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

Pull networking fixes from David Miller:

 1) Handle max TX power properly wrt VIFs and the MAC in iwlwifi, from
    Avri Altman.

 2) Use the correct FW API for scan completions in iwlwifi, from Avraham
    Stern.

 3) FW monitor in iwlwifi accidently uses unmapped memory, fix from Liad
    Kaufman.

 4) rhashtable conversion of mac80211 station table was buggy, the
    virtual interface was not taken into account.  Fix from Johannes
    Berg.

 5) Fix deadlock in rtlwifi by not using a zero timeout for
    usb_control_msg(), from Larry Finger.

 6) Update reordering state before calculating loss detection, from
    Yuchung Cheng.

 7) Fix off by one in bluetooth firmward parsing, from Dan Carpenter.

 8) Fix extended frame handling in xiling_can driver, from Jeppe
    Ledet-Pedersen.

 9) Fix CODEL packet scheduler behavior in the presence of TSO packets,
    from Eric Dumazet.

10) Fix NAPI budget testing in fm10k driver, from Alexander Duyck.

11) macvlan needs to propagate promisc settings down the the lower
    device, from Vlad Yasevich.

12) igb driver can oops when changing number of rings, from Toshiaki
    Makita.

13) Source specific default routes not handled properly in ipv6, from
    Markus Stenberg.

14) Use after free in tc_ctl_tfilter(), from WANG Cong.

15) Use softirq spinlocking in netxen driver, from Tony Camuso.

16) Two ARM bpf JIT fixes from Nicolas Schichan.

17) Handle MSG_DONTWAIT properly in ring based AF_PACKET sends, from
    Mathias Kretschmer.

18) Fix x86 bpf JIT implementation of FROM_{BE16,LE16,LE32}, from Alexei
    Starovoitov.

19) ll_temac driver DMA maps TX packet header with incorrect length, fix
    from Michal Simek.

20) We removed pm_qos bits from netdevice.h, but some indirect
    references remained.  Kill them.  From David Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (90 commits)
  net: Remove remaining remnants of pm_qos from netdevice.h
  e1000e: Add pm_qos header
  net: phy: micrel: Fix regression in kszphy_probe
  net: ll_temac: Fix DMA map size bug
  x86: bpf_jit: fix FROM_BE16 and FROM_LE16/32 instructions
  netns: return RTM_NEWNSID instead of RTM_GETNSID on a get
  Update be2net maintainers' email addresses
  net_sched: gred: use correct backlog value in WRED mode
  pppoe: drop pppoe device in pppoe_unbind_sock_work
  net: qca_spi: Fix possible race during probe
  net: mdio-gpio: Allow for unspecified bus id
  af_packet / TX_RING not fully non-blocking (w/ MSG_DONTWAIT).
  bnx2x: limit fw delay in kdump to 5s after boot
  ARM: net: delegate filter to kernel interpreter when imm_offset() return value can't fit into 12bits.
  ARM: net fix emit_udiv() for BPF_ALU | BPF_DIV | BPF_K intruction.
  mpls: Change reserved label names to be consistent with netbsd
  usbnet: avoid integer overflow in start_xmit
  netxen_nic: use spin_[un]lock_bh around tx_clean_lock (2)
  net: xgene_enet: Set hardware dependency
  net: amd-xgbe: Add hardware dependency
  ...

2 files changed, 67 insertions, 3 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index e1268f905026..e0e23582c8b4 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -54,6 +54,7 @@
 #define SEEN_DATA		(1 << (BPF_MEMWORDS + 3))
 
 #define FLAG_NEED_X_RESET	(1 << 0)
+#define FLAG_IMM_OVERFLOW	(1 << 1)
 
 struct jit_ctx {
 	const struct bpf_prog *skf;
@@ -293,6 +294,15 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx)
 	/* PC in ARM mode == address of the instruction + 8 */
 	imm = offset - (8 + ctx->idx * 4);
 
+	if (imm & ~0xfff) {
+		/*
+		 * literal pool is too far, signal it into flags. we
+		 * can only detect it on the second pass unfortunately.
+		 */
+		ctx->flags |= FLAG_IMM_OVERFLOW;
+		return 0;
+	}
+
 	return imm;
 }
 
@@ -449,10 +459,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
 		return;
 	}
 #endif
-	if (rm != ARM_R0)
-		emit(ARM_MOV_R(ARM_R0, rm), ctx);
+
+	/*
+	 * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4
+	 * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into
+	 * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm
+	 * before using it as a source for ARM_R1.
+	 *
+	 * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is
+	 * ARM_R5 (r_X) so there is no particular register overlap
+	 * issues.
+	 */
 	if (rn != ARM_R1)
 		emit(ARM_MOV_R(ARM_R1, rn), ctx);
+	if (rm != ARM_R0)
+		emit(ARM_MOV_R(ARM_R0, rm), ctx);
 
 	ctx->seen |= SEEN_CALL;
 	emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
@@ -855,6 +876,14 @@ b_epilogue:
 		default:
 			return -1;
 		}
+
+		if (ctx->flags & FLAG_IMM_OVERFLOW)
+			/*
+			 * this instruction generated an overflow when
+			 * trying to access the literal pool, so
+			 * delegate this filter to the kernel interpreter.
+			 */
+			return -1;
 	}
 
 	/* compute offsets only during the first pass */
@@ -917,7 +946,14 @@ void bpf_jit_compile(struct bpf_prog *fp)
 	ctx.idx = 0;
 
 	build_prologue(&ctx);
-	build_body(&ctx);
+	if (build_body(&ctx) < 0) {
+#if __LINUX_ARM_ARCH__ < 7
+		if (ctx.imm_count)
+			kfree(ctx.imms);
+#endif
+		bpf_jit_binary_free(header);
+		goto out;
+	}
 	build_epilogue(&ctx);
 
 	flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 987514396c1e..99f76103c6b7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -559,6 +559,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				if (is_ereg(dst_reg))
 					EMIT1(0x41);
 				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+
+				/* emit 'movzwl eax, ax' */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
 				/* emit 'bswap eax' to swap lower 4 bytes */
@@ -577,6 +584,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			switch (imm32) {
+			case 16:
+				/* emit 'movzwl eax, ax' to zero extend 16-bit
+				 * into 64 bit
+				 */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 32:
+				/* emit 'mov eax, eax' to clear upper 32-bits */
+				if (is_ereg(dst_reg))
+					EMIT1(0x45);
+				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 64:
+				/* nop */
+				break;
+			}
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */