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

Pull networking fixes from David Miller:

 1) The value choosen for the new SO_MAX_PACING_RATE socket option on
    parisc was very poorly choosen, let's fix it while we still can.
    From Eric Dumazet.

 2) Our generic reciprocal divide was found to handle some edge cases
    incorrectly, part of this is encoded into the BPF as deep as the JIT
    engines themselves.  Just use a real divide throughout for now.
    From Eric Dumazet.

 3) Because the initial lookup is lockless, the TCP metrics engine can
    end up creating two entries for the same lookup key.  Fix this by
    doing a second lookup under the lock before we actually create the
    new entry.  From Christoph Paasch.

 4) Fix scatter-gather list init in usbnet driver, from Bjørn Mork.

 5) Fix unintended 32-bit truncation in cxgb4 driver's bit shifting.
    From Dan Carpenter.

 6) Netlink socket dumping uses the wrong socket state for timewait
    sockets.  Fix from Neal Cardwell.

 7) Fix netlink memory leak in ieee802154_add_iface(), from Christian
    Engelmayer.

 8) Multicast forwarding in ipv4 can overflow the per-rule reference
    counts, causing all multicast traffic to cease.  Fix from Hannes
    Frederic Sowa.

 9) via-rhine needs to stop all TX queues when it resets the device,
    from Richard Weinberger.

10) Fix RDS per-cpu accesses broken by the this_cpu_* conversions.  From
    Gerald Schaefer.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  s390/bpf,jit: fix 32 bit divisions, use unsigned divide instructions
  parisc: fix SO_MAX_PACING_RATE typo
  ipv6: simplify detection of first operational link-local address on interface
  tcp: metrics: Avoid duplicate entries with the same destination-IP
  net: rds: fix per-cpu helper usage
  e1000e: Fix compilation warning when !CONFIG_PM_SLEEP
  bpf: do not use reciprocal divide
  be2net: add dma_mapping_error() check for dma_map_page()
  bnx2x: Don't release PCI bars on shutdown
  net,via-rhine: Fix tx_timeout handling
  batman-adv: fix batman-adv header overhead calculation
  qlge: Fix vlan netdev features.
  net: avoid reference counter overflows on fib_rules in multicast forwarding
  dm9601: add USB IDs for new dm96xx variants
  MAINTAINERS: add virtio-dev ML for virtio
  ieee802154: Fix memory leak in ieee802154_add_iface()
  net: usbnet: fix SG initialisation
  inet_diag: fix inet_diag_dump_icsk() to use correct state for timewait sockets
  cxgb4: silence shift wrapping static checker warning

6 files changed, 50 insertions, 25 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 9ed155ad0f97..271b5e971568 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -641,10 +641,10 @@ load_ind:
 			emit(ARM_MUL(r_A, r_A, r_X), ctx);
 			break;
 		case BPF_S_ALU_DIV_K:
-			/* current k == reciprocal_value(userspace k) */
+			if (k == 1)
+				break;
 			emit_mov_i(r_scratch, k, ctx);
-			/* A = top 32 bits of the product */
-			emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+			emit_udiv(r_A, r_A, r_scratch, ctx);
 			break;
 		case BPF_S_ALU_DIV_X:
 			update_on_xread(ctx);
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index f33113a6141e..70b3674dac4e 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -75,6 +75,6 @@
 
 #define SO_BUSY_POLL		0x4027
 
-#define SO_MAX_PACING_RATE	0x4048
+#define SO_MAX_PACING_RATE	0x4028
 
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index ac3c2a10dafd..555034f8505e 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -223,10 +223,11 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			}
 			PPC_DIVWU(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
+		case BPF_S_ALU_DIV_K: /* A /= K */
+			if (K == 1)
+				break;
 			PPC_LI32(r_scratch1, K);
-			/* Top 32 bits of 64bit result -> A */
-			PPC_MULHWU(r_A, r_A, r_scratch1);
+			PPC_DIVWU(r_A, r_A, r_scratch1);
 			break;
 		case BPF_S_ALU_AND_X:
 			ctx->seen |= SEEN_XREG;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 16871da37371..708d60e40066 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -368,14 +368,16 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* dr %r4,%r12 */
-		EMIT2(0x1d4c);
+		/* dlr %r4,%r12 */
+		EMIT4(0xb997004c);
 		break;
-	case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K) */
-		/* m %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5c40d000, EMIT_CONST(K));
-		/* lr %r5,%r4 */
-		EMIT2(0x1854);
+	case BPF_S_ALU_DIV_K: /* A /= K */
+		if (K == 1)
+			break;
+		/* lhi %r4,0 */
+		EMIT4(0xa7480000);
+		/* dl %r4,<d(K)>(%r13) */
+		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		break;
 	case BPF_S_ALU_MOD_X: /* A %= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
@@ -385,16 +387,21 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* dr %r4,%r12 */
-		EMIT2(0x1d4c);
+		/* dlr %r4,%r12 */
+		EMIT4(0xb997004c);
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
 	case BPF_S_ALU_MOD_K: /* A %= K */
+		if (K == 1) {
+			/* lhi %r5,0 */
+			EMIT4(0xa7580000);
+			break;
+		}
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* d %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
+		/* dl %r4,<d(K)>(%r13) */
+		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 218b6b23c378..01fe9946d388 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -497,9 +497,20 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ALU_MUL_K:	/* A *= K */
 				emit_alu_K(MUL, K);
 				break;
-			case BPF_S_ALU_DIV_K:	/* A /= K */
-				emit_alu_K(MUL, K);
-				emit_read_y(r_A);
+			case BPF_S_ALU_DIV_K:	/* A /= K with K != 0*/
+				if (K == 1)
+					break;
+				emit_write_y(G0);
+#ifdef CONFIG_SPARC32
+				/* The Sparc v8 architecture requires
+				 * three instructions between a %y
+				 * register write and the first use.
+				 */
+				emit_nop();
+				emit_nop();
+				emit_nop();
+#endif
+				emit_alu_K(DIV, K);
 				break;
 			case BPF_S_ALU_DIV_X:	/* A /= X; */
 				emit_cmpi(r_X, 0);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 26328e800869..4ed75dd81d05 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -359,15 +359,21 @@ void bpf_jit_compile(struct sk_filter *fp)
 				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
 				break;
 			case BPF_S_ALU_MOD_K: /* A %= K; */
+				if (K == 1) {
+					CLEAR_A();
+					break;
+				}
 				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
 				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
 				EMIT2(0xf7, 0xf1);	/* div %ecx */
 				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
 				break;
-			case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
-				EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */
-				EMIT(K, 4);
-				EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */
+			case BPF_S_ALU_DIV_K: /* A /= K */
+				if (K == 1)
+					break;
+				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
+				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
+				EMIT2(0xf7, 0xf1);	/* div %ecx */
 				break;
 			case BPF_S_ALU_AND_X:
 				seen |= SEEN_XREG;