Merge tag 'nfs-for-3.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Feature highlights include:
   - Add basic client support for NFSv4.2
   - Add basic client support for Labeled NFS (selinux for NFSv4.2)
   - Fix the use of credentials in NFSv4.1 stateful operations, and add
     support for NFSv4.1 state protection.

  Bugfix highlights:
   - Fix another NFSv4 open state recovery race
   - Fix an NFSv4.1 back channel session regression
   - Various rpc_pipefs races
   - Fix another issue with NFSv3 auth negotiation

  Please note that Labeled NFS does require some additional support from
  the security subsystem.  The relevant changesets have all been
  reviewed and acked by James Morris."

* tag 'nfs-for-3.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (54 commits)
  NFS: Set NFS_CS_MIGRATION for NFSv4 mounts
  NFSv4.1 Refactor nfs4_init_session and nfs4_init_channel_attrs
  nfs: have NFSv3 try server-specified auth flavors in turn
  nfs: have nfs_mount fake up a auth_flavs list when the server didn't provide it
  nfs: move server_authlist into nfs_try_mount_request
  nfs: refactor "need_mount" code out of nfs_try_mount
  SUNRPC: PipeFS MOUNT notification optimization for dying clients
  SUNRPC: split client creation routine into setup and registration
  SUNRPC: fix races on PipeFS UMOUNT notifications
  SUNRPC: fix races on PipeFS MOUNT notifications
  NFSv4.1 use pnfs_device maxcount for the objectlayout gdia_maxcount
  NFSv4.1 use pnfs_device maxcount for the blocklayout gdia_maxcount
  NFSv4.1 Fix gdia_maxcount calculation to fit in ca_maxresponsesize
  NFS: Improve legacy idmapping fallback
  NFSv4.1 end back channel session draining
  NFS: Apply v4.1 capabilities to v4.2
  NFSv4.1: Clean up layout segment comparison helper names
  NFSv4.1: layout segment comparison helpers should take 'const' parameters
  NFSv4: Move the DNS resolver into the NFSv4 module
  rpc_pipefs: only set rpc_dentry_ops if d_op isn't already set
  ...

6 files changed, 138 insertions, 15 deletions

diff --git a/security/capability.c b/security/capability.c
index 1728d4e375d..d32e16e3c6a 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -91,7 +91,10 @@ static int cap_sb_pivotroot(struct path *old_path, struct path *new_path)
 }
 
 static int cap_sb_set_mnt_opts(struct super_block *sb,
-			       struct security_mnt_opts *opts)
+			       struct security_mnt_opts *opts,
+			       unsigned long kern_flags,
+			       unsigned long *set_kern_flags)
+
 {
 	if (unlikely(opts->num_mnt_opts))
 		return -EOPNOTSUPP;
@@ -109,6 +112,13 @@ static int cap_sb_parse_opts_str(char *options, struct security_mnt_opts *opts)
 	return 0;
 }
 
+static int cap_dentry_init_security(struct dentry *dentry, int mode,
+					struct qstr *name, void **ctx,
+					u32 *ctxlen)
+{
+	return 0;
+}
+
 static int cap_inode_alloc_security(struct inode *inode)
 {
 	return 0;
@@ -816,6 +826,11 @@ static int cap_setprocattr(struct task_struct *p, char *name, void *value,
 	return -EINVAL;
 }
 
+static int cap_ismaclabel(const char *name)
+{
+	return 0;
+}
+
 static int cap_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 {
 	return -EOPNOTSUPP;
@@ -931,6 +946,7 @@ void __init security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, sb_set_mnt_opts);
 	set_to_cap_if_null(ops, sb_clone_mnt_opts);
 	set_to_cap_if_null(ops, sb_parse_opts_str);
+	set_to_cap_if_null(ops, dentry_init_security);
 	set_to_cap_if_null(ops, inode_alloc_security);
 	set_to_cap_if_null(ops, inode_free_security);
 	set_to_cap_if_null(ops, inode_init_security);
@@ -1034,6 +1050,7 @@ void __init security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, d_instantiate);
 	set_to_cap_if_null(ops, getprocattr);
 	set_to_cap_if_null(ops, setprocattr);
+	set_to_cap_if_null(ops, ismaclabel);
 	set_to_cap_if_null(ops, secid_to_secctx);
 	set_to_cap_if_null(ops, secctx_to_secid);
 	set_to_cap_if_null(ops, release_secctx);
diff --git a/security/security.c b/security/security.c
index a3dce87d1ae..94b35aef687 100644
--- a/security/security.c
+++ b/security/security.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/capability.h>
+#include <linux/dcache.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -293,9 +294,12 @@ int security_sb_pivotroot(struct path *old_path, struct path *new_path)
 }
 
 int security_sb_set_mnt_opts(struct super_block *sb,
-				struct security_mnt_opts *opts)
+				struct security_mnt_opts *opts,
+				unsigned long kern_flags,
+				unsigned long *set_kern_flags)
 {
-	return security_ops->sb_set_mnt_opts(sb, opts);
+	return security_ops->sb_set_mnt_opts(sb, opts, kern_flags,
+						set_kern_flags);
 }
 EXPORT_SYMBOL(security_sb_set_mnt_opts);
 
@@ -324,6 +328,15 @@ void security_inode_free(struct inode *inode)
 	security_ops->inode_free_security(inode);
 }
 
+int security_dentry_init_security(struct dentry *dentry, int mode,
+					struct qstr *name, void **ctx,
+					u32 *ctxlen)
+{
+	return security_ops->dentry_init_security(dentry, mode, name,
+							ctx, ctxlen);
+}
+EXPORT_SYMBOL(security_dentry_init_security);
+
 int security_inode_init_security(struct inode *inode, struct inode *dir,
 				 const struct qstr *qstr,
 				 const initxattrs initxattrs, void *fs_data)
@@ -647,6 +660,7 @@ int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer
 		return 0;
 	return security_ops->inode_listsecurity(inode, buffer, buffer_size);
 }
+EXPORT_SYMBOL(security_inode_listsecurity);
 
 void security_inode_getsecid(const struct inode *inode, u32 *secid)
 {
@@ -1047,6 +1061,12 @@ int security_netlink_send(struct sock *sk, struct sk_buff *skb)
 	return security_ops->netlink_send(sk, skb);
 }
 
+int security_ismaclabel(const char *name)
+{
+	return security_ops->ismaclabel(name);
+}
+EXPORT_SYMBOL(security_ismaclabel);
+
 int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 {
 	return security_ops->secid_to_secctx(secid, secdata, seclen);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index db1fca990a2..c956390a913 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -81,6 +81,7 @@
 #include <linux/syslog.h>
 #include <linux/user_namespace.h>
 #include <linux/export.h>
+#include <linux/security.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
 
@@ -284,13 +285,14 @@ static void superblock_free_security(struct super_block *sb)
 
 /* The file system's label must be initialized prior to use. */
 
-static const char *labeling_behaviors[6] = {
+static const char *labeling_behaviors[7] = {
 	"uses xattr",
 	"uses transition SIDs",
 	"uses task SIDs",
 	"uses genfs_contexts",
 	"not configured for labeling",
 	"uses mountpoint labeling",
+	"uses native labeling",
 };
 
 static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry);
@@ -552,7 +554,9 @@ static int bad_option(struct superblock_security_struct *sbsec, char flag,
  * labeling information.
  */
 static int selinux_set_mnt_opts(struct super_block *sb,
-				struct security_mnt_opts *opts)
+				struct security_mnt_opts *opts,
+				unsigned long kern_flags,
+				unsigned long *set_kern_flags)
 {
 	const struct cred *cred = current_cred();
 	int rc = 0, i;
@@ -580,6 +584,12 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 			"before the security server is initialized\n");
 		goto out;
 	}
+	if (kern_flags && !set_kern_flags) {
+		/* Specifying internal flags without providing a place to
+		 * place the results is not allowed */
+		rc = -EINVAL;
+		goto out;
+	}
 
 	/*
 	 * Binary mount data FS will come through this function twice.  Once
@@ -670,14 +680,21 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	if (strcmp(sb->s_type->name, "proc") == 0)
 		sbsec->flags |= SE_SBPROC;
 
-	/* Determine the labeling behavior to use for this filesystem type. */
-	rc = security_fs_use((sbsec->flags & SE_SBPROC) ? "proc" : sb->s_type->name, &sbsec->behavior, &sbsec->sid);
-	if (rc) {
-		printk(KERN_WARNING "%s: security_fs_use(%s) returned %d\n",
-		       __func__, sb->s_type->name, rc);
-		goto out;
+	if (!sbsec->behavior) {
+		/*
+		 * Determine the labeling behavior to use for this
+		 * filesystem type.
+		 */
+		rc = security_fs_use((sbsec->flags & SE_SBPROC) ?
+					"proc" : sb->s_type->name,
+					&sbsec->behavior, &sbsec->sid);
+		if (rc) {
+			printk(KERN_WARNING
+				"%s: security_fs_use(%s) returned %d\n",
+					__func__, sb->s_type->name, rc);
+			goto out;
+		}
 	}
-
 	/* sets the context of the superblock for the fs being mounted. */
 	if (fscontext_sid) {
 		rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred);
@@ -692,6 +709,11 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	 * sets the label used on all file below the mountpoint, and will set
 	 * the superblock context if not already set.
 	 */
+	if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) {
+		sbsec->behavior = SECURITY_FS_USE_NATIVE;
+		*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
+	}
+
 	if (context_sid) {
 		if (!fscontext_sid) {
 			rc = may_context_mount_sb_relabel(context_sid, sbsec,
@@ -723,7 +745,8 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	}
 
 	if (defcontext_sid) {
-		if (sbsec->behavior != SECURITY_FS_USE_XATTR) {
+		if (sbsec->behavior != SECURITY_FS_USE_XATTR &&
+			sbsec->behavior != SECURITY_FS_USE_NATIVE) {
 			rc = -EINVAL;
 			printk(KERN_WARNING "SELinux: defcontext option is "
 			       "invalid for this filesystem type\n");
@@ -980,7 +1003,7 @@ static int superblock_doinit(struct super_block *sb, void *data)
 		goto out_err;
 
 out:
-	rc = selinux_set_mnt_opts(sb, &opts);
+	rc = selinux_set_mnt_opts(sb, &opts, 0, NULL);
 
 out_err:
 	security_free_mnt_opts(&opts);
@@ -1222,6 +1245,8 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 	}
 
 	switch (sbsec->behavior) {
+	case SECURITY_FS_USE_NATIVE:
+		break;
 	case SECURITY_FS_USE_XATTR:
 		if (!inode->i_op->getxattr) {
 			isec->sid = sbsec->def_sid;
@@ -2527,6 +2552,40 @@ static void selinux_inode_free_security(struct inode *inode)
 	inode_free_security(inode);
 }
 
+static int selinux_dentry_init_security(struct dentry *dentry, int mode,
+					struct qstr *name, void **ctx,
+					u32 *ctxlen)
+{
+	const struct cred *cred = current_cred();
+	struct task_security_struct *tsec;
+	struct inode_security_struct *dsec;
+	struct superblock_security_struct *sbsec;
+	struct inode *dir = dentry->d_parent->d_inode;
+	u32 newsid;
+	int rc;
+
+	tsec = cred->security;
+	dsec = dir->i_security;
+	sbsec = dir->i_sb->s_security;
+
+	if (tsec->create_sid && sbsec->behavior != SECURITY_FS_USE_MNTPOINT) {
+		newsid = tsec->create_sid;
+	} else {
+		rc = security_transition_sid(tsec->sid, dsec->sid,
+					     inode_mode_to_security_class(mode),
+					     name,
+					     &newsid);
+		if (rc) {
+			printk(KERN_WARNING
+				"%s: security_transition_sid failed, rc=%d\n",
+			       __func__, -rc);
+			return rc;
+		}
+	}
+
+	return security_sid_to_context(newsid, (char **)ctx, ctxlen);
+}
+
 static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
 				       const struct qstr *qstr, char **name,
 				       void **value, size_t *len)
@@ -2861,7 +2920,10 @@ static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name,
 		return;
 	}
 
+	isec->sclass = inode_mode_to_security_class(inode->i_mode);
 	isec->sid = newsid;
+	isec->initialized = 1;
+
 	return;
 }
 
@@ -2949,6 +3011,7 @@ static int selinux_inode_setsecurity(struct inode *inode, const char *name,
 	if (rc)
 		return rc;
 
+	isec->sclass = inode_mode_to_security_class(inode->i_mode);
 	isec->sid = newsid;
 	isec->initialized = 1;
 	return 0;
@@ -5432,6 +5495,11 @@ abort_change:
 	return error;
 }
 
+static int selinux_ismaclabel(const char *name)
+{
+	return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0);
+}
+
 static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 {
 	return security_sid_to_context(secid, secdata, seclen);
@@ -5574,6 +5642,7 @@ static struct security_operations selinux_ops = {
 	.sb_clone_mnt_opts =		selinux_sb_clone_mnt_opts,
 	.sb_parse_opts_str = 		selinux_parse_opts_str,
 
+	.dentry_init_security =		selinux_dentry_init_security,
 
 	.inode_alloc_security =		selinux_inode_alloc_security,
 	.inode_free_security =		selinux_inode_free_security,
@@ -5669,6 +5738,7 @@ static struct security_operations selinux_ops = {
 	.getprocattr =			selinux_getprocattr,
 	.setprocattr =			selinux_setprocattr,
 
+	.ismaclabel =			selinux_ismaclabel,
 	.secid_to_secctx =		selinux_secid_to_secctx,
 	.secctx_to_secid =		selinux_secctx_to_secid,
 	.release_secctx =		selinux_release_secctx,
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 6d3885165d1..8fd8e18ea34 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -169,6 +169,8 @@ int security_get_allow_unknown(void);
 #define SECURITY_FS_USE_GENFS		4 /* use the genfs support */
 #define SECURITY_FS_USE_NONE		5 /* no labeling support */
 #define SECURITY_FS_USE_MNTPOINT	6 /* use mountpoint labeling */
+#define SECURITY_FS_USE_NATIVE		7 /* use native label support */
+#define SECURITY_FS_USE_MAX		7 /* Highest SECURITY_FS_USE_XXX */
 
 int security_fs_use(const char *fstype, unsigned int *behavior,
 	u32 *sid);
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 9cd9b7c661e..c8adde3aff8 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -2168,7 +2168,10 @@ static int ocontext_read(struct policydb *p, struct policydb_compat_info *info,
 
 				rc = -EINVAL;
 				c->v.behavior = le32_to_cpu(buf[0]);
-				if (c->v.behavior > SECURITY_FS_USE_NONE)
+				/* Determined at runtime, not in policy DB. */
+				if (c->v.behavior == SECURITY_FS_USE_MNTPOINT)
+					goto out;
+				if (c->v.behavior > SECURITY_FS_USE_MAX)
 					goto out;
 
 				rc = -ENOMEM;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 6a083303501..3f7682a387b 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -3640,6 +3640,16 @@ static void smack_audit_rule_free(void *vrule)
 #endif /* CONFIG_AUDIT */
 
 /**
+ * smack_ismaclabel - check if xattr @name references a smack MAC label
+ * @name: Full xattr name to check.
+ */
+static int smack_ismaclabel(const char *name)
+{
+	return (strcmp(name, XATTR_SMACK_SUFFIX) == 0);
+}
+
+
+/**
  * smack_secid_to_secctx - return the smack label for a secid
  * @secid: incoming integer
  * @secdata: destination
@@ -3836,6 +3846,7 @@ struct security_operations smack_ops = {
 	.audit_rule_free =		smack_audit_rule_free,
 #endif /* CONFIG_AUDIT */
 
+	.ismaclabel =			smack_ismaclabel,
 	.secid_to_secctx = 		smack_secid_to_secctx,
 	.secctx_to_secid = 		smack_secctx_to_secid,
 	.release_secctx = 		smack_release_secctx,