much xattrs!"); + goto out_release; + } + + lowest_xent_key(c, &key, inode->i_ino); + while (1) { + xent = ubifs_tnc_next_ent(c, &key, &nm); + if (IS_ERR(xent)) { + err = PTR_ERR(xent); + if (err == -ENOENT) + break; + + goto out_release; + } + + fname_name(&nm) = xent->name; + fname_len(&nm) = le16_to_cpu(xent->nlen); + + xino = ubifs_iget(c->vfs_sb, xent->inum); + if (IS_ERR(xino)) { + err = PTR_ERR(xino); + ubifs_err(c, "dead directory entry '%s', error %d", + xent->name, err); + ubifs_ro_mode(c, err); + goto out_release; + } + ubifs_assert(c, ubifs_inode(xino)->xattr); + + clear_nlink(xino); + pack_inode(c, ino, xino, 0); + ino = (void *)ino + UBIFS_INO_NODE_SZ; + iput(xino); + + kfree(pxent); + pxent = xent; + key_read(c, &xent->key, &key); + } + kfree(pxent); + } + pack_inode(c, ino, inode, 1); err = ubifs_node_calc_hash(c, ino, hash); if (err) goto out_release; - err = write_head(c, BASEHD, ino, write_len, &lnum, &offs, sync); + err = write_head(c, BASEHD, ino_start, write_len, &lnum, &offs, sync); if (err) goto out_release; if (!sync) @@ -903,7 +953,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) if (err) goto out_ro; ubifs_delete_orphan(c, inode->i_ino); - err = ubifs_add_dirt(c, lnum, ilen); + err = ubifs_add_dirt(c, lnum, write_len); } else { union ubifs_key key; @@ -917,7 +967,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) spin_lock(&ui->ui_lock); ui->synced_i_size = ui->ui_size; spin_unlock(&ui->ui_lock); - kfree(ino); + kfree(ino_start); return 0; out_release: @@ -926,7 +976,7 @@ out_ro: ubifs_ro_mode(c, err); finish_reservation(c); out_free: - kfree(ino); + kfree(ino_start); return err; } @@ -966,8 +1016,8 @@ int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode) ubifs_assert(c, inode->i_nlink == 0); - if (ui->del_cmtno != c->cmt_no) - /* A commit happened for sure */ + if (ui->xattr_cnt || ui->del_cmtno != c->cmt_no) + /* A commit happened for sure or inode hosts xattrs */ return ubifs_jnl_write_inode(c, inode); down_read(&c->commit_sem); diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index 6f87237fdbf4..78a6e97f846e 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -288,6 +288,14 @@ static inline int ubifs_next_log_lnum(const struct ubifs_info *c, int lnum) return lnum; } +static inline int ubifs_xattr_max_cnt(struct ubifs_info *c) +{ + int max_xattrs = (c->leb_size / 2) / UBIFS_INO_NODE_SZ; + + ubifs_assert(c, max_xattrs < c->max_orphans); + return max_xattrs; +} + const char *ubifs_assert_action_name(struct ubifs_info *c); #endif /* __UBIFS_MISC_H__ */ diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 8f70494efb0c..2f1618f300fb 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -54,30 +54,24 @@ static int dbg_check_orphans(struct ubifs_info *c); -/** - * ubifs_add_orphan - add an orphan. - * @c: UBIFS file-system description object - * @inum: orphan inode number - * - * Add an orphan. This function is called when an inodes link count drops to - * zero. - */ -int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) +static struct ubifs_orphan *orphan_add(struct ubifs_info *c, ino_t inum, + struct ubifs_orphan *parent_orphan) { struct ubifs_orphan *orphan, *o; struct rb_node **p, *parent = NULL; orphan = kzalloc(sizeof(struct ubifs_orphan), GFP_NOFS); if (!orphan) - return -ENOMEM; + return ERR_PTR(-ENOMEM); orphan->inum = inum; orphan->new = 1; + INIT_LIST_HEAD(&orphan->child_list); spin_lock(&c->orphan_lock); if (c->tot_orphans >= c->max_orphans) { spin_unlock(&c->orphan_lock); kfree(orphan); - return -ENFILE; + return ERR_PTR(-ENFILE); } p = &c->orph_tree.rb_node; while (*p) { @@ -91,7 +85,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) ubifs_err(c, "orphaned twice"); spin_unlock(&c->orphan_lock); kfree(orphan); - return 0; + return ERR_PTR(-EINVAL); } } c->tot_orphans += 1; @@ -100,24 +94,22 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) rb_insert_color(&orphan->rb, &c->orph_tree); list_add_tail(&orphan->list, &c->orph_list); list_add_tail(&orphan->new_list, &c->orph_new); + + if (parent_orphan) { + list_add_tail(&orphan->child_list, + &parent_orphan->child_list); + } + spin_unlock(&c->orphan_lock); dbg_gen("ino %lu", (unsigned long)inum); - return 0; + return orphan; } -/** - * ubifs_delete_orphan - delete an orphan. - * @c: UBIFS file-system description object - * @inum: orphan inode number - * - * Delete an orphan. This function is called when an inode is deleted. - */ -void ubifs_delete_orphan(struct ubifs_info *c, ino_t inum) +static struct ubifs_orphan *lookup_orphan(struct ubifs_info *c, ino_t inum) { struct ubifs_orphan *o; struct rb_node *p; - spin_lock(&c->orphan_lock); p = c->orph_tree.rb_node; while (p) { o = rb_entry(p, struct ubifs_orphan, rb); @@ -126,37 +118,124 @@ void ubifs_delete_orphan(struct ubifs_info *c, ino_t inum) else if (inum > o->inum) p = p->rb_right; else { - if (o->del) { - spin_unlock(&c->orphan_lock); - dbg_gen("deleted twice ino %lu", - (unsigned long)inum); - return; - } - if (o->cmt) { - o->del = 1; - o->dnext = c->orph_dnext; - c->orph_dnext = o; - spin_unlock(&c->orphan_lock); - dbg_gen("delete later ino %lu", - (unsigned long)inum); - return; - } - rb_erase(p, &c->orph_tree); - list_del(&o->list); - c->tot_orphans -= 1; - if (o->new) { - list_del(&o->new_list); - c->new_orphans -= 1; - } - spin_unlock(&c->orphan_lock); - kfree(o); - dbg_gen("inum %lu", (unsigned long)inum); - return; + return o; } } + return NULL; +} + +static void __orphan_drop(struct ubifs_info *c, struct ubifs_orphan *o) +{ + rb_erase(&o->rb, &c->orph_tree); + list_del(&o->list); + c->tot_orphans -= 1; + + if (o->new) { + list_del(&o->new_list); + c->new_orphans -= 1; + } + + kfree(o); +} + +static void orphan_delete(struct ubifs_info *c, ino_t inum) +{ + struct ubifs_orphan *orph, *child_orph, *tmp_o; + + spin_lock(&c->orphan_lock); + + orph = lookup_orphan(c, inum); + if (!orph) { + spin_unlock(&c->orphan_lock); + ubifs_err(c, "missing orphan ino %lu", (unsigned long)inum); + dump_stack(); + + return; + } + + if (orph->del) { + spin_unlock(&c->orphan_lock); + dbg_gen("deleted twice ino %lu", + (unsigned long)inum); + return; + } + + if (orph->cmt) { + orph->del = 1; + orph->dnext = c->orph_dnext; + c->orph_dnext = orph; + spin_unlock(&c->orphan_lock); + dbg_gen("delete later ino %lu", + (unsigned long)inum); + return; + } + + list_for_each_entry_safe(child_orph, tmp_o, &orph->child_list, child_list) { + list_del(&child_orph->child_list); + __orphan_drop(c, child_orph); + } + + __orphan_drop(c, orph); + spin_unlock(&c->orphan_lock); - ubifs_err(c, "missing orphan ino %lu", (unsigned long)inum); - dump_stack(); +} + +/** + * ubifs_add_orphan - add an orphan. + * @c: UBIFS file-system description object + * @inum: orphan inode number + * + * Add an orphan. This function is called when an inodes link count drops to + * zero. + */ +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 fscrypt_name nm = {0}; + struct ubifs_orphan *xattr_orphan; + struct ubifs_orphan *orphan; + + orphan = orphan_add(c, inum, NULL); + if (IS_ERR(orphan)) + return PTR_ERR(orphan); + + lowest_xent_key(c, &key, inum); + while (1) { + xent = ubifs_tnc_next_ent(c, &key, &nm); + if (IS_ERR(xent)) { + err = PTR_ERR(xent); + if (err == -ENOENT) + break; + return err; + } + + fname_name(&nm) = xent->name; + fname_len(&nm) = le16_to_cpu(xent->nlen); + xattr_inum = le64_to_cpu(xent->inum); + + xattr_orphan = orphan_add(c, xattr_inum, orphan); + if (IS_ERR(xattr_orphan)) + return PTR_ERR(xattr_orphan); + + key_read(c, &xent->key, &key); + } + + return 0; +} + +/** + * ubifs_delete_orphan - delete an orphan. + * @c: UBIFS file-system description object + * @inum: orphan inode number + * + * Delete an orphan. This function is called when an inode is deleted. + */ +void ubifs_delete_orphan(struct ubifs_info *c, ino_t inum) +{ + orphan_delete(c, inum); } /** @@ -611,10 +690,16 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb, n = (le32_to_cpu(orph->ch.len) - UBIFS_ORPH_NODE_SZ) >> 3; for (i = 0; i < n; i++) { + union ubifs_key key1, key2; + inum = le64_to_cpu(orph->inos[i]); dbg_rcvry("deleting orphaned inode %lu", (unsigned long)inum); - err = ubifs_tnc_remove_ino(c, inum); + + lowest_ino_key(c, &key1, inum); + highest_ino_key(c, &key2, inum); + + err = ubifs_tnc_remove_range(c, &key1, &key2); if (err) return err; err = insert_dead_orphan(c, inum); @@ -744,26 +829,15 @@ struct check_info { struct rb_root root; }; -static int dbg_find_orphan(struct ubifs_info *c, ino_t inum) +static bool dbg_find_orphan(struct ubifs_info *c, ino_t inum) { - struct ubifs_orphan *o; - struct rb_node *p; + bool found = false; spin_lock(&c->orphan_lock); - p = c->orph_tree.rb_node; - while (p) { - o = rb_entry(p, struct ubifs_orphan, rb); - if (inum < o->inum) - p = p->rb_left; - else if (inum > o->inum) - p = p->rb_right; - else { - spin_unlock(&c->orphan_lock); - return 1; - } - } + found = !!lookup_orphan(c, inum); spin_unlock(&c->orphan_lock); - return 0; + + return found; } static int dbg_ins_check_orphan(struct rb_root *root, ino_t inum) diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 0a0e65c07c6d..5c8a81a019a4 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -576,7 +576,6 @@ static int authenticate_sleb_hash(struct ubifs_info *c, struct shash_desc *log_h SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm); hash_desc->tfm = c->hash_tfm; - hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; ubifs_shash_copy_state(c, log_hash, hash_desc); return crypto_shash_final(hash_desc, hash); @@ -587,7 +586,6 @@ static int authenticate_sleb_hmac(struct ubifs_info *c, u8 *hash, u8 *hmac) SHASH_DESC_ON_STACK(hmac_desc, c->hmac_tfm); hmac_desc->tfm = c->hmac_tfm; - hmac_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; return crypto_shash_digest(hmac_desc, hash, c->hash_len, hmac); } diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 67fac1e8adfb..2afc8b1d4c3b 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -748,14 +748,12 @@ int ubifs_read_superblock(struct ubifs_info *c) goto out; } -#ifndef CONFIG_FS_ENCRYPTION - if (c->encrypted) { + if (!IS_ENABLED(CONFIG_UBIFS_FS_ENCRYPTION) && c->encrypted) { ubifs_err(c, "file system contains encrypted files but UBIFS" " was built without crypto support."); err = -EINVAL; goto out; } -#endif /* Automatically increase file system size to the maximum size */ c->old_leb_cnt = c->leb_cnt; @@ -943,6 +941,9 @@ int ubifs_enable_encryption(struct ubifs_info *c) int err; struct ubifs_sb_node *sup = c->sup_node; + if (!IS_ENABLED(CONFIG_UBIFS_FS_ENCRYPTION)) + return -EOPNOTSUPP; + if (c->encrypted) return 0; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 8dc2818fdd84..04b8ecfd3470 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -129,9 +129,10 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) goto out_ino; inode->i_flags |= S_NOCMTIME; -#ifndef CONFIG_UBIFS_ATIME_SUPPORT - inode->i_flags |= S_NOATIME; -#endif + + if (!IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT)) + inode->i_flags |= S_NOATIME; + set_nlink(inode, le32_to_cpu(ino->nlink)); i_uid_write(inode, le32_to_cpu(ino->uid)); i_gid_write(inode, le32_to_cpu(ino->gid)); @@ -272,19 +273,14 @@ static struct inode *ubifs_alloc_inode(struct super_block *sb) return &ui->vfs_inode; }; -static void ubifs_i_callback(struct rcu_head *head) -{ - struct inode *inode = container_of(head, struct inode, i_rcu); - struct ubifs_inode *ui = ubifs_inode(inode); - kmem_cache_free(ubifs_inode_slab, ui); -} - -static void ubifs_destroy_inode(struct inode *inode) +static void ubifs_free_inode(struct inode *inode) { struct ubifs_inode *ui = ubifs_inode(inode); kfree(ui->data); - call_rcu(&inode->i_rcu, ubifs_i_callback); + fscrypt_free_inode(inode); + + kmem_cache_free(ubifs_inode_slab, ui); } /* @@ -1550,6 +1546,8 @@ static int mount_ubifs(struct ubifs_info *c) c->bud_bytes, c->bud_bytes >> 10, c->bud_bytes >> 20); dbg_gen("max. seq. number: %llu", c->max_sqnum); dbg_gen("commit number: %llu", c->cmt_no); + dbg_gen("max. xattrs per inode: %d", ubifs_xattr_max_cnt(c)); + dbg_gen("max orphans: %d", c->max_orphans); return 0; @@ -1979,7 +1977,7 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) const struct super_operations ubifs_super_operations = { .alloc_inode = ubifs_alloc_inode, - .destroy_inode = ubifs_destroy_inode, + .free_inode = ubifs_free_inode, .put_super = ubifs_put_super, .write_inode = ubifs_write_inode, .evict_inode = ubifs_evict_inode, @@ -2146,9 +2144,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_UBIFS_FS_XATTR sb->s_xattr = ubifs_xattr_handlers; #endif -#ifdef CONFIG_FS_ENCRYPTION - sb->s_cop = &ubifs_crypt_operations; -#endif + fscrypt_set_ops(sb, &ubifs_crypt_operations); mutex_lock(&c->umount_mutex); err = mount_ubifs(c); @@ -2250,11 +2246,10 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, goto out_deact; /* We do not support atime */ sb->s_flags |= SB_ACTIVE; -#ifndef CONFIG_UBIFS_ATIME_SUPPORT - sb->s_flags |= SB_NOATIME; -#else - ubifs_msg(c, "full atime support is enabled."); -#endif + if (IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT)) + ubifs_msg(c, "full atime support is enabled."); + else + sb->s_flags |= SB_NOATIME; } /* 'fill_super()' opens ubi again so we must close it here */ diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 25572ffea163..ebf8c26f5b22 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -479,14 +479,13 @@ static int try_read_node(const struct ubifs_info *c, void *buf, int type, if (node_len != len) return 0; - if (type == UBIFS_DATA_NODE && c->no_chk_data_crc && !c->mounting && - !c->remounting_rw) - return 1; - - crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8); - node_crc = le32_to_cpu(ch->crc); - if (crc != node_crc) - return 0; + if (type != UBIFS_DATA_NODE || !c->no_chk_data_crc || c->mounting || + c->remounting_rw) { + crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8); + node_crc = le32_to_cpu(ch->crc); + if (crc != node_crc) + return 0; + } err = ubifs_node_check_hash(c, buf, zbr->hash); if (err) { diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 1ae12900e01d..379b9f791ff6 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -924,6 +924,8 @@ struct ubifs_budget_req { * @rb: rb-tree node of rb-tree of orphans sorted by inode number * @list: list head of list of orphans in order added * @new_list: list head of list of orphans added since the last commit + * @child_list: list of xattr childs if this orphan hosts xattrs, list head + * if this orphan is a xattr, not used otherwise. * @cnext: next orphan to commit * @dnext: next orphan to delete * @inum: inode number @@ -935,6 +937,7 @@ struct ubifs_orphan { struct rb_node rb; struct list_head list; struct list_head new_list; + struct list_head child_list; struct ubifs_orphan *cnext; struct ubifs_orphan *dnext; ino_t inum; @@ -1996,9 +1999,7 @@ int ubifs_calc_dark(const struct ubifs_info *c, int spc); /* file.c */ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync); int ubifs_setattr(struct dentry *dentry, struct iattr *attr); -#ifdef CONFIG_UBIFS_ATIME_SUPPORT int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags); -#endif /* dir.c */ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, @@ -2014,6 +2015,7 @@ int ubifs_xattr_set(struct inode *host, const char *name, const void *value, size_t size, int flags, bool check_lock); ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf, size_t size); +int ubifs_purge_xattrs(struct inode *host); #ifdef CONFIG_UBIFS_FS_XATTR void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index f5ad1ede7990..acab3181ab35 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -61,12 +61,6 @@ #include <linux/xattr.h> /* - * Limit the number of extended attributes per inode so that the total size - * (@xattr_size) is guaranteeded to fit in an 'unsigned int'. - */ -#define MAX_XATTRS_PER_INODE 65535 - -/* * Extended attribute type constants. * * USER_XATTR: user extended attribute ("user.*") @@ -106,7 +100,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, .new_ino_d = ALIGN(size, 8), .dirtied_ino = 1, .dirtied_ino_d = ALIGN(host_ui->data_len, 8) }; - if (host_ui->xattr_cnt >= MAX_XATTRS_PER_INODE) { + if (host_ui->xattr_cnt >= ubifs_xattr_max_cnt(c)) { ubifs_err(c, "inode %lu already has too many xattrs (%d), cannot create more", host->i_ino, host_ui->xattr_cnt); return -ENOSPC; @@ -507,6 +501,69 @@ out_cancel: return err; } +int ubifs_purge_xattrs(struct inode *host) +{ + union ubifs_key key; + struct ubifs_info *c = host->i_sb->s_fs_info; + struct ubifs_dent_node *xent, *pxent = NULL; + struct inode *xino; + struct fscrypt_name nm = {0}; + int err; + + if (ubifs_inode(host)->xattr_cnt < ubifs_xattr_max_cnt(c)) + return 0; + + ubifs_warn(c, "inode %lu has too many xattrs, doing a non-atomic deletion", + host->i_ino); + + lowest_xent_key(c, &key, host->i_ino); + while (1) { + xent = ubifs_tnc_next_ent(c, &key, &nm); + if (IS_ERR(xent)) { + err = PTR_ERR(xent); + break; + } + + fname_name(&nm) = xent->name; + fname_len(&nm) = le16_to_cpu(xent->nlen); + + xino = ubifs_iget(c->vfs_sb, xent->inum); + if (IS_ERR(xino)) { + err = PTR_ERR(xino); + ubifs_err(c, "dead directory entry '%s', error %d", + xent->name, err); + ubifs_ro_mode(c, err); + kfree(pxent); + return err; + } + + ubifs_assert(c, ubifs_inode(xino)->xattr); + + clear_nlink(xino); + err = remove_xattr(c, host, xino, &nm); + if (err) { + kfree(pxent); + iput(xino); + ubifs_err(c, "cannot remove xattr, error %d", err); + return err; + } + + iput(xino); + + kfree(pxent); + pxent = xent; + key_read(c, &xent->key, &key); + } + + kfree(pxent); + if (err != -ENOENT) { + ubifs_err(c, "cannot find next direntry, error %d", err); + return err; + } + + return 0; +} + /** * ubifs_evict_xattr_inode - Evict an xattr inode. * @c: UBIFS file-system description object diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 58cc2414992b..77b6d89b9bcd 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -304,21 +304,6 @@ static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry, if (dentry->d_name.len > UDF_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); -#ifdef UDF_RECOVERY - /* temporary shorthand for specifying files by inode number */ - if (!strncmp(dentry->d_name.name, ".B=", 3)) { - struct kernel_lb_addr lb = { - .logicalBlockNum = 0, - .partitionReferenceNum = - simple_strtoul(dentry->d_name.name + 3, - NULL, 0), - }; - inode = udf_iget(dir->i_sb, lb); - if (IS_ERR(inode)) - return inode; - } else -#endif /* UDF_RECOVERY */ - fi = udf_find_entry(dir, &dentry->d_name, &fibh, &cfi); if (IS_ERR(fi)) return ERR_CAST(fi); diff --git a/fs/udf/super.c b/fs/udf/super.c index ffd8038ff728..a14346137361 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -161,17 +161,11 @@ static struct inode *udf_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void udf_i_callback(struct rcu_head *head) +static void udf_free_in_core_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(udf_inode_cachep, UDF_I(inode)); } -static void udf_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, udf_i_callback); -} - static void init_once(void *foo) { struct udf_inode_info *ei = (struct udf_inode_info *)foo; @@ -206,7 +200,7 @@ static void destroy_inodecache(void) /* Superblock operations */ static const struct super_operations udf_sb_ops = { .alloc_inode = udf_alloc_inode, - .destroy_inode = udf_destroy_inode, + .free_inode = udf_free_in_core_inode, .write_inode = udf_write_inode, .evict_inode = udf_evict_inode, .put_super = udf_put_super, @@ -572,6 +566,11 @@ static int udf_parse_options(char *options, struct udf_options *uopt, if (!remount) { if (uopt->nls_map) unload_nls(uopt->nls_map); + /* + * load_nls() failure is handled later in + * udf_fill_super() after all options are + * parsed. + */ uopt->nls_map = load_nls(args[0].from); uopt->flags |= (1 << UDF_FLAG_NLS_MAP); } diff --git a/fs/ufs/super.c b/fs/ufs/super.c index a4e07e910f1b..84c0c5178cd2 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1449,17 +1449,11 @@ static struct inode *ufs_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void ufs_i_callback(struct rcu_head *head) +static void ufs_free_in_core_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(ufs_inode_cachep, UFS_I(inode)); } -static void ufs_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, ufs_i_callback); -} - static void init_once(void *foo) { struct ufs_inode_info *ei = (struct ufs_inode_info *) foo; @@ -1494,7 +1488,7 @@ static void destroy_inodecache(void) static const struct super_operations ufs_super_ops = { .alloc_inode = ufs_alloc_inode, - .destroy_inode = ufs_destroy_inode, + .free_inode = ufs_free_in_core_inode, .write_inode = ufs_write_inode, .evict_inode = ufs_evict_inode, .put_super = ufs_put_super, diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 1fd3011ea623..e1f1b2e868a7 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -42,7 +42,7 @@ ufs_get_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1, case UFS_ST_SUNOS: if (fs32_to_cpu(sb, usb3->fs_postblformat) == UFS_42POSTBLFMT) return fs32_to_cpu(sb, usb1->fs_u0.fs_sun.fs_state); - /* Fall Through to UFS_ST_SUN */ + /* Fall Through - to UFS_ST_SUN */ case UFS_ST_SUN: return fs32_to_cpu(sb, usb3->fs_un2.fs_sun.fs_state); case UFS_ST_SUNx86: @@ -63,7 +63,7 @@ ufs_set_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1, usb1->fs_u0.fs_sun.fs_state = cpu_to_fs32(sb, value); break; } - /* Fall Through to UFS_ST_SUN */ + /* Fall Through - to UFS_ST_SUN */ case UFS_ST_SUN: usb3->fs_un2.fs_sun.fs_state = cpu_to_fs32(sb, value); break; @@ -229,7 +229,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode) case UFS_UID_44BSD: return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid); case UFS_UID_EFT: - if (inode->ui_u1.oldids.ui_suid == 0xFFFF) + if (inode->ui_u1.oldids.ui_sgid == 0xFFFF) return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid); /* Fall through */ default: diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..3b30301c90ec 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -30,6 +30,8 @@ #include <linux/security.h> #include <linux/hugetlb.h> +int sysctl_unprivileged_userfaultfd __read_mostly = 1; + static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; enum userfaultfd_state { @@ -629,6 +631,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +887,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +911,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1340,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1529,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1921,6 +1932,9 @@ SYSCALL_DEFINE1(userfaultfd, int, flags) struct userfaultfd_ctx *ctx; int fd; + if (!sysctl_unprivileged_userfaultfd && !capable(CAP_SYS_PTRACE)) + return -EPERM; + BUG_ON(!current->mm); /* Check the UFFD_* constants for consistency. */ diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 457ac9f97377..99af5e5bda9f 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -1,7 +1,6 @@ config XFS_FS tristate "XFS filesystem support" depends on BLOCK - depends on (64BIT || LBDAF) select EXPORTFS select LIBCRC32C select FS_IOMAP diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 7f96bdadc372..1dfc6df2e2bd 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -73,6 +73,7 @@ xfs-y += xfs_aops.o \ xfs_fsmap.o \ xfs_fsops.o \ xfs_globals.o \ + xfs_health.o \ xfs_icache.o \ xfs_ioctl.o \ xfs_iomap.o \ @@ -142,6 +143,8 @@ xfs-y += $(addprefix scrub/, \ common.o \ dabtree.o \ dir.o \ + fscounters.o \ + health.o \ ialloc.o \ inode.o \ parent.o \ diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 1ef8acf35e7d..b0c89f54d1bb 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -19,6 +19,8 @@ #include "xfs_ialloc.h" #include "xfs_rmap.h" #include "xfs_ag.h" +#include "xfs_ag_resv.h" +#include "xfs_health.h" static struct xfs_buf * xfs_get_aghdr_buf( @@ -461,3 +463,55 @@ xfs_ag_extend_space( len, &XFS_RMAP_OINFO_SKIP_UPDATE, XFS_AG_RESV_NONE); } + +/* Retrieve AG geometry. */ +int +xfs_ag_get_geometry( + struct xfs_mount *mp, + xfs_agnumber_t agno, + struct xfs_ag_geometry *ageo) +{ + struct xfs_buf *agi_bp; + struct xfs_buf *agf_bp; + struct xfs_agi *agi; + struct xfs_agf *agf; + struct xfs_perag *pag; + unsigned int freeblks; + int error; + + if (agno >= mp->m_sb.sb_agcount) + return -EINVAL; + + /* Lock the AG headers. */ + error = xfs_ialloc_read_agi(mp, NULL, agno, &agi_bp); + if (error) + return error; + error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agf_bp); + if (error) + goto out_agi; + pag = xfs_perag_get(mp, agno); + + /* Fill out form. */ + memset(ageo, 0, sizeof(*ageo)); + ageo->ag_number = agno; + + agi = XFS_BUF_TO_AGI(agi_bp); + ageo->ag_icount = be32_to_cpu(agi->agi_count); + ageo->ag_ifree = be32_to_cpu(agi->agi_freecount); + + agf = XFS_BUF_TO_AGF(agf_bp); + ageo->ag_length = be32_to_cpu(agf->agf_length); + freeblks = pag->pagf_freeblks + + pag->pagf_flcount + + pag->pagf_btreeblks - + xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE); + ageo->ag_freeblks = freeblks; + xfs_ag_geom_health(pag, ageo); + + /* Release resources. */ + xfs_perag_put(pag); + xfs_buf_relse(agf_bp); +out_agi: + xfs_buf_relse(agi_bp); + return error; +} diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 412702e23f61..5166322807e7 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -26,5 +26,7 @@ struct aghdr_init_data { int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id); int xfs_ag_extend_space(struct xfs_mount *mp, struct xfs_trans *tp, struct aghdr_init_data *id, xfs_extlen_t len); +int xfs_ag_get_geometry(struct xfs_mount *mp, xfs_agnumber_t agno, + struct xfs_ag_geometry *ageo); #endif /* __LIBXFS_AG_H */ diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index bc3367b8b7bb..a9ff3cf82cce 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2042,6 +2042,7 @@ xfs_alloc_space_available( xfs_extlen_t alloc_len, longest; xfs_extlen_t reservation; /* blocks that are still reserved */ int available; + xfs_extlen_t agflcount; if (flags & XFS_ALLOC_FLAG_FREEING) return true; @@ -2054,8 +2055,13 @@ xfs_alloc_space_available( if (longest < alloc_len) return false; - /* do we have enough free space remaining for the allocation? */ - available = (int)(pag->pagf_freeblks + pag->pagf_flcount - + /* + * Do we have enough free space remaining for the allocation? Don't + * account extra agfl blocks because we are about to defer free them, + * making them unavailable until the current transaction commits. + */ + agflcount = min_t(xfs_extlen_t, pag->pagf_flcount, min_free); + available = (int)(pag->pagf_freeblks + agflcount - reservation - min_free - args->minleft); if (available < (int)max(args->total, alloc_len)) return false; @@ -2237,6 +2243,9 @@ xfs_alloc_fix_freelist( xfs_extlen_t need; /* total blocks needed in freelist */ int error = 0; + /* deferred ops (AGFL block frees) require permanent transactions */ + ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); + if (!pag->pagf_init) { error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp); if (error) diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 2dd9ee2a2e08..c441f41f14e8 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -224,10 +224,10 @@ xfs_attr_try_sf_addname( */ int xfs_attr_set_args( - struct xfs_da_args *args, - struct xfs_buf **leaf_bp) + struct xfs_da_args *args) { struct xfs_inode *dp = args->dp; + struct xfs_buf *leaf_bp = NULL; int error; /* @@ -255,7 +255,7 @@ xfs_attr_set_args( * It won't fit in the shortform, transform to a leaf block. * GROT: another possible req'mt for a double-split btree op. */ - error = xfs_attr_shortform_to_leaf(args, leaf_bp); + error = xfs_attr_shortform_to_leaf(args, &leaf_bp); if (error) return error; @@ -263,23 +263,16 @@ xfs_attr_set_args( * Prevent the leaf buffer from being unlocked so that a * concurrent AIL push cannot grab the half-baked leaf * buffer and run into problems with the write verifier. + * Once we're done rolling the transaction we can release + * the hold and add the attr to the leaf. */ - xfs_trans_bhold(args->trans, *leaf_bp); - + xfs_trans_bhold(args->trans, leaf_bp); error = xfs_defer_finish(&args->trans); - if (error) - return error; - - /* - * Commit the leaf transformation. We'll need another - * (linked) transaction to add the new attribute to the - * leaf. - */ - error = xfs_trans_roll_inode(&args->trans, dp); - if (error) + xfs_trans_bhold_release(args->trans, leaf_bp); + if (error) { + xfs_trans_brelse(args->trans, leaf_bp); return error; - xfs_trans_bjoin(args->trans, *leaf_bp); - *leaf_bp = NULL; + } } if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) @@ -322,7 +315,6 @@ xfs_attr_set( int flags) { struct xfs_mount *mp = dp->i_mount; - struct xfs_buf *leaf_bp = NULL; struct xfs_da_args args; struct xfs_trans_res tres; int rsvd = (flags & ATTR_ROOT) != 0; @@ -381,9 +373,9 @@ xfs_attr_set( goto out_trans_cancel; xfs_trans_ijoin(args.trans, dp, 0); - error = xfs_attr_set_args(&args, &leaf_bp); + error = xfs_attr_set_args(&args); if (error) - goto out_release_leaf; + goto out_trans_cancel; if (!args.trans) { /* shortform attribute has already been committed */ goto out_unlock; @@ -408,9 +400,6 @@ out_unlock: xfs_iunlock(dp, XFS_ILOCK_EXCL); return error; -out_release_leaf: - if (leaf_bp) - xfs_trans_brelse(args.trans, leaf_bp); out_trans_cancel: if (args.trans) xfs_trans_cancel(args.trans); diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index 2297d8467666..3b0dce06e454 100644 --- a/fs/xfs/libxfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -140,7 +140,7 @@ int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name, unsigned char *value, int *valuelenp, int flags); int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name, unsigned char *value, int valuelen, int flags); -int xfs_attr_set_args(struct xfs_da_args *args, struct xfs_buf **leaf_bp); +int xfs_attr_set_args(struct xfs_da_args *args); int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags); int xfs_attr_remove_args(struct xfs_da_args *args); int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize, diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 4637ae1ae91c..356ebd1cbe82 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -2009,6 +2009,9 @@ xfs_bmap_add_extent_delay_real( goto done; } + if (da_new != da_old) + xfs_mod_delalloc(mp, (int64_t)da_new - da_old); + if (bma->cur) { da_new += bma->cur->bc_private.b.allocated; bma->cur->bc_private.b.allocated = 0; @@ -2640,6 +2643,7 @@ xfs_bmap_add_extent_hole_delay( /* * Nothing to do for disk quota accounting here. */ + xfs_mod_delalloc(ip->i_mount, (int64_t)newlen - oldlen); } } @@ -3352,8 +3356,10 @@ xfs_bmap_btalloc_accounting( * already have quota reservation and there's nothing to do * yet. */ - if (ap->wasdel) + if (ap->wasdel) { + xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len); return; + } /* * Otherwise, we've allocated blocks in a hole. The transaction @@ -3372,8 +3378,10 @@ xfs_bmap_btalloc_accounting( /* data/attr fork only */ ap->ip->i_d.di_nblocks += args->len; xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE); - if (ap->wasdel) + if (ap->wasdel) { ap->ip->i_delayed_blks -= args->len; + xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len); + } xfs_trans_mod_dquot_byino(ap->tp, ap->ip, ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT, args->len); @@ -3969,6 +3977,7 @@ xfs_bmapi_reserve_delalloc( ip->i_delayed_blks += alen; + xfs_mod_delalloc(ip->i_mount, alen + indlen); got->br_startoff = aoff; got->br_startblock = nullstartblock(indlen); @@ -4840,8 +4849,10 @@ xfs_bmap_del_extent_delay( da_diff = da_old - da_new; if (!isrt) da_diff += del->br_blockcount; - if (da_diff) + if (da_diff) { xfs_mod_fdblocks(mp, da_diff, false); + xfs_mod_delalloc(mp, -da_diff); + } return error; } diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 94f00427de98..1c6bf2105939 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -274,13 +274,15 @@ xfs_defer_trans_roll( trace_xfs_defer_trans_roll(tp, _RET_IP_); - /* Roll the transaction. */ + /* + * Roll the transaction. Rolling always given a new transaction (even + * if committing the old one fails!) to hand back to the caller, so we + * join the held resources to the new transaction so that we always + * return with the held resources joined to @tpp, no matter what + * happened. + */ error = xfs_trans_roll(tpp); tp = *tpp; - if (error) { - trace_xfs_defer_trans_roll_error(tp, error); - return error; - } /* Rejoin the joined inodes. */ for (i = 0; i < ipcount; i++) @@ -292,6 +294,8 @@ xfs_defer_trans_roll( xfs_trans_bhold(tp, bplist[i]); } + if (error) + trace_xfs_defer_trans_roll_error(tp, error); return error; } diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index fb5bd9a804f6..88fa11071f9f 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -110,7 +110,7 @@ xfs_dqblk_verify( /* * Do some primitive error checking on ondisk dquot data structures. */ -int +void xfs_dqblk_repair( struct xfs_mount *mp, struct xfs_dqblk *dqb, @@ -133,8 +133,6 @@ xfs_dqblk_repair( xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); } - - return 0; } STATIC bool diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index f3aa59302fef..e7382c780ed7 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -124,7 +124,7 @@ typedef struct xfs_flock64 { /* * Output for XFS_IOC_FSGEOMETRY_V1 */ -typedef struct xfs_fsop_geom_v1 { +struct xfs_fsop_geom_v1 { __u32 blocksize; /* filesystem (data) block size */ __u32 rtextsize; /* realtime extent size */ __u32 agblocks; /* fsblocks in an AG */ @@ -145,12 +145,39 @@ typedef struct xfs_fsop_geom_v1 { __u32 logsectsize; /* log sector size, bytes */ __u32 rtsectsize; /* realtime sector size, bytes */ __u32 dirblocksize; /* directory block size, bytes */ -} xfs_fsop_geom_v1_t; +}; + +/* + * Output for XFS_IOC_FSGEOMETRY_V4 + */ +struct xfs_fsop_geom_v4 { + __u32 blocksize; /* filesystem (data) block size */ + __u32 rtextsize; /* realtime extent size */ + __u32 agblocks; /* fsblocks in an AG */ + __u32 agcount; /* number of allocation groups */ + __u32 logblocks; /* fsblocks in the log */ + __u32 sectsize; /* (data) sector size, bytes */ + __u32 inodesize; /* inode size in bytes */ + __u32 imaxpct; /* max allowed inode space(%) */ + __u64 datablocks; /* fsblocks in data subvolume */ + __u64 rtblocks; /* fsblocks in realtime subvol */ + __u64 rtextents; /* rt extents in realtime subvol*/ + __u64 logstart; /* starting fsblock of the log */ + unsigned char uuid[16]; /* unique id of the filesystem */ + __u32 sunit; /* stripe unit, fsblocks */ + __u32 swidth; /* stripe width, fsblocks */ + __s32 version; /* structure version */ + __u32 flags; /* superblock version flags */ + __u32 logsectsize; /* log sector size, bytes */ + __u32 rtsectsize; /* realtime sector size, bytes */ + __u32 dirblocksize; /* directory block size, bytes */ + __u32 logsunit; /* log stripe unit, bytes */ +}; /* * Output for XFS_IOC_FSGEOMETRY */ -typedef struct xfs_fsop_geom { +struct xfs_fsop_geom { __u32 blocksize; /* filesystem (data) block size */ __u32 rtextsize; /* realtime extent size */ __u32 agblocks; /* fsblocks in an AG */ @@ -171,8 +198,18 @@ typedef struct xfs_fsop_geom { __u32 logsectsize; /* log sector size, bytes */ __u32 rtsectsize; /* realtime sector size, bytes */ __u32 dirblocksize; /* directory block size, bytes */ - __u32 logsunit; /* log stripe unit, bytes */ -} xfs_fsop_geom_t; + __u32 logsunit; /* log stripe unit, bytes */ + uint32_t sick; /* o: unhealthy fs & rt metadata */ + uint32_t checked; /* o: checked fs & rt metadata */ + __u64 reserved[17]; /* reserved space */ +}; + +#define XFS_FSOP_GEOM_SICK_COUNTERS (1 << 0) /* summary counters */ +#define XFS_FSOP_GEOM_SICK_UQUOTA (1 << 1) /* user quota */ +#define XFS_FSOP_GEOM_SICK_GQUOTA (1 << 2) /* group quota */ +#define XFS_FSOP_GEOM_SICK_PQUOTA (1 << 3) /* project quota */ +#define XFS_FSOP_GEOM_SICK_RT_BITMAP (1 << 4) /* realtime bitmap */ +#define XFS_FSOP_GEOM_SICK_RT_SUMMARY (1 << 5) /* realtime summary */ /* Output for XFS_FS_COUNTS */ typedef struct xfs_fsop_counts { @@ -188,28 +225,30 @@ typedef struct xfs_fsop_resblks { __u64 resblks_avail; } xfs_fsop_resblks_t; -#define XFS_FSOP_GEOM_VERSION 0 - -#define XFS_FSOP_GEOM_FLAGS_ATTR 0x0001 /* attributes in use */ -#define XFS_FSOP_GEOM_FLAGS_NLINK 0x0002 /* 32-bit nlink values */ -#define XFS_FSOP_GEOM_FLAGS_QUOTA 0x0004 /* quotas enabled */ -#define XFS_FSOP_GEOM_FLAGS_IALIGN 0x0008 /* inode alignment */ -#define XFS_FSOP_GEOM_FLAGS_DALIGN 0x0010 /* large data alignment */ -#define XFS_FSOP_GEOM_FLAGS_SHARED 0x0020 /* read-only shared */ -#define XFS_FSOP_GEOM_FLAGS_EXTFLG 0x0040 /* special extent flag */ -#define XFS_FSOP_GEOM_FLAGS_DIRV2 0x0080 /* directory version 2 */ -#define XFS_FSOP_GEOM_FLAGS_LOGV2 0x0100 /* log format version 2 */ -#define XFS_FSOP_GEOM_FLAGS_SECTOR 0x0200 /* sector sizes >1BB */ -#define XFS_FSOP_GEOM_FLAGS_ATTR2 0x0400 /* inline attributes rework */ -#define XFS_FSOP_GEOM_FLAGS_PROJID32 0x0800 /* 32-bit project IDs */ -#define XFS_FSOP_GEOM_FLAGS_DIRV2CI 0x1000 /* ASCII only CI names */ -#define XFS_FSOP_GEOM_FLAGS_LAZYSB 0x4000 /* lazy superblock counters */ -#define XFS_FSOP_GEOM_FLAGS_V5SB 0x8000 /* version 5 superblock */ -#define XFS_FSOP_GEOM_FLAGS_FTYPE 0x10000 /* inode directory types */ -#define XFS_FSOP_GEOM_FLAGS_FINOBT 0x20000 /* free inode btree */ -#define XFS_FSOP_GEOM_FLAGS_SPINODES 0x40000 /* sparse inode chunks */ -#define XFS_FSOP_GEOM_FLAGS_RMAPBT 0x80000 /* reverse mapping btree */ -#define XFS_FSOP_GEOM_FLAGS_REFLINK 0x100000 /* files can share blocks */ +#define XFS_FSOP_GEOM_VERSION 0 +#define XFS_FSOP_GEOM_VERSION_V5 5 + +#define XFS_FSOP_GEOM_FLAGS_ATTR (1 << 0) /* attributes in use */ +#define XFS_FSOP_GEOM_FLAGS_NLINK (1 << 1) /* 32-bit nlink values */ +#define XFS_FSOP_GEOM_FLAGS_QUOTA (1 << 2) /* quotas enabled */ +#define XFS_FSOP_GEOM_FLAGS_IALIGN (1 << 3) /* inode alignment */ +#define XFS_FSOP_GEOM_FLAGS_DALIGN (1 << 4) /* large data alignment */ +#define XFS_FSOP_GEOM_FLAGS_SHARED (1 << 5) /* read-only shared */ +#define XFS_FSOP_GEOM_FLAGS_EXTFLG (1 << 6) /* special extent flag */ +#define XFS_FSOP_GEOM_FLAGS_DIRV2 (1 << 7) /* directory version 2 */ +#define XFS_FSOP_GEOM_FLAGS_LOGV2 (1 << 8) /* log format version 2 */ +#define XFS_FSOP_GEOM_FLAGS_SECTOR (1 << 9) /* sector sizes >1BB */ +#define XFS_FSOP_GEOM_FLAGS_ATTR2 (1 << 10) /* inline attributes rework */ +#define XFS_FSOP_GEOM_FLAGS_PROJID32 (1 << 11) /* 32-bit project IDs */ +#define XFS_FSOP_GEOM_FLAGS_DIRV2CI (1 << 12) /* ASCII only CI names */ + /* -- Do not use -- (1 << 13) SGI parent pointers */ +#define XFS_FSOP_GEOM_FLAGS_LAZYSB (1 << 14) /* lazy superblock counters */ +#define XFS_FSOP_GEOM_FLAGS_V5SB (1 << 15) /* version 5 superblock */ +#define XFS_FSOP_GEOM_FLAGS_FTYPE (1 << 16) /* inode directory types */ +#define XFS_FSOP_GEOM_FLAGS_FINOBT (1 << 17) /* free inode btree */ +#define XFS_FSOP_GEOM_FLAGS_SPINODES (1 << 18) /* sparse inode chunks */ +#define XFS_FSOP_GEOM_FLAGS_RMAPBT (1 << 19) /* reverse mapping btree */ +#define XFS_FSOP_GEOM_FLAGS_REFLINK (1 << 20) /* files can share blocks */ /* * Minimum and maximum sizes need for growth checks. @@ -238,6 +277,31 @@ typedef struct xfs_fsop_resblks { (s)->sb_agblocks + XFS_MIN_AG_BLOCKS) /* + * Output for XFS_IOC_AG_GEOMETRY + */ +struct xfs_ag_geometry { + uint32_t ag_number; /* i/o: AG number */ + uint32_t ag_length; /* o: length in blocks */ + uint32_t ag_freeblks; /* o: free space */ + uint32_t ag_icount; /* o: inodes allocated */ + uint32_t ag_ifree; /* o: inodes free */ + uint32_t ag_sick; /* o: sick things in ag */ + uint32_t ag_checked; /* o: checked metadata in ag */ + uint32_t ag_reserved32; /* o: zero */ + uint64_t ag_reserved[12];/* o: zero */ +}; +#define XFS_AG_GEOM_SICK_SB (1 << 0) /* superblock */ +#define XFS_AG_GEOM_SICK_AGF (1 << 1) /* AGF header */ +#define XFS_AG_GEOM_SICK_AGFL (1 << 2) /* AGFL header */ +#define XFS_AG_GEOM_SICK_AGI (1 << 3) /* AGI header */ +#define XFS_AG_GEOM_SICK_BNOBT (1 << 4) /* free space by block */ +#define XFS_AG_GEOM_SICK_CNTBT (1 << 5) /* free space by length */ +#define XFS_AG_GEOM_SICK_INOBT (1 << 6) /* inode index */ +#define XFS_AG_GEOM_SICK_FINOBT (1 << 7) /* free inode index */ +#define XFS_AG_GEOM_SICK_RMAPBT (1 << 8) /* reverse mappings */ +#define XFS_AG_GEOM_SICK_REFCNTBT (1 << 9) /* reference counts */ + +/* * Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT */ typedef struct xfs_growfs_data { @@ -285,13 +349,25 @@ typedef struct xfs_bstat { #define bs_projid bs_projid_lo /* (previously just bs_projid) */ __u16 bs_forkoff; /* inode fork offset in bytes */ __u16 bs_projid_hi; /* higher part of project id */ - unsigned char bs_pad[6]; /* pad space, unused */ + uint16_t bs_sick; /* sick inode metadata */ + uint16_t bs_checked; /* checked inode metadata */ + unsigned char bs_pad[2]; /* pad space, unused */ __u32 bs_cowextsize; /* cow extent size */ __u32 bs_dmevmask; /* DMIG event mask */ __u16 bs_dmstate; /* DMIG state info */ __u16 bs_aextents; /* attribute number of extents */ } xfs_bstat_t; +/* bs_sick flags */ +#define XFS_BS_SICK_INODE (1 << 0) /* inode core */ +#define XFS_BS_SICK_BMBTD (1 << 1) /* data fork */ +#define XFS_BS_SICK_BMBTA (1 << 2) /* attr fork */ +#define XFS_BS_SICK_BMBTC (1 << 3) /* cow fork */ +#define XFS_BS_SICK_DIR (1 << 4) /* directory */ +#define XFS_BS_SICK_XATTR (1 << 5) /* extended attributes */ +#define XFS_BS_SICK_SYMLINK (1 << 6) /* symbolic link remote target */ +#define XFS_BS_SICK_PARENT (1 << 7) /* parent pointers */ + /* * Project quota id helpers (previously projid was 16bit only * and using two 16bit values to hold new 32bit projid was choosen @@ -502,9 +578,10 @@ struct xfs_scrub_metadata { #define XFS_SCRUB_TYPE_UQUOTA 21 /* user quotas */ #define XFS_SCRUB_TYPE_GQUOTA 22 /* group quotas */ #define XFS_SCRUB_TYPE_PQUOTA 23 /* project quotas */ +#define XFS_SCRUB_TYPE_FSCOUNTERS 24 /* fs summary counters */ /* Number of scrub subcommands. */ -#define XFS_SCRUB_TYPE_NR 24 +#define XFS_SCRUB_TYPE_NR 25 /* i: Repair this metadata. */ #define XFS_SCRUB_IFLAG_REPAIR (1 << 0) @@ -590,6 +667,7 @@ struct xfs_scrub_metadata { #define XFS_IOC_FREE_EOFBLOCKS _IOR ('X', 58, struct xfs_fs_eofblocks) /* XFS_IOC_GETFSMAP ------ hoisted 59 */ #define XFS_IOC_SCRUB_METADATA _IOWR('X', 60, struct xfs_scrub_metadata) +#define XFS_IOC_AG_GEOMETRY _IOWR('X', 61, struct xfs_ag_geometry) /* * ioctl commands that replace IRIX syssgi()'s @@ -620,8 +698,9 @@ struct xfs_scrub_metadata { #define XFS_IOC_FSSETDM_BY_HANDLE _IOW ('X', 121, struct xfs_fsop_setdm_handlereq) #define XFS_IOC_ATTRLIST_BY_HANDLE _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq) #define XFS_IOC_ATTRMULTI_BY_HANDLE _IOW ('X', 123, struct xfs_fsop_attrmulti_handlereq) -#define XFS_IOC_FSGEOMETRY _IOR ('X', 124, struct xfs_fsop_geom) +#define XFS_IOC_FSGEOMETRY_V4 _IOR ('X', 124, struct xfs_fsop_geom_v4) #define XFS_IOC_GOINGDOWN _IOR ('X', 125, uint32_t) +#define XFS_IOC_FSGEOMETRY _IOR ('X', 126, struct xfs_fsop_geom) /* XFS_IOC_GETFSUUID ---------- deprecated 140 */ diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h new file mode 100644 index 000000000000..49ddfeac19f2 --- /dev/null +++ b/fs/xfs/libxfs/xfs_health.h @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#ifndef __XFS_HEALTH_H__ +#define __XFS_HEALTH_H__ + +/* + * In-Core Filesystem Health Assessments + * ===================================== + * + * We'd like to be able to summarize the current health status of the + * filesystem so that the administrator knows when it's necessary to schedule + * some downtime for repairs. Until then, we would also like to avoid abrupt + * shutdowns due to corrupt metadata. + * + * The online scrub feature evaluates the health of all filesystem metadata. + * When scrub detects corruption in a piece of metadata it will set the + * corresponding sickness flag, and repair will clear it if successful. If + * problems remain at unmount time, we can also request manual intervention by + * logging a notice to run xfs_repair. + * + * Each health tracking group uses a pair of fields for reporting. The + * "checked" field tell us if a given piece of metadata has ever been examined, + * and the "sick" field tells us if that piece was found to need repairs. + * Therefore we can conclude that for a given sick flag value: + * + * - checked && sick => metadata needs repair + * - checked && !sick => metadata is ok + * - !checked => has not been examined since mount + */ + +struct xfs_mount; +struct xfs_perag; +struct xfs_inode; +struct xfs_fsop_geom; + +/* Observable health issues for metadata spanning the entire filesystem. */ +#define XFS_SICK_FS_COUNTERS (1 << 0) /* summary counters */ +#define XFS_SICK_FS_UQUOTA (1 << 1) /* user quota */ +#define XFS_SICK_FS_GQUOTA (1 << 2) /* group quota */ +#define XFS_SICK_FS_PQUOTA (1 << 3) /* project quota */ + +/* Observable health issues for realtime volume metadata. */ +#define XFS_SICK_RT_BITMAP (1 << 0) /* realtime bitmap */ +#define XFS_SICK_RT_SUMMARY (1 << 1) /* realtime summary */ + +/* Observable health issues for AG metadata. */ +#define XFS_SICK_AG_SB (1 << 0) /* superblock */ +#define XFS_SICK_AG_AGF (1 << 1) /* AGF header */ +#define XFS_SICK_AG_AGFL (1 << 2) /* AGFL header */ +#define XFS_SICK_AG_AGI (1 << 3) /* AGI header */ +#define XFS_SICK_AG_BNOBT (1 << 4) /* free space by block */ +#define XFS_SICK_AG_CNTBT (1 << 5) /* free space by length */ +#define XFS_SICK_AG_INOBT (1 << 6) /* inode index */ +#define XFS_SICK_AG_FINOBT (1 << 7) /* free inode index */ +#define XFS_SICK_AG_RMAPBT (1 << 8) /* reverse mappings */ +#define XFS_SICK_AG_REFCNTBT (1 << 9) /* reference counts */ + +/* Observable health issues for inode metadata. */ +#define XFS_SICK_INO_CORE (1 << 0) /* inode core */ +#define XFS_SICK_INO_BMBTD (1 << 1) /* data fork */ +#define XFS_SICK_INO_BMBTA (1 << 2) /* attr fork */ +#define XFS_SICK_INO_BMBTC (1 << 3) /* cow fork */ +#define XFS_SICK_INO_DIR (1 << 4) /* directory */ +#define XFS_SICK_INO_XATTR (1 << 5) /* extended attributes */ +#define XFS_SICK_INO_SYMLINK (1 << 6) /* symbolic link remote target */ +#define XFS_SICK_INO_PARENT (1 << 7) /* parent pointers */ + +/* Primary evidence of health problems in a given group. */ +#define XFS_SICK_FS_PRIMARY (XFS_SICK_FS_COUNTERS | \ + XFS_SICK_FS_UQUOTA | \ + XFS_SICK_FS_GQUOTA | \ + XFS_SICK_FS_PQUOTA) + +#define XFS_SICK_RT_PRIMARY (XFS_SICK_RT_BITMAP | \ + XFS_SICK_RT_SUMMARY) + +#define XFS_SICK_AG_PRIMARY (XFS_SICK_AG_SB | \ + XFS_SICK_AG_AGF | \ + XFS_SICK_AG_AGFL | \ + XFS_SICK_AG_AGI | \ + XFS_SICK_AG_BNOBT | \ + XFS_SICK_AG_CNTBT | \ + XFS_SICK_AG_INOBT | \ + XFS_SICK_AG_FINOBT | \ + XFS_SICK_AG_RMAPBT | \ + XFS_SICK_AG_REFCNTBT) + +#define XFS_SICK_INO_PRIMARY (XFS_SICK_INO_CORE | \ + XFS_SICK_INO_BMBTD | \ + XFS_SICK_INO_BMBTA | \ + XFS_SICK_INO_BMBTC | \ + XFS_SICK_INO_DIR | \ + XFS_SICK_INO_XATTR | \ + XFS_SICK_INO_SYMLINK | \ + XFS_SICK_INO_PARENT) + +/* These functions must be provided by the xfs implementation. */ + +void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask); +void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask); +void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick, + unsigned int *checked); + +void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask); +void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask); +void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick, + unsigned int *checked); + +void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask); +void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask); +void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick, + unsigned int *checked); + +void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask); +void xfs_inode_mark_healthy(struct xfs_inode *ip, unsigned int mask); +void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick, + unsigned int *checked); + +void xfs_health_unmount(struct xfs_mount *mp); + +/* Now some helpers. */ + +static inline bool +xfs_fs_has_sickness(struct xfs_mount *mp, unsigned int mask) +{ + unsigned int sick, checked; + + xfs_fs_measure_sickness(mp, &sick, &checked); + return sick & mask; +} + +static inline bool +xfs_rt_has_sickness(struct xfs_mount *mp, unsigned int mask) +{ + unsigned int sick, checked; + + xfs_rt_measure_sickness(mp, &sick, &checked); + return sick & mask; +} + +static inline bool +xfs_ag_has_sickness(struct xfs_perag *pag, unsigned int mask) +{ + unsigned int sick, checked; + + xfs_ag_measure_sickness(pag, &sick, &checked); + return sick & mask; +} + +static inline bool +xfs_inode_has_sickness(struct xfs_inode *ip, unsigned int mask) +{ + unsigned int sick, checked; + + xfs_inode_measure_sickness(ip, &sick, &checked); + return sick & mask; +} + +static inline bool +xfs_fs_is_healthy(struct xfs_mount *mp) +{ + return !xfs_fs_has_sickness(mp, -1U); +} + +static inline bool +xfs_rt_is_healthy(struct xfs_mount *mp) +{ + return !xfs_rt_has_sickness(mp, -1U); +} + +static inline bool +xfs_ag_is_healthy(struct xfs_perag *pag) +{ + return !xfs_ag_has_sickness(pag, -1U); +} + +static inline bool +xfs_inode_is_healthy(struct xfs_inode *ip) +{ + return !xfs_inode_has_sickness(ip, -1U); +} + +void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo); +void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo); +void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bstat *bs); + +#endif /* __XFS_HEALTH_H__ */ diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index 4bfdd5f4c6af..b2113b17e53c 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -142,7 +142,7 @@ extern xfs_failaddr_t xfs_dquot_verify(struct xfs_mount *mp, extern xfs_failaddr_t xfs_dqblk_verify(struct xfs_mount *mp, struct xfs_dqblk *dqb, xfs_dqid_t id, uint type); extern int xfs_calc_dquots_per_chunk(unsigned int nbblks); -extern int xfs_dqblk_repair(struct xfs_mount *mp, struct xfs_dqblk *dqb, +extern void xfs_dqblk_repair(struct xfs_mount *mp, struct xfs_dqblk *dqb, xfs_dqid_t id, uint type); #endif /* __XFS_QUOTA_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 77a3a4085de3..e76a3e5d28d7 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -30,6 +30,7 @@ #include "xfs_refcount_btree.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" +#include "xfs_health.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. @@ -905,7 +906,7 @@ xfs_initialize_perag_data( /* * If the new summary counts are obviously incorrect, fail the * mount operation because that implies the AGFs are also corrupt. - * Clear BAD_SUMMARY so that we don't unmount with a dirty log, which + * Clear FS_COUNTERS so that we don't unmount with a dirty log, which * will prevent xfs_repair from fixing anything. */ if (fdblocks > sbp->sb_dblocks || ifree > ialloc) { @@ -923,7 +924,7 @@ xfs_initialize_perag_data( xfs_reinit_percpu_counters(mp); out: - mp->m_flags &= ~XFS_MOUNT_BAD_SUMMARY; + xfs_fs_mark_healthy(mp, XFS_SICK_FS_COUNTERS); return error; } @@ -1084,7 +1085,7 @@ out: return error; } -int +void xfs_fs_geometry( struct xfs_sb *sbp, struct xfs_fsop_geom *geo, @@ -1108,13 +1109,13 @@ xfs_fs_geometry( memcpy(geo->uuid, &sbp->sb_uuid, sizeof(sbp->sb_uuid)); if (struct_version < 2) - return 0; + return; geo->sunit = sbp->sb_unit; geo->swidth = sbp->sb_width; if (struct_version < 3) - return 0; + return; geo->version = XFS_FSOP_GEOM_VERSION; geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK | @@ -1158,14 +1159,17 @@ xfs_fs_geometry( geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp); if (struct_version < 4) - return 0; + return; if (xfs_sb_version_haslogv2(sbp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_LOGV2; geo->logsunit = sbp->sb_logsunit; - return 0; + if (struct_version < 5) + return; + + geo->version = XFS_FSOP_GEOM_VERSION_V5; } /* Read a secondary superblock. */ diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index 13564d69800a..92465a9a5162 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -33,7 +33,7 @@ extern void xfs_sb_quota_from_disk(struct xfs_sb *sbp); extern int xfs_update_secondary_sbs(struct xfs_mount *mp); #define XFS_FS_GEOM_MAX_STRUCT_VER (4) -extern int xfs_fs_geometry(struct xfs_sb *sbp, struct xfs_fsop_geom *geo, +extern void xfs_fs_geometry(struct xfs_sb *sbp, struct xfs_fsop_geom *geo, int struct_version); extern int xfs_sb_read_secondary(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index f99a7aefe418..83f4ee2afc49 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -876,9 +876,13 @@ xfs_trans_resv_calc( resp->tr_sb.tr_logres = xfs_calc_sb_reservation(mp); resp->tr_sb.tr_logcount = XFS_DEFAULT_LOG_COUNT; + /* growdata requires permanent res; it can free space to the last AG */ + resp->tr_growdata.tr_logres = xfs_calc_growdata_reservation(mp); + resp->tr_growdata.tr_logcount = XFS_DEFAULT_PERM_LOG_COUNT; + resp->tr_growdata.tr_logflags |= XFS_TRANS_PERM_LOG_RES; + /* The following transaction are logged in logical format */ resp->tr_ichange.tr_logres = xfs_calc_ichange_reservation(mp); - resp->tr_growdata.tr_logres = xfs_calc_growdata_reservation(mp); resp->tr_fsyncts.tr_logres = xfs_calc_swrite_reservation(mp); resp->tr_writeid.tr_logres = xfs_calc_writeid_reservation(mp); resp->tr_attrsetrt.tr_logres = xfs_calc_attrsetrt_reservation(mp); diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c index de310712dd6d..d51acc95bc00 100644 --- a/fs/xfs/libxfs/xfs_types.c +++ b/fs/xfs/libxfs/xfs_types.c @@ -185,7 +185,7 @@ xfs_verify_rtbno( } /* Calculate the range of valid icount values. */ -static void +void xfs_icount_range( struct xfs_mount *mp, unsigned long long *min, diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index c5a25403b4db..802b34cd10fe 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -191,5 +191,7 @@ bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino); bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno); bool xfs_verify_icount(struct xfs_mount *mp, unsigned long long icount); bool xfs_verify_dablk(struct xfs_mount *mp, xfs_fileoff_t off); +void xfs_icount_range(struct xfs_mount *mp, unsigned long long *min, + unsigned long long *max); #endif /* __XFS_TYPES_H__ */ diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index ddf06bfaa29d..adaeabdefdd3 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -514,6 +514,7 @@ xchk_agf( { struct xfs_mount *mp = sc->mp; struct xfs_agf *agf; + struct xfs_perag *pag; xfs_agnumber_t agno; xfs_agblock_t agbno; xfs_agblock_t eoag; @@ -586,6 +587,16 @@ xchk_agf( if (agfl_count != 0 && fl_count != agfl_count) xchk_block_set_corrupt(sc, sc->sa.agf_bp); + /* Do the incore counters match? */ + pag = xfs_perag_get(mp, agno); + if (pag->pagf_freeblks != be32_to_cpu(agf->agf_freeblks)) + xchk_block_set_corrupt(sc, sc->sa.agf_bp); + if (pag->pagf_flcount != be32_to_cpu(agf->agf_flcount)) + xchk_block_set_corrupt(sc, sc->sa.agf_bp); + if (pag->pagf_btreeblks != be32_to_cpu(agf->agf_btreeblks)) + xchk_block_set_corrupt(sc, sc->sa.agf_bp); + xfs_perag_put(pag); + xchk_agf_xref(sc); out: return error; @@ -811,6 +822,7 @@ xchk_agi( { struct xfs_mount *mp = sc->mp; struct xfs_agi *agi; + struct xfs_perag *pag; xfs_agnumber_t agno; xfs_agblock_t agbno; xfs_agblock_t eoag; @@ -881,6 +893,14 @@ xchk_agi( if (agi->agi_pad32 != cpu_to_be32(0)) xchk_block_set_corrupt(sc, sc->sa.agi_bp); + /* Do the incore counters match? */ + pag = xfs_perag_get(mp, agno); + if (pag->pagi_count != be32_to_cpu(agi->agi_count)) + xchk_block_set_corrupt(sc, sc->sa.agi_bp); + if (pag->pagi_freecount != be32_to_cpu(agi->agi_freecount)) + xchk_block_set_corrupt(sc, sc->sa.agi_bp); + xfs_perag_put(pag); + xchk_agi_xref(sc); out: return error; diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 0c54ff55b901..973aa59975e3 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -38,6 +38,7 @@ #include "scrub/trace.h" #include "scrub/btree.h" #include "scrub/repair.h" +#include "scrub/health.h" /* Common code for the metadata scrubbers. */ @@ -208,6 +209,15 @@ xchk_ino_set_preen( trace_xchk_ino_preen(sc, ino, __return_address); } +/* Record something being wrong with the filesystem primary superblock. */ +void +xchk_set_corrupt( + struct xfs_scrub *sc) +{ + sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + trace_xchk_fs_error(sc, 0, __return_address); +} + /* Record a corrupt block. */ void xchk_block_set_corrupt( @@ -458,13 +468,18 @@ xchk_ag_btcur_init( struct xfs_mount *mp = sc->mp; xfs_agnumber_t agno = sa->agno; - if (sa->agf_bp) { + xchk_perag_get(sc->mp, sa); + if (sa->agf_bp && + xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_BNO)) { /* Set up a bnobt cursor for cross-referencing. */ sa->bno_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp, agno, XFS_BTNUM_BNO); if (!sa->bno_cur) goto err; + } + if (sa->agf_bp && + xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_CNT)) { /* Set up a cntbt cursor for cross-referencing. */ sa->cnt_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp, agno, XFS_BTNUM_CNT); @@ -473,7 +488,8 @@ xchk_ag_btcur_init( } /* Set up a inobt cursor for cross-referencing. */ - if (sa->agi_bp) { + if (sa->agi_bp && + xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_INO)) { sa->ino_cur = xfs_inobt_init_cursor(mp, sc->tp, sa->agi_bp, agno, XFS_BTNUM_INO); if (!sa->ino_cur) @@ -481,7 +497,8 @@ xchk_ag_btcur_init( } /* Set up a finobt cursor for cross-referencing. */ - if (sa->agi_bp && xfs_sb_version_hasfinobt(&mp->m_sb)) { + if (sa->agi_bp && xfs_sb_version_hasfinobt(&mp->m_sb) && + xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_FINO)) { sa->fino_cur = xfs_inobt_init_cursor(mp, sc->tp, sa->agi_bp, agno, XFS_BTNUM_FINO); if (!sa->fino_cur) @@ -489,7 +506,8 @@ xchk_ag_btcur_init( } /* Set up a rmapbt cursor for cross-referencing. */ - if (sa->agf_bp && xfs_sb_version_hasrmapbt(&mp->m_sb)) { + if (sa->agf_bp && xfs_sb_version_hasrmapbt(&mp->m_sb) && + xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_RMAP)) { sa->rmap_cur = xfs_rmapbt_init_cursor(mp, sc->tp, sa->agf_bp, agno); if (!sa->rmap_cur) @@ -497,7 +515,8 @@ xchk_ag_btcur_init( } /* Set up a refcountbt cursor for cross-referencing. */ - if (sa->agf_bp && xfs_sb_version_hasreflink(&mp->m_sb)) { + if (sa->agf_bp && xfs_sb_version_hasreflink(&mp->m_sb) && + xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_REFC)) { sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp, sa->agf_bp, agno); if (!sa->refc_cur) @@ -884,3 +903,21 @@ xchk_ilock_inverted( } return -EDEADLOCK; } + +/* Pause background reaping of resources. */ +void +xchk_stop_reaping( + struct xfs_scrub *sc) +{ + sc->flags |= XCHK_REAPING_DISABLED; + xfs_stop_block_reaping(sc->mp); +} + +/* Restart background reaping of resources. */ +void +xchk_start_reaping( + struct xfs_scrub *sc) +{ + xfs_start_block_reaping(sc->mp); + sc->flags &= ~XCHK_REAPING_DISABLED; +} diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index e26a430bd466..003a772cd26c 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -39,6 +39,7 @@ void xchk_block_set_preen(struct xfs_scrub *sc, struct xfs_buf *bp); void xchk_ino_set_preen(struct xfs_scrub *sc, xfs_ino_t ino); +void xchk_set_corrupt(struct xfs_scrub *sc); void xchk_block_set_corrupt(struct xfs_scrub *sc, struct xfs_buf *bp); void xchk_ino_set_corrupt(struct xfs_scrub *sc, xfs_ino_t ino); @@ -105,6 +106,7 @@ xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip) return -ENOENT; } #endif +int xchk_setup_fscounters(struct xfs_scrub *sc, struct xfs_inode *ip); void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa); int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno, @@ -137,5 +139,7 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm) int xchk_metadata_inode_forks(struct xfs_scrub *sc); int xchk_ilock_inverted(struct xfs_inode *ip, uint lock_mode); +void xchk_stop_reaping(struct xfs_scrub *sc); +void xchk_start_reaping(struct xfs_scrub *sc); #endif /* __XFS_SCRUB_COMMON_H__ */ diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c new file mode 100644 index 000000000000..07c11e3e6437 --- /dev/null +++ b/fs/xfs/scrub/fscounters.c @@ -0,0 +1,366 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_inode.h" +#include "xfs_alloc.h" +#include "xfs_ialloc.h" +#include "xfs_rmap.h" +#include "xfs_error.h" +#include "xfs_errortag.h" +#include "xfs_icache.h" +#include "xfs_health.h" +#include "xfs_bmap.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/trace.h" + +/* + * FS Summary Counters + * =================== + * + * The basics of filesystem summary counter checking are that we iterate the + * AGs counting the number of free blocks, free space btree blocks, per-AG + * reservations, inodes, delayed allocation reservations, and free inodes. + * Then we compare what we computed against the in-core counters. + * + * However, the reality is that summary counters are a tricky beast to check. + * While we /could/ freeze the filesystem and scramble around the AGs counting + * the free blocks, in practice we prefer not do that for a scan because + * freezing is costly. To get around this, we added a per-cpu counter of the + * delalloc reservations so that we can rotor around the AGs relatively + * quickly, and we allow the counts to be slightly off because we're not taking + * any locks while we do this. + * + * So the first thing we do is warm up the buffer cache in the setup routine by + * walking all the AGs to make sure the incore per-AG structure has been + * initialized. The expected value calculation then iterates the incore per-AG + * structures as quickly as it can. We snapshot the percpu counters before and + * after this operation and use the difference in counter values to guess at + * our tolerance for mismatch between expected and actual counter values. + */ + +/* + * Since the expected value computation is lockless but only browses incore + * values, the percpu counters should be fairly close to each other. However, + * we'll allow ourselves to be off by at least this (arbitrary) amount. + */ +#define XCHK_FSCOUNT_MIN_VARIANCE (512) + +/* + * Make sure the per-AG structure has been initialized from the on-disk header + * contents and trust that the incore counters match the ondisk counters. (The + * AGF and AGI scrubbers check them, and a normal xfs_scrub run checks the + * summary counters after checking all AG headers). Do this from the setup + * function so that the inner AG aggregation loop runs as quickly as possible. + * + * This function runs during the setup phase /before/ we start checking any + * metadata. + */ +STATIC int +xchk_fscount_warmup( + struct xfs_scrub *sc) +{ + struct xfs_mount *mp = sc->mp; + struct xfs_buf *agi_bp = NULL; + struct xfs_buf *agf_bp = NULL; + struct xfs_perag *pag = NULL; + xfs_agnumber_t agno; + int error = 0; + + for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { + pag = xfs_perag_get(mp, agno); + + if (pag->pagi_init && pag->pagf_init) + goto next_loop_perag; + + /* Lock both AG headers. */ + error = xfs_ialloc_read_agi(mp, sc->tp, agno, &agi_bp); + if (error) + break; + error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, &agf_bp); + if (error) + break; + error = -ENOMEM; + if (!agf_bp || !agi_bp) + break; + + /* + * These are supposed to be initialized by the header read + * function. + */ + error = -EFSCORRUPTED; + if (!pag->pagi_init || !pag->pagf_init) + break; + + xfs_buf_relse(agf_bp); + agf_bp = NULL; + xfs_buf_relse(agi_bp); + agi_bp = NULL; +next_loop_perag: + xfs_perag_put(pag); + pag = NULL; + error = 0; + + if (fatal_signal_pending(current)) + break; + } + + if (agf_bp) + xfs_buf_relse(agf_bp); + if (agi_bp) + xfs_buf_relse(agi_bp); + if (pag) + xfs_perag_put(pag); + return error; +} + +int +xchk_setup_fscounters( + struct xfs_scrub *sc, + struct xfs_inode *ip) +{ + struct xchk_fscounters *fsc; + int error; + + sc->buf = kmem_zalloc(sizeof(struct xchk_fscounters), KM_SLEEP); + if (!sc->buf) + return -ENOMEM; + fsc = sc->buf; + + xfs_icount_range(sc->mp, &fsc->icount_min, &fsc->icount_max); + + /* We must get the incore counters set up before we can proceed. */ + error = xchk_fscount_warmup(sc); + if (error) + return error; + + /* + * Pause background reclaim while we're scrubbing to reduce the + * likelihood of background perturbations to the counters throwing off + * our calculations. + */ + xchk_stop_reaping(sc); + + return xchk_trans_alloc(sc, 0); +} + +/* + * Calculate what the global in-core counters ought to be from the incore + * per-AG structure. Callers can compare this to the actual in-core counters + * to estimate by how much both in-core and on-disk counters need to be + * adjusted. + */ +STATIC int +xchk_fscount_aggregate_agcounts( + struct xfs_scrub *sc, + struct xchk_fscounters *fsc) +{ + struct xfs_mount *mp = sc->mp; + struct xfs_perag *pag; + uint64_t delayed; + xfs_agnumber_t agno; + int tries = 8; + +retry: + fsc->icount = 0; + fsc->ifree = 0; + fsc->fdblocks = 0; + + for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { + pag = xfs_perag_get(mp, agno); + + /* This somehow got unset since the warmup? */ + if (!pag->pagi_init || !pag->pagf_init) { + xfs_perag_put(pag); + return -EFSCORRUPTED; + } + + /* Count all the inodes */ + fsc->icount += pag->pagi_count; + fsc->ifree += pag->pagi_freecount; + + /* Add up the free/freelist/bnobt/cntbt blocks */ + fsc->fdblocks += pag->pagf_freeblks; + fsc->fdblocks += pag->pagf_flcount; + fsc->fdblocks += pag->pagf_btreeblks; + + /* + * Per-AG reservations are taken out of the incore counters, + * so they must be left out of the free blocks computation. + */ + fsc->fdblocks -= pag->pag_meta_resv.ar_reserved; + fsc->fdblocks -= pag->pag_rmapbt_resv.ar_orig_reserved; + + xfs_perag_put(pag); + + if (fatal_signal_pending(current)) + break; + } + + /* + * The global incore space reservation is taken from the incore + * counters, so leave that out of the computation. + */ + fsc->fdblocks -= mp->m_resblks_avail; + + /* + * Delayed allocation reservations are taken out of the incore counters + * but not recorded on disk, so leave them and their indlen blocks out + * of the computation. + */ + delayed = percpu_counter_sum(&mp->m_delalloc_blks); + fsc->fdblocks -= delayed; + + trace_xchk_fscounters_calc(mp, fsc->icount, fsc->ifree, fsc->fdblocks, + delayed); + + + /* Bail out if the values we compute are totally nonsense. */ + if (fsc->icount < fsc->icount_min || fsc->icount > fsc->icount_max || + fsc->fdblocks > mp->m_sb.sb_dblocks || + fsc->ifree > fsc->icount_max) + return -EFSCORRUPTED; + + /* + * If ifree > icount then we probably had some perturbation in the + * counters while we were calculating things. We'll try a few times + * to maintain ifree <= icount before giving up. + */ + if (fsc->ifree > fsc->icount) { + if (tries--) + goto retry; + xchk_set_incomplete(sc); + return 0; + } + + return 0; +} + +/* + * Is the @counter reasonably close to the @expected value? + * + * We neither locked nor froze anything in the filesystem while aggregating the + * per-AG data to compute the @expected value, which means that the counter + * could have changed. We know the @old_value of the summation of the counter + * before the aggregation, and we re-sum the counter now. If the expected + * value falls between the two summations, we're ok. + * + * Otherwise, we /might/ have a problem. If the change in the summations is + * more than we want to tolerate, the filesystem is probably busy and we should + * just send back INCOMPLETE and see if userspace will try again. + */ +static inline bool +xchk_fscount_within_range( + struct xfs_scrub *sc, + const int64_t old_value, + struct percpu_counter *counter, + uint64_t expected) +{ + int64_t min_value, max_value; + int64_t curr_value = percpu_counter_sum(counter); + + trace_xchk_fscounters_within_range(sc->mp, expected, curr_value, + old_value); + + /* Negative values are always wrong. */ + if (curr_value < 0) + return false; + + /* Exact matches are always ok. */ + if (curr_value == expected) + return true; + + min_value = min(old_value, curr_value); + max_value = max(old_value, curr_value); + + /* Within the before-and-after range is ok. */ + if (expected >= min_value && expected <= max_value) + return true; + + /* + * If the difference between the two summations is too large, the fs + * might just be busy and so we'll mark the scrub incomplete. Return + * true here so that we don't mark the counter corrupt. + * + * XXX: In the future when userspace can grant scrub permission to + * quiesce the filesystem to solve the outsized variance problem, this + * check should be moved up and the return code changed to signal to + * userspace that we need quiesce permission. + */ + if (max_value - min_value >= XCHK_FSCOUNT_MIN_VARIANCE) { + xchk_set_incomplete(sc); + return true; + } + + return false; +} + +/* Check the superblock counters. */ +int +xchk_fscounters( + struct xfs_scrub *sc) +{ + struct xfs_mount *mp = sc->mp; + struct xchk_fscounters *fsc = sc->buf; + int64_t icount, ifree, fdblocks; + int error; + + /* Snapshot the percpu counters. */ + icount = percpu_counter_sum(&mp->m_icount); + ifree = percpu_counter_sum(&mp->m_ifree); + fdblocks = percpu_counter_sum(&mp->m_fdblocks); + + /* No negative values, please! */ + if (icount < 0 || ifree < 0 || fdblocks < 0) + xchk_set_corrupt(sc); + + /* See if icount is obviously wrong. */ + if (icount < fsc->icount_min || icount > fsc->icount_max) + xchk_set_corrupt(sc); + + /* See if fdblocks is obviously wrong. */ + if (fdblocks > mp->m_sb.sb_dblocks) + xchk_set_corrupt(sc); + + /* + * If ifree exceeds icount by more than the minimum variance then + * something's probably wrong with the counters. + */ + if (ifree > icount && ifree - icount > XCHK_FSCOUNT_MIN_VARIANCE) + xchk_set_corrupt(sc); + + /* Walk the incore AG headers to calculate the expected counters. */ + error = xchk_fscount_aggregate_agcounts(sc, fsc); + if (!xchk_process_error(sc, 0, XFS_SB_BLOCK(mp), &error)) + return error; + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE) + return 0; + + /* Compare the in-core counters with whatever we counted. */ + if (!xchk_fscount_within_range(sc, icount, &mp->m_icount, fsc->icount)) + xchk_set_corrupt(sc); + + if (!xchk_fscount_within_range(sc, ifree, &mp->m_ifree, fsc->ifree)) + xchk_set_corrupt(sc); + + if (!xchk_fscount_within_range(sc, fdblocks, &mp->m_fdblocks, + fsc->fdblocks)) + xchk_set_corrupt(sc); + + return 0; +} diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c new file mode 100644 index 000000000000..23cf8e2f25db --- /dev/null +++ b/fs/xfs/scrub/health.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_inode.h" +#include "xfs_health.h" +#include "scrub/scrub.h" +#include "scrub/health.h" + +/* + * Scrub and In-Core Filesystem Health Assessments + * =============================================== + * + * Online scrub and repair have the time and the ability to perform stronger + * checks than we can do from the metadata verifiers, because they can + * cross-reference records between data structures. Therefore, scrub is in a + * good position to update the online filesystem health assessments to reflect + * the good/bad state of the data structure. + * + * We therefore extend scrub in the following ways to achieve this: + * + * 1. Create a "sick_mask" field in the scrub context. When we're setting up a + * scrub call, set this to the default XFS_SICK_* flag(s) for the selected + * scrub type (call it A). Scrub and repair functions can override the default + * sick_mask value if they choose. + * + * 2. If the scrubber returns a runtime error code, we exit making no changes + * to the incore sick state. + * + * 3. If the scrubber finds that A is clean, use sick_mask to clear the incore + * sick flags before exiting. + * + * 4. If the scrubber finds that A is corrupt, use sick_mask to set the incore + * sick flags. If the user didn't want to repair then we exit, leaving the + * metadata structure unfixed and the sick flag set. + * + * 5. Now we know that A is corrupt and the user wants to repair, so run the + * repairer. If the repairer returns an error code, we exit with that error + * code, having made no further changes to the incore sick state. + * + * 6. If repair rebuilds A correctly and the subsequent re-scrub of A is clean, + * use sick_mask to clear the incore sick flags. This should have the effect + * that A is no longer marked sick. + * + * 7. If repair rebuilds A incorrectly, the re-scrub will find it corrupt and + * use sick_mask to set the incore sick flags. This should have no externally + * visible effect since we already set them in step (4). + * + * There are some complications to this story, however. For certain types of + * complementary metadata indices (e.g. inobt/finobt), it is easier to rebuild + * both structures at the same time. The following principles apply to this + * type of repair strategy: + * + * 8. Any repair function that rebuilds multiple structures should update + * sick_mask_visible to reflect whatever other structures are rebuilt, and + * verify that all the rebuilt structures can pass a scrub check. The outcomes + * of 5-7 still apply, but with a sick_mask that covers everything being + * rebuilt. + */ + +/* Map our scrub type to a sick mask and a set of health update functions. */ + +enum xchk_health_group { + XHG_FS = 1, + XHG_RT, + XHG_AG, + XHG_INO, +}; + +struct xchk_health_map { + enum xchk_health_group group; + unsigned int sick_mask; +}; + +static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = { + [XFS_SCRUB_TYPE_SB] = { XHG_AG, XFS_SICK_AG_SB }, + [XFS_SCRUB_TYPE_AGF] = { XHG_AG, XFS_SICK_AG_AGF }, + [XFS_SCRUB_TYPE_AGFL] = { XHG_AG, XFS_SICK_AG_AGFL }, + [XFS_SCRUB_TYPE_AGI] = { XHG_AG, XFS_SICK_AG_AGI }, + [XFS_SCRUB_TYPE_BNOBT] = { XHG_AG, XFS_SICK_AG_BNOBT }, + [XFS_SCRUB_TYPE_CNTBT] = { XHG_AG, XFS_SICK_AG_CNTBT }, + [XFS_SCRUB_TYPE_INOBT] = { XHG_AG, XFS_SICK_AG_INOBT }, + [XFS_SCRUB_TYPE_FINOBT] = { XHG_AG, XFS_SICK_AG_FINOBT }, + [XFS_SCRUB_TYPE_RMAPBT] = { XHG_AG, XFS_SICK_AG_RMAPBT }, + [XFS_SCRUB_TYPE_REFCNTBT] = { XHG_AG, XFS_SICK_AG_REFCNTBT }, + [XFS_SCRUB_TYPE_INODE] = { XHG_INO, XFS_SICK_INO_CORE }, + [XFS_SCRUB_TYPE_BMBTD] = { XHG_INO, XFS_SICK_INO_BMBTD }, + [XFS_SCRUB_TYPE_BMBTA] = { XHG_INO, XFS_SICK_INO_BMBTA }, + [XFS_SCRUB_TYPE_BMBTC] = { XHG_INO, XFS_SICK_INO_BMBTC }, + [XFS_SCRUB_TYPE_DIR] = { XHG_INO, XFS_SICK_INO_DIR }, + [XFS_SCRUB_TYPE_XATTR] = { XHG_INO, XFS_SICK_INO_XATTR }, + [XFS_SCRUB_TYPE_SYMLINK] = { XHG_INO, XFS_SICK_INO_SYMLINK }, + [XFS_SCRUB_TYPE_PARENT] = { XHG_INO, XFS_SICK_INO_PARENT }, + [XFS_SCRUB_TYPE_RTBITMAP] = { XHG_RT, XFS_SICK_RT_BITMAP }, + [XFS_SCRUB_TYPE_RTSUM] = { XHG_RT, XFS_SICK_RT_SUMMARY }, + [XFS_SCRUB_TYPE_UQUOTA] = { XHG_FS, XFS_SICK_FS_UQUOTA }, + [XFS_SCRUB_TYPE_GQUOTA] = { XHG_FS, XFS_SICK_FS_GQUOTA }, + [XFS_SCRUB_TYPE_PQUOTA] = { XHG_FS, XFS_SICK_FS_PQUOTA }, + [XFS_SCRUB_TYPE_FSCOUNTERS] = { XHG_FS, XFS_SICK_FS_COUNTERS }, +}; + +/* Return the health status mask for this scrub type. */ +unsigned int +xchk_health_mask_for_scrub_type( + __u32 scrub_type) +{ + return type_to_health_flag[scrub_type].sick_mask; +} + +/* + * Update filesystem health assessments based on what we found and did. + * + * If the scrubber finds errors, we mark sick whatever's mentioned in + * sick_mask, no matter whether this is a first scan or an + * evaluation of repair effectiveness. + * + * Otherwise, no direct corruption was found, so mark whatever's in + * sick_mask as healthy. + */ +void +xchk_update_health( + struct xfs_scrub *sc) +{ + struct xfs_perag *pag; + bool bad; + + if (!sc->sick_mask) + return; + + bad = (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT); + switch (type_to_health_flag[sc->sm->sm_type].group) { + case XHG_AG: + pag = xfs_perag_get(sc->mp, sc->sm->sm_agno); + if (bad) + xfs_ag_mark_sick(pag, sc->sick_mask); + else + xfs_ag_mark_healthy(pag, sc->sick_mask); + xfs_perag_put(pag); + break; + case XHG_INO: + if (!sc->ip) + return; + if (bad) + xfs_inode_mark_sick(sc->ip, sc->sick_mask); + else + xfs_inode_mark_healthy(sc->ip, sc->sick_mask); + break; + case XHG_FS: + if (bad) + xfs_fs_mark_sick(sc->mp, sc->sick_mask); + else + xfs_fs_mark_healthy(sc->mp, sc->sick_mask); + break; + case XHG_RT: + if (bad) + xfs_rt_mark_sick(sc->mp, sc->sick_mask); + else + xfs_rt_mark_healthy(sc->mp, sc->sick_mask); + break; + default: + ASSERT(0); + break; + } +} + +/* Is the given per-AG btree healthy enough for scanning? */ +bool +xchk_ag_btree_healthy_enough( + struct xfs_scrub *sc, + struct xfs_perag *pag, + xfs_btnum_t btnum) +{ + unsigned int mask = 0; + + /* + * We always want the cursor if it's the same type as whatever we're + * scrubbing, even if we already know the structure is corrupt. + * + * Otherwise, we're only interested in the btree for cross-referencing. + * If we know the btree is bad then don't bother, just set XFAIL. + */ + switch (btnum) { + case XFS_BTNUM_BNO: + if (sc->sm->sm_type == XFS_SCRUB_TYPE_BNOBT) + return true; + mask = XFS_SICK_AG_BNOBT; + break; + case XFS_BTNUM_CNT: + if (sc->sm->sm_type == XFS_SCRUB_TYPE_CNTBT) + return true; + mask = XFS_SICK_AG_CNTBT; + break; + case XFS_BTNUM_INO: + if (sc->sm->sm_type == XFS_SCRUB_TYPE_INOBT) + return true; + mask = XFS_SICK_AG_INOBT; + break; + case XFS_BTNUM_FINO: + if (sc->sm->sm_type == XFS_SCRUB_TYPE_FINOBT) + return true; + mask = XFS_SICK_AG_FINOBT; + break; + case XFS_BTNUM_RMAP: + if (sc->sm->sm_type == XFS_SCRUB_TYPE_RMAPBT) + return true; + mask = XFS_SICK_AG_RMAPBT; + break; + case XFS_BTNUM_REFC: + if (sc->sm->sm_type == XFS_SCRUB_TYPE_REFCNTBT) + return true; + mask = XFS_SICK_AG_REFCNTBT; + break; + default: + ASSERT(0); + return true; + } + + if (xfs_ag_has_sickness(pag, mask)) { + sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL; + return false; + } + + return true; +} diff --git a/fs/xfs/scrub/health.h b/fs/xfs/scrub/health.h new file mode 100644 index 000000000000..d0b938d3d028 --- /dev/null +++ b/fs/xfs/scrub/health.h @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#ifndef __XFS_SCRUB_HEALTH_H__ +#define __XFS_SCRUB_HEALTH_H__ + +unsigned int xchk_health_mask_for_scrub_type(__u32 scrub_type); +void xchk_update_health(struct xfs_scrub *sc); +bool xchk_ag_btree_healthy_enough(struct xfs_scrub *sc, struct xfs_perag *pag, + xfs_btnum_t btnum); + +#endif /* __XFS_SCRUB_HEALTH_H__ */ diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 700114f79a7d..693eb51f5efb 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -39,7 +39,7 @@ xchk_setup_ag_iallocbt( struct xfs_scrub *sc, struct xfs_inode *ip) { - return xchk_setup_ag_btree(sc, ip, sc->try_harder); + return xchk_setup_ag_btree(sc, ip, sc->flags & XCHK_TRY_HARDER); } /* Inode btree scrubber. */ @@ -185,7 +185,7 @@ xchk_iallocbt_check_cluster_ifree( if (error == -ENODATA) { /* Not cached, just read the disk buffer */ freemask_ok = irec_free ^ !!(dip->di_mode); - if (!bs->sc->try_harder && !freemask_ok) + if (!(bs->sc->flags & XCHK_TRY_HARDER) && !freemask_ok) return -EDEADLOCK; } else if (error < 0) { /* diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index 1c9d7c7f64f5..d5d197f1b80f 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -320,7 +320,7 @@ out: * If we failed to lock the parent inode even after a retry, just mark * this scrub incomplete and return. */ - if (sc->try_harder && error == -EDEADLOCK) { + if ((sc->flags & XCHK_TRY_HARDER) && error == -EDEADLOCK) { error = 0; xchk_set_incomplete(sc); } diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 782d582d3edd..5dfe2b5924db 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -60,7 +60,7 @@ xchk_setup_quota( dqtype = xchk_quota_to_dqtype(sc); if (dqtype == 0) return -EINVAL; - sc->has_quotaofflock = true; + sc->flags |= XCHK_HAS_QUOTAOFFLOCK; mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock); if (!xfs_this_quota_on(sc->mp, dqtype)) return -ENOENT; diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index f28f4bad317b..eb358f0f5e0a 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -46,8 +46,7 @@ int xrep_attempt( struct xfs_inode *ip, - struct xfs_scrub *sc, - bool *fixed) + struct xfs_scrub *sc) { int error = 0; @@ -66,13 +65,13 @@ xrep_attempt( * scrub so that we can tell userspace if we fixed the problem. */ sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT; - *fixed = true; + sc->flags |= XREP_ALREADY_FIXED; return -EAGAIN; case -EDEADLOCK: case -EAGAIN: /* Tell the caller to try again having grabbed all the locks. */ - if (!sc->try_harder) { - sc->try_harder = true; + if (!(sc->flags & XCHK_TRY_HARDER)) { + sc->flags |= XCHK_TRY_HARDER; return -EAGAIN; } /* @@ -137,10 +136,16 @@ xrep_roll_ag_trans( if (sc->sa.agfl_bp) xfs_trans_bhold(sc->tp, sc->sa.agfl_bp); - /* Roll the transaction. */ + /* + * Roll the transaction. We still own the buffer and the buffer lock + * regardless of whether or not the roll succeeds. If the roll fails, + * the buffers will be released during teardown on our way out of the + * kernel. If it succeeds, we join them to the new transaction and + * move on. + */ error = xfs_trans_roll(&sc->tp); if (error) - goto out_release; + return error; /* Join AG headers to the new transaction. */ if (sc->sa.agi_bp) @@ -151,21 +156,6 @@ xrep_roll_ag_trans( xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp); return 0; - -out_release: - /* - * Rolling failed, so release the hold on the buffers. The - * buffers will be released during teardown on our way out - * of the kernel. - */ - if (sc->sa.agi_bp) - xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp); - if (sc->sa.agf_bp) - xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp); - if (sc->sa.agfl_bp) - xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp); - - return error; } /* diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index d990314eb08b..60c61d7052a8 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -15,7 +15,7 @@ static inline int xrep_notsupported(struct xfs_scrub *sc) /* Repair helpers */ -int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc, bool *fixed); +int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc); void xrep_failure(struct xfs_mount *mp); int xrep_roll_ag_trans(struct xfs_scrub *sc); bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks, @@ -64,8 +64,7 @@ int xrep_agi(struct xfs_scrub *sc); static inline int xrep_attempt( struct xfs_inode *ip, - struct xfs_scrub *sc, - bool *fixed) + struct xfs_scrub *sc) { return -EOPNOTSUPP; } diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 1b2344d00525..f630389ee176 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -40,6 +40,7 @@ #include "scrub/trace.h" #include "scrub/btree.h" #include "scrub/repair.h" +#include "scrub/health.h" /* * Online Scrub and Repair @@ -186,8 +187,12 @@ xchk_teardown( xfs_irele(sc->ip); sc->ip = NULL; } - if (sc->has_quotaofflock) + if (sc->flags & XCHK_REAPING_DISABLED) + xchk_start_reaping(sc); + if (sc->flags & XCHK_HAS_QUOTAOFFLOCK) { mutex_unlock(&sc->mp->m_quotainfo->qi_quotaofflock); + sc->flags &= ~XCHK_HAS_QUOTAOFFLOCK; + } if (sc->buf) { kmem_free(sc->buf); sc->buf = NULL; @@ -347,6 +352,12 @@ static const struct xchk_meta_ops meta_scrub_ops[] = { .scrub = xchk_quota, .repair = xrep_notsupported, }, + [XFS_SCRUB_TYPE_FSCOUNTERS] = { /* fs summary counters */ + .type = ST_FS, + .setup = xchk_setup_fscounters, + .scrub = xchk_fscounters, + .repair = xrep_notsupported, + }, }; /* This isn't a stable feature, warn once per day. */ @@ -466,10 +477,14 @@ xfs_scrub_metadata( struct xfs_inode *ip, struct xfs_scrub_metadata *sm) { - struct xfs_scrub sc; + struct xfs_scrub sc = { + .mp = ip->i_mount, + .sm = sm, + .sa = { + .agno = NULLAGNUMBER, + }, + }; struct xfs_mount *mp = ip->i_mount; - bool try_harder = false; - bool already_fixed = false; int error = 0; BUILD_BUG_ON(sizeof(meta_scrub_ops) != @@ -491,21 +506,17 @@ xfs_scrub_metadata( xchk_experimental_warning(mp); + sc.ops = &meta_scrub_ops[sm->sm_type]; + sc.sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type); retry_op: /* Set up for the operation. */ - memset(&sc, 0, sizeof(sc)); - sc.mp = ip->i_mount; - sc.sm = sm; - sc.ops = &meta_scrub_ops[sm->sm_type]; - sc.try_harder = try_harder; - sc.sa.agno = NULLAGNUMBER; error = sc.ops->setup(&sc, ip); if (error) goto out_teardown; /* Scrub for errors. */ error = sc.ops->scrub(&sc); - if (!try_harder && error == -EDEADLOCK) { + if (!(sc.flags & XCHK_TRY_HARDER) && error == -EDEADLOCK) { /* * Scrubbers return -EDEADLOCK to mean 'try harder'. * Tear down everything we hold, then set up again with @@ -514,12 +525,15 @@ retry_op: error = xchk_teardown(&sc, ip, 0); if (error) goto out; - try_harder = true; + sc.flags |= XCHK_TRY_HARDER; goto retry_op; } else if (error) goto out_teardown; - if ((sc.sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) && !already_fixed) { + xchk_update_health(&sc); + + if ((sc.sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) && + !(sc.flags & XREP_ALREADY_FIXED)) { bool needs_fix; /* Let debug users force us into the repair routines. */ @@ -542,10 +556,13 @@ retry_op: * If it's broken, userspace wants us to fix it, and we haven't * already tried to fix it, then attempt a repair. */ - error = xrep_attempt(ip, &sc, &already_fixed); + error = xrep_attempt(ip, &sc); if (error == -EAGAIN) { - if (sc.try_harder) - try_harder = true; + /* + * Either the repair function succeeded or it couldn't + * get all the resources it needs; either way, we go + * back to the beginning and call the scrub function. + */ error = xchk_teardown(&sc, ip, 0); if (error) { xrep_failure(mp); diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index 22f754fba8e5..ad1ceb44a628 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -62,13 +62,27 @@ struct xfs_scrub { struct xfs_inode *ip; void *buf; uint ilock_flags; - bool try_harder; - bool has_quotaofflock; + + /* See the XCHK/XREP state flags below. */ + unsigned int flags; + + /* + * The XFS_SICK_* flags that correspond to the metadata being scrubbed + * or repaired. We will use this mask to update the in-core fs health + * status with whatever we find. + */ + unsigned int sick_mask; /* State tracking for single-AG operations. */ struct xchk_ag sa; }; +/* XCHK state flags grow up from zero, XREP state flags grown down from 2^31 */ +#define XCHK_TRY_HARDER (1 << 0) /* can't get resources, try again */ +#define XCHK_HAS_QUOTAOFFLOCK (1 << 1) /* we hold the quotaoff lock */ +#define XCHK_REAPING_DISABLED (1 << 2) /* background block reaping paused */ +#define XREP_ALREADY_FIXED (1 << 31) /* checking our repair work */ + /* Metadata scrubbers */ int xchk_tester(struct xfs_scrub *sc); int xchk_superblock(struct xfs_scrub *sc); @@ -113,6 +127,7 @@ xchk_quota(struct xfs_scrub *sc) return -ENOENT; } #endif +int xchk_fscounters(struct xfs_scrub *sc); /* cross-referencing helpers */ void xchk_xref_is_used_space(struct xfs_scrub *sc, xfs_agblock_t agbno, @@ -138,4 +153,12 @@ void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno, # define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0) #endif +struct xchk_fscounters { + uint64_t icount; + uint64_t ifree; + uint64_t fdblocks; + unsigned long long icount_min; + unsigned long long icount_max; +}; + #endif /* __XFS_SCRUB_SCRUB_H__ */ diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 3c83e8b3b39c..3362bae28b46 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -50,6 +50,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTSUM); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_UQUOTA); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_GQUOTA); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PQUOTA); +TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS); #define XFS_SCRUB_TYPE_STRINGS \ { XFS_SCRUB_TYPE_PROBE, "probe" }, \ @@ -75,7 +76,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PQUOTA); { XFS_SCRUB_TYPE_RTSUM, "rtsummary" }, \ { XFS_SCRUB_TYPE_UQUOTA, "usrquota" }, \ { XFS_SCRUB_TYPE_GQUOTA, "grpquota" }, \ - { XFS_SCRUB_TYPE_PQUOTA, "prjquota" } + { XFS_SCRUB_TYPE_PQUOTA, "prjquota" }, \ + { XFS_SCRUB_TYPE_FSCOUNTERS, "fscounters" } DECLARE_EVENT_CLASS(xchk_class, TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm, @@ -223,6 +225,7 @@ DEFINE_EVENT(xchk_block_error_class, name, \ void *ret_ip), \ TP_ARGS(sc, daddr, ret_ip)) +DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_fs_error); DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_error); DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_preen); @@ -590,6 +593,64 @@ TRACE_EVENT(xchk_iallocbt_check_cluster, __entry->cluster_ino) ) +TRACE_EVENT(xchk_fscounters_calc, + TP_PROTO(struct xfs_mount *mp, uint64_t icount, uint64_t ifree, + uint64_t fdblocks, uint64_t delalloc), + TP_ARGS(mp, icount, ifree, fdblocks, delalloc), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int64_t, icount_sb) + __field(uint64_t, icount_calculated) + __field(int64_t, ifree_sb) + __field(uint64_t, ifree_calculated) + __field(int64_t, fdblocks_sb) + __field(uint64_t, fdblocks_calculated) + __field(uint64_t, delalloc) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->icount_sb = mp->m_sb.sb_icount; + __entry->icount_calculated = icount; + __entry->ifree_sb = mp->m_sb.sb_ifree; + __entry->ifree_calculated = ifree; + __entry->fdblocks_sb = mp->m_sb.sb_fdblocks; + __entry->fdblocks_calculated = fdblocks; + __entry->delalloc = delalloc; + ), + TP_printk("dev %d:%d icount %lld:%llu ifree %lld::%llu fdblocks %lld::%llu delalloc %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->icount_sb, + __entry->icount_calculated, + __entry->ifree_sb, + __entry->ifree_calculated, + __entry->fdblocks_sb, + __entry->fdblocks_calculated, + __entry->delalloc) +) + +TRACE_EVENT(xchk_fscounters_within_range, + TP_PROTO(struct xfs_mount *mp, uint64_t expected, int64_t curr_value, + int64_t old_value), + TP_ARGS(mp, expected, curr_value, old_value), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(uint64_t, expected) + __field(int64_t, curr_value) + __field(int64_t, old_value) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->expected = expected; + __entry->curr_value = curr_value; + __entry->old_value = old_value; + ), + TP_printk("dev %d:%d expected %llu curr_value %lld old_value %lld", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->expected, + __entry->curr_value, + __entry->old_value) +) + /* repair tracepoints */ #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 3619e9e8d359..a6f0f4761a37 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -98,7 +98,6 @@ xfs_destroy_ioend( for (bio = &ioend->io_inline_bio; bio; bio = next) { struct bio_vec *bvec; - int i; struct bvec_iter_all iter_all; /* @@ -111,7 +110,7 @@ xfs_destroy_ioend( next = bio->bi_private; /* walk each page on bio, ending page IO on them */ - bio_for_each_segment_all(bvec, bio, i, iter_all) + bio_for_each_segment_all(bvec, bio, iter_all) xfs_finish_page_writeback(inode, bvec, error); bio_put(bio); } @@ -234,11 +233,10 @@ xfs_setfilesize_ioend( * IO write completion. */ STATIC void -xfs_end_io( - struct work_struct *work) +xfs_end_ioend( + struct xfs_ioend *ioend) { - struct xfs_ioend *ioend = - container_of(work, struct xfs_ioend, io_work); + struct list_head ioend_list; struct xfs_inode *ip = XFS_I(ioend->io_inode); xfs_off_t offset = ioend->io_offset; size_t size = ioend->io_size; @@ -275,7 +273,116 @@ xfs_end_io( done: if (ioend->io_append_trans) error = xfs_setfilesize_ioend(ioend, error); + list_replace_init(&ioend->io_list, &ioend_list); xfs_destroy_ioend(ioend, error); + + while (!list_empty(&ioend_list)) { + ioend = list_first_entry(&ioend_list, struct xfs_ioend, + io_list); + list_del_init(&ioend->io_list); + xfs_destroy_ioend(ioend, error); + } +} + +/* + * We can merge two adjacent ioends if they have the same set of work to do. + */ +static bool +xfs_ioend_can_merge( + struct xfs_ioend *ioend, + int ioend_error, + struct xfs_ioend *next) +{ + int next_error; + + next_error = blk_status_to_errno(next->io_bio->bi_status); + if (ioend_error != next_error) + return false; + if ((ioend->io_fork == XFS_COW_FORK) ^ (next->io_fork == XFS_COW_FORK)) + return false; + if ((ioend->io_state == XFS_EXT_UNWRITTEN) ^ + (next->io_state == XFS_EXT_UNWRITTEN)) + return false; + if (ioend->io_offset + ioend->io_size != next->io_offset) + return false; + if (xfs_ioend_is_append(ioend) != xfs_ioend_is_append(next)) + return false; + return true; +} + +/* Try to merge adjacent completions. */ +STATIC void +xfs_ioend_try_merge( + struct xfs_ioend *ioend, + struct list_head *more_ioends) +{ + struct xfs_ioend *next_ioend; + int ioend_error; + int error; + + if (list_empty(more_ioends)) + return; + + ioend_error = blk_status_to_errno(ioend->io_bio->bi_status); + + while (!list_empty(more_ioends)) { + next_ioend = list_first_entry(more_ioends, struct xfs_ioend, + io_list); + if (!xfs_ioend_can_merge(ioend, ioend_error, next_ioend)) + break; + list_move_tail(&next_ioend->io_list, &ioend->io_list); + ioend->io_size += next_ioend->io_size; + if (ioend->io_append_trans) { + error = xfs_setfilesize_ioend(next_ioend, 1); + ASSERT(error == 1); + } + } +} + +/* list_sort compare function for ioends */ +static int +xfs_ioend_compare( + void *priv, + struct list_head *a, + struct list_head *b) +{ + struct xfs_ioend *ia; + struct xfs_ioend *ib; + + ia = container_of(a, struct xfs_ioend, io_list); + ib = container_of(b, struct xfs_ioend, io_list); + if (ia->io_offset < ib->io_offset) + return -1; + else if (ia->io_offset > ib->io_offset) + return 1; + return 0; +} + +/* Finish all pending io completions. */ +void +xfs_end_io( + struct work_struct *work) +{ + struct xfs_inode *ip; + struct xfs_ioend *ioend; + struct list_head completion_list; + unsigned long flags; + + ip = container_of(work, struct xfs_inode, i_ioend_work); + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + list_replace_init(&ip->i_ioend_list, &completion_list); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); + + list_sort(NULL, &completion_list, xfs_ioend_compare); + + while (!list_empty(&completion_list)) { + ioend = list_first_entry(&completion_list, struct xfs_ioend, + io_list); + list_del_init(&ioend->io_list); + xfs_ioend_try_merge(ioend, &completion_list); + xfs_end_ioend(ioend); + } } STATIC void @@ -283,14 +390,20 @@ xfs_end_bio( struct bio *bio) { struct xfs_ioend *ioend = bio->bi_private; - struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount; + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + unsigned long flags; if (ioend->io_fork == XFS_COW_FORK || - ioend->io_state == XFS_EXT_UNWRITTEN) - queue_work(mp->m_unwritten_workqueue, &ioend->io_work); - else if (ioend->io_append_trans) - queue_work(mp->m_data_workqueue, &ioend->io_work); - else + ioend->io_state == XFS_EXT_UNWRITTEN || + ioend->io_append_trans != NULL) { + spin_lock_irqsave(&ip->i_ioend_lock, flags); + if (list_empty(&ip->i_ioend_list)) + WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, + &ip->i_ioend_work)); + list_add_tail(&ioend->io_list, &ip->i_ioend_list); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); + } else xfs_destroy_ioend(ioend, blk_status_to_errno(bio->bi_status)); } @@ -594,7 +707,6 @@ xfs_alloc_ioend( ioend->io_inode = inode; ioend->io_size = 0; ioend->io_offset = offset; - INIT_WORK(&ioend->io_work, xfs_end_io); ioend->io_append_trans = NULL; ioend->io_bio = bio; return ioend; diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 6c2615b83c5d..f62b03186c62 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -18,7 +18,6 @@ struct xfs_ioend { struct inode *io_inode; /* file being written to */ size_t io_size; /* size of the extent */ xfs_off_t io_offset; /* offset in the file */ - struct work_struct io_work; /* xfsdatad work queue */ struct xfs_trans *io_append_trans;/* xact. for size update */ struct bio *io_bio; /* bio being built */ struct bio io_inline_bio; /* MUST BE LAST! */ diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 2db43ff4f8b5..06d07f1e310b 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1193,6 +1193,8 @@ xfs_prepare_shift( * about to shift down every extent from offset to EOF. */ error = xfs_flush_unmap_range(ip, offset, XFS_ISIZE(ip)); + if (error) + return error; /* * Clean out anything hanging around in the cow fork now that diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 010db5f8fb00..65b32acfa0f6 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -605,6 +605,8 @@ xfs_buf_item_unlock( #if defined(DEBUG) || defined(XFS_WARN) bool ordered = bip->bli_flags & XFS_BLI_ORDERED; bool dirty = bip->bli_flags & XFS_BLI_DIRTY; + bool aborted = test_bit(XFS_LI_ABORTED, + &lip->li_flags); #endif trace_xfs_buf_item_unlock(bip); @@ -633,7 +635,7 @@ xfs_buf_item_unlock( released = xfs_buf_item_put(bip); if (hold || (stale && !released)) return; - ASSERT(!stale || test_bit(XFS_LI_ABORTED, &lip->li_flags)); + ASSERT(!stale || aborted); xfs_buf_relse(bp); } diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 9ee2a7d02e70..d0df0ed50f4b 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -172,6 +172,8 @@ xfs_ioc_trim( if (copy_from_user(&range, urange, sizeof(range))) return -EFAULT; + range.minlen = max_t(u64, granularity, range.minlen); + minlen = BTOBB(range.minlen); /* * Truncating down the len isn't actually quite correct, but using * BBTOB would mean we trivially get overflows for values @@ -186,7 +188,6 @@ xfs_ioc_trim( start = BTOBB(range.start); end = start + BTOBBT(range.len) - 1; - minlen = BTOBB(max_t(u64, granularity, range.minlen)); if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1) end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 87e6dd5326d5..a1af984e4913 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -277,7 +277,8 @@ xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp) /* * Ensure that the given in-core dquot has a buffer on disk backing it, and - * return the buffer. This is called when the bmapi finds a hole. + * return the buffer locked and held. This is called when the bmapi finds a + * hole. */ STATIC int xfs_dquot_disk_alloc( @@ -355,13 +356,14 @@ xfs_dquot_disk_alloc( * If everything succeeds, the caller of this function is returned a * buffer that is locked and held to the transaction. The caller * is responsible for unlocking any buffer passed back, either - * manually or by committing the transaction. + * manually or by committing the transaction. On error, the buffer is + * released and not passed back. */ xfs_trans_bhold(tp, bp); error = xfs_defer_finish(tpp); - tp = *tpp; if (error) { - xfs_buf_relse(bp); + xfs_trans_bhold_release(*tpp, bp); + xfs_trans_brelse(*tpp, bp); return error; } *bpp = bp; @@ -521,7 +523,6 @@ xfs_qm_dqread_alloc( struct xfs_buf **bpp) { struct xfs_trans *tp; - struct xfs_buf *bp; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc, @@ -529,7 +530,7 @@ xfs_qm_dqread_alloc( if (error) goto err; - error = xfs_dquot_disk_alloc(&tp, dqp, &bp); + error = xfs_dquot_disk_alloc(&tp, dqp, bpp); if (error) goto err_cancel; @@ -539,10 +540,10 @@ xfs_qm_dqread_alloc( * Buffer was held to the transaction, so we have to unlock it * manually here because we're not passing it back. */ - xfs_buf_relse(bp); + xfs_buf_relse(*bpp); + *bpp = NULL; goto err; } - *bpp = bp; return 0; err_cancel: diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index a7ceae90110e..76748255f843 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -517,6 +517,9 @@ xfs_file_dio_aio_write( } if (iocb->ki_flags & IOCB_NOWAIT) { + /* unaligned dio always waits, bail */ + if (unaligned_io) + return -EAGAIN; if (!xfs_ilock_nowait(ip, iolock)) return -EAGAIN; } else { @@ -536,9 +539,6 @@ xfs_file_dio_aio_write( * xfs_file_aio_write_checks() for other reasons. */ if (unaligned_io) { - /* unaligned dio always waits, bail */ - if (iocb->ki_flags & IOCB_NOWAIT) - return -EAGAIN; inode_dio_wait(inode); } else if (iolock == XFS_IOLOCK_EXCL) { xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 584648582ba7..3d0e0570e3aa 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -289,7 +289,7 @@ xfs_growfs_log( * exported through ioctl XFS_IOC_FSCOUNTS */ -int +void xfs_fs_counts( xfs_mount_t *mp, xfs_fsop_counts_t *cnt) @@ -302,7 +302,6 @@ xfs_fs_counts( spin_lock(&mp->m_sb_lock); cnt->freertx = mp->m_sb.sb_frextents; spin_unlock(&mp->m_sb_lock); - return 0; } /* diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h index d023db0862c2..92869f6ec8d3 100644 --- a/fs/xfs/xfs_fsops.h +++ b/fs/xfs/xfs_fsops.h @@ -8,7 +8,7 @@ extern int xfs_growfs_data(xfs_mount_t *mp, xfs_growfs_data_t *in); extern int xfs_growfs_log(xfs_mount_t *mp, xfs_growfs_log_t *in); -extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt); +extern void xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt); extern int xfs_reserve_blocks(xfs_mount_t *mp, uint64_t *inval, xfs_fsop_resblks_t *outval); extern int xfs_fs_goingdown(xfs_mount_t *mp, uint32_t inflags); diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c new file mode 100644 index 000000000000..4c4929f9e7bf --- /dev/null +++ b/fs/xfs/xfs_health.c @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_da_format.h" +#include "xfs_da_btree.h" +#include "xfs_inode.h" +#include "xfs_trace.h" +#include "xfs_health.h" + +/* + * Warn about metadata corruption that we detected but haven't fixed, and + * make sure we're not sitting on anything that would get in the way of + * recovery. + */ +void +xfs_health_unmount( + struct xfs_mount *mp) +{ + struct xfs_perag *pag; + xfs_agnumber_t agno; + unsigned int sick = 0; + unsigned int checked = 0; + bool warn = false; + + if (XFS_FORCED_SHUTDOWN(mp)) + return; + + /* Measure AG corruption levels. */ + for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { + pag = xfs_perag_get(mp, agno); + xfs_ag_measure_sickness(pag, &sick, &checked); + if (sick) { + trace_xfs_ag_unfixed_corruption(mp, agno, sick); + warn = true; + } + xfs_perag_put(pag); + } + + /* Measure realtime volume corruption levels. */ + xfs_rt_measure_sickness(mp, &sick, &checked); + if (sick) { + trace_xfs_rt_unfixed_corruption(mp, sick); + warn = true; + } + + /* + * Measure fs corruption and keep the sample around for the warning. + * See the note below for why we exempt FS_COUNTERS. + */ + xfs_fs_measure_sickness(mp, &sick, &checked); + if (sick & ~XFS_SICK_FS_COUNTERS) { + trace_xfs_fs_unfixed_corruption(mp, sick); + warn = true; + } + + if (warn) { + xfs_warn(mp, +"Uncorrected metadata errors detected; please run xfs_repair."); + + /* + * We discovered uncorrected metadata problems at some point + * during this filesystem mount and have advised the + * administrator to run repair once the unmount completes. + * + * However, we must be careful -- when FSCOUNTERS are flagged + * unhealthy, the unmount procedure omits writing the clean + * unmount record to the log so that the next mount will run + * recovery and recompute the summary counters. In other + * words, we leave a dirty log to get the counters fixed. + * + * Unfortunately, xfs_repair cannot recover dirty logs, so if + * there were filesystem problems, FSCOUNTERS was flagged, and + * the administrator takes our advice to run xfs_repair, + * they'll have to zap the log before repairing structures. + * We don't really want to encourage this, so we mark the + * FSCOUNTERS healthy so that a subsequent repair run won't see + * a dirty log. + */ + if (sick & XFS_SICK_FS_COUNTERS) + xfs_fs_mark_healthy(mp, XFS_SICK_FS_COUNTERS); + } +} + +/* Mark unhealthy per-fs metadata. */ +void +xfs_fs_mark_sick( + struct xfs_mount *mp, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_FS_PRIMARY)); + trace_xfs_fs_mark_sick(mp, mask); + + spin_lock(&mp->m_sb_lock); + mp->m_fs_sick |= mask; + mp->m_fs_checked |= mask; + spin_unlock(&mp->m_sb_lock); +} + +/* Mark a per-fs metadata healed. */ +void +xfs_fs_mark_healthy( + struct xfs_mount *mp, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_FS_PRIMARY)); + trace_xfs_fs_mark_healthy(mp, mask); + + spin_lock(&mp->m_sb_lock); + mp->m_fs_sick &= ~mask; + mp->m_fs_checked |= mask; + spin_unlock(&mp->m_sb_lock); +} + +/* Sample which per-fs metadata are unhealthy. */ +void +xfs_fs_measure_sickness( + struct xfs_mount *mp, + unsigned int *sick, + unsigned int *checked) +{ + spin_lock(&mp->m_sb_lock); + *sick = mp->m_fs_sick; + *checked = mp->m_fs_checked; + spin_unlock(&mp->m_sb_lock); +} + +/* Mark unhealthy realtime metadata. */ +void +xfs_rt_mark_sick( + struct xfs_mount *mp, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_RT_PRIMARY)); + trace_xfs_rt_mark_sick(mp, mask); + + spin_lock(&mp->m_sb_lock); + mp->m_rt_sick |= mask; + mp->m_rt_checked |= mask; + spin_unlock(&mp->m_sb_lock); +} + +/* Mark a realtime metadata healed. */ +void +xfs_rt_mark_healthy( + struct xfs_mount *mp, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_RT_PRIMARY)); + trace_xfs_rt_mark_healthy(mp, mask); + + spin_lock(&mp->m_sb_lock); + mp->m_rt_sick &= ~mask; + mp->m_rt_checked |= mask; + spin_unlock(&mp->m_sb_lock); +} + +/* Sample which realtime metadata are unhealthy. */ +void +xfs_rt_measure_sickness( + struct xfs_mount *mp, + unsigned int *sick, + unsigned int *checked) +{ + spin_lock(&mp->m_sb_lock); + *sick = mp->m_rt_sick; + *checked = mp->m_rt_checked; + spin_unlock(&mp->m_sb_lock); +} + +/* Mark unhealthy per-ag metadata. */ +void +xfs_ag_mark_sick( + struct xfs_perag *pag, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_AG_PRIMARY)); + trace_xfs_ag_mark_sick(pag->pag_mount, pag->pag_agno, mask); + + spin_lock(&pag->pag_state_lock); + pag->pag_sick |= mask; + pag->pag_checked |= mask; + spin_unlock(&pag->pag_state_lock); +} + +/* Mark per-ag metadata ok. */ +void +xfs_ag_mark_healthy( + struct xfs_perag *pag, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_AG_PRIMARY)); + trace_xfs_ag_mark_healthy(pag->pag_mount, pag->pag_agno, mask); + + spin_lock(&pag->pag_state_lock); + pag->pag_sick &= ~mask; + pag->pag_checked |= mask; + spin_unlock(&pag->pag_state_lock); +} + +/* Sample which per-ag metadata are unhealthy. */ +void +xfs_ag_measure_sickness( + struct xfs_perag *pag, + unsigned int *sick, + unsigned int *checked) +{ + spin_lock(&pag->pag_state_lock); + *sick = pag->pag_sick; + *checked = pag->pag_checked; + spin_unlock(&pag->pag_state_lock); +} + +/* Mark the unhealthy parts of an inode. */ +void +xfs_inode_mark_sick( + struct xfs_inode *ip, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_INO_PRIMARY)); + trace_xfs_inode_mark_sick(ip, mask); + + spin_lock(&ip->i_flags_lock); + ip->i_sick |= mask; + ip->i_checked |= mask; + spin_unlock(&ip->i_flags_lock); +} + +/* Mark parts of an inode healed. */ +void +xfs_inode_mark_healthy( + struct xfs_inode *ip, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_INO_PRIMARY)); + trace_xfs_inode_mark_healthy(ip, mask); + + spin_lock(&ip->i_flags_lock); + ip->i_sick &= ~mask; + ip->i_checked |= mask; + spin_unlock(&ip->i_flags_lock); +} + +/* Sample which parts of an inode are unhealthy. */ +void +xfs_inode_measure_sickness( + struct xfs_inode *ip, + unsigned int *sick, + unsigned int *checked) +{ + spin_lock(&ip->i_flags_lock); + *sick = ip->i_sick; + *checked = ip->i_checked; + spin_unlock(&ip->i_flags_lock); +} + +/* Mappings between internal sick masks and ioctl sick masks. */ + +struct ioctl_sick_map { + unsigned int sick_mask; + unsigned int ioctl_mask; +}; + +static const struct ioctl_sick_map fs_map[] = { + { XFS_SICK_FS_COUNTERS, XFS_FSOP_GEOM_SICK_COUNTERS}, + { XFS_SICK_FS_UQUOTA, XFS_FSOP_GEOM_SICK_UQUOTA }, + { XFS_SICK_FS_GQUOTA, XFS_FSOP_GEOM_SICK_GQUOTA }, + { XFS_SICK_FS_PQUOTA, XFS_FSOP_GEOM_SICK_PQUOTA }, + { 0, 0 }, +}; + +static const struct ioctl_sick_map rt_map[] = { + { XFS_SICK_RT_BITMAP, XFS_FSOP_GEOM_SICK_RT_BITMAP }, + { XFS_SICK_RT_SUMMARY, XFS_FSOP_GEOM_SICK_RT_SUMMARY }, + { 0, 0 }, +}; + +static inline void +xfgeo_health_tick( + struct xfs_fsop_geom *geo, + unsigned int sick, + unsigned int checked, + const struct ioctl_sick_map *m) +{ + if (checked & m->sick_mask) + geo->checked |= m->ioctl_mask; + if (sick & m->sick_mask) + geo->sick |= m->ioctl_mask; +} + +/* Fill out fs geometry health info. */ +void +xfs_fsop_geom_health( + struct xfs_mount *mp, + struct xfs_fsop_geom *geo) +{ + const struct ioctl_sick_map *m; + unsigned int sick; + unsigned int checked; + + geo->sick = 0; + geo->checked = 0; + + xfs_fs_measure_sickness(mp, &sick, &checked); + for (m = fs_map; m->sick_mask; m++) + xfgeo_health_tick(geo, sick, checked, m); + + xfs_rt_measure_sickness(mp, &sick, &checked); + for (m = rt_map; m->sick_mask; m++) + xfgeo_health_tick(geo, sick, checked, m); +} + +static const struct ioctl_sick_map ag_map[] = { + { XFS_SICK_AG_SB, XFS_AG_GEOM_SICK_SB }, + { XFS_SICK_AG_AGF, XFS_AG_GEOM_SICK_AGF }, + { XFS_SICK_AG_AGFL, XFS_AG_GEOM_SICK_AGFL }, + { XFS_SICK_AG_AGI, XFS_AG_GEOM_SICK_AGI }, + { XFS_SICK_AG_BNOBT, XFS_AG_GEOM_SICK_BNOBT }, + { XFS_SICK_AG_CNTBT, XFS_AG_GEOM_SICK_CNTBT }, + { XFS_SICK_AG_INOBT, XFS_AG_GEOM_SICK_INOBT }, + { XFS_SICK_AG_FINOBT, XFS_AG_GEOM_SICK_FINOBT }, + { XFS_SICK_AG_RMAPBT, XFS_AG_GEOM_SICK_RMAPBT }, + { XFS_SICK_AG_REFCNTBT, XFS_AG_GEOM_SICK_REFCNTBT }, + { 0, 0 }, +}; + +/* Fill out ag geometry health info. */ +void +xfs_ag_geom_health( + struct xfs_perag *pag, + struct xfs_ag_geometry *ageo) +{ + const struct ioctl_sick_map *m; + unsigned int sick; + unsigned int checked; + + ageo->ag_sick = 0; + ageo->ag_checked = 0; + + xfs_ag_measure_sickness(pag, &sick, &checked); + for (m = ag_map; m->sick_mask; m++) { + if (checked & m->sick_mask) + ageo->ag_checked |= m->ioctl_mask; + if (sick & m->sick_mask) + ageo->ag_sick |= m->ioctl_mask; + } +} + +static const struct ioctl_sick_map ino_map[] = { + { XFS_SICK_INO_CORE, XFS_BS_SICK_INODE }, + { XFS_SICK_INO_BMBTD, XFS_BS_SICK_BMBTD }, + { XFS_SICK_INO_BMBTA, XFS_BS_SICK_BMBTA }, + { XFS_SICK_INO_BMBTC, XFS_BS_SICK_BMBTC }, + { XFS_SICK_INO_DIR, XFS_BS_SICK_DIR }, + { XFS_SICK_INO_XATTR, XFS_BS_SICK_XATTR }, + { XFS_SICK_INO_SYMLINK, XFS_BS_SICK_SYMLINK }, + { XFS_SICK_INO_PARENT, XFS_BS_SICK_PARENT }, + { 0, 0 }, +}; + +/* Fill out bulkstat health info. */ +void +xfs_bulkstat_health( + struct xfs_inode *ip, + struct xfs_bstat *bs) +{ + const struct ioctl_sick_map *m; + unsigned int sick; + unsigned int checked; + + bs->bs_sick = 0; + bs->bs_checked = 0; + + xfs_inode_measure_sickness(ip, &sick, &checked); + for (m = ino_map; m->sick_mask; m++) { + if (checked & m->sick_mask) + bs->bs_checked |= m->ioctl_mask; + if (sick & m->sick_mask) + bs->bs_sick |= m->ioctl_mask; + } +} diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 245483cc282b..a76b27565a18 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -70,6 +70,11 @@ xfs_inode_alloc( ip->i_flags = 0; ip->i_delayed_blks = 0; memset(&ip->i_d, 0, sizeof(ip->i_d)); + ip->i_sick = 0; + ip->i_checked = 0; + INIT_WORK(&ip->i_ioend_work, xfs_end_io); + INIT_LIST_HEAD(&ip->i_ioend_list); + spin_lock_init(&ip->i_ioend_lock); return ip; } @@ -446,6 +451,8 @@ xfs_iget_cache_hit( ip->i_flags |= XFS_INEW; xfs_inode_clear_reclaim_tag(pag, ip->i_ino); inode->i_state = I_NEW; + ip->i_sick = 0; + ip->i_checked = 0; ASSERT(!rwsem_is_locked(&inode->i_rwsem)); init_rwsem(&inode->i_rwsem); @@ -1815,7 +1822,7 @@ xfs_inode_clear_cowblocks_tag( /* Disable post-EOF and CoW block auto-reclamation. */ void -xfs_icache_disable_reclaim( +xfs_stop_block_reaping( struct xfs_mount *mp) { cancel_delayed_work_sync(&mp->m_eofblocks_work); @@ -1824,7 +1831,7 @@ xfs_icache_disable_reclaim( /* Enable post-EOF and CoW block auto-reclamation. */ void -xfs_icache_enable_reclaim( +xfs_start_block_reaping( struct xfs_mount *mp) { xfs_queue_eofblocks(mp); diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 26c0626f1f75..48f1fd2bb6ad 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -119,7 +119,7 @@ xfs_fs_eofblocks_from_user( int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino, bool *inuse); -void xfs_icache_disable_reclaim(struct xfs_mount *mp); -void xfs_icache_enable_reclaim(struct xfs_mount *mp); +void xfs_stop_block_reaping(struct xfs_mount *mp); +void xfs_start_block_reaping(struct xfs_mount *mp); #endif diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index f643a9295179..71d216cf6f87 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1116,7 +1116,7 @@ xfs_droplink( /* * Increment the link count on an inode & log the change. */ -static int +static void xfs_bumplink( xfs_trans_t *tp, xfs_inode_t *ip) @@ -1126,7 +1126,6 @@ xfs_bumplink( ASSERT(ip->i_d.di_version > 1); inc_nlink(VFS_I(ip)); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - return 0; } int @@ -1235,9 +1234,7 @@ xfs_create( if (error) goto out_trans_cancel; - error = xfs_bumplink(tp, dp); - if (error) - goto out_trans_cancel; + xfs_bumplink(tp, dp); } /* @@ -1454,9 +1451,7 @@ xfs_link( xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE); - error = xfs_bumplink(tp, sip); - if (error) - goto error_return; + xfs_bumplink(tp, sip); /* * If this is a synchronous mount, make sure that the @@ -3097,9 +3092,7 @@ xfs_cross_rename( error = xfs_droplink(tp, dp2); if (error) goto out_trans_abort; - error = xfs_bumplink(tp, dp1); - if (error) - goto out_trans_abort; + xfs_bumplink(tp, dp1); } /* @@ -3123,9 +3116,7 @@ xfs_cross_rename( error = xfs_droplink(tp, dp1); if (error) goto out_trans_abort; - error = xfs_bumplink(tp, dp2); - if (error) - goto out_trans_abort; + xfs_bumplink(tp, dp2); } /* @@ -3322,9 +3313,7 @@ xfs_rename( XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); if (new_parent && src_is_directory) { - error = xfs_bumplink(tp, target_dp); - if (error) - goto out_trans_cancel; + xfs_bumplink(tp, target_dp); } } else { /* target_ip != NULL */ /* @@ -3443,9 +3432,7 @@ xfs_rename( */ if (wip) { ASSERT(VFS_I(wip)->i_nlink == 0); - error = xfs_bumplink(tp, wip); - if (error) - goto out_trans_cancel; + xfs_bumplink(tp, wip); error = xfs_iunlink_remove(tp, wip); if (error) goto out_trans_cancel; @@ -3614,7 +3601,6 @@ cluster_corrupt_out: * inode buffer and shut down the filesystem. */ rcu_read_unlock(); - xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); /* * We'll always have an inode attached to the buffer for completion @@ -3624,11 +3610,14 @@ cluster_corrupt_out: * xfs_buf_submit(). */ ASSERT(bp->b_iodone); + bp->b_flags |= XBF_ASYNC; bp->b_flags &= ~XBF_DONE; xfs_buf_stale(bp); xfs_buf_ioerror(bp, -EIO); xfs_buf_ioend(bp); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + /* abort the corrupt inode, as it was not attached to the buffer */ xfs_iflush_abort(cip, false); kmem_free(cilist); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index e62074a5257c..558173f95a03 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -45,10 +45,18 @@ typedef struct xfs_inode { mrlock_t i_lock; /* inode lock */ mrlock_t i_mmaplock; /* inode mmap IO lock */ atomic_t i_pincount; /* inode pin count */ + + /* + * Bitsets of inode metadata that have been checked and/or are sick. + * Callers must hold i_flags_lock before accessing this field. + */ + uint16_t i_checked; + uint16_t i_sick; + spinlock_t i_flags_lock; /* inode i_flags lock */ /* Miscellaneous state. */ unsigned long i_flags; /* see defined flags below */ - unsigned int i_delayed_blks; /* count of delay alloc blks */ + uint64_t i_delayed_blks; /* count of delay alloc blks */ struct xfs_icdinode i_d; /* most of ondisk inode */ @@ -57,6 +65,11 @@ typedef struct xfs_inode { /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ + + /* pending io completions */ + spinlock_t i_ioend_lock; + struct work_struct i_ioend_work; + struct list_head i_ioend_list; } xfs_inode_t; /* Convert from vfs inode to xfs inode */ @@ -503,4 +516,6 @@ bool xfs_inode_verify_forks(struct xfs_inode *ip); int xfs_iunlink_init(struct xfs_perag *pag); void xfs_iunlink_destroy(struct xfs_perag *pag); +void xfs_end_io(struct work_struct *work); + #endif /* __XFS_INODE_H__ */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 6ecdbb3af7de..d7dfc13f30f5 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -33,6 +33,8 @@ #include "xfs_fsmap.h" #include "scrub/xfs_scrub.h" #include "xfs_sb.h" +#include "xfs_ag.h" +#include "xfs_health.h" #include <linux/capability.h> #include <linux/cred.h> @@ -779,40 +781,46 @@ xfs_ioc_bulkstat( } STATIC int -xfs_ioc_fsgeometry_v1( - xfs_mount_t *mp, - void __user *arg) +xfs_ioc_fsgeometry( + struct xfs_mount *mp, + void __user *arg, + int struct_version) { - xfs_fsop_geom_t fsgeo; - int error; + struct xfs_fsop_geom fsgeo; + size_t len; - error = xfs_fs_geometry(&mp->m_sb, &fsgeo, 3); - if (error) - return error; + xfs_fs_geometry(&mp->m_sb, &fsgeo, struct_version); - /* - * Caller should have passed an argument of type - * xfs_fsop_geom_v1_t. This is a proper subset of the - * xfs_fsop_geom_t that xfs_fs_geometry() fills in. - */ - if (copy_to_user(arg, &fsgeo, sizeof(xfs_fsop_geom_v1_t))) + if (struct_version <= 3) + len = sizeof(struct xfs_fsop_geom_v1); + else if (struct_version == 4) + len = sizeof(struct xfs_fsop_geom_v4); + else { + xfs_fsop_geom_health(mp, &fsgeo); + len = sizeof(fsgeo); + } + + if (copy_to_user(arg, &fsgeo, len)) return -EFAULT; return 0; } STATIC int -xfs_ioc_fsgeometry( - xfs_mount_t *mp, +xfs_ioc_ag_geometry( + struct xfs_mount *mp, void __user *arg) { - xfs_fsop_geom_t fsgeo; + struct xfs_ag_geometry ageo; int error; - error = xfs_fs_geometry(&mp->m_sb, &fsgeo, 4); + if (copy_from_user(&ageo, arg, sizeof(ageo))) + return -EFAULT; + + error = xfs_ag_get_geometry(mp, ageo.ag_number, &ageo); if (error) return error; - if (copy_to_user(arg, &fsgeo, sizeof(fsgeo))) + if (copy_to_user(arg, &ageo, sizeof(ageo))) return -EFAULT; return 0; } @@ -1142,7 +1150,7 @@ xfs_ioctl_setattr_get_trans( error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); if (error) - return ERR_PTR(error); + goto out_unlock; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags); @@ -1937,10 +1945,14 @@ xfs_file_ioctl( return xfs_ioc_bulkstat(mp, cmd, arg); case XFS_IOC_FSGEOMETRY_V1: - return xfs_ioc_fsgeometry_v1(mp, arg); - + return xfs_ioc_fsgeometry(mp, arg, 3); + case XFS_IOC_FSGEOMETRY_V4: + return xfs_ioc_fsgeometry(mp, arg, 4); case XFS_IOC_FSGEOMETRY: - return xfs_ioc_fsgeometry(mp, arg); + return xfs_ioc_fsgeometry(mp, arg, 5); + + case XFS_IOC_AG_GEOMETRY: + return xfs_ioc_ag_geometry(mp, arg); case XFS_IOC_GETVERSION: return put_user(inode->i_generation, (int __user *)arg); @@ -2031,9 +2043,7 @@ xfs_file_ioctl( case XFS_IOC_FSCOUNTS: { xfs_fsop_counts_t out; - error = xfs_fs_counts(mp, &out); - if (error) - return error; + xfs_fs_counts(mp, &out); if (copy_to_user(arg, &out, sizeof(out))) return -EFAULT; diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index 5001dca361e9..614fc6886d24 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -52,12 +52,9 @@ xfs_compat_ioc_fsgeometry_v1( struct xfs_mount *mp, compat_xfs_fsop_geom_v1_t __user *arg32) { - xfs_fsop_geom_t fsgeo; - int error; + struct xfs_fsop_geom fsgeo; - error = xfs_fs_geometry(&mp->m_sb, &fsgeo, 3); - if (error) - return error; + xfs_fs_geometry(&mp->m_sb, &fsgeo, 3); /* The 32-bit variant simply has some padding at the end */ if (copy_to_user(arg32, &fsgeo, sizeof(struct compat_xfs_fsop_geom_v1))) return -EFAULT; @@ -561,7 +558,9 @@ xfs_file_compat_ioctl( switch (cmd) { /* No size or alignment issues on any arch */ case XFS_IOC_DIOINFO: + case XFS_IOC_FSGEOMETRY_V4: case XFS_IOC_FSGEOMETRY: + case XFS_IOC_AG_GEOMETRY: case XFS_IOC_FSGETXATTR: case XFS_IOC_FSSETXATTR: case XFS_IOC_FSGETXATTRA: diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 942e4aa5e729..1e1a0af1dd34 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -18,6 +18,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_icache.h" +#include "xfs_health.h" /* * Return stat information for one inode. @@ -84,6 +85,7 @@ xfs_bulkstat_one_int( buf->bs_extsize = dic->di_extsize << mp->m_sb.sb_blocklog; buf->bs_extents = dic->di_nextents; memset(buf->bs_pad, 0, sizeof(buf->bs_pad)); + xfs_bulkstat_health(ip, buf); buf->bs_dmevmask = dic->di_dmevmask; buf->bs_dmstate = dic->di_dmstate; buf->bs_aextents = dic->di_anextents; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index c3b610b687d1..457ced3ee3e1 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -23,6 +23,7 @@ #include "xfs_cksum.h" #include "xfs_sysfs.h" #include "xfs_sb.h" +#include "xfs_health.h" kmem_zone_t *xfs_log_ticket_zone; @@ -861,7 +862,7 @@ xfs_log_write_unmount_record( * recalculated during log recovery at next mount. Refer to * xlog_check_unmount_rec for more details. */ - if (XFS_TEST_ERROR((mp->m_flags & XFS_MOUNT_BAD_SUMMARY), mp, + if (XFS_TEST_ERROR(xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS), mp, XFS_ERRTAG_FORCE_SUMMARY_RECALC)) { xfs_alert(mp, "%s: will fix summary counters at next mount", __func__); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index d3884e08b43c..5e595948bc5a 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -582,6 +582,19 @@ xlog_cil_committed( struct xfs_cil_ctx *ctx = args; struct xfs_mount *mp = ctx->cil->xc_log->l_mp; + /* + * If the I/O failed, we're aborting the commit and already shutdown. + * Wake any commit waiters before aborting the log items so we don't + * block async log pushers on callbacks. Async log pushers explicitly do + * not wait on log force completion because they may be holding locks + * required to unpin items. + */ + if (abort) { + spin_lock(&ctx->cil->xc_push_lock); + wake_up_all(&ctx->cil->xc_commit_wait); + spin_unlock(&ctx->cil->xc_push_lock); + } + xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, ctx->lv_chain, ctx->start_lsn, abort); @@ -589,15 +602,7 @@ xlog_cil_committed( xfs_extent_busy_clear(mp, &ctx->busy_extents, (mp->m_flags & XFS_MOUNT_DISCARD) && !abort); - /* - * If we are aborting the commit, wake up anyone waiting on the - * committing list. If we don't, then a shutdown we can leave processes - * waiting in xlog_cil_force_lsn() waiting on a sequence commit that - * will never happen because we aborted it. - */ spin_lock(&ctx->cil->xc_push_lock); - if (abort) - wake_up_all(&ctx->cil->xc_commit_wait); list_del(&ctx->committing); spin_unlock(&ctx->cil->xc_push_lock); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 3371d1ff27c4..9329f5adbfbe 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -5167,7 +5167,7 @@ xlog_recover_process_iunlinks( } } -STATIC int +STATIC void xlog_unpack_data( struct xlog_rec_header *rhead, char *dp, @@ -5190,8 +5190,6 @@ xlog_unpack_data( dp += BBSIZE; } } - - return 0; } /* @@ -5206,11 +5204,9 @@ xlog_recover_process( int pass, struct list_head *buffer_list) { - int error; __le32 old_crc = rhead->h_crc; __le32 crc; - crc = xlog_cksum(log, rhead, dp, be32_to_cpu(rhead->h_len)); /* @@ -5249,9 +5245,7 @@ xlog_recover_process( return -EFSCORRUPTED; } - error = xlog_unpack_data(rhead, dp, log); - if (error) - return error; + xlog_unpack_data(rhead, dp, log); return xlog_recover_process_data(log, rhash, rhead, dp, pass, buffer_list); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index fd63b0b1307c..6b2bfe81dc51 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -34,6 +34,7 @@ #include "xfs_refcount_btree.h" #include "xfs_reflink.h" #include "xfs_extent_busy.h" +#include "xfs_health.h" static DEFINE_MUTEX(xfs_uuid_table_mutex); @@ -231,6 +232,7 @@ xfs_initialize_perag( error = xfs_iunlink_init(pag); if (error) goto out_hash_destroy; + spin_lock_init(&pag->pag_state_lock); } index = xfs_set_inode_alloc(mp, agcount); @@ -644,7 +646,7 @@ xfs_check_summary_counts( (mp->m_sb.sb_fdblocks > mp->m_sb.sb_dblocks || !xfs_verify_icount(mp, mp->m_sb.sb_icount) || mp->m_sb.sb_ifree > mp->m_sb.sb_icount)) - mp->m_flags |= XFS_MOUNT_BAD_SUMMARY; + xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS); /* * We can safely re-initialise incore superblock counters from the @@ -659,7 +661,7 @@ xfs_check_summary_counts( */ if ((!xfs_sb_version_haslazysbcount(&mp->m_sb) || XFS_LAST_UNMOUNT_WAS_CLEAN(mp)) && - !(mp->m_flags & XFS_MOUNT_BAD_SUMMARY)) + !xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS)) return 0; return xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount); @@ -1068,6 +1070,7 @@ xfs_mountfs( */ cancel_delayed_work_sync(&mp->m_reclaim_work); xfs_reclaim_inodes(mp, SYNC_WAIT); + xfs_health_unmount(mp); out_log_dealloc: mp->m_flags |= XFS_MOUNT_UNMOUNTING; xfs_log_mount_cancel(mp); @@ -1104,7 +1107,7 @@ xfs_unmountfs( uint64_t resblks; int error; - xfs_icache_disable_reclaim(mp); + xfs_stop_block_reaping(mp); xfs_fs_unreserve_ag_blocks(mp); xfs_qm_unmount_quotas(mp); xfs_rtunmount_inodes(mp); @@ -1150,6 +1153,7 @@ xfs_unmountfs( */ cancel_delayed_work_sync(&mp->m_reclaim_work); xfs_reclaim_inodes(mp, SYNC_WAIT); + xfs_health_unmount(mp); xfs_qm_unmount(mp); @@ -1445,7 +1449,26 @@ xfs_force_summary_recalc( if (!xfs_sb_version_haslazysbcount(&mp->m_sb)) return; - spin_lock(&mp->m_sb_lock); - mp->m_flags |= XFS_MOUNT_BAD_SUMMARY; - spin_unlock(&mp->m_sb_lock); + xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS); +} + +/* + * Update the in-core delayed block counter. + * + * We prefer to update the counter without having to take a spinlock for every + * counter update (i.e. batching). Each change to delayed allocation + * reservations can change can easily exceed the default percpu counter + * batching, so we use a larger batch factor here. + * + * Note that we don't currently have any callers requiring fast summation + * (e.g. percpu_counter_read) so we can use a big batch value here. + */ +#define XFS_DELALLOC_BATCH (4096) +void +xfs_mod_delalloc( + struct xfs_mount *mp, + int64_t delta) +{ + percpu_counter_add_batch(&mp->m_delalloc_blks, delta, + XFS_DELALLOC_BATCH); } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 110f927cf943..c81a5cd7c228 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -60,6 +60,20 @@ struct xfs_error_cfg { typedef struct xfs_mount { struct super_block *m_super; xfs_tid_t m_tid; /* next unused tid for fs */ + + /* + * Bitsets of per-fs metadata that have been checked and/or are sick. + * Callers must hold m_sb_lock to access these two fields. + */ + uint8_t m_fs_checked; + uint8_t m_fs_sick; + /* + * Bitsets of rt metadata that have been checked and/or are sick. + * Callers must hold m_sb_lock to access this field. + */ + uint8_t m_rt_checked; + uint8_t m_rt_sick; + struct xfs_ail *m_ail; /* fs active log item list */ struct xfs_sb m_sb; /* copy of fs superblock */ @@ -67,6 +81,12 @@ typedef struct xfs_mount { struct percpu_counter m_icount; /* allocated inodes counter */ struct percpu_counter m_ifree; /* free inodes counter */ struct percpu_counter m_fdblocks; /* free block counter */ + /* + * Count of data device blocks reserved for delayed allocations, + * including indlen blocks. Does not include allocated CoW staging + * extents or anything related to the rt device. + */ + struct percpu_counter m_delalloc_blks; struct xfs_buf *m_sb_bp; /* buffer for superblock */ char *m_fsname; /* filesystem name */ @@ -175,7 +195,6 @@ typedef struct xfs_mount { struct xstats m_stats; /* per-fs stats */ struct workqueue_struct *m_buf_workqueue; - struct workqueue_struct *m_data_workqueue; struct workqueue_struct *m_unwritten_workqueue; struct workqueue_struct *m_cil_workqueue; struct workqueue_struct *m_reclaim_workqueue; @@ -214,7 +233,6 @@ typedef struct xfs_mount { must be synchronous except for space allocations */ #define XFS_MOUNT_UNMOUNTING (1ULL << 1) /* filesystem is unmounting */ -#define XFS_MOUNT_BAD_SUMMARY (1ULL << 2) /* summary counters are bad */ #define XFS_MOUNT_WAS_CLEAN (1ULL << 3) #define XFS_MOUNT_FS_SHUTDOWN (1ULL << 4) /* atomic stop of all filesystem operations, typically for @@ -369,6 +387,15 @@ typedef struct xfs_perag { xfs_agino_t pagl_pagino; xfs_agino_t pagl_leftrec; xfs_agino_t pagl_rightrec; + + /* + * Bitsets of per-ag metadata that have been checked and/or are sick. + * Callers should hold pag_state_lock before accessing this field. + */ + uint16_t pag_checked; + uint16_t pag_sick; + spinlock_t pag_state_lock; + spinlock_t pagb_lock; /* lock for pagb_tree */ struct rb_root pagb_tree; /* ordered tree of busy extents */ unsigned int pagb_gen; /* generation count for pagb_tree */ @@ -454,5 +481,6 @@ int xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb, struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp, int error_class, int error); void xfs_force_summary_recalc(struct xfs_mount *mp); +void xfs_mod_delalloc(struct xfs_mount *mp, int64_t delta); #endif /* __XFS_MOUNT_H__ */ diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 52ed7904df10..aa6b6db3db0e 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1812,7 +1812,8 @@ xfs_qm_vop_chown_reserve( uint flags) { struct xfs_mount *mp = ip->i_mount; - uint delblks, blkflags, prjflags = 0; + uint64_t delblks; + unsigned int blkflags, prjflags = 0; struct xfs_dquot *udq_unres = NULL; struct xfs_dquot *gdq_unres = NULL; struct xfs_dquot *pdq_unres = NULL; diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 3ccf0fbc9071..b41b75089548 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -113,12 +113,8 @@ xfs_quota_inode(xfs_mount_t *mp, uint dq_flags) return NULL; } -extern void xfs_trans_mod_dquot(struct xfs_trans *, - struct xfs_dquot *, uint, long); -extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, - struct xfs_mount *, struct xfs_dquot *, - struct xfs_dquot *, struct xfs_dquot *, - long, long, uint); +extern void xfs_trans_mod_dquot(struct xfs_trans *tp, struct xfs_dquot *dqp, + uint field, int64_t delta); extern void xfs_trans_dqjoin(struct xfs_trans *, struct xfs_dquot *); extern void xfs_trans_log_dquot(struct xfs_trans *, struct xfs_dquot *); diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index 55b798265ef7..efe42ae7a2f3 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -56,32 +56,35 @@ xfs_quota_chkd_flag( * The structure kept inside the xfs_trans_t keep track of dquot changes * within a transaction and apply them later. */ -typedef struct xfs_dqtrx { +struct xfs_dqtrx { struct xfs_dquot *qt_dquot; /* the dquot this refers to */ - ulong qt_blk_res; /* blks reserved on a dquot */ - ulong qt_ino_res; /* inode reserved on a dquot */ - ulong qt_ino_res_used; /* inodes used from the reservation */ - long qt_bcount_delta; /* dquot blk count changes */ - long qt_delbcnt_delta; /* delayed dquot blk count changes */ - long qt_icount_delta; /* dquot inode count changes */ - ulong qt_rtblk_res; /* # blks reserved on a dquot */ - ulong qt_rtblk_res_used;/* # blks used from reservation */ - long qt_rtbcount_delta;/* dquot realtime blk changes */ - long qt_delrtb_delta; /* delayed RT blk count changes */ -} xfs_dqtrx_t; + + uint64_t qt_blk_res; /* blks reserved on a dquot */ + int64_t qt_bcount_delta; /* dquot blk count changes */ + int64_t qt_delbcnt_delta; /* delayed dquot blk count changes */ + + uint64_t qt_rtblk_res; /* # blks reserved on a dquot */ + uint64_t qt_rtblk_res_used;/* # blks used from reservation */ + int64_t qt_rtbcount_delta;/* dquot realtime blk changes */ + int64_t qt_delrtb_delta; /* delayed RT blk count changes */ + + uint64_t qt_ino_res; /* inode reserved on a dquot */ + uint64_t qt_ino_res_used; /* inodes used from the reservation */ + int64_t qt_icount_delta; /* dquot inode count changes */ +}; #ifdef CONFIG_XFS_QUOTA extern void xfs_trans_dup_dqinfo(struct xfs_trans *, struct xfs_trans *); extern void xfs_trans_free_dqinfo(struct xfs_trans *); extern void xfs_trans_mod_dquot_byino(struct xfs_trans *, struct xfs_inode *, - uint, long); + uint, int64_t); extern void xfs_trans_apply_dquot_deltas(struct xfs_trans *); extern void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *); extern int xfs_trans_reserve_quota_nblks(struct xfs_trans *, - struct xfs_inode *, long, long, uint); + struct xfs_inode *, int64_t, long, uint); extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, struct xfs_mount *, struct xfs_dquot *, - struct xfs_dquot *, struct xfs_dquot *, long, long, uint); + struct xfs_dquot *, struct xfs_dquot *, int64_t, long, uint); extern int xfs_qm_vop_dqalloc(struct xfs_inode *, xfs_dqid_t, xfs_dqid_t, prid_t, uint, struct xfs_dquot **, struct xfs_dquot **, @@ -121,14 +124,14 @@ xfs_qm_vop_dqalloc(struct xfs_inode *ip, xfs_dqid_t uid, xfs_dqid_t gid, #define xfs_trans_apply_dquot_deltas(tp) #define xfs_trans_unreserve_and_mod_dquots(tp) static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, - struct xfs_inode *ip, long nblks, long ninos, uint flags) + struct xfs_inode *ip, int64_t nblks, long ninos, uint flags) { return 0; } static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp, struct xfs_mount *mp, struct xfs_dquot *udqp, struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, - long nblks, long nions, uint flags) + int64_t nblks, long nions, uint flags) { return 0; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f093ea244849..a14d11d78bd8 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -66,7 +66,7 @@ static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ enum { Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize, Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid, - Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups, + Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups, Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep, Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, @@ -87,7 +87,6 @@ static const match_table_t tokens = { {Opt_sunit, "sunit=%u"}, /* data volume stripe unit */ {Opt_swidth, "swidth=%u"}, /* data volume stripe width */ {Opt_nouuid, "nouuid"}, /* ignore filesystem UUID */ - {Opt_mtpt, "mtpt"}, /* filesystem mount point */ {Opt_grpid, "grpid"}, /* group-ID from parent directory */ {Opt_nogrpid, "nogrpid"}, /* group-ID from current process */ {Opt_bsdgroups, "bsdgroups"}, /* group-ID from parent directory */ @@ -236,9 +235,6 @@ xfs_parseargs( if (!mp->m_logname) return -ENOMEM; break; - case Opt_mtpt: - xfs_warn(mp, "%s option not allowed on this system", p); - return -EINVAL; case Opt_rtdev: kfree(mp->m_rtname); mp->m_rtname = match_strdup(args); @@ -448,7 +444,7 @@ struct proc_xfs_info { char *str; }; -STATIC int +STATIC void xfs_showargs( struct xfs_mount *mp, struct seq_file *m) @@ -527,9 +523,8 @@ xfs_showargs( if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT)) seq_puts(m, ",noquota"); - - return 0; } + static uint64_t xfs_max_file_offset( unsigned int blockshift) @@ -539,26 +534,18 @@ xfs_max_file_offset( /* Figure out maximum filesize, on Linux this can depend on * the filesystem blocksize (on 32 bit platforms). - * __block_write_begin does this in an [unsigned] long... + * __block_write_begin does this in an [unsigned] long long... * page->index << (PAGE_SHIFT - bbits) * So, for page sized blocks (4K on 32 bit platforms), * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is * (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1) * but for smaller blocksizes it is less (bbits = log2 bsize). - * Note1: get_block_t takes a long (implicit cast from above) - * Note2: The Large Block Device (LBD and HAVE_SECTOR_T) patch - * can optionally convert the [unsigned] long from above into - * an [unsigned] long long. */ #if BITS_PER_LONG == 32 -# if defined(CONFIG_LBDAF) ASSERT(sizeof(sector_t) == 8); pagefactor = PAGE_SIZE; bitshift = BITS_PER_LONG; -# else - pagefactor = PAGE_SIZE >> (PAGE_SHIFT - blockshift); -# endif #endif return (((uint64_t)pagefactor) << bitshift) - 1; @@ -838,15 +825,10 @@ xfs_init_mount_workqueues( if (!mp->m_buf_workqueue) goto out; - mp->m_data_workqueue = alloc_workqueue("xfs-data/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname); - if (!mp->m_data_workqueue) - goto out_destroy_buf; - mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s", WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname); if (!mp->m_unwritten_workqueue) - goto out_destroy_data_iodone_queue; + goto out_destroy_buf; mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s", WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname); @@ -886,8 +868,6 @@ out_destroy_cil: destroy_workqueue(mp->m_cil_workqueue); out_destroy_unwritten: destroy_workqueue(mp->m_unwritten_workqueue); -out_destroy_data_iodone_queue: - destroy_workqueue(mp->m_data_workqueue); out_destroy_buf: destroy_workqueue(mp->m_buf_workqueue); out: @@ -903,7 +883,6 @@ xfs_destroy_mount_workqueues( destroy_workqueue(mp->m_log_workqueue); destroy_workqueue(mp->m_reclaim_workqueue); destroy_workqueue(mp->m_cil_workqueue); - destroy_workqueue(mp->m_data_workqueue); destroy_workqueue(mp->m_unwritten_workqueue); destroy_workqueue(mp->m_buf_workqueue); } @@ -1376,7 +1355,7 @@ xfs_fs_remount( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } - xfs_icache_enable_reclaim(mp); + xfs_start_block_reaping(mp); /* Create the per-AG metadata reservation pool .*/ error = xfs_fs_reserve_ag_blocks(mp); @@ -1390,7 +1369,7 @@ xfs_fs_remount( * Cancel background eofb scanning so it cannot race with the * final log force+buftarg wait and deadlock the remount. */ - xfs_icache_disable_reclaim(mp); + xfs_stop_block_reaping(mp); /* Get rid of any leftover CoW reservations... */ error = xfs_icache_free_cowblocks(mp, NULL); @@ -1434,7 +1413,7 @@ xfs_fs_freeze( { struct xfs_mount *mp = XFS_M(sb); - xfs_icache_disable_reclaim(mp); + xfs_stop_block_reaping(mp); xfs_save_resvblks(mp); xfs_quiesce_attr(mp); return xfs_sync_sb(mp, true); @@ -1448,7 +1427,7 @@ xfs_fs_unfreeze( xfs_restore_resvblks(mp); xfs_log_work_queue(mp); - xfs_icache_enable_reclaim(mp); + xfs_start_block_reaping(mp); return 0; } @@ -1457,7 +1436,8 @@ xfs_fs_show_options( struct seq_file *m, struct dentry *root) { - return xfs_showargs(XFS_M(root->d_sb), m); + xfs_showargs(XFS_M(root->d_sb), m); + return 0; } /* @@ -1546,8 +1526,14 @@ xfs_init_percpu_counters( if (error) goto free_ifree; + error = percpu_counter_init(&mp->m_delalloc_blks, 0, GFP_KERNEL); + if (error) + goto free_fdblocks; + return 0; +free_fdblocks: + percpu_counter_destroy(&mp->m_fdblocks); free_ifree: percpu_counter_destroy(&mp->m_ifree); free_icount: @@ -1571,6 +1557,9 @@ xfs_destroy_percpu_counters( percpu_counter_destroy(&mp->m_icount); percpu_counter_destroy(&mp->m_ifree); percpu_counter_destroy(&mp->m_fdblocks); + ASSERT(XFS_FORCED_SHUTDOWN(mp) || + percpu_counter_sum(&mp->m_delalloc_blks) == 0); + percpu_counter_destroy(&mp->m_delalloc_blks); } static struct xfs_mount * diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 47fb07d86efd..2464ea351f83 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3440,6 +3440,82 @@ DEFINE_AGINODE_EVENT(xfs_iunlink); DEFINE_AGINODE_EVENT(xfs_iunlink_remove); DEFINE_AG_EVENT(xfs_iunlink_map_prev_fallback); +DECLARE_EVENT_CLASS(xfs_fs_corrupt_class, + TP_PROTO(struct xfs_mount *mp, unsigned int flags), + TP_ARGS(mp, flags), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, flags) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->flags = flags; + ), + TP_printk("dev %d:%d flags 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->flags) +); +#define DEFINE_FS_CORRUPT_EVENT(name) \ +DEFINE_EVENT(xfs_fs_corrupt_class, name, \ + TP_PROTO(struct xfs_mount *mp, unsigned int flags), \ + TP_ARGS(mp, flags)) +DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_sick); +DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_healthy); +DEFINE_FS_CORRUPT_EVENT(xfs_fs_unfixed_corruption); +DEFINE_FS_CORRUPT_EVENT(xfs_rt_mark_sick); +DEFINE_FS_CORRUPT_EVENT(xfs_rt_mark_healthy); +DEFINE_FS_CORRUPT_EVENT(xfs_rt_unfixed_corruption); + +DECLARE_EVENT_CLASS(xfs_ag_corrupt_class, + TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int flags), + TP_ARGS(mp, agno, flags), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(unsigned int, flags) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->agno = agno; + __entry->flags = flags; + ), + TP_printk("dev %d:%d agno %u flags 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->agno, __entry->flags) +); +#define DEFINE_AG_CORRUPT_EVENT(name) \ +DEFINE_EVENT(xfs_ag_corrupt_class, name, \ + TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \ + unsigned int flags), \ + TP_ARGS(mp, agno, flags)) +DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_sick); +DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_healthy); +DEFINE_AG_CORRUPT_EVENT(xfs_ag_unfixed_corruption); + +DECLARE_EVENT_CLASS(xfs_inode_corrupt_class, + TP_PROTO(struct xfs_inode *ip, unsigned int flags), + TP_ARGS(ip, flags), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_ino_t, ino) + __field(unsigned int, flags) + ), + TP_fast_assign( + __entry->dev = ip->i_mount->m_super->s_dev; + __entry->ino = ip->i_ino; + __entry->flags = flags; + ), + TP_printk("dev %d:%d ino 0x%llx flags 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, __entry->flags) +); +#define DEFINE_INODE_CORRUPT_EVENT(name) \ +DEFINE_EVENT(xfs_inode_corrupt_class, name, \ + TP_PROTO(struct xfs_inode *ip, unsigned int flags), \ + TP_ARGS(ip, flags)) +DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_sick); +DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_healthy); + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index c23257a26c2b..cd664a03613f 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -74,13 +74,13 @@ xfs_trans_log_dquot( */ void xfs_trans_dup_dqinfo( - xfs_trans_t *otp, - xfs_trans_t *ntp) + struct xfs_trans *otp, + struct xfs_trans *ntp) { - xfs_dqtrx_t *oq, *nq; - int i, j; - xfs_dqtrx_t *oqa, *nqa; - ulong blk_res_used; + struct xfs_dqtrx *oq, *nq; + int i, j; + struct xfs_dqtrx *oqa, *nqa; + uint64_t blk_res_used; if (!otp->t_dqinfo) return; @@ -137,7 +137,7 @@ xfs_trans_mod_dquot_byino( xfs_trans_t *tp, xfs_inode_t *ip, uint field, - long delta) + int64_t delta) { xfs_mount_t *mp = tp->t_mountp; @@ -191,12 +191,12 @@ xfs_trans_get_dqtrx( */ void xfs_trans_mod_dquot( - xfs_trans_t *tp, - xfs_dquot_t *dqp, - uint field, - long delta) + struct xfs_trans *tp, + struct xfs_dquot *dqp, + uint field, + int64_t delta) { - xfs_dqtrx_t *qtrx; + struct xfs_dqtrx *qtrx; ASSERT(tp); ASSERT(XFS_IS_QUOTA_RUNNING(tp->t_mountp)); @@ -219,14 +219,14 @@ xfs_trans_mod_dquot( * regular disk blk reservation */ case XFS_TRANS_DQ_RES_BLKS: - qtrx->qt_blk_res += (ulong)delta; + qtrx->qt_blk_res += delta; break; /* * inode reservation */ case XFS_TRANS_DQ_RES_INOS: - qtrx->qt_ino_res += (ulong)delta; + qtrx->qt_ino_res += delta; break; /* @@ -245,7 +245,7 @@ xfs_trans_mod_dquot( */ case XFS_TRANS_DQ_ICOUNT: if (qtrx->qt_ino_res && delta > 0) { - qtrx->qt_ino_res_used += (ulong)delta; + qtrx->qt_ino_res_used += delta; ASSERT(qtrx->qt_ino_res >= qtrx->qt_ino_res_used); } qtrx->qt_icount_delta += delta; @@ -255,7 +255,7 @@ xfs_trans_mod_dquot( * rtblk reservation */ case XFS_TRANS_DQ_RES_RTBLKS: - qtrx->qt_rtblk_res += (ulong)delta; + qtrx->qt_rtblk_res += delta; break; /* @@ -263,7 +263,7 @@ xfs_trans_mod_dquot( */ case XFS_TRANS_DQ_RTBCOUNT: if (qtrx->qt_rtblk_res && delta > 0) { - qtrx->qt_rtblk_res_used += (ulong)delta; + qtrx->qt_rtblk_res_used += delta; ASSERT(qtrx->qt_rtblk_res >= qtrx->qt_rtblk_res_used); } qtrx->qt_rtbcount_delta += delta; @@ -288,8 +288,8 @@ xfs_trans_mod_dquot( */ STATIC void xfs_trans_dqlockedjoin( - xfs_trans_t *tp, - xfs_dqtrx_t *q) + struct xfs_trans *tp, + struct xfs_dqtrx *q) { ASSERT(q[0].qt_dquot != NULL); if (q[1].qt_dquot == NULL) { @@ -320,8 +320,8 @@ xfs_trans_apply_dquot_deltas( struct xfs_dquot *dqp; struct xfs_dqtrx *qtrx, *qa; struct xfs_disk_dquot *d; - long totalbdelta; - long totalrtbdelta; + int64_t totalbdelta; + int64_t totalrtbdelta; if (!(tp->t_flags & XFS_TRANS_DQ_DIRTY)) return; @@ -413,7 +413,7 @@ xfs_trans_apply_dquot_deltas( * reservation that a transaction structure knows of. */ if (qtrx->qt_blk_res != 0) { - ulong blk_res_used = 0; + uint64_t blk_res_used = 0; if (qtrx->qt_bcount_delta > 0) blk_res_used = qtrx->qt_bcount_delta; @@ -501,7 +501,7 @@ xfs_trans_unreserve_and_mod_dquots( { int i, j; xfs_dquot_t *dqp; - xfs_dqtrx_t *qtrx, *qa; + struct xfs_dqtrx *qtrx, *qa; bool locked; if (!tp->t_dqinfo || !(tp->t_flags & XFS_TRANS_DQ_DIRTY)) @@ -585,7 +585,7 @@ xfs_trans_dqresv( xfs_trans_t *tp, xfs_mount_t *mp, xfs_dquot_t *dqp, - long nblks, + int64_t nblks, long ninos, uint flags) { @@ -745,7 +745,7 @@ xfs_trans_reserve_quota_bydquots( struct xfs_dquot *udqp, struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, - long nblks, + int64_t nblks, long ninos, uint flags) { @@ -804,7 +804,7 @@ int xfs_trans_reserve_quota_nblks( struct xfs_trans *tp, struct xfs_inode *ip, - long nblks, + int64_t nblks, long ninos, uint flags) { |