diff options
Diffstat (limited to 'fs')
99 files changed, 796 insertions, 623 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index a7e28890f5ef..929b618da43b 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -282,32 +282,26 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, switch (handler->flags) { case ACL_TYPE_ACCESS: if (acl) { - umode_t mode = inode->i_mode; - retval = posix_acl_equiv_mode(acl, &mode); - if (retval < 0) + struct iattr iattr; + + retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); + if (retval) goto err_out; - else { - struct iattr iattr; - if (retval == 0) { - /* - * ACL can be represented - * by the mode bits. So don't - * update ACL. - */ - acl = NULL; - value = NULL; - size = 0; - } - /* Updte the mode bits */ - iattr.ia_mode = ((mode & S_IALLUGO) | - (inode->i_mode & ~S_IALLUGO)); - iattr.ia_valid = ATTR_MODE; - /* FIXME should we update ctime ? - * What is the following setxattr update the - * mode ? + if (!acl) { + /* + * ACL can be represented + * by the mode bits. So don't + * update ACL. */ - v9fs_vfs_setattr_dotl(dentry, &iattr); + value = NULL; + size = 0; } + iattr.ia_valid = ATTR_MODE; + /* FIXME should we update ctime ? + * What is the following setxattr update the + * mode ? + */ + v9fs_vfs_setattr_dotl(dentry, &iattr); } break; case ACL_TYPE_DEFAULT: @@ -239,7 +239,12 @@ static struct dentry *aio_mount(struct file_system_type *fs_type, static const struct dentry_operations ops = { .d_dname = simple_dname, }; - return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC); + struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops, + AIO_RING_MAGIC); + + if (!IS_ERR(root)) + root->d_sb->s_iflags |= SB_I_NOEXEC; + return root; } /* aio_setup diff --git a/fs/attr.c b/fs/attr.c index 6530ced19697..d62f674a605f 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -202,6 +202,21 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de return -EPERM; } + /* + * If utimes(2) and friends are called with times == NULL (or both + * times are UTIME_NOW), then we need to check for write permission + */ + if (ia_valid & ATTR_TOUCH) { + if (IS_IMMUTABLE(inode)) + return -EPERM; + + if (!inode_owner_or_capable(inode)) { + error = inode_permission(inode, MAY_WRITE); + if (error) + return error; + } + } + if ((ia_valid & ATTR_MODE)) { umode_t amode = attr->ia_mode; /* Flag setting protected by i_mutex */ diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index c37149b929be..502d3892d8a4 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -79,9 +79,13 @@ struct autofs_info { }; #define AUTOFS_INF_EXPIRING (1<<0) /* dentry is in the process of expiring */ -#define AUTOFS_INF_NO_RCU (1<<1) /* the dentry is being considered +#define AUTOFS_INF_WANT_EXPIRE (1<<1) /* the dentry is being considered * for expiry, so RCU_walk is - * not permitted + * not permitted. If it progresses to + * actual expiry attempt, the flag is + * not cleared when EXPIRING is set - + * in that case it gets cleared only + * when it comes to clearing EXPIRING. */ #define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */ diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 1cebc3c52fa5..7a5a598a2d94 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -315,19 +315,17 @@ struct dentry *autofs4_expire_direct(struct super_block *sb, if (ino->flags & AUTOFS_INF_PENDING) goto out; if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { - ino->flags |= AUTOFS_INF_NO_RCU; + ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); spin_lock(&sbi->fs_lock); if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { ino->flags |= AUTOFS_INF_EXPIRING; - smp_mb(); - ino->flags &= ~AUTOFS_INF_NO_RCU; init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); return root; } - ino->flags &= ~AUTOFS_INF_NO_RCU; + ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; } out: spin_unlock(&sbi->fs_lock); @@ -417,6 +415,7 @@ static struct dentry *should_expire(struct dentry *dentry, } return NULL; } + /* * Find an eligible tree to time-out * A tree is eligible if :- @@ -432,6 +431,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, struct dentry *root = sb->s_root; struct dentry *dentry; struct dentry *expired; + struct dentry *found; struct autofs_info *ino; if (!root) @@ -442,48 +442,54 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, dentry = NULL; while ((dentry = get_next_positive_subdir(dentry, root))) { + int flags = how; + spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(dentry); - if (ino->flags & AUTOFS_INF_NO_RCU) - expired = NULL; - else - expired = should_expire(dentry, mnt, timeout, how); - if (!expired) { + if (ino->flags & AUTOFS_INF_WANT_EXPIRE) { spin_unlock(&sbi->fs_lock); continue; } + spin_unlock(&sbi->fs_lock); + + expired = should_expire(dentry, mnt, timeout, flags); + if (!expired) + continue; + + spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(expired); - ino->flags |= AUTOFS_INF_NO_RCU; + ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); - spin_lock(&sbi->fs_lock); - if (should_expire(expired, mnt, timeout, how)) { - if (expired != dentry) - dput(dentry); - goto found; - } - ino->flags &= ~AUTOFS_INF_NO_RCU; + /* Make sure a reference is not taken on found if + * things have changed. + */ + flags &= ~AUTOFS_EXP_LEAVES; + found = should_expire(expired, mnt, timeout, how); + if (!found || found != expired) + /* Something has changed, continue */ + goto next; + if (expired != dentry) - dput(expired); + dput(dentry); + + spin_lock(&sbi->fs_lock); + goto found; +next: + spin_lock(&sbi->fs_lock); + ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); + if (expired != dentry) + dput(expired); } return NULL; found: DPRINTK("returning %p %pd", expired, expired); ino->flags |= AUTOFS_INF_EXPIRING; - smp_mb(); - ino->flags &= ~AUTOFS_INF_NO_RCU; init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); - spin_lock(&sbi->lookup_lock); - spin_lock(&expired->d_parent->d_lock); - spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&expired->d_parent->d_subdirs, &expired->d_child); - spin_unlock(&expired->d_lock); - spin_unlock(&expired->d_parent->d_lock); - spin_unlock(&sbi->lookup_lock); return expired; } @@ -492,15 +498,27 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk) struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); int status; + int state; /* Block on any pending expire */ - if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))) + if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE)) return 0; if (rcu_walk) return -ECHILD; +retry: spin_lock(&sbi->fs_lock); - if (ino->flags & AUTOFS_INF_EXPIRING) { + state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING); + if (state == AUTOFS_INF_WANT_EXPIRE) { + spin_unlock(&sbi->fs_lock); + /* + * Possibly being selected for expire, wait until + * it's selected or not. + */ + schedule_timeout_uninterruptible(HZ/10); + goto retry; + } + if (state & AUTOFS_INF_EXPIRING) { spin_unlock(&sbi->fs_lock); DPRINTK("waiting for expire %p name=%pd", dentry, dentry); @@ -551,7 +569,7 @@ int autofs4_expire_run(struct super_block *sb, ino = autofs4_dentry_ino(dentry); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = now; - ino->flags &= ~AUTOFS_INF_EXPIRING; + ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); @@ -579,7 +597,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, spin_lock(&sbi->fs_lock); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = now; - ino->flags &= ~AUTOFS_INF_EXPIRING; + ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); dput(dentry); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index c6d7d3dbd52a..7a54c6a867c8 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -455,7 +455,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk) * a mount-trap. */ struct inode *inode; - if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)) + if (ino->flags & AUTOFS_INF_WANT_EXPIRE) return 0; if (d_mountpoint(dentry)) return 0; diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 9a0124a95851..fb3e64d37cb4 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -83,11 +83,9 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &inode->i_mode); - if (ret < 0) + ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (ret) return ret; - if (ret == 0) - acl = NULL; } ret = 0; break; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index c473c42d7d6c..bae05c5c75ba 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -694,7 +694,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0); if (ret) { - bio->bi_error = ret; + comp_bio->bi_error = ret; bio_endio(comp_bio); } @@ -723,7 +723,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0); if (ret) { - bio->bi_error = ret; + comp_bio->bi_error = ret; bio_endio(comp_bio); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4bc9dbf29a73..3cff6523f27d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8691,9 +8691,14 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, * So even we call qgroup_free_data(), it won't decrease reserved * space. * 2) Not written to disk - * This means the reserved space should be freed here. + * This means the reserved space should be freed here. However, + * if a truncate invalidates the page (by clearing PageDirty) + * and the page is accounted for while allocating extent + * in btrfs_check_data_free_space() we let delayed_ref to + * free the entire extent. */ - btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE); + if (PageDirty(page)) + btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 65f30b3b04f9..a7e18dbadf74 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1619,6 +1619,9 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, int namelen; int ret = 0; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + ret = mnt_want_write_file(file); if (ret) goto out; @@ -1676,6 +1679,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, struct btrfs_ioctl_vol_args *vol_args; int ret; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -1699,6 +1705,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, bool readonly = false; struct btrfs_qgroup_inherit *inherit = NULL; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -2345,6 +2354,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, int ret; int err = 0; + if (!S_ISDIR(dir->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 0e044d7ee721..f7441193bf35 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2696,14 +2696,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root, int index, int error) { struct btrfs_log_ctx *ctx; + struct btrfs_log_ctx *safe; - if (!error) { - INIT_LIST_HEAD(&root->log_ctxs[index]); - return; - } - - list_for_each_entry(ctx, &root->log_ctxs[index], list) + list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) { + list_del_init(&ctx->list); ctx->log_ret = error; + } INIT_LIST_HEAD(&root->log_ctxs[index]); } @@ -2850,6 +2848,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { blk_finish_plug(&plug); + list_del_init(&root_log_ctx.list); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; @@ -2943,13 +2942,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&root->log_mutex); out_wake_log_root: - /* - * We needn't get log_mutex here because we are sure all - * the other tasks are blocked. - */ + mutex_lock(&log_root_tree->log_mutex); btrfs_remove_all_log_ctxs(log_root_tree, index2, ret); - mutex_lock(&log_root_tree->log_mutex); log_root_tree->log_transid_committed++; atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); @@ -2960,10 +2955,8 @@ out_wake_log_root: if (waitqueue_active(&log_root_tree->log_commit_wait[index2])) wake_up(&log_root_tree->log_commit_wait[index2]); out: - /* See above. */ - btrfs_remove_all_log_ctxs(root, index1, ret); - mutex_lock(&root->log_mutex); + btrfs_remove_all_log_ctxs(root, index1, ret); root->log_transid_committed++; atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 8f84646f10e9..4d8caeb94a11 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -94,11 +94,9 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &new_mode); - if (ret < 0) + ret = posix_acl_update_mode(inode, &new_mode, &acl); + if (ret) goto out; - if (ret == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 3c68e6aee2f0..c8222bfe1e56 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -929,7 +929,8 @@ again: statret = __ceph_do_getattr(inode, page, CEPH_STAT_CAP_INLINE_DATA, !!page); if (statret < 0) { - __free_page(page); + if (page) + __free_page(page); if (statret == -ENODATA) { BUG_ON(retry_op != READ_INLINE); goto again; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 498dcfa2dcdb..d98536c8abfc 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1358,15 +1358,20 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn, if (!ctl->page || pgoff != page_index(ctl->page)) { ceph_readdir_cache_release(ctl); - ctl->page = grab_cache_page(&dir->i_data, pgoff); + if (idx == 0) + ctl->page = grab_cache_page(&dir->i_data, pgoff); + else + ctl->page = find_lock_page(&dir->i_data, pgoff); if (!ctl->page) { ctl->index = -1; - return -ENOMEM; + return idx == 0 ? -ENOMEM : 0; } /* reading/filling the cache are serialized by * i_mutex, no need to use page lock */ unlock_page(ctl->page); ctl->dentries = kmap(ctl->page); + if (idx == 0) + memset(ctl->dentries, 0, PAGE_CACHE_SIZE); } if (req->r_dir_release_cnt == atomic64_read(&ci->i_release_count) && diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 50b268483302..0a3544fb50f9 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -152,6 +152,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) list_for_each(tmp1, &cifs_tcp_ses_list) { server = list_entry(tmp1, struct TCP_Server_Info, tcp_ses_list); + seq_printf(m, "\nNumber of credits: %d", server->credits); i++; list_for_each(tmp2, &server->smb_ses_list) { ses = list_entry(tmp2, struct cifs_ses, @@ -255,7 +256,6 @@ static const struct file_operations cifs_debug_data_proc_fops = { static ssize_t cifs_stats_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - char c; bool bv; int rc; struct list_head *tmp1, *tmp2, *tmp3; @@ -263,11 +263,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, struct cifs_ses *ses; struct cifs_tcon *tcon; - rc = get_user(c, buffer); - if (rc) - return rc; - - if (strtobool(&c, &bv) == 0) { + rc = kstrtobool_from_user(buffer, count, &bv); + if (rc == 0) { #ifdef CONFIG_CIFS_STATS2 atomic_set(&totBufAllocCount, 0); atomic_set(&totSmBufAllocCount, 0); @@ -290,6 +287,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, } } spin_unlock(&cifs_tcp_ses_lock); + } else { + return rc; } return count; @@ -433,17 +432,17 @@ static int cifsFYI_proc_open(struct inode *inode, struct file *file) static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - char c; + char c[2] = { '\0' }; bool bv; int rc; - rc = get_user(c, buffer); + rc = get_user(c[0], buffer); if (rc) return rc; - if (strtobool(&c, &bv) == 0) + if (strtobool(c, &bv) == 0) cifsFYI = bv; - else if ((c > '1') && (c <= '9')) - cifsFYI = (int) (c - '0'); /* see cifs_debug.h for meanings */ + else if ((c[0] > '1') && (c[0] <= '9')) + cifsFYI = (int) (c[0] - '0'); /* see cifs_debug.h for meanings */ return count; } @@ -471,20 +470,12 @@ static int cifs_linux_ext_proc_open(struct inode *inode, struct file *file) static ssize_t cifs_linux_ext_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - char c; - bool bv; int rc; - rc = get_user(c, buffer); + rc = kstrtobool_from_user(buffer, count, &linuxExtEnabled); if (rc) return rc; - rc = strtobool(&c, &bv); - if (rc) - return rc; - - linuxExtEnabled = bv; - return count; } @@ -511,20 +502,12 @@ static int cifs_lookup_cache_proc_open(struct inode *inode, struct file *file) static ssize_t cifs_lookup_cache_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - char c; - bool bv; int rc; - rc = get_user(c, buffer); + rc = kstrtobool_from_user(buffer, count, &lookupCacheEnabled); if (rc) return rc; - rc = strtobool(&c, &bv); - if (rc) - return rc; - - lookupCacheEnabled = bv; - return count; } @@ -551,20 +534,12 @@ static int traceSMB_proc_open(struct inode *inode, struct file *file) static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - char c; - bool bv; int rc; - rc = get_user(c, buffer); + rc = kstrtobool_from_user(buffer, count, &traceSMB); if (rc) return rc; - rc = strtobool(&c, &bv); - if (rc) - return rc; - - traceSMB = bv; - return count; } @@ -622,7 +597,6 @@ static ssize_t cifs_security_flags_proc_write(struct file *file, int rc; unsigned int flags; char flags_string[12]; - char c; bool bv; if ((count < 1) || (count > 11)) @@ -635,11 +609,10 @@ static ssize_t cifs_security_flags_proc_write(struct file *file, if (count < 3) { /* single char or single char followed by null */ - c = flags_string[0]; - if (strtobool(&c, &bv) == 0) { + if (strtobool(flags_string, &bv) == 0) { global_secflags = bv ? CIFSSEC_MAX : CIFSSEC_DEF; return count; - } else if (!isdigit(c)) { + } else if (!isdigit(flags_string[0])) { cifs_dbg(VFS, "Invalid SecurityFlags: %s\n", flags_string); return -EINVAL; diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index 66cf0f9fff89..c611ca2339d7 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -25,7 +25,7 @@ void cifs_dump_mem(char *label, void *data, int length); void cifs_dump_detail(void *); void cifs_dump_mids(struct TCP_Server_Info *); -extern int traceSMB; /* flag which enables the function below */ +extern bool traceSMB; /* flag which enables the function below */ void dump_smb(void *, int); #define CIFS_INFO 0x01 #define CIFS_RC 0x02 diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 450578097fb7..4f4fc9ff3636 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -54,10 +54,10 @@ #endif int cifsFYI = 0; -int traceSMB = 0; +bool traceSMB; bool enable_oplocks = true; -unsigned int linuxExtEnabled = 1; -unsigned int lookupCacheEnabled = 1; +bool linuxExtEnabled = true; +bool lookupCacheEnabled = true; unsigned int global_secflags = CIFSSEC_DEF; /* unsigned int ntlmv2_support = 0; */ unsigned int sign_CIFS_PDUs = 1; @@ -268,7 +268,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode->createtime = 0; cifs_inode->epoch = 0; #ifdef CONFIG_CIFS_SMB2 - get_random_bytes(cifs_inode->lease_key, SMB2_LEASE_KEY_SIZE); + generate_random_uuid(cifs_inode->lease_key); #endif /* * Can not set i_flags here - they get immediately overwritten to zero @@ -1210,7 +1210,6 @@ init_cifs(void) GlobalTotalActiveXid = 0; GlobalMaxActiveXid = 0; spin_lock_init(&cifs_tcp_ses_lock); - spin_lock_init(&cifs_file_list_lock); spin_lock_init(&GlobalMid_Lock); if (cifs_max_pending < 2) { diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 2b510c537a0d..c669a1471395 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -827,6 +827,7 @@ struct cifs_tcon { struct list_head tcon_list; int tc_count; struct list_head openFileList; + spinlock_t open_file_lock; /* protects list above */ struct cifs_ses *ses; /* pointer to session associated with */ char treeName[MAX_TREE_SIZE + 1]; /* UNC name of resource in ASCII */ char *nativeFileSystem; @@ -883,7 +884,7 @@ struct cifs_tcon { #endif /* CONFIG_CIFS_STATS2 */ __u64 bytes_read; __u64 bytes_written; - spinlock_t stat_lock; + spinlock_t stat_lock; /* protects the two fields above */ #endif /* CONFIG_CIFS_STATS */ FILE_SYSTEM_DEVICE_INFO fsDevInfo; FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */ @@ -1034,8 +1035,10 @@ struct cifs_fid_locks { }; struct cifsFileInfo { + /* following two lists are protected by tcon->open_file_lock */ struct list_head tlist; /* pointer to next fid owned by tcon */ struct list_head flist; /* next fid (file instance) for this inode */ + /* lock list below protected by cifsi->lock_sem */ struct cifs_fid_locks *llist; /* brlocks held by this fid */ kuid_t uid; /* allows finding which FileInfo structure */ __u32 pid; /* process id who opened file */ @@ -1043,11 +1046,12 @@ struct cifsFileInfo { /* BB add lock scope info here if needed */ ; /* lock scope id (0 if none) */ struct dentry *dentry; - unsigned int f_flags; struct tcon_link *tlink; + unsigned int f_flags; bool invalidHandle:1; /* file closed via session abend */ bool oplock_break_cancelled:1; - int count; /* refcount protected by cifs_file_list_lock */ + int count; + spinlock_t file_info_lock; /* protects four flag/count fields above */ struct mutex fh_mutex; /* prevents reopen race after dead ses*/ struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ @@ -1114,7 +1118,7 @@ struct cifs_writedata { /* * Take a reference on the file private data. Must be called with - * cifs_file_list_lock held. + * cfile->file_info_lock held. */ static inline void cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) @@ -1508,8 +1512,10 @@ require use of the stronger protocol */ * GlobalMid_Lock protects: * list operations on pending_mid_q and oplockQ * updates to XID counters, multiplex id and SMB sequence numbers - * cifs_file_list_lock protects: - * list operations on tcp and SMB session lists and tCon lists + * tcp_ses_lock protects: + * list operations on tcp and SMB session lists + * tcon->open_file_lock protects the list of open files hanging off the tcon + * cfile->file_info_lock protects counters and fields in cifs file struct * f_owner.lock protects certain per file struct operations * mapping->page_lock protects certain per page operations * @@ -1541,18 +1547,12 @@ GLOBAL_EXTERN struct list_head cifs_tcp_ses_list; * tcp session, and the list of tcon's per smb session. It also protects * the reference counters for the server, smb session, and tcon. Finally, * changes to the tcon->tidStatus should be done while holding this lock. + * generally the locks should be taken in order tcp_ses_lock before + * tcon->open_file_lock and that before file->file_info_lock since the + * structure order is cifs_socket-->cifs_ses-->cifs_tcon-->cifs_file */ GLOBAL_EXTERN spinlock_t cifs_tcp_ses_lock; -/* - * This lock protects the cifs_file->llist and cifs_file->flist - * list operations, and updates to some flags (cifs_file->invalidHandle) - * It will be moved to either use the tcon->stat_lock or equivalent later. - * If cifs_tcp_ses_lock and the lock below are both needed to be held, then - * the cifs_tcp_ses_lock must be grabbed first and released last. - */ -GLOBAL_EXTERN spinlock_t cifs_file_list_lock; - #ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */ /* Outstanding dir notify requests */ GLOBAL_EXTERN struct list_head GlobalDnotifyReqList; @@ -1588,11 +1588,11 @@ GLOBAL_EXTERN atomic_t midCount; /* Misc globals */ GLOBAL_EXTERN bool enable_oplocks; /* enable or disable oplocks */ -GLOBAL_EXTERN unsigned int lookupCacheEnabled; +GLOBAL_EXTERN bool lookupCacheEnabled; GLOBAL_EXTERN unsigned int global_secflags; /* if on, session setup sent with more secure ntlmssp2 challenge/resp */ GLOBAL_EXTERN unsigned int sign_CIFS_PDUs; /* enable smb packet signing */ -GLOBAL_EXTERN unsigned int linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/ +GLOBAL_EXTERN bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/ GLOBAL_EXTERN unsigned int CIFSMaxBufSize; /* max size not including hdr */ GLOBAL_EXTERN unsigned int cifs_min_rcv; /* min size of big ntwrk buf pool */ GLOBAL_EXTERN unsigned int cifs_min_small; /* min size of small buf pool */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 76fcb50295a3..b1104ed8f54c 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -98,13 +98,13 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) struct list_head *tmp1; /* list all files open on tree connection and mark them invalid */ - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); list_for_each_safe(tmp, tmp1, &tcon->openFileList) { open_file = list_entry(tmp, struct cifsFileInfo, tlist); open_file->invalidHandle = true; open_file->oplock_break_cancelled = true; } - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); /* * BB Add call to invalidate_inodes(sb) for all superblocks mounted * to this tcon. diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 61c3a5ab8637..812a8cb07c63 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2200,7 +2200,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr, sizeof(tcp_ses->dstaddr)); #ifdef CONFIG_CIFS_SMB2 - get_random_bytes(tcp_ses->client_guid, SMB2_CLIENT_GUID_SIZE); + generate_random_uuid(tcp_ses->client_guid); #endif /* * at this point we are the only ones with the pointer @@ -3693,14 +3693,16 @@ remote_path_check: goto mount_fail_check; } - rc = cifs_are_all_path_components_accessible(server, + if (rc != -EREMOTE) { + rc = cifs_are_all_path_components_accessible(server, xid, tcon, cifs_sb, full_path); - if (rc != 0) { - cifs_dbg(VFS, "cannot query dirs between root and final path, " - "enabling CIFS_MOUNT_USE_PREFIX_PATH\n"); - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; - rc = 0; + if (rc != 0) { + cifs_dbg(VFS, "cannot query dirs between root and final path, " + "enabling CIFS_MOUNT_USE_PREFIX_PATH\n"); + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; + rc = 0; + } } kfree(full_path); } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0068e82217c3..72f270d4bd17 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -305,6 +305,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); mutex_init(&cfile->fh_mutex); + spin_lock_init(&cfile->file_info_lock); cifs_sb_active(inode->i_sb); @@ -317,7 +318,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, oplock = 0; } - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE && oplock) oplock = fid->pending_open->oplock; list_del(&fid->pending_open->olist); @@ -326,12 +327,13 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, server->ops->set_fid(cfile, fid, oplock); list_add(&cfile->tlist, &tcon->openFileList); + /* if readable file instance put first in list*/ if (file->f_mode & FMODE_READ) list_add(&cfile->flist, &cinode->openFileList); else list_add_tail(&cfile->flist, &cinode->openFileList); - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); if (fid->purge_cache) cifs_zap_mapping(inode); @@ -343,16 +345,16 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct cifsFileInfo * cifsFileInfo_get(struct cifsFileInfo *cifs_file) { - spin_lock(&cifs_file_list_lock); + spin_lock(&cifs_file->file_info_lock); cifsFileInfo_get_locked(cifs_file); - spin_unlock(&cifs_file_list_lock); + spin_unlock(&cifs_file->file_info_lock); return cifs_file; } /* * Release a reference on the file private data. This may involve closing * the filehandle out on the server. Must be called without holding - * cifs_file_list_lock. + * tcon->open_file_lock and cifs_file->file_info_lock. */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { @@ -367,11 +369,15 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) struct cifs_pending_open open; bool oplock_break_cancelled; - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); + + spin_lock(&cifs_file->file_info_lock); if (--cifs_file->count > 0) { - spin_unlock(&cifs_file_list_lock); + spin_unlock(&cifs_file->file_info_lock); + spin_unlock(&tcon->open_file_lock); return; } + spin_unlock(&cifs_file->file_info_lock); if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &fid); @@ -395,7 +401,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags); cifs_set_oplock_level(cifsi, 0); } - spin_unlock(&cifs_file_list_lock); + + spin_unlock(&tcon->open_file_lock); oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); @@ -772,10 +779,10 @@ int cifs_closedir(struct inode *inode, struct file *file) server = tcon->ses->server; cifs_dbg(FYI, "Freeing private data in close dir\n"); - spin_lock(&cifs_file_list_lock); + spin_lock(&cfile->file_info_lock); if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; - spin_unlock(&cifs_file_list_lock); + spin_unlock(&cfile->file_info_lock); if (server->ops->close_dir) rc = server->ops->close_dir(xid, tcon, &cfile->fid); else @@ -784,7 +791,7 @@ int cifs_closedir(struct inode *inode, struct file *file) /* not much we can do if it fails anyway, ignore rc */ rc = 0; } else - spin_unlock(&cifs_file_list_lock); + spin_unlock(&cfile->file_info_lock); buf = cfile->srch_inf.ntwrk_buf_start; if (buf) { @@ -1720,12 +1727,13 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, { struct cifsFileInfo *open_file = NULL; struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); + struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); /* only filter by fsuid on multiuser mounts */ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) fsuid_only = false; - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); /* we could simply get the first_list_entry since write-only entries are always at the end of the list but since the first entry might have a close pending, we go through the whole list */ @@ -1736,8 +1744,8 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, if (!open_file->invalidHandle) { /* found a good file */ /* lock it so it will not be closed on us */ - cifsFileInfo_get_locked(open_file); - spin_unlock(&cifs_file_list_lock); + cifsFileInfo_get(open_file); + spin_unlock(&tcon->open_file_lock); return open_file; } /* else might as well continue, and look for another, or simply have the caller reopen it @@ -1745,7 +1753,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, } else /* write only file */ break; /* write only files are last so must be done */ } - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); return NULL; } @@ -1754,6 +1762,7 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, { struct cifsFileInfo *open_file, *inv_file = NULL; struct cifs_sb_info *cifs_sb; + struct cifs_tcon *tcon; bool any_available = false; int rc; unsigned int refind = 0; @@ -1769,15 +1778,16 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, } cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); + tcon = cifs_sb_master_tcon(cifs_sb); /* only filter by fsuid on multiuser mounts */ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) fsuid_only = false; - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); refind_writable: if (refind > MAX_REOPEN_ATT) { - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); return NULL; } list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { @@ -1788,8 +1798,8 @@ refind_writable: if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { if (!open_file->invalidHandle) { /* found a good writable file */ - cifsFileInfo_get_locked(open_file); - spin_unlock(&cifs_file_list_lock); + cifsFileInfo_get(open_file); + spin_unlock(&tcon->open_file_lock); return open_file; } else { if (!inv_file) @@ -1805,24 +1815,24 @@ refind_writable: if (inv_file) { any_available = false; - cifsFileInfo_get_locked(inv_file); + cifsFileInfo_get(inv_file); } - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); if (inv_file) { rc = cifs_reopen_file(inv_file, false); if (!rc) return inv_file; else { - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); list_move_tail(&inv_file->flist, &cifs_inode->openFileList); - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); cifsFileInfo_put(inv_file); - spin_lock(&cifs_file_list_lock); ++refind; inv_file = NULL; + spin_lock(&tcon->open_file_lock); goto refind_writable; } } @@ -3632,15 +3642,17 @@ static int cifs_readpage(struct file *file, struct page *page) static int is_inode_writable(struct cifsInodeInfo *cifs_inode) { struct cifsFileInfo *open_file; + struct cifs_tcon *tcon = + cifs_sb_master_tcon(CIFS_SB(cifs_inode->vfs_inode.i_sb)); - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); return 1; } } - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); return 0; } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 8442b8b8e0be..2396ab099849 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -120,6 +120,7 @@ tconInfoAlloc(void) ++ret_buf->tc_count; INIT_LIST_HEAD(&ret_buf->openFileList); INIT_LIST_HEAD(&ret_buf->tcon_list); + spin_lock_init(&ret_buf->open_file_lock); #ifdef CONFIG_CIFS_STATS spin_lock_init(&ret_buf->stat_lock); #endif @@ -465,7 +466,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) continue; cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks); - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); list_for_each(tmp2, &tcon->openFileList) { netfile = list_entry(tmp2, struct cifsFileInfo, tlist); @@ -495,11 +496,11 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) &netfile->oplock_break); netfile->oplock_break_cancelled = false; - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); return true; } - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); cifs_dbg(FYI, "No matching file for oplock break\n"); return true; @@ -613,9 +614,9 @@ backup_cred(struct cifs_sb_info *cifs_sb) void cifs_del_pending_open(struct cifs_pending_open *open) { - spin_lock(&cifs_file_list_lock); + spin_lock(&tlink_tcon(open->tlink)->open_file_lock); list_del(&open->olist); - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tlink_tcon(open->tlink)->open_file_lock); } void @@ -635,7 +636,7 @@ void cifs_add_pending_open(struct cifs_fid *fid, struct tcon_link *tlink, struct cifs_pending_open *open) { - spin_lock(&cifs_file_list_lock); + spin_lock(&tlink_tcon(tlink)->open_file_lock); cifs_add_pending_open_locked(fid, tlink, open); - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tlink_tcon(open->tlink)->open_file_lock); } diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index b30a4a6d98a0..833e5844a2db 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -594,14 +594,14 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, is_dir_changed(file)) || (index_to_find < first_entry_in_buffer)) { /* close and restart search */ cifs_dbg(FYI, "search backing up - close and restart search\n"); - spin_lock(&cifs_file_list_lock); + spin_lock(&cfile->file_info_lock); if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; - spin_unlock(&cifs_file_list_lock); + spin_unlock(&cfile->file_info_lock); if (server->ops->close_dir) server->ops->close_dir(xid, tcon, &cfile->fid); } else - spin_unlock(&cifs_file_list_lock); + spin_unlock(&cfile->file_info_lock); if (cfile->srch_inf.ntwrk_buf_start) { cifs_dbg(FYI, "freeing SMB ff cache buf on search rewind\n"); if (cfile->srch_inf.smallBuf) diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index 0ffa18094335..238759c146ba 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -61,4 +61,14 @@ /* Maximum buffer size value we can send with 1 credit */ #define SMB2_MAX_BUFFER_SIZE 65536 +/* + * Maximum number of credits to keep available. + * This value is chosen somewhat arbitrarily. The Windows client + * defaults to 128 credits, the Windows server allows clients up to + * 512 credits, and the NetApp server does not limit clients at all. + * Choose a high enough value such that the client shouldn't limit + * performance. + */ +#define SMB2_MAX_CREDITS_AVAILABLE 32000 + #endif /* _SMB2_GLOB_H */ diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 4f0231e685a9..1238cd3552f9 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -266,9 +266,15 @@ smb2_set_file_info(struct inode *inode, const char *full_path, struct tcon_link *tlink; int rc; + if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) && + (buf->LastWriteTime == 0) && (buf->ChangeTime) && + (buf->Attributes == 0)) + return 0; /* would be a no op, no sense sending this */ + tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); + rc = smb2_open_op_close(xid, tlink_tcon(tlink), cifs_sb, full_path, FILE_WRITE_ATTRIBUTES, FILE_OPEN, 0, buf, SMB2_OP_SET_INFO); diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 1c5907019045..e5bc85e49be7 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -525,19 +525,19 @@ smb2_is_valid_lease_break(char *buffer) list_for_each(tmp1, &server->smb_ses_list) { ses = list_entry(tmp1, struct cifs_ses, smb_ses_list); - spin_lock(&cifs_file_list_lock); list_for_each(tmp2, &ses->tcon_list) { tcon = list_entry(tmp2, struct cifs_tcon, tcon_list); + spin_lock(&tcon->open_file_lock); cifs_stats_inc( &tcon->stats.cifs_stats.num_oplock_brks); if (smb2_tcon_has_lease(tcon, rsp, lw)) { - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); return true; } + spin_unlock(&tcon->open_file_lock); } - spin_unlock(&cifs_file_list_lock); } } spin_unlock(&cifs_tcp_ses_lock); @@ -579,7 +579,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks); - spin_lock(&cifs_file_list_lock); + spin_lock(&tcon->open_file_lock); list_for_each(tmp2, &tcon->openFileList) { cfile = list_entry(tmp2, struct cifsFileInfo, tlist); @@ -591,7 +591,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) cifs_dbg(FYI, "file id match, oplock break\n"); cinode = CIFS_I(d_inode(cfile->dentry)); - + spin_lock(&cfile->file_info_lock); if (!CIFS_CACHE_WRITE(cinode) && rsp->OplockLevel == SMB2_OPLOCK_LEVEL_NONE) cfile->oplock_break_cancelled = true; @@ -613,14 +613,14 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) clear_bit( CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); - + spin_unlock(&cfile->file_info_lock); queue_work(cifsiod_wq, &cfile->oplock_break); - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); return true; } - spin_unlock(&cifs_file_list_lock); + spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); cifs_dbg(FYI, "No matching file for oplock break\n"); return true; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index dd8543caa56e..be34b4860675 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -282,7 +282,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) cifs_dbg(FYI, "Link Speed %lld\n", le64_to_cpu(out_buf->LinkSpeed)); } - + kfree(out_buf); return rc; } #endif /* STATS2 */ @@ -536,6 +536,7 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) server->ops->set_oplock_level(cinode, oplock, fid->epoch, &fid->purge_cache); cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); + memcpy(cfile->fid.create_guid, fid->create_guid, 16); } static void @@ -694,6 +695,7 @@ smb2_clone_range(const unsigned int xid, cchunk_out: kfree(pcchunk); + kfree(retbuf); return rc; } @@ -818,7 +820,6 @@ smb2_duplicate_extents(const unsigned int xid, { int rc; unsigned int ret_data_len; - char *retbuf = NULL; struct duplicate_extents_to_file dup_ext_buf; struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink); @@ -844,7 +845,7 @@ smb2_duplicate_extents(const unsigned int xid, FSCTL_DUPLICATE_EXTENTS_TO_FILE, true /* is_fsctl */, (char *)&dup_ext_buf, sizeof(struct duplicate_extents_to_file), - (char **)&retbuf, + NULL, &ret_data_len); if (ret_data_len > 0) @@ -867,7 +868,6 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *cfile) { struct fsctl_set_integrity_information_req integr_info; - char *retbuf = NULL; unsigned int ret_data_len; integr_info.ChecksumAlgorithm = cpu_to_le16(CHECKSUM_TYPE_UNCHANGED); @@ -879,7 +879,7 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, FSCTL_SET_INTEGRITY_INFORMATION, true /* is_fsctl */, (char *)&integr_info, sizeof(struct fsctl_set_integrity_information_req), - (char **)&retbuf, + NULL, &ret_data_len); } @@ -1036,7 +1036,7 @@ smb2_set_lease_key(struct inode *inode, struct cifs_fid *fid) static void smb2_new_lease_key(struct cifs_fid *fid) { - get_random_bytes(fid->lease_key, SMB2_LEASE_KEY_SIZE); + generate_random_uuid(fid->lease_key); } #define SMB2_SYMLINK_STRUCT_SIZE \ diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 0b6dc1942bdc..0dbbdf5e4aee 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -103,7 +103,21 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ , hdr->ProtocolId[3] = 'B'; hdr->StructureSize = cpu_to_le16(64); hdr->Command = smb2_cmd; - hdr->CreditRequest = cpu_to_le16(2); /* BB make this dynamic */ + if (tcon && tcon->ses && tcon->ses->server) { + struct TCP_Server_Info *server = tcon->ses->server; + + spin_lock(&server->req_lock); + /* Request up to 2 credits but don't go over the limit. */ + if (server->credits >= SMB2_MAX_CREDITS_AVAILABLE) + hdr->CreditRequest = cpu_to_le16(0); + else + hdr->CreditRequest = cpu_to_le16( + min_t(int, SMB2_MAX_CREDITS_AVAILABLE - + server->credits, 2)); + spin_unlock(&server->req_lock); + } else { + hdr->CreditRequest = cpu_to_le16(2); + } hdr->ProcessId = cpu_to_le32((__u16)current->tgid); if (!tcon) @@ -593,6 +607,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, char *security_blob = NULL; unsigned char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ + u64 previous_session = ses->Suid; cifs_dbg(FYI, "Session Setup\n"); @@ -630,6 +645,10 @@ ssetup_ntlmssp_authenticate: return rc; req->hdr.SessionId = 0; /* First session, not a reauthenticate */ + + /* if reconnect, we need to send previous sess id, otherwise it is 0 */ + req->PreviousSessionId = previous_session; + req->Flags = 0; /* MBZ */ /* to enable echos and oplocks */ req->hdr.CreditRequest = cpu_to_le16(3); @@ -1167,7 +1186,7 @@ create_durable_v2_buf(struct cifs_fid *pfid) buf->dcontext.Timeout = 0; /* Should this be configurable by workload */ buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); - get_random_bytes(buf->dcontext.CreateGuid, 16); + generate_random_uuid(buf->dcontext.CreateGuid); memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16); /* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */ @@ -2059,6 +2078,7 @@ smb2_async_readv(struct cifs_readdata *rdata) if (rdata->credits) { buf->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes, SMB2_MAX_BUFFER_SIZE)); + buf->CreditRequest = buf->CreditCharge; spin_lock(&server->req_lock); server->credits += rdata->credits - le16_to_cpu(buf->CreditCharge); @@ -2245,6 +2265,7 @@ smb2_async_writev(struct cifs_writedata *wdata, if (wdata->credits) { req->hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes, SMB2_MAX_BUFFER_SIZE)); + req->hdr.CreditRequest = req->hdr.CreditCharge; spin_lock(&server->req_lock); server->credits += wdata->credits - le16_to_cpu(req->hdr.CreditCharge); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 4af52780ec35..b8f553b32dda 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -276,7 +276,7 @@ struct smb2_sess_setup_req { __le32 Channel; __le16 SecurityBufferOffset; __le16 SecurityBufferLength; - __le64 PreviousSessionId; + __u64 PreviousSessionId; __u8 Buffer[1]; /* variable length GSS security buffer */ } __packed; diff --git a/fs/coredump.c b/fs/coredump.c index dfc87c5f5a54..5d15c4975ba1 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1,6 +1,7 @@ #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/freezer.h> #include <linux/mm.h> #include <linux/stat.h> #include <linux/fcntl.h> @@ -399,7 +400,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state) if (core_waiters > 0) { struct core_thread *ptr; + freezer_do_not_count(); wait_for_completion(&core_state->startup); + freezer_count(); /* * Wait for all the threads to become inactive, so that * all the thread context (extended register state, like diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 3a37bd3f9637..9d7a4a714907 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1607,16 +1607,12 @@ void dlm_lowcomms_stop(void) mutex_lock(&connections_lock); dlm_allow_conn = 0; foreach_conn(stop_conn); + clean_writequeues(); + foreach_conn(free_conn); mutex_unlock(&connections_lock); work_stop(); - mutex_lock(&connections_lock); - clean_writequeues(); - - foreach_conn(free_conn); - - mutex_unlock(&connections_lock); kmem_cache_destroy(con_cache); } diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 27695e6f4e46..d6aeb84e90b6 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -193,15 +193,11 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - inode->i_ctime = CURRENT_TIME_SEC; - mark_inode_dirty(inode); - if (error == 0) - acl = NULL; - } + inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(inode); } break; diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 69b1e73026a5..c3fe1e323951 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -196,15 +196,11 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - if (error == 0) - acl = NULL; - } + inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); } break; diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c index ad050698143f..8a9feb341f31 100644 --- a/fs/ext4/crypto_policy.c +++ b/fs/ext4/crypto_policy.c @@ -102,6 +102,9 @@ static int ext4_create_encryption_context_from_policy( int ext4_process_policy(const struct ext4_encryption_policy *policy, struct inode *inode) { + if (!inode_owner_or_capable(inode)) + return -EACCES; + if (policy->version != 0) return -EINVAL; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5d9d0be2770c..14d7f72f8092 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -221,6 +221,7 @@ struct ext4_io_submit { #define EXT4_MAX_BLOCK_SIZE 65536 #define EXT4_MIN_BLOCK_LOG_SIZE 10 #define EXT4_MAX_BLOCK_LOG_SIZE 16 +#define EXT4_MAX_CLUSTER_LOG_SIZE 30 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 8eac7d586997..9da42ace762a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5738,6 +5738,9 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } + } else { + ext4_ext_drop_refs(path); + kfree(path); } ret = ext4_es_remove_extent(inode, offset_lblk, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 55a1b5c0072a..eaab159a9c89 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3652,7 +3652,7 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, } /* - * ext4_punch_hole: punches a hole in a file by releaseing the blocks + * ext4_punch_hole: punches a hole in a file by releasing the blocks * associated with the given offset and length * * @inode: File inode @@ -3682,7 +3682,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) * Write out all dirty pages to avoid race conditions * Then release them. */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { ret = filemap_write_and_wait_range(mapping, offset, offset + length - 1); if (ret) @@ -4563,14 +4563,14 @@ static int ext4_do_update_inode(handle_t *handle, * Fix up interoperability with old kernels. Otherwise, old inodes get * re-used with the upper 16 bits of the uid/gid intact */ - if (!ei->i_dtime) { + if (ei->i_dtime && list_empty(&ei->i_orphan)) { + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } else { raw_inode->i_uid_high = cpu_to_le16(high_16_bits(i_uid)); raw_inode->i_gid_high = cpu_to_le16(high_16_bits(i_gid)); - } else { - raw_inode->i_uid_high = 0; - raw_inode->i_gid_high = 0; } } else { raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 95315b1f4b71..7e974878d9a9 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -633,7 +633,13 @@ resizefs_out: goto encryption_policy_out; } + err = mnt_want_write_file(filp); + if (err) + goto encryption_policy_out; + err = ext4_process_policy(&policy, inode); + + mnt_drop_write_file(filp); encryption_policy_out: return err; #else diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a0daca4b127b..0b1c97875686 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -815,7 +815,7 @@ static void mb_regenerate_buddy(struct ext4_buddy *e4b) * for this page; do not hold this lock when calling this routine! */ -static int ext4_mb_init_cache(struct page *page, char *incore) +static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) { ext4_group_t ngroups; int blocksize; @@ -848,7 +848,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) /* allocate buffer_heads to read bitmaps */ if (groups_per_page > 1) { i = sizeof(struct buffer_head *) * groups_per_page; - bh = kzalloc(i, GFP_NOFS); + bh = kzalloc(i, gfp); if (bh == NULL) { err = -ENOMEM; goto out; @@ -983,7 +983,7 @@ out: * are on the same page e4b->bd_buddy_page is NULL and return value is 0. */ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, - ext4_group_t group, struct ext4_buddy *e4b) + ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { struct inode *inode = EXT4_SB(sb)->s_buddy_cache; int block, pnum, poff; @@ -1002,7 +1002,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; - page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, pnum, gfp); if (!page) return -ENOMEM; BUG_ON(page->mapping != inode->i_mapping); @@ -1016,7 +1016,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, block++; pnum = block / blocks_per_page; - page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, pnum, gfp); if (!page) return -ENOMEM; BUG_ON(page->mapping != inode->i_mapping); @@ -1042,7 +1042,7 @@ static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b) * calling this routine! */ static noinline_for_stack -int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) +int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) { struct ext4_group_info *this_grp; @@ -1062,7 +1062,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) * The call to ext4_mb_get_buddy_page_lock will mark the * page accessed. */ - ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b); + ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { /* * somebody initialized the group @@ -1072,7 +1072,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) } page = e4b.bd_bitmap_page; - ret = ext4_mb_init_cache(page, NULL); + ret = ext4_mb_init_cache(page, NULL, gfp); if (ret) goto err; if (!PageUptodate(page)) { @@ -1091,7 +1091,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) } /* init buddy cache */ page = e4b.bd_buddy_page; - ret = ext4_mb_init_cache(page, e4b.bd_bitmap); + ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp); if (ret) goto err; if (!PageUptodate(page)) { @@ -1109,8 +1109,8 @@ err: * calling this routine! */ static noinline_for_stack int -ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, - struct ext4_buddy *e4b) +ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, + struct ext4_buddy *e4b, gfp_t gfp) { int blocks_per_page; int block; @@ -1140,7 +1140,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, * we need full data about the group * to make a good selection */ - ret = ext4_mb_init_group(sb, group); + ret = ext4_mb_init_group(sb, group, gfp); if (ret) return ret; } @@ -1168,11 +1168,11 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, * wait for it to initialize. */ page_cache_release(page); - page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, pnum, gfp); if (page) { BUG_ON(page->mapping != inode->i_mapping); if (!PageUptodate(page)) { - ret = ext4_mb_init_cache(page, NULL); + ret = ext4_mb_init_cache(page, NULL, gfp); if (ret) { unlock_page(page); goto err; @@ -1204,11 +1204,12 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, if (page == NULL || !PageUptodate(page)) { if (page) page_cache_release(page); - page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, pnum, gfp); if (page) { BUG_ON(page->mapping != inode->i_mapping); if (!PageUptodate(page)) { - ret = ext4_mb_init_cache(page, e4b->bd_bitmap); + ret = ext4_mb_init_cache(page, e4b->bd_bitmap, + gfp); if (ret) { unlock_page(page); goto err; @@ -1247,6 +1248,12 @@ err: return ret; } +static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, + struct ext4_buddy *e4b) +{ + return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS); +} + static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_page) @@ -2047,7 +2054,7 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { - int ret = ext4_mb_init_group(ac->ac_sb, group); + int ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS); if (ret) return ret; } @@ -4809,7 +4816,9 @@ do_more: #endif trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); - err = ext4_mb_load_buddy(sb, block_group, &e4b); + /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ + err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, + GFP_NOFS|__GFP_NOFAIL); if (err) goto error_return; @@ -5218,7 +5227,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range, grp = ext4_get_group_info(sb, group); /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { - ret = ext4_mb_init_group(sb, group); + ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) break; } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 796ff0eafd3c..7861d801b048 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -598,6 +598,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, return -EOPNOTSUPP; } + if (ext4_encrypted_inode(orig_inode) || + ext4_encrypted_inode(donor_inode)) { + ext4_msg(orig_inode->i_sb, KERN_ERR, + "Online defrag not supported for encrypted files"); + return -EOPNOTSUPP; + } + /* Protect orig and donor inodes against a truncate */ lock_two_nondirectories(orig_inode, donor_inode); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 20892f27f7be..b936da9d3d0c 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2034,33 +2034,31 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, frame->entries = entries; frame->at = entries; frame->bh = bh; - bh = bh2; retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh); if (retval) goto out_frames; - retval = ext4_handle_dirty_dirent_node(handle, dir, bh); + retval = ext4_handle_dirty_dirent_node(handle, dir, bh2); if (retval) goto out_frames; - de = do_split(handle,dir, &bh, frame, &fname->hinfo); + de = do_split(handle,dir, &bh2, frame, &fname->hinfo); if (IS_ERR(de)) { retval = PTR_ERR(de); goto out_frames; } - dx_release(frames); - retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh); - brelse(bh); - return retval; + retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh2); out_frames: /* * Even if the block split failed, we have to properly write * out all the changes we did so far. Otherwise we can end up * with corrupted filesystem. */ - ext4_mark_inode_dirty(handle, dir); + if (retval) + ext4_mark_inode_dirty(handle, dir); dx_release(frames); + brelse(bh2); return retval; } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index dd98270d0b21..71a08a294529 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -330,6 +330,5 @@ int ext4_mpage_readpages(struct address_space *mapping, BUG_ON(pages && !list_empty(pages)); if (bio) submit_bio(READ, bio); - return 0; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5bab28caa9d4..127155b82e6e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3394,7 +3394,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { ext4_msg(sb, KERN_ERR, - "Unsupported filesystem blocksize %d", blocksize); + "Unsupported filesystem blocksize %d (%d log_block_size)", + blocksize, le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } + if (le32_to_cpu(es->s_log_block_size) > + (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); goto failed_mount; } @@ -3533,6 +3541,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "block size (%d)", clustersize, blocksize); goto failed_mount; } + if (le32_to_cpu(es->s_log_cluster_size) > + (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log cluster size: %u", + le32_to_cpu(es->s_log_cluster_size)); + goto failed_mount; + } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); sbi->s_clusters_per_group = diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 1420a3c614af..5d09ea585840 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -223,14 +223,18 @@ static struct attribute *ext4_attrs[] = { EXT4_ATTR_FEATURE(lazy_itable_init); EXT4_ATTR_FEATURE(batched_discard); EXT4_ATTR_FEATURE(meta_bg_resize); +#ifdef CONFIG_EXT4_FS_ENCRYPTION EXT4_ATTR_FEATURE(encryption); +#endif EXT4_ATTR_FEATURE(metadata_csum_seed); static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), ATTR_LIST(batched_discard), ATTR_LIST(meta_bg_resize), +#ifdef CONFIG_EXT4_FS_ENCRYPTION ATTR_LIST(encryption), +#endif ATTR_LIST(metadata_csum_seed), NULL, }; diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index c8f25f7241f0..e9a8d676c6bc 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -214,12 +214,10 @@ static int __f2fs_set_acl(struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; set_acl_inode(fi, inode->i_mode); - if (error == 0) - acl = NULL; } break; diff --git a/fs/f2fs/crypto_policy.c b/fs/f2fs/crypto_policy.c index d4a96af513c2..e504f548b64e 100644 --- a/fs/f2fs/crypto_policy.c +++ b/fs/f2fs/crypto_policy.c @@ -89,6 +89,9 @@ static int f2fs_create_encryption_context_from_policy( int f2fs_process_policy(const struct f2fs_encryption_policy *policy, struct inode *inode) { + if (!inode_owner_or_capable(inode)) + return -EACCES; + if (policy->version != 0) return -EINVAL; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 48fb86bc153d..b237862dc274 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1745,14 +1745,46 @@ error: static int fuse_setattr(struct dentry *entry, struct iattr *attr) { struct inode *inode = d_inode(entry); + struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL; + int ret; if (!fuse_allow_current_process(get_fuse_conn(inode))) return -EACCES; - if (attr->ia_valid & ATTR_FILE) - return fuse_do_setattr(inode, attr, attr->ia_file); - else - return fuse_do_setattr(inode, attr, NULL); + if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) { + int kill; + + attr->ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | + ATTR_MODE); + /* + * ia_mode calculation may have used stale i_mode. Refresh and + * recalculate. + */ + ret = fuse_do_getattr(inode, NULL, file); + if (ret) + return ret; + + attr->ia_mode = inode->i_mode; + kill = should_remove_suid(entry); + if (kill & ATTR_KILL_SUID) { + attr->ia_valid |= ATTR_MODE; + attr->ia_mode &= ~S_ISUID; + } + if (kill & ATTR_KILL_SGID) { + attr->ia_valid |= ATTR_MODE; + attr->ia_mode &= ~S_ISGID; + } + } + if (!attr->ia_valid) + return 0; + + ret = fuse_do_setattr(inode, attr, file); + if (!ret) { + /* Directory mode changed, may need to revalidate access */ + if (d_is_dir(entry) && (attr->ia_valid & ATTR_MODE)) + fuse_invalidate_entry_cache(entry); + } + return ret; } static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, @@ -1845,6 +1877,23 @@ static ssize_t fuse_getxattr(struct dentry *entry, const char *name, return ret; } +static int fuse_verify_xattr_list(char *list, size_t size) +{ + size_t origsize = size; + + while (size) { + size_t thislen = strnlen(list, size); + + if (!thislen || thislen == size) + return -EIO; + + size -= thislen + 1; + list += thislen + 1; + } + + return origsize; +} + static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) { struct inode *inode = d_inode(entry); @@ -1880,6 +1929,8 @@ static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) ret = fuse_simple_request(fc, &args); if (!ret && !size) ret = outarg.size; + if (ret > 0 && size) + ret = fuse_verify_xattr_list(list, ret); if (ret == -ENOSYS) { fc->no_listxattr = 1; ret = -EOPNOTSUPP; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 025f11b9cffa..64eb2c6ee450 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -558,13 +558,13 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos, req->out.args[0].size = count; } -static void fuse_release_user_pages(struct fuse_req *req, int write) +static void fuse_release_user_pages(struct fuse_req *req, bool should_dirty) { unsigned i; for (i = 0; i < req->num_pages; i++) { struct page *page = req->pages[i]; - if (write) + if (should_dirty) set_page_dirty_lock(page); put_page(page); } @@ -1400,6 +1400,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, loff_t *ppos, int flags) { int write = flags & FUSE_DIO_WRITE; + bool should_dirty = !write && iter_is_iovec(iter); int cuse = flags & FUSE_DIO_CUSE; struct file *file = io->file; struct inode *inode = file->f_mapping->host; @@ -1444,7 +1445,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, nres = fuse_send_read(req, io, pos, nbytes, owner); if (!io->async) - fuse_release_user_pages(req, !write); + fuse_release_user_pages(req, should_dirty); if (req->out.h.error) { if (!res) res = req->out.h.error; @@ -2065,6 +2066,10 @@ static int fuse_write_end(struct file *file, struct address_space *mapping, { struct inode *inode = page->mapping->host; + /* Haven't copied anything? Skip zeroing, size extending, dirtying. */ + if (!copied) + goto unlock; + if (!PageUptodate(page)) { /* Zero any unwritten bytes at the end of the page */ size_t endoff = (pos + copied) & ~PAGE_CACHE_MASK; @@ -2075,6 +2080,8 @@ static int fuse_write_end(struct file *file, struct address_space *mapping, fuse_write_update_size(inode, pos + copied); set_page_dirty(page); + +unlock: unlock_page(page); page_cache_release(page); diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 1be3b061c05c..ff0ac96a8e7b 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -79,17 +79,11 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (type == ACL_TYPE_ACCESS) { umode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - - if (error == 0) - acl = NULL; - - if (mode != inode->i_mode) { - inode->i_mode = mode; + if (mode != inode->i_mode) mark_inode_dirty(inode); - } } if (acl) { diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index df0c9af68d05..71b3087b7e32 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -68,8 +68,8 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, case ACL_TYPE_ACCESS: xattr_name = POSIX_ACL_XATTR_ACCESS; if (acl) { - err = posix_acl_equiv_mode(acl, &inode->i_mode); - if (err < 0) + err = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (err) return err; } err = 0; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 5a7b3229b956..f34d6f5a5aca 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -959,10 +959,11 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) if (S_ISLNK(root_inode->i_mode)) { char *name = follow_link(host_root_path); - if (IS_ERR(name)) + if (IS_ERR(name)) { err = PTR_ERR(name); - else - err = read_name(root_inode, name); + goto out_put; + } + err = read_name(root_inode, name); kfree(name); if (err) goto out_put; diff --git a/fs/inode.c b/fs/inode.c index b0edef500590..2c16b758831d 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -154,6 +154,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_rdev = 0; inode->dirtied_when = 0; +#ifdef CONFIG_CGROUP_WRITEBACK + inode->i_wb_frn_winner = 0; + inode->i_wb_frn_avg_time = 0; + inode->i_wb_frn_history = 0; +#endif + if (security_inode_alloc(inode)) goto out; spin_lock_init(&inode->i_lock); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d67a16f2a45d..350f67fb5b9c 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -690,6 +690,11 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) pri_bh = NULL; root_found: + /* We don't support read-write mounts */ + if (!(s->s_flags & MS_RDONLY)) { + error = -EACCES; + goto out_freebh; + } if (joliet_level && (pri == NULL || !opt.rock)) { /* This is the case of Joliet with the norock mount flag. @@ -1503,9 +1508,6 @@ struct inode *__isofs_iget(struct super_block *sb, static struct dentry *isofs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - /* We don't support read-write mounts */ - if (!(flags & MS_RDONLY)) - return ERR_PTR(-EACCES); return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super); } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index ca181e81c765..fa1b8e0dcacf 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1156,6 +1156,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "file as BJ_Reserved"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); + spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction == journal->j_committing_transaction) { /* first access by this transaction */ jh->b_modified = 0; @@ -1163,8 +1164,8 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "set next transaction"); spin_lock(&journal->j_list_lock); jh->b_next_transaction = transaction; + spin_unlock(&journal->j_list_lock); } - spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); /* diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 2f7a3c090489..f9f86f87d32b 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -235,9 +235,10 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: xprefix = JFFS2_XPREFIX_ACL_ACCESS; if (acl) { - umode_t mode = inode->i_mode; - rc = posix_acl_equiv_mode(acl, &mode); - if (rc < 0) + umode_t mode; + + rc = posix_acl_update_mode(inode, &mode, &acl); + if (rc) return rc; if (inode->i_mode != mode) { struct iattr attr; @@ -249,8 +250,6 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (rc < 0) return rc; } - if (rc == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 0c8ca830b113..9fad9f4fe883 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -84,13 +84,11 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, case ACL_TYPE_ACCESS: ea_name = POSIX_ACL_XATTR_ACCESS; if (acl) { - rc = posix_acl_equiv_mode(acl, &inode->i_mode); - if (rc < 0) + rc = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (rc) return rc; inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); - if (rc == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 7247252ee9b1..6e9a912d394c 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -833,21 +833,35 @@ repeat: mutex_lock(&kernfs_mutex); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { + struct kernfs_node *parent; struct inode *inode; - struct dentry *dentry; + /* + * We want fsnotify_modify() on @kn but as the + * modifications aren't originating from userland don't + * have the matching @file available. Look up the inodes + * and generate the events manually. + */ inode = ilookup(info->sb, kn->ino); if (!inode) continue; - dentry = d_find_any_alias(inode); - if (dentry) { - fsnotify_parent(NULL, dentry, FS_MODIFY); - fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, - NULL, 0); - dput(dentry); + parent = kernfs_get_parent(kn); + if (parent) { + struct inode *p_inode; + + p_inode = ilookup(info->sb, parent->ino); + if (p_inode) { + fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD, + inode, FSNOTIFY_EVENT_INODE, kn->name, 0); + iput(p_inode); + } + + kernfs_put(parent); } + fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, + kn->name, 0); iput(inode); } diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index a7f2e6e33305..48efe62e1302 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -261,7 +261,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, } ret = -EPROTONOSUPPORT; - if (minorversion == 0) + if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0) ret = nfs4_callback_up_net(serv, net); else if (xprt->ops->bc_up) ret = xprt->ops->bc_up(serv, net); @@ -275,6 +275,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, err_socks: svc_rpcb_cleanup(serv, net); err_bind: + nn->cb_users[minorversion]--; dprintk("NFS: Couldn't create callback socket: err = %d; " "net = %p\n", ret, net); return ret; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 646cdac73488..e2e857affbf2 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -912,7 +912,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r if (hdr_arg.minorversion == 0) { cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident); if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp)) - return rpc_drop_reply; + goto out_invalidcred; } cps.minorversion = hdr_arg.minorversion; @@ -940,6 +940,10 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r nfs_put_client(cps.clp); dprintk("%s: done, status = %u\n", __func__, ntohl(status)); return rpc_success; + +out_invalidcred: + pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n"); + return rpc_autherr_badcred; } /* diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5166adcfc0fb..7af5eeabc80e 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -41,6 +41,17 @@ void nfs_mark_delegation_referenced(struct nfs_delegation *delegation) set_bit(NFS_DELEGATION_REFERENCED, &delegation->flags); } +static bool +nfs4_is_valid_delegation(const struct nfs_delegation *delegation, + fmode_t flags) +{ + if (delegation != NULL && (delegation->type & flags) == flags && + !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) && + !test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) + return true; + return false; +} + static int nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark) { @@ -50,8 +61,7 @@ nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark) flags &= FMODE_READ|FMODE_WRITE; rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); - if (delegation != NULL && (delegation->type & flags) == flags && - !test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + if (nfs4_is_valid_delegation(delegation, flags)) { if (mark) nfs_mark_delegation_referenced(delegation); ret = 1; @@ -892,7 +902,7 @@ bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, flags &= FMODE_READ|FMODE_WRITE; rcu_read_lock(); delegation = rcu_dereference(nfsi->delegation); - ret = (delegation != NULL && (delegation->type & flags) == flags); + ret = nfs4_is_valid_delegation(delegation, flags); if (ret) { nfs4_stateid_copy(dst, &delegation->stateid); nfs_mark_delegation_referenced(delegation); diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 02ec07973bc4..fd8da630fd22 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -374,8 +374,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task, return -EAGAIN; } - if (data->verf.committed == NFS_UNSTABLE) - pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb); + pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb); return 0; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 2a2e2d8ddee5..54313322ee5b 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1414,8 +1414,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, return -EAGAIN; } - if (data->verf.committed == NFS_UNSTABLE - && ff_layout_need_layoutcommit(data->lseg)) + if (ff_layout_need_layoutcommit(data->lseg)) pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb); return 0; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 6b1ce9825430..7f1a0fb8c493 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -269,6 +269,7 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, task = rpc_run_task(&task_setup); if (IS_ERR(task)) return PTR_ERR(task); + rpc_put_task(task); return 0; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index fc215ab4dcd5..3c69299c01ab 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7424,12 +7424,20 @@ static int _nfs4_proc_create_session(struct nfs_client *clp, status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); trace_nfs4_create_session(clp, status); + switch (status) { + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_DELAY: + case -ETIMEDOUT: + case -EACCES: + case -EAGAIN: + goto out; + }; + + clp->cl_seqid++; if (!status) { /* Verify the session's negotiated channel_attrs values */ status = nfs4_verify_channel_attrs(&args, &res); /* Increment the clientid slot sequence id */ - if (clp->cl_seqid == res.seqid) - clp->cl_seqid++; if (status) goto out; nfs4_update_session(session, &res); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index d854693a15b0..82dc3035ea45 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1493,6 +1493,9 @@ restart: __func__, status); case -ENOENT: case -ENOMEM: + case -EACCES: + case -EROFS: + case -EIO: case -ESTALE: /* Open state on this file cannot be recovered */ nfs4_state_mark_recovery_failed(state, status); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index bec0384499f7..5cd3568eea06 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -365,6 +365,9 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo, static bool pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) { + /* Serialise LAYOUTGET/LAYOUTRETURN */ + if (atomic_read(&lo->plh_outstanding) != 0) + return false; if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) return false; lo->plh_return_iomode = 0; @@ -1530,6 +1533,7 @@ pnfs_update_layout(struct inode *ino, goto out; lookup_again: + nfs4_client_recover_expired_lease(clp); first = false; spin_lock(&ino->i_lock); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f7ea624780a7..55638110cb06 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1200,27 +1200,6 @@ free_ol_stateid_reaplist(struct list_head *reaplist) } } -static void release_lockowner(struct nfs4_lockowner *lo) -{ - struct nfs4_client *clp = lo->lo_owner.so_client; - struct nfs4_ol_stateid *stp; - struct list_head reaplist; - - INIT_LIST_HEAD(&reaplist); - - spin_lock(&clp->cl_lock); - unhash_lockowner_locked(lo); - while (!list_empty(&lo->lo_owner.so_stateids)) { - stp = list_first_entry(&lo->lo_owner.so_stateids, - struct nfs4_ol_stateid, st_perstateowner); - WARN_ON(!unhash_lock_stateid(stp)); - put_ol_stateid_locked(stp, &reaplist); - } - spin_unlock(&clp->cl_lock); - free_ol_stateid_reaplist(&reaplist); - nfs4_put_stateowner(&lo->lo_owner); -} - static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, struct list_head *reaplist) { @@ -5952,6 +5931,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct nfs4_client *clp; + LIST_HEAD (reaplist); dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); @@ -5982,9 +5962,23 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, nfs4_get_stateowner(sop); break; } + if (!lo) { + spin_unlock(&clp->cl_lock); + return status; + } + + unhash_lockowner_locked(lo); + while (!list_empty(&lo->lo_owner.so_stateids)) { + stp = list_first_entry(&lo->lo_owner.so_stateids, + struct nfs4_ol_stateid, + st_perstateowner); + WARN_ON(!unhash_lock_stateid(stp)); + put_ol_stateid_locked(stp, &reaplist); + } spin_unlock(&clp->cl_lock); - if (lo) - release_lockowner(lo); + free_ol_stateid_reaplist(&reaplist); + nfs4_put_stateowner(&lo->lo_owner); + return status; } diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d2f97ecca6a5..e0e5f7c3c99f 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - wait_event(group->fanotify_data.access_waitq, event->response || - atomic_read(&group->fanotify_data.bypass_perm)); - - if (!event->response) { /* bypass_perm set */ - /* - * Event was canceled because group is being destroyed. Remove - * it from group's event list because we are responsible for - * freeing the permission event. - */ - fsnotify_remove_event(group, &event->fae.fse); - return 0; - } + wait_event(group->fanotify_data.access_waitq, event->response); /* userspace responded, convert to something usable */ switch (event->response) { diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 8e8e6bcd1d43..a64313868d3a 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS struct fanotify_perm_event_info *event, *next; + struct fsnotify_event *fsn_event; /* - * There may be still new events arriving in the notification queue - * but since userspace cannot use fanotify fd anymore, no event can - * enter or leave access_list by now. + * Stop new events from arriving in the notification queue. since + * userspace cannot use fanotify fd anymore, no event can enter or + * leave access_list by now either. */ - spin_lock(&group->fanotify_data.access_lock); - - atomic_inc(&group->fanotify_data.bypass_perm); + fsnotify_group_stop_queueing(group); + /* + * Process all permission events on access_list and notification queue + * and simulate reply from userspace. + */ + spin_lock(&group->fanotify_data.access_lock); list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, fae.fse.list) { pr_debug("%s: found group=%p event=%p\n", __func__, group, @@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file) spin_unlock(&group->fanotify_data.access_lock); /* - * Since bypass_perm is set, newly queued events will not wait for - * access response. Wake up the already sleeping ones now. - * synchronize_srcu() in fsnotify_destroy_group() will wait for all - * processes sleeping in fanotify_handle_event() waiting for access - * response and thus also for all permission events to be freed. + * Destroy all non-permission events. For permission events just + * dequeue them and set the response. They will be freed once the + * response is consumed and fanotify_get_response() returns. */ + mutex_lock(&group->notification_mutex); + while (!fsnotify_notify_queue_is_empty(group)) { + fsn_event = fsnotify_remove_first_event(group); + if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) + fsnotify_destroy_event(group, fsn_event); + else + FANOTIFY_PE(fsn_event)->response = FAN_ALLOW; + } + mutex_unlock(&group->notification_mutex); + + /* Response for all permission events it set, wakeup waiters */ wake_up(&group->fanotify_data.access_waitq); #endif @@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) spin_lock_init(&group->fanotify_data.access_lock); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); - atomic_set(&group->fanotify_data.bypass_perm, 0); #endif switch (flags & FAN_ALL_CLASS_BITS) { case FAN_CLASS_NOTIF: diff --git a/fs/notify/group.c b/fs/notify/group.c index d16b62cb2854..18eb30c6bd8f 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -40,6 +40,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) } /* + * Stop queueing new events for this group. Once this function returns + * fsnotify_add_event() will not add any new events to the group's queue. + */ +void fsnotify_group_stop_queueing(struct fsnotify_group *group) +{ + mutex_lock(&group->notification_mutex); + group->shutdown = true; + mutex_unlock(&group->notification_mutex); +} + +/* * Trying to get rid of a group. Remove all marks, flush all events and release * the group reference. * Note that another thread calling fsnotify_clear_marks_by_group() may still @@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) */ void fsnotify_destroy_group(struct fsnotify_group *group) { + /* + * Stop queueing new events. The code below is careful enough to not + * require this but fanotify needs to stop queuing events even before + * fsnotify_destroy_group() is called and this makes the other callers + * of fsnotify_destroy_group() to see the same behavior. + */ + fsnotify_group_stop_queueing(group); + /* clear all inode marks for this group */ fsnotify_clear_marks_by_group(group); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index a95d8e037aeb..e455e83ceeeb 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * Add an event to the group notification queue. The group can later pull this * event off the queue to deal with. The function returns 0 if the event was * added to the queue, 1 if the event was merged with some other queued event, - * 2 if the queue of events has overflown. + * 2 if the event was not queued - either the queue of events has overflown + * or the group is shutting down. */ int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, @@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group, mutex_lock(&group->notification_mutex); + if (group->shutdown) { + mutex_unlock(&group->notification_mutex); + return 2; + } + if (group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ @@ -126,21 +132,6 @@ queue: } /* - * Remove @event from group's notification queue. It is the responsibility of - * the caller to destroy the event. - */ -void fsnotify_remove_event(struct fsnotify_group *group, - struct fsnotify_event *event) -{ - mutex_lock(&group->notification_mutex); - if (!list_empty(&event->list)) { - list_del_init(&event->list); - group->q_len--; - } - mutex_unlock(&group->notification_mutex); -} - -/* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event */ diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 2162434728c0..164307b99405 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -241,13 +241,11 @@ int ocfs2_set_acl(handle_t *handle, case ACL_TYPE_ACCESS: name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - umode_t mode = inode->i_mode; - ret = posix_acl_equiv_mode(acl, &mode); - if (ret < 0) - return ret; + umode_t mode; - if (ret == 0) - acl = NULL; + ret = posix_acl_update_mode(inode, &mode, &acl); + if (ret) + return ret; ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode); diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index f90931335c6b..2e11658676eb 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -262,7 +262,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, struct dlm_lock *lock, int flags, int type) { enum dlm_status status; - u8 old_owner = res->owner; mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); @@ -329,7 +328,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; - lock->convert_pending = 0; /* if it failed, move it back to granted queue. * if master returns DLM_NORMAL and then down before sending ast, * it may have already been moved to granted queue, reset to @@ -338,12 +336,14 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, if (status != DLM_NOTQUEUED) dlm_error(status); dlm_revert_pending_convert(res, lock); - } else if ((res->state & DLM_LOCK_RES_RECOVERING) || - (old_owner != res->owner)) { - mlog(0, "res %.*s is in recovering or has been recovered.\n", - res->lockname.len, res->lockname.name); + } else if (!lock->convert_pending) { + mlog(0, "%s: res %.*s, owner died and lock has been moved back " + "to granted list, retry convert.\n", + dlm->name, res->lockname.len, res->lockname.name); status = DLM_RECOVERING; } + + lock->convert_pending = 0; bail: spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 77d30cbd944d..56dd3957cc91 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1536,7 +1536,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { int ret = 0; - u64 tmpend, end = start + len; + u64 tmpend = 0; + u64 end = start + len; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; @@ -1568,18 +1569,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, } /* - * We want to get the byte offset of the end of the 1st cluster. + * If start is on a cluster boundary and end is somewhere in another + * cluster, we have not COWed the cluster starting at start, unless + * end is also within the same cluster. So, in this case, we skip this + * first call to ocfs2_zero_range_for_truncate() truncate and move on + * to the next one. */ - tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1)); - if (tmpend > end) - tmpend = end; + if ((start & (csize - 1)) != 0) { + /* + * We want to get the byte offset of the end of the 1st + * cluster. + */ + tmpend = (u64)osb->s_clustersize + + (start & ~(osb->s_clustersize - 1)); + if (tmpend > end) + tmpend = end; - trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start, - (unsigned long long)tmpend); + trace_ocfs2_zero_partial_clusters_range1( + (unsigned long long)start, + (unsigned long long)tmpend); - ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend); - if (ret) - mlog_errno(ret); + ret = ocfs2_zero_range_for_truncate(inode, handle, start, + tmpend); + if (ret) + mlog_errno(ret); + } if (tmpend < end) { /* diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 9e52609cd683..63a0d0ba36de 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -25,6 +25,7 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) ssize_t list_size, size, value_size = 0; char *buf, *name, *value = NULL; int uninitialized_var(error); + size_t slen; if (!old->d_inode->i_op->getxattr || !new->d_inode->i_op->getxattr) @@ -47,7 +48,16 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) goto out; } - for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { + for (name = buf; list_size; name += slen) { + slen = strnlen(name, list_size) + 1; + + /* underlying fs providing us with an broken xattr list? */ + if (WARN_ON(slen > list_size)) { + error = -EIO; + break; + } + list_size -= slen; + if (ovl_is_private_xattr(name)) continue; retry: @@ -129,6 +139,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) len -= bytes; } + if (!error) + error = vfs_fsync(new_file, 0); fput(new_file); out_fput: fput(old_file); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index ba5ef733951f..327177df03a5 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -12,6 +12,7 @@ #include <linux/xattr.h> #include <linux/security.h> #include <linux/cred.h> +#include <linux/atomic.h> #include "overlayfs.h" void ovl_cleanup(struct inode *wdir, struct dentry *wdentry) @@ -35,8 +36,10 @@ struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry) { struct dentry *temp; char name[20]; + static atomic_t temp_id = ATOMIC_INIT(0); - snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry); + /* counter is allowed to wrap, since temp dentries are ephemeral */ + snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id)); temp = lookup_one_len(name, workdir, strlen(name)); if (!IS_ERR(temp) && temp->d_inode) { diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 34bd1bd354e6..a60d3cc5b55d 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -592,6 +592,37 @@ no_mem: } EXPORT_SYMBOL_GPL(posix_acl_create); +/** + * posix_acl_update_mode - update mode in set_acl + * + * Update the file mode when setting an ACL: compute the new file permission + * bits based on the ACL. In addition, if the ACL is equivalent to the new + * file mode, set *acl to NULL to indicate that no ACL should be set. + * + * As with chmod, clear the setgit bit if the caller is not in the owning group + * or capable of CAP_FSETID (see inode_change_ok). + * + * Called from set_acl inode operations. + */ +int posix_acl_update_mode(struct inode *inode, umode_t *mode_p, + struct posix_acl **acl) +{ + umode_t mode = inode->i_mode; + int error; + + error = posix_acl_equiv_mode(*acl, &mode); + if (error < 0) + return error; + if (error == 0) + *acl = NULL; + if (!in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + mode &= ~S_ISGID; + *mode_p = mode; + return 0; +} +EXPORT_SYMBOL(posix_acl_update_mode); + /* * Fix up the uids and gids in posix acl extended attributes in place. */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 67c6dd28d59e..1f5f654983ec 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1748,18 +1748,13 @@ static const struct file_operations proc_pid_set_comm_operations = { static int proc_exe_link(struct dentry *dentry, struct path *exe_path) { struct task_struct *task; - struct mm_struct *mm; struct file *exe_file; task = get_proc_task(d_inode(dentry)); if (!task) return -ENOENT; - mm = get_task_mm(task); + exe_file = get_task_exe_file(task); put_task_struct(task); - if (!mm) - return -ENOENT; - exe_file = get_mm_exe_file(mm); - mmput(mm); if (exe_file) { *exe_path = exe_file->f_path; path_get(&exe_file->f_path); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 92e6726f6e37..21f198aa0961 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -430,6 +430,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) static ssize_t read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) { + char *buf = file->private_data; ssize_t acc = 0; size_t size, tsz; size_t elf_buflen; @@ -500,23 +501,20 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) if (clear_user(buffer, tsz)) return -EFAULT; } else if (is_vmalloc_or_module_addr((void *)start)) { - char * elf_buf; - - elf_buf = kzalloc(tsz, GFP_KERNEL); - if (!elf_buf) - return -ENOMEM; - vread(elf_buf, (char *)start, tsz); + vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ - if (copy_to_user(buffer, elf_buf, tsz)) { - kfree(elf_buf); + if (copy_to_user(buffer, buf, tsz)) return -EFAULT; - } - kfree(elf_buf); } else { if (kern_addr_valid(start)) { unsigned long n; - n = copy_to_user(buffer, (char *)start, tsz); + /* + * Using bounce buffer to bypass the + * hardened user copy kernel text checks. + */ + memcpy(buf, (char *) start, tsz); + n = copy_to_user(buffer, buf, tsz); /* * We cannot distinguish between fault on source * and fault on destination. When this happens @@ -549,6 +547,11 @@ static int open_kcore(struct inode *inode, struct file *filp) { if (!capable(CAP_SYS_RAWIO)) return -EPERM; + + filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!filp->private_data) + return -ENOMEM; + if (kcore_need_update) kcore_update_ram(); if (i_size_read(inode) != proc_root_kcore->size) { @@ -559,10 +562,16 @@ static int open_kcore(struct inode *inode, struct file *filp) return 0; } +static int release_kcore(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} static const struct file_operations proc_kcore_operations = { .read = read_kcore, .open = open_kcore, + .release = release_kcore, .llseek = default_llseek, }; diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index d8c439d813ce..ac6c78fe19cf 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -178,7 +178,6 @@ static loff_t pstore_file_llseek(struct file *file, loff_t off, int whence) } static const struct file_operations pstore_file_operations = { - .owner = THIS_MODULE, .open = pstore_file_open, .read = pstore_file_read, .llseek = pstore_file_llseek, diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 5b10c2b4146c..8d1e5e2db6a1 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -396,13 +396,14 @@ static void ramoops_free_przs(struct ramoops_context *cxt) { int i; - cxt->max_dump_cnt = 0; if (!cxt->przs) return; - for (i = 0; !IS_ERR_OR_NULL(cxt->przs[i]); i++) + for (i = 0; i < cxt->max_dump_cnt; i++) persistent_ram_free(cxt->przs[i]); + kfree(cxt->przs); + cxt->max_dump_cnt = 0; } static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, @@ -427,7 +428,7 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, GFP_KERNEL); if (!cxt->przs) { dev_err(dev, "failed to initialize a prz array for dumps\n"); - goto fail_prz; + goto fail_mem; } for (i = 0; i < cxt->max_dump_cnt; i++) { @@ -438,6 +439,11 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, err = PTR_ERR(cxt->przs[i]); dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n", cxt->record_size, (unsigned long long)*paddr, err); + + while (i > 0) { + i--; + persistent_ram_free(cxt->przs[i]); + } goto fail_prz; } *paddr += cxt->record_size; @@ -445,7 +451,9 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, return 0; fail_prz: - ramoops_free_przs(cxt); + kfree(cxt->przs); +fail_mem: + cxt->max_dump_cnt = 0; return err; } @@ -707,7 +715,6 @@ static int ramoops_remove(struct platform_device *pdev) struct ramoops_context *cxt = &oops_cxt; pstore_unregister(&cxt->pstore); - cxt->max_dump_cnt = 0; kfree(cxt->pstore.buf); cxt->pstore.bufsize = 0; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index aa9afe573155..3975deec02f8 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -48,43 +48,10 @@ static inline size_t buffer_start(struct persistent_ram_zone *prz) return atomic_read(&prz->buffer->start); } -/* increase and wrap the start pointer, returning the old value */ -static size_t buffer_start_add_atomic(struct persistent_ram_zone *prz, size_t a) -{ - int old; - int new; - - do { - old = atomic_read(&prz->buffer->start); - new = old + a; - while (unlikely(new >= prz->buffer_size)) - new -= prz->buffer_size; - } while (atomic_cmpxchg(&prz->buffer->start, old, new) != old); - - return old; -} - -/* increase the size counter until it hits the max size */ -static void buffer_size_add_atomic(struct persistent_ram_zone *prz, size_t a) -{ - size_t old; - size_t new; - - if (atomic_read(&prz->buffer->size) == prz->buffer_size) - return; - - do { - old = atomic_read(&prz->buffer->size); - new = old + a; - if (new > prz->buffer_size) - new = prz->buffer_size; - } while (atomic_cmpxchg(&prz->buffer->size, old, new) != old); -} - static DEFINE_RAW_SPINLOCK(buffer_lock); /* increase and wrap the start pointer, returning the old value */ -static size_t buffer_start_add_locked(struct persistent_ram_zone *prz, size_t a) +static size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a) { int old; int new; @@ -104,7 +71,7 @@ static size_t buffer_start_add_locked(struct persistent_ram_zone *prz, size_t a) } /* increase the size counter until it hits the max size */ -static void buffer_size_add_locked(struct persistent_ram_zone *prz, size_t a) +static void buffer_size_add(struct persistent_ram_zone *prz, size_t a) { size_t old; size_t new; @@ -125,9 +92,6 @@ exit: raw_spin_unlock_irqrestore(&buffer_lock, flags); } -static size_t (*buffer_start_add)(struct persistent_ram_zone *, size_t) = buffer_start_add_atomic; -static void (*buffer_size_add)(struct persistent_ram_zone *, size_t) = buffer_size_add_atomic; - static void notrace persistent_ram_encode_rs8(struct persistent_ram_zone *prz, uint8_t *data, size_t len, uint8_t *ecc) { @@ -300,7 +264,7 @@ static void notrace persistent_ram_update(struct persistent_ram_zone *prz, const void *s, unsigned int start, unsigned int count) { struct persistent_ram_buffer *buffer = prz->buffer; - memcpy(buffer->data + start, s, count); + memcpy_toio(buffer->data + start, s, count); persistent_ram_update_ecc(prz, start, count); } @@ -333,8 +297,8 @@ void persistent_ram_save_old(struct persistent_ram_zone *prz) } prz->old_log_size = size; - memcpy(prz->old_log, &buffer->data[start], size - start); - memcpy(prz->old_log + size - start, &buffer->data[0], start); + memcpy_fromio(prz->old_log, &buffer->data[start], size - start); + memcpy_fromio(prz->old_log + size - start, &buffer->data[0], start); } int notrace persistent_ram_write(struct persistent_ram_zone *prz, @@ -469,9 +433,6 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size, return NULL; } - buffer_start_add = buffer_start_add_locked; - buffer_size_add = buffer_size_add_locked; - if (memtype) va = ioremap(start, size); else diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 96a1bcf33db4..8f5ccdf81c25 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -260,10 +260,10 @@ const struct file_operations reiserfs_file_operations = { const struct inode_operations reiserfs_file_inode_operations = { .setattr = reiserfs_setattr, - .setxattr = reiserfs_setxattr, - .getxattr = reiserfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = reiserfs_listxattr, - .removexattr = reiserfs_removexattr, + .removexattr = generic_removexattr, .permission = reiserfs_permission, .get_acl = reiserfs_get_acl, .set_acl = reiserfs_set_acl, diff --git a/fs/reiserfs/ibalance.c b/fs/reiserfs/ibalance.c index b751eea32e20..5db6f45b3fed 100644 --- a/fs/reiserfs/ibalance.c +++ b/fs/reiserfs/ibalance.c @@ -1153,8 +1153,9 @@ int balance_internal(struct tree_balance *tb, insert_ptr); } - memcpy(new_insert_key_addr, &new_insert_key, KEY_SIZE); insert_ptr[0] = new_insert_ptr; + if (new_insert_ptr) + memcpy(new_insert_key_addr, &new_insert_key, KEY_SIZE); return order; } diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 47f96988fdd4..3ebc70167e41 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -1649,10 +1649,10 @@ const struct inode_operations reiserfs_dir_inode_operations = { .mknod = reiserfs_mknod, .rename = reiserfs_rename, .setattr = reiserfs_setattr, - .setxattr = reiserfs_setxattr, - .getxattr = reiserfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = reiserfs_listxattr, - .removexattr = reiserfs_removexattr, + .removexattr = generic_removexattr, .permission = reiserfs_permission, .get_acl = reiserfs_get_acl, .set_acl = reiserfs_set_acl, @@ -1667,10 +1667,10 @@ const struct inode_operations reiserfs_symlink_inode_operations = { .follow_link = page_follow_link_light, .put_link = page_put_link, .setattr = reiserfs_setattr, - .setxattr = reiserfs_setxattr, - .getxattr = reiserfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = reiserfs_listxattr, - .removexattr = reiserfs_removexattr, + .removexattr = generic_removexattr, .permission = reiserfs_permission, }; @@ -1679,10 +1679,10 @@ const struct inode_operations reiserfs_symlink_inode_operations = { */ const struct inode_operations reiserfs_special_inode_operations = { .setattr = reiserfs_setattr, - .setxattr = reiserfs_setxattr, - .getxattr = reiserfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = reiserfs_listxattr, - .removexattr = reiserfs_removexattr, + .removexattr = generic_removexattr, .permission = reiserfs_permission, .get_acl = reiserfs_get_acl, .set_acl = reiserfs_set_acl, diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 4a62fe8cc3bf..f9f3be50081a 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -190,7 +190,15 @@ static int remove_save_link_only(struct super_block *s, static int reiserfs_quota_on_mount(struct super_block *, int); #endif -/* look for uncompleted unlinks and truncates and complete them */ +/* + * Look for uncompleted unlinks and truncates and complete them + * + * Called with superblock write locked. If quotas are enabled, we have to + * release/retake lest we call dquot_quota_on_mount(), proceed to + * schedule_on_each_cpu() in invalidate_bdev() and deadlock waiting for the per + * cpu worklets to complete flush_async_commits() that in turn wait for the + * superblock write lock. + */ static int finish_unfinished(struct super_block *s) { INITIALIZE_PATH(path); @@ -237,7 +245,9 @@ static int finish_unfinished(struct super_block *s) quota_enabled[i] = 0; continue; } + reiserfs_write_unlock(s); ret = reiserfs_quota_on_mount(s, i); + reiserfs_write_lock(s); if (ret < 0) reiserfs_warning(s, "reiserfs-2500", "cannot turn on journaled " diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 66b26fdfff8d..a8dbc93e45eb 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -763,60 +763,6 @@ find_xattr_handler_prefix(const struct xattr_handler **handlers, return xah; } - -/* - * Inode operation getxattr() - */ -ssize_t -reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer, - size_t size) -{ - const struct xattr_handler *handler; - - handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name); - - if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) - return -EOPNOTSUPP; - - return handler->get(handler, dentry, name, buffer, size); -} - -/* - * Inode operation setxattr() - * - * d_inode(dentry)->i_mutex down - */ -int -reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) -{ - const struct xattr_handler *handler; - - handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name); - - if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) - return -EOPNOTSUPP; - - return handler->set(handler, dentry, name, value, size, flags); -} - -/* - * Inode operation removexattr() - * - * d_inode(dentry)->i_mutex down - */ -int reiserfs_removexattr(struct dentry *dentry, const char *name) -{ - const struct xattr_handler *handler; - - handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name); - - if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) - return -EOPNOTSUPP; - - return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE); -} - struct listxattr_buf { struct dir_context ctx; size_t size; diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h index 15dde6262c00..613ff5aef94e 100644 --- a/fs/reiserfs/xattr.h +++ b/fs/reiserfs/xattr.h @@ -2,6 +2,7 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/rwsem.h> +#include <linux/xattr.h> struct inode; struct dentry; @@ -18,12 +19,7 @@ int reiserfs_permission(struct inode *inode, int mask); #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) -ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size); -int reiserfs_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); ssize_t reiserfs_listxattr(struct dentry *dentry, char *buffer, size_t size); -int reiserfs_removexattr(struct dentry *dentry, const char *name); int reiserfs_xattr_get(struct inode *, const char *, void *, size_t); int reiserfs_xattr_set(struct inode *, const char *, const void *, size_t, int); @@ -92,10 +88,7 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode) #else -#define reiserfs_getxattr NULL -#define reiserfs_setxattr NULL #define reiserfs_listxattr NULL -#define reiserfs_removexattr NULL static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 4b34b9dc03dd..9b1824f35501 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -246,13 +246,9 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - if (error == 0) - acl = NULL; - } } break; case ACL_TYPE_DEFAULT: diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index ac659af431ae..60de069225ba 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -12,26 +12,24 @@ static int security_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX)) - return -EINVAL; - if (IS_PRIVATE(d_inode(dentry))) return -EPERM; - return reiserfs_xattr_get(d_inode(dentry), name, buffer, size); + return reiserfs_xattr_get(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size); } static int security_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX)) - return -EINVAL; - if (IS_PRIVATE(d_inode(dentry))) return -EPERM; - return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); + return reiserfs_xattr_set(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size, flags); } static size_t security_list(const struct xattr_handler *handler, diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c index a338adf1b8b4..ebba1ebf28ad 100644 --- a/fs/reiserfs/xattr_trusted.c +++ b/fs/reiserfs/xattr_trusted.c @@ -11,26 +11,24 @@ static int trusted_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX)) - return -EINVAL; - if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry))) return -EPERM; - return reiserfs_xattr_get(d_inode(dentry), name, buffer, size); + return reiserfs_xattr_get(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size); } static int trusted_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX)) - return -EINVAL; - if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry))) return -EPERM; - return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); + return reiserfs_xattr_set(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size, flags); } static size_t trusted_list(const struct xattr_handler *handler, diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c index 39c9667191c5..6ac8a8c8bd9c 100644 --- a/fs/reiserfs/xattr_user.c +++ b/fs/reiserfs/xattr_user.c @@ -10,24 +10,22 @@ static int user_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - - if (strlen(name) < sizeof(XATTR_USER_PREFIX)) - return -EINVAL; if (!reiserfs_xattrs_user(dentry->d_sb)) return -EOPNOTSUPP; - return reiserfs_xattr_get(d_inode(dentry), name, buffer, size); + return reiserfs_xattr_get(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size); } static int user_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (strlen(name) < sizeof(XATTR_USER_PREFIX)) - return -EINVAL; - if (!reiserfs_xattrs_user(dentry->d_sb)) return -EOPNOTSUPP; - return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); + return reiserfs_xattr_set(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size, flags); } static size_t user_list(const struct xattr_handler *handler, diff --git a/fs/super.c b/fs/super.c index 8d99a7b948ff..b938b14f6041 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1326,8 +1326,8 @@ int freeze_super(struct super_block *sb) } } /* - * This is just for debugging purposes so that fs can warn if it - * sees write activity when frozen is set to SB_FREEZE_COMPLETE. + * For debugging purposes so that fs can warn if it sees write activity + * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super(). */ sb->s_writers.frozen = SB_FREEZE_COMPLETE; up_write(&sb->s_umount); @@ -1346,7 +1346,7 @@ int thaw_super(struct super_block *sb) int error; down_write(&sb->s_umount); - if (sb->s_writers.frozen == SB_UNFROZEN) { + if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) { up_write(&sb->s_umount); return -EINVAL; } diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index e49bd2808bf3..f5d5ee43ae6e 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -350,7 +350,7 @@ static unsigned int vfs_dent_type(uint8_t type) */ static int ubifs_readdir(struct file *file, struct dir_context *ctx) { - int err; + int err = 0; struct qstr nm; union ubifs_key key; struct ubifs_dent_node *dent; @@ -452,14 +452,20 @@ out: kfree(file->private_data); file->private_data = NULL; - if (err != -ENOENT) { + if (err != -ENOENT) ubifs_err(c, "cannot find next direntry, error %d", err); - return err; - } + else + /* + * -ENOENT is a non-fatal error in this context, the TNC uses + * it to indicate that the cursor moved past the current directory + * and readdir() has to stop. + */ + err = 0; + /* 2 is a special value indicating that there are no more direntries */ ctx->pos = 2; - return 0; + return err; } /* Free saved readdir() state when the directory is closed */ diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index e53292d0c21b..de6f82d4eda2 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -173,6 +173,7 @@ out_cancel: host_ui->xattr_cnt -= 1; host_ui->xattr_size -= CALC_DENT_SIZE(nm->len); host_ui->xattr_size -= CALC_XATTR_BYTES(size); + host_ui->xattr_names -= nm->len; mutex_unlock(&host_ui->ui_mutex); out_free: make_bad_inode(inode); @@ -533,6 +534,7 @@ out_cancel: host_ui->xattr_cnt += 1; host_ui->xattr_size += CALC_DENT_SIZE(nm->len); host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len); + host_ui->xattr_names += nm->len; mutex_unlock(&host_ui->ui_mutex); ubifs_release_budget(c, &req); make_bad_inode(inode); diff --git a/fs/utimes.c b/fs/utimes.c index aa138d64560a..cb771c30d102 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -87,20 +87,7 @@ static int utimes_common(struct path *path, struct timespec *times) */ newattrs.ia_valid |= ATTR_TIMES_SET; } else { - /* - * If times is NULL (or both times are UTIME_NOW), - * then we need to check permissions, because - * inode_change_ok() won't do it. - */ - error = -EACCES; - if (IS_IMMUTABLE(inode)) - goto mnt_drop_write_and_out; - - if (!inode_owner_or_capable(inode)) { - error = inode_permission(inode, MAY_WRITE); - if (error) - goto mnt_drop_write_and_out; - } + newattrs.ia_valid |= ATTR_TOUCH; } retry_deleg: mutex_lock(&inode->i_mutex); @@ -112,7 +99,6 @@ retry_deleg: goto retry_deleg; } -mnt_drop_write_and_out: mnt_drop_write(path->mnt); out: return error; diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index 3cc3cf767474..ac9a003dd29a 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc( if (mp->m_quotainfo) ndquots = mp->m_quotainfo->qi_dqperchunk; else - ndquots = xfs_calc_dquots_per_chunk( - XFS_BB_TO_FSB(mp, bp->b_length)); + ndquots = xfs_calc_dquots_per_chunk(bp->b_length); for (i = 0; i < ndquots; i++, d++) { if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk), diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 6bb470fbb8e8..c5101a3295d8 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -288,16 +288,11 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - umode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); - - if (error <= 0) { - acl = NULL; - - if (error < 0) - return error; - } + umode_t mode; + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + return error; error = xfs_set_mode(inode, mode); if (error) return error; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 39090fc56f09..eb1b8c8acfcb 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1535,7 +1535,7 @@ xfs_wait_buftarg( * ensure here that all reference counts have been dropped before we * start walking the LRU list. */ - drain_workqueue(btp->bt_mount->m_buf_workqueue); + flush_workqueue(btp->bt_mount->m_buf_workqueue); /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { |