x86/mm, sched/core: Uninline switch_mm()
It's fairly large and it has quite a few callers. This may also help untangle some headers down the road. Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Borislav Petkov <bp@suse.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/54f3367803e7f80b2be62c8a21879aa74b1a5f57.1461688545.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
e1074888c3
commit
69c0319aab
|
@ -115,103 +115,9 @@ static inline void destroy_context(struct mm_struct *mm)
|
|||
destroy_context_ldt(mm);
|
||||
}
|
||||
|
||||
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
||||
struct task_struct *tsk)
|
||||
{
|
||||
unsigned cpu = smp_processor_id();
|
||||
extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
||||
struct task_struct *tsk);
|
||||
|
||||
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.
|
||||
*
|
||||
* This logic has an ordering constraint:
|
||||
*
|
||||
* CPU 0: Write to a PTE for 'next'
|
||||
* CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI.
|
||||
* CPU 1: set bit 1 in next's mm_cpumask
|
||||
* CPU 1: load from the PTE that CPU 0 writes (implicit)
|
||||
*
|
||||
* We need to prevent an outcome in which CPU 1 observes
|
||||
* the new PTE value and CPU 0 observes bit 1 clear in
|
||||
* mm_cpumask. (If that occurs, then the IPI will never
|
||||
* be sent, and CPU 0's TLB will contain a stale entry.)
|
||||
*
|
||||
* The bad outcome can occur if either CPU's load is
|
||||
* reordered before that CPU's store, so both CPUs must
|
||||
* execute full barriers to prevent this from happening.
|
||||
*
|
||||
* Thus, switch_mm needs a full barrier between the
|
||||
* store to mm_cpumask and any operation that could load
|
||||
* from next->pgd. TLB fills are special and can happen
|
||||
* due to instruction fetches or for no reason at all,
|
||||
* and neither LOCK nor MFENCE orders them.
|
||||
* Fortunately, load_cr3() is serializing and gives the
|
||||
* ordering guarantee we need.
|
||||
*
|
||||
*/
|
||||
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 per-mm CR4 state */
|
||||
load_mm_cr4(next);
|
||||
|
||||
#ifdef CONFIG_MODIFY_LDT_SYSCALL
|
||||
/*
|
||||
* Load the LDT, if the LDT is different.
|
||||
*
|
||||
* It's possible that prev->context.ldt doesn't match
|
||||
* the LDT register. This can happen if leave_mm(prev)
|
||||
* was called and then modify_ldt changed
|
||||
* prev->context.ldt but suppressed an IPI to this CPU.
|
||||
* In this case, prev->context.ldt != NULL, because we
|
||||
* never set context.ldt to NULL while the mm still
|
||||
* exists. That means that next->context.ldt !=
|
||||
* prev->context.ldt, because mms never share an LDT.
|
||||
*/
|
||||
if (unlikely(prev->context.ldt != next->context.ldt))
|
||||
load_mm_ldt(next);
|
||||
#endif
|
||||
}
|
||||
#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.
|
||||
*
|
||||
* As above, load_cr3() is serializing and orders TLB
|
||||
* fills with respect to the mm_cpumask write.
|
||||
*/
|
||||
load_cr3(next->pgd);
|
||||
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
|
||||
load_mm_cr4(next);
|
||||
load_mm_ldt(next);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
#define activate_mm(prev, next) \
|
||||
do { \
|
||||
|
|
|
@ -59,6 +59,108 @@ void leave_mm(int cpu)
|
|||
}
|
||||
EXPORT_SYMBOL_GPL(leave_mm);
|
||||
|
||||
#endif /* CONFIG_SMP */
|
||||
|
||||
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.
|
||||
*
|
||||
* This logic has an ordering constraint:
|
||||
*
|
||||
* CPU 0: Write to a PTE for 'next'
|
||||
* CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI.
|
||||
* CPU 1: set bit 1 in next's mm_cpumask
|
||||
* CPU 1: load from the PTE that CPU 0 writes (implicit)
|
||||
*
|
||||
* We need to prevent an outcome in which CPU 1 observes
|
||||
* the new PTE value and CPU 0 observes bit 1 clear in
|
||||
* mm_cpumask. (If that occurs, then the IPI will never
|
||||
* be sent, and CPU 0's TLB will contain a stale entry.)
|
||||
*
|
||||
* The bad outcome can occur if either CPU's load is
|
||||
* reordered before that CPU's store, so both CPUs must
|
||||
* execute full barriers to prevent this from happening.
|
||||
*
|
||||
* Thus, switch_mm needs a full barrier between the
|
||||
* store to mm_cpumask and any operation that could load
|
||||
* from next->pgd. TLB fills are special and can happen
|
||||
* due to instruction fetches or for no reason at all,
|
||||
* and neither LOCK nor MFENCE orders them.
|
||||
* Fortunately, load_cr3() is serializing and gives the
|
||||
* ordering guarantee we need.
|
||||
*
|
||||
*/
|
||||
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 per-mm CR4 state */
|
||||
load_mm_cr4(next);
|
||||
|
||||
#ifdef CONFIG_MODIFY_LDT_SYSCALL
|
||||
/*
|
||||
* Load the LDT, if the LDT is different.
|
||||
*
|
||||
* It's possible that prev->context.ldt doesn't match
|
||||
* the LDT register. This can happen if leave_mm(prev)
|
||||
* was called and then modify_ldt changed
|
||||
* prev->context.ldt but suppressed an IPI to this CPU.
|
||||
* In this case, prev->context.ldt != NULL, because we
|
||||
* never set context.ldt to NULL while the mm still
|
||||
* exists. That means that next->context.ldt !=
|
||||
* prev->context.ldt, because mms never share an LDT.
|
||||
*/
|
||||
if (unlikely(prev->context.ldt != next->context.ldt))
|
||||
load_mm_ldt(next);
|
||||
#endif
|
||||
}
|
||||
#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.
|
||||
*
|
||||
* As above, load_cr3() is serializing and orders TLB
|
||||
* fills with respect to the mm_cpumask write.
|
||||
*/
|
||||
load_cr3(next->pgd);
|
||||
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
|
||||
load_mm_cr4(next);
|
||||
load_mm_ldt(next);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
|
||||
/*
|
||||
* The flush IPI assumes that a thread switch happens in this order:
|
||||
* [cpu0: the cpu that switches]
|
||||
|
|
Loading…
Reference in New Issue