From 464d1a78fbf8cf6c7fd970e7b3e2db50a320ce28 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Tue, 13 Feb 2007 13:26:20 +0100 Subject: [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 Signed-off-by: Andi Kleen Cc: Ian Campbell Acked-by: Ingo Molnar Acked-by: Zachary Amsden Cc: Eric Dumazet Signed-off-by: Frederik Deweerdt Signed-off-by: Andrew Morton --- include/asm-i386/processor.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/asm-i386/processor.h') diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index 359f10b54f59..11bf899de8aa 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -424,7 +424,7 @@ struct thread_struct { .vm86_info = NULL, \ .sysenter_cs = __KERNEL_CS, \ .io_bitmap_ptr = NULL, \ - .gs = __KERNEL_PDA, \ + .fs = __KERNEL_PDA, \ } /* @@ -442,8 +442,8 @@ struct thread_struct { } #define start_thread(regs, new_eip, new_esp) do { \ - __asm__("movl %0,%%fs": :"r" (0)); \ - regs->xgs = 0; \ + __asm__("movl %0,%%gs": :"r" (0)); \ + regs->xfs = 0; \ set_fs(USER_DS); \ regs->xds = __USER_DS; \ regs->xes = __USER_DS; \ -- cgit v1.2.2 From 2ff2d3d74705d34ab71b21f54634fcf50d57bdd5 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 13 Feb 2007 13:26:22 +0100 Subject: [PATCH] i386: add idle notifier Add a notifier mechanism to the low level idle loop. You can register a callback function which gets invoked on entry and exit from the low level idle loop. The low level idle loop is defined as the polling loop, low-power call, or the mwait instruction. Interrupts processed by the idle thread are not considered part of the low level loop. The notifier can be used to measure precisely how much is spent in useless execution (or low power mode). The perfmon subsystem uses it to turn on/off monitoring. Signed-off-by: stephane eranian Signed-off-by: Andrew Morton Signed-off-by: Andi Kleen --- include/asm-i386/processor.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/asm-i386/processor.h') diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index 11bf899de8aa..edfbe46a5e13 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -257,6 +257,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) : :"a" (eax), "c" (ecx)); } +static inline void __sti_mwait(unsigned long eax, unsigned long ecx) +{ + /* "mwait %eax,%ecx;" */ + asm volatile( + "sti; .byte 0x0f,0x01,0xc9;" + : :"a" (eax), "c" (ecx)); +} + extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx); /* from system description table in BIOS. Mostly for MCA use, but -- cgit v1.2.2