#include <net/icmp.h>
#include <net/ip.h> /* for local_port_range[] */
#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>
return 0;
}
+static void inode_free_rcu(struct rcu_head *head)
+{
+ struct inode_security_struct *isec;
+
+ isec = container_of(head, struct inode_security_struct, rcu);
+ kmem_cache_free(sel_inode_cache, isec);
+}
+
static void inode_free_security(struct inode *inode)
{
struct inode_security_struct *isec = inode->i_security;
list_del_init(&isec->list);
spin_unlock(&sbsec->isec_lock);
- inode->i_security = NULL;
- kmem_cache_free(sel_inode_cache, isec);
+ /*
+ * The inode may still be referenced in a path walk and
+ * a call to selinux_inode_permission() can be made
+ * after inode_free_security() is called. Ideally, the VFS
+ * wouldn't do this, but fixing that is a much harder
+ * job. For now, simply free the i_security via RCU, and
+ * leave the current inode->i_security pointer intact.
+ * The inode will be freed after the RCU grace period too.
+ */
+ call_rcu(&isec->rcu, inode_free_rcu);
}
static int file_alloc_security(struct file *file)
list_entry(sbsec->isec_head.next,
struct inode_security_struct, list);
struct inode *inode = isec->inode;
+ list_del_init(&isec->list);
spin_unlock(&sbsec->isec_lock);
inode = igrab(inode);
if (inode) {
iput(inode);
}
spin_lock(&sbsec->isec_lock);
- list_del_init(&isec->list);
goto next_inode;
}
spin_unlock(&sbsec->isec_lock);
goto out_err;
opts->mnt_opts_flags = kcalloc(NUM_SEL_MNT_OPTS, sizeof(int), GFP_ATOMIC);
- if (!opts->mnt_opts_flags) {
- kfree(opts->mnt_opts);
+ if (!opts->mnt_opts_flags)
goto out_err;
- }
if (fscontext) {
opts->mnt_opts[num_mnt_opts] = fscontext;
return 0;
out_err:
+ security_free_mnt_opts(opts);
kfree(context);
kfree(defcontext);
kfree(fscontext);
seq_puts(m, prefix);
if (has_comma)
seq_putc(m, '\"');
- seq_puts(m, opts->mnt_opts[i]);
+ seq_escape(m, opts->mnt_opts[i], "\"\n\\");
if (has_comma)
seq_putc(m, '\"');
}
isec->sid = sbsec->sid;
if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
- if (opt_dentry) {
- isec->sclass = inode_mode_to_security_class(inode->i_mode);
- rc = selinux_proc_get_sid(opt_dentry,
- isec->sclass,
- &sid);
- if (rc)
- goto out_unlock;
- isec->sid = sid;
- }
+ /* We must have a dentry to determine the label on
+ * procfs inodes */
+ if (opt_dentry)
+ /* Called from d_instantiate or
+ * d_splice_alias. */
+ dentry = dget(opt_dentry);
+ else
+ /* Called from selinux_complete_init, try to
+ * find a dentry. */
+ dentry = d_find_alias(inode);
+ /*
+ * This can be hit on boot when a file is accessed
+ * before the policy is loaded. When we load policy we
+ * may find inodes that have no dentry on the
+ * sbsec->isec_head list. No reason to complain as
+ * these will get fixed up the next time we go through
+ * inode_doinit() with a dentry, before these inodes
+ * could be used again by userspace.
+ */
+ if (!dentry)
+ goto out_unlock;
+ isec->sclass = inode_mode_to_security_class(inode->i_mode);
+ rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
+ dput(dentry);
+ if (rc)
+ goto out_unlock;
+ isec->sid = sid;
}
break;
}
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,
}
err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER,
PEER__RECV, &ad);
- if (err)
+ if (err) {
selinux_netlbl_err(skb, err, 0);
+ return err;
+ }
}
if (secmark_active) {
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 */
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);
}
static unsigned int selinux_ip_output(struct sk_buff *skb,
u16 family)
{
+ struct sock *sk;
u32 sid;
if (!netlbl_enabled())
/* 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;
* 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 = netlbl_enabled() || selinux_xfrm_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))
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;
/* Check for ptracing, and update the task SID if ok.
Otherwise, leave SID unchanged and fail. */
ptsid = 0;
- task_lock(p);
+ rcu_read_lock();
tracer = ptrace_parent(p);
if (tracer)
ptsid = task_sid(tracer);
- task_unlock(p);
+ rcu_read_unlock();
if (tracer) {
error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS,