OpenCloudOS-Kernel/arch/x86/include/asm/mmu_context.h

94 lines
2.1 KiB
C
Raw Normal View History

#ifndef _ASM_X86_MMU_CONTEXT_H
#define _ASM_X86_MMU_CONTEXT_H
#include <asm/desc.h>
#include <linux/atomic.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
#ifndef CONFIG_PARAVIRT
#include <asm-generic/mm_hooks.h>
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
}
#endif /* !CONFIG_PARAVIRT */
/*
* Used for LDT copy/destruction.
*/
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
void destroy_context(struct mm_struct *mm);
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
#ifdef CONFIG_SMP
if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
#endif
}
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
unsigned cpu = smp_processor_id();
if (likely(prev != next)) {
#ifdef CONFIG_SMP
percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
percpu_write(cpu_tlbstate.active_mm, next);
#endif
cpumask_set_cpu(cpu, mm_cpumask(next));
/* Re-load page tables */
load_cr3(next->pgd);
x86, mm: avoid possible bogus tlb entries by clearing prev mm_cpumask after switching mm Clearing the cpu in prev's mm_cpumask early will avoid the flush tlb IPI's while the cr3 is still pointing to the prev mm. And this window can lead to the possibility of bogus TLB fills resulting in strange failures. One such problematic scenario is mentioned below. T1. CPU-1 is context switching from mm1 to mm2 context and got a NMI etc between the point of clearing the cpu from the mm_cpumask(mm1) and before reloading the cr3 with the new mm2. T2. CPU-2 is tearing down a specific vma for mm1 and will proceed with flushing the TLB for mm1. It doesn't send the flush TLB to CPU-1 as it doesn't see that cpu listed in the mm_cpumask(mm1). T3. After the TLB flush is complete, CPU-2 goes ahead and frees the page-table pages associated with the removed vma mapping. T4. CPU-2 now allocates those freed page-table pages for something else. T5. As the CR3 and TLB caches for mm1 is still active on CPU-1, CPU-1 can potentially speculate and walk through the page-table caches and can insert new TLB entries. As the page-table pages are already freed and being used on CPU-2, this page walk can potentially insert a bogus global TLB entry depending on the (random) contents of the page that is being used on CPU-2. T6. This bogus TLB entry being global will be active across future CR3 changes and can result in weird memory corruption etc. To avoid this issue, for the prev mm that is handing over the cpu to another mm, clear the cpu from the mm_cpumask(prev) after the cr3 is changed. Marking it for -stable, though we haven't seen any reported failure that can be attributed to this. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: stable@kernel.org [v2.6.32+] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-04 04:20:04 +08:00
/* stop flush ipis for the previous mm */
cpumask_clear_cpu(cpu, mm_cpumask(prev));
/*
* load the LDT, if the LDT is different:
*/
if (unlikely(prev->context.ldt != next->context.ldt))
load_LDT_nolock(&next->context);
}
#ifdef CONFIG_SMP
else {
percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
/* We were in lazy tlb mode and leave_mm disabled
* tlb flush IPI delivery. We must reload CR3
* to make sure to use no freed page tables.
*/
load_cr3(next->pgd);
load_LDT_nolock(&next->context);
}
}
#endif
}
#define activate_mm(prev, next) \
do { \
paravirt_activate_mm((prev), (next)); \
switch_mm((prev), (next), NULL); \
} while (0);
#ifdef CONFIG_X86_32
#define deactivate_mm(tsk, mm) \
do { \
lazy_load_gs(0); \
} while (0)
#else
#define deactivate_mm(tsk, mm) \
do { \
load_gs_index(0); \
loadsegment(fs, 0); \
} while (0)
#endif
#endif /* _ASM_X86_MMU_CONTEXT_H */