Netdev List
 help / color / mirror / Atom feed
* (unknown), 
From: 2012 SCAM VICTIMS COMPENSATIONS PAYMENTS. @ 2012-03-30 16:40 UTC (permalink / raw)


2012 SCAM VICTIMS COMPENSATIONS PAYMENTS.
ECOWAS NATIONS STATE/UNITED NATIONS
YOUR REF/PAYMENTS CODE: ECB/06654 FOR $500,000 USD ONLY.


Dear Victims of scam,
 This is to bring to your notice that our bank (ECOBANK INTL. PLC) is
delegated by the ECOWAS/UNITED NATIONS in Central Bank to compensate victims
of scam $500,000 (Five Hundred Thousand Dollars Only).

Your Name.___________________________
Address.___________________________
Phone .___________________________
Amount Defrauded.___________________________
Country.________________________

Send a copy of your response with the PAYMENT CODE
NUMBER(ECB/06654).

NAME: MR.CLEMENT SYLVANIUS
      SCAMMED VICTIM/REF/PAYMENTS CODE:
      ECB/06654 $500,000 USD.

Email: scamvictimstransfer_22@yahoo.co.jp

Yours Faithfully,
Mrs. Rosemary Peter
PUBLIC RELATIONS OFFICER
Copyright © 2012

^ permalink raw reply

* [REGRESSION][PATCH V4 3/3] bpf jit: Let the powerpc jit handle negative offsets
From: Jan Seiffert @ 2012-03-30 15:35 UTC (permalink / raw)
  To: netdev
  Cc: linux-kernel, linuxppc-dev, Matt Evans, Eric Dumazet,
	David S. Miller
In-Reply-To: <4F75CA89.4010709@googlemail.com>

Now the helper function from filter.c for negative offsets is exported,
it can be used it in the jit to handle negative offsets.

First modify the asm load helper functions to handle:
- know positive offsets
- know negative offsets
- any offset

then the compiler can be modified to explicitly use these helper
when appropriate.

This fixes the case of a negative X register and allows to lift
the restriction that bpf programs with negative offsets can't
be jited.

Signed-off-by: Jan Seiffert <kaffeemonster@googlemail.com>

I have only compile tested this, -ENOHARDWARE.
Can someone with more powerpc kung-fu review and maybe test this?
Esp. powerpc asm is not my strong point. I think i botched the
stack frame in the call setup. Help?

diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index ff4506e..e590aa5 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 +137,85 @@ 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 73619d3..2dc8b14 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;
 

^ permalink raw reply related

* Re: [REGRESSION][PATCH] bpf_jit drops the ball on indirect negative mem references
From: Matt Evans @ 2012-03-30 15:24 UTC (permalink / raw)
  To: Eric Dumazet
  Cc: Jan Seiffert, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org, David S. Miller
In-Reply-To: <1333116493.2325.2125.camel@edumazet-glaptop>

Howdy Eric,

On 30 Mar 2012, at 15:08, Eric Dumazet <eric.dumazet@gmail.com> wrote:

> On Fri, 2012-03-30 at 15:42 +0200, Jan Seiffert wrote:
> 
>> Do you know where i can ping the powerpc guys a little bit harder?
> 
> maybe using CC linux-arch@vger.kernel.org
> 
> One way to handle that would be to split this patch in 3 parts, so that
> I can Ack the non ppc part.
> 
> [1] introduce bpf_internal_load_pointer_neg_helper()
>    [BTW no need to EXPORT_SYMBOL it, since jit is not a module ]
> 
> [2] x86_bpf_iit: handle negative offsets in loads
> 
> [3] ppc_bpf_jit: handle negative offsets in loads

Yeah, that'd be great, then I can stew on it without holding you up further. 

Cheers,

Matt



> 
> 

^ permalink raw reply

* [REGRESSION][PATCH V4 2/3] bpf jit: Let the x86 jit handle negative offsets
From: Jan Seiffert @ 2012-03-30 15:24 UTC (permalink / raw)
  To: netdev; +Cc: linux-kernel, Eric Dumazet, David S. Miller
In-Reply-To: <4F75CA89.4010709@googlemail.com>

Now the helper function from filter.c for negative offsets is exported,
it can be used it in the jit to handle negative offsets.

First modify the asm load helper functions to handle:
- know positive offsets
- know negative offsets
- any offset

then the compiler can be modified to explicitly use these helper
when appropriate.

This fixes the case of a negative X register and allows to lift
the restriction that bpf programs with negative offsets can't
be jited.

Signed-of-by: Jan Seiffert <kaffeemonster@googlemail.com>

diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 6687022..2897d7f 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 +134,68 @@ 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 5671752..39a2e2c 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];

^ permalink raw reply related

* Re: [PATCH 05/12] Add dummy smsc911x regulators to cm-t35.
From: Igor Grinberg @ 2012-03-30 15:23 UTC (permalink / raw)
  To: Tony Lindgren
  Cc: Russ Dill, linux-omap, Mark Brown, Matt Porter, robert.marklund,
	linus.walleij, linux-arm-kernel, netdev@vger.kernel.org
In-Reply-To: <20120328170316.GR9859@atomide.com>

On 03/28/12 19:03, Tony Lindgren wrote:
> * Igor Grinberg <grinberg@compulab.co.il> [120327 23:36]:
>> Hi Tony,
>>
>> On 03/27/12 19:28, Tony Lindgren wrote:
>>> * Igor Grinberg <grinberg@compulab.co.il> [120327 08:56]:
>>>> Hi Russ,
>>>>
>>>> This patch works, but can we, please use the attached patch instead?
>>>
>>> Hmm what's the difference here? Do you have some real controllable
>>> regulator for one of the smsc911x instances?
>>
>> Well, the difference here is that those regulators will only be present
>> if the smsc911x controllers are present and their initialization is done
>> along with the controllers.
>> Also, I want to separate the cm-t35 from sb-t35 for future easier
>> refactoring of the sb-t35 code so it can be reused also on cm-t3517.
>>
>> Only vddvario for smsc911x.0 is controllable - connected to VIO, but
>> VIO will never be disabled as it also controls many other devices
>> (DRAM is among them), so I prefer it to be dummy and keep it together
>> with vdd33a.
> 
> OK thanks for the clarification. 
> 
>>> Anyways, I take it that you have tested that both smsc911x interfaces
>>> work now?
>>
>> Yes, both regulators are registered and found by the smsc911x driver.
>> There is some kind of problem with the smsc911x.1, but it looks unrelated
>> to the patch:
> 
> OK good to hear. Regarding the following problem..
>  
>> smsc911x: Driver version 2008-10-21
>> irq 323: nobody cared (try booting with the "irqpoll" option)
>> [<c001ae6c>] (unwind_backtrace+0x0/0xfc) from [<c0088960>] (__report_bad_irq+0x28/0xbc)
>> [<c0088960>] (__report_bad_irq+0x28/0xbc) from [<c0088bd4>] (note_interrupt+0x1e0/0x230)
>> [<c0088bd4>] (note_interrupt+0x1e0/0x230) from [<c0086e48>] (handle_irq_event_percpu+0xb0/0x1a0)
>> [<c0086e48>] (handle_irq_event_percpu+0xb0/0x1a0) from [<c0086f74>] (handle_irq_event+0x3c/0x5c)
>> [<c0086f74>] (handle_irq_event+0x3c/0x5c) from [<c00895a0>] (handle_level_irq+0x90/0xfc)
>> [<c00895a0>] (handle_level_irq+0x90/0xfc) from [<c008699c>] (generic_handle_irq+0x38/0x40)
>> [<c008699c>] (generic_handle_irq+0x38/0x40) from [<c02635a0>] (gpio_irq_handler+0x1b0/0x20c)
>> [<c02635a0>] (gpio_irq_handler+0x1b0/0x20c) from [<c008699c>] (generic_handle_irq+0x38/0x40)
>> [<c008699c>] (generic_handle_irq+0x38/0x40) from [<c0015404>] (handle_IRQ+0x38/0x84)
>> [<c0015404>] (handle_IRQ+0x38/0x84) from [<c000865c>] (omap3_intc_handle_irq+0x48/0x4c)
>> [<c000865c>] (omap3_intc_handle_irq+0x48/0x4c) from [<c00140c4>] (__irq_svc+0x44/0x78)
>> Exception stack(0xcf02de20 to 0xcf02de68)
>> de20: cf02c018 cf02c000 00000000 cf02de58 60000013 c06739fc 00000143 c06739fc
>> de40: 60000013 00000508 c06739dc 00000000 00022d69 cf02de68 cf02b3c0 c04890fc
>> de60: 20000013 ffffffff
>> [<c00140c4>] (__irq_svc+0x44/0x78) from [<c04890fc>] (_raw_spin_unlock_irqrestore+0x64/0x68)
>> [<c04890fc>] (_raw_spin_unlock_irqrestore+0x64/0x68) from [<c0087d50>] (__setup_irq+0x1b4/0x3d4)
>> [<c0087d50>] (__setup_irq+0x1b4/0x3d4) from [<c00881a0>] (request_threaded_irq+0xdc/0x148)
>> [<c00881a0>] (request_threaded_irq+0xdc/0x148) from [<c0482954>] (smsc911x_drv_probe+0x350/0x528)
>> [<c0482954>] (smsc911x_drv_probe+0x350/0x528) from [<c02d5a8c>] (platform_drv_probe+0x18/0x1c)
>> [<c02d5a8c>] (platform_drv_probe+0x18/0x1c) from [<c02d4580>] (really_probe+0x64/0x160)
>> [<c02d4580>] (really_probe+0x64/0x160) from [<c02d46c4>] (driver_probe_device+0x48/0x60)
>> [<c02d46c4>] (driver_probe_device+0x48/0x60) from [<c02d4770>] (__driver_attach+0x94/0x98)
>> [<c02d4770>] (__driver_attach+0x94/0x98) from [<c02d2ffc>] (bus_for_each_dev+0x54/0x80)
>> [<c02d2ffc>] (bus_for_each_dev+0x54/0x80) from [<c02d3730>] (bus_add_driver+0xa8/0x2a4)
>> [<c02d3730>] (bus_add_driver+0xa8/0x2a4) from [<c02d4d6c>] (driver_register+0x78/0x184)
>> [<c02d4d6c>] (driver_register+0x78/0x184) from [<c0008758>] (do_one_initcall+0x34/0x184)
>> [<c0008758>] (do_one_initcall+0x34/0x184) from [<c0613248>] (do_basic_setup+0x34/0x40)
>> [<c0613248>] (do_basic_setup+0x34/0x40) from [<c06132b8>] (kernel_init+0x64/0xec)
>> [<c06132b8>] (kernel_init+0x64/0xec) from [<c00154cc>] (kernel_thread_exit+0x0/0x8)
>> handlers:
>> [<c032ea98>] smsc911x_irqhandler
>> Disabling IRQ #323
>>
>> I still haven't had a chance to look into this.
>> Does anyone have a clue?
> 
> ..care to see if you have OMAP_GPIO_IRQ entry for your board? If so, we're
> still waiting for the cleanup-fixes branch to get merged that changes
> things to use gpio_to_irq() instead.

Nope, no OMAP_GPIO_IRQ in the board code.
Also, the GPIO -> IRQ mapping for the smsc911x is done in gpmc-smsc911x.c
and it uses gpio_to_irq() already.


-- 
Regards,
Igor.

^ permalink raw reply

* Re: [REGRESSION][PATCH] bpf_jit drops the ball on indirect negative mem references
From: Matt Evans @ 2012-03-30 15:19 UTC (permalink / raw)
  To: Jan Seiffert
  Cc: <netdev@vger.kernel.org>, Eric Dumazet,
	<linux-kernel@vger.kernel.org>, David S. Miller
In-Reply-To: <4F75B828.3090705@googlemail.com>

Hi Jan,

On 30 Mar 2012, at 14:42, Jan Seiffert <kaffeemonster@googlemail.com> wrote:

> Eric Dumazet schrieb:
>> [snip]
>> All these ".p2align 1" are noise for this patch.
>> 
>> This should be done as separate patch, explaining the rationale.
>> 
>> ...
> Ok, i thought since you where concerned with the performance and
> I'm touching this stuff anyway.
> But you are right, can be done separately.
> So gone.
> 
>> [snip]
>> 
>> Please add the code for imm8 offsets as well ?
>> 
>> if (is_imm8(K))
>>    EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx),%esi */
>> else
>>    EMIT2_off32(0x8d, 0xb3, K); /* lea imm32(%rbx),%esi */
> 
> Right, there is this imm8 form. I left it out because i never saw gas emit it
> and totally forgot about it.
> Your wish is my command. But since there is no EMIT2_off32 and introducing
> it would mean additional cleanup noise, i stayed with two emits.
> 
> Do you know where i can ping the powerpc guys a little bit harder?

No need (unless you mean a different guy), I have enough guilt as it is! :) (Sorry for no response, am moving house and am netless.) I skimmed your patches on my phone but hope to be in a state to review/test over the weekend or early next week. :)


Cheers,

Matt


> 
> So here a v3 of the patch:
> 
> Consider the following test program:
> 
> #include <stdio.h>
> #include <sys/types.h>
> #include <sys/socket.h>
> #include <netinet/in.h>
> #include <pcap-bpf.h>
> 
> #define die(x) do {perror(x); return 1;} while (0)
> struct bpf_insn udp_filter[] = {
>    /*   0 */ BPF_STMT(BPF_LDX|BPF_W|BPF_IMM, -1048576+(0)), /* leax    net[0] */
>    /*   1 */ BPF_STMT(BPF_LD|BPF_B|BPF_IND, 0),             /* ldb    [x+0] */
>    /*   2 */ BPF_STMT(BPF_RET|BPF_A, 0),                    /* ret    a */
> };
> 
> int main(int argc, char *argv[])
> {
>    char buf[512];
>    struct sockaddr_in addr;
>    struct bpf_program prg;
>    socklen_t addr_s;
>    ssize_t res;
>    int fd;
> 
>    addr.sin_family = AF_INET;
>    addr.sin_port = htons(5000);
>    addr.sin_addr.s_addr = 0;
>    addr_s = sizeof(addr);
>    prg.bf_len = sizeof(udp_filter)/sizeof(udp_filter[0]);
>    prg.bf_insns = udp_filter;
>    if(-1 == (fd = socket(AF_INET, SOCK_DGRAM, 0)))
>        die("socket");
>    if(-1 == bind(fd, (struct sockaddr *)&addr, sizeof(addr)))
>        die("bind");
>    if(-1 == setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prg, sizeof(prg)))
>        die("setsockopt");
>    res = recvfrom(fd, buf, sizeof(buf), 0, (struct sockaddr *)&addr, &addr_s);
>    if(res != -1)
>        printf("packet received: %zi bytes\n", res);
>    else
>        die("recvfrom");
>    return 0;
> }
> 
> when used with the bpf jit disabled works:
> console 1 $ ./bpf
> console 2 $ echo "hello" | nc -u localhost 5000
> console 1: packet received: 6 bytes
> 
> When the bpf jit gets enabled (echo 100 >
> /proc/sys/net/core/bpf_jit_enable) the same program stops working:
> console 1 $ ./bpf
> console 2 $ echo "hello" | nc -u localhost 5000
> console 1:
> 
> The reason is that both jits (x86 and powerpc) do not handle negative
> memory references like SKF_NET_OFF or SKF_LL_OFF, only the simple
> ancillary data references are supported (by mapping to special
> instructions).
> In the case of an absolute reference, the jit aborts the translation
> if a negative reference is seen, also a negative k on the indirect
> load aborts the translation, but if X is negative to begin with, only
> the error handler is reached at runtime which drops the whole packet.
> 
> I propose the following patch to fix this situation.
> Lightly tested on x86, but the powerpc asm part is prop. wrong.
> 
> Signed-of-by: Jan Seiffert <kaffeemonster@googlemail.com>
> 
> diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
> index af1ab5e..e9b57b3 100644
> --- a/arch/powerpc/net/bpf_jit.h
> +++ b/arch/powerpc/net/bpf_jit.h
> @@ -49,6 +49,10 @@
>  * Assembly helpers from arch/powerpc/net/bpf_jit.S:
>  */
> extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
> +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[];
> 
> #define FUNCTION_DESCR_SIZE    24
> 
> diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
> index ff4506e..e590aa5 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 +137,85 @@ 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 73619d3..2dc8b14 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;
> 
> diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
> index 6687022..2897d7f 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 +134,68 @@ 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 5671752..39a2e2c 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];
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 5dea452..04ca613 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -41,7 +41,7 @@
> #include <linux/ratelimit.h>
> 
> /* No hurry in this branch */
> -static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
> +void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
> {
>    u8 *ptr = NULL;
> 
> @@ -54,13 +54,14 @@ static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
>        return ptr;
>    return NULL;
> }
> +EXPORT_SYMBOL(bpf_internal_load_pointer_neg_helper);
> 
> static inline void *load_pointer(const struct sk_buff *skb, int k,
>                 unsigned int size, void *buffer)
> {
>    if (k >= 0)
>        return skb_header_pointer(skb, k, size, buffer);
> -    return __load_pointer(skb, k, size);
> +    return bpf_internal_load_pointer_neg_helper(skb, k, size);
> }
> 
> /**
> 

^ permalink raw reply

* Re: [PATCH net V4 2/2] igb: offer a PTP Hardware Clock instead of the timecompare method
From: chetan loke @ 2012-03-30 15:17 UTC (permalink / raw)
  To: Keller, Jacob E
  Cc: Richard Cochran, netdev@vger.kernel.org,
	e1000-devel@lists.sourceforge.net, Kirsher, Jeffrey T,
	Ronciak, John, john.stultz@linaro.org, tglx@linutronix.de
In-Reply-To: <02874ECE860811409154E81DA85FBB580DD9C8@ORSMSX105.amr.corp.intel.com>

On Thu, Mar 29, 2012 at 7:08 PM, Keller, Jacob E
<jacob.e.keller@intel.com> wrote:

>
> I performed this test on my machine. Even with a buggy app that calls clock_gettime
> inside a while loop, this does not produce any contention whatsoever with
> time stamping. I checked the timestamps returned also, and it appears to be running
> more than 20k times a second.
>

Great. Thanks for running the tests. I'm all set.

Intel/Richard - thanks for being patient.

Chetan

^ permalink raw reply

* Re: [REGRESSION][PATCH] bpf_jit drops the ball on indirect negative mem references
From: Josh Boyer @ 2012-03-30 14:11 UTC (permalink / raw)
  To: Eric Dumazet
  Cc: Jan Seiffert, netdev, linux-kernel, David S. Miller, Matt Evans
In-Reply-To: <1333116493.2325.2125.camel@edumazet-glaptop>

On Fri, Mar 30, 2012 at 10:08 AM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> On Fri, 2012-03-30 at 15:42 +0200, Jan Seiffert wrote:
>
>> Do you know where i can ping the powerpc guys a little bit harder?
>
> maybe using CC linux-arch@vger.kernel.org

Or linuxppc-dev@lists.ozlabs.org

josh

^ permalink raw reply

* Re: [REGRESSION][PATCH] bpf_jit drops the ball on indirect negative mem references
From: Eric Dumazet @ 2012-03-30 14:08 UTC (permalink / raw)
  To: Jan Seiffert; +Cc: netdev, linux-kernel, David S. Miller, Matt Evans
In-Reply-To: <4F75B828.3090705@googlemail.com>

On Fri, 2012-03-30 at 15:42 +0200, Jan Seiffert wrote:

> Do you know where i can ping the powerpc guys a little bit harder?

maybe using CC linux-arch@vger.kernel.org

One way to handle that would be to split this patch in 3 parts, so that
I can Ack the non ppc part.

[1] introduce bpf_internal_load_pointer_neg_helper()
	[BTW no need to EXPORT_SYMBOL it, since jit is not a module ]

[2] x86_bpf_iit: handle negative offsets in loads

[3] ppc_bpf_jit: handle negative offsets in loads

^ permalink raw reply

* Re: [REGRESSION][PATCH] bpf_jit drops the ball on indirect negative mem references
From: Jan Seiffert @ 2012-03-30 13:42 UTC (permalink / raw)
  To: netdev; +Cc: Eric Dumazet, linux-kernel, David S. Miller, Matt Evans
In-Reply-To: <1333098711.19659.9.camel@edumazet-laptop>

Eric Dumazet schrieb:
> [snip]
> All these ".p2align 1" are noise for this patch.
>
> This should be done as separate patch, explaining the rationale.
>
> ...
Ok, i thought since you where concerned with the performance and
I'm touching this stuff anyway.
But you are right, can be done separately.
So gone.

> [snip]
>
> Please add the code for imm8 offsets as well ?
>
> if (is_imm8(K))
> 	EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx),%esi */
> else
> 	EMIT2_off32(0x8d, 0xb3, K); /* lea imm32(%rbx),%esi */

Right, there is this imm8 form. I left it out because i never saw gas emit it
and totally forgot about it.
Your wish is my command. But since there is no EMIT2_off32 and introducing
it would mean additional cleanup noise, i stayed with two emits.

Do you know where i can ping the powerpc guys a little bit harder?

So here a v3 of the patch:

Consider the following test program:

#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <pcap-bpf.h>

#define die(x) do {perror(x); return 1;} while (0)
struct bpf_insn udp_filter[] = {
	/*   0 */ BPF_STMT(BPF_LDX|BPF_W|BPF_IMM, -1048576+(0)), /* leax	net[0] */
	/*   1 */ BPF_STMT(BPF_LD|BPF_B|BPF_IND, 0),             /* ldb	[x+0] */
	/*   2 */ BPF_STMT(BPF_RET|BPF_A, 0),                    /* ret	a */
};

int main(int argc, char *argv[])
{
	char buf[512];
	struct sockaddr_in addr;
	struct bpf_program prg;
	socklen_t addr_s;
	ssize_t res;
	int fd;

	addr.sin_family = AF_INET;
	addr.sin_port = htons(5000);
	addr.sin_addr.s_addr = 0;
	addr_s = sizeof(addr);
	prg.bf_len = sizeof(udp_filter)/sizeof(udp_filter[0]);
	prg.bf_insns = udp_filter;
	if(-1 == (fd = socket(AF_INET, SOCK_DGRAM, 0)))
		die("socket");
	if(-1 == bind(fd, (struct sockaddr *)&addr, sizeof(addr)))
		die("bind");
	if(-1 == setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prg, sizeof(prg)))
		die("setsockopt");
	res = recvfrom(fd, buf, sizeof(buf), 0, (struct sockaddr *)&addr, &addr_s);
	if(res != -1)
		printf("packet received: %zi bytes\n", res);
	else
		die("recvfrom");
	return 0;
}

when used with the bpf jit disabled works:
console 1 $ ./bpf
console 2 $ echo "hello" | nc -u localhost 5000
console 1: packet received: 6 bytes

When the bpf jit gets enabled (echo 100 >
/proc/sys/net/core/bpf_jit_enable) the same program stops working:
console 1 $ ./bpf
console 2 $ echo "hello" | nc -u localhost 5000
console 1:

The reason is that both jits (x86 and powerpc) do not handle negative
memory references like SKF_NET_OFF or SKF_LL_OFF, only the simple
ancillary data references are supported (by mapping to special
instructions).
In the case of an absolute reference, the jit aborts the translation
if a negative reference is seen, also a negative k on the indirect
load aborts the translation, but if X is negative to begin with, only
the error handler is reached at runtime which drops the whole packet.

I propose the following patch to fix this situation.
Lightly tested on x86, but the powerpc asm part is prop. wrong.

Signed-of-by: Jan Seiffert <kaffeemonster@googlemail.com>

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index af1ab5e..e9b57b3 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -49,6 +49,10 @@
  * Assembly helpers from arch/powerpc/net/bpf_jit.S:
  */
 extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
+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[];
 
 #define FUNCTION_DESCR_SIZE	24
 
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index ff4506e..e590aa5 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 +137,85 @@ 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 73619d3..2dc8b14 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;
 
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 6687022..2897d7f 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 +134,68 @@ 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 5671752..39a2e2c 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];
diff --git a/net/core/filter.c b/net/core/filter.c
index 5dea452..04ca613 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -41,7 +41,7 @@
 #include <linux/ratelimit.h>
 
 /* No hurry in this branch */
-static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
+void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
 {
 	u8 *ptr = NULL;
 
@@ -54,13 +54,14 @@ static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
 		return ptr;
 	return NULL;
 }
+EXPORT_SYMBOL(bpf_internal_load_pointer_neg_helper);
 
 static inline void *load_pointer(const struct sk_buff *skb, int k,
 				 unsigned int size, void *buffer)
 {
 	if (k >= 0)
 		return skb_header_pointer(skb, k, size, buffer);
-	return __load_pointer(skb, k, size);
+	return bpf_internal_load_pointer_neg_helper(skb, k, size);
 }
 
 /**

^ permalink raw reply related

* sendmmsg: put_user vs __put_user
From: Ulrich Drepper @ 2012-03-30 13:36 UTC (permalink / raw)
  To: David S. Miller, netdev, Linux Kernel Mailing List

Shouldn't the compat code in the sendmmsg implementation use the same
code as the normal code?  In which case you probably want something
like this:

diff --git a/net/socket.c b/net/socket.c
index 484cc69..ff40409 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2064,7 +2064,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user
*mmsg, unsigned int vlen,
                                            &msg_sys, flags, &used_address);
                        if (err < 0)
                                break;
-                       err = __put_user(err, &compat_entry->msg_len);
+                       err = put_user(err, &compat_entry->msg_len);
                        ++compat_entry;
                } else {
                        err = __sys_sendmsg(sock, (struct msghdr __user *)entry,

^ permalink raw reply related

* TCP_MAXSEG option with TSO enabled
From: Daniel Baluta @ 2012-03-30 11:33 UTC (permalink / raw)
  To: netdev

Hello,

I am using TCP_MAXSEG option on an interface which has TSO enabled.

strace output for connection looks as follows:

socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 26
setsockopt(26, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
setsockopt(26, SOL_TCP, TCP_NODELAY, [1], 4) = 0
setsockopt(26, SOL_TCP, TCP_MAXSEG, [300], 4) = 0
connect(26, {sa_family=AF_INET, sin_port=htons(1935),
sin_addr=inet_addr("10.10.0.1")}, 16) = -1 EINPROGRESS (Operation now
in progress)

I can see that MSS (300) is advertised in SYN packet, anyhow capturing
the traffic
I notice that are some TCP segments with length greater than MSS.

Is this normal taking in consideration that TSO is enabled?

thanks,
Daniel.

^ permalink raw reply

* [PATCH] rionet: fix page allocation order of rionet_active
From: Akinobu Mita @ 2012-03-30 11:01 UTC (permalink / raw)
  To: netdev; +Cc: Akinobu Mita, Matt Porter, Alexandre Bounine

rionet_active is allocated from the page allocator and the allocation
order is calculated on the assumption that the page size is 4KB, so it
wastes memory on more than 4K page systems.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: netdev@vger.kernel.org
---
 drivers/net/rionet.c |   11 ++++++-----
 1 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index a57f057..91d2588 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -375,8 +375,8 @@ static void rionet_remove(struct rio_dev *rdev)
 	struct net_device *ndev = rio_get_drvdata(rdev);
 	struct rionet_peer *peer, *tmp;
 
-	free_pages((unsigned long)rionet_active, rdev->net->hport->sys_size ?
-					__fls(sizeof(void *)) + 4 : 0);
+	free_pages((unsigned long)rionet_active, get_order(sizeof(void *) *
+			RIO_MAX_ROUTE_ENTRIES(rdev->net->hport->sys_size)));
 	unregister_netdev(ndev);
 	free_netdev(ndev);
 
@@ -432,15 +432,16 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev)
 	int rc = 0;
 	struct rionet_private *rnet;
 	u16 device_id;
+	const size_t rionet_active_bytes = sizeof(void *) *
+				RIO_MAX_ROUTE_ENTRIES(mport->sys_size);
 
 	rionet_active = (struct rio_dev **)__get_free_pages(GFP_KERNEL,
-			mport->sys_size ? __fls(sizeof(void *)) + 4 : 0);
+			get_order(rionet_active_bytes));
 	if (!rionet_active) {
 		rc = -ENOMEM;
 		goto out;
 	}
-	memset((void *)rionet_active, 0, sizeof(void *) *
-				RIO_MAX_ROUTE_ENTRIES(mport->sys_size));
+	memset((void *)rionet_active, 0, rionet_active_bytes);
 
 	/* Set up private area */
 	rnet = netdev_priv(ndev);
-- 
1.7.4.4

^ permalink raw reply related

* [PATCH] usb/rtl8150 : Remove duplicated definitions
From: Huajun Li @ 2012-03-30 10:11 UTC (permalink / raw)
  To: David Miller; +Cc: petkan, netdev, Huajun Li

There exist duplicated macro definitions in rtl8150.c, remove them.

Signed-off-by: Huajun Li <huajun.li.lee@gmail.com>
---
 drivers/net/usb/rtl8150.c |   26 --------------------------
 1 files changed, 0 insertions(+), 26 deletions(-)

diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 6dda2fe..d363b31 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -85,32 +85,6 @@
 #define INT_CRERR_CNT		0x06
 #define INT_COL_CNT		0x07

-/* Transmit status register errors */
-#define TSR_ECOL		(1<<5)
-#define TSR_LCOL		(1<<4)
-#define TSR_LOSS_CRS		(1<<3)
-#define TSR_JBR			(1<<2)
-#define TSR_ERRORS		(TSR_ECOL | TSR_LCOL | TSR_LOSS_CRS | TSR_JBR)
-/* Receive status register errors */
-#define RSR_CRC			(1<<2)
-#define RSR_FAE			(1<<1)
-#define RSR_ERRORS		(RSR_CRC | RSR_FAE)
-
-/* Media status register definitions */
-#define MSR_DUPLEX		(1<<4)
-#define MSR_SPEED		(1<<3)
-#define MSR_LINK		(1<<2)
-
-/* Interrupt pipe data */
-#define INT_TSR			0x00
-#define INT_RSR			0x01
-#define INT_MSR			0x02
-#define INT_WAKSR		0x03
-#define INT_TXOK_CNT		0x04
-#define INT_RXLOST_CNT		0x05
-#define INT_CRERR_CNT		0x06
-#define INT_COL_CNT		0x07
-

 #define	RTL8150_MTU		1540
 #define	RTL8150_TX_TIMEOUT	(HZ)
-- 
1.7.4.1

^ permalink raw reply related

* Re: [PATCH 00/17] mark const init data with __initconst instead of __initdata
From: Uwe Kleine-König @ 2012-03-30  9:59 UTC (permalink / raw)
  To: linux-kernel, Andrew Morton
  Cc: Alexey Dobriyan, Anatolij Gustschin, Andreas Koensgen,
	Andrew Lunn, Andrew Victor, Arnd Bergmann, Barry Song,
	Benjamin Herrenschmidt, Bryan Huntsman, cbe-oss-dev,
	Christoph Lameter, Daniel Walker, David Brown, David Howells,
	David S. Miller, David Woodhouse, davinci-linux-open-source,
	Eric Miao, Fenghua Yu, Grant Likely <gran
In-Reply-To: <20120329211131.GA31250@pengutronix.de>

On Thu, Mar 29, 2012 at 11:11:31PM +0200, Uwe Kleine-König wrote:
> Hello,
> 
> this series fixes a common error to use __initdata to mark const
> variables. Most of the time this works well enough to go unnoticed
> (though I wonder why the linker doesn't warn about that).
> Just try adding something like
> 
> 	int something __initdata;
> 
> to one of the patched files and compile to see the error.
> 
> While touching these annotations I also corrected the position where it
> was wrong to go between the variable name and the =.
> 
> Note this series is not compile tested.
After a question by Shawn Guo I noticed that my command to do the changes
was to lax and changed things that must not be changed (at least not
with further care). Affected are lines like:

	static const char *at91_dt_board_compat[] __initconst = {

While at91_dt_board_compat[0] is const, at91_dt_board_compat is not.

I will send a fixed series later today.

Best regards
Uwe

-- 
Pengutronix e.K.                           | Uwe Kleine-König            |
Industrial Linux Solutions                 | http://www.pengutronix.de/  |

^ permalink raw reply

* Re: [PATCH v5 2/2] Ethernet driver for the WIZnet W5100 chip
From: Eric Dumazet @ 2012-03-30  9:23 UTC (permalink / raw)
  To: Mike Sinkovsky; +Cc: netdev, linux-kernel
In-Reply-To: <1333090806-27988-2-git-send-email-msink@permonline.ru>

Le vendredi 30 mars 2012 à 13:00 +0600, Mike Sinkovsky a écrit :
> Tested and used in production with Blackfin BF531 embedded processor.
> 
> Signed-off-by: Mike Sinkovsky <msink@permonline.ru>
> ---

> +
> +static int w5100_start_tx(struct sk_buff *skb, struct net_device *ndev)
> +{
> +	struct w5100_priv *priv = netdev_priv(ndev);
> +	u16 offset;
> +
> +	if (w5100_read16(priv, W5100_S0_TX_FSR) < skb->len) {

There is a race here.

Interrupt came come right here before you set the stop_queue()


> +		netif_stop_queue(ndev);

So Here I suggest adding a test again
	
	if (w5100_read16(priv, W5100_S0_TX_FSR) >= skb->len)
		netif_wake_queue(ndev);
	else
		return NETDEV_TX_BUSY;

> +		return NETDEV_TX_BUSY;
> +	}
> +
> +	offset = w5100_read16(priv, W5100_S0_TX_WR);
> +	w5100_writebuf(priv, offset, skb->data, skb->len);
> +	w5100_write16(priv, W5100_S0_TX_WR, offset + skb->len);
> +	w5100_command(priv, S0_CR_SEND);
> +	ndev->stats.tx_bytes += skb->len;
> +	ndev->stats.tx_packets++;
> +	dev_kfree_skb(skb);
> +
> +	return NETDEV_TX_OK;
> +}
> +

^ permalink raw reply

* Re: [REGRESSION][PATCH] bpf_jit drops the ball on indirect negative mem references
From: Eric Dumazet @ 2012-03-30  9:11 UTC (permalink / raw)
  To: Jan Seiffert; +Cc: netdev, linux-kernel, David S. Miller, Matt Evans
In-Reply-To: <4F744D58.3070009@googlemail.com>

Le jeudi 29 mars 2012 à 13:54 +0200, Jan Seiffert a écrit :

> 
> +	.p2align 1
>  bpf_slow_path_word:
>  	bpf_slow_path_common(4)
>  	js	bpf_error
> @@ -115,6 +116,7 @@ bpf_slow_path_word:
>  	bswap	%eax
>  	ret
>  
> +	.p2align 1
>  bpf_slow_path_half:
>  	bpf_slow_path_common(2)
>  	js	bpf_error
> @@ -123,12 +125,14 @@ bpf_slow_path_half:
>  	movzwl	%ax,%eax
>  	ret

All these ".p2align 1" are noise for this patch.

This should be done as separate patch, explaining the rationale.

...

>  			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) {
> +					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;


Please add the code for imm8 offsets as well ?

if (is_imm8(K))
	EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx),%esi */
else
	EMIT2_off32(0x8d, 0xb3, K); /* lea imm32(%rbx),%esi */

Thanks

^ permalink raw reply

* Re: [PATCH net-next v3 5/5] r8169: support RTL8411
From: Francois Romieu @ 2012-03-30  7:25 UTC (permalink / raw)
  To: Hayes Wang; +Cc: netdev, linux-kernel
In-Reply-To: <1333090086-1815-1-git-send-email-hayeswang@realtek.com>

Hayes Wang <hayeswang@realtek.com> :
> Support the new chip RTL8411.
> 
> Signed-off-by: Hayes Wang <hayeswang@realtek.com>

I do not see any change related to rtl_init_jumbo_ops. If NULL is ok for
jumbo_{enable / disable}, it deserves to be outlined in the commit
message.

No reviewer can figure what's going on otherwise.

-- 
Ueimor

^ permalink raw reply

* [PATCH v5 1/2] Ethernet driver for the WIZnet W5300 chip
From: Mike Sinkovsky @ 2012-03-30  7:00 UTC (permalink / raw)
  To: netdev, linux-kernel; +Cc: Mike Sinkovsky
In-Reply-To: <1332752876-1650-1-git-send-email-msink@permonline.ru>

Based on original driver from chip manufacturer, but nearly full rewite.

Tested and used in production with Blackfin BF531 embedded processor.

Signed-off-by: Mike Sinkovsky <msink@permonline.ru>
---
v5:
 - disabled VLAN (NETIF_F_VLAN_CHALLENGED)
v4:
 - netif_stop_queue if tx fifo is full, netif_wake_queue in interrupt
 - use netif_info macro
v3:
 - reading macaddr from platform_data
 - ethtool: get_link, get_msglevel, set_msglevel
 - more cleanups
v2:
 - corrected handling of NET_ADDR_RANDOM flag
 - support for WIZNET_BUS_ANY mode
 - link detection using gpio
 - registers read using ethtool
 - more cleanups
---
 drivers/net/ethernet/Kconfig         |    1 +
 drivers/net/ethernet/Makefile        |    1 +
 drivers/net/ethernet/wiznet/Kconfig  |   61 +++
 drivers/net/ethernet/wiznet/Makefile |    1 +
 drivers/net/ethernet/wiznet/w5300.c  |  714 ++++++++++++++++++++++++++++++++++
 include/linux/platform_data/wiznet.h |   23 ++
 6 files changed, 801 insertions(+), 0 deletions(-)
 create mode 100644 drivers/net/ethernet/wiznet/Kconfig
 create mode 100644 drivers/net/ethernet/wiznet/Makefile
 create mode 100644 drivers/net/ethernet/wiznet/w5300.c
 create mode 100644 include/linux/platform_data/wiznet.h

diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index c63a64c..a11af5c 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -174,6 +174,7 @@ source "drivers/net/ethernet/tile/Kconfig"
 source "drivers/net/ethernet/toshiba/Kconfig"
 source "drivers/net/ethernet/tundra/Kconfig"
 source "drivers/net/ethernet/via/Kconfig"
+source "drivers/net/ethernet/wiznet/Kconfig"
 source "drivers/net/ethernet/xilinx/Kconfig"
 source "drivers/net/ethernet/xircom/Kconfig"
 
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 9676a51..878ad32 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -73,5 +73,6 @@ obj-$(CONFIG_TILE_NET) += tile/
 obj-$(CONFIG_NET_VENDOR_TOSHIBA) += toshiba/
 obj-$(CONFIG_NET_VENDOR_TUNDRA) += tundra/
 obj-$(CONFIG_NET_VENDOR_VIA) += via/
+obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/
 obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/
 obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/
diff --git a/drivers/net/ethernet/wiznet/Kconfig b/drivers/net/ethernet/wiznet/Kconfig
new file mode 100644
index 0000000..7ca5c95
--- /dev/null
+++ b/drivers/net/ethernet/wiznet/Kconfig
@@ -0,0 +1,61 @@
+#
+# WIZnet device configuration
+#
+
+config NET_VENDOR_WIZNET
+	bool "WIZnet devices"
+	default y
+	---help---
+	  If you have a network (Ethernet) card belonging to this class, say Y
+	  and read the Ethernet-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about WIZnet devices. If you say Y, you will be asked
+	  for your specific card in the following questions.
+
+if NET_VENDOR_WIZNET
+
+config WIZNET_W5300
+	tristate "WIZnet W5300 Ethernet support"
+	depends on ARM || BLACKFIN
+	---help---
+	  Support for WIZnet W5300 chips.
+
+	  W5300 is a single chip with integrated 10/100 Ethernet MAC,
+	  PHY and hardware TCP/IP stack, but this driver is limited to
+	  the MAC and PHY functions only, onchip TCP/IP is unused.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called w5300.
+
+choice
+	prompt "WIZnet interface mode"
+	depends on NET_VENDOR_WIZNET
+	default WIZNET_BUS_ANY
+
+config WIZNET_BUS_DIRECT
+	bool "Direct address bus mode"
+	---help---
+	  In direct address mode host system can directly access W5300 registers
+	  after mapping to Memory-mapped I/O Space.
+	  0x400 bytes are required for memory space.
+
+config WIZNET_BUS_INDIRECT
+	bool "Indirect address bus mode"
+	---help---
+	  In indirect address mode host system indirectly accesses registers by
+	  using Indirect Mode Address Register (IDM_AR) and Indirect Mode Data
+	  Register (IDM_DR), which are directly mapped to Memory-mapped I/O Space.
+	  Only 0x06 bytes are required for memory space.
+
+config WIZNET_BUS_ANY
+	bool "Select interface mode in runtime"
+	---help---
+	  If interface mode is unknown in compile time, you can selectied it
+	  in runtime.
+	  Performance may decrease compared to explicitly selected bus mode.
+endchoice
+
+endif # NET_VENDOR_WIZNET
diff --git a/drivers/net/ethernet/wiznet/Makefile b/drivers/net/ethernet/wiznet/Makefile
new file mode 100644
index 0000000..88e0a3e
--- /dev/null
+++ b/drivers/net/ethernet/wiznet/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_WIZNET_W5300) += w5300.o
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
new file mode 100644
index 0000000..8059aa9
--- /dev/null
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -0,0 +1,714 @@
+/*
+ * Ethernet driver for the WIZnet W5300 chip.
+ *
+ * Copyright (C) 2008-2009 WIZnet Co.,Ltd.
+ * Copyright (C) 2011 Taehun Kim <kth3321 <at> gmail.com>
+ * Copyright (C) 2012 Mike Sinkovsky <msink@permonline.ru>
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/wiznet.h>
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/gpio.h>
+
+#define DRV_NAME	"WIZnet W5300"
+#define DRV_VERSION	"2012-03-28"
+
+MODULE_DESCRIPTION(DRV_NAME" Ethernet driver v"DRV_VERSION);
+MODULE_AUTHOR("Mike Sinkovsky <msink@permonline.ru>");
+MODULE_ALIAS("platform:"KBUILD_MODNAME);
+MODULE_LICENSE("GPL");
+
+/*
+ * Registers
+ */
+#define W5300_MR		0x0000	/* Mode Register */
+#define   MR_DBW		  (1 << 15) /* Data bus width */
+#define   MR_MPF		  (1 << 14) /* Mac layer pause frame */
+#define   MR_WDF(n)		  (((n)&7)<<11) /* Write data fetch time */
+#define   MR_RDH		  (1 << 10) /* Read data hold time */
+#define   MR_FS			  (1 << 8)  /* FIFO swap */
+#define   MR_RST		  (1 << 7)  /* S/W reset */
+#define   MR_PB			  (1 << 4)  /* Ping block */
+#define   MR_DBS		  (1 << 2)  /* Data bus swap */
+#define   MR_IND		  (1 << 0)  /* Indirect mode */
+#define W5300_IR		0x0002	/* Interrupt Register */
+#define W5300_IMR		0x0004	/* Interrupt Mask Register */
+#define   IR_S0			  0x0001  /* S0 interrupt */
+#define W5300_SHARL		0x0008	/* Source MAC address (0123) */
+#define W5300_SHARH		0x000c	/* Source MAC address (45) */
+#define W5300_TMSRL		0x0020	/* Transmit Memory Size (0123) */
+#define W5300_TMSRH		0x0024	/* Transmit Memory Size (4567) */
+#define W5300_RMSRL		0x0028	/* Receive Memory Size (0123) */
+#define W5300_RMSRH		0x002c	/* Receive Memory Size (4567) */
+#define W5300_MTYPE		0x0030	/* Memory Type */
+#define W5300_IDR		0x00fe	/* Chip ID register */
+#define   IDR_W5300		  0x5300  /* =0x5300 for WIZnet W5300 */
+#define W5300_S0_MR		0x0200	/* S0 Mode Register */
+#define   S0_MR_CLOSED		  0x0000  /* Close mode */
+#define   S0_MR_MACRAW		  0x0004  /* MAC RAW mode (promiscous) */
+#define   S0_MR_MACRAW_MF	  0x0044  /* MAC RAW mode (filtered) */
+#define W5300_S0_CR		0x0202	/* S0 Command Register */
+#define   S0_CR_OPEN		  0x0001  /* OPEN command */
+#define   S0_CR_CLOSE		  0x0010  /* CLOSE command */
+#define   S0_CR_SEND		  0x0020  /* SEND command */
+#define   S0_CR_RECV		  0x0040  /* RECV command */
+#define W5300_S0_IMR		0x0204	/* S0 Interrupt Mask Register */
+#define W5300_S0_IR		0x0206	/* S0 Interrupt Register */
+#define   S0_IR_RECV		  0x0004  /* Receive interrupt */
+#define   S0_IR_SENDOK		  0x0010  /* Send OK interrupt */
+#define W5300_S0_SSR		0x0208	/* S0 Socket Status Register */
+#define W5300_S0_TX_WRSR	0x0220	/* S0 TX Write Size Register */
+#define W5300_S0_TX_FSR		0x0224	/* S0 TX Free Size Register */
+#define W5300_S0_RX_RSR		0x0228	/* S0 Received data Size */
+#define W5300_S0_TX_FIFO	0x022e	/* S0 Transmit FIFO */
+#define W5300_S0_RX_FIFO	0x0230	/* S0 Receive FIFO */
+#define W5300_REGS_LEN		0x0400
+
+/*
+ * Device driver private data structure
+ */
+struct w5300_priv {
+	void __iomem *base;
+	bool indirect;
+	spinlock_t reg_lock;
+	u16  (*read) (struct w5300_priv *priv, u16 addr);
+	void (*write)(struct w5300_priv *priv, u16 addr, u16 data);
+	int irq;
+	int link_irq;
+	int link_gpio;
+
+	struct napi_struct napi;
+	struct net_device *ndev;
+	bool promisc;
+	u32 msg_enable;
+};
+
+/************************************************************************
+ *
+ *  Lowlevel I/O functions
+ *
+ ***********************************************************************/
+
+/*
+ * In direct address mode host system can directly access W5300 registers
+ * after mapping to Memory-Mapped I/O space.
+ *
+ * 0x400 bytes are required for memory space.
+ */
+static inline u16 w5300_read_direct(struct w5300_priv *priv, u16 addr)
+{
+	return ioread16(priv->base + (addr << CONFIG_WIZNET_BUS_SHIFT));
+}
+
+static inline void w5300_write_direct(struct w5300_priv *priv,
+				      u16 addr, u16 data)
+{
+	iowrite16(data, priv->base + (addr << CONFIG_WIZNET_BUS_SHIFT));
+}
+
+/*
+ * In indirect address mode host system indirectly accesses registers by
+ * using Indirect Mode Address Register (IDM_AR) and Indirect Mode Data
+ * Register (IDM_DR), which are directly mapped to Memory-Mapped I/O space.
+ * Mode Register (MR) is directly accessible.
+ *
+ * Only 0x06 bytes are required for memory space.
+ */
+#define W5300_IDM_AR		0x0002	 /* Indirect Mode Address */
+#define W5300_IDM_DR		0x0004	 /* Indirect Mode Data */
+
+static u16 w5300_read_indirect(struct w5300_priv *priv, u16 addr)
+{
+	unsigned long flags;
+	u16 data;
+
+	spin_lock_irqsave(&priv->reg_lock, flags);
+	w5300_write_direct(priv, W5300_IDM_AR, addr);
+	mmiowb();
+	data = w5300_read_direct(priv, W5300_IDM_DR);
+	spin_unlock_irqrestore(&priv->reg_lock, flags);
+
+	return data;
+}
+
+static void w5300_write_indirect(struct w5300_priv *priv, u16 addr, u16 data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->reg_lock, flags);
+	w5300_write_direct(priv, W5300_IDM_AR, addr);
+	mmiowb();
+	w5300_write_direct(priv, W5300_IDM_DR, data);
+	mmiowb();
+	spin_unlock_irqrestore(&priv->reg_lock, flags);
+}
+
+#if defined(CONFIG_WIZNET_BUS_DIRECT)
+#define w5300_read	w5300_read_direct
+#define w5300_write	w5300_write_direct
+
+#elif defined(CONFIG_WIZNET_BUS_INDIRECT)
+#define w5300_read	w5300_read_indirect
+#define w5300_write	w5300_write_indirect
+
+#else /* CONFIG_WIZNET_BUS_ANY */
+#define w5300_read	priv->read
+#define w5300_write	priv->write
+#endif
+
+static u32 w5300_read32(struct w5300_priv *priv, u16 addr)
+{
+	u32 data;
+	data  = w5300_read(priv, addr) << 16;
+	data |= w5300_read(priv, addr + 2);
+	return data;
+}
+
+static void w5300_write32(struct w5300_priv *priv, u16 addr, u32 data)
+{
+	w5300_write(priv, addr, data >> 16);
+	w5300_write(priv, addr + 2, data);
+}
+
+static int w5300_command(struct w5300_priv *priv, u16 cmd)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(100);
+
+	w5300_write(priv, W5300_S0_CR, cmd);
+	mmiowb();
+
+	while (w5300_read(priv, W5300_S0_CR) != 0) {
+		if (time_after(jiffies, timeout))
+			return -EIO;
+		cpu_relax();
+	}
+
+	return 0;
+}
+
+static void w5300_read_frame(struct w5300_priv *priv, u8 *buf, int len)
+{
+	u16 fifo;
+	int i;
+
+	for (i = 0; i < len; i += 2) {
+		fifo = w5300_read(priv, W5300_S0_RX_FIFO);
+		*buf++ = fifo >> 8;
+		*buf++ = fifo;
+	}
+	fifo = w5300_read(priv, W5300_S0_RX_FIFO);
+	fifo = w5300_read(priv, W5300_S0_RX_FIFO);
+}
+
+static void w5300_write_frame(struct w5300_priv *priv, u8 *buf, int len)
+{
+	u16 fifo;
+	int i;
+
+	for (i = 0; i < len; i += 2) {
+		fifo  = *buf++ << 8;
+		fifo |= *buf++;
+		w5300_write(priv, W5300_S0_TX_FIFO, fifo);
+	}
+	w5300_write32(priv, W5300_S0_TX_WRSR, len);
+	mmiowb();
+	w5300_command(priv, S0_CR_SEND);
+}
+
+static void w5300_write_macaddr(struct w5300_priv *priv)
+{
+	struct net_device *ndev = priv->ndev;
+	w5300_write32(priv, W5300_SHARL,
+		      ndev->dev_addr[0] << 24 |
+		      ndev->dev_addr[1] << 16 |
+		      ndev->dev_addr[2] << 8 |
+		      ndev->dev_addr[3]);
+	w5300_write(priv, W5300_SHARH,
+		      ndev->dev_addr[4] << 8 |
+		      ndev->dev_addr[5]);
+	mmiowb();
+}
+
+static void w5300_hw_reset(struct w5300_priv *priv)
+{
+	w5300_write_direct(priv, W5300_MR, MR_RST);
+	mmiowb();
+	mdelay(5);
+	w5300_write_direct(priv, W5300_MR, priv->indirect ?
+				 MR_WDF(7) | MR_PB | MR_IND :
+				 MR_WDF(7) | MR_PB);
+	mmiowb();
+	w5300_write(priv, W5300_IMR, 0);
+	w5300_write_macaddr(priv);
+
+	/*
+	 * Configure 128K of internal memory
+	 * as 64K RX fifo and 64K TX fifo
+	 */
+	w5300_write32(priv, W5300_RMSRL, 64 << 24);
+	w5300_write32(priv, W5300_RMSRH, 0);
+	w5300_write32(priv, W5300_TMSRL, 64 << 24);
+	w5300_write32(priv, W5300_TMSRH, 0);
+	w5300_write(priv, W5300_MTYPE, 0x00ff);
+	mmiowb();
+}
+
+static void w5300_hw_start(struct w5300_priv *priv)
+{
+	w5300_write(priv, W5300_S0_MR, priv->promisc ?
+			  S0_MR_MACRAW : S0_MR_MACRAW_MF);
+	mmiowb();
+	w5300_command(priv, S0_CR_OPEN);
+	w5300_write(priv, W5300_S0_IMR, S0_IR_RECV);
+	w5300_write(priv, W5300_IMR, IR_S0);
+	mmiowb();
+}
+
+static void w5300_hw_close(struct w5300_priv *priv)
+{
+	w5300_write(priv, W5300_IMR, 0);
+	mmiowb();
+	w5300_command(priv, S0_CR_CLOSE);
+}
+
+/***********************************************************************
+ *
+ *   Device driver functions / callbacks
+ *
+ ***********************************************************************/
+
+static void w5300_get_drvinfo(struct net_device *ndev,
+			      struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, dev_name(ndev->dev.parent),
+		sizeof(info->bus_info));
+}
+
+static u32 w5300_get_link(struct net_device *ndev)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	if (priv->link_gpio < 0)
+		return 1;
+
+	return !!gpio_get_value(priv->link_gpio);
+}
+
+static u32 w5300_get_msglevel(struct net_device *ndev)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	return priv->msg_enable;
+}
+
+static void w5300_set_msglevel(struct net_device *ndev, u32 value)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	priv->msg_enable = value;
+}
+
+static int w5300_get_regs_len(struct net_device *ndev)
+{
+	return W5300_REGS_LEN;
+}
+
+static void w5300_get_regs(struct net_device *ndev,
+			   struct ethtool_regs *regs, void *_buf)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+	u8 *buf = _buf;
+	u16 addr;
+	u16 data;
+
+	regs->version = 1;
+	for (addr = 0; addr < W5300_REGS_LEN; addr += 2) {
+		switch (addr & 0x23f) {
+		case W5300_S0_TX_FIFO: /* cannot read TX_FIFO */
+		case W5300_S0_RX_FIFO: /* cannot read RX_FIFO */
+			data = 0xffff;
+			break;
+		default:
+			data = w5300_read(priv, addr);
+			break;
+		}
+		*buf++ = data >> 8;
+		*buf++ = data;
+	}
+}
+
+static void w5300_tx_timeout(struct net_device *ndev)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	w5300_hw_reset(priv);
+	w5300_hw_start(priv);
+	ndev->stats.tx_errors++;
+	ndev->trans_start = jiffies;
+	netif_wake_queue(ndev);
+}
+
+static int w5300_start_tx(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	if (unlikely(w5300_read32(priv, W5300_S0_TX_FSR) < skb->len)) {
+		netif_stop_queue(ndev);
+		w5300_write(priv, W5300_S0_IMR, S0_IR_RECV | S0_IR_SENDOK);
+		mmiowb();
+		return NETDEV_TX_BUSY;
+	}
+
+	w5300_write_frame(priv, skb->data, skb->len);
+	ndev->stats.tx_packets++;
+	ndev->stats.tx_bytes += skb->len;
+	dev_kfree_skb(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static int w5300_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct w5300_priv *priv = container_of(napi, struct w5300_priv, napi);
+	struct net_device *ndev = priv->ndev;
+	struct sk_buff *skb;
+	int rx_count;
+	u16 rx_len;
+
+	for (rx_count = 0; rx_count < budget; rx_count++) {
+		u32 rx_fifo_len = w5300_read32(priv, W5300_S0_RX_RSR);
+		if (rx_fifo_len == 0)
+			break;
+
+		rx_len = w5300_read(priv, W5300_S0_RX_FIFO);
+
+		skb = netdev_alloc_skb_ip_align(ndev, roundup(rx_len, 2));
+		if (unlikely(!skb)) {
+			u32 i;
+			for (i = 0; i < rx_fifo_len; i += 2)
+				w5300_read(priv, W5300_S0_RX_FIFO);
+			ndev->stats.rx_dropped++;
+			return -ENOMEM;
+		}
+
+		skb_put(skb, rx_len);
+		w5300_read_frame(priv, skb->data, rx_len);
+		skb->protocol = eth_type_trans(skb, ndev);
+
+		netif_receive_skb(skb);
+		ndev->stats.rx_packets++;
+		ndev->stats.rx_bytes += rx_len;
+	}
+
+	if (rx_count < budget) {
+		w5300_write(priv, W5300_IMR, IR_S0);
+		mmiowb();
+		napi_complete(napi);
+	}
+
+	return rx_count;
+}
+
+static irqreturn_t w5300_interrupt(int irq, void *ndev_instance)
+{
+	struct net_device *ndev = ndev_instance;
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	w5300_write(priv, W5300_S0_IR, S0_IR_RECV);
+	mmiowb();
+
+	if (napi_schedule_prep(&priv->napi)) {
+		w5300_write(priv, W5300_IMR, 0);
+		mmiowb();
+		__napi_schedule(&priv->napi);
+	}
+
+	if (unlikely(netif_queue_stopped(ndev))) {
+		w5300_write(priv, W5300_S0_IR, S0_IR_SENDOK);
+		w5300_write(priv, W5300_S0_IMR, S0_IR_RECV);
+		mmiowb();
+		netif_wake_queue(ndev);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t w5300_detect_link(int irq, void *ndev_instance)
+{
+	struct net_device *ndev = ndev_instance;
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	if (netif_running(ndev)) {
+		if (gpio_get_value(priv->link_gpio) != 0) {
+			netif_info(priv, link, ndev, "link is up\n");
+			netif_carrier_on(ndev);
+		} else {
+			netif_info(priv, link, ndev, "link is down\n");
+			netif_carrier_off(ndev);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void w5300_set_rx_mode(struct net_device *ndev)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+	bool set_promisc = (ndev->flags & IFF_PROMISC) != 0;
+
+	if (priv->promisc != set_promisc) {
+		priv->promisc = set_promisc;
+		w5300_hw_start(priv);
+	}
+}
+
+static int w5300_set_macaddr(struct net_device *ndev, void *addr)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+	struct sockaddr *sock_addr = addr;
+
+	if (!is_valid_ether_addr(sock_addr->sa_data))
+		return -EADDRNOTAVAIL;
+	memcpy(ndev->dev_addr, sock_addr->sa_data, ETH_ALEN);
+	ndev->addr_assign_type &= ~NET_ADDR_RANDOM;
+	w5300_write_macaddr(priv);
+	return 0;
+}
+
+static int w5300_open(struct net_device *ndev)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	netif_info(priv, ifup, ndev, "enabling\n");
+	if (!is_valid_ether_addr(ndev->dev_addr))
+		return -EINVAL;
+	w5300_hw_start(priv);
+	napi_enable(&priv->napi);
+	netif_start_queue(ndev);
+	if (priv->link_gpio < 0 || gpio_get_value(priv->link_gpio))
+		netif_carrier_on(ndev);
+	return 0;
+}
+
+static int w5300_stop(struct net_device *ndev)
+{
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	netif_info(priv, ifdown, ndev, "shutting down\n");
+	w5300_hw_close(priv);
+	netif_carrier_off(ndev);
+	netif_stop_queue(ndev);
+	napi_disable(&priv->napi);
+	return 0;
+}
+
+static const struct ethtool_ops w5300_ethtool_ops = {
+	.get_drvinfo		= w5300_get_drvinfo,
+	.get_msglevel		= w5300_get_msglevel,
+	.set_msglevel		= w5300_set_msglevel,
+	.get_link		= w5300_get_link,
+	.get_regs_len		= w5300_get_regs_len,
+	.get_regs		= w5300_get_regs,
+};
+
+static const struct net_device_ops w5300_netdev_ops = {
+	.ndo_open		= w5300_open,
+	.ndo_stop		= w5300_stop,
+	.ndo_start_xmit		= w5300_start_tx,
+	.ndo_tx_timeout		= w5300_tx_timeout,
+	.ndo_set_rx_mode	= w5300_set_rx_mode,
+	.ndo_set_mac_address	= w5300_set_macaddr,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= eth_change_mtu,
+};
+
+static int __devinit w5300_hw_probe(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct w5300_priv *priv = netdev_priv(ndev);
+	const char *name = netdev_name(ndev);
+	struct resource *link;
+	struct resource *mem;
+	int mem_size;
+	int irq;
+	int ret;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem)
+		return -ENXIO;
+	mem_size = resource_size(mem);
+	if (!devm_request_mem_region(&pdev->dev, mem->start, mem_size, name))
+		return -EBUSY;
+	priv->base = devm_ioremap(&pdev->dev, mem->start, mem_size);
+	if (!priv->base)
+		return -EBUSY;
+
+	spin_lock_init(&priv->reg_lock);
+	priv->indirect = mem_size < W5300_BUS_DIRECT_SIZE;
+	if (priv->indirect) {
+		priv->read  = w5300_read_indirect;
+		priv->write = w5300_write_indirect;
+	} else {
+		priv->read  = w5300_read_direct;
+		priv->write = w5300_write_direct;
+	}
+	w5300_hw_reset(priv);
+	if (w5300_read(priv, W5300_IDR) != IDR_W5300)
+		return -ENODEV;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+	ret = devm_request_irq(&pdev->dev, irq, w5300_interrupt,
+			       IRQ_TYPE_LEVEL_LOW, name, ndev);
+	if (ret < 0)
+		return ret;
+	priv->irq = irq;
+
+	link = platform_get_resource(pdev, IORESOURCE_IO, 0);
+	if (!link) {
+		priv->link_gpio = -1;
+	} else {
+		char *link_name = devm_kzalloc(&pdev->dev, 16, GFP_KERNEL);
+		if (!link_name)
+			return -ENOMEM;
+		snprintf(link_name, 16, "%s-link", name);
+		priv->link_gpio = link->start;
+		priv->link_irq = gpio_to_irq(priv->link_gpio);
+		if (request_irq(priv->link_irq, w5300_detect_link,
+				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
+				link_name, priv->ndev) < 0)
+			priv->link_gpio = -1;
+	}
+
+	netdev_info(ndev, "at 0x%llx irq %d\n", (u64)mem->start, irq);
+	return 0;
+}
+
+static int __devinit w5300_probe(struct platform_device *pdev)
+{
+	struct wiznet_platform_data *data = pdev->dev.platform_data;
+	struct w5300_priv *priv;
+	struct net_device *ndev;
+	int err;
+
+	ndev = alloc_etherdev(sizeof(*priv));
+	if (!ndev)
+		return -ENOMEM;
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+	platform_set_drvdata(pdev, ndev);
+	priv = netdev_priv(ndev);
+	priv->ndev = ndev;
+
+	ether_setup(ndev);
+	ndev->netdev_ops = &w5300_netdev_ops;
+	ndev->ethtool_ops = &w5300_ethtool_ops;
+	ndev->watchdog_timeo = 2 * HZ;
+	netif_napi_add(ndev, &priv->napi, w5300_napi_poll, 16);
+
+	/* This chip doesn't support VLAN packets with normal MTU,
+	 * so disable VLAN for this device.
+	 */
+	ndev->features |= NETIF_F_VLAN_CHALLENGED;
+
+	err = register_netdev(ndev);
+	if (err < 0)
+		goto err_register;
+
+	if (data && is_valid_ether_addr(data->mac_addr)) {
+		memcpy(ndev->dev_addr, data->mac_addr, ETH_ALEN);
+	} else {
+		random_ether_addr(ndev->dev_addr);
+		ndev->addr_assign_type |= NET_ADDR_RANDOM;
+	}
+	err = w5300_hw_probe(pdev);
+	if (err < 0)
+		goto err_hw_probe;
+
+	return 0;
+
+err_hw_probe:
+	unregister_netdev(ndev);
+err_register:
+	free_netdev(ndev);
+	platform_set_drvdata(pdev, NULL);
+	dev_info(&pdev->dev, "probe failed (%d)\n", err);
+	return err;
+}
+
+static int __devexit w5300_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+
+	unregister_netdev(ndev);
+	free_netdev(ndev);
+	platform_set_drvdata(pdev, NULL);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int w5300_suspend(struct platform_device *pdev, pm_message_t mesg)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	if (netif_running(ndev)) {
+		netif_carrier_off(ndev);
+		netif_device_detach(ndev);
+
+		w5300_hw_close(priv);
+	}
+	return 0;
+}
+
+static int w5300_resume(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct w5300_priv *priv = netdev_priv(ndev);
+
+	if (netif_running(ndev)) {
+		w5300_hw_reset(priv);
+		w5300_hw_start(priv);
+
+		netif_device_attach(ndev);
+		if (priv->link_gpio < 0 || gpio_get_value(priv->link_gpio))
+			netif_carrier_on(ndev);
+	}
+	return 0;
+}
+#endif /* CONFIG_PM */
+
+static SIMPLE_DEV_PM_OPS(w5300_pm_ops, w5300_suspend, w5300_resume);
+
+static struct platform_driver w5300_driver = {
+	.driver		= {
+		.name	= KBUILD_MODNAME,
+		.owner	= THIS_MODULE,
+		.pm	= &w5300_pm_ops,
+	},
+	.probe		= w5300_probe,
+	.remove		= __devexit_p(w5300_remove),
+};
+
+module_platform_driver(w5300_driver);
diff --git a/include/linux/platform_data/wiznet.h b/include/linux/platform_data/wiznet.h
new file mode 100644
index 0000000..efd247f
--- /dev/null
+++ b/include/linux/platform_data/wiznet.h
@@ -0,0 +1,23 @@
+/*
+ * Ethernet driver for the WIZnet W5300 chip.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef PLATFORM_DATA_WIZNET_H
+#define PLATFORM_DATA_WIZNET_H
+
+#include <linux/if_ether.h>
+
+#ifndef CONFIG_WIZNET_BUS_SHIFT
+#define CONFIG_WIZNET_BUS_SHIFT 0
+#endif
+
+#define W5100_BUS_DIRECT_SIZE	(0x8000 << CONFIG_WIZNET_BUS_SHIFT)
+#define W5300_BUS_DIRECT_SIZE	(0x0400 << CONFIG_WIZNET_BUS_SHIFT)
+
+struct wiznet_platform_data {
+	u8	mac_addr[ETH_ALEN];
+};
+
+#endif /* PLATFORM_DATA_WIZNET_H */
-- 

^ permalink raw reply related

* [PATCH v5 2/2] Ethernet driver for the WIZnet W5100 chip
From: Mike Sinkovsky @ 2012-03-30  7:00 UTC (permalink / raw)
  To: netdev, linux-kernel; +Cc: Mike Sinkovsky
In-Reply-To: <1332752876-1650-1-git-send-email-msink@permonline.ru>

Tested and used in production with Blackfin BF531 embedded processor.

Signed-off-by: Mike Sinkovsky <msink@permonline.ru>
---
v5:
 - added driver for WIZnet W5100

---
 drivers/net/ethernet/wiznet/Kconfig  |   13 +
 drivers/net/ethernet/wiznet/Makefile |    1 +
 drivers/net/ethernet/wiznet/w5100.c  |  799 ++++++++++++++++++++++++++++++++++
 3 files changed, 814 insertions(+), 1 deletions(-)
 create mode 100644 drivers/net/ethernet/wiznet/w5100.c

diff --git a/drivers/net/ethernet/wiznet/Kconfig b/drivers/net/ethernet/wiznet/Kconfig
index 7ca5c95..8ad5bfa 100644
--- a/drivers/net/ethernet/wiznet/Kconfig
+++ b/drivers/net/ethernet/wiznet/Kconfig
@@ -17,6 +17,19 @@ config NET_VENDOR_WIZNET
 
 if NET_VENDOR_WIZNET
 
+config WIZNET_W5100
+	tristate "WIZnet W5100 Ethernet support"
+	depends on ARM || BLACKFIN
+	---help---
+	  Support for WIZnet W5100 chips.
+
+	  W5100 is a single chip with integrated 10/100 Ethernet MAC,
+	  PHY and hardware TCP/IP stack, but this driver is limited to
+	  the MAC and PHY functions only, onchip TCP/IP is unused.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called w5100.
+
 config WIZNET_W5300
 	tristate "WIZnet W5300 Ethernet support"
 	depends on ARM || BLACKFIN
diff --git a/drivers/net/ethernet/wiznet/Makefile b/drivers/net/ethernet/wiznet/Makefile
index 88e0a3e..c614535 100644
--- a/drivers/net/ethernet/wiznet/Makefile
+++ b/drivers/net/ethernet/wiznet/Makefile
@@ -1 +1,2 @@
+obj-$(CONFIG_WIZNET_W5100) += w5100.o
 obj-$(CONFIG_WIZNET_W5300) += w5300.o
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
new file mode 100644
index 0000000..ce7dfba
--- /dev/null
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -0,0 +1,799 @@
+/*
+ * Ethernet driver for the WIZnet W5100 chip.
+ *
+ * Copyright (C) 2006-2008 WIZnet Co.,Ltd.
+ * Copyright (C) 2012 Mike Sinkovsky <msink@permonline.ru>
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/wiznet.h>
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/gpio.h>
+
+#define DRV_NAME	"WIZnet W5100"
+#define DRV_VERSION	"2012-03-28"
+
+MODULE_DESCRIPTION(DRV_NAME" Ethernet driver v"DRV_VERSION);
+MODULE_AUTHOR("Mike Sinkovsky <msink@permonline.ru>");
+MODULE_ALIAS("platform:"KBUILD_MODNAME);
+MODULE_LICENSE("GPL");
+
+/*
+ * Registers
+ */
+#define W5100_COMM_REGS		0x0000
+#define W5100_MR		0x0000 /* Mode Register */
+#define   MR_RST		  0x80 /* S/W reset */
+#define   MR_PB			  0x10 /* Ping block */
+#define   MR_AI			  0x02 /* Address Auto-Increment */
+#define   MR_IND		  0x01 /* Indirect mode */
+#define W5100_SHAR		0x0009 /* Source MAC address */
+#define W5100_IR		0x0015 /* Interrupt */
+#define W5100_IMR		0x0016 /* Interrupt Mask */
+#define   IR_S0			  0x01 /* S0 interrupt */
+#define W5100_RTR		0x0017 /* Retry Time-value Register */
+#define   RTR_DEFAULT		  2000 /* =0x07d0 (2000) */
+#define W5100_RMSR		0x001a /* Receive memory size */
+#define W5100_TMSR		0x001b /* Transmit memory size */
+#define W5100_COMM_REGS_LEN	0x0040
+
+#define W5100_S0_REGS		0x0400
+#define W5100_S0_MR		0x0400 /* Socket Mode */
+#define   S0_MR_MACRAW		  0x04 /* MAC RAW mode (promiscous) */
+#define   S0_MR_MACRAW_MF	  0x44 /* MAC RAW mode (filtered) */
+#define W5100_S0_CR		0x0401 /* Socket Command */
+#define   S0_CR_OPEN		  0x01 /* OPEN command */
+#define   S0_CR_CLOSE		  0x10 /* CLOSE command */
+#define   S0_CR_SEND		  0x21 /* SEND command */
+#define   S0_CR_RECV		  0x40 /* RECV command */
+#define W5100_S0_IR		0x0402 /* Socket Interrupt */
+#define   S0_IR_SENDOK		  0x10 /* complete sending */
+#define   S0_IR_RECV		  0x04 /* receiving data */
+#define W5100_S0_SR		0x0403 /* Socket Status */
+#define   S0_SR_MACRAW		  0x42 /* mac raw mode socket */
+#define W5100_S0_TX_FSR		0x0420 /* Transmit free memory size */
+#define W5100_S0_TX_RD		0x0422 /* Transmit memory read pointer */
+#define W5100_S0_TX_WR		0x0424 /* Transmit memory write pointer */
+#define W5100_S0_RX_RSR		0x0426 /* Receive free memory size */
+#define W5100_S0_RX_RD		0x0428 /* Receive memory read pointer */
+#define W5100_S0_REGS_LEN	0x0040
+
+#define W5100_TX_MEM_START	0x4000
+#define W5100_TX_MEM_END	0x5fff
+#define W5100_TX_MEM_MASK	0x1fff
+#define W5100_RX_MEM_START	0x6000
+#define W5100_RX_MEM_END	0x7fff
+#define W5100_RX_MEM_MASK	0x1fff
+
+/*
+ * Device driver private data structure
+ */
+struct w5100_priv {
+	void __iomem *base;
+	bool indirect;
+	spinlock_t reg_lock;
+	u8   (*read)(struct w5100_priv *priv, u16 addr);
+	void (*write)(struct w5100_priv *priv, u16 addr, u8 data);
+	u16  (*read16)(struct w5100_priv *priv, u16 addr);
+	void (*write16)(struct w5100_priv *priv, u16 addr, u16 data);
+	void (*readbuf)(struct w5100_priv *priv, u16 addr, u8 *buf, int len);
+	void (*writebuf)(struct w5100_priv *priv, u16 addr, u8 *buf, int len);
+	int irq;
+	int link_irq;
+	int link_gpio;
+
+	struct napi_struct napi;
+	struct net_device *ndev;
+	bool promisc;
+	u32 msg_enable;
+};
+
+/************************************************************************
+ *
+ *  Lowlevel I/O functions
+ *
+ ***********************************************************************/
+
+/*
+ * In direct address mode host system can directly access W5100 registers
+ * after mapping to Memory-Mapped I/O space.
+ *
+ * 0x8000 bytes are required for memory space.
+ */
+static inline u8 w5100_read_direct(struct w5100_priv *priv, u16 addr)
+{
+	return ioread8(priv->base + (addr << CONFIG_WIZNET_BUS_SHIFT));
+}
+
+static inline void w5100_write_direct(struct w5100_priv *priv,
+				      u16 addr, u8 data)
+{
+	iowrite8(data, priv->base + (addr << CONFIG_WIZNET_BUS_SHIFT));
+}
+
+static u16 w5100_read16_direct(struct w5100_priv *priv, u16 addr)
+{
+	u16 ret;
+	ret  = w5100_read_direct(priv, addr) << 8;
+	ret |= w5100_read_direct(priv, addr + 1);
+	return ret;
+}
+
+static void w5100_write16_direct(struct w5100_priv *priv, u16 addr, u16 data)
+{
+	w5100_write_direct(priv, addr, data >> 8);
+	w5100_write_direct(priv, addr + 1, data);
+}
+
+static void w5100_readbuf_direct(struct w5100_priv *priv,
+				 u16 offset, u8 *buf, int len)
+{
+	u16 addr = W5100_RX_MEM_START + (offset & W5100_RX_MEM_MASK);
+	int i;
+
+	for (i = 0; i < len; i++, addr++) {
+		if (unlikely(addr > W5100_RX_MEM_END))
+			addr = W5100_RX_MEM_START;
+		*buf++ = w5100_read_direct(priv, addr);
+	}
+}
+
+static void w5100_writebuf_direct(struct w5100_priv *priv,
+				  u16 offset, u8 *buf, int len)
+{
+	u16 addr = W5100_TX_MEM_START + (offset & W5100_TX_MEM_MASK);
+	int i;
+
+	for (i = 0; i < len; i++, addr++) {
+		if (unlikely(addr > W5100_TX_MEM_END))
+			addr = W5100_TX_MEM_START;
+		w5100_write_direct(priv, addr, *buf++);
+	}
+}
+
+/*
+ * In indirect address mode host system indirectly accesses registers by
+ * using Indirect Mode Address Register (IDM_AR) and Indirect Mode Data
+ * Register (IDM_DR), which are directly mapped to Memory-Mapped I/O space.
+ * Mode Register (MR) is directly accessible.
+ *
+ * Only 0x04 bytes are required for memory space.
+ */
+#define W5100_IDM_AR		0x01   /* Indirect Mode Address Register */
+#define W5100_IDM_DR		0x03   /* Indirect Mode Data Register */
+
+static u8 w5100_read_indirect(struct w5100_priv *priv, u16 addr)
+{
+	unsigned long flags;
+	u8 data;
+
+	spin_lock_irqsave(&priv->reg_lock, flags);
+	w5100_write16_direct(priv, W5100_IDM_AR, addr);
+	mmiowb();
+	data = w5100_read_direct(priv, W5100_IDM_DR);
+	spin_unlock_irqrestore(&priv->reg_lock, flags);
+
+	return data;
+}
+
+static void w5100_write_indirect(struct w5100_priv *priv, u16 addr, u8 data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->reg_lock, flags);
+	w5100_write16_direct(priv, W5100_IDM_AR, addr);
+	mmiowb();
+	w5100_write_direct(priv, W5100_IDM_DR, data);
+	mmiowb();
+	spin_unlock_irqrestore(&priv->reg_lock, flags);
+}
+
+static u16 w5100_read16_indirect(struct w5100_priv *priv, u16 addr)
+{
+	unsigned long flags;
+	u16 data;
+
+	spin_lock_irqsave(&priv->reg_lock, flags);
+	w5100_write16_direct(priv, W5100_IDM_AR, addr);
+	mmiowb();
+	data  = w5100_read_direct(priv, W5100_IDM_DR) << 8;
+	data |= w5100_read_direct(priv, W5100_IDM_DR);
+	spin_unlock_irqrestore(&priv->reg_lock, flags);
+
+	return data;
+}
+
+static void w5100_write16_indirect(struct w5100_priv *priv, u16 addr, u16 data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->reg_lock, flags);
+	w5100_write16_direct(priv, W5100_IDM_AR, addr);
+	mmiowb();
+	w5100_write_direct(priv, W5100_IDM_DR, data >> 8);
+	w5100_write_direct(priv, W5100_IDM_DR, data);
+	mmiowb();
+	spin_unlock_irqrestore(&priv->reg_lock, flags);
+}
+
+static void w5100_readbuf_indirect(struct w5100_priv *priv,
+				   u16 offset, u8 *buf, int len)
+{
+	u16 addr = (offset & W5100_RX_MEM_MASK) + W5100_RX_MEM_START;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&priv->reg_lock, flags);
+	w5100_write16_direct(priv, W5100_IDM_AR, addr);
+	mmiowb();
+
+	for (i = 0; i < len; i++, addr++) {
+		if (unlikely(addr > W5100_RX_MEM_END)) {
+			addr = W5100_RX_MEM_START;
+			w5100_write16_direct(priv, W5100_IDM_AR, addr);
+			mmiowb();
+		}
+		*buf++ = w5100_read_direct(priv, W5100_IDM_DR);
+	}
+	mmiowb();
+	spin_unlock_irqrestore(&priv->reg_lock, flags);
+}
+
+static void w5100_writebuf_indirect(struct w5100_priv *priv,
+				    u16 offset, u8 *buf, int len)
+{
+	u16 addr = (offset & W5100_TX_MEM_MASK) + W5100_TX_MEM_START;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&priv->reg_lock, flags);
+	w5100_write16_direct(priv, W5100_IDM_AR, addr);
+	mmiowb();
+
+	for (i = 0; i < len; i++, addr++) {
+		if (unlikely(addr > W5100_TX_MEM_END)) {
+			addr = W5100_TX_MEM_START;
+			w5100_write16_direct(priv, W5100_IDM_AR, addr);
+			mmiowb();
+		}
+		w5100_write_direct(priv, W5100_IDM_DR, *buf++);
+	}
+	mmiowb();
+	spin_unlock_irqrestore(&priv->reg_lock, flags);
+}
+
+#if defined(CONFIG_WIZNET_BUS_DIRECT)
+#define w5100_read	w5100_read_direct
+#define w5100_write	w5100_write_direct
+#define w5100_read16	w5100_read16_direct
+#define w5100_write16	w5100_write16_direct
+#define w5100_readbuf	w5100_readbuf_direct
+#define w5100_writebuf	w5100_writebuf_direct
+
+#elif defined(CONFIG_WIZNET_BUS_INDIRECT)
+#define w5100_read	w5100_read_indirect
+#define w5100_write	w5100_write_indirect
+#define w5100_read16	w5100_read16_indirect
+#define w5100_write16	w5100_write16_indirect
+#define w5100_readbuf	w5100_readbuf_indirect
+#define w5100_writebuf	w5100_writebuf_indirect
+
+#else /* CONFIG_WIZNET_BUS_ANY */
+#define w5100_read	priv->read
+#define w5100_write	priv->write
+#define w5100_read16	priv->read16
+#define w5100_write16	priv->write16
+#define w5100_readbuf	priv->readbuf
+#define w5100_writebuf	priv->writebuf
+#endif
+
+static int w5100_command(struct w5100_priv *priv, u16 cmd)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(100);
+
+	w5100_write(priv, W5100_S0_CR, cmd);
+	mmiowb();
+
+	while (w5100_read(priv, W5100_S0_CR) != 0) {
+		if (time_after(jiffies, timeout))
+			return -EIO;
+		cpu_relax();
+	}
+
+	return 0;
+}
+
+static void w5100_write_macaddr(struct w5100_priv *priv)
+{
+	struct net_device *ndev = priv->ndev;
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		w5100_write(priv, W5100_SHAR + i, ndev->dev_addr[i]);
+	mmiowb();
+}
+
+static void w5100_hw_reset(struct w5100_priv *priv)
+{
+	w5100_write_direct(priv, W5100_MR, MR_RST);
+	mmiowb();
+	mdelay(5);
+	w5100_write_direct(priv, W5100_MR, priv->indirect ?
+				  MR_PB | MR_AI | MR_IND :
+				  MR_PB);
+	mmiowb();
+	w5100_write(priv, W5100_IMR, 0);
+	w5100_write_macaddr(priv);
+
+	/*
+	 * Configure 16K of internal memory
+	 * as 8K RX buffer and 8K TX buffer
+	 */
+	w5100_write(priv, W5100_RMSR, 0x03);
+	w5100_write(priv, W5100_TMSR, 0x03);
+	mmiowb();
+}
+
+static void w5100_hw_start(struct w5100_priv *priv)
+{
+	w5100_write(priv, W5100_S0_MR, priv->promisc ?
+			  S0_MR_MACRAW : S0_MR_MACRAW_MF);
+	w5100_command(priv, S0_CR_OPEN);
+	w5100_write(priv, W5100_IMR, IR_S0);
+	mmiowb();
+}
+
+static void w5100_hw_close(struct w5100_priv *priv)
+{
+	w5100_write(priv, W5100_IMR, 0);
+	mmiowb();
+	w5100_command(priv, S0_CR_CLOSE);
+}
+
+/***********************************************************************
+ *
+ *   Device driver functions / callbacks
+ *
+ ***********************************************************************/
+
+static void w5100_get_drvinfo(struct net_device *ndev,
+			      struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, dev_name(ndev->dev.parent),
+		sizeof(info->bus_info));
+}
+
+static u32 w5100_get_link(struct net_device *ndev)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	if (priv->link_gpio < 0)
+		return 1;
+
+	return !!gpio_get_value(priv->link_gpio);
+}
+
+static u32 w5100_get_msglevel(struct net_device *ndev)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	return priv->msg_enable;
+}
+
+static void w5100_set_msglevel(struct net_device *ndev, u32 value)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	priv->msg_enable = value;
+}
+
+static int w5100_get_regs_len(struct net_device *ndev)
+{
+	return W5100_COMM_REGS_LEN + W5100_S0_REGS_LEN;
+}
+
+static void w5100_get_regs(struct net_device *ndev,
+			   struct ethtool_regs *regs, void *_buf)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+	u8 *buf = _buf;
+	u16 i;
+
+	regs->version = 1;
+	for (i = 0; i < W5100_COMM_REGS_LEN; i++)
+		*buf++ = w5100_read(priv, W5100_COMM_REGS + i);
+	for (i = 0; i < W5100_S0_REGS_LEN; i++)
+		*buf++ = w5100_read(priv, W5100_S0_REGS + i);
+}
+
+static void w5100_tx_timeout(struct net_device *ndev)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	w5100_hw_reset(priv);
+	w5100_hw_start(priv);
+	ndev->stats.tx_errors++;
+	ndev->trans_start = jiffies;
+	netif_wake_queue(ndev);
+}
+
+static int w5100_start_tx(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+	u16 offset;
+
+	if (w5100_read16(priv, W5100_S0_TX_FSR) < skb->len) {
+		netif_stop_queue(ndev);
+		return NETDEV_TX_BUSY;
+	}
+
+	offset = w5100_read16(priv, W5100_S0_TX_WR);
+	w5100_writebuf(priv, offset, skb->data, skb->len);
+	w5100_write16(priv, W5100_S0_TX_WR, offset + skb->len);
+	w5100_command(priv, S0_CR_SEND);
+	ndev->stats.tx_bytes += skb->len;
+	ndev->stats.tx_packets++;
+	dev_kfree_skb(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static int w5100_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct w5100_priv *priv = container_of(napi, struct w5100_priv, napi);
+	struct net_device *ndev = priv->ndev;
+	struct sk_buff *skb;
+	int rx_count;
+	u16 rx_len;
+	u16 offset;
+	u8 header[2];
+
+	for (rx_count = 0; rx_count < budget; rx_count++) {
+		u16 rx_buf_len = w5100_read16(priv, W5100_S0_RX_RSR);
+		if (rx_buf_len == 0)
+			break;
+
+		offset = w5100_read16(priv, W5100_S0_RX_RD);
+		w5100_readbuf(priv, offset, header, 2);
+		rx_len = get_unaligned_be16(header) - 2;
+
+		skb = netdev_alloc_skb_ip_align(ndev, rx_len);
+		if (unlikely(!skb)) {
+			w5100_write16(priv, W5100_S0_RX_RD,
+					    offset + rx_buf_len);
+			w5100_command(priv, S0_CR_RECV);
+			ndev->stats.rx_dropped++;
+			return -ENOMEM;
+		}
+
+		skb_put(skb, rx_len);
+		w5100_readbuf(priv, offset + 2, skb->data, rx_len);
+		w5100_write16(priv, W5100_S0_RX_RD, offset + 2 + rx_len);
+		mmiowb();
+		w5100_command(priv, S0_CR_RECV);
+		skb->protocol = eth_type_trans(skb, ndev);
+
+		netif_receive_skb(skb);
+		ndev->stats.rx_packets++;
+		ndev->stats.rx_bytes += rx_len;
+	}
+
+	if (rx_count < budget) {
+		w5100_write(priv, W5100_IMR, IR_S0);
+		mmiowb();
+		napi_complete(napi);
+	}
+
+	return rx_count;
+}
+
+static irqreturn_t w5100_interrupt(int irq, void *ndev_instance)
+{
+	struct net_device *ndev = ndev_instance;
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	int ir = w5100_read(priv, W5100_S0_IR);
+	w5100_write(priv, W5100_S0_IR, ir);
+
+	if (ir & S0_IR_RECV) {
+		if (napi_schedule_prep(&priv->napi)) {
+			w5100_write(priv, W5100_IMR, 0);
+			mmiowb();
+			__napi_schedule(&priv->napi);
+		}
+	}
+
+	if (ir & S0_IR_SENDOK) {
+		if (unlikely(netif_queue_stopped(ndev)))
+			netif_wake_queue(ndev);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t w5100_detect_link(int irq, void *ndev_instance)
+{
+	struct net_device *ndev = ndev_instance;
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	if (netif_running(ndev)) {
+		if (gpio_get_value(priv->link_gpio) != 0) {
+			netif_info(priv, link, ndev, "link is up\n");
+			netif_carrier_on(ndev);
+		} else {
+			netif_info(priv, link, ndev, "link is down\n");
+			netif_carrier_off(ndev);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void w5100_set_rx_mode(struct net_device *ndev)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+	bool set_promisc = (ndev->flags & IFF_PROMISC) != 0;
+
+	if (priv->promisc != set_promisc) {
+		priv->promisc = set_promisc;
+		w5100_hw_start(priv);
+	}
+}
+
+static int w5100_set_macaddr(struct net_device *ndev, void *addr)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+	struct sockaddr *sock_addr = addr;
+
+	if (!is_valid_ether_addr(sock_addr->sa_data))
+		return -EADDRNOTAVAIL;
+	memcpy(ndev->dev_addr, sock_addr->sa_data, ETH_ALEN);
+	ndev->addr_assign_type &= ~NET_ADDR_RANDOM;
+	w5100_write_macaddr(priv);
+	return 0;
+}
+
+static int w5100_open(struct net_device *ndev)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	netif_info(priv, ifup, ndev, "enabling\n");
+	if (!is_valid_ether_addr(ndev->dev_addr))
+		return -EINVAL;
+	w5100_hw_start(priv);
+	napi_enable(&priv->napi);
+	netif_start_queue(ndev);
+	if (priv->link_gpio < 0 || gpio_get_value(priv->link_gpio))
+		netif_carrier_on(ndev);
+	return 0;
+}
+
+static int w5100_stop(struct net_device *ndev)
+{
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	netif_info(priv, ifdown, ndev, "shutting down\n");
+	w5100_hw_close(priv);
+	netif_carrier_off(ndev);
+	netif_stop_queue(ndev);
+	napi_disable(&priv->napi);
+	return 0;
+}
+
+static const struct ethtool_ops w5100_ethtool_ops = {
+	.get_drvinfo		= w5100_get_drvinfo,
+	.get_msglevel		= w5100_get_msglevel,
+	.set_msglevel		= w5100_set_msglevel,
+	.get_link		= w5100_get_link,
+	.get_regs_len		= w5100_get_regs_len,
+	.get_regs		= w5100_get_regs,
+};
+
+static const struct net_device_ops w5100_netdev_ops = {
+	.ndo_open		= w5100_open,
+	.ndo_stop		= w5100_stop,
+	.ndo_start_xmit		= w5100_start_tx,
+	.ndo_tx_timeout		= w5100_tx_timeout,
+	.ndo_set_rx_mode	= w5100_set_rx_mode,
+	.ndo_set_mac_address	= w5100_set_macaddr,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= eth_change_mtu,
+};
+
+static int __devinit w5100_hw_probe(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct w5100_priv *priv = netdev_priv(ndev);
+	const char *name = netdev_name(ndev);
+	struct resource *link;
+	struct resource *mem;
+	int mem_size;
+	int irq;
+	int ret;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem)
+		return -ENXIO;
+	mem_size = resource_size(mem);
+	if (!devm_request_mem_region(&pdev->dev, mem->start, mem_size, name))
+		return -EBUSY;
+	priv->base = devm_ioremap(&pdev->dev, mem->start, mem_size);
+	if (!priv->base)
+		return -EBUSY;
+
+	spin_lock_init(&priv->reg_lock);
+	priv->indirect = mem_size < W5100_BUS_DIRECT_SIZE;
+	if (priv->indirect) {
+		priv->read     = w5100_read_indirect;
+		priv->write    = w5100_write_indirect;
+		priv->read16   = w5100_read16_indirect;
+		priv->write16  = w5100_write16_indirect;
+		priv->readbuf  = w5100_readbuf_indirect;
+		priv->writebuf = w5100_writebuf_indirect;
+	} else {
+		priv->read     = w5100_read_direct;
+		priv->write    = w5100_write_direct;
+		priv->read16   = w5100_read16_direct;
+		priv->write16  = w5100_write16_direct;
+		priv->readbuf  = w5100_readbuf_direct;
+		priv->writebuf = w5100_writebuf_direct;
+	}
+	w5100_hw_reset(priv);
+	if (w5100_read16(priv, W5100_RTR) != RTR_DEFAULT)
+		return -ENODEV;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+	ret = devm_request_irq(&pdev->dev, irq, w5100_interrupt,
+			       IRQ_TYPE_LEVEL_LOW, name, ndev);
+	if (ret < 0)
+		return ret;
+	priv->irq = irq;
+
+	link = platform_get_resource(pdev, IORESOURCE_IO, 0);
+	if (!link) {
+		priv->link_gpio = -1;
+	} else {
+		char *link_name = devm_kzalloc(&pdev->dev, 16, GFP_KERNEL);
+		if (!link_name)
+			return -ENOMEM;
+		snprintf(link_name, 16, "%s-link", name);
+		priv->link_gpio = link->start;
+		priv->link_irq = gpio_to_irq(priv->link_gpio);
+		if (request_irq(priv->link_irq, w5100_detect_link,
+				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
+				link_name, priv->ndev) < 0)
+			priv->link_gpio = -1;
+	}
+
+	netdev_info(ndev, "at 0x%llx irq %d\n", (u64)mem->start, irq);
+	return 0;
+}
+
+static int __devinit w5100_probe(struct platform_device *pdev)
+{
+	struct wiznet_platform_data *data = pdev->dev.platform_data;
+	struct w5100_priv *priv;
+	struct net_device *ndev;
+	int err;
+
+	ndev = alloc_etherdev(sizeof(*priv));
+	if (!ndev)
+		return -ENOMEM;
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+	platform_set_drvdata(pdev, ndev);
+	priv = netdev_priv(ndev);
+	priv->ndev = ndev;
+
+	ether_setup(ndev);
+	ndev->netdev_ops = &w5100_netdev_ops;
+	ndev->ethtool_ops = &w5100_ethtool_ops;
+	ndev->watchdog_timeo = 2 * HZ;
+	netif_napi_add(ndev, &priv->napi, w5100_napi_poll, 16);
+
+	/* This chip doesn't support VLAN packets with normal MTU,
+	 * so disable VLAN for this device.
+	 */
+	ndev->features |= NETIF_F_VLAN_CHALLENGED;
+
+	err = register_netdev(ndev);
+	if (err < 0)
+		goto err_register;
+
+	if (data && is_valid_ether_addr(data->mac_addr)) {
+		memcpy(ndev->dev_addr, data->mac_addr, ETH_ALEN);
+	} else {
+		random_ether_addr(ndev->dev_addr);
+		ndev->addr_assign_type |= NET_ADDR_RANDOM;
+	}
+	err = w5100_hw_probe(pdev);
+	if (err < 0)
+		goto err_hw_probe;
+
+	return 0;
+
+err_hw_probe:
+	unregister_netdev(ndev);
+err_register:
+	free_netdev(ndev);
+	platform_set_drvdata(pdev, NULL);
+	dev_info(&pdev->dev, "probe failed (%d)\n", err);
+	return err;
+}
+
+static int __devexit w5100_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+
+	unregister_netdev(ndev);
+	free_netdev(ndev);
+	platform_set_drvdata(pdev, NULL);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int w5100_suspend(struct platform_device *pdev, pm_message_t mesg)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	if (netif_running(ndev)) {
+		netif_carrier_off(ndev);
+		netif_device_detach(ndev);
+
+		w5100_hw_close(priv);
+	}
+	return 0;
+}
+
+static int w5100_resume(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct w5100_priv *priv = netdev_priv(ndev);
+
+	if (netif_running(ndev)) {
+		w5100_hw_reset(priv);
+		w5100_hw_start(priv);
+
+		netif_device_attach(ndev);
+		if (priv->link_gpio < 0 || gpio_get_value(priv->link_gpio))
+			netif_carrier_on(ndev);
+	}
+	return 0;
+}
+#endif /* CONFIG_PM */
+
+static SIMPLE_DEV_PM_OPS(w5100_pm_ops, w5100_suspend, w5100_resume);
+
+static struct platform_driver w5100_driver = {
+	.driver		= {
+		.name	= KBUILD_MODNAME,
+		.owner	= THIS_MODULE,
+		.pm	= &w5100_pm_ops,
+	},
+	.probe		= w5100_probe,
+	.remove		= __devexit_p(w5100_remove),
+};
+
+module_platform_driver(w5100_driver);
-- 

^ permalink raw reply related

* [PATCH net-next v3 5/5] r8169: support RTL8411
From: Hayes Wang @ 2012-03-30  6:48 UTC (permalink / raw)
  To: romieu; +Cc: netdev, linux-kernel, Hayes Wang
In-Reply-To: <1333089184-1773-5-git-send-email-hayeswang@realtek.com>

Support the new chip RTL8411.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
 drivers/net/ethernet/realtek/r8169.c |  140 +++++++++++++++++++++++++++++++++-
 1 files changed, 138 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 3ba49dc..dcc1ec5 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -46,6 +46,7 @@
 #define FIRMWARE_8168F_2	"rtl_nic/rtl8168f-2.fw"
 #define FIRMWARE_8105E_1	"rtl_nic/rtl8105e-1.fw"
 #define FIRMWARE_8402_1		"rtl_nic/rtl8402-1.fw"
+#define FIRMWARE_8411_1		"rtl_nic/rtl8411-1.fw"
 
 #ifdef RTL8169_DEBUG
 #define assert(expr) \
@@ -136,6 +137,7 @@ enum mac_version {
 	RTL_GIGA_MAC_VER_35,
 	RTL_GIGA_MAC_VER_36,
 	RTL_GIGA_MAC_VER_37,
+	RTL_GIGA_MAC_VER_38,
 	RTL_GIGA_MAC_NONE   = 0xff,
 };
 
@@ -251,6 +253,9 @@ static const struct {
 	[RTL_GIGA_MAC_VER_37] =
 		_R("RTL8402",		RTL_TD_1, FIRMWARE_8402_1,
 							JUMBO_1K, true),
+	[RTL_GIGA_MAC_VER_38] =
+		_R("RTL8411",		RTL_TD_1, FIRMWARE_8411_1,
+							JUMBO_9K, false),
 };
 #undef _R
 
@@ -783,6 +788,7 @@ MODULE_FIRMWARE(FIRMWARE_8105E_1);
 MODULE_FIRMWARE(FIRMWARE_8168F_1);
 MODULE_FIRMWARE(FIRMWARE_8168F_2);
 MODULE_FIRMWARE(FIRMWARE_8402_1);
+MODULE_FIRMWARE(FIRMWARE_8411_1);
 
 static void rtl_lock_work(struct rtl8169_private *tp)
 {
@@ -1262,7 +1268,8 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 	if (!netif_running(dev))
 		return;
 
-	if (tp->mac_version == RTL_GIGA_MAC_VER_34) {
+	if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_38) {
 		if (RTL_R8(PHYstatus) & _1000bpsF) {
 			rtl_eri_write(ioaddr, 0x1bc, ERIAR_MASK_1111,
 				      0x00000011, ERIAR_EXGMAC);
@@ -1867,6 +1874,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 		int mac_version;
 	} mac_info[] = {
 		/* 8168F family. */
+		{ 0x7c800000, 0x48800000,	RTL_GIGA_MAC_VER_38 },
 		{ 0x7cf00000, 0x48100000,	RTL_GIGA_MAC_VER_36 },
 		{ 0x7cf00000, 0x48000000,	RTL_GIGA_MAC_VER_35 },
 
@@ -3084,6 +3092,104 @@ static void rtl8168f_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl8168f_hw_phy_config(tp);
 }
 
+static void rtl8411_hw_phy_config(struct rtl8169_private *tp)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+	static const struct phy_reg phy_reg_init[] = {
+		/* Channel estimation fine tune */
+		{ 0x1f, 0x0003 },
+		{ 0x09, 0xa20f },
+		{ 0x1f, 0x0000 },
+
+		/* Modify green table for giga & fnet */
+		{ 0x1f, 0x0005 },
+		{ 0x05, 0x8b55 },
+		{ 0x06, 0x0000 },
+		{ 0x05, 0x8b5e },
+		{ 0x06, 0x0000 },
+		{ 0x05, 0x8b67 },
+		{ 0x06, 0x0000 },
+		{ 0x05, 0x8b70 },
+		{ 0x06, 0x0000 },
+		{ 0x1f, 0x0000 },
+		{ 0x1f, 0x0007 },
+		{ 0x1e, 0x0078 },
+		{ 0x17, 0x0000 },
+		{ 0x19, 0x00aa },
+		{ 0x1f, 0x0000 },
+
+		/* Modify green table for 10M */
+		{ 0x1f, 0x0005 },
+		{ 0x05, 0x8b79 },
+		{ 0x06, 0xaa00 },
+		{ 0x1f, 0x0000 },
+
+		/* Disable hiimpedance detection (RTCT) */
+		{ 0x1f, 0x0003 },
+		{ 0x01, 0x328a },
+		{ 0x1f, 0x0000 }
+	};
+
+
+	rtl_apply_firmware(tp);
+
+	rtl8168f_hw_phy_config(tp);
+
+	/* Improve 2-pair detection performance */
+	rtl_writephy(tp, 0x1f, 0x0005);
+	rtl_writephy(tp, 0x05, 0x8b85);
+	rtl_w1w0_phy(tp, 0x06, 0x4000, 0x0000);
+	rtl_writephy(tp, 0x1f, 0x0000);
+
+	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+
+	/* Modify green table for giga */
+	rtl_writephy(tp, 0x1f, 0x0005);
+	rtl_writephy(tp, 0x05, 0x8b54);
+	rtl_w1w0_phy(tp, 0x06, 0x0000, 0x0800);
+	rtl_writephy(tp, 0x05, 0x8b5d);
+	rtl_w1w0_phy(tp, 0x06, 0x0000, 0x0800);
+	rtl_writephy(tp, 0x05, 0x8a7c);
+	rtl_w1w0_phy(tp, 0x06, 0x0000, 0x0100);
+	rtl_writephy(tp, 0x05, 0x8a7f);
+	rtl_w1w0_phy(tp, 0x06, 0x0100, 0x0000);
+	rtl_writephy(tp, 0x05, 0x8a82);
+	rtl_w1w0_phy(tp, 0x06, 0x0000, 0x0100);
+	rtl_writephy(tp, 0x05, 0x8a85);
+	rtl_w1w0_phy(tp, 0x06, 0x0000, 0x0100);
+	rtl_writephy(tp, 0x05, 0x8a88);
+	rtl_w1w0_phy(tp, 0x06, 0x0000, 0x0100);
+	rtl_writephy(tp, 0x1f, 0x0000);
+
+	/* uc same-seed solution */
+	rtl_writephy(tp, 0x1f, 0x0005);
+	rtl_writephy(tp, 0x05, 0x8b85);
+	rtl_w1w0_phy(tp, 0x06, 0x8000, 0x0000);
+	rtl_writephy(tp, 0x1f, 0x0000);
+
+	/* eee setting */
+	rtl_w1w0_eri(ioaddr, 0x1b0, ERIAR_MASK_0001, 0x00, 0x03, ERIAR_EXGMAC);
+	rtl_writephy(tp, 0x1f, 0x0005);
+	rtl_writephy(tp, 0x05, 0x8b85);
+	rtl_w1w0_phy(tp, 0x06, 0x0000, 0x2000);
+	rtl_writephy(tp, 0x1f, 0x0004);
+	rtl_writephy(tp, 0x1f, 0x0007);
+	rtl_writephy(tp, 0x1e, 0x0020);
+	rtl_w1w0_phy(tp, 0x15, 0x0000, 0x0100);
+	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl_writephy(tp, 0x0d, 0x0007);
+	rtl_writephy(tp, 0x0e, 0x003c);
+	rtl_writephy(tp, 0x0d, 0x4007);
+	rtl_writephy(tp, 0x0e, 0x0000);
+	rtl_writephy(tp, 0x0d, 0x0000);
+
+	/* Green feature */
+	rtl_writephy(tp, 0x1f, 0x0003);
+	rtl_w1w0_phy(tp, 0x19, 0x0000, 0x0001);
+	rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0400);
+	rtl_writephy(tp, 0x1f, 0x0000);
+}
+
 static void rtl8102e_hw_phy_config(struct rtl8169_private *tp)
 {
 	static const struct phy_reg phy_reg_init[] = {
@@ -3238,6 +3344,10 @@ static void rtl_hw_phy_config(struct net_device *dev)
 		rtl8402_hw_phy_config(tp);
 		break;
 
+	case RTL_GIGA_MAC_VER_38:
+		rtl8411_hw_phy_config(tp);
+		break;
+
 	default:
 		break;
 	}
@@ -3476,6 +3586,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_33:
 	case RTL_GIGA_MAC_VER_34:
 	case RTL_GIGA_MAC_VER_37:
+	case RTL_GIGA_MAC_VER_38:
 		RTL_W32(RxConfig, RTL_R32(RxConfig) |
 			AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
 		break;
@@ -3722,6 +3833,7 @@ static void __devinit rtl_init_pll_power_ops(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_34:
 	case RTL_GIGA_MAC_VER_35:
 	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
 		ops->down	= r8168_pll_power_down;
 		ops->up		= r8168_pll_power_up;
 		break;
@@ -4008,7 +4120,8 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
 	           tp->mac_version == RTL_GIGA_MAC_VER_35 ||
 	           tp->mac_version == RTL_GIGA_MAC_VER_36 ||
-	           tp->mac_version == RTL_GIGA_MAC_VER_37) {
+	           tp->mac_version == RTL_GIGA_MAC_VER_37 ||
+	           tp->mac_version == RTL_GIGA_MAC_VER_38) {
 		RTL_W8(ChipCmd, RTL_R8(ChipCmd) | StopReq);
 		while (!(RTL_R32(TxConfig) & TXCFG_EMPTY))
 			udelay(100);
@@ -4339,6 +4452,7 @@ static void __devinit rtl_init_csi_ops(struct rtl8169_private *tp)
 		break;
 
 	case RTL_GIGA_MAC_VER_37:
+	case RTL_GIGA_MAC_VER_38:
 		ops->write	= r8402_csi_write;
 		ops->read	= r8402_csi_read;
 		break;
@@ -4727,6 +4841,24 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
 	RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07);
 }
 
+static void rtl_hw_start_8411(struct rtl8169_private *tp)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+	static const struct ephy_info e_info_8168f_1[] = {
+		{ 0x06, 0x00c0,	0x0020 },
+		{ 0x0f, 0xffff,	0x5200 },
+		{ 0x1e, 0x0000,	0x4000 },
+		{ 0x19, 0x0000,	0x0224 }
+	};
+
+	rtl_hw_start_8168f(tp);
+
+	rtl_ephy_init(ioaddr, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
+
+	rtl_w1w0_eri(ioaddr, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0x0000,
+		     ERIAR_EXGMAC);
+}
+
 static void rtl_hw_start_8168(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
@@ -4824,6 +4956,10 @@ static void rtl_hw_start_8168(struct net_device *dev)
 		rtl_hw_start_8168f_1(tp);
 		break;
 
+	case RTL_GIGA_MAC_VER_38:
+		rtl_hw_start_8411(tp);
+		break;
+
 	default:
 		printk(KERN_ERR PFX "%s: unknown chipset (mac_version = %d).\n",
 			dev->name, tp->mac_version);
-- 
1.7.7.6

^ permalink raw reply related

* [PATCH net-next v3 4/5] r8169: adjust some functions of 8111f
From: Hayes Wang @ 2012-03-30  6:33 UTC (permalink / raw)
  To: romieu; +Cc: netdev, linux-kernel, Hayes Wang
In-Reply-To: <1333089184-1773-1-git-send-email-hayeswang@realtek.com>

Put some settings of 8111f into one function which may be reused.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
 drivers/net/ethernet/realtek/r8169.c |   99 ++++++++++++++++------------------
 1 files changed, 47 insertions(+), 52 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b7a21de..3ba49dc 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -3005,6 +3005,28 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 }
 
+static void rtl8168f_hw_phy_config(struct rtl8169_private *tp)
+{
+	/* For 4-corner performance improve */
+	rtl_writephy(tp, 0x1f, 0x0005);
+	rtl_writephy(tp, 0x05, 0x8b80);
+	rtl_w1w0_phy(tp, 0x06, 0x0006, 0x0000);
+	rtl_writephy(tp, 0x1f, 0x0000);
+
+	/* PHY auto speed down */
+	rtl_writephy(tp, 0x1f, 0x0007);
+	rtl_writephy(tp, 0x1e, 0x002d);
+	rtl_w1w0_phy(tp, 0x18, 0x0010, 0x0000);
+	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl_w1w0_phy(tp, 0x14, 0x8000, 0x0000);
+
+	/* Improve 10M EEE waveform */
+	rtl_writephy(tp, 0x1f, 0x0005);
+	rtl_writephy(tp, 0x05, 0x8b86);
+	rtl_w1w0_phy(tp, 0x06, 0x0001, 0x0000);
+	rtl_writephy(tp, 0x1f, 0x0000);
+}
+
 static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp)
 {
 	static const struct phy_reg phy_reg_init[] = {
@@ -3046,24 +3068,7 @@ static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp)
 
 	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
 
-	/* For 4-corner performance improve */
-	rtl_writephy(tp, 0x1f, 0x0005);
-	rtl_writephy(tp, 0x05, 0x8b80);
-	rtl_w1w0_phy(tp, 0x06, 0x0006, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
-
-	/* PHY auto speed down */
-	rtl_writephy(tp, 0x1f, 0x0007);
-	rtl_writephy(tp, 0x1e, 0x002d);
-	rtl_w1w0_phy(tp, 0x18, 0x0010, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_w1w0_phy(tp, 0x14, 0x8000, 0x0000);
-
-	/* Improve 10M EEE waveform */
-	rtl_writephy(tp, 0x1f, 0x0005);
-	rtl_writephy(tp, 0x05, 0x8b86);
-	rtl_w1w0_phy(tp, 0x06, 0x0001, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168f_hw_phy_config(tp);
 
 	/* Improve 2-pair detection performance */
 	rtl_writephy(tp, 0x1f, 0x0005);
@@ -3076,24 +3081,7 @@ static void rtl8168f_2_hw_phy_config(struct rtl8169_private *tp)
 {
 	rtl_apply_firmware(tp);
 
-	/* For 4-corner performance improve */
-	rtl_writephy(tp, 0x1f, 0x0005);
-	rtl_writephy(tp, 0x05, 0x8b80);
-	rtl_w1w0_phy(tp, 0x06, 0x0006, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
-
-	/* PHY auto speed down */
-	rtl_writephy(tp, 0x1f, 0x0007);
-	rtl_writephy(tp, 0x1e, 0x002d);
-	rtl_w1w0_phy(tp, 0x18, 0x0010, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_w1w0_phy(tp, 0x14, 0x8000, 0x0000);
-
-	/* Improve 10M EEE waveform */
-	rtl_writephy(tp, 0x1f, 0x0005);
-	rtl_writephy(tp, 0x05, 0x8b86);
-	rtl_w1w0_phy(tp, 0x06, 0x0001, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168f_hw_phy_config(tp);
 }
 
 static void rtl8102e_hw_phy_config(struct rtl8169_private *tp)
@@ -4687,20 +4675,12 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 	RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en);
 }
 
-static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
+static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 	struct pci_dev *pdev = tp->pci_dev;
-	static const struct ephy_info e_info_8168f_1[] = {
-		{ 0x06, 0x00c0,	0x0020 },
-		{ 0x08, 0x0001,	0x0002 },
-		{ 0x09, 0x0000,	0x0080 },
-		{ 0x19, 0x0000,	0x0224 }
-	};
-
-	rtl_csi_access_enable_1(tp);
 
-	rtl_ephy_init(ioaddr, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
+	rtl_csi_access_enable_2(tp);
 
 	rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT);
 
@@ -4714,8 +4694,6 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
 	rtl_w1w0_eri(ioaddr, 0x1d0, ERIAR_MASK_0001, 0x10, 0x00, ERIAR_EXGMAC);
 	rtl_eri_write(ioaddr, 0xcc, ERIAR_MASK_1111, 0x00000050, ERIAR_EXGMAC);
 	rtl_eri_write(ioaddr, 0xd0, ERIAR_MASK_1111, 0x00000060, ERIAR_EXGMAC);
-	rtl_w1w0_eri(ioaddr, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00,
-		     ERIAR_EXGMAC);
 
 	RTL_W8(MaxTxPacketSize, EarlySize);
 
@@ -4723,15 +4701,32 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
 
 	RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO);
 	RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB);
-
-	/* Adjust EEE LED frequency */
-	RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07);
-
 	RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN);
 	RTL_W32(MISC, RTL_R32(MISC) | PWM_EN);
 	RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en);
 }
 
+static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+	static const struct ephy_info e_info_8168f_1[] = {
+		{ 0x06, 0x00c0,	0x0020 },
+		{ 0x08, 0x0001,	0x0002 },
+		{ 0x09, 0x0000,	0x0080 },
+		{ 0x19, 0x0000,	0x0224 }
+	};
+
+	rtl_hw_start_8168f(tp);
+
+	rtl_ephy_init(ioaddr, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
+
+	rtl_w1w0_eri(ioaddr, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00,
+		     ERIAR_EXGMAC);
+
+	/* Adjust EEE LED frequency */
+	RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07);
+}
+
 static void rtl_hw_start_8168(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-- 
1.7.7.6

^ permalink raw reply related

* [PATCH net-next v3 3/5] r8169: support RTL8402
From: Hayes Wang @ 2012-03-30  6:33 UTC (permalink / raw)
  To: romieu; +Cc: netdev, linux-kernel, Hayes Wang
In-Reply-To: <1333089184-1773-1-git-send-email-hayeswang@realtek.com>

Support the new chip RTL8402.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
 drivers/net/ethernet/realtek/r8169.c |  122 +++++++++++++++++++++++++++++++++-
 1 files changed, 121 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 268ed51..b7a21de 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -45,6 +45,7 @@
 #define FIRMWARE_8168F_1	"rtl_nic/rtl8168f-1.fw"
 #define FIRMWARE_8168F_2	"rtl_nic/rtl8168f-2.fw"
 #define FIRMWARE_8105E_1	"rtl_nic/rtl8105e-1.fw"
+#define FIRMWARE_8402_1		"rtl_nic/rtl8402-1.fw"
 
 #ifdef RTL8169_DEBUG
 #define assert(expr) \
@@ -134,6 +135,7 @@ enum mac_version {
 	RTL_GIGA_MAC_VER_34,
 	RTL_GIGA_MAC_VER_35,
 	RTL_GIGA_MAC_VER_36,
+	RTL_GIGA_MAC_VER_37,
 	RTL_GIGA_MAC_NONE   = 0xff,
 };
 
@@ -246,6 +248,9 @@ static const struct {
 	[RTL_GIGA_MAC_VER_36] =
 		_R("RTL8168f/8111f",	RTL_TD_1, FIRMWARE_8168F_2,
 							JUMBO_9K, false),
+	[RTL_GIGA_MAC_VER_37] =
+		_R("RTL8402",		RTL_TD_1, FIRMWARE_8402_1,
+							JUMBO_1K, true),
 };
 #undef _R
 
@@ -356,6 +361,9 @@ enum rtl8168_8101_registers {
 #define	CSIAR_BYTE_ENABLE		0x0f
 #define	CSIAR_BYTE_ENABLE_SHIFT		12
 #define	CSIAR_ADDR_MASK			0x0fff
+#define CSIAR_FUNC_CARD			0x00000000
+#define CSIAR_FUNC_SDIO			0x00010000
+#define CSIAR_FUNC_NIC			0x00020000
 	PMCH			= 0x6f,
 	EPHYAR			= 0x80,
 #define	EPHYAR_FLAG			0x80000000
@@ -774,6 +782,7 @@ MODULE_FIRMWARE(FIRMWARE_8168E_3);
 MODULE_FIRMWARE(FIRMWARE_8105E_1);
 MODULE_FIRMWARE(FIRMWARE_8168F_1);
 MODULE_FIRMWARE(FIRMWARE_8168F_2);
+MODULE_FIRMWARE(FIRMWARE_8402_1);
 
 static void rtl_lock_work(struct rtl8169_private *tp)
 {
@@ -1288,6 +1297,16 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 			rtl_eri_write(ioaddr, 0x1dc, ERIAR_MASK_1111,
 				      0x0000003f, ERIAR_EXGMAC);
 		}
+	} else if (tp->mac_version == RTL_GIGA_MAC_VER_37) {
+		if (RTL_R8(PHYstatus) & _10bps) {
+			rtl_eri_write(ioaddr, 0x1d0, ERIAR_MASK_0011,
+				      0x4d02, ERIAR_EXGMAC);
+			rtl_eri_write(ioaddr, 0x1dc, ERIAR_MASK_0011,
+				      0x0060, ERIAR_EXGMAC);
+		} else {
+			rtl_eri_write(ioaddr, 0x1d0, ERIAR_MASK_0011,
+				      0x0000, ERIAR_EXGMAC);
+		}
 	}
 }
 
@@ -1885,6 +1904,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 		{ 0x7c800000, 0x30000000,	RTL_GIGA_MAC_VER_11 },
 
 		/* 8101 family. */
+		{ 0x7c800000, 0x44000000,	RTL_GIGA_MAC_VER_37 },
 		{ 0x7cf00000, 0x40b00000,	RTL_GIGA_MAC_VER_30 },
 		{ 0x7cf00000, 0x40a00000,	RTL_GIGA_MAC_VER_30 },
 		{ 0x7cf00000, 0x40900000,	RTL_GIGA_MAC_VER_29 },
@@ -3119,6 +3139,25 @@ static void rtl8105e_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
 }
 
+static void rtl8402_hw_phy_config(struct rtl8169_private *tp)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	/* Disable ALDPS before setting firmware */
+	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl_writephy(tp, 0x18, 0x0310);
+	msleep(20);
+
+	rtl_apply_firmware(tp);
+
+	/* EEE setting */
+	rtl_eri_write(ioaddr, 0x1b0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
+	rtl_writephy(tp, 0x1f, 0x0004);
+	rtl_writephy(tp, 0x10, 0x401f);
+	rtl_writephy(tp, 0x19, 0x7030);
+	rtl_writephy(tp, 0x1f, 0x0000);
+}
+
 static void rtl_hw_phy_config(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
@@ -3207,6 +3246,10 @@ static void rtl_hw_phy_config(struct net_device *dev)
 		rtl8168f_2_hw_phy_config(tp);
 		break;
 
+	case RTL_GIGA_MAC_VER_37:
+		rtl8402_hw_phy_config(tp);
+		break;
+
 	default:
 		break;
 	}
@@ -3444,6 +3487,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_32:
 	case RTL_GIGA_MAC_VER_33:
 	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_37:
 		RTL_W32(RxConfig, RTL_R32(RxConfig) |
 			AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
 		break;
@@ -3665,6 +3709,7 @@ static void __devinit rtl_init_pll_power_ops(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_16:
 	case RTL_GIGA_MAC_VER_29:
 	case RTL_GIGA_MAC_VER_30:
+	case RTL_GIGA_MAC_VER_37:
 		ops->down	= r810x_pll_power_down;
 		ops->up		= r810x_pll_power_up;
 		break;
@@ -3974,7 +4019,8 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
 			udelay(20);
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
 	           tp->mac_version == RTL_GIGA_MAC_VER_35 ||
-	           tp->mac_version == RTL_GIGA_MAC_VER_36) {
+	           tp->mac_version == RTL_GIGA_MAC_VER_36 ||
+	           tp->mac_version == RTL_GIGA_MAC_VER_37) {
 		RTL_W8(ChipCmd, RTL_R8(ChipCmd) | StopReq);
 		while (!(RTL_R32(TxConfig) & TXCFG_EMPTY))
 			udelay(100);
@@ -4246,6 +4292,41 @@ static u32 r8169_csi_read(void __iomem *ioaddr, int addr)
 	return value;
 }
 
+static void r8402_csi_write(void __iomem *ioaddr, int addr, int value)
+{
+	unsigned int i;
+
+	RTL_W32(CSIDR, value);
+	RTL_W32(CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) |
+		CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT |
+		CSIAR_FUNC_NIC);
+
+	for (i = 0; i < 100; i++) {
+		if (!(RTL_R32(CSIAR) & CSIAR_FLAG))
+			break;
+		udelay(10);
+	}
+}
+
+static u32 r8402_csi_read(void __iomem *ioaddr, int addr)
+{
+	u32 value = ~0x00;
+	unsigned int i;
+
+	RTL_W32(CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC |
+		CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
+
+	for (i = 0; i < 100; i++) {
+		if (RTL_R32(CSIAR) & CSIAR_FLAG) {
+			value = RTL_R32(CSIDR);
+			break;
+		}
+		udelay(10);
+	}
+
+	return value;
+}
+
 static void __devinit rtl_init_csi_ops(struct rtl8169_private *tp)
 {
 	struct csi_ops *ops = &tp->csi_ops;
@@ -4269,6 +4350,11 @@ static void __devinit rtl_init_csi_ops(struct rtl8169_private *tp)
 		ops->read	= NULL;
 		break;
 
+	case RTL_GIGA_MAC_VER_37:
+		ops->write	= r8402_csi_write;
+		ops->read	= r8402_csi_read;
+		break;
+
 	default:
 		ops->write	= r8169_csi_write;
 		ops->read	= r8169_csi_read;
@@ -4854,6 +4940,36 @@ static void rtl_hw_start_8105e_2(struct rtl8169_private *tp)
 	rtl_ephy_write(ioaddr, 0x1e, rtl_ephy_read(ioaddr, 0x1e) | 0x8000);
 }
 
+static void rtl_hw_start_8402(struct rtl8169_private *tp)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+	static const struct ephy_info e_info_8402[] = {
+		{ 0x19,	0xffff, 0xff64 },
+		{ 0x1e,	0, 0x4000 }
+	};
+
+	rtl_csi_access_enable_2(tp);
+
+	/* Force LAN exit from ASPM if Rx/Tx are not idle */
+	RTL_W32(FuncEvent, RTL_R32(FuncEvent) | 0x002800);
+
+	RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO);
+	RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB);
+
+	rtl_ephy_init(ioaddr, e_info_8402, ARRAY_SIZE(e_info_8402));
+
+	rtl_tx_performance_tweak(tp->pci_dev, 0x5 << MAX_READ_REQUEST_SHIFT);
+
+	rtl_eri_write(ioaddr, 0xc8, ERIAR_MASK_1111, 0x00000002, ERIAR_EXGMAC);
+	rtl_eri_write(ioaddr, 0xe8, ERIAR_MASK_1111, 0x00000006, ERIAR_EXGMAC);
+	rtl_w1w0_eri(ioaddr, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC);
+	rtl_w1w0_eri(ioaddr, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC);
+	rtl_eri_write(ioaddr, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
+	rtl_eri_write(ioaddr, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
+	rtl_w1w0_eri(ioaddr, 0x0d4, ERIAR_MASK_0011, 0x0e00, 0xff00,
+		     ERIAR_EXGMAC);
+}
+
 static void rtl_hw_start_8101(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
@@ -4894,6 +5010,10 @@ static void rtl_hw_start_8101(struct net_device *dev)
 	case RTL_GIGA_MAC_VER_30:
 		rtl_hw_start_8105e_2(tp);
 		break;
+
+	case RTL_GIGA_MAC_VER_37:
+		rtl_hw_start_8402(tp);
+		break;
 	}
 
 	RTL_W8(Cfg9346, Cfg9346_Lock);
-- 
1.7.7.6

^ permalink raw reply related

* [PATCH net-next v3 2/5] r8169: add csi_opt
From: Hayes Wang @ 2012-03-30  6:33 UTC (permalink / raw)
  To: romieu; +Cc: netdev, linux-kernel, Hayes Wang
In-Reply-To: <1333089184-1773-1-git-send-email-hayeswang@realtek.com>

Modify the CSI relative functions by using csi_opt method.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
 drivers/net/ethernet/realtek/r8169.c |  300 ++++++++++++++++++++++------------
 1 files changed, 194 insertions(+), 106 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 3edb996..268ed51 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -717,6 +717,11 @@ struct rtl8169_private {
 		void (*disable)(struct rtl8169_private *);
 	} jumbo_ops;
 
+	struct csi_ops {
+		void (*write)(void __iomem *, int, int);
+		u32 (*read)(void __iomem *, int);
+	} csi_ops;
+
 	int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv);
 	int (*get_settings)(struct net_device *, struct ethtool_cmd *);
 	void (*phy_reset_enable)(struct rtl8169_private *tp);
@@ -1079,40 +1084,6 @@ static u16 rtl_ephy_read(void __iomem *ioaddr, int reg_addr)
 	return value;
 }
 
-static void rtl_csi_write(void __iomem *ioaddr, int addr, int value)
-{
-	unsigned int i;
-
-	RTL_W32(CSIDR, value);
-	RTL_W32(CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) |
-		CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
-
-	for (i = 0; i < 100; i++) {
-		if (!(RTL_R32(CSIAR) & CSIAR_FLAG))
-			break;
-		udelay(10);
-	}
-}
-
-static u32 rtl_csi_read(void __iomem *ioaddr, int addr)
-{
-	u32 value = ~0x00;
-	unsigned int i;
-
-	RTL_W32(CSIAR, (addr & CSIAR_ADDR_MASK) |
-		CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
-
-	for (i = 0; i < 100; i++) {
-		if (RTL_R32(CSIAR) & CSIAR_FLAG) {
-			value = RTL_R32(CSIDR);
-			break;
-		}
-		udelay(10);
-	}
-
-	return value;
-}
-
 static
 void rtl_eri_write(void __iomem *ioaddr, int addr, u32 mask, u32 val, int type)
 {
@@ -4209,22 +4180,100 @@ static void rtl_hw_start_8169(struct net_device *dev)
 	RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xF000);
 }
 
-static void rtl_csi_access_enable(void __iomem *ioaddr, u32 bits)
+static void rtl_csi_write(struct rtl8169_private *tp, int addr, int value)
+{
+	if (tp->csi_ops.write)
+		tp->csi_ops.write(tp->mmio_addr, addr, value);
+}
+
+static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
+{
+	if (tp->csi_ops.read)
+		return tp->csi_ops.read(tp->mmio_addr, addr);
+	else
+		return ~0;
+}
+
+static void rtl_csi_access_enable(struct rtl8169_private *tp, u32 bits)
 {
 	u32 csi;
 
-	csi = rtl_csi_read(ioaddr, 0x070c) & 0x00ffffff;
-	rtl_csi_write(ioaddr, 0x070c, csi | bits);
+	csi = rtl_csi_read(tp, 0x070c) & 0x00ffffff;
+	rtl_csi_write(tp, 0x070c, csi | bits);
+}
+
+static void rtl_csi_access_enable_1(struct rtl8169_private *tp)
+{
+	rtl_csi_access_enable(tp, 0x17000000);
 }
 
-static void rtl_csi_access_enable_1(void __iomem *ioaddr)
+static void rtl_csi_access_enable_2(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable(ioaddr, 0x17000000);
+	rtl_csi_access_enable(tp, 0x27000000);
 }
 
-static void rtl_csi_access_enable_2(void __iomem *ioaddr)
+static void r8169_csi_write(void __iomem *ioaddr, int addr, int value)
 {
-	rtl_csi_access_enable(ioaddr, 0x27000000);
+	unsigned int i;
+
+	RTL_W32(CSIDR, value);
+	RTL_W32(CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) |
+		CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
+
+	for (i = 0; i < 100; i++) {
+		if (!(RTL_R32(CSIAR) & CSIAR_FLAG))
+			break;
+		udelay(10);
+	}
+}
+
+static u32 r8169_csi_read(void __iomem *ioaddr, int addr)
+{
+	u32 value = ~0x00;
+	unsigned int i;
+
+	RTL_W32(CSIAR, (addr & CSIAR_ADDR_MASK) |
+		CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
+
+	for (i = 0; i < 100; i++) {
+		if (RTL_R32(CSIAR) & CSIAR_FLAG) {
+			value = RTL_R32(CSIDR);
+			break;
+		}
+		udelay(10);
+	}
+
+	return value;
+}
+
+static void __devinit rtl_init_csi_ops(struct rtl8169_private *tp)
+{
+	struct csi_ops *ops = &tp->csi_ops;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_01:
+	case RTL_GIGA_MAC_VER_02:
+	case RTL_GIGA_MAC_VER_03:
+	case RTL_GIGA_MAC_VER_04:
+	case RTL_GIGA_MAC_VER_05:
+	case RTL_GIGA_MAC_VER_06:
+	case RTL_GIGA_MAC_VER_10:
+	case RTL_GIGA_MAC_VER_11:
+	case RTL_GIGA_MAC_VER_12:
+	case RTL_GIGA_MAC_VER_13:
+	case RTL_GIGA_MAC_VER_14:
+	case RTL_GIGA_MAC_VER_15:
+	case RTL_GIGA_MAC_VER_16:
+	case RTL_GIGA_MAC_VER_17:
+		ops->write	= NULL;
+		ops->read	= NULL;
+		break;
+
+	default:
+		ops->write	= r8169_csi_write;
+		ops->read	= r8169_csi_read;
+		break;
+	}
 }
 
 struct ephy_info {
@@ -4281,8 +4330,11 @@ static void rtl_enable_clock_request(struct pci_dev *pdev)
 	PktCntrDisable | \
 	Mac_dbgo_sel)
 
-static void rtl_hw_start_8168bb(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168bb(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
+
 	RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en);
 
 	RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
@@ -4291,17 +4343,22 @@ static void rtl_hw_start_8168bb(void __iomem *ioaddr, struct pci_dev *pdev)
 		(0x5 << MAX_READ_REQUEST_SHIFT) | PCI_EXP_DEVCTL_NOSNOOP_EN);
 }
 
-static void rtl_hw_start_8168bef(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168bef(struct rtl8169_private *tp)
 {
-	rtl_hw_start_8168bb(ioaddr, pdev);
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	rtl_hw_start_8168bb(tp);
 
 	RTL_W8(MaxTxPacketSize, TxPacketMax);
 
 	RTL_W8(Config4, RTL_R8(Config4) & ~(1 << 0));
 }
 
-static void __rtl_hw_start_8168cp(void __iomem *ioaddr, struct pci_dev *pdev)
+static void __rtl_hw_start_8168cp(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
+
 	RTL_W8(Config1, RTL_R8(Config1) | Speed_down);
 
 	RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en);
@@ -4313,8 +4370,9 @@ static void __rtl_hw_start_8168cp(void __iomem *ioaddr, struct pci_dev *pdev)
 	RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
 }
 
-static void rtl_hw_start_8168cp_1(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
 	static const struct ephy_info e_info_8168cp[] = {
 		{ 0x01, 0,	0x0001 },
 		{ 0x02, 0x0800,	0x1000 },
@@ -4323,16 +4381,19 @@ static void rtl_hw_start_8168cp_1(void __iomem *ioaddr, struct pci_dev *pdev)
 		{ 0x07, 0,	0x2000 }
 	};
 
-	rtl_csi_access_enable_2(ioaddr);
+	rtl_csi_access_enable_2(tp);
 
 	rtl_ephy_init(ioaddr, e_info_8168cp, ARRAY_SIZE(e_info_8168cp));
 
-	__rtl_hw_start_8168cp(ioaddr, pdev);
+	__rtl_hw_start_8168cp(tp);
 }
 
-static void rtl_hw_start_8168cp_2(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(ioaddr);
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
+
+	rtl_csi_access_enable_2(tp);
 
 	RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en);
 
@@ -4341,9 +4402,12 @@ static void rtl_hw_start_8168cp_2(void __iomem *ioaddr, struct pci_dev *pdev)
 	RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
 }
 
-static void rtl_hw_start_8168cp_3(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(ioaddr);
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
+
+	rtl_csi_access_enable_2(tp);
 
 	RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en);
 
@@ -4357,52 +4421,57 @@ static void rtl_hw_start_8168cp_3(void __iomem *ioaddr, struct pci_dev *pdev)
 	RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
 }
 
-static void rtl_hw_start_8168c_1(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168c_1(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
 	static const struct ephy_info e_info_8168c_1[] = {
 		{ 0x02, 0x0800,	0x1000 },
 		{ 0x03, 0,	0x0002 },
 		{ 0x06, 0x0080,	0x0000 }
 	};
 
-	rtl_csi_access_enable_2(ioaddr);
+	rtl_csi_access_enable_2(tp);
 
 	RTL_W8(DBG_REG, 0x06 | FIX_NAK_1 | FIX_NAK_2);
 
 	rtl_ephy_init(ioaddr, e_info_8168c_1, ARRAY_SIZE(e_info_8168c_1));
 
-	__rtl_hw_start_8168cp(ioaddr, pdev);
+	__rtl_hw_start_8168cp(tp);
 }
 
-static void rtl_hw_start_8168c_2(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168c_2(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
 	static const struct ephy_info e_info_8168c_2[] = {
 		{ 0x01, 0,	0x0001 },
 		{ 0x03, 0x0400,	0x0220 }
 	};
 
-	rtl_csi_access_enable_2(ioaddr);
+	rtl_csi_access_enable_2(tp);
 
 	rtl_ephy_init(ioaddr, e_info_8168c_2, ARRAY_SIZE(e_info_8168c_2));
 
-	__rtl_hw_start_8168cp(ioaddr, pdev);
+	__rtl_hw_start_8168cp(tp);
 }
 
-static void rtl_hw_start_8168c_3(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168c_3(struct rtl8169_private *tp)
 {
-	rtl_hw_start_8168c_2(ioaddr, pdev);
+	rtl_hw_start_8168c_2(tp);
 }
 
-static void rtl_hw_start_8168c_4(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168c_4(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(ioaddr);
+	rtl_csi_access_enable_2(tp);
 
-	__rtl_hw_start_8168cp(ioaddr, pdev);
+	__rtl_hw_start_8168cp(tp);
 }
 
-static void rtl_hw_start_8168d(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168d(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(ioaddr);
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
+
+	rtl_csi_access_enable_2(tp);
 
 	rtl_disable_clock_request(pdev);
 
@@ -4413,9 +4482,12 @@ static void rtl_hw_start_8168d(void __iomem *ioaddr, struct pci_dev *pdev)
 	RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
 }
 
-static void rtl_hw_start_8168dp(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168dp(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_1(ioaddr);
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
+
+	rtl_csi_access_enable_1(tp);
 
 	rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT);
 
@@ -4424,8 +4496,10 @@ static void rtl_hw_start_8168dp(void __iomem *ioaddr, struct pci_dev *pdev)
 	rtl_disable_clock_request(pdev);
 }
 
-static void rtl_hw_start_8168d_4(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168d_4(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
 	static const struct ephy_info e_info_8168d_4[] = {
 		{ 0x0b, ~0,	0x48 },
 		{ 0x19, 0x20,	0x50 },
@@ -4433,7 +4507,7 @@ static void rtl_hw_start_8168d_4(void __iomem *ioaddr, struct pci_dev *pdev)
 	};
 	int i;
 
-	rtl_csi_access_enable_1(ioaddr);
+	rtl_csi_access_enable_1(tp);
 
 	rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT);
 
@@ -4450,8 +4524,10 @@ static void rtl_hw_start_8168d_4(void __iomem *ioaddr, struct pci_dev *pdev)
 	rtl_enable_clock_request(pdev);
 }
 
-static void rtl_hw_start_8168e_1(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168e_1(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
 	static const struct ephy_info e_info_8168e_1[] = {
 		{ 0x00, 0x0200,	0x0100 },
 		{ 0x00, 0x0000,	0x0004 },
@@ -4468,7 +4544,7 @@ static void rtl_hw_start_8168e_1(void __iomem *ioaddr, struct pci_dev *pdev)
 		{ 0x0a, 0x0000,	0x0040 }
 	};
 
-	rtl_csi_access_enable_2(ioaddr);
+	rtl_csi_access_enable_2(tp);
 
 	rtl_ephy_init(ioaddr, e_info_8168e_1, ARRAY_SIZE(e_info_8168e_1));
 
@@ -4485,14 +4561,16 @@ static void rtl_hw_start_8168e_1(void __iomem *ioaddr, struct pci_dev *pdev)
 	RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en);
 }
 
-static void rtl_hw_start_8168e_2(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
 	static const struct ephy_info e_info_8168e_2[] = {
 		{ 0x09, 0x0000,	0x0080 },
 		{ 0x19, 0x0000,	0x0224 }
 	};
 
-	rtl_csi_access_enable_1(ioaddr);
+	rtl_csi_access_enable_1(tp);
 
 	rtl_ephy_init(ioaddr, e_info_8168e_2, ARRAY_SIZE(e_info_8168e_2));
 
@@ -4523,8 +4601,10 @@ static void rtl_hw_start_8168e_2(void __iomem *ioaddr, struct pci_dev *pdev)
 	RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en);
 }
 
-static void rtl_hw_start_8168f_1(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
 	static const struct ephy_info e_info_8168f_1[] = {
 		{ 0x06, 0x00c0,	0x0020 },
 		{ 0x08, 0x0001,	0x0002 },
@@ -4532,7 +4612,7 @@ static void rtl_hw_start_8168f_1(void __iomem *ioaddr, struct pci_dev *pdev)
 		{ 0x19, 0x0000,	0x0224 }
 	};
 
-	rtl_csi_access_enable_1(ioaddr);
+	rtl_csi_access_enable_1(tp);
 
 	rtl_ephy_init(ioaddr, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
 
@@ -4570,7 +4650,6 @@ static void rtl_hw_start_8168(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
-	struct pci_dev *pdev = tp->pci_dev;
 
 	RTL_W8(Cfg9346, Cfg9346_Unlock);
 
@@ -4601,67 +4680,67 @@ static void rtl_hw_start_8168(struct net_device *dev)
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_11:
-		rtl_hw_start_8168bb(ioaddr, pdev);
+		rtl_hw_start_8168bb(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_12:
 	case RTL_GIGA_MAC_VER_17:
-		rtl_hw_start_8168bef(ioaddr, pdev);
+		rtl_hw_start_8168bef(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_18:
-		rtl_hw_start_8168cp_1(ioaddr, pdev);
+		rtl_hw_start_8168cp_1(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_19:
-		rtl_hw_start_8168c_1(ioaddr, pdev);
+		rtl_hw_start_8168c_1(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_20:
-		rtl_hw_start_8168c_2(ioaddr, pdev);
+		rtl_hw_start_8168c_2(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_21:
-		rtl_hw_start_8168c_3(ioaddr, pdev);
+		rtl_hw_start_8168c_3(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_22:
-		rtl_hw_start_8168c_4(ioaddr, pdev);
+		rtl_hw_start_8168c_4(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_23:
-		rtl_hw_start_8168cp_2(ioaddr, pdev);
+		rtl_hw_start_8168cp_2(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_24:
-		rtl_hw_start_8168cp_3(ioaddr, pdev);
+		rtl_hw_start_8168cp_3(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_25:
 	case RTL_GIGA_MAC_VER_26:
 	case RTL_GIGA_MAC_VER_27:
-		rtl_hw_start_8168d(ioaddr, pdev);
+		rtl_hw_start_8168d(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_28:
-		rtl_hw_start_8168d_4(ioaddr, pdev);
+		rtl_hw_start_8168d_4(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_31:
-		rtl_hw_start_8168dp(ioaddr, pdev);
+		rtl_hw_start_8168dp(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_32:
 	case RTL_GIGA_MAC_VER_33:
-		rtl_hw_start_8168e_1(ioaddr, pdev);
+		rtl_hw_start_8168e_1(tp);
 		break;
 	case RTL_GIGA_MAC_VER_34:
-		rtl_hw_start_8168e_2(ioaddr, pdev);
+		rtl_hw_start_8168e_2(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_35:
 	case RTL_GIGA_MAC_VER_36:
-		rtl_hw_start_8168f_1(ioaddr, pdev);
+		rtl_hw_start_8168f_1(tp);
 		break;
 
 	default:
@@ -4688,8 +4767,10 @@ static void rtl_hw_start_8168(struct net_device *dev)
 	PktCntrDisable | \
 	Mac_dbgo_sel)
 
-static void rtl_hw_start_8102e_1(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
 	static const struct ephy_info e_info_8102e_1[] = {
 		{ 0x01,	0, 0x6e65 },
 		{ 0x02,	0, 0x091f },
@@ -4702,7 +4783,7 @@ static void rtl_hw_start_8102e_1(void __iomem *ioaddr, struct pci_dev *pdev)
 	};
 	u8 cfg1;
 
-	rtl_csi_access_enable_2(ioaddr);
+	rtl_csi_access_enable_2(tp);
 
 	RTL_W8(DBG_REG, FIX_NAK_1);
 
@@ -4719,9 +4800,12 @@ static void rtl_hw_start_8102e_1(void __iomem *ioaddr, struct pci_dev *pdev)
 	rtl_ephy_init(ioaddr, e_info_8102e_1, ARRAY_SIZE(e_info_8102e_1));
 }
 
-static void rtl_hw_start_8102e_2(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8102e_2(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(ioaddr);
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
+
+	rtl_csi_access_enable_2(tp);
 
 	rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT);
 
@@ -4729,15 +4813,16 @@ static void rtl_hw_start_8102e_2(void __iomem *ioaddr, struct pci_dev *pdev)
 	RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en);
 }
 
-static void rtl_hw_start_8102e_3(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8102e_3(struct rtl8169_private *tp)
 {
-	rtl_hw_start_8102e_2(ioaddr, pdev);
+	rtl_hw_start_8102e_2(tp);
 
-	rtl_ephy_write(ioaddr, 0x03, 0xc2f9);
+	rtl_ephy_write(tp->mmio_addr, 0x03, 0xc2f9);
 }
 
-static void rtl_hw_start_8105e_1(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8105e_1(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
 	static const struct ephy_info e_info_8105e_1[] = {
 		{ 0x07,	0, 0x4000 },
 		{ 0x19,	0, 0x0200 },
@@ -4761,9 +4846,11 @@ static void rtl_hw_start_8105e_1(void __iomem *ioaddr, struct pci_dev *pdev)
 	rtl_ephy_init(ioaddr, e_info_8105e_1, ARRAY_SIZE(e_info_8105e_1));
 }
 
-static void rtl_hw_start_8105e_2(void __iomem *ioaddr, struct pci_dev *pdev)
+static void rtl_hw_start_8105e_2(struct rtl8169_private *tp)
 {
-	rtl_hw_start_8105e_1(ioaddr, pdev);
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	rtl_hw_start_8105e_1(tp);
 	rtl_ephy_write(ioaddr, 0x1e, rtl_ephy_read(ioaddr, 0x1e) | 0x8000);
 }
 
@@ -4790,22 +4877,22 @@ static void rtl_hw_start_8101(struct net_device *dev)
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_07:
-		rtl_hw_start_8102e_1(ioaddr, pdev);
+		rtl_hw_start_8102e_1(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_08:
-		rtl_hw_start_8102e_3(ioaddr, pdev);
+		rtl_hw_start_8102e_3(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_09:
-		rtl_hw_start_8102e_2(ioaddr, pdev);
+		rtl_hw_start_8102e_2(tp);
 		break;
 
 	case RTL_GIGA_MAC_VER_29:
-		rtl_hw_start_8105e_1(ioaddr, pdev);
+		rtl_hw_start_8105e_1(tp);
 		break;
 	case RTL_GIGA_MAC_VER_30:
-		rtl_hw_start_8105e_2(ioaddr, pdev);
+		rtl_hw_start_8105e_2(tp);
 		break;
 	}
 
@@ -6199,6 +6286,7 @@ rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	rtl_init_mdio_ops(tp);
 	rtl_init_pll_power_ops(tp);
 	rtl_init_jumbo_ops(tp);
+	rtl_init_csi_ops(tp);
 
 	rtl8169_print_mac_version(tp);
 
-- 
1.7.7.6

^ permalink raw reply related

* [PATCH net-next v3 1/5] r8169: modify pll power function
From: Hayes Wang @ 2012-03-30  6:33 UTC (permalink / raw)
  To: romieu; +Cc: netdev, linux-kernel, Hayes Wang

Adjust r810x_pll_power_down, r810x_pll_power_up, and r8168_pll_power_up.
Always power up device during rtl_open. For r810x, turn off more power
when the WOL is disabled.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
 drivers/net/ethernet/realtek/r8169.c |   37 +++++++++++++++++++++++++++------
 1 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 27c358c..3edb996 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -3508,15 +3508,45 @@ static void r810x_phy_power_up(struct rtl8169_private *tp)
 
 static void r810x_pll_power_down(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+
 	if (rtl_wol_pll_power_down(tp))
 		return;
 
 	r810x_phy_power_down(tp);
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_07:
+	case RTL_GIGA_MAC_VER_08:
+	case RTL_GIGA_MAC_VER_09:
+	case RTL_GIGA_MAC_VER_10:
+	case RTL_GIGA_MAC_VER_13:
+	case RTL_GIGA_MAC_VER_16:
+		break;
+	default:
+		RTL_W8(PMCH, RTL_R8(PMCH) & ~0x80);
+		break;
+	}
 }
 
 static void r810x_pll_power_up(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+
 	r810x_phy_power_up(tp);
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_07:
+	case RTL_GIGA_MAC_VER_08:
+	case RTL_GIGA_MAC_VER_09:
+	case RTL_GIGA_MAC_VER_10:
+	case RTL_GIGA_MAC_VER_13:
+	case RTL_GIGA_MAC_VER_16:
+		break;
+	default:
+		RTL_W8(PMCH, RTL_R8(PMCH) | 0x80);
+		break;
+	}
 }
 
 static void r8168_phy_power_up(struct rtl8169_private *tp)
@@ -3620,13 +3650,6 @@ static void r8168_pll_power_up(struct rtl8169_private *tp)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 
-	if ((tp->mac_version == RTL_GIGA_MAC_VER_27 ||
-	     tp->mac_version == RTL_GIGA_MAC_VER_28 ||
-	     tp->mac_version == RTL_GIGA_MAC_VER_31) &&
-	    r8168dp_check_dash(tp)) {
-		return;
-	}
-
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_25:
 	case RTL_GIGA_MAC_VER_26:
-- 
1.7.7.6

^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox