Merge branch 'topic/irqs-off-activate-mm' into next

Merge Nick's series to add ARCH_WANT_IRQS_OFF_ACTIVATE_MM.

arch/Kconfig

@@ -414,6 +414,13 @@ config MMU_GATHER_NO_GATHER
 	bool
 	depends on MMU_GATHER_TABLE_FREE
 
+config ARCH_WANT_IRQS_OFF_ACTIVATE_MM
+	bool
+	help
+	  Temporary select until all architectures can be converted to have
+	  irqs disabled over activate_mm. Architectures that do IPI based TLB
+	  shootdowns should enable this.
+
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool
 

arch/powerpc/Kconfig

@@ -151,6 +151,7 @@ config PPC
 	select ARCH_USE_QUEUED_RWLOCKS		if PPC_QUEUED_SPINLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS	if PPC_QUEUED_SPINLOCKS
 	select ARCH_WANT_IPC_PARSE_VERSION
+	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	select ARCH_WEAK_RELEASE_ACQUIRE
 	select BINFMT_ELF
 	select BUILDTIME_TABLE_SORT

arch/powerpc/include/asm/mmu_context.h

@@ -244,7 +244,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
  */
 static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
 {
-	switch_mm(prev, next, current);
+	switch_mm_irqs_off(prev, next, current);
 }
 
 /* We don't currently use enter_lazy_tlb() for anything */

arch/powerpc/include/asm/tlb.h

@@ -66,19 +66,6 @@ static inline int mm_is_thread_local(struct mm_struct *mm)
 		return false;
 	return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm));
 }
-static inline void mm_reset_thread_local(struct mm_struct *mm)
-{
-	WARN_ON(atomic_read(&mm->context.copros) > 0);
-	/*
-	 * It's possible for mm_access to take a reference on mm_users to
-	 * access the remote mm from another thread, but it's not allowed
-	 * to set mm_cpumask, so mm_users may be > 1 here.
-	 */
-	WARN_ON(current->mm != mm);
-	atomic_set(&mm->context.active_cpus, 1);
-	cpumask_clear(mm_cpumask(mm));
-	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-}
 #else /* CONFIG_PPC_BOOK3S_64 */
 static inline int mm_is_thread_local(struct mm_struct *mm)
 {

arch/powerpc/mm/book3s64/radix_tlb.c

@@ -645,19 +645,29 @@ static void do_exit_flush_lazy_tlb(void *arg)
 	struct mm_struct *mm = arg;
 	unsigned long pid = mm->context.id;
 
+	/*
+	 * A kthread could have done a mmget_not_zero() after the flushing CPU
+	 * checked mm_is_singlethreaded, and be in the process of
+	 * kthread_use_mm when interrupted here. In that case, current->mm will
+	 * be set to mm, because kthread_use_mm() setting ->mm and switching to
+	 * the mm is done with interrupts off.
+	 */
 	if (current->mm == mm)
-		return; /* Local CPU */
+		goto out_flush;
 
 	if (current->active_mm == mm) {
-		/*
-		 * Must be a kernel thread because sender is single-threaded.
-		 */
-		BUG_ON(current->mm);
+		WARN_ON_ONCE(current->mm != NULL);
+		/* Is a kernel thread and is using mm as the lazy tlb */
 		mmgrab(&init_mm);
-		switch_mm(mm, &init_mm, current);
 		current->active_mm = &init_mm;
+		switch_mm_irqs_off(mm, &init_mm, current);
 		mmdrop(mm);
 	}
+
+	atomic_dec(&mm->context.active_cpus);
+	cpumask_clear_cpu(smp_processor_id(), mm_cpumask(mm));
+
+out_flush:
 	_tlbiel_pid(pid, RIC_FLUSH_ALL);
 }
 
@@ -672,7 +682,6 @@ static void exit_flush_lazy_tlbs(struct mm_struct *mm)
 	 */
 	smp_call_function_many(mm_cpumask(mm), do_exit_flush_lazy_tlb,
 				(void *)mm, 1);
-	mm_reset_thread_local(mm);
 }
 
 void radix__flush_tlb_mm(struct mm_struct *mm)

arch/sparc/kernel/smp_64.c

@@ -1039,38 +1039,9 @@ void smp_fetch_global_pmu(void)
  * are flush_tlb_*() routines, and these run after flush_cache_*()
  * which performs the flushw.
  *
- * The SMP TLB coherency scheme we use works as follows:
- *
- * 1) mm->cpu_vm_mask is a bit mask of which cpus an address
- *    space has (potentially) executed on, this is the heuristic
- *    we use to avoid doing cross calls.
- *
- *    Also, for flushing from kswapd and also for clones, we
- *    use cpu_vm_mask as the list of cpus to make run the TLB.
- *
- * 2) TLB context numbers are shared globally across all processors
- *    in the system, this allows us to play several games to avoid
- *    cross calls.
- *
- *    One invariant is that when a cpu switches to a process, and
- *    that processes tsk->active_mm->cpu_vm_mask does not have the
- *    current cpu's bit set, that tlb context is flushed locally.
- *
- *    If the address space is non-shared (ie. mm->count == 1) we avoid
- *    cross calls when we want to flush the currently running process's
- *    tlb state.  This is done by clearing all cpu bits except the current
- *    processor's in current->mm->cpu_vm_mask and performing the
- *    flush locally only.  This will force any subsequent cpus which run
- *    this task to flush the context from the local tlb if the process
- *    migrates to another cpu (again).
- *
- * 3) For shared address spaces (threads) and swapping we bite the
- *    bullet for most cases and perform the cross call (but only to
- *    the cpus listed in cpu_vm_mask).
- *
- *    The performance gain from "optimizing" away the cross call for threads is
- *    questionable (in theory the big win for threads is the massive sharing of
- *    address space state across processors).
+ * mm->cpu_vm_mask is a bit mask of which cpus an address
+ * space has (potentially) executed on, this is the heuristic
+ * we use to limit cross calls.
  */
 
 /* This currently is only used by the hugetlb arch pre-fault
@@ -1080,18 +1051,13 @@ void smp_fetch_global_pmu(void)
 void smp_flush_tlb_mm(struct mm_struct *mm)
 {
 	u32 ctx = CTX_HWBITS(mm->context);
-	int cpu = get_cpu();
 
-	if (atomic_read(&mm->mm_users) == 1) {
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-		goto local_flush_and_out;
-	}
+	get_cpu();
 
 	smp_cross_call_masked(&xcall_flush_tlb_mm,
 			      ctx, 0, 0,
 			      mm_cpumask(mm));
 
-local_flush_and_out:
 	__flush_tlb_mm(ctx, SECONDARY_CONTEXT);
 
 	put_cpu();
@@ -1114,17 +1080,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long
 {
 	u32 ctx = CTX_HWBITS(mm->context);
 	struct tlb_pending_info info;
-	int cpu = get_cpu();
+
+	get_cpu();
 
 	info.ctx = ctx;
 	info.nr = nr;
 	info.vaddrs = vaddrs;
 
-	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-	else
-		smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
-				       &info, 1);
+	smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+			       &info, 1);
 
 	__flush_tlb_pending(ctx, nr, vaddrs);
 
@@ -1134,14 +1098,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long
 void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
 {
 	unsigned long context = CTX_HWBITS(mm->context);
-	int cpu = get_cpu();
 
-	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-	else
-		smp_cross_call_masked(&xcall_flush_tlb_page,
-				      context, vaddr, 0,
-				      mm_cpumask(mm));
+	get_cpu();
+
+	smp_cross_call_masked(&xcall_flush_tlb_page,
+			      context, vaddr, 0,
+			      mm_cpumask(mm));
+
 	__flush_tlb_page(context, vaddr);
 
 	put_cpu();

fs/exec.c

@@ -1130,11 +1130,24 @@ static int exec_mmap(struct mm_struct *mm)
 	}
 
 	task_lock(tsk);
-	active_mm = tsk->active_mm;
 	membarrier_exec_mmap(mm);
-	tsk->mm = mm;
+
+	local_irq_disable();
+	active_mm = tsk->active_mm;
 	tsk->active_mm = mm;
+	tsk->mm = mm;
+	/*
+	 * This prevents preemption while active_mm is being loaded and
+	 * it and mm are being updated, which could cause problems for
+	 * lazy tlb mm refcounting when these are updated by context
+	 * switches. Not all architectures can handle irqs off over
+	 * activate_mm yet.
+	 */
+	if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
+		local_irq_enable();
 	activate_mm(active_mm, mm);
+	if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
+		local_irq_enable();
 	tsk->mm->vmacache_seqnum = 0;
 	vmacache_flush(tsk);
 	task_unlock(tsk);