linux_dsm_epyc7002/arch/x86/include/asm/mmu_context.h
Andy Lutomirski c4a7bba29b sched/x86: Add a comment clarifying LDT context switching
The code is correct, but only for a rather subtle reason.  This
confused me for quite a while when I read switch_mm, so clarify
the code to avoid confusing other people, too.

TBH, I wouldn't be surprised if this code was only correct by
accident.

[ I wouldn't normally send a comment-only patch, but it took me a long
  time to first figure out wtf was going on here, and then to figure
  out why this wasn't exploitable by malicious code, and then to
  figure out why this oddity had no user-visible effect at all.  Let's
  spare future readers the same confusion. ]

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/36275c99801a87d8dcf0502a41cf4e2ad81aae46.1412623954.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-28 11:11:57 +01:00

115 lines
3.0 KiB
C

#ifndef _ASM_X86_MMU_CONTEXT_H
#define _ASM_X86_MMU_CONTEXT_H
#include <asm/desc.h>
#include <linux/atomic.h>
#include <linux/mm_types.h>
#include <trace/events/tlb.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 (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
this_cpu_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
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
this_cpu_write(cpu_tlbstate.active_mm, next);
#endif
cpumask_set_cpu(cpu, mm_cpumask(next));
/* Re-load page tables */
load_cr3(next->pgd);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
/* Stop flush ipis for the previous mm */
cpumask_clear_cpu(cpu, mm_cpumask(prev));
/*
* Load the LDT, if the LDT is different.
*
* It's possible leave_mm(prev) has been called. If so,
* then prev->context.ldt could be out of sync with the
* LDT descriptor or the LDT register. This can only happen
* if prev->context.ldt is non-null, since we never free
* an LDT. But LDTs can't be shared across mms, so
* prev->context.ldt won't be equal to next->context.ldt.
*/
if (unlikely(prev->context.ldt != next->context.ldt))
load_LDT_nolock(&next->context);
}
#ifdef CONFIG_SMP
else {
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
/*
* On established mms, the mm_cpumask is only changed
* from irq context, from ptep_clear_flush() while in
* lazy tlb mode, and here. Irqs are blocked during
* schedule, protecting us from simultaneous changes.
*/
cpumask_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);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
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 */