mm/rmap: batched invalidations should use existing api

The recently introduced batched invalidations mechanism uses its own
mechanism for shootdown.  However, it does wrong accounting of
interrupts (e.g., inc_irq_stat is called for local invalidations),
trace-points (e.g., TLB_REMOTE_SHOOTDOWN for local invalidations) and
may break some platforms as it bypasses the invalidation mechanisms of
Xen and SGI UV.

This patch reuses the existing TLB flushing mechnaisms instead.  We use
NULL as mm to indicate a global invalidation is required.

Fixes 72b252aed506b8 ("mm: send one IPI per CPU to TLB flush all entries after unmapping pages")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index c24b4224d439267051d85af645a026a54fd67f84..1fde8d580a5bac371c7a56cf60e688c49d2299f6 100644 (file)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -319,12 +319,6 @@ static inline void reset_lazy_tlbstate(void)
 
 #endif /* SMP */
 
-/* Not inlined due to inc_irq_stat not being defined yet */
-#define flush_tlb_local() {            \
-       inc_irq_stat(irq_tlb_count);    \
-       local_flush_tlb();              \
-}
-
 #ifndef CONFIG_PARAVIRT
 #define flush_tlb_others(mask, mm, start, end) \
        native_flush_tlb_others(mask, mm, start, end)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5fb6adaaa7964d68c1bd7cbc81d6c2ed6bd44bcd..fe9b9f77636168752f989b9d007634396864bf13 100644 (file)
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -104,7 +104,7 @@ static void flush_tlb_func(void *info)
 
        inc_irq_stat(irq_tlb_count);
 
-       if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
+       if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
                return;
 
        count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);

diff --git a/mm/rmap.c b/mm/rmap.c
index c399a0d41b3132f8322a1f7f76eb00231d20c52f..395e314b79962696d9be729861bd28300fd7e68b 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -569,19 +569,6 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 }
 
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
-static void percpu_flush_tlb_batch_pages(void *data)
-{
-       /*
-        * All TLB entries are flushed on the assumption that it is
-        * cheaper to flush all TLBs and let them be refilled than
-        * flushing individual PFNs. Note that we do not track mm's
-        * to flush as that might simply be multiple full TLB flushes
-        * for no gain.
-        */
-       count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
-       flush_tlb_local();
-}
-
 /*
  * Flush TLB entries for recently unmapped pages from remote CPUs. It is
  * important if a PTE was dirty when it was unmapped that it's flushed
@@ -598,15 +585,14 @@ void try_to_unmap_flush(void)
 
        cpu = get_cpu();
 
-       trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, -1UL);
-
-       if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask))
-               percpu_flush_tlb_batch_pages(&tlb_ubc->cpumask);
-
-       if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) {
-               smp_call_function_many(&tlb_ubc->cpumask,
-                       percpu_flush_tlb_batch_pages, (void *)tlb_ubc, true);
+       if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) {
+               count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
+               local_flush_tlb();
+               trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
        }
+
+       if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids)
+               flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL);
        cpumask_clear(&tlb_ubc->cpumask);
        tlb_ubc->flush_required = false;
        tlb_ubc->writable = false;