kernel_optimize_test/arch/x86/power/cpu.c

260 lines
6.2 KiB
C
Raw Normal View History

/*
* Suspend support specific for i386/x86-64.
*
* Distribute under GPLv2
*
* Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl>
* Copyright (c) 2002 Pavel Machek <pavel@suse.cz>
* Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
*/
#include <linux/suspend.h>
#include <linux/smp.h>
[PATCH] x86_64: Set up safe page tables during resume The following patch makes swsusp avoid the possible temporary corruption of page translation tables during resume on x86-64. This is achieved by creating a copy of the relevant page tables that will not be modified by swsusp and can be safely used by it on resume. The problem is that during resume on x86-64 swsusp may temporarily corrupt the page tables used for the direct mapping of RAM. If that happens, a page fault occurs and cannot be handled properly, which leads to the solid hang of the affected system. This leads to the loss of the system's state from before suspend and may result in the loss of data or the corruption of filesystems, so it is a serious issue. Also, it appears to happen quite often (for me, as often as 50% of the time). The problem is related to the fact that (at least) one of the PMD entries used in the direct memory mapping (starting at PAGE_OFFSET) points to a page table the physical address of which is much greater than the physical address of the PMD entry itself. Moreover, unfortunately, the physical address of the page table before suspend (i.e. the one stored in the suspend image) happens to be different to the physical address of the corresponding page table used during resume (i.e. the one that is valid right before swsusp_arch_resume() in arch/x86_64/kernel/suspend_asm.S is executed). Thus while the image is restored, the "offending" PMD entry gets overwritten, so it does not point to the right physical address any more (i.e. there's no page table at the address pointed to by it, because it points to the address the page table has been at during suspend). Consequently, if the PMD entry is used later on, and it _is_ used in the process of copying the image pages, a page fault occurs, but it cannot be handled in the normal way and the system hangs. In principle we can call create_resume_mapping() from swsusp_arch_resume() (ie. from suspend_asm.S), but then the memory allocations in create_resume_mapping(), resume_pud_mapping(), and resume_pmd_mapping() must be made carefully so that we use _only_ NosaveFree pages in them (the other pages are overwritten by the loop in swsusp_arch_resume()). Additionally, we are in atomic context at that time, so we cannot use GFP_KERNEL. Moreover, if one of the allocations fails, we should free all of the allocated pages, so we need to trace them somehow. All of this is done in the appended patch, except that the functions populating the page tables are located in arch/x86_64/kernel/suspend.c rather than in init.c. It may be done in a more elegan way in the future, with the help of some swsusp patches that are in the works now. [AK: move some externs into headers, renamed a function] Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-10 03:19:40 +08:00
#include <asm/pgtable.h>
#include <asm/proto.h>
#include <asm/mtrr.h>
#include <asm/page.h>
#include <asm/mce.h>
#include <asm/xcr.h>
#include <asm/suspend.h>
#ifdef CONFIG_X86_32
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;
#else
/* CONFIG_X86_64 */
struct saved_context saved_context;
#endif
/**
* __save_processor_state - save CPU registers before creating a
* hibernation image and before restoring the memory state from it
* @ctxt - structure to store the registers contents in
*
* NOTE: If there is a CPU register the modification of which by the
* boot kernel (ie. the kernel used for loading the hibernation image)
* might affect the operations of the restored target kernel (ie. the one
* saved in the hibernation image), then its contents must be saved by this
* function. In other words, if kernel A is hibernated and different
* kernel B is used for loading the hibernation image into memory, the
* kernel A's __save_processor_state() function must save all registers
* needed by kernel A, so that it can operate correctly after the resume
* regardless of what kernel B does in the meantime.
*/
static void __save_processor_state(struct saved_context *ctxt)
{
#ifdef CONFIG_X86_32
mtrr_save_fixed_ranges(NULL);
#endif
kernel_fpu_begin();
/*
* descriptor tables
*/
#ifdef CONFIG_X86_32
store_gdt(&ctxt->gdt);
store_idt(&ctxt->idt);
#else
/* CONFIG_X86_64 */
store_gdt((struct desc_ptr *)&ctxt->gdt_limit);
store_idt((struct desc_ptr *)&ctxt->idt_limit);
#endif
store_tr(ctxt->tr);
/* XMM0..XMM15 should be handled by kernel_fpu_begin(). */
/*
* segment registers
*/
#ifdef CONFIG_X86_32
savesegment(es, ctxt->es);
savesegment(fs, ctxt->fs);
savesegment(gs, ctxt->gs);
savesegment(ss, ctxt->ss);
#else
/* CONFIG_X86_64 */
asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
rdmsrl(MSR_FS_BASE, ctxt->fs_base);
rdmsrl(MSR_GS_BASE, ctxt->gs_base);
rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
mtrr_save_fixed_ranges(NULL);
rdmsrl(MSR_EFER, ctxt->efer);
#endif
/*
* control registers
*/
ctxt->cr0 = read_cr0();
ctxt->cr2 = read_cr2();
ctxt->cr3 = read_cr3();
#ifdef CONFIG_X86_32
ctxt->cr4 = read_cr4_safe();
#else
/* CONFIG_X86_64 */
ctxt->cr4 = read_cr4();
ctxt->cr8 = read_cr8();
#endif
}
/* Needed by apm.c */
void save_processor_state(void)
{
__save_processor_state(&saved_context);
}
#ifdef CONFIG_X86_32
EXPORT_SYMBOL(save_processor_state);
#endif
static void do_fpu_end(void)
{
/*
* Restore FPU regs if necessary.
*/
kernel_fpu_end();
}
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.
*/
#ifdef CONFIG_X86_64
get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9;
syscall_init(); /* This sets MSR_*STAR and related */
#endif
load_TR_desc(); /* This does ltr */
load_LDT(&current->active_mm->context); /* This does lldt */
/*
* Now maybe reload the debug registers
*/
if (current->thread.debugreg7) {
#ifdef CONFIG_X86_32
set_debugreg(current->thread.debugreg0, 0);
set_debugreg(current->thread.debugreg1, 1);
set_debugreg(current->thread.debugreg2, 2);
set_debugreg(current->thread.debugreg3, 3);
/* no 4 and 5 */
set_debugreg(current->thread.debugreg6, 6);
set_debugreg(current->thread.debugreg7, 7);
#else
/* CONFIG_X86_64 */
loaddebug(&current->thread, 0);
loaddebug(&current->thread, 1);
loaddebug(&current->thread, 2);
loaddebug(&current->thread, 3);
/* no 4 and 5 */
loaddebug(&current->thread, 6);
loaddebug(&current->thread, 7);
#endif
}
}
/**
* __restore_processor_state - restore the contents of CPU registers saved
* by __save_processor_state()
* @ctxt - structure to load the registers contents from
*/
static void __restore_processor_state(struct saved_context *ctxt)
{
/*
* control registers
*/
/* cr4 was introduced in the Pentium CPU */
#ifdef CONFIG_X86_32
if (ctxt->cr4)
write_cr4(ctxt->cr4);
#else
/* CONFIG X86_64 */
wrmsrl(MSR_EFER, ctxt->efer);
write_cr8(ctxt->cr8);
write_cr4(ctxt->cr4);
#endif
write_cr3(ctxt->cr3);
write_cr2(ctxt->cr2);
write_cr0(ctxt->cr0);
/*
* now restore the descriptor tables to their proper values
* ltr is done i fix_processor_context().
*/
#ifdef CONFIG_X86_32
load_gdt(&ctxt->gdt);
load_idt(&ctxt->idt);
#else
/* CONFIG_X86_64 */
load_gdt((const struct desc_ptr *)&ctxt->gdt_limit);
load_idt((const struct desc_ptr *)&ctxt->idt_limit);
#endif
/*
* segment registers
*/
#ifdef CONFIG_X86_32
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();
#else
/* CONFIG_X86_64 */
asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
load_gs_index(ctxt->gs);
asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
wrmsrl(MSR_FS_BASE, ctxt->fs_base);
wrmsrl(MSR_GS_BASE, ctxt->gs_base);
wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
#endif
/*
* restore XCR0 for xsave capable cpu's.
*/
if (cpu_has_xsave)
xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
fix_processor_context();
do_fpu_end();
mtrr_ap_init();
#ifdef CONFIG_X86_OLD_MCE
mcheck_init(&boot_cpu_data);
#endif
}
/* Needed by apm.c */
void restore_processor_state(void)
{
__restore_processor_state(&saved_context);
}
#ifdef CONFIG_X86_32
EXPORT_SYMBOL(restore_processor_state);
#endif