diff options
Diffstat (limited to 'fs')
273 files changed, 5655 insertions, 4094 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index eed551d8555f..633da5e37299 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -6,6 +6,7 @@ #include <linux/module.h> #include <linux/fs.h> +#include <linux/fs_struct.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <linux/slab.h> diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index eb0b083da269..612a230bc012 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -483,24 +483,15 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf) static void v9fs_mmap_vm_close(struct vm_area_struct *vma) { - struct inode *inode; - - struct writeback_control wbc = { - .nr_to_write = LONG_MAX, - .sync_mode = WB_SYNC_ALL, - .range_start = (loff_t)vma->vm_pgoff * PAGE_SIZE, - /* absolute end, byte at end included */ - .range_end = (loff_t)vma->vm_pgoff * PAGE_SIZE + - (vma->vm_end - vma->vm_start - 1), - }; - if (!(vma->vm_flags & VM_SHARED)) return; p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma); - inode = file_inode(vma->vm_file); - filemap_fdatawrite_wbc(inode->i_mapping, &wbc); + filemap_fdatawrite_range(file_inode(vma->vm_file)->i_mapping, + (loff_t)vma->vm_pgoff * PAGE_SIZE, + (loff_t)vma->vm_pgoff * PAGE_SIZE + + (vma->vm_end - vma->vm_start - 1)); } static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index d0c77ec31b1d..8666c9c62258 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -422,7 +422,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode, st); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; /* * initialize the inode with the stat info diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index be297e335468..1661a25f2772 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -112,7 +112,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode_dotl, st); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; /* * initialize the inode with the stat info diff --git a/fs/Makefile b/fs/Makefile index e3523ab2e587..a04274a3c854 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -14,7 +14,7 @@ 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 fsopen.o init.o \ + fs_dirent.o fs_context.o fs_parser.o fsopen.o init.o \ kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o \ file_attr.o diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 0210df8d3500..0bfc7d151dcd 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -29,7 +29,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; pr_debug("affs_iget(%lu)\n", inode->i_ino); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index f31359922e98..71c10a05cebe 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -140,7 +140,9 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, return ERR_PTR(-ENOMEM); } - cell->name = kmalloc(1 + namelen + 1, GFP_KERNEL); + /* Allocate the cell name and the key name in one go. */ + cell->name = kmalloc(1 + namelen + 1 + + 4 + namelen + 1, GFP_KERNEL); if (!cell->name) { kfree(cell); return ERR_PTR(-ENOMEM); @@ -151,7 +153,11 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, cell->name_len = namelen; for (i = 0; i < namelen; i++) cell->name[i] = tolower(name[i]); - cell->name[i] = 0; + cell->name[i++] = 0; + + cell->key_desc = cell->name + i; + memcpy(cell->key_desc, "afs@", 4); + memcpy(cell->key_desc + 4, cell->name, cell->name_len + 1); cell->net = net; refcount_set(&cell->ref, 1); @@ -229,7 +235,7 @@ error: * @name: The name of the cell. * @namesz: The strlen of the cell name. * @vllist: A colon/comma separated list of numeric IP addresses or NULL. - * @excl: T if an error should be given if the cell name already exists. + * @reason: The reason we're doing the lookup * @trace: The reason to be logged if the lookup is successful. * * Look up a cell record by name and query the DNS for VL server addresses if @@ -239,7 +245,8 @@ error: */ struct afs_cell *afs_lookup_cell(struct afs_net *net, const char *name, unsigned int namesz, - const char *vllist, bool excl, + const char *vllist, + enum afs_lookup_cell_for reason, enum afs_cell_trace trace) { struct afs_cell *cell, *candidate, *cursor; @@ -247,12 +254,18 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, enum afs_cell_state state; int ret, n; - _enter("%s,%s", name, vllist); + _enter("%s,%s,%u", name, vllist, reason); - if (!excl) { + if (reason != AFS_LOOKUP_CELL_PRELOAD) { cell = afs_find_cell(net, name, namesz, trace); - if (!IS_ERR(cell)) + if (!IS_ERR(cell)) { + if (reason == AFS_LOOKUP_CELL_DYNROOT) + goto no_wait; + if (cell->state == AFS_CELL_SETTING_UP || + cell->state == AFS_CELL_UNLOOKED) + goto lookup_cell; goto wait_for_cell; + } } /* Assume we're probably going to create a cell and preallocate and @@ -298,26 +311,69 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, rb_insert_color(&cell->net_node, &net->cells); up_write(&net->cells_lock); - afs_queue_cell(cell, afs_cell_trace_queue_new); +lookup_cell: + if (reason != AFS_LOOKUP_CELL_PRELOAD && + reason != AFS_LOOKUP_CELL_ROOTCELL) { + set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags); + afs_queue_cell(cell, afs_cell_trace_queue_new); + } wait_for_cell: - _debug("wait_for_cell"); state = smp_load_acquire(&cell->state); /* vs error */ - if (state != AFS_CELL_ACTIVE && - state != AFS_CELL_DEAD) { + switch (state) { + case AFS_CELL_ACTIVE: + case AFS_CELL_DEAD: + break; + case AFS_CELL_UNLOOKED: + default: + if (reason == AFS_LOOKUP_CELL_PRELOAD || + reason == AFS_LOOKUP_CELL_ROOTCELL) + break; + _debug("wait_for_cell"); afs_see_cell(cell, afs_cell_trace_wait); wait_var_event(&cell->state, ({ state = smp_load_acquire(&cell->state); /* vs error */ state == AFS_CELL_ACTIVE || state == AFS_CELL_DEAD; })); + _debug("waited_for_cell %d %d", cell->state, cell->error); } +no_wait: /* Check the state obtained from the wait check. */ + state = smp_load_acquire(&cell->state); /* vs error */ if (state == AFS_CELL_DEAD) { ret = cell->error; goto error; } + if (state == AFS_CELL_ACTIVE) { + switch (cell->dns_status) { + case DNS_LOOKUP_NOT_DONE: + if (cell->dns_source == DNS_RECORD_FROM_CONFIG) { + ret = 0; + break; + } + fallthrough; + default: + ret = -EIO; + goto error; + case DNS_LOOKUP_GOOD: + case DNS_LOOKUP_GOOD_WITH_BAD: + ret = 0; + break; + case DNS_LOOKUP_GOT_NOT_FOUND: + ret = -ENOENT; + goto error; + case DNS_LOOKUP_BAD: + ret = -EREMOTEIO; + goto error; + case DNS_LOOKUP_GOT_LOCAL_FAILURE: + case DNS_LOOKUP_GOT_TEMP_FAILURE: + case DNS_LOOKUP_GOT_NS_FAILURE: + ret = -EDESTADDRREQ; + goto error; + } + } _leave(" = %p [cell]", cell); return cell; @@ -325,7 +381,7 @@ wait_for_cell: cell_already_exists: _debug("cell exists"); cell = cursor; - if (excl) { + if (reason == AFS_LOOKUP_CELL_PRELOAD) { ret = -EEXIST; } else { afs_use_cell(cursor, trace); @@ -384,7 +440,8 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) return -EINVAL; /* allocate a cell record for the root/workstation cell */ - new_root = afs_lookup_cell(net, rootcell, len, vllist, false, + new_root = afs_lookup_cell(net, rootcell, len, vllist, + AFS_LOOKUP_CELL_ROOTCELL, afs_cell_trace_use_lookup_ws); if (IS_ERR(new_root)) { _leave(" = %ld", PTR_ERR(new_root)); @@ -660,33 +717,6 @@ void afs_set_cell_timer(struct afs_cell *cell, unsigned int delay_secs) } /* - * Allocate a key to use as a placeholder for anonymous user security. - */ -static int afs_alloc_anon_key(struct afs_cell *cell) -{ - struct key *key; - char keyname[4 + AFS_MAXCELLNAME + 1], *cp, *dp; - - /* Create a key to represent an anonymous user. */ - memcpy(keyname, "afs@", 4); - dp = keyname + 4; - cp = cell->name; - do { - *dp++ = tolower(*cp); - } while (*cp++); - - key = rxrpc_get_null_key(keyname); - if (IS_ERR(key)) - return PTR_ERR(key); - - cell->anonymous_key = key; - - _debug("anon key %p{%x}", - cell->anonymous_key, key_serial(cell->anonymous_key)); - return 0; -} - -/* * Activate a cell. */ static int afs_activate_cell(struct afs_net *net, struct afs_cell *cell) @@ -695,12 +725,6 @@ static int afs_activate_cell(struct afs_net *net, struct afs_cell *cell) struct afs_cell *pcell; int ret; - if (!cell->anonymous_key) { - ret = afs_alloc_anon_key(cell); - if (ret < 0) - return ret; - } - ret = afs_proc_cell_setup(cell); if (ret < 0) return ret; @@ -777,6 +801,7 @@ static bool afs_manage_cell(struct afs_cell *cell) switch (cell->state) { case AFS_CELL_SETTING_UP: goto set_up_cell; + case AFS_CELL_UNLOOKED: case AFS_CELL_ACTIVE: goto cell_is_active; case AFS_CELL_REMOVING: @@ -797,7 +822,7 @@ set_up_cell: goto remove_cell; } - afs_set_cell_state(cell, AFS_CELL_ACTIVE); + afs_set_cell_state(cell, AFS_CELL_UNLOOKED); cell_is_active: if (afs_has_cell_expired(cell, &next_manage)) @@ -807,6 +832,8 @@ cell_is_active: ret = afs_update_cell(cell); if (ret < 0) cell->error = ret; + if (cell->state == AFS_CELL_UNLOOKED) + afs_set_cell_state(cell, AFS_CELL_ACTIVE); } if (next_manage < TIME64_MAX && cell->net->live) { diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 89d36e3e5c79..f4e9e12373ac 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -779,7 +779,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry) struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; struct inode *inode = NULL, *ti; afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version); - bool supports_ibulk; + bool supports_ibulk, isnew; long ret; int i; @@ -850,7 +850,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry) * callback counters. */ ti = ilookup5_nowait(dir->i_sb, vp->fid.vnode, - afs_ilookup5_test_by_fid, &vp->fid); + afs_ilookup5_test_by_fid, &vp->fid, &isnew); if (!IS_ERR_OR_NULL(ti)) { vnode = AFS_FS_I(ti); vp->dv_before = vnode->status.data_version; diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 8c6130789fde..aa56e8951e03 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -64,7 +64,7 @@ static struct inode *afs_iget_pseudo_dir(struct super_block *sb, ino_t ino) vnode = AFS_FS_I(inode); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { netfs_inode_init(&vnode->netfs, NULL, false); simple_inode_init_ts(inode); set_nlink(inode, 2); @@ -108,7 +108,8 @@ static struct dentry *afs_dynroot_lookup_cell(struct inode *dir, struct dentry * dotted = true; } - cell = afs_lookup_cell(net, name, len, NULL, false, + cell = afs_lookup_cell(net, name, len, NULL, + AFS_LOOKUP_CELL_DYNROOT, afs_cell_trace_use_lookup_dynroot); if (IS_ERR(cell)) { ret = PTR_ERR(cell); @@ -258,7 +259,7 @@ static struct dentry *afs_lookup_atcell(struct inode *dir, struct dentry *dentry vnode = AFS_FS_I(inode); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { netfs_inode_init(&vnode->netfs, NULL, false); simple_inode_init_ts(inode); set_nlink(inode, 1); @@ -383,7 +384,7 @@ struct inode *afs_dynroot_iget_root(struct super_block *sb) vnode = AFS_FS_I(inode); /* there shouldn't be an existing inode */ - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { netfs_inode_init(&vnode->netfs, NULL, false); simple_inode_init_ts(inode); set_nlink(inode, 2); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index e1cb17b85791..dde1857fcabb 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -427,7 +427,7 @@ static void afs_fetch_status_success(struct afs_operation *op) struct afs_vnode *vnode = vp->vnode; int ret; - if (vnode->netfs.inode.i_state & I_NEW) { + if (inode_state_read_once(&vnode->netfs.inode) & I_NEW) { ret = afs_inode_init_from_status(op, vp, vnode); afs_op_set_error(op, ret); if (ret == 0) @@ -579,7 +579,7 @@ struct inode *afs_iget(struct afs_operation *op, struct afs_vnode_param *vp) inode, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); /* deal with an existing inode */ - if (!(inode->i_state & I_NEW)) { + if (!(inode_state_read_once(inode) & I_NEW)) { _leave(" = %p", inode); return inode; } @@ -639,7 +639,7 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key) _debug("GOT ROOT INODE %p { vl=%llx }", inode, as->volume->vid); - BUG_ON(!(inode->i_state & I_NEW)); + BUG_ON(!(inode_state_read_once(inode) & I_NEW)); vnode = AFS_FS_I(inode); vnode->cb_v_check = atomic_read(&as->volume->cb_v_break); @@ -748,7 +748,7 @@ void afs_evict_inode(struct inode *inode) if ((S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && - (inode->i_state & I_DIRTY) && + (inode_state_read_once(inode) & I_DIRTY) && !sbi->dyn_root) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, diff --git a/fs/afs/internal.h b/fs/afs/internal.h index a45ae5c2ef8a..009064b8d661 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -343,6 +343,7 @@ extern const char afs_init_sysname[]; enum afs_cell_state { AFS_CELL_SETTING_UP, + AFS_CELL_UNLOOKED, AFS_CELL_ACTIVE, AFS_CELL_REMOVING, AFS_CELL_DEAD, @@ -412,6 +413,7 @@ struct afs_cell { u8 name_len; /* Length of name */ char *name; /* Cell name, case-flattened and NUL-padded */ + char *key_desc; /* Authentication key description */ }; /* @@ -1049,9 +1051,18 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, extern int afs_cell_init(struct afs_net *, const char *); extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned, enum afs_cell_trace); +enum afs_lookup_cell_for { + AFS_LOOKUP_CELL_DYNROOT, + AFS_LOOKUP_CELL_MOUNTPOINT, + AFS_LOOKUP_CELL_DIRECT_MOUNT, + AFS_LOOKUP_CELL_PRELOAD, + AFS_LOOKUP_CELL_ROOTCELL, + AFS_LOOKUP_CELL_ALIAS_CHECK, +}; struct afs_cell *afs_lookup_cell(struct afs_net *net, const char *name, unsigned int namesz, - const char *vllist, bool excl, + const char *vllist, + enum afs_lookup_cell_for reason, enum afs_cell_trace trace); extern struct afs_cell *afs_use_cell(struct afs_cell *, enum afs_cell_trace); void afs_unuse_cell(struct afs_cell *cell, enum afs_cell_trace reason); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 1ad048e6e164..57c204a3c04e 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -107,7 +107,8 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) if (size > AFS_MAXCELLNAME) return -ENAMETOOLONG; - cell = afs_lookup_cell(ctx->net, p, size, NULL, false, + cell = afs_lookup_cell(ctx->net, p, size, NULL, + AFS_LOOKUP_CELL_MOUNTPOINT, afs_cell_trace_use_lookup_mntpt); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%pd'\n", mntpt); diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 40e879c8ca77..44520549b509 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -122,7 +122,8 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) if (strcmp(buf, "add") == 0) { struct afs_cell *cell; - cell = afs_lookup_cell(net, name, strlen(name), args, true, + cell = afs_lookup_cell(net, name, strlen(name), args, + AFS_LOOKUP_CELL_PRELOAD, afs_cell_trace_use_lookup_add); if (IS_ERR(cell)) { ret = PTR_ERR(cell); diff --git a/fs/afs/security.c b/fs/afs/security.c index 6a7744c9e2a2..55ddce94af03 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -16,6 +16,31 @@ static DEFINE_HASHTABLE(afs_permits_cache, 10); static DEFINE_SPINLOCK(afs_permits_lock); +static DEFINE_MUTEX(afs_key_lock); + +/* + * Allocate a key to use as a placeholder for anonymous user security. + */ +static int afs_alloc_anon_key(struct afs_cell *cell) +{ + struct key *key; + + mutex_lock(&afs_key_lock); + key = cell->anonymous_key; + if (!key) { + key = rxrpc_get_null_key(cell->key_desc); + if (!IS_ERR(key)) + cell->anonymous_key = key; + } + mutex_unlock(&afs_key_lock); + + if (IS_ERR(key)) + return PTR_ERR(key); + + _debug("anon key %p{%x}", + cell->anonymous_key, key_serial(cell->anonymous_key)); + return 0; +} /* * get a key @@ -23,11 +48,12 @@ static DEFINE_SPINLOCK(afs_permits_lock); struct key *afs_request_key(struct afs_cell *cell) { struct key *key; + int ret; - _enter("{%x}", key_serial(cell->anonymous_key)); + _enter("{%s}", cell->key_desc); - _debug("key %s", cell->anonymous_key->description); - key = request_key_net(&key_type_rxrpc, cell->anonymous_key->description, + _debug("key %s", cell->key_desc); + key = request_key_net(&key_type_rxrpc, cell->key_desc, cell->net->net, NULL); if (IS_ERR(key)) { if (PTR_ERR(key) != -ENOKEY) { @@ -35,6 +61,12 @@ struct key *afs_request_key(struct afs_cell *cell) return key; } + if (!cell->anonymous_key) { + ret = afs_alloc_anon_key(cell); + if (ret < 0) + return ERR_PTR(ret); + } + /* act as anonymous user */ _leave(" = {%x} [anon]", key_serial(cell->anonymous_key)); return key_get(cell->anonymous_key); @@ -52,11 +84,10 @@ struct key *afs_request_key_rcu(struct afs_cell *cell) { struct key *key; - _enter("{%x}", key_serial(cell->anonymous_key)); + _enter("{%s}", cell->key_desc); - _debug("key %s", cell->anonymous_key->description); - key = request_key_net_rcu(&key_type_rxrpc, - cell->anonymous_key->description, + _debug("key %s", cell->key_desc); + key = request_key_net_rcu(&key_type_rxrpc, cell->key_desc, cell->net->net); if (IS_ERR(key)) { if (PTR_ERR(key) != -ENOKEY) { @@ -65,6 +96,8 @@ struct key *afs_request_key_rcu(struct afs_cell *cell) } /* act as anonymous user */ + if (!cell->anonymous_key) + return NULL; /* Need to allocate */ _leave(" = {%x} [anon]", key_serial(cell->anonymous_key)); return key_get(cell->anonymous_key); } else { @@ -408,7 +441,7 @@ int afs_permission(struct mnt_idmap *idmap, struct inode *inode, if (mask & MAY_NOT_BLOCK) { key = afs_request_key_rcu(vnode->volume->cell); - if (IS_ERR(key)) + if (IS_ERR_OR_NULL(key)) return -ECHILD; ret = -ECHILD; diff --git a/fs/afs/super.c b/fs/afs/super.c index da407f2d6f0d..d672b7ab57ae 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -290,7 +290,7 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) /* lookup the cell record */ if (cellname) { cell = afs_lookup_cell(ctx->net, cellname, cellnamesz, - NULL, false, + NULL, AFS_LOOKUP_CELL_DIRECT_MOUNT, afs_cell_trace_use_lookup_mount); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%*.*s'\n", diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 709b4cdb723e..fc9676abd252 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -269,7 +269,8 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) if (!name_len || name_len > AFS_MAXCELLNAME) master = ERR_PTR(-EOPNOTSUPP); else - master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false, + master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, + AFS_LOOKUP_CELL_ALIAS_CHECK, afs_cell_trace_use_lookup_canonical); kfree(cell_name); if (IS_ERR(master)) @@ -1640,10 +1640,10 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, static void aio_fsync_work(struct work_struct *work) { struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work); - const struct cred *old_cred = override_creds(iocb->fsync.creds); - iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); - revert_creds(old_cred); + scoped_with_creds(iocb->fsync.creds) + iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); + put_cred(iocb->fsync.creds); iocb_put(iocb); } diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 180a458fc4f7..b8381c7fb636 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -280,27 +280,8 @@ static int __anon_inode_getfd(const char *name, const struct inode *context_inode, bool make_inode) { - int error, fd; - struct file *file; - - error = get_unused_fd_flags(flags); - if (error < 0) - return error; - fd = error; - - file = __anon_inode_getfile(name, fops, priv, flags, context_inode, - make_inode); - if (IS_ERR(file)) { - error = PTR_ERR(file); - goto err_put_unused_fd; - } - fd_install(fd, file); - - return fd; - -err_put_unused_fd: - put_unused_fd(fd); - return error; + return FD_ADD(flags, __anon_inode_getfile(name, fops, priv, flags, + context_inode, make_inode)); } /** diff --git a/fs/attr.c b/fs/attr.c index 795f231d00e8..b9ec6b47bab2 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -415,7 +415,7 @@ EXPORT_SYMBOL(may_setattr); * performed on the raw inode simply pass @nop_mnt_idmap. */ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, - struct iattr *attr, struct inode **delegated_inode) + struct iattr *attr, struct delegated_inode *delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index 23cea74f9933..4fd555528c5d 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -16,6 +16,7 @@ #include <linux/wait.h> #include <linux/sched.h> #include <linux/sched/signal.h> +#include <uapi/linux/mount.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/uaccess.h> @@ -27,6 +28,9 @@ #include <linux/magic.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> +#include "../mount.h" +#include <linux/ns_common.h> + /* This is the range of ioctl() numbers we claim as ours */ #define AUTOFS_IOC_FIRST AUTOFS_IOC_READY @@ -114,6 +118,7 @@ struct autofs_sb_info { int pipefd; struct file *pipe; struct pid *oz_pgrp; + u64 mnt_ns_id; int version; int sub_version; int min_proto; diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index d8dd150cbd74..a58f9248b0f5 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -231,32 +231,14 @@ static int test_by_type(const struct path *path, void *p) */ static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid) { - int err, fd; - - fd = get_unused_fd_flags(O_CLOEXEC); - if (likely(fd >= 0)) { - struct file *filp; - struct path path; - - err = find_autofs_mount(name, &path, test_by_dev, &devid); - if (err) - goto out; - - filp = dentry_open(&path, O_RDONLY, current_cred()); - path_put(&path); - if (IS_ERR(filp)) { - err = PTR_ERR(filp); - goto out; - } - - fd_install(fd, filp); - } + struct path path __free(path_put) = {}; + int err; - return fd; + err = find_autofs_mount(name, &path, test_by_dev, &devid); + if (err) + return err; -out: - put_unused_fd(fd); - return err; + return FD_ADD(O_CLOEXEC, dentry_open(&path, O_RDONLY, current_cred())); } /* Open a file descriptor on an autofs mount point */ @@ -381,6 +363,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp, swap(sbi->oz_pgrp, new_pid); sbi->pipefd = pipefd; sbi->pipe = pipe; + sbi->mnt_ns_id = to_ns_common(current->nsproxy->mnt_ns)->ns_id; sbi->flags &= ~AUTOFS_SBI_CATATONIC; } out: diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index f5c16ffba013..732aee76a24c 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -251,6 +251,7 @@ static struct autofs_sb_info *autofs_alloc_sbi(void) sbi->min_proto = AUTOFS_MIN_PROTO_VERSION; sbi->max_proto = AUTOFS_MAX_PROTO_VERSION; sbi->pipefd = -1; + sbi->mnt_ns_id = to_ns_common(current->nsproxy->mnt_ns)->ns_id; set_autofs_type_indirect(&sbi->type); mutex_init(&sbi->wq_mutex); diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 174c7205fee4..d10df9d89d1c 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -341,6 +341,14 @@ static struct vfsmount *autofs_d_automount(struct path *path) if (autofs_oz_mode(sbi)) return NULL; + /* Refuse to trigger mount if current namespace is not the owner + * and the mount is propagation private. + */ + if (sbi->mnt_ns_id != to_ns_common(current->nsproxy->mnt_ns)->ns_id) { + if (vfsmount_to_propagation_flags(path->mnt) & MS_PRIVATE) + return ERR_PTR(-EPERM); + } + /* * If an expire request is pending everyone must wait. * If the expire fails we're still mounted so continue diff --git a/fs/backing-file.c b/fs/backing-file.c index 15a7f8031084..45da8600d564 100644 --- a/fs/backing-file.c +++ b/fs/backing-file.c @@ -157,13 +157,37 @@ static int backing_aio_init_wq(struct kiocb *iocb) return sb_init_dio_done_wq(sb); } +static int do_backing_file_read_iter(struct file *file, struct iov_iter *iter, + struct kiocb *iocb, int flags) +{ + struct backing_aio *aio = NULL; + int ret; + + if (is_sync_kiocb(iocb)) { + rwf_t rwf = iocb_to_rw_flags(flags); + + return vfs_iter_read(file, iter, &iocb->ki_pos, rwf); + } + + aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL); + if (!aio) + return -ENOMEM; + + aio->orig_iocb = iocb; + kiocb_clone(&aio->iocb, iocb, get_file(file)); + aio->iocb.ki_complete = backing_aio_rw_complete; + refcount_set(&aio->ref, 2); + ret = vfs_iocb_iter_read(file, &aio->iocb, iter); + backing_aio_put(aio); + if (ret != -EIOCBQUEUED) + backing_aio_cleanup(aio, ret); + return ret; +} ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, struct kiocb *iocb, int flags, struct backing_file_ctx *ctx) { - struct backing_aio *aio = NULL; - const struct cred *old_cred; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING))) @@ -176,41 +200,57 @@ ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, !(file->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; - old_cred = override_creds(ctx->cred); + scoped_with_creds(ctx->cred) + ret = do_backing_file_read_iter(file, iter, iocb, flags); + + if (ctx->accessed) + ctx->accessed(iocb->ki_filp); + + return ret; +} +EXPORT_SYMBOL_GPL(backing_file_read_iter); + +static int do_backing_file_write_iter(struct file *file, struct iov_iter *iter, + struct kiocb *iocb, int flags, + void (*end_write)(struct kiocb *, ssize_t)) +{ + struct backing_aio *aio; + int ret; + if (is_sync_kiocb(iocb)) { rwf_t rwf = iocb_to_rw_flags(flags); - ret = vfs_iter_read(file, iter, &iocb->ki_pos, rwf); - } else { - ret = -ENOMEM; - aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL); - if (!aio) - goto out; - - aio->orig_iocb = iocb; - kiocb_clone(&aio->iocb, iocb, get_file(file)); - aio->iocb.ki_complete = backing_aio_rw_complete; - refcount_set(&aio->ref, 2); - ret = vfs_iocb_iter_read(file, &aio->iocb, iter); - backing_aio_put(aio); - if (ret != -EIOCBQUEUED) - backing_aio_cleanup(aio, ret); + ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf); + if (end_write) + end_write(iocb, ret); + return ret; } -out: - revert_creds(old_cred); - if (ctx->accessed) - ctx->accessed(iocb->ki_filp); + ret = backing_aio_init_wq(iocb); + if (ret) + return ret; + + aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL); + if (!aio) + return -ENOMEM; + aio->orig_iocb = iocb; + aio->end_write = end_write; + kiocb_clone(&aio->iocb, iocb, get_file(file)); + aio->iocb.ki_flags = flags; + aio->iocb.ki_complete = backing_aio_queue_completion; + refcount_set(&aio->ref, 2); + ret = vfs_iocb_iter_write(file, &aio->iocb, iter); + backing_aio_put(aio); + if (ret != -EIOCBQUEUED) + backing_aio_cleanup(aio, ret); return ret; } -EXPORT_SYMBOL_GPL(backing_file_read_iter); ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, struct kiocb *iocb, int flags, struct backing_file_ctx *ctx) { - const struct cred *old_cred; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING))) @@ -227,46 +267,8 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, !(file->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; - /* - * Stacked filesystems don't support deferred completions, don't copy - * this property in case it is set by the issuer. - */ - flags &= ~IOCB_DIO_CALLER_COMP; - - old_cred = override_creds(ctx->cred); - if (is_sync_kiocb(iocb)) { - rwf_t rwf = iocb_to_rw_flags(flags); - - ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf); - if (ctx->end_write) - ctx->end_write(iocb, ret); - } else { - struct backing_aio *aio; - - ret = backing_aio_init_wq(iocb); - if (ret) - goto out; - - ret = -ENOMEM; - aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL); - if (!aio) - goto out; - - aio->orig_iocb = iocb; - aio->end_write = ctx->end_write; - kiocb_clone(&aio->iocb, iocb, get_file(file)); - aio->iocb.ki_flags = flags; - aio->iocb.ki_complete = backing_aio_queue_completion; - refcount_set(&aio->ref, 2); - ret = vfs_iocb_iter_write(file, &aio->iocb, iter); - backing_aio_put(aio); - if (ret != -EIOCBQUEUED) - backing_aio_cleanup(aio, ret); - } -out: - revert_creds(old_cred); - - return ret; + scoped_with_creds(ctx->cred) + return do_backing_file_write_iter(file, iter, iocb, flags, ctx->end_write); } EXPORT_SYMBOL_GPL(backing_file_write_iter); @@ -275,15 +277,13 @@ ssize_t backing_file_splice_read(struct file *in, struct kiocb *iocb, unsigned int flags, struct backing_file_ctx *ctx) { - const struct cred *old_cred; ssize_t ret; if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING))) return -EIO; - old_cred = override_creds(ctx->cred); - ret = vfs_splice_read(in, &iocb->ki_pos, pipe, len, flags); - revert_creds(old_cred); + scoped_with_creds(ctx->cred) + ret = vfs_splice_read(in, &iocb->ki_pos, pipe, len, flags); if (ctx->accessed) ctx->accessed(iocb->ki_filp); @@ -297,7 +297,6 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, size_t len, unsigned int flags, struct backing_file_ctx *ctx) { - const struct cred *old_cred; ssize_t ret; if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING))) @@ -310,11 +309,11 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, if (ret) return ret; - old_cred = override_creds(ctx->cred); - file_start_write(out); - ret = out->f_op->splice_write(pipe, out, &iocb->ki_pos, len, flags); - file_end_write(out); - revert_creds(old_cred); + scoped_with_creds(ctx->cred) { + file_start_write(out); + ret = out->f_op->splice_write(pipe, out, &iocb->ki_pos, len, flags); + file_end_write(out); + } if (ctx->end_write) ctx->end_write(iocb, ret); @@ -326,7 +325,6 @@ EXPORT_SYMBOL_GPL(backing_file_splice_write); int backing_file_mmap(struct file *file, struct vm_area_struct *vma, struct backing_file_ctx *ctx) { - const struct cred *old_cred; struct file *user_file = vma->vm_file; int ret; @@ -338,9 +336,8 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma, vma_set_file(vma, file); - old_cred = override_creds(ctx->cred); - ret = vfs_mmap(vma->vm_file, vma); - revert_creds(old_cred); + scoped_with_creds(ctx->cred) + ret = vfs_mmap(vma->vm_file, vma); if (ctx->accessed) ctx->accessed(user_file); diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 8f430ff8e445..9fcfdd6b8189 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -307,7 +307,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; befs_ino = BEFS_I(inode); diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 1d41ce477df5..ce6f83234b67 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -42,7 +42,7 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; if ((ino < BFS_ROOT_INO) || (ino > BFS_SB(inode->i_sb)->si_lasti)) { @@ -61,7 +61,19 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino) off = (ino - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK; di = (struct bfs_inode *)bh->b_data + off; - inode->i_mode = 0x0000FFFF & le32_to_cpu(di->i_mode); + /* + * https://martin.hinner.info/fs/bfs/bfs-structure.html explains that + * BFS in SCO UnixWare environment used only lower 9 bits of di->i_mode + * value. This means that, although bfs_write_inode() saves whole + * inode->i_mode bits (which include S_IFMT bits and S_IS{UID,GID,VTX} + * bits), middle 7 bits of di->i_mode value can be garbage when these + * bits were not saved by bfs_write_inode(). + * Since we can't tell whether middle 7 bits are garbage, use only + * lower 12 bits (i.e. tolerate S_IS{UID,GID,VTX} bits possibly being + * garbage) and reconstruct S_IFMT bits for Linux environment from + * di->i_vtype value. + */ + inode->i_mode = 0x00000FFF & le32_to_cpu(di->i_mode); if (le32_to_cpu(di->i_vtype) == BFS_VDIR) { inode->i_mode |= S_IFDIR; inode->i_op = &bfs_dir_inops; @@ -71,6 +83,11 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino) inode->i_op = &bfs_file_inops; inode->i_fop = &bfs_file_operations; inode->i_mapping->a_ops = &bfs_aops; + } else { + brelse(bh); + printf("Unknown vtype=%u %s:%08lx\n", + le32_to_cpu(di->i_vtype), inode->i_sb->s_id, ino); + goto error; } BFS_I(inode)->i_sblock = le32_to_cpu(di->i_sblock); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index e4653bb99946..3eb734c192e9 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -46,7 +46,7 @@ #include <linux/cred.h> #include <linux/dax.h> #include <linux/uaccess.h> -#include <linux/rseq.h> +#include <uapi/linux/rseq.h> #include <asm/param.h> #include <asm/page.h> diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index a839f960cd4a..d7aec5b87c2b 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -782,8 +782,6 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, return PTR_ERR(e); if (e->flags & MISC_FMT_OPEN_FILE) { - const struct cred *old_cred; - /* * Now that we support unprivileged binfmt_misc mounts make * sure we use the credentials that the register @file was @@ -791,9 +789,8 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, * didn't matter much as only a privileged process could open * the register file. */ - old_cred = override_creds(file->f_cred); - f = open_exec(e->interpreter); - revert_creds(old_cred); + scoped_with_creds(file->f_cred) + f = open_exec(e->interpreter); if (IS_ERR(f)) { pr_notice("register: failed to install interpreter file %s\n", e->interpreter); @@ -837,8 +834,10 @@ out: inode_unlock(d_inode(root)); if (err) { - if (f) + if (f) { + exe_file_allow_write_access(f); filp_close(f, NULL); + } kfree(e); return err; } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 5322ef2ae015..08cdda47509f 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1850,12 +1850,10 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) if (!btrfs_should_reclaim(fs_info)) return; - sb_start_write(fs_info->sb); + guard(super_write)(fs_info->sb); - if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { - sb_end_write(fs_info->sb); + if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) return; - } /* * Long running balances can keep us blocked here for eternity, so @@ -1863,7 +1861,6 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) */ if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) { btrfs_exclop_finish(fs_info); - sb_end_write(fs_info->sb); return; } @@ -1947,7 +1944,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) /* * Get out fast, in case we're read-only or unmounting the * filesystem. It is OK to drop block groups from the list even - * for the read-only case. As we did sb_start_write(), + * for the read-only case. As we did take the super write lock, * "mount -o remount,ro" won't happen and read-only filesystem * means it is forced read-only due to a fatal error. So, it * never gets back to read-write to let us reclaim again. @@ -2030,7 +2027,6 @@ end: list_splice_tail(&retry_list, &fs_info->reclaim_bgs); spin_unlock(&fs_info->unused_bgs_lock); btrfs_exclop_finish(fs_info); - sb_end_write(fs_info->sb); } void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index eba188a9e3bb..aee1fd21cdd6 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -85,8 +85,8 @@ static inline u32 btrfs_calc_input_length(struct folio *folio, u64 range_end, u6 { /* @cur must be inside the folio. */ ASSERT(folio_pos(folio) <= cur); - ASSERT(cur < folio_end(folio)); - return min(range_end, folio_end(folio)) - cur; + ASSERT(cur < folio_next_pos(folio)); + return umin(range_end, folio_next_pos(folio)) - cur; } int btrfs_alloc_compress_wsm(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index 7b277934f66f..a7f20f048398 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -254,10 +254,9 @@ again: range.extent_thresh = defrag->extent_thresh; file_ra_state_init(ra, inode->vfs_inode.i_mapping); - sb_start_write(fs_info->sb); - ret = btrfs_defrag_file(inode, ra, &range, defrag->transid, - BTRFS_DEFRAG_BATCH); - sb_end_write(fs_info->sb); + scoped_guard(super_write, fs_info->sb) + ret = btrfs_defrag_file(inode, ra, &range, + defrag->transid, BTRFS_DEFRAG_BATCH); iput(&inode->vfs_inode); if (ret < 0) @@ -886,7 +885,7 @@ again: } lock_start = folio_pos(folio); - lock_end = folio_end(folio) - 1; + lock_end = folio_next_pos(folio) - 1; /* Wait for any existing ordered extent in the range */ while (1) { struct btrfs_ordered_extent *ordered; @@ -1178,7 +1177,8 @@ static int defrag_one_locked_target(struct btrfs_inode *inode, if (!folio) break; - if (start >= folio_end(folio) || start + len <= folio_pos(folio)) + if (start >= folio_next_pos(folio) || + start + len <= folio_pos(folio)) continue; btrfs_folio_clamp_clear_checked(fs_info, folio, start, len); btrfs_folio_clamp_set_dirty(fs_info, folio, start, len); @@ -1219,7 +1219,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len, folios[i] = NULL; goto free_folios; } - cur = folio_end(folios[i]); + cur = folio_next_pos(folios[i]); } for (int i = 0; i < nr_pages; i++) { if (!folios[i]) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 23273d0e6f22..7361d5d890d2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -333,7 +333,7 @@ static noinline int lock_delalloc_folios(struct inode *inode, goto out; } range_start = max_t(u64, folio_pos(folio), start); - range_len = min_t(u64, folio_end(folio), end + 1) - range_start; + range_len = min_t(u64, folio_next_pos(folio), end + 1) - range_start; btrfs_folio_set_lock(fs_info, folio, range_start, range_len); processed_end = range_start + range_len - 1; @@ -387,7 +387,7 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode, ASSERT(orig_end > orig_start); /* The range should at least cover part of the folio */ - ASSERT(!(orig_start >= folio_end(locked_folio) || + ASSERT(!(orig_start >= folio_next_pos(locked_folio) || orig_end <= folio_pos(locked_folio))); again: /* step one, find a bunch of delalloc bytes starting at start */ @@ -493,7 +493,7 @@ static void end_folio_read(struct folio *folio, bool uptodate, u64 start, u32 le struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); ASSERT(folio_pos(folio) <= start && - start + len <= folio_end(folio)); + start + len <= folio_next_pos(folio)); if (uptodate && btrfs_verify_folio(folio, start, len)) btrfs_folio_set_uptodate(fs_info, folio, start, len); @@ -1201,7 +1201,7 @@ static bool can_skip_one_ordered_range(struct btrfs_inode *inode, * finished our folio read and unlocked the folio. */ if (btrfs_folio_test_dirty(fs_info, folio, cur, blocksize)) { - u64 range_len = min(folio_end(folio), + u64 range_len = umin(folio_next_pos(folio), ordered->file_offset + ordered->num_bytes) - cur; ret = true; @@ -1223,7 +1223,7 @@ static bool can_skip_one_ordered_range(struct btrfs_inode *inode, * So we return true and update @next_ret to the OE/folio boundary. */ if (btrfs_folio_test_uptodate(fs_info, folio, cur, blocksize)) { - u64 range_len = min(folio_end(folio), + u64 range_len = umin(folio_next_pos(folio), ordered->file_offset + ordered->num_bytes) - cur; /* @@ -2215,7 +2215,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i]; u64 range_start = max_t(u64, eb->start, folio_pos(folio)); - u32 range_len = min_t(u64, folio_end(folio), + u32 range_len = min_t(u64, folio_next_pos(folio), eb->start + eb->len) - range_start; folio_lock(folio); @@ -2468,10 +2468,7 @@ static int extent_write_cache_pages(struct address_space *mapping, &BTRFS_I(inode)->runtime_flags)) wbc->tagged_writepages = 1; - if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) - tag = PAGECACHE_TAG_TOWRITE; - else - tag = PAGECACHE_TAG_DIRTY; + tag = wbc_to_tag(wbc); retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, index, end); @@ -2627,7 +2624,7 @@ void extent_write_locked_range(struct inode *inode, const struct folio *locked_f continue; } - cur_end = min_t(u64, folio_end(folio) - 1, end); + cur_end = min_t(u64, folio_next_pos(folio) - 1, end); cur_len = cur_end + 1 - cur; ASSERT(folio_test_locked(folio)); @@ -3868,7 +3865,7 @@ int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i]; u64 range_start = max_t(u64, eb->start, folio_pos(folio)); - u32 range_len = min_t(u64, folio_end(folio), + u32 range_len = min_t(u64, folio_next_pos(folio), eb->start + eb->len) - range_start; bio_add_folio_nofail(&bbio->bio, folio, range_len, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index fa82def46e39..e7453f992e1e 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -89,7 +89,8 @@ int btrfs_dirty_folio(struct btrfs_inode *inode, struct folio *folio, loff_t pos num_bytes = round_up(write_bytes + pos - start_pos, fs_info->sectorsize); ASSERT(num_bytes <= U32_MAX); - ASSERT(folio_pos(folio) <= pos && folio_end(folio) >= pos + write_bytes); + ASSERT(folio_pos(folio) <= pos && + folio_next_pos(folio) >= pos + write_bytes); end_of_last_block = start_pos + num_bytes - 1; @@ -799,7 +800,7 @@ static int prepare_uptodate_folio(struct inode *inode, struct folio *folio, u64 u64 len) { u64 clamp_start = max_t(u64, pos, folio_pos(folio)); - u64 clamp_end = min_t(u64, pos + len, folio_end(folio)); + u64 clamp_end = min_t(u64, pos + len, folio_next_pos(folio)); const u32 blocksize = inode_to_fs_info(inode)->sectorsize; int ret = 0; @@ -1254,8 +1255,8 @@ again: * The reserved range goes beyond the current folio, shrink the reserved * space to the folio boundary. */ - if (reserved_start + reserved_len > folio_end(folio)) { - const u64 last_block = folio_end(folio); + if (reserved_start + reserved_len > folio_next_pos(folio)) { + const u64 last_block = folio_next_pos(folio); shrink_reserved_space(inode, *data_reserved, reserved_start, reserved_len, last_block - reserved_start, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3df5f36185a0..9c6ca87b3d56 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9,6 +9,7 @@ #include <linux/blk-cgroup.h> #include <linux/file.h> #include <linux/fs.h> +#include <linux/fs_struct.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/time.h> @@ -177,8 +178,10 @@ static int data_reloc_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, return ret; } ret = paths_from_inode(inum, ipath); - if (ret < 0) + if (ret < 0) { + btrfs_put_root(local_root); goto err; + } /* * We deliberately ignore the bit ipath might have been too small to @@ -409,7 +412,7 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, continue; } - index = folio_end(folio) >> PAGE_SHIFT; + index = folio_next_index(folio); /* * Here we just clear all Ordered bits for every page in the * range, then btrfs_mark_ordered_io_finished() will handle @@ -2336,7 +2339,8 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct folio *locked_fol * The range must cover part of the @locked_folio, or a return of 1 * can confuse the caller. */ - ASSERT(!(end <= folio_pos(locked_folio) || start >= folio_end(locked_folio))); + ASSERT(!(end <= folio_pos(locked_folio) || + start >= folio_next_pos(locked_folio))); if (should_nocow(inode, start, end)) { ret = run_delalloc_nocow(inode, locked_folio, start, end); @@ -2743,7 +2747,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) struct btrfs_inode *inode = fixup->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 page_start = folio_pos(folio); - u64 page_end = folio_end(folio) - 1; + u64 page_end = folio_next_pos(folio) - 1; int ret = 0; bool free_delalloc_space = true; @@ -3884,7 +3888,7 @@ static int btrfs_add_inode_to_root(struct btrfs_inode *inode, bool prealloc) ASSERT(ret != -ENOMEM); return ret; } else if (existing) { - WARN_ON(!(existing->vfs_inode.i_state & (I_WILL_FREE | I_FREEING))); + WARN_ON(!(inode_state_read_once(&existing->vfs_inode) & (I_WILL_FREE | I_FREEING))); } return 0; @@ -4855,7 +4859,7 @@ again: */ zero_start = max_t(u64, folio_pos(folio), start); - zero_end = folio_end(folio); + zero_end = folio_next_pos(folio); folio_zero_range(folio, zero_start - folio_pos(folio), zero_end - zero_start); @@ -5038,7 +5042,7 @@ again: * not reach disk, it still affects our page caches. */ zero_start = max_t(u64, folio_pos(folio), start); - zero_end = min_t(u64, folio_end(folio) - 1, end); + zero_end = min_t(u64, folio_next_pos(folio) - 1, end); } else { zero_start = max_t(u64, block_start, start); zero_end = min_t(u64, block_end, end); @@ -5361,7 +5365,7 @@ static void evict_inode_truncate_pages(struct inode *inode) struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct rb_node *node; - ASSERT(inode->i_state & I_FREEING); + ASSERT(inode_state_read_once(inode) & I_FREEING); truncate_inode_pages_final(&inode->i_data); btrfs_drop_extent_map_range(BTRFS_I(inode), 0, (u64)-1, false); @@ -5799,7 +5803,7 @@ struct btrfs_inode *btrfs_iget_path(u64 ino, struct btrfs_root *root, if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->vfs_inode.i_state & I_NEW)) + if (!(inode_state_read_once(&inode->vfs_inode) & I_NEW)) return inode; ret = btrfs_read_locked_inode(inode, path); @@ -5823,7 +5827,7 @@ struct btrfs_inode *btrfs_iget(u64 ino, struct btrfs_root *root) if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->vfs_inode.i_state & I_NEW)) + if (!(inode_state_read_once(&inode->vfs_inode) & I_NEW)) return inode; path = btrfs_alloc_path(); @@ -5837,6 +5841,8 @@ struct btrfs_inode *btrfs_iget(u64 ino, struct btrfs_root *root) if (ret) return ERR_PTR(ret); + if (S_ISDIR(inode->vfs_inode.i_mode)) + inode->vfs_inode.i_opflags |= IOP_FASTPERM_MAY_EXEC; unlock_new_inode(&inode->vfs_inode); return inode; } @@ -6289,8 +6295,8 @@ static int btrfs_dirty_inode(struct btrfs_inode *inode) } /* - * This is a copy of file_update_time. We need this so we can return error on - * ENOSPC for updating the inode in the case of file write and mmap writes. + * We need our own ->update_time so that we can return error on ENOSPC for + * updating the inode in the case of file write and mmap writes. */ static int btrfs_update_time(struct inode *inode, int flags) { @@ -6788,8 +6794,11 @@ static int btrfs_create_common(struct inode *dir, struct dentry *dentry, } ret = btrfs_create_new_inode(trans, &new_inode_args); - if (!ret) + if (!ret) { + if (S_ISDIR(inode->i_mode)) + inode->i_opflags |= IOP_FASTPERM_MAY_EXEC; d_instantiate_new(dentry, inode); + } btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); @@ -7479,7 +7488,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset, u64 page_start = folio_pos(folio); u64 page_end = page_start + folio_size(folio) - 1; u64 cur; - int inode_evicting = inode->vfs_inode.i_state & I_FREEING; + int inode_evicting = inode_state_read_once(&inode->vfs_inode) & I_FREEING; /* * We have folio locked so no new ordered extent can be created on this @@ -8708,15 +8717,13 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode * some fairly slow code that needs optimization. This walks the list * of all the inodes with pending delalloc and forces them to disk. */ -static int start_delalloc_inodes(struct btrfs_root *root, - struct writeback_control *wbc, bool snapshot, - bool in_reclaim_context) +static int start_delalloc_inodes(struct btrfs_root *root, long *nr_to_write, + bool snapshot, bool in_reclaim_context) { struct btrfs_delalloc_work *work, *next; LIST_HEAD(works); LIST_HEAD(splice); int ret = 0; - bool full_flush = wbc->nr_to_write == LONG_MAX; mutex_lock(&root->delalloc_mutex); spin_lock(&root->delalloc_lock); @@ -8742,10 +8749,10 @@ static int start_delalloc_inodes(struct btrfs_root *root, if (snapshot) set_bit(BTRFS_INODE_SNAPSHOT_FLUSH, &inode->runtime_flags); - if (full_flush) { - work = btrfs_alloc_delalloc_work(&inode->vfs_inode); + if (nr_to_write == NULL) { + work = btrfs_alloc_delalloc_work(tmp_inode); if (!work) { - iput(&inode->vfs_inode); + iput(tmp_inode); ret = -ENOMEM; goto out; } @@ -8753,9 +8760,11 @@ static int start_delalloc_inodes(struct btrfs_root *root, btrfs_queue_work(root->fs_info->flush_workers, &work->work); } else { - ret = filemap_fdatawrite_wbc(inode->vfs_inode.i_mapping, wbc); + ret = filemap_flush_nr(tmp_inode->i_mapping, + nr_to_write); btrfs_add_delayed_iput(inode); - if (ret || wbc->nr_to_write <= 0) + + if (ret || *nr_to_write <= 0) goto out; } cond_resched(); @@ -8781,29 +8790,17 @@ out: int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context) { - struct writeback_control wbc = { - .nr_to_write = LONG_MAX, - .sync_mode = WB_SYNC_NONE, - .range_start = 0, - .range_end = LLONG_MAX, - }; struct btrfs_fs_info *fs_info = root->fs_info; if (BTRFS_FS_ERROR(fs_info)) return -EROFS; - - return start_delalloc_inodes(root, &wbc, true, in_reclaim_context); + return start_delalloc_inodes(root, NULL, true, in_reclaim_context); } int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, bool in_reclaim_context) { - struct writeback_control wbc = { - .nr_to_write = nr, - .sync_mode = WB_SYNC_NONE, - .range_start = 0, - .range_end = LLONG_MAX, - }; + long *nr_to_write = nr == LONG_MAX ? NULL : &nr; struct btrfs_root *root; LIST_HEAD(splice); int ret; @@ -8815,13 +8812,6 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, spin_lock(&fs_info->delalloc_root_lock); list_splice_init(&fs_info->delalloc_roots, &splice); while (!list_empty(&splice)) { - /* - * Reset nr_to_write here so we know that we're doing a full - * flush. - */ - if (nr == LONG_MAX) - wbc.nr_to_write = LONG_MAX; - root = list_first_entry(&splice, struct btrfs_root, delalloc_root); root = btrfs_grab_root(root); @@ -8830,9 +8820,10 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, &fs_info->delalloc_roots); spin_unlock(&fs_info->delalloc_root_lock); - ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context); + ret = start_delalloc_inodes(root, nr_to_write, false, + in_reclaim_context); btrfs_put_root(root); - if (ret < 0 || wbc.nr_to_write <= 0) + if (ret < 0 || nr <= 0) goto out; spin_lock(&fs_info->delalloc_root_lock); } @@ -9168,6 +9159,11 @@ int btrfs_prealloc_file_range_trans(struct inode *inode, min_size, actual_len, alloc_hint, trans); } +/* + * NOTE: in case you are adding MAY_EXEC check for directories: + * we are marking them with IOP_FASTPERM_MAY_EXEC, allowing path lookup to + * elide calls here. + */ static int btrfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8cb7d5a462ef..b138120feba3 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -904,14 +904,9 @@ static noinline int btrfs_mksubvol(struct dentry *parent, struct fscrypt_str name_str = FSTR_INIT((char *)qname->name, qname->len); int ret; - ret = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); - if (ret == -EINTR) - return ret; - - dentry = lookup_one(idmap, qname, parent); - ret = PTR_ERR(dentry); + dentry = start_creating_killable(idmap, parent, qname); if (IS_ERR(dentry)) - goto out_unlock; + return PTR_ERR(dentry); ret = btrfs_may_create(idmap, dir, dentry); if (ret) @@ -940,9 +935,7 @@ static noinline int btrfs_mksubvol(struct dentry *parent, out_up_read: up_read(&fs_info->subvol_sem); out_dput: - dput(dentry); -out_unlock: - btrfs_inode_unlock(BTRFS_I(dir), 0); + end_creating(dentry); return ret; } @@ -2417,18 +2410,10 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, goto free_subvol_name; } - ret = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); - if (ret == -EINTR) - goto free_subvol_name; - dentry = lookup_one(idmap, &QSTR(subvol_name), parent); + dentry = start_removing_killable(idmap, parent, &QSTR(subvol_name)); if (IS_ERR(dentry)) { ret = PTR_ERR(dentry); - goto out_unlock_dir; - } - - if (d_really_is_negative(dentry)) { - ret = -ENOENT; - goto out_dput; + goto out_end_removing; } inode = d_inode(dentry); @@ -2449,7 +2434,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, */ ret = -EPERM; if (!btrfs_test_opt(fs_info, USER_SUBVOL_RM_ALLOWED)) - goto out_dput; + goto out_end_removing; /* * Do not allow deletion if the parent dir is the same @@ -2460,21 +2445,21 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, */ ret = -EINVAL; if (root == dest) - goto out_dput; + goto out_end_removing; ret = inode_permission(idmap, inode, MAY_WRITE | MAY_EXEC); if (ret) - goto out_dput; + goto out_end_removing; } /* check if subvolume may be deleted by a user */ ret = btrfs_may_delete(idmap, dir, dentry, 1); if (ret) - goto out_dput; + goto out_end_removing; if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) { ret = -EINVAL; - goto out_dput; + goto out_end_removing; } btrfs_inode_lock(BTRFS_I(inode), 0); @@ -2483,10 +2468,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, if (!ret) d_delete_notify(dir, dentry); -out_dput: - dput(dentry); -out_unlock_dir: - btrfs_inode_unlock(BTRFS_I(dir), 0); +out_end_removing: + end_removing(dentry); free_subvol_name: kfree(subvol_name_ptr); free_parent: diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h index 60f9b000d644..17b71e1285e5 100644 --- a/fs/btrfs/misc.h +++ b/fs/btrfs/misc.h @@ -209,9 +209,4 @@ static inline bool bitmap_test_range_all_zero(const unsigned long *addr, return (found_set == start + nbits); } -static inline u64 folio_end(struct folio *folio) -{ - return folio_pos(folio) + folio_size(folio); -} - #endif diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 2829f20d7bb5..7fedebbee558 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -359,7 +359,7 @@ static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered, if (folio) { ASSERT(folio->mapping); ASSERT(folio_pos(folio) <= file_offset); - ASSERT(file_offset + len <= folio_end(folio)); + ASSERT(file_offset + len <= folio_next_pos(folio)); /* * Ordered flag indicates whether we still have diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 651b11884f82..ba20d9286a34 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2203,6 +2203,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, full_stripe_start, &length, &bioc, NULL, NULL); if (ret < 0) { + bio_put(bio); btrfs_put_bioc(bioc); btrfs_bio_counter_dec(fs_info); goto out; @@ -2212,6 +2213,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, btrfs_put_bioc(bioc); if (!rbio) { ret = -ENOMEM; + bio_put(bio); btrfs_bio_counter_dec(fs_info); goto out; } diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 5ca8d4db6722..a7ba868e9372 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -186,7 +186,8 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info, * unmapped page like dummy extent buffer pages. */ if (folio->mapping) - ASSERT(folio_pos(folio) <= start && start + len <= folio_end(folio), + ASSERT(folio_pos(folio) <= start && + start + len <= folio_next_pos(folio), "start=%llu len=%u folio_pos=%llu folio_size=%zu", start, len, folio_pos(folio), folio_size(folio)); } @@ -217,7 +218,7 @@ static void btrfs_subpage_clamp_range(struct folio *folio, u64 *start, u32 *len) if (folio_pos(folio) >= orig_start + orig_len) *len = 0; else - *len = min_t(u64, folio_end(folio), orig_start + orig_len) - *start; + *len = min_t(u64, folio_next_pos(folio), orig_start + orig_len) - *start; } static bool btrfs_subpage_end_and_test_lock(const struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c90b2d2cb08f..30f3c3b849c1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7122,7 +7122,7 @@ log_extents: * a power failure unless the log was synced as part of an fsync * against any other unrelated inode. */ - if (inode_only != LOG_INODE_EXISTS) + if (!ctx->logging_new_name && inode_only != LOG_INODE_EXISTS) inode->last_log_commit = inode->last_sub_trans; spin_unlock(&inode->lock); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2bec544d8ba3..cc8aa4a04348 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2002,14 +2002,11 @@ out: static void update_dev_time(const char *device_path) { struct path path; - int ret; - - ret = kern_path(device_path, LOOKUP_FOLLOW, &path); - if (ret) - return; - inode_update_time(d_inode(path.dentry), S_MTIME | S_CTIME | S_VERSION); - path_put(&path); + if (!kern_path(device_path, LOOKUP_FOLLOW, &path)) { + vfs_utimes(&path, NULL); + path_put(&path); + } } static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans, @@ -4660,12 +4657,12 @@ static int balance_kthread(void *data) struct btrfs_fs_info *fs_info = data; int ret = 0; - sb_start_write(fs_info->sb); + guard(super_write)(fs_info->sb); + mutex_lock(&fs_info->balance_mutex); if (fs_info->balance_ctl) ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL); mutex_unlock(&fs_info->balance_mutex); - sb_end_write(fs_info->sb); return ret; } @@ -8177,12 +8174,12 @@ static int relocating_repair_kthread(void *data) target = cache->start; btrfs_put_block_group(cache); - sb_start_write(fs_info->sb); + guard(super_write)(fs_info->sb); + if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { btrfs_info(fs_info, "zoned: skip relocating block group %llu to repair: EBUSY", target); - sb_end_write(fs_info->sb); return -EBUSY; } @@ -8210,7 +8207,6 @@ out: btrfs_put_block_group(cache); mutex_unlock(&fs_info->reclaim_bgs_lock); btrfs_exclop_finish(fs_info); - sb_end_write(fs_info->sb); return ret; } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 0ea0df18a8e4..d1db7fa1fe58 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1317,6 +1317,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, if (!btrfs_dev_is_sequential(device, info->physical)) { up_read(&dev_replace->rwsem); info->alloc_offset = WP_CONVENTIONAL; + info->capacity = device->zone_info->zone_size; return 0; } @@ -1522,6 +1523,8 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg, u64 last_alloc) { struct btrfs_fs_info *fs_info = bg->fs_info; + u64 stripe_nr = 0, stripe_offset = 0; + u32 stripe_index = 0; if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) { btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree", @@ -1529,28 +1532,26 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg, return -EINVAL; } + if (last_alloc) { + u32 factor = map->num_stripes; + + stripe_nr = last_alloc >> BTRFS_STRIPE_LEN_SHIFT; + stripe_offset = last_alloc & BTRFS_STRIPE_LEN_MASK; + stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index); + } + for (int i = 0; i < map->num_stripes; i++) { if (zone_info[i].alloc_offset == WP_MISSING_DEV) continue; if (zone_info[i].alloc_offset == WP_CONVENTIONAL) { - u64 stripe_nr, full_stripe_nr; - u64 stripe_offset; - int stripe_index; - stripe_nr = div64_u64(last_alloc, map->stripe_size); - stripe_offset = stripe_nr * map->stripe_size; - full_stripe_nr = div_u64(stripe_nr, map->num_stripes); - div_u64_rem(stripe_nr, map->num_stripes, &stripe_index); - - zone_info[i].alloc_offset = - full_stripe_nr * map->stripe_size; + zone_info[i].alloc_offset = btrfs_stripe_nr_to_offset(stripe_nr); if (stripe_index > i) - zone_info[i].alloc_offset += map->stripe_size; + zone_info[i].alloc_offset += BTRFS_STRIPE_LEN; else if (stripe_index == i) - zone_info[i].alloc_offset += - (last_alloc - stripe_offset); + zone_info[i].alloc_offset += stripe_offset; } if (test_bit(0, active) != test_bit(i, active)) { @@ -1574,6 +1575,8 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, u64 last_alloc) { struct btrfs_fs_info *fs_info = bg->fs_info; + u64 stripe_nr = 0, stripe_offset = 0; + u32 stripe_index = 0; if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) { btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree", @@ -1581,6 +1584,14 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, return -EINVAL; } + if (last_alloc) { + u32 factor = map->num_stripes / map->sub_stripes; + + stripe_nr = last_alloc >> BTRFS_STRIPE_LEN_SHIFT; + stripe_offset = last_alloc & BTRFS_STRIPE_LEN_MASK; + stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index); + } + for (int i = 0; i < map->num_stripes; i++) { if (zone_info[i].alloc_offset == WP_MISSING_DEV) continue; @@ -1594,26 +1605,12 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, } if (zone_info[i].alloc_offset == WP_CONVENTIONAL) { - u64 stripe_nr, full_stripe_nr; - u64 stripe_offset; - int stripe_index; - - stripe_nr = div64_u64(last_alloc, map->stripe_size); - stripe_offset = stripe_nr * map->stripe_size; - full_stripe_nr = div_u64(stripe_nr, - map->num_stripes / map->sub_stripes); - div_u64_rem(stripe_nr, - (map->num_stripes / map->sub_stripes), - &stripe_index); - - zone_info[i].alloc_offset = - full_stripe_nr * map->stripe_size; + zone_info[i].alloc_offset = btrfs_stripe_nr_to_offset(stripe_nr); if (stripe_index > (i / map->sub_stripes)) - zone_info[i].alloc_offset += map->stripe_size; + zone_info[i].alloc_offset += BTRFS_STRIPE_LEN; else if (stripe_index == (i / map->sub_stripes)) - zone_info[i].alloc_offset += - (last_alloc - stripe_offset); + zone_info[i].alloc_offset += stripe_offset; } if ((i % map->sub_stripes) == 0) { @@ -1683,8 +1680,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) set_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags); if (num_conventional > 0) { - /* Zone capacity is always zone size in emulation */ - cache->zone_capacity = cache->length; ret = calculate_alloc_pointer(cache, &last_alloc, new); if (ret) { btrfs_err(fs_info, @@ -1693,6 +1688,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } else if (map->num_stripes == num_conventional) { cache->alloc_offset = last_alloc; + cache->zone_capacity = cache->length; set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags); goto out; } diff --git a/fs/buffer.c b/fs/buffer.c index 6a8752f7bbed..838c0c571022 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -611,9 +611,9 @@ int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, return err; ret = sync_mapping_buffers(inode->i_mapping); - if (!(inode->i_state & I_DIRTY_ALL)) + if (!(inode_state_read_once(inode) & I_DIRTY_ALL)) goto out; - if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) + if (datasync && !(inode_state_read_once(inode) & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); @@ -2732,7 +2732,7 @@ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, loff_t i_size = i_size_read(inode); /* Is the folio fully inside i_size? */ - if (folio_pos(folio) + folio_size(folio) <= i_size) + if (folio_next_pos(folio) <= i_size) return __block_write_full_folio(inode, folio, get_block, wbc); /* Is the folio fully outside i_size? (truncate in progress) */ diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 3e63cfe15874..a08250d244ea 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -9,6 +9,7 @@ #include <linux/mount.h> #include <linux/xattr.h> #include <linux/file.h> +#include <linux/namei.h> #include <linux/falloc.h> #include <trace/events/fscache.h> #include "internal.h" @@ -428,11 +429,13 @@ static bool cachefiles_invalidate_cookie(struct fscache_cookie *cookie) if (!old_tmpfile) { struct cachefiles_volume *volume = object->volume; struct dentry *fan = volume->fanout[(u8)cookie->key_hash]; + struct dentry *obj; - inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); - cachefiles_bury_object(volume->cache, object, fan, - old_file->f_path.dentry, - FSCACHE_OBJECT_INVALIDATED); + obj = start_removing_dentry(fan, old_file->f_path.dentry); + if (!IS_ERR(obj)) + cachefiles_bury_object(volume->cache, object, + fan, obj, + FSCACHE_OBJECT_INVALIDATED); } fput(old_file); } diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index d1edb2ac3837..e5ec90dccc27 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -93,12 +93,11 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, _enter(",,%s", dirname); /* search the current directory for the element name */ - inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); retry: ret = cachefiles_inject_read_error(); if (ret == 0) - subdir = lookup_one(&nop_mnt_idmap, &QSTR(dirname), dir); + subdir = start_creating(&nop_mnt_idmap, dir, &QSTR(dirname)); else subdir = ERR_PTR(ret); trace_cachefiles_lookup(NULL, dir, subdir); @@ -129,10 +128,12 @@ retry: if (ret < 0) goto mkdir_error; ret = cachefiles_inject_write_error(); - if (ret == 0) - subdir = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700); - else + if (ret == 0) { + subdir = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700, NULL); + } else { + end_creating(subdir); subdir = ERR_PTR(ret); + } if (IS_ERR(subdir)) { trace_cachefiles_vfs_error(NULL, d_inode(dir), ret, cachefiles_trace_mkdir_error); @@ -141,7 +142,7 @@ retry: trace_cachefiles_mkdir(dir, subdir); if (unlikely(d_unhashed(subdir) || d_is_negative(subdir))) { - dput(subdir); + end_creating(subdir); goto retry; } ASSERT(d_backing_inode(subdir)); @@ -154,7 +155,7 @@ retry: /* Tell rmdir() it's not allowed to delete the subdir */ inode_lock(d_inode(subdir)); - inode_unlock(d_inode(dir)); + end_creating_keep(subdir); if (!__cachefiles_mark_inode_in_use(NULL, d_inode(subdir))) { pr_notice("cachefiles: Inode already in use: %pd (B=%lx)\n", @@ -196,14 +197,11 @@ mark_error: return ERR_PTR(-EBUSY); mkdir_error: - inode_unlock(d_inode(dir)); - if (!IS_ERR(subdir)) - dput(subdir); + end_creating(subdir); pr_err("mkdir %s failed with error %d\n", dirname, ret); return ERR_PTR(ret); lookup_error: - inode_unlock(d_inode(dir)); ret = PTR_ERR(subdir); pr_err("Lookup %s failed with error %d\n", dirname, ret); return ERR_PTR(ret); @@ -263,6 +261,8 @@ static int cachefiles_unlink(struct cachefiles_cache *cache, * - File backed objects are unlinked * - Directory backed objects are stuffed into the graveyard for userspace to * delete + * On entry dir must be locked. It will be unlocked on exit. + * On entry there must be at least 2 refs on rep, one will be dropped on exit. */ int cachefiles_bury_object(struct cachefiles_cache *cache, struct cachefiles_object *object, @@ -278,27 +278,23 @@ int cachefiles_bury_object(struct cachefiles_cache *cache, _enter(",'%pd','%pd'", dir, rep); if (rep->d_parent != dir) { - inode_unlock(d_inode(dir)); + end_removing(rep); _leave(" = -ESTALE"); return -ESTALE; } /* non-directories can just be unlinked */ if (!d_is_dir(rep)) { - dget(rep); /* Stop the dentry being negated if it's only pinned - * by a file struct. - */ ret = cachefiles_unlink(cache, object, dir, rep, why); - dput(rep); + end_removing(rep); - inode_unlock(d_inode(dir)); _leave(" = %d", ret); return ret; } /* directories have to be moved to the graveyard */ _debug("move stale object to graveyard"); - inode_unlock(d_inode(dir)); + end_removing(rep); try_again: /* first step is to make up a grave dentry in the graveyard */ @@ -425,13 +421,12 @@ int cachefiles_delete_object(struct cachefiles_object *object, _enter(",OBJ%x{%pD}", object->debug_id, object->file); - /* Stop the dentry being negated if it's only pinned by a file struct. */ - dget(dentry); - - inode_lock_nested(d_backing_inode(fan), I_MUTEX_PARENT); - ret = cachefiles_unlink(volume->cache, object, fan, dentry, why); - inode_unlock(d_backing_inode(fan)); - dput(dentry); + dentry = start_removing_dentry(fan, dentry); + if (IS_ERR(dentry)) + ret = PTR_ERR(dentry); + else + ret = cachefiles_unlink(volume->cache, object, fan, dentry, why); + end_removing(dentry); return ret; } @@ -644,9 +639,13 @@ bool cachefiles_look_up_object(struct cachefiles_object *object) if (!d_is_reg(dentry)) { pr_err("%pd is not a file\n", dentry); - inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); - ret = cachefiles_bury_object(volume->cache, object, fan, dentry, - FSCACHE_OBJECT_IS_WEIRD); + struct dentry *de = start_removing_dentry(fan, dentry); + if (IS_ERR(de)) + ret = PTR_ERR(de); + else + ret = cachefiles_bury_object(volume->cache, object, + fan, de, + FSCACHE_OBJECT_IS_WEIRD); dput(dentry); if (ret < 0) return false; @@ -679,36 +678,41 @@ bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, _enter(",%pD", object->file); - inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); ret = cachefiles_inject_read_error(); if (ret == 0) - dentry = lookup_one(&nop_mnt_idmap, &QSTR(object->d_name), fan); + dentry = start_creating(&nop_mnt_idmap, fan, &QSTR(object->d_name)); else dentry = ERR_PTR(ret); if (IS_ERR(dentry)) { trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(dentry), cachefiles_trace_lookup_error); _debug("lookup fail %ld", PTR_ERR(dentry)); - goto out_unlock; + goto out; } - if (!d_is_negative(dentry)) { + /* + * This loop will only execute more than once if some other thread + * races to create the object we are trying to create. + */ + while (!d_is_negative(dentry)) { ret = cachefiles_unlink(volume->cache, object, fan, dentry, FSCACHE_OBJECT_IS_STALE); if (ret < 0) - goto out_dput; + goto out_end; + + end_creating(dentry); - dput(dentry); ret = cachefiles_inject_read_error(); if (ret == 0) - dentry = lookup_one(&nop_mnt_idmap, &QSTR(object->d_name), fan); + dentry = start_creating(&nop_mnt_idmap, fan, + &QSTR(object->d_name)); else dentry = ERR_PTR(ret); if (IS_ERR(dentry)) { trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(dentry), cachefiles_trace_lookup_error); _debug("lookup fail %ld", PTR_ERR(dentry)); - goto out_unlock; + goto out; } } @@ -729,10 +733,9 @@ bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, success = true; } -out_dput: - dput(dentry); -out_unlock: - inode_unlock(d_inode(fan)); +out_end: + end_creating(dentry); +out: _leave(" = %u", success); return success; } @@ -748,26 +751,20 @@ static struct dentry *cachefiles_lookup_for_cull(struct cachefiles_cache *cache, struct dentry *victim; int ret = -ENOENT; - inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); + victim = start_removing(&nop_mnt_idmap, dir, &QSTR(filename)); - victim = lookup_one(&nop_mnt_idmap, &QSTR(filename), dir); if (IS_ERR(victim)) goto lookup_error; - if (d_is_negative(victim)) - goto lookup_put; if (d_inode(victim)->i_flags & S_KERNEL_FILE) goto lookup_busy; return victim; lookup_busy: ret = -EBUSY; -lookup_put: - inode_unlock(d_inode(dir)); - dput(victim); + end_removing(victim); return ERR_PTR(ret); lookup_error: - inode_unlock(d_inode(dir)); ret = PTR_ERR(victim); if (ret == -ENOENT) return ERR_PTR(-ESTALE); /* Probably got retired by the netfs */ @@ -815,18 +812,17 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, ret = cachefiles_bury_object(cache, NULL, dir, victim, FSCACHE_OBJECT_WAS_CULLED); + dput(victim); if (ret < 0) goto error; fscache_count_culled(); - dput(victim); _leave(" = 0"); return 0; error_unlock: - inode_unlock(d_inode(dir)); + end_removing(victim); error: - dput(victim); if (ret == -ENOENT) return -ESTALE; /* Probably got retired by the netfs */ diff --git a/fs/cachefiles/volume.c b/fs/cachefiles/volume.c index 781aac4ef274..90ba926f488e 100644 --- a/fs/cachefiles/volume.c +++ b/fs/cachefiles/volume.c @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/slab.h> +#include <linux/namei.h> #include "internal.h" #include <trace/events/fscache.h> @@ -58,9 +59,11 @@ retry: if (ret < 0) { if (ret != -ESTALE) goto error_dir; - inode_lock_nested(d_inode(cache->store), I_MUTEX_PARENT); - cachefiles_bury_object(cache, NULL, cache->store, vdentry, - FSCACHE_VOLUME_IS_WEIRD); + vdentry = start_removing_dentry(cache->store, vdentry); + if (!IS_ERR(vdentry)) + cachefiles_bury_object(cache, NULL, cache->store, + vdentry, + FSCACHE_VOLUME_IS_WEIRD); cachefiles_put_directory(volume->dentry); cond_resched(); goto retry; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 322ed268f14a..63b75d214210 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1045,11 +1045,7 @@ void ceph_init_writeback_ctl(struct address_space *mapping, ceph_wbc->index = ceph_wbc->start_index; ceph_wbc->end = -1; - if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { - ceph_wbc->tag = PAGECACHE_TAG_TOWRITE; - } else { - ceph_wbc->tag = PAGECACHE_TAG_DIRTY; - } + ceph_wbc->tag = wbc_to_tag(wbc); ceph_wbc->op_idx = -1; ceph_wbc->num_ops = 0; diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 930fbd54d2c8..f678bab189d8 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -26,7 +26,7 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) return; /* Only new inodes! */ - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return; WARN_ON_ONCE(ci->netfs.cache); diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index 7026e794813c..928746b92512 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -329,7 +329,7 @@ int ceph_encode_encrypted_dname(struct inode *parent, char *buf, int elen) out: kfree(cryptbuf); if (dir != parent) { - if ((dir->i_state & I_NEW)) + if ((inode_state_read_once(dir) & I_NEW)) discard_new_inode(dir); else iput(dir); @@ -438,7 +438,7 @@ out: fscrypt_fname_free_buffer(&_tname); out_inode: if (dir != fname->dir) { - if ((dir->i_state & I_NEW)) + if ((inode_state_read_once(dir) & I_NEW)) discard_new_inode(dir); else iput(dir); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 99b30f784ee2..983390069f73 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -740,7 +740,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode, vino.ino, ceph_ino(dir), dentry->d_name.name); ceph_dir_clear_ordered(dir); ceph_init_inode_acls(inode, as_ctx); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { /* * If it's not I_NEW, then someone created this before * we got here. Assume the server is aware of it at @@ -901,7 +901,7 @@ retry: new_inode = NULL; goto out_req; } - WARN_ON_ONCE(!(new_inode->i_state & I_NEW)); + WARN_ON_ONCE(!(inode_state_read_once(new_inode) & I_NEW)); spin_lock(&dentry->d_lock); di->flags |= CEPH_DENTRY_ASYNC_CREATE; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index a6e260d9e420..37d3a2477c17 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -132,7 +132,7 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry, goto out_err; } - inode->i_state = 0; + inode_state_assign_raw(inode, 0); inode->i_mode = *mode; err = ceph_security_init_secctx(dentry, *mode, as_ctx); @@ -201,7 +201,7 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino, doutc(cl, "on %llx=%llx.%llx got %p new %d\n", ceph_present_inode(inode), ceph_vinop(inode), inode, - !!(inode->i_state & I_NEW)); + !!(inode_state_read_once(inode) & I_NEW)); return inode; } @@ -228,7 +228,7 @@ struct inode *ceph_get_snapdir(struct inode *parent) goto err; } - if (!(inode->i_state & I_NEW) && !S_ISDIR(inode->i_mode)) { + if (!(inode_state_read_once(inode) & I_NEW) && !S_ISDIR(inode->i_mode)) { pr_warn_once_client(cl, "bad snapdir inode type (mode=0%o)\n", inode->i_mode); goto err; @@ -261,7 +261,7 @@ struct inode *ceph_get_snapdir(struct inode *parent) } } #endif - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { inode->i_op = &ceph_snapdir_iops; inode->i_fop = &ceph_snapdir_fops; ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */ @@ -270,7 +270,7 @@ struct inode *ceph_get_snapdir(struct inode *parent) return inode; err: - if ((inode->i_state & I_NEW)) + if ((inode_state_read_once(inode) & I_NEW)) discard_new_inode(inode); else iput(inode); @@ -744,7 +744,7 @@ void ceph_evict_inode(struct inode *inode) netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); - if (inode->i_state & I_PINNING_NETFS_WB) + if (inode_state_read_once(inode) & I_PINNING_NETFS_WB) ceph_fscache_unuse_cookie(inode, true); clear_inode(inode); @@ -1013,7 +1013,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page, le64_to_cpu(info->version), ci->i_version); /* Once I_NEW is cleared, we can't change type or dev numbers */ - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { inode->i_mode = mode; } else { if (inode_wrong_type(inode, mode)) { @@ -1090,7 +1090,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page, #ifdef CONFIG_FS_ENCRYPTION if (iinfo->fscrypt_auth_len && - ((inode->i_state & I_NEW) || (ci->fscrypt_auth_len == 0))) { + ((inode_state_read_once(inode) & I_NEW) || (ci->fscrypt_auth_len == 0))) { kfree(ci->fscrypt_auth); ci->fscrypt_auth_len = iinfo->fscrypt_auth_len; ci->fscrypt_auth = iinfo->fscrypt_auth; @@ -1692,13 +1692,13 @@ retry_lookup: pr_err_client(cl, "badness %p %llx.%llx\n", in, ceph_vinop(in)); req->r_target_inode = NULL; - if (in->i_state & I_NEW) + if (inode_state_read_once(in) & I_NEW) discard_new_inode(in); else iput(in); goto done; } - if (in->i_state & I_NEW) + if (inode_state_read_once(in) & I_NEW) unlock_new_inode(in); } @@ -1898,11 +1898,11 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req, pr_err_client(cl, "inode badness on %p got %d\n", in, rc); err = rc; - if (in->i_state & I_NEW) { + if (inode_state_read_once(in) & I_NEW) { ihold(in); discard_new_inode(in); } - } else if (in->i_state & I_NEW) { + } else if (inode_state_read_once(in) & I_NEW) { unlock_new_inode(in); } @@ -2114,7 +2114,7 @@ retry_lookup: pr_err_client(cl, "badness on %p %llx.%llx\n", in, ceph_vinop(in)); if (d_really_is_negative(dn)) { - if (in->i_state & I_NEW) { + if (inode_state_read_once(in) & I_NEW) { ihold(in); discard_new_inode(in); } @@ -2124,7 +2124,7 @@ retry_lookup: err = ret; goto next_item; } - if (in->i_state & I_NEW) + if (inode_state_read_once(in) & I_NEW) unlock_new_inode(in); if (d_really_is_negative(dn)) { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index ad0cf177e75a..f6bf24b5c683 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1149,7 +1149,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, const char *path = fsc->mount_options->server_path ? fsc->mount_options->server_path + 1 : ""; - err = __ceph_open_session(fsc->client, started); + err = __ceph_open_session(fsc->client); if (err < 0) goto out; diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c index 62a3d2565c26..70bb0579b40c 100644 --- a/fs/coda/cnode.c +++ b/fs/coda/cnode.c @@ -70,7 +70,7 @@ retry: if (!inode) return ERR_PTR(-ENOMEM); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { cii = ITOC(inode); /* we still need to set i_ino for things like stat(2) */ inode->i_ino = hash; @@ -148,7 +148,7 @@ struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb) /* we should never see newly created inodes because we intentionally * fail in the initialization callback */ - BUG_ON(inode->i_state & I_NEW); + BUG_ON(inode_state_read_once(inode) & I_NEW); return inode; } diff --git a/fs/coredump.c b/fs/coredump.c index 5c1c381ee380..fe4099e0530b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1036,7 +1036,7 @@ static bool coredump_pipe(struct core_name *cn, struct coredump_params *cprm, static bool coredump_write(struct core_name *cn, struct coredump_params *cprm, - struct linux_binfmt *binfmt) + const struct linux_binfmt *binfmt) { if (dump_interrupted()) @@ -1086,119 +1086,119 @@ static inline bool coredump_skip(const struct coredump_params *cprm, return false; } -void vfs_coredump(const kernel_siginfo_t *siginfo) +static void do_coredump(struct core_name *cn, struct coredump_params *cprm, + size_t **argv, int *argc, const struct linux_binfmt *binfmt) { - struct cred *cred __free(put_cred) = NULL; - size_t *argv __free(kfree) = NULL; - struct core_state core_state; - struct core_name cn; - struct mm_struct *mm = current->mm; - struct linux_binfmt *binfmt = mm->binfmt; - const struct cred *old_cred; - int argc = 0; - struct coredump_params cprm = { - .siginfo = siginfo, - .limit = rlimit(RLIMIT_CORE), - /* - * We must use the same mm->flags while dumping core to avoid - * inconsistency of bit flags, since this flag is not protected - * by any locks. - * - * Note that we only care about MMF_DUMP* flags. - */ - .mm_flags = __mm_flags_get_dumpable(mm), - .vma_meta = NULL, - .cpu = raw_smp_processor_id(), - }; - - audit_core_dumps(siginfo->si_signo); - - if (coredump_skip(&cprm, binfmt)) - return; - - cred = prepare_creds(); - if (!cred) - return; - /* - * We cannot trust fsuid as being the "true" uid of the process - * nor do we know its entire history. We only know it was tainted - * so we dump it as root in mode 2, and only into a controlled - * environment (pipe handler or fully qualified path). - */ - if (coredump_force_suid_safe(&cprm)) - cred->fsuid = GLOBAL_ROOT_UID; - - if (coredump_wait(siginfo->si_signo, &core_state) < 0) - return; - - old_cred = override_creds(cred); - - if (!coredump_parse(&cn, &cprm, &argv, &argc)) { + if (!coredump_parse(cn, cprm, argv, argc)) { coredump_report_failure("format_corename failed, aborting core"); - goto close_fail; + return; } - switch (cn.core_type) { + switch (cn->core_type) { case COREDUMP_FILE: - if (!coredump_file(&cn, &cprm, binfmt)) - goto close_fail; + if (!coredump_file(cn, cprm, binfmt)) + return; break; case COREDUMP_PIPE: - if (!coredump_pipe(&cn, &cprm, argv, argc)) - goto close_fail; + if (!coredump_pipe(cn, cprm, *argv, *argc)) + return; break; case COREDUMP_SOCK_REQ: fallthrough; case COREDUMP_SOCK: - if (!coredump_socket(&cn, &cprm)) - goto close_fail; + if (!coredump_socket(cn, cprm)) + return; break; default: WARN_ON_ONCE(true); - goto close_fail; + return; } /* Don't even generate the coredump. */ - if (cn.mask & COREDUMP_REJECT) - goto close_fail; + if (cn->mask & COREDUMP_REJECT) + return; /* get us an unshared descriptor table; almost always a no-op */ /* The cell spufs coredump code reads the file descriptor tables */ if (unshare_files()) - goto close_fail; + return; - if ((cn.mask & COREDUMP_KERNEL) && !coredump_write(&cn, &cprm, binfmt)) - goto close_fail; + if ((cn->mask & COREDUMP_KERNEL) && !coredump_write(cn, cprm, binfmt)) + return; - coredump_sock_shutdown(cprm.file); + coredump_sock_shutdown(cprm->file); /* Let the parent know that a coredump was generated. */ - if (cn.mask & COREDUMP_USERSPACE) - cn.core_dumped = true; + if (cn->mask & COREDUMP_USERSPACE) + cn->core_dumped = true; /* * When core_pipe_limit is set we wait for the coredump server * or usermodehelper to finish before exiting so it can e.g., * inspect /proc/<pid>. */ - if (cn.mask & COREDUMP_WAIT) { - switch (cn.core_type) { + if (cn->mask & COREDUMP_WAIT) { + switch (cn->core_type) { case COREDUMP_PIPE: - wait_for_dump_helpers(cprm.file); + wait_for_dump_helpers(cprm->file); break; case COREDUMP_SOCK_REQ: fallthrough; case COREDUMP_SOCK: - coredump_sock_wait(cprm.file); + coredump_sock_wait(cprm->file); break; default: break; } } +} + +void vfs_coredump(const kernel_siginfo_t *siginfo) +{ + size_t *argv __free(kfree) = NULL; + struct core_state core_state; + struct core_name cn; + const struct mm_struct *mm = current->mm; + const struct linux_binfmt *binfmt = mm->binfmt; + int argc = 0; + struct coredump_params cprm = { + .siginfo = siginfo, + .limit = rlimit(RLIMIT_CORE), + /* + * We must use the same mm->flags while dumping core to avoid + * inconsistency of bit flags, since this flag is not protected + * by any locks. + * + * Note that we only care about MMF_DUMP* flags. + */ + .mm_flags = __mm_flags_get_dumpable(mm), + .vma_meta = NULL, + .cpu = raw_smp_processor_id(), + }; + + audit_core_dumps(siginfo->si_signo); + + if (coredump_skip(&cprm, binfmt)) + return; + + CLASS(prepare_creds, cred)(); + if (!cred) + return; + /* + * We cannot trust fsuid as being the "true" uid of the process + * nor do we know its entire history. We only know it was tainted + * so we dump it as root in mode 2, and only into a controlled + * environment (pipe handler or fully qualified path). + */ + if (coredump_force_suid_safe(&cprm)) + cred->fsuid = GLOBAL_ROOT_UID; + + if (coredump_wait(siginfo->si_signo, &core_state) < 0) + return; -close_fail: + scoped_with_creds(cred) + do_coredump(&cn, &cprm, &argv, &argc, binfmt); coredump_cleanup(&cn, &cprm); - revert_creds(old_cred); return; } diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index ca54bf24b719..e54ebe402df7 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -95,7 +95,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb, inode = iget_locked(sb, cramino(cramfs_inode, offset)); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; switch (cramfs_inode->mode & S_IFMT) { diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 3adbd7167055..5e939ea3ac28 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -945,7 +945,7 @@ static void evict_dentries_for_decrypted_inodes(struct fscrypt_master_key *mk) list_for_each_entry(ci, &mk->mk_decrypted_inodes, ci_master_key_link) { inode = ci->ci_inode; spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) { + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); continue; } diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 4bd3918f50e3..40fa05688d3a 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -834,7 +834,7 @@ int fscrypt_drop_inode(struct inode *inode) * userspace is still using the files, inodes can be dirtied between * then and now. We mustn't lose any writes, so skip dirty inodes here. */ - if (inode->i_state & I_DIRTY_ALL) + if (inode_state_read(inode) & I_DIRTY_ALL) return 0; /* @@ -1507,7 +1507,7 @@ static int dax_zero_iter(struct iomap_iter *iter, bool *did_zero) /* already zeroed? we're done. */ if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, length); /* * invalidate the pages whose sharing state is to be changed @@ -1536,10 +1536,10 @@ static int dax_zero_iter(struct iomap_iter *iter, bool *did_zero) if (ret < 0) return ret; - ret = iomap_iter_advance(iter, &length); + ret = iomap_iter_advance(iter, length); if (ret) return ret; - } while (length > 0); + } while ((length = iomap_length(iter)) > 0); if (did_zero) *did_zero = true; @@ -1597,7 +1597,7 @@ static int dax_iomap_iter(struct iomap_iter *iomi, struct iov_iter *iter) if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) { done = iov_iter_zero(min(length, end - pos), iter); - return iomap_iter_advance(iomi, &done); + return iomap_iter_advance(iomi, done); } } @@ -1681,12 +1681,12 @@ static int dax_iomap_iter(struct iomap_iter *iomi, struct iov_iter *iter) xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr, map_len, iter); - length = xfer; - ret = iomap_iter_advance(iomi, &length); + ret = iomap_iter_advance(iomi, xfer); if (!ret && xfer == 0) ret = -EFAULT; if (xfer < map_len) break; + length = iomap_length(iomi); } dax_read_unlock(id); @@ -1919,10 +1919,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, unsigned long *pfnp, ret |= VM_FAULT_MAJOR; } - if (!(ret & VM_FAULT_ERROR)) { - u64 length = PAGE_SIZE; - iter.status = iomap_iter_advance(&iter, &length); - } + if (!(ret & VM_FAULT_ERROR)) + iter.status = iomap_iter_advance(&iter, PAGE_SIZE); } if (iomap_errp) @@ -2034,10 +2032,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, unsigned long *pfnp, continue; /* actually breaks out of the loop */ ret = dax_fault_iter(vmf, &iter, pfnp, &xas, &entry, true); - if (ret != VM_FAULT_FALLBACK) { - u64 length = PMD_SIZE; - iter.status = iomap_iter_advance(&iter, &length); - } + if (ret != VM_FAULT_FALLBACK) + iter.status = iomap_iter_advance(&iter, PMD_SIZE); } unlock_entry: @@ -2163,7 +2159,6 @@ static int dax_range_compare_iter(struct iomap_iter *it_src, const struct iomap *smap = &it_src->iomap; const struct iomap *dmap = &it_dest->iomap; loff_t pos1 = it_src->pos, pos2 = it_dest->pos; - u64 dest_len; void *saddr, *daddr; int id, ret; @@ -2196,10 +2191,9 @@ static int dax_range_compare_iter(struct iomap_iter *it_src, dax_read_unlock(id); advance: - dest_len = len; - ret = iomap_iter_advance(it_src, &len); + ret = iomap_iter_advance(it_src, len); if (!ret) - ret = iomap_iter_advance(it_dest, &dest_len); + ret = iomap_iter_advance(it_dest, len); return ret; out_unlock: diff --git a/fs/dcache.c b/fs/dcache.c index 035cccbc9276..9143fd502def 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -86,7 +86,8 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); -static struct kmem_cache *dentry_cache __ro_after_init; +static struct kmem_cache *__dentry_cache __ro_after_init; +#define dentry_cache runtime_const_ptr(__dentry_cache) const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); @@ -794,7 +795,7 @@ void d_mark_dontcache(struct inode *inode) de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } - inode->i_state |= I_DONTCACHE; + inode_state_set(inode, I_DONTCACHE); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); @@ -1073,7 +1074,7 @@ struct dentry *d_find_alias_rcu(struct inode *inode) spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left - if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { + if (likely(!(inode_state_read(inode) & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_u.d_alias); } else { @@ -1980,14 +1981,8 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode) security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); - WARN_ON(!(inode->i_state & I_NEW)); - inode->i_state &= ~I_NEW & ~I_CREATING; - /* - * Pairs with the barrier in prepare_to_wait_event() to make sure - * ___wait_var_event() either sees the bit cleared or - * waitqueue_active() check in wake_up_var() sees the waiter. - */ - smp_mb(); + WARN_ON(!(inode_state_read(inode) & I_NEW)); + inode_state_clear(inode, I_NEW | I_CREATING); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } @@ -2306,11 +2301,20 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent, seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; - if (d_unhashed(dentry)) - continue; if (dentry->d_name.hash_len != hashlen) continue; - if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) + if (unlikely(dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0)) + continue; + /* + * Check for the dentry being unhashed. + * + * As tempting as it is, we *can't* skip it because of a race window + * between us finding the dentry before it gets unhashed and loading + * the sequence counter after unhashing is finished. + * + * We can at least predict on it. + */ + if (unlikely(d_unhashed(dentry))) continue; *seqp = seq; return dentry; @@ -3222,9 +3226,10 @@ static void __init dcache_init(void) * but it is probably not worth it because of the cache nature * of the dcache. */ - dentry_cache = KMEM_CACHE_USERCOPY(dentry, + __dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, d_shortname.string); + runtime_const_init(ptr, __dentry_cache); /* Hash may have been set up in dcache_init_early */ if (!hashdist) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 661a99a7dfbe..532bd7c46baf 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -403,7 +403,7 @@ static struct dentry *debugfs_start_creating(const char *name, return dentry; } -static struct dentry *failed_creating(struct dentry *dentry) +static struct dentry *debugfs_failed_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); dput(dentry); @@ -411,7 +411,7 @@ static struct dentry *failed_creating(struct dentry *dentry) return ERR_PTR(-ENOMEM); } -static struct dentry *end_creating(struct dentry *dentry) +static struct dentry *debugfs_end_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); return dentry; @@ -435,7 +435,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { - failed_creating(dentry); + debugfs_failed_creating(dentry); return ERR_PTR(-EPERM); } @@ -443,7 +443,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, if (unlikely(!inode)) { pr_err("out of free dentries, can not create file '%s'\n", name); - return failed_creating(dentry); + return debugfs_failed_creating(dentry); } inode->i_mode = mode; @@ -458,7 +458,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, d_instantiate(dentry, inode); fsnotify_create(d_inode(dentry->d_parent), dentry); - return end_creating(dentry); + return debugfs_end_creating(dentry); } struct dentry *debugfs_create_file_full(const char *name, umode_t mode, @@ -585,7 +585,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { - failed_creating(dentry); + debugfs_failed_creating(dentry); return ERR_PTR(-EPERM); } @@ -593,7 +593,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) if (unlikely(!inode)) { pr_err("out of free dentries, can not create directory '%s'\n", name); - return failed_creating(dentry); + return debugfs_failed_creating(dentry); } inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; @@ -605,7 +605,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); - return end_creating(dentry); + return debugfs_end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_dir); @@ -632,7 +632,7 @@ struct dentry *debugfs_create_automount(const char *name, return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { - failed_creating(dentry); + debugfs_failed_creating(dentry); return ERR_PTR(-EPERM); } @@ -640,7 +640,7 @@ struct dentry *debugfs_create_automount(const char *name, if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); - return failed_creating(dentry); + return debugfs_failed_creating(dentry); } make_empty_dir_inode(inode); @@ -652,7 +652,7 @@ struct dentry *debugfs_create_automount(const char *name, d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); - return end_creating(dentry); + return debugfs_end_creating(dentry); } EXPORT_SYMBOL(debugfs_create_automount); @@ -699,13 +699,13 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, pr_err("out of free dentries, can not create symlink '%s'\n", name); kfree(link); - return failed_creating(dentry); + return debugfs_failed_creating(dentry); } inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_op = &debugfs_symlink_inode_operations; inode->i_link = link; d_instantiate(dentry, inode); - return end_creating(dentry); + return debugfs_end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_symlink); @@ -842,7 +842,8 @@ int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, . int error = 0; const char *new_name; struct name_snapshot old_name; - struct dentry *parent, *target; + struct dentry *target; + struct renamedata rd = {}; struct inode *dir; va_list ap; @@ -855,36 +856,31 @@ int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, . if (!new_name) return -ENOMEM; - parent = dget_parent(dentry); - dir = d_inode(parent); - inode_lock(dir); + rd.old_parent = dget_parent(dentry); + rd.new_parent = rd.old_parent; + rd.flags = RENAME_NOREPLACE; + target = lookup_noperm_unlocked(&QSTR(new_name), rd.new_parent); + if (IS_ERR(target)) + return PTR_ERR(target); - take_dentry_name_snapshot(&old_name, dentry); - - if (WARN_ON_ONCE(dentry->d_parent != parent)) { - error = -EINVAL; - goto out; - } - if (strcmp(old_name.name.name, new_name) == 0) - goto out; - target = lookup_noperm(&QSTR(new_name), parent); - if (IS_ERR(target)) { - error = PTR_ERR(target); - goto out; - } - if (d_really_is_positive(target)) { - dput(target); - error = -EINVAL; + error = start_renaming_two_dentries(&rd, dentry, target); + if (error) { + if (error == -EEXIST && target == dentry) + /* it isn't an error to rename a thing to itself */ + error = 0; goto out; } - simple_rename_timestamp(dir, dentry, dir, target); - d_move(dentry, target); - dput(target); + + dir = d_inode(rd.old_parent); + take_dentry_name_snapshot(&old_name, dentry); + simple_rename_timestamp(dir, dentry, dir, rd.new_dentry); + d_move(dentry, rd.new_dentry); fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry); -out: release_dentry_name_snapshot(&old_name); - inode_unlock(dir); - dput(parent); + end_renaming(&rd); +out: + dput(rd.old_parent); + dput(target); kfree_const(new_name); return error; } diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 019a8b4eaaf9..49f56a598ecb 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -28,7 +28,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) * inodes without pages but we deliberately won't in case * we need to reschedule to avoid softlockups. */ - if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || + if ((inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) || (mapping_empty(inode->i_mapping) && !need_resched())) { spin_unlock(&inode->i_lock); continue; diff --git a/fs/ecryptfs/Kconfig b/fs/ecryptfs/Kconfig index 1bdeaa6d5790..c2f4fb41b4e6 100644 --- a/fs/ecryptfs/Kconfig +++ b/fs/ecryptfs/Kconfig @@ -4,7 +4,7 @@ config ECRYPT_FS depends on KEYS && CRYPTO && (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n) select CRYPTO_ECB select CRYPTO_CBC - select CRYPTO_MD5 + select CRYPTO_LIB_MD5 help Encrypted filesystem that operates on the VFS layer. See <file:Documentation/filesystems/ecryptfs.rst> to learn more about diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 69536cacdea8..260f8a4938b0 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -9,7 +9,6 @@ * Michael C. Thompson <mcthomps@us.ibm.com> */ -#include <crypto/hash.h> #include <crypto/skcipher.h> #include <linux/fs.h> #include <linux/mount.h> @@ -48,32 +47,6 @@ void ecryptfs_from_hex(char *dst, char *src, int dst_size) } } -/** - * ecryptfs_calculate_md5 - calculates the md5 of @src - * @dst: Pointer to 16 bytes of allocated memory - * @crypt_stat: Pointer to crypt_stat struct for the current inode - * @src: Data to be md5'd - * @len: Length of @src - * - * Uses the allocated crypto context that crypt_stat references to - * generate the MD5 sum of the contents of src. - */ -static int ecryptfs_calculate_md5(char *dst, - struct ecryptfs_crypt_stat *crypt_stat, - char *src, int len) -{ - int rc = crypto_shash_tfm_digest(crypt_stat->hash_tfm, src, len, dst); - - if (rc) { - printk(KERN_ERR - "%s: Error computing crypto hash; rc = [%d]\n", - __func__, rc); - goto out; - } -out: - return rc; -} - static int ecryptfs_crypto_api_algify_cipher_name(char **algified_name, char *cipher_name, char *chaining_modifier) @@ -104,13 +77,10 @@ out: * * Generate the initialization vector from the given root IV and page * offset. - * - * Returns zero on success; non-zero on error. */ -int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat, - loff_t offset) +void ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat, + loff_t offset) { - int rc = 0; char dst[MD5_DIGEST_SIZE]; char src[ECRYPTFS_MAX_IV_BYTES + 16]; @@ -129,20 +99,12 @@ int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat, ecryptfs_printk(KERN_DEBUG, "source:\n"); ecryptfs_dump_hex(src, (crypt_stat->iv_bytes + 16)); } - rc = ecryptfs_calculate_md5(dst, crypt_stat, src, - (crypt_stat->iv_bytes + 16)); - if (rc) { - ecryptfs_printk(KERN_WARNING, "Error attempting to compute " - "MD5 while generating IV for a page\n"); - goto out; - } + md5(src, crypt_stat->iv_bytes + 16, dst); memcpy(iv, dst, crypt_stat->iv_bytes); if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "derived iv:\n"); ecryptfs_dump_hex(iv, crypt_stat->iv_bytes); } -out: - return rc; } /** @@ -151,29 +113,14 @@ out: * * Initialize the crypt_stat structure. */ -int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat) +void ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat) { - struct crypto_shash *tfm; - int rc; - - tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0); - if (IS_ERR(tfm)) { - rc = PTR_ERR(tfm); - ecryptfs_printk(KERN_ERR, "Error attempting to " - "allocate crypto context; rc = [%d]\n", - rc); - return rc; - } - memset((void *)crypt_stat, 0, sizeof(struct ecryptfs_crypt_stat)); INIT_LIST_HEAD(&crypt_stat->keysig_list); mutex_init(&crypt_stat->keysig_list_mutex); mutex_init(&crypt_stat->cs_mutex); mutex_init(&crypt_stat->cs_tfm_mutex); - crypt_stat->hash_tfm = tfm; crypt_stat->flags |= ECRYPTFS_STRUCT_INITIALIZED; - - return 0; } /** @@ -187,7 +134,6 @@ void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat) struct ecryptfs_key_sig *key_sig, *key_sig_tmp; crypto_free_skcipher(crypt_stat->tfm); - crypto_free_shash(crypt_stat->hash_tfm); list_for_each_entry_safe(key_sig, key_sig_tmp, &crypt_stat->keysig_list, crypt_stat_list) { list_del(&key_sig->crypt_stat_list); @@ -361,14 +307,7 @@ static int crypt_extent(struct ecryptfs_crypt_stat *crypt_stat, int rc; extent_base = (((loff_t)page_index) * (PAGE_SIZE / extent_size)); - rc = ecryptfs_derive_iv(extent_iv, crypt_stat, - (extent_base + extent_offset)); - if (rc) { - ecryptfs_printk(KERN_ERR, "Error attempting to derive IV for " - "extent [0x%.16llx]; rc = [%d]\n", - (unsigned long long)(extent_base + extent_offset), rc); - goto out; - } + ecryptfs_derive_iv(extent_iv, crypt_stat, extent_base + extent_offset); sg_init_table(&src_sg, 1); sg_init_table(&dst_sg, 1); @@ -609,31 +548,20 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat) */ int ecryptfs_compute_root_iv(struct ecryptfs_crypt_stat *crypt_stat) { - int rc = 0; char dst[MD5_DIGEST_SIZE]; BUG_ON(crypt_stat->iv_bytes > MD5_DIGEST_SIZE); BUG_ON(crypt_stat->iv_bytes <= 0); if (!(crypt_stat->flags & ECRYPTFS_KEY_VALID)) { - rc = -EINVAL; ecryptfs_printk(KERN_WARNING, "Session key not valid; " "cannot generate root IV\n"); - goto out; - } - rc = ecryptfs_calculate_md5(dst, crypt_stat, crypt_stat->key, - crypt_stat->key_size); - if (rc) { - ecryptfs_printk(KERN_WARNING, "Error attempting to compute " - "MD5 while generating root IV\n"); - goto out; - } - memcpy(crypt_stat->root_iv, dst, crypt_stat->iv_bytes); -out: - if (rc) { memset(crypt_stat->root_iv, 0, crypt_stat->iv_bytes); crypt_stat->flags |= ECRYPTFS_SECURITY_WARNING; + return -EINVAL; } - return rc; + md5(crypt_stat->key, crypt_stat->key_size, dst); + memcpy(crypt_stat->root_iv, dst, crypt_stat->iv_bytes); + return 0; } static void ecryptfs_generate_new_key(struct ecryptfs_crypt_stat *crypt_stat) diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 9e6ab0b41337..62a2ea7f59ed 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -14,6 +14,7 @@ #ifndef ECRYPTFS_KERNEL_H #define ECRYPTFS_KERNEL_H +#include <crypto/md5.h> #include <crypto/skcipher.h> #include <keys/user-type.h> #include <keys/encrypted-type.h> @@ -137,8 +138,6 @@ ecryptfs_get_key_payload_data(struct key *key) + MAGIC_ECRYPTFS_MARKER_SIZE_BYTES) #define ECRYPTFS_DEFAULT_CIPHER "aes" #define ECRYPTFS_DEFAULT_KEY_BYTES 16 -#define ECRYPTFS_DEFAULT_HASH "md5" -#define ECRYPTFS_TAG_70_DIGEST ECRYPTFS_DEFAULT_HASH #define ECRYPTFS_TAG_1_PACKET_TYPE 0x01 #define ECRYPTFS_TAG_3_PACKET_TYPE 0x8C #define ECRYPTFS_TAG_11_PACKET_TYPE 0xED @@ -163,8 +162,6 @@ ecryptfs_get_key_payload_data(struct key *key) * ECRYPTFS_MAX_IV_BYTES */ #define ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES 16 #define ECRYPTFS_NON_NULL 0x42 /* A reasonable substitute for NULL */ -#define MD5_DIGEST_SIZE 16 -#define ECRYPTFS_TAG_70_DIGEST_SIZE MD5_DIGEST_SIZE #define ECRYPTFS_TAG_70_MIN_METADATA_SIZE (1 + ECRYPTFS_MIN_PKT_LEN_SIZE \ + ECRYPTFS_SIG_SIZE + 1 + 1) #define ECRYPTFS_TAG_70_MAX_METADATA_SIZE (1 + ECRYPTFS_MAX_PKT_LEN_SIZE \ @@ -237,8 +234,6 @@ struct ecryptfs_crypt_stat { unsigned int extent_mask; struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct crypto_skcipher *tfm; - struct crypto_shash *hash_tfm; /* Crypto context for generating - * the initialization vectors */ unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1]; unsigned char key[ECRYPTFS_MAX_KEY_BYTES]; unsigned char root_iv[ECRYPTFS_MAX_IV_BYTES]; @@ -558,7 +553,7 @@ int virt_to_scatterlist(const void *addr, int size, struct scatterlist *sg, int sg_size); int ecryptfs_compute_root_iv(struct ecryptfs_crypt_stat *crypt_stat); void ecryptfs_rotate_iv(unsigned char *iv); -int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat); +void ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat); void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat); void ecryptfs_destroy_mount_crypt_stat( struct ecryptfs_mount_crypt_stat *mount_crypt_stat); @@ -693,8 +688,8 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size, char *data, size_t max_packet_size); int ecryptfs_set_f_namelen(long *namelen, long lower_namelen, struct ecryptfs_mount_crypt_stat *mount_crypt_stat); -int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat, - loff_t offset); +void ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat, + loff_t offset); extern const struct xattr_handler * const ecryptfs_xattr_handlers[]; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index ed1394da8d6b..3978248247dc 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -24,18 +24,26 @@ #include <linux/unaligned.h> #include "ecryptfs_kernel.h" -static int lock_parent(struct dentry *dentry, - struct dentry **lower_dentry, - struct inode **lower_dir) +static struct dentry *ecryptfs_start_creating_dentry(struct dentry *dentry) { - struct dentry *lower_dir_dentry; + struct dentry *parent = dget_parent(dentry); + struct dentry *ret; - lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent); - *lower_dir = d_inode(lower_dir_dentry); - *lower_dentry = ecryptfs_dentry_to_lower(dentry); + ret = start_creating_dentry(ecryptfs_dentry_to_lower(parent), + ecryptfs_dentry_to_lower(dentry)); + dput(parent); + return ret; +} - inode_lock_nested(*lower_dir, I_MUTEX_PARENT); - return (*lower_dentry)->d_parent == lower_dir_dentry ? 0 : -EINVAL; +static struct dentry *ecryptfs_start_removing_dentry(struct dentry *dentry) +{ + struct dentry *parent = dget_parent(dentry); + struct dentry *ret; + + ret = start_removing_dentry(ecryptfs_dentry_to_lower(parent), + ecryptfs_dentry_to_lower(dentry)); + dput(parent); + return ret; } static int ecryptfs_inode_test(struct inode *inode, void *lower_inode) @@ -95,7 +103,7 @@ static struct inode *__ecryptfs_get_inode(struct inode *lower_inode, iput(lower_inode); return ERR_PTR(-EACCES); } - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) iput(lower_inode); return inode; @@ -106,7 +114,7 @@ struct inode *ecryptfs_get_inode(struct inode *lower_inode, { struct inode *inode = __ecryptfs_get_inode(lower_inode, sb); - if (!IS_ERR(inode) && (inode->i_state & I_NEW)) + if (!IS_ERR(inode) && (inode_state_read_once(inode) & I_NEW)) unlock_new_inode(inode); return inode; @@ -141,15 +149,12 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry, struct inode *lower_dir; int rc; - rc = lock_parent(dentry, &lower_dentry, &lower_dir); - dget(lower_dentry); // don't even try to make the lower negative - if (!rc) { - if (d_unhashed(lower_dentry)) - rc = -EINVAL; - else - rc = vfs_unlink(&nop_mnt_idmap, lower_dir, lower_dentry, - NULL); - } + lower_dentry = ecryptfs_start_removing_dentry(dentry); + if (IS_ERR(lower_dentry)) + return PTR_ERR(lower_dentry); + + lower_dir = lower_dentry->d_parent->d_inode; + rc = vfs_unlink(&nop_mnt_idmap, lower_dir, lower_dentry, NULL); if (rc) { printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc); goto out_unlock; @@ -158,8 +163,7 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry, set_nlink(inode, ecryptfs_inode_to_lower(inode)->i_nlink); inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); out_unlock: - dput(lower_dentry); - inode_unlock(lower_dir); + end_removing(lower_dentry); if (!rc) d_drop(dentry); return rc; @@ -186,10 +190,11 @@ ecryptfs_do_create(struct inode *directory_inode, struct inode *lower_dir; struct inode *inode; - rc = lock_parent(ecryptfs_dentry, &lower_dentry, &lower_dir); - if (!rc) - rc = vfs_create(&nop_mnt_idmap, lower_dir, - lower_dentry, mode, true); + lower_dentry = ecryptfs_start_creating_dentry(ecryptfs_dentry); + if (IS_ERR(lower_dentry)) + return ERR_CAST(lower_dentry); + lower_dir = lower_dentry->d_parent->d_inode; + rc = vfs_create(&nop_mnt_idmap, lower_dentry, mode, NULL); if (rc) { printk(KERN_ERR "%s: Failure to create dentry in lower fs; " "rc = [%d]\n", __func__, rc); @@ -205,7 +210,7 @@ ecryptfs_do_create(struct inode *directory_inode, fsstack_copy_attr_times(directory_inode, lower_dir); fsstack_copy_inode_size(directory_inode, lower_dir); out_lock: - inode_unlock(lower_dir); + end_creating(lower_dentry); return inode; } @@ -364,7 +369,7 @@ static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry, } } - if (inode->i_state & I_NEW) + if (inode_state_read_once(inode) & I_NEW) unlock_new_inode(inode); return d_splice_alias(inode, dentry); } @@ -433,10 +438,12 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir, file_size_save = i_size_read(d_inode(old_dentry)); lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry); - rc = lock_parent(new_dentry, &lower_new_dentry, &lower_dir); - if (!rc) - rc = vfs_link(lower_old_dentry, &nop_mnt_idmap, lower_dir, - lower_new_dentry, NULL); + lower_new_dentry = ecryptfs_start_creating_dentry(new_dentry); + if (IS_ERR(lower_new_dentry)) + return PTR_ERR(lower_new_dentry); + lower_dir = lower_new_dentry->d_parent->d_inode; + rc = vfs_link(lower_old_dentry, &nop_mnt_idmap, lower_dir, + lower_new_dentry, NULL); if (rc || d_really_is_negative(lower_new_dentry)) goto out_lock; rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb); @@ -448,7 +455,7 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir, ecryptfs_inode_to_lower(d_inode(old_dentry))->i_nlink); i_size_write(d_inode(new_dentry), file_size_save); out_lock: - inode_unlock(lower_dir); + end_creating(lower_new_dentry); return rc; } @@ -468,9 +475,11 @@ static int ecryptfs_symlink(struct mnt_idmap *idmap, size_t encoded_symlen; struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL; - rc = lock_parent(dentry, &lower_dentry, &lower_dir); - if (rc) - goto out_lock; + lower_dentry = ecryptfs_start_creating_dentry(dentry); + if (IS_ERR(lower_dentry)) + return PTR_ERR(lower_dentry); + lower_dir = lower_dentry->d_parent->d_inode; + mount_crypt_stat = &ecryptfs_superblock_to_private( dir->i_sb)->mount_crypt_stat; rc = ecryptfs_encrypt_and_encode_filename(&encoded_symname, @@ -480,7 +489,7 @@ static int ecryptfs_symlink(struct mnt_idmap *idmap, if (rc) goto out_lock; rc = vfs_symlink(&nop_mnt_idmap, lower_dir, lower_dentry, - encoded_symname); + encoded_symname, NULL); kfree(encoded_symname); if (rc || d_really_is_negative(lower_dentry)) goto out_lock; @@ -490,7 +499,7 @@ static int ecryptfs_symlink(struct mnt_idmap *idmap, fsstack_copy_attr_times(dir, lower_dir); fsstack_copy_inode_size(dir, lower_dir); out_lock: - inode_unlock(lower_dir); + end_creating(lower_dentry); if (d_really_is_negative(dentry)) d_drop(dentry); return rc; @@ -501,14 +510,16 @@ static struct dentry *ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, { int rc; struct dentry *lower_dentry; + struct dentry *lower_dir_dentry; struct inode *lower_dir; - rc = lock_parent(dentry, &lower_dentry, &lower_dir); - if (rc) - goto out; - + lower_dentry = ecryptfs_start_creating_dentry(dentry); + if (IS_ERR(lower_dentry)) + return lower_dentry; + lower_dir_dentry = dget(lower_dentry->d_parent); + lower_dir = lower_dir_dentry->d_inode; lower_dentry = vfs_mkdir(&nop_mnt_idmap, lower_dir, - lower_dentry, mode); + lower_dentry, mode, NULL); rc = PTR_ERR(lower_dentry); if (IS_ERR(lower_dentry)) goto out; @@ -522,7 +533,7 @@ static struct dentry *ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, fsstack_copy_inode_size(dir, lower_dir); set_nlink(dir, lower_dir->i_nlink); out: - inode_unlock(lower_dir); + end_creating(lower_dentry); if (d_really_is_negative(dentry)) d_drop(dentry); return ERR_PTR(rc); @@ -534,21 +545,18 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) struct inode *lower_dir; int rc; - rc = lock_parent(dentry, &lower_dentry, &lower_dir); - dget(lower_dentry); // don't even try to make the lower negative - if (!rc) { - if (d_unhashed(lower_dentry)) - rc = -EINVAL; - else - rc = vfs_rmdir(&nop_mnt_idmap, lower_dir, lower_dentry); - } + lower_dentry = ecryptfs_start_removing_dentry(dentry); + if (IS_ERR(lower_dentry)) + return PTR_ERR(lower_dentry); + lower_dir = lower_dentry->d_parent->d_inode; + + rc = vfs_rmdir(&nop_mnt_idmap, lower_dir, lower_dentry, NULL); if (!rc) { clear_nlink(d_inode(dentry)); fsstack_copy_attr_times(dir, lower_dir); set_nlink(dir, lower_dir->i_nlink); } - dput(lower_dentry); - inode_unlock(lower_dir); + end_removing(lower_dentry); if (!rc) d_drop(dentry); return rc; @@ -562,10 +570,12 @@ ecryptfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *lower_dentry; struct inode *lower_dir; - rc = lock_parent(dentry, &lower_dentry, &lower_dir); - if (!rc) - rc = vfs_mknod(&nop_mnt_idmap, lower_dir, - lower_dentry, mode, dev); + lower_dentry = ecryptfs_start_creating_dentry(dentry); + if (IS_ERR(lower_dentry)) + return PTR_ERR(lower_dentry); + lower_dir = lower_dentry->d_parent->d_inode; + + rc = vfs_mknod(&nop_mnt_idmap, lower_dir, lower_dentry, mode, dev, NULL); if (rc || d_really_is_negative(lower_dentry)) goto out; rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb); @@ -574,7 +584,7 @@ ecryptfs_mknod(struct mnt_idmap *idmap, struct inode *dir, fsstack_copy_attr_times(dir, lower_dir); fsstack_copy_inode_size(dir, lower_dir); out: - inode_unlock(lower_dir); + end_removing(lower_dentry); if (d_really_is_negative(dentry)) d_drop(dentry); return rc; @@ -590,7 +600,6 @@ ecryptfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *lower_new_dentry; struct dentry *lower_old_dir_dentry; struct dentry *lower_new_dir_dentry; - struct dentry *trap; struct inode *target_inode; struct renamedata rd = {}; @@ -605,31 +614,13 @@ ecryptfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, target_inode = d_inode(new_dentry); - trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); - if (IS_ERR(trap)) - return PTR_ERR(trap); - dget(lower_new_dentry); - rc = -EINVAL; - if (lower_old_dentry->d_parent != lower_old_dir_dentry) - goto out_lock; - if (lower_new_dentry->d_parent != lower_new_dir_dentry) - goto out_lock; - if (d_unhashed(lower_old_dentry) || d_unhashed(lower_new_dentry)) - goto out_lock; - /* source should not be ancestor of target */ - if (trap == lower_old_dentry) - goto out_lock; - /* target should not be ancestor of source */ - if (trap == lower_new_dentry) { - rc = -ENOTEMPTY; - goto out_lock; - } + rd.mnt_idmap = &nop_mnt_idmap; + rd.old_parent = lower_old_dir_dentry; + rd.new_parent = lower_new_dir_dentry; + rc = start_renaming_two_dentries(&rd, lower_old_dentry, lower_new_dentry); + if (rc) + return rc; - rd.mnt_idmap = &nop_mnt_idmap; - rd.old_parent = lower_old_dir_dentry; - rd.old_dentry = lower_old_dentry; - rd.new_parent = lower_new_dir_dentry; - rd.new_dentry = lower_new_dentry; rc = vfs_rename(&rd); if (rc) goto out_lock; @@ -640,8 +631,7 @@ ecryptfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (new_dir != old_dir) fsstack_copy_attr_all(old_dir, d_inode(lower_old_dir_dentry)); out_lock: - dput(lower_new_dentry); - unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + end_renaming(&rd); return rc; } @@ -903,11 +893,8 @@ static int ecryptfs_setattr(struct mnt_idmap *idmap, struct ecryptfs_crypt_stat *crypt_stat; crypt_stat = &ecryptfs_inode_to_private(d_inode(dentry))->crypt_stat; - if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) { - rc = ecryptfs_init_crypt_stat(crypt_stat); - if (rc) - return rc; - } + if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) + ecryptfs_init_crypt_stat(crypt_stat); inode = d_inode(dentry); lower_inode = ecryptfs_inode_to_lower(inode); lower_dentry = ecryptfs_dentry_to_lower(dentry); diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 7f9f68c00ef6..bbf8603242fa 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -11,7 +11,6 @@ * Trevor S. Highland <trevor.highland@gmail.com> */ -#include <crypto/hash.h> #include <crypto/skcipher.h> #include <linux/string.h> #include <linux/pagemap.h> @@ -601,10 +600,7 @@ struct ecryptfs_write_tag_70_packet_silly_stack { struct crypto_skcipher *skcipher_tfm; struct skcipher_request *skcipher_req; char iv[ECRYPTFS_MAX_IV_BYTES]; - char hash[ECRYPTFS_TAG_70_DIGEST_SIZE]; - char tmp_hash[ECRYPTFS_TAG_70_DIGEST_SIZE]; - struct crypto_shash *hash_tfm; - struct shash_desc *hash_desc; + char hash[MD5_DIGEST_SIZE]; }; /* @@ -741,51 +737,15 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes, "password tokens\n", __func__); goto out_free_unlock; } - s->hash_tfm = crypto_alloc_shash(ECRYPTFS_TAG_70_DIGEST, 0, 0); - if (IS_ERR(s->hash_tfm)) { - rc = PTR_ERR(s->hash_tfm); - printk(KERN_ERR "%s: Error attempting to " - "allocate hash crypto context; rc = [%d]\n", - __func__, rc); - goto out_free_unlock; - } - - s->hash_desc = kmalloc(sizeof(*s->hash_desc) + - crypto_shash_descsize(s->hash_tfm), GFP_KERNEL); - if (!s->hash_desc) { - rc = -ENOMEM; - goto out_release_free_unlock; - } - s->hash_desc->tfm = s->hash_tfm; - - rc = crypto_shash_digest(s->hash_desc, - (u8 *)s->auth_tok->token.password.session_key_encryption_key, - s->auth_tok->token.password.session_key_encryption_key_bytes, - s->hash); - if (rc) { - printk(KERN_ERR - "%s: Error computing crypto hash; rc = [%d]\n", - __func__, rc); - goto out_release_free_unlock; - } + md5(s->auth_tok->token.password.session_key_encryption_key, + s->auth_tok->token.password.session_key_encryption_key_bytes, + s->hash); for (s->j = 0; s->j < (s->num_rand_bytes - 1); s->j++) { s->block_aligned_filename[s->j] = - s->hash[(s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)]; - if ((s->j % ECRYPTFS_TAG_70_DIGEST_SIZE) - == (ECRYPTFS_TAG_70_DIGEST_SIZE - 1)) { - rc = crypto_shash_digest(s->hash_desc, (u8 *)s->hash, - ECRYPTFS_TAG_70_DIGEST_SIZE, - s->tmp_hash); - if (rc) { - printk(KERN_ERR - "%s: Error computing crypto hash; " - "rc = [%d]\n", __func__, rc); - goto out_release_free_unlock; - } - memcpy(s->hash, s->tmp_hash, - ECRYPTFS_TAG_70_DIGEST_SIZE); - } + s->hash[s->j % MD5_DIGEST_SIZE]; + if ((s->j % MD5_DIGEST_SIZE) == (MD5_DIGEST_SIZE - 1)) + md5(s->hash, MD5_DIGEST_SIZE, s->hash); if (s->block_aligned_filename[s->j] == '\0') s->block_aligned_filename[s->j] = ECRYPTFS_NON_NULL; } @@ -798,7 +758,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes, "convert filename memory to scatterlist; rc = [%d]. " "block_aligned_filename_size = [%zd]\n", __func__, rc, s->block_aligned_filename_size); - goto out_release_free_unlock; + goto out_free_unlock; } rc = virt_to_scatterlist(&dest[s->i], s->block_aligned_filename_size, s->dst_sg, 2); @@ -807,7 +767,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes, "convert encrypted filename memory to scatterlist; " "rc = [%d]. block_aligned_filename_size = [%zd]\n", __func__, rc, s->block_aligned_filename_size); - goto out_release_free_unlock; + goto out_free_unlock; } /* The characters in the first block effectively do the job * of the IV here, so we just use 0's for the IV. Note the @@ -825,7 +785,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes, rc, s->auth_tok->token.password.session_key_encryption_key, mount_crypt_stat->global_default_fn_cipher_key_bytes); - goto out_release_free_unlock; + goto out_free_unlock; } skcipher_request_set_crypt(s->skcipher_req, s->src_sg, s->dst_sg, s->block_aligned_filename_size, s->iv); @@ -833,13 +793,11 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes, if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt filename; " "rc = [%d]\n", __func__, rc); - goto out_release_free_unlock; + goto out_free_unlock; } s->i += s->block_aligned_filename_size; (*packet_size) = s->i; (*remaining_bytes) -= (*packet_size); -out_release_free_unlock: - crypto_free_shash(s->hash_tfm); out_free_unlock: kfree_sensitive(s->block_aligned_filename); out_unlock: @@ -850,7 +808,6 @@ out: key_put(auth_tok_key); } skcipher_request_free(s->skcipher_req); - kfree_sensitive(s->hash_desc); kfree(s); return rc; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 16ea14dd2c62..c12dc680f8fe 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -12,6 +12,7 @@ #include <linux/dcache.h> #include <linux/file.h> +#include <linux/fips.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/skbuff.h> @@ -454,6 +455,12 @@ static int ecryptfs_get_tree(struct fs_context *fc) goto out; } + if (fips_enabled) { + rc = -EINVAL; + err = "eCryptfs support is disabled due to FIPS"; + goto out; + } + s = sget_fc(fc, NULL, set_anon_super_fc); if (IS_ERR(s)) { rc = PTR_ERR(s); diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index e7b7f426fecf..3bc21d677564 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -41,10 +41,7 @@ static struct inode *ecryptfs_alloc_inode(struct super_block *sb) inode_info = alloc_inode_sb(sb, ecryptfs_inode_info_cache, GFP_KERNEL); if (unlikely(!inode_info)) goto out; - if (ecryptfs_init_crypt_stat(&inode_info->crypt_stat)) { - kmem_cache_free(ecryptfs_inode_info_cache, inode_info); - goto out; - } + ecryptfs_init_crypt_stat(&inode_info->crypt_stat); mutex_init(&inode_info->lower_file_mutex); atomic_set(&inode_info->lower_file_count, 0); inode_info->lower_file = NULL; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 1f4d8ce56667..6de97565d5f7 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -533,6 +533,7 @@ static struct file_system_type efivarfs_type = { .init_fs_context = efivarfs_init_fs_context, .kill_sb = efivarfs_kill_sb, .parameters = efivarfs_parameters, + .fs_flags = FS_POWER_FREEZE, }; static __init int efivarfs_init(void) diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 462619e59766..28407578f83a 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -62,7 +62,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) inode = iget_locked(super, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; in = INODE_INFO(inode); diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 8ca29962a3dd..bb13c4cb8455 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -371,7 +371,8 @@ static int erofs_read_folio(struct file *file, struct folio *folio) { trace_erofs_read_folio(folio, true); - return iomap_read_folio(folio, &erofs_iomap_ops); + iomap_bio_read_folio(folio, &erofs_iomap_ops); + return 0; } static void erofs_readahead(struct readahead_control *rac) @@ -379,7 +380,7 @@ static void erofs_readahead(struct readahead_control *rac) trace_erofs_readahead(rac->mapping->host, readahead_index(rac), readahead_count(rac), true); - return iomap_readahead(rac, &erofs_iomap_ops); + iomap_bio_readahead(rac, &erofs_iomap_ops); } static sector_t erofs_bmap(struct address_space *mapping, sector_t block) diff --git a/fs/erofs/decompressor_zstd.c b/fs/erofs/decompressor_zstd.c index b4bfe14229f9..e38d93bb2104 100644 --- a/fs/erofs/decompressor_zstd.c +++ b/fs/erofs/decompressor_zstd.c @@ -172,7 +172,6 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq, dctx.bounce = strm->bounce; do { - dctx.avail_out = out_buf.size - out_buf.pos; dctx.inbuf_sz = in_buf.size; dctx.inbuf_pos = in_buf.pos; err = z_erofs_stream_switch_bufs(&dctx, &out_buf.dst, @@ -188,14 +187,18 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq, in_buf.pos = dctx.inbuf_pos; zerr = zstd_decompress_stream(stream, &out_buf, &in_buf); - if (zstd_is_error(zerr) || (!zerr && rq->outputsize)) { + dctx.avail_out = out_buf.size - out_buf.pos; + if (zstd_is_error(zerr) || + ((rq->outputsize + dctx.avail_out) && (!zerr || (zerr > 0 && + !(rq->inputsize + in_buf.size - in_buf.pos))))) { erofs_err(sb, "failed to decompress in[%u] out[%u]: %s", rq->inputsize, rq->outputsize, - zerr ? zstd_get_error_name(zerr) : "unexpected end of stream"); + zstd_is_error(zerr) ? zstd_get_error_name(zerr) : + "unexpected end of stream"); err = -EFSCORRUPTED; break; } - } while (rq->outputsize || out_buf.pos < out_buf.size); + } while (rq->outputsize + dctx.avail_out); if (dctx.kout) kunmap_local(dctx.kout); diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index b7b3432a9882..d27938435b2f 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -47,7 +47,6 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret) static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) { - const struct cred *old_cred; struct iov_iter iter; int ret; @@ -61,9 +60,8 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); - old_cred = override_creds(rq->iocb.ki_filp->f_cred); - ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); - revert_creds(old_cred); + scoped_with_creds(rq->iocb.ki_filp->f_cred) + ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); if (ret != -EIOCBQUEUED) erofs_fileio_ki_complete(&rq->iocb, ret); } diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index cb780c095d28..bce98c845a18 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -295,7 +295,7 @@ struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid) if (!inode) return ERR_PTR(-ENOMEM); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { int err = erofs_fill_inode(inode); if (err) { diff --git a/fs/eventfd.c b/fs/eventfd.c index af42b2c7d235..3219e0d596fe 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -378,9 +378,7 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_fileget); static int do_eventfd(unsigned int count, int flags) { - struct eventfd_ctx *ctx; - struct file *file; - int fd; + struct eventfd_ctx *ctx __free(kfree) = NULL; /* Check the EFD_* constants for consistency. */ BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC); @@ -398,26 +396,19 @@ static int do_eventfd(unsigned int count, int flags) init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; - ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL); flags &= EFD_SHARED_FCNTL_FLAGS; flags |= O_RDWR; - fd = get_unused_fd_flags(flags); - if (fd < 0) - goto err; - - file = anon_inode_getfile_fmode("[eventfd]", &eventfd_fops, - ctx, flags, FMODE_NOWAIT); - if (IS_ERR(file)) { - put_unused_fd(fd); - fd = PTR_ERR(file); - goto err; - } - fd_install(fd, file); - return fd; -err: - eventfd_free_ctx(ctx); - return fd; + + FD_PREPARE(fdf, flags, + anon_inode_getfile_fmode("[eventfd]", &eventfd_fops, ctx, + flags, FMODE_NOWAIT)); + if (fdf.err) + return fdf.err; + + ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL); + retain_and_null_ptr(ctx); + return fd_publish(fdf); } SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index ee7c4b683ec3..6c36d9dc6926 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -2165,9 +2165,8 @@ static void clear_tfile_check_list(void) */ static int do_epoll_create(int flags) { - int error, fd; - struct eventpoll *ep = NULL; - struct file *file; + int error; + struct eventpoll *ep; /* Check the EPOLL_* constant for consistency. */ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); @@ -2184,26 +2183,15 @@ static int do_epoll_create(int flags) * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ - fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC)); - if (fd < 0) { - error = fd; - goto out_free_ep; - } - file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, - O_RDWR | (flags & O_CLOEXEC)); - if (IS_ERR(file)) { - error = PTR_ERR(file); - goto out_free_fd; + FD_PREPARE(fdf, O_RDWR | (flags & O_CLOEXEC), + anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, + O_RDWR | (flags & O_CLOEXEC))); + if (fdf.err) { + ep_clear_and_put(ep); + return fdf.err; } - ep->file = file; - fd_install(fd, file); - return fd; - -out_free_fd: - put_unused_fd(fd); -out_free_ep: - ep_clear_and_put(ep); - return error; + ep->file = fd_prepare_file(fdf); + return fd_publish(fdf); } SYSCALL_DEFINE1(epoll_create1, int, flags) diff --git a/fs/exec.c b/fs/exec.c index 4298e7e08d5d..9d5ebc9d15b0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1280,10 +1280,9 @@ int begin_new_exec(struct linux_binprm * bprm) /* Pass the opened binary to the interpreter. */ if (bprm->have_execfd) { - retval = get_unused_fd_flags(0); + retval = FD_ADD(0, bprm->executable); if (retval < 0) goto out_unlock; - fd_install(retval, bprm->executable); bprm->executable = NULL; bprm->execfd = retval; } @@ -1775,7 +1774,7 @@ out: force_fatal_sig(SIGSEGV); sched_mm_cid_after_execve(current); - rseq_set_notify_resume(current); + rseq_force_update(); current->in_execve = 0; return retval; diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 7f9592856bf7..74d451f732c7 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -433,7 +433,10 @@ static int exfat_read_boot_sector(struct super_block *sb) struct exfat_sb_info *sbi = EXFAT_SB(sb); /* set block size to read super block */ - sb_min_blocksize(sb, 512); + if (!sb_min_blocksize(sb, 512)) { + exfat_err(sb, "unable to set blocksize"); + return -EINVAL; + } /* read boot sector */ sbi->boot_bh = sb_bread(sb, 0); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index e10c376843d7..dbfe9098a124 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1398,7 +1398,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; ei = EXT2_I(inode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e99306a8f47c..78ea864fa8cd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -202,8 +202,7 @@ void ext4_evict_inode(struct inode *inode) * the inode. Flush worker is ignoring it because of I_FREEING flag but * we still need to remove the inode from the writeback lists. */ - if (!list_empty_careful(&inode->i_io_list)) - inode_io_list_del(inode); + inode_io_list_del(inode); /* * Protect us against freezing - iput() caller didn't have to have any @@ -425,7 +424,7 @@ void ext4_check_map_extents_env(struct inode *inode) if (!S_ISREG(inode->i_mode) || IS_NOQUOTA(inode) || IS_VERITY(inode) || is_special_ino(inode->i_sb, inode->i_ino) || - (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) || + (inode_state_read_once(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) || ext4_verity_in_progress(inode)) return; @@ -1319,8 +1318,8 @@ retry_grab: if (IS_ERR(folio)) return PTR_ERR(folio); - if (pos + len > folio_pos(folio) + folio_size(folio)) - len = folio_pos(folio) + folio_size(folio) - pos; + if (len > folio_next_pos(folio) - pos) + len = folio_next_pos(folio) - pos; from = offset_in_folio(folio, pos); to = from + len; @@ -2619,10 +2618,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) handle_t *handle = NULL; int bpp = ext4_journal_blocks_per_folio(mpd->inode); - if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages) - tag = PAGECACHE_TAG_TOWRITE; - else - tag = PAGECACHE_TAG_DIRTY; + tag = wbc_to_tag(mpd->wbc); mpd->map.m_len = 0; mpd->next_pos = mpd->start_pos; @@ -2704,7 +2700,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) if (mpd->map.m_len == 0) mpd->start_pos = folio_pos(folio); - mpd->next_pos = folio_pos(folio) + folio_size(folio); + mpd->next_pos = folio_next_pos(folio); /* * Writeout when we cannot modify metadata is simple. * Just submit the page. For data=journal mode we @@ -3146,8 +3142,8 @@ retry: if (IS_ERR(folio)) return PTR_ERR(folio); - if (pos + len > folio_pos(folio) + folio_size(folio)) - len = folio_pos(folio) + folio_size(folio) - pos; + if (len > folio_next_pos(folio) - pos) + len = folio_next_pos(folio) - pos; ret = ext4_block_write_begin(NULL, folio, pos, len, ext4_da_get_block_prep); @@ -3473,7 +3469,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) /* Any metadata buffers to write? */ if (!list_empty(&inode->i_mapping->i_private_list)) return true; - return inode->i_state & I_DIRTY_DATASYNC; + return inode_state_read_once(inode) & I_DIRTY_DATASYNC; } static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, @@ -4552,7 +4548,7 @@ int ext4_truncate(struct inode *inode) * or it's a completely new inode. In those cases we might not * have i_rwsem locked because it's not necessary. */ - if (!(inode->i_state & (I_NEW|I_FREEING))) + if (!(inode_state_read_once(inode) & (I_NEW | I_FREEING))) WARN_ON(!inode_is_locked(inode)); trace_ext4_truncate_enter(inode); @@ -5210,7 +5206,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) { + if (!(inode_state_read_once(inode) & I_NEW)) { ret = check_igot_inode(inode, flags, function, line); if (ret) { iput(inode); @@ -5549,7 +5545,7 @@ static void __ext4_update_other_inode_time(struct super_block *sb, if (inode_is_dirtytime_only(inode)) { struct ext4_inode_info *ei = EXT4_I(inode); - inode->i_state &= ~I_DIRTY_TIME; + inode_state_clear(inode, I_DIRTY_TIME); spin_unlock(&inode->i_lock); spin_lock(&ei->i_raw_lock); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index ab1ff51302fb..6f57c181ff77 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -57,16 +57,12 @@ static int write_mmp_block_thawed(struct super_block *sb, static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) { - int err; - /* * We protect against freezing so that we don't create dirty buffers * on frozen filesystem. */ - sb_start_write(sb); - err = write_mmp_block_thawed(sb, bh); - sb_end_write(sb); - return err; + scoped_guard(super_write, sb) + return write_mmp_block_thawed(sb, bh); } /* diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c index 82d5e7501455..5fd54adf0c88 100644 --- a/fs/ext4/orphan.c +++ b/fs/ext4/orphan.c @@ -107,7 +107,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) if (!sbi->s_journal || is_bad_inode(inode)) return 0; - WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) && + WARN_ON_ONCE(!(inode_state_read_once(inode) & (I_NEW | I_FREEING)) && !inode_is_locked(inode)); if (ext4_inode_orphan_tracked(inode)) return 0; @@ -232,7 +232,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS)) return 0; - WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) && + WARN_ON_ONCE(!(inode_state_read_once(inode) & (I_NEW | I_FREEING)) && !inode_is_locked(inode)); if (ext4_test_inode_state(inode, EXT4_STATE_ORPHAN_FILE)) return ext4_orphan_file_del(handle, inode); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index d4d7f329d23f..fa8d81a30fb9 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -9,6 +9,7 @@ * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> */ +#include <linux/fs_struct.h> #include <linux/f2fs_fs.h> #include "f2fs.h" #include "xattr.h" diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 6ad8d3bc6df7..be53e06caf3d 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1329,7 +1329,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, } folio = page_folio(cc->rpages[last_index]); - psize = folio_pos(folio) + folio_size(folio); + psize = folio_next_pos(folio); err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false); if (err) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 775aa4f63aa3..8bf4feda42b0 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2986,10 +2986,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; } - if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) - tag = PAGECACHE_TAG_TOWRITE; - else - tag = PAGECACHE_TAG_DIRTY; + tag = wbc_to_tag(wbc); retry: retry = 0; if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) @@ -4222,7 +4219,7 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, if (map.m_flags & F2FS_MAP_NEW) iomap->flags |= IOMAP_F_NEW; - if ((inode->i_state & I_DIRTY_DATASYNC) || + if ((inode_state_read_once(inode) & I_DIRTY_DATASYNC) || offset + length > i_size_read(inode)) iomap->flags |= IOMAP_F_DIRTY; diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 8c4eafe9ffac..f1cda1900658 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -569,7 +569,7 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) { + if (!(inode_state_read_once(inode) & I_NEW)) { if (is_meta_ino(sbi, ino)) { f2fs_err(sbi, "inaccessible inode: %lu, run fsck to repair", ino); set_sbi_flag(sbi, SBI_NEED_FSCK); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index b882771e4699..af40282a6948 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -844,7 +844,7 @@ static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, f2fs_i_links_write(inode, false); spin_lock(&inode->i_lock); - inode->i_state |= I_LINKABLE; + inode_state_set(inode, I_LINKABLE); spin_unlock(&inode->i_lock); } else { if (file) @@ -1057,7 +1057,7 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, goto put_out_dir; spin_lock(&whiteout->i_lock); - whiteout->i_state &= ~I_LINKABLE; + inode_state_clear(whiteout, I_LINKABLE); spin_unlock(&whiteout->i_lock); iput(whiteout); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index db7afb806411..47489d48f2b9 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1798,7 +1798,7 @@ static int f2fs_drop_inode(struct inode *inode) * - f2fs_gc -> iput -> evict * - inode_wait_for_writeback(inode) */ - if ((!inode_unhashed(inode) && inode->i_state & I_SYNC)) { + if ((!inode_unhashed(inode) && inode_state_read(inode) & I_SYNC)) { if (!inode->i_nlink && !is_bad_inode(inode)) { /* to avoid evict_inode call simultaneously */ __iget(inode); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 9648ed097816..0b6009cd1844 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -22,6 +22,7 @@ #include <linux/unaligned.h> #include <linux/random.h> #include <linux/iversion.h> +#include <linux/fs_struct.h> #include "fat.h" #ifndef CONFIG_FAT_DEFAULT_IOCHARSET @@ -1595,8 +1596,12 @@ int fat_fill_super(struct super_block *sb, struct fs_context *fc, setup(sb); /* flavour-specific stuff that needs options */ + error = -EINVAL; + if (!sb_min_blocksize(sb, 512)) { + fat_msg(sb, KERN_ERR, "unable to set blocksize"); + goto out_fail; + } error = -EIO; - sb_min_blocksize(sb, 512); bh = sb_bread(sb, 0); if (bh == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector"); diff --git a/fs/fcntl.c b/fs/fcntl.c index 72f8433d9109..f93dbca08435 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -445,6 +445,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; + struct delegation deleg; int argi = (int)arg; struct flock flock; long err = -EINVAL; @@ -550,6 +551,18 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_SET_RW_HINT: err = fcntl_set_rw_hint(filp, arg); break; + case F_GETDELEG: + if (copy_from_user(&deleg, argp, sizeof(deleg))) + return -EFAULT; + err = fcntl_getdeleg(filp, &deleg); + if (!err && copy_to_user(argp, &deleg, sizeof(deleg))) + return -EFAULT; + break; + case F_SETDELEG: + if (copy_from_user(&deleg, argp, sizeof(deleg))) + return -EFAULT; + err = fcntl_setdeleg(fd, filp, &deleg); + break; default: break; } diff --git a/fs/fhandle.c b/fs/fhandle.c index 052f9c9368fb..3de1547ec9d4 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -404,32 +404,28 @@ out_path: return retval; } +static struct file *file_open_handle(struct path *path, int open_flag) +{ + const struct export_operations *eops; + + eops = path->mnt->mnt_sb->s_export_op; + if (eops->open) + return eops->open(path, open_flag); + + return file_open_root(path, "", open_flag, 0); +} + static long do_handle_open(int mountdirfd, struct file_handle __user *ufh, int open_flag) { - long retval = 0; + long retval; struct path path __free(path_put) = {}; - struct file *file; - const struct export_operations *eops; retval = handle_to_path(mountdirfd, ufh, &path, open_flag); if (retval) return retval; - CLASS(get_unused_fd, fd)(open_flag); - if (fd < 0) - return fd; - - eops = path.mnt->mnt_sb->s_export_op; - if (eops->open) - file = eops->open(&path, open_flag); - else - file = file_open_root(&path, "", open_flag, 0); - if (IS_ERR(file)) - return PTR_ERR(file); - - fd_install(fd, file); - return take_fd(fd); + return FD_ADD(open_flag, file_open_handle(&path, open_flag)); } /** diff --git a/fs/file.c b/fs/file.c index 28743b742e3c..0a4f3bdb2dec 100644 --- a/fs/file.c +++ b/fs/file.c @@ -641,6 +641,34 @@ void put_unused_fd(unsigned int fd) EXPORT_SYMBOL(put_unused_fd); +/* + * Install a file pointer in the fd array while it is being resized. + * + * We need to make sure our update to the array does not get lost as the resizing + * thread can be copying the content as we modify it. + * + * We have two ways to do it: + * - go off CPU waiting for resize_in_progress to clear + * - take the spin lock + * + * The latter is trivial to implement and saves us from having to might_sleep() + * for debugging purposes. + * + * This is moved out of line from fd_install() to convince gcc to optimize that + * routine better. + */ +static void noinline fd_install_slowpath(unsigned int fd, struct file *file) +{ + struct files_struct *files = current->files; + struct fdtable *fdt; + + spin_lock(&files->file_lock); + fdt = files_fdtable(files); + VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); + rcu_assign_pointer(fdt->fd[fd], file); + spin_unlock(&files->file_lock); +} + /** * fd_install - install a file pointer in the fd array * @fd: file descriptor to install the file in @@ -658,14 +686,9 @@ void fd_install(unsigned int fd, struct file *file) return; rcu_read_lock_sched(); - if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); - spin_lock(&files->file_lock); - fdt = files_fdtable(files); - VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); - rcu_assign_pointer(fdt->fd[fd], file); - spin_unlock(&files->file_lock); + fd_install_slowpath(fd, file); return; } /* coupled with smp_wmb() in expand_fdtable() */ @@ -1357,28 +1380,25 @@ out_unlock: */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { - int new_fd; int error; error = security_file_receive(file); if (error) return error; - new_fd = get_unused_fd_flags(o_flags); - if (new_fd < 0) - return new_fd; + FD_PREPARE(fdf, o_flags, file); + if (fdf.err) + return fdf.err; + get_file(file); if (ufd) { - error = put_user(new_fd, ufd); - if (error) { - put_unused_fd(new_fd); + error = put_user(fd_prepare_fd(fdf), ufd); + if (error) return error; - } } - fd_install(new_fd, get_file(file)); - __receive_sock(file); - return new_fd; + __receive_sock(fd_prepare_file(fdf)); + return fd_publish(fdf); } EXPORT_SYMBOL_GPL(receive_fd); diff --git a/fs/file_attr.c b/fs/file_attr.c index 1dcec88c0680..4c4916632f11 100644 --- a/fs/file_attr.c +++ b/fs/file_attr.c @@ -316,7 +316,6 @@ int ioctl_getflags(struct file *file, unsigned int __user *argp) err = put_user(fa.flags, argp); return err; } -EXPORT_SYMBOL(ioctl_getflags); int ioctl_setflags(struct file *file, unsigned int __user *argp) { @@ -337,7 +336,6 @@ int ioctl_setflags(struct file *file, unsigned int __user *argp) } return err; } -EXPORT_SYMBOL(ioctl_setflags); int ioctl_fsgetxattr(struct file *file, void __user *argp) { @@ -350,7 +348,6 @@ int ioctl_fsgetxattr(struct file *file, void __user *argp) return err; } -EXPORT_SYMBOL(ioctl_fsgetxattr); int ioctl_fssetxattr(struct file *file, void __user *argp) { @@ -369,7 +366,6 @@ int ioctl_fssetxattr(struct file *file, void __user *argp) } return err; } -EXPORT_SYMBOL(ioctl_fssetxattr); SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename, struct file_attr __user *, ufattr, size_t, usize, diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index 20600e9ea202..21fc94b98209 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -258,7 +258,7 @@ vxfs_iget(struct super_block *sbp, ino_t ino) ip = iget_locked(sbp, ino); if (!ip) return ERR_PTR(-ENOMEM); - if (!(ip->i_state & I_NEW)) + if (!(inode_state_read_once(ip) & I_NEW)) return ip; vip = VXFS_INO(ip); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 2b35e80037fe..6800886c4d10 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -14,6 +14,7 @@ * Additions for address_space-based writeback */ +#include <linux/sched/sysctl.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> @@ -32,11 +33,6 @@ #include "internal.h" /* - * 4MB minimal write chunk size - */ -#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) - -/* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { @@ -121,7 +117,7 @@ static bool inode_io_list_move_locked(struct inode *inode, { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); - WARN_ON_ONCE(inode->i_state & I_FREEING); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); list_move(&inode->i_io_list, head); @@ -200,6 +196,19 @@ static void wb_queue_work(struct bdi_writeback *wb, spin_unlock_irq(&wb->work_lock); } +static bool wb_wait_for_completion_cb(struct wb_completion *done) +{ + unsigned long waited_secs = (jiffies - done->wait_start) / HZ; + + done->progress_stamp = jiffies; + if (waited_secs > sysctl_hung_task_timeout_secs) + pr_info("INFO: The task %s:%d has been waiting for writeback " + "completion for more than %lu seconds.", + current->comm, current->pid, waited_secs); + + return !atomic_read(&done->cnt); +} + /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion @@ -212,8 +221,9 @@ static void wb_queue_work(struct bdi_writeback *wb, */ void wb_wait_for_completion(struct wb_completion *done) { + done->wait_start = jiffies; atomic_dec(&done->cnt); /* put down the initial count */ - wait_event(*done->waitq, !atomic_read(&done->cnt)); + wait_event(*done->waitq, wb_wait_for_completion_cb(done)); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -304,9 +314,9 @@ static void inode_cgwb_move_to_attached(struct inode *inode, { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); - WARN_ON_ONCE(inode->i_state & I_FREEING); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); - inode->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); if (wb != &wb->bdi->wb) list_move(&inode->i_io_list, &wb->b_attached); else @@ -408,7 +418,7 @@ static bool inode_do_switch_wbs(struct inode *inode, * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction * path owns the inode and we shouldn't modify ->i_io_list. */ - if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE))) + if (unlikely(inode_state_read(inode) & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); @@ -451,7 +461,7 @@ static bool inode_do_switch_wbs(struct inode *inode, if (!list_empty(&inode->i_io_list)) { inode->i_wb = new_wb; - if (inode->i_state & I_DIRTY_ALL) { + if (inode_state_read(inode) & I_DIRTY_ALL) { /* * We need to keep b_dirty list sorted by * dirtied_time_when. However properly sorting the @@ -476,10 +486,11 @@ static bool inode_do_switch_wbs(struct inode *inode, switched = true; skip_switch: /* - * Paired with load_acquire in unlocked_inode_to_wb_begin() and + * Paired with an acquire fence in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ - smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); + smp_wmb(); + inode_state_clear(inode, I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); @@ -600,12 +611,12 @@ static bool inode_prepare_wbs_switch(struct inode *inode, /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || - inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || + inode_state_read(inode) & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || inode_to_wb(inode) == new_wb) { spin_unlock(&inode->i_lock); return false; } - inode->i_state |= I_WB_SWITCH; + inode_state_set(inode, I_WB_SWITCH); __iget(inode); spin_unlock(&inode->i_lock); @@ -635,7 +646,7 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) struct bdi_writeback *new_wb = NULL; /* noop if seems to be already in progress */ - if (inode->i_state & I_WB_SWITCH) + if (inode_state_read_once(inode) & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ @@ -807,9 +818,9 @@ static void wbc_attach_and_unlock_inode(struct writeback_control *wbc, * @wbc: writeback_control of interest * @inode: target inode * - * This function is to be used by __filemap_fdatawrite_range(), which is an - * alternative entry point into writeback code, and first ensures @inode is - * associated with a bdi_writeback and attaches it to @wbc. + * This function is to be used by filemap_writeback(), which is an alternative + * entry point into writeback code, and first ensures @inode is associated with + * a bdi_writeback and attaches it to @wbc. */ void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) @@ -1236,9 +1247,9 @@ static void inode_cgwb_move_to_attached(struct inode *inode, { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); - WARN_ON_ONCE(inode->i_state & I_FREEING); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); - inode->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } @@ -1348,10 +1359,17 @@ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; + /* + * FIXME: ext4 can call here from ext4_evict_inode() after evict() already + * unlinked the inode. + */ + if (list_empty_careful(&inode->i_io_list)) + return; + wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); - inode->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); @@ -1409,13 +1427,13 @@ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); - inode->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); /* * When the inode is being freed just don't bother with dirty list * tracking. Flush worker will ignore this inode anyway and it will * trigger assertions in inode_io_list_move_locked(). */ - if (inode->i_state & I_FREEING) { + if (inode_state_read(inode) & I_FREEING) { list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); return; @@ -1449,9 +1467,9 @@ static void inode_sync_complete(struct inode *inode) { assert_spin_locked(&inode->i_lock); - inode->i_state &= ~I_SYNC; + inode_state_clear(inode, I_SYNC); /* If inode is clean an unused, put it into LRU now... */ - inode_add_lru(inode); + inode_lru_list_add(inode); /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_SYNC); } @@ -1493,7 +1511,7 @@ static int move_expired_inodes(struct list_head *delaying_queue, spin_lock(&inode->i_lock); list_move(&inode->i_io_list, &tmp); moved++; - inode->i_state |= I_SYNC_QUEUED; + inode_state_set(inode, I_SYNC_QUEUED); spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; @@ -1579,14 +1597,14 @@ void inode_wait_for_writeback(struct inode *inode) assert_spin_locked(&inode->i_lock); - if (!(inode->i_state & I_SYNC)) + if (!(inode_state_read(inode) & I_SYNC)) return; wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); for (;;) { prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ - if (!(inode->i_state & I_SYNC)) + if (!(inode_state_read(inode) & I_SYNC)) break; spin_unlock(&inode->i_lock); schedule(); @@ -1612,7 +1630,7 @@ static void inode_sleep_on_writeback(struct inode *inode) wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ - sleep = !!(inode->i_state & I_SYNC); + sleep = !!(inode_state_read(inode) & I_SYNC); spin_unlock(&inode->i_lock); if (sleep) schedule(); @@ -1631,7 +1649,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc, unsigned long dirtied_before) { - if (inode->i_state & I_FREEING) + if (inode_state_read(inode) & I_FREEING) return; /* @@ -1639,7 +1657,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ - if ((inode->i_state & I_DIRTY) && + if ((inode_state_read(inode) & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; @@ -1650,7 +1668,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * is odd for clean inodes, it can happen for some * filesystems so handle that gracefully. */ - if (inode->i_state & I_DIRTY_ALL) + if (inode_state_read(inode) & I_DIRTY_ALL) redirty_tail_locked(inode, wb); else inode_cgwb_move_to_attached(inode, wb); @@ -1676,17 +1694,17 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, */ redirty_tail_locked(inode, wb); } - } else if (inode->i_state & I_DIRTY) { + } else if (inode_state_read(inode) & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); - } else if (inode->i_state & I_DIRTY_TIME) { + } else if (inode_state_read(inode) & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); - inode->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); } else { /* The inode is clean. Remove from writeback lists. */ inode_cgwb_move_to_attached(inode, wb); @@ -1712,7 +1730,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) unsigned dirty; int ret; - WARN_ON(!(inode->i_state & I_SYNC)); + WARN_ON(!(inode_state_read_once(inode) & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); @@ -1736,7 +1754,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ - if ((inode->i_state & I_DIRTY_TIME) && + if ((inode_state_read_once(inode) & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { @@ -1751,8 +1769,8 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * after handling timestamp expiration, as that may dirty the inode too. */ spin_lock(&inode->i_lock); - dirty = inode->i_state & I_DIRTY; - inode->i_state &= ~dirty; + dirty = inode_state_read(inode) & I_DIRTY; + inode_state_clear(inode, dirty); /* * Paired with smp_mb() in __mark_inode_dirty(). This allows @@ -1768,10 +1786,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - inode->i_state |= I_DIRTY_PAGES; - else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) { - if (!(inode->i_state & I_DIRTY_PAGES)) { - inode->i_state &= ~I_PINNING_NETFS_WB; + inode_state_set(inode, I_DIRTY_PAGES); + else if (unlikely(inode_state_read(inode) & I_PINNING_NETFS_WB)) { + if (!(inode_state_read(inode) & I_DIRTY_PAGES)) { + inode_state_clear(inode, I_PINNING_NETFS_WB); wbc->unpinned_netfs_wb = true; dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */ } @@ -1807,11 +1825,11 @@ static int writeback_single_inode(struct inode *inode, spin_lock(&inode->i_lock); if (!icount_read(inode)) - WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); + WARN_ON(!(inode_state_read(inode) & (I_WILL_FREE | I_FREEING))); else - WARN_ON(inode->i_state & I_WILL_FREE); + WARN_ON(inode_state_read(inode) & I_WILL_FREE); - if (inode->i_state & I_SYNC) { + if (inode_state_read(inode) & I_SYNC) { /* * Writeback is already running on the inode. For WB_SYNC_NONE, * that's enough and we can just return. For WB_SYNC_ALL, we @@ -1822,7 +1840,7 @@ static int writeback_single_inode(struct inode *inode, goto out; inode_wait_for_writeback(inode); } - WARN_ON(inode->i_state & I_SYNC); + WARN_ON(inode_state_read(inode) & I_SYNC); /* * If the inode is already fully clean, then there's nothing to do. * @@ -1830,11 +1848,11 @@ static int writeback_single_inode(struct inode *inode, * still under writeback, e.g. due to prior WB_SYNC_NONE writeback. If * there are any such pages, we'll need to wait for them. */ - if (!(inode->i_state & I_DIRTY_ALL) && + if (!(inode_state_read(inode) & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; - inode->i_state |= I_SYNC; + inode_state_set(inode, I_SYNC); wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); @@ -1847,18 +1865,18 @@ static int writeback_single_inode(struct inode *inode, * If the inode is freeing, its i_io_list shoudn't be updated * as it can be finally deleted at this moment. */ - if (!(inode->i_state & I_FREEING)) { + if (!(inode_state_read(inode) & I_FREEING)) { /* * If the inode is now fully clean, then it can be safely * removed from its writeback list (if any). Otherwise the * flusher threads are responsible for the writeback lists. */ - if (!(inode->i_state & I_DIRTY_ALL)) + if (!(inode_state_read(inode) & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); - else if (!(inode->i_state & I_SYNC_QUEUED)) { - if ((inode->i_state & I_DIRTY)) + else if (!(inode_state_read(inode) & I_SYNC_QUEUED)) { + if ((inode_state_read(inode) & I_DIRTY)) redirty_tail_locked(inode, wb); - else if (inode->i_state & I_DIRTY_TIME) { + else if (inode_state_read(inode) & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, @@ -1874,8 +1892,8 @@ out: return ret; } -static long writeback_chunk_size(struct bdi_writeback *wb, - struct wb_writeback_work *work) +static long writeback_chunk_size(struct super_block *sb, + struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; @@ -1893,16 +1911,13 @@ static long writeback_chunk_size(struct bdi_writeback *wb, * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) - pages = LONG_MAX; - else { - pages = min(wb->avg_write_bandwidth / 2, - global_wb_domain.dirty_limit / DIRTY_SCOPE); - pages = min(pages, work->nr_pages); - pages = round_down(pages + MIN_WRITEBACK_PAGES, - MIN_WRITEBACK_PAGES); - } + return LONG_MAX; - return pages; + pages = min(wb->avg_write_bandwidth / 2, + global_wb_domain.dirty_limit / DIRTY_SCOPE); + pages = min(pages, work->nr_pages); + return round_down(pages + sb->s_min_writeback_pages, + sb->s_min_writeback_pages); } /* @@ -1967,12 +1982,12 @@ static long writeback_sb_inodes(struct super_block *sb, * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); - if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + if (inode_state_read(inode) & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } - if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { + if ((inode_state_read(inode) & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to @@ -1994,17 +2009,17 @@ static long writeback_sb_inodes(struct super_block *sb, * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ - if (inode->i_state & I_SYNC) { + if (inode_state_read(inode) & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } - inode->i_state |= I_SYNC; + inode_state_set(inode, I_SYNC); wbc_attach_and_unlock_inode(&wbc, inode); - write_chunk = writeback_chunk_size(wb, work); + write_chunk = writeback_chunk_size(inode->i_sb, wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; @@ -2014,6 +2029,12 @@ static long writeback_sb_inodes(struct super_block *sb, */ __writeback_single_inode(inode, &wbc); + /* Report progress to inform the hung task detector of the progress. */ + if (work->done && work->done->progress_stamp && + (jiffies - work->done->progress_stamp) > HZ * + sysctl_hung_task_timeout_secs / 2) + wake_up_all(work->done->waitq); + wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; @@ -2039,7 +2060,7 @@ static long writeback_sb_inodes(struct super_block *sb, */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); - if (!(inode->i_state & I_DIRTY_ALL)) + if (!(inode_state_read(inode) & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc, dirtied_before); inode_sync_complete(inode); @@ -2545,10 +2566,10 @@ void __mark_inode_dirty(struct inode *inode, int flags) * We tell ->dirty_inode callback that timestamps need to * be updated by setting I_DIRTY_TIME in flags. */ - if (inode->i_state & I_DIRTY_TIME) { + if (inode_state_read_once(inode) & I_DIRTY_TIME) { spin_lock(&inode->i_lock); - if (inode->i_state & I_DIRTY_TIME) { - inode->i_state &= ~I_DIRTY_TIME; + if (inode_state_read(inode) & I_DIRTY_TIME) { + inode_state_clear(inode, I_DIRTY_TIME); flags |= I_DIRTY_TIME; } spin_unlock(&inode->i_lock); @@ -2585,16 +2606,16 @@ void __mark_inode_dirty(struct inode *inode, int flags) */ smp_mb(); - if ((inode->i_state & flags) == flags) + if ((inode_state_read_once(inode) & flags) == flags) return; spin_lock(&inode->i_lock); - if ((inode->i_state & flags) != flags) { - const int was_dirty = inode->i_state & I_DIRTY; + if ((inode_state_read(inode) & flags) != flags) { + const int was_dirty = inode_state_read(inode) & I_DIRTY; inode_attach_wb(inode, NULL); - inode->i_state |= flags; + inode_state_set(inode, flags); /* * Grab inode's wb early because it requires dropping i_lock and we @@ -2613,7 +2634,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) * the inode it will place it on the appropriate superblock * list, based upon its state. */ - if (inode->i_state & I_SYNC_QUEUED) + if (inode_state_read(inode) & I_SYNC_QUEUED) goto out_unlock; /* @@ -2624,7 +2645,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (inode_unhashed(inode)) goto out_unlock; } - if (inode->i_state & I_FREEING) + if (inode_state_read(inode) & I_FREEING) goto out_unlock; /* @@ -2639,7 +2660,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (dirtytime) inode->dirtied_time_when = jiffies; - if (inode->i_state & I_DIRTY) + if (inode_state_read(inode) & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; @@ -2736,7 +2757,7 @@ static void wait_sb_inodes(struct super_block *sb) spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); diff --git a/fs/fs_types.c b/fs/fs_dirent.c index 78365e5dc08c..e5e08f213816 100644 --- a/fs/fs_types.c +++ b/fs/fs_dirent.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/fs.h> +#include <linux/fs_dirent.h> #include <linux/export.h> /* diff --git a/fs/fs_struct.c b/fs/fs_struct.c index 28be762ac1c6..b8c46c5a38a0 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -146,12 +146,6 @@ int unshare_fs_struct(void) } EXPORT_SYMBOL_GPL(unshare_fs_struct); -int current_umask(void) -{ - return current->fs->umask; -} -EXPORT_SYMBOL(current_umask); - /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index ecaec0fea3a1..87a63ae93a45 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1192,7 +1192,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode, if (attr->blksize != 0) blkbits = ilog2(attr->blksize); else - blkbits = fc->blkbits; + blkbits = inode->i_sb->s_blocksize_bits; stat->blksize = 1 << blkbits; } @@ -1397,27 +1397,25 @@ int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid, if (!parent) return -ENOENT; - inode_lock_nested(parent, I_MUTEX_PARENT); if (!S_ISDIR(parent->i_mode)) - goto unlock; + goto put_parent; err = -ENOENT; dir = d_find_alias(parent); if (!dir) - goto unlock; + goto put_parent; - name->hash = full_name_hash(dir, name->name, name->len); - entry = d_lookup(dir, name); + entry = start_removing_noperm(dir, name); dput(dir); - if (!entry) - goto unlock; + if (IS_ERR(entry)) + goto put_parent; fuse_dir_changed(parent); if (!(flags & FUSE_EXPIRE_ONLY)) d_invalidate(entry); fuse_invalidate_entry_cache(entry); - if (child_nodeid != 0 && d_really_is_positive(entry)) { + if (child_nodeid != 0) { inode_lock(d_inode(entry)); if (get_node_id(d_inode(entry)) != child_nodeid) { err = -ENOENT; @@ -1445,10 +1443,9 @@ int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid, } else { err = 0; } - dput(entry); - unlock: - inode_unlock(parent); + end_removing(entry); + put_parent: iput(parent); return err; } @@ -2230,6 +2227,7 @@ static const struct file_operations fuse_dir_operations = { .fsync = fuse_dir_fsync, .unlocked_ioctl = fuse_dir_ioctl, .compat_ioctl = fuse_dir_compat_ioctl, + .setlease = simple_nosetlease, }; static const struct inode_operations fuse_common_inode_operations = { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f1ef77a0be05..7bcb650a9f26 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -834,23 +834,142 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio, return 0; } +static int fuse_iomap_begin(struct inode *inode, loff_t offset, loff_t length, + unsigned int flags, struct iomap *iomap, + struct iomap *srcmap) +{ + iomap->type = IOMAP_MAPPED; + iomap->length = length; + iomap->offset = offset; + return 0; +} + +static const struct iomap_ops fuse_iomap_ops = { + .iomap_begin = fuse_iomap_begin, +}; + +struct fuse_fill_read_data { + struct file *file; + + /* Fields below are used if sending the read request asynchronously */ + struct fuse_conn *fc; + struct fuse_io_args *ia; + unsigned int nr_bytes; +}; + +/* forward declarations */ +static bool fuse_folios_need_send(struct fuse_conn *fc, loff_t pos, + unsigned len, struct fuse_args_pages *ap, + unsigned cur_bytes, bool write); +static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file, + unsigned int count, bool async); + +static int fuse_handle_readahead(struct folio *folio, + struct readahead_control *rac, + struct fuse_fill_read_data *data, loff_t pos, + size_t len) +{ + struct fuse_io_args *ia = data->ia; + size_t off = offset_in_folio(folio, pos); + struct fuse_conn *fc = data->fc; + struct fuse_args_pages *ap; + unsigned int nr_pages; + + if (ia && fuse_folios_need_send(fc, pos, len, &ia->ap, data->nr_bytes, + false)) { + fuse_send_readpages(ia, data->file, data->nr_bytes, + fc->async_read); + data->nr_bytes = 0; + data->ia = NULL; + ia = NULL; + } + if (!ia) { + if (fc->num_background >= fc->congestion_threshold && + rac->ra->async_size >= readahead_count(rac)) + /* + * Congested and only async pages left, so skip the + * rest. + */ + return -EAGAIN; + + nr_pages = min(fc->max_pages, readahead_count(rac)); + data->ia = fuse_io_alloc(NULL, nr_pages); + if (!data->ia) + return -ENOMEM; + ia = data->ia; + } + folio_get(folio); + ap = &ia->ap; + ap->folios[ap->num_folios] = folio; + ap->descs[ap->num_folios].offset = off; + ap->descs[ap->num_folios].length = len; + data->nr_bytes += len; + ap->num_folios++; + + return 0; +} + +static int fuse_iomap_read_folio_range_async(const struct iomap_iter *iter, + struct iomap_read_folio_ctx *ctx, + size_t len) +{ + struct fuse_fill_read_data *data = ctx->read_ctx; + struct folio *folio = ctx->cur_folio; + loff_t pos = iter->pos; + size_t off = offset_in_folio(folio, pos); + struct file *file = data->file; + int ret; + + if (ctx->rac) { + ret = fuse_handle_readahead(folio, ctx->rac, data, pos, len); + } else { + /* + * for non-readahead read requests, do reads synchronously + * since it's not guaranteed that the server can handle + * out-of-order reads + */ + ret = fuse_do_readfolio(file, folio, off, len); + if (!ret) + iomap_finish_folio_read(folio, off, len, ret); + } + return ret; +} + +static void fuse_iomap_read_submit(struct iomap_read_folio_ctx *ctx) +{ + struct fuse_fill_read_data *data = ctx->read_ctx; + + if (data->ia) + fuse_send_readpages(data->ia, data->file, data->nr_bytes, + data->fc->async_read); +} + +static const struct iomap_read_ops fuse_iomap_read_ops = { + .read_folio_range = fuse_iomap_read_folio_range_async, + .submit_read = fuse_iomap_read_submit, +}; + static int fuse_read_folio(struct file *file, struct folio *folio) { struct inode *inode = folio->mapping->host; - int err; + struct fuse_fill_read_data data = { + .file = file, + }; + struct iomap_read_folio_ctx ctx = { + .cur_folio = folio, + .ops = &fuse_iomap_read_ops, + .read_ctx = &data, - err = -EIO; - if (fuse_is_bad(inode)) - goto out; + }; - err = fuse_do_readfolio(file, folio, 0, folio_size(folio)); - if (!err) - folio_mark_uptodate(folio); + if (fuse_is_bad(inode)) { + folio_unlock(folio); + return -EIO; + } + iomap_read_folio(&fuse_iomap_ops, &ctx); fuse_invalidate_atime(inode); - out: - folio_unlock(folio); - return err; + return 0; } static int fuse_iomap_read_folio_range(const struct iomap_iter *iter, @@ -887,7 +1006,8 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args, fuse_invalidate_atime(inode); for (i = 0; i < ap->num_folios; i++) { - folio_end_read(ap->folios[i], !err); + iomap_finish_folio_read(ap->folios[i], ap->descs[i].offset, + ap->descs[i].length, err); folio_put(ap->folios[i]); } if (ia->ff) @@ -897,7 +1017,7 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args, } static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file, - unsigned int count) + unsigned int count, bool async) { struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; @@ -919,7 +1039,7 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file, fuse_read_args_fill(ia, file, pos, count, FUSE_READ); ia->read.attr_ver = fuse_get_attr_version(fm->fc); - if (fm->fc->async_read) { + if (async) { ia->ff = fuse_file_get(ff); ap->args.end = fuse_readpages_end; err = fuse_simple_background(fm, &ap->args, GFP_KERNEL); @@ -936,81 +1056,20 @@ static void fuse_readahead(struct readahead_control *rac) { struct inode *inode = rac->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); - unsigned int max_pages, nr_pages; - struct folio *folio = NULL; + struct fuse_fill_read_data data = { + .file = rac->file, + .fc = fc, + }; + struct iomap_read_folio_ctx ctx = { + .ops = &fuse_iomap_read_ops, + .rac = rac, + .read_ctx = &data + }; if (fuse_is_bad(inode)) return; - max_pages = min_t(unsigned int, fc->max_pages, - fc->max_read / PAGE_SIZE); - - /* - * This is only accurate the first time through, since readahead_folio() - * doesn't update readahead_count() from the previous folio until the - * next call. Grab nr_pages here so we know how many pages we're going - * to have to process. This means that we will exit here with - * readahead_count() == folio_nr_pages(last_folio), but we will have - * consumed all of the folios, and read_pages() will call - * readahead_folio() again which will clean up the rac. - */ - nr_pages = readahead_count(rac); - - while (nr_pages) { - struct fuse_io_args *ia; - struct fuse_args_pages *ap; - unsigned cur_pages = min(max_pages, nr_pages); - unsigned int pages = 0; - - if (fc->num_background >= fc->congestion_threshold && - rac->ra->async_size >= readahead_count(rac)) - /* - * Congested and only async pages left, so skip the - * rest. - */ - break; - - ia = fuse_io_alloc(NULL, cur_pages); - if (!ia) - break; - ap = &ia->ap; - - while (pages < cur_pages) { - unsigned int folio_pages; - - /* - * This returns a folio with a ref held on it. - * The ref needs to be held until the request is - * completed, since the splice case (see - * fuse_try_move_page()) drops the ref after it's - * replaced in the page cache. - */ - if (!folio) - folio = __readahead_folio(rac); - - folio_pages = folio_nr_pages(folio); - if (folio_pages > cur_pages - pages) { - /* - * Large folios belonging to fuse will never - * have more pages than max_pages. - */ - WARN_ON(!pages); - break; - } - - ap->folios[ap->num_folios] = folio; - ap->descs[ap->num_folios].length = folio_size(folio); - ap->num_folios++; - pages += folio_pages; - folio = NULL; - } - fuse_send_readpages(ia, rac->file, pages << PAGE_SHIFT); - nr_pages -= pages; - } - if (folio) { - folio_end_read(folio, false); - folio_put(folio); - } + iomap_readahead(&fuse_iomap_ops, &ctx); } static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -1397,20 +1456,6 @@ static const struct iomap_write_ops fuse_iomap_write_ops = { .read_folio_range = fuse_iomap_read_folio_range, }; -static int fuse_iomap_begin(struct inode *inode, loff_t offset, loff_t length, - unsigned int flags, struct iomap *iomap, - struct iomap *srcmap) -{ - iomap->type = IOMAP_MAPPED; - iomap->length = length; - iomap->offset = offset; - return 0; -} - -static const struct iomap_ops fuse_iomap_ops = { - .iomap_begin = fuse_iomap_begin, -}; - static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; @@ -1834,7 +1879,8 @@ static void fuse_writepage_finish(struct fuse_writepage_args *wpa) * scope of the fi->lock alleviates xarray lock * contention and noticeably improves performance. */ - iomap_finish_folio_write(inode, ap->folios[i], 1); + iomap_finish_folio_write(inode, ap->folios[i], + ap->descs[i].length); wake_up(&fi->page_waitq); } @@ -2047,7 +2093,7 @@ struct fuse_fill_wb_data { struct fuse_file *ff; unsigned int max_folios; /* - * nr_bytes won't overflow since fuse_writepage_need_send() caps + * nr_bytes won't overflow since fuse_folios_need_send() caps * wb requests to never exceed fc->max_pages (which has an upper bound * of U16_MAX). */ @@ -2092,14 +2138,15 @@ static void fuse_writepages_send(struct inode *inode, spin_unlock(&fi->lock); } -static bool fuse_writepage_need_send(struct fuse_conn *fc, loff_t pos, - unsigned len, struct fuse_args_pages *ap, - struct fuse_fill_wb_data *data) +static bool fuse_folios_need_send(struct fuse_conn *fc, loff_t pos, + unsigned len, struct fuse_args_pages *ap, + unsigned cur_bytes, bool write) { struct folio *prev_folio; struct fuse_folio_desc prev_desc; - unsigned bytes = data->nr_bytes + len; + unsigned bytes = cur_bytes + len; loff_t prev_pos; + size_t max_bytes = write ? fc->max_write : fc->max_read; WARN_ON(!ap->num_folios); @@ -2107,8 +2154,7 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, loff_t pos, if ((bytes + PAGE_SIZE - 1) >> PAGE_SHIFT > fc->max_pages) return true; - /* Reached max write bytes */ - if (bytes > fc->max_write) + if (bytes > max_bytes) return true; /* Discontinuity */ @@ -2118,11 +2164,6 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, loff_t pos, if (prev_pos != pos) return true; - /* Need to grow the pages array? If so, did the expansion fail? */ - if (ap->num_folios == data->max_folios && - !fuse_pages_realloc(data, fc->max_pages)) - return true; - return false; } @@ -2146,10 +2187,24 @@ static ssize_t fuse_iomap_writeback_range(struct iomap_writepage_ctx *wpc, return -EIO; } - if (wpa && fuse_writepage_need_send(fc, pos, len, ap, data)) { - fuse_writepages_send(inode, data); - data->wpa = NULL; - data->nr_bytes = 0; + if (wpa) { + bool send = fuse_folios_need_send(fc, pos, len, ap, + data->nr_bytes, true); + + if (!send) { + /* + * Need to grow the pages array? If so, did the + * expansion fail? + */ + send = (ap->num_folios == data->max_folios) && + !fuse_pages_realloc(data, fc->max_pages); + } + + if (send) { + fuse_writepages_send(inode, data); + data->wpa = NULL; + data->nr_bytes = 0; + } } if (data->wpa == NULL) { @@ -2161,7 +2216,6 @@ static ssize_t fuse_iomap_writeback_range(struct iomap_writepage_ctx *wpc, ap = &wpa->ia.ap; } - iomap_start_folio_write(inode, folio, 1); fuse_writepage_args_page_fill(wpa, folio, ap->num_folios, offset, len); data->nr_bytes += len; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index c2f2a48156d6..f616c1991fed 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -981,14 +981,6 @@ struct fuse_conn { /* Request timeout (in jiffies). 0 = no timeout */ unsigned int req_timeout; } timeout; - - /* - * This is a workaround until fuse uses iomap for reads. - * For fuseblk servers, this represents the blocksize passed in at - * mount time and for regular fuse servers, this is equivalent to - * inode->i_blkbits. - */ - u8 blkbits; }; /* diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d1babf56f254..1a397be53f49 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -160,7 +160,7 @@ static void fuse_evict_inode(struct inode *inode) struct fuse_inode *fi = get_fuse_inode(inode); /* Will write inode on close/munmap and in all other dirtiers */ - WARN_ON(inode->i_state & I_DIRTY_INODE); + WARN_ON(inode_state_read_once(inode) & I_DIRTY_INODE); if (FUSE_IS_DAX(inode)) dax_break_layout_final(inode); @@ -291,7 +291,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, if (attr->blksize) fi->cached_i_blkbits = ilog2(attr->blksize); else - fi->cached_i_blkbits = fc->blkbits; + fi->cached_i_blkbits = inode->i_sb->s_blocksize_bits; /* * Don't set the sticky bit in i_mode, unless we want the VFS @@ -505,7 +505,7 @@ retry: if (!inode) return NULL; - if ((inode->i_state & I_NEW)) { + if ((inode_state_read_once(inode) & I_NEW)) { inode->i_flags |= S_NOATIME; if (!fc->writeback_cache || !S_ISREG(attr->mode)) inode->i_flags |= S_NOCMTIME; @@ -1838,22 +1838,11 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx) err = -EINVAL; if (!sb_set_blocksize(sb, ctx->blksize)) goto err; - /* - * This is a workaround until fuse hooks into iomap for reads. - * Use PAGE_SIZE for the blocksize else if the writeback cache - * is enabled, buffered writes go through iomap and a read may - * overwrite partially written data if blocksize < PAGE_SIZE - */ - fc->blkbits = sb->s_blocksize_bits; - if (ctx->blksize != PAGE_SIZE && - !sb_set_blocksize(sb, PAGE_SIZE)) - goto err; #endif fc->sync_fs = 1; } else { sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; - fc->blkbits = sb->s_blocksize_bits; } sb->s_subtype = ctx->subtype; diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 6bc7c97b017d..b2f6486fe1d5 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -373,7 +373,7 @@ static int virtio_fs_add_queues_sysfs(struct virtio_fs *fs) sprintf(buff, "%d", i); fsvq->kobj = kobject_create_and_add(buff, fs->mqs_kobj); - if (!fs->mqs_kobj) { + if (!fsvq->kobj) { ret = -ENOMEM; goto out_del; } diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 47d74afd63ac..ff1cf335449a 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -81,8 +81,7 @@ static int gfs2_write_jdata_folio(struct folio *folio, * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - if (folio_pos(folio) < i_size && - i_size < folio_pos(folio) + folio_size(folio)) + if (folio_pos(folio) < i_size && i_size < folio_next_pos(folio)) folio_zero_segment(folio, offset_in_folio(folio, i_size), folio_size(folio)); @@ -311,10 +310,7 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ } - if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) - tag = PAGECACHE_TAG_TOWRITE; - else - tag = PAGECACHE_TAG_DIRTY; + tag = wbc_to_tag(wbc); retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) @@ -424,11 +420,11 @@ static int gfs2_read_folio(struct file *file, struct folio *folio) struct inode *inode = folio->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); - int error; + int error = 0; if (!gfs2_is_jdata(ip) || (i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) { - error = iomap_read_folio(folio, &gfs2_iomap_ops); + iomap_bio_read_folio(folio, &gfs2_iomap_ops); } else if (gfs2_is_stuffed(ip)) { error = stuffed_read_folio(ip, folio); } else { @@ -503,7 +499,7 @@ static void gfs2_readahead(struct readahead_control *rac) else if (gfs2_is_jdata(ip)) mpage_readahead(rac, gfs2_block_map); else - iomap_readahead(rac, &gfs2_iomap_ops); + iomap_bio_readahead(rac, &gfs2_iomap_ops); } /** diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index bc67fa058c84..ee92f5910ae1 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -744,7 +744,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - int sync_state = inode->i_state & I_DIRTY; + int sync_state = inode_state_read_once(inode) & I_DIRTY; struct gfs2_inode *ip = GFS2_I(inode); int ret = 0, ret1 = 0; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index b677c0e6b9ab..c9712235e7a0 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -957,7 +957,7 @@ static struct gfs2_inode *gfs2_grab_existing_inode(struct gfs2_glock *gl) ip = NULL; spin_unlock(&gl->gl_lockref.lock); if (ip) { - wait_on_inode(&ip->i_inode); + wait_on_new_inode(&ip->i_inode); if (is_bad_inode(&ip->i_inode)) { iput(&ip->i_inode); ip = NULL; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 0c0a80b3baca..c94e42b0c94d 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -394,7 +394,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) u16 height, depth; umode_t mode = be32_to_cpu(str->di_mode); struct inode *inode = &ip->i_inode; - bool is_new = inode->i_state & I_NEW; + bool is_new = inode_state_read_once(inode) & I_NEW; if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr))) { gfs2_consist_inode(ip); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 8a7ed80d9f2d..890c87e3e365 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -127,7 +127,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, ip = GFS2_I(inode); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_glock *io_gl; int extra_flags = 0; @@ -924,7 +924,7 @@ fail_gunlock: gfs2_dir_no_add(&da); gfs2_glock_dq_uninit(&d_gh); if (!IS_ERR_OR_NULL(inode)) { - if (inode->i_state & I_NEW) + if (inode_state_read_once(inode) & I_NEW) iget_failed(inode); else iput(inode); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index aa15183f9a16..889682f051ea 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1751,7 +1751,7 @@ static void gfs2_evict_inodes(struct super_block *sb) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); - if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) && + if ((inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) && !need_resched()) { spin_unlock(&inode->i_lock); continue; diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 22e62fe7448b..54c20d01c342 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -42,7 +42,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke tree->inode = iget_locked(sb, id); if (!tree->inode) goto free_tree; - BUG_ON(!(tree->inode->i_state & I_NEW)); + BUG_ON(!(inode_state_read_once(tree->inode) & I_NEW)); { struct hfs_mdb *mdb = HFS_SB(sb)->mdb; HFS_I(tree->inode)->flags = 0; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 9cd449913dc8..81ad93e6312f 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -412,7 +412,7 @@ struct inode *hfs_iget(struct super_block *sb, struct hfs_cat_key *key, hfs_cat_ return NULL; } inode = iget5_locked(sb, cnid, hfs_test_inode, hfs_read_inode, &data); - if (inode && (inode->i_state & I_NEW)) + if (inode && (inode_state_read_once(inode) & I_NEW)) unlock_new_inode(inode); return inode; } diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index a66a09a56bf7..9b377481f397 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/fs_struct.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/nls.h> diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 16bc4abc67e0..54e85e25a259 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -65,7 +65,7 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; atomic_set(&HFSPLUS_I(inode)->opencnt, 0); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 1e1acf5775ab..51d26aa2b93e 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -581,7 +581,7 @@ static struct inode *hostfs_iget(struct super_block *sb, char *name) if (!inode) return ERR_PTR(-ENOMEM); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { unlock_new_inode(inode); } else { spin_lock(&inode->i_lock); @@ -979,7 +979,7 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct hostfs_fs_info *fsi = fc->s_fs_info; struct fs_parse_result result; - char *host_root; + char *host_root, *tmp_root; int opt; opt = fs_parse(fc, hostfs_param_specs, param, &result); @@ -990,11 +990,13 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_hostfs: host_root = param->string; if (!*host_root) - host_root = ""; - fsi->host_root_path = - kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root); - if (fsi->host_root_path == NULL) + break; + tmp_root = kasprintf(GFP_KERNEL, "%s%s", + fsi->host_root_path, host_root); + if (!tmp_root) return -ENOMEM; + kfree(fsi->host_root_path); + fsi->host_root_path = tmp_root; break; } @@ -1004,17 +1006,17 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param) static int hostfs_parse_monolithic(struct fs_context *fc, void *data) { struct hostfs_fs_info *fsi = fc->s_fs_info; - char *host_root = (char *)data; + char *tmp_root, *host_root = (char *)data; /* NULL is printed as '(null)' by printf(): avoid that. */ if (host_root == NULL) - host_root = ""; + return 0; - fsi->host_root_path = - kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root); - if (fsi->host_root_path == NULL) + tmp_root = kasprintf(GFP_KERNEL, "%s%s", fsi->host_root_path, host_root); + if (!tmp_root) return -ENOMEM; - + kfree(fsi->host_root_path); + fsi->host_root_path = tmp_root; return 0; } @@ -1049,6 +1051,11 @@ static int hostfs_init_fs_context(struct fs_context *fc) if (!fsi) return -ENOMEM; + fsi->host_root_path = kasprintf(GFP_KERNEL, "%s/", root_ino); + if (!fsi->host_root_path) { + kfree(fsi); + return -ENOMEM; + } fc->s_fs_info = fsi; fc->ops = &hostfs_context_ops; return 0; diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index 49dd585c2b17..ceb50b2dc91a 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -247,7 +247,7 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in result = ERR_PTR(-ENOMEM); goto bail1; } - if (result->i_state & I_NEW) { + if (inode_state_read_once(result) & I_NEW) { hpfs_init_inode(result); if (de->directory) hpfs_read_inode(result); diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 34008442ee26..93d528f4f4f2 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -196,7 +196,7 @@ void hpfs_write_inode(struct inode *i) parent = iget_locked(i->i_sb, hpfs_inode->i_parent_dir); if (parent) { hpfs_inode->i_dirty = 0; - if (parent->i_state & I_NEW) { + if (inode_state_read_once(parent) & I_NEW) { hpfs_init_inode(parent); hpfs_read_inode(parent); unlock_new_inode(parent); diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 8ab85e7ac91e..371aa6de8075 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -9,6 +9,7 @@ #include "hpfs_fn.h" #include <linux/module.h> +#include <linux/fs_struct.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/init.h> diff --git a/fs/init.c b/fs/init.c index 07f592ccdba8..e0f5429c0a49 100644 --- a/fs/init.c +++ b/fs/init.c @@ -157,7 +157,7 @@ int __init init_mknod(const char *filename, umode_t mode, unsigned int dev) error = security_path_mknod(&path, dentry, mode, dev); if (!error) error = vfs_mknod(mnt_idmap(path.mnt), path.dentry->d_inode, - dentry, mode, new_decode_dev(dev)); + dentry, mode, new_decode_dev(dev), NULL); end_creating_path(&path, dentry); return error; } @@ -209,7 +209,7 @@ int __init init_symlink(const char *oldname, const char *newname) error = security_path_symlink(&path, dentry, oldname); if (!error) error = vfs_symlink(mnt_idmap(path.mnt), path.dentry->d_inode, - dentry, oldname); + dentry, oldname, NULL); end_creating_path(&path, dentry); return error; } @@ -233,7 +233,7 @@ int __init init_mkdir(const char *pathname, umode_t mode) error = security_path_mkdir(&path, dentry, mode); if (!error) { dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, - dentry, mode); + dentry, mode, NULL); if (IS_ERR(dentry)) error = PTR_ERR(dentry); } diff --git a/fs/inode.c b/fs/inode.c index ec9339024ac3..cc8265cfe80e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -233,7 +233,7 @@ int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; - inode->i_state = 0; + inode_state_assign_raw(inode, 0); atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; @@ -471,7 +471,7 @@ EXPORT_SYMBOL(set_nlink); void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { - WARN_ON(!(inode->i_state & I_LINKABLE)); + WARN_ON(!(inode_state_read_once(inode) & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } @@ -530,9 +530,48 @@ void ihold(struct inode *inode) } EXPORT_SYMBOL(ihold); -static void __inode_add_lru(struct inode *inode, bool rotate) +struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, + struct inode *inode, u32 bit) +{ + void *bit_address; + + bit_address = inode_state_wait_address(inode, bit); + init_wait_var_entry(wqe, bit_address, 0); + return __var_waitqueue(bit_address); +} +EXPORT_SYMBOL(inode_bit_waitqueue); + +void wait_on_new_inode(struct inode *inode) +{ + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + + spin_lock(&inode->i_lock); + if (!(inode_state_read(inode) & I_NEW)) { + spin_unlock(&inode->i_lock); + return; + } + + wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW); + for (;;) { + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); + if (!(inode_state_read(inode) & I_NEW)) + break; + spin_unlock(&inode->i_lock); + schedule(); + spin_lock(&inode->i_lock); + } + finish_wait(wq_head, &wqe.wq_entry); + WARN_ON(inode_state_read(inode) & I_NEW); + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL(wait_on_new_inode); + +static void __inode_lru_list_add(struct inode *inode, bool rotate) { - if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) + lockdep_assert_held(&inode->i_lock); + + if (inode_state_read(inode) & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) return; if (icount_read(inode)) return; @@ -544,32 +583,22 @@ static void __inode_add_lru(struct inode *inode, bool rotate) if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else if (rotate) - inode->i_state |= I_REFERENCED; -} - -struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, - struct inode *inode, u32 bit) -{ - void *bit_address; - - bit_address = inode_state_wait_address(inode, bit); - init_wait_var_entry(wqe, bit_address, 0); - return __var_waitqueue(bit_address); + inode_state_set(inode, I_REFERENCED); } -EXPORT_SYMBOL(inode_bit_waitqueue); /* * Add inode to LRU if needed (inode is unused and clean). - * - * Needs inode->i_lock held. */ -void inode_add_lru(struct inode *inode) +void inode_lru_list_add(struct inode *inode) { - __inode_add_lru(inode, false); + __inode_lru_list_add(inode, false); } static void inode_lru_list_del(struct inode *inode) { + if (list_empty(&inode->i_lru)) + return; + if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } @@ -577,15 +606,15 @@ static void inode_lru_list_del(struct inode *inode) static void inode_pin_lru_isolating(struct inode *inode) { lockdep_assert_held(&inode->i_lock); - WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); - inode->i_state |= I_LRU_ISOLATING; + WARN_ON(inode_state_read(inode) & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode_state_set(inode, I_LRU_ISOLATING); } static void inode_unpin_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); - WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); - inode->i_state &= ~I_LRU_ISOLATING; + WARN_ON(!(inode_state_read(inode) & I_LRU_ISOLATING)); + inode_state_clear(inode, I_LRU_ISOLATING); /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); @@ -597,7 +626,7 @@ static void inode_wait_for_lru_isolating(struct inode *inode) struct wait_queue_head *wq_head; lockdep_assert_held(&inode->i_lock); - if (!(inode->i_state & I_LRU_ISOLATING)) + if (!(inode_state_read(inode) & I_LRU_ISOLATING)) return; wq_head = inode_bit_waitqueue(&wqe, inode, __I_LRU_ISOLATING); @@ -607,14 +636,14 @@ static void inode_wait_for_lru_isolating(struct inode *inode) * Checking I_LRU_ISOLATING with inode->i_lock guarantees * memory ordering. */ - if (!(inode->i_state & I_LRU_ISOLATING)) + if (!(inode_state_read(inode) & I_LRU_ISOLATING)) break; spin_unlock(&inode->i_lock); schedule(); spin_lock(&inode->i_lock); } finish_wait(wq_head, &wqe.wq_entry); - WARN_ON(inode->i_state & I_LRU_ISOLATING); + WARN_ON(inode_state_read(inode) & I_LRU_ISOLATING); } /** @@ -761,11 +790,11 @@ void clear_inode(struct inode *inode) */ xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!list_empty(&inode->i_data.i_private_list)); - BUG_ON(!(inode->i_state & I_FREEING)); - BUG_ON(inode->i_state & I_CLEAR); + BUG_ON(!(inode_state_read_once(inode) & I_FREEING)); + BUG_ON(inode_state_read_once(inode) & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ - inode->i_state = I_FREEING | I_CLEAR; + inode_state_assign_raw(inode, I_FREEING | I_CLEAR); } EXPORT_SYMBOL(clear_inode); @@ -786,12 +815,10 @@ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; - BUG_ON(!(inode->i_state & I_FREEING)); + BUG_ON(!(inode_state_read_once(inode) & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); - if (!list_empty(&inode->i_io_list)) - inode_io_list_del(inode); - + inode_io_list_del(inode); inode_sb_list_del(inode); spin_lock(&inode->i_lock); @@ -829,7 +856,7 @@ static void evict(struct inode *inode) * This also means we don't need any fences for the call below. */ inode_wake_up_bit(inode, __I_NEW); - BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); + BUG_ON(inode_state_read_once(inode) != (I_FREEING | I_CLEAR)); destroy_inode(inode); } @@ -879,12 +906,12 @@ again: spin_unlock(&inode->i_lock); continue; } - if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + if (inode_state_read(inode) & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } - inode->i_state |= I_FREEING; + inode_state_set(inode, I_FREEING); inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); @@ -938,7 +965,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * sync, or the last page cache deletion will requeue them. */ if (icount_read(inode) || - (inode->i_state & ~I_REFERENCED) || + (inode_state_read(inode) & ~I_REFERENCED) || !mapping_shrinkable(&inode->i_data)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); @@ -947,8 +974,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, } /* Recently referenced inodes get one more pass */ - if (inode->i_state & I_REFERENCED) { - inode->i_state &= ~I_REFERENCED; + if (inode_state_read(inode) & I_REFERENCED) { + inode_state_clear(inode, I_REFERENCED); spin_unlock(&inode->i_lock); return LRU_ROTATE; } @@ -975,8 +1002,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_RETRY; } - WARN_ON(inode->i_state & I_NEW); - inode->i_state |= I_FREEING; + WARN_ON(inode_state_read(inode) & I_NEW); + inode_state_set(inode, I_FREEING); list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); @@ -1008,7 +1035,8 @@ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_lock static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), - void *data, bool is_inode_hash_locked) + void *data, bool is_inode_hash_locked, + bool *isnew) { struct inode *inode = NULL; @@ -1025,16 +1053,17 @@ repeat: if (!test(inode, data)) continue; spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE)) { + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE)) { __wait_on_freeing_inode(inode, is_inode_hash_locked); goto repeat; } - if (unlikely(inode->i_state & I_CREATING)) { + if (unlikely(inode_state_read(inode) & I_CREATING)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); + *isnew = !!(inode_state_read(inode) & I_NEW); spin_unlock(&inode->i_lock); rcu_read_unlock(); return inode; @@ -1049,7 +1078,7 @@ repeat: */ static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino, - bool is_inode_hash_locked) + bool is_inode_hash_locked, bool *isnew) { struct inode *inode = NULL; @@ -1066,16 +1095,17 @@ repeat: if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE)) { + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE)) { __wait_on_freeing_inode(inode, is_inode_hash_locked); goto repeat; } - if (unlikely(inode->i_state & I_CREATING)) { + if (unlikely(inode_state_read(inode) & I_CREATING)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); + *isnew = !!(inode_state_read(inode) & I_NEW); spin_unlock(&inode->i_lock); rcu_read_unlock(); return inode; @@ -1180,14 +1210,8 @@ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); - WARN_ON(!(inode->i_state & I_NEW)); - inode->i_state &= ~I_NEW & ~I_CREATING; - /* - * Pairs with the barrier in prepare_to_wait_event() to make sure - * ___wait_var_event() either sees the bit cleared or - * waitqueue_active() check in wake_up_var() sees the waiter. - */ - smp_mb(); + WARN_ON(!(inode_state_read(inode) & I_NEW)); + inode_state_clear(inode, I_NEW | I_CREATING); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } @@ -1197,14 +1221,8 @@ void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); - WARN_ON(!(inode->i_state & I_NEW)); - inode->i_state &= ~I_NEW; - /* - * Pairs with the barrier in prepare_to_wait_event() to make sure - * ___wait_var_event() either sees the bit cleared or - * waitqueue_active() check in wake_up_var() sees the waiter. - */ - smp_mb(); + WARN_ON(!(inode_state_read(inode) & I_NEW)); + inode_state_clear(inode, I_NEW); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); @@ -1260,6 +1278,7 @@ EXPORT_SYMBOL(unlock_two_nondirectories); * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set + * @isnew: pointer to a bool which will indicate whether I_NEW is set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present return it with an increased reference count. This is a @@ -1278,12 +1297,13 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; + bool isnew; might_sleep(); again: spin_lock(&inode_hash_lock); - old = find_inode(inode->i_sb, head, test, data, true); + old = find_inode(inode->i_sb, head, test, data, true, &isnew); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. @@ -1292,7 +1312,8 @@ again: spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; - wait_on_inode(old); + if (unlikely(isnew)) + wait_on_new_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; @@ -1310,7 +1331,7 @@ again: * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); - inode->i_state |= I_NEW; + inode_state_set(inode, I_NEW); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); @@ -1383,15 +1404,17 @@ struct inode *iget5_locked_rcu(struct super_block *sb, unsigned long hashval, { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *new; + bool isnew; might_sleep(); again: - inode = find_inode(sb, head, test, data, false); + inode = find_inode(sb, head, test, data, false, &isnew); if (inode) { if (IS_ERR(inode)) return NULL; - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1426,15 +1449,17 @@ struct inode *iget_locked(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; + bool isnew; might_sleep(); again: - inode = find_inode_fast(sb, head, ino, false); + inode = find_inode_fast(sb, head, ino, false, &isnew); if (inode) { if (IS_ERR(inode)) return NULL; - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1448,11 +1473,11 @@ again: spin_lock(&inode_hash_lock); /* We released the lock, so.. */ - old = find_inode_fast(sb, head, ino, true); + old = find_inode_fast(sb, head, ino, true, &isnew); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); - inode->i_state = I_NEW; + inode_state_assign(inode, I_NEW); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); @@ -1474,7 +1499,8 @@ again: if (IS_ERR(old)) return NULL; inode = old; - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1545,7 +1571,7 @@ EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); - if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { + if (!(inode_state_read(inode) & (I_FREEING | I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { @@ -1578,13 +1604,13 @@ EXPORT_SYMBOL(igrab); * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, - int (*test)(struct inode *, void *), void *data) + int (*test)(struct inode *, void *), void *data, bool *isnew) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); - inode = find_inode(sb, head, test, data, true); + inode = find_inode(sb, head, test, data, true, isnew); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; @@ -1612,13 +1638,15 @@ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; + bool isnew; might_sleep(); again: - inode = ilookup5_nowait(sb, hashval, test, data); + inode = ilookup5_nowait(sb, hashval, test, data, &isnew); if (inode) { - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1640,16 +1668,18 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; + bool isnew; might_sleep(); again: - inode = find_inode_fast(sb, head, ino, false); + inode = find_inode_fast(sb, head, ino, false, &isnew); if (inode) { if (IS_ERR(inode)) return NULL; - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1741,7 +1771,7 @@ struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval, hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb == sb && - !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) && + !(inode_state_read_once(inode) & (I_FREEING | I_WILL_FREE)) && test(inode, data)) return inode; } @@ -1780,7 +1810,7 @@ struct inode *find_inode_by_ino_rcu(struct super_block *sb, hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb && - !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE))) + !(inode_state_read_once(inode) & (I_FREEING | I_WILL_FREE))) return inode; } return NULL; @@ -1792,6 +1822,7 @@ int insert_inode_locked(struct inode *inode) struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); + bool isnew; might_sleep(); @@ -1804,7 +1835,7 @@ int insert_inode_locked(struct inode *inode) if (old->i_sb != sb) continue; spin_lock(&old->i_lock); - if (old->i_state & (I_FREEING|I_WILL_FREE)) { + if (inode_state_read(old) & (I_FREEING | I_WILL_FREE)) { spin_unlock(&old->i_lock); continue; } @@ -1812,21 +1843,23 @@ int insert_inode_locked(struct inode *inode) } if (likely(!old)) { spin_lock(&inode->i_lock); - inode->i_state |= I_NEW | I_CREATING; + inode_state_set(inode, I_NEW | I_CREATING); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } - if (unlikely(old->i_state & I_CREATING)) { + if (unlikely(inode_state_read(old) & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); + isnew = !!(inode_state_read(old) & I_NEW); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); - wait_on_inode(old); + if (isnew) + wait_on_new_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; @@ -1843,7 +1876,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, might_sleep(); - inode->i_state |= I_CREATING; + inode_state_set_raw(inode, I_CREATING); old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { @@ -1875,10 +1908,10 @@ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; - unsigned long state; int drop; - WARN_ON(inode->i_state & I_NEW); + WARN_ON(inode_state_read(inode) & I_NEW); + VFS_BUG_ON_INODE(atomic_read(&inode->i_count) != 0, inode); if (op->drop_inode) drop = op->drop_inode(inode); @@ -1886,29 +1919,33 @@ static void iput_final(struct inode *inode) drop = inode_generic_drop(inode); if (!drop && - !(inode->i_state & I_DONTCACHE) && + !(inode_state_read(inode) & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { - __inode_add_lru(inode, true); + __inode_lru_list_add(inode, true); spin_unlock(&inode->i_lock); return; } - state = inode->i_state; - if (!drop) { - WRITE_ONCE(inode->i_state, state | I_WILL_FREE); + /* + * Re-check ->i_count in case the ->drop_inode() hooks played games. + * Note we only execute this if the verdict was to drop the inode. + */ + VFS_BUG_ON_INODE(atomic_read(&inode->i_count) != 0, inode); + + if (drop) { + inode_state_set(inode, I_FREEING); + } else { + inode_state_set(inode, I_WILL_FREE); spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); - state = inode->i_state; - WARN_ON(state & I_NEW); - state &= ~I_WILL_FREE; + WARN_ON(inode_state_read(inode) & I_NEW); + inode_state_replace(inode, I_WILL_FREE, I_FREEING); } - WRITE_ONCE(inode->i_state, state | I_FREEING); - if (!list_empty(&inode->i_lru)) - inode_lru_list_del(inode); + inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); @@ -1931,7 +1968,7 @@ void iput(struct inode *inode) retry: lockdep_assert_not_held(&inode->i_lock); - VFS_BUG_ON_INODE(inode->i_state & I_CLEAR, inode); + VFS_BUG_ON_INODE(inode_state_read_once(inode) & I_CLEAR, inode); /* * Note this assert is technically racy as if the count is bogusly * equal to one, then two CPUs racing to further drop it can both @@ -1942,14 +1979,14 @@ retry: if (atomic_add_unless(&inode->i_count, -1, 1)) return; - if ((inode->i_state & I_DIRTY_TIME) && inode->i_nlink) { + if ((inode_state_read_once(inode) & I_DIRTY_TIME) && inode->i_nlink) { trace_writeback_lazytime_iput(inode); mark_inode_dirty_sync(inode); goto retry; } spin_lock(&inode->i_lock); - if (unlikely((inode->i_state & I_DIRTY_TIME) && inode->i_nlink)) { + if (unlikely((inode_state_read(inode) & I_DIRTY_TIME) && inode->i_nlink)) { spin_unlock(&inode->i_lock); goto retry; } @@ -1967,6 +2004,18 @@ retry: } EXPORT_SYMBOL(iput); +/** + * iput_not_last - put an inode assuming this is not the last reference + * @inode: inode to put + */ +void iput_not_last(struct inode *inode) +{ + VFS_BUG_ON_INODE(atomic_read(&inode->i_count) < 2, inode); + + WARN_ON(atomic_sub_return(1, &inode->i_count) == 0); +} +EXPORT_SYMBOL(iput_not_last); + #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file @@ -2310,42 +2359,40 @@ out: } EXPORT_SYMBOL(current_time); -static int inode_needs_update_time(struct inode *inode) +static int file_update_time_flags(struct file *file, unsigned int flags) { + struct inode *inode = file_inode(file); struct timespec64 now, ts; - int sync_it = 0; + int sync_mode = 0; + int ret = 0; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; + if (unlikely(file->f_mode & FMODE_NOCMTIME)) + return 0; now = current_time(inode); ts = inode_get_mtime(inode); if (!timespec64_equal(&ts, &now)) - sync_it |= S_MTIME; - + sync_mode |= S_MTIME; ts = inode_get_ctime(inode); if (!timespec64_equal(&ts, &now)) - sync_it |= S_CTIME; - + sync_mode |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) - sync_it |= S_VERSION; + sync_mode |= S_VERSION; - return sync_it; -} - -static int __file_update_time(struct file *file, int sync_mode) -{ - int ret = 0; - struct inode *inode = file_inode(file); + if (!sync_mode) + return 0; - /* try to update time settings */ - if (!mnt_get_write_access_file(file)) { - ret = inode_update_time(inode, sync_mode); - mnt_put_write_access_file(file); - } + if (flags & IOCB_NOWAIT) + return -EAGAIN; + if (mnt_get_write_access_file(file)) + return 0; + ret = inode_update_time(inode, sync_mode); + mnt_put_write_access_file(file); return ret; } @@ -2365,14 +2412,7 @@ static int __file_update_time(struct file *file, int sync_mode) */ int file_update_time(struct file *file) { - int ret; - struct inode *inode = file_inode(file); - - ret = inode_needs_update_time(inode); - if (ret <= 0) - return ret; - - return __file_update_time(file, ret); + return file_update_time_flags(file, 0); } EXPORT_SYMBOL(file_update_time); @@ -2394,7 +2434,6 @@ EXPORT_SYMBOL(file_update_time); static int file_modified_flags(struct file *file, int flags) { int ret; - struct inode *inode = file_inode(file); /* * Clear the security bits if the process is not being run by root. @@ -2403,17 +2442,7 @@ static int file_modified_flags(struct file *file, int flags) ret = file_remove_privs_flags(file, flags); if (ret) return ret; - - if (unlikely(file->f_mode & FMODE_NOCMTIME)) - return 0; - - ret = inode_needs_update_time(inode); - if (ret <= 0) - return ret; - if (flags & IOCB_NOWAIT) - return -EAGAIN; - - return __file_update_time(file, ret); + return file_update_time_flags(file, flags); } /** @@ -2970,7 +2999,7 @@ void dump_inode(struct inode *inode, const char *reason) pr_warn("%s encountered for inode %px\n" "fs %s mode %ho opflags 0x%hx flags 0x%x state 0x%x count %d\n", reason, inode, sb->s_type->name, inode->i_mode, inode->i_opflags, - inode->i_flags, inode->i_state, atomic_read(&inode->i_count)); + inode->i_flags, inode_state_read_once(inode), atomic_read(&inode->i_count)); } EXPORT_SYMBOL(dump_inode); diff --git a/fs/internal.h b/fs/internal.h index 9b2b4d116880..d08d5e2235e9 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -67,6 +67,9 @@ int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode); struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); +struct dentry *start_dirop(struct dentry *parent, struct qstr *name, + unsigned int lookup_flags); +int lookup_noperm_common(struct qstr *qname, struct dentry *base); /* * namespace.c diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile index f7e1c8534c46..a572b8808524 100644 --- a/fs/iomap/Makefile +++ b/fs/iomap/Makefile @@ -14,5 +14,6 @@ iomap-y += trace.o \ iomap-$(CONFIG_BLOCK) += direct-io.o \ ioend.o \ fiemap.o \ - seek.o + seek.o \ + bio.o iomap-$(CONFIG_SWAP) += swapfile.o diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c new file mode 100644 index 000000000000..fc045f2e4c45 --- /dev/null +++ b/fs/iomap/bio.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010 Red Hat, Inc. + * Copyright (C) 2016-2023 Christoph Hellwig. + */ +#include <linux/iomap.h> +#include <linux/pagemap.h> +#include "internal.h" +#include "trace.h" + +static void iomap_read_end_io(struct bio *bio) +{ + int error = blk_status_to_errno(bio->bi_status); + struct folio_iter fi; + + bio_for_each_folio_all(fi, bio) + iomap_finish_folio_read(fi.folio, fi.offset, fi.length, error); + bio_put(bio); +} + +static void iomap_bio_submit_read(struct iomap_read_folio_ctx *ctx) +{ + struct bio *bio = ctx->read_ctx; + + if (bio) + submit_bio(bio); +} + +static int iomap_bio_read_folio_range(const struct iomap_iter *iter, + struct iomap_read_folio_ctx *ctx, size_t plen) +{ + struct folio *folio = ctx->cur_folio; + const struct iomap *iomap = &iter->iomap; + loff_t pos = iter->pos; + size_t poff = offset_in_folio(folio, pos); + loff_t length = iomap_length(iter); + sector_t sector; + struct bio *bio = ctx->read_ctx; + + sector = iomap_sector(iomap, pos); + if (!bio || bio_end_sector(bio) != sector || + !bio_add_folio(bio, folio, plen, poff)) { + gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL); + gfp_t orig_gfp = gfp; + unsigned int nr_vecs = DIV_ROUND_UP(length, PAGE_SIZE); + + if (bio) + submit_bio(bio); + + if (ctx->rac) /* same as readahead_gfp_mask */ + gfp |= __GFP_NORETRY | __GFP_NOWARN; + bio = bio_alloc(iomap->bdev, bio_max_segs(nr_vecs), REQ_OP_READ, + gfp); + /* + * If the bio_alloc fails, try it again for a single page to + * avoid having to deal with partial page reads. This emulates + * what do_mpage_read_folio does. + */ + if (!bio) + bio = bio_alloc(iomap->bdev, 1, REQ_OP_READ, orig_gfp); + if (ctx->rac) + bio->bi_opf |= REQ_RAHEAD; + bio->bi_iter.bi_sector = sector; + bio->bi_end_io = iomap_read_end_io; + bio_add_folio_nofail(bio, folio, plen, poff); + ctx->read_ctx = bio; + } + return 0; +} + +const struct iomap_read_ops iomap_bio_read_ops = { + .read_folio_range = iomap_bio_read_folio_range, + .submit_read = iomap_bio_submit_read, +}; +EXPORT_SYMBOL_GPL(iomap_bio_read_ops); + +int iomap_bio_read_folio_range_sync(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, size_t len) +{ + const struct iomap *srcmap = iomap_iter_srcmap(iter); + struct bio_vec bvec; + struct bio bio; + + bio_init(&bio, srcmap->bdev, &bvec, 1, REQ_OP_READ); + bio.bi_iter.bi_sector = iomap_sector(srcmap, pos); + bio_add_folio_nofail(&bio, folio, len, offset_in_folio(folio, pos)); + return submit_bio_wait(&bio); +} diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 8b847a1e27f1..e5c1ca440d93 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -8,6 +8,7 @@ #include <linux/writeback.h> #include <linux/swap.h> #include <linux/migrate.h> +#include "internal.h" #include "trace.h" #include "../internal.h" @@ -37,10 +38,28 @@ static inline bool ifs_is_fully_uptodate(struct folio *folio, return bitmap_full(ifs->state, i_blocks_per_folio(inode, folio)); } -static inline bool ifs_block_is_uptodate(struct iomap_folio_state *ifs, - unsigned int block) +/* + * Find the next uptodate block in the folio. end_blk is inclusive. + * If no uptodate block is found, this will return end_blk + 1. + */ +static unsigned ifs_next_uptodate_block(struct folio *folio, + unsigned start_blk, unsigned end_blk) +{ + struct iomap_folio_state *ifs = folio->private; + + return find_next_bit(ifs->state, end_blk + 1, start_blk); +} + +/* + * Find the next non-uptodate block in the folio. end_blk is inclusive. + * If no non-uptodate block is found, this will return end_blk + 1. + */ +static unsigned ifs_next_nonuptodate_block(struct folio *folio, + unsigned start_blk, unsigned end_blk) { - return test_bit(block, ifs->state); + struct iomap_folio_state *ifs = folio->private; + + return find_next_zero_bit(ifs->state, end_blk + 1, start_blk); } static bool ifs_set_range_uptodate(struct folio *folio, @@ -75,13 +94,34 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off, folio_mark_uptodate(folio); } -static inline bool ifs_block_is_dirty(struct folio *folio, - struct iomap_folio_state *ifs, int block) +/* + * Find the next dirty block in the folio. end_blk is inclusive. + * If no dirty block is found, this will return end_blk + 1. + */ +static unsigned ifs_next_dirty_block(struct folio *folio, + unsigned start_blk, unsigned end_blk) { + struct iomap_folio_state *ifs = folio->private; struct inode *inode = folio->mapping->host; - unsigned int blks_per_folio = i_blocks_per_folio(inode, folio); + unsigned int blks = i_blocks_per_folio(inode, folio); + + return find_next_bit(ifs->state, blks + end_blk + 1, + blks + start_blk) - blks; +} + +/* + * Find the next clean block in the folio. end_blk is inclusive. + * If no clean block is found, this will return end_blk + 1. + */ +static unsigned ifs_next_clean_block(struct folio *folio, + unsigned start_blk, unsigned end_blk) +{ + struct iomap_folio_state *ifs = folio->private; + struct inode *inode = folio->mapping->host; + unsigned int blks = i_blocks_per_folio(inode, folio); - return test_bit(block + blks_per_folio, ifs->state); + return find_next_zero_bit(ifs->state, blks + end_blk + 1, + blks + start_blk) - blks; } static unsigned ifs_find_dirty_range(struct folio *folio, @@ -92,18 +132,17 @@ static unsigned ifs_find_dirty_range(struct folio *folio, offset_in_folio(folio, *range_start) >> inode->i_blkbits; unsigned end_blk = min_not_zero( offset_in_folio(folio, range_end) >> inode->i_blkbits, - i_blocks_per_folio(inode, folio)); - unsigned nblks = 1; + i_blocks_per_folio(inode, folio)) - 1; + unsigned nblks; - while (!ifs_block_is_dirty(folio, ifs, start_blk)) - if (++start_blk == end_blk) - return 0; - - while (start_blk + nblks < end_blk) { - if (!ifs_block_is_dirty(folio, ifs, start_blk + nblks)) - break; - nblks++; - } + start_blk = ifs_next_dirty_block(folio, start_blk, end_blk); + if (start_blk > end_blk) + return 0; + if (start_blk == end_blk) + nblks = 1; + else + nblks = ifs_next_clean_block(folio, start_blk + 1, end_blk) - + start_blk; *range_start = folio_pos(folio) + (start_blk << inode->i_blkbits); return nblks << inode->i_blkbits; @@ -218,6 +257,22 @@ static void ifs_free(struct folio *folio) } /* + * Calculate how many bytes to truncate based off the number of blocks to + * truncate and the end position to start truncating from. + */ +static size_t iomap_bytes_to_truncate(loff_t end_pos, unsigned block_bits, + unsigned blocks_truncated) +{ + unsigned block_size = 1 << block_bits; + unsigned block_offset = end_pos & (block_size - 1); + + if (!block_offset) + return blocks_truncated << block_bits; + + return ((blocks_truncated - 1) << block_bits) + block_offset; +} + +/* * Calculate the range inside the folio that we actually need to read. */ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, @@ -240,24 +295,29 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, * to avoid reading in already uptodate ranges. */ if (ifs) { - unsigned int i; - - /* move forward for each leading block marked uptodate */ - for (i = first; i <= last; i++) { - if (!ifs_block_is_uptodate(ifs, i)) - break; - *pos += block_size; - poff += block_size; - plen -= block_size; - first++; + unsigned int next, blocks_skipped; + + next = ifs_next_nonuptodate_block(folio, first, last); + blocks_skipped = next - first; + + if (blocks_skipped) { + unsigned long block_offset = *pos & (block_size - 1); + unsigned bytes_skipped = + (blocks_skipped << block_bits) - block_offset; + + *pos += bytes_skipped; + poff += bytes_skipped; + plen -= bytes_skipped; } + first = next; /* truncate len if we find any trailing uptodate block(s) */ - while (++i <= last) { - if (ifs_block_is_uptodate(ifs, i)) { - plen -= (last - i + 1) * block_size; - last = i - 1; - break; + if (++next <= last) { + next = ifs_next_uptodate_block(folio, next, last); + if (next <= last) { + plen -= iomap_bytes_to_truncate(*pos + plen, + block_bits, last - next + 1); + last = next - 1; } } } @@ -271,7 +331,8 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, unsigned end = offset_in_folio(folio, isize - 1) >> block_bits; if (first <= end && last > end) - plen -= (last - end) * block_size; + plen -= iomap_bytes_to_truncate(*pos + plen, block_bits, + last - end); } *offp = poff; @@ -320,9 +381,8 @@ static int iomap_read_inline_data(const struct iomap_iter *iter, return 0; } -#ifdef CONFIG_BLOCK -static void iomap_finish_folio_read(struct folio *folio, size_t off, - size_t len, int error) +void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len, + int error) { struct iomap_folio_state *ifs = folio->private; bool uptodate = !error; @@ -342,169 +402,201 @@ static void iomap_finish_folio_read(struct folio *folio, size_t off, if (finished) folio_end_read(folio, uptodate); } +EXPORT_SYMBOL_GPL(iomap_finish_folio_read); -static void iomap_read_end_io(struct bio *bio) +static void iomap_read_init(struct folio *folio) { - int error = blk_status_to_errno(bio->bi_status); - struct folio_iter fi; + struct iomap_folio_state *ifs = folio->private; - bio_for_each_folio_all(fi, bio) - iomap_finish_folio_read(fi.folio, fi.offset, fi.length, error); - bio_put(bio); + if (ifs) { + size_t len = folio_size(folio); + + /* + * ifs->read_bytes_pending is used to track how many bytes are + * read in asynchronously by the IO helper. We need to track + * this so that we can know when the IO helper has finished + * reading in all the necessary ranges of the folio and can end + * the read. + * + * Increase ->read_bytes_pending by the folio size to start, and + * add a +1 bias. We'll subtract the bias and any uptodate / + * zeroed ranges that did not require IO in iomap_read_end() + * after we're done processing the folio. + * + * We do this because otherwise, we would have to increment + * ifs->read_bytes_pending every time a range in the folio needs + * to be read in, which can get expensive since the spinlock + * needs to be held whenever modifying ifs->read_bytes_pending. + * + * We add the bias to ensure the read has not been ended on the + * folio when iomap_read_end() is called, even if the IO helper + * has already finished reading in the entire folio. + */ + spin_lock_irq(&ifs->state_lock); + WARN_ON_ONCE(ifs->read_bytes_pending != 0); + ifs->read_bytes_pending = len + 1; + spin_unlock_irq(&ifs->state_lock); + } } -struct iomap_readpage_ctx { - struct folio *cur_folio; - bool cur_folio_in_bio; - struct bio *bio; - struct readahead_control *rac; -}; +/* + * This ends IO if no bytes were submitted to an IO helper. + * + * Otherwise, this calibrates ifs->read_bytes_pending to represent only the + * submitted bytes (see comment in iomap_read_init()). If all bytes submitted + * have already been completed by the IO helper, then this will end the read. + * Else the IO helper will end the read after all submitted ranges have been + * read. + */ +static void iomap_read_end(struct folio *folio, size_t bytes_submitted) +{ + struct iomap_folio_state *ifs = folio->private; -static int iomap_readpage_iter(struct iomap_iter *iter, - struct iomap_readpage_ctx *ctx) + if (ifs) { + bool end_read, uptodate; + + spin_lock_irq(&ifs->state_lock); + if (!ifs->read_bytes_pending) { + WARN_ON_ONCE(bytes_submitted); + spin_unlock_irq(&ifs->state_lock); + folio_unlock(folio); + return; + } + + /* + * Subtract any bytes that were initially accounted to + * read_bytes_pending but skipped for IO. The +1 accounts for + * the bias we added in iomap_read_init(). + */ + ifs->read_bytes_pending -= + (folio_size(folio) + 1 - bytes_submitted); + + /* + * If !ifs->read_bytes_pending, this means all pending reads by + * the IO helper have already completed, which means we need to + * end the folio read here. If ifs->read_bytes_pending != 0, + * the IO helper will end the folio read. + */ + end_read = !ifs->read_bytes_pending; + if (end_read) + uptodate = ifs_is_fully_uptodate(folio, ifs); + spin_unlock_irq(&ifs->state_lock); + if (end_read) + folio_end_read(folio, uptodate); + } else if (!bytes_submitted) { + /* + * If there were no bytes submitted, this means we are + * responsible for unlocking the folio here, since no IO helper + * has taken ownership of it. If there were bytes submitted, + * then the IO helper will end the read via + * iomap_finish_folio_read(). + */ + folio_unlock(folio); + } +} + +static int iomap_read_folio_iter(struct iomap_iter *iter, + struct iomap_read_folio_ctx *ctx, size_t *bytes_submitted) { const struct iomap *iomap = &iter->iomap; loff_t pos = iter->pos; loff_t length = iomap_length(iter); struct folio *folio = ctx->cur_folio; - struct iomap_folio_state *ifs; size_t poff, plen; - sector_t sector; + loff_t pos_diff; int ret; if (iomap->type == IOMAP_INLINE) { ret = iomap_read_inline_data(iter, folio); if (ret) return ret; - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, length); } - /* zero post-eof blocks as the page may be mapped */ - ifs = ifs_alloc(iter->inode, folio, iter->flags); - iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, &plen); - if (plen == 0) - goto done; + ifs_alloc(iter->inode, folio, iter->flags); - if (iomap_block_needs_zeroing(iter, pos)) { - folio_zero_range(folio, poff, plen); - iomap_set_range_uptodate(folio, poff, plen); - goto done; - } + length = min_t(loff_t, length, + folio_size(folio) - offset_in_folio(folio, pos)); + while (length) { + iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, + &plen); - ctx->cur_folio_in_bio = true; - if (ifs) { - spin_lock_irq(&ifs->state_lock); - ifs->read_bytes_pending += plen; - spin_unlock_irq(&ifs->state_lock); - } + pos_diff = pos - iter->pos; + if (WARN_ON_ONCE(pos_diff + plen > length)) + return -EIO; - sector = iomap_sector(iomap, pos); - if (!ctx->bio || - bio_end_sector(ctx->bio) != sector || - !bio_add_folio(ctx->bio, folio, plen, poff)) { - gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL); - gfp_t orig_gfp = gfp; - unsigned int nr_vecs = DIV_ROUND_UP(length, PAGE_SIZE); - - if (ctx->bio) - submit_bio(ctx->bio); - - if (ctx->rac) /* same as readahead_gfp_mask */ - gfp |= __GFP_NORETRY | __GFP_NOWARN; - ctx->bio = bio_alloc(iomap->bdev, bio_max_segs(nr_vecs), - REQ_OP_READ, gfp); - /* - * If the bio_alloc fails, try it again for a single page to - * avoid having to deal with partial page reads. This emulates - * what do_mpage_read_folio does. - */ - if (!ctx->bio) { - ctx->bio = bio_alloc(iomap->bdev, 1, REQ_OP_READ, - orig_gfp); - } - if (ctx->rac) - ctx->bio->bi_opf |= REQ_RAHEAD; - ctx->bio->bi_iter.bi_sector = sector; - ctx->bio->bi_end_io = iomap_read_end_io; - bio_add_folio_nofail(ctx->bio, folio, plen, poff); - } + ret = iomap_iter_advance(iter, pos_diff); + if (ret) + return ret; -done: - /* - * Move the caller beyond our range so that it keeps making progress. - * For that, we have to include any leading non-uptodate ranges, but - * we can skip trailing ones as they will be handled in the next - * iteration. - */ - length = pos - iter->pos + plen; - return iomap_iter_advance(iter, &length); -} + if (plen == 0) + return 0; -static int iomap_read_folio_iter(struct iomap_iter *iter, - struct iomap_readpage_ctx *ctx) -{ - int ret; + /* zero post-eof blocks as the page may be mapped */ + if (iomap_block_needs_zeroing(iter, pos)) { + folio_zero_range(folio, poff, plen); + iomap_set_range_uptodate(folio, poff, plen); + } else { + if (!*bytes_submitted) + iomap_read_init(folio); + ret = ctx->ops->read_folio_range(iter, ctx, plen); + if (ret) + return ret; + *bytes_submitted += plen; + } - while (iomap_length(iter)) { - ret = iomap_readpage_iter(iter, ctx); + ret = iomap_iter_advance(iter, plen); if (ret) return ret; + length -= pos_diff + plen; + pos = iter->pos; } - return 0; } -int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops) +void iomap_read_folio(const struct iomap_ops *ops, + struct iomap_read_folio_ctx *ctx) { + struct folio *folio = ctx->cur_folio; struct iomap_iter iter = { .inode = folio->mapping->host, .pos = folio_pos(folio), .len = folio_size(folio), }; - struct iomap_readpage_ctx ctx = { - .cur_folio = folio, - }; + size_t bytes_submitted = 0; int ret; trace_iomap_readpage(iter.inode, 1); while ((ret = iomap_iter(&iter, ops)) > 0) - iter.status = iomap_read_folio_iter(&iter, &ctx); + iter.status = iomap_read_folio_iter(&iter, ctx, + &bytes_submitted); - if (ctx.bio) { - submit_bio(ctx.bio); - WARN_ON_ONCE(!ctx.cur_folio_in_bio); - } else { - WARN_ON_ONCE(ctx.cur_folio_in_bio); - folio_unlock(folio); - } + if (ctx->ops->submit_read) + ctx->ops->submit_read(ctx); - /* - * Just like mpage_readahead and block_read_full_folio, we always - * return 0 and just set the folio error flag on errors. This - * should be cleaned up throughout the stack eventually. - */ - return 0; + iomap_read_end(folio, bytes_submitted); } EXPORT_SYMBOL_GPL(iomap_read_folio); static int iomap_readahead_iter(struct iomap_iter *iter, - struct iomap_readpage_ctx *ctx) + struct iomap_read_folio_ctx *ctx, size_t *cur_bytes_submitted) { int ret; while (iomap_length(iter)) { if (ctx->cur_folio && offset_in_folio(ctx->cur_folio, iter->pos) == 0) { - if (!ctx->cur_folio_in_bio) - folio_unlock(ctx->cur_folio); + iomap_read_end(ctx->cur_folio, *cur_bytes_submitted); ctx->cur_folio = NULL; } if (!ctx->cur_folio) { ctx->cur_folio = readahead_folio(ctx->rac); - ctx->cur_folio_in_bio = false; + if (WARN_ON_ONCE(!ctx->cur_folio)) + return -EINVAL; + *cur_bytes_submitted = 0; } - ret = iomap_readpage_iter(iter, ctx); + ret = iomap_read_folio_iter(iter, ctx, cur_bytes_submitted); if (ret) return ret; } @@ -514,8 +606,8 @@ static int iomap_readahead_iter(struct iomap_iter *iter, /** * iomap_readahead - Attempt to read pages from a file. - * @rac: Describes the pages to be read. * @ops: The operations vector for the filesystem. + * @ctx: The ctx used for issuing readahead. * * This function is for filesystems to call to implement their readahead * address_space operation. @@ -527,51 +619,30 @@ static int iomap_readahead_iter(struct iomap_iter *iter, * function is called with memalloc_nofs set, so allocations will not cause * the filesystem to be reentered. */ -void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) +void iomap_readahead(const struct iomap_ops *ops, + struct iomap_read_folio_ctx *ctx) { + struct readahead_control *rac = ctx->rac; struct iomap_iter iter = { .inode = rac->mapping->host, .pos = readahead_pos(rac), .len = readahead_length(rac), }; - struct iomap_readpage_ctx ctx = { - .rac = rac, - }; + size_t cur_bytes_submitted; trace_iomap_readahead(rac->mapping->host, readahead_count(rac)); while (iomap_iter(&iter, ops) > 0) - iter.status = iomap_readahead_iter(&iter, &ctx); + iter.status = iomap_readahead_iter(&iter, ctx, + &cur_bytes_submitted); - if (ctx.bio) - submit_bio(ctx.bio); - if (ctx.cur_folio) { - if (!ctx.cur_folio_in_bio) - folio_unlock(ctx.cur_folio); - } -} -EXPORT_SYMBOL_GPL(iomap_readahead); - -static int iomap_read_folio_range(const struct iomap_iter *iter, - struct folio *folio, loff_t pos, size_t len) -{ - const struct iomap *srcmap = iomap_iter_srcmap(iter); - struct bio_vec bvec; - struct bio bio; + if (ctx->ops->submit_read) + ctx->ops->submit_read(ctx); - bio_init(&bio, srcmap->bdev, &bvec, 1, REQ_OP_READ); - bio.bi_iter.bi_sector = iomap_sector(srcmap, pos); - bio_add_folio_nofail(&bio, folio, len, offset_in_folio(folio, pos)); - return submit_bio_wait(&bio); + if (ctx->cur_folio) + iomap_read_end(ctx->cur_folio, cur_bytes_submitted); } -#else -static int iomap_read_folio_range(const struct iomap_iter *iter, - struct folio *folio, loff_t pos, size_t len) -{ - WARN_ON_ONCE(1); - return -EIO; -} -#endif /* CONFIG_BLOCK */ +EXPORT_SYMBOL_GPL(iomap_readahead); /* * iomap_is_partially_uptodate checks whether blocks within a folio are @@ -584,7 +655,7 @@ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { struct iomap_folio_state *ifs = folio->private; struct inode *inode = folio->mapping->host; - unsigned first, last, i; + unsigned first, last; if (!ifs) return false; @@ -596,10 +667,7 @@ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count) first = from >> inode->i_blkbits; last = (from + count - 1) >> inode->i_blkbits; - for (i = first; i <= last; i++) - if (!ifs_block_is_uptodate(ifs, i)) - return false; - return true; + return ifs_next_nonuptodate_block(folio, first, last) > last; } EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); @@ -707,7 +775,7 @@ static int __iomap_write_begin(const struct iomap_iter *iter, * are not changing pagecache contents. */ if (!(iter->flags & IOMAP_UNSHARE) && pos <= folio_pos(folio) && - pos + len >= folio_pos(folio) + folio_size(folio)) + pos + len >= folio_next_pos(folio)) return 0; ifs = ifs_alloc(iter->inode, folio, iter->flags); @@ -723,9 +791,12 @@ static int __iomap_write_begin(const struct iomap_iter *iter, if (plen == 0) break; - if (!(iter->flags & IOMAP_UNSHARE) && - (from <= poff || from >= poff + plen) && - (to <= poff || to >= poff + plen)) + /* + * If the read range will be entirely overwritten by the write, + * we can skip having to zero/read it in. + */ + if (!(iter->flags & IOMAP_UNSHARE) && from <= poff && + to >= poff + plen) continue; if (iomap_block_needs_zeroing(iter, block_start)) { @@ -742,7 +813,7 @@ static int __iomap_write_begin(const struct iomap_iter *iter, status = write_ops->read_folio_range(iter, folio, block_start, plen); else - status = iomap_read_folio_range(iter, + status = iomap_bio_read_folio_range_sync(iter, folio, block_start, plen); if (status) return status; @@ -761,6 +832,28 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, if (!mapping_large_folio_support(iter->inode->i_mapping)) len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); + if (iter->fbatch) { + struct folio *folio = folio_batch_next(iter->fbatch); + + if (!folio) + return NULL; + + /* + * The folio mapping generally shouldn't have changed based on + * fs locks, but be consistent with filemap lookup and retry + * the iter if it does. + */ + folio_lock(folio); + if (unlikely(folio->mapping != iter->inode->i_mapping)) { + iter->iomap.flags |= IOMAP_F_STALE; + folio_unlock(folio); + return NULL; + } + + folio_get(folio); + return folio; + } + if (write_ops && write_ops->get_folio) return write_ops->get_folio(iter, pos, len); return iomap_get_folio(iter, pos, len); @@ -815,15 +908,14 @@ static int iomap_write_begin(struct iomap_iter *iter, size_t *poffset, u64 *plen) { const struct iomap *srcmap = iomap_iter_srcmap(iter); - loff_t pos = iter->pos; + loff_t pos; u64 len = min_t(u64, SIZE_MAX, iomap_length(iter)); struct folio *folio; int status = 0; len = min_not_zero(len, *plen); - BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length); - if (srcmap != &iter->iomap) - BUG_ON(pos + len > srcmap->offset + srcmap->length); + *foliop = NULL; + *plen = 0; if (fatal_signal_pending(current)) return -EINTR; @@ -833,6 +925,15 @@ static int iomap_write_begin(struct iomap_iter *iter, return PTR_ERR(folio); /* + * No folio means we're done with a batch. We still have range to + * process so return and let the caller iterate and refill the batch. + */ + if (!folio) { + WARN_ON_ONCE(!iter->fbatch); + return 0; + } + + /* * Now we have a locked folio, before we do anything with it we need to * check that the iomap we have cached is not stale. The inode extent * mapping can change due to concurrent IO in flight (e.g. @@ -852,6 +953,22 @@ static int iomap_write_begin(struct iomap_iter *iter, } } + /* + * The folios in a batch may not be contiguous. If we've skipped + * forward, advance the iter to the pos of the current folio. If the + * folio starts beyond the end of the mapping, it may have been trimmed + * since the lookup for whatever reason. Return a NULL folio to + * terminate the op. + */ + if (folio_pos(folio) > iter->pos) { + len = min_t(u64, folio_pos(folio) - iter->pos, + iomap_length(iter)); + status = iomap_iter_advance(iter, len); + len = iomap_length(iter); + if (status || !len) + goto out_unlock; + } + pos = iomap_trim_folio_range(iter, folio, poffset, &len); if (srcmap->type == IOMAP_INLINE) @@ -1041,7 +1158,7 @@ retry: } } else { total_written += written; - iomap_iter_advance(iter, &written); + iomap_iter_advance(iter, written); } } while (iov_iter_count(i) && iomap_length(iter)); @@ -1082,7 +1199,7 @@ static void iomap_write_delalloc_ifs_punch(struct inode *inode, struct folio *folio, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { - unsigned int first_blk, last_blk, i; + unsigned int first_blk, last_blk; loff_t last_byte; u8 blkbits = inode->i_blkbits; struct iomap_folio_state *ifs; @@ -1097,14 +1214,14 @@ static void iomap_write_delalloc_ifs_punch(struct inode *inode, if (!ifs) return; - last_byte = min_t(loff_t, end_byte - 1, - folio_pos(folio) + folio_size(folio) - 1); + last_byte = min_t(loff_t, end_byte - 1, folio_next_pos(folio) - 1); first_blk = offset_in_folio(folio, start_byte) >> blkbits; last_blk = offset_in_folio(folio, last_byte) >> blkbits; - for (i = first_blk; i <= last_blk; i++) { - if (!ifs_block_is_dirty(folio, ifs, i)) - punch(inode, folio_pos(folio) + (i << blkbits), - 1 << blkbits, iomap); + while ((first_blk = ifs_next_clean_block(folio, first_blk, last_blk)) + <= last_blk) { + punch(inode, folio_pos(folio) + (first_blk << blkbits), + 1 << blkbits, iomap); + first_blk++; } } @@ -1129,8 +1246,7 @@ static void iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, * Make sure the next punch start is correctly bound to * the end of this data range, not the end of the folio. */ - *punch_start_byte = min_t(loff_t, end_byte, - folio_pos(folio) + folio_size(folio)); + *punch_start_byte = min_t(loff_t, end_byte, folio_next_pos(folio)); } /* @@ -1170,7 +1286,7 @@ static void iomap_write_delalloc_scan(struct inode *inode, start_byte, end_byte, iomap, punch); /* move offset to start of next folio in range */ - start_byte = folio_pos(folio) + folio_size(folio); + start_byte = folio_next_pos(folio); folio_unlock(folio); folio_put(folio); } @@ -1310,7 +1426,7 @@ static int iomap_unshare_iter(struct iomap_iter *iter, int status; if (!iomap_want_unshare_iter(iter)) - return iomap_iter_advance(iter, &bytes); + return iomap_iter_advance(iter, bytes); do { struct folio *folio; @@ -1334,10 +1450,10 @@ static int iomap_unshare_iter(struct iomap_iter *iter, balance_dirty_pages_ratelimited(iter->inode->i_mapping); - status = iomap_iter_advance(iter, &bytes); + status = iomap_iter_advance(iter, bytes); if (status) break; - } while (bytes > 0); + } while ((bytes = iomap_length(iter)) > 0); return status; } @@ -1398,6 +1514,12 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero, if (iter->iomap.flags & IOMAP_F_STALE) break; + /* a NULL folio means we're done with a folio batch */ + if (!folio) { + status = iomap_iter_advance_full(iter); + break; + } + /* warn about zeroing folios beyond eof that won't write back */ WARN_ON_ONCE(folio_pos(folio) > iter->inode->i_size); @@ -1412,16 +1534,36 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero, if (WARN_ON_ONCE(!ret)) return -EIO; - status = iomap_iter_advance(iter, &bytes); + status = iomap_iter_advance(iter, bytes); if (status) break; - } while (bytes > 0); + } while ((bytes = iomap_length(iter)) > 0); if (did_zero) *did_zero = true; return status; } +loff_t +iomap_fill_dirty_folios( + struct iomap_iter *iter, + loff_t offset, + loff_t length) +{ + struct address_space *mapping = iter->inode->i_mapping; + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + length - 1) >> PAGE_SHIFT; + + iter->fbatch = kmalloc(sizeof(struct folio_batch), GFP_KERNEL); + if (!iter->fbatch) + return offset + length; + folio_batch_init(iter->fbatch); + + filemap_get_folios_dirty(mapping, &start, end, iter->fbatch); + return (start << PAGE_SHIFT); +} +EXPORT_SYMBOL_GPL(iomap_fill_dirty_folios); + int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops, @@ -1435,46 +1577,26 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, .private = private, }; struct address_space *mapping = inode->i_mapping; - unsigned int blocksize = i_blocksize(inode); - unsigned int off = pos & (blocksize - 1); - loff_t plen = min_t(loff_t, len, blocksize - off); int ret; bool range_dirty; /* - * Zero range can skip mappings that are zero on disk so long as - * pagecache is clean. If pagecache was dirty prior to zero range, the - * mapping converts on writeback completion and so must be zeroed. - * - * The simplest way to deal with this across a range is to flush - * pagecache and process the updated mappings. To avoid excessive - * flushing on partial eof zeroing, special case it to zero the - * unaligned start portion if already dirty in pagecache. - */ - if (off && - filemap_range_needs_writeback(mapping, pos, pos + plen - 1)) { - iter.len = plen; - while ((ret = iomap_iter(&iter, ops)) > 0) - iter.status = iomap_zero_iter(&iter, did_zero, - write_ops); - - iter.len = len - (iter.pos - pos); - if (ret || !iter.len) - return ret; - } - - /* * To avoid an unconditional flush, check pagecache state and only flush * if dirty and the fs returns a mapping that might convert on * writeback. */ - range_dirty = filemap_range_needs_writeback(inode->i_mapping, - iter.pos, iter.pos + iter.len - 1); + range_dirty = filemap_range_needs_writeback(mapping, iter.pos, + iter.pos + iter.len - 1); while ((ret = iomap_iter(&iter, ops)) > 0) { const struct iomap *srcmap = iomap_iter_srcmap(&iter); - if (srcmap->type == IOMAP_HOLE || - srcmap->type == IOMAP_UNWRITTEN) { + if (WARN_ON_ONCE(iter.fbatch && + srcmap->type != IOMAP_UNWRITTEN)) + return -EIO; + + if (!iter.fbatch && + (srcmap->type == IOMAP_HOLE || + srcmap->type == IOMAP_UNWRITTEN)) { s64 status; if (range_dirty) { @@ -1526,7 +1648,7 @@ static int iomap_folio_mkwrite_iter(struct iomap_iter *iter, folio_mark_dirty(folio); } - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, length); } vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops, @@ -1559,16 +1681,25 @@ out_unlock: } EXPORT_SYMBOL_GPL(iomap_page_mkwrite); -void iomap_start_folio_write(struct inode *inode, struct folio *folio, - size_t len) +static void iomap_writeback_init(struct inode *inode, struct folio *folio) { struct iomap_folio_state *ifs = folio->private; WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs); - if (ifs) - atomic_add(len, &ifs->write_bytes_pending); + if (ifs) { + WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0); + /* + * Set this to the folio size. After processing the folio for + * writeback in iomap_writeback_folio(), we'll subtract any + * ranges not written back. + * + * We do this because otherwise, we would have to atomically + * increment ifs->write_bytes_pending every time a range in the + * folio needs to be written back. + */ + atomic_set(&ifs->write_bytes_pending, folio_size(folio)); + } } -EXPORT_SYMBOL_GPL(iomap_start_folio_write); void iomap_finish_folio_write(struct inode *inode, struct folio *folio, size_t len) @@ -1585,7 +1716,7 @@ EXPORT_SYMBOL_GPL(iomap_finish_folio_write); static int iomap_writeback_range(struct iomap_writepage_ctx *wpc, struct folio *folio, u64 pos, u32 rlen, u64 end_pos, - bool *wb_pending) + size_t *bytes_submitted) { do { ssize_t ret; @@ -1599,11 +1730,11 @@ static int iomap_writeback_range(struct iomap_writepage_ctx *wpc, pos += ret; /* - * Holes are not be written back by ->writeback_range, so track + * Holes are not written back by ->writeback_range, so track * if we did handle anything that is not a hole here. */ if (wpc->iomap.type != IOMAP_HOLE) - *wb_pending = true; + *bytes_submitted += ret; } while (rlen); return 0; @@ -1674,7 +1805,7 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio) u64 pos = folio_pos(folio); u64 end_pos = pos + folio_size(folio); u64 end_aligned = 0; - bool wb_pending = false; + size_t bytes_submitted = 0; int error = 0; u32 rlen; @@ -1694,14 +1825,7 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio) iomap_set_range_dirty(folio, 0, end_pos - pos); } - /* - * Keep the I/O completion handler from clearing the writeback - * bit until we have submitted all blocks by adding a bias to - * ifs->write_bytes_pending, which is dropped after submitting - * all blocks. - */ - WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0); - iomap_start_folio_write(inode, folio, 1); + iomap_writeback_init(inode, folio); } /* @@ -1716,13 +1840,13 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio) end_aligned = round_up(end_pos, i_blocksize(inode)); while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { error = iomap_writeback_range(wpc, folio, pos, rlen, end_pos, - &wb_pending); + &bytes_submitted); if (error) break; pos += rlen; } - if (wb_pending) + if (bytes_submitted) wpc->nr_folios++; /* @@ -1740,12 +1864,20 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio) * bit ourselves right after unlocking the page. */ if (ifs) { - if (atomic_dec_and_test(&ifs->write_bytes_pending)) - folio_end_writeback(folio); - } else { - if (!wb_pending) - folio_end_writeback(folio); + /* + * Subtract any bytes that were initially accounted to + * write_bytes_pending but skipped for writeback. + */ + size_t bytes_not_submitted = folio_size(folio) - + bytes_submitted; + + if (bytes_not_submitted) + iomap_finish_folio_write(inode, folio, + bytes_not_submitted); + } else if (!bytes_submitted) { + folio_end_writeback(folio); } + mapping_set_error(inode->i_mapping, error); return error; } diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 5d5d63efbd57..8e273408453a 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -16,21 +16,13 @@ * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: */ -#define IOMAP_DIO_NO_INVALIDATE (1U << 25) -#define IOMAP_DIO_CALLER_COMP (1U << 26) -#define IOMAP_DIO_INLINE_COMP (1U << 27) +#define IOMAP_DIO_NO_INVALIDATE (1U << 26) +#define IOMAP_DIO_COMP_WORK (1U << 27) #define IOMAP_DIO_WRITE_THROUGH (1U << 28) #define IOMAP_DIO_NEED_SYNC (1U << 29) #define IOMAP_DIO_WRITE (1U << 30) #define IOMAP_DIO_DIRTY (1U << 31) -/* - * Used for sub block zeroing in iomap_dio_zero() - */ -#define IOMAP_ZERO_PAGE_SIZE (SZ_64K) -#define IOMAP_ZERO_PAGE_ORDER (get_order(IOMAP_ZERO_PAGE_SIZE)) -static struct page *zero_page; - struct iomap_dio { struct kiocb *iocb; const struct iomap_dio_ops *dops; @@ -140,11 +132,6 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio) } EXPORT_SYMBOL_GPL(iomap_dio_complete); -static ssize_t iomap_dio_deferred_complete(void *data) -{ - return iomap_dio_complete(data); -} - static void iomap_dio_complete_work(struct work_struct *work) { struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work); @@ -179,33 +166,33 @@ static void iomap_dio_done(struct iomap_dio *dio) WRITE_ONCE(dio->submit.waiter, NULL); blk_wake_io_task(waiter); - } else if (dio->flags & IOMAP_DIO_INLINE_COMP) { - WRITE_ONCE(iocb->private, NULL); - iomap_dio_complete_work(&dio->aio.work); - } else if (dio->flags & IOMAP_DIO_CALLER_COMP) { - /* - * If this dio is flagged with IOMAP_DIO_CALLER_COMP, then - * schedule our completion that way to avoid an async punt to a - * workqueue. - */ - /* only polled IO cares about private cleared */ - iocb->private = dio; - iocb->dio_complete = iomap_dio_deferred_complete; + return; + } - /* - * Invoke ->ki_complete() directly. We've assigned our - * dio_complete callback handler, and since the issuer set - * IOCB_DIO_CALLER_COMP, we know their ki_complete handler will - * notice ->dio_complete being set and will defer calling that - * handler until it can be done from a safe task context. - * - * Note that the 'res' being passed in here is not important - * for this case. The actual completion value of the request - * will be gotten from dio_complete when that is run by the - * issuer. - */ - iocb->ki_complete(iocb, 0); - } else { + /* + * Always run error completions in user context. These are not + * performance critical and some code relies on taking sleeping locks + * for error handling. + */ + if (dio->error) + dio->flags |= IOMAP_DIO_COMP_WORK; + + /* + * Never invalidate pages from this context to avoid deadlocks with + * buffered I/O completions when called from the ioend workqueue, + * or avoid sleeping when called directly from ->bi_end_io. + * Tough luck if you hit the tiny race with someone dirtying the range + * right between this check and the actual completion. + */ + if ((dio->flags & IOMAP_DIO_WRITE) && + !(dio->flags & IOMAP_DIO_COMP_WORK)) { + if (dio->iocb->ki_filp->f_mapping->nrpages) + dio->flags |= IOMAP_DIO_COMP_WORK; + else + dio->flags |= IOMAP_DIO_NO_INVALIDATE; + } + + if (dio->flags & IOMAP_DIO_COMP_WORK) { struct inode *inode = file_inode(iocb->ki_filp); /* @@ -216,7 +203,11 @@ static void iomap_dio_done(struct iomap_dio *dio) */ INIT_WORK(&dio->aio.work, iomap_dio_complete_work); queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work); + return; } + + WRITE_ONCE(iocb->private, NULL); + iomap_dio_complete_work(&dio->aio.work); } void iomap_dio_bio_end_io(struct bio *bio) @@ -252,16 +243,9 @@ u32 iomap_finish_ioend_direct(struct iomap_ioend *ioend) /* * Try to avoid another context switch for the completion given * that we are already called from the ioend completion - * workqueue, but never invalidate pages from this thread to - * avoid deadlocks with buffered I/O completions. Tough luck if - * you hit the tiny race with someone dirtying the range now - * between this check and the actual completion. + * workqueue. */ - if (!dio->iocb->ki_filp->f_mapping->nrpages) { - dio->flags |= IOMAP_DIO_INLINE_COMP; - dio->flags |= IOMAP_DIO_NO_INVALIDATE; - } - dio->flags &= ~IOMAP_DIO_CALLER_COMP; + dio->flags &= ~IOMAP_DIO_COMP_WORK; iomap_dio_done(dio); } @@ -285,42 +269,36 @@ static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, { struct inode *inode = file_inode(dio->iocb->ki_filp); struct bio *bio; + struct folio *zero_folio = largest_zero_folio(); + int nr_vecs = max(1, i_blocksize(inode) / folio_size(zero_folio)); if (!len) return 0; + /* - * Max block size supported is 64k + * This limit shall never be reached as most filesystems have a + * maximum blocksize of 64k. */ - if (WARN_ON_ONCE(len > IOMAP_ZERO_PAGE_SIZE)) + if (WARN_ON_ONCE(nr_vecs > BIO_MAX_VECS)) return -EINVAL; - bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE); + bio = iomap_dio_alloc_bio(iter, dio, nr_vecs, + REQ_OP_WRITE | REQ_SYNC | REQ_IDLE); fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos); bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; - __bio_add_page(bio, zero_page, len, 0); + while (len > 0) { + unsigned int io_len = min(len, folio_size(zero_folio)); + + bio_add_folio_nofail(bio, zero_folio, io_len, 0); + len -= io_len; + } iomap_dio_submit_bio(iter, dio, bio, pos); - return 0; -} -/* - * Use a FUA write if we need datasync semantics and this is a pure data I/O - * that doesn't require any metadata updates (including after I/O completion - * such as unwritten extent conversion) and the underlying device either - * doesn't have a volatile write cache or supports FUA. - * This allows us to avoid cache flushes on I/O completion. - */ -static inline bool iomap_dio_can_use_fua(const struct iomap *iomap, - struct iomap_dio *dio) -{ - if (iomap->flags & (IOMAP_F_SHARED | IOMAP_F_DIRTY)) - return false; - if (!(dio->flags & IOMAP_DIO_WRITE_THROUGH)) - return false; - return !bdev_write_cache(iomap->bdev) || bdev_fua(iomap->bdev); + return 0; } static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) @@ -336,12 +314,39 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) int nr_pages, ret = 0; u64 copied = 0; size_t orig_count; + unsigned int alignment; + + /* + * File systems that write out of place and always allocate new blocks + * need each bio to be block aligned as that's the unit of allocation. + */ + if (dio->flags & IOMAP_DIO_FSBLOCK_ALIGNED) + alignment = fs_block_size; + else + alignment = bdev_logical_block_size(iomap->bdev); - if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1)) + if ((pos | length) & (alignment - 1)) return -EINVAL; if (dio->flags & IOMAP_DIO_WRITE) { - bio_opf |= REQ_OP_WRITE; + bool need_completion_work = true; + + switch (iomap->type) { + case IOMAP_MAPPED: + /* + * Directly mapped I/O does not inherently need to do + * work at I/O completion time. But there are various + * cases below where this will get set again. + */ + need_completion_work = false; + break; + case IOMAP_UNWRITTEN: + dio->flags |= IOMAP_DIO_UNWRITTEN; + need_zeroout = true; + break; + default: + break; + } if (iomap->flags & IOMAP_F_ATOMIC_BIO) { /* @@ -354,35 +359,54 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) bio_opf |= REQ_ATOMIC; } - if (iomap->type == IOMAP_UNWRITTEN) { - dio->flags |= IOMAP_DIO_UNWRITTEN; - need_zeroout = true; - } - - if (iomap->flags & IOMAP_F_SHARED) + if (iomap->flags & IOMAP_F_SHARED) { + /* + * Unsharing of needs to update metadata at I/O + * completion time. + */ + need_completion_work = true; dio->flags |= IOMAP_DIO_COW; + } - if (iomap->flags & IOMAP_F_NEW) + if (iomap->flags & IOMAP_F_NEW) { + /* + * Newly allocated blocks might need recording in + * metadata at I/O completion time. + */ + need_completion_work = true; need_zeroout = true; - else if (iomap->type == IOMAP_MAPPED && - iomap_dio_can_use_fua(iomap, dio)) - bio_opf |= REQ_FUA; + } - if (!(bio_opf & REQ_FUA)) - dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; + /* + * Use a FUA write if we need datasync semantics and this is a + * pure overwrite that doesn't require any metadata updates. + * + * This allows us to avoid cache flushes on I/O completion. + */ + if (dio->flags & IOMAP_DIO_WRITE_THROUGH) { + if (!need_completion_work && + !(iomap->flags & IOMAP_F_DIRTY) && + (!bdev_write_cache(iomap->bdev) || + bdev_fua(iomap->bdev))) + bio_opf |= REQ_FUA; + else + dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; + } /* - * We can only do deferred completion for pure overwrites that + * We can only do inline completion for pure overwrites that * don't require additional I/O at completion time. * - * This rules out writes that need zeroing or extent conversion, - * extend the file size, or issue metadata I/O or cache flushes - * during completion processing. + * This rules out writes that need zeroing or metdata updates to + * convert unwritten or shared extents. + * + * Writes that extend i_size are also not supported, but this is + * handled in __iomap_dio_rw(). */ - if (need_zeroout || (pos >= i_size_read(inode)) || - ((dio->flags & IOMAP_DIO_NEED_SYNC) && - !(bio_opf & REQ_FUA))) - dio->flags &= ~IOMAP_DIO_CALLER_COMP; + if (need_completion_work) + dio->flags |= IOMAP_DIO_COMP_WORK; + + bio_opf |= REQ_OP_WRITE; } else { bio_opf |= REQ_OP_READ; } @@ -403,7 +427,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) * ones we set for inline and deferred completions. If none of those * are available for this IO, clear the polled flag. */ - if (!(dio->flags & (IOMAP_DIO_INLINE_COMP|IOMAP_DIO_CALLER_COMP))) + if (dio->flags & IOMAP_DIO_COMP_WORK) dio->iocb->ki_flags &= ~IOCB_HIPRI; if (need_zeroout) { @@ -434,7 +458,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) bio->bi_end_io = iomap_dio_bio_end_io; ret = bio_iov_iter_get_pages(bio, dio->submit.iter, - bdev_logical_block_size(iomap->bdev) - 1); + alignment - 1); if (unlikely(ret)) { /* * We have to stop part way through an IO. We must fall @@ -496,7 +520,7 @@ out: /* Undo iter limitation to current extent */ iov_iter_reexpand(dio->submit.iter, orig_count - copied); if (copied) - return iomap_iter_advance(iter, &copied); + return iomap_iter_advance(iter, copied); return ret; } @@ -507,7 +531,7 @@ static int iomap_dio_hole_iter(struct iomap_iter *iter, struct iomap_dio *dio) dio->size += length; if (!length) return -EFAULT; - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, length); } static int iomap_dio_inline_iter(struct iomap_iter *iomi, struct iomap_dio *dio) @@ -542,7 +566,7 @@ static int iomap_dio_inline_iter(struct iomap_iter *iomi, struct iomap_dio *dio) dio->size += copied; if (!copied) return -EFAULT; - return iomap_iter_advance(iomi, &copied); + return iomap_iter_advance(iomi, copied); } static int iomap_dio_iter(struct iomap_iter *iter, struct iomap_dio *dio) @@ -639,10 +663,10 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (iocb->ki_flags & IOCB_NOWAIT) iomi.flags |= IOMAP_NOWAIT; - if (iov_iter_rw(iter) == READ) { - /* reads can always complete inline */ - dio->flags |= IOMAP_DIO_INLINE_COMP; + if (dio_flags & IOMAP_DIO_FSBLOCK_ALIGNED) + dio->flags |= IOMAP_DIO_FSBLOCK_ALIGNED; + if (iov_iter_rw(iter) == READ) { if (iomi.pos >= dio->i_size) goto out_free_dio; @@ -656,15 +680,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, iomi.flags |= IOMAP_WRITE; dio->flags |= IOMAP_DIO_WRITE; - /* - * Flag as supporting deferred completions, if the issuer - * groks it. This can avoid a workqueue punt for writes. - * We may later clear this flag if we need to do other IO - * as part of this IO completion. - */ - if (iocb->ki_flags & IOCB_DIO_CALLER_COMP) - dio->flags |= IOMAP_DIO_CALLER_COMP; - if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) { ret = -EAGAIN; if (iomi.pos >= dio->i_size || @@ -694,6 +709,12 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, } /* + * i_size updates must to happen from process context. + */ + if (iomi.pos + iomi.len > dio->i_size) + dio->flags |= IOMAP_DIO_COMP_WORK; + + /* * Try to invalidate cache pages for the range we are writing. * If this invalidation fails, let the caller fall back to * buffered I/O. @@ -717,12 +738,12 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, } goto out_free_dio; } + } - if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) { - ret = sb_init_dio_done_wq(inode->i_sb); - if (ret < 0) - goto out_free_dio; - } + if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + goto out_free_dio; } inode_dio_begin(inode); @@ -765,9 +786,14 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, * If all the writes we issued were already written through to the * media, we don't need to flush the cache on IO completion. Clear the * sync flag for this case. + * + * Otherwise clear the inline completion flag if any sync work is + * needed, as that needs to be performed from process context. */ if (dio->flags & IOMAP_DIO_WRITE_THROUGH) dio->flags &= ~IOMAP_DIO_NEED_SYNC; + else if (dio->flags & IOMAP_DIO_NEED_SYNC) + dio->flags |= IOMAP_DIO_COMP_WORK; /* * We are about to drop our additional submission reference, which @@ -825,15 +851,3 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, return iomap_dio_complete(dio); } EXPORT_SYMBOL_GPL(iomap_dio_rw); - -static int __init iomap_dio_init(void) -{ - zero_page = alloc_pages(GFP_KERNEL | __GFP_ZERO, - IOMAP_ZERO_PAGE_ORDER); - - if (!zero_page) - return -ENOMEM; - - return 0; -} -fs_initcall(iomap_dio_init); diff --git a/fs/iomap/internal.h b/fs/iomap/internal.h index d05cb3aed96e..3a4e4aad2bd1 100644 --- a/fs/iomap/internal.h +++ b/fs/iomap/internal.h @@ -6,4 +6,16 @@ u32 iomap_finish_ioend_direct(struct iomap_ioend *ioend); +#ifdef CONFIG_BLOCK +int iomap_bio_read_folio_range_sync(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, size_t len); +#else +static inline int iomap_bio_read_folio_range_sync(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, size_t len) +{ + WARN_ON_ONCE(1); + return -EIO; +} +#endif /* CONFIG_BLOCK */ + #endif /* _IOMAP_INTERNAL_H */ diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c index b49fa75eab26..86f44922ed3b 100644 --- a/fs/iomap/ioend.c +++ b/fs/iomap/ioend.c @@ -194,8 +194,6 @@ new_ioend: if (!bio_add_folio(&ioend->io_bio, folio, map_len, poff)) goto new_ioend; - iomap_start_folio_write(wpc->inode, folio, map_len); - /* * Clamp io_offset and io_size to the incore EOF so that ondisk * file size updates in the ioend completion are byte-accurate. diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index cef77ca0c20b..8692e5e41c6d 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -8,22 +8,24 @@ static inline void iomap_iter_reset_iomap(struct iomap_iter *iter) { + if (iter->fbatch) { + folio_batch_release(iter->fbatch); + kfree(iter->fbatch); + iter->fbatch = NULL; + } + iter->status = 0; memset(&iter->iomap, 0, sizeof(iter->iomap)); memset(&iter->srcmap, 0, sizeof(iter->srcmap)); } -/* - * Advance the current iterator position and output the length remaining for the - * current mapping. - */ -int iomap_iter_advance(struct iomap_iter *iter, u64 *count) +/* Advance the current iterator position and decrement the remaining length */ +int iomap_iter_advance(struct iomap_iter *iter, u64 count) { - if (WARN_ON_ONCE(*count > iomap_length(iter))) + if (WARN_ON_ONCE(count > iomap_length(iter))) return -EIO; - iter->pos += *count; - iter->len -= *count; - *count = iomap_length(iter); + iter->pos += count; + iter->len -= count; return 0; } diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index 56db2dd4b10d..6cbc587c93da 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -16,13 +16,13 @@ static int iomap_seek_hole_iter(struct iomap_iter *iter, *hole_pos = mapping_seek_hole_data(iter->inode->i_mapping, iter->pos, iter->pos + length, SEEK_HOLE); if (*hole_pos == iter->pos + length) - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, length); return 0; case IOMAP_HOLE: *hole_pos = iter->pos; return 0; default: - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, length); } } @@ -59,12 +59,12 @@ static int iomap_seek_data_iter(struct iomap_iter *iter, switch (iter->iomap.type) { case IOMAP_HOLE: - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, length); case IOMAP_UNWRITTEN: *hole_pos = mapping_seek_hole_data(iter->inode->i_mapping, iter->pos, iter->pos + length, SEEK_DATA); if (*hole_pos < 0) - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, length); return 0; default: *hole_pos = iter->pos; diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index a61c1dae4742..532787277b16 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -122,9 +122,10 @@ DEFINE_RANGE_EVENT(iomap_zero_iter); #define IOMAP_DIO_STRINGS \ - {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ - {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ - {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" } + {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ + {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ + {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" }, \ + {IOMAP_DIO_FSBLOCK_ALIGNED, "DIO_FSBLOCK_ALIGNED" } DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 6f0e6b19383c..b7cbe126faf3 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -610,6 +610,11 @@ static int isofs_fill_super(struct super_block *s, struct fs_context *fc) goto out_freesbi; } opt->blocksize = sb_min_blocksize(s, opt->blocksize); + if (!opt->blocksize) { + printk(KERN_ERR + "ISOFS: unable to set blocksize\n"); + goto out_freesbi; + } sbi->s_high_sierra = 0; /* default is iso9660 */ sbi->s_session = opt->session; @@ -1515,7 +1520,7 @@ struct inode *__isofs_iget(struct super_block *sb, if (!inode) return ERR_PTR(-ENOMEM); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { ret = isofs_read_inode(inode, relocated); if (ret < 0) { iget_failed(inode); diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index d175cccb7c55..764bba8ba999 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -265,7 +265,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; f = JFFS2_INODE_INFO(inode); @@ -373,7 +373,7 @@ void jffs2_dirty_inode(struct inode *inode, int flags) { struct iattr iattr; - if (!(inode->i_state & I_DIRTY_DATASYNC)) { + if (!(inode_state_read_once(inode) & I_DIRTY_DATASYNC)) { jffs2_dbg(2, "%s(): not calling setattr() for ino #%lu\n", __func__, inode->i_ino); return; diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 2a4a288b821c..87ad042221e7 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -26,8 +26,8 @@ int jfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) return rc; inode_lock(inode); - if (!(inode->i_state & I_DIRTY_ALL) || - (datasync && !(inode->i_state & I_DIRTY_DATASYNC))) { + if (!(inode_state_read_once(inode) & I_DIRTY_ALL) || + (datasync && !(inode_state_read_once(inode) & I_DIRTY_DATASYNC))) { /* Make sure committed changes hit the disk */ jfs_flush_journal(JFS_SBI(inode->i_sb)->log, 1); inode_unlock(inode); diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 21f3d029da7d..4709762713ef 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -29,7 +29,7 @@ struct inode *jfs_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; ret = diRead(inode); diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 10934f9a11be..5aaafedb8fbc 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -76,14 +76,14 @@ struct jfs_inode_info { struct { unchar _unused[16]; /* 16: */ dxd_t _dxd; /* 16: */ - /* _inline may overflow into _inline_ea when needed */ + /* _inline_sym may overflow into _inline_ea when needed */ /* _inline_ea may overlay the last part of * file._xtroot if maxentry = XTROOTINITSLOT */ union { struct { /* 128: inline symlink */ - unchar _inline[128]; + unchar _inline_sym[128]; /* 128: inline extended attr */ unchar _inline_ea[128]; }; @@ -101,7 +101,7 @@ struct jfs_inode_info { #define i_imap u.file._imap #define i_dirtable u.dir._table #define i_dtroot u.dir._dtroot -#define i_inline u.link._inline +#define i_inline u.link._inline_sym #define i_inline_ea u.link._inline_ea #define i_inline_all u.link._inline_all diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index 7840a03e5bcb..c16578af3a77 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1287,7 +1287,7 @@ int txCommit(tid_t tid, /* transaction identifier */ * to verify this, only a trivial s/I_LOCK/I_SYNC/ was done. * Joern */ - if (tblk->u.ip->i_state & I_SYNC) + if (inode_state_read_once(tblk->u.ip) & I_SYNC) tblk->xflag &= ~COMMIT_LAZY; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 457f91c412d4..a36aaee98dce 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -251,7 +251,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) struct inode *inode; inode = iget_locked(sb, kernfs_ino(kn)); - if (inode && (inode->i_state & I_NEW)) + if (inode && (inode_state_read_once(inode) & I_NEW)) kernfs_init_inode(kn, inode); return inode; diff --git a/fs/libfs.c b/fs/libfs.c index ce8c496a6940..2d6657947abd 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -680,6 +680,7 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) s->s_export_op = ctx->eops; s->s_xattr = ctx->xattr; s->s_time_gran = 1; + s->s_d_flags |= ctx->s_d_flags; root = new_inode(s); if (!root) return -ENOMEM; @@ -1542,9 +1543,9 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, inode_lock(inode); ret = sync_mapping_buffers(inode->i_mapping); - if (!(inode->i_state & I_DIRTY_ALL)) + if (!(inode_state_read_once(inode) & I_DIRTY_ALL)) goto out; - if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) + if (datasync && !(inode_state_read_once(inode) & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); @@ -1664,7 +1665,7 @@ struct inode *alloc_anon_inode(struct super_block *s) * list because mark_inode_dirty() will think * that it already _is_ on the dirty list. */ - inode->i_state = I_DIRTY; + inode_state_assign_raw(inode, I_DIRTY); /* * Historically anonymous inodes don't have a type at all and * userspace has come to rely on this. @@ -2289,27 +2290,25 @@ void stashed_dentry_prune(struct dentry *dentry) cmpxchg(stashed, dentry, NULL); } -/* parent must be held exclusive */ +/** + * simple_start_creating - prepare to create a given name + * @parent: directory in which to prepare to create the name + * @name: the name to be created + * + * Required lock is taken and a lookup in performed prior to creating an + * object in a directory. No permission checking is performed. + * + * Returns: a negative dentry on which vfs_create() or similar may + * be attempted, or an error. + */ struct dentry *simple_start_creating(struct dentry *parent, const char *name) { - struct dentry *dentry; - struct inode *dir = d_inode(parent); + struct qstr qname = QSTR(name); + int err; - inode_lock(dir); - if (unlikely(IS_DEADDIR(dir))) { - inode_unlock(dir); - return ERR_PTR(-ENOENT); - } - dentry = lookup_noperm(&QSTR(name), parent); - if (IS_ERR(dentry)) { - inode_unlock(dir); - return dentry; - } - if (dentry->d_inode) { - dput(dentry); - inode_unlock(dir); - return ERR_PTR(-EEXIST); - } - return dentry; + err = lookup_noperm_common(&qname, parent); + if (err) + return ERR_PTR(err); + return start_dirop(parent, &qname, LOOKUP_CREATE | LOOKUP_EXCL); } EXPORT_SYMBOL(simple_start_creating); diff --git a/fs/locks.c b/fs/locks.c index 04a3f0e20724..9f565802a88c 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -585,7 +585,7 @@ static const struct lease_manager_operations lease_manager_ops = { /* * Initialize a lease, use the default lock manager operations */ -static int lease_init(struct file *filp, int type, struct file_lease *fl) +static int lease_init(struct file *filp, unsigned int flags, int type, struct file_lease *fl) { if (assign_type(&fl->c, type) != 0) return -EINVAL; @@ -594,13 +594,13 @@ static int lease_init(struct file *filp, int type, struct file_lease *fl) fl->c.flc_pid = current->tgid; fl->c.flc_file = filp; - fl->c.flc_flags = FL_LEASE; + fl->c.flc_flags = flags; fl->fl_lmops = &lease_manager_ops; return 0; } /* Allocate a file_lock initialised to this type of lease */ -static struct file_lease *lease_alloc(struct file *filp, int type) +static struct file_lease *lease_alloc(struct file *filp, unsigned int flags, int type) { struct file_lease *fl = locks_alloc_lease(); int error = -ENOMEM; @@ -608,7 +608,7 @@ static struct file_lease *lease_alloc(struct file *filp, int type) if (fl == NULL) return ERR_PTR(error); - error = lease_init(filp, type, fl); + error = lease_init(filp, flags, type, fl); if (error) { locks_free_lease(fl); return ERR_PTR(error); @@ -1529,29 +1529,35 @@ any_leases_conflict(struct inode *inode, struct file_lease *breaker) /** * __break_lease - revoke all outstanding leases on file * @inode: the inode of the file to return - * @mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR: - * break all leases - * @type: FL_LEASE: break leases and delegations; FL_DELEG: break - * only delegations + * @flags: LEASE_BREAK_* flags * * break_lease (inlined for speed) has checked there already is at least * some kind of lock (maybe a lease) on this file. Leases are broken on - * a call to open() or truncate(). This function can sleep unless you - * specified %O_NONBLOCK to your open(). + * a call to open() or truncate(). This function can block waiting for the + * lease break unless you specify LEASE_BREAK_NONBLOCK. */ -int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) +int __break_lease(struct inode *inode, unsigned int flags) { - int error = 0; - struct file_lock_context *ctx; struct file_lease *new_fl, *fl, *tmp; + struct file_lock_context *ctx; unsigned long break_time; - int want_write = (mode & O_ACCMODE) != O_RDONLY; + unsigned int type; LIST_HEAD(dispose); + bool want_write = !(flags & LEASE_BREAK_OPEN_RDONLY); + int error = 0; - new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); + if (flags & LEASE_BREAK_LEASE) + type = FL_LEASE; + else if (flags & LEASE_BREAK_DELEG) + type = FL_DELEG; + else if (flags & LEASE_BREAK_LAYOUT) + type = FL_LAYOUT; + else + return -EINVAL; + + new_fl = lease_alloc(NULL, type, want_write ? F_WRLCK : F_RDLCK); if (IS_ERR(new_fl)) return PTR_ERR(new_fl); - new_fl->c.flc_flags = type; /* typically we will check that ctx is non-NULL before calling */ ctx = locks_inode_context(inode); @@ -1596,7 +1602,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) if (list_empty(&ctx->flc_lease)) goto out; - if (mode & O_NONBLOCK) { + if (flags & LEASE_BREAK_NONBLOCK) { trace_break_lease_noblock(inode, new_fl); error = -EWOULDBLOCK; goto out; @@ -1675,8 +1681,9 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time) EXPORT_SYMBOL(lease_get_mtime); /** - * fcntl_getlease - Enquire what lease is currently active + * __fcntl_getlease - Enquire what lease is currently active * @filp: the file + * @flavor: type of lease flags to check * * The value returned by this function will be one of * (if no lease break is pending): @@ -1697,7 +1704,7 @@ EXPORT_SYMBOL(lease_get_mtime); * XXX: sfr & willy disagree over whether F_INPROGRESS * should be returned to userspace. */ -int fcntl_getlease(struct file *filp) +static int __fcntl_getlease(struct file *filp, unsigned int flavor) { struct file_lease *fl; struct inode *inode = file_inode(filp); @@ -1713,7 +1720,8 @@ int fcntl_getlease(struct file *filp) list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file != filp) continue; - type = target_leasetype(fl); + if (fl->c.flc_flags & flavor) + type = target_leasetype(fl); break; } spin_unlock(&ctx->flc_lock); @@ -1724,6 +1732,19 @@ int fcntl_getlease(struct file *filp) return type; } +int fcntl_getlease(struct file *filp) +{ + return __fcntl_getlease(filp, FL_LEASE); +} + +int fcntl_getdeleg(struct file *filp, struct delegation *deleg) +{ + if (deleg->d_flags != 0 || deleg->__pad != 0) + return -EINVAL; + deleg->d_type = __fcntl_getlease(filp, FL_DELEG); + return 0; +} + /** * check_conflicting_open - see if the given file points to an inode that has * an existing open that would conflict with the @@ -1929,11 +1950,19 @@ static int generic_delete_lease(struct file *filp, void *owner) int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { + struct inode *inode = file_inode(filp); + + if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) + return -EINVAL; + switch (arg) { case F_UNLCK: return generic_delete_lease(filp, *priv); - case F_RDLCK: case F_WRLCK: + if (S_ISDIR(inode->i_mode)) + return -EINVAL; + fallthrough; + case F_RDLCK: if (!(*flp)->fl_lmops->lm_break) { WARN_ON_ONCE(1); return -ENOLCK; @@ -2018,8 +2047,6 @@ vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE)) return -EACCES; - if (!S_ISREG(inode->i_mode)) - return -EINVAL; error = security_file_lock(filp, arg); if (error) return error; @@ -2027,13 +2054,13 @@ vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) } EXPORT_SYMBOL_GPL(vfs_setlease); -static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg) +static int do_fcntl_add_lease(unsigned int fd, struct file *filp, unsigned int flavor, int arg) { struct file_lease *fl; struct fasync_struct *new; int error; - fl = lease_alloc(filp, arg); + fl = lease_alloc(filp, flavor, arg); if (IS_ERR(fl)) return PTR_ERR(fl); @@ -2064,9 +2091,33 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg) */ int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { + if (S_ISDIR(file_inode(filp)->i_mode)) + return -EINVAL; + if (arg == F_UNLCK) return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); - return do_fcntl_add_lease(fd, filp, arg); + return do_fcntl_add_lease(fd, filp, FL_LEASE, arg); +} + +/** + * fcntl_setdeleg - sets a delegation on an open file + * @fd: open file descriptor + * @filp: file pointer + * @deleg: delegation request from userland + * + * Call this fcntl to establish a delegation on the file. + * Note that you also need to call %F_SETSIG to + * receive a signal when the lease is broken. + */ +int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg) +{ + /* For now, no flags are supported */ + if (deleg->d_flags != 0 || deleg->__pad != 0) + return -EINVAL; + + if (deleg->d_type == F_UNLCK) + return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); + return do_fcntl_add_lease(fd, filp, FL_DELEG, deleg->d_type); } /** diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 32db676127a9..51ea9bdc813f 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -26,6 +26,22 @@ static int minix_write_inode(struct inode *inode, struct writeback_control *wbc); static int minix_statfs(struct dentry *dentry, struct kstatfs *buf); +void __minix_error_inode(struct inode *inode, const char *function, + unsigned int line, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk(KERN_CRIT "minix-fs error (device %s): %s:%d: " + "inode #%lu: comm %s: %pV\n", + inode->i_sb->s_id, function, line, inode->i_ino, + current->comm, &vaf); + va_end(args); +} + static void minix_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); @@ -589,7 +605,7 @@ struct inode *minix_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; if (INODE_VERSION(inode) == MINIX_V1) diff --git a/fs/minix/minix.h b/fs/minix/minix.h index d54273c3c9ff..2bfaf377f208 100644 --- a/fs/minix/minix.h +++ b/fs/minix/minix.h @@ -42,6 +42,9 @@ struct minix_sb_info { unsigned short s_version; }; +void __minix_error_inode(struct inode *inode, const char *function, + unsigned int line, const char *fmt, ...); + struct inode *minix_iget(struct super_block *, unsigned long); struct minix_inode *minix_V1_raw_inode(struct super_block *, ino_t, struct buffer_head **); struct minix2_inode *minix_V2_raw_inode(struct super_block *, ino_t, struct buffer_head **); @@ -168,4 +171,10 @@ static inline int minix_test_bit(int nr, const void *vaddr) #endif +#define minix_error_inode(inode, fmt, ...) \ + __minix_error_inode((inode), __func__, __LINE__, \ + (fmt), ##__VA_ARGS__) + +#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ + #endif /* FS_MINIX_H */ diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 8938536d8d3c..263e4ba8b1c8 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -145,6 +145,11 @@ static int minix_unlink(struct inode * dir, struct dentry *dentry) struct minix_dir_entry * de; int err; + if (inode->i_nlink == 0) { + minix_error_inode(inode, "inode has corrupted nlink"); + return -EFSCORRUPTED; + } + de = minix_find_entry(dentry, &folio); if (!de) return -ENOENT; @@ -161,15 +166,24 @@ static int minix_unlink(struct inode * dir, struct dentry *dentry) static int minix_rmdir(struct inode * dir, struct dentry *dentry) { struct inode * inode = d_inode(dentry); - int err = -ENOTEMPTY; + int err = -EFSCORRUPTED; - if (minix_empty_dir(inode)) { - err = minix_unlink(dir, dentry); - if (!err) { - inode_dec_link_count(dir); - inode_dec_link_count(inode); - } + if (dir->i_nlink <= 2) { + minix_error_inode(dir, "inode has corrupted nlink"); + goto out; + } + + err = -ENOTEMPTY; + if (!minix_empty_dir(inode)) + goto out; + + err = minix_unlink(dir, dentry); + if (!err) { + inode_dec_link_count(dir); + inode_dec_link_count(inode); } + +out: return err; } @@ -208,6 +222,17 @@ static int minix_rename(struct mnt_idmap *idmap, if (dir_de && !minix_empty_dir(new_inode)) goto out_dir; + err = -EFSCORRUPTED; + if (new_inode->i_nlink == 0 || (dir_de && new_inode->i_nlink != 2)) { + minix_error_inode(new_inode, "inode has corrupted nlink"); + goto out_dir; + } + + if (dir_de && old_dir->i_nlink <= 2) { + minix_error_inode(old_dir, "inode has corrupted nlink"); + goto out_dir; + } + err = -ENOENT; new_de = minix_find_entry(new_dentry, &new_folio); if (!new_de) diff --git a/fs/mount.h b/fs/mount.h index f13a28752d0b..2d28ef2a3aed 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -27,6 +27,7 @@ struct mnt_namespace { unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; refcount_t passive; /* number references not pinning @mounts */ + bool is_anon; } __randomize_layout; struct mnt_pcp { @@ -175,7 +176,7 @@ static inline bool is_local_mountpoint(const struct dentry *dentry) static inline bool is_anon_ns(struct mnt_namespace *ns) { - return ns->ns.ns_id == 0; + return ns->is_anon; } static inline bool anon_ns_root(const struct mount *m) diff --git a/fs/namei.c b/fs/namei.c index 7377020a2cba..bf0f66f0e9b9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -282,7 +282,7 @@ void putname(struct filename *name) return; refcnt = atomic_read(&name->refcnt); - if (refcnt != 1) { + if (unlikely(refcnt != 1)) { if (WARN_ON_ONCE(!refcnt)) return; @@ -290,7 +290,7 @@ void putname(struct filename *name) return; } - if (name->name != name->iname) { + if (unlikely(name->name != name->iname)) { __putname(name->name); kfree(name); } else @@ -540,10 +540,13 @@ static inline int do_inode_permission(struct mnt_idmap *idmap, * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. + * + * Note: lookup_inode_permission_may_exec() does not call here. If you add + * MAY_EXEC checks, adjust it. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { - if (unlikely(mask & MAY_WRITE)) { + if (mask & MAY_WRITE) { umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ @@ -574,7 +577,7 @@ int inode_permission(struct mnt_idmap *idmap, if (unlikely(retval)) return retval; - if (unlikely(mask & MAY_WRITE)) { + if (mask & MAY_WRITE) { /* * Nobody gets write access to an immutable file. */ @@ -602,6 +605,42 @@ int inode_permission(struct mnt_idmap *idmap, } EXPORT_SYMBOL(inode_permission); +/* + * lookup_inode_permission_may_exec - Check traversal right for given inode + * + * This is a special case routine for may_lookup() making assumptions specific + * to path traversal. Use inode_permission() if you are doing something else. + * + * Work is shaved off compared to inode_permission() as follows: + * - we know for a fact there is no MAY_WRITE to worry about + * - it is an invariant the inode is a directory + * + * Since majority of real-world traversal happens on inodes which grant it for + * everyone, we check it upfront and only resort to more expensive work if it + * fails. + * + * Filesystems which have their own ->permission hook and consequently miss out + * on IOP_FASTPERM can still get the optimization if they set IOP_FASTPERM_MAY_EXEC + * on their directory inodes. + */ +static __always_inline int lookup_inode_permission_may_exec(struct mnt_idmap *idmap, + struct inode *inode, int mask) +{ + /* Lookup already checked this to return -ENOTDIR */ + VFS_BUG_ON_INODE(!S_ISDIR(inode->i_mode), inode); + VFS_BUG_ON((mask & ~MAY_NOT_BLOCK) != 0); + + mask |= MAY_EXEC; + + if (unlikely(!(inode->i_opflags & (IOP_FASTPERM | IOP_FASTPERM_MAY_EXEC)))) + return inode_permission(idmap, inode, mask); + + if (unlikely(((inode->i_mode & 0111) != 0111) || !no_acl_inode(inode))) + return inode_permission(idmap, inode, mask); + + return security_inode_permission(inode, mask); +} + /** * path_get - get a reference to a path * @path: path to get the reference to @@ -746,7 +785,8 @@ static void leave_rcu(struct nameidata *nd) static void terminate_walk(struct nameidata *nd) { - drop_links(nd); + if (unlikely(nd->depth)) + drop_links(nd); if (!(nd->flags & LOOKUP_RCU)) { int i; path_put(&nd->path); @@ -843,7 +883,7 @@ static bool try_to_unlazy(struct nameidata *nd) BUG_ON(!(nd->flags & LOOKUP_RCU)); - if (unlikely(!legitimize_links(nd))) + if (unlikely(nd->depth && !legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; @@ -878,7 +918,7 @@ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry) int res; BUG_ON(!(nd->flags & LOOKUP_RCU)); - if (unlikely(!legitimize_links(nd))) + if (unlikely(nd->depth && !legitimize_links(nd))) goto out2; res = __legitimize_mnt(nd->path.mnt, nd->m_seq); if (unlikely(res)) { @@ -951,8 +991,8 @@ static int complete_walk(struct nameidata *nd) * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ - if (!(nd->state & ND_ROOT_PRESET)) - if (!(nd->flags & LOOKUP_IS_SCOPED)) + if (likely(!(nd->state & ND_ROOT_PRESET))) + if (likely(!(nd->flags & LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) @@ -1034,7 +1074,7 @@ static int nd_jump_root(struct nameidata *nd) } if (!nd->root.mnt) { int error = set_root(nd); - if (error) + if (unlikely(error)) return error; } if (nd->flags & LOOKUP_RCU) { @@ -1632,13 +1672,15 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, path->dentry = dentry; if (nd->flags & LOOKUP_RCU) { unsigned int seq = nd->next_seq; + if (likely(!d_managed(dentry))) + return 0; if (likely(__follow_mount_rcu(nd, path))) return 0; // *path and nd->next_seq might've been clobbered path->mnt = nd->path.mnt; path->dentry = dentry; nd->next_seq = seq; - if (!try_to_unlazy_next(nd, dentry)) + if (unlikely(!try_to_unlazy_next(nd, dentry))) return -ECHILD; } ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); @@ -1823,7 +1865,7 @@ again: return dentry; } -static struct dentry *lookup_slow(const struct qstr *name, +static noinline struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { @@ -1855,7 +1897,7 @@ static inline int may_lookup(struct mnt_idmap *idmap, int err, mask; mask = nd->flags & LOOKUP_RCU ? MAY_NOT_BLOCK : 0; - err = inode_permission(idmap, nd->inode, mask | MAY_EXEC); + err = lookup_inode_permission_may_exec(idmap, nd->inode, mask); if (likely(!err)) return 0; @@ -1870,7 +1912,7 @@ static inline int may_lookup(struct mnt_idmap *idmap, if (err != -ECHILD) // hard error return err; - return inode_permission(idmap, nd->inode, MAY_EXEC); + return lookup_inode_permission_may_exec(idmap, nd->inode, 0); } static int reserve_stack(struct nameidata *nd, struct path *link) @@ -1901,13 +1943,23 @@ static int reserve_stack(struct nameidata *nd, struct path *link) enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; -static const char *pick_link(struct nameidata *nd, struct path *link, +static noinline const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, int flags) { struct saved *last; const char *res; - int error = reserve_stack(nd, link); + int error; + if (nd->flags & LOOKUP_RCU) { + /* make sure that d_is_symlink from step_into_slowpath() matches the inode */ + if (read_seqcount_retry(&link->dentry->d_seq, nd->next_seq)) + return ERR_PTR(-ECHILD); + } else { + if (link->mnt == nd->path.mnt) + mntget(link->mnt); + } + + error = reserve_stack(nd, link); if (unlikely(error)) { if (!(nd->flags & LOOKUP_RCU)) path_put(link); @@ -1981,14 +2033,15 @@ all_done: // pure jump * * NOTE: dentry must be what nd->next_seq had been sampled from. */ -static const char *step_into(struct nameidata *nd, int flags, +static noinline const char *step_into_slowpath(struct nameidata *nd, int flags, struct dentry *dentry) { struct path path; struct inode *inode; - int err = handle_mounts(nd, dentry, &path); + int err; - if (err < 0) + err = handle_mounts(nd, dentry, &path); + if (unlikely(err < 0)) return ERR_PTR(err); inode = path.dentry->d_inode; if (likely(!d_is_symlink(path.dentry)) || @@ -2010,15 +2063,32 @@ static const char *step_into(struct nameidata *nd, int flags, nd->seq = nd->next_seq; return NULL; } - if (nd->flags & LOOKUP_RCU) { - /* make sure that d_is_symlink above matches inode */ - if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq)) + return pick_link(nd, &path, inode, flags); +} + +static __always_inline const char *step_into(struct nameidata *nd, int flags, + struct dentry *dentry) +{ + /* + * In the common case we are in rcu-walk and traversing over a non-mounted on + * directory (as opposed to e.g., a symlink). + * + * We can handle that and negative entries with the checks below. + */ + if (likely((nd->flags & LOOKUP_RCU) && + !d_managed(dentry) && !d_is_symlink(dentry))) { + struct inode *inode = dentry->d_inode; + if (read_seqcount_retry(&dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); - } else { - if (path.mnt == nd->path.mnt) - mntget(path.mnt); + if (unlikely(!inode)) + return ERR_PTR(-ENOENT); + nd->path.dentry = dentry; + /* nd->path.mnt is retained on purpose */ + nd->inode = inode; + nd->seq = nd->next_seq; + return NULL; } - return pick_link(nd, &path, inode, flags); + return step_into_slowpath(nd, flags, dentry); } static struct dentry *follow_dotdot_rcu(struct nameidata *nd) @@ -2101,7 +2171,7 @@ static const char *handle_dots(struct nameidata *nd, int type) if (!nd->root.mnt) { error = ERR_PTR(set_root(nd)); - if (error) + if (unlikely(error)) return error; } if (nd->flags & LOOKUP_RCU) @@ -2131,7 +2201,7 @@ static const char *handle_dots(struct nameidata *nd, int type) return NULL; } -static const char *walk_component(struct nameidata *nd, int flags) +static __always_inline const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; /* @@ -2140,7 +2210,7 @@ static const char *walk_component(struct nameidata *nd, int flags) * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { - if (!(flags & WALK_MORE) && nd->depth) + if (unlikely(nd->depth) && !(flags & WALK_MORE)) put_link(nd); return handle_dots(nd, nd->last_type); } @@ -2152,7 +2222,7 @@ static const char *walk_component(struct nameidata *nd, int flags) if (IS_ERR(dentry)) return ERR_CAST(dentry); } - if (!(flags & WALK_MORE) && nd->depth) + if (unlikely(nd->depth) && !(flags & WALK_MORE)) put_link(nd); return step_into(nd, flags, dentry); } @@ -2505,7 +2575,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) if (unlikely(!*name)) { OK: /* pathname or trailing symlink, done */ - if (!depth) { + if (likely(!depth)) { nd->dir_vfsuid = i_uid_into_vfsuid(idmap, nd->inode); nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; @@ -2543,10 +2613,10 @@ static const char *path_init(struct nameidata *nd, unsigned flags) const char *s = nd->pathname; /* LOOKUP_CACHED requires RCU, ask caller to retry */ - if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) + if (unlikely((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED)) return ERR_PTR(-EAGAIN); - if (!*s) + if (unlikely(!*s)) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); @@ -2560,7 +2630,7 @@ static const char *path_init(struct nameidata *nd, unsigned flags) nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); - if (nd->state & ND_ROOT_PRESET) { + if (unlikely(nd->state & ND_ROOT_PRESET)) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) @@ -2579,7 +2649,7 @@ static const char *path_init(struct nameidata *nd, unsigned flags) nd->root.mnt = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ - if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { + if (*s == '/' && likely(!(flags & LOOKUP_IN_ROOT))) { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); @@ -2632,7 +2702,7 @@ static const char *path_init(struct nameidata *nd, unsigned flags) } /* For scoped-lookups we need to set the root to the dirfd as well. */ - if (flags & LOOKUP_IS_SCOPED) { + if (unlikely(flags & LOOKUP_IS_SCOPED)) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq; @@ -2765,6 +2835,62 @@ static int filename_parentat(int dfd, struct filename *name, return __filename_parentat(dfd, name, flags, parent, last, type, NULL); } +/** + * start_dirop - begin a create or remove dirop, performing locking and lookup + * @parent: the dentry of the parent in which the operation will occur + * @name: a qstr holding the name within that parent + * @lookup_flags: intent and other lookup flags. + * + * The lookup is performed and necessary locks are taken so that, on success, + * the returned dentry can be operated on safely. + * The qstr must already have the hash value calculated. + * + * Returns: a locked dentry, or an error. + * + */ +static struct dentry *__start_dirop(struct dentry *parent, struct qstr *name, + unsigned int lookup_flags, + unsigned int state) +{ + struct dentry *dentry; + struct inode *dir = d_inode(parent); + + if (state == TASK_KILLABLE) { + int ret = down_write_killable_nested(&dir->i_rwsem, + I_MUTEX_PARENT); + if (ret) + return ERR_PTR(ret); + } else { + inode_lock_nested(dir, I_MUTEX_PARENT); + } + dentry = lookup_one_qstr_excl(name, parent, lookup_flags); + if (IS_ERR(dentry)) + inode_unlock(dir); + return dentry; +} + +struct dentry *start_dirop(struct dentry *parent, struct qstr *name, + unsigned int lookup_flags) +{ + return __start_dirop(parent, name, lookup_flags, TASK_NORMAL); +} + +/** + * end_dirop - signal completion of a dirop + * @de: the dentry which was returned by start_dirop or similar. + * + * If the de is an error, nothing happens. Otherwise any lock taken to + * protect the dentry is dropped and the dentry itself is release (dput()). + */ +void end_dirop(struct dentry *de) +{ + if (!IS_ERR(de)) { + inode_unlock(de->d_parent->d_inode); + dput(de); + } +} +EXPORT_SYMBOL(end_dirop); + /* does lookup, returns the object with parent locked */ static struct dentry *__start_removing_path(int dfd, struct filename *name, struct path *path) @@ -2781,10 +2907,9 @@ static struct dentry *__start_removing_path(int dfd, struct filename *name, return ERR_PTR(-EINVAL); /* don't fail immediately if it's r/o, at least try to report other errors */ error = mnt_want_write(parent_path.mnt); - inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT); - d = lookup_one_qstr_excl(&last, parent_path.dentry, 0); + d = start_dirop(parent_path.dentry, &last, 0); if (IS_ERR(d)) - goto unlock; + goto drop; if (error) goto fail; path->dentry = no_free_ptr(parent_path.dentry); @@ -2792,10 +2917,9 @@ static struct dentry *__start_removing_path(int dfd, struct filename *name, return d; fail: - dput(d); + end_dirop(d); d = ERR_PTR(error); -unlock: - inode_unlock(parent_path.dentry->d_inode); +drop: if (!error) mnt_drop_write(parent_path.mnt); return d; @@ -2910,7 +3034,7 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, } EXPORT_SYMBOL(vfs_path_lookup); -static int lookup_noperm_common(struct qstr *qname, struct dentry *base) +int lookup_noperm_common(struct qstr *qname, struct dentry *base) { const char *name = qname->name; u32 len = qname->len; @@ -3181,6 +3305,234 @@ struct dentry *lookup_noperm_positive_unlocked(struct qstr *name, } EXPORT_SYMBOL(lookup_noperm_positive_unlocked); +/** + * start_creating - prepare to create a given name with permission checking + * @idmap: idmap of the mount + * @parent: directory in which to prepare to create the name + * @name: the name to be created + * + * Locks are taken and a lookup is performed prior to creating + * an object in a directory. Permission checking (MAY_EXEC) is performed + * against @idmap. + * + * If the name already exists, a positive dentry is returned, so + * behaviour is similar to O_CREAT without O_EXCL, which doesn't fail + * with -EEXIST. + * + * Returns: a negative or positive dentry, or an error. + */ +struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent, + struct qstr *name) +{ + int err = lookup_one_common(idmap, name, parent); + + if (err) + return ERR_PTR(err); + return start_dirop(parent, name, LOOKUP_CREATE); +} +EXPORT_SYMBOL(start_creating); + +/** + * start_removing - prepare to remove a given name with permission checking + * @idmap: idmap of the mount + * @parent: directory in which to find the name + * @name: the name to be removed + * + * Locks are taken and a lookup in performed prior to removing + * an object from a directory. Permission checking (MAY_EXEC) is performed + * against @idmap. + * + * If the name doesn't exist, an error is returned. + * + * end_removing() should be called when removal is complete, or aborted. + * + * Returns: a positive dentry, or an error. + */ +struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent, + struct qstr *name) +{ + int err = lookup_one_common(idmap, name, parent); + + if (err) + return ERR_PTR(err); + return start_dirop(parent, name, 0); +} +EXPORT_SYMBOL(start_removing); + +/** + * start_creating_killable - prepare to create a given name with permission checking + * @idmap: idmap of the mount + * @parent: directory in which to prepare to create the name + * @name: the name to be created + * + * Locks are taken and a lookup in performed prior to creating + * an object in a directory. Permission checking (MAY_EXEC) is performed + * against @idmap. + * + * If the name already exists, a positive dentry is returned. + * + * If a signal is received or was already pending, the function aborts + * with -EINTR; + * + * Returns: a negative or positive dentry, or an error. + */ +struct dentry *start_creating_killable(struct mnt_idmap *idmap, + struct dentry *parent, + struct qstr *name) +{ + int err = lookup_one_common(idmap, name, parent); + + if (err) + return ERR_PTR(err); + return __start_dirop(parent, name, LOOKUP_CREATE, TASK_KILLABLE); +} +EXPORT_SYMBOL(start_creating_killable); + +/** + * start_removing_killable - prepare to remove a given name with permission checking + * @idmap: idmap of the mount + * @parent: directory in which to find the name + * @name: the name to be removed + * + * Locks are taken and a lookup in performed prior to removing + * an object from a directory. Permission checking (MAY_EXEC) is performed + * against @idmap. + * + * If the name doesn't exist, an error is returned. + * + * end_removing() should be called when removal is complete, or aborted. + * + * If a signal is received or was already pending, the function aborts + * with -EINTR; + * + * Returns: a positive dentry, or an error. + */ +struct dentry *start_removing_killable(struct mnt_idmap *idmap, + struct dentry *parent, + struct qstr *name) +{ + int err = lookup_one_common(idmap, name, parent); + + if (err) + return ERR_PTR(err); + return __start_dirop(parent, name, 0, TASK_KILLABLE); +} +EXPORT_SYMBOL(start_removing_killable); + +/** + * start_creating_noperm - prepare to create a given name without permission checking + * @parent: directory in which to prepare to create the name + * @name: the name to be created + * + * Locks are taken and a lookup in performed prior to creating + * an object in a directory. + * + * If the name already exists, a positive dentry is returned. + * + * Returns: a negative or positive dentry, or an error. + */ +struct dentry *start_creating_noperm(struct dentry *parent, + struct qstr *name) +{ + int err = lookup_noperm_common(name, parent); + + if (err) + return ERR_PTR(err); + return start_dirop(parent, name, LOOKUP_CREATE); +} +EXPORT_SYMBOL(start_creating_noperm); + +/** + * start_removing_noperm - prepare to remove a given name without permission checking + * @parent: directory in which to find the name + * @name: the name to be removed + * + * Locks are taken and a lookup in performed prior to removing + * an object from a directory. + * + * If the name doesn't exist, an error is returned. + * + * end_removing() should be called when removal is complete, or aborted. + * + * Returns: a positive dentry, or an error. + */ +struct dentry *start_removing_noperm(struct dentry *parent, + struct qstr *name) +{ + int err = lookup_noperm_common(name, parent); + + if (err) + return ERR_PTR(err); + return start_dirop(parent, name, 0); +} +EXPORT_SYMBOL(start_removing_noperm); + +/** + * start_creating_dentry - prepare to create a given dentry + * @parent: directory from which dentry should be removed + * @child: the dentry to be removed + * + * A lock is taken to protect the dentry again other dirops and + * the validity of the dentry is checked: correct parent and still hashed. + * + * If the dentry is valid and negative a reference is taken and + * returned. If not an error is returned. + * + * end_creating() should be called when creation is complete, or aborted. + * + * Returns: the valid dentry, or an error. + */ +struct dentry *start_creating_dentry(struct dentry *parent, + struct dentry *child) +{ + inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); + if (unlikely(IS_DEADDIR(parent->d_inode) || + child->d_parent != parent || + d_unhashed(child))) { + inode_unlock(parent->d_inode); + return ERR_PTR(-EINVAL); + } + if (d_is_positive(child)) { + inode_unlock(parent->d_inode); + return ERR_PTR(-EEXIST); + } + return dget(child); +} +EXPORT_SYMBOL(start_creating_dentry); + +/** + * start_removing_dentry - prepare to remove a given dentry + * @parent: directory from which dentry should be removed + * @child: the dentry to be removed + * + * A lock is taken to protect the dentry again other dirops and + * the validity of the dentry is checked: correct parent and still hashed. + * + * If the dentry is valid and positive, a reference is taken and + * returned. If not an error is returned. + * + * end_removing() should be called when removal is complete, or aborted. + * + * Returns: the valid dentry, or an error. + */ +struct dentry *start_removing_dentry(struct dentry *parent, + struct dentry *child) +{ + inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); + if (unlikely(IS_DEADDIR(parent->d_inode) || + child->d_parent != parent || + d_unhashed(child))) { + inode_unlock(parent->d_inode); + return ERR_PTR(-EINVAL); + } + if (d_is_negative(child)) { + inode_unlock(parent->d_inode); + return ERR_PTR(-ENOENT); + } + return dget(child); +} +EXPORT_SYMBOL(start_removing_dentry); + #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { @@ -3419,6 +3771,290 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) EXPORT_SYMBOL(unlock_rename); /** + * __start_renaming - lookup and lock names for rename + * @rd: rename data containing parents and flags, and + * for receiving found dentries + * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, + * LOOKUP_NO_SYMLINKS etc). + * @old_last: name of object in @rd.old_parent + * @new_last: name of object in @rd.new_parent + * + * Look up two names and ensure locks are in place for + * rename. + * + * On success the found dentries are stored in @rd.old_dentry, + * @rd.new_dentry and an extra ref is taken on @rd.old_parent. + * These references and the lock are dropped by end_renaming(). + * + * The passed in qstrs must have the hash calculated, and no permission + * checking is performed. + * + * Returns: zero or an error. + */ +static int +__start_renaming(struct renamedata *rd, int lookup_flags, + struct qstr *old_last, struct qstr *new_last) +{ + struct dentry *trap; + struct dentry *d1, *d2; + int target_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE; + int err; + + if (rd->flags & RENAME_EXCHANGE) + target_flags = 0; + if (rd->flags & RENAME_NOREPLACE) + target_flags |= LOOKUP_EXCL; + + trap = lock_rename(rd->old_parent, rd->new_parent); + if (IS_ERR(trap)) + return PTR_ERR(trap); + + d1 = lookup_one_qstr_excl(old_last, rd->old_parent, + lookup_flags); + err = PTR_ERR(d1); + if (IS_ERR(d1)) + goto out_unlock; + + d2 = lookup_one_qstr_excl(new_last, rd->new_parent, + lookup_flags | target_flags); + err = PTR_ERR(d2); + if (IS_ERR(d2)) + goto out_dput_d1; + + if (d1 == trap) { + /* source is an ancestor of target */ + err = -EINVAL; + goto out_dput_d2; + } + + if (d2 == trap) { + /* target is an ancestor of source */ + if (rd->flags & RENAME_EXCHANGE) + err = -EINVAL; + else + err = -ENOTEMPTY; + goto out_dput_d2; + } + + rd->old_dentry = d1; + rd->new_dentry = d2; + dget(rd->old_parent); + return 0; + +out_dput_d2: + dput(d2); +out_dput_d1: + dput(d1); +out_unlock: + unlock_rename(rd->old_parent, rd->new_parent); + return err; +} + +/** + * start_renaming - lookup and lock names for rename with permission checking + * @rd: rename data containing parents and flags, and + * for receiving found dentries + * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, + * LOOKUP_NO_SYMLINKS etc). + * @old_last: name of object in @rd.old_parent + * @new_last: name of object in @rd.new_parent + * + * Look up two names and ensure locks are in place for + * rename. + * + * On success the found dentries are stored in @rd.old_dentry, + * @rd.new_dentry. Also the refcount on @rd->old_parent is increased. + * These references and the lock are dropped by end_renaming(). + * + * The passed in qstrs need not have the hash calculated, and basic + * eXecute permission checking is performed against @rd.mnt_idmap. + * + * Returns: zero or an error. + */ +int start_renaming(struct renamedata *rd, int lookup_flags, + struct qstr *old_last, struct qstr *new_last) +{ + int err; + + err = lookup_one_common(rd->mnt_idmap, old_last, rd->old_parent); + if (err) + return err; + err = lookup_one_common(rd->mnt_idmap, new_last, rd->new_parent); + if (err) + return err; + return __start_renaming(rd, lookup_flags, old_last, new_last); +} +EXPORT_SYMBOL(start_renaming); + +static int +__start_renaming_dentry(struct renamedata *rd, int lookup_flags, + struct dentry *old_dentry, struct qstr *new_last) +{ + struct dentry *trap; + struct dentry *d2; + int target_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE; + int err; + + if (rd->flags & RENAME_EXCHANGE) + target_flags = 0; + if (rd->flags & RENAME_NOREPLACE) + target_flags |= LOOKUP_EXCL; + + /* Already have the dentry - need to be sure to lock the correct parent */ + trap = lock_rename_child(old_dentry, rd->new_parent); + if (IS_ERR(trap)) + return PTR_ERR(trap); + if (d_unhashed(old_dentry) || + (rd->old_parent && rd->old_parent != old_dentry->d_parent)) { + /* dentry was removed, or moved and explicit parent requested */ + err = -EINVAL; + goto out_unlock; + } + + d2 = lookup_one_qstr_excl(new_last, rd->new_parent, + lookup_flags | target_flags); + err = PTR_ERR(d2); + if (IS_ERR(d2)) + goto out_unlock; + + if (old_dentry == trap) { + /* source is an ancestor of target */ + err = -EINVAL; + goto out_dput_d2; + } + + if (d2 == trap) { + /* target is an ancestor of source */ + if (rd->flags & RENAME_EXCHANGE) + err = -EINVAL; + else + err = -ENOTEMPTY; + goto out_dput_d2; + } + + rd->old_dentry = dget(old_dentry); + rd->new_dentry = d2; + rd->old_parent = dget(old_dentry->d_parent); + return 0; + +out_dput_d2: + dput(d2); +out_unlock: + unlock_rename(old_dentry->d_parent, rd->new_parent); + return err; +} + +/** + * start_renaming_dentry - lookup and lock name for rename with permission checking + * @rd: rename data containing parents and flags, and + * for receiving found dentries + * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, + * LOOKUP_NO_SYMLINKS etc). + * @old_dentry: dentry of name to move + * @new_last: name of target in @rd.new_parent + * + * Look up target name and ensure locks are in place for + * rename. + * + * On success the found dentry is stored in @rd.new_dentry and + * @rd.old_parent is confirmed to be the parent of @old_dentry. If it + * was originally %NULL, it is set. In either case a reference is taken + * so that end_renaming() can have a stable reference to unlock. + * + * References and the lock can be dropped with end_renaming() + * + * The passed in qstr need not have the hash calculated, and basic + * eXecute permission checking is performed against @rd.mnt_idmap. + * + * Returns: zero or an error. + */ +int start_renaming_dentry(struct renamedata *rd, int lookup_flags, + struct dentry *old_dentry, struct qstr *new_last) +{ + int err; + + err = lookup_one_common(rd->mnt_idmap, new_last, rd->new_parent); + if (err) + return err; + return __start_renaming_dentry(rd, lookup_flags, old_dentry, new_last); +} +EXPORT_SYMBOL(start_renaming_dentry); + +/** + * start_renaming_two_dentries - Lock to dentries in given parents for rename + * @rd: rename data containing parent + * @old_dentry: dentry of name to move + * @new_dentry: dentry to move to + * + * Ensure locks are in place for rename and check parentage is still correct. + * + * On success the two dentries are stored in @rd.old_dentry and + * @rd.new_dentry and @rd.old_parent and @rd.new_parent are confirmed to + * be the parents of the dentries. + * + * References and the lock can be dropped with end_renaming() + * + * Returns: zero or an error. + */ +int +start_renaming_two_dentries(struct renamedata *rd, + struct dentry *old_dentry, struct dentry *new_dentry) +{ + struct dentry *trap; + int err; + + /* Already have the dentry - need to be sure to lock the correct parent */ + trap = lock_rename_child(old_dentry, rd->new_parent); + if (IS_ERR(trap)) + return PTR_ERR(trap); + err = -EINVAL; + if (d_unhashed(old_dentry) || + (rd->old_parent && rd->old_parent != old_dentry->d_parent)) + /* old_dentry was removed, or moved and explicit parent requested */ + goto out_unlock; + if (d_unhashed(new_dentry) || + rd->new_parent != new_dentry->d_parent) + /* new_dentry was removed or moved */ + goto out_unlock; + + if (old_dentry == trap) + /* source is an ancestor of target */ + goto out_unlock; + + if (new_dentry == trap) { + /* target is an ancestor of source */ + if (rd->flags & RENAME_EXCHANGE) + err = -EINVAL; + else + err = -ENOTEMPTY; + goto out_unlock; + } + + err = -EEXIST; + if (d_is_positive(new_dentry) && (rd->flags & RENAME_NOREPLACE)) + goto out_unlock; + + rd->old_dentry = dget(old_dentry); + rd->new_dentry = dget(new_dentry); + rd->old_parent = dget(old_dentry->d_parent); + return 0; + +out_unlock: + unlock_rename(old_dentry->d_parent, rd->new_parent); + return err; +} +EXPORT_SYMBOL(start_renaming_two_dentries); + +void end_renaming(struct renamedata *rd) +{ + unlock_rename(rd->old_parent, rd->new_parent); + dput(rd->old_dentry); + dput(rd->new_dentry); + dput(rd->old_parent); +} +EXPORT_SYMBOL(end_renaming); + +/** * vfs_prepare_mode - prepare the mode to be used for a new inode * @idmap: idmap of the mount the inode was found from * @dir: parent directory of the new inode @@ -3461,10 +4097,9 @@ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap, /** * vfs_create - create new file * @idmap: idmap of the mount the inode was found from - * @dir: inode of the parent directory * @dentry: dentry of the child file * @mode: mode of the child file - * @want_excl: whether the file must not yet exist + * @di: returns parent inode, if the inode is delegated. * * Create a new file. * @@ -3474,9 +4109,10 @@ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap, * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ -int vfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool want_excl) +int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode, + struct delegated_inode *di) { + struct inode *dir = d_inode(dentry->d_parent); int error; error = may_create(idmap, dir, dentry); @@ -3490,7 +4126,10 @@ int vfs_create(struct mnt_idmap *idmap, struct inode *dir, error = security_inode_create(dir, dentry, mode); if (error) return error; - error = dir->i_op->create(idmap, dir, dentry, mode, want_excl); + error = try_break_deleg(dir, di); + if (error) + return error; + error = dir->i_op->create(idmap, dir, dentry, mode, true); if (!error) fsnotify_create(dir, dentry); return error; @@ -3697,7 +4336,7 @@ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry, */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, - bool got_write) + bool got_write, struct delegated_inode *delegated_inode) { struct mnt_idmap *idmap; struct dentry *dir = nd->path.dentry; @@ -3786,6 +4425,11 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, /* Negative dentry, just create the file */ if (!dentry->d_inode && (open_flag & O_CREAT)) { + /* but break the directory lease first! */ + error = try_break_deleg(dir_inode, delegated_inode); + if (error) + goto out_dput; + file->f_mode |= FMODE_CREATED; audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) { @@ -3848,6 +4492,7 @@ static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag) static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { + struct delegated_inode delegated_inode = { }; struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; bool got_write = false; @@ -3879,7 +4524,7 @@ static const char *open_last_lookups(struct nameidata *nd, return ERR_PTR(-ECHILD); } } - +retry: if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt); /* @@ -3892,7 +4537,7 @@ static const char *open_last_lookups(struct nameidata *nd, inode_lock(dir->d_inode); else inode_lock_shared(dir->d_inode); - dentry = lookup_open(nd, file, op, got_write); + dentry = lookup_open(nd, file, op, got_write, &delegated_inode); if (!IS_ERR(dentry)) { if (file->f_mode & FMODE_CREATED) fsnotify_create(dir->d_inode, dentry); @@ -3907,8 +4552,16 @@ static const char *open_last_lookups(struct nameidata *nd, if (got_write) mnt_drop_write(nd->path.mnt); - if (IS_ERR(dentry)) + if (IS_ERR(dentry)) { + if (is_delegated(&delegated_inode)) { + int error = break_deleg_wait(&delegated_inode); + + if (!error) + goto retry; + return ERR_PTR(error); + } return ERR_CAST(dentry); + } if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry); @@ -4036,7 +4689,7 @@ int vfs_tmpfile(struct mnt_idmap *idmap, inode = file_inode(file); if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); - inode->i_state |= I_LINKABLE; + inode_state_set(inode, I_LINKABLE); spin_unlock(&inode->i_lock); } security_inode_post_create_tmpfile(idmap, inode); @@ -4223,21 +4876,18 @@ static struct dentry *filename_create(int dfd, struct filename *name, */ if (last.name[last.len] && !want_dir) create_flags &= ~LOOKUP_CREATE; - inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = lookup_one_qstr_excl(&last, path->dentry, - reval_flag | create_flags); + dentry = start_dirop(path->dentry, &last, reval_flag | create_flags); if (IS_ERR(dentry)) - goto unlock; + goto out_drop_write; if (unlikely(error)) goto fail; return dentry; fail: - dput(dentry); + end_dirop(dentry); dentry = ERR_PTR(error); -unlock: - inode_unlock(path->dentry->d_inode); +out_drop_write: if (!error) mnt_drop_write(path->mnt); out: @@ -4256,11 +4906,20 @@ struct dentry *start_creating_path(int dfd, const char *pathname, } EXPORT_SYMBOL(start_creating_path); +/** + * end_creating_path - finish a code section started by start_creating_path() + * @path: the path instantiated by start_creating_path() + * @dentry: the dentry returned by start_creating_path() + * + * end_creating_path() will unlock and locks taken by start_creating_path() + * and drop an references that were taken. It should only be called + * if start_creating_path() returned a non-error. + * If vfs_mkdir() was called and it returned an error, that error *should* + * be passed to end_creating_path() together with the path. + */ void end_creating_path(const struct path *path, struct dentry *dentry) { - if (!IS_ERR(dentry)) - dput(dentry); - inode_unlock(path->dentry->d_inode); + end_creating(dentry); mnt_drop_write(path->mnt); path_put(path); } @@ -4278,13 +4937,15 @@ inline struct dentry *start_creating_user_path( } EXPORT_SYMBOL(start_creating_user_path); + /** * vfs_mknod - create device node or file - * @idmap: idmap of the mount the inode was found from - * @dir: inode of the parent directory - * @dentry: dentry of the child device node - * @mode: mode of the child device node - * @dev: device number of device to create + * @idmap: idmap of the mount the inode was found from + * @dir: inode of the parent directory + * @dentry: dentry of the child device node + * @mode: mode of the child device node + * @dev: device number of device to create + * @delegated_inode: returns parent inode, if the inode is delegated. * * Create a device node or file. * @@ -4295,7 +4956,8 @@ EXPORT_SYMBOL(start_creating_user_path); * raw inode simply pass @nop_mnt_idmap. */ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, dev_t dev) + struct dentry *dentry, umode_t mode, dev_t dev, + struct delegated_inode *delegated_inode) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; int error = may_create(idmap, dir, dentry); @@ -4319,6 +4981,10 @@ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, if (error) return error; + error = try_break_deleg(dir, delegated_inode); + if (error) + return error; + error = dir->i_op->mknod(idmap, dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); @@ -4346,6 +5012,7 @@ static int may_mknod(umode_t mode) static int do_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev) { + struct delegated_inode di = { }; struct mnt_idmap *idmap; struct dentry *dentry; struct path path; @@ -4369,22 +5036,26 @@ retry: idmap = mnt_idmap(path.mnt); switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(idmap, path.dentry->d_inode, - dentry, mode, true); + error = vfs_create(idmap, dentry, mode, &di); if (!error) security_path_post_mknod(idmap, dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(idmap, path.dentry->d_inode, - dentry, mode, new_decode_dev(dev)); + dentry, mode, new_decode_dev(dev), &di); break; case S_IFIFO: case S_IFSOCK: error = vfs_mknod(idmap, path.dentry->d_inode, - dentry, mode, 0); + dentry, mode, 0, &di); break; } out2: end_creating_path(&path, dentry); + if (is_delegated(&di)) { + error = break_deleg_wait(&di); + if (!error) + goto retry; + } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; @@ -4407,10 +5078,11 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d /** * vfs_mkdir - create directory returning correct dentry if possible - * @idmap: idmap of the mount the inode was found from - * @dir: inode of the parent directory - * @dentry: dentry of the child directory - * @mode: mode of the child directory + * @idmap: idmap of the mount the inode was found from + * @dir: inode of the parent directory + * @dentry: dentry of the child directory + * @mode: mode of the child directory + * @delegated_inode: returns parent inode, if the inode is delegated. * * Create a directory. * @@ -4427,7 +5099,8 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d * In case of an error the dentry is dput() and an ERR_PTR() is returned. */ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) + struct dentry *dentry, umode_t mode, + struct delegated_inode *delegated_inode) { int error; unsigned max_links = dir->i_sb->s_max_links; @@ -4450,6 +5123,10 @@ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, if (max_links && dir->i_nlink >= max_links) goto err; + error = try_break_deleg(dir, delegated_inode); + if (error) + goto err; + de = dir->i_op->mkdir(idmap, dir, dentry, mode); error = PTR_ERR(de); if (IS_ERR(de)) @@ -4462,7 +5139,7 @@ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, return dentry; err: - dput(dentry); + end_creating(dentry); return ERR_PTR(error); } EXPORT_SYMBOL(vfs_mkdir); @@ -4473,6 +5150,7 @@ int do_mkdirat(int dfd, struct filename *name, umode_t mode) struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; + struct delegated_inode delegated_inode = { }; retry: dentry = filename_create(dfd, name, &path, lookup_flags); @@ -4484,11 +5162,16 @@ retry: mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, - dentry, mode); + dentry, mode, &delegated_inode); if (IS_ERR(dentry)) error = PTR_ERR(dentry); } end_creating_path(&path, dentry); + if (is_delegated(&delegated_inode)) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry; + } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; @@ -4510,9 +5193,10 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) /** * vfs_rmdir - remove directory - * @idmap: idmap of the mount the inode was found from - * @dir: inode of the parent directory - * @dentry: dentry of the child directory + * @idmap: idmap of the mount the inode was found from + * @dir: inode of the parent directory + * @dentry: dentry of the child directory + * @delegated_inode: returns parent inode, if it's delegated. * * Remove a directory. * @@ -4523,7 +5207,7 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) * raw inode simply pass @nop_mnt_idmap. */ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry) + struct dentry *dentry, struct delegated_inode *delegated_inode) { int error = may_delete(idmap, dir, dentry, 1); @@ -4545,6 +5229,10 @@ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, if (error) goto out; + error = try_break_deleg(dir, delegated_inode); + if (error) + goto out; + error = dir->i_op->rmdir(dir, dentry); if (error) goto out; @@ -4571,6 +5259,7 @@ int do_rmdir(int dfd, struct filename *name) struct qstr last; int type; unsigned int lookup_flags = 0; + struct delegated_inode delegated_inode = { }; retry: error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) @@ -4592,22 +5281,26 @@ retry: if (error) goto exit2; - inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); - dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); + dentry = start_dirop(path.dentry, &last, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit3; error = security_path_rmdir(&path, dentry); if (error) goto exit4; - error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry); + error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode, + dentry, &delegated_inode); exit4: - dput(dentry); + end_dirop(dentry); exit3: - inode_unlock(path.dentry->d_inode); mnt_drop_write(path.mnt); exit2: path_put(&path); + if (is_delegated(&delegated_inode)) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry; + } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; @@ -4648,7 +5341,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) * raw inode simply pass @nop_mnt_idmap. */ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, struct inode **delegated_inode) + struct dentry *dentry, struct delegated_inode *delegated_inode) { struct inode *target = dentry->d_inode; int error = may_delete(idmap, dir, dentry, 0); @@ -4667,6 +5360,9 @@ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir, else { error = security_inode_unlink(dir, dentry); if (!error) { + error = try_break_deleg(dir, delegated_inode); + if (error) + goto out; error = try_break_deleg(target, delegated_inode); if (error) goto out; @@ -4705,67 +5401,62 @@ int do_unlinkat(int dfd, struct filename *name) struct path path; struct qstr last; int type; - struct inode *inode = NULL; - struct inode *delegated_inode = NULL; + struct inode *inode; + struct delegated_inode delegated_inode = { }; unsigned int lookup_flags = 0; retry: error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) - goto exit1; + goto exit_putname; error = -EISDIR; if (type != LAST_NORM) - goto exit2; + goto exit_path_put; error = mnt_want_write(path.mnt); if (error) - goto exit2; + goto exit_path_put; retry_deleg: - inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); - dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); + dentry = start_dirop(path.dentry, &last, lookup_flags); error = PTR_ERR(dentry); - if (!IS_ERR(dentry)) { + if (IS_ERR(dentry)) + goto exit_drop_write; - /* Why not before? Because we want correct error value */ - if (last.name[last.len]) - goto slashes; - inode = dentry->d_inode; - ihold(inode); - error = security_path_unlink(&path, dentry); - if (error) - goto exit3; - error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode, - dentry, &delegated_inode); -exit3: - dput(dentry); + /* Why not before? Because we want correct error value */ + if (unlikely(last.name[last.len])) { + if (d_is_dir(dentry)) + error = -EISDIR; + else + error = -ENOTDIR; + end_dirop(dentry); + goto exit_drop_write; } - inode_unlock(path.dentry->d_inode); - if (inode) - iput(inode); /* truncate the inode here */ - inode = NULL; - if (delegated_inode) { + inode = dentry->d_inode; + ihold(inode); + error = security_path_unlink(&path, dentry); + if (error) + goto exit_end_dirop; + error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode, + dentry, &delegated_inode); +exit_end_dirop: + end_dirop(dentry); + iput(inode); /* truncate the inode here */ + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } +exit_drop_write: mnt_drop_write(path.mnt); -exit2: +exit_path_put: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; - inode = NULL; goto retry; } -exit1: +exit_putname: putname(name); return error; - -slashes: - if (d_is_dir(dentry)) - error = -EISDIR; - else - error = -ENOTDIR; - goto exit3; } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) @@ -4789,6 +5480,7 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) * @dir: inode of the parent directory * @dentry: dentry of the child symlink file * @oldname: name of the file to link to + * @delegated_inode: returns victim inode, if the inode is delegated. * * Create a symlink. * @@ -4799,7 +5491,8 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) * raw inode simply pass @nop_mnt_idmap. */ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, const char *oldname) + struct dentry *dentry, const char *oldname, + struct delegated_inode *delegated_inode) { int error; @@ -4814,6 +5507,10 @@ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, if (error) return error; + error = try_break_deleg(dir, delegated_inode); + if (error) + return error; + error = dir->i_op->symlink(idmap, dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); @@ -4827,6 +5524,7 @@ int do_symlinkat(struct filename *from, int newdfd, struct filename *to) struct dentry *dentry; struct path path; unsigned int lookup_flags = 0; + struct delegated_inode delegated_inode = { }; if (IS_ERR(from)) { error = PTR_ERR(from); @@ -4841,8 +5539,13 @@ retry: error = security_path_symlink(&path, dentry, from->name); if (!error) error = vfs_symlink(mnt_idmap(path.mnt), path.dentry->d_inode, - dentry, from->name); + dentry, from->name, &delegated_inode); end_creating_path(&path, dentry); + if (is_delegated(&delegated_inode)) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry; + } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; @@ -4892,7 +5595,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn */ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap, struct inode *dir, struct dentry *new_dentry, - struct inode **delegated_inode) + struct delegated_inode *delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; @@ -4931,19 +5634,21 @@ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap, inode_lock(inode); /* Make sure we don't allow creating hardlink to an unlinked file */ - if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE)) + if (inode->i_nlink == 0 && !(inode_state_read_once(inode) & I_LINKABLE)) error = -ENOENT; else if (max_links && inode->i_nlink >= max_links) error = -EMLINK; else { - error = try_break_deleg(inode, delegated_inode); + error = try_break_deleg(dir, delegated_inode); + if (!error) + error = try_break_deleg(inode, delegated_inode); if (!error) error = dir->i_op->link(old_dentry, dir, new_dentry); } - if (!error && (inode->i_state & I_LINKABLE)) { + if (!error && (inode_state_read_once(inode) & I_LINKABLE)) { spin_lock(&inode->i_lock); - inode->i_state &= ~I_LINKABLE; + inode_state_clear(inode, I_LINKABLE); spin_unlock(&inode->i_lock); } inode_unlock(inode); @@ -4968,7 +5673,7 @@ int do_linkat(int olddfd, struct filename *old, int newdfd, struct mnt_idmap *idmap; struct dentry *new_dentry; struct path old_path, new_path; - struct inode *delegated_inode = NULL; + struct delegated_inode delegated_inode = { }; int how = 0; int error; @@ -5012,7 +5717,7 @@ retry: new_dentry, &delegated_inode); out_dput: end_creating_path(&new_path, new_dentry); - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) { path_put(&old_path); @@ -5098,7 +5803,7 @@ int vfs_rename(struct renamedata *rd) struct inode *new_dir = d_inode(rd->new_parent); struct dentry *old_dentry = rd->old_dentry; struct dentry *new_dentry = rd->new_dentry; - struct inode **delegated_inode = rd->delegated_inode; + struct delegated_inode *delegated_inode = rd->delegated_inode; unsigned int flags = rd->flags; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; @@ -5203,6 +5908,14 @@ int vfs_rename(struct renamedata *rd) old_dir->i_nlink >= max_links) goto out; } + error = try_break_deleg(old_dir, delegated_inode); + if (error) + goto out; + if (new_dir != old_dir) { + error = try_break_deleg(new_dir, delegated_inode); + if (error) + goto out; + } if (!is_dir) { error = try_break_deleg(source, delegated_inode); if (error) @@ -5256,14 +5969,11 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { struct renamedata rd; - struct dentry *old_dentry, *new_dentry; - struct dentry *trap; struct path old_path, new_path; struct qstr old_last, new_last; int old_type, new_type; - struct inode *delegated_inode = NULL; - unsigned int lookup_flags = 0, target_flags = - LOOKUP_RENAME_TARGET | LOOKUP_CREATE; + struct delegated_inode delegated_inode = { }; + unsigned int lookup_flags = 0; bool should_retry = false; int error = -EINVAL; @@ -5274,11 +5984,6 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd, (flags & RENAME_EXCHANGE)) goto put_names; - if (flags & RENAME_EXCHANGE) - target_flags = 0; - if (flags & RENAME_NOREPLACE) - target_flags |= LOOKUP_EXCL; - retry: error = filename_parentat(olddfd, from, lookup_flags, &old_path, &old_last, &old_type); @@ -5308,68 +6013,42 @@ retry: goto exit2; retry_deleg: - trap = lock_rename(new_path.dentry, old_path.dentry); - if (IS_ERR(trap)) { - error = PTR_ERR(trap); + rd.old_parent = old_path.dentry; + rd.mnt_idmap = mnt_idmap(old_path.mnt); + rd.new_parent = new_path.dentry; + rd.delegated_inode = &delegated_inode; + rd.flags = flags; + + error = __start_renaming(&rd, lookup_flags, &old_last, &new_last); + if (error) goto exit_lock_rename; - } - old_dentry = lookup_one_qstr_excl(&old_last, old_path.dentry, - lookup_flags); - error = PTR_ERR(old_dentry); - if (IS_ERR(old_dentry)) - goto exit3; - new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry, - lookup_flags | target_flags); - error = PTR_ERR(new_dentry); - if (IS_ERR(new_dentry)) - goto exit4; if (flags & RENAME_EXCHANGE) { - if (!d_is_dir(new_dentry)) { + if (!d_is_dir(rd.new_dentry)) { error = -ENOTDIR; if (new_last.name[new_last.len]) - goto exit5; + goto exit_unlock; } } /* unless the source is a directory trailing slashes give -ENOTDIR */ - if (!d_is_dir(old_dentry)) { + if (!d_is_dir(rd.old_dentry)) { error = -ENOTDIR; if (old_last.name[old_last.len]) - goto exit5; + goto exit_unlock; if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len]) - goto exit5; + goto exit_unlock; } - /* source should not be ancestor of target */ - error = -EINVAL; - if (old_dentry == trap) - goto exit5; - /* target should not be an ancestor of source */ - if (!(flags & RENAME_EXCHANGE)) - error = -ENOTEMPTY; - if (new_dentry == trap) - goto exit5; - error = security_path_rename(&old_path, old_dentry, - &new_path, new_dentry, flags); + error = security_path_rename(&old_path, rd.old_dentry, + &new_path, rd.new_dentry, flags); if (error) - goto exit5; + goto exit_unlock; - rd.old_parent = old_path.dentry; - rd.old_dentry = old_dentry; - rd.mnt_idmap = mnt_idmap(old_path.mnt); - rd.new_parent = new_path.dentry; - rd.new_dentry = new_dentry; - rd.delegated_inode = &delegated_inode; - rd.flags = flags; error = vfs_rename(&rd); -exit5: - dput(new_dentry); -exit4: - dput(old_dentry); -exit3: - unlock_rename(new_path.dentry, old_path.dentry); +exit_unlock: + end_renaming(&rd); exit_lock_rename: - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; diff --git a/fs/namespace.c b/fs/namespace.c index d82910f33dc4..c58674a20cad 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -132,16 +132,6 @@ EXPORT_SYMBOL_GPL(fs_kobj); */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); -static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node) -{ - struct ns_common *ns; - - if (!node) - return NULL; - ns = rb_entry(node, struct ns_common, ns_tree_node); - return container_of(ns, struct mnt_namespace, ns); -} - static void mnt_ns_release(struct mnt_namespace *ns) { /* keep alive for {list,stat}mount() */ @@ -151,7 +141,8 @@ static void mnt_ns_release(struct mnt_namespace *ns) kfree(ns); } } -DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T)) +DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, + if (!IS_ERR(_T)) mnt_ns_release(_T)) static void mnt_ns_release_rcu(struct rcu_head *rcu) { @@ -1345,26 +1336,12 @@ static void delayed_mntput(struct work_struct *unused) } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); -static void mntput_no_expire(struct mount *mnt) +static void noinline mntput_no_expire_slowpath(struct mount *mnt) { LIST_HEAD(list); int count; - rcu_read_lock(); - if (likely(READ_ONCE(mnt->mnt_ns))) { - /* - * Since we don't do lock_mount_hash() here, - * ->mnt_ns can change under us. However, if it's - * non-NULL, then there's a reference that won't - * be dropped until after an RCU delay done after - * turning ->mnt_ns NULL. So if we observe it - * non-NULL under rcu_read_lock(), the reference - * we are dropping is not the final one. - */ - mnt_add_count(mnt, -1); - rcu_read_unlock(); - return; - } + VFS_BUG_ON(mnt->mnt_ns); lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab @@ -1415,6 +1392,26 @@ static void mntput_no_expire(struct mount *mnt) cleanup_mnt(mnt); } +static void mntput_no_expire(struct mount *mnt) +{ + rcu_read_lock(); + if (likely(READ_ONCE(mnt->mnt_ns))) { + /* + * Since we don't do lock_mount_hash() here, + * ->mnt_ns can change under us. However, if it's + * non-NULL, then there's a reference that won't + * be dropped until after an RCU delay done after + * turning ->mnt_ns NULL. So if we observe it + * non-NULL under rcu_read_lock(), the reference + * we are dropping is not the final one. + */ + mnt_add_count(mnt, -1); + rcu_read_unlock(); + return; + } + mntput_no_expire_slowpath(mnt); +} + void mntput(struct vfsmount *mnt) { if (mnt) { @@ -3103,19 +3100,7 @@ static struct file *vfs_open_tree(int dfd, const char __user *filename, unsigned SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { - int fd; - struct file *file __free(fput) = NULL; - - file = vfs_open_tree(dfd, filename, flags); - if (IS_ERR(file)) - return PTR_ERR(file); - - fd = get_unused_fd_flags(flags & O_CLOEXEC); - if (fd < 0) - return fd; - - fd_install(fd, no_free_ptr(file)); - return fd; + return FD_ADD(flags, vfs_open_tree(dfd, filename, flags)); } /* @@ -4093,8 +4078,9 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } - if (!anon) - ns_tree_gen_id(&new_ns->ns); + ns_tree_gen_id(new_ns); + + new_ns->is_anon = anon; refcount_set(&new_ns->passive, 1); new_ns->mounts = RB_ROOT; init_waitqueue_head(&new_ns->poll); @@ -4283,10 +4269,10 @@ static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { + struct path new_path __free(path_put) = {}; struct mnt_namespace *ns; struct fs_context *fc; - struct file *file; - struct path newmount; + struct vfsmount *new_mnt; struct mount *mnt; unsigned int mnt_flags = 0; long ret; @@ -4324,35 +4310,36 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, fc = fd_file(f)->private_data; - ret = mutex_lock_interruptible(&fc->uapi_mutex); - if (ret < 0) + ACQUIRE(mutex_intr, uapi_mutex)(&fc->uapi_mutex); + ret = ACQUIRE_ERR(mutex_intr, &uapi_mutex); + if (ret) return ret; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) - goto err_unlock; + return ret; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { errorfcp(fc, "VFS", "Mount too revealing"); - goto err_unlock; + return ret; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) - goto err_unlock; + return ret; if (fc->sb_flags & SB_MANDLOCK) warn_mandlock(); - 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; + new_mnt = vfs_create_mount(fc); + if (IS_ERR(new_mnt)) + return PTR_ERR(new_mnt); + new_mnt->mnt_flags = mnt_flags; + + new_path.dentry = dget(fc->root); + new_path.mnt = new_mnt; /* 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 @@ -4362,38 +4349,27 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, 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); + if (IS_ERR(ns)) + return PTR_ERR(ns); + mnt = real_mount(new_path.mnt); ns->root = mnt; ns->nr_mounts = 1; mnt_add_to_ns(ns, mnt); - mntget(newmount.mnt); + mntget(new_path.mnt); - /* 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; + FD_PREPARE(fdf, (flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0, + dentry_open(&new_path, O_PATH, fc->cred)); + if (fdf.err) { + dissolve_on_fput(new_path.mnt); + return fdf.err; } - 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); - return ret; + /* + * Attach to an apparent O_PATH fd with a note that we + * need to unmount it, not just simply put it. + */ + fd_prepare_file(fdf)->f_mode |= FMODE_NEED_UNMOUNT; + return fd_publish(fdf); } static inline int vfs_move_mount(const struct path *from_path, @@ -5035,19 +5011,17 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename, unsigned, flags, struct mount_attr __user *, uattr, size_t, usize) { - struct file __free(fput) *file = NULL; - int fd; - if (!uattr && usize) return -EINVAL; - file = vfs_open_tree(dfd, filename, flags); - if (IS_ERR(file)) - return PTR_ERR(file); + FD_PREPARE(fdf, flags, vfs_open_tree(dfd, filename, flags)); + if (fdf.err) + return fdf.err; if (uattr) { - int ret; struct mount_kattr kattr = {}; + struct file *file = fd_prepare_file(fdf); + int ret; if (flags & OPEN_TREE_CLONE) kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE; @@ -5063,12 +5037,7 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename, return ret; } - fd = get_unused_fd_flags(flags & O_CLOEXEC); - if (fd < 0) - return fd; - - fd_install(fd, no_free_ptr(file)); - return fd; + return fd_publish(fdf); } int show_path(struct seq_file *m, struct dentry *root) @@ -5150,6 +5119,12 @@ static u64 mnt_to_propagation_flags(struct mount *m) return propagation; } +u64 vfsmount_to_propagation_flags(struct vfsmount *mnt) +{ + return mnt_to_propagation_flags(real_mount(mnt)); +} +EXPORT_SYMBOL_GPL(vfsmount_to_propagation_flags); + static void statmount_sb_basic(struct kstatmount *s) { struct super_block *sb = s->mnt->mnt_sb; @@ -5454,11 +5429,11 @@ static int statmount_string(struct kstatmount *s, u64 flag) ret = statmount_sb_source(s, seq); break; case STATMOUNT_MNT_UIDMAP: - sm->mnt_uidmap = start; + offp = &sm->mnt_uidmap; ret = statmount_mnt_uidmap(s, seq); break; case STATMOUNT_MNT_GIDMAP: - sm->mnt_gidmap = start; + offp = &sm->mnt_gidmap; ret = statmount_mnt_gidmap(s, seq); break; default: @@ -5736,7 +5711,7 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req, ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); if (ret) return ret; - if (kreq->spare != 0) + if (kreq->mnt_ns_fd != 0 && kreq->mnt_ns_id) return -EINVAL; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (kreq->mnt_id <= MNT_UNIQUE_ID_OFFSET) @@ -5753,16 +5728,14 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq { struct mnt_namespace *mnt_ns; - if (kreq->mnt_ns_id && kreq->spare) - return ERR_PTR(-EINVAL); - - if (kreq->mnt_ns_id) - return lookup_mnt_ns(kreq->mnt_ns_id); - - if (kreq->spare) { + if (kreq->mnt_ns_id) { + mnt_ns = lookup_mnt_ns(kreq->mnt_ns_id); + if (!mnt_ns) + return ERR_PTR(-ENOENT); + } else if (kreq->mnt_ns_fd) { struct ns_common *ns; - CLASS(fd, f)(kreq->spare); + CLASS(fd, f)(kreq->mnt_ns_fd); if (fd_empty(f)) return ERR_PTR(-EBADF); @@ -5774,11 +5747,12 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq return ERR_PTR(-EINVAL); mnt_ns = to_mnt_ns(ns); + refcount_inc(&mnt_ns->passive); } else { mnt_ns = current->nsproxy->mnt_ns; + refcount_inc(&mnt_ns->passive); } - refcount_inc(&mnt_ns->passive); return mnt_ns; } @@ -5801,8 +5775,8 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, return ret; ns = grab_requested_mnt_ns(&kreq); - if (!ns) - return -ENOENT; + if (IS_ERR(ns)) + return PTR_ERR(ns); if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) @@ -5912,8 +5886,8 @@ static void __free_klistmount_free(const struct klistmount *kls) static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req *kreq, size_t nr_mnt_ids) { - u64 last_mnt_id = kreq->param; + struct mnt_namespace *ns; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET) @@ -5927,9 +5901,10 @@ static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req * if (!kls->kmnt_ids) return -ENOMEM; - kls->ns = grab_requested_mnt_ns(kreq); - if (!kls->ns) - return -ENOENT; + ns = grab_requested_mnt_ns(kreq); + if (IS_ERR(ns)) + return PTR_ERR(ns); + kls->ns = ns; kls->mnt_parent_id = kreq->mnt_id; return 0; @@ -5985,11 +5960,8 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, } struct mnt_namespace init_mnt_ns = { - .ns.inum = ns_init_inum(&init_mnt_ns), - .ns.ops = &mntns_operations, + .ns = NS_COMMON_INIT(init_mnt_ns), .user_ns = &init_user_ns, - .ns.__ns_ref = REFCOUNT_INIT(1), - .ns.ns_type = ns_common_type(&init_mnt_ns), .passive = REFCOUNT_INIT(1), .mounts = RB_ROOT, .poll = __WAIT_QUEUE_HEAD_INITIALIZER(init_mnt_ns.poll), diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 09394ac2c180..f9d62abef2ac 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -535,7 +535,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr folio_unlock(folio); err = filemap_fdatawrite_range(mapping, folio_pos(folio), - folio_pos(folio) + folio_size(folio)); + folio_next_pos(folio)); switch (err) { case 0: ret = VM_FAULT_RETRY; diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 486166460e17..6df89c92b10b 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -147,10 +147,10 @@ bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio) if (!fscache_cookie_valid(cookie)) return true; - if (!(inode->i_state & I_PINNING_NETFS_WB)) { + if (!(inode_state_read_once(inode) & I_PINNING_NETFS_WB)) { spin_lock(&inode->i_lock); - if (!(inode->i_state & I_PINNING_NETFS_WB)) { - inode->i_state |= I_PINNING_NETFS_WB; + if (!(inode_state_read(inode) & I_PINNING_NETFS_WB)) { + inode_state_set(inode, I_PINNING_NETFS_WB); need_use = true; } spin_unlock(&inode->i_lock); @@ -192,7 +192,7 @@ void netfs_clear_inode_writeback(struct inode *inode, const void *aux) { struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode)); - if (inode->i_state & I_PINNING_NETFS_WB) { + if (inode_state_read_once(inode) & I_PINNING_NETFS_WB) { loff_t i_size = i_size_read(inode); fscache_unuse_cookie(cookie, aux, &i_size); } @@ -298,7 +298,7 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp) if (folio_test_dirty(folio)) return false; - end = umin(folio_pos(folio) + folio_size(folio), i_size_read(&ctx->inode)); + end = umin(folio_next_pos(folio), i_size_read(&ctx->inode)); if (end > ctx->zero_point) ctx->zero_point = end; diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index 5c0dc4efc792..8e6264f62a8f 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -36,12 +36,12 @@ void netfs_single_mark_inode_dirty(struct inode *inode) mark_inode_dirty(inode); - if (caching && !(inode->i_state & I_PINNING_NETFS_WB)) { + if (caching && !(inode_state_read_once(inode) & I_PINNING_NETFS_WB)) { bool need_use = false; spin_lock(&inode->i_lock); - if (!(inode->i_state & I_PINNING_NETFS_WB)) { - inode->i_state |= I_PINNING_NETFS_WB; + if (!(inode_state_read(inode) & I_PINNING_NETFS_WB)) { + inode_state_set(inode, I_PINNING_NETFS_WB); need_use = true; } spin_unlock(&inode->i_lock); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 4e3dcc157a83..54699299d5b1 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -338,6 +338,14 @@ again: /* Match the xprt security policy */ if (clp->cl_xprtsec.policy != data->xprtsec.policy) continue; + if (clp->cl_xprtsec.policy == RPC_XPRTSEC_TLS_X509) { + if (clp->cl_xprtsec.cert_serial != + data->xprtsec.cert_serial) + continue; + if (clp->cl_xprtsec.privkey_serial != + data->xprtsec.privkey_serial) + continue; + } refcount_inc(&clp->cl_count); return clp; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 46d9c65d50f8..ea9f6ca8f30f 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2268,11 +2268,12 @@ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, return -ENAMETOOLONG; if (open_flags & O_CREAT) { - file->f_mode |= FMODE_CREATED; error = nfs_do_create(dir, dentry, mode, open_flags); - if (error) + if (!error) { + file->f_mode |= FMODE_CREATED; + return finish_open(file, dentry, NULL); + } else if (error != -EEXIST || open_flags & O_EXCL) return error; - return finish_open(file, dentry, NULL); } if (d_in_lookup(dentry)) { /* The only flags nfs_lookup considers are diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 18b57c7c2f97..f76fe406937a 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -475,7 +475,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) goto out_no_inode; } - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long now = jiffies; @@ -718,6 +718,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct nfs_fattr *fattr; loff_t oldsize = i_size_read(inode); int error = 0; + kuid_t task_uid = current_fsuid(); + kuid_t owner_uid = inode->i_uid; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); @@ -739,9 +741,11 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) { spin_lock(&inode->i_lock); if (attr->ia_valid & ATTR_MTIME_SET) { - nfs_set_timestamps_to_ts(inode, attr); - attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET| + if (uid_eq(task_uid, owner_uid)) { + nfs_set_timestamps_to_ts(inode, attr); + attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET| ATTR_ATIME|ATTR_ATIME_SET); + } } else { nfs_update_timestamps(inode, attr->ia_valid); attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME); @@ -751,10 +755,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, attr->ia_valid & ATTR_ATIME && !(attr->ia_valid & ATTR_MTIME)) { if (attr->ia_valid & ATTR_ATIME_SET) { - spin_lock(&inode->i_lock); - nfs_set_timestamps_to_ts(inode, attr); - spin_unlock(&inode->i_lock); - attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET); + if (uid_eq(task_uid, owner_uid)) { + spin_lock(&inode->i_lock); + nfs_set_timestamps_to_ts(inode, attr); + spin_unlock(&inode->i_lock); + attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET); + } } else { nfs_update_delegated_atime(inode); attr->ia_valid &= ~ATTR_ATIME; diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index 2c0455e91571..49ed90c6b9f2 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -42,10 +42,9 @@ struct nfs_local_kiocb { /* Begin mostly DIO-specific members */ size_t end_len; short int end_iter_index; - short int n_iters; + atomic_t n_iters; bool iter_is_dio_aligned[NFSLOCAL_MAX_IOS]; - loff_t offset[NFSLOCAL_MAX_IOS] ____cacheline_aligned; - struct iov_iter iters[NFSLOCAL_MAX_IOS]; + struct iov_iter iters[NFSLOCAL_MAX_IOS] ____cacheline_aligned; /* End mostly DIO-specific members */ }; @@ -314,7 +313,9 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, init_sync_kiocb(&iocb->kiocb, file); iocb->hdr = hdr; + iocb->kiocb.ki_pos = hdr->args.offset; iocb->kiocb.ki_flags &= ~IOCB_APPEND; + iocb->kiocb.ki_complete = NULL; iocb->aio_complete_work = NULL; iocb->end_iter_index = -1; @@ -388,13 +389,24 @@ static bool nfs_iov_iter_aligned_bvec(const struct iov_iter *i, return true; } +static void +nfs_local_iter_setup(struct iov_iter *iter, int rw, struct bio_vec *bvec, + unsigned int nvecs, unsigned long total, + size_t start, size_t len) +{ + iov_iter_bvec(iter, rw, bvec, nvecs, total); + if (start) + iov_iter_advance(iter, start); + iov_iter_truncate(iter, len); +} + /* * Setup as many as 3 iov_iter based on extents described by @local_dio. * Returns the number of iov_iter that were setup. */ static int nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw, - unsigned int nvecs, size_t len, + unsigned int nvecs, unsigned long total, struct nfs_local_dio *local_dio) { int n_iters = 0; @@ -402,39 +414,17 @@ nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw, /* Setup misaligned start? */ if (local_dio->start_len) { - iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len); - iters[n_iters].count = local_dio->start_len; - iocb->offset[n_iters] = iocb->hdr->args.offset; - iocb->iter_is_dio_aligned[n_iters] = false; + nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec, + nvecs, total, 0, local_dio->start_len); ++n_iters; } - /* Setup misaligned end? - * If so, the end is purposely setup to be issued using buffered IO - * before the middle (which will use DIO, if DIO-aligned, with AIO). - * This creates problems if/when the end results in a partial write. - * So must save index and length of end to handle this corner case. - */ - if (local_dio->end_len) { - iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len); - iocb->offset[n_iters] = local_dio->end_offset; - iov_iter_advance(&iters[n_iters], - local_dio->start_len + local_dio->middle_len); - iocb->iter_is_dio_aligned[n_iters] = false; - /* Save index and length of end */ - iocb->end_iter_index = n_iters; - iocb->end_len = local_dio->end_len; - ++n_iters; - } - - /* Setup DIO-aligned middle to be issued last, to allow for - * DIO with AIO completion (see nfs_local_call_{read,write}). + /* + * Setup DIO-aligned middle, if there is no misaligned end (below) + * then AIO completion is used, see nfs_local_call_{read,write} */ - iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len); - if (local_dio->start_len) - iov_iter_advance(&iters[n_iters], local_dio->start_len); - iters[n_iters].count -= local_dio->end_len; - iocb->offset[n_iters] = local_dio->middle_offset; + nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec, nvecs, + total, local_dio->start_len, local_dio->middle_len); iocb->iter_is_dio_aligned[n_iters] = nfs_iov_iter_aligned_bvec(&iters[n_iters], @@ -442,12 +432,22 @@ nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw, if (unlikely(!iocb->iter_is_dio_aligned[n_iters])) { trace_nfs_local_dio_misaligned(iocb->hdr->inode, - iocb->hdr->args.offset, len, local_dio); + local_dio->start_len, local_dio->middle_len, local_dio); return 0; /* no DIO-aligned IO possible */ } + iocb->end_iter_index = n_iters; ++n_iters; - iocb->n_iters = n_iters; + /* Setup misaligned end? */ + if (local_dio->end_len) { + nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec, + nvecs, total, local_dio->start_len + + local_dio->middle_len, local_dio->end_len); + iocb->end_iter_index = n_iters; + ++n_iters; + } + + atomic_set(&iocb->n_iters, n_iters); return n_iters; } @@ -473,18 +473,26 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw) } len = hdr->args.count - total; + /* + * For each iocb, iocb->n_iters is always at least 1 and we always + * end io after first nfs_local_pgio_done call unless misaligned DIO. + */ + atomic_set(&iocb->n_iters, 1); + if (test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) { struct nfs_local_dio local_dio; if (nfs_is_local_dio_possible(iocb, rw, len, &local_dio) && - nfs_local_iters_setup_dio(iocb, rw, v, len, &local_dio) != 0) + nfs_local_iters_setup_dio(iocb, rw, v, len, &local_dio) != 0) { + /* Ensure DIO WRITE's IO on stable storage upon completion */ + if (rw == ITER_SOURCE) + iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC; return; /* is DIO-aligned */ + } } /* Use buffered IO */ - iocb->offset[0] = hdr->args.offset; iov_iter_bvec(&iocb->iters[0], rw, iocb->bvec, v, len); - iocb->n_iters = 1; } static void @@ -504,9 +512,11 @@ nfs_local_pgio_init(struct nfs_pgio_header *hdr, hdr->task.tk_start = ktime_get(); } -static void -nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status) +static bool +nfs_local_pgio_done(struct nfs_local_kiocb *iocb, long status, bool force) { + struct nfs_pgio_header *hdr = iocb->hdr; + /* Must handle partial completions */ if (status >= 0) { hdr->res.count += status; @@ -517,6 +527,12 @@ nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status) hdr->res.op_status = nfs_localio_errno_to_nfs4_stat(status); hdr->task.tk_status = status; } + + if (force) + return true; + + BUG_ON(atomic_read(&iocb->n_iters) <= 0); + return atomic_dec_and_test(&iocb->n_iters); } static void @@ -547,11 +563,11 @@ static inline void nfs_local_pgio_aio_complete(struct nfs_local_kiocb *iocb) queue_work(nfsiod_workqueue, &iocb->work); } -static void -nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) +static void nfs_local_read_done(struct nfs_local_kiocb *iocb) { struct nfs_pgio_header *hdr = iocb->hdr; struct file *filp = iocb->kiocb.ki_filp; + long status = hdr->task.tk_status; if ((iocb->kiocb.ki_flags & IOCB_DIRECT) && status == -EINVAL) { /* Underlying FS will return -EINVAL if misaligned DIO is attempted. */ @@ -564,20 +580,27 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) */ hdr->res.replen = 0; - if (hdr->res.count != hdr->args.count || - hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp))) + /* nfs_readpage_result() handles short read */ + + if (hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp))) hdr->res.eof = true; dprintk("%s: read %ld bytes eof %d.\n", __func__, status > 0 ? status : 0, hdr->res.eof); } +static inline void nfs_local_read_iocb_done(struct nfs_local_kiocb *iocb) +{ + nfs_local_read_done(iocb); + nfs_local_pgio_release(iocb); +} + static void nfs_local_read_aio_complete_work(struct work_struct *work) { struct nfs_local_kiocb *iocb = container_of(work, struct nfs_local_kiocb, work); - nfs_local_pgio_release(iocb); + nfs_local_read_iocb_done(iocb); } static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret) @@ -585,43 +608,51 @@ static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret) struct nfs_local_kiocb *iocb = container_of(kiocb, struct nfs_local_kiocb, kiocb); - nfs_local_pgio_done(iocb->hdr, ret); - nfs_local_read_done(iocb, ret); + /* AIO completion of DIO read should always be last to complete */ + if (unlikely(!nfs_local_pgio_done(iocb, ret, false))) + return; + nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */ } -static void nfs_local_call_read(struct work_struct *work) +static void do_nfs_local_call_read(struct nfs_local_kiocb *iocb, struct file *filp) { - struct nfs_local_kiocb *iocb = - container_of(work, struct nfs_local_kiocb, work); - struct file *filp = iocb->kiocb.ki_filp; - const struct cred *save_cred; + bool force_done = false; ssize_t status; + int n_iters; - save_cred = override_creds(filp->f_cred); - - for (int i = 0; i < iocb->n_iters ; i++) { + n_iters = atomic_read(&iocb->n_iters); + for (int i = 0; i < n_iters ; i++) { if (iocb->iter_is_dio_aligned[i]) { iocb->kiocb.ki_flags |= IOCB_DIRECT; - iocb->kiocb.ki_complete = nfs_local_read_aio_complete; - iocb->aio_complete_work = nfs_local_read_aio_complete_work; - } + /* Only use AIO completion if DIO-aligned segment is last */ + if (i == iocb->end_iter_index) { + iocb->kiocb.ki_complete = nfs_local_read_aio_complete; + iocb->aio_complete_work = nfs_local_read_aio_complete_work; + } + } else + iocb->kiocb.ki_flags &= ~IOCB_DIRECT; - iocb->kiocb.ki_pos = iocb->offset[i]; status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]); if (status != -EIOCBQUEUED) { - nfs_local_pgio_done(iocb->hdr, status); - if (iocb->hdr->task.tk_status) + if (unlikely(status >= 0 && status < iocb->iters[i].count)) + force_done = true; /* Partial read */ + if (nfs_local_pgio_done(iocb, status, force_done)) { + nfs_local_read_iocb_done(iocb); break; + } } } +} - revert_creds(save_cred); +static void nfs_local_call_read(struct work_struct *work) +{ + struct nfs_local_kiocb *iocb = + container_of(work, struct nfs_local_kiocb, work); + struct file *filp = iocb->kiocb.ki_filp; - if (status != -EIOCBQUEUED) { - nfs_local_read_done(iocb, status); - nfs_local_pgio_release(iocb); - } + scoped_with_creds(filp->f_cred) + do_nfs_local_call_read(iocb, filp); } static int @@ -736,11 +767,10 @@ static void nfs_local_vfs_getattr(struct nfs_local_kiocb *iocb) fattr->du.nfs3.used = stat.blocks << 9; } -static void -nfs_local_write_done(struct nfs_local_kiocb *iocb, long status) +static void nfs_local_write_done(struct nfs_local_kiocb *iocb) { struct nfs_pgio_header *hdr = iocb->hdr; - struct inode *inode = hdr->inode; + long status = hdr->task.tk_status; dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0); @@ -759,10 +789,17 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status) nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset); status = -ENOSPC; /* record -ENOSPC in terms of nfs_local_pgio_done */ - nfs_local_pgio_done(hdr, status); + (void) nfs_local_pgio_done(iocb, status, true); } if (hdr->task.tk_status < 0) - nfs_reset_boot_verifier(inode); + nfs_reset_boot_verifier(hdr->inode); +} + +static inline void nfs_local_write_iocb_done(struct nfs_local_kiocb *iocb) +{ + nfs_local_write_done(iocb); + nfs_local_vfs_getattr(iocb); + nfs_local_pgio_release(iocb); } static void nfs_local_write_aio_complete_work(struct work_struct *work) @@ -770,8 +807,7 @@ static void nfs_local_write_aio_complete_work(struct work_struct *work) struct nfs_local_kiocb *iocb = container_of(work, struct nfs_local_kiocb, work); - nfs_local_vfs_getattr(iocb); - nfs_local_pgio_release(iocb); + nfs_local_write_iocb_done(iocb); } static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret) @@ -779,75 +815,62 @@ static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret) struct nfs_local_kiocb *iocb = container_of(kiocb, struct nfs_local_kiocb, kiocb); - nfs_local_pgio_done(iocb->hdr, ret); - nfs_local_write_done(iocb, ret); + /* AIO completion of DIO write should always be last to complete */ + if (unlikely(!nfs_local_pgio_done(iocb, ret, false))) + return; + nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */ } -static void nfs_local_call_write(struct work_struct *work) +static ssize_t do_nfs_local_call_write(struct nfs_local_kiocb *iocb, + struct file *filp) { - struct nfs_local_kiocb *iocb = - container_of(work, struct nfs_local_kiocb, work); - struct file *filp = iocb->kiocb.ki_filp; - unsigned long old_flags = current->flags; - const struct cred *save_cred; + bool force_done = false; ssize_t status; - - current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; - save_cred = override_creds(filp->f_cred); + int n_iters; file_start_write(filp); - for (int i = 0; i < iocb->n_iters ; i++) { + n_iters = atomic_read(&iocb->n_iters); + for (int i = 0; i < n_iters ; i++) { if (iocb->iter_is_dio_aligned[i]) { iocb->kiocb.ki_flags |= IOCB_DIRECT; - iocb->kiocb.ki_complete = nfs_local_write_aio_complete; - iocb->aio_complete_work = nfs_local_write_aio_complete_work; - } -retry: - iocb->kiocb.ki_pos = iocb->offset[i]; + /* Only use AIO completion if DIO-aligned segment is last */ + if (i == iocb->end_iter_index) { + iocb->kiocb.ki_complete = nfs_local_write_aio_complete; + iocb->aio_complete_work = nfs_local_write_aio_complete_work; + } + } else + iocb->kiocb.ki_flags &= ~IOCB_DIRECT; + status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]); if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) { - /* partial write */ - if (i == iocb->end_iter_index) { - /* Must not account partial end, otherwise, due - * to end being issued before middle: the partial - * write accounting in nfs_local_write_done() - * would incorrectly advance hdr->args.offset - */ - status = 0; - } else { - /* Partial write at start or buffered middle, - * exit early. - */ - nfs_local_pgio_done(iocb->hdr, status); - break; - } - } else if (unlikely(status == -ENOTBLK && - (iocb->kiocb.ki_flags & IOCB_DIRECT))) { - /* VFS will return -ENOTBLK if DIO WRITE fails to - * invalidate the page cache. Retry using buffered IO. - */ - iocb->kiocb.ki_flags &= ~IOCB_DIRECT; - iocb->kiocb.ki_complete = NULL; - iocb->aio_complete_work = NULL; - goto retry; - } - nfs_local_pgio_done(iocb->hdr, status); - if (iocb->hdr->task.tk_status) + if (unlikely(status >= 0 && status < iocb->iters[i].count)) + force_done = true; /* Partial write */ + if (nfs_local_pgio_done(iocb, status, force_done)) { + nfs_local_write_iocb_done(iocb); break; + } } } file_end_write(filp); - revert_creds(save_cred); - current->flags = old_flags; + return status; +} - if (status != -EIOCBQUEUED) { - nfs_local_write_done(iocb, status); - nfs_local_vfs_getattr(iocb); - nfs_local_pgio_release(iocb); - } +static void nfs_local_call_write(struct work_struct *work) +{ + struct nfs_local_kiocb *iocb = + container_of(work, struct nfs_local_kiocb, work); + struct file *filp = iocb->kiocb.ki_filp; + unsigned long old_flags = current->flags; + ssize_t status; + + current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; + + scoped_with_creds(filp->f_cred) + status = do_nfs_local_call_write(iocb, filp); + + current->flags = old_flags; } static int diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 0d7310c1ee0c..5d97c1d38bb6 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -2,6 +2,7 @@ #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/sunrpc/addr.h> +#include <net/handshake.h> #include "internal.h" #include "nfs3_fs.h" #include "netns.h" @@ -98,7 +99,11 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, .net = mds_clp->cl_net, .timeparms = &ds_timeout, .cred = mds_srv->cred, - .xprtsec = mds_clp->cl_xprtsec, + .xprtsec = { + .policy = RPC_XPRTSEC_NONE, + .cert_serial = TLS_NO_CERT, + .privkey_serial = TLS_NO_PRIVKEY, + }, .connect_timeout = connect_timeout, .reconnect_timeout = connect_timeout, }; @@ -111,9 +116,14 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, cl_init.hostname = buf; switch (ds_proto) { + case XPRT_TRANSPORT_TCP_TLS: + if (mds_clp->cl_xprtsec.policy != RPC_XPRTSEC_NONE) + cl_init.xprtsec = mds_clp->cl_xprtsec; + else + ds_proto = XPRT_TRANSPORT_TCP; + fallthrough; case XPRT_TRANSPORT_RDMA: case XPRT_TRANSPORT_TCP: - case XPRT_TRANSPORT_TCP_TLS: if (mds_clp->cl_nconnect > 1) cl_init.nconnect = mds_clp->cl_nconnect; } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 5998d6bd8a4f..3a4baed993c9 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -11,6 +11,7 @@ #include <linux/sunrpc/xprt.h> #include <linux/sunrpc/bc_xprt.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include <net/handshake.h> #include "internal.h" #include "callback.h" #include "delegation.h" @@ -983,7 +984,11 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, .net = mds_clp->cl_net, .timeparms = &ds_timeout, .cred = mds_srv->cred, - .xprtsec = mds_srv->nfs_client->cl_xprtsec, + .xprtsec = { + .policy = RPC_XPRTSEC_NONE, + .cert_serial = TLS_NO_CERT, + .privkey_serial = TLS_NO_PRIVKEY, + }, }; char buf[INET6_ADDRSTRLEN + 1]; @@ -992,9 +997,14 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, cl_init.hostname = buf; switch (ds_proto) { + case XPRT_TRANSPORT_TCP_TLS: + if (mds_srv->nfs_client->cl_xprtsec.policy != RPC_XPRTSEC_NONE) + cl_init.xprtsec = mds_srv->nfs_client->cl_xprtsec; + else + ds_proto = XPRT_TRANSPORT_TCP; + fallthrough; case XPRT_TRANSPORT_RDMA: case XPRT_TRANSPORT_TCP: - case XPRT_TRANSPORT_TCP_TLS: if (mds_clp->cl_nconnect > 1) { cl_init.nconnect = mds_clp->cl_nconnect; cl_init.max_connect = NFS_MAX_TRANSPORTS; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 7f43e890d356..7317f26892c5 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -431,6 +431,8 @@ void nfs42_ssc_unregister_ops(void) static int nfs4_setlease(struct file *file, int arg, struct file_lease **lease, void **priv) { + if (!S_ISREG(file_inode(file)->i_mode)) + return -EINVAL; return nfs4_proc_setlease(file, arg, lease, priv); } diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 00932500fce4..9e1c48c5c0b8 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -306,15 +306,12 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, const char *type, void *data, size_t data_size, struct idmap *idmap) { - const struct cred *saved_cred; struct key *rkey; const struct user_key_payload *payload; ssize_t ret; - saved_cred = override_creds(id_resolver_cache); - rkey = nfs_idmap_request_key(name, namelen, type, idmap); - revert_creds(saved_cred); - + scoped_with_creds(id_resolver_cache) + rkey = nfs_idmap_request_key(name, namelen, type, idmap); if (IS_ERR(rkey)) { ret = PTR_ERR(rkey); goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 411776718494..93c6ce04332b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4715,16 +4715,19 @@ static int _nfs4_proc_lookupp(struct inode *inode, }; unsigned short task_flags = 0; - if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL) + if (server->flags & NFS_MOUNT_SOFTREVAL) task_flags |= RPC_TASK_TIMEOUT; + if (server->caps & NFS_CAP_MOVEABLE) + task_flags |= RPC_TASK_MOVEABLE; args.bitmask = nfs4_bitmask(server, fattr->label); nfs_fattr_init(fattr); + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); dprintk("NFS call lookupp ino=0x%lx\n", inode->i_ino); - status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, - &res.seq_res, task_flags); + status = nfs4_do_call_sync(clnt, server, &msg, &args.seq_args, + &res.seq_res, task_flags); dprintk("NFS reply lookupp: %d\n", status); return status; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index a3135b5af7ee..f157d43d1312 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -317,7 +317,7 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); pnfs_detach_layout_hdr(lo); /* Notify pnfs_destroy_layout_final() that we're done */ - if (inode->i_state & (I_FREEING | I_CLEAR)) + if (inode_state_read(inode) & (I_FREEING | I_CLEAR)) wake_up_var_locked(lo, &inode->i_lock); spin_unlock(&inode->i_lock); pnfs_free_layout_hdr(lo); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 7b32afb29782..9976cc16b689 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -809,8 +809,11 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, unsigned int retrans) { struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs_client *mds_clp = mds_srv->nfs_client; + enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy; struct nfs4_pnfs_ds_addr *da; unsigned long connect_timeout = timeo * (retrans + 1) * HZ / 10; + int ds_proto; int status = 0; dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); @@ -834,27 +837,28 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, .xprtsec = clp->cl_xprtsec, }; - if (da->da_transport != clp->cl_proto && - clp->cl_proto != XPRT_TRANSPORT_TCP_TLS) - continue; - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS) + if (xprt_args.ident == XPRT_TRANSPORT_TCP && + clp->cl_proto == XPRT_TRANSPORT_TCP_TLS) xprt_args.ident = XPRT_TRANSPORT_TCP_TLS; - if (da->da_addr.ss_family != clp->cl_addr.ss_family) + if (xprt_args.ident != clp->cl_proto) + continue; + if (xprt_args.dstaddr->sa_family != + clp->cl_addr.ss_family) continue; /* Add this address as an alias */ rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, - rpc_clnt_test_and_add_xprt, NULL); + rpc_clnt_test_and_add_xprt, NULL); continue; } - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS) - da->da_transport = XPRT_TRANSPORT_TCP_TLS; - clp = get_v3_ds_connect(mds_srv, - &da->da_addr, - da->da_addrlen, da->da_transport, - timeo, retrans); + + ds_proto = da->da_transport; + if (ds_proto == XPRT_TRANSPORT_TCP && + xprtsec_policy != RPC_XPRTSEC_NONE) + ds_proto = XPRT_TRANSPORT_TCP_TLS; + + clp = get_v3_ds_connect(mds_srv, &da->da_addr, da->da_addrlen, + ds_proto, timeo, retrans); if (IS_ERR(clp)) continue; clp->cl_rpcclient->cl_softerr = 0; @@ -880,7 +884,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, u32 minor_version) { struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs_client *mds_clp = mds_srv->nfs_client; + enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy; struct nfs4_pnfs_ds_addr *da; + int ds_proto; int status = 0; dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); @@ -908,12 +915,8 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, .data = &xprtdata, }; - if (da->da_transport != clp->cl_proto && - clp->cl_proto != XPRT_TRANSPORT_TCP_TLS) - continue; - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == - XPRT_TRANSPORT_TCP_TLS) { + if (xprt_args.ident == XPRT_TRANSPORT_TCP && + clp->cl_proto == XPRT_TRANSPORT_TCP_TLS) { struct sockaddr *addr = (struct sockaddr *)&da->da_addr; struct sockaddr_in *sin = @@ -944,7 +947,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, xprt_args.ident = XPRT_TRANSPORT_TCP_TLS; xprt_args.servername = servername; } - if (da->da_addr.ss_family != clp->cl_addr.ss_family) + if (xprt_args.ident != clp->cl_proto) + continue; + if (xprt_args.dstaddr->sa_family != + clp->cl_addr.ss_family) continue; /** @@ -958,15 +964,14 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, if (xprtdata.cred) put_cred(xprtdata.cred); } else { - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == - XPRT_TRANSPORT_TCP_TLS) - da->da_transport = XPRT_TRANSPORT_TCP_TLS; - clp = nfs4_set_ds_client(mds_srv, - &da->da_addr, - da->da_addrlen, - da->da_transport, timeo, - retrans, minor_version); + ds_proto = da->da_transport; + if (ds_proto == XPRT_TRANSPORT_TCP && + xprtsec_policy != RPC_XPRTSEC_NONE) + ds_proto = XPRT_TRANSPORT_TCP_TLS; + + clp = nfs4_set_ds_client(mds_srv, &da->da_addr, + da->da_addrlen, ds_proto, + timeo, retrans, minor_version); if (IS_ERR(clp)) continue; @@ -977,7 +982,6 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, clp = ERR_PTR(-EIO); continue; } - } } diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index 545148d42dcc..ea6e6168092b 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -189,6 +189,7 @@ static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent, return p; kobject_put(&p->kobject); + kobject_put(&p->nfs_net_kobj); } return NULL; } diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index a238b6725008..93798575b807 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1086,7 +1086,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, struct auth_domain *client, struct svc_fh *fhp, unsigned int may_flags, struct file *file, - struct nfsd_file **pnf, bool want_gc) + umode_t type, bool want_gc, struct nfsd_file **pnf) { unsigned char need = may_flags & NFSD_FILE_MAY_MASK; struct nfsd_file *new, *nf; @@ -1097,13 +1097,13 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, int ret; retry: - if (rqstp) { - status = fh_verify(rqstp, fhp, S_IFREG, + if (rqstp) + status = fh_verify(rqstp, fhp, type, may_flags|NFSD_MAY_OWNER_OVERRIDE); - } else { - status = fh_verify_local(net, cred, client, fhp, S_IFREG, + else + status = fh_verify_local(net, cred, client, fhp, type, may_flags|NFSD_MAY_OWNER_OVERRIDE); - } + if (status != nfs_ok) return status; inode = d_inode(fhp->fh_dentry); @@ -1176,15 +1176,18 @@ out: open_file: trace_nfsd_file_alloc(nf); - nf->nf_mark = nfsd_file_mark_find_or_create(inode); - if (nf->nf_mark) { + + if (type == S_IFREG) + nf->nf_mark = nfsd_file_mark_find_or_create(inode); + + if (type != S_IFREG || nf->nf_mark) { if (file) { get_file(file); nf->nf_file = file; status = nfs_ok; trace_nfsd_file_opened(nf, status); } else { - ret = nfsd_open_verified(fhp, may_flags, &nf->nf_file); + ret = nfsd_open_verified(fhp, type, may_flags, &nf->nf_file); if (ret == -EOPENSTALE && stale_retry) { stale_retry = false; nfsd_file_unhash(nf); @@ -1246,7 +1249,7 @@ nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, - fhp, may_flags, NULL, pnf, true); + fhp, may_flags, NULL, S_IFREG, true, pnf); } /** @@ -1271,7 +1274,7 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, - fhp, may_flags, NULL, pnf, false); + fhp, may_flags, NULL, S_IFREG, false, pnf); } /** @@ -1314,8 +1317,8 @@ nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, const struct cred *save_cred = get_current_cred(); __be32 beres; - beres = nfsd_file_do_acquire(NULL, net, cred, client, - fhp, may_flags, NULL, pnf, false); + beres = nfsd_file_do_acquire(NULL, net, cred, client, fhp, may_flags, + NULL, S_IFREG, false, pnf); put_cred(revert_creds(save_cred)); return beres; } @@ -1344,7 +1347,33 @@ nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file **pnf) { return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, - fhp, may_flags, file, pnf, false); + fhp, may_flags, file, S_IFREG, false, pnf); +} + +/** + * nfsd_file_acquire_dir - Get a struct nfsd_file with an open directory + * @rqstp: the RPC transaction being executed + * @fhp: the NFS filehandle of the file to be opened + * @pnf: OUT: new or found "struct nfsd_file" object + * + * The nfsd_file_object returned by this API is reference-counted + * but not garbage-collected. The object is unhashed after the + * final nfsd_file_put(). This opens directories only, and only + * in O_RDONLY mode. + * + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. + */ +__be32 +nfsd_file_acquire_dir(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file **pnf) +{ + return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, fhp, + NFSD_MAY_READ|NFSD_MAY_64BIT_COOKIE, + NULL, S_IFDIR, false, pnf); } /* diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index e3d6ca2b6030..b383dbc5b921 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -82,5 +82,7 @@ __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, struct auth_domain *client, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf); +__be32 nfsd_file_acquire_dir(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file **pnf); int nfsd_file_cache_stats_show(struct seq_file *m, void *v); #endif /* _FS_NFSD_FILECACHE_H */ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index b6d03e1ef5f7..42adc5461db0 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -281,14 +281,11 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - inode_lock_nested(inode, I_MUTEX_PARENT); - - child = lookup_one(&nop_mnt_idmap, - &QSTR_LEN(argp->name, argp->len), - parent); + child = start_creating(&nop_mnt_idmap, parent, + &QSTR_LEN(argp->name, argp->len)); if (IS_ERR(child)) { status = nfserrno(PTR_ERR(child)); - goto out; + goto out_write; } if (d_really_is_negative(child)) { @@ -344,7 +341,7 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, status = fh_fill_pre_attrs(fhp); if (status != nfs_ok) goto out; - host_err = vfs_create(&nop_mnt_idmap, inode, child, iap->ia_mode, true); + host_err = vfs_create(&nop_mnt_idmap, child, iap->ia_mode, NULL); if (host_err < 0) { status = nfserrno(host_err); goto out; @@ -367,9 +364,8 @@ set_attr: status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs); out: - inode_unlock(inode); - if (child && !IS_ERR(child)) - dput(child); + end_creating(child); +out_write: fh_drop_write(fhp); return status; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 7f7e6bb23a90..b74800917583 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -264,14 +264,11 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (is_create_with_attrs(open)) nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs); - inode_lock_nested(inode, I_MUTEX_PARENT); - - child = lookup_one(&nop_mnt_idmap, - &QSTR_LEN(open->op_fname, open->op_fnamelen), - parent); + child = start_creating(&nop_mnt_idmap, parent, + &QSTR_LEN(open->op_fname, open->op_fnamelen)); if (IS_ERR(child)) { status = nfserrno(PTR_ERR(child)); - goto out; + goto out_write; } if (d_really_is_negative(child)) { @@ -379,10 +376,9 @@ set_attr: if (attrs.na_aclerr) open->op_bmval[0] &= ~FATTR4_WORD0_ACL; out: - inode_unlock(inode); + end_creating(child); nfsd_attrs_free(&attrs); - if (child && !IS_ERR(child)) - dput(child); +out_write: fh_drop_write(fhp); return status; } @@ -2342,6 +2338,13 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp, union nfsd4_op_u *u) { struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation; + struct nfs4_delegation *dd; + struct nfsd_file *nf; + __be32 status; + + status = nfsd_file_acquire_dir(rqstp, &cstate->current_fh, &nf); + if (status != nfs_ok) + return status; /* * RFC 8881, section 18.39.3 says: @@ -2355,7 +2358,20 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp, * return NFS4_OK with a non-fatal status of GDD4_UNAVAIL in this * situation. */ - gdd->gddrnf_status = GDD4_UNAVAIL; + dd = nfsd_get_dir_deleg(cstate, gdd, nf); + nfsd_file_put(nf); + if (IS_ERR(dd)) { + int err = PTR_ERR(dd); + + if (err != -EAGAIN) + return nfserrno(err); + gdd->gddrnf_status = GDD4_UNAVAIL; + return nfs_ok; + } + + gdd->gddrnf_status = GDD4_OK; + memcpy(&gdd->gddr_stateid, &dd->dl_stid.sc_stateid, sizeof(gdd->gddr_stateid)); + nfs4_put_stid(&dd->dl_stid); return nfs_ok; } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index e2b9472e5c78..b39d4cbdfd35 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -195,13 +195,11 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) goto out_creds; dir = nn->rec_file->f_path.dentry; - /* lock the parent */ - inode_lock(d_inode(dir)); - dentry = lookup_one(&nop_mnt_idmap, &QSTR(dname), dir); + dentry = start_creating(&nop_mnt_idmap, dir, &QSTR(dname)); if (IS_ERR(dentry)) { status = PTR_ERR(dentry); - goto out_unlock; + goto out; } if (d_really_is_positive(dentry)) /* @@ -212,15 +210,13 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) * In the 4.0 case, we should never get here; but we may * as well be forgiving and just succeed silently. */ - goto out_put; - dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU); + goto out_end; + dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, 0700, NULL); if (IS_ERR(dentry)) status = PTR_ERR(dentry); -out_put: - if (!status) - dput(dentry); -out_unlock: - inode_unlock(d_inode(dir)); +out_end: + end_creating(dentry); +out: if (status == 0) { if (nn->in_grace) __nfsd4_create_reclaim_record_grace(clp, dname, @@ -328,20 +324,12 @@ nfsd4_unlink_clid_dir(char *name, struct nfsd_net *nn) dprintk("NFSD: nfsd4_unlink_clid_dir. name %s\n", name); dir = nn->rec_file->f_path.dentry; - inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); - dentry = lookup_one(&nop_mnt_idmap, &QSTR(name), dir); - if (IS_ERR(dentry)) { - status = PTR_ERR(dentry); - goto out_unlock; - } - status = -ENOENT; - if (d_really_is_negative(dentry)) - goto out; - status = vfs_rmdir(&nop_mnt_idmap, d_inode(dir), dentry); -out: - dput(dentry); -out_unlock: - inode_unlock(d_inode(dir)); + dentry = start_removing(&nop_mnt_idmap, dir, &QSTR(name)); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + status = vfs_rmdir(&nop_mnt_idmap, d_inode(dir), dentry, NULL); + end_removing(dentry); return status; } @@ -427,7 +415,7 @@ purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) if (nfs4_has_reclaimed_state(name, nn)) goto out_free; - status = vfs_rmdir(&nop_mnt_idmap, d_inode(parent), child); + status = vfs_rmdir(&nop_mnt_idmap, d_inode(parent), child, NULL); if (status) printk("failed to remove client recovery directory %pd\n", child); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c1b54322c412..6791fc239dbd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1542,7 +1542,8 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid) release_all_access(stp); if (stp->st_stateowner) nfs4_put_stateowner(stp->st_stateowner); - WARN_ON(!list_empty(&stid->sc_cp_list)); + if (!list_empty(&stid->sc_cp_list)) + nfs4_free_cpntf_statelist(stid->sc_client->net, stid); kmem_cache_free(stateid_slab, stid); } @@ -3486,7 +3487,20 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; - dprintk("--> %s slot %p\n", __func__, slot); + /* + * RFC 5661 Section 2.10.6.1.2: + * + * Any time SEQUENCE ... returns an error ... [t]he replier MUST NOT + * modify the reply cache entry for the slot whenever an error is + * returned from SEQUENCE ... + * + * Because nfsd4_store_cache_entry is called only by + * nfsd4_sequence_done(), nfsd4_store_cache_entry() is called only + * when a SEQUENCE operation was part of the COMPOUND. + * nfs41_check_op_ordering() ensures SEQUENCE is the first op. + */ + if (resp->opcnt == 1 && resp->cstate.status != nfs_ok) + return; slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; @@ -4349,6 +4363,36 @@ static bool replay_matches_cache(struct svc_rqst *rqstp, return true; } +/* + * Note that the response is constructed here both for the case + * of a new SEQUENCE request and for a replayed SEQUENCE request. + * We do not cache SEQUENCE responses as SEQUENCE is idempotent. + */ +static void nfsd4_construct_sequence_response(struct nfsd4_session *session, + struct nfsd4_sequence *seq) +{ + struct nfs4_client *clp = session->se_client; + + seq->maxslots_response = max(session->se_target_maxslots, + seq->maxslots); + seq->target_maxslots = session->se_target_maxslots; + + switch (clp->cl_cb_state) { + case NFSD4_CB_DOWN: + seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; + break; + case NFSD4_CB_FAULT: + seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; + break; + default: + seq->status_flags = 0; + } + if (!list_empty(&clp->cl_revoked)) + seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; + if (atomic_read(&clp->cl_admin_revoked)) + seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -4398,6 +4442,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("%s: slotid %d\n", __func__, seq->slotid); trace_nfsd_slot_seqid_sequence(clp, seq, slot); + + nfsd4_construct_sequence_response(session, seq); + status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags); if (status == nfserr_replay_cache) { status = nfserr_seq_misordered; @@ -4495,23 +4542,6 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } out: - seq->maxslots = max(session->se_target_maxslots, seq->maxslots); - seq->target_maxslots = session->se_target_maxslots; - - switch (clp->cl_cb_state) { - case NFSD4_CB_DOWN: - seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; - break; - case NFSD4_CB_FAULT: - seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; - break; - default: - seq->status_flags = 0; - } - if (!list_empty(&clp->cl_revoked)) - seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; - if (atomic_read(&clp->cl_admin_revoked)) - seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; trace_nfsd_seq4_status(rqstp, seq); out_no_session: if (conn) @@ -7829,7 +7859,8 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) + status = fh_verify(rqstp, &cstate->current_fh, 0, 0); + if (status) return status; status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, SC_STATUS_REVOKED, &s, nn); @@ -9347,3 +9378,103 @@ out_status: nfs4_put_stid(&dp->dl_stid); return status; } + +/** + * nfsd_get_dir_deleg - attempt to get a directory delegation + * @cstate: compound state + * @gdd: GET_DIR_DELEGATION arg/resp structure + * @nf: nfsd_file opened on the directory + * + * Given a GET_DIR_DELEGATION request @gdd, attempt to acquire a delegation + * on the directory to which @nf refers. Note that this does not set up any + * sort of async notifications for the delegation. + */ +struct nfs4_delegation * +nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate, + struct nfsd4_get_dir_delegation *gdd, + struct nfsd_file *nf) +{ + struct nfs4_client *clp = cstate->clp; + struct nfs4_delegation *dp; + struct file_lease *fl; + struct nfs4_file *fp, *rfp; + int status = 0; + + fp = nfsd4_alloc_file(); + if (!fp) + return ERR_PTR(-ENOMEM); + + nfsd4_file_init(&cstate->current_fh, fp); + + rfp = nfsd4_file_hash_insert(fp, &cstate->current_fh); + if (unlikely(!rfp)) { + put_nfs4_file(fp); + return ERR_PTR(-ENOMEM); + } + + if (rfp != fp) { + put_nfs4_file(fp); + fp = rfp; + } + + /* if this client already has one, return that it's unavailable */ + spin_lock(&state_lock); + spin_lock(&fp->fi_lock); + /* existing delegation? */ + if (nfs4_delegation_exists(clp, fp)) { + status = -EAGAIN; + } else if (!fp->fi_deleg_file) { + fp->fi_deleg_file = nfsd_file_get(nf); + fp->fi_delegees = 1; + } else { + ++fp->fi_delegees; + } + spin_unlock(&fp->fi_lock); + spin_unlock(&state_lock); + + if (status) { + put_nfs4_file(fp); + return ERR_PTR(status); + } + + /* Try to set up the lease */ + status = -ENOMEM; + dp = alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ); + if (!dp) + goto out_delegees; + + fl = nfs4_alloc_init_lease(dp); + if (!fl) + goto out_put_stid; + + status = kernel_setlease(nf->nf_file, + fl->c.flc_type, &fl, NULL); + if (fl) + locks_free_lease(fl); + if (status) + goto out_put_stid; + + /* + * Now, try to hash it. This can fail if we race another nfsd task + * trying to set a delegation on the same file. If that happens, + * then just say UNAVAIL. + */ + spin_lock(&state_lock); + spin_lock(&clp->cl_lock); + spin_lock(&fp->fi_lock); + status = hash_delegation_locked(dp, fp); + spin_unlock(&fp->fi_lock); + spin_unlock(&clp->cl_lock); + spin_unlock(&state_lock); + + if (!status) + return dp; + + /* Something failed. Drop the lease and clean up the stid */ + kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); +out_put_stid: + nfs4_put_stid(&dp->dl_stid); +out_delegees: + put_deleg_file(fp); + return ERR_PTR(status); +} diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 6040a6145dad..67bb9c0b9fcb 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -5073,7 +5073,7 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr; /* Note slotid's are numbered from zero: */ /* sr_highest_slotid */ - nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots - 1); + nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots_response - 1); if (nfserr != nfs_ok) return nfserr; /* sr_target_highest_slotid */ @@ -5925,8 +5925,7 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) */ warn_on_nonidempotent_op(op); xdr_truncate_encode(xdr, op_status_offset + XDR_UNIT); - } - if (so) { + } else if (so) { int len = xdr->buf->len - (op_status_offset + XDR_UNIT); so->so_replay.rp_status = op->status; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index f19320018639..b752433c3c2c 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -458,6 +458,7 @@ enum { #define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \ FATTR4_WORD2_MODE_UMASK | \ + FATTR4_WORD2_CLONE_BLKSIZE | \ NFSD4_2_SECURITY_ATTRS | \ FATTR4_WORD2_XATTR_SUPPORT | \ FATTR4_WORD2_TIME_DELEG_ACCESS | \ diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 3eb724ec9566..ed85dd43da18 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -269,9 +269,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, dentry); } - fhp->fh_dentry = dentry; - fhp->fh_export = exp; - switch (fhp->fh_maxsize) { case NFS4_FHSIZE: if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR) @@ -293,6 +290,9 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, goto out; } + fhp->fh_dentry = dentry; + fhp->fh_export = exp; + return 0; out: exp_put(exp); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 8f71f5748c75..481e789a7697 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -306,18 +306,16 @@ nfsd_proc_create(struct svc_rqst *rqstp) goto done; } - inode_lock_nested(dirfhp->fh_dentry->d_inode, I_MUTEX_PARENT); - dchild = lookup_one(&nop_mnt_idmap, &QSTR_LEN(argp->name, argp->len), - dirfhp->fh_dentry); + dchild = start_creating(&nop_mnt_idmap, dirfhp->fh_dentry, + &QSTR_LEN(argp->name, argp->len)); if (IS_ERR(dchild)) { resp->status = nfserrno(PTR_ERR(dchild)); - goto out_unlock; + goto out_write; } fh_init(newfhp, NFS_FHSIZE); resp->status = fh_compose(newfhp, dirfhp->fh_export, dchild, dirfhp); if (!resp->status && d_really_is_negative(dchild)) resp->status = nfserr_noent; - dput(dchild); if (resp->status) { if (resp->status != nfserr_noent) goto out_unlock; @@ -409,6 +407,9 @@ nfsd_proc_create(struct svc_rqst *rqstp) /* File doesn't exist. Create it and set attrs */ resp->status = nfsd_create_locked(rqstp, dirfhp, &attrs, type, rdev, newfhp); + /* nfsd_create_locked() unlocked the parent */ + dput(dchild); + goto out_write; } else if (type == S_IFREG) { dprintk("nfsd: existing %s, valid=%x, size=%ld\n", argp->name, attr->ia_valid, (long) attr->ia_size); @@ -423,7 +424,8 @@ nfsd_proc_create(struct svc_rqst *rqstp) } out_unlock: - inode_unlock(dirfhp->fh_dentry->d_inode); + end_creating(dchild); +out_write: fh_drop_write(dirfhp); done: fh_put(dirfhp); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 1e736f402426..b052c1effdc5 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -867,4 +867,9 @@ static inline bool try_to_expire_client(struct nfs4_client *clp) extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_delegation **pdp); + +struct nfsd4_get_dir_delegation; +struct nfs4_delegation *nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate, + struct nfsd4_get_dir_delegation *gdd, + struct nfsd_file *nf); #endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9cb20d4aeab1..31cbf46b47b1 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -959,15 +959,16 @@ retry: /** * nfsd_open_verified - Open a regular file for the filecache * @fhp: NFS filehandle of the file to open + * @type: S_IFMT inode type allowed (0 means any type is allowed) * @may_flags: internal permission flags * @filp: OUT: open "struct file *" * * Returns zero on success, or a negative errno value. */ int -nfsd_open_verified(struct svc_fh *fhp, int may_flags, struct file **filp) +nfsd_open_verified(struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { - return __nfsd_open(fhp, S_IFREG, may_flags, filp); + return __nfsd_open(fhp, type, may_flags, filp); } /* @@ -1159,7 +1160,7 @@ static int wait_for_concurrent_writes(struct file *file) dprintk("nfsd: write resume %d\n", task_pid_nr(current)); } - if (inode->i_state & I_DIRTY) { + if (inode_state_read_once(inode) & I_DIRTY) { dprintk("nfsd: write sync %d\n", task_pid_nr(current)); err = vfs_fsync(file, 0); } @@ -1521,7 +1522,7 @@ nfsd_check_ignore_resizing(struct iattr *iap) iap->ia_valid &= ~ATTR_SIZE; } -/* The parent directory should already be locked: */ +/* The parent directory should already be locked - we will unlock */ __be32 nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_attrs *attrs, @@ -1552,13 +1553,12 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, err = 0; switch (type) { case S_IFREG: - host_err = vfs_create(&nop_mnt_idmap, dirp, dchild, - iap->ia_mode, true); + host_err = vfs_create(&nop_mnt_idmap, dchild, iap->ia_mode, NULL); if (!host_err) nfsd_check_ignore_resizing(iap); break; case S_IFDIR: - dchild = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode); + dchild = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode, NULL); if (IS_ERR(dchild)) { host_err = PTR_ERR(dchild); } else if (d_is_negative(dchild)) { @@ -1574,7 +1574,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, case S_IFIFO: case S_IFSOCK: host_err = vfs_mknod(&nop_mnt_idmap, dirp, dchild, - iap->ia_mode, rdev); + iap->ia_mode, rdev, NULL); break; default: printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n", @@ -1587,8 +1587,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs); out: - if (!IS_ERR(dchild)) - dput(dchild); + if (!err) + fh_fill_post_attrs(fhp); + end_creating(dchild); return err; out_nfserr: @@ -1626,28 +1627,24 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); - dchild = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry); + dchild = start_creating(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen)); host_err = PTR_ERR(dchild); - if (IS_ERR(dchild)) { - err = nfserrno(host_err); - goto out_unlock; - } + if (IS_ERR(dchild)) + return nfserrno(host_err); + err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); - /* - * We unconditionally drop our ref to dchild as fh_compose will have - * already grabbed its own ref for it. - */ - dput(dchild); if (err) goto out_unlock; err = fh_fill_pre_attrs(fhp); if (err != nfs_ok) goto out_unlock; err = nfsd_create_locked(rqstp, fhp, attrs, type, rdev, resfhp); - fh_fill_post_attrs(fhp); + /* nfsd_create_locked() unlocked the parent */ + dput(dchild); + return err; + out_unlock: - inode_unlock(dentry->d_inode); + end_creating(dchild); return err; } @@ -1733,28 +1730,26 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, } dentry = fhp->fh_dentry; - inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); - dnew = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry); + dnew = start_creating(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen)); if (IS_ERR(dnew)) { err = nfserrno(PTR_ERR(dnew)); - inode_unlock(dentry->d_inode); goto out_drop_write; } err = fh_fill_pre_attrs(fhp); if (err != nfs_ok) goto out_unlock; - host_err = vfs_symlink(&nop_mnt_idmap, d_inode(dentry), dnew, path); + host_err = vfs_symlink(&nop_mnt_idmap, d_inode(dentry), dnew, path, NULL); err = nfserrno(host_err); cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); if (!err) nfsd_create_setattr(rqstp, fhp, resfhp, attrs); fh_fill_post_attrs(fhp); out_unlock: - inode_unlock(dentry->d_inode); + end_creating(dnew); if (!err) err = nfserrno(commit_metadata(fhp)); - dput(dnew); - if (err==0) err = cerr; + if (!err) + err = cerr; out_drop_write: fh_drop_write(fhp); out: @@ -1809,32 +1804,31 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, ddir = ffhp->fh_dentry; dirp = d_inode(ddir); - inode_lock_nested(dirp, I_MUTEX_PARENT); + dnew = start_creating(&nop_mnt_idmap, ddir, &QSTR_LEN(name, len)); - dnew = lookup_one(&nop_mnt_idmap, &QSTR_LEN(name, len), ddir); if (IS_ERR(dnew)) { host_err = PTR_ERR(dnew); - goto out_unlock; + goto out_drop_write; } dold = tfhp->fh_dentry; err = nfserr_noent; if (d_really_is_negative(dold)) - goto out_dput; + goto out_unlock; err = fh_fill_pre_attrs(ffhp); if (err != nfs_ok) - goto out_dput; + goto out_unlock; host_err = vfs_link(dold, &nop_mnt_idmap, dirp, dnew, NULL); fh_fill_post_attrs(ffhp); - inode_unlock(dirp); +out_unlock: + end_creating(dnew); if (!host_err) { host_err = commit_metadata(ffhp); if (!host_err) host_err = commit_metadata(tfhp); } - dput(dnew); out_drop_write: fh_drop_write(tfhp); if (host_err == -EBUSY) { @@ -1849,12 +1843,6 @@ out_drop_write: } out: return err != nfs_ok ? err : nfserrno(host_err); - -out_dput: - dput(dnew); -out_unlock: - inode_unlock(dirp); - goto out_drop_write; } static void @@ -1895,11 +1883,12 @@ __be32 nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, struct svc_fh *tfhp, char *tname, int tlen) { - struct dentry *fdentry, *tdentry, *odentry, *ndentry, *trap; + struct dentry *fdentry, *tdentry; int type = S_IFDIR; + struct renamedata rd = {}; __be32 err; int host_err; - bool close_cached = false; + struct dentry *close_cached; trace_nfsd_vfs_rename(rqstp, ffhp, tfhp, fname, flen, tname, tlen); @@ -1925,15 +1914,22 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, goto out; retry: + close_cached = NULL; host_err = fh_want_write(ffhp); if (host_err) { err = nfserrno(host_err); goto out; } - trap = lock_rename(tdentry, fdentry); - if (IS_ERR(trap)) { - err = nfserr_xdev; + rd.mnt_idmap = &nop_mnt_idmap; + rd.old_parent = fdentry; + rd.new_parent = tdentry; + + host_err = start_renaming(&rd, 0, &QSTR_LEN(fname, flen), + &QSTR_LEN(tname, tlen)); + + if (host_err) { + err = nfserrno(host_err); goto out_want_write; } err = fh_fill_pre_attrs(ffhp); @@ -1943,48 +1939,23 @@ retry: if (err != nfs_ok) goto out_unlock; - odentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), fdentry); - host_err = PTR_ERR(odentry); - if (IS_ERR(odentry)) - goto out_nfserr; + type = d_inode(rd.old_dentry)->i_mode & S_IFMT; + + if (d_inode(rd.new_dentry)) + type = d_inode(rd.new_dentry)->i_mode & S_IFMT; - host_err = -ENOENT; - if (d_really_is_negative(odentry)) - goto out_dput_old; - host_err = -EINVAL; - if (odentry == trap) - goto out_dput_old; - type = d_inode(odentry)->i_mode & S_IFMT; - - ndentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(tname, tlen), tdentry); - host_err = PTR_ERR(ndentry); - if (IS_ERR(ndentry)) - goto out_dput_old; - if (d_inode(ndentry)) - type = d_inode(ndentry)->i_mode & S_IFMT; - host_err = -ENOTEMPTY; - if (ndentry == trap) - goto out_dput_new; - - if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) && - nfsd_has_cached_files(ndentry)) { - close_cached = true; - goto out_dput_old; + if ((rd.new_dentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) && + nfsd_has_cached_files(rd.new_dentry)) { + close_cached = dget(rd.new_dentry); + goto out_unlock; } else { - struct renamedata rd = { - .mnt_idmap = &nop_mnt_idmap, - .old_parent = fdentry, - .old_dentry = odentry, - .new_parent = tdentry, - .new_dentry = ndentry, - }; int retries; for (retries = 1;;) { host_err = vfs_rename(&rd); if (host_err != -EAGAIN || !retries--) break; - if (!nfsd_wait_for_delegreturn(rqstp, d_inode(odentry))) + if (!nfsd_wait_for_delegreturn(rqstp, d_inode(rd.old_dentry))) break; } if (!host_err) { @@ -1993,11 +1964,6 @@ retry: host_err = commit_metadata(ffhp); } } - out_dput_new: - dput(ndentry); - out_dput_old: - dput(odentry); - out_nfserr: if (host_err == -EBUSY) { /* * See RFC 8881 Section 18.26.4 para 1-3: NFSv4 RENAME @@ -2016,7 +1982,7 @@ retry: fh_fill_post_attrs(tfhp); } out_unlock: - unlock_rename(tdentry, fdentry); + end_renaming(&rd); out_want_write: fh_drop_write(ffhp); @@ -2027,9 +1993,8 @@ out_want_write: * until this point and then reattempt the whole shebang. */ if (close_cached) { - close_cached = false; - nfsd_close_cached_files(ndentry); - dput(ndentry); + nfsd_close_cached_files(close_cached); + dput(close_cached); goto retry; } out: @@ -2054,7 +2019,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, { struct dentry *dentry, *rdentry; struct inode *dirp; - struct inode *rinode; + struct inode *rinode = NULL; __be32 err; int host_err; @@ -2073,24 +2038,21 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, dentry = fhp->fh_dentry; dirp = d_inode(dentry); - inode_lock_nested(dirp, I_MUTEX_PARENT); - rdentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry); + rdentry = start_removing(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen)); + host_err = PTR_ERR(rdentry); if (IS_ERR(rdentry)) - goto out_unlock; + goto out_drop_write; - if (d_really_is_negative(rdentry)) { - dput(rdentry); - host_err = -ENOENT; - goto out_unlock; - } - rinode = d_inode(rdentry); err = fh_fill_pre_attrs(fhp); if (err != nfs_ok) goto out_unlock; + rinode = d_inode(rdentry); + /* Prevent truncation until after locks dropped */ ihold(rinode); + if (!type) type = d_inode(rdentry)->i_mode & S_IFMT; @@ -2108,14 +2070,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, break; } } else { - host_err = vfs_rmdir(&nop_mnt_idmap, dirp, rdentry); + host_err = vfs_rmdir(&nop_mnt_idmap, dirp, rdentry, NULL); } fh_fill_post_attrs(fhp); - inode_unlock(dirp); - if (!host_err) +out_unlock: + end_removing(rdentry); + if (!err && !host_err) host_err = commit_metadata(fhp); - dput(rdentry); iput(rinode); /* truncate the inode here */ out_drop_write: @@ -2133,9 +2095,6 @@ out_nfserr: } out: return err != nfs_ok ? err : nfserrno(host_err); -out_unlock: - inode_unlock(dirp); - goto out_drop_write; } /* diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 0c0292611c6d..09de48c50cbe 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -114,7 +114,7 @@ __be32 nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, int nfsd_open_break_lease(struct inode *, int); __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); -int nfsd_open_verified(struct svc_fh *fhp, int may_flags, +int nfsd_open_verified(struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp); __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index ee0570cbdd9e..1ce8e12ae335 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -574,8 +574,9 @@ struct nfsd4_sequence { struct nfs4_sessionid sessionid; /* request/response */ u32 seqid; /* request/response */ u32 slotid; /* request/response */ - u32 maxslots; /* request/response */ + u32 maxslots; /* request */ u32 cachethis; /* request */ + u32 maxslots_response; /* response */ u32 target_maxslots; /* response */ u32 status_flags; /* response */ }; diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index bcc7d76269ac..4bbdc832d7f2 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -1148,7 +1148,7 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize, cpfile = nilfs_iget_locked(sb, NULL, NILFS_CPFILE_INO); if (unlikely(!cpfile)) return -ENOMEM; - if (!(cpfile->i_state & I_NEW)) + if (!(inode_state_read_once(cpfile) & I_NEW)) goto out; err = nilfs_mdt_init(cpfile, NILFS_MDT_GFP, 0); diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index c664daba56ae..674380837ab9 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -506,7 +506,7 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size, dat = nilfs_iget_locked(sb, NULL, NILFS_DAT_INO); if (unlikely(!dat)) return -ENOMEM; - if (!(dat->i_state & I_NEW)) + if (!(inode_state_read_once(dat) & I_NEW)) goto out; err = nilfs_mdt_init(dat, NILFS_MDT_GFP, sizeof(*di)); diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c index c4cd4a4dedd0..99eb8a59009e 100644 --- a/fs/nilfs2/ifile.c +++ b/fs/nilfs2/ifile.c @@ -188,7 +188,7 @@ int nilfs_ifile_read(struct super_block *sb, struct nilfs_root *root, ifile = nilfs_iget_locked(sb, root, NILFS_IFILE_INO); if (unlikely(!ifile)) return -ENOMEM; - if (!(ifile->i_state & I_NEW)) + if (!(inode_state_read_once(ifile) & I_NEW)) goto out; err = nilfs_mdt_init(ifile, NILFS_MDT_GFP, diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 87ddde159f0c..51bde45d5865 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -365,7 +365,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) failed_after_creation: clear_nlink(inode); - if (inode->i_state & I_NEW) + if (inode_state_read_once(inode) & I_NEW) unlock_new_inode(inode); iput(inode); /* * raw_inode will be deleted through @@ -562,7 +562,7 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) { + if (!(inode_state_read_once(inode) & I_NEW)) { if (!inode->i_nlink) { iput(inode); return ERR_PTR(-ESTALE); @@ -591,7 +591,7 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, inode = iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; err = nilfs_init_gcinode(inode); @@ -631,7 +631,7 @@ int nilfs_attach_btree_node_cache(struct inode *inode) nilfs_iget_set, &args); if (unlikely(!btnc_inode)) return -ENOMEM; - if (btnc_inode->i_state & I_NEW) { + if (inode_state_read_once(btnc_inode) & I_NEW) { nilfs_init_btnc_inode(btnc_inode); unlock_new_inode(btnc_inode); } @@ -686,7 +686,7 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode) nilfs_iget_set, &args); if (unlikely(!s_inode)) return ERR_PTR(-ENOMEM); - if (!(s_inode->i_state & I_NEW)) + if (!(inode_state_read_once(s_inode) & I_NEW)) return inode; NILFS_I(s_inode)->i_flags = 0; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index f466daa39440..b7e3d91b6243 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -14,6 +14,7 @@ #include <linux/buffer_head.h> #include <linux/spinlock.h> #include <linux/blkdev.h> +#include <linux/fs_struct.h> #include <linux/nilfs2_api.h> #include <linux/nilfs2_ondisk.h> #include "the_nilfs.h" diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index f15ca6fc400d..deee16bc9d4e 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2768,7 +2768,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) if (sci->sc_task) { wake_up(&sci->sc_wait_daemon); - kthread_stop(sci->sc_task); + if (kthread_stop(sci->sc_task)) { + spin_lock(&sci->sc_state_lock); + sci->sc_task = NULL; + timer_shutdown_sync(&sci->sc_timer); + spin_unlock(&sci->sc_state_lock); + } } spin_lock(&sci->sc_state_lock); diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 330f269abedf..83f93337c01b 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -1226,7 +1226,7 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize, sufile = nilfs_iget_locked(sb, NULL, NILFS_SUFILE_INO); if (unlikely(!sufile)) return -ENOMEM; - if (!(sufile->i_state & I_NEW)) + if (!(inode_state_read_once(sufile) & I_NEW)) goto out; err = nilfs_mdt_init(sufile, NILFS_MDT_GFP, sizeof(*sui)); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 1dadda82cae5..d0b9b984002f 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1597,16 +1597,20 @@ static struct hlist_head *fanotify_alloc_merge_hash(void) return hash; } +DEFINE_CLASS(fsnotify_group, + struct fsnotify_group *, + if (!IS_ERR_OR_NULL(_T)) fsnotify_destroy_group(_T), + fsnotify_alloc_group(ops, flags), + const struct fsnotify_ops *ops, int flags) + /* fanotify syscalls */ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) { struct user_namespace *user_ns = current_user_ns(); - struct fsnotify_group *group; int f_flags, fd; unsigned int fid_mode = flags & FANOTIFY_FID_BITS; unsigned int class = flags & FANOTIFY_CLASS_BITS; unsigned int internal_flags = 0; - struct file *file; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); @@ -1690,36 +1694,29 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if (flags & FAN_NONBLOCK) f_flags |= O_NONBLOCK; - /* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */ - group = fsnotify_alloc_group(&fanotify_fsnotify_ops, + CLASS(fsnotify_group, group)(&fanotify_fsnotify_ops, FSNOTIFY_GROUP_USER); - if (IS_ERR(group)) { + /* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */ + if (IS_ERR(group)) return PTR_ERR(group); - } /* Enforce groups limits per user in all containing user ns */ group->fanotify_data.ucounts = inc_ucount(user_ns, current_euid(), UCOUNT_FANOTIFY_GROUPS); - if (!group->fanotify_data.ucounts) { - fd = -EMFILE; - goto out_destroy_group; - } + if (!group->fanotify_data.ucounts) + return -EMFILE; group->fanotify_data.flags = flags | internal_flags; group->memcg = get_mem_cgroup_from_mm(current->mm); group->user_ns = get_user_ns(user_ns); group->fanotify_data.merge_hash = fanotify_alloc_merge_hash(); - if (!group->fanotify_data.merge_hash) { - fd = -ENOMEM; - goto out_destroy_group; - } + if (!group->fanotify_data.merge_hash) + return -ENOMEM; group->overflow_event = fanotify_alloc_overflow_event(); - if (unlikely(!group->overflow_event)) { - fd = -ENOMEM; - goto out_destroy_group; - } + if (unlikely(!group->overflow_event)) + return -ENOMEM; if (force_o_largefile()) event_f_flags |= O_LARGEFILE; @@ -1738,8 +1735,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->priority = FSNOTIFY_PRIO_PRE_CONTENT; break; default: - fd = -EINVAL; - goto out_destroy_group; + return -EINVAL; } BUILD_BUG_ON(!(FANOTIFY_ADMIN_INIT_FLAGS & FAN_UNLIMITED_QUEUE)); @@ -1750,27 +1746,15 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) } if (flags & FAN_ENABLE_AUDIT) { - fd = -EPERM; if (!capable(CAP_AUDIT_WRITE)) - goto out_destroy_group; - } - - fd = get_unused_fd_flags(f_flags); - if (fd < 0) - goto out_destroy_group; - - file = anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, group, - f_flags, FMODE_NONOTIFY); - if (IS_ERR(file)) { - put_unused_fd(fd); - fd = PTR_ERR(file); - goto out_destroy_group; + return -EPERM; } - fd_install(fd, file); - return fd; -out_destroy_group: - fsnotify_destroy_group(group); + fd = FD_ADD(f_flags, + anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, + group, f_flags, FMODE_NONOTIFY)); + if (fd >= 0) + retain_and_null_ptr(group); return fd; } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 46bfc543f946..d27ff5e5f165 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -52,7 +52,7 @@ static void fsnotify_unmount_inodes(struct super_block *sb) * the inode cannot have any associated watches. */ spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); continue; } diff --git a/fs/nsfs.c b/fs/nsfs.c index 79b026a36fb6..bf27d5da91f1 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -58,6 +58,8 @@ const struct dentry_operations ns_dentry_operations = { static void nsfs_evict(struct inode *inode) { struct ns_common *ns = inode->i_private; + + __ns_ref_active_put(ns); clear_inode(inode); ns->ops->put(ns); } @@ -108,7 +110,6 @@ int ns_get_path(struct path *path, struct task_struct *task, int open_namespace(struct ns_common *ns) { struct path path __free(path_put) = {}; - struct file *f; int err; /* call first to consume reference */ @@ -116,16 +117,7 @@ int open_namespace(struct ns_common *ns) if (err < 0) return err; - CLASS(get_unused_fd, fd)(O_CLOEXEC); - if (fd < 0) - return fd; - - f = dentry_open(&path, O_RDONLY, current_cred()); - if (IS_ERR(f)) - return PTR_ERR(f); - - fd_install(fd, f); - return take_fd(fd); + return FD_ADD(O_CLOEXEC, dentry_open(&path, O_RDONLY, current_cred())); } int open_related_ns(struct ns_common *ns, @@ -311,7 +303,6 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, struct mnt_ns_info kinfo = {}; struct mnt_ns_info __user *uinfo = (struct mnt_ns_info __user *)arg; struct path path __free(path_put) = {}; - struct file *f __free(fput) = NULL; size_t usize = _IOC_SIZE(ioctl); if (ns->ns_type != CLONE_NEWNS) @@ -330,28 +321,18 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, if (ret) return ret; - CLASS(get_unused_fd, fd)(O_CLOEXEC); - if (fd < 0) - return fd; - - f = dentry_open(&path, O_RDONLY, current_cred()); - if (IS_ERR(f)) - return PTR_ERR(f); - - if (uinfo) { - /* - * If @uinfo is passed return all information about the - * mount namespace as well. - */ - ret = copy_ns_info_to_user(to_mnt_ns(ns), uinfo, usize, &kinfo); - if (ret) - return ret; - } - - /* Transfer reference of @f to caller's fdtable. */ - fd_install(fd, no_free_ptr(f)); - /* File descriptor is live so hand it off to the caller. */ - return take_fd(fd); + FD_PREPARE(fdf, O_CLOEXEC, dentry_open(&path, O_RDONLY, current_cred())); + if (fdf.err) + return fdf.err; + /* + * If @uinfo is passed return all information about the + * mount namespace as well. + */ + ret = copy_ns_info_to_user(to_mnt_ns(ns), uinfo, usize, &kinfo); + if (ret) + return ret; + ret = fd_publish(fdf); + break; } default: ret = -ENOTTY; @@ -408,6 +389,7 @@ static const struct super_operations nsfs_ops = { .statfs = simple_statfs, .evict_inode = nsfs_evict, .show_path = nsfs_show_path, + .drop_inode = inode_just_drop, }; static int nsfs_init_inode(struct inode *inode, void *data) @@ -418,6 +400,16 @@ static int nsfs_init_inode(struct inode *inode, void *data) inode->i_mode |= S_IRUGO; inode->i_fop = &ns_file_operations; inode->i_ino = ns->inum; + + /* + * Bring the namespace subtree back to life if we have to. This + * can happen when e.g., all processes using a network namespace + * and all namespace files or namespace file bind-mounts have + * died but there are still sockets pinning it. The SIOCGSKNS + * ioctl on such a socket will resurrect the relevant namespace + * subtree. + */ + __ns_ref_active_get(ns); return 0; } @@ -458,6 +450,45 @@ static int nsfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, return FILEID_NSFS; } +bool is_current_namespace(struct ns_common *ns) +{ + switch (ns->ns_type) { +#ifdef CONFIG_CGROUPS + case CLONE_NEWCGROUP: + return current_in_namespace(to_cg_ns(ns)); +#endif +#ifdef CONFIG_IPC_NS + case CLONE_NEWIPC: + return current_in_namespace(to_ipc_ns(ns)); +#endif + case CLONE_NEWNS: + return current_in_namespace(to_mnt_ns(ns)); +#ifdef CONFIG_NET_NS + case CLONE_NEWNET: + return current_in_namespace(to_net_ns(ns)); +#endif +#ifdef CONFIG_PID_NS + case CLONE_NEWPID: + return current_in_namespace(to_pid_ns(ns)); +#endif +#ifdef CONFIG_TIME_NS + case CLONE_NEWTIME: + return current_in_namespace(to_time_ns(ns)); +#endif +#ifdef CONFIG_USER_NS + case CLONE_NEWUSER: + return current_in_namespace(to_user_ns(ns)); +#endif +#ifdef CONFIG_UTS_NS + case CLONE_NEWUTS: + return current_in_namespace(to_uts_ns(ns)); +#endif + default: + VFS_WARN_ON_ONCE(true); + return false; + } +} + static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { @@ -483,18 +514,35 @@ static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh, return NULL; } + if (!fid->ns_id) + return NULL; + /* Either both are set or both are unset. */ + if (!fid->ns_inum != !fid->ns_type) + return NULL; + scoped_guard(rcu) { ns = ns_tree_lookup_rcu(fid->ns_id, fid->ns_type); if (!ns) return NULL; VFS_WARN_ON_ONCE(ns->ns_id != fid->ns_id); - VFS_WARN_ON_ONCE(ns->ns_type != fid->ns_type); - if (ns->inum != fid->ns_inum) + if (fid->ns_inum && (fid->ns_inum != ns->inum)) + return NULL; + if (fid->ns_type && (fid->ns_type != ns->ns_type)) return NULL; - if (!__ns_ref_get(ns)) + /* + * This is racy because we're not actually taking an + * active reference. IOW, it could happen that the + * namespace becomes inactive after this check. + * We don't care because nsfs_init_inode() will just + * resurrect the relevant namespace tree for us. If it + * has been active here we just allow it's resurrection. + * We could try to take an active reference here and + * then drop it again. But really, why bother. + */ + if (!ns_get_unless_inactive(ns)) return NULL; } @@ -590,6 +638,8 @@ static int nsfs_init_fs_context(struct fs_context *fc) struct pseudo_fs_context *ctx = init_pseudo(fc, NSFS_MAGIC); if (!ctx) return -ENOMEM; + fc->s_iflags |= SB_I_NOEXEC | SB_I_NODEV; + ctx->s_d_flags |= DCACHE_DONTCACHE; ctx->ops = &nsfs_ops; ctx->eops = &nsfs_export_operations; ctx->dops = &ns_dentry_operations; @@ -612,3 +662,27 @@ void __init nsfs_init(void) nsfs_root_path.mnt = nsfs_mnt; nsfs_root_path.dentry = nsfs_mnt->mnt_root; } + +void nsproxy_ns_active_get(struct nsproxy *ns) +{ + ns_ref_active_get(ns->mnt_ns); + ns_ref_active_get(ns->uts_ns); + ns_ref_active_get(ns->ipc_ns); + ns_ref_active_get(ns->pid_ns_for_children); + ns_ref_active_get(ns->cgroup_ns); + ns_ref_active_get(ns->net_ns); + ns_ref_active_get(ns->time_ns); + ns_ref_active_get(ns->time_ns_for_children); +} + +void nsproxy_ns_active_put(struct nsproxy *ns) +{ + ns_ref_active_put(ns->mnt_ns); + ns_ref_active_put(ns->uts_ns); + ns_ref_active_put(ns->ipc_ns); + ns_ref_active_put(ns->pid_ns_for_children); + ns_ref_active_put(ns->cgroup_ns); + ns_ref_active_put(ns->net_ns); + ns_ref_active_put(ns->time_ns); + ns_ref_active_put(ns->time_ns_for_children); +} diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 3959f23c487a..08266adc42ba 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -537,7 +537,7 @@ struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, return ERR_PTR(-ENOMEM); /* If this is a freshly allocated inode, need to read it now. */ - if (inode->i_state & I_NEW) + if (inode_state_read_once(inode) & I_NEW) inode = ntfs_read_mft(inode, name, ref); else if (ref->seq != ntfs_i(inode)->mi.mrec->seq) { /* diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index ddff94c091b8..8d09dfec970a 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -51,6 +51,7 @@ #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/fs.h> +#include <linux/fs_struct.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/log2.h> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 62464d194da3..af1e2cedb217 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/fs_struct.h> #include <cluster/masklog.h> diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 162711cc5b20..b267ec580da9 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6892,7 +6892,7 @@ static void ocfs2_zero_cluster_folios(struct inode *inode, loff_t start, ocfs2_map_and_dirty_folio(inode, handle, from, to, folio, 1, &phys); - start = folio_next_index(folio) << PAGE_SHIFT; + start = folio_next_pos(folio); } out: if (folios) diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 92a6149da9c1..619ff03b15d6 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2487,7 +2487,7 @@ update: * which hasn't been populated yet, so clear the refresh flag * and let the caller handle it. */ - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { status = 0; if (lockres) ocfs2_complete_lock_res_refresh(lockres, 0); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index fcc89856ab95..78f81950c9ee 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -152,8 +152,8 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags, mlog_errno(PTR_ERR(inode)); goto bail; } - trace_ocfs2_iget5_locked(inode->i_state); - if (inode->i_state & I_NEW) { + trace_ocfs2_iget5_locked(inode_state_read_once(inode)); + if (inode_state_read_once(inode) & I_NEW) { rc = ocfs2_read_locked_inode(inode, &args); unlock_new_inode(inode); } @@ -1290,6 +1290,8 @@ static void ocfs2_clear_inode(struct inode *inode) void ocfs2_evict_inode(struct inode *inode) { + write_inode_now(inode, 1); + if (!inode->i_nlink || (OCFS2_I(inode)->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)) { ocfs2_delete_inode(inode); @@ -1299,27 +1301,6 @@ void ocfs2_evict_inode(struct inode *inode) ocfs2_clear_inode(inode); } -/* Called under inode_lock, with no more references on the - * struct inode, so it's safe here to check the flags field - * and to manipulate i_nlink without any other locks. */ -int ocfs2_drop_inode(struct inode *inode) -{ - struct ocfs2_inode_info *oi = OCFS2_I(inode); - - trace_ocfs2_drop_inode((unsigned long long)oi->ip_blkno, - inode->i_nlink, oi->ip_flags); - - assert_spin_locked(&inode->i_lock); - inode->i_state |= I_WILL_FREE; - spin_unlock(&inode->i_lock); - write_inode_now(inode, 1); - spin_lock(&inode->i_lock); - WARN_ON(inode->i_state & I_NEW); - inode->i_state &= ~I_WILL_FREE; - - return 1; -} - /* * This is called from our getattr. */ diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index accf03d4765e..07bd838e7843 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -116,7 +116,6 @@ static inline struct ocfs2_caching_info *INODE_CACHE(struct inode *inode) } void ocfs2_evict_inode(struct inode *inode); -int ocfs2_drop_inode(struct inode *inode); /* Flags for ocfs2_iget() */ #define OCFS2_FI_FLAG_SYSFILE 0x1 diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index e5f58ff2175f..85239807dec7 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -902,15 +902,8 @@ bail: static int ocfs2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) { - struct address_space *mapping = jinode->i_vfs_inode->i_mapping; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = mapping->nrpages * 2, - .range_start = jinode->i_dirty_start, - .range_end = jinode->i_dirty_end, - }; - - return filemap_fdatawrite_wbc(mapping, &wbc); + return filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping, + jinode->i_dirty_start, jinode->i_dirty_end); } int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty) diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 54ed1495de9a..4b32fb5658ad 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -1569,8 +1569,6 @@ DEFINE_OCFS2_ULL_ULL_UINT_EVENT(ocfs2_delete_inode); DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_clear_inode); -DEFINE_OCFS2_ULL_UINT_UINT_EVENT(ocfs2_drop_inode); - TRACE_EVENT(ocfs2_inode_revalidate, TP_PROTO(void *inode, unsigned long long ino, unsigned int flags), diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 53daa4482406..2c7ba1480f7a 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -129,7 +129,7 @@ static const struct super_operations ocfs2_sops = { .statfs = ocfs2_statfs, .alloc_inode = ocfs2_alloc_inode, .free_inode = ocfs2_free_inode, - .drop_inode = ocfs2_drop_inode, + .drop_inode = inode_just_drop, .evict_inode = ocfs2_evict_inode, .sync_fs = ocfs2_sync_fs, .put_super = ocfs2_put_super, diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 135c49c5d848..701ed85d9831 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -14,6 +14,7 @@ #include <linux/writeback.h> #include <linux/seq_file.h> #include <linux/crc-itu-t.h> +#include <linux/fs_struct.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "omfs.h" @@ -212,7 +213,7 @@ struct inode *omfs_iget(struct super_block *sb, ino_t ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; bh = omfs_bread(inode->i_sb, ino); diff --git a/fs/open.c b/fs/open.c index 3d64372ecc67..f328622061c5 100644 --- a/fs/open.c +++ b/fs/open.c @@ -191,12 +191,9 @@ int do_ftruncate(struct file *file, loff_t length, int small) if (error) return error; - sb_start_write(inode->i_sb); - error = do_truncate(file_mnt_idmap(file), dentry, length, - ATTR_MTIME | ATTR_CTIME, file); - sb_end_write(inode->i_sb); - - return error; + scoped_guard(super_write, inode->i_sb) + return do_truncate(file_mnt_idmap(file), dentry, length, + ATTR_MTIME | ATTR_CTIME, file); } int do_sys_ftruncate(unsigned int fd, loff_t length, int small) @@ -631,7 +628,7 @@ out: int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; - struct inode *delegated_inode = NULL; + struct delegated_inode delegated_inode = { }; struct iattr newattrs; int error; @@ -651,7 +648,7 @@ retry_deleg: &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; @@ -756,7 +753,7 @@ int chown_common(const struct path *path, uid_t user, gid_t group) struct mnt_idmap *idmap; struct user_namespace *fs_userns; struct inode *inode = path->dentry->d_inode; - struct inode *delegated_inode = NULL; + struct delegated_inode delegated_inode = { }; int error; struct iattr newattrs; kuid_t uid; @@ -791,7 +788,7 @@ retry_deleg: error = notify_change(idmap, path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; @@ -940,7 +937,7 @@ static int do_dentry_open(struct file *f, } error = security_file_open(f); - if (error) + if (unlikely(error)) goto cleanup_all; /* @@ -950,11 +947,11 @@ static int do_dentry_open(struct file *f, * pseudo file, this call will not change the mode. */ error = fsnotify_open_perm_and_set_mode(f); - if (error) + if (unlikely(error)) goto cleanup_all; error = break_lease(file_inode(f), f->f_flags); - if (error) + if (unlikely(error)) goto cleanup_all; /* normally all 3 are set; ->open() can clear them if needed */ @@ -1171,9 +1168,7 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode, if (IS_ERR(f)) return f; - error = vfs_create(mnt_idmap(path->mnt), - d_inode(path->dentry->d_parent), - path->dentry, mode, true); + error = vfs_create(mnt_idmap(path->mnt), path->dentry, mode, NULL); if (!error) error = vfs_open(path, f); @@ -1421,8 +1416,8 @@ static int do_sys_openat2(int dfd, const char __user *filename, struct open_how *how) { struct open_flags op; - struct filename *tmp; - int err, fd; + struct filename *tmp __free(putname) = NULL; + int err; err = build_open_flags(how, &op); if (unlikely(err)) @@ -1432,18 +1427,7 @@ static int do_sys_openat2(int dfd, const char __user *filename, if (IS_ERR(tmp)) return PTR_ERR(tmp); - fd = get_unused_fd_flags(how->flags); - if (likely(fd >= 0)) { - struct file *f = do_filp_open(dfd, tmp, &op); - if (IS_ERR(f)) { - put_unused_fd(fd); - fd = PTR_ERR(f); - } else { - fd_install(fd, f); - } - } - putname(tmp); - return fd; + return FD_ADD(how->flags, do_filp_open(dfd, tmp, &op)); } int do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 26ecda0e4d19..fb8d84bdedfb 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -236,7 +236,7 @@ found: mutex_unlock(&op_mutex); if (IS_ERR(inode)) return ERR_CAST(inode); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { simple_inode_init_ts(inode); ent_oi = OP_I(inode); ent_oi->type = ent_type; diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index a01400cd41fd..d7275990ffa4 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -878,7 +878,9 @@ int orangefs_update_time(struct inode *inode, int flags) gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_update_time: %pU\n", get_khandle_from_ino(inode)); - flags = generic_update_time(inode, flags); + + flags = inode_update_timestamps(inode, flags); + memset(&iattr, 0, sizeof iattr); if (flags & S_ATIME) iattr.ia_valid |= ATTR_ATIME; @@ -1041,7 +1043,7 @@ struct inode *orangefs_iget(struct super_block *sb, if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; error = orangefs_inode_getattr(inode, ORANGEFS_GETATTR_NEW); diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c index 0fdceb00ca07..9ab1119ebd28 100644 --- a/fs/orangefs/orangefs-utils.c +++ b/fs/orangefs/orangefs-utils.c @@ -247,7 +247,7 @@ 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) { + orangefs_inode->attr_valid || inode_state_read(inode) & I_DIRTY_PAGES) { if (orangefs_inode->attr_valid) { spin_unlock(&inode->i_lock); write_inode_now(inode, 1); @@ -281,13 +281,13 @@ 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) { + orangefs_inode->attr_valid || inode_state_read(inode) & 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) { + if (inode_state_read(inode) & I_DIRTY_PAGES) { ret = 0; goto out_unlock; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 604a82acd164..758611ee4475 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -523,8 +523,8 @@ static int ovl_create_index(struct dentry *dentry, const struct ovl_fh *fh, { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *indexdir = ovl_indexdir(dentry->d_sb); - struct dentry *index = NULL; struct dentry *temp = NULL; + struct renamedata rd = {}; struct qstr name = { }; int err; @@ -556,17 +556,15 @@ static int ovl_create_index(struct dentry *dentry, const struct ovl_fh *fh, if (err) goto out; - err = ovl_parent_lock(indexdir, temp); + rd.mnt_idmap = ovl_upper_mnt_idmap(ofs); + rd.old_parent = indexdir; + rd.new_parent = indexdir; + err = start_renaming_dentry(&rd, 0, temp, &name); if (err) goto out; - index = ovl_lookup_upper(ofs, name.name, indexdir, name.len); - if (IS_ERR(index)) { - err = PTR_ERR(index); - } else { - err = ovl_do_rename(ofs, indexdir, temp, indexdir, index, 0); - dput(index); - } - ovl_parent_unlock(indexdir); + + err = ovl_do_rename_rd(&rd); + end_renaming(&rd); out: if (err) ovl_cleanup(ofs, indexdir, temp); @@ -613,9 +611,9 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) if (err) goto out; - inode_lock_nested(udir, I_MUTEX_PARENT); - upper = ovl_lookup_upper(ofs, c->dentry->d_name.name, upperdir, - c->dentry->d_name.len); + upper = ovl_start_creating_upper(ofs, upperdir, + &QSTR_LEN(c->dentry->d_name.name, + c->dentry->d_name.len)); err = PTR_ERR(upper); if (!IS_ERR(upper)) { err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper); @@ -626,9 +624,8 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) ovl_dentry_set_upper_alias(c->dentry); ovl_dentry_update_reval(c->dentry, upper); } - dput(upper); + end_creating(upper); } - inode_unlock(udir); if (err) goto out; @@ -727,34 +724,33 @@ static int ovl_copy_up_metadata(struct ovl_copy_up_ctx *c, struct dentry *temp) return err; } -struct ovl_cu_creds { - const struct cred *old; - struct cred *new; -}; - -static int ovl_prep_cu_creds(struct dentry *dentry, struct ovl_cu_creds *cc) +static const struct cred *ovl_prepare_copy_up_creds(struct dentry *dentry) { + struct cred *copy_up_cred = NULL; int err; - cc->old = cc->new = NULL; - err = security_inode_copy_up(dentry, &cc->new); + err = security_inode_copy_up(dentry, ©_up_cred); if (err < 0) - return err; + return ERR_PTR(err); - if (cc->new) - cc->old = override_creds(cc->new); + if (!copy_up_cred) + return NULL; - return 0; + return override_creds(copy_up_cred); } -static void ovl_revert_cu_creds(struct ovl_cu_creds *cc) +static void ovl_revert_copy_up_creds(const struct cred *orig_cred) { - if (cc->new) { - revert_creds(cc->old); - put_cred(cc->new); - } + const struct cred *copy_up_cred; + + copy_up_cred = revert_creds(orig_cred); + put_cred(copy_up_cred); } +DEFINE_CLASS(copy_up_creds, const struct cred *, + if (!IS_ERR_OR_NULL(_T)) ovl_revert_copy_up_creds(_T), + ovl_prepare_copy_up_creds(dentry), struct dentry *dentry) + /* * Copyup using workdir to prepare temp file. Used when copying up directories, * special files or when upper fs doesn't support O_TMPFILE. @@ -764,8 +760,8 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct inode *inode; struct path path = { .mnt = ovl_upper_mnt(ofs) }; - struct dentry *temp, *upper, *trap; - struct ovl_cu_creds cc; + struct renamedata rd = {}; + struct dentry *temp; int err; struct ovl_cattr cattr = { /* Can't properly set mode on creation because of the umask */ @@ -774,14 +770,14 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) .link = c->link }; - err = ovl_prep_cu_creds(c->dentry, &cc); - if (err) - return err; + scoped_class(copy_up_creds, copy_up_creds, c->dentry) { + if (IS_ERR(copy_up_creds)) + return PTR_ERR(copy_up_creds); - ovl_start_write(c->dentry); - temp = ovl_create_temp(ofs, c->workdir, &cattr); - ovl_end_write(c->dentry); - ovl_revert_cu_creds(&cc); + ovl_start_write(c->dentry); + temp = ovl_create_temp(ofs, c->workdir, &cattr); + ovl_end_write(c->dentry); + } if (IS_ERR(temp)) return PTR_ERR(temp); @@ -808,29 +804,24 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) * ovl_copy_up_data(), so lock workdir and destdir and make sure that * temp wasn't moved before copy up completion or cleanup. */ - trap = lock_rename(c->workdir, c->destdir); - if (trap || temp->d_parent != c->workdir) { - /* temp or workdir moved underneath us? abort without cleanup */ - dput(temp); + rd.mnt_idmap = ovl_upper_mnt_idmap(ofs); + rd.old_parent = c->workdir; + rd.new_parent = c->destdir; + rd.flags = 0; + err = start_renaming_dentry(&rd, 0, temp, + &QSTR_LEN(c->destname.name, c->destname.len)); + if (err) { + /* temp or workdir moved underneath us? map to -EIO */ err = -EIO; - if (!IS_ERR(trap)) - unlock_rename(c->workdir, c->destdir); - goto out; } - - err = ovl_copy_up_metadata(c, temp); if (err) - goto cleanup; + goto cleanup_unlocked; - upper = ovl_lookup_upper(ofs, c->destname.name, c->destdir, - c->destname.len); - err = PTR_ERR(upper); - if (IS_ERR(upper)) - goto cleanup; + err = ovl_copy_up_metadata(c, temp); + if (!err) + err = ovl_do_rename_rd(&rd); + end_renaming(&rd); - err = ovl_do_rename(ofs, c->workdir, temp, c->destdir, upper, 0); - unlock_rename(c->workdir, c->destdir); - dput(upper); if (err) goto cleanup_unlocked; @@ -851,8 +842,6 @@ out: return err; -cleanup: - unlock_rename(c->workdir, c->destdir); cleanup_unlocked: ovl_cleanup(ofs, c->workdir, temp); dput(temp); @@ -866,17 +855,17 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) struct inode *udir = d_inode(c->destdir); struct dentry *temp, *upper; struct file *tmpfile; - struct ovl_cu_creds cc; int err; - err = ovl_prep_cu_creds(c->dentry, &cc); - if (err) - return err; + scoped_class(copy_up_creds, copy_up_creds, c->dentry) { + if (IS_ERR(copy_up_creds)) + return PTR_ERR(copy_up_creds); + + ovl_start_write(c->dentry); + tmpfile = ovl_do_tmpfile(ofs, c->workdir, c->stat.mode); + ovl_end_write(c->dentry); + } - ovl_start_write(c->dentry); - tmpfile = ovl_do_tmpfile(ofs, c->workdir, c->stat.mode); - ovl_end_write(c->dentry); - ovl_revert_cu_creds(&cc); if (IS_ERR(tmpfile)) return PTR_ERR(tmpfile); @@ -894,16 +883,14 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) if (err) goto out; - inode_lock_nested(udir, I_MUTEX_PARENT); - - upper = ovl_lookup_upper(ofs, c->destname.name, c->destdir, - c->destname.len); + upper = ovl_start_creating_upper(ofs, c->destdir, + &QSTR_LEN(c->destname.name, + c->destname.len)); err = PTR_ERR(upper); if (!IS_ERR(upper)) { err = ovl_do_link(ofs, temp, udir, upper); - dput(upper); + end_creating(upper); } - inode_unlock(udir); if (err) goto out; @@ -1214,7 +1201,6 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, static int ovl_copy_up_flags(struct dentry *dentry, int flags) { int err = 0; - const struct cred *old_cred; bool disconnected = (dentry->d_flags & DCACHE_DISCONNECTED); /* @@ -1234,7 +1220,6 @@ static int ovl_copy_up_flags(struct dentry *dentry, int flags) if (err) return err; - old_cred = ovl_override_creds(dentry->d_sb); while (!err) { struct dentry *next; struct dentry *parent = NULL; @@ -1254,12 +1239,12 @@ static int ovl_copy_up_flags(struct dentry *dentry, int flags) next = parent; } - err = ovl_copy_up_one(parent, next, flags); + with_ovl_creds(dentry->d_sb) + err = ovl_copy_up_one(parent, next, flags); dput(parent); dput(next); } - ovl_revert_creds(old_cred); return err; } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index a5e9ddf3023b..06b860b9ded6 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -47,79 +47,70 @@ static int ovl_cleanup_locked(struct ovl_fs *ofs, struct inode *wdir, int ovl_cleanup(struct ovl_fs *ofs, struct dentry *workdir, struct dentry *wdentry) { - int err; - - err = ovl_parent_lock(workdir, wdentry); - if (err) - return err; + wdentry = start_removing_dentry(workdir, wdentry); + if (IS_ERR(wdentry)) + return PTR_ERR(wdentry); ovl_cleanup_locked(ofs, workdir->d_inode, wdentry); - ovl_parent_unlock(workdir); + end_removing(wdentry); return 0; } -struct dentry *ovl_lookup_temp(struct ovl_fs *ofs, struct dentry *workdir) +void ovl_tempname(char name[OVL_TEMPNAME_SIZE]) { - struct dentry *temp; - char name[20]; static atomic_t temp_id = ATOMIC_INIT(0); /* counter is allowed to wrap, since temp dentries are ephemeral */ - snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id)); + snprintf(name, OVL_TEMPNAME_SIZE, "#%x", atomic_inc_return(&temp_id)); +} - temp = ovl_lookup_upper(ofs, name, workdir, strlen(name)); - if (!IS_ERR(temp) && temp->d_inode) { - pr_err("workdir/%s already exists\n", name); - dput(temp); - temp = ERR_PTR(-EIO); - } +static struct dentry *ovl_start_creating_temp(struct ovl_fs *ofs, + struct dentry *workdir) +{ + char name[OVL_TEMPNAME_SIZE]; - return temp; + ovl_tempname(name); + return start_creating(ovl_upper_mnt_idmap(ofs), workdir, + &QSTR(name)); } static struct dentry *ovl_whiteout(struct ovl_fs *ofs) { int err; - struct dentry *whiteout; + struct dentry *whiteout, *link; struct dentry *workdir = ofs->workdir; struct inode *wdir = workdir->d_inode; guard(mutex)(&ofs->whiteout_lock); if (!ofs->whiteout) { - inode_lock_nested(wdir, I_MUTEX_PARENT); - whiteout = ovl_lookup_temp(ofs, workdir); - if (!IS_ERR(whiteout)) { - err = ovl_do_whiteout(ofs, wdir, whiteout); - if (err) { - dput(whiteout); - whiteout = ERR_PTR(err); - } - } - inode_unlock(wdir); + whiteout = ovl_start_creating_temp(ofs, workdir); if (IS_ERR(whiteout)) return whiteout; - ofs->whiteout = whiteout; + err = ovl_do_whiteout(ofs, wdir, whiteout); + if (!err) + ofs->whiteout = dget(whiteout); + end_creating(whiteout); + if (err) + return ERR_PTR(err); } if (!ofs->no_shared_whiteout) { - inode_lock_nested(wdir, I_MUTEX_PARENT); - whiteout = ovl_lookup_temp(ofs, workdir); - if (!IS_ERR(whiteout)) { - err = ovl_do_link(ofs, ofs->whiteout, wdir, whiteout); - if (err) { - dput(whiteout); - whiteout = ERR_PTR(err); - } - } - inode_unlock(wdir); - if (!IS_ERR(whiteout)) + link = ovl_start_creating_temp(ofs, workdir); + if (IS_ERR(link)) + return link; + err = ovl_do_link(ofs, ofs->whiteout, wdir, link); + if (!err) + whiteout = dget(link); + end_creating(link); + if (!err) return whiteout; - if (PTR_ERR(whiteout) != -EMLINK) { - pr_warn("Failed to link whiteout - disabling whiteout inode sharing(nlink=%u, err=%lu)\n", + + if (err != -EMLINK) { + pr_warn("Failed to link whiteout - disabling whiteout inode sharing(nlink=%u, err=%u)\n", ofs->whiteout->d_inode->i_nlink, - PTR_ERR(whiteout)); + err); ofs->no_shared_whiteout = true; } } @@ -132,6 +123,7 @@ int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir, struct dentry *dentry) { struct dentry *whiteout; + struct renamedata rd = {}; int err; int flags = 0; @@ -143,10 +135,14 @@ int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir, if (d_is_dir(dentry)) flags = RENAME_EXCHANGE; - err = ovl_lock_rename_workdir(ofs->workdir, whiteout, dir, dentry); + rd.mnt_idmap = ovl_upper_mnt_idmap(ofs); + rd.old_parent = ofs->workdir; + rd.new_parent = dir; + rd.flags = flags; + err = start_renaming_two_dentries(&rd, whiteout, dentry); if (!err) { - err = ovl_do_rename(ofs, ofs->workdir, whiteout, dir, dentry, flags); - unlock_rename(ofs->workdir, dir); + err = ovl_do_rename_rd(&rd); + end_renaming(&rd); } if (err) goto kill_whiteout; @@ -191,7 +187,7 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent, if (!err && ofs->casefold != ovl_dentry_casefolded(newdentry)) { pr_warn_ratelimited("wrong inherited casefold (%pd2)\n", newdentry); - dput(newdentry); + end_creating(newdentry); err = -EINVAL; } break; @@ -241,8 +237,7 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent, } out: if (err) { - if (!IS_ERR(newdentry)) - dput(newdentry); + end_creating(newdentry); return ERR_PTR(err); } return newdentry; @@ -252,11 +247,11 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir, struct ovl_cattr *attr) { struct dentry *ret; - inode_lock_nested(workdir->d_inode, I_MUTEX_PARENT); - ret = ovl_create_real(ofs, workdir, - ovl_lookup_temp(ofs, workdir), attr); - inode_unlock(workdir->d_inode); - return ret; + ret = ovl_start_creating_temp(ofs, workdir); + if (IS_ERR(ret)) + return ret; + ret = ovl_create_real(ofs, workdir, ret, attr); + return end_creating_keep(ret); } static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper, @@ -354,18 +349,19 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode, { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); - struct inode *udir = upperdir->d_inode; struct dentry *newdentry; int err; - inode_lock_nested(udir, I_MUTEX_PARENT); - newdentry = ovl_create_real(ofs, upperdir, - ovl_lookup_upper(ofs, dentry->d_name.name, - upperdir, dentry->d_name.len), - attr); - inode_unlock(udir); + newdentry = ovl_start_creating_upper(ofs, upperdir, + &QSTR_LEN(dentry->d_name.name, + dentry->d_name.len)); if (IS_ERR(newdentry)) return PTR_ERR(newdentry); + newdentry = ovl_create_real(ofs, upperdir, newdentry, attr); + if (IS_ERR(newdentry)) + return PTR_ERR(newdentry); + + end_creating_keep(newdentry); if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry) && !ovl_allow_offline_changes(ofs)) { @@ -391,6 +387,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry, struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *workdir = ovl_workdir(dentry); struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct renamedata rd = {}; struct path upperpath; struct dentry *upper; struct dentry *opaquedir; @@ -416,7 +413,11 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry, if (IS_ERR(opaquedir)) goto out; - err = ovl_lock_rename_workdir(workdir, opaquedir, upperdir, upper); + rd.mnt_idmap = ovl_upper_mnt_idmap(ofs); + rd.old_parent = workdir; + rd.new_parent = upperdir; + rd.flags = RENAME_EXCHANGE; + err = start_renaming_two_dentries(&rd, opaquedir, upper); if (err) goto out_cleanup_unlocked; @@ -434,8 +435,8 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry, if (err) goto out_cleanup; - err = ovl_do_rename(ofs, workdir, opaquedir, upperdir, upper, RENAME_EXCHANGE); - unlock_rename(workdir, upperdir); + err = ovl_do_rename_rd(&rd); + end_renaming(&rd); if (err) goto out_cleanup_unlocked; @@ -448,7 +449,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry, return opaquedir; out_cleanup: - unlock_rename(workdir, upperdir); + end_renaming(&rd); out_cleanup_unlocked: ovl_cleanup(ofs, workdir, opaquedir); dput(opaquedir); @@ -471,6 +472,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *workdir = ovl_workdir(dentry); struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct renamedata rd = {}; struct dentry *upper; struct dentry *newdentry; int err; @@ -502,7 +504,11 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, if (IS_ERR(newdentry)) goto out_dput; - err = ovl_lock_rename_workdir(workdir, newdentry, upperdir, upper); + rd.mnt_idmap = ovl_upper_mnt_idmap(ofs); + rd.old_parent = workdir; + rd.new_parent = upperdir; + rd.flags = 0; + err = start_renaming_two_dentries(&rd, newdentry, upper); if (err) goto out_cleanup_unlocked; @@ -539,16 +545,16 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, if (err) goto out_cleanup; - err = ovl_do_rename(ofs, workdir, newdentry, upperdir, upper, - RENAME_EXCHANGE); - unlock_rename(workdir, upperdir); + rd.flags = RENAME_EXCHANGE; + err = ovl_do_rename_rd(&rd); + end_renaming(&rd); if (err) goto out_cleanup_unlocked; ovl_cleanup(ofs, workdir, upper); } else { - err = ovl_do_rename(ofs, workdir, newdentry, upperdir, upper, 0); - unlock_rename(workdir, upperdir); + err = ovl_do_rename_rd(&rd); + end_renaming(&rd); if (err) goto out_cleanup_unlocked; } @@ -568,66 +574,76 @@ out: return err; out_cleanup: - unlock_rename(workdir, upperdir); + end_renaming(&rd); out_cleanup_unlocked: ovl_cleanup(ofs, workdir, newdentry); dput(newdentry); goto out_dput; } -static const struct cred *ovl_setup_cred_for_create(struct dentry *dentry, - struct inode *inode, - umode_t mode, - const struct cred *old_cred) +static const struct cred *ovl_override_creator_creds(struct dentry *dentry, struct inode *inode, umode_t mode) { int err; - struct cred *override_cred; - override_cred = prepare_creds(); + if (WARN_ON_ONCE(current->cred != ovl_creds(dentry->d_sb))) + return ERR_PTR(-EINVAL); + + CLASS(prepare_creds, override_cred)(); if (!override_cred) return ERR_PTR(-ENOMEM); override_cred->fsuid = inode->i_uid; override_cred->fsgid = inode->i_gid; + err = security_dentry_create_files_as(dentry, mode, &dentry->d_name, - old_cred, override_cred); - if (err) { - put_cred(override_cred); + current->cred, override_cred); + if (err) return ERR_PTR(err); - } - /* - * Caller is going to match this with revert_creds() and drop - * referenec on the returned creds. - * We must be called with creator creds already, otherwise we risk - * leaking creds. - */ - old_cred = override_creds(override_cred); - WARN_ON_ONCE(old_cred != ovl_creds(dentry->d_sb)); + return override_creds(no_free_ptr(override_cred)); +} + +static void ovl_revert_creator_creds(const struct cred *old_cred) +{ + const struct cred *override_cred; - return override_cred; + override_cred = revert_creds(old_cred); + put_cred(override_cred); +} + +DEFINE_CLASS(ovl_override_creator_creds, + const struct cred *, + if (!IS_ERR_OR_NULL(_T)) ovl_revert_creator_creds(_T), + ovl_override_creator_creds(dentry, inode, mode), + struct dentry *dentry, struct inode *inode, umode_t mode) + +static int ovl_create_handle_whiteouts(struct dentry *dentry, + struct inode *inode, + struct ovl_cattr *attr) +{ + if (!ovl_dentry_is_whiteout(dentry)) + return ovl_create_upper(dentry, inode, attr); + + return ovl_create_over_whiteout(dentry, inode, attr); } static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, struct ovl_cattr *attr, bool origin) { int err; - const struct cred *old_cred, *new_cred = NULL; struct dentry *parent = dentry->d_parent; - old_cred = ovl_override_creds(dentry->d_sb); - - /* - * When linking a file with copy up origin into a new parent, mark the - * new parent dir "impure". - */ - if (origin) { - err = ovl_set_impure(parent, ovl_dentry_upper(parent)); - if (err) - goto out_revert_creds; - } + with_ovl_creds(dentry->d_sb) { + /* + * When linking a file with copy up origin into a new parent, mark the + * new parent dir "impure". + */ + if (origin) { + err = ovl_set_impure(parent, ovl_dentry_upper(parent)); + if (err) + return err; + } - if (!attr->hardlink) { /* * In the creation cases(create, mkdir, mknod, symlink), * ovl should transfer current's fs{u,g}id to underlying @@ -641,23 +657,16 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, * create a new inode, so just use the ovl mounter's * fs{u,g}id. */ - new_cred = ovl_setup_cred_for_create(dentry, inode, attr->mode, - old_cred); - err = PTR_ERR(new_cred); - if (IS_ERR(new_cred)) { - new_cred = NULL; - goto out_revert_creds; - } - } - if (!ovl_dentry_is_whiteout(dentry)) - err = ovl_create_upper(dentry, inode, attr); - else - err = ovl_create_over_whiteout(dentry, inode, attr); + if (attr->hardlink) + return ovl_create_handle_whiteouts(dentry, inode, attr); -out_revert_creds: - ovl_revert_creds(old_cred); - put_cred(new_cred); + scoped_class(ovl_override_creator_creds, cred, dentry, inode, attr->mode) { + if (IS_ERR(cred)) + return PTR_ERR(cred); + return ovl_create_handle_whiteouts(dentry, inode, attr); + } + } return err; } @@ -686,7 +695,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, goto out_drop_write; spin_lock(&inode->i_lock); - inode->i_state |= I_CREATING; + inode_state_set(inode, I_CREATING); spin_unlock(&inode->i_lock); inode_init_owner(&nop_mnt_idmap, inode, dentry->d_parent->d_inode, mode); @@ -733,14 +742,8 @@ static int ovl_symlink(struct mnt_idmap *idmap, struct inode *dir, static int ovl_set_link_redirect(struct dentry *dentry) { - const struct cred *old_cred; - int err; - - old_cred = ovl_override_creds(dentry->d_sb); - err = ovl_set_redirect(dentry, false); - ovl_revert_creds(old_cred); - - return err; + with_ovl_creds(dentry->d_sb) + return ovl_set_redirect(dentry, false); } static int ovl_link(struct dentry *old, struct inode *newdir, @@ -850,17 +853,17 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir, goto out; } - inode_lock_nested(dir, I_MUTEX_PARENT); - upper = ovl_lookup_upper(ofs, dentry->d_name.name, upperdir, - dentry->d_name.len); + upper = ovl_start_removing_upper(ofs, upperdir, + &QSTR_LEN(dentry->d_name.name, + dentry->d_name.len)); err = PTR_ERR(upper); if (IS_ERR(upper)) - goto out_unlock; + goto out_dput; err = -ESTALE; if ((opaquedir && upper != opaquedir) || (!opaquedir && !ovl_matches_upper(dentry, upper))) - goto out_dput_upper; + goto out_unlock; if (is_dir) err = ovl_do_rmdir(ofs, dir, upper); @@ -876,10 +879,9 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir, */ if (!err) d_drop(dentry); -out_dput_upper: - dput(upper); out_unlock: - inode_unlock(dir); + end_removing(upper); +out_dput: dput(opaquedir); out: return err; @@ -916,7 +918,6 @@ static void ovl_drop_nlink(struct dentry *dentry) static int ovl_do_remove(struct dentry *dentry, bool is_dir) { int err; - const struct cred *old_cred; bool lower_positive = ovl_lower_positive(dentry); LIST_HEAD(list); @@ -935,12 +936,12 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) if (err) goto out; - old_cred = ovl_override_creds(dentry->d_sb); - if (!lower_positive) - err = ovl_remove_upper(dentry, is_dir, &list); - else - err = ovl_remove_and_whiteout(dentry, &list); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) { + if (!lower_positive) + err = ovl_remove_upper(dentry, is_dir, &list); + else + err = ovl_remove_and_whiteout(dentry, &list); + } if (!err) { if (is_dir) clear_nlink(dentry->d_inode); @@ -1104,102 +1105,107 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir) return err; } -static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, - struct dentry *old, struct inode *newdir, - struct dentry *new, unsigned int flags) +struct ovl_renamedata { + struct renamedata; + struct dentry *opaquedir; + bool cleanup_whiteout; + bool update_nlink; + bool overwrite; +}; + +static int ovl_rename_start(struct ovl_renamedata *ovlrd, struct list_head *list) { - int err; - struct dentry *old_upperdir; - struct dentry *new_upperdir; - struct dentry *olddentry = NULL; - struct dentry *newdentry = NULL; - struct dentry *trap, *de; - bool old_opaque; - bool new_opaque; - bool cleanup_whiteout = false; - bool update_nlink = false; - bool overwrite = !(flags & RENAME_EXCHANGE); + struct dentry *old = ovlrd->old_dentry; + struct dentry *new = ovlrd->new_dentry; bool is_dir = d_is_dir(old); bool new_is_dir = d_is_dir(new); - bool samedir = olddir == newdir; - struct dentry *opaquedir = NULL; - const struct cred *old_cred = NULL; - struct ovl_fs *ofs = OVL_FS(old->d_sb); - LIST_HEAD(list); + int err; - err = -EINVAL; - if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE)) - goto out; + if (ovlrd->flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE)) + return -EINVAL; - flags &= ~RENAME_NOREPLACE; + ovlrd->flags &= ~RENAME_NOREPLACE; /* Don't copy up directory trees */ err = -EXDEV; if (!ovl_can_move(old)) - goto out; - if (!overwrite && !ovl_can_move(new)) - goto out; + return err; + if (!ovlrd->overwrite && !ovl_can_move(new)) + return err; - if (overwrite && new_is_dir && !ovl_pure_upper(new)) { - err = ovl_check_empty_dir(new, &list); + if (ovlrd->overwrite && new_is_dir && !ovl_pure_upper(new)) { + err = ovl_check_empty_dir(new, list); if (err) - goto out; + return err; } - if (overwrite) { + if (ovlrd->overwrite) { if (ovl_lower_positive(old)) { if (!ovl_dentry_is_whiteout(new)) { /* Whiteout source */ - flags |= RENAME_WHITEOUT; + ovlrd->flags |= RENAME_WHITEOUT; } else { /* Switch whiteouts */ - flags |= RENAME_EXCHANGE; + ovlrd->flags |= RENAME_EXCHANGE; } } else if (is_dir && ovl_dentry_is_whiteout(new)) { - flags |= RENAME_EXCHANGE; - cleanup_whiteout = true; + ovlrd->flags |= RENAME_EXCHANGE; + ovlrd->cleanup_whiteout = true; } } err = ovl_copy_up(old); if (err) - goto out; + return err; err = ovl_copy_up(new->d_parent); if (err) - goto out; - if (!overwrite) { + return err; + + if (!ovlrd->overwrite) { err = ovl_copy_up(new); if (err) - goto out; + return err; } else if (d_inode(new)) { err = ovl_nlink_start(new); if (err) - goto out; + return err; - update_nlink = true; + ovlrd->update_nlink = true; } - if (!update_nlink) { + if (!ovlrd->update_nlink) { /* ovl_nlink_start() took ovl_want_write() */ err = ovl_want_write(old); if (err) - goto out; + return err; } - old_cred = ovl_override_creds(old->d_sb); + return 0; +} - if (!list_empty(&list)) { - opaquedir = ovl_clear_empty(new, &list); - err = PTR_ERR(opaquedir); - if (IS_ERR(opaquedir)) { - opaquedir = NULL; - goto out_revert_creds; - } - } +static int ovl_rename_upper(struct ovl_renamedata *ovlrd, struct list_head *list) +{ + struct dentry *old = ovlrd->old_dentry; + struct dentry *new = ovlrd->new_dentry; + struct ovl_fs *ofs = OVL_FS(old->d_sb); + struct dentry *old_upperdir = ovl_dentry_upper(old->d_parent); + struct dentry *new_upperdir = ovl_dentry_upper(new->d_parent); + bool is_dir = d_is_dir(old); + bool new_is_dir = d_is_dir(new); + bool samedir = old->d_parent == new->d_parent; + struct renamedata rd = {}; + struct dentry *de; + struct dentry *whiteout = NULL; + bool old_opaque, new_opaque; + int err; - old_upperdir = ovl_dentry_upper(old->d_parent); - new_upperdir = ovl_dentry_upper(new->d_parent); + if (!list_empty(list)) { + de = ovl_clear_empty(new, list); + if (IS_ERR(de)) + return PTR_ERR(de); + ovlrd->opaquedir = de; + } if (!samedir) { /* @@ -1211,95 +1217,88 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, if (ovl_type_origin(old)) { err = ovl_set_impure(new->d_parent, new_upperdir); if (err) - goto out_revert_creds; + return err; } - if (!overwrite && ovl_type_origin(new)) { + if (!ovlrd->overwrite && ovl_type_origin(new)) { err = ovl_set_impure(old->d_parent, old_upperdir); if (err) - goto out_revert_creds; + return err; } } - trap = lock_rename(new_upperdir, old_upperdir); - if (IS_ERR(trap)) { - err = PTR_ERR(trap); - goto out_revert_creds; - } + rd.mnt_idmap = ovl_upper_mnt_idmap(ofs); + rd.old_parent = old_upperdir; + rd.new_parent = new_upperdir; + rd.flags = ovlrd->flags; - de = ovl_lookup_upper(ofs, old->d_name.name, old_upperdir, - old->d_name.len); - err = PTR_ERR(de); - if (IS_ERR(de)) - goto out_unlock; - olddentry = de; + err = start_renaming(&rd, 0, + &QSTR_LEN(old->d_name.name, old->d_name.len), + &QSTR_LEN(new->d_name.name, new->d_name.len)); + if (err) + return err; err = -ESTALE; - if (!ovl_matches_upper(old, olddentry)) + if (!ovl_matches_upper(old, rd.old_dentry)) goto out_unlock; - de = ovl_lookup_upper(ofs, new->d_name.name, new_upperdir, - new->d_name.len); - err = PTR_ERR(de); - if (IS_ERR(de)) - goto out_unlock; - newdentry = de; - old_opaque = ovl_dentry_is_opaque(old); new_opaque = ovl_dentry_is_opaque(new); err = -ESTALE; if (d_inode(new) && ovl_dentry_upper(new)) { - if (opaquedir) { - if (newdentry != opaquedir) + if (ovlrd->opaquedir) { + if (rd.new_dentry != ovlrd->opaquedir) goto out_unlock; } else { - if (!ovl_matches_upper(new, newdentry)) + if (!ovl_matches_upper(new, rd.new_dentry)) goto out_unlock; } } else { - if (!d_is_negative(newdentry)) { - if (!new_opaque || !ovl_upper_is_whiteout(ofs, newdentry)) + if (!d_is_negative(rd.new_dentry)) { + if (!new_opaque || !ovl_upper_is_whiteout(ofs, rd.new_dentry)) goto out_unlock; } else { - if (flags & RENAME_EXCHANGE) + if (ovlrd->flags & RENAME_EXCHANGE) goto out_unlock; } } - if (olddentry == trap) - goto out_unlock; - if (newdentry == trap) - goto out_unlock; - - if (olddentry->d_inode == newdentry->d_inode) + if (rd.old_dentry->d_inode == rd.new_dentry->d_inode) goto out_unlock; err = 0; if (ovl_type_merge_or_lower(old)) err = ovl_set_redirect(old, samedir); else if (is_dir && !old_opaque && ovl_type_merge(new->d_parent)) - err = ovl_set_opaque_xerr(old, olddentry, -EXDEV); + err = ovl_set_opaque_xerr(old, rd.old_dentry, -EXDEV); if (err) goto out_unlock; - if (!overwrite && ovl_type_merge_or_lower(new)) + if (!ovlrd->overwrite && ovl_type_merge_or_lower(new)) err = ovl_set_redirect(new, samedir); - else if (!overwrite && new_is_dir && !new_opaque && + else if (!ovlrd->overwrite && new_is_dir && !new_opaque && ovl_type_merge(old->d_parent)) - err = ovl_set_opaque_xerr(new, newdentry, -EXDEV); + err = ovl_set_opaque_xerr(new, rd.new_dentry, -EXDEV); if (err) goto out_unlock; - err = ovl_do_rename(ofs, old_upperdir, olddentry, - new_upperdir, newdentry, flags); - unlock_rename(new_upperdir, old_upperdir); + err = ovl_do_rename_rd(&rd); + + if (!err && ovlrd->cleanup_whiteout) + whiteout = dget(rd.new_dentry); + +out_unlock: + end_renaming(&rd); + if (err) - goto out_revert_creds; + return err; - if (cleanup_whiteout) - ovl_cleanup(ofs, old_upperdir, newdentry); + if (whiteout) { + ovl_cleanup(ofs, old_upperdir, whiteout); + dput(whiteout); + } - if (overwrite && d_inode(new)) { + if (ovlrd->overwrite && d_inode(new)) { if (new_is_dir) clear_nlink(d_inode(new)); else @@ -1307,7 +1306,7 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, } ovl_dir_modified(old->d_parent, ovl_type_origin(old) || - (!overwrite && ovl_type_origin(new))); + (!ovlrd->overwrite && ovl_type_origin(new))); ovl_dir_modified(new->d_parent, ovl_type_origin(old) || (d_inode(new) && ovl_type_origin(new))); @@ -1316,28 +1315,47 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, if (d_inode(new) && ovl_dentry_upper(new)) ovl_copyattr(d_inode(new)); -out_revert_creds: - ovl_revert_creds(old_cred); - if (update_nlink) - ovl_nlink_end(new); + return err; +} + +static void ovl_rename_end(struct ovl_renamedata *ovlrd) +{ + if (ovlrd->update_nlink) + ovl_nlink_end(ovlrd->new_dentry); else - ovl_drop_write(old); -out: - dput(newdentry); - dput(olddentry); - dput(opaquedir); + ovl_drop_write(ovlrd->old_dentry); +} + +static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, + struct dentry *old, struct inode *newdir, + struct dentry *new, unsigned int flags) +{ + struct ovl_renamedata ovlrd = { + .old_parent = old->d_parent, + .old_dentry = old, + .new_parent = new->d_parent, + .new_dentry = new, + .flags = flags, + .overwrite = !(flags & RENAME_EXCHANGE), + }; + LIST_HEAD(list); + int err; + + err = ovl_rename_start(&ovlrd, &list); + if (!err) { + with_ovl_creds(old->d_sb) + err = ovl_rename_upper(&ovlrd, &list); + ovl_rename_end(&ovlrd); + } + + dput(ovlrd.opaquedir); ovl_cache_free(&list); return err; - -out_unlock: - unlock_rename(new_upperdir, old_upperdir); - goto out_revert_creds; } static int ovl_create_tmpfile(struct file *file, struct dentry *dentry, struct inode *inode, umode_t mode) { - const struct cred *old_cred, *new_cred = NULL; struct path realparentpath; struct file *realfile; struct ovl_file *of; @@ -1346,41 +1364,36 @@ static int ovl_create_tmpfile(struct file *file, struct dentry *dentry, int flags = file->f_flags | OVL_OPEN_FLAGS; int err; - old_cred = ovl_override_creds(dentry->d_sb); - new_cred = ovl_setup_cred_for_create(dentry, inode, mode, old_cred); - err = PTR_ERR(new_cred); - if (IS_ERR(new_cred)) { - new_cred = NULL; - goto out_revert_creds; - } + with_ovl_creds(dentry->d_sb) { + scoped_class(ovl_override_creator_creds, cred, dentry, inode, mode) { + if (IS_ERR(cred)) + return PTR_ERR(cred); - ovl_path_upper(dentry->d_parent, &realparentpath); - realfile = backing_tmpfile_open(&file->f_path, flags, &realparentpath, - mode, current_cred()); - err = PTR_ERR_OR_ZERO(realfile); - pr_debug("tmpfile/open(%pd2, 0%o) = %i\n", realparentpath.dentry, mode, err); - if (err) - goto out_revert_creds; + ovl_path_upper(dentry->d_parent, &realparentpath); + realfile = backing_tmpfile_open(&file->f_path, flags, &realparentpath, + mode, current_cred()); + err = PTR_ERR_OR_ZERO(realfile); + pr_debug("tmpfile/open(%pd2, 0%o) = %i\n", realparentpath.dentry, mode, err); + if (err) + return err; - of = ovl_file_alloc(realfile); - if (!of) { - fput(realfile); - err = -ENOMEM; - goto out_revert_creds; - } + of = ovl_file_alloc(realfile); + if (!of) { + fput(realfile); + return -ENOMEM; + } - /* ovl_instantiate() consumes the newdentry reference on success */ - newdentry = dget(realfile->f_path.dentry); - err = ovl_instantiate(dentry, inode, newdentry, false, file); - if (!err) { - file->private_data = of; - } else { - dput(newdentry); - ovl_file_free(of); + /* ovl_instantiate() consumes the newdentry reference on success */ + newdentry = dget(realfile->f_path.dentry); + err = ovl_instantiate(dentry, inode, newdentry, false, file); + if (!err) { + file->private_data = of; + } else { + dput(newdentry); + ovl_file_free(of); + } + } } -out_revert_creds: - ovl_revert_creds(old_cred); - put_cred(new_cred); return err; } diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 7ab2c9daffd0..cbae89457234 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -31,7 +31,6 @@ static struct file *ovl_open_realfile(const struct file *file, struct inode *inode = file_inode(file); struct mnt_idmap *real_idmap; struct file *realfile; - const struct cred *old_cred; int flags = file->f_flags | OVL_OPEN_FLAGS; int acc_mode = ACC_MODE(flags); int err; @@ -39,19 +38,19 @@ static struct file *ovl_open_realfile(const struct file *file, if (flags & O_APPEND) acc_mode |= MAY_APPEND; - old_cred = ovl_override_creds(inode->i_sb); - real_idmap = mnt_idmap(realpath->mnt); - err = inode_permission(real_idmap, realinode, MAY_OPEN | acc_mode); - if (err) { - realfile = ERR_PTR(err); - } else { - if (!inode_owner_or_capable(real_idmap, realinode)) - flags &= ~O_NOATIME; - - realfile = backing_file_open(file_user_path(file), - flags, realpath, current_cred()); + with_ovl_creds(inode->i_sb) { + real_idmap = mnt_idmap(realpath->mnt); + err = inode_permission(real_idmap, realinode, MAY_OPEN | acc_mode); + if (err) { + realfile = ERR_PTR(err); + } else { + if (!inode_owner_or_capable(real_idmap, realinode)) + flags &= ~O_NOATIME; + + realfile = backing_file_open(file_user_path(file), + flags, realpath, current_cred()); + } } - ovl_revert_creds(old_cred); pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n", file, file, ovl_whatisit(inode, realinode), file->f_flags, @@ -244,7 +243,6 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); struct file *realfile; - const struct cred *old_cred; loff_t ret; /* @@ -273,9 +271,8 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) ovl_inode_lock(inode); realfile->f_pos = file->f_pos; - old_cred = ovl_override_creds(inode->i_sb); - ret = vfs_llseek(realfile, offset, whence); - ovl_revert_creds(old_cred); + with_ovl_creds(inode->i_sb) + ret = vfs_llseek(realfile, offset, whence); file->f_pos = realfile->f_pos; ovl_inode_unlock(inode); @@ -447,7 +444,6 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) enum ovl_path_type type; struct path upperpath; struct file *upperfile; - const struct cred *old_cred; int ret; ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb)); @@ -464,11 +460,8 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) if (IS_ERR(upperfile)) return PTR_ERR(upperfile); - old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fsync_range(upperfile, start, end, datasync); - ovl_revert_creds(old_cred); - - return ret; + with_ovl_creds(file_inode(file)->i_sb) + return vfs_fsync_range(upperfile, start, end, datasync); } static int ovl_mmap(struct file *file, struct vm_area_struct *vma) @@ -486,7 +479,6 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len { struct inode *inode = file_inode(file); struct file *realfile; - const struct cred *old_cred; int ret; inode_lock(inode); @@ -501,9 +493,8 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len if (IS_ERR(realfile)) goto out_unlock; - old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fallocate(realfile, mode, offset, len); - ovl_revert_creds(old_cred); + with_ovl_creds(inode->i_sb) + ret = vfs_fallocate(realfile, mode, offset, len); /* Update size */ ovl_file_modified(file); @@ -517,18 +508,13 @@ out_unlock: static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice) { struct file *realfile; - const struct cred *old_cred; - int ret; realfile = ovl_real_file(file); if (IS_ERR(realfile)) return PTR_ERR(realfile); - old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fadvise(realfile, offset, len, advice); - ovl_revert_creds(old_cred); - - return ret; + with_ovl_creds(file_inode(file)->i_sb) + return vfs_fadvise(realfile, offset, len, advice); } enum ovl_copyop { @@ -543,7 +529,6 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, { struct inode *inode_out = file_inode(file_out); struct file *realfile_in, *realfile_out; - const struct cred *old_cred; loff_t ret; inode_lock(inode_out); @@ -565,25 +550,25 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, if (IS_ERR(realfile_in)) goto out_unlock; - old_cred = ovl_override_creds(file_inode(file_out)->i_sb); - switch (op) { - case OVL_COPY: - ret = vfs_copy_file_range(realfile_in, pos_in, - realfile_out, pos_out, len, flags); - break; - - case OVL_CLONE: - ret = vfs_clone_file_range(realfile_in, pos_in, - realfile_out, pos_out, len, flags); - break; - - case OVL_DEDUPE: - ret = vfs_dedupe_file_range_one(realfile_in, pos_in, - realfile_out, pos_out, len, - flags); - break; + with_ovl_creds(file_inode(file_out)->i_sb) { + switch (op) { + case OVL_COPY: + ret = vfs_copy_file_range(realfile_in, pos_in, + realfile_out, pos_out, len, flags); + break; + + case OVL_CLONE: + ret = vfs_clone_file_range(realfile_in, pos_in, + realfile_out, pos_out, len, flags); + break; + + case OVL_DEDUPE: + ret = vfs_dedupe_file_range_one(realfile_in, pos_in, + realfile_out, pos_out, len, + flags); + break; + } } - ovl_revert_creds(old_cred); /* Update size */ ovl_file_modified(file_out); @@ -632,7 +617,6 @@ static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in, static int ovl_flush(struct file *file, fl_owner_t id) { struct file *realfile; - const struct cred *old_cred; int err = 0; realfile = ovl_real_file(file); @@ -640,9 +624,8 @@ static int ovl_flush(struct file *file, fl_owner_t id) return PTR_ERR(realfile); if (realfile->f_op->flush) { - old_cred = ovl_override_creds(file_inode(file)->i_sb); - err = realfile->f_op->flush(realfile, id); - ovl_revert_creds(old_cred); + with_ovl_creds(file_inode(file)->i_sb) + err = realfile->f_op->flush(realfile, id); } return err; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index e11f310ce092..bdbf86b56a9b 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -25,7 +25,6 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct ovl_fs *ofs = OVL_FS(dentry->d_sb); bool full_copy_up = false; struct dentry *upperdentry; - const struct cred *old_cred; err = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (err) @@ -78,9 +77,8 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, goto out_put_write; inode_lock(upperdentry->d_inode); - old_cred = ovl_override_creds(dentry->d_sb); - err = ovl_do_notify_change(ofs, upperdentry, attr); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) + err = ovl_do_notify_change(ofs, upperdentry, attr); if (!err) ovl_copyattr(dentry->d_inode); inode_unlock(upperdentry->d_inode); @@ -153,13 +151,22 @@ static void ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) } } +static inline int ovl_real_getattr_nosec(struct super_block *sb, + const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int flags) +{ + with_ovl_creds(sb) + return vfs_getattr_nosec(path, stat, request_mask, flags); +} + int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; + struct super_block *sb = dentry->d_sb; enum ovl_path_type type; struct path realpath; - const struct cred *old_cred; struct inode *inode = d_inode(dentry); bool is_dir = S_ISDIR(inode->i_mode); int fsid = 0; @@ -169,10 +176,9 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, metacopy_blocks = ovl_is_metacopy_dentry(dentry); type = ovl_path_real(dentry, &realpath); - old_cred = ovl_override_creds(dentry->d_sb); - err = vfs_getattr_nosec(&realpath, stat, request_mask, flags); + err = ovl_real_getattr_nosec(sb, &realpath, stat, request_mask, flags); if (err) - goto out; + return err; /* Report the effective immutable/append-only STATX flags */ generic_fill_statx_attr(inode, stat); @@ -195,10 +201,9 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, (!is_dir ? STATX_NLINK : 0); ovl_path_lower(dentry, &realpath); - err = vfs_getattr_nosec(&realpath, &lowerstat, lowermask, - flags); + err = ovl_real_getattr_nosec(sb, &realpath, &lowerstat, lowermask, flags); if (err) - goto out; + return err; /* * Lower hardlinks may be broken on copy up to different @@ -248,10 +253,10 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, ovl_path_lowerdata(dentry, &realpath); if (realpath.dentry) { - err = vfs_getattr_nosec(&realpath, &lowerdatastat, - lowermask, flags); + err = ovl_real_getattr_nosec(sb, &realpath, &lowerdatastat, + lowermask, flags); if (err) - goto out; + return err; } else { lowerdatastat.blocks = round_up(stat->size, stat->blksize) >> 9; @@ -279,9 +284,6 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, if (!is_dir && ovl_test_flag(OVL_INDEX, d_inode(dentry))) stat->nlink = dentry->d_inode->i_nlink; -out: - ovl_revert_creds(old_cred); - return err; } @@ -291,7 +293,6 @@ int ovl_permission(struct mnt_idmap *idmap, struct inode *upperinode = ovl_inode_upper(inode); struct inode *realinode; struct path realpath; - const struct cred *old_cred; int err; /* Careful in RCU walk mode */ @@ -309,33 +310,26 @@ int ovl_permission(struct mnt_idmap *idmap, if (err) return err; - old_cred = ovl_override_creds(inode->i_sb); if (!upperinode && !special_file(realinode->i_mode) && mask & MAY_WRITE) { mask &= ~(MAY_WRITE | MAY_APPEND); /* Make sure mounter can read file for copy up later */ mask |= MAY_READ; } - err = inode_permission(mnt_idmap(realpath.mnt), realinode, mask); - ovl_revert_creds(old_cred); - return err; + with_ovl_creds(inode->i_sb) + return inode_permission(mnt_idmap(realpath.mnt), realinode, mask); } static const char *ovl_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - const struct cred *old_cred; - const char *p; - if (!dentry) return ERR_PTR(-ECHILD); - old_cred = ovl_override_creds(dentry->d_sb); - p = vfs_get_link(ovl_dentry_real(dentry), done); - ovl_revert_creds(old_cred); - return p; + with_ovl_creds(dentry->d_sb) + return vfs_get_link(ovl_dentry_real(dentry), done); } #ifdef CONFIG_FS_POSIX_ACL @@ -465,11 +459,8 @@ struct posix_acl *do_ovl_get_acl(struct mnt_idmap *idmap, acl = get_cached_acl_rcu(realinode, type); } else { - const struct cred *old_cred; - - old_cred = ovl_override_creds(inode->i_sb); - acl = ovl_get_acl_path(&realpath, posix_acl_xattr_name(type), noperm); - ovl_revert_creds(old_cred); + with_ovl_creds(inode->i_sb) + acl = ovl_get_acl_path(&realpath, posix_acl_xattr_name(type), noperm); } return acl; @@ -481,7 +472,6 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode, int err; struct path realpath; const char *acl_name; - const struct cred *old_cred; struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *upperdentry = ovl_dentry_upper(dentry); struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry); @@ -495,10 +485,8 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode, struct posix_acl *real_acl; ovl_path_lower(dentry, &realpath); - old_cred = ovl_override_creds(dentry->d_sb); - real_acl = vfs_get_acl(mnt_idmap(realpath.mnt), realdentry, - acl_name); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) + real_acl = vfs_get_acl(mnt_idmap(realpath.mnt), realdentry, acl_name); if (IS_ERR(real_acl)) { err = PTR_ERR(real_acl); goto out; @@ -518,12 +506,12 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode, if (err) goto out; - old_cred = ovl_override_creds(dentry->d_sb); - if (acl) - err = ovl_do_set_acl(ofs, realdentry, acl_name, acl); - else - err = ovl_do_remove_acl(ofs, realdentry, acl_name); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) { + if (acl) + err = ovl_do_set_acl(ofs, realdentry, acl_name, acl); + else + err = ovl_do_remove_acl(ofs, realdentry, acl_name); + } ovl_drop_write(dentry); /* copy c/mtime */ @@ -588,9 +576,7 @@ int ovl_update_time(struct inode *inode, int flags) static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { - int err; struct inode *realinode = ovl_inode_realdata(inode); - const struct cred *old_cred; if (!realinode) return -EIO; @@ -598,11 +584,8 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (!realinode->i_op->fiemap) return -EOPNOTSUPP; - old_cred = ovl_override_creds(inode->i_sb); - err = realinode->i_op->fiemap(realinode, fieinfo, start, len); - ovl_revert_creds(old_cred); - - return err; + with_ovl_creds(inode->i_sb) + return realinode->i_op->fiemap(realinode, fieinfo, start, len); } /* @@ -653,7 +636,6 @@ int ovl_fileattr_set(struct mnt_idmap *idmap, { struct inode *inode = d_inode(dentry); struct path upperpath; - const struct cred *old_cred; unsigned int flags; int err; @@ -665,18 +647,18 @@ int ovl_fileattr_set(struct mnt_idmap *idmap, if (err) goto out; - old_cred = ovl_override_creds(inode->i_sb); - /* - * Store immutable/append-only flags in xattr and clear them - * in upper fileattr (in case they were set by older kernel) - * so children of "ovl-immutable" directories lower aliases of - * "ovl-immutable" hardlinks could be copied up. - * Clear xattr when flags are cleared. - */ - err = ovl_set_protattr(inode, upperpath.dentry, fa); - if (!err) - err = ovl_real_fileattr_set(&upperpath, fa); - ovl_revert_creds(old_cred); + with_ovl_creds(inode->i_sb) { + /* + * Store immutable/append-only flags in xattr and clear them + * in upper fileattr (in case they were set by older kernel) + * so children of "ovl-immutable" directories lower aliases of + * "ovl-immutable" hardlinks could be copied up. + * Clear xattr when flags are cleared. + */ + err = ovl_set_protattr(inode, upperpath.dentry, fa); + if (!err) + err = ovl_real_fileattr_set(&upperpath, fa); + } ovl_drop_write(dentry); /* @@ -730,15 +712,13 @@ int ovl_fileattr_get(struct dentry *dentry, struct file_kattr *fa) { struct inode *inode = d_inode(dentry); struct path realpath; - const struct cred *old_cred; int err; ovl_path_real(dentry, &realpath); - old_cred = ovl_override_creds(inode->i_sb); - err = ovl_real_fileattr_get(&realpath, fa); + with_ovl_creds(inode->i_sb) + err = ovl_real_fileattr_get(&realpath, fa); ovl_fileattr_prot_flags(inode, fa); - ovl_revert_creds(old_cred); return err; } @@ -1152,7 +1132,7 @@ struct inode *ovl_get_trap_inode(struct super_block *sb, struct dentry *dir) if (!trap) return ERR_PTR(-ENOMEM); - if (!(trap->i_state & I_NEW)) { + if (!(inode_state_read_once(trap) & I_NEW)) { /* Conflicting layer roots? */ iput(trap); return ERR_PTR(-ELOOP); @@ -1243,7 +1223,7 @@ struct inode *ovl_get_inode(struct super_block *sb, inode = ovl_iget5(sb, oip->newinode, key); if (!inode) goto out_err; - if (!(inode->i_state & I_NEW)) { + if (!(inode_state_read_once(inode) & I_NEW)) { /* * Verify that the underlying files stored in the inode * match those in the dentry. @@ -1303,7 +1283,7 @@ struct inode *ovl_get_inode(struct super_block *sb, if (upperdentry) ovl_check_protattr(inode, upperdentry); - if (inode->i_state & I_NEW) + if (inode_state_read_once(inode) & I_NEW) unlock_new_inode(inode); out: return inode; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index e93bcc5727bc..e9a69c95be91 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -979,15 +979,10 @@ static int ovl_maybe_validate_verity(struct dentry *dentry) return err; if (!ovl_test_flag(OVL_VERIFIED_DIGEST, inode)) { - const struct cred *old_cred; - - old_cred = ovl_override_creds(dentry->d_sb); - - err = ovl_validate_verity(ofs, &metapath, &datapath); + with_ovl_creds(dentry->d_sb) + err = ovl_validate_verity(ofs, &metapath, &datapath); if (err == 0) ovl_set_flag(OVL_VERIFIED_DIGEST, inode); - - ovl_revert_creds(old_cred); } ovl_inode_unlock(inode); @@ -1001,7 +996,6 @@ static int ovl_maybe_lookup_lowerdata(struct dentry *dentry) struct inode *inode = d_inode(dentry); const char *redirect = ovl_lowerdata_redirect(inode); struct ovl_path datapath = {}; - const struct cred *old_cred; int err; if (!redirect || ovl_dentry_lowerdata(dentry)) @@ -1019,9 +1013,8 @@ static int ovl_maybe_lookup_lowerdata(struct dentry *dentry) if (ovl_dentry_lowerdata(dentry)) goto out; - old_cred = ovl_override_creds(dentry->d_sb); - err = ovl_lookup_data_layers(dentry, redirect, &datapath); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) + err = ovl_lookup_data_layers(dentry, redirect, &datapath); if (err) goto out_err; @@ -1077,57 +1070,44 @@ static bool ovl_check_follow_redirect(struct ovl_lookup_data *d) return true; } -struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, - unsigned int flags) +struct ovl_lookup_ctx { + struct dentry *dentry; + struct ovl_entry *oe; + struct ovl_path *stack; + struct ovl_path *origin_path; + struct dentry *upperdentry; + struct dentry *index; + struct inode *inode; + unsigned int ctr; +}; + +static int ovl_lookup_layers(struct ovl_lookup_ctx *ctx, struct ovl_lookup_data *d) { - struct ovl_entry *oe = NULL; - const struct cred *old_cred; + struct dentry *dentry = ctx->dentry; struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct ovl_entry *poe = OVL_E(dentry->d_parent); struct ovl_entry *roe = OVL_E(dentry->d_sb->s_root); - struct ovl_path *stack = NULL, *origin_path = NULL; - struct dentry *upperdir, *upperdentry = NULL; - struct dentry *origin = NULL; - struct dentry *index = NULL; - unsigned int ctr = 0; - struct inode *inode = NULL; - bool upperopaque = false; bool check_redirect = (ovl_redirect_follow(ofs) || ofs->numdatalayer); + struct dentry *upperdir; struct dentry *this; - unsigned int i; - int err; + struct dentry *origin = NULL; + bool upperopaque = false; bool uppermetacopy = false; int metacopy_size = 0; - struct ovl_lookup_data d = { - .sb = dentry->d_sb, - .dentry = dentry, - .name = dentry->d_name, - .is_dir = false, - .opaque = false, - .stop = false, - .last = check_redirect ? false : !ovl_numlower(poe), - .redirect = NULL, - .upperredirect = NULL, - .metacopy = 0, - }; - - if (dentry->d_name.len > ofs->namelen) - return ERR_PTR(-ENAMETOOLONG); + unsigned int i; + int err; - old_cred = ovl_override_creds(dentry->d_sb); upperdir = ovl_dentry_upper(dentry->d_parent); if (upperdir) { - d.layer = &ofs->layers[0]; - err = ovl_lookup_layer(upperdir, &d, &upperdentry, true); + d->layer = &ofs->layers[0]; + err = ovl_lookup_layer(upperdir, d, &ctx->upperdentry, true); if (err) - goto out; + return err; - if (upperdentry && upperdentry->d_flags & DCACHE_OP_REAL) { - dput(upperdentry); - err = -EREMOTE; - goto out; - } - if (upperdentry && !d.is_dir) { + if (ctx->upperdentry && ctx->upperdentry->d_flags & DCACHE_OP_REAL) + return -EREMOTE; + + if (ctx->upperdentry && !d->is_dir) { /* * Lookup copy up origin by decoding origin file handle. * We may get a disconnected dentry, which is fine, @@ -1138,50 +1118,50 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, * number - it's the same as if we held a reference * to a dentry in lower layer that was moved under us. */ - err = ovl_check_origin(ofs, upperdentry, &origin_path); + err = ovl_check_origin(ofs, ctx->upperdentry, &ctx->origin_path); if (err) - goto out_put_upper; + return err; - if (d.metacopy) + if (d->metacopy) uppermetacopy = true; - metacopy_size = d.metacopy; + metacopy_size = d->metacopy; } - if (d.redirect) { + if (d->redirect) { err = -ENOMEM; - d.upperredirect = kstrdup(d.redirect, GFP_KERNEL); - if (!d.upperredirect) - goto out_put_upper; - if (d.redirect[0] == '/') + d->upperredirect = kstrdup(d->redirect, GFP_KERNEL); + if (!d->upperredirect) + return err; + if (d->redirect[0] == '/') poe = roe; } - upperopaque = d.opaque; + upperopaque = d->opaque; } - if (!d.stop && ovl_numlower(poe)) { + if (!d->stop && ovl_numlower(poe)) { err = -ENOMEM; - stack = ovl_stack_alloc(ofs->numlayer - 1); - if (!stack) - goto out_put_upper; + ctx->stack = ovl_stack_alloc(ofs->numlayer - 1); + if (!ctx->stack) + return err; } - for (i = 0; !d.stop && i < ovl_numlower(poe); i++) { + for (i = 0; !d->stop && i < ovl_numlower(poe); i++) { struct ovl_path lower = ovl_lowerstack(poe)[i]; - if (!ovl_check_follow_redirect(&d)) { + if (!ovl_check_follow_redirect(d)) { err = -EPERM; - goto out_put; + return err; } if (!check_redirect) - d.last = i == ovl_numlower(poe) - 1; - else if (d.is_dir || !ofs->numdatalayer) - d.last = lower.layer->idx == ovl_numlower(roe); + d->last = i == ovl_numlower(poe) - 1; + else if (d->is_dir || !ofs->numdatalayer) + d->last = lower.layer->idx == ovl_numlower(roe); - d.layer = lower.layer; - err = ovl_lookup_layer(lower.dentry, &d, &this, false); + d->layer = lower.layer; + err = ovl_lookup_layer(lower.dentry, d, &this, false); if (err) - goto out_put; + return err; if (!this) continue; @@ -1190,11 +1170,11 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, * If no origin fh is stored in upper of a merge dir, store fh * of lower dir and set upper parent "impure". */ - if (upperdentry && !ctr && !ofs->noxattr && d.is_dir) { - err = ovl_fix_origin(ofs, dentry, this, upperdentry); + if (ctx->upperdentry && !ctx->ctr && !ofs->noxattr && d->is_dir) { + err = ovl_fix_origin(ofs, dentry, this, ctx->upperdentry); if (err) { dput(this); - goto out_put; + return err; } } @@ -1207,23 +1187,23 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, * matches the dentry found using path based lookup, * otherwise error out. */ - if (upperdentry && !ctr && - ((d.is_dir && ovl_verify_lower(dentry->d_sb)) || - (!d.is_dir && ofs->config.index && origin_path))) { - err = ovl_verify_origin(ofs, upperdentry, this, false); + if (ctx->upperdentry && !ctx->ctr && + ((d->is_dir && ovl_verify_lower(dentry->d_sb)) || + (!d->is_dir && ofs->config.index && ctx->origin_path))) { + err = ovl_verify_origin(ofs, ctx->upperdentry, this, false); if (err) { dput(this); - if (d.is_dir) + if (d->is_dir) break; - goto out_put; + return err; } origin = this; } - if (!upperdentry && !d.is_dir && !ctr && d.metacopy) - metacopy_size = d.metacopy; + if (!ctx->upperdentry && !d->is_dir && !ctx->ctr && d->metacopy) + metacopy_size = d->metacopy; - if (d.metacopy && ctr) { + if (d->metacopy && ctx->ctr) { /* * Do not store intermediate metacopy dentries in * lower chain, except top most lower metacopy dentry. @@ -1233,15 +1213,15 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, dput(this); this = NULL; } else { - stack[ctr].dentry = this; - stack[ctr].layer = lower.layer; - ctr++; + ctx->stack[ctx->ctr].dentry = this; + ctx->stack[ctx->ctr].layer = lower.layer; + ctx->ctr++; } - if (d.stop) + if (d->stop) break; - if (d.redirect && d.redirect[0] == '/' && poe != roe) { + if (d->redirect && d->redirect[0] == '/' && poe != roe) { poe = roe; /* Find the current layer on the root dentry */ i = lower.layer->idx - 1; @@ -1252,12 +1232,12 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, * Defer lookup of lowerdata in data-only layers to first access. * Don't require redirect=follow and metacopy=on in this case. */ - if (d.metacopy && ctr && ofs->numdatalayer && d.absolute_redirect) { - d.metacopy = 0; - ctr++; - } else if (!ovl_check_follow_redirect(&d)) { + if (d->metacopy && ctx->ctr && ofs->numdatalayer && d->absolute_redirect) { + d->metacopy = 0; + ctx->ctr++; + } else if (!ovl_check_follow_redirect(d)) { err = -EPERM; - goto out_put; + return err; } /* @@ -1268,20 +1248,20 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, * For metacopy dentry, path based lookup will find lower dentries. * Just make sure a corresponding data dentry has been found. */ - if (d.metacopy || (uppermetacopy && !ctr)) { + if (d->metacopy || (uppermetacopy && !ctx->ctr)) { pr_warn_ratelimited("metacopy with no lower data found - abort lookup (%pd2)\n", dentry); err = -EIO; - goto out_put; - } else if (!d.is_dir && upperdentry && !ctr && origin_path) { - if (WARN_ON(stack != NULL)) { + return err; + } else if (!d->is_dir && ctx->upperdentry && !ctx->ctr && ctx->origin_path) { + if (WARN_ON(ctx->stack != NULL)) { err = -EIO; - goto out_put; + return err; } - stack = origin_path; - ctr = 1; - origin = origin_path->dentry; - origin_path = NULL; + ctx->stack = ctx->origin_path; + ctx->ctr = 1; + origin = ctx->origin_path->dentry; + ctx->origin_path = NULL; } /* @@ -1303,38 +1283,39 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, * is enabled and if upper had an ORIGIN xattr. * */ - if (!upperdentry && ctr) - origin = stack[0].dentry; + if (!ctx->upperdentry && ctx->ctr) + origin = ctx->stack[0].dentry; if (origin && ovl_indexdir(dentry->d_sb) && - (!d.is_dir || ovl_index_all(dentry->d_sb))) { - index = ovl_lookup_index(ofs, upperdentry, origin, true); - if (IS_ERR(index)) { - err = PTR_ERR(index); - index = NULL; - goto out_put; + (!d->is_dir || ovl_index_all(dentry->d_sb))) { + ctx->index = ovl_lookup_index(ofs, ctx->upperdentry, origin, true); + if (IS_ERR(ctx->index)) { + err = PTR_ERR(ctx->index); + ctx->index = NULL; + return err; } } - if (ctr) { - oe = ovl_alloc_entry(ctr); + if (ctx->ctr) { + ctx->oe = ovl_alloc_entry(ctx->ctr); err = -ENOMEM; - if (!oe) - goto out_put; + if (!ctx->oe) + return err; - ovl_stack_cpy(ovl_lowerstack(oe), stack, ctr); + ovl_stack_cpy(ovl_lowerstack(ctx->oe), ctx->stack, ctx->ctr); } if (upperopaque) ovl_dentry_set_opaque(dentry); - if (d.xwhiteouts) + if (d->xwhiteouts) ovl_dentry_set_xwhiteouts(dentry); - if (upperdentry) + if (ctx->upperdentry) ovl_dentry_set_upper_alias(dentry); - else if (index) { + else if (ctx->index) { + char *upperredirect; struct path upperpath = { - .dentry = upperdentry = dget(index), + .dentry = ctx->upperdentry = dget(ctx->index), .mnt = ovl_upper_mnt(ofs), }; @@ -1343,84 +1324,100 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, * assignment happens only if upperdentry is non-NULL, and * this one only if upperdentry is NULL. */ - d.upperredirect = ovl_get_redirect_xattr(ofs, &upperpath, 0); - if (IS_ERR(d.upperredirect)) { - err = PTR_ERR(d.upperredirect); - d.upperredirect = NULL; - goto out_free_oe; - } + upperredirect = ovl_get_redirect_xattr(ofs, &upperpath, 0); + if (IS_ERR(upperredirect)) + return PTR_ERR(upperredirect); + d->upperredirect = upperredirect; err = ovl_check_metacopy_xattr(ofs, &upperpath, NULL); if (err < 0) - goto out_free_oe; - d.metacopy = uppermetacopy = err; + return err; + d->metacopy = uppermetacopy = err; metacopy_size = err; - if (!ovl_check_follow_redirect(&d)) { + if (!ovl_check_follow_redirect(d)) { err = -EPERM; - goto out_free_oe; + return err; } } - if (upperdentry || ctr) { + if (ctx->upperdentry || ctx->ctr) { + struct inode *inode; struct ovl_inode_params oip = { - .upperdentry = upperdentry, - .oe = oe, - .index = index, - .redirect = d.upperredirect, + .upperdentry = ctx->upperdentry, + .oe = ctx->oe, + .index = ctx->index, + .redirect = d->upperredirect, }; /* Store lowerdata redirect for lazy lookup */ - if (ctr > 1 && !d.is_dir && !stack[ctr - 1].dentry) { - oip.lowerdata_redirect = d.redirect; - d.redirect = NULL; + if (ctx->ctr > 1 && !d->is_dir && !ctx->stack[ctx->ctr - 1].dentry) { + oip.lowerdata_redirect = d->redirect; + d->redirect = NULL; } + inode = ovl_get_inode(dentry->d_sb, &oip); - err = PTR_ERR(inode); if (IS_ERR(inode)) - goto out_free_oe; - if (upperdentry && !uppermetacopy) - ovl_set_flag(OVL_UPPERDATA, inode); + return PTR_ERR(inode); + + ctx->inode = inode; + if (ctx->upperdentry && !uppermetacopy) + ovl_set_flag(OVL_UPPERDATA, ctx->inode); if (metacopy_size > OVL_METACOPY_MIN_SIZE) - ovl_set_flag(OVL_HAS_DIGEST, inode); + ovl_set_flag(OVL_HAS_DIGEST, ctx->inode); } - ovl_dentry_init_reval(dentry, upperdentry, OVL_I_E(inode)); + ovl_dentry_init_reval(dentry, ctx->upperdentry, OVL_I_E(ctx->inode)); + + return 0; +} + +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + struct ovl_entry *poe = OVL_E(dentry->d_parent); + bool check_redirect = (ovl_redirect_follow(ofs) || ofs->numdatalayer); + int err; + struct ovl_lookup_ctx ctx = { + .dentry = dentry, + }; + struct ovl_lookup_data d = { + .sb = dentry->d_sb, + .dentry = dentry, + .name = dentry->d_name, + .last = check_redirect ? false : !ovl_numlower(poe), + }; + + if (dentry->d_name.len > ofs->namelen) + return ERR_PTR(-ENAMETOOLONG); + + with_ovl_creds(dentry->d_sb) + err = ovl_lookup_layers(&ctx, &d); - ovl_revert_creds(old_cred); - if (origin_path) { - dput(origin_path->dentry); - kfree(origin_path); + if (ctx.origin_path) { + dput(ctx.origin_path->dentry); + kfree(ctx.origin_path); } - dput(index); - ovl_stack_free(stack, ctr); + dput(ctx.index); + ovl_stack_free(ctx.stack, ctx.ctr); kfree(d.redirect); - return d_splice_alias(inode, dentry); -out_free_oe: - ovl_free_entry(oe); -out_put: - dput(index); - ovl_stack_free(stack, ctr); -out_put_upper: - if (origin_path) { - dput(origin_path->dentry); - kfree(origin_path); + if (err) { + ovl_free_entry(ctx.oe); + dput(ctx.upperdentry); + kfree(d.upperredirect); + return ERR_PTR(err); } - dput(upperdentry); - kfree(d.upperredirect); -out: - kfree(d.redirect); - ovl_revert_creds(old_cred); - return ERR_PTR(err); + + return d_splice_alias(ctx.inode, dentry); } bool ovl_lower_positive(struct dentry *dentry) { struct ovl_entry *poe = OVL_E(dentry->d_parent); const struct qstr *name = &dentry->d_name; - const struct cred *old_cred; unsigned int i; bool positive = false; bool done = false; @@ -1436,46 +1433,45 @@ bool ovl_lower_positive(struct dentry *dentry) if (!ovl_dentry_upper(dentry)) return true; - old_cred = ovl_override_creds(dentry->d_sb); - /* Positive upper -> have to look up lower to see whether it exists */ - for (i = 0; !done && !positive && i < ovl_numlower(poe); i++) { - struct dentry *this; - struct ovl_path *parentpath = &ovl_lowerstack(poe)[i]; + with_ovl_creds(dentry->d_sb) { + /* Positive upper -> have to look up lower to see whether it exists */ + for (i = 0; !done && !positive && i < ovl_numlower(poe); i++) { + struct dentry *this; + struct ovl_path *parentpath = &ovl_lowerstack(poe)[i]; - /* - * We need to make a non-const copy of dentry->d_name, - * because lookup_one_positive_unlocked() will hash name - * with parentpath base, which is on another (lower fs). - */ - this = lookup_one_positive_unlocked( - mnt_idmap(parentpath->layer->mnt), - &QSTR_LEN(name->name, name->len), - parentpath->dentry); - if (IS_ERR(this)) { - switch (PTR_ERR(this)) { - case -ENOENT: - case -ENAMETOOLONG: - break; - - default: - /* - * Assume something is there, we just couldn't - * access it. - */ - positive = true; - break; + /* + * We need to make a non-const copy of dentry->d_name, + * because lookup_one_positive_unlocked() will hash name + * with parentpath base, which is on another (lower fs). + */ + this = lookup_one_positive_unlocked(mnt_idmap(parentpath->layer->mnt), + &QSTR_LEN(name->name, name->len), + parentpath->dentry); + if (IS_ERR(this)) { + switch (PTR_ERR(this)) { + case -ENOENT: + case -ENAMETOOLONG: + break; + + default: + /* + * Assume something is there, we just couldn't + * access it. + */ + positive = true; + break; + } + } else { + struct path path = { + .dentry = this, + .mnt = parentpath->layer->mnt, + }; + positive = !ovl_path_is_whiteout(OVL_FS(dentry->d_sb), &path); + done = true; + dput(this); } - } else { - struct path path = { - .dentry = this, - .mnt = parentpath->layer->mnt, - }; - positive = !ovl_path_is_whiteout(OVL_FS(dentry->d_sb), &path); - done = true; - dput(this); } } - ovl_revert_creds(old_cred); return positive; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index c8fd5951fc5e..f9ac9bdde830 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -206,7 +206,7 @@ static inline int ovl_do_notify_change(struct ovl_fs *ofs, static inline int ovl_do_rmdir(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry) { - int err = vfs_rmdir(ovl_upper_mnt_idmap(ofs), dir, dentry); + int err = vfs_rmdir(ovl_upper_mnt_idmap(ofs), dir, dentry, NULL); pr_debug("rmdir(%pd2) = %i\n", dentry, err); return err; @@ -235,7 +235,7 @@ static inline int ovl_do_create(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, umode_t mode) { - int err = vfs_create(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, true); + int err = vfs_create(ovl_upper_mnt_idmap(ofs), dentry, mode, NULL); pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err); return err; @@ -248,7 +248,7 @@ static inline struct dentry *ovl_do_mkdir(struct ovl_fs *ofs, { struct dentry *ret; - ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode); + ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, NULL); pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(ret)); return ret; } @@ -257,7 +257,7 @@ static inline int ovl_do_mknod(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { - int err = vfs_mknod(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, dev); + int err = vfs_mknod(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, dev, NULL); pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", dentry, mode, dev, err); return err; @@ -267,7 +267,7 @@ static inline int ovl_do_symlink(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, const char *oldname) { - int err = vfs_symlink(ovl_upper_mnt_idmap(ofs), dir, dentry, oldname); + int err = vfs_symlink(ovl_upper_mnt_idmap(ofs), dir, dentry, oldname, NULL); pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err); return err; @@ -355,11 +355,24 @@ static inline int ovl_do_remove_acl(struct ovl_fs *ofs, struct dentry *dentry, return vfs_remove_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name); } +static inline int ovl_do_rename_rd(struct renamedata *rd) +{ + int err; + + pr_debug("rename(%pd2, %pd2, 0x%x)\n", rd->old_dentry, rd->new_dentry, + rd->flags); + err = vfs_rename(rd); + if (err) { + pr_debug("...rename(%pd2, %pd2, ...) = %i\n", + rd->old_dentry, rd->new_dentry, err); + } + return err; +} + static inline int ovl_do_rename(struct ovl_fs *ofs, struct dentry *olddir, struct dentry *olddentry, struct dentry *newdir, struct dentry *newdentry, unsigned int flags) { - int err; struct renamedata rd = { .mnt_idmap = ovl_upper_mnt_idmap(ofs), .old_parent = olddir, @@ -369,13 +382,7 @@ static inline int ovl_do_rename(struct ovl_fs *ofs, struct dentry *olddir, .flags = flags, }; - pr_debug("rename(%pd2, %pd2, 0x%x)\n", olddentry, newdentry, flags); - err = vfs_rename(&rd); - if (err) { - pr_debug("...rename(%pd2, %pd2, ...) = %i\n", - olddentry, newdentry, err); - } - return err; + return ovl_do_rename_rd(&rd); } static inline int ovl_do_whiteout(struct ovl_fs *ofs, @@ -415,6 +422,22 @@ static inline struct dentry *ovl_lookup_upper_unlocked(struct ovl_fs *ofs, &QSTR_LEN(name, len), base); } +static inline struct dentry *ovl_start_creating_upper(struct ovl_fs *ofs, + struct dentry *parent, + struct qstr *name) +{ + return start_creating(ovl_upper_mnt_idmap(ofs), + parent, name); +} + +static inline struct dentry *ovl_start_removing_upper(struct ovl_fs *ofs, + struct dentry *parent, + struct qstr *name) +{ + return start_removing(ovl_upper_mnt_idmap(ofs), + parent, name); +} + static inline bool ovl_open_flags_need_copy_up(int flags) { if (!flags) @@ -424,11 +447,6 @@ static inline bool ovl_open_flags_need_copy_up(int flags) } /* util.c */ -int ovl_parent_lock(struct dentry *parent, struct dentry *child); -static inline void ovl_parent_unlock(struct dentry *parent) -{ - inode_unlock(parent->d_inode); -} int ovl_get_write_access(struct dentry *dentry); void ovl_put_write_access(struct dentry *dentry); void ovl_start_write(struct dentry *dentry); @@ -437,7 +455,11 @@ int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); struct dentry *ovl_workdir(struct dentry *dentry); const struct cred *ovl_override_creds(struct super_block *sb); -void ovl_revert_creds(const struct cred *old_cred); + +EXTEND_CLASS(override_creds, _ovl, ovl_override_creds(sb), struct super_block *sb) + +#define with_ovl_creds(sb) \ + scoped_class(override_creds_ovl, __UNIQUE_ID(label), sb) static inline const struct cred *ovl_creds(struct super_block *sb) { @@ -865,7 +887,8 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent, struct dentry *newdentry, struct ovl_cattr *attr); int ovl_cleanup(struct ovl_fs *ofs, struct dentry *workdir, struct dentry *dentry); -struct dentry *ovl_lookup_temp(struct ovl_fs *ofs, struct dentry *workdir); +#define OVL_TEMPNAME_SIZE 20 +void ovl_tempname(char name[OVL_TEMPNAME_SIZE]); struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir, struct ovl_cattr *attr); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 1e9792cc557b..160960bb0ad0 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -348,11 +348,7 @@ static bool ovl_fill_merge(struct dir_context *ctx, const char *name, static int ovl_check_whiteouts(const struct path *path, struct ovl_readdir_data *rdd) { - int err = 0; struct dentry *dentry, *dir = path->dentry; - const struct cred *old_cred; - - old_cred = ovl_override_creds(rdd->dentry->d_sb); while (rdd->first_maybe_whiteout) { struct ovl_cache_entry *p = @@ -365,13 +361,11 @@ static int ovl_check_whiteouts(const struct path *path, struct ovl_readdir_data p->is_whiteout = ovl_is_whiteout(dentry); dput(dentry); } else if (PTR_ERR(dentry) == -EINTR) { - err = -EINTR; - break; + return -EINTR; } } - ovl_revert_creds(old_cred); - return err; + return 0; } static inline int ovl_dir_read(const struct path *realpath, @@ -838,36 +832,12 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx) return err; } - -static int ovl_iterate(struct file *file, struct dir_context *ctx) +static int ovl_iterate_merged(struct file *file, struct dir_context *ctx) { struct ovl_dir_file *od = file->private_data; struct dentry *dentry = file->f_path.dentry; - struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct ovl_cache_entry *p; - const struct cred *old_cred; - int err; - - old_cred = ovl_override_creds(dentry->d_sb); - if (!ctx->pos) - ovl_dir_reset(file); - - if (od->is_real) { - /* - * If parent is merge, then need to adjust d_ino for '..', if - * dir is impure then need to adjust d_ino for copied up - * entries. - */ - if (ovl_xino_bits(ofs) || - (ovl_same_fs(ofs) && - (ovl_is_impure_dir(file) || - OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) { - err = ovl_iterate_real(file, ctx); - } else { - err = iterate_dir(od->realfile, ctx); - } - goto out; - } + int err = 0; if (!od->cache) { struct ovl_dir_cache *cache; @@ -875,7 +845,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) cache = ovl_cache_get(dentry); err = PTR_ERR(cache); if (IS_ERR(cache)) - goto out; + return err; od->cache = cache; ovl_seek_cursor(od, ctx->pos); @@ -887,7 +857,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) if (!p->ino || p->check_xwhiteout) { err = ovl_cache_update(&file->f_path, p, !p->ino); if (err) - goto out; + return err; } } /* ovl_cache_update() sets is_whiteout on stale entry */ @@ -898,12 +868,50 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) od->cursor = p->l_node.next; ctx->pos++; } - err = 0; -out: - ovl_revert_creds(old_cred); return err; } +static bool ovl_need_adjust_d_ino(struct file *file) +{ + struct dentry *dentry = file->f_path.dentry; + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + + /* If parent is merge, then need to adjust d_ino for '..' */ + if (ovl_xino_bits(ofs)) + return true; + + /* Can't do consistent inode numbering */ + if (!ovl_same_fs(ofs)) + return false; + + /* If dir is impure then need to adjust d_ino for copied up entries */ + if (ovl_is_impure_dir(file) || + OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))) + return true; + + /* Pure: no need to adjust d_ino */ + return false; +} + + +static int ovl_iterate(struct file *file, struct dir_context *ctx) +{ + struct ovl_dir_file *od = file->private_data; + + if (!ctx->pos) + ovl_dir_reset(file); + + with_ovl_creds(file_dentry(file)->d_sb) { + if (!od->is_real) + return ovl_iterate_merged(file, ctx); + + if (ovl_need_adjust_d_ino(file)) + return ovl_iterate_real(file, ctx); + + return iterate_dir(od->realfile, ctx); + } +} + static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin) { loff_t res; @@ -947,14 +955,8 @@ out_unlock: static struct file *ovl_dir_open_realfile(const struct file *file, const struct path *realpath) { - struct file *res; - const struct cred *old_cred; - - old_cred = ovl_override_creds(file_inode(file)->i_sb); - res = ovl_path_open(realpath, O_RDONLY | (file->f_flags & O_LARGEFILE)); - ovl_revert_creds(old_cred); - - return res; + with_ovl_creds(file_inode(file)->i_sb) + return ovl_path_open(realpath, O_RDONLY | (file->f_flags & O_LARGEFILE)); } /* @@ -1075,11 +1077,9 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list) int err; struct ovl_cache_entry *p, *n; struct rb_root root = RB_ROOT; - const struct cred *old_cred; - old_cred = ovl_override_creds(dentry->d_sb); - err = ovl_dir_read_merged(dentry, list, &root); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) + err = ovl_dir_read_merged(dentry, list, &root); if (err) return err; @@ -1242,11 +1242,11 @@ int ovl_workdir_cleanup(struct ovl_fs *ofs, struct dentry *parent, if (!d_is_dir(dentry) || level > 1) return ovl_cleanup(ofs, parent, dentry); - err = ovl_parent_lock(parent, dentry); - if (err) - return err; + dentry = start_removing_dentry(parent, dentry); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); err = ovl_do_rmdir(ofs, parent->d_inode, dentry); - ovl_parent_unlock(parent); + end_removing(dentry); if (err) { struct path path = { .mnt = mnt, .dentry = dentry }; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 43ee4c7296a7..28b2f707cfbc 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -310,8 +310,7 @@ static struct dentry *ovl_workdir_create(struct ovl_fs *ofs, bool retried = false; retry: - inode_lock_nested(dir, I_MUTEX_PARENT); - work = ovl_lookup_upper(ofs, name, ofs->workbasedir, strlen(name)); + work = ovl_start_creating_upper(ofs, ofs->workbasedir, &QSTR(name)); if (!IS_ERR(work)) { struct iattr attr = { @@ -320,14 +319,12 @@ retry: }; if (work->d_inode) { + end_creating_keep(work); + if (persist) + return work; err = -EEXIST; - inode_unlock(dir); if (retried) goto out_dput; - - if (persist) - return work; - retried = true; err = ovl_workdir_cleanup(ofs, ofs->workbasedir, mnt, work, 0); dput(work); @@ -338,7 +335,7 @@ retry: } work = ovl_do_mkdir(ofs, dir, work, attr.ia_mode); - inode_unlock(dir); + end_creating_keep(work); err = PTR_ERR(work); if (IS_ERR(work)) goto out_err; @@ -376,7 +373,6 @@ retry: if (err) goto out_dput; } else { - inode_unlock(dir); err = PTR_ERR(work); goto out_err; } @@ -567,9 +563,10 @@ static int ovl_check_rename_whiteout(struct ovl_fs *ofs) { struct dentry *workdir = ofs->workdir; struct dentry *temp; - struct dentry *dest; struct dentry *whiteout; struct name_snapshot name; + struct renamedata rd = {}; + char name2[OVL_TEMPNAME_SIZE]; int err; temp = ovl_create_temp(ofs, workdir, OVL_CATTR(S_IFREG | 0)); @@ -577,23 +574,21 @@ static int ovl_check_rename_whiteout(struct ovl_fs *ofs) if (IS_ERR(temp)) return err; - err = ovl_parent_lock(workdir, temp); + rd.mnt_idmap = ovl_upper_mnt_idmap(ofs); + rd.old_parent = workdir; + rd.new_parent = workdir; + rd.flags = RENAME_WHITEOUT; + ovl_tempname(name2); + err = start_renaming_dentry(&rd, 0, temp, &QSTR(name2)); if (err) { dput(temp); return err; } - dest = ovl_lookup_temp(ofs, workdir); - err = PTR_ERR(dest); - if (IS_ERR(dest)) { - dput(temp); - ovl_parent_unlock(workdir); - return err; - } /* Name is inline and stable - using snapshot as a copy helper */ take_dentry_name_snapshot(&name, temp); - err = ovl_do_rename(ofs, workdir, temp, workdir, dest, RENAME_WHITEOUT); - ovl_parent_unlock(workdir); + err = ovl_do_rename_rd(&rd); + end_renaming(&rd); if (err) { if (err == -EINVAL) err = 0; @@ -617,7 +612,6 @@ cleanup_temp: ovl_cleanup(ofs, workdir, temp); release_dentry_name_snapshot(&name); dput(temp); - dput(dest); return err; } @@ -626,14 +620,15 @@ static struct dentry *ovl_lookup_or_create(struct ovl_fs *ofs, struct dentry *parent, const char *name, umode_t mode) { - size_t len = strlen(name); struct dentry *child; - inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); - child = ovl_lookup_upper(ofs, name, parent, len); - if (!IS_ERR(child) && !child->d_inode) - child = ovl_create_real(ofs, parent, child, OVL_CATTR(mode)); - inode_unlock(parent->d_inode); + child = ovl_start_creating_upper(ofs, parent, &QSTR(name)); + if (!IS_ERR(child)) { + if (!child->d_inode) + child = ovl_create_real(ofs, parent, child, + OVL_CATTR(mode)); + end_creating_keep(child); + } dput(parent); return child; @@ -1369,53 +1364,35 @@ static void ovl_set_d_op(struct super_block *sb) set_default_d_op(sb, &ovl_dentry_operations); } -int ovl_fill_super(struct super_block *sb, struct fs_context *fc) +static int ovl_fill_super_creds(struct fs_context *fc, struct super_block *sb) { struct ovl_fs *ofs = sb->s_fs_info; + struct cred *creator_cred = (struct cred *)ofs->creator_cred; struct ovl_fs_context *ctx = fc->fs_private; - const struct cred *old_cred = NULL; - struct dentry *root_dentry; - struct ovl_entry *oe; struct ovl_layer *layers; - struct cred *cred; + struct ovl_entry *oe = NULL; int err; - err = -EIO; - if (WARN_ON(fc->user_ns != current_user_ns())) - goto out_err; - - ovl_set_d_op(sb); - - err = -ENOMEM; - if (!ofs->creator_cred) - ofs->creator_cred = cred = prepare_creds(); - else - cred = (struct cred *)ofs->creator_cred; - if (!cred) - goto out_err; - - old_cred = ovl_override_creds(sb); - err = ovl_fs_params_verify(ctx, &ofs->config); if (err) - goto out_err; + return err; err = -EINVAL; if (ctx->nr == 0) { if (!(fc->sb_flags & SB_SILENT)) pr_err("missing 'lowerdir'\n"); - goto out_err; + return err; } err = -ENOMEM; layers = kcalloc(ctx->nr + 1, sizeof(struct ovl_layer), GFP_KERNEL); if (!layers) - goto out_err; + return err; ofs->config.lowerdirs = kcalloc(ctx->nr + 1, sizeof(char *), GFP_KERNEL); if (!ofs->config.lowerdirs) { kfree(layers); - goto out_err; + return err; } ofs->layers = layers; /* @@ -1448,12 +1425,12 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) err = -EINVAL; if (!ofs->config.workdir) { pr_err("missing 'workdir'\n"); - goto out_err; + return err; } err = ovl_get_upper(sb, ofs, &layers[0], &ctx->upper); if (err) - goto out_err; + return err; upper_sb = ovl_upper_mnt(ofs)->mnt_sb; if (!ovl_should_sync(ofs)) { @@ -1461,13 +1438,13 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) { err = -EIO; pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n"); - goto out_err; + return err; } } err = ovl_get_workdir(sb, ofs, &ctx->upper, &ctx->work); if (err) - goto out_err; + return err; if (!ofs->workdir) sb->s_flags |= SB_RDONLY; @@ -1478,7 +1455,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) oe = ovl_get_lowerstack(sb, ctx, ofs, layers); err = PTR_ERR(oe); if (IS_ERR(oe)) - goto out_err; + return err; /* If the upper fs is nonexistent, we mark overlayfs r/o too */ if (!ovl_upper_mnt(ofs)) @@ -1531,7 +1508,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_export_op = &ovl_export_fid_operations; /* Never override disk quota limits or use reserved space */ - cap_lower(cred->cap_effective, CAP_SYS_RESOURCE); + cap_lower(creator_cred->cap_effective, CAP_SYS_RESOURCE); sb->s_magic = OVERLAYFS_SUPER_MAGIC; sb->s_xattr = ovl_xattr_handlers(ofs); @@ -1549,27 +1526,44 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_iflags |= SB_I_EVM_HMAC_UNSUPPORTED; err = -ENOMEM; - root_dentry = ovl_get_root(sb, ctx->upper.dentry, oe); - if (!root_dentry) + sb->s_root = ovl_get_root(sb, ctx->upper.dentry, oe); + if (!sb->s_root) goto out_free_oe; - sb->s_root = root_dentry; - - ovl_revert_creds(old_cred); return 0; out_free_oe: ovl_free_entry(oe); + return err; +} + +int ovl_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct ovl_fs *ofs = sb->s_fs_info; + int err; + + err = -EIO; + if (WARN_ON(fc->user_ns != current_user_ns())) + goto out_err; + + ovl_set_d_op(sb); + + if (!ofs->creator_cred) { + err = -ENOMEM; + ofs->creator_cred = prepare_creds(); + if (!ofs->creator_cred) + goto out_err; + } + + with_ovl_creds(sb) + err = ovl_fill_super_creds(fc, sb); + out_err: - /* - * Revert creds before calling ovl_free_fs() which will call - * put_cred() and put_cred() requires that the cred's that are - * put are not the caller's creds, i.e., current->cred. - */ - if (old_cred) - ovl_revert_creds(old_cred); - ovl_free_fs(ofs); - sb->s_fs_info = NULL; + if (err) { + ovl_free_fs(ofs); + sb->s_fs_info = NULL; + } + return err; } diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index f76672f2e686..94986d11a166 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -69,11 +69,6 @@ const struct cred *ovl_override_creds(struct super_block *sb) return override_creds(ofs->creator_cred); } -void ovl_revert_creds(const struct cred *old_cred) -{ - revert_creds(old_cred); -} - /* * Check if underlying fs supports file handles and try to determine encoding * type, in order to deduce maximum inode number used by fs. @@ -1019,8 +1014,8 @@ bool ovl_inuse_trylock(struct dentry *dentry) bool locked = false; spin_lock(&inode->i_lock); - if (!(inode->i_state & I_OVL_INUSE)) { - inode->i_state |= I_OVL_INUSE; + if (!(inode_state_read(inode) & I_OVL_INUSE)) { + inode_state_set(inode, I_OVL_INUSE); locked = true; } spin_unlock(&inode->i_lock); @@ -1034,8 +1029,8 @@ void ovl_inuse_unlock(struct dentry *dentry) struct inode *inode = d_inode(dentry); spin_lock(&inode->i_lock); - WARN_ON(!(inode->i_state & I_OVL_INUSE)); - inode->i_state &= ~I_OVL_INUSE; + WARN_ON(!(inode_state_read(inode) & I_OVL_INUSE)); + inode_state_clear(inode, I_OVL_INUSE); spin_unlock(&inode->i_lock); } } @@ -1046,7 +1041,7 @@ bool ovl_is_inuse(struct dentry *dentry) bool inuse; spin_lock(&inode->i_lock); - inuse = (inode->i_state & I_OVL_INUSE); + inuse = (inode_state_read(inode) & I_OVL_INUSE); spin_unlock(&inode->i_lock); return inuse; @@ -1147,7 +1142,6 @@ fail: int ovl_nlink_start(struct dentry *dentry) { struct inode *inode = d_inode(dentry); - const struct cred *old_cred; int err; if (WARN_ON(!inode)) @@ -1184,15 +1178,14 @@ int ovl_nlink_start(struct dentry *dentry) if (d_is_dir(dentry) || !ovl_test_flag(OVL_INDEX, inode)) return 0; - old_cred = ovl_override_creds(dentry->d_sb); /* * The overlay inode nlink should be incremented/decremented IFF the * upper operation succeeds, along with nlink change of upper inode. * Therefore, before link/unlink/rename, we store the union nlink * value relative to the upper inode nlink in an upper inode xattr. */ - err = ovl_set_nlink_upper(dentry); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) + err = ovl_set_nlink_upper(dentry); if (err) goto out_drop_write; @@ -1213,11 +1206,8 @@ void ovl_nlink_end(struct dentry *dentry) ovl_drop_write(dentry); if (ovl_test_flag(OVL_INDEX, inode) && inode->i_nlink == 0) { - const struct cred *old_cred; - - old_cred = ovl_override_creds(dentry->d_sb); - ovl_cleanup_index(dentry); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) + ovl_cleanup_index(dentry); } ovl_inode_unlock(inode); @@ -1234,9 +1224,9 @@ int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *work, goto err; if (trap) goto err_unlock; - if (work && work->d_parent != workdir) + if (work && (work->d_parent != workdir || d_unhashed(work))) goto err_unlock; - if (upper && upper->d_parent != upperdir) + if (upper && (upper->d_parent != upperdir || d_unhashed(upper))) goto err_unlock; return 0; @@ -1548,14 +1538,3 @@ void ovl_copyattr(struct inode *inode) i_size_write(inode, i_size_read(realinode)); spin_unlock(&inode->i_lock); } - -int ovl_parent_lock(struct dentry *parent, struct dentry *child) -{ - inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); - if (!child || - (!d_unhashed(child) && child->d_parent == parent)) - return 0; - - inode_unlock(parent->d_inode); - return -EINVAL; -} diff --git a/fs/overlayfs/xattrs.c b/fs/overlayfs/xattrs.c index 88055deca936..aa95855c7023 100644 --- a/fs/overlayfs/xattrs.c +++ b/fs/overlayfs/xattrs.c @@ -41,13 +41,11 @@ static int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char struct dentry *upperdentry = ovl_i_dentry_upper(inode); struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry); struct path realpath; - const struct cred *old_cred; if (!value && !upperdentry) { ovl_path_lower(dentry, &realpath); - old_cred = ovl_override_creds(dentry->d_sb); - err = vfs_getxattr(mnt_idmap(realpath.mnt), realdentry, name, NULL, 0); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) + err = vfs_getxattr(mnt_idmap(realpath.mnt), realdentry, name, NULL, 0); if (err < 0) goto out; } @@ -64,15 +62,14 @@ static int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char if (err) goto out; - old_cred = ovl_override_creds(dentry->d_sb); - if (value) { - err = ovl_do_setxattr(ofs, realdentry, name, value, size, - flags); - } else { - WARN_ON(flags != XATTR_REPLACE); - err = ovl_do_removexattr(ofs, realdentry, name); + with_ovl_creds(dentry->d_sb) { + if (value) { + err = ovl_do_setxattr(ofs, realdentry, name, value, size, flags); + } else { + WARN_ON(flags != XATTR_REPLACE); + err = ovl_do_removexattr(ofs, realdentry, name); + } } - ovl_revert_creds(old_cred); ovl_drop_write(dentry); /* copy c/mtime */ @@ -84,15 +81,11 @@ out: static int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { - ssize_t res; - const struct cred *old_cred; struct path realpath; ovl_i_path_real(inode, &realpath); - old_cred = ovl_override_creds(dentry->d_sb); - res = vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size); - ovl_revert_creds(old_cred); - return res; + with_ovl_creds(dentry->d_sb) + return vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size); } static bool ovl_can_list(struct super_block *sb, const char *s) @@ -116,12 +109,10 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) ssize_t res; size_t len; char *s; - const struct cred *old_cred; size_t prefix_len, name_len; - old_cred = ovl_override_creds(dentry->d_sb); - res = vfs_listxattr(realdentry, list, size); - ovl_revert_creds(old_cred); + with_ovl_creds(dentry->d_sb) + res = vfs_listxattr(realdentry, list, size); if (res <= 0 || size == 0) return res; diff --git a/fs/pidfs.c b/fs/pidfs.c index 0ef5b47d796a..dba703d4ce4a 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -39,20 +39,20 @@ void pidfs_get_root(struct path *path) path_get(path); } -/* - * Stashes information that userspace needs to access even after the - * process has been reaped. - */ -struct pidfs_exit_info { - __u64 cgroupid; - __s32 exit_code; - __u32 coredump_mask; +enum pidfs_attr_mask_bits { + PIDFS_ATTR_BIT_EXIT = 0, + PIDFS_ATTR_BIT_COREDUMP = 1, }; struct pidfs_attr { + unsigned long attr_mask; struct simple_xattrs *xattrs; - struct pidfs_exit_info __pei; - struct pidfs_exit_info *exit_info; + struct /* exit info */ { + __u64 cgroupid; + __s32 exit_code; + }; + __u32 coredump_mask; + __u32 coredump_signal; }; static struct rb_root pidfs_ino_tree = RB_ROOT; @@ -293,6 +293,15 @@ static __u32 pidfs_coredump_mask(unsigned long mm_flags) return 0; } +/* This must be updated whenever a new flag is added */ +#define PIDFD_INFO_SUPPORTED (PIDFD_INFO_PID | \ + PIDFD_INFO_CREDS | \ + PIDFD_INFO_CGROUPID | \ + PIDFD_INFO_EXIT | \ + PIDFD_INFO_COREDUMP | \ + PIDFD_INFO_SUPPORTED_MASK | \ + PIDFD_INFO_COREDUMP_SIGNAL) + static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) { struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg; @@ -300,12 +309,13 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) struct pid *pid = pidfd_pid(file); size_t usize = _IOC_SIZE(cmd); struct pidfd_info kinfo = {}; - struct pidfs_exit_info *exit_info; struct user_namespace *user_ns; struct pidfs_attr *attr; const struct cred *c; __u64 mask; + BUILD_BUG_ON(sizeof(struct pidfd_info) != PIDFD_INFO_SIZE_VER2); + if (!uinfo) return -EINVAL; if (usize < PIDFD_INFO_SIZE_VER0) @@ -323,20 +333,24 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) attr = READ_ONCE(pid->attr); if (mask & PIDFD_INFO_EXIT) { - exit_info = READ_ONCE(attr->exit_info); - if (exit_info) { + if (test_bit(PIDFS_ATTR_BIT_EXIT, &attr->attr_mask)) { + smp_rmb(); kinfo.mask |= PIDFD_INFO_EXIT; #ifdef CONFIG_CGROUPS - kinfo.cgroupid = exit_info->cgroupid; + kinfo.cgroupid = attr->cgroupid; kinfo.mask |= PIDFD_INFO_CGROUPID; #endif - kinfo.exit_code = exit_info->exit_code; + kinfo.exit_code = attr->exit_code; } } if (mask & PIDFD_INFO_COREDUMP) { - kinfo.mask |= PIDFD_INFO_COREDUMP; - kinfo.coredump_mask = READ_ONCE(attr->__pei.coredump_mask); + if (test_bit(PIDFS_ATTR_BIT_COREDUMP, &attr->attr_mask)) { + smp_rmb(); + kinfo.mask |= PIDFD_INFO_COREDUMP | PIDFD_INFO_COREDUMP_SIGNAL; + kinfo.coredump_mask = attr->coredump_mask; + kinfo.coredump_signal = attr->coredump_signal; + } } task = get_pid_task(pid, PIDTYPE_PID); @@ -355,14 +369,15 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) if (!c) return -ESRCH; - if ((kinfo.mask & PIDFD_INFO_COREDUMP) && !(kinfo.coredump_mask)) { - task_lock(task); + if ((mask & PIDFD_INFO_COREDUMP) && !kinfo.coredump_mask) { + guard(task_lock)(task); if (task->mm) { unsigned long flags = __mm_flags_get_dumpable(task->mm); kinfo.coredump_mask = pidfs_coredump_mask(flags); + kinfo.mask |= PIDFD_INFO_COREDUMP; + /* No coredump actually took place, so no coredump signal. */ } - task_unlock(task); } /* Unconditionally return identifiers and credentials, the rest only on request */ @@ -409,6 +424,13 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) return -ESRCH; copy_out: + if (mask & PIDFD_INFO_SUPPORTED_MASK) { + kinfo.mask |= PIDFD_INFO_SUPPORTED_MASK; + kinfo.supported_mask = PIDFD_INFO_SUPPORTED; + } + + /* Are there bits in the return mask not present in PIDFD_INFO_SUPPORTED? */ + WARN_ON_ONCE(~PIDFD_INFO_SUPPORTED & kinfo.mask); /* * If userspace and the kernel have the same struct size it can just * be copied. If userspace provides an older struct, only the bits that @@ -454,7 +476,6 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct task_struct *task __free(put_task) = NULL; struct nsproxy *nsp __free(put_nsproxy) = NULL; struct ns_common *ns_common = NULL; - struct pid_namespace *pid_ns; if (!pidfs_ioctl_valid(cmd)) return -ENOIOCTLCMD; @@ -496,66 +517,64 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) switch (cmd) { /* Namespaces that hang of nsproxy. */ case PIDFD_GET_CGROUP_NAMESPACE: - if (IS_ENABLED(CONFIG_CGROUPS)) { - get_cgroup_ns(nsp->cgroup_ns); - ns_common = to_ns_common(nsp->cgroup_ns); - } + if (!ns_ref_get(nsp->cgroup_ns)) + break; + ns_common = to_ns_common(nsp->cgroup_ns); break; case PIDFD_GET_IPC_NAMESPACE: - if (IS_ENABLED(CONFIG_IPC_NS)) { - get_ipc_ns(nsp->ipc_ns); - ns_common = to_ns_common(nsp->ipc_ns); - } + if (!ns_ref_get(nsp->ipc_ns)) + break; + ns_common = to_ns_common(nsp->ipc_ns); break; case PIDFD_GET_MNT_NAMESPACE: - get_mnt_ns(nsp->mnt_ns); + if (!ns_ref_get(nsp->mnt_ns)) + break; ns_common = to_ns_common(nsp->mnt_ns); break; case PIDFD_GET_NET_NAMESPACE: - if (IS_ENABLED(CONFIG_NET_NS)) { - ns_common = to_ns_common(nsp->net_ns); - get_net_ns(ns_common); - } + if (!ns_ref_get(nsp->net_ns)) + break; + ns_common = to_ns_common(nsp->net_ns); break; case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE: - if (IS_ENABLED(CONFIG_PID_NS)) { - get_pid_ns(nsp->pid_ns_for_children); - ns_common = to_ns_common(nsp->pid_ns_for_children); - } + if (!ns_ref_get(nsp->pid_ns_for_children)) + break; + ns_common = to_ns_common(nsp->pid_ns_for_children); break; case PIDFD_GET_TIME_NAMESPACE: - if (IS_ENABLED(CONFIG_TIME_NS)) { - get_time_ns(nsp->time_ns); - ns_common = to_ns_common(nsp->time_ns); - } + if (!ns_ref_get(nsp->time_ns)) + break; + ns_common = to_ns_common(nsp->time_ns); break; case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE: - if (IS_ENABLED(CONFIG_TIME_NS)) { - get_time_ns(nsp->time_ns_for_children); - ns_common = to_ns_common(nsp->time_ns_for_children); - } + if (!ns_ref_get(nsp->time_ns_for_children)) + break; + ns_common = to_ns_common(nsp->time_ns_for_children); break; case PIDFD_GET_UTS_NAMESPACE: - if (IS_ENABLED(CONFIG_UTS_NS)) { - get_uts_ns(nsp->uts_ns); - ns_common = to_ns_common(nsp->uts_ns); - } + if (!ns_ref_get(nsp->uts_ns)) + break; + ns_common = to_ns_common(nsp->uts_ns); break; /* Namespaces that don't hang of nsproxy. */ case PIDFD_GET_USER_NAMESPACE: - if (IS_ENABLED(CONFIG_USER_NS)) { - rcu_read_lock(); - ns_common = to_ns_common(get_user_ns(task_cred_xxx(task, user_ns))); - rcu_read_unlock(); + scoped_guard(rcu) { + struct user_namespace *user_ns; + + user_ns = task_cred_xxx(task, user_ns); + if (!ns_ref_get(user_ns)) + break; + ns_common = to_ns_common(user_ns); } break; case PIDFD_GET_PID_NAMESPACE: - if (IS_ENABLED(CONFIG_PID_NS)) { - rcu_read_lock(); + scoped_guard(rcu) { + struct pid_namespace *pid_ns; + pid_ns = task_active_pid_ns(task); - if (pid_ns) - ns_common = to_ns_common(get_pid_ns(pid_ns)); - rcu_read_unlock(); + if (!ns_ref_get(pid_ns)) + break; + ns_common = to_ns_common(pid_ns); } break; default: @@ -606,24 +625,25 @@ void pidfs_exit(struct task_struct *tsk) { struct pid *pid = task_pid(tsk); struct pidfs_attr *attr; - struct pidfs_exit_info *exit_info; #ifdef CONFIG_CGROUPS struct cgroup *cgrp; #endif might_sleep(); - guard(spinlock_irq)(&pid->wait_pidfd.lock); - attr = pid->attr; - if (!attr) { - /* - * No one ever held a pidfd for this struct pid. - * Mark it as dead so no one can add a pidfs - * entry anymore. We're about to be reaped and - * so no exit information would be available. - */ - pid->attr = PIDFS_PID_DEAD; - return; + /* Synchronize with pidfs_register_pid(). */ + scoped_guard(spinlock_irq, &pid->wait_pidfd.lock) { + attr = pid->attr; + if (!attr) { + /* + * No one ever held a pidfd for this struct pid. + * Mark it as dead so no one can add a pidfs + * entry anymore. We're about to be reaped and + * so no exit information would be available. + */ + pid->attr = PIDFS_PID_DEAD; + return; + } } /* @@ -634,41 +654,39 @@ void pidfs_exit(struct task_struct *tsk) * is put */ - exit_info = &attr->__pei; - #ifdef CONFIG_CGROUPS rcu_read_lock(); cgrp = task_dfl_cgroup(tsk); - exit_info->cgroupid = cgroup_id(cgrp); + attr->cgroupid = cgroup_id(cgrp); rcu_read_unlock(); #endif - exit_info->exit_code = tsk->exit_code; + attr->exit_code = tsk->exit_code; /* Ensure that PIDFD_GET_INFO sees either all or nothing. */ - smp_store_release(&attr->exit_info, &attr->__pei); + smp_wmb(); + set_bit(PIDFS_ATTR_BIT_EXIT, &attr->attr_mask); } #ifdef CONFIG_COREDUMP void pidfs_coredump(const struct coredump_params *cprm) { struct pid *pid = cprm->pid; - struct pidfs_exit_info *exit_info; struct pidfs_attr *attr; - __u32 coredump_mask = 0; attr = READ_ONCE(pid->attr); VFS_WARN_ON_ONCE(!attr); VFS_WARN_ON_ONCE(attr == PIDFS_PID_DEAD); - exit_info = &attr->__pei; - /* Note how we were coredumped. */ - coredump_mask = pidfs_coredump_mask(cprm->mm_flags); - /* Note that we actually did coredump. */ - coredump_mask |= PIDFD_COREDUMPED; + /* Note how we were coredumped and that we coredumped. */ + attr->coredump_mask = pidfs_coredump_mask(cprm->mm_flags) | + PIDFD_COREDUMPED; /* If coredumping is set to skip we should never end up here. */ - VFS_WARN_ON_ONCE(coredump_mask & PIDFD_COREDUMP_SKIP); - smp_store_release(&exit_info->coredump_mask, coredump_mask); + VFS_WARN_ON_ONCE(attr->coredump_mask & PIDFD_COREDUMP_SKIP); + /* Expose the signal number that caused the coredump. */ + attr->coredump_signal = cprm->siginfo->si_signo; + smp_wmb(); + set_bit(PIDFS_ATTR_BIT_COREDUMP, &attr->attr_mask); } #endif @@ -1022,6 +1040,7 @@ static int pidfs_init_fs_context(struct fs_context *fc) fc->s_iflags |= SB_I_NOEXEC; fc->s_iflags |= SB_I_NODEV; + ctx->s_d_flags |= DCACHE_DONTCACHE; ctx->ops = &pidfs_sops; ctx->eops = &pidfs_export_operations; ctx->dops = &pidfs_dentry_operations; diff --git a/fs/pipe.c b/fs/pipe.c index 42fead1efe52..2d0fed2ecbfd 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -908,7 +908,7 @@ static struct inode * get_pipe_inode(void) * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ - inode->i_state = I_DIRTY; + inode_state_assign_raw(inode, I_DIRTY); inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 4050942ab52f..768f027c1428 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -1091,7 +1091,7 @@ int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, int acl_type; int error; struct inode *inode = d_inode(dentry); - struct inode *delegated_inode = NULL; + struct delegated_inode delegated_inode = { }; acl_type = posix_acl_type(acl_name); if (acl_type < 0) @@ -1141,7 +1141,7 @@ retry_deleg: out_inode_unlock: inode_unlock(inode); - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; @@ -1212,7 +1212,7 @@ int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, int acl_type; int error; struct inode *inode = d_inode(dentry); - struct inode *delegated_inode = NULL; + struct delegated_inode delegated_inode = { }; acl_type = posix_acl_type(acl_name); if (acl_type < 0) @@ -1249,7 +1249,7 @@ retry_deleg: out_inode_unlock: inode_unlock(inode); - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; diff --git a/fs/proc/array.c b/fs/proc/array.c index 2ae63189091e..cbd4bc4a58e4 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -481,7 +481,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, unsigned long flags; int exit_code = task->exit_code; struct signal_struct *sig = task->signal; - unsigned int seq = 1; state = *get_task_state(task); vsize = eip = esp = 0; @@ -538,10 +537,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (permitted && (!whole || num_threads < 2)) wchan = !task_is_running(task); - do { - seq++; /* 2 on the 1st/lockless path, otherwise odd */ - flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); - + scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) { cmin_flt = sig->cmin_flt; cmaj_flt = sig->cmaj_flt; cutime = sig->cutime; @@ -563,8 +559,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, } rcu_read_unlock(); } - } while (need_seqretry(&sig->stats_lock, seq)); - done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + } if (whole) { thread_group_cputime_adjusted(task, &utime, &stime); diff --git a/fs/proc/base.c b/fs/proc/base.c index 6299878e3d97..407b41cb6e7c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3043,21 +3043,14 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh if (whole) { struct signal_struct *sig = task->signal; struct task_struct *t; - unsigned int seq = 1; - unsigned long flags; - - rcu_read_lock(); - do { - seq++; /* 2 on the 1st/lockless path, otherwise odd */ - flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + guard(rcu)(); + scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) { acct = sig->ioac; __for_each_thread(sig, t) task_io_accounting_add(&acct, &t->ioac); - } while (need_seqretry(&sig->stats_lock, seq)); - done_seqretry_irqrestore(&sig->stats_lock, seq, flags); - rcu_read_unlock(); + } } else { acct = task->ioac; } diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 176281112273..501889856461 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -698,6 +698,12 @@ void pde_put(struct proc_dir_entry *pde) } } +static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent) +{ + rb_erase(&pde->subdir_node, &parent->subdir); + RB_CLEAR_NODE(&pde->subdir_node); +} + /* * Remove a /proc entry and free it if it's not currently in use. */ @@ -720,7 +726,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) WARN(1, "removing permanent /proc entry '%s'", de->name); de = NULL; } else { - rb_erase(&de->subdir_node, &parent->subdir); + pde_erase(de, parent); if (S_ISDIR(de->mode)) parent->nlink--; } @@ -764,7 +770,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) root->parent->name, root->name); return -EINVAL; } - rb_erase(&root->subdir_node, &parent->subdir); + pde_erase(root, parent); de = root; while (1) { @@ -776,7 +782,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) next->parent->name, next->name); return -EINVAL; } - rb_erase(&next->subdir_node, &de->subdir); + pde_erase(next, de); de = next; continue; } diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index e399e2dd3a12..31d78da203ea 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -290,7 +290,7 @@ struct inode *qnx4_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; qnx4_inode = qnx4_raw_inode(inode); diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 3310d1ad4d0e..88d285005083 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -521,7 +521,7 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; ei = QNX6_I(inode); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 6c4a6ee1fa2b..376739f6420e 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1033,7 +1033,7 @@ static int add_dquot_ref(struct super_block *sb, int type) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); - if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || + if ((inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) || !atomic_read(&inode->i_writecount) || !dqinit_needed(inode, type)) { spin_unlock(&inode->i_lock); diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index 0d0ef54fc4de..b2d178d3556e 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -24,7 +24,8 @@ #include "internal.h" struct rdt_parse_data { - struct rdtgroup *rdtgrp; + u32 closid; + enum rdtgrp_mode mode; char *buf; }; @@ -77,8 +78,8 @@ static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_ctrl_domain *d) { struct resctrl_staged_config *cfg; - u32 closid = data->rdtgrp->closid; struct rdt_resource *r = s->res; + u32 closid = data->closid; u32 bw_val; cfg = &d->staged_config[s->conf_type]; @@ -156,9 +157,10 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_ctrl_domain *d) { - struct rdtgroup *rdtgrp = data->rdtgrp; + enum rdtgrp_mode mode = data->mode; struct resctrl_staged_config *cfg; struct rdt_resource *r = s->res; + u32 closid = data->closid; u32 cbm_val; cfg = &d->staged_config[s->conf_type]; @@ -171,7 +173,7 @@ static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, * Cannot set up more than one pseudo-locked region in a cache * hierarchy. */ - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + if (mode == RDT_MODE_PSEUDO_LOCKSETUP && rdtgroup_pseudo_locked_in_hierarchy(d)) { rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n"); return -EINVAL; @@ -180,8 +182,7 @@ static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, if (!cbm_validate(data->buf, &cbm_val, r)) return -EINVAL; - if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE || - rdtgrp->mode == RDT_MODE_SHAREABLE) && + if ((mode == RDT_MODE_EXCLUSIVE || mode == RDT_MODE_SHAREABLE) && rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) { rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n"); return -EINVAL; @@ -191,14 +192,14 @@ static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, * The CBM may not overlap with the CBM of another closid if * either is exclusive. */ - if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) { + if (rdtgroup_cbm_overlaps(s, d, cbm_val, closid, true)) { rdt_last_cmd_puts("Overlaps with exclusive group\n"); return -EINVAL; } - if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) { - if (rdtgrp->mode == RDT_MODE_EXCLUSIVE || - rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + if (rdtgroup_cbm_overlaps(s, d, cbm_val, closid, false)) { + if (mode == RDT_MODE_EXCLUSIVE || + mode == RDT_MODE_PSEUDO_LOCKSETUP) { rdt_last_cmd_puts("Overlaps with other group\n"); return -EINVAL; } @@ -262,7 +263,8 @@ next: list_for_each_entry(d, &r->ctrl_domains, hdr.list) { if (d->hdr.id == dom_id) { data.buf = dom; - data.rdtgrp = rdtgrp; + data.closid = rdtgrp->closid; + data.mode = rdtgrp->mode; if (parse_ctrlval(&data, s, d)) return -EINVAL; if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { @@ -381,7 +383,8 @@ out: return ret ?: nbytes; } -static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) +static void show_doms(struct seq_file *s, struct resctrl_schema *schema, + char *resource_name, int closid) { struct rdt_resource *r = schema->res; struct rdt_ctrl_domain *dom; @@ -391,7 +394,8 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); - seq_printf(s, "%*s:", max_name_width, schema->name); + if (resource_name) + seq_printf(s, "%*s:", max_name_width, resource_name); list_for_each_entry(dom, &r->ctrl_domains, hdr.list) { if (sep) seq_puts(s, ";"); @@ -437,7 +441,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, closid = rdtgrp->closid; list_for_each_entry(schema, &resctrl_schema_all, list) { if (closid < schema->num_closid) - show_doms(s, schema, closid); + show_doms(s, schema, schema->name, closid); } } } else { @@ -676,3 +680,280 @@ out: rdtgroup_kn_unlock(of->kn); return ret; } + +int resctrl_io_alloc_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + mutex_lock(&rdtgroup_mutex); + + if (r->cache.io_alloc_capable) { + if (resctrl_arch_get_io_alloc_enabled(r)) + seq_puts(seq, "enabled\n"); + else + seq_puts(seq, "disabled\n"); + } else { + seq_puts(seq, "not supported\n"); + } + + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +/* + * resctrl_io_alloc_closid_supported() - io_alloc feature utilizes the + * highest CLOSID value to direct I/O traffic. Ensure that io_alloc_closid + * is in the supported range. + */ +static bool resctrl_io_alloc_closid_supported(u32 io_alloc_closid) +{ + return io_alloc_closid < closids_supported(); +} + +/* + * Initialize io_alloc CLOSID cache resource CBM with all usable (shared + * and unused) cache portions. + */ +static int resctrl_io_alloc_init_cbm(struct resctrl_schema *s, u32 closid) +{ + enum resctrl_conf_type peer_type; + struct rdt_resource *r = s->res; + struct rdt_ctrl_domain *d; + int ret; + + rdt_staged_configs_clear(); + + ret = rdtgroup_init_cat(s, closid); + if (ret < 0) + goto out; + + /* Keep CDP_CODE and CDP_DATA of io_alloc CLOSID's CBM in sync. */ + if (resctrl_arch_get_cdp_enabled(r->rid)) { + peer_type = resctrl_peer_type(s->conf_type); + list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) + memcpy(&d->staged_config[peer_type], + &d->staged_config[s->conf_type], + sizeof(d->staged_config[0])); + } + + ret = resctrl_arch_update_domains(r, closid); +out: + rdt_staged_configs_clear(); + return ret; +} + +/* + * resctrl_io_alloc_closid() - io_alloc feature routes I/O traffic using + * the highest available CLOSID. Retrieve the maximum CLOSID supported by the + * resource. Note that if Code Data Prioritization (CDP) is enabled, the number + * of available CLOSIDs is reduced by half. + */ +u32 resctrl_io_alloc_closid(struct rdt_resource *r) +{ + if (resctrl_arch_get_cdp_enabled(r->rid)) + return resctrl_arch_get_num_closid(r) / 2 - 1; + else + return resctrl_arch_get_num_closid(r) - 1; +} + +ssize_t resctrl_io_alloc_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + char const *grp_name; + u32 io_alloc_closid; + bool enable; + int ret; + + ret = kstrtobool(buf, &enable); + if (ret) + return ret; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + if (!r->cache.io_alloc_capable) { + rdt_last_cmd_printf("io_alloc is not supported on %s\n", s->name); + ret = -ENODEV; + goto out_unlock; + } + + /* If the feature is already up to date, no action is needed. */ + if (resctrl_arch_get_io_alloc_enabled(r) == enable) + goto out_unlock; + + io_alloc_closid = resctrl_io_alloc_closid(r); + if (!resctrl_io_alloc_closid_supported(io_alloc_closid)) { + rdt_last_cmd_printf("io_alloc CLOSID (ctrl_hw_id) %u is not available\n", + io_alloc_closid); + ret = -EINVAL; + goto out_unlock; + } + + if (enable) { + if (!closid_alloc_fixed(io_alloc_closid)) { + grp_name = rdtgroup_name_by_closid(io_alloc_closid); + WARN_ON_ONCE(!grp_name); + rdt_last_cmd_printf("CLOSID (ctrl_hw_id) %u for io_alloc is used by %s group\n", + io_alloc_closid, grp_name ? grp_name : "another"); + ret = -ENOSPC; + goto out_unlock; + } + + ret = resctrl_io_alloc_init_cbm(s, io_alloc_closid); + if (ret) { + rdt_last_cmd_puts("Failed to initialize io_alloc allocations\n"); + closid_free(io_alloc_closid); + goto out_unlock; + } + } else { + closid_free(io_alloc_closid); + } + + ret = resctrl_arch_io_alloc_enable(r, enable); + if (enable && ret) { + rdt_last_cmd_puts("Failed to enable io_alloc feature\n"); + closid_free(io_alloc_closid); + } + +out_unlock: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + + return ret ?: nbytes; +} + +int resctrl_io_alloc_cbm_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + int ret = 0; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + if (!r->cache.io_alloc_capable) { + rdt_last_cmd_printf("io_alloc is not supported on %s\n", s->name); + ret = -ENODEV; + goto out_unlock; + } + + if (!resctrl_arch_get_io_alloc_enabled(r)) { + rdt_last_cmd_printf("io_alloc is not enabled on %s\n", s->name); + ret = -EINVAL; + goto out_unlock; + } + + /* + * When CDP is enabled, the CBMs of the highest CLOSID of CDP_CODE and + * CDP_DATA are kept in sync. As a result, the io_alloc CBMs shown for + * either CDP resource are identical and accurately represent the CBMs + * used for I/O. + */ + show_doms(seq, s, NULL, resctrl_io_alloc_closid(r)); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + return ret; +} + +static int resctrl_io_alloc_parse_line(char *line, struct rdt_resource *r, + struct resctrl_schema *s, u32 closid) +{ + enum resctrl_conf_type peer_type; + struct rdt_parse_data data; + struct rdt_ctrl_domain *d; + char *dom = NULL, *id; + unsigned long dom_id; + +next: + if (!line || line[0] == '\0') + return 0; + + dom = strsep(&line, ";"); + id = strsep(&dom, "="); + if (!dom || kstrtoul(id, 10, &dom_id)) { + rdt_last_cmd_puts("Missing '=' or non-numeric domain\n"); + return -EINVAL; + } + + dom = strim(dom); + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + if (d->hdr.id == dom_id) { + data.buf = dom; + data.mode = RDT_MODE_SHAREABLE; + data.closid = closid; + if (parse_cbm(&data, s, d)) + return -EINVAL; + /* + * Keep io_alloc CLOSID's CBM of CDP_CODE and CDP_DATA + * in sync. + */ + if (resctrl_arch_get_cdp_enabled(r->rid)) { + peer_type = resctrl_peer_type(s->conf_type); + memcpy(&d->staged_config[peer_type], + &d->staged_config[s->conf_type], + sizeof(d->staged_config[0])); + } + goto next; + } + } + + return -EINVAL; +} + +ssize_t resctrl_io_alloc_cbm_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + u32 io_alloc_closid; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + + buf[nbytes - 1] = '\0'; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + rdt_last_cmd_clear(); + + if (!r->cache.io_alloc_capable) { + rdt_last_cmd_printf("io_alloc is not supported on %s\n", s->name); + ret = -ENODEV; + goto out_unlock; + } + + if (!resctrl_arch_get_io_alloc_enabled(r)) { + rdt_last_cmd_printf("io_alloc is not enabled on %s\n", s->name); + ret = -EINVAL; + goto out_unlock; + } + + io_alloc_closid = resctrl_io_alloc_closid(r); + + rdt_staged_configs_clear(); + ret = resctrl_io_alloc_parse_line(buf, r, s, io_alloc_closid); + if (ret) + goto out_clear_configs; + + ret = resctrl_arch_update_domains(r, io_alloc_closid); + +out_clear_configs: + rdt_staged_configs_clear(); +out_unlock: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + + return ret ?: nbytes; +} diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index cf1fd82dc5a9..bff4a54ae333 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -390,6 +390,8 @@ void rdt_staged_configs_clear(void); bool closid_allocated(unsigned int closid); +bool closid_alloc_fixed(u32 closid); + int resctrl_find_cleanest_closid(void); void *rdt_kn_parent_priv(struct kernfs_node *kn); @@ -426,6 +428,21 @@ int mbm_L3_assignments_show(struct kernfs_open_file *of, struct seq_file *s, voi ssize_t mbm_L3_assignments_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); +int resctrl_io_alloc_show(struct kernfs_open_file *of, struct seq_file *seq, void *v); + +int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid); + +enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type); + +ssize_t resctrl_io_alloc_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off); + +const char *rdtgroup_name_by_closid(u32 closid); +int resctrl_io_alloc_cbm_show(struct kernfs_open_file *of, struct seq_file *seq, + void *v); +ssize_t resctrl_io_alloc_cbm_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off); +u32 resctrl_io_alloc_closid(struct rdt_resource *r); #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 0320360cd7a6..8e39dfda56bc 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -226,6 +226,11 @@ bool closid_allocated(unsigned int closid) return !test_bit(closid, closid_free_map); } +bool closid_alloc_fixed(u32 closid) +{ + return __test_and_clear_bit(closid, closid_free_map); +} + /** * rdtgroup_mode_by_closid - Return mode of resource group with closid * @closid: closid if the resource group @@ -1057,15 +1062,17 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - hw_shareable = r->cache.shareable_bits; list_for_each_entry(dom, &r->ctrl_domains, hdr.list) { if (sep) seq_putc(seq, ';'); + hw_shareable = r->cache.shareable_bits; sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->hdr.id); for (i = 0; i < closids_supported(); i++) { - if (!closid_allocated(i)) + if (!closid_allocated(i) || + (resctrl_arch_get_io_alloc_enabled(r) && + i == resctrl_io_alloc_closid(r))) continue; ctrl_val = resctrl_arch_get_config(r, dom, i, s->conf_type); @@ -1093,6 +1100,21 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, break; } } + + /* + * When the "io_alloc" feature is enabled, a portion of the cache + * is configured for shared use between hardware and software. + * Also, when CDP is enabled the CBMs of CDP_CODE and CDP_DATA + * resources are kept in sync. So, the CBMs for "io_alloc" can + * be accessed through either resource. + */ + if (resctrl_arch_get_io_alloc_enabled(r)) { + ctrl_val = resctrl_arch_get_config(r, dom, + resctrl_io_alloc_closid(r), + s->conf_type); + hw_shareable |= ctrl_val; + } + for (i = r->cache.cbm_len - 1; i >= 0; i--) { pseudo_locked = dom->plr ? dom->plr->cbm : 0; hwb = test_bit(i, &hw_shareable); @@ -1247,7 +1269,7 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, return 0; } -static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) +enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) { switch (my_type) { case CDP_CODE: @@ -1838,6 +1860,18 @@ void resctrl_bmec_files_show(struct rdt_resource *r, struct kernfs_node *l3_mon_ kernfs_put(mon_kn); } +const char *rdtgroup_name_by_closid(u32 closid) +{ + struct rdtgroup *rdtgrp; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->closid == closid) + return rdt_kn_name(rdtgrp->kn); + } + + return NULL; +} + /* rdtgroup information files for one cache resource. */ static struct rftype res_common_files[] = { { @@ -1948,6 +1982,20 @@ static struct rftype res_common_files[] = { .seq_show = rdt_thread_throttle_mode_show, }, { + .name = "io_alloc", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = resctrl_io_alloc_show, + .write = resctrl_io_alloc_write, + }, + { + .name = "io_alloc_cbm", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = resctrl_io_alloc_cbm_show, + .write = resctrl_io_alloc_cbm_write, + }, + { .name = "max_threshold_occupancy", .mode = 0644, .kf_ops = &rdtgroup_kf_single_ops, @@ -2138,6 +2186,23 @@ static void thread_throttle_mode_init(void) RFTYPE_CTRL_INFO | RFTYPE_RES_MB); } +/* + * The resctrl file "io_alloc" is added using L3 resource. However, it results + * in this file being visible for *all* cache resources (eg. L2 cache), + * whether it supports "io_alloc" or not. + */ +static void io_alloc_init(void) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + + if (r->cache.io_alloc_capable) { + resctrl_file_fflags_init("io_alloc", RFTYPE_CTRL_INFO | + RFTYPE_RES_CACHE); + resctrl_file_fflags_init("io_alloc_cbm", + RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE); + } +} + void resctrl_file_fflags_init(const char *config, unsigned long fflags) { struct rftype *rft; @@ -3383,11 +3448,12 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r) { unsigned int cbm_len = r->cache.cbm_len; unsigned long first_bit, zero_bit; - unsigned long val = _val; + unsigned long val; - if (!val) - return 0; + if (!_val || r->cache.arch_has_sparse_bitmasks) + return _val; + val = _val; first_bit = find_first_bit(&val, cbm_len); zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); @@ -3480,7 +3546,7 @@ static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schem * If there are no more shareable bits available on any domain then * the entire allocation will fail. */ -static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid) +int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid) { struct rdt_ctrl_domain *d; int ret; @@ -4408,6 +4474,8 @@ int resctrl_init(void) thread_throttle_mode_init(); + io_alloc_init(); + ret = resctrl_mon_resource_init(); if (ret) return ret; diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 0addcc849ff2..360b00854115 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -302,7 +302,7 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) if (!i) return ERR_PTR(-ENOMEM); - if (!(i->i_state & I_NEW)) + if (!(inode_state_read_once(i) & I_NEW)) return i; /* precalculate the data offset */ diff --git a/fs/select.c b/fs/select.c index 082cf60c7e23..65019b8ba3f7 100644 --- a/fs/select.c +++ b/fs/select.c @@ -776,17 +776,13 @@ static inline int get_sigset_argpack(struct sigset_argpack *to, { // the path is hot enough for overhead of copy_from_user() to matter if (from) { - if (can_do_masked_user_access()) - from = masked_user_access_begin(from); - else if (!user_read_access_begin(from, sizeof(*from))) - return -EFAULT; - unsafe_get_user(to->p, &from->p, Efault); - unsafe_get_user(to->size, &from->size, Efault); - user_read_access_end(); + scoped_user_read_access(from, Efault) { + unsafe_get_user(to->p, &from->p, Efault); + unsafe_get_user(to->size, &from->size, Efault); + } } return 0; Efault: - user_read_access_end(); return -EFAULT; } diff --git a/fs/signalfd.c b/fs/signalfd.c index d469782f97f4..d69eab584bc6 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -250,8 +250,6 @@ static const struct file_operations signalfd_fops = { static int do_signalfd4(int ufd, sigset_t *mask, int flags) { - struct signalfd_ctx *ctx; - /* Check the SFD_* constants for consistency. */ BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK); @@ -263,7 +261,8 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags) signotset(mask); if (ufd == -1) { - struct file *file; + int fd; + struct signalfd_ctx *ctx __free(kfree) = NULL; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -271,22 +270,16 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags) ctx->sigmask = *mask; - ufd = get_unused_fd_flags(flags & O_CLOEXEC); - if (ufd < 0) { - kfree(ctx); - return ufd; - } - - file = anon_inode_getfile_fmode("[signalfd]", &signalfd_fops, - ctx, O_RDWR | (flags & O_NONBLOCK), - FMODE_NOWAIT); - if (IS_ERR(file)) { - put_unused_fd(ufd); - kfree(ctx); - return PTR_ERR(file); - } - fd_install(ufd, file); + fd = FD_ADD(flags & O_CLOEXEC, + anon_inode_getfile_fmode( + "[signalfd]", &signalfd_fops, ctx, + O_RDWR | (flags & O_NONBLOCK), FMODE_NOWAIT)); + if (fd >= 0) + retain_and_null_ptr(ctx); + return fd; } else { + struct signalfd_ctx *ctx; + CLASS(fd, f)(ufd); if (fd_empty(f)) return -EBADF; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 018055fd2cdb..e3ea6fe7edb4 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -16,6 +16,7 @@ static struct cached_fid *init_cached_dir(const char *path); static void free_cached_dir(struct cached_fid *cfid); static void smb2_close_cached_fid(struct kref *ref); static void cfids_laundromat_worker(struct work_struct *work); +static void close_cached_dir_locked(struct cached_fid *cfid); struct cached_dir_dentry { struct list_head entry; @@ -388,7 +389,7 @@ out: * lease. Release one here, and the second below. */ cfid->has_lease = false; - close_cached_dir(cfid); + close_cached_dir_locked(cfid); } spin_unlock(&cfids->cfid_list_lock); @@ -480,18 +481,52 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon, spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->has_lease) { cfid->has_lease = false; - close_cached_dir(cfid); + close_cached_dir_locked(cfid); } spin_unlock(&cfid->cfids->cfid_list_lock); close_cached_dir(cfid); } - +/** + * close_cached_dir - drop a reference of a cached dir + * + * The release function will be called with cfid_list_lock held to remove the + * cached dirs from the list before any other thread can take another @cfid + * ref. Must not be called with cfid_list_lock held; use + * close_cached_dir_locked() called instead. + * + * @cfid: cached dir + */ void close_cached_dir(struct cached_fid *cfid) { + lockdep_assert_not_held(&cfid->cfids->cfid_list_lock); kref_put_lock(&cfid->refcount, smb2_close_cached_fid, &cfid->cfids->cfid_list_lock); } +/** + * close_cached_dir_locked - put a reference of a cached dir with + * cfid_list_lock held + * + * Calling close_cached_dir() with cfid_list_lock held has the potential effect + * of causing a deadlock if the invariant of refcount >= 2 is false. + * + * This function is used in paths that hold cfid_list_lock and expect at least + * two references. If that invariant is violated, WARNs and returns without + * dropping a reference; the final put must still go through + * close_cached_dir(). + * + * @cfid: cached dir + */ +static void close_cached_dir_locked(struct cached_fid *cfid) +{ + lockdep_assert_held(&cfid->cfids->cfid_list_lock); + + if (WARN_ON(kref_read(&cfid->refcount) < 2)) + return; + + kref_put(&cfid->refcount, smb2_close_cached_fid); +} + /* * Called from cifs_kill_sb when we unmount a share */ diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 9891f55bac1e..da935bd1ce87 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -90,7 +90,6 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo, size_t desc_len; struct key *spnego_key; const char *hostname = server->hostname; - const struct cred *saved_cred; /* length of fields (with semicolons): ver=0xyz ip4=ipaddress host=hostname sec=mechanism uid=0xFF user=username */ @@ -158,9 +157,8 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo, dp += sprintf(dp, ";upcall_target=app"); cifs_dbg(FYI, "key description = %s\n", description); - saved_cred = override_creds(spnego_cred); - spnego_key = request_key(&cifs_spnego_key_type, description, ""); - revert_creds(saved_cred); + scoped_with_creds(spnego_cred) + spnego_key = request_key(&cifs_spnego_key_type, description, ""); #ifdef CONFIG_CIFS_DEBUG2 if (cifsFYI && !IS_ERR(spnego_key)) { diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 185ac41bd7e9..6eccb9ed9daa 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -500,7 +500,7 @@ cifs_evict_inode(struct inode *inode) { netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); - if (inode->i_state & I_PINNING_NETFS_WB) + if (inode_state_read_once(inode) & I_PINNING_NETFS_WB) cifs_fscache_unuse_inode_cookie(inode, true); cifs_fscache_release_inode_cookie(inode); clear_inode(inode); @@ -1149,6 +1149,9 @@ cifs_setlease(struct file *file, int arg, struct file_lease **lease, void **priv struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + /* Check if file is oplocked if this is request for new lease */ if (arg == F_UNLCK || ((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) || diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 7da194f29fef..dcc50a2bfa4b 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1363,6 +1363,14 @@ do_retry: if (rdata->result == -ENODATA) { rdata->result = 0; __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + trace_smb3_read_err(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, + rdata->req->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + rdata->subreq.start + rdata->subreq.transferred, + rdata->subreq.len - rdata->subreq.transferred, + rdata->result); } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && @@ -1374,6 +1382,13 @@ do_retry: } if (rdata->got_bytes) __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); + trace_smb3_read_done(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, + rdata->req->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + rdata->subreq.start + rdata->subreq.transferred, + rdata->got_bytes); } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, @@ -1445,6 +1460,13 @@ cifs_async_readv(struct cifs_io_subrequest *rdata) rdata->iov[1].iov_base = (char *)smb + 4; rdata->iov[1].iov_len = get_rfc1002_length(smb); + trace_smb3_read_enter(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, + rdata->req->cfile->fid.netfid, + tcon->tid, tcon->ses->Suid, + rdata->subreq.start, rdata->subreq.len); + rc = cifs_call_async(tcon->ses->server, &rqst, cifs_readv_receive, cifs_readv_callback, NULL, rdata, 0, NULL); diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 55cb4b0cbd48..2f94d93b95e9 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -4451,6 +4451,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) out: kfree(ctx->username); + kfree(ctx->domainname); kfree_sensitive(ctx->password); kfree(origin_fullpath); kfree(ctx); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 474dadeb1593..9dc0a968ec89 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -9,6 +9,7 @@ * */ #include <linux/fs.h> +#include <linux/fs_struct.h> #include <linux/filelock.h> #include <linux/backing-dev.h> #include <linux/stat.h> diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index e60927b2a7c8..2a0d8b87bd8e 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1435,12 +1435,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_errorf(fc, "Unknown error parsing devname\n"); goto cifs_parse_mount_err; } + kfree(ctx->source); ctx->source = smb3_fs_context_fullpath(ctx, '/'); if (IS_ERR(ctx->source)) { ctx->source = NULL; cifs_errorf(fc, "OOM when copying UNC string\n"); goto cifs_parse_mount_err; } + kfree(fc->source); fc->source = kstrdup(ctx->source, GFP_KERNEL); if (fc->source == NULL) { cifs_errorf(fc, "OOM when copying UNC string\n"); @@ -1468,7 +1470,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, break; } - if (strnlen(param->string, CIFS_MAX_USERNAME_LEN) > + if (strnlen(param->string, CIFS_MAX_USERNAME_LEN) == CIFS_MAX_USERNAME_LEN) { pr_warn("username too long\n"); goto cifs_parse_mount_err; @@ -1832,6 +1834,10 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->password = NULL; kfree_sensitive(ctx->password2); ctx->password2 = NULL; + kfree(ctx->source); + ctx->source = NULL; + kfree(fc->source); + fc->source = NULL; return -EINVAL; } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index cac355364e43..b75482730912 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -6,6 +6,7 @@ * */ #include <linux/fs.h> +#include <linux/fs_struct.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/pagemap.h> @@ -101,7 +102,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) cifs_dbg(FYI, "%s: revalidating inode %llu\n", __func__, cifs_i->uniqueid); - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { cifs_dbg(FYI, "%s: inode %llu is new\n", __func__, cifs_i->uniqueid); return; @@ -146,7 +147,7 @@ cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) */ if (fattr->cf_flags & CIFS_FATTR_UNKNOWN_NLINK) { /* only provide fake values on a new inode */ - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { if (fattr->cf_cifsattrs & ATTR_DIRECTORY) set_nlink(inode, 2); else @@ -167,12 +168,12 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, struct cifsInodeInfo *cifs_i = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - if (!(inode->i_state & I_NEW) && + if (!(inode_state_read_once(inode) & I_NEW) && unlikely(inode_wrong_type(inode, fattr->cf_mode))) { CIFS_I(inode)->time = 0; /* force reval */ return -ESTALE; } - if (inode->i_state & I_NEW) + if (inode_state_read_once(inode) & I_NEW) CIFS_I(inode)->netfs.zero_point = fattr->cf_eof; cifs_revalidate_cache(inode, fattr); @@ -194,7 +195,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, inode->i_gid = fattr->cf_gid; /* if dynperm is set, don't clobber existing mode */ - if (inode->i_state & I_NEW || + if (inode_state_read(inode) & I_NEW || !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) inode->i_mode = fattr->cf_mode; @@ -236,7 +237,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, if (fattr->cf_flags & CIFS_FATTR_JUNCTION) inode->i_flags |= S_AUTOMOUNT; - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { cifs_set_netfs_context(inode); cifs_set_ops(inode); } @@ -1638,7 +1639,7 @@ retry_iget5_locked: cifs_fattr_to_inode(inode, fattr, false); if (sb->s_flags & SB_NOATIME) inode->i_flags |= S_NOATIME | S_NOCMTIME; - if (inode->i_state & I_NEW) { + if (inode_state_read_once(inode) & I_NEW) { inode->i_ino = hash; cifs_fscache_get_inode_cookie(inode); unlock_new_inode(inode); diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index ca8f3dd7ff63..78650527d4bb 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -7,6 +7,7 @@ #include <linux/pagemap.h> #include <linux/vfs.h> +#include <linux/fs_struct.h> #include <uapi/linux/magic.h> #include "cifsglob.h" #include "cifsproto.h" diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 85a4c55b61b8..c6c428c2e08d 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -290,6 +290,9 @@ static void smbd_disconnect_rdma_connection(struct smbdirect_socket *sc) break; case SMBDIRECT_SOCKET_CREATED: + sc->status = SMBDIRECT_SOCKET_DISCONNECTED; + break; + case SMBDIRECT_SOCKET_CONNECTED: sc->status = SMBDIRECT_SOCKET_ERROR; break; diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 051cd9dbba13..915cedde5d66 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -830,7 +830,7 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) if (!server || server->terminate) continue; - if (CIFS_CHAN_NEEDS_RECONNECT(ses, i)) + if (CIFS_CHAN_NEEDS_RECONNECT(ses, cur)) continue; /* diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f901ae18e68a..94454e8826b0 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -6092,8 +6092,8 @@ static int smb2_create_link(struct ksmbd_work *work, } ksmbd_debug(SMB, "target name is %s\n", target_name); - rc = ksmbd_vfs_kern_path_locked(work, link_name, LOOKUP_NO_SYMLINKS, - &path, 0); + rc = ksmbd_vfs_kern_path_start_removing(work, link_name, LOOKUP_NO_SYMLINKS, + &path, 0); if (rc) { if (rc != -ENOENT) goto out; @@ -6111,7 +6111,7 @@ static int smb2_create_link(struct ksmbd_work *work, ksmbd_debug(SMB, "link already exists\n"); goto out; } - ksmbd_vfs_kern_path_unlock(&path); + ksmbd_vfs_kern_path_end_removing(&path); } rc = ksmbd_vfs_link(work, target_name, link_name); if (rc) diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 5d3b48e77012..e2be9a496154 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -334,6 +334,9 @@ smb_direct_disconnect_rdma_connection(struct smbdirect_socket *sc) break; case SMBDIRECT_SOCKET_CREATED: + sc->status = SMBDIRECT_SOCKET_DISCONNECTED; + break; + case SMBDIRECT_SOCKET_CONNECTED: sc->status = SMBDIRECT_SOCKET_ERROR; break; @@ -1883,6 +1886,7 @@ static int smb_direct_accept_client(struct smbdirect_socket *sc) static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc) { struct smbdirect_recv_io *recvmsg; + bool recv_posted = false; int ret; WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_CREATED); @@ -1899,6 +1903,7 @@ static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc) pr_err("Can't post recv: %d\n", ret); goto out_err; } + recv_posted = true; ret = smb_direct_accept_client(sc); if (ret) { @@ -1908,7 +1913,14 @@ static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc) return 0; out_err: - put_recvmsg(sc, recvmsg); + /* + * If the recv was never posted, return it to the free list. + * If it was posted, leave it alone so disconnect teardown can + * drain the QP and complete it (flush) and the completion path + * will unmap it exactly once. + */ + if (!recv_posted) + put_recvmsg(sc, recvmsg); return ret; } diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 7a1e3dcc2cde..d2e391c29464 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -290,8 +290,11 @@ static int ksmbd_kthread_fn(void *p) } } up_read(&conn_list_lock); - if (ret == -EAGAIN) + if (ret == -EAGAIN) { + /* Per-IP limit hit: release the just-accepted socket. */ + sock_release(client_sk); continue; + } skip_max_ip_conns_limit: if (server_conf.max_connections && diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 891ed2dc2b73..03fd7409be79 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -49,27 +49,9 @@ static void ksmbd_vfs_inherit_owner(struct ksmbd_work *work, i_uid_write(inode, i_uid_read(parent_inode)); } -/** - * ksmbd_vfs_lock_parent() - lock parent dentry if it is stable - * @parent: parent dentry - * @child: child dentry - * - * Returns: %0 on success, %-ENOENT if the parent dentry is not stable - */ -int ksmbd_vfs_lock_parent(struct dentry *parent, struct dentry *child) -{ - inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); - if (child->d_parent != parent) { - inode_unlock(d_inode(parent)); - return -ENOENT; - } - - return 0; -} - static int ksmbd_vfs_path_lookup(struct ksmbd_share_config *share_conf, char *pathname, unsigned int flags, - struct path *path, bool do_lock) + struct path *path, bool for_remove) { struct qstr last; struct filename *filename __free(putname) = NULL; @@ -99,22 +81,20 @@ static int ksmbd_vfs_path_lookup(struct ksmbd_share_config *share_conf, return -ENOENT; } - if (do_lock) { + if (for_remove) { err = mnt_want_write(path->mnt); if (err) { path_put(path); return -ENOENT; } - inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - d = lookup_one_qstr_excl(&last, path->dentry, 0); + d = start_removing_noperm(path->dentry, &last); if (!IS_ERR(d)) { dput(path->dentry); path->dentry = d; return 0; } - inode_unlock(path->dentry->d_inode); mnt_drop_write(path->mnt); path_put(path); return -ENOENT; @@ -188,8 +168,7 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) } mode |= S_IFREG; - err = vfs_create(mnt_idmap(path.mnt), d_inode(path.dentry), - dentry, mode, true); + err = vfs_create(mnt_idmap(path.mnt), dentry, mode, NULL); if (!err) { ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(dentry)); @@ -230,7 +209,7 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) idmap = mnt_idmap(path.mnt); mode |= S_IFDIR; d = dentry; - dentry = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode); + dentry = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode, NULL); if (IS_ERR(dentry)) err = PTR_ERR(dentry); else if (d_is_negative(dentry)) @@ -609,7 +588,7 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) idmap = mnt_idmap(path->mnt); if (S_ISDIR(d_inode(path->dentry)->i_mode)) { - err = vfs_rmdir(idmap, d_inode(parent), path->dentry); + err = vfs_rmdir(idmap, d_inode(parent), path->dentry, NULL); if (err && err != -ENOTEMPTY) ksmbd_debug(VFS, "rmdir failed, err %d\n", err); } else { @@ -681,7 +660,6 @@ out1: int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, char *newname, int flags) { - struct dentry *old_parent, *new_dentry, *trap; struct dentry *old_child = old_path->dentry; struct path new_path; struct qstr new_last; @@ -691,7 +669,6 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, struct ksmbd_file *parent_fp; int new_type; int err, lookup_flags = LOOKUP_NO_SYMLINKS; - int target_lookup_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE; if (ksmbd_override_fsids(work)) return -ENOMEM; @@ -702,14 +679,6 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, goto revert_fsids; } - /* - * explicitly handle file overwrite case, for compatibility with - * filesystems that may not support rename flags (e.g: fuse) - */ - if (flags & RENAME_NOREPLACE) - target_lookup_flags |= LOOKUP_EXCL; - flags &= ~(RENAME_NOREPLACE); - retry: err = vfs_path_parent_lookup(to, lookup_flags | LOOKUP_BENEATH, &new_path, &new_last, &new_type, @@ -726,17 +695,14 @@ retry: if (err) goto out2; - trap = lock_rename_child(old_child, new_path.dentry); - if (IS_ERR(trap)) { - err = PTR_ERR(trap); + rd.mnt_idmap = mnt_idmap(old_path->mnt); + rd.old_parent = NULL; + rd.new_parent = new_path.dentry; + rd.flags = flags; + rd.delegated_inode = NULL, + err = start_renaming_dentry(&rd, lookup_flags, old_child, &new_last); + if (err) goto out_drop_write; - } - - old_parent = dget(old_child->d_parent); - if (d_unhashed(old_child)) { - err = -EINVAL; - goto out3; - } parent_fp = ksmbd_lookup_fd_inode(old_child->d_parent); if (parent_fp) { @@ -749,44 +715,17 @@ retry: ksmbd_fd_put(work, parent_fp); } - new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry, - lookup_flags | target_lookup_flags); - if (IS_ERR(new_dentry)) { - err = PTR_ERR(new_dentry); - goto out3; - } - - if (d_is_symlink(new_dentry)) { + if (d_is_symlink(rd.new_dentry)) { err = -EACCES; - goto out4; - } - - if (old_child == trap) { - err = -EINVAL; - goto out4; - } - - if (new_dentry == trap) { - err = -ENOTEMPTY; - goto out4; + goto out3; } - rd.mnt_idmap = mnt_idmap(old_path->mnt), - rd.old_parent = old_parent, - rd.old_dentry = old_child, - rd.new_parent = new_path.dentry, - rd.new_dentry = new_dentry, - rd.flags = flags, - rd.delegated_inode = NULL, err = vfs_rename(&rd); if (err) ksmbd_debug(VFS, "vfs_rename failed err %d\n", err); -out4: - dput(new_dentry); out3: - dput(old_parent); - unlock_rename(old_parent, new_path.dentry); + end_renaming(&rd); out_drop_write: mnt_drop_write(old_path->mnt); out2: @@ -1084,18 +1023,17 @@ int ksmbd_vfs_unlink(struct file *filp) return err; dir = dget_parent(dentry); - err = ksmbd_vfs_lock_parent(dir, dentry); - if (err) + dentry = start_removing_dentry(dir, dentry); + err = PTR_ERR(dentry); + if (IS_ERR(dentry)) goto out; - dget(dentry); if (S_ISDIR(d_inode(dentry)->i_mode)) - err = vfs_rmdir(idmap, d_inode(dir), dentry); + err = vfs_rmdir(idmap, d_inode(dir), dentry, NULL); else err = vfs_unlink(idmap, d_inode(dir), dentry, NULL); - dput(dentry); - inode_unlock(d_inode(dir)); + end_removing(dentry); if (err) ksmbd_debug(VFS, "failed to delete, err %d\n", err); out: @@ -1207,7 +1145,7 @@ static int ksmbd_vfs_lookup_in_dir(const struct path *dir, char *name, static int __ksmbd_vfs_kern_path(struct ksmbd_work *work, char *filepath, unsigned int flags, - struct path *path, bool caseless, bool do_lock) + struct path *path, bool caseless, bool for_remove) { struct ksmbd_share_config *share_conf = work->tcon->share_conf; struct path parent_path; @@ -1215,7 +1153,7 @@ int __ksmbd_vfs_kern_path(struct ksmbd_work *work, char *filepath, int err; retry: - err = ksmbd_vfs_path_lookup(share_conf, filepath, flags, path, do_lock); + err = ksmbd_vfs_path_lookup(share_conf, filepath, flags, path, for_remove); if (!err || !caseless) return err; @@ -1286,7 +1224,7 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *filepath, } /** - * ksmbd_vfs_kern_path_locked() - lookup a file and get path info + * ksmbd_vfs_kern_path_start_remove() - lookup a file and get path info prior to removal * @work: work * @filepath: file path that is relative to share * @flags: lookup flags @@ -1298,20 +1236,19 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *filepath, * filesystem will have been gained. * Return: 0 on if file was found, otherwise error */ -int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *filepath, - unsigned int flags, - struct path *path, bool caseless) +int ksmbd_vfs_kern_path_start_removing(struct ksmbd_work *work, char *filepath, + unsigned int flags, + struct path *path, bool caseless) { return __ksmbd_vfs_kern_path(work, filepath, flags, path, caseless, true); } -void ksmbd_vfs_kern_path_unlock(const struct path *path) +void ksmbd_vfs_kern_path_end_removing(const struct path *path) { - /* While lock is still held, ->d_parent is safe */ - inode_unlock(d_inode(path->dentry->d_parent)); + end_removing(path->dentry); mnt_drop_write(path->mnt); - path_put(path); + mntput(path->mnt); } struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index df6421b4590b..16ca29ee16e5 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -120,10 +120,10 @@ int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, unsigned int flags, struct path *path, bool caseless); -int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, - unsigned int flags, - struct path *path, bool caseless); -void ksmbd_vfs_kern_path_unlock(const struct path *path); +int ksmbd_vfs_kern_path_start_removing(struct ksmbd_work *work, char *name, + unsigned int flags, + struct path *path, bool caseless); +void ksmbd_vfs_kern_path_end_removing(const struct path *path); struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, const char *name, unsigned int flags, diff --git a/fs/splice.c b/fs/splice.c index f5094b6d00a0..d338fe56b50b 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1498,7 +1498,7 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, /* * For lack of a better implementation, implement vmsplice() to userspace - * as a simple copy of the pipes pages to the user iov. + * as a simple copy of the pipe's pages to the user iov. */ static ssize_t vmsplice_to_user(struct file *file, struct iov_iter *iter, unsigned int flags) diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index cceae3b78698..82b687414e65 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -86,7 +86,7 @@ struct inode *squashfs_iget(struct super_block *sb, long long ino, if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; err = squashfs_read_inode(inode, ino); diff --git a/fs/super.c b/fs/super.c index 5bab94fb7e03..7c66b96b59be 100644 --- a/fs/super.c +++ b/fs/super.c @@ -389,6 +389,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, goto fail; if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink)) goto fail; + s->s_min_writeback_pages = MIN_WRITEBACK_PAGES; return s; fail: @@ -1183,11 +1184,14 @@ static inline bool get_active_super(struct super_block *sb) static const char *filesystems_freeze_ptr = "filesystems_freeze"; -static void filesystems_freeze_callback(struct super_block *sb, void *unused) +static void filesystems_freeze_callback(struct super_block *sb, void *freeze_all_ptr) { if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) return; + if (freeze_all_ptr && !(sb->s_type->fs_flags & FS_POWER_FREEZE)) + return; + if (!get_active_super(sb)) return; @@ -1201,9 +1205,13 @@ static void filesystems_freeze_callback(struct super_block *sb, void *unused) deactivate_super(sb); } -void filesystems_freeze(void) +void filesystems_freeze(bool freeze_all) { - __iterate_supers(filesystems_freeze_callback, NULL, + void *freeze_all_ptr = NULL; + + if (freeze_all) + freeze_all_ptr = &freeze_all; + __iterate_supers(filesystems_freeze_callback, freeze_all_ptr, SUPER_ITER_UNLOCKED | SUPER_ITER_REVERSE); } diff --git a/fs/sync.c b/fs/sync.c index 2955cd4c77a3..431fc5f5be06 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -117,16 +117,17 @@ SYSCALL_DEFINE0(sync) static void do_sync_work(struct work_struct *work) { int nowait = 0; + int wait = 1; /* * Sync twice to reduce the possibility we skipped some inodes / pages * because they were temporarily locked */ - iterate_supers(sync_inodes_one_sb, &nowait); + iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); sync_bdevs(false); - iterate_supers(sync_inodes_one_sb, &nowait); - iterate_supers(sync_fs_one_sb, &nowait); + iterate_supers(sync_inodes_one_sb, NULL); + iterate_supers(sync_fs_one_sb, &wait); sync_bdevs(false); printk("Emergency Sync complete\n"); kfree(work); @@ -182,7 +183,7 @@ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) if (!file->f_op->fsync) return -EINVAL; - if (!datasync && (inode->i_state & I_DIRTY_TIME)) + if (!datasync && (inode_state_read_once(inode) & I_DIRTY_TIME)) mark_inode_dirty_sync(inode); return file->f_op->fsync(file, start, end, datasync); } @@ -280,14 +281,12 @@ int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, } 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, - sync_mode); + ret = filemap_fdatawrite_range(mapping, offset, + endbyte); + else + ret = filemap_flush_range(mapping, offset, endbyte); if (ret < 0) goto out; } diff --git a/fs/timerfd.c b/fs/timerfd.c index c68f28d9c426..9fcea7860ddf 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -393,9 +393,8 @@ static const struct file_operations timerfd_fops = { SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) { - int ufd; - struct timerfd_ctx *ctx; - struct file *file; + struct timerfd_ctx *ctx __free(kfree) = NULL; + int ret; /* Check the TFD_* constants for consistency. */ BUILD_BUG_ON(TFD_CLOEXEC != O_CLOEXEC); @@ -432,23 +431,13 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) ctx->moffs = ktime_mono_to_real(0); - ufd = get_unused_fd_flags(flags & TFD_SHARED_FCNTL_FLAGS); - if (ufd < 0) { - kfree(ctx); - return ufd; - } - - file = anon_inode_getfile_fmode("[timerfd]", &timerfd_fops, ctx, - O_RDWR | (flags & TFD_SHARED_FCNTL_FLAGS), - FMODE_NOWAIT); - if (IS_ERR(file)) { - put_unused_fd(ufd); - kfree(ctx); - return PTR_ERR(file); - } - - fd_install(ufd, file); - return ufd; + ret = FD_ADD(flags & TFD_SHARED_FCNTL_FLAGS, + anon_inode_getfile_fmode("[timerfd]", &timerfd_fops, ctx, + O_RDWR | (flags & TFD_SHARED_FCNTL_FLAGS), + FMODE_NOWAIT)); + if (ret >= 0) + retain_and_null_ptr(ctx); + return ret; } static int do_timerfd_settime(int ufd, int flags, diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index ca41ce8208c4..c3265b8804f5 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1323,7 +1323,7 @@ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) inode_lock(inode); /* Synchronize the inode unless this is a 'datasync()' call. */ - if (!datasync || (inode->i_state & I_DIRTY_DATASYNC)) { + if (!datasync || (inode_state_read_once(inode) & I_DIRTY_DATASYNC)) { err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) goto out; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 46952a33c4e6..f453c37cee37 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -114,7 +114,7 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) inode = iget_locked(sb, inum); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; ui = ubifs_inode(inode); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index a79d73f28aa7..7fae8002344a 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1962,7 +1962,7 @@ struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino, if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) { + if (!(inode_state_read_once(inode) & I_NEW)) { if (UDF_I(inode)->i_hidden != hidden_inode) { iput(inode); return ERR_PTR(-EFSCORRUPTED); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 8361c00e8fa6..e2b0a35de2a7 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -655,7 +655,7 @@ struct inode *ufs_iget(struct super_block *sb, unsigned long ino) inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; ufsi = UFS_I(inode); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 54c6cc7fe9c6..e6e74b384087 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -2111,9 +2111,7 @@ static void init_once_userfaultfd_ctx(void *mem) static int new_userfaultfd(int flags) { - struct userfaultfd_ctx *ctx; - struct file *file; - int fd; + struct userfaultfd_ctx *ctx __free(kfree) = NULL; VM_WARN_ON_ONCE(!current->mm); @@ -2135,26 +2133,18 @@ static int new_userfaultfd(int flags) atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; - fd = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS); - if (fd < 0) - goto err_out; + FD_PREPARE(fdf, flags & UFFD_SHARED_FCNTL_FLAGS, + anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx, + O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), + NULL)); + if (fdf.err) + return fdf.err; - /* Create a new inode so that the LSM can block the creation. */ - file = anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx, - O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); - if (IS_ERR(file)) { - put_unused_fd(fd); - fd = PTR_ERR(file); - goto err_out; - } /* prevent the mm struct to be freed */ mmgrab(ctx->mm); - file->f_mode |= FMODE_NOWAIT; - fd_install(fd, file); - return fd; -err_out: - kmem_cache_free(userfaultfd_ctx_cachep, ctx); - return fd; + fd_prepare_file(fdf)->f_mode |= FMODE_NOWAIT; + retain_and_null_ptr(ctx); + return fd_publish(fdf); } static inline bool userfaultfd_syscall_allowed(int flags) diff --git a/fs/utimes.c b/fs/utimes.c index c7c7958e57b2..86f8ce8cd6b1 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -22,7 +22,7 @@ int vfs_utimes(const struct path *path, struct timespec64 *times) int error; struct iattr newattrs; struct inode *inode = path->dentry->d_inode; - struct inode *delegated_inode = NULL; + struct delegated_inode delegated_inode = { }; if (times) { if (!nsec_valid(times[0].tv_nsec) || @@ -66,7 +66,7 @@ retry_deleg: error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; @@ -76,6 +76,7 @@ retry_deleg: out: return error; } +EXPORT_SYMBOL_GPL(vfs_utimes); static int do_utimes_path(int dfd, const char __user *filename, struct timespec64 *times, int flags) diff --git a/fs/xattr.c b/fs/xattr.c index 8851a5ef34f5..32d445fb60aa 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -274,7 +274,7 @@ int __vfs_setxattr_noperm(struct mnt_idmap *idmap, int __vfs_setxattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, - int flags, struct inode **delegated_inode) + int flags, struct delegated_inode *delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -305,7 +305,7 @@ vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; - struct inode *delegated_inode = NULL; + struct delegated_inode delegated_inode = { }; const void *orig_value = value; int error; @@ -322,7 +322,7 @@ retry_deleg: flags, &delegated_inode); inode_unlock(inode); - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; @@ -533,7 +533,7 @@ EXPORT_SYMBOL(__vfs_removexattr); int __vfs_removexattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, - struct inode **delegated_inode) + struct delegated_inode *delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -567,7 +567,7 @@ vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = dentry->d_inode; - struct inode *delegated_inode = NULL; + struct delegated_inode delegated_inode = { }; int error; retry_deleg: @@ -576,7 +576,7 @@ retry_deleg: name, &delegated_inode); inode_unlock(inode); - if (delegated_inode) { + if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h index de840abc0bcd..57e47077c75a 100644 --- a/fs/xfs/libxfs/xfs_errortag.h +++ b/fs/xfs/libxfs/xfs_errortag.h @@ -73,7 +73,8 @@ #define XFS_ERRTAG_WRITE_DELAY_MS 43 #define XFS_ERRTAG_EXCHMAPS_FINISH_ONE 44 #define XFS_ERRTAG_METAFILE_RESV_CRITICAL 45 -#define XFS_ERRTAG_MAX 46 +#define XFS_ERRTAG_FORCE_ZERO_RANGE 46 +#define XFS_ERRTAG_MAX 47 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -133,7 +134,8 @@ XFS_ERRTAG(ATTR_LEAF_TO_NODE, attr_leaf_to_node, 1) \ XFS_ERRTAG(WB_DELAY_MS, wb_delay_ms, 3000) \ XFS_ERRTAG(WRITE_DELAY_MS, write_delay_ms, 3000) \ XFS_ERRTAG(EXCHMAPS_FINISH_ONE, exchmaps_finish_one, 1) \ -XFS_ERRTAG(METAFILE_RESV_CRITICAL, metafile_resv_crit, 4) +XFS_ERRTAG(METAFILE_RESV_CRITICAL, metafile_resv_crit, 4) \ +XFS_ERRTAG(FORCE_ZERO_RANGE, force_zero_range, 4) #endif /* XFS_ERRTAG */ #endif /* __XFS_ERRORTAG_H_ */ diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 2ef7742be7d3..7bfa37c99480 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -1249,7 +1249,7 @@ xchk_irele( * hits do not clear DONTCACHE, so we must do it here. */ spin_lock(&VFS_I(ip)->i_lock); - VFS_I(ip)->i_state &= ~I_DONTCACHE; + inode_state_clear(VFS_I(ip), I_DONTCACHE); spin_unlock(&VFS_I(ip)->i_lock); } diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index a90a011c7e5f..4f7040c9ddf0 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -1933,7 +1933,7 @@ xrep_inode_pptr( * Unlinked inodes that cannot be added to the directory tree will not * have a parent pointer. */ - if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE)) + if (inode->i_nlink == 0 && !(inode_state_read_once(inode) & I_LINKABLE)) return 0; /* Children of the superblock do not have parent pointers. */ diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c index 9c12cb844231..4e550a1d5353 100644 --- a/fs/xfs/scrub/orphanage.c +++ b/fs/xfs/scrub/orphanage.c @@ -152,11 +152,10 @@ xrep_orphanage_create( } /* Try to find the orphanage directory. */ - inode_lock_nested(root_inode, I_MUTEX_PARENT); - orphanage_dentry = lookup_noperm(&QSTR(ORPHANAGE), root_dentry); + orphanage_dentry = start_creating_noperm(root_dentry, &QSTR(ORPHANAGE)); if (IS_ERR(orphanage_dentry)) { error = PTR_ERR(orphanage_dentry); - goto out_unlock_root; + goto out_dput_root; } /* @@ -167,10 +166,10 @@ xrep_orphanage_create( */ if (d_really_is_negative(orphanage_dentry)) { orphanage_dentry = vfs_mkdir(&nop_mnt_idmap, root_inode, - orphanage_dentry, 0750); + orphanage_dentry, 0750, NULL); error = PTR_ERR(orphanage_dentry); if (IS_ERR(orphanage_dentry)) - goto out_unlock_root; + goto out_dput_orphanage; } /* Not a directory? Bail out. */ @@ -200,9 +199,7 @@ xrep_orphanage_create( sc->orphanage_ilock_flags = 0; out_dput_orphanage: - dput(orphanage_dentry); -out_unlock_root: - inode_unlock(VFS_I(sc->mp->m_rootip)); + end_creating(orphanage_dentry); out_dput_root: dput(root_dentry); out: diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index 3b692c4acc1e..11d5de10fd56 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -915,7 +915,7 @@ xchk_pptr_looks_zapped( * Temporary files that cannot be linked into the directory tree do not * have attr forks because they cannot ever have parents. */ - if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE)) + if (inode->i_nlink == 0 && !(inode_state_read_once(inode) & I_LINKABLE)) return false; /* diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index 5902398185a8..df629892462f 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -184,7 +184,7 @@ xrep_symlink_salvage_inline( sc->ip->i_disk_size == 1 && old_target[0] == '?') return 0; - nr = min(XFS_SYMLINK_MAXLEN, xfs_inode_data_fork_size(ip)); + nr = min(XFS_SYMLINK_MAXLEN, ifp->if_bytes); memcpy(target_buf, ifp->if_data, nr); return nr; } diff --git a/fs/xfs/scrub/xfarray.c b/fs/xfs/scrub/xfarray.c index cdd13ed9c569..ed2e8c64b1a8 100644 --- a/fs/xfs/scrub/xfarray.c +++ b/fs/xfs/scrub/xfarray.c @@ -834,7 +834,7 @@ xfarray_sort_scan( si->first_folio_idx = xfarray_idx(si->array, folio_pos(si->folio) + si->array->obj_size - 1); - next_pos = folio_pos(si->folio) + folio_size(si->folio); + next_pos = folio_next_pos(si->folio); si->last_folio_idx = xfarray_idx(si->array, next_pos - 1); if (xfarray_pos(si->array, si->last_folio_idx + 1) > next_pos) si->last_folio_idx--; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index a26f79815533..56a544638491 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -271,7 +271,7 @@ xfs_discard_folio( * folio itself and not the start offset that is passed in. */ xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos, - folio_pos(folio) + folio_size(folio), NULL); + folio_next_pos(folio), NULL); } /* @@ -742,14 +742,15 @@ xfs_vm_read_folio( struct file *unused, struct folio *folio) { - return iomap_read_folio(folio, &xfs_read_iomap_ops); + iomap_bio_read_folio(folio, &xfs_read_iomap_ops); + return 0; } STATIC void xfs_vm_readahead( struct readahead_control *rac) { - iomap_readahead(rac, &xfs_read_iomap_ops); + iomap_bio_readahead(rac, &xfs_read_iomap_ops); } static int diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 06ca11731e43..2208a720ec3f 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -514,7 +514,7 @@ xfs_can_free_eofblocks( * Caller must either hold the exclusive io lock; or be inactivating * the inode, which guarantees there are no other users of the inode. */ - if (!(VFS_I(ip)->i_state & I_FREEING)) + if (!(inode_state_read_once(VFS_I(ip)) & I_FREEING)) xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL); /* prealloc/delalloc exists only on regular files */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 2702fef2c90c..6108612182e2 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -27,6 +27,8 @@ #include "xfs_file.h" #include "xfs_aops.h" #include "xfs_zone_alloc.h" +#include "xfs_error.h" +#include "xfs_errortag.h" #include <linux/dax.h> #include <linux/falloc.h> @@ -674,8 +676,17 @@ xfs_file_dio_write_aligned( struct xfs_zone_alloc_ctx *ac) { unsigned int iolock = XFS_IOLOCK_SHARED; + unsigned int dio_flags = 0; ssize_t ret; + /* + * For always COW inodes, each bio must be aligned to the file system + * block size and not just the device sector size because we need to + * allocate a block-aligned amount of space for each write. + */ + if (xfs_is_always_cow_inode(ip)) + dio_flags |= IOMAP_DIO_FSBLOCK_ALIGNED; + ret = xfs_ilock_iocb_for_write(iocb, &iolock); if (ret) return ret; @@ -693,7 +704,7 @@ xfs_file_dio_write_aligned( iolock = XFS_IOLOCK_SHARED; } trace_xfs_file_direct_write(iocb, from); - ret = iomap_dio_rw(iocb, from, ops, dops, 0, ac, 0); + ret = iomap_dio_rw(iocb, from, ops, dops, dio_flags, ac, 0); out_unlock: xfs_iunlock(ip, iolock); return ret; @@ -890,15 +901,7 @@ xfs_file_dio_write( if ((iocb->ki_pos | count) & target->bt_logical_sectormask) return -EINVAL; - /* - * For always COW inodes we also must check the alignment of each - * individual iovec segment, as they could end up with different - * I/Os due to the way bio_iov_iter_get_pages works, and we'd - * then overwrite an already written block. - */ - if (((iocb->ki_pos | count) & ip->i_mount->m_blockmask) || - (xfs_is_always_cow_inode(ip) && - (iov_iter_alignment(from) & ip->i_mount->m_blockmask))) + if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask) return xfs_file_dio_write_unaligned(ip, iocb, from); if (xfs_is_zoned_inode(ip)) return xfs_file_dio_write_zoned(ip, iocb, from); @@ -1254,23 +1257,36 @@ xfs_falloc_zero_range( struct xfs_zone_alloc_ctx *ac) { struct inode *inode = file_inode(file); + struct xfs_inode *ip = XFS_I(inode); unsigned int blksize = i_blocksize(inode); loff_t new_size = 0; int error; - trace_xfs_zero_file_space(XFS_I(inode)); + trace_xfs_zero_file_space(ip); error = xfs_falloc_newsize(file, mode, offset, len, &new_size); if (error) return error; - error = xfs_free_file_space(XFS_I(inode), offset, len, ac); - if (error) - return error; + /* + * Zero range implements a full zeroing mechanism but is only used in + * limited situations. It is more efficient to allocate unwritten + * extents than to perform zeroing here, so use an errortag to randomly + * force zeroing on DEBUG kernels for added test coverage. + */ + if (XFS_TEST_ERROR(ip->i_mount, + XFS_ERRTAG_FORCE_ZERO_RANGE)) { + error = xfs_zero_range(ip, offset, len, ac, NULL); + } else { + error = xfs_free_file_space(ip, offset, len, ac); + if (error) + return error; - len = round_up(offset + len, blksize) - round_down(offset, blksize); - offset = round_down(offset, blksize); - error = xfs_alloc_file_space(XFS_I(inode), offset, len); + len = round_up(offset + len, blksize) - + round_down(offset, blksize); + offset = round_down(offset, blksize); + error = xfs_alloc_file_space(ip, offset, len); + } if (error) return error; return xfs_falloc_setsize(file, new_size); diff --git a/fs/xfs/xfs_handle.c b/fs/xfs/xfs_handle.c index f19fce557354..5a3e3bf4e7cc 100644 --- a/fs/xfs/xfs_handle.c +++ b/fs/xfs/xfs_handle.c @@ -233,14 +233,11 @@ xfs_open_by_handle( xfs_fsop_handlereq_t *hreq) { const struct cred *cred = current_cred(); - int error; - int fd; int permflag; - struct file *filp; struct inode *inode; struct dentry *dentry; fmode_t fmode; - struct path path; + struct path path __free(path_put) = {}; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -249,12 +246,11 @@ xfs_open_by_handle( if (IS_ERR(dentry)) return PTR_ERR(dentry); inode = d_inode(dentry); + path.dentry = dentry; /* Restrict xfs_open_by_handle to directories & regular files. */ - if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) { - error = -EPERM; - goto out_dput; - } + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) + return -EPERM; #if BITS_PER_LONG != 32 hreq->oflags |= O_LARGEFILE; @@ -263,48 +259,30 @@ xfs_open_by_handle( permflag = hreq->oflags; fmode = OPEN_FMODE(permflag); if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) && - (fmode & FMODE_WRITE) && IS_APPEND(inode)) { - error = -EPERM; - goto out_dput; - } + (fmode & FMODE_WRITE) && IS_APPEND(inode)) + return -EPERM; - if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) { - error = -EPERM; - goto out_dput; - } + if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) + return -EPERM; /* Can't write directories. */ - if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) { - error = -EISDIR; - goto out_dput; - } + if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) + return -EISDIR; - fd = get_unused_fd_flags(0); - if (fd < 0) { - error = fd; - goto out_dput; - } + path.mnt = mntget(parfilp->f_path.mnt); - path.mnt = parfilp->f_path.mnt; - path.dentry = dentry; - filp = dentry_open(&path, hreq->oflags, cred); - dput(dentry); - if (IS_ERR(filp)) { - put_unused_fd(fd); - return PTR_ERR(filp); - } + FD_PREPARE(fdf, 0, dentry_open(&path, hreq->oflags, cred)); + if (fdf.err) + return fdf.err; if (S_ISREG(inode->i_mode)) { + struct file *filp = fd_prepare_file(fdf); + filp->f_flags |= O_NOATIME; filp->f_mode |= FMODE_NOCMTIME; } - fd_install(fd, filp); - return fd; - - out_dput: - dput(dentry); - return error; + return fd_publish(fdf); } int diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c index 7c541fb373d5..3c1557fb1cf0 100644 --- a/fs/xfs/xfs_health.c +++ b/fs/xfs/xfs_health.c @@ -285,7 +285,7 @@ xfs_inode_mark_sick( * is not the case here. */ spin_lock(&VFS_I(ip)->i_lock); - VFS_I(ip)->i_state &= ~I_DONTCACHE; + inode_state_clear(VFS_I(ip), I_DONTCACHE); spin_unlock(&VFS_I(ip)->i_lock); } @@ -309,7 +309,7 @@ xfs_inode_mark_corrupt( * is not the case here. */ spin_lock(&VFS_I(ip)->i_lock); - VFS_I(ip)->i_state &= ~I_DONTCACHE; + inode_state_clear(VFS_I(ip), I_DONTCACHE); spin_unlock(&VFS_I(ip)->i_lock); } diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index e44040206851..f3fc4d21bfe1 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -334,7 +334,7 @@ xfs_reinit_inode( dev_t dev = inode->i_rdev; kuid_t uid = inode->i_uid; kgid_t gid = inode->i_gid; - unsigned long state = inode->i_state; + unsigned long state = inode_state_read_once(inode); error = inode_init_always(mp->m_super, inode); @@ -345,7 +345,7 @@ xfs_reinit_inode( inode->i_rdev = dev; inode->i_uid = uid; inode->i_gid = gid; - inode->i_state = state; + inode_state_assign_raw(inode, state); mapping_set_folio_min_order(inode->i_mapping, M_IGEO(mp)->min_folio_order); return error; @@ -411,7 +411,7 @@ xfs_iget_recycle( ip->i_flags |= XFS_INEW; xfs_perag_clear_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG); - inode->i_state = I_NEW; + inode_state_assign_raw(inode, I_NEW); spin_unlock(&ip->i_flags_lock); spin_unlock(&pag->pag_ici_lock); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 36b39539e561..f1f88e48fe22 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1580,7 +1580,7 @@ xfs_iunlink_reload_next( next_ip->i_prev_unlinked = prev_agino; trace_xfs_iunlink_reload_next(next_ip); rele: - ASSERT(!(VFS_I(next_ip)->i_state & I_DONTCACHE)); + ASSERT(!(inode_state_read_once(VFS_I(next_ip)) & I_DONTCACHE)); if (xfs_is_quotacheck_running(mp) && next_ip) xfs_iflags_set(next_ip, XFS_IQUOTAUNCHECKED); xfs_irele(next_ip); @@ -2111,7 +2111,7 @@ xfs_rename_alloc_whiteout( */ xfs_setup_iops(tmpfile); xfs_finish_inode_setup(tmpfile); - VFS_I(tmpfile)->i_state |= I_LINKABLE; + inode_state_set_raw(VFS_I(tmpfile), I_LINKABLE); *wip = tmpfile; return 0; @@ -2330,7 +2330,7 @@ retry: * flag from the inode so it doesn't accidentally get misused in * future. */ - VFS_I(du_wip.ip)->i_state &= ~I_LINKABLE; + inode_state_clear_raw(VFS_I(du_wip.ip), I_LINKABLE); } out_commit: diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 1bd411a1114c..2eb0c6011a2e 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -113,9 +113,9 @@ xfs_inode_item_precommit( * to log the timestamps, or will clear already cleared fields in the * worst case. */ - if (inode->i_state & I_DIRTY_TIME) { + if (inode_state_read_once(inode) & I_DIRTY_TIME) { spin_lock(&inode->i_lock); - inode->i_state &= ~I_DIRTY_TIME; + inode_state_clear(inode, I_DIRTY_TIME); spin_unlock(&inode->i_lock); } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a6bb7ee7a27a..59eaad774371 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1408,10 +1408,8 @@ xfs_file_ioctl( trace_xfs_ioc_free_eofblocks(mp, &icw, _RET_IP_); - sb_start_write(mp->m_super); - error = xfs_blockgc_free_space(mp, &icw); - sb_end_write(mp->m_super); - return error; + guard(super_write)(mp->m_super); + return xfs_blockgc_free_space(mp, &icw); } case XFS_IOC_EXCHANGE_RANGE: diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 490e12cb99be..04f39ea15898 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1758,6 +1758,8 @@ xfs_buffered_write_iomap_begin( struct iomap *iomap, struct iomap *srcmap) { + struct iomap_iter *iter = container_of(iomap, struct iomap_iter, + iomap); struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); @@ -1823,21 +1825,41 @@ xfs_buffered_write_iomap_begin( } /* - * For zeroing, trim a delalloc extent that extends beyond the EOF - * block. If it starts beyond the EOF block, convert it to an + * For zeroing, trim extents that extend beyond the EOF block. If a + * delalloc extent starts beyond the EOF block, convert it to an * unwritten extent. */ - if ((flags & IOMAP_ZERO) && imap.br_startoff <= offset_fsb && - isnullstartblock(imap.br_startblock)) { + if (flags & IOMAP_ZERO) { xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)); + u64 end; - if (offset_fsb >= eof_fsb) + if (isnullstartblock(imap.br_startblock) && + offset_fsb >= eof_fsb) goto convert_delay; - if (end_fsb > eof_fsb) { + if (offset_fsb < eof_fsb && end_fsb > eof_fsb) end_fsb = eof_fsb; - xfs_trim_extent(&imap, offset_fsb, - end_fsb - offset_fsb); + + /* + * Look up dirty folios for unwritten mappings within EOF. + * Providing this bypasses the flush iomap uses to trigger + * extent conversion when unwritten mappings have dirty + * pagecache in need of zeroing. + * + * Trim the mapping to the end pos of the lookup, which in turn + * was trimmed to the end of the batch if it became full before + * the end of the mapping. + */ + if (imap.br_state == XFS_EXT_UNWRITTEN && + offset_fsb < eof_fsb) { + loff_t len = min(count, + XFS_FSB_TO_B(mp, imap.br_blockcount)); + + end = iomap_fill_dirty_folios(iter, offset, len); + end_fsb = min_t(xfs_fileoff_t, end_fsb, + XFS_B_TO_FSB(mp, end)); } + + xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb); } /* diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index caff0125faea..ad94fbf55014 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1420,7 +1420,7 @@ xfs_setup_inode( bool is_meta = xfs_is_internal_inode(ip); inode->i_ino = ip->i_ino; - inode->i_state |= I_NEW; + inode_state_set_raw(inode, I_NEW); inode_sb_list_add(inode); /* make the inode look hashed for the writeback code */ diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 36cda724da89..9d1ed9bb0bee 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -17,7 +17,7 @@ xfs_can_free_cowblocks(struct xfs_inode *ip) { struct inode *inode = VFS_I(ip); - if ((inode->i_state & I_DIRTY_PAGES) || + if ((inode_state_read_once(inode) & I_DIRTY_PAGES) || mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY) || mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK) || atomic_read(&inode->i_dio_count)) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 1067ebb3b001..bc71aa9dcee8 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1693,7 +1693,10 @@ xfs_fs_fill_super( if (error) return error; - sb_min_blocksize(sb, BBSIZE); + if (!sb_min_blocksize(sb, BBSIZE)) { + xfs_err(mp, "unable to set blocksize"); + return -EINVAL; + } sb->s_xattr = xfs_xattr_handlers; sb->s_export_op = &xfs_export_operations; #ifdef CONFIG_XFS_QUOTA diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index ef7a931ebde5..8dde444596f1 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -1204,6 +1204,7 @@ xfs_mount_zones( .mp = mp, }; struct xfs_buftarg *bt = mp->m_rtdev_targp; + xfs_extlen_t zone_blocks = mp->m_groups[XG_TYPE_RTG].blocks; int error; if (!bt) { @@ -1234,10 +1235,33 @@ xfs_mount_zones( return -ENOMEM; xfs_info(mp, "%u zones of %u blocks (%u max open zones)", - mp->m_sb.sb_rgcount, mp->m_groups[XG_TYPE_RTG].blocks, - mp->m_max_open_zones); + mp->m_sb.sb_rgcount, zone_blocks, mp->m_max_open_zones); trace_xfs_zones_mount(mp); + /* + * The writeback code switches between inodes regularly to provide + * fairness. The default lower bound is 4MiB, but for zoned file + * systems we want to increase that both to reduce seeks, but also more + * importantly so that workloads that writes files in a multiple of the + * zone size do not get fragmented and require garbage collection when + * they shouldn't. Increase is to the zone size capped by the max + * extent len. + * + * Note that because s_min_writeback_pages is a superblock field, this + * value also get applied to non-zoned files on the data device if + * there are any. On typical zoned setup all data is on the RT device + * because using the more efficient sequential write required zones + * is the reason for using the zone allocator, and either the RT device + * and the (meta)data device are on the same block device, or the + * (meta)data device is on a fast SSD while the data on the RT device + * is on a SMR HDD. In any combination of the above cases enforcing + * the higher min_writeback_pages for non-RT inodes is either a noop + * or beneficial. + */ + mp->m_super->s_min_writeback_pages = + XFS_FSB_TO_B(mp, min(zone_blocks, XFS_MAX_BMBT_EXTLEN)) >> + PAGE_SHIFT; + if (bdev_is_zoned(bt->bt_bdev)) { error = blkdev_report_zones(bt->bt_bdev, XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart), diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 90e2ad8ee5f4..c1e5e30e90a0 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -112,12 +112,13 @@ static const struct iomap_ops zonefs_write_iomap_ops = { static int zonefs_read_folio(struct file *unused, struct folio *folio) { - return iomap_read_folio(folio, &zonefs_read_iomap_ops); + iomap_bio_read_folio(folio, &zonefs_read_iomap_ops); + return 0; } static void zonefs_readahead(struct readahead_control *rac) { - iomap_readahead(rac, &zonefs_read_iomap_ops); + iomap_bio_readahead(rac, &zonefs_read_iomap_ops); } /* diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 70be0b3dda49..086a31269198 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -644,7 +644,7 @@ static struct inode *zonefs_get_file_inode(struct inode *dir, inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) { + if (!(inode_state_read_once(inode) & I_NEW)) { WARN_ON_ONCE(inode->i_private != z); return inode; } @@ -683,7 +683,7 @@ static struct inode *zonefs_get_zgroup_inode(struct super_block *sb, inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) return inode; inode->i_ino = ino; |