[PATCH] i386: Convert i386 PDA code to use %fs

Convert the PDA code to use %fs rather than %gs as the segment for
per-processor data.  This is because some processors show a small but
measurable performance gain for reloading a NULL segment selector (as %fs
generally is in user-space) versus a non-NULL one (as %gs generally is).

On modern processors the difference is very small, perhaps undetectable.
Some old AMD "K6 3D+" processors are noticably slower when %fs is used
rather than %gs; I have no idea why this might be, but I think they're
sufficiently rare that it doesn't matter much.

This patch also fixes the math emulator, which had not been adjusted to
match the changed struct pt_regs.

[frederik.deweerdt@gmail.com: fixit with gdb]
[mingo@elte.hu: Fix KVM too]

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Ian Campbell <Ian.Campbell@XenSource.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Zachary Amsden <zach@vmware.com>
Cc: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: Frederik Deweerdt <frederik.deweerdt@gmail.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>

1 files changed, 8 insertions, 8 deletions

diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c
index af8aabe8580..4a8f8a25972 100644
--- a/arch/i386/kernel/ptrace.c
+++ b/arch/i386/kernel/ptrace.c
@@ -89,14 +89,14 @@ static int putreg(struct task_struct *child,
 	unsigned long regno, unsigned long value)
 {
 	switch (regno >> 2) {
-		case FS:
+		case GS:
 			if (value && (value & 3) != 3)
 				return -EIO;
-			child->thread.fs = value;
+			child->thread.gs = value;
 			return 0;
 		case DS:
 		case ES:
-		case GS:
+		case FS:
 			if (value && (value & 3) != 3)
 				return -EIO;
 			value &= 0xffff;
@@ -112,7 +112,7 @@ static int putreg(struct task_struct *child,
 			value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
 			break;
 	}
-	if (regno > ES*4)
+	if (regno > FS*4)
 		regno -= 1*4;
 	put_stack_long(child, regno, value);
 	return 0;
@@ -124,18 +124,18 @@ static unsigned long getreg(struct task_struct *child,
 	unsigned long retval = ~0UL;
 
 	switch (regno >> 2) {
-		case FS:
-			retval = child->thread.fs;
+		case GS:
+			retval = child->thread.gs;
 			break;
 		case DS:
 		case ES:
-		case GS:
+		case FS:
 		case SS:
 		case CS:
 			retval = 0xffff;
 			/* fall through */
 		default:
-			if (regno > ES*4)
+			if (regno > FS*4)
 				regno -= 1*4;
 			retval &= get_stack_long(child, regno);
 	}