Merge tag 'net-5.12-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.12-rc8, including fixes from netfilter, and
  bpf. BPF verifier changes stand out, otherwise things have slowed
  down.

  Current release - regressions:

   - gro: ensure frag0 meets IP header alignment

   - Revert "net: stmmac: re-init rx buffers when mac resume back"

   - ethernet: macb: fix the restore of cmp registers

  Previous releases - regressions:

   - ixgbe: Fix NULL pointer dereference in ethtool loopback test

   - ixgbe: fix unbalanced device enable/disable in suspend/resume

   - phy: marvell: fix detection of PHY on Topaz switches

   - make tcp_allowed_congestion_control readonly in non-init netns

   - xen-netback: Check for hotplug-status existence before watching

  Previous releases - always broken:

   - bpf: mitigate a speculative oob read of up to map value size by
     tightening the masking window

   - sctp: fix race condition in sctp_destroy_sock

   - sit, ip6_tunnel: Unregister catch-all devices

   - netfilter: nftables: clone set element expression template

   - netfilter: flowtable: fix NAT IPv6 offload mangling

   - net: geneve: check skb is large enough for IPv4/IPv6 header

   - netlink: don't call ->netlink_bind with table lock held"

* tag 'net-5.12-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (52 commits)
  netlink: don't call ->netlink_bind with table lock held
  MAINTAINERS: update my email
  bpf: Update selftests to reflect new error states
  bpf: Tighten speculative pointer arithmetic mask
  bpf: Move sanitize_val_alu out of op switch
  bpf: Refactor and streamline bounds check into helper
  bpf: Improve verifier error messages for users
  bpf: Rework ptr_limit into alu_limit and add common error path
  bpf: Ensure off_reg has no mixed signed bounds for all types
  bpf: Move off_reg into sanitize_ptr_alu
  bpf: Use correct permission flag for mixed signed bounds arithmetic
  ch_ktls: do not send snd_una update to TCB in middle
  ch_ktls: tcb close causes tls connection failure
  ch_ktls: fix device connection close
  ch_ktls: Fix kernel panic
  i40e: fix the panic when running bpf in xdpdrv mode
  net/mlx5e: fix ingress_ifindex check in mlx5e_flower_parse_meta
  net/mlx5e: Fix setting of RS FEC mode
  net/mlx5: Fix setting of devlink traps in switchdev mode
  Revert "net: stmmac: re-init rx buffers when mac resume back"
  ...

1 files changed, 156 insertions, 74 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3a738724a380..0399ac092b36 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5856,40 +5856,51 @@ static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
 	return &env->insn_aux_data[env->insn_idx];
 }
 
+enum {
+	REASON_BOUNDS	= -1,
+	REASON_TYPE	= -2,
+	REASON_PATHS	= -3,
+	REASON_LIMIT	= -4,
+	REASON_STACK	= -5,
+};
+
 static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
-			      u32 *ptr_limit, u8 opcode, bool off_is_neg)
+			      const struct bpf_reg_state *off_reg,
+			      u32 *alu_limit, u8 opcode)
 {
+	bool off_is_neg = off_reg->smin_value < 0;
 	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
 			    (opcode == BPF_SUB && !off_is_neg);
-	u32 off, max;
+	u32 max = 0, ptr_limit = 0;
+
+	if (!tnum_is_const(off_reg->var_off) &&
+	    (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
+		return REASON_BOUNDS;
 
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
 		/* Offset 0 is out-of-bounds, but acceptable start for the
-		 * left direction, see BPF_REG_FP.
+		 * left direction, see BPF_REG_FP. Also, unknown scalar
+		 * offset where we would need to deal with min/max bounds is
+		 * currently prohibited for unprivileged.
 		 */
 		max = MAX_BPF_STACK + mask_to_left;
-		/* Indirect variable offset stack access is prohibited in
-		 * unprivileged mode so it's not handled here.
-		 */
-		off = ptr_reg->off + ptr_reg->var_off.value;
-		if (mask_to_left)
-			*ptr_limit = MAX_BPF_STACK + off;
-		else
-			*ptr_limit = -off - 1;
-		return *ptr_limit >= max ? -ERANGE : 0;
+		ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off);
+		break;
 	case PTR_TO_MAP_VALUE:
 		max = ptr_reg->map_ptr->value_size;
-		if (mask_to_left) {
-			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
-		} else {
-			off = ptr_reg->smin_value + ptr_reg->off;
-			*ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
-		}
-		return *ptr_limit >= max ? -ERANGE : 0;
+		ptr_limit = (mask_to_left ?
+			     ptr_reg->smin_value :
+			     ptr_reg->umax_value) + ptr_reg->off;
+		break;
 	default:
-		return -EINVAL;
+		return REASON_TYPE;
 	}
+
+	if (ptr_limit >= max)
+		return REASON_LIMIT;
+	*alu_limit = ptr_limit;
+	return 0;
 }
 
 static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
@@ -5907,7 +5918,7 @@ static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
 	if (aux->alu_state &&
 	    (aux->alu_state != alu_state ||
 	     aux->alu_limit != alu_limit))
-		return -EACCES;
+		return REASON_PATHS;
 
 	/* Corresponding fixup done in fixup_bpf_calls(). */
 	aux->alu_state = alu_state;
@@ -5926,14 +5937,22 @@ static int sanitize_val_alu(struct bpf_verifier_env *env,
 	return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
 }
 
+static bool sanitize_needed(u8 opcode)
+{
+	return opcode == BPF_ADD || opcode == BPF_SUB;
+}
+
 static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 			    struct bpf_insn *insn,
 			    const struct bpf_reg_state *ptr_reg,
+			    const struct bpf_reg_state *off_reg,
 			    struct bpf_reg_state *dst_reg,
-			    bool off_is_neg)
+			    struct bpf_insn_aux_data *tmp_aux,
+			    const bool commit_window)
 {
+	struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux;
 	struct bpf_verifier_state *vstate = env->cur_state;
-	struct bpf_insn_aux_data *aux = cur_aux(env);
+	bool off_is_neg = off_reg->smin_value < 0;
 	bool ptr_is_dst_reg = ptr_reg == dst_reg;
 	u8 opcode = BPF_OP(insn->code);
 	u32 alu_state, alu_limit;
@@ -5951,18 +5970,33 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	if (vstate->speculative)
 		goto do_sim;
 
-	alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
-	alu_state |= ptr_is_dst_reg ?
-		     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
-
-	err = retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg);
+	err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode);
 	if (err < 0)
 		return err;
 
+	if (commit_window) {
+		/* In commit phase we narrow the masking window based on
+		 * the observed pointer move after the simulated operation.
+		 */
+		alu_state = tmp_aux->alu_state;
+		alu_limit = abs(tmp_aux->alu_limit - alu_limit);
+	} else {
+		alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+		alu_state |= ptr_is_dst_reg ?
+			     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+	}
+
 	err = update_alu_sanitation_state(aux, alu_state, alu_limit);
 	if (err < 0)
 		return err;
 do_sim:
+	/* If we're in commit phase, we're done here given we already
+	 * pushed the truncated dst_reg into the speculative verification
+	 * stack.
+	 */
+	if (commit_window)
+		return 0;
+
 	/* Simulate and find potential out-of-bounds access under
 	 * speculative execution from truncation as a result of
 	 * masking when off was not within expected range. If off
@@ -5979,7 +6013,46 @@ do_sim:
 	ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
 	if (!ptr_is_dst_reg && ret)
 		*dst_reg = tmp;
-	return !ret ? -EFAULT : 0;
+	return !ret ? REASON_STACK : 0;
+}
+
+static int sanitize_err(struct bpf_verifier_env *env,
+			const struct bpf_insn *insn, int reason,
+			const struct bpf_reg_state *off_reg,
+			const struct bpf_reg_state *dst_reg)
+{
+	static const char *err = "pointer arithmetic with it prohibited for !root";
+	const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub";
+	u32 dst = insn->dst_reg, src = insn->src_reg;
+
+	switch (reason) {
+	case REASON_BOUNDS:
+		verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n",
+			off_reg == dst_reg ? dst : src, err);
+		break;
+	case REASON_TYPE:
+		verbose(env, "R%d has pointer with unsupported alu operation, %s\n",
+			off_reg == dst_reg ? src : dst, err);
+		break;
+	case REASON_PATHS:
+		verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n",
+			dst, op, err);
+		break;
+	case REASON_LIMIT:
+		verbose(env, "R%d tried to %s beyond pointer bounds, %s\n",
+			dst, op, err);
+		break;
+	case REASON_STACK:
+		verbose(env, "R%d could not be pushed for speculative verification, %s\n",
+			dst, err);
+		break;
+	default:
+		verbose(env, "verifier internal error: unknown reason (%d)\n",
+			reason);
+		break;
+	}
+
+	return -EACCES;
 }
 
 /* check that stack access falls within stack limits and that 'reg' doesn't
@@ -6016,6 +6089,37 @@ static int check_stack_access_for_ptr_arithmetic(
 	return 0;
 }
 
+static int sanitize_check_bounds(struct bpf_verifier_env *env,
+				 const struct bpf_insn *insn,
+				 const struct bpf_reg_state *dst_reg)
+{
+	u32 dst = insn->dst_reg;
+
+	/* For unprivileged we require that resulting offset must be in bounds
+	 * in order to be able to sanitize access later on.
+	 */
+	if (env->bypass_spec_v1)
+		return 0;
+
+	switch (dst_reg->type) {
+	case PTR_TO_STACK:
+		if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg,
+					dst_reg->off + dst_reg->var_off.value))
+			return -EACCES;
+		break;
+	case PTR_TO_MAP_VALUE:
+		if (check_map_access(env, dst, dst_reg->off, 1, false)) {
+			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
+				"prohibited for !root\n", dst);
+			return -EACCES;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
 
 /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
  * Caller should also handle BPF_MOV case separately.
@@ -6035,8 +6139,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	    smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
 	u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
 	    umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
-	u32 dst = insn->dst_reg, src = insn->src_reg;
+	struct bpf_insn_aux_data tmp_aux = {};
 	u8 opcode = BPF_OP(insn->code);
+	u32 dst = insn->dst_reg;
 	int ret;
 
 	dst_reg = &regs[dst];
@@ -6084,13 +6189,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		verbose(env, "R%d pointer arithmetic on %s prohibited\n",
 			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
-	case PTR_TO_MAP_VALUE:
-		if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) {
-			verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
-				off_reg == dst_reg ? dst : src);
-			return -EACCES;
-		}
-		fallthrough;
 	default:
 		break;
 	}
@@ -6108,13 +6206,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	/* pointer types do not carry 32-bit bounds at the moment. */
 	__mark_reg32_unbounded(dst_reg);
 
+	if (sanitize_needed(opcode)) {
+		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
+				       &tmp_aux, false);
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, off_reg, dst_reg);
+	}
+
 	switch (opcode) {
 	case BPF_ADD:
-		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
-		if (ret < 0) {
-			verbose(env, "R%d tried to add from different maps, paths, or prohibited types\n", dst);
-			return ret;
-		}
 		/* We can take a fixed offset as long as it doesn't overflow
 		 * the s32 'off' field
 		 */
@@ -6165,11 +6265,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		}
 		break;
 	case BPF_SUB:
-		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
-		if (ret < 0) {
-			verbose(env, "R%d tried to sub from different maps, paths, or prohibited types\n", dst);
-			return ret;
-		}
 		if (dst_reg == off_reg) {
 			/* scalar -= pointer.  Creates an unknown scalar */
 			verbose(env, "R%d tried to subtract pointer from scalar\n",
@@ -6250,21 +6345,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	__reg_deduce_bounds(dst_reg);
 	__reg_bound_offset(dst_reg);
 
-	/* For unprivileged we require that resulting offset must be in bounds
-	 * in order to be able to sanitize access later on.
-	 */
-	if (!env->bypass_spec_v1) {
-		if (dst_reg->type == PTR_TO_MAP_VALUE &&
-		    check_map_access(env, dst, dst_reg->off, 1, false)) {
-			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
-				"prohibited for !root\n", dst);
-			return -EACCES;
-		} else if (dst_reg->type == PTR_TO_STACK &&
-			   check_stack_access_for_ptr_arithmetic(
-				   env, dst, dst_reg, dst_reg->off +
-				   dst_reg->var_off.value)) {
-			return -EACCES;
-		}
+	if (sanitize_check_bounds(env, insn, dst_reg) < 0)
+		return -EACCES;
+	if (sanitize_needed(opcode)) {
+		ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
+				       &tmp_aux, true);
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, off_reg, dst_reg);
 	}
 
 	return 0;
@@ -6858,9 +6945,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	s32 s32_min_val, s32_max_val;
 	u32 u32_min_val, u32_max_val;
 	u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
-	u32 dst = insn->dst_reg;
-	int ret;
 	bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
+	int ret;
 
 	smin_val = src_reg.smin_value;
 	smax_val = src_reg.smax_value;
@@ -6902,6 +6988,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		return 0;
 	}
 
+	if (sanitize_needed(opcode)) {
+		ret = sanitize_val_alu(env, insn);
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, NULL, NULL);
+	}
+
 	/* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops.
 	 * There are two classes of instructions: The first class we track both
 	 * alu32 and alu64 sign/unsigned bounds independently this provides the
@@ -6918,21 +7010,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	 */
 	switch (opcode) {
 	case BPF_ADD:
-		ret = sanitize_val_alu(env, insn);
-		if (ret < 0) {
-			verbose(env, "R%d tried to add from different pointers or scalars\n", dst);
-			return ret;
-		}
 		scalar32_min_max_add(dst_reg, &src_reg);
 		scalar_min_max_add(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
 		break;
 	case BPF_SUB:
-		ret = sanitize_val_alu(env, insn);
-		if (ret < 0) {
-			verbose(env, "R%d tried to sub from different pointers or scalars\n", dst);
-			return ret;
-		}
 		scalar32_min_max_sub(dst_reg, &src_reg);
 		scalar_min_max_sub(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);