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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 157 insertions, 20 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a28e09c7825d..630a7bac1e51 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -755,7 +755,7 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 	enum bpf_reg_type expected_type;
 	int err = 0;
 
-	if (arg_type == ARG_ANYTHING)
+	if (arg_type == ARG_DONTCARE)
 		return 0;
 
 	if (reg->type == NOT_INIT) {
@@ -763,6 +763,9 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 		return -EACCES;
 	}
 
+	if (arg_type == ARG_ANYTHING)
+		return 0;
+
 	if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY ||
 	    arg_type == ARG_PTR_TO_MAP_VALUE) {
 		expected_type = PTR_TO_STACK;
@@ -770,6 +773,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 		expected_type = CONST_IMM;
 	} else if (arg_type == ARG_CONST_MAP_PTR) {
 		expected_type = CONST_PTR_TO_MAP;
+	} else if (arg_type == ARG_PTR_TO_CTX) {
+		expected_type = PTR_TO_CTX;
 	} else {
 		verbose("unsupported arg_type %d\n", arg_type);
 		return -EFAULT;
@@ -852,7 +857,7 @@ static int check_call(struct verifier_env *env, int func_id)
 	}
 
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
-	if (!env->prog->aux->is_gpl_compatible && fn->gpl_only) {
+	if (!env->prog->gpl_compatible && fn->gpl_only) {
 		verbose("cannot call GPL only function from proprietary program\n");
 		return -EINVAL;
 	}
@@ -1172,6 +1177,18 @@ static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+static bool may_access_skb(enum bpf_prog_type type)
+{
+	switch (type) {
+	case BPF_PROG_TYPE_SOCKET_FILTER:
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* verify safety of LD_ABS|LD_IND instructions:
  * - they can only appear in the programs where ctx == skb
  * - since they are wrappers of function calls, they scratch R1-R5 registers,
@@ -1194,8 +1211,8 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
 	struct reg_state *reg;
 	int i, err;
 
-	if (env->prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
-		verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n");
+	if (!may_access_skb(env->prog->type)) {
+		verbose("BPF_LD_ABS|IND instructions not allowed for this program type\n");
 		return -EINVAL;
 	}
 
@@ -1606,11 +1623,10 @@ static int do_check(struct verifier_env *env)
 				return err;
 
 		} else if (class == BPF_LDX) {
-			if (BPF_MODE(insn->code) != BPF_MEM ||
-			    insn->imm != 0) {
-				verbose("BPF_LDX uses reserved fields\n");
-				return -EINVAL;
-			}
+			enum bpf_reg_type src_reg_type;
+
+			/* check for reserved fields is already done */
+
 			/* check src operand */
 			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
 			if (err)
@@ -1629,6 +1645,29 @@ static int do_check(struct verifier_env *env)
 			if (err)
 				return err;
 
+			src_reg_type = regs[insn->src_reg].type;
+
+			if (insn->imm == 0 && BPF_SIZE(insn->code) == BPF_W) {
+				/* saw a valid insn
+				 * dst_reg = *(u32 *)(src_reg + off)
+				 * use reserved 'imm' field to mark this insn
+				 */
+				insn->imm = src_reg_type;
+
+			} else if (src_reg_type != insn->imm &&
+				   (src_reg_type == PTR_TO_CTX ||
+				    insn->imm == PTR_TO_CTX)) {
+				/* ABuser program is trying to use the same insn
+				 * dst_reg = *(u32*) (src_reg + off)
+				 * with different pointer types:
+				 * src_reg == ctx in one branch and
+				 * src_reg == stack|map in some other branch.
+				 * Reject it.
+				 */
+				verbose("same insn cannot be used with different pointers\n");
+				return -EINVAL;
+			}
+
 		} else if (class == BPF_STX) {
 			if (BPF_MODE(insn->code) == BPF_XADD) {
 				err = check_xadd(env, insn);
@@ -1776,6 +1815,13 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 	int i, j;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (BPF_CLASS(insn->code) == BPF_LDX &&
+		    (BPF_MODE(insn->code) != BPF_MEM ||
+		     insn->imm != 0)) {
+			verbose("BPF_LDX uses reserved fields\n");
+			return -EINVAL;
+		}
+
 		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
 			struct bpf_map *map;
 			struct fd f;
@@ -1867,6 +1913,92 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env)
 			insn->src_reg = 0;
 }
 
+static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
+{
+	struct bpf_insn *insn = prog->insnsi;
+	int insn_cnt = prog->len;
+	int i;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (BPF_CLASS(insn->code) != BPF_JMP ||
+		    BPF_OP(insn->code) == BPF_CALL ||
+		    BPF_OP(insn->code) == BPF_EXIT)
+			continue;
+
+		/* adjust offset of jmps if necessary */
+		if (i < pos && i + insn->off + 1 > pos)
+			insn->off += delta;
+		else if (i > pos && i + insn->off + 1 < pos)
+			insn->off -= delta;
+	}
+}
+
+/* convert load instructions that access fields of 'struct __sk_buff'
+ * into sequence of instructions that access fields of 'struct sk_buff'
+ */
+static int convert_ctx_accesses(struct verifier_env *env)
+{
+	struct bpf_insn *insn = env->prog->insnsi;
+	int insn_cnt = env->prog->len;
+	struct bpf_insn insn_buf[16];
+	struct bpf_prog *new_prog;
+	u32 cnt;
+	int i;
+
+	if (!env->prog->aux->ops->convert_ctx_access)
+		return 0;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (insn->code != (BPF_LDX | BPF_MEM | BPF_W))
+			continue;
+
+		if (insn->imm != PTR_TO_CTX) {
+			/* clear internal mark */
+			insn->imm = 0;
+			continue;
+		}
+
+		cnt = env->prog->aux->ops->
+			convert_ctx_access(insn->dst_reg, insn->src_reg,
+					   insn->off, insn_buf);
+		if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+			verbose("bpf verifier is misconfigured\n");
+			return -EINVAL;
+		}
+
+		if (cnt == 1) {
+			memcpy(insn, insn_buf, sizeof(*insn));
+			continue;
+		}
+
+		/* several new insns need to be inserted. Make room for them */
+		insn_cnt += cnt - 1;
+		new_prog = bpf_prog_realloc(env->prog,
+					    bpf_prog_size(insn_cnt),
+					    GFP_USER);
+		if (!new_prog)
+			return -ENOMEM;
+
+		new_prog->len = insn_cnt;
+
+		memmove(new_prog->insnsi + i + cnt, new_prog->insns + i + 1,
+			sizeof(*insn) * (insn_cnt - i - cnt));
+
+		/* copy substitute insns in place of load instruction */
+		memcpy(new_prog->insnsi + i, insn_buf, sizeof(*insn) * cnt);
+
+		/* adjust branches in the whole program */
+		adjust_branches(new_prog, i, cnt - 1);
+
+		/* keep walking new program and skip insns we just inserted */
+		env->prog = new_prog;
+		insn = new_prog->insnsi + i + cnt - 1;
+		i += cnt - 1;
+	}
+
+	return 0;
+}
+
 static void free_states(struct verifier_env *env)
 {
 	struct verifier_state_list *sl, *sln;
@@ -1889,13 +2021,13 @@ static void free_states(struct verifier_env *env)
 	kfree(env->explored_states);
 }
 
-int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
+int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 {
 	char __user *log_ubuf = NULL;
 	struct verifier_env *env;
 	int ret = -EINVAL;
 
-	if (prog->len <= 0 || prog->len > BPF_MAXINSNS)
+	if ((*prog)->len <= 0 || (*prog)->len > BPF_MAXINSNS)
 		return -E2BIG;
 
 	/* 'struct verifier_env' can be global, but since it's not small,
@@ -1905,7 +2037,7 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 	if (!env)
 		return -ENOMEM;
 
-	env->prog = prog;
+	env->prog = *prog;
 
 	/* grab the mutex to protect few globals used by verifier */
 	mutex_lock(&bpf_verifier_lock);
@@ -1937,7 +2069,7 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 	if (ret < 0)
 		goto skip_full_check;
 
-	env->explored_states = kcalloc(prog->len,
+	env->explored_states = kcalloc(env->prog->len,
 				       sizeof(struct verifier_state_list *),
 				       GFP_USER);
 	ret = -ENOMEM;
@@ -1954,6 +2086,10 @@ skip_full_check:
 	while (pop_stack(env, NULL) >= 0);
 	free_states(env);
 
+	if (ret == 0)
+		/* program is valid, convert *(u32*)(ctx + off) accesses */
+		ret = convert_ctx_accesses(env);
+
 	if (log_level && log_len >= log_size - 1) {
 		BUG_ON(log_len >= log_size);
 		/* verifier log exceeded user supplied buffer */
@@ -1969,18 +2105,18 @@ skip_full_check:
 
 	if (ret == 0 && env->used_map_cnt) {
 		/* if program passed verifier, update used_maps in bpf_prog_info */
-		prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
-						     sizeof(env->used_maps[0]),
-						     GFP_KERNEL);
+		env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
+							  sizeof(env->used_maps[0]),
+							  GFP_KERNEL);
 
-		if (!prog->aux->used_maps) {
+		if (!env->prog->aux->used_maps) {
 			ret = -ENOMEM;
 			goto free_log_buf;
 		}
 
-		memcpy(prog->aux->used_maps, env->used_maps,
+		memcpy(env->prog->aux->used_maps, env->used_maps,
 		       sizeof(env->used_maps[0]) * env->used_map_cnt);
-		prog->aux->used_map_cnt = env->used_map_cnt;
+		env->prog->aux->used_map_cnt = env->used_map_cnt;
 
 		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
 		 * bpf_ld_imm64 instructions
@@ -1992,11 +2128,12 @@ free_log_buf:
 	if (log_level)
 		vfree(log_buf);
 free_env:
-	if (!prog->aux->used_maps)
+	if (!env->prog->aux->used_maps)
 		/* if we didn't copy map pointers into bpf_prog_info, release
 		 * them now. Otherwise free_bpf_prog_info() will release them.
 		 */
 		release_maps(env);
+	*prog = env->prog;
 	kfree(env);
 	mutex_unlock(&bpf_verifier_lock);
 	return ret;