powerpc/64s/radix: Fix mm_cpumask trimming race vs kthread_use_mm

Commit 0cef77c7798a7 ("powerpc/64s/radix: flush remote CPUs out of
single-threaded mm_cpumask") added a mechanism to trim the mm_cpumask of
a process under certain conditions. One of the assumptions is that
mm_users would not be incremented via a reference outside the process
context with mmget_not_zero() then go on to kthread_use_mm() via that
reference.

That invariant was broken by io_uring code (see previous sparc64 fix),
but I'll point Fixes: to the original powerpc commit because we are
changing that assumption going forward, so this will make backports
match up.

Fix this by no longer relying on that assumption, but by having each CPU
check the mm is not being used, and clearing their own bit from the mask
only if it hasn't been switched-to by the time the IPI is processed.

This relies on commit 38cf307c1f20 ("mm: fix kthread_use_mm() vs TLB
invalidate") and ARCH_WANT_IRQS_OFF_ACTIVATE_MM to disable irqs over mm
switch sequences.

Fixes: 0cef77c7798a7 ("powerpc/64s/radix: flush remote CPUs out of single-threaded mm_cpumask")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Michael Ellerman <mpe@ellerman.id.au>
Depends-on: 38cf307c1f20 ("mm: fix kthread_use_mm() vs TLB invalidate")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200914045219.3736466-5-npiggin@gmail.com

diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index fbc6f30..d97f061 100644 (file)
--- a/arch/powerpc/include/asm/tlb.h
+++ b/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)
 {

diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 0d23376..143b4fd 100644 (file)
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/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)