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

Pull networking fixes from David Miller:
 "Lots of bug fixes here:

   1) Out of bounds access in __bpf_skc_lookup, from Lorenz Bauer.

   2) Fix rate reporting in cfg80211_calculate_bitrate_he(), from John
      Crispin.

   3) Use after free in psock backlog workqueue, from John Fastabend.

   4) Fix source port matching in fdb peer flow rule of mlx5, from Raed
      Salem.

   5) Use atomic_inc_not_zero() in fl6_sock_lookup(), from Eric Dumazet.

   6) Network header needs to be set for packet redirect in nfp, from
      John Hurley.

   7) Fix udp zerocopy refcnt, from Willem de Bruijn.

   8) Don't assume linear buffers in vxlan and geneve error handlers,
      from Stefano Brivio.

   9) Fix TOS matching in mlxsw, from Jiri Pirko.

  10) More SCTP cookie memory leak fixes, from Neil Horman.

  11) Fix VLAN filtering in rtl8366, from Linus Walluij.

  12) Various TCP SACK payload size and fragmentation memory limit fixes
      from Eric Dumazet.

  13) Use after free in pneigh_get_next(), also from Eric Dumazet.

  14) LAPB control block leak fix from Jeremy Sowden"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (145 commits)
  lapb: fixed leak of control-blocks.
  tipc: purge deferredq list for each grp member in tipc_group_delete
  ax25: fix inconsistent lock state in ax25_destroy_timer
  neigh: fix use-after-free read in pneigh_get_next
  tcp: fix compile error if !CONFIG_SYSCTL
  hv_sock: Suppress bogus "may be used uninitialized" warnings
  be2net: Fix number of Rx queues used for flow hashing
  net: handle 802.1P vlan 0 packets properly
  tcp: enforce tcp_min_snd_mss in tcp_mtu_probing()
  tcp: add tcp_min_snd_mss sysctl
  tcp: tcp_fragment() should apply sane memory limits
  tcp: limit payload size of sacked skbs
  Revert "net: phylink: set the autoneg state in phylink_phy_change"
  bpf: fix nested bpf tracepoints with per-cpu data
  bpf: Fix out of bounds memory access in bpf_sk_storage
  vsock/virtio: set SOCK_DONE on peer shutdown
  net: dsa: rtl8366: Fix up VLAN filtering
  net: phylink: set the autoneg state in phylink_phy_change
  net: add high_order_alloc_disable sysctl/static key
  tcp: add tcp_tx_skb_cache sysctl
  ...

5 files changed, 51 insertions, 58 deletions

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 493c5c943acd..2291daf39cd1 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -338,6 +338,7 @@
 #define PPC_INST_MADDLD			0x10000033
 #define PPC_INST_DIVWU			0x7c000396
 #define PPC_INST_DIVD			0x7c0003d2
+#define PPC_INST_DIVDU			0x7c000392
 #define PPC_INST_RLWINM			0x54000000
 #define PPC_INST_RLWINM_DOT		0x54000001
 #define PPC_INST_RLWIMI			0x50000000
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 6026a7af031d..55d4377ccfae 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -112,7 +112,7 @@
 				     ___PPC_RA(a) | IMM_L(i))
 #define PPC_DIVWU(d, a, b)	EMIT(PPC_INST_DIVWU | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_DIVD(d, a, b)	EMIT(PPC_INST_DIVD | ___PPC_RT(d) |	      \
+#define PPC_DIVDU(d, a, b)	EMIT(PPC_INST_DIVDU | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_AND(d, a, b)	EMIT(PPC_INST_AND | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(b))
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 63d05c499cac..c2ee6041f02c 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -395,12 +395,12 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
 		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
 			if (BPF_OP(code) == BPF_MOD) {
-				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
+				PPC_DIVDU(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULD(b2p[TMP_REG_1], src_reg,
 						b2p[TMP_REG_1]);
 				PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
 			} else
-				PPC_DIVD(dst_reg, dst_reg, src_reg);
+				PPC_DIVDU(dst_reg, dst_reg, src_reg);
 			break;
 		case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
 		case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */
@@ -428,7 +428,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 				break;
 			case BPF_ALU64:
 				if (BPF_OP(code) == BPF_MOD) {
-					PPC_DIVD(b2p[TMP_REG_2], dst_reg,
+					PPC_DIVDU(b2p[TMP_REG_2], dst_reg,
 							b2p[TMP_REG_1]);
 					PPC_MULD(b2p[TMP_REG_1],
 							b2p[TMP_REG_1],
@@ -436,7 +436,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 					PPC_SUB(dst_reg, dst_reg,
 							b2p[TMP_REG_1]);
 				} else
-					PPC_DIVD(dst_reg, dst_reg,
+					PPC_DIVDU(dst_reg, dst_reg,
 							b2p[TMP_REG_1]);
 				break;
 			}
diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c
index 80b12aa5e10d..426d5c33ea90 100644
--- a/arch/riscv/net/bpf_jit_comp.c
+++ b/arch/riscv/net/bpf_jit_comp.c
@@ -751,22 +751,32 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_ADD | BPF_X:
 	case BPF_ALU64 | BPF_ADD | BPF_X:
 		emit(is64 ? rv_add(rd, rd, rs) : rv_addw(rd, rd, rs), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_X:
 	case BPF_ALU64 | BPF_SUB | BPF_X:
 		emit(is64 ? rv_sub(rd, rd, rs) : rv_subw(rd, rd, rs), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_X:
 	case BPF_ALU64 | BPF_AND | BPF_X:
 		emit(rv_and(rd, rd, rs), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_X:
 	case BPF_ALU64 | BPF_OR | BPF_X:
 		emit(rv_or(rd, rd, rs), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_X:
 	case BPF_ALU64 | BPF_XOR | BPF_X:
 		emit(rv_xor(rd, rd, rs), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_X:
 	case BPF_ALU64 | BPF_MUL | BPF_X:
@@ -789,14 +799,20 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
 		emit(is64 ? rv_sll(rd, rd, rs) : rv_sllw(rd, rd, rs), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_RSH | BPF_X:
 	case BPF_ALU64 | BPF_RSH | BPF_X:
 		emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_X:
 	case BPF_ALU64 | BPF_ARSH | BPF_X:
 		emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 
 	/* dst = -dst */
@@ -804,6 +820,8 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU64 | BPF_NEG:
 		emit(is64 ? rv_sub(rd, RV_REG_ZERO, rd) :
 		     rv_subw(rd, RV_REG_ZERO, rd), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 
 	/* dst = BSWAP##imm(dst) */
@@ -958,14 +976,20 @@ out_be:
 	case BPF_ALU | BPF_LSH | BPF_K:
 	case BPF_ALU64 | BPF_LSH | BPF_K:
 		emit(is64 ? rv_slli(rd, rd, imm) : rv_slliw(rd, rd, imm), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_RSH | BPF_K:
 	case BPF_ALU64 | BPF_RSH | BPF_K:
 		emit(is64 ? rv_srli(rd, rd, imm) : rv_srliw(rd, rd, imm), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_K:
 	case BPF_ALU64 | BPF_ARSH | BPF_K:
 		emit(is64 ? rv_srai(rd, rd, imm) : rv_sraiw(rd, rd, imm), ctx);
+		if (!is64)
+			emit_zext_32(rd, ctx);
 		break;
 
 	/* JUMP off */
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 32bfab4e21eb..eaaed5bfc4a4 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -186,9 +186,7 @@ struct jit_context {
 #define BPF_MAX_INSN_SIZE	128
 #define BPF_INSN_SAFETY		64
 
-#define AUX_STACK_SPACE		40 /* Space for RBX, R13, R14, R15, tailcnt */
-
-#define PROLOGUE_SIZE		37
+#define PROLOGUE_SIZE		20
 
 /*
  * Emit x86-64 prologue code for BPF program and check its size.
@@ -199,44 +197,19 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-	/* push rbp */
-	EMIT1(0x55);
-
-	/* mov rbp,rsp */
-	EMIT3(0x48, 0x89, 0xE5);
-
-	/* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */
-	EMIT3_off32(0x48, 0x81, 0xEC,
-		    round_up(stack_depth, 8) + AUX_STACK_SPACE);
-
-	/* sub rbp, AUX_STACK_SPACE */
-	EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE);
-
-	/* mov qword ptr [rbp+0],rbx */
-	EMIT4(0x48, 0x89, 0x5D, 0);
-	/* mov qword ptr [rbp+8],r13 */
-	EMIT4(0x4C, 0x89, 0x6D, 8);
-	/* mov qword ptr [rbp+16],r14 */
-	EMIT4(0x4C, 0x89, 0x75, 16);
-	/* mov qword ptr [rbp+24],r15 */
-	EMIT4(0x4C, 0x89, 0x7D, 24);
-
+	EMIT1(0x55);             /* push rbp */
+	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+	/* sub rsp, rounded_stack_depth */
+	EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
+	EMIT1(0x53);             /* push rbx */
+	EMIT2(0x41, 0x55);       /* push r13 */
+	EMIT2(0x41, 0x56);       /* push r14 */
+	EMIT2(0x41, 0x57);       /* push r15 */
 	if (!ebpf_from_cbpf) {
-		/*
-		 * Clear the tail call counter (tail_call_cnt): for eBPF tail
-		 * calls we need to reset the counter to 0. It's done in two
-		 * instructions, resetting RAX register to 0, and moving it
-		 * to the counter location.
-		 */
-
-		/* xor eax, eax */
-		EMIT2(0x31, 0xc0);
-		/* mov qword ptr [rbp+32], rax */
-		EMIT4(0x48, 0x89, 0x45, 32);
-
+		/* zero init tail_call_cnt */
+		EMIT2(0x6a, 0x00);
 		BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
 	}
-
 	*pprog = prog;
 }
 
@@ -281,13 +254,13 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 */
-	EMIT2_off32(0x8B, 0x85, 36);              /* mov eax, dword ptr [rbp + 36] */
+	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
 #define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
-	EMIT2_off32(0x89, 0x85, 36);              /* mov dword ptr [rbp + 36], eax */
+	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
 
 	/* prog = array->ptrs[index]; */
 	EMIT4_off32(0x48, 0x8B, 0x84, 0xD6,       /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
@@ -1036,19 +1009,14 @@ emit_jmp:
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
-			/* mov rbx, qword ptr [rbp+0] */
-			EMIT4(0x48, 0x8B, 0x5D, 0);
-			/* mov r13, qword ptr [rbp+8] */
-			EMIT4(0x4C, 0x8B, 0x6D, 8);
-			/* mov r14, qword ptr [rbp+16] */
-			EMIT4(0x4C, 0x8B, 0x75, 16);
-			/* mov r15, qword ptr [rbp+24] */
-			EMIT4(0x4C, 0x8B, 0x7D, 24);
-
-			/* add rbp, AUX_STACK_SPACE */
-			EMIT4(0x48, 0x83, 0xC5, AUX_STACK_SPACE);
-			EMIT1(0xC9); /* leave */
-			EMIT1(0xC3); /* ret */
+			if (!bpf_prog_was_classic(bpf_prog))
+				EMIT1(0x5B); /* get rid of tail_call_cnt */
+			EMIT2(0x41, 0x5F);   /* pop r15 */
+			EMIT2(0x41, 0x5E);   /* pop r14 */
+			EMIT2(0x41, 0x5D);   /* pop r13 */
+			EMIT1(0x5B);         /* pop rbx */
+			EMIT1(0xC9);         /* leave */
+			EMIT1(0xC3);         /* ret */
 			break;
 
 		default: