1 files changed, 189 insertions, 64 deletions

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 5b5231068516..419491d8e7d2 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -53,6 +53,7 @@
 #include <net/ip.h>             /* for local_port_range[] */
 #include <net/sock.h>
 #include <net/tcp.h>            /* struct or_callable used in sock_rcv_skb */
+#include <net/inet_connection_sock.h>
 #include <net/net_namespace.h>
 #include <net/netlabel.h>
 #include <linux/uaccess.h>
@@ -95,8 +96,6 @@
 #include "audit.h"
 #include "avc_ss.h"
 
-#define NUM_SEL_MNT_OPTS 5
-
 extern struct security_operations *security_ops;
 
 /* SECMARK reference count */
@@ -139,12 +138,28 @@ static struct kmem_cache *sel_inode_cache;
  * This function checks the SECMARK reference counter to see if any SECMARK
  * targets are currently configured, if the reference counter is greater than
  * zero SECMARK is considered to be enabled.  Returns true (1) if SECMARK is
- * enabled, false (0) if SECMARK is disabled.
+ * enabled, false (0) if SECMARK is disabled.  If the always_check_network
+ * policy capability is enabled, SECMARK is always considered enabled.
  *
  */
 static int selinux_secmark_enabled(void)
 {
-        return (atomic_read(&selinux_secmark_refcount) > 0);
+        return (selinux_policycap_alwaysnetwork || atomic_read(&selinux_secmark_refcount));
+}
+
+/**
+ * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled
+ *
+ * Description:
+ * This function checks if NetLabel or labeled IPSEC is enabled.  Returns true
+ * (1) if any are enabled or false (0) if neither are enabled.  If the
+ * always_check_network policy capability is enabled, peer labeling
+ * is always considered enabled.
+ *
+ */
+static int selinux_peerlbl_enabled(void)
+{
+        return (selinux_policycap_alwaysnetwork || netlbl_enabled() || selinux_xfrm_enabled());
 }
 
 /*
@@ -309,8 +324,11 @@ enum {
         Opt_defcontext = 3,
         Opt_rootcontext = 4,
         Opt_labelsupport = 5,
+        Opt_nextmntopt = 6,
 };
 
+#define NUM_SEL_MNT_OPTS        (Opt_nextmntopt - 1)
+
 static const match_table_t tokens = {
         {Opt_context, CONTEXT_STR "%s"},
         {Opt_fscontext, FSCONTEXT_STR "%s"},
@@ -355,6 +373,29 @@ static int may_context_mount_inode_relabel(u32 sid,
         return rc;
 }
 
+static int selinux_is_sblabel_mnt(struct super_block *sb)
+{
+        struct superblock_security_struct *sbsec = sb->s_security;
+
+        if (sbsec->behavior == SECURITY_FS_USE_XATTR ||
+            sbsec->behavior == SECURITY_FS_USE_TRANS ||
+            sbsec->behavior == SECURITY_FS_USE_TASK)
+                return 1;
+
+        /* Special handling for sysfs. Is genfs but also has setxattr handler*/
+        if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
+                return 1;
+
+        /*
+         * Special handling for rootfs. Is genfs but supports
+         * setting SELinux context on in-core inodes.
+         */
+        if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0)
+                return 1;
+
+        return 0;
+}
+
 static int sb_finish_set_opts(struct super_block *sb)
 {
         struct superblock_security_struct *sbsec = sb->s_security;
@@ -388,8 +429,6 @@ static int sb_finish_set_opts(struct super_block *sb)
                 }
         }
 
-        sbsec->flags |= (SE_SBINITIALIZED | SE_SBLABELSUPP);
-
         if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
                 printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n",
                        sb->s_id, sb->s_type->name);
@@ -398,15 +437,9 @@ static int sb_finish_set_opts(struct super_block *sb)
                        sb->s_id, sb->s_type->name,
                        labeling_behaviors[sbsec->behavior-1]);
 
-        if (sbsec->behavior == SECURITY_FS_USE_GENFS ||
-            sbsec->behavior == SECURITY_FS_USE_MNTPOINT ||
-            sbsec->behavior == SECURITY_FS_USE_NONE ||
-            sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
-                sbsec->flags &= ~SE_SBLABELSUPP;
-
-        /* Special handling for sysfs. Is genfs but also has setxattr handler*/
-        if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
-                sbsec->flags |= SE_SBLABELSUPP;
+        sbsec->flags |= SE_SBINITIALIZED;
+        if (selinux_is_sblabel_mnt(sb))
+                sbsec->flags |= SBLABEL_MNT;
 
         /* Initialize the root inode. */
         rc = inode_doinit_with_dentry(root_inode, root);
@@ -460,15 +493,18 @@ static int selinux_get_mnt_opts(const struct super_block *sb,
         if (!ss_initialized)
                 return -EINVAL;
 
+        /* make sure we always check enough bits to cover the mask */
+        BUILD_BUG_ON(SE_MNTMASK >= (1 << NUM_SEL_MNT_OPTS));
+
         tmp = sbsec->flags & SE_MNTMASK;
         /* count the number of mount options for this sb */
-        for (i = 0; i < 8; i++) {
+        for (i = 0; i < NUM_SEL_MNT_OPTS; i++) {
                 if (tmp & 0x01)
                         opts->num_mnt_opts++;
                 tmp >>= 1;
         }
         /* Check if the Label support flag is set */
-        if (sbsec->flags & SE_SBLABELSUPP)
+        if (sbsec->flags & SBLABEL_MNT)
                 opts->num_mnt_opts++;
 
         opts->mnt_opts = kcalloc(opts->num_mnt_opts, sizeof(char *), GFP_ATOMIC);
@@ -515,9 +551,9 @@ static int selinux_get_mnt_opts(const struct super_block *sb,
                 opts->mnt_opts[i] = context;
                 opts->mnt_opts_flags[i++] = ROOTCONTEXT_MNT;
         }
-        if (sbsec->flags & SE_SBLABELSUPP) {
+        if (sbsec->flags & SBLABEL_MNT) {
                 opts->mnt_opts[i] = NULL;
-                opts->mnt_opts_flags[i++] = SE_SBLABELSUPP;
+                opts->mnt_opts_flags[i++] = SBLABEL_MNT;
         }
 
         BUG_ON(i != opts->num_mnt_opts);
@@ -614,7 +650,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
         for (i = 0; i < num_opts; i++) {
                 u32 sid;
 
-                if (flags[i] == SE_SBLABELSUPP)
+                if (flags[i] == SBLABEL_MNT)
                         continue;
                 rc = security_context_to_sid(mount_options[i],
                                              strlen(mount_options[i]), &sid);
@@ -685,9 +721,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
                  * 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);
+                rc = security_fs_use(sb);
                 if (rc) {
                         printk(KERN_WARNING
                                 "%s: security_fs_use(%s) returned %d\n",
@@ -1037,7 +1071,7 @@ static void selinux_write_opts(struct seq_file *m,
                 case DEFCONTEXT_MNT:
                         prefix = DEFCONTEXT_STR;
                         break;
-                case SE_SBLABELSUPP:
+                case SBLABEL_MNT:
                         seq_putc(m, ',');
                         seq_puts(m, LABELSUPP_STR);
                         continue;
@@ -1649,7 +1683,7 @@ static int may_create(struct inode *dir,
         if (rc)
                 return rc;
 
-        if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
+        if (!newsid || !(sbsec->flags & SBLABEL_MNT)) {
                 rc = security_transition_sid(sid, dsec->sid, tclass,
                                              &dentry->d_name, &newsid);
                 if (rc)
@@ -2437,7 +2471,7 @@ static int selinux_sb_remount(struct super_block *sb, void *data)
                 u32 sid;
                 size_t len;
 
-                if (flags[i] == SE_SBLABELSUPP)
+                if (flags[i] == SBLABEL_MNT)
                         continue;
                 len = strlen(mount_options[i]);
                 rc = security_context_to_sid(mount_options[i], len, &sid);
@@ -2606,7 +2640,7 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
         if ((sbsec->flags & SE_SBINITIALIZED) &&
             (sbsec->behavior == SECURITY_FS_USE_MNTPOINT))
                 newsid = sbsec->mntpoint_sid;
-        else if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
+        else if (!newsid || !(sbsec->flags & SBLABEL_MNT)) {
                 rc = security_transition_sid(sid, dsec->sid,
                                              inode_mode_to_security_class(inode->i_mode),
                                              qstr, &newsid);
@@ -2628,7 +2662,7 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
                 isec->initialized = 1;
         }
 
-        if (!ss_initialized || !(sbsec->flags & SE_SBLABELSUPP))
+        if (!ss_initialized || !(sbsec->flags & SBLABEL_MNT))
                 return -EOPNOTSUPP;
 
         if (name)
@@ -2830,7 +2864,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
                 return selinux_inode_setotherxattr(dentry, name);
 
         sbsec = inode->i_sb->s_security;
-        if (!(sbsec->flags & SE_SBLABELSUPP))
+        if (!(sbsec->flags & SBLABEL_MNT))
                 return -EOPNOTSUPP;
 
         if (!inode_owner_or_capable(inode))
@@ -3791,8 +3825,12 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
         u32 nlbl_sid;
         u32 nlbl_type;
 
-        selinux_skb_xfrm_sid(skb, &xfrm_sid);
-        selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
+        err = selinux_xfrm_skb_sid(skb, &xfrm_sid);
+        if (unlikely(err))
+                return -EACCES;
+        err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
+        if (unlikely(err))
+                return -EACCES;
 
         err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid);
         if (unlikely(err)) {
@@ -3805,6 +3843,30 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
         return 0;
 }
 
+/**
+ * selinux_conn_sid - Determine the child socket label for a connection
+ * @sk_sid: the parent socket's SID
+ * @skb_sid: the packet's SID
+ * @conn_sid: the resulting connection SID
+ *
+ * If @skb_sid is valid then the user:role:type information from @sk_sid is
+ * combined with the MLS information from @skb_sid in order to create
+ * @conn_sid.  If @skb_sid is not valid then then @conn_sid is simply a copy
+ * of @sk_sid.  Returns zero on success, negative values on failure.
+ *
+ */
+static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid)
+{
+        int err = 0;
+
+        if (skb_sid != SECSID_NULL)
+                err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid);
+        else
+                *conn_sid = sk_sid;
+
+        return err;
+}
+
 /* socket security operations */
 
 static int socket_sockcreate_sid(const struct task_security_struct *tsec,
@@ -3928,7 +3990,7 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
                 if (snum) {
                         int low, high;
 
-                        inet_get_local_port_range(&low, &high);
+                        inet_get_local_port_range(sock_net(sk), &low, &high);
 
                         if (snum < max(PROT_SOCK, low) || snum > high) {
                                 err = sel_netport_sid(sk->sk_protocol,
@@ -4246,7 +4308,7 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
                 return selinux_sock_rcv_skb_compat(sk, skb, family);
 
         secmark_active = selinux_secmark_enabled();
-        peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
+        peerlbl_active = selinux_peerlbl_enabled();
         if (!secmark_active && !peerlbl_active)
                 return 0;
 
@@ -4411,7 +4473,7 @@ static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb,
         struct sk_security_struct *sksec = sk->sk_security;
         int err;
         u16 family = sk->sk_family;
-        u32 newsid;
+        u32 connsid;
         u32 peersid;
 
         /* handle mapped IPv4 packets arriving via IPv6 sockets */
@@ -4421,16 +4483,11 @@ static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb,
         err = selinux_skb_peerlbl_sid(skb, family, &peersid);
         if (err)
                 return err;
-        if (peersid == SECSID_NULL) {
-                req->secid = sksec->sid;
-                req->peer_secid = SECSID_NULL;
-        } else {
-                err = security_sid_mls_copy(sksec->sid, peersid, &newsid);
-                if (err)
-                        return err;
-                req->secid = newsid;
-                req->peer_secid = peersid;
-        }
+        err = selinux_conn_sid(sksec->sid, peersid, &connsid);
+        if (err)
+                return err;
+        req->secid = connsid;
+        req->peer_secid = peersid;
 
         return selinux_netlbl_inet_conn_request(req, family);
 }
@@ -4628,7 +4685,7 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
 
         secmark_active = selinux_secmark_enabled();
         netlbl_active = netlbl_enabled();
-        peerlbl_active = netlbl_active || selinux_xfrm_enabled();
+        peerlbl_active = selinux_peerlbl_enabled();
         if (!secmark_active && !peerlbl_active)
                 return NF_ACCEPT;
 
@@ -4667,7 +4724,7 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
         return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_forward(unsigned int hooknum,
+static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops,
                                          struct sk_buff *skb,
                                          const struct net_device *in,
                                          const struct net_device *out,
@@ -4677,7 +4734,7 @@ static unsigned int selinux_ipv4_forward(unsigned int hooknum,
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static unsigned int selinux_ipv6_forward(unsigned int hooknum,
+static unsigned int selinux_ipv6_forward(const struct nf_hook_ops *ops,
                                          struct sk_buff *skb,
                                          const struct net_device *in,
                                          const struct net_device *out,
@@ -4690,6 +4747,7 @@ static unsigned int selinux_ipv6_forward(unsigned int hooknum,
 static unsigned int selinux_ip_output(struct sk_buff *skb,
                                       u16 family)
 {
+        struct sock *sk;
         u32 sid;
 
         if (!netlbl_enabled())
@@ -4698,8 +4756,27 @@ static unsigned int selinux_ip_output(struct sk_buff *skb,
         /* we do this in the LOCAL_OUT path and not the POST_ROUTING path
          * because we want to make sure we apply the necessary labeling
          * before IPsec is applied so we can leverage AH protection */
-        if (skb->sk) {
-                struct sk_security_struct *sksec = skb->sk->sk_security;
+        sk = skb->sk;
+        if (sk) {
+                struct sk_security_struct *sksec;
+
+                if (sk->sk_state == TCP_LISTEN)
+                        /* if the socket is the listening state then this
+                         * packet is a SYN-ACK packet which means it needs to
+                         * be labeled based on the connection/request_sock and
+                         * not the parent socket.  unfortunately, we can't
+                         * lookup the request_sock yet as it isn't queued on
+                         * the parent socket until after the SYN-ACK is sent.
+                         * the "solution" is to simply pass the packet as-is
+                         * as any IP option based labeling should be copied
+                         * from the initial connection request (in the IP
+                         * layer).  it is far from ideal, but until we get a
+                         * security label in the packet itself this is the
+                         * best we can do. */
+                        return NF_ACCEPT;
+
+                /* standard practice, label using the parent socket */
+                sksec = sk->sk_security;
                 sid = sksec->sid;
         } else
                 sid = SECINITSID_KERNEL;
@@ -4709,7 +4786,7 @@ static unsigned int selinux_ip_output(struct sk_buff *skb,
         return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_output(unsigned int hooknum,
+static unsigned int selinux_ipv4_output(const struct nf_hook_ops *ops,
                                         struct sk_buff *skb,
                                         const struct net_device *in,
                                         const struct net_device *out,
@@ -4769,27 +4846,36 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
          * as fast and as clean as possible. */
         if (!selinux_policycap_netpeer)
                 return selinux_ip_postroute_compat(skb, ifindex, family);
+
+        secmark_active = selinux_secmark_enabled();
+        peerlbl_active = selinux_peerlbl_enabled();
+        if (!secmark_active && !peerlbl_active)
+                return NF_ACCEPT;
+
+        sk = skb->sk;
+
 #ifdef CONFIG_XFRM
         /* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec
          * packet transformation so allow the packet to pass without any checks
          * since we'll have another chance to perform access control checks
          * when the packet is on it's final way out.
          * NOTE: there appear to be some IPv6 multicast cases where skb->dst
-         *       is NULL, in this case go ahead and apply access control. */
-        if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL)
+         *       is NULL, in this case go ahead and apply access control.
+         * NOTE: if this is a local socket (skb->sk != NULL) that is in the
+         *       TCP listening state we cannot wait until the XFRM processing
+         *       is done as we will miss out on the SA label if we do;
+         *       unfortunately, this means more work, but it is only once per
+         *       connection. */
+        if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL &&
+            !(sk != NULL && sk->sk_state == TCP_LISTEN))
                 return NF_ACCEPT;
 #endif
-        secmark_active = selinux_secmark_enabled();
-        peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
-        if (!secmark_active && !peerlbl_active)
-                return NF_ACCEPT;
 
-        /* if the packet is being forwarded then get the peer label from the
-         * packet itself; otherwise check to see if it is from a local
-         * application or the kernel, if from an application get the peer label
-         * from the sending socket, otherwise use the kernel's sid */
-        sk = skb->sk;
         if (sk == NULL) {
+                /* Without an associated socket the packet is either coming
+                 * from the kernel or it is being forwarded; check the packet
+                 * to determine which and if the packet is being forwarded
+                 * query the packet directly to determine the security label. */
                 if (skb->skb_iif) {
                         secmark_perm = PACKET__FORWARD_OUT;
                         if (selinux_skb_peerlbl_sid(skb, family, &peer_sid))
@@ -4798,7 +4884,45 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
                         secmark_perm = PACKET__SEND;
                         peer_sid = SECINITSID_KERNEL;
                 }
+        } else if (sk->sk_state == TCP_LISTEN) {
+                /* Locally generated packet but the associated socket is in the
+                 * listening state which means this is a SYN-ACK packet.  In
+                 * this particular case the correct security label is assigned
+                 * to the connection/request_sock but unfortunately we can't
+                 * query the request_sock as it isn't queued on the parent
+                 * socket until after the SYN-ACK packet is sent; the only
+                 * viable choice is to regenerate the label like we do in
+                 * selinux_inet_conn_request().  See also selinux_ip_output()
+                 * for similar problems. */
+                u32 skb_sid;
+                struct sk_security_struct *sksec = sk->sk_security;
+                if (selinux_skb_peerlbl_sid(skb, family, &skb_sid))
+                        return NF_DROP;
+                /* At this point, if the returned skb peerlbl is SECSID_NULL
+                 * and the packet has been through at least one XFRM
+                 * transformation then we must be dealing with the "final"
+                 * form of labeled IPsec packet; since we've already applied
+                 * all of our access controls on this packet we can safely
+                 * pass the packet. */
+                if (skb_sid == SECSID_NULL) {
+                        switch (family) {
+                        case PF_INET:
+                                if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
+                                        return NF_ACCEPT;
+                                break;
+                        case PF_INET6:
+                                if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
+                                        return NF_ACCEPT;
+                        default:
+                                return NF_DROP_ERR(-ECONNREFUSED);
+                        }
+                }
+                if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid))
+                        return NF_DROP;
+                secmark_perm = PACKET__SEND;
         } else {
+                /* Locally generated packet, fetch the security label from the
+                 * associated socket. */
                 struct sk_security_struct *sksec = sk->sk_security;
                 peer_sid = sksec->sid;
                 secmark_perm = PACKET__SEND;
@@ -4836,7 +4960,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
         return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_postroute(unsigned int hooknum,
+static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops,
                                            struct sk_buff *skb,
                                            const struct net_device *in,
                                            const struct net_device *out,
@@ -4846,7 +4970,7 @@ static unsigned int selinux_ipv4_postroute(unsigned int hooknum,
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static unsigned int selinux_ipv6_postroute(unsigned int hooknum,
+static unsigned int selinux_ipv6_postroute(const struct nf_hook_ops *ops,
                                            struct sk_buff *skb,
                                            const struct net_device *in,
                                            const struct net_device *out,
@@ -5784,7 +5908,8 @@ static struct security_operations selinux_ops = {
         .xfrm_policy_clone_security =   selinux_xfrm_policy_clone,
         .xfrm_policy_free_security =    selinux_xfrm_policy_free,
         .xfrm_policy_delete_security =  selinux_xfrm_policy_delete,
-        .xfrm_state_alloc_security =    selinux_xfrm_state_alloc,
+        .xfrm_state_alloc =             selinux_xfrm_state_alloc,
+        .xfrm_state_alloc_acquire =     selinux_xfrm_state_alloc_acquire,
         .xfrm_state_free_security =     selinux_xfrm_state_free,
         .xfrm_state_delete_security =   selinux_xfrm_state_delete,
         .xfrm_policy_lookup =           selinux_xfrm_policy_lookup,