[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, 7 insertions, 7 deletions

diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 8a8bbdaaf38..dcbbd0a8bfc 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -605,7 +605,7 @@ void __init early_cpu_init(void)
 struct pt_regs * __devinit idle_regs(struct pt_regs *regs)
 {
 	memset(regs, 0, sizeof(struct pt_regs));
-	regs->xgs = __KERNEL_PDA;
+	regs->xfs = __KERNEL_PDA;
 	return regs;
 }
 
@@ -662,12 +662,12 @@ struct i386_pda boot_pda = {
 	.pcurrent = &init_task,
 };
 
-static inline void set_kernel_gs(void)
+static inline void set_kernel_fs(void)
 {
-	/* Set %gs for this CPU's PDA.  Memory clobber is to create a
+	/* Set %fs for this CPU's PDA.  Memory clobber is to create a
 	   barrier with respect to any PDA operations, so the compiler
 	   doesn't move any before here. */
-	asm volatile ("mov %0, %%gs" : : "r" (__KERNEL_PDA) : "memory");
+	asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_PDA) : "memory");
 }
 
 /* Initialize the CPU's GDT and PDA.  The boot CPU does this for
@@ -718,7 +718,7 @@ void __cpuinit cpu_set_gdt(int cpu)
 	   the boot CPU, this will transition from the boot gdt+pda to
 	   the real ones). */
 	load_gdt(cpu_gdt_descr);
-	set_kernel_gs();
+	set_kernel_fs();
 }
 
 /* Common CPU init for both boot and secondary CPUs */
@@ -764,8 +764,8 @@ static void __cpuinit _cpu_init(int cpu, struct task_struct *curr)
 	__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
 #endif
 
-	/* Clear %fs. */
-	asm volatile ("mov %0, %%fs" : : "r" (0));
+	/* Clear %gs. */
+	asm volatile ("mov %0, %%gs" : : "r" (0));
 
 	/* Clear all 6 debug registers: */
 	set_debugreg(0, 0);