[PATCH] powerpc: emulate power5 popcntb instruction

[Will Schmidt]

In an attempt to make it easier for a power5 optimized app to run on a 
power4 or a 970 or random earlier machine, this provides emulation of
the popcntb instruction.    Rewritten to use a slicker algorithm as
suggested by Segher.   I left a 'tmp' variable in play, as it seemed
cleaner to use tmp than referring to regs->gpr[rs] and [ra] multiple
times within the magic algorithm.  

Also tested on power4 with both 32 and 64 userspace this time.
*blush*.  :-) 


Signed-off-by: Will Schmidt <will_schmidt at vnet.ibm.com>

---

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 2105767..a0e80dd 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -588,6 +588,8 @@ #define INST_LSWX		0x7c00042a
 #define INST_STSWI		0x7c0005aa
 #define INST_STSWX		0x7c00052a
 
+#define INST_POPCNTB		0x7c0000f4
+
 static int emulate_string_inst(struct pt_regs *regs, u32 instword)
 {
 	u8 rT = (instword >> 21) & 0x1f;
@@ -656,6 +658,23 @@ static int emulate_string_inst(struct pt
 	return 0;
 }
 
+static int emulate_popcntb_inst(struct pt_regs *regs, u32 instword)
+{
+	u32 ra,rs;
+	unsigned long tmp;
+
+	ra = (instword >> 16) & 0x1f;
+	rs = (instword >> 21) & 0x1f;
+
+	tmp = regs->gpr[rs];
+	tmp = tmp - ((tmp >> 1) & 0x5555555555555555);
+	tmp = (tmp & 0x3333333333333333) + ((tmp >> 2) & 0x3333333333333333);
+	tmp = (tmp + (tmp >> 4)) & 0x0f0f0f0f0f0f0f0f;
+	regs->gpr[ra] = tmp;
+
+	return 0;
+}
+
 static int emulate_instruction(struct pt_regs *regs)
 {
 	u32 instword;
@@ -693,6 +712,11 @@ static int emulate_instruction(struct pt
 	if ((instword & INST_STRING_GEN_MASK) == INST_STRING)
 		return emulate_string_inst(regs, instword);
 
+	/* Emulate the popcntb (Population Count Bytes) instruction. */
+	if ((instword & INST_POPCNTB) == INST_POPCNTB) {
+		return emulate_popcntb_inst(regs, instword);
+	}
+
 	return -EINVAL;
 }