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

Pull networking fixes from David Miller:

 1) Transfer padding was wrong for full-speed USB in ASIX driver, fix
    from Ingo van Lil.

 2) Propagate the negative packet offset fix into the PowerPC BPF JIT.
    From Jan Seiffert.

 3) dl2k driver's private ioctls were letting unprivileged tasks make
    MII writes and other ugly bits like that.  Fix from Jeff Mahoney.

 4) Fix TX VLAN and RX packet drops in ucc_geth, from Joakim Tjernlund.

 5) OOPS and network namespace fixes in IPVS from Hans Schillstrom and
    Julian Anastasov.

 6) Fix races and sleeping in locked context bugs in drop_monitor, from
    Neil Horman.

 7) Fix link status indication in smsc95xx driver, from Paolo Pisati.

 8) Fix bridge netfilter OOPS, from Peter Huang.

 9) L2TP sendmsg can return on error conditions with the socket lock
    held, oops.  Fix from Sasha Levin.

10) udp_diag should return meaningful values for socket memory usage,
    from Shan Wei.

11) Eric Dumazet is so awesome he gets his own section:

       Socket memory cgroup code (I never should have applied those
       patches, grumble...) made erroneous changes to
       sk_sockets_allocated_read_positive().  It was changed to
       use percpu_counter_sum_positive (which requires BH disabling)
       instead of percpu_counter_read_positive (which does not).
       Revert back to avoid crashes and lockdep warnings.

       Adjust the default tcp_adv_win_scale and tcp_rmem[2] values
       to fix throughput regressions.  This is necessary as a result
       of our more precise skb->truesize tracking.

       Fix SKB leak in netem packet scheduler.

12) New device IDs for various bluetooth devices, from Manoj Iyer,
    AceLan Kao, and Steven Harms.

13) Fix command completion race in ipw2200, from Stanislav Yakovlev.

14) Fix rtlwifi oops on unload, from Larry Finger.

15) Fix hard_mtu when adjusting hard_header_len in smsc95xx driver.
    From Stephane Fillod.

16) ehea driver registers it's IRQ before all the necessary state is
    setup, resulting in crashes.  Fix from Thadeu Lima de Souza
    Cascardo.

17) Fix PHY connection failures in davinci_emac driver, from Anatolij
    Gustschin.

18) Missing break; in switch statement in bluetooth's
    hci_cmd_complete_evt().  Fix from Szymon Janc.

19) Fix queue programming in iwlwifi, from Johannes Berg.

20) Interrupt throttling defaults not being actually programmed into the
    hardware, fix from Jeff Kirsher and Ying Cai.

21) TLAN driver SKB encoding in descriptor busted on 64-bit, fix from
    Benjamin Poirier.

22) Fix blind status block RX producer pointer deref in TG3 driver, from
    Matt Carlson.

23) Promisc and multicast are busted on ehea, fixes from Thadeu Lima de
    Souza Cascardo.

24) Fix crashes in 6lowpan, from Alexander Smirnov.

25) tcp_complete_cwr() needs to be careful to not rewind the CWND to
    ssthresh if ssthresh has the "infinite" value.  Fix from Yuchung
    Cheng.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (81 commits)
  sungem: Fix WakeOnLan
  tcp: change tcp_adv_win_scale and tcp_rmem[2]
  net: l2tp: unlock socket lock before returning from l2tp_ip_sendmsg
  drop_monitor: prevent init path from scheduling on the wrong cpu
  usbnet: fix failure handling in usbnet_probe
  usbnet: fix leak of transfer buffer of dev->interrupt
  ucc_geth: Add 16 bytes to max TX frame for VLANs
  net: ucc_geth, increase no. of HW RX descriptors
  netem: fix possible skb leak
  sky2: fix receive length error in mixed non-VLAN/VLAN traffic
  sky2: propogate rx hash when packet is copied
  net: fix two typos in skbuff.h
  cxgb3: Don't call cxgb_vlan_mode until q locks are initialized
  ixgbe: fix calling skb_put on nonlinear skb assertion bug
  ixgbe: Fix a memory leak in IEEE DCB
  igbvf: fix the bug when initializing the igbvf
  smsc75xx: enable mac to detect speed/duplex from phy
  smsc75xx: declare smsc75xx's MII as GMII capable
  smsc75xx: fix phy interrupt acknowledge
  smsc75xx: fix phy init reset loop
  ...

3 files changed, 111 insertions, 31 deletions

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index af1ab5e9a691..5c3cf2d04e41 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -48,7 +48,13 @@
 /*
  * Assembly helpers from arch/powerpc/net/bpf_jit.S:
  */
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
+#define DECLARE_LOAD_FUNC(func)	\
+	extern u8 func[], func##_negative_offset[], func##_positive_offset[]
+
+DECLARE_LOAD_FUNC(sk_load_word);
+DECLARE_LOAD_FUNC(sk_load_half);
+DECLARE_LOAD_FUNC(sk_load_byte);
+DECLARE_LOAD_FUNC(sk_load_byte_msh);
 
 #define FUNCTION_DESCR_SIZE	24
 
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index ff4506e85cce..55ba3855a97f 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -31,14 +31,13 @@
  * then branch directly to slow_path_XXX if required.  (In fact, could
  * load a spare GPR with the address of slow_path_generic and pass size
  * as an argument, making the call site a mtlr, li and bllr.)
- *
- * Technically, the "is addr < 0" check is unnecessary & slowing down
- * the ABS path, as it's statically checked on generation.
  */
 	.globl	sk_load_word
 sk_load_word:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_word_neg
+	.globl	sk_load_word_positive_offset
+sk_load_word_positive_offset:
 	/* Are we accessing past headlen? */
 	subi	r_scratch1, r_HL, 4
 	cmpd	r_scratch1, r_addr
@@ -51,7 +50,9 @@ sk_load_word:
 	.globl	sk_load_half
 sk_load_half:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_half_neg
+	.globl	sk_load_half_positive_offset
+sk_load_half_positive_offset:
 	subi	r_scratch1, r_HL, 2
 	cmpd	r_scratch1, r_addr
 	blt	bpf_slow_path_half
@@ -61,7 +62,9 @@ sk_load_half:
 	.globl	sk_load_byte
 sk_load_byte:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_byte_neg
+	.globl	sk_load_byte_positive_offset
+sk_load_byte_positive_offset:
 	cmpd	r_HL, r_addr
 	ble	bpf_slow_path_byte
 	lbzx	r_A, r_D, r_addr
@@ -69,22 +72,20 @@ sk_load_byte:
 
 /*
  * BPF_S_LDX_B_MSH: ldxb  4*([offset]&0xf)
- * r_addr is the offset value, already known positive
+ * r_addr is the offset value
  */
 	.globl sk_load_byte_msh
 sk_load_byte_msh:
+	cmpdi	r_addr, 0
+	blt	bpf_slow_path_byte_msh_neg
+	.globl sk_load_byte_msh_positive_offset
+sk_load_byte_msh_positive_offset:
 	cmpd	r_HL, r_addr
 	ble	bpf_slow_path_byte_msh
 	lbzx	r_X, r_D, r_addr
 	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
 	blr
 
-bpf_error:
-	/* Entered with cr0 = lt */
-	li	r3, 0
-	/* Generated code will 'blt epilogue', returning 0. */
-	blr
-
 /* Call out to skb_copy_bits:
  * We'll need to back up our volatile regs first; we have
  * local variable space at r1+(BPF_PPC_STACK_BASIC).
@@ -136,3 +137,84 @@ bpf_slow_path_byte_msh:
 	lbz	r_X, BPF_PPC_STACK_BASIC+(2*8)(r1)
 	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
 	blr
+
+/* Call out to bpf_internal_load_pointer_neg_helper:
+ * We'll need to back up our volatile regs first; we have
+ * local variable space at r1+(BPF_PPC_STACK_BASIC).
+ * Allocate a new stack frame here to remain ABI-compliant in
+ * stashing LR.
+ */
+#define sk_negative_common(SIZE)				\
+	mflr	r0;						\
+	std	r0, 16(r1);					\
+	/* R3 goes in parameter space of caller's frame */	\
+	std	r_skb, (BPF_PPC_STACKFRAME+48)(r1);		\
+	std	r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1);		\
+	std	r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1);		\
+	stdu	r1, -BPF_PPC_SLOWPATH_FRAME(r1);		\
+	/* R3 = r_skb, as passed */				\
+	mr	r4, r_addr;					\
+	li	r5, SIZE;					\
+	bl	bpf_internal_load_pointer_neg_helper;		\
+	/* R3 != 0 on success */				\
+	addi	r1, r1, BPF_PPC_SLOWPATH_FRAME;			\
+	ld	r0, 16(r1);					\
+	ld	r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1);		\
+	ld	r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1);		\
+	mtlr	r0;						\
+	cmpldi	r3, 0;						\
+	beq	bpf_error_slow;	/* cr0 = EQ */			\
+	mr	r_addr, r3;					\
+	ld	r_skb, (BPF_PPC_STACKFRAME+48)(r1);		\
+	/* Great success! */
+
+bpf_slow_path_word_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_word_negative_offset
+sk_load_word_negative_offset:
+	sk_negative_common(4)
+	lwz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_half_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_half_negative_offset
+sk_load_half_negative_offset:
+	sk_negative_common(2)
+	lhz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_byte_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_byte_negative_offset
+sk_load_byte_negative_offset:
+	sk_negative_common(1)
+	lbz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_byte_msh_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_byte_msh_negative_offset
+sk_load_byte_msh_negative_offset:
+	sk_negative_common(1)
+	lbz	r_X, 0(r_addr)
+	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
+	blr
+
+bpf_error_slow:
+	/* fabricate a cr0 = lt */
+	li	r_scratch1, -1
+	cmpdi	r_scratch1, 0
+bpf_error:
+	/* Entered with cr0 = lt */
+	li	r3, 0
+	/* Generated code will 'blt epilogue', returning 0. */
+	blr
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 73619d3aeb6c..2dc8b1484845 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -127,6 +127,9 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 	PPC_BLR();
 }
 
+#define CHOOSE_LOAD_FUNC(K, func) \
+	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
+
 /* Assemble the body code between the prologue & epilogue. */
 static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			      struct codegen_context *ctx,
@@ -391,21 +394,16 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 
 			/*** Absolute loads from packet header/data ***/
 		case BPF_S_LD_W_ABS:
-			func = sk_load_word;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 			goto common_load;
 		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);
 		common_load:
-			/*
-			 * Load from [K].  Reference with the (negative)
-			 * SKF_NET_OFF/SKF_LL_OFF offsets is unsupported.
-			 */
+			/* Load from [K]. */
 			ctx->seen |= SEEN_DATAREF;
-			if ((int)K < 0)
-				return -ENOTSUPP;
 			PPC_LI64(r_scratch1, func);
 			PPC_MTLR(r_scratch1);
 			PPC_LI32(r_addr, K);
@@ -429,7 +427,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 		common_load_ind:
 			/*
 			 * Load from [X + K].  Negative offsets are tested for
-			 * in the helper functions, and result in a 'ret 0'.
+			 * in the helper functions.
 			 */
 			ctx->seen |= SEEN_DATAREF | SEEN_XREG;
 			PPC_LI64(r_scratch1, func);
@@ -443,13 +441,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			break;
 
 		case BPF_S_LDX_B_MSH:
-			/*
-			 * x86 version drops packet (RET 0) when K<0, whereas
-			 * interpreter does allow K<0 (__load_pointer, special
-			 * ancillary data).  common_load returns ENOTSUPP if K<0,
-			 * so we fall back to interpreter & filter works.
-			 */
-			func = sk_load_byte_msh;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 			goto common_load;
 			break;