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

Pull networking fixes from David Miller:

 1) Track alignment in BPF verifier so that legitimate programs won't be
    rejected on !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS architectures.

 2) Make tail calls work properly in arm64 BPF JIT, from Deniel
    Borkmann.

 3) Make the configuration and semantics Generic XDP make more sense and
    don't allow both generic XDP and a driver specific instance to be
    active at the same time. Also from Daniel.

 4) Don't crash on resume in xen-netfront, from Vitaly Kuznetsov.

 5) Fix use-after-free in VRF driver, from Gao Feng.

 6) Use netdev_alloc_skb_ip_align() to avoid unaligned IP headers in
    qca_spi driver, from Stefan Wahren.

 7) Always run cleanup routines in BPF samples when we get SIGTERM, from
    Andy Gospodarek.

 8) The mdio phy code should bring PHYs out of reset using the shared
    GPIO lines before invoking bus->reset(). From Florian Fainelli.

 9) Some USB descriptor access endian fixes in various drivers from
    Johan Hovold.

10) Handle PAUSE advertisements properly in mlx5 driver, from Gal
    Pressman.

11) Fix reversed test in mlx5e_setup_tc(), from Saeed Mahameed.

12) Cure netdev leak in AF_PACKET when using timestamping via control
    messages. From Douglas Caetano dos Santos.

13) netcp doesn't support HWTSTAMP_FILTER_ALl, reject it. From Miroslav
    Lichvar.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (52 commits)
  ldmvsw: stop the clean timer at beginning of remove
  ldmvsw: unregistering netdev before disable hardware
  net: netcp: fix check of requested timestamping filter
  ipv6: avoid dad-failures for addresses with NODAD
  qed: Fix uninitialized data in aRFS infrastructure
  mdio: mux: fix device_node_continue.cocci warnings
  net/packet: fix missing net_device reference release
  net/mlx4_core: Use min3 to select number of MSI-X vectors
  macvlan: Fix performance issues with vlan tagged packets
  net: stmmac: use correct pointer when printing normal descriptor ring
  net/mlx5: Use underlay QPN from the root name space
  net/mlx5e: IPoIB, Only support regular RQ for now
  net/mlx5e: Fix setup TC ndo
  net/mlx5e: Fix ethtool pause support and advertise reporting
  net/mlx5e: Use the correct pause values for ethtool advertising
  vmxnet3: ensure that adapter is in proper state during force_close
  sfc: revert changes to NIC revision numbers
  net: ch9200: add missing USB-descriptor endianness conversions
  net: irda: irda-usb: fix firmware name on big-endian hosts
  net: dsa: mv88e6xxx: add default case to switch
  ...

2 files changed, 113 insertions, 25 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fd2411f..265a0d8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -783,7 +783,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
 EXPORT_SYMBOL_GPL(bpf_prog_get_type);
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD kern_version
+#define	BPF_PROG_LOAD_LAST_FIELD prog_flags
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
@@ -796,6 +796,9 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_PROG_LOAD))
 		return -EINVAL;
 
+	if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT)
+		return -EINVAL;
+
 	/* copy eBPF program license from user space */
 	if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
 			      sizeof(license) - 1) < 0)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c5b56c9..39f2dcb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -241,6 +241,12 @@ static void print_verifier_state(struct bpf_verifier_state *state)
 		if (reg->max_value != BPF_REGISTER_MAX_RANGE)
 			verbose(",max_value=%llu",
 				(unsigned long long)reg->max_value);
+		if (reg->min_align)
+			verbose(",min_align=%u", reg->min_align);
+		if (reg->aux_off)
+			verbose(",aux_off=%u", reg->aux_off);
+		if (reg->aux_off_align)
+			verbose(",aux_off_align=%u", reg->aux_off_align);
 	}
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] == STACK_SPILL)
@@ -466,6 +472,9 @@ static void init_reg_state(struct bpf_reg_state *regs)
 		regs[i].imm = 0;
 		regs[i].min_value = BPF_REGISTER_MIN_RANGE;
 		regs[i].max_value = BPF_REGISTER_MAX_RANGE;
+		regs[i].min_align = 0;
+		regs[i].aux_off = 0;
+		regs[i].aux_off_align = 0;
 	}
 
 	/* frame pointer */
@@ -492,6 +501,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
 {
 	regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
 	regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+	regs[regno].min_align = 0;
 }
 
 static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs,
@@ -779,17 +789,33 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 }
 
 static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
-				   int off, int size)
+				   int off, int size, bool strict)
 {
-	if (reg->id && size != 1) {
-		verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
-		return -EACCES;
+	int ip_align;
+	int reg_off;
+
+	/* Byte size accesses are always allowed. */
+	if (!strict || size == 1)
+		return 0;
+
+	reg_off = reg->off;
+	if (reg->id) {
+		if (reg->aux_off_align % size) {
+			verbose("Packet access is only %u byte aligned, %d byte access not allowed\n",
+				reg->aux_off_align, size);
+			return -EACCES;
+		}
+		reg_off += reg->aux_off;
 	}
 
-	/* skb->data is NET_IP_ALIGN-ed */
-	if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
+	/* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking
+	 * we force this to 2 which is universally what architectures use
+	 * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+	 */
+	ip_align = strict ? 2 : NET_IP_ALIGN;
+	if ((ip_align + reg_off + off) % size != 0) {
 		verbose("misaligned packet access off %d+%d+%d size %d\n",
-			NET_IP_ALIGN, reg->off, off, size);
+			ip_align, reg_off, off, size);
 		return -EACCES;
 	}
 
@@ -797,9 +823,9 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
 }
 
 static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
-				   int size)
+				   int size, bool strict)
 {
-	if (size != 1) {
+	if (strict && size != 1) {
 		verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
 		return -EACCES;
 	}
@@ -807,16 +833,20 @@ static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
 	return 0;
 }
 
-static int check_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_ptr_alignment(struct bpf_verifier_env *env,
+			       const struct bpf_reg_state *reg,
 			       int off, int size)
 {
+	bool strict = env->strict_alignment;
+
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+		strict = true;
+
 	switch (reg->type) {
 	case PTR_TO_PACKET:
-		return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
-		       check_pkt_ptr_alignment(reg, off, size);
+		return check_pkt_ptr_alignment(reg, off, size, strict);
 	case PTR_TO_MAP_VALUE_ADJ:
-		return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
-		       check_val_ptr_alignment(reg, size);
+		return check_val_ptr_alignment(reg, size, strict);
 	default:
 		if (off % size != 0) {
 			verbose("misaligned access off %d size %d\n",
@@ -849,7 +879,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 	if (size < 0)
 		return size;
 
-	err = check_ptr_alignment(reg, off, size);
+	err = check_ptr_alignment(env, reg, off, size);
 	if (err)
 		return err;
 
@@ -883,6 +913,8 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 							 value_regno);
 			/* note that reg.[id|off|range] == 0 */
 			state->regs[value_regno].type = reg_type;
+			state->regs[value_regno].aux_off = 0;
+			state->regs[value_regno].aux_off_align = 0;
 		}
 
 	} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
@@ -1455,6 +1487,8 @@ add_imm:
 		 */
 		dst_reg->off += imm;
 	} else {
+		bool had_id;
+
 		if (src_reg->type == PTR_TO_PACKET) {
 			/* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */
 			tmp_reg = *dst_reg;  /* save r7 state */
@@ -1488,14 +1522,23 @@ add_imm:
 				src_reg->imm);
 			return -EACCES;
 		}
+
+		had_id = (dst_reg->id != 0);
+
 		/* dst_reg stays as pkt_ptr type and since some positive
 		 * integer value was added to the pointer, increment its 'id'
 		 */
 		dst_reg->id = ++env->id_gen;
 
-		/* something was added to pkt_ptr, set range and off to zero */
+		/* something was added to pkt_ptr, set range to zero */
+		dst_reg->aux_off += dst_reg->off;
 		dst_reg->off = 0;
 		dst_reg->range = 0;
+		if (had_id)
+			dst_reg->aux_off_align = min(dst_reg->aux_off_align,
+						     src_reg->min_align);
+		else
+			dst_reg->aux_off_align = src_reg->min_align;
 	}
 	return 0;
 }
@@ -1669,6 +1712,13 @@ static void check_reg_overflow(struct bpf_reg_state *reg)
 		reg->min_value = BPF_REGISTER_MIN_RANGE;
 }
 
+static u32 calc_align(u32 imm)
+{
+	if (!imm)
+		return 1U << 31;
+	return imm - ((imm - 1) & imm);
+}
+
 static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				    struct bpf_insn *insn)
 {
@@ -1676,8 +1726,10 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	s64 min_val = BPF_REGISTER_MIN_RANGE;
 	u64 max_val = BPF_REGISTER_MAX_RANGE;
 	u8 opcode = BPF_OP(insn->code);
+	u32 dst_align, src_align;
 
 	dst_reg = &regs[insn->dst_reg];
+	src_align = 0;
 	if (BPF_SRC(insn->code) == BPF_X) {
 		check_reg_overflow(&regs[insn->src_reg]);
 		min_val = regs[insn->src_reg].min_value;
@@ -1693,12 +1745,18 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		    regs[insn->src_reg].type != UNKNOWN_VALUE) {
 			min_val = BPF_REGISTER_MIN_RANGE;
 			max_val = BPF_REGISTER_MAX_RANGE;
+			src_align = 0;
+		} else {
+			src_align = regs[insn->src_reg].min_align;
 		}
 	} else if (insn->imm < BPF_REGISTER_MAX_RANGE &&
 		   (s64)insn->imm > BPF_REGISTER_MIN_RANGE) {
 		min_val = max_val = insn->imm;
+		src_align = calc_align(insn->imm);
 	}
 
+	dst_align = dst_reg->min_align;
+
 	/* We don't know anything about what was done to this register, mark it
 	 * as unknown.
 	 */
@@ -1723,18 +1781,21 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 			dst_reg->min_value += min_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value += max_val;
+		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_SUB:
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
 			dst_reg->min_value -= min_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value -= max_val;
+		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_MUL:
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
 			dst_reg->min_value *= min_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value *= max_val;
+		dst_reg->min_align = max(src_align, dst_align);
 		break;
 	case BPF_AND:
 		/* Disallow AND'ing of negative numbers, ain't nobody got time
@@ -1746,17 +1807,23 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		else
 			dst_reg->min_value = 0;
 		dst_reg->max_value = max_val;
+		dst_reg->min_align = max(src_align, dst_align);
 		break;
 	case BPF_LSH:
 		/* Gotta have special overflow logic here, if we're shifting
 		 * more than MAX_RANGE then just assume we have an invalid
 		 * range.
 		 */
-		if (min_val > ilog2(BPF_REGISTER_MAX_RANGE))
+		if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) {
 			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-		else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
-			dst_reg->min_value <<= min_val;
-
+			dst_reg->min_align = 1;
+		} else {
+			if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+				dst_reg->min_value <<= min_val;
+			if (!dst_reg->min_align)
+				dst_reg->min_align = 1;
+			dst_reg->min_align <<= min_val;
+		}
 		if (max_val > ilog2(BPF_REGISTER_MAX_RANGE))
 			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
 		else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
@@ -1766,11 +1833,19 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		/* RSH by a negative number is undefined, and the BPF_RSH is an
 		 * unsigned shift, so make the appropriate casts.
 		 */
-		if (min_val < 0 || dst_reg->min_value < 0)
+		if (min_val < 0 || dst_reg->min_value < 0) {
 			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-		else
+		} else {
 			dst_reg->min_value =
 				(u64)(dst_reg->min_value) >> min_val;
+		}
+		if (min_val < 0) {
+			dst_reg->min_align = 1;
+		} else {
+			dst_reg->min_align >>= (u64) min_val;
+			if (!dst_reg->min_align)
+				dst_reg->min_align = 1;
+		}
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value >>= max_val;
 		break;
@@ -1872,6 +1947,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			regs[insn->dst_reg].imm = insn->imm;
 			regs[insn->dst_reg].max_value = insn->imm;
 			regs[insn->dst_reg].min_value = insn->imm;
+			regs[insn->dst_reg].min_align = calc_align(insn->imm);
 		}
 
 	} else if (opcode > BPF_END) {
@@ -2856,8 +2932,12 @@ static int do_check(struct bpf_verifier_env *env)
 			goto process_bpf_exit;
 		}
 
-		if (log_level && do_print_state) {
-			verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
+		if (log_level > 1 || (log_level && do_print_state)) {
+			if (log_level > 1)
+				verbose("%d:", insn_idx);
+			else
+				verbose("\nfrom %d to %d:",
+					prev_insn_idx, insn_idx);
 			print_verifier_state(&env->cur_state);
 			do_print_state = false;
 		}
@@ -3494,6 +3574,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	} else {
 		log_level = 0;
 	}
+	if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT)
+		env->strict_alignment = true;
+	else
+		env->strict_alignment = false;
 
 	ret = replace_map_fd_with_map_ptr(env);
 	if (ret < 0)
@@ -3599,6 +3683,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
 	mutex_lock(&bpf_verifier_lock);
 
 	log_level = 0;
+	env->strict_alignment = false;
 
 	env->explored_states = kcalloc(env->prog->len,
 				       sizeof(struct bpf_verifier_state_list *),