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

Pull networking updates from David Miller:

 1) Fix inaccuracies in network driver interface documentation, from Ben
    Hutchings.

 2) Fix handling of negative offsets in BPF JITs, from Jan Seiffert.

 3) Compile warning, locking, and refcounting fixes in netfilter's
    xt_CT, from Pablo Neira Ayuso.

 4) phonet sendmsg needs to validate user length just like any other
    datagram protocol, fix from Sasha Levin.

 5) Ipv6 multicast code uses wrong loop index, from RongQing Li.

 6) Link handling and firmware fixes in bnx2x driver from Yaniv Rosner
    and Yuval Mintz.

 7) mlx4 erroneously allocates 4 pages at a time, regardless of page
    size, fix from Thadeu Lima de Souza Cascardo.

 8) SCTP socket option wasn't extended in a backwards compatible way,
    fix from Thomas Graf.

 9) Add missing address change event emissions to bonding, from Shlomo
    Pongratz.

10) /proc/net/dev regressed because it uses a private offset to track
    where we are in the hash table, but this doesn't track the offset
    pullback that the seq_file code does resulting in some entries being
    missed in large dumps.

    Fix from Eric Dumazet.

11) do_tcp_sendpage() unloads the send queue way too fast, because it
    invokes tcp_push() when it shouldn't.  Let the natural sequence
    generated by the splice paths, and the assosciated MSG_MORE
    settings, guide the tcp_push() calls.

    Otherwise what goes out of TCP is spaghetti and doesn't batch
    effectively into GSO/TSO clusters.

    From Eric Dumazet.

12) Once we put a SKB into either the netlink receiver's queue or a
    socket error queue, it can be consumed and freed up, therefore we
    cannot touch it after queueing it like that.

    Fixes from Eric Dumazet.

13) PPP has this annoying behavior in that for every transmit call it
    immediately stops the TX queue, then calls down into the next layer
    to transmit the PPP frame.

    But if that next layer can take it immediately, it just un-stops the
    TX queue right before returning from the transmit method.

    Besides being useless work, it makes several facilities unusable, in
    particular things like the equalizers.  Well behaved devices should
    only stop the TX queue when they really are full, and in PPP's case
    when it gets backlogged to the downstream device.

    David Woodhouse therefore fixed PPP to not stop the TX queue until
    it's downstream can't take data any more.

14) IFF_UNICAST_FLT got accidently lost in some recent stmmac driver
    changes, re-add.  From Marc Kleine-Budde.

15) Fix link flaps in ixgbe, from Eric W. Multanen.

16) Descriptor writeback fixes in e1000e from Matthew Vick.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (47 commits)
  net: fix a race in sock_queue_err_skb()
  netlink: fix races after skb queueing
  doc, net: Update ndo_start_xmit return type and values
  doc, net: Remove instruction to set net_device::trans_start
  doc, net: Update netdev operation names
  doc, net: Update documentation of synchronisation for TX multiqueue
  doc, net: Remove obsolete reference to dev->poll
  ethtool: Remove exception to the requirement of holding RTNL lock
  MAINTAINERS: update for Marvell Ethernet drivers
  bonding: properly unset current_arp_slave on slave link up
  phonet: Check input from user before allocating
  tcp: tcp_sendpages() should call tcp_push() once
  ipv6: fix array index in ip6_mc_add_src()
  mlx4: allocate just enough pages instead of always 4 pages
  stmmac: re-add IFF_UNICAST_FLT for dwmac1000
  bnx2x: Clear MDC/MDIO warning message
  bnx2x: Fix BCM57711+BCM84823 link issue
  bnx2x: Clear BCM84833 LED after fan failure
  bnx2x: Fix BCM84833 PHY FW version presentation
  bnx2x: Fix link issue for BCM8727 boards.
  ...

2 files changed, 115 insertions, 48 deletions

diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 6687022..877b9a1 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -18,17 +18,17 @@
  * r9d : hlen = skb->len - skb->data_len
  */
 #define SKBDATA	%r8
-
-sk_load_word_ind:
-	.globl	sk_load_word_ind
-
-	add	%ebx,%esi	/* offset += X */
-#	test    %esi,%esi	/* if (offset < 0) goto bpf_error; */
-	js	bpf_error
+#define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
 
 sk_load_word:
 	.globl	sk_load_word
 
+	test	%esi,%esi
+	js	bpf_slow_path_word_neg
+
+sk_load_word_positive_offset:
+	.globl	sk_load_word_positive_offset
+
 	mov	%r9d,%eax		# hlen
 	sub	%esi,%eax		# hlen - offset
 	cmp	$3,%eax
@@ -37,16 +37,15 @@ sk_load_word:
 	bswap   %eax  			/* ntohl() */
 	ret
 
-
-sk_load_half_ind:
-	.globl sk_load_half_ind
-
-	add	%ebx,%esi	/* offset += X */
-	js	bpf_error
-
 sk_load_half:
 	.globl	sk_load_half
 
+	test	%esi,%esi
+	js	bpf_slow_path_half_neg
+
+sk_load_half_positive_offset:
+	.globl	sk_load_half_positive_offset
+
 	mov	%r9d,%eax
 	sub	%esi,%eax		#	hlen - offset
 	cmp	$1,%eax
@@ -55,14 +54,15 @@ sk_load_half:
 	rol	$8,%ax			# ntohs()
 	ret
 
-sk_load_byte_ind:
-	.globl sk_load_byte_ind
-	add	%ebx,%esi	/* offset += X */
-	js	bpf_error
-
 sk_load_byte:
 	.globl	sk_load_byte
 
+	test	%esi,%esi
+	js	bpf_slow_path_byte_neg
+
+sk_load_byte_positive_offset:
+	.globl	sk_load_byte_positive_offset
+
 	cmp	%esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
 	jle	bpf_slow_path_byte
 	movzbl	(SKBDATA,%rsi),%eax
@@ -73,25 +73,21 @@ sk_load_byte:
  *
  * Implements BPF_S_LDX_B_MSH : ldxb  4*([offset]&0xf)
  * Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value, already known positive
+ * Inputs : %esi is the offset value
  */
-ENTRY(sk_load_byte_msh)
-	CFI_STARTPROC
+sk_load_byte_msh:
+	.globl	sk_load_byte_msh
+	test	%esi,%esi
+	js	bpf_slow_path_byte_msh_neg
+
+sk_load_byte_msh_positive_offset:
+	.globl	sk_load_byte_msh_positive_offset
 	cmp	%esi,%r9d      /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
 	jle	bpf_slow_path_byte_msh
 	movzbl	(SKBDATA,%rsi),%ebx
 	and	$15,%bl
 	shl	$2,%bl
 	ret
-	CFI_ENDPROC
-ENDPROC(sk_load_byte_msh)
-
-bpf_error:
-# force a return 0 from jit handler
-	xor		%eax,%eax
-	mov		-8(%rbp),%rbx
-	leaveq
-	ret
 
 /* rsi contains offset and can be scratched */
 #define bpf_slow_path_common(LEN)		\
@@ -138,3 +134,67 @@ bpf_slow_path_byte_msh:
 	shl	$2,%al
 	xchg	%eax,%ebx
 	ret
+
+#define sk_negative_common(SIZE)				\
+	push	%rdi;	/* save skb */				\
+	push	%r9;						\
+	push	SKBDATA;					\
+/* rsi already has offset */					\
+	mov	$SIZE,%ecx;	/* size */			\
+	call	bpf_internal_load_pointer_neg_helper;		\
+	test	%rax,%rax;					\
+	pop	SKBDATA;					\
+	pop	%r9;						\
+	pop	%rdi;						\
+	jz	bpf_error
+
+
+bpf_slow_path_word_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
+	jl	bpf_error	/* offset lower -> error  */
+sk_load_word_negative_offset:
+	.globl	sk_load_word_negative_offset
+	sk_negative_common(4)
+	mov	(%rax), %eax
+	bswap	%eax
+	ret
+
+bpf_slow_path_half_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_half_negative_offset:
+	.globl	sk_load_half_negative_offset
+	sk_negative_common(2)
+	mov	(%rax),%ax
+	rol	$8,%ax
+	movzwl	%ax,%eax
+	ret
+
+bpf_slow_path_byte_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_byte_negative_offset:
+	.globl	sk_load_byte_negative_offset
+	sk_negative_common(1)
+	movzbl	(%rax), %eax
+	ret
+
+bpf_slow_path_byte_msh_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_byte_msh_negative_offset:
+	.globl	sk_load_byte_msh_negative_offset
+	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
+	sk_negative_common(1)
+	movzbl	(%rax),%eax
+	and	$15,%al
+	shl	$2,%al
+	xchg	%eax,%ebx
+	ret
+
+bpf_error:
+# force a return 0 from jit handler
+	xor		%eax,%eax
+	mov		-8(%rbp),%rbx
+	leaveq
+	ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5a5b6e4..0597f95 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -30,7 +30,10 @@ int bpf_jit_enable __read_mostly;
  * assembly code in arch/x86/net/bpf_jit.S
  */
 extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
-extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[];
+extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
+extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
+extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
 
 static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -117,6 +120,8 @@ static inline void bpf_flush_icache(void *start, void *end)
 	set_fs(old_fs);
 }
 
+#define CHOOSE_LOAD_FUNC(K, func) \
+	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
 void bpf_jit_compile(struct sk_filter *fp)
 {
@@ -473,44 +478,46 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
 				break;
 			case BPF_S_LD_W_ABS:
-				func = sk_load_word;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 common_load:			seen |= SEEN_DATAREF;
-				if ((int)K < 0) {
-					/* Abort the JIT because __load_pointer() is needed. */
-					goto out;
-				}
 				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K); /* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call */
 				break;
 			case BPF_S_LD_H_ABS:
-				func = sk_load_half;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_half);
 				goto common_load;
 			case BPF_S_LD_B_ABS:
-				func = sk_load_byte;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
 				goto common_load;
 			case BPF_S_LDX_B_MSH:
-				if ((int)K < 0) {
-					/* Abort the JIT because __load_pointer() is needed. */
-					goto out;
-				}
+				func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 				seen |= SEEN_DATAREF | SEEN_XREG;
-				t_offset = sk_load_byte_msh - (image + addrs[i]);
+				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K);	/* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
 				break;
 			case BPF_S_LD_W_IND:
-				func = sk_load_word_ind;
+				func = sk_load_word;
 common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 				t_offset = func - (image + addrs[i]);
-				EMIT1_off32(0xbe, K);	/* mov imm32,%esi   */
+				if (K) {
+					if (is_imm8(K)) {
+						EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */
+					} else {
+						EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
+						EMIT(K, 4);
+					}
+				} else {
+					EMIT2(0x89,0xde); /* mov %ebx,%esi */
+				}
 				EMIT1_off32(0xe8, t_offset);	/* call sk_load_xxx_ind */
 				break;
 			case BPF_S_LD_H_IND:
-				func = sk_load_half_ind;
+				func = sk_load_half;
 				goto common_load_ind;
 			case BPF_S_LD_B_IND:
-				func = sk_load_byte_ind;
+				func = sk_load_byte;
 				goto common_load_ind;
 			case BPF_S_JMP_JA:
 				t_offset = addrs[i + K] - addrs[i];