x86/mm: Rework lazy TLB to track the actual loaded mm

Lazy TLB state is currently managed in a rather baroque manner.
AFAICT, there are three possible states:

 - Non-lazy.  This means that we're running a user thread or a
   kernel thread that has called use_mm().  current->mm ==
   current->active_mm == cpu_tlbstate.active_mm and
   cpu_tlbstate.state == TLBSTATE_OK.

 - Lazy with user mm.  We're running a kernel thread without an mm
   and we're borrowing an mm_struct.  We have current->mm == NULL,
   current->active_mm == cpu_tlbstate.active_mm, cpu_tlbstate.state
   != TLBSTATE_OK (i.e. TLBSTATE_LAZY or 0).  The current cpu is set
   in mm_cpumask(current->active_mm).  CR3 points to
   current->active_mm->pgd.  The TLB is up to date.

 - Lazy with init_mm.  This happens when we call leave_mm().  We
   have current->mm == NULL, current->active_mm ==
   cpu_tlbstate.active_mm, but that mm is only relelvant insofar as
   the scheduler is tracking it for refcounting.  cpu_tlbstate.state
   != TLBSTATE_OK.  The current cpu is clear in
   mm_cpumask(current->active_mm).  CR3 points to swapper_pg_dir,
   i.e. init_mm->pgd.

This patch simplifies the situation.  Other than perf, x86 stops
caring about current->active_mm at all.  We have
cpu_tlbstate.loaded_mm pointing to the mm that CR3 references.  The
TLB is always up to date for that mm.  leave_mm() just switches us
to init_mm.  There are no longer any special cases for mm_cpumask,
and switch_mm() switches mms without worrying about laziness.

After this patch, cpu_tlbstate.state serves only to tell the TLB
flush code whether it may switch to init_mm instead of doing a
normal flush.

This makes fairly extensive changes to xen_exit_mmap(), which used
to look a bit like black magic.

Perf is unchanged.  With or without this change, perf may behave a bit
erratically if it tries to read user memory in kernel thread context.
We should build on this patch to teach perf to never look at user
memory when cpu_tlbstate.loaded_mm != current->mm.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 108 insertions, 108 deletions

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index da1416c77bfb..44db82013f1c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -28,26 +28,25 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
-/*
- * We cannot call mmdrop() because we are in interrupt context,
- * instead update mm->cpu_vm_mask.
- */
 void leave_mm(int cpu)
 {
-	struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm);
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+
+	/*
+	 * It's plausible that we're in lazy TLB mode while our mm is init_mm.
+	 * If so, our callers still expect us to flush the TLB, but there
+	 * aren't any user TLB entries in init_mm to worry about.
+	 *
+	 * This needs to happen before any other sanity checks due to
+	 * intel_idle's shenanigans.
+	 */
+	if (loaded_mm == &init_mm)
+		return;
+
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
 		BUG();
-	if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
-		cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
-		load_cr3(swapper_pg_dir);
-		/*
-		 * This gets called in the idle path where RCU
-		 * functions differently.  Tracing normally
-		 * uses RCU, so we have to call the tracepoint
-		 * specially here.
-		 */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-	}
+
+	switch_mm(NULL, &init_mm, NULL);
 }
 EXPORT_SYMBOL_GPL(leave_mm);
 
@@ -65,108 +64,109 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			struct task_struct *tsk)
 {
 	unsigned cpu = smp_processor_id();
+	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 
-	if (likely(prev != next)) {
-		if (IS_ENABLED(CONFIG_VMAP_STACK)) {
-			/*
-			 * If our current stack is in vmalloc space and isn't
-			 * mapped in the new pgd, we'll double-fault.  Forcibly
-			 * map it.
-			 */
-			unsigned int stack_pgd_index = pgd_index(current_stack_pointer());
-
-			pgd_t *pgd = next->pgd + stack_pgd_index;
+	/*
+	 * NB: The scheduler will call us with prev == next when
+	 * switching from lazy TLB mode to normal mode if active_mm
+	 * isn't changing.  When this happens, there is no guarantee
+	 * that CR3 (and hence cpu_tlbstate.loaded_mm) matches next.
+	 *
+	 * NB: leave_mm() calls us with prev == NULL and tsk == NULL.
+	 */
 
-			if (unlikely(pgd_none(*pgd)))
-				set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
-		}
-
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		this_cpu_write(cpu_tlbstate.active_mm, next);
+	this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 
-		cpumask_set_cpu(cpu, mm_cpumask(next));
+	if (real_prev == next) {
+		/*
+		 * There's nothing to do: we always keep the per-mm control
+		 * regs in sync with cpu_tlbstate.loaded_mm.  Just
+		 * sanity-check mm_cpumask.
+		 */
+		if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(next))))
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+		return;
+	}
 
+	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
 		/*
-		 * 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.
-		 *
+		 * If our current stack is in vmalloc space and isn't
+		 * mapped in the new pgd, we'll double-fault.  Forcibly
+		 * map it.
 		 */
-		load_cr3(next->pgd);
+		unsigned int stack_pgd_index = pgd_index(current_stack_pointer());
 
-		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+		pgd_t *pgd = next->pgd + stack_pgd_index;
 
-		/* Stop flush ipis for the previous mm */
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		if (unlikely(pgd_none(*pgd)))
+			set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
+	}
 
-		/* Load per-mm CR4 state */
-		load_mm_cr4(next);
+	this_cpu_write(cpu_tlbstate.loaded_mm, next);
+
+	WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next)));
+	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);
+
+	/*
+	 * This gets called via leave_mm() in the idle path where RCU
+	 * functions differently.  Tracing normally uses RCU, so we have to
+	 * call the tracepoint specially here.
+	 */
+	trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+
+	/* Stop flush ipis for the previous mm */
+	WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
+		     real_prev != &init_mm);
+	cpumask_clear_cpu(cpu, mm_cpumask(real_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);
+	/*
+	 * 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(real_prev->context.ldt != next->context.ldt))
+		load_mm_ldt(next);
 #endif
-	} 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);
-		}
-	}
 }
 
 /*
@@ -246,7 +246,7 @@ static void flush_tlb_func_remote(void *info)
 
 	inc_irq_stat(irq_tlb_count);
 
-	if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.active_mm))
+	if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm))
 		return;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -314,7 +314,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		info.end = TLB_FLUSH_ALL;
 	}
 
-	if (mm == current->active_mm)
+	if (mm == this_cpu_read(cpu_tlbstate.loaded_mm))
 		flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN);
 	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), &info);