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

Pull networking updates from David Miller:
 "Highlights:

   1) Support SPI based w5100 devices, from Akinobu Mita.

   2) Partial Segmentation Offload, from Alexander Duyck.

   3) Add GMAC4 support to stmmac driver, from Alexandre TORGUE.

   4) Allow cls_flower stats offload, from Amir Vadai.

   5) Implement bpf blinding, from Daniel Borkmann.

   6) Optimize _ASYNC_ bit twiddling on sockets, unless the socket is
      actually using FASYNC these atomics are superfluous.  From Eric
      Dumazet.

   7) Run TCP more preemptibly, also from Eric Dumazet.

   8) Support LED blinking, EEPROM dumps, and rxvlan offloading in mlx5e
      driver, from Gal Pressman.

   9) Allow creating ppp devices via rtnetlink, from Guillaume Nault.

  10) Improve BPF usage documentation, from Jesper Dangaard Brouer.

  11) Support tunneling offloads in qed, from Manish Chopra.

  12) aRFS offloading in mlx5e, from Maor Gottlieb.

  13) Add RFS and RPS support to SCTP protocol, from Marcelo Ricardo
      Leitner.

  14) Add MSG_EOR support to TCP, this allows controlling packet
      coalescing on application record boundaries for more accurate
      socket timestamp sampling.  From Martin KaFai Lau.

  15) Fix alignment of 64-bit netlink attributes across the board, from
      Nicolas Dichtel.

  16) Per-vlan stats in bridging, from Nikolay Aleksandrov.

  17) Several conversions of drivers to ethtool ksettings, from Philippe
      Reynes.

  18) Checksum neutral ILA in ipv6, from Tom Herbert.

  19) Factorize all of the various marvell dsa drivers into one, from
      Vivien Didelot

  20) Add VF support to qed driver, from Yuval Mintz"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1649 commits)
  Revert "phy dp83867: Fix compilation with CONFIG_OF_MDIO=m"
  Revert "phy dp83867: Make rgmii parameters optional"
  r8169: default to 64-bit DMA on recent PCIe chips
  phy dp83867: Make rgmii parameters optional
  phy dp83867: Fix compilation with CONFIG_OF_MDIO=m
  bpf: arm64: remove callee-save registers use for tmp registers
  asix: Fix offset calculation in asix_rx_fixup() causing slow transmissions
  switchdev: pass pointer to fib_info instead of copy
  net_sched: close another race condition in tcf_mirred_release()
  tipc: fix nametable publication field in nl compat
  drivers: net: Don't print unpopulated net_device name
  qed: add support for dcbx.
  ravb: Add missing free_irq() calls to ravb_close()
  qed: Remove a stray tab
  net: ethernet: fec-mpc52xx: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fec-mpc52xx: use phydev from struct net_device
  bpf, doc: fix typo on bpf_asm descriptions
  stmmac: hardware TX COE doesn't work when force_thresh_dma_mode is set
  net: ethernet: fs-enet: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fs-enet: use phydev from struct net_device
  ...

13 files changed, 1122 insertions, 231 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index be0abf669ced..f1e8a0def99b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -129,14 +129,83 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 
 	return fp;
 }
-EXPORT_SYMBOL_GPL(bpf_prog_realloc);
 
 void __bpf_prog_free(struct bpf_prog *fp)
 {
 	kfree(fp->aux);
 	vfree(fp);
 }
-EXPORT_SYMBOL_GPL(__bpf_prog_free);
+
+static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn)
+{
+	return BPF_CLASS(insn->code) == BPF_JMP  &&
+	       /* Call and Exit are both special jumps with no
+		* target inside the BPF instruction image.
+		*/
+	       BPF_OP(insn->code) != BPF_CALL &&
+	       BPF_OP(insn->code) != BPF_EXIT;
+}
+
+static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
+{
+	struct bpf_insn *insn = prog->insnsi;
+	u32 i, insn_cnt = prog->len;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (!bpf_is_jmp_and_has_target(insn))
+			continue;
+
+		/* Adjust offset of jmps if we cross boundaries. */
+		if (i < pos && i + insn->off + 1 > pos)
+			insn->off += delta;
+		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
+			insn->off -= delta;
+	}
+}
+
+struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
+				       const struct bpf_insn *patch, u32 len)
+{
+	u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
+	struct bpf_prog *prog_adj;
+
+	/* Since our patchlet doesn't expand the image, we're done. */
+	if (insn_delta == 0) {
+		memcpy(prog->insnsi + off, patch, sizeof(*patch));
+		return prog;
+	}
+
+	insn_adj_cnt = prog->len + insn_delta;
+
+	/* Several new instructions need to be inserted. Make room
+	 * for them. Likely, there's no need for a new allocation as
+	 * last page could have large enough tailroom.
+	 */
+	prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
+				    GFP_USER);
+	if (!prog_adj)
+		return NULL;
+
+	prog_adj->len = insn_adj_cnt;
+
+	/* Patching happens in 3 steps:
+	 *
+	 * 1) Move over tail of insnsi from next instruction onwards,
+	 *    so we can patch the single target insn with one or more
+	 *    new ones (patching is always from 1 to n insns, n > 0).
+	 * 2) Inject new instructions at the target location.
+	 * 3) Adjust branch offsets if necessary.
+	 */
+	insn_rest = insn_adj_cnt - off - len;
+
+	memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1,
+		sizeof(*patch) * insn_rest);
+	memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
+
+	bpf_adj_branches(prog_adj, off, insn_delta);
+
+	return prog_adj;
+}
 
 #ifdef CONFIG_BPF_JIT
 struct bpf_binary_header *
@@ -174,6 +243,209 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr)
 {
 	module_memfree(hdr);
 }
+
+int bpf_jit_harden __read_mostly;
+
+static int bpf_jit_blind_insn(const struct bpf_insn *from,
+			      const struct bpf_insn *aux,
+			      struct bpf_insn *to_buff)
+{
+	struct bpf_insn *to = to_buff;
+	u32 imm_rnd = prandom_u32();
+	s16 off;
+
+	BUILD_BUG_ON(BPF_REG_AX  + 1 != MAX_BPF_JIT_REG);
+	BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG);
+
+	if (from->imm == 0 &&
+	    (from->code == (BPF_ALU   | BPF_MOV | BPF_K) ||
+	     from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) {
+		*to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg);
+		goto out;
+	}
+
+	switch (from->code) {
+	case BPF_ALU | BPF_ADD | BPF_K:
+	case BPF_ALU | BPF_SUB | BPF_K:
+	case BPF_ALU | BPF_AND | BPF_K:
+	case BPF_ALU | BPF_OR  | BPF_K:
+	case BPF_ALU | BPF_XOR | BPF_K:
+	case BPF_ALU | BPF_MUL | BPF_K:
+	case BPF_ALU | BPF_MOV | BPF_K:
+	case BPF_ALU | BPF_DIV | BPF_K:
+	case BPF_ALU | BPF_MOD | BPF_K:
+		*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+		*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
+		break;
+
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+	case BPF_ALU64 | BPF_AND | BPF_K:
+	case BPF_ALU64 | BPF_OR  | BPF_K:
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+	case BPF_ALU64 | BPF_DIV | BPF_K:
+	case BPF_ALU64 | BPF_MOD | BPF_K:
+		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
+		break;
+
+	case BPF_JMP | BPF_JEQ  | BPF_K:
+	case BPF_JMP | BPF_JNE  | BPF_K:
+	case BPF_JMP | BPF_JGT  | BPF_K:
+	case BPF_JMP | BPF_JGE  | BPF_K:
+	case BPF_JMP | BPF_JSGT | BPF_K:
+	case BPF_JMP | BPF_JSGE | BPF_K:
+	case BPF_JMP | BPF_JSET | BPF_K:
+		/* Accommodate for extra offset in case of a backjump. */
+		off = from->off;
+		if (off < 0)
+			off -= 2;
+		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
+		break;
+
+	case BPF_LD | BPF_ABS | BPF_W:
+	case BPF_LD | BPF_ABS | BPF_H:
+	case BPF_LD | BPF_ABS | BPF_B:
+		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
+		break;
+
+	case BPF_LD | BPF_IND | BPF_W:
+	case BPF_LD | BPF_IND | BPF_H:
+	case BPF_LD | BPF_IND | BPF_B:
+		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg);
+		*to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
+		break;
+
+	case BPF_LD | BPF_IMM | BPF_DW:
+		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
+		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32);
+		*to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX);
+		break;
+	case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */
+		*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm);
+		*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_ALU64_REG(BPF_OR,  aux[0].dst_reg, BPF_REG_AX);
+		break;
+
+	case BPF_ST | BPF_MEM | BPF_DW:
+	case BPF_ST | BPF_MEM | BPF_W:
+	case BPF_ST | BPF_MEM | BPF_H:
+	case BPF_ST | BPF_MEM | BPF_B:
+		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off);
+		break;
+	}
+out:
+	return to - to_buff;
+}
+
+static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,
+					      gfp_t gfp_extra_flags)
+{
+	gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
+			  gfp_extra_flags;
+	struct bpf_prog *fp;
+
+	fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
+	if (fp != NULL) {
+		kmemcheck_annotate_bitfield(fp, meta);
+
+		/* aux->prog still points to the fp_other one, so
+		 * when promoting the clone to the real program,
+		 * this still needs to be adapted.
+		 */
+		memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE);
+	}
+
+	return fp;
+}
+
+static void bpf_prog_clone_free(struct bpf_prog *fp)
+{
+	/* aux was stolen by the other clone, so we cannot free
+	 * it from this path! It will be freed eventually by the
+	 * other program on release.
+	 *
+	 * At this point, we don't need a deferred release since
+	 * clone is guaranteed to not be locked.
+	 */
+	fp->aux = NULL;
+	__bpf_prog_free(fp);
+}
+
+void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other)
+{
+	/* We have to repoint aux->prog to self, as we don't
+	 * know whether fp here is the clone or the original.
+	 */
+	fp->aux->prog = fp;
+	bpf_prog_clone_free(fp_other);
+}
+
+struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
+{
+	struct bpf_insn insn_buff[16], aux[2];
+	struct bpf_prog *clone, *tmp;
+	int insn_delta, insn_cnt;
+	struct bpf_insn *insn;
+	int i, rewritten;
+
+	if (!bpf_jit_blinding_enabled())
+		return prog;
+
+	clone = bpf_prog_clone_create(prog, GFP_USER);
+	if (!clone)
+		return ERR_PTR(-ENOMEM);
+
+	insn_cnt = clone->len;
+	insn = clone->insnsi;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		/* We temporarily need to hold the original ld64 insn
+		 * so that we can still access the first part in the
+		 * second blinding run.
+		 */
+		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) &&
+		    insn[1].code == 0)
+			memcpy(aux, insn, sizeof(aux));
+
+		rewritten = bpf_jit_blind_insn(insn, aux, insn_buff);
+		if (!rewritten)
+			continue;
+
+		tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
+		if (!tmp) {
+			/* Patching may have repointed aux->prog during
+			 * realloc from the original one, so we need to
+			 * fix it up here on error.
+			 */
+			bpf_jit_prog_release_other(prog, clone);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		clone = tmp;
+		insn_delta = rewritten - 1;
+
+		/* Walk new program and skip insns we just inserted. */
+		insn = clone->insnsi + i + insn_delta;
+		insn_cnt += insn_delta;
+		i        += insn_delta;
+	}
+
+	return clone;
+}
 #endif /* CONFIG_BPF_JIT */
 
 /* Base function for offset calculation. Needs to go into .text section,
@@ -692,15 +964,22 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 /**
  *	bpf_prog_select_runtime - select exec runtime for BPF program
  *	@fp: bpf_prog populated with internal BPF program
+ *	@err: pointer to error variable
  *
  * Try to JIT eBPF program, if JIT is not available, use interpreter.
  * The BPF program will be executed via BPF_PROG_RUN() macro.
  */
-int bpf_prog_select_runtime(struct bpf_prog *fp)
+struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 {
 	fp->bpf_func = (void *) __bpf_prog_run;
 
-	bpf_int_jit_compile(fp);
+	/* eBPF JITs can rewrite the program in case constant
+	 * blinding is active. However, in case of error during
+	 * blinding, bpf_int_jit_compile() must always return a
+	 * valid program, which in this case would simply not
+	 * be JITed, but falls back to the interpreter.
+	 */
+	fp = bpf_int_jit_compile(fp);
 	bpf_prog_lock_ro(fp);
 
 	/* The tail call compatibility check can only be done at
@@ -708,7 +987,9 @@ int bpf_prog_select_runtime(struct bpf_prog *fp)
 	 * with JITed or non JITed program concatenations and not
 	 * all eBPF JITs might immediately support all features.
 	 */
-	return bpf_check_tail_call(fp);
+	*err = bpf_check_tail_call(fp);
+
+	return fp;
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
@@ -764,14 +1045,21 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
 const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
 const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
+
 const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
 const struct bpf_func_proto bpf_get_current_comm_proto __weak;
+
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
 	return NULL;
 }
 
+const struct bpf_func_proto * __weak bpf_get_event_output_proto(void)
+{
+	return NULL;
+}
+
 /* Always built-in helper functions. */
 const struct bpf_func_proto bpf_tail_call_proto = {
 	.func		= NULL,
@@ -783,8 +1071,14 @@ const struct bpf_func_proto bpf_tail_call_proto = {
 };
 
 /* For classic BPF JITs that don't implement bpf_int_jit_compile(). */
-void __weak bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog)
+{
+	return prog;
+}
+
+bool __weak bpf_helper_changes_skb_data(void *func)
 {
+	return false;
 }
 
 /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 50da680c479f..ad7a0573f71b 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -163,17 +163,26 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5)
 	struct task_struct *task = current;
 	char *buf = (char *) (long) r1;
 
-	if (!task)
-		return -EINVAL;
+	if (unlikely(!task))
+		goto err_clear;
 
-	strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
+	strncpy(buf, task->comm, size);
+
+	/* Verifier guarantees that size > 0. For task->comm exceeding
+	 * size, guarantee that buf is %NUL-terminated. Unconditionally
+	 * done here to save the size test.
+	 */
+	buf[size - 1] = 0;
 	return 0;
+err_clear:
+	memset(buf, 0, size);
+	return -EINVAL;
 }
 
 const struct bpf_func_proto bpf_get_current_comm_proto = {
 	.func		= bpf_get_current_comm,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_STACK,
+	.arg1_type	= ARG_PTR_TO_RAW_STACK,
 	.arg2_type	= ARG_CONST_STACK_SIZE,
 };
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index f5a19548be12..c8ee35287bfe 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -116,7 +116,7 @@ free_smap:
 	return ERR_PTR(err);
 }
 
-static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
+u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
 {
 	struct pt_regs *regs = (struct pt_regs *) (long) r1;
 	struct bpf_map *map = (struct bpf_map *) (long) r2;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cf5e9f7ad13a..46ecce4b79ed 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -762,7 +762,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 	fixup_bpf_calls(prog);
 
 	/* eBPF program is ready to be JITed */
-	err = bpf_prog_select_runtime(prog);
+	prog = bpf_prog_select_runtime(prog, &err);
 	if (err < 0)
 		goto free_used_maps;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c5c17a62f509..a08d66215245 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1,4 +1,5 @@
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 Facebook
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -136,13 +137,32 @@ enum bpf_reg_type {
 	FRAME_PTR,		 /* reg == frame_pointer */
 	PTR_TO_STACK,		 /* reg == frame_pointer + imm */
 	CONST_IMM,		 /* constant integer value */
+
+	/* PTR_TO_PACKET represents:
+	 * skb->data
+	 * skb->data + imm
+	 * skb->data + (u16) var
+	 * skb->data + (u16) var + imm
+	 * if (range > 0) then [ptr, ptr + range - off) is safe to access
+	 * if (id > 0) means that some 'var' was added
+	 * if (off > 0) menas that 'imm' was added
+	 */
+	PTR_TO_PACKET,
+	PTR_TO_PACKET_END,	 /* skb->data + headlen */
 };
 
 struct reg_state {
 	enum bpf_reg_type type;
 	union {
-		/* valid when type == CONST_IMM | PTR_TO_STACK */
-		int imm;
+		/* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */
+		s64 imm;
+
+		/* valid when type == PTR_TO_PACKET* */
+		struct {
+			u32 id;
+			u16 off;
+			u16 range;
+		};
 
 		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
 		 *   PTR_TO_MAP_VALUE_OR_NULL
@@ -202,6 +222,16 @@ struct verifier_env {
 	bool allow_ptr_leaks;
 };
 
+#define BPF_COMPLEXITY_LIMIT_INSNS	65536
+#define BPF_COMPLEXITY_LIMIT_STACK	1024
+
+struct bpf_call_arg_meta {
+	struct bpf_map *map_ptr;
+	bool raw_mode;
+	int regno;
+	int access_size;
+};
+
 /* verbose verifier prints what it's seeing
  * bpf_check() is called under lock, so no race to access these global vars
  */
@@ -237,30 +267,39 @@ static const char * const reg_type_str[] = {
 	[FRAME_PTR]		= "fp",
 	[PTR_TO_STACK]		= "fp",
 	[CONST_IMM]		= "imm",
+	[PTR_TO_PACKET]		= "pkt",
+	[PTR_TO_PACKET_END]	= "pkt_end",
 };
 
-static void print_verifier_state(struct verifier_env *env)
+static void print_verifier_state(struct verifier_state *state)
 {
+	struct reg_state *reg;
 	enum bpf_reg_type t;
 	int i;
 
 	for (i = 0; i < MAX_BPF_REG; i++) {
-		t = env->cur_state.regs[i].type;
+		reg = &state->regs[i];
+		t = reg->type;
 		if (t == NOT_INIT)
 			continue;
 		verbose(" R%d=%s", i, reg_type_str[t]);
 		if (t == CONST_IMM || t == PTR_TO_STACK)
-			verbose("%d", env->cur_state.regs[i].imm);
+			verbose("%lld", reg->imm);
+		else if (t == PTR_TO_PACKET)
+			verbose("(id=%d,off=%d,r=%d)",
+				reg->id, reg->off, reg->range);
+		else if (t == UNKNOWN_VALUE && reg->imm)
+			verbose("%lld", reg->imm);
 		else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
 			 t == PTR_TO_MAP_VALUE_OR_NULL)
 			verbose("(ks=%d,vs=%d)",
-				env->cur_state.regs[i].map_ptr->key_size,
-				env->cur_state.regs[i].map_ptr->value_size);
+				reg->map_ptr->key_size,
+				reg->map_ptr->value_size);
 	}
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
-		if (env->cur_state.stack_slot_type[i] == STACK_SPILL)
+		if (state->stack_slot_type[i] == STACK_SPILL)
 			verbose(" fp%d=%s", -MAX_BPF_STACK + i,
-				reg_type_str[env->cur_state.spilled_regs[i / BPF_REG_SIZE].type]);
+				reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]);
 	}
 	verbose("\n");
 }
@@ -444,7 +483,7 @@ static struct verifier_state *push_stack(struct verifier_env *env, int insn_idx,
 	elem->next = env->head;
 	env->head = elem;
 	env->stack_size++;
-	if (env->stack_size > 1024) {
+	if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
 		verbose("BPF program is too complex\n");
 		goto err;
 	}
@@ -467,7 +506,6 @@ static void init_reg_state(struct reg_state *regs)
 	for (i = 0; i < MAX_BPF_REG; i++) {
 		regs[i].type = NOT_INIT;
 		regs[i].imm = 0;
-		regs[i].map_ptr = NULL;
 	}
 
 	/* frame pointer */
@@ -482,7 +520,6 @@ static void mark_reg_unknown_value(struct reg_state *regs, u32 regno)
 	BUG_ON(regno >= MAX_BPF_REG);
 	regs[regno].type = UNKNOWN_VALUE;
 	regs[regno].imm = 0;
-	regs[regno].map_ptr = NULL;
 }
 
 enum reg_arg_type {
@@ -538,6 +575,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_MAP_VALUE_OR_NULL:
 	case PTR_TO_STACK:
 	case PTR_TO_CTX:
+	case PTR_TO_PACKET:
+	case PTR_TO_PACKET_END:
 	case FRAME_PTR:
 	case CONST_PTR_TO_MAP:
 		return true;
@@ -637,13 +676,38 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off,
 	return 0;
 }
 
+#define MAX_PACKET_OFF 0xffff
+
+static int check_packet_access(struct verifier_env *env, u32 regno, int off,
+			       int size)
+{
+	struct reg_state *regs = env->cur_state.regs;
+	struct reg_state *reg = &regs[regno];
+	int linear_size = (int) reg->range - (int) reg->off;
+
+	if (linear_size < 0 || linear_size >= MAX_PACKET_OFF) {
+		verbose("verifier bug\n");
+		return -EFAULT;
+	}
+	if (off < 0 || off + size > linear_size) {
+		verbose("invalid access to packet, off=%d size=%d, allowed=%d\n",
+			off, size, linear_size);
+		return -EACCES;
+	}
+	return 0;
+}
+
 /* check access to 'struct bpf_context' fields */
 static int check_ctx_access(struct verifier_env *env, int off, int size,
 			    enum bpf_access_type t)
 {
 	if (env->prog->aux->ops->is_valid_access &&
-	    env->prog->aux->ops->is_valid_access(off, size, t))
+	    env->prog->aux->ops->is_valid_access(off, size, t)) {
+		/* remember the offset of last byte accessed in ctx */
+		if (env->prog->aux->max_ctx_offset < off + size)
+			env->prog->aux->max_ctx_offset = off + size;
 		return 0;
+	}
 
 	verbose("invalid bpf_context access off=%d size=%d\n", off, size);
 	return -EACCES;
@@ -663,6 +727,45 @@ static bool is_pointer_value(struct verifier_env *env, int regno)
 	}
 }
 
+static int check_ptr_alignment(struct verifier_env *env, struct reg_state *reg,
+			       int off, int size)
+{
+	if (reg->type != PTR_TO_PACKET) {
+		if (off % size != 0) {
+			verbose("misaligned access off %d size %d\n", off, size);
+			return -EACCES;
+		} else {
+			return 0;
+		}
+	}
+
+	switch (env->prog->type) {
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+		break;
+	default:
+		verbose("verifier is misconfigured\n");
+		return -EACCES;
+	}
+
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+		/* misaligned access to packet is ok on x86,arm,arm64 */
+		return 0;
+
+	if (reg->id && size != 1) {
+		verbose("Unknown packet alignment. Only byte-sized access allowed\n");
+		return -EACCES;
+	}
+
+	/* skb->data is NET_IP_ALIGN-ed */
+	if ((NET_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);
+		return -EACCES;
+	}
+	return 0;
+}
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -674,21 +777,21 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 			    int value_regno)
 {
 	struct verifier_state *state = &env->cur_state;
+	struct reg_state *reg = &state->regs[regno];
 	int size, err = 0;
 
-	if (state->regs[regno].type == PTR_TO_STACK)
-		off += state->regs[regno].imm;
+	if (reg->type == PTR_TO_STACK)
+		off += reg->imm;
 
 	size = bpf_size_to_bytes(bpf_size);
 	if (size < 0)
 		return size;
 
-	if (off % size != 0) {
-		verbose("misaligned access off %d size %d\n", off, size);
-		return -EACCES;
-	}
+	err = check_ptr_alignment(env, reg, off, size);
+	if (err)
+		return err;
 
-	if (state->regs[regno].type == PTR_TO_MAP_VALUE) {
+	if (reg->type == PTR_TO_MAP_VALUE) {
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
 			verbose("R%d leaks addr into map\n", value_regno);
@@ -698,18 +801,25 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown_value(state->regs, value_regno);
 
-	} else if (state->regs[regno].type == PTR_TO_CTX) {
+	} else if (reg->type == PTR_TO_CTX) {
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
 			verbose("R%d leaks addr into ctx\n", value_regno);
 			return -EACCES;
 		}
 		err = check_ctx_access(env, off, size, t);
-		if (!err && t == BPF_READ && value_regno >= 0)
+		if (!err && t == BPF_READ && value_regno >= 0) {
 			mark_reg_unknown_value(state->regs, value_regno);
+			if (off == offsetof(struct __sk_buff, data) &&
+			    env->allow_ptr_leaks)
+				/* note that reg.[id|off|range] == 0 */
+				state->regs[value_regno].type = PTR_TO_PACKET;
+			else if (off == offsetof(struct __sk_buff, data_end) &&
+				 env->allow_ptr_leaks)
+				state->regs[value_regno].type = PTR_TO_PACKET_END;
+		}
 
-	} else if (state->regs[regno].type == FRAME_PTR ||
-		   state->regs[regno].type == PTR_TO_STACK) {
+	} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
 		if (off >= 0 || off < -MAX_BPF_STACK) {
 			verbose("invalid stack off=%d size=%d\n", off, size);
 			return -EACCES;
@@ -725,11 +835,28 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 		} else {
 			err = check_stack_read(state, off, size, value_regno);
 		}
+	} else if (state->regs[regno].type == PTR_TO_PACKET) {
+		if (t == BPF_WRITE) {
+			verbose("cannot write into packet\n");
+			return -EACCES;
+		}
+		err = check_packet_access(env, regno, off, size);
+		if (!err && t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown_value(state->regs, value_regno);
 	} else {
 		verbose("R%d invalid mem access '%s'\n",
-			regno, reg_type_str[state->regs[regno].type]);
+			regno, reg_type_str[reg->type]);
 		return -EACCES;
 	}
+
+	if (!err && size <= 2 && value_regno >= 0 && env->allow_ptr_leaks &&
+	    state->regs[value_regno].type == UNKNOWN_VALUE) {
+		/* 1 or 2 byte load zero-extends, determine the number of
+		 * zero upper bits. Not doing it fo 4 byte load, since
+		 * such values cannot be added to ptr_to_packet anyway.
+		 */
+		state->regs[value_regno].imm = 64 - size * 8;
+	}
 	return err;
 }
 
@@ -770,7 +897,8 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
  * and all elements of stack are initialized
  */
 static int check_stack_boundary(struct verifier_env *env, int regno,
-				int access_size, bool zero_size_allowed)
+				int access_size, bool zero_size_allowed,
+				struct bpf_call_arg_meta *meta)
 {
 	struct verifier_state *state = &env->cur_state;
 	struct reg_state *regs = state->regs;
@@ -796,6 +924,12 @@ static int check_stack_boundary(struct verifier_env *env, int regno,
 		return -EACCES;
 	}
 
+	if (meta && meta->raw_mode) {
+		meta->access_size = access_size;
+		meta->regno = regno;
+		return 0;
+	}
+
 	for (i = 0; i < access_size; i++) {
 		if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) {
 			verbose("invalid indirect read from stack off %d+%d size %d\n",
@@ -807,7 +941,8 @@ static int check_stack_boundary(struct verifier_env *env, int regno,
 }
 
 static int check_func_arg(struct verifier_env *env, u32 regno,
-			  enum bpf_arg_type arg_type, struct bpf_map **mapp)
+			  enum bpf_arg_type arg_type,
+			  struct bpf_call_arg_meta *meta)
 {
 	struct reg_state *reg = env->cur_state.regs + regno;
 	enum bpf_reg_type expected_type;
@@ -839,7 +974,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 		expected_type = CONST_PTR_TO_MAP;
 	} else if (arg_type == ARG_PTR_TO_CTX) {
 		expected_type = PTR_TO_CTX;
-	} else if (arg_type == ARG_PTR_TO_STACK) {
+	} else if (arg_type == ARG_PTR_TO_STACK ||
+		   arg_type == ARG_PTR_TO_RAW_STACK) {
 		expected_type = PTR_TO_STACK;
 		/* One exception here. In case function allows for NULL to be
 		 * passed in as argument, it's a CONST_IMM type. Final test
@@ -847,6 +983,7 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 		 */
 		if (reg->type == CONST_IMM && reg->imm == 0)
 			expected_type = CONST_IMM;
+		meta->raw_mode = arg_type == ARG_PTR_TO_RAW_STACK;
 	} else {
 		verbose("unsupported arg_type %d\n", arg_type);
 		return -EFAULT;
@@ -860,14 +997,13 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 
 	if (arg_type == ARG_CONST_MAP_PTR) {
 		/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
-		*mapp = reg->map_ptr;
-
+		meta->map_ptr = reg->map_ptr;
 	} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
 		/* bpf_map_xxx(..., map_ptr, ..., key) call:
 		 * check that [key, key + map->key_size) are within
 		 * stack limits and initialized
 		 */
-		if (!*mapp) {
+		if (!meta->map_ptr) {
 			/* in function declaration map_ptr must come before
 			 * map_key, so that it's verified and known before
 			 * we have to check map_key here. Otherwise it means
@@ -876,19 +1012,20 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 			verbose("invalid map_ptr to access map->key\n");
 			return -EACCES;
 		}
-		err = check_stack_boundary(env, regno, (*mapp)->key_size,
-					   false);
+		err = check_stack_boundary(env, regno, meta->map_ptr->key_size,
+					   false, NULL);
 	} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
 		/* bpf_map_xxx(..., map_ptr, ..., value) call:
 		 * check [value, value + map->value_size) validity
 		 */
-		if (!*mapp) {
+		if (!meta->map_ptr) {
 			/* kernel subsystem misconfigured verifier */
 			verbose("invalid map_ptr to access map->value\n");
 			return -EACCES;
 		}
-		err = check_stack_boundary(env, regno, (*mapp)->value_size,
-					   false);
+		err = check_stack_boundary(env, regno,
+					   meta->map_ptr->value_size,
+					   false, NULL);
 	} else if (arg_type == ARG_CONST_STACK_SIZE ||
 		   arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) {
 		bool zero_size_allowed = (arg_type == ARG_CONST_STACK_SIZE_OR_ZERO);
@@ -903,7 +1040,7 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 			return -EACCES;
 		}
 		err = check_stack_boundary(env, regno - 1, reg->imm,
-					   zero_size_allowed);
+					   zero_size_allowed, meta);
 	}
 
 	return err;
@@ -959,13 +1096,55 @@ error:
 	return -EINVAL;
 }
 
+static int check_raw_mode(const struct bpf_func_proto *fn)
+{
+	int count = 0;
+
+	if (fn->arg1_type == ARG_PTR_TO_RAW_STACK)
+		count++;
+	if (fn->arg2_type == ARG_PTR_TO_RAW_STACK)
+		count++;
+	if (fn->arg3_type == ARG_PTR_TO_RAW_STACK)
+		count++;
+	if (fn->arg4_type == ARG_PTR_TO_RAW_STACK)
+		count++;
+	if (fn->arg5_type == ARG_PTR_TO_RAW_STACK)
+		count++;
+
+	return count > 1 ? -EINVAL : 0;
+}
+
+static void clear_all_pkt_pointers(struct verifier_env *env)
+{
+	struct verifier_state *state = &env->cur_state;
+	struct reg_state *regs = state->regs, *reg;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++)
+		if (regs[i].type == PTR_TO_PACKET ||
+		    regs[i].type == PTR_TO_PACKET_END)
+			mark_reg_unknown_value(regs, i);
+
+	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
+		if (state->stack_slot_type[i] != STACK_SPILL)
+			continue;
+		reg = &state->spilled_regs[i / BPF_REG_SIZE];
+		if (reg->type != PTR_TO_PACKET &&
+		    reg->type != PTR_TO_PACKET_END)
+			continue;
+		reg->type = UNKNOWN_VALUE;
+		reg->imm = 0;
+	}
+}
+
 static int check_call(struct verifier_env *env, int func_id)
 {
 	struct verifier_state *state = &env->cur_state;
 	const struct bpf_func_proto *fn = NULL;
 	struct reg_state *regs = state->regs;
-	struct bpf_map *map = NULL;
 	struct reg_state *reg;
+	struct bpf_call_arg_meta meta;
+	bool changes_data;
 	int i, err;
 
 	/* find function prototype */
@@ -988,23 +1167,45 @@ static int check_call(struct verifier_env *env, int func_id)
 		return -EINVAL;
 	}
 
+	changes_data = bpf_helper_changes_skb_data(fn->func);
+
+	memset(&meta, 0, sizeof(meta));
+
+	/* We only support one arg being in raw mode at the moment, which
+	 * is sufficient for the helper functions we have right now.
+	 */
+	err