Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

5 files changed, 222 insertions, 67 deletions

diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 5ef7e52..c65b39b 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -15,15 +15,6 @@
 #include <linux/rcupdate.h>
 #include <linux/mutex.h>
 
-#define ACC_MKNOD 1
-#define ACC_READ  2
-#define ACC_WRITE 4
-#define ACC_MASK (ACC_MKNOD | ACC_READ | ACC_WRITE)
-
-#define DEV_BLOCK 1
-#define DEV_CHAR  2
-#define DEV_ALL   4  /* this represents all devices */
-
 static DEFINE_MUTEX(devcgroup_mutex);
 
 enum devcg_behavior {
@@ -246,21 +237,21 @@ static void set_access(char *acc, short access)
 {
 	int idx = 0;
 	memset(acc, 0, ACCLEN);
-	if (access & ACC_READ)
+	if (access & DEVCG_ACC_READ)
 		acc[idx++] = 'r';
-	if (access & ACC_WRITE)
+	if (access & DEVCG_ACC_WRITE)
 		acc[idx++] = 'w';
-	if (access & ACC_MKNOD)
+	if (access & DEVCG_ACC_MKNOD)
 		acc[idx++] = 'm';
 }
 
 static char type_to_char(short type)
 {
-	if (type == DEV_ALL)
+	if (type == DEVCG_DEV_ALL)
 		return 'a';
-	if (type == DEV_CHAR)
+	if (type == DEVCG_DEV_CHAR)
 		return 'c';
-	if (type == DEV_BLOCK)
+	if (type == DEVCG_DEV_BLOCK)
 		return 'b';
 	return 'X';
 }
@@ -287,10 +278,10 @@ static int devcgroup_seq_show(struct seq_file *m, void *v)
 	 * This way, the file remains as a "whitelist of devices"
 	 */
 	if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
-		set_access(acc, ACC_MASK);
+		set_access(acc, DEVCG_ACC_MASK);
 		set_majmin(maj, ~0);
 		set_majmin(min, ~0);
-		seq_printf(m, "%c %s:%s %s\n", type_to_char(DEV_ALL),
+		seq_printf(m, "%c %s:%s %s\n", type_to_char(DEVCG_DEV_ALL),
 			   maj, min, acc);
 	} else {
 		list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) {
@@ -309,10 +300,10 @@ static int devcgroup_seq_show(struct seq_file *m, void *v)
 /**
  * match_exception	- iterates the exception list trying to find a complete match
  * @exceptions: list of exceptions
- * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR)
  * @major: device file major number, ~0 to match all
  * @minor: device file minor number, ~0 to match all
- * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD)
  *
  * It is considered a complete match if an exception is found that will
  * contain the entire range of provided parameters.
@@ -325,9 +316,9 @@ static bool match_exception(struct list_head *exceptions, short type,
 	struct dev_exception_item *ex;
 
 	list_for_each_entry_rcu(ex, exceptions, list) {
-		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+		if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
 			continue;
-		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))
 			continue;
 		if (ex->major != ~0 && ex->major != major)
 			continue;
@@ -344,10 +335,10 @@ static bool match_exception(struct list_head *exceptions, short type,
 /**
  * match_exception_partial - iterates the exception list trying to find a partial match
  * @exceptions: list of exceptions
- * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR)
  * @major: device file major number, ~0 to match all
  * @minor: device file minor number, ~0 to match all
- * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD)
  *
  * It is considered a partial match if an exception's range is found to
  * contain *any* of the devices specified by provided parameters. This is
@@ -362,9 +353,9 @@ static bool match_exception_partial(struct list_head *exceptions, short type,
 	struct dev_exception_item *ex;
 
 	list_for_each_entry_rcu(ex, exceptions, list) {
-		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+		if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
 			continue;
-		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))
 			continue;
 		/*
 		 * We must be sure that both the exception and the provided
@@ -647,10 +638,10 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 		}
 		return 0;
 	case 'b':
-		ex.type = DEV_BLOCK;
+		ex.type = DEVCG_DEV_BLOCK;
 		break;
 	case 'c':
-		ex.type = DEV_CHAR;
+		ex.type = DEVCG_DEV_CHAR;
 		break;
 	default:
 		return -EINVAL;
@@ -703,13 +694,13 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	for (b++, count = 0; count < 3; count++, b++) {
 		switch (*b) {
 		case 'r':
-			ex.access |= ACC_READ;
+			ex.access |= DEVCG_ACC_READ;
 			break;
 		case 'w':
-			ex.access |= ACC_WRITE;
+			ex.access |= DEVCG_ACC_WRITE;
 			break;
 		case 'm':
-			ex.access |= ACC_MKNOD;
+			ex.access |= DEVCG_ACC_MKNOD;
 			break;
 		case '\n':
 		case '\0':
@@ -806,12 +797,12 @@ struct cgroup_subsys devices_cgrp_subsys = {
  * @type: device type
  * @major: device major number
  * @minor: device minor number
- * @access: combination of ACC_WRITE, ACC_READ and ACC_MKNOD
+ * @access: combination of DEVCG_ACC_WRITE, DEVCG_ACC_READ and DEVCG_ACC_MKNOD
  *
  * returns 0 on success, -EPERM case the operation is not permitted
  */
-static int __devcgroup_check_permission(short type, u32 major, u32 minor,
-				        short access)
+int __devcgroup_check_permission(short type, u32 major, u32 minor,
+				 short access)
 {
 	struct dev_cgroup *dev_cgroup;
 	bool rc;
@@ -833,37 +824,3 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor,
 
 	return 0;
 }
-
-int __devcgroup_inode_permission(struct inode *inode, int mask)
-{
-	short type, access = 0;
-
-	if (S_ISBLK(inode->i_mode))
-		type = DEV_BLOCK;
-	if (S_ISCHR(inode->i_mode))
-		type = DEV_CHAR;
-	if (mask & MAY_WRITE)
-		access |= ACC_WRITE;
-	if (mask & MAY_READ)
-		access |= ACC_READ;
-
-	return __devcgroup_check_permission(type, imajor(inode), iminor(inode),
-			access);
-}
-
-int devcgroup_inode_mknod(int mode, dev_t dev)
-{
-	short type;
-
-	if (!S_ISBLK(mode) && !S_ISCHR(mode))
-		return 0;
-
-	if (S_ISBLK(mode))
-		type = DEV_BLOCK;
-	else
-		type = DEV_CHAR;
-
-	return __devcgroup_check_permission(type, MAJOR(dev), MINOR(dev),
-			ACC_MKNOD);
-
-}
diff --git a/security/security.c b/security/security.c
index 4bf0f57..1cd8526 100644
--- a/security/security.c
+++ b/security/security.c
@@ -12,6 +12,7 @@
  *	(at your option) any later version.
  */
 
+#include <linux/bpf.h>
 #include <linux/capability.h>
 #include <linux/dcache.h>
 #include <linux/module.h>
@@ -1703,3 +1704,34 @@ int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule,
 				actx);
 }
 #endif /* CONFIG_AUDIT */
+
+#ifdef CONFIG_BPF_SYSCALL
+int security_bpf(int cmd, union bpf_attr *attr, unsigned int size)
+{
+	return call_int_hook(bpf, 0, cmd, attr, size);
+}
+int security_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+	return call_int_hook(bpf_map, 0, map, fmode);
+}
+int security_bpf_prog(struct bpf_prog *prog)
+{
+	return call_int_hook(bpf_prog, 0, prog);
+}
+int security_bpf_map_alloc(struct bpf_map *map)
+{
+	return call_int_hook(bpf_map_alloc_security, 0, map);
+}
+int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+	return call_int_hook(bpf_prog_alloc_security, 0, aux);
+}
+void security_bpf_map_free(struct bpf_map *map)
+{
+	call_void_hook(bpf_map_free_security, map);
+}
+void security_bpf_prog_free(struct bpf_prog_aux *aux)
+{
+	call_void_hook(bpf_prog_free_security, aux);
+}
+#endif /* CONFIG_BPF_SYSCALL */
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index f5d3047..2e3a627 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -85,6 +85,7 @@
 #include <linux/export.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
+#include <linux/bpf.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -1814,6 +1815,10 @@ static inline int file_path_has_perm(const struct cred *cred,
 	return inode_has_perm(cred, file_inode(file), av, &ad);
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+static int bpf_fd_pass(struct file *file, u32 sid);
+#endif
+
 /* Check whether a task can use an open file descriptor to
    access an inode in a given way.  Check access to the
    descriptor itself, and then use dentry_has_perm to
@@ -1844,6 +1849,12 @@ static int file_has_perm(const struct cred *cred,
 			goto out;
 	}
 
+#ifdef CONFIG_BPF_SYSCALL
+	rc = bpf_fd_pass(file, cred_sid(cred));
+	if (rc)
+		return rc;
+#endif
+
 	/* av is zero if only checking access to the descriptor. */
 	rc = 0;
 	if (av)
@@ -2164,6 +2175,12 @@ static int selinux_binder_transfer_file(struct task_struct *from,
 			return rc;
 	}
 
+#ifdef CONFIG_BPF_SYSCALL
+	rc = bpf_fd_pass(file, sid);
+	if (rc)
+		return rc;
+#endif
+
 	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
 		return 0;
 
@@ -6252,6 +6269,139 @@ static void selinux_ib_free_security(void *ib_sec)
 }
 #endif
 
+#ifdef CONFIG_BPF_SYSCALL
+static int selinux_bpf(int cmd, union bpf_attr *attr,
+				     unsigned int size)
+{
+	u32 sid = current_sid();
+	int ret;
+
+	switch (cmd) {
+	case BPF_MAP_CREATE:
+		ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE,
+				   NULL);
+		break;
+	case BPF_PROG_LOAD:
+		ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD,
+				   NULL);
+		break;
+	default:
+		ret = 0;
+		break;
+	}
+
+	return ret;
+}
+
+static u32 bpf_map_fmode_to_av(fmode_t fmode)
+{
+	u32 av = 0;
+
+	if (fmode & FMODE_READ)
+		av |= BPF__MAP_READ;
+	if (fmode & FMODE_WRITE)
+		av |= BPF__MAP_WRITE;
+	return av;
+}
+
+/* This function will check the file pass through unix socket or binder to see
+ * if it is a bpf related object. And apply correspinding checks on the bpf
+ * object based on the type. The bpf maps and programs, not like other files and
+ * socket, are using a shared anonymous inode inside the kernel as their inode.
+ * So checking that inode cannot identify if the process have privilege to
+ * access the bpf object and that's why we have to add this additional check in
+ * selinux_file_receive and selinux_binder_transfer_files.
+ */
+static int bpf_fd_pass(struct file *file, u32 sid)
+{
+	struct bpf_security_struct *bpfsec;
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	int ret;
+
+	if (file->f_op == &bpf_map_fops) {
+		map = file->private_data;
+		bpfsec = map->security;
+		ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+				   bpf_map_fmode_to_av(file->f_mode), NULL);
+		if (ret)
+			return ret;
+	} else if (file->f_op == &bpf_prog_fops) {
+		prog = file->private_data;
+		bpfsec = prog->aux->security;
+		ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+				   BPF__PROG_RUN, NULL);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+	u32 sid = current_sid();
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = map->security;
+	return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+			    bpf_map_fmode_to_av(fmode), NULL);
+}
+
+static int selinux_bpf_prog(struct bpf_prog *prog)
+{
+	u32 sid = current_sid();
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = prog->aux->security;
+	return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+			    BPF__PROG_RUN, NULL);
+}
+
+static int selinux_bpf_map_alloc(struct bpf_map *map)
+{
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL);
+	if (!bpfsec)
+		return -ENOMEM;
+
+	bpfsec->sid = current_sid();
+	map->security = bpfsec;
+
+	return 0;
+}
+
+static void selinux_bpf_map_free(struct bpf_map *map)
+{
+	struct bpf_security_struct *bpfsec = map->security;
+
+	map->security = NULL;
+	kfree(bpfsec);
+}
+
+static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL);
+	if (!bpfsec)
+		return -ENOMEM;
+
+	bpfsec->sid = current_sid();
+	aux->security = bpfsec;
+
+	return 0;
+}
+
+static void selinux_bpf_prog_free(struct bpf_prog_aux *aux)
+{
+	struct bpf_security_struct *bpfsec = aux->security;
+
+	aux->security = NULL;
+	kfree(bpfsec);
+}
+#endif
+
 static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr),
 	LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction),
@@ -6471,6 +6621,16 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match),
 	LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free),
 #endif
+
+#ifdef CONFIG_BPF_SYSCALL
+	LSM_HOOK_INIT(bpf, selinux_bpf),
+	LSM_HOOK_INIT(bpf_map, selinux_bpf_map),
+	LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog),
+	LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc),
+	LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc),
+	LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free),
+	LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free),
+#endif
 };
 
 static __init int selinux_init(void)
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index cc35695..acdee77 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -238,6 +238,8 @@ struct security_class_mapping secclass_map[] = {
 	  { "access", NULL } },
 	{ "infiniband_endport",
 	  { "manage_subnet", NULL } },
+	{ "bpf",
+	  {"map_create", "map_read", "map_write", "prog_load", "prog_run"} },
 	{ NULL }
   };
 
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 1649cd1..3d54468 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -150,6 +150,10 @@ struct pkey_security_struct {
 	u32	sid;	/* SID of pkey */
 };
 
+struct bpf_security_struct {
+	u32 sid;  /*SID of bpf obj creater*/
+};
+
 extern unsigned int selinux_checkreqprot;
 
 #endif /* _SELINUX_OBJSEC_H_ */