linux-kernel-test/arch/i386/power/cpu.c
Zachary Amsden e9f86e351f [PATCH] x86: remove redundant TSS clearing
When reviewing GDT updates, I found the code:

	set_tss_desc(cpu,t);	/* This just modifies memory; ... */
        per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS].b &= 0xfffffdff;

This second line is unnecessary, since set_tss_desc() has already cleared
the busy bit.

Commented disassembly, line 1:

c028b8bd:       8b 0c 86                mov    (%esi,%eax,4),%ecx
c028b8c0:       01 cb                   add    %ecx,%ebx
c028b8c2:       8d 0c 39                lea    (%ecx,%edi,1),%ecx

  => %ecx = per_cpu(cpu_gdt_table, cpu)

c028b8c5:       8d 91 80 00 00 00       lea    0x80(%ecx),%edx

  => %edx = &per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS]

c028b8cb:       66 c7 42 00 73 20       movw   $0x2073,0x0(%edx)
c028b8d1:       66 89 5a 02             mov    %bx,0x2(%edx)
c028b8d5:       c1 cb 10                ror    $0x10,%ebx
c028b8d8:       88 5a 04                mov    %bl,0x4(%edx)
c028b8db:       c6 42 05 89             movb   $0x89,0x5(%edx)

  => ((char *)%edx)[5] = 0x89
  (equivalent) ((char *)per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS])[5] = 0x89

c028b8df:       c6 42 06 00             movb   $0x0,0x6(%edx)
c028b8e3:       88 7a 07                mov    %bh,0x7(%edx)
c028b8e6:       c1 cb 10                ror    $0x10,%ebx

  => other bits

Commented disassembly, line 2:

c028b8e9:       8b 14 86                mov    (%esi,%eax,4),%edx
c028b8ec:       8d 04 3a                lea    (%edx,%edi,1),%eax

  => %eax = per_cpu(cpu_gdt_table, cpu)

c028b8ef:       81 a0 84 00 00 00 ff    andl   $0xfffffdff,0x84(%eax)

  => per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS].b &= 0xfffffdff;
  (equivalent) ((char *)per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS])[5] &= 0xfd

Note that (0x89 & ~0xfd) == 0; i.e, set_tss_desc(cpu,t) has already stored
the type field in the GDT with the busy bit clear.

Eliminating redundant and obscure code is always a good thing; in fact, I
pointed out this same optimization many moons ago in arch/i386/setup.c,
back when it used to be called that.

Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-05 00:06:13 -07:00

150 lines
3.2 KiB
C

/*
* Suspend support specific for i386.
*
* Distribute under GPLv2
*
* Copyright (c) 2002 Pavel Machek <pavel@suse.cz>
* Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
*/
#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/poll.h>
#include <linux/delay.h>
#include <linux/sysrq.h>
#include <linux/proc_fs.h>
#include <linux/irq.h>
#include <linux/pm.h>
#include <linux/device.h>
#include <linux/suspend.h>
#include <linux/acpi.h>
#include <asm/uaccess.h>
#include <asm/acpi.h>
#include <asm/tlbflush.h>
#include <asm/processor.h>
static struct saved_context saved_context;
unsigned long saved_context_ebx;
unsigned long saved_context_esp, saved_context_ebp;
unsigned long saved_context_esi, saved_context_edi;
unsigned long saved_context_eflags;
void __save_processor_state(struct saved_context *ctxt)
{
kernel_fpu_begin();
/*
* descriptor tables
*/
store_gdt(&ctxt->gdt_limit);
store_idt(&ctxt->idt_limit);
store_tr(ctxt->tr);
/*
* segment registers
*/
savesegment(es, ctxt->es);
savesegment(fs, ctxt->fs);
savesegment(gs, ctxt->gs);
savesegment(ss, ctxt->ss);
/*
* control registers
*/
ctxt->cr0 = read_cr0();
ctxt->cr2 = read_cr2();
ctxt->cr3 = read_cr3();
ctxt->cr4 = read_cr4();
}
void save_processor_state(void)
{
__save_processor_state(&saved_context);
}
static void
do_fpu_end(void)
{
/* restore FPU regs if necessary */
/* Do it out of line so that gcc does not move cr0 load to some stupid place */
kernel_fpu_end();
mxcsr_feature_mask_init();
}
static void fix_processor_context(void)
{
int cpu = smp_processor_id();
struct tss_struct * t = &per_cpu(init_tss, cpu);
set_tss_desc(cpu,t); /* This just modifies memory; should not be necessary. But... This is necessary, because 386 hardware has concept of busy TSS or some similar stupidity. */
load_TR_desc(); /* This does ltr */
load_LDT(&current->active_mm->context); /* This does lldt */
/*
* Now maybe reload the debug registers
*/
if (current->thread.debugreg[7]){
set_debugreg(current->thread.debugreg[0], 0);
set_debugreg(current->thread.debugreg[1], 1);
set_debugreg(current->thread.debugreg[2], 2);
set_debugreg(current->thread.debugreg[3], 3);
/* no 4 and 5 */
set_debugreg(current->thread.debugreg[6], 6);
set_debugreg(current->thread.debugreg[7], 7);
}
}
void __restore_processor_state(struct saved_context *ctxt)
{
/*
* control registers
*/
write_cr4(ctxt->cr4);
write_cr3(ctxt->cr3);
write_cr2(ctxt->cr2);
write_cr2(ctxt->cr0);
/*
* now restore the descriptor tables to their proper values
* ltr is done i fix_processor_context().
*/
load_gdt(&ctxt->gdt_limit);
load_idt(&ctxt->idt_limit);
/*
* segment registers
*/
loadsegment(es, ctxt->es);
loadsegment(fs, ctxt->fs);
loadsegment(gs, ctxt->gs);
loadsegment(ss, ctxt->ss);
/*
* sysenter MSRs
*/
if (boot_cpu_has(X86_FEATURE_SEP))
enable_sep_cpu();
fix_processor_context();
do_fpu_end();
mtrr_ap_init();
}
void restore_processor_state(void)
{
__restore_processor_state(&saved_context);
}
/* Needed by apm.c */
EXPORT_SYMBOL(save_processor_state);
EXPORT_SYMBOL(restore_processor_state);