2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 06:34:11 +08:00
linux-next/arch/x86/include/asm/tlbflush.h
Andy Lutomirski 1e02ce4ccc x86: Store a per-cpu shadow copy of CR4
Context switches and TLB flushes can change individual bits of CR4.
CR4 reads take several cycles, so store a shadow copy of CR4 in a
per-cpu variable.

To avoid wasting a cache line, I added the CR4 shadow to
cpu_tlbstate, which is already touched in switch_mm.  The heaviest
users of the cr4 shadow will be switch_mm and __switch_to_xtra, and
__switch_to_xtra is called shortly after switch_mm during context
switch, so the cacheline is likely to be hot.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Vince Weaver <vince@deater.net>
Cc: "hillf.zj" <hillf.zj@alibaba-inc.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/3a54dd3353fffbf84804398e00dfdc5b7c1afd7d.1414190806.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-04 12:10:42 +01:00

270 lines
6.2 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/special_insns.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
struct tlb_state {
#ifdef CONFIG_SMP
struct mm_struct *active_mm;
int state;
#endif
/*
* Access to this CR4 shadow and to H/W CR4 is protected by
* disabling interrupts when modifying either one.
*/
unsigned long cr4;
};
DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
/* Initialize cr4 shadow for this CPU. */
static inline void cr4_init_shadow(void)
{
this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
}
/* Set in this cpu's CR4. */
static inline void cr4_set_bits(unsigned long mask)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
if ((cr4 | mask) != cr4) {
cr4 |= mask;
this_cpu_write(cpu_tlbstate.cr4, cr4);
__write_cr4(cr4);
}
}
/* Clear in this cpu's CR4. */
static inline void cr4_clear_bits(unsigned long mask)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
if ((cr4 & ~mask) != cr4) {
cr4 &= ~mask;
this_cpu_write(cpu_tlbstate.cr4, cr4);
__write_cr4(cr4);
}
}
/* Read the CR4 shadow. */
static inline unsigned long cr4_read_shadow(void)
{
return this_cpu_read(cpu_tlbstate.cr4);
}
/*
* Save some of cr4 feature set we're using (e.g. Pentium 4MB
* enable and PPro Global page enable), so that any CPU's that boot
* up after us can get the correct flags. This should only be used
* during boot on the boot cpu.
*/
extern unsigned long mmu_cr4_features;
extern u32 *trampoline_cr4_features;
static inline void cr4_set_bits_and_update_boot(unsigned long mask)
{
mmu_cr4_features |= mask;
if (trampoline_cr4_features)
*trampoline_cr4_features = mmu_cr4_features;
cr4_set_bits(mask);
}
static inline void __native_flush_tlb(void)
{
native_write_cr3(native_read_cr3());
}
static inline void __native_flush_tlb_global_irq_disabled(void)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
/* clear PGE */
native_write_cr4(cr4 & ~X86_CR4_PGE);
/* write old PGE again and flush TLBs */
native_write_cr4(cr4);
}
static inline void __native_flush_tlb_global(void)
{
unsigned long flags;
/*
* 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);
__native_flush_tlb_global_irq_disabled();
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)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
}
#define TLB_FLUSH_ALL -1UL
/*
* 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, start, end) 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.
*/
#ifndef CONFIG_SMP
/* "_up" is for UniProcessor.
*
* This is a helper for other header functions. *Not* intended to be called
* directly. All global TLB flushes need to either call this, or to bump the
* vm statistics themselves.
*/
static inline void __flush_tlb_up(void)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb();
}
static inline void flush_tlb_all(void)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb_all();
}
static inline void flush_tlb(void)
{
__flush_tlb_up();
}
static inline void local_flush_tlb(void)
{
__flush_tlb_up();
}
static inline void flush_tlb_mm(struct mm_struct *mm)
{
if (mm == current->active_mm)
__flush_tlb_up();
}
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_up();
}
static inline void flush_tlb_mm_range(struct mm_struct *mm,
unsigned long start, unsigned long end, unsigned long vmflag)
{
if (mm == current->active_mm)
__flush_tlb_up();
}
static inline void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
}
static inline void reset_lazy_tlbstate(void)
{
}
static inline void flush_tlb_kernel_range(unsigned long start,
unsigned long end)
{
flush_tlb_all();
}
#else /* SMP */
#include <asm/smp.h>
#define local_flush_tlb() __flush_tlb()
#define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
#define flush_tlb_range(vma, start, end) \
flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
extern void flush_tlb_all(void);
extern void flush_tlb_current_task(void);
extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long vmflag);
extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
#define flush_tlb() flush_tlb_current_task()
void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
unsigned long start, unsigned long end);
#define TLBSTATE_OK 1
#define TLBSTATE_LAZY 2
static inline void reset_lazy_tlbstate(void)
{
this_cpu_write(cpu_tlbstate.state, 0);
this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
}
#endif /* SMP */
#ifndef CONFIG_PARAVIRT
#define flush_tlb_others(mask, mm, start, end) \
native_flush_tlb_others(mask, mm, start, end)
#endif
#endif /* _ASM_X86_TLBFLUSH_H */