summaryrefslogtreecommitdiffstats
path: root/arch/i386/kernel/vm86.c
diff options
context:
space:
mode:
authorJeremy Fitzhardinge <jeremy@goop.org>2007-02-13 13:26:20 +0100
committerAndi Kleen <andi@basil.nowhere.org>2007-02-13 13:26:20 +0100
commit464d1a78fbf8cf6c7fd970e7b3e2db50a320ce28 (patch)
tree536d8a92976e675b484b35dec88d40c97fab8ac8 /arch/i386/kernel/vm86.c
parent54413927f022292aeccadd268fbf1c0b42129945 (diff)
downloadblackbird-op-linux-464d1a78fbf8cf6c7fd970e7b3e2db50a320ce28.tar.gz
blackbird-op-linux-464d1a78fbf8cf6c7fd970e7b3e2db50a320ce28.zip
[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>
Diffstat (limited to 'arch/i386/kernel/vm86.c')
-rw-r--r--arch/i386/kernel/vm86.c33
1 files changed, 17 insertions, 16 deletions
diff --git a/arch/i386/kernel/vm86.c b/arch/i386/kernel/vm86.c
index be2f96e67f78..d1b8f2b7aea6 100644
--- a/arch/i386/kernel/vm86.c
+++ b/arch/i386/kernel/vm86.c
@@ -96,12 +96,12 @@ static int copy_vm86_regs_to_user(struct vm86_regs __user *user,
{
int ret = 0;
- /* kernel_vm86_regs is missing xfs, so copy everything up to
- (but not including) xgs, and then rest after xgs. */
- ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.xgs));
- ret += copy_to_user(&user->__null_gs, &regs->pt.xgs,
+ /* kernel_vm86_regs is missing xgs, so copy everything up to
+ (but not including) orig_eax, and then rest including orig_eax. */
+ ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.orig_eax));
+ ret += copy_to_user(&user->orig_eax, &regs->pt.orig_eax,
sizeof(struct kernel_vm86_regs) -
- offsetof(struct kernel_vm86_regs, pt.xgs));
+ offsetof(struct kernel_vm86_regs, pt.orig_eax));
return ret;
}
@@ -113,12 +113,13 @@ static int copy_vm86_regs_from_user(struct kernel_vm86_regs *regs,
{
int ret = 0;
- ret += copy_from_user(regs, user, offsetof(struct kernel_vm86_regs, pt.xgs));
- ret += copy_from_user(&regs->pt.xgs, &user->__null_gs,
+ /* copy eax-xfs inclusive */
+ ret += copy_from_user(regs, user, offsetof(struct kernel_vm86_regs, pt.orig_eax));
+ /* copy orig_eax-__gsh+extra */
+ ret += copy_from_user(&regs->pt.orig_eax, &user->orig_eax,
sizeof(struct kernel_vm86_regs) -
- offsetof(struct kernel_vm86_regs, pt.xgs) +
+ offsetof(struct kernel_vm86_regs, pt.orig_eax) +
extra);
-
return ret;
}
@@ -157,8 +158,8 @@ struct pt_regs * fastcall save_v86_state(struct kernel_vm86_regs * regs)
ret = KVM86->regs32;
- loadsegment(fs, current->thread.saved_fs);
- ret->xgs = current->thread.saved_gs;
+ ret->xfs = current->thread.saved_fs;
+ loadsegment(gs, current->thread.saved_gs);
return ret;
}
@@ -285,9 +286,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
*/
info->regs.pt.xds = 0;
info->regs.pt.xes = 0;
- info->regs.pt.xgs = 0;
+ info->regs.pt.xfs = 0;
-/* we are clearing fs later just before "jmp resume_userspace",
+/* we are clearing gs later just before "jmp resume_userspace",
* because it is not saved/restored.
*/
@@ -321,8 +322,8 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
*/
info->regs32->eax = 0;
tsk->thread.saved_esp0 = tsk->thread.esp0;
- savesegment(fs, tsk->thread.saved_fs);
- tsk->thread.saved_gs = info->regs32->xgs;
+ tsk->thread.saved_fs = info->regs32->xfs;
+ savesegment(gs, tsk->thread.saved_gs);
tss = &per_cpu(init_tss, get_cpu());
tsk->thread.esp0 = (unsigned long) &info->VM86_TSS_ESP0;
@@ -342,7 +343,7 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
__asm__ __volatile__(
"movl %0,%%esp\n\t"
"movl %1,%%ebp\n\t"
- "mov %2, %%fs\n\t"
+ "mov %2, %%gs\n\t"
"jmp resume_userspace"
: /* no outputs */
:"r" (&info->regs), "r" (task_thread_info(tsk)), "r" (0));
OpenPOWER on IntegriCloud