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

Two cases of overlapping changes, nothing fancy.

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 29 insertions, 255 deletions

diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 133433d181ba..393d251798c0 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -732,9 +732,6 @@ static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[],
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
-	static int jmp_label1 = -1;
-	static int jmp_label2 = -1;
-	static int jmp_label3 = -1;
 	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 
@@ -753,79 +750,23 @@ static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[],
 		/* mov ecx,src_lo */
 		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
 
-	/* cmp ecx,32 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
-	/* Jumps when >= 32 */
-	if (is_imm8(jmp_label(jmp_label1, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
-	/* < 32 */
-	/* shl dreg_hi,cl */
-	EMIT2(0xD3, add_1reg(0xE0, dreg_hi));
-	/* mov ebx,dreg_lo */
-	EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+	/* shld dreg_hi,dreg_lo,cl */
+	EMIT3(0x0F, 0xA5, add_2reg(0xC0, dreg_hi, dreg_lo));
 	/* shl dreg_lo,cl */
 	EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
 
-	/* IA32_ECX = -IA32_ECX + 32 */
-	/* neg ecx */
-	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-	/* add ecx,32 */
-	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+	/* if ecx >= 32, mov dreg_lo into dreg_hi and clear dreg_lo */
 
-	/* shr ebx,cl */
-	EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
-	/* or dreg_hi,ebx */
-	EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
-
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 32 */
-	if (jmp_label1 == -1)
-		jmp_label1 = cnt;
-
-	/* cmp ecx,64 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
-	/* Jumps when >= 64 */
-	if (is_imm8(jmp_label(jmp_label2, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* skip the next two instructions (4 bytes) when < 32 */
+	EMIT2(IA32_JB, 4);
 
-	/* >= 32 && < 64 */
-	/* sub ecx,32 */
-	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
-	/* shl dreg_lo,cl */
-	EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
 	/* mov dreg_hi,dreg_lo */
 	EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
-
 	/* xor dreg_lo,dreg_lo */
 	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
 
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 64 */
-	if (jmp_label2 == -1)
-		jmp_label2 = cnt;
-	/* xor dreg_lo,dreg_lo */
-	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
-	/* xor dreg_hi,dreg_hi */
-	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
-
-	if (jmp_label3 == -1)
-		jmp_label3 = cnt;
-
 	if (dstk) {
 		/* mov dword ptr [ebp+off],dreg_lo */
 		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
@@ -844,9 +785,6 @@ static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[],
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
-	static int jmp_label1 = -1;
-	static int jmp_label2 = -1;
-	static int jmp_label3 = -1;
 	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 
@@ -865,79 +803,23 @@ static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[],
 		/* mov ecx,src_lo */
 		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
 
-	/* cmp ecx,32 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
-	/* Jumps when >= 32 */
-	if (is_imm8(jmp_label(jmp_label1, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
-	/* < 32 */
-	/* lshr dreg_lo,cl */
-	EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
-	/* mov ebx,dreg_hi */
-	EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
-	/* ashr dreg_hi,cl */
+	/* shrd dreg_lo,dreg_hi,cl */
+	EMIT3(0x0F, 0xAD, add_2reg(0xC0, dreg_lo, dreg_hi));
+	/* sar dreg_hi,cl */
 	EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
 
-	/* IA32_ECX = -IA32_ECX + 32 */
-	/* neg ecx */
-	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-	/* add ecx,32 */
-	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-	/* shl ebx,cl */
-	EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
-	/* or dreg_lo,ebx */
-	EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+	/* if ecx >= 32, mov dreg_hi to dreg_lo and set/clear dreg_hi depending on sign */
 
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 32 */
-	if (jmp_label1 == -1)
-		jmp_label1 = cnt;
-
-	/* cmp ecx,64 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
-	/* Jumps when >= 64 */
-	if (is_imm8(jmp_label(jmp_label2, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* skip the next two instructions (5 bytes) when < 32 */
+	EMIT2(IA32_JB, 5);
 
-	/* >= 32 && < 64 */
-	/* sub ecx,32 */
-	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
-	/* ashr dreg_hi,cl */
-	EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
 	/* mov dreg_lo,dreg_hi */
 	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
-
-	/* ashr dreg_hi,imm8 */
+	/* sar dreg_hi,31 */
 	EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
 
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 64 */
-	if (jmp_label2 == -1)
-		jmp_label2 = cnt;
-	/* ashr dreg_hi,imm8 */
-	EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
-	/* mov dreg_lo,dreg_hi */
-	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
-
-	if (jmp_label3 == -1)
-		jmp_label3 = cnt;
-
 	if (dstk) {
 		/* mov dword ptr [ebp+off],dreg_lo */
 		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
@@ -956,9 +838,6 @@ static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
-	static int jmp_label1 = -1;
-	static int jmp_label2 = -1;
-	static int jmp_label3 = -1;
 	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 
@@ -977,77 +856,23 @@ static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
 		/* mov ecx,src_lo */
 		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
 
-	/* cmp ecx,32 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
-	/* Jumps when >= 32 */
-	if (is_imm8(jmp_label(jmp_label1, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
-	/* < 32 */
-	/* lshr dreg_lo,cl */
-	EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
-	/* mov ebx,dreg_hi */
-	EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+	/* shrd dreg_lo,dreg_hi,cl */
+	EMIT3(0x0F, 0xAD, add_2reg(0xC0, dreg_lo, dreg_hi));
 	/* shr dreg_hi,cl */
 	EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
 
-	/* IA32_ECX = -IA32_ECX + 32 */
-	/* neg ecx */
-	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-	/* add ecx,32 */
-	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-	/* shl ebx,cl */
-	EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
-	/* or dreg_lo,ebx */
-	EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
-
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+	/* if ecx >= 32, mov dreg_hi to dreg_lo and clear dreg_hi */
 
-	/* >= 32 */
-	if (jmp_label1 == -1)
-		jmp_label1 = cnt;
-	/* cmp ecx,64 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
-	/* Jumps when >= 64 */
-	if (is_imm8(jmp_label(jmp_label2, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* skip the next two instructions (4 bytes) when < 32 */
+	EMIT2(IA32_JB, 4);
 
-	/* >= 32 && < 64 */
-	/* sub ecx,32 */
-	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
-	/* shr dreg_hi,cl */
-	EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
 	/* mov dreg_lo,dreg_hi */
 	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
 	/* xor dreg_hi,dreg_hi */
 	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 64 */
-	if (jmp_label2 == -1)
-		jmp_label2 = cnt;
-	/* xor dreg_lo,dreg_lo */
-	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
-	/* xor dreg_hi,dreg_hi */
-	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
-
-	if (jmp_label3 == -1)
-		jmp_label3 = cnt;
-
 	if (dstk) {
 		/* mov dword ptr [ebp+off],dreg_lo */
 		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
@@ -1077,27 +902,10 @@ static inline void emit_ia32_lsh_i64(const u8 dst[], const u32 val,
 	}
 	/* Do LSH operation */
 	if (val < 32) {
-		/* shl dreg_hi,imm8 */
-		EMIT3(0xC1, add_1reg(0xE0, dreg_hi), val);
-		/* mov ebx,dreg_lo */
-		EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+		/* shld dreg_hi,dreg_lo,imm8 */
+		EMIT4(0x0F, 0xA4, add_2reg(0xC0, dreg_hi, dreg_lo), val);
 		/* shl dreg_lo,imm8 */
 		EMIT3(0xC1, add_1reg(0xE0, dreg_lo), val);
-
-		/* IA32_ECX = 32 - val */
-		/* mov ecx,val */
-		EMIT2(0xB1, val);
-		/* movzx ecx,ecx */
-		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-		/* neg ecx */
-		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-		/* add ecx,32 */
-		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-		/* shr ebx,cl */
-		EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
-		/* or dreg_hi,ebx */
-		EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
 	} else if (val >= 32 && val < 64) {
 		u32 value = val - 32;
 
@@ -1143,27 +951,10 @@ static inline void emit_ia32_rsh_i64(const u8 dst[], const u32 val,
 
 	/* Do RSH operation */
 	if (val < 32) {
-		/* shr dreg_lo,imm8 */
-		EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
-		/* mov ebx,dreg_hi */
-		EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+		/* shrd dreg_lo,dreg_hi,imm8 */
+		EMIT4(0x0F, 0xAC, add_2reg(0xC0, dreg_lo, dreg_hi), val);
 		/* shr dreg_hi,imm8 */
 		EMIT3(0xC1, add_1reg(0xE8, dreg_hi), val);
-
-		/* IA32_ECX = 32 - val */
-		/* mov ecx,val */
-		EMIT2(0xB1, val);
-		/* movzx ecx,ecx */
-		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-		/* neg ecx */
-		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-		/* add ecx,32 */
-		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-		/* shl ebx,cl */
-		EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
-		/* or dreg_lo,ebx */
-		EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
 	} else if (val >= 32 && val < 64) {
 		u32 value = val - 32;
 
@@ -1208,27 +999,10 @@ static inline void emit_ia32_arsh_i64(const u8 dst[], const u32 val,
 	}
 	/* Do RSH operation */
 	if (val < 32) {
-		/* shr dreg_lo,imm8 */
-		EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
-		/* mov ebx,dreg_hi */
-		EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+		/* shrd dreg_lo,dreg_hi,imm8 */
+		EMIT4(0x0F, 0xAC, add_2reg(0xC0, dreg_lo, dreg_hi), val);
 		/* ashr dreg_hi,imm8 */
 		EMIT3(0xC1, add_1reg(0xF8, dreg_hi), val);
-
-		/* IA32_ECX = 32 - val */
-		/* mov ecx,val */
-		EMIT2(0xB1, val);
-		/* movzx ecx,ecx */
-		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-		/* neg ecx */
-		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-		/* add ecx,32 */
-		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-		/* shl ebx,cl */
-		EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
-		/* or dreg_lo,ebx */
-		EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
 	} else if (val >= 32 && val < 64) {
 		u32 value = val - 32;