1 files changed, 165 insertions, 19 deletions

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 596f35170137..f76fe406937a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -74,6 +74,8 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
 
 int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
+	if (unlikely(nfs_current_task_exiting()))
+		return -EINTR;
 	schedule();
 	if (signal_pending_state(mode, current))
 		return -ERESTARTSYS;
@@ -106,7 +108,7 @@ u64 nfs_compat_user_ino64(u64 fileid)
 
 int nfs_drop_inode(struct inode *inode)
 {
-	return NFS_STALE(inode) || generic_drop_inode(inode);
+	return NFS_STALE(inode) || inode_generic_drop(inode);
 }
 EXPORT_SYMBOL_GPL(nfs_drop_inode);
 
@@ -195,6 +197,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 		if (!(flags & NFS_INO_REVAL_FORCED))
 			flags &= ~(NFS_INO_INVALID_MODE |
 				   NFS_INO_INVALID_OTHER |
+				   NFS_INO_INVALID_BTIME |
 				   NFS_INO_INVALID_XATTR);
 		flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE);
 	}
@@ -472,7 +475,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		goto out_no_inode;
 	}
 
-	if (inode->i_state & I_NEW) {
+	if (inode_state_read_once(inode) & I_NEW) {
 		struct nfs_inode *nfsi = NFS_I(inode);
 		unsigned long now = jiffies;
 
@@ -520,6 +523,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		inode_set_atime(inode, 0, 0);
 		inode_set_mtime(inode, 0, 0);
 		inode_set_ctime(inode, 0, 0);
+		memset(&nfsi->btime, 0, sizeof(nfsi->btime));
 		inode_set_iversion_raw(inode, 0);
 		inode->i_size = 0;
 		clear_nlink(inode);
@@ -543,6 +547,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 			inode_set_ctime_to_ts(inode, fattr->ctime);
 		else if (fattr_supported & NFS_ATTR_FATTR_CTIME)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME);
+		if (fattr->valid & NFS_ATTR_FATTR_BTIME)
+			nfsi->btime = fattr->btime;
+		else if (fattr_supported & NFS_ATTR_FATTR_BTIME)
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_BTIME);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode_set_iversion_raw(inode, fattr->change_attr);
 		else
@@ -555,6 +563,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 			set_nlink(inode, fattr->nlink);
 		else if (fattr_supported & NFS_ATTR_FATTR_NLINK)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK);
+		else
+			set_nlink(inode, 1);
 		if (fattr->valid & NFS_ATTR_FATTR_OWNER)
 			inode->i_uid = fattr->uid;
 		else if (fattr_supported & NFS_ATTR_FATTR_OWNER)
@@ -598,7 +608,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		inode->i_sb->s_id,
 		(unsigned long long)NFS_FILEID(inode),
 		nfs_display_fhandle_hash(fh),
-		atomic_read(&inode->i_count));
+		icount_read(inode));
 
 out:
 	return inode;
@@ -631,6 +641,34 @@ nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr)
 	}
 }
 
+static void nfs_set_timestamps_to_ts(struct inode *inode, struct iattr *attr)
+{
+	unsigned int cache_flags = 0;
+
+	if (attr->ia_valid & ATTR_MTIME_SET) {
+		struct timespec64 ctime = inode_get_ctime(inode);
+		struct timespec64 mtime = inode_get_mtime(inode);
+		struct timespec64 now;
+		int updated = 0;
+
+		now = inode_set_ctime_current(inode);
+		if (!timespec64_equal(&now, &ctime))
+			updated |= S_CTIME;
+
+		inode_set_mtime_to_ts(inode, attr->ia_mtime);
+		if (!timespec64_equal(&now, &mtime))
+			updated |= S_MTIME;
+
+		inode_maybe_inc_iversion(inode, updated);
+		cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
+	}
+	if (attr->ia_valid & ATTR_ATIME_SET) {
+		inode_set_atime_to_ts(inode, attr->ia_atime);
+		cache_flags |= NFS_INO_INVALID_ATIME;
+	}
+	NFS_I(inode)->cache_validity &= ~cache_flags;
+}
+
 static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid)
 {
 	enum file_time_flags time_flags = 0;
@@ -678,7 +716,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 {
 	struct inode *inode = d_inode(dentry);
 	struct nfs_fattr *fattr;
+	loff_t oldsize = i_size_read(inode);
 	int error = 0;
+	kuid_t task_uid = current_fsuid();
+	kuid_t owner_uid = inode->i_uid;
 
 	nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
 
@@ -693,20 +734,37 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		if (error)
 			return error;
 
-		if (attr->ia_size == i_size_read(inode))
+		if (attr->ia_size == oldsize)
 			attr->ia_valid &= ~ATTR_SIZE;
 	}
 
 	if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) {
 		spin_lock(&inode->i_lock);
-		nfs_update_timestamps(inode, attr->ia_valid);
+		if (attr->ia_valid & ATTR_MTIME_SET) {
+			if (uid_eq(task_uid, owner_uid)) {
+				nfs_set_timestamps_to_ts(inode, attr);
+				attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET|
+						ATTR_ATIME|ATTR_ATIME_SET);
+			}
+		} else {
+			nfs_update_timestamps(inode, attr->ia_valid);
+			attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME);
+		}
 		spin_unlock(&inode->i_lock);
-		attr->ia_valid &= ~(ATTR_MTIME | ATTR_ATIME);
 	} else if (nfs_have_delegated_atime(inode) &&
 		   attr->ia_valid & ATTR_ATIME &&
 		   !(attr->ia_valid & ATTR_MTIME)) {
-		nfs_update_delegated_atime(inode);
-		attr->ia_valid &= ~ATTR_ATIME;
+		if (attr->ia_valid & ATTR_ATIME_SET) {
+			if (uid_eq(task_uid, owner_uid)) {
+				spin_lock(&inode->i_lock);
+				nfs_set_timestamps_to_ts(inode, attr);
+				spin_unlock(&inode->i_lock);
+				attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET);
+			}
+		} else {
+			nfs_update_delegated_atime(inode);
+			attr->ia_valid &= ~ATTR_ATIME;
+		}
 	}
 
 	/* Optimization: if the end result is no change, don't RPC */
@@ -716,8 +774,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	trace_nfs_setattr_enter(inode);
 
 	/* Write all dirty data */
-	if (S_ISREG(inode->i_mode))
+	if (S_ISREG(inode->i_mode)) {
+		nfs_file_block_o_direct(NFS_I(inode));
 		nfs_sync_inode(inode);
+	}
 
 	fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
 	if (fattr == NULL) {
@@ -726,8 +786,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	}
 
 	error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
-	if (error == 0)
+	if (error == 0) {
+		if (attr->ia_valid & ATTR_SIZE)
+			nfs_truncate_last_folio(inode->i_mapping, oldsize,
+						attr->ia_size);
 		error = nfs_refresh_inode(inode, fattr);
+	}
 	nfs_free_fattr(fattr);
 out:
 	trace_nfs_setattr_exit(inode, error);
@@ -886,6 +950,7 @@ static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
 
 static u32 nfs_get_valid_attrmask(struct inode *inode)
 {
+	u64 fattr_valid = NFS_SERVER(inode)->fattr_valid;
 	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
 	u32 reply_mask = STATX_INO | STATX_TYPE;
 
@@ -905,6 +970,9 @@ static u32 nfs_get_valid_attrmask(struct inode *inode)
 		reply_mask |= STATX_UID | STATX_GID;
 	if (!(cache_validity & NFS_INO_INVALID_BLOCKS))
 		reply_mask |= STATX_BLOCKS;
+	if (!(cache_validity & NFS_INO_INVALID_BTIME) &&
+	    (fattr_valid & NFS_ATTR_FATTR_BTIME))
+		reply_mask |= STATX_BTIME;
 	if (!(cache_validity & NFS_INO_INVALID_CHANGE))
 		reply_mask |= STATX_CHANGE_COOKIE;
 	return reply_mask;
@@ -915,6 +983,7 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 {
 	struct inode *inode = d_inode(path->dentry);
 	struct nfs_server *server = NFS_SERVER(inode);
+	u64 fattr_valid = server->fattr_valid;
 	unsigned long cache_validity;
 	int err = 0;
 	bool force_sync = query_flags & AT_STATX_FORCE_SYNC;
@@ -925,9 +994,12 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 	request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID |
 			STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME |
-			STATX_INO | STATX_SIZE | STATX_BLOCKS |
+			STATX_INO | STATX_SIZE | STATX_BLOCKS | STATX_BTIME |
 			STATX_CHANGE_COOKIE;
 
+	if (!(fattr_valid & NFS_ATTR_FATTR_BTIME))
+		request_mask &= ~STATX_BTIME;
+
 	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {
 		if (readdirplus_enabled)
 			nfs_readdirplus_parent_cache_hit(path->dentry);
@@ -959,7 +1031,7 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 	/* Is the user requesting attributes that might need revalidation? */
 	if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME|
 					STATX_MTIME|STATX_UID|STATX_GID|
-					STATX_SIZE|STATX_BLOCKS|
+					STATX_SIZE|STATX_BLOCKS|STATX_BTIME|
 					STATX_CHANGE_COOKIE)))
 		goto out_no_revalidate;
 
@@ -983,6 +1055,8 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 		do_update |= cache_validity & NFS_INO_INVALID_OTHER;
 	if (request_mask & STATX_BLOCKS)
 		do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
+	if (request_mask & STATX_BTIME)
+		do_update |= cache_validity & NFS_INO_INVALID_BTIME;
 
 	if (do_update) {
 		if (readdirplus_enabled)
@@ -1004,6 +1078,22 @@ out_no_revalidate:
 		stat->attributes |= STATX_ATTR_CHANGE_MONOTONIC;
 	if (S_ISDIR(inode->i_mode))
 		stat->blksize = NFS_SERVER(inode)->dtsize;
+	stat->btime = NFS_I(inode)->btime;
+
+	/* Special handling for STATX_DIOALIGN and STATX_DIO_READ_ALIGN
+	 * - NFS doesn't have DIO alignment constraints, avoid getting
+	 *   these DIO attrs from remote and just respond with most
+	 *   accommodating limits (so client will issue supported DIO).
+	 * - this is unintuitive, but the most coarse-grained
+	 *   dio_offset_align is the most accommodating.
+	 */
+	if ((request_mask & (STATX_DIOALIGN | STATX_DIO_READ_ALIGN)) &&
+	    S_ISREG(inode->i_mode)) {
+		stat->result_mask |= STATX_DIOALIGN | STATX_DIO_READ_ALIGN;
+		stat->dio_mem_align = 4; /* 4-byte alignment */
+		stat->dio_offset_align = PAGE_SIZE;
+		stat->dio_read_offset_align = stat->dio_offset_align;
+	}
 out:
 	trace_nfs_getattr_exit(inode, err);
 	return err;
@@ -1137,6 +1227,8 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
 	ctx->lock_context.open_context = ctx;
 	INIT_LIST_HEAD(&ctx->list);
 	ctx->mdsthreshold = NULL;
+	nfs_localio_file_init(&ctx->nfl);
+
 	return ctx;
 }
 EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
@@ -1168,6 +1260,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 	nfs_sb_deactive(sb);
 	put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1));
 	kfree(ctx->mdsthreshold);
+	nfs_close_local_fh(&ctx->nfl);
 	kfree_rcu(ctx, rcu_head);
 }
 
@@ -1895,7 +1988,7 @@ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr,
 		NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME |
 		NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
 		NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER |
-		NFS_INO_INVALID_NLINK;
+		NFS_INO_INVALID_NLINK | NFS_INO_INVALID_BTIME;
 	unsigned long cache_validity = NFS_I(inode)->cache_validity;
 	enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type;
 
@@ -2161,10 +2254,10 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	bool attr_changed = false;
 	bool have_delegation;
 
-	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
+	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%llx)\n",
 			__func__, inode->i_sb->s_id, inode->i_ino,
 			nfs_display_fhandle_hash(NFS_FH(inode)),
-			atomic_read(&inode->i_count), fattr->valid);
+			icount_read(inode), fattr->valid);
 
 	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
 		/* Only a mounted-on-fileid? Just exit */
@@ -2256,7 +2349,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					| NFS_INO_INVALID_BLOCKS
 					| NFS_INO_INVALID_NLINK
 					| NFS_INO_INVALID_MODE
-					| NFS_INO_INVALID_OTHER;
+					| NFS_INO_INVALID_OTHER
+					| NFS_INO_INVALID_BTIME;
 				if (S_ISDIR(inode->i_mode))
 					nfs_force_lookup_revalidate(inode);
 				attr_changed = true;
@@ -2290,6 +2384,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		nfsi->cache_validity |=
 			save_cache_validity & NFS_INO_INVALID_CTIME;
 
+	if (fattr->valid & NFS_ATTR_FATTR_BTIME)
+		nfsi->btime = fattr->btime;
+	else if (fattr_supported & NFS_ATTR_FATTR_BTIME)
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_BTIME;
+
 	/* Check if our cached file size is stale */
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		new_isize = nfs_size_to_loff_t(fattr->size);
@@ -2541,15 +2641,26 @@ EXPORT_SYMBOL_GPL(nfs_net_id);
 static int nfs_net_init(struct net *net)
 {
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	int err;
 
 	nfs_clients_init(net);
 
 	if (!rpc_proc_register(net, &nn->rpcstats)) {
-		nfs_clients_exit(net);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_proc_rpc;
 	}
 
-	return nfs_fs_proc_net_init(net);
+	err = nfs_fs_proc_net_init(net);
+	if (err)
+		goto err_proc_nfs;
+
+	return 0;
+
+err_proc_nfs:
+	rpc_proc_unregister(net, "nfs");
+err_proc_rpc:
+	nfs_clients_exit(net);
+	return err;
 }
 
 static void nfs_net_exit(struct net *net)
@@ -2566,6 +2677,35 @@ static struct pernet_operations nfs_net_ops = {
 	.size = sizeof(struct nfs_net),
 };
 
+#ifdef CONFIG_KEYS
+static struct key *nfs_keyring;
+
+static int __init nfs_init_keyring(void)
+{
+	nfs_keyring = keyring_alloc(".nfs",
+			     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+			     current_cred(),
+			     (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+			     (KEY_USR_ALL & ~KEY_USR_SETATTR),
+			     KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
+	return PTR_ERR_OR_ZERO(nfs_keyring);
+}
+
+static void nfs_exit_keyring(void)
+{
+	key_put(nfs_keyring);
+}
+#else
+static inline int nfs_init_keyring(void)
+{
+	return 0;
+}
+
+static inline void nfs_exit_keyring(void)
+{
+}
+#endif /* CONFIG_KEYS */
+
 /*
  * Initialize NFS
  */
@@ -2573,6 +2713,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_init_keyring();
+	if (err)
+		return err;
+
 	err = nfs_sysfs_init();
 	if (err < 0)
 		goto out10;
@@ -2633,6 +2777,7 @@ out7:
 out9:
 	nfs_sysfs_exit();
 out10:
+	nfs_exit_keyring();
 	return err;
 }
 
@@ -2648,6 +2793,7 @@ static void __exit exit_nfs_fs(void)
 	nfs_fs_proc_exit();
 	nfsiod_stop();
 	nfs_sysfs_exit();
+	nfs_exit_keyring();
 }
 
 /* Not quite true; I just maintain it */