b1979a5fda
CR4 manipulation is not protected against interrupts and preemption, but KVM uses smp_function_call to manipulate the X86_CR4_VMXE bit either from the CPU hotplug code or from the kvm_init call. We need to protect the CR4 manipulation from both interrupts and preemption. Original bug report: http://lkml.org/lkml/2008/5/7/48 Bugzilla entry: http://bugzilla.kernel.org/show_bug.cgi?id=10642 This is not a regression from 2.6.25, it's a long standing and hard to trigger bug. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
169 lines
3.8 KiB
C
169 lines
3.8 KiB
C
#ifndef _ASM_X86_TLBFLUSH_H
|
|
#define _ASM_X86_TLBFLUSH_H
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/sched.h>
|
|
|
|
#include <asm/processor.h>
|
|
#include <asm/system.h>
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
#include <asm/paravirt.h>
|
|
#else
|
|
#define __flush_tlb() __native_flush_tlb()
|
|
#define __flush_tlb_global() __native_flush_tlb_global()
|
|
#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
|
|
#endif
|
|
|
|
static inline void __native_flush_tlb(void)
|
|
{
|
|
write_cr3(read_cr3());
|
|
}
|
|
|
|
static inline void __native_flush_tlb_global(void)
|
|
{
|
|
unsigned long flags;
|
|
unsigned long cr4;
|
|
|
|
/*
|
|
* Read-modify-write to CR4 - protect it from preemption and
|
|
* from interrupts. (Use the raw variant because this code can
|
|
* be called from deep inside debugging code.)
|
|
*/
|
|
raw_local_irq_save(flags);
|
|
|
|
cr4 = read_cr4();
|
|
/* clear PGE */
|
|
write_cr4(cr4 & ~X86_CR4_PGE);
|
|
/* write old PGE again and flush TLBs */
|
|
write_cr4(cr4);
|
|
|
|
raw_local_irq_restore(flags);
|
|
}
|
|
|
|
static inline void __native_flush_tlb_single(unsigned long addr)
|
|
{
|
|
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
|
|
}
|
|
|
|
static inline void __flush_tlb_all(void)
|
|
{
|
|
if (cpu_has_pge)
|
|
__flush_tlb_global();
|
|
else
|
|
__flush_tlb();
|
|
}
|
|
|
|
static inline void __flush_tlb_one(unsigned long addr)
|
|
{
|
|
if (cpu_has_invlpg)
|
|
__flush_tlb_single(addr);
|
|
else
|
|
__flush_tlb();
|
|
}
|
|
|
|
#ifdef CONFIG_X86_32
|
|
# define TLB_FLUSH_ALL 0xffffffff
|
|
#else
|
|
# define TLB_FLUSH_ALL -1ULL
|
|
#endif
|
|
|
|
/*
|
|
* TLB flushing:
|
|
*
|
|
* - flush_tlb() flushes the current mm struct TLBs
|
|
* - flush_tlb_all() flushes all processes TLBs
|
|
* - flush_tlb_mm(mm) flushes the specified mm context TLB's
|
|
* - flush_tlb_page(vma, vmaddr) flushes one page
|
|
* - flush_tlb_range(vma, start, end) flushes a range of pages
|
|
* - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
|
|
* - flush_tlb_others(cpumask, mm, va) flushes TLBs on other cpus
|
|
*
|
|
* ..but the i386 has somewhat limited tlb flushing capabilities,
|
|
* and page-granular flushes are available only on i486 and up.
|
|
*
|
|
* x86-64 can only flush individual pages or full VMs. For a range flush
|
|
* we always do the full VM. Might be worth trying if for a small
|
|
* range a few INVLPGs in a row are a win.
|
|
*/
|
|
|
|
#ifndef CONFIG_SMP
|
|
|
|
#define flush_tlb() __flush_tlb()
|
|
#define flush_tlb_all() __flush_tlb_all()
|
|
#define local_flush_tlb() __flush_tlb()
|
|
|
|
static inline void flush_tlb_mm(struct mm_struct *mm)
|
|
{
|
|
if (mm == current->active_mm)
|
|
__flush_tlb();
|
|
}
|
|
|
|
static inline void flush_tlb_page(struct vm_area_struct *vma,
|
|
unsigned long addr)
|
|
{
|
|
if (vma->vm_mm == current->active_mm)
|
|
__flush_tlb_one(addr);
|
|
}
|
|
|
|
static inline void flush_tlb_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
if (vma->vm_mm == current->active_mm)
|
|
__flush_tlb();
|
|
}
|
|
|
|
static inline void native_flush_tlb_others(const cpumask_t *cpumask,
|
|
struct mm_struct *mm,
|
|
unsigned long va)
|
|
{
|
|
}
|
|
|
|
#else /* SMP */
|
|
|
|
#include <asm/smp.h>
|
|
|
|
#define local_flush_tlb() __flush_tlb()
|
|
|
|
extern void flush_tlb_all(void);
|
|
extern void flush_tlb_current_task(void);
|
|
extern void flush_tlb_mm(struct mm_struct *);
|
|
extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
|
|
|
|
#define flush_tlb() flush_tlb_current_task()
|
|
|
|
static inline void flush_tlb_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
flush_tlb_mm(vma->vm_mm);
|
|
}
|
|
|
|
void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm,
|
|
unsigned long va);
|
|
|
|
#define TLBSTATE_OK 1
|
|
#define TLBSTATE_LAZY 2
|
|
|
|
#ifdef CONFIG_X86_32
|
|
struct tlb_state {
|
|
struct mm_struct *active_mm;
|
|
int state;
|
|
char __cacheline_padding[L1_CACHE_BYTES-8];
|
|
};
|
|
DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
|
|
#endif
|
|
|
|
#endif /* SMP */
|
|
|
|
#ifndef CONFIG_PARAVIRT
|
|
#define flush_tlb_others(mask, mm, va) native_flush_tlb_others(&mask, mm, va)
|
|
#endif
|
|
|
|
static inline void flush_tlb_kernel_range(unsigned long start,
|
|
unsigned long end)
|
|
{
|
|
flush_tlb_all();
|
|
}
|
|
|
|
#endif /* _ASM_X86_TLBFLUSH_H */
|