mm: vmalloc: clean up vunmap to avoid pgtable ops twice

vunmap does page table clear operations twice in the case when
DEBUG_PAGEALLOC_ENABLE_DEFAULT is enabled.

So, clean up the code as that is unintended.

As a perf gain, we save few us.  Below ftrace data was obtained while
doing 1 MB of vmalloc/vfree on ARM64 based SoC *without* this patch
applied.  After this patch, we can save ~3 us (on 1 extra
vunmap_page_range).

  CPU  DURATION                  FUNCTION CALLS
  |     |   |                     |   |   |   |
 6)               |  __vunmap() {
 6)               |    vmap_debug_free_range() {
 6)   3.281 us    |      vunmap_page_range();
 6) + 45.468 us   |    }
 6)   2.760 us    |    vunmap_page_range();
 6) ! 505.105 us  |  }

[cpandya@codeaurora.org: v3]
  Link: http://lkml.kernel.org/r/1525176960-18408-1-git-send-email-cpandya@codeaurora.org
Link: http://lkml.kernel.org/r/1523876342-10545-1-git-send-email-cpandya@codeaurora.orgSigned-off-by: Chintan Pandya <cpandya@codeaurora.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/vmalloc.c

@@ -603,26 +603,6 @@ static void unmap_vmap_area(struct vmap_area *va)
 	vunmap_page_range(va->va_start, va->va_end);
 }
 
-static void vmap_debug_free_range(unsigned long start, unsigned long end)
-{
-	/*
-	 * Unmap page tables and force a TLB flush immediately if pagealloc
-	 * debugging is enabled.  This catches use after free bugs similarly to
-	 * those in linear kernel virtual address space after a page has been
-	 * freed.
-	 *
-	 * All the lazy freeing logic is still retained, in order to minimise
-	 * intrusiveness of this debugging feature.
-	 *
-	 * This is going to be *slow* (linear kernel virtual address debugging
-	 * doesn't do a broadcast TLB flush so it is a lot faster).
-	 */
-	if (debug_pagealloc_enabled()) {
-		vunmap_page_range(start, end);
-		flush_tlb_kernel_range(start, end);
-	}
-}
-
 /*
  * lazy_max_pages is the maximum amount of virtual address space we gather up
  * before attempting to purge with a TLB flush.
@@ -756,6 +736,9 @@ static void free_unmap_vmap_area(struct vmap_area *va)
 {
 	flush_cache_vunmap(va->va_start, va->va_end);
 	unmap_vmap_area(va);
+	if (debug_pagealloc_enabled())
+		flush_tlb_kernel_range(va->va_start, va->va_end);
+
 	free_vmap_area_noflush(va);
 }
 
@@ -1053,6 +1036,10 @@ static void vb_free(const void *addr, unsigned long size)
 
 	vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
 
+	if (debug_pagealloc_enabled())
+		flush_tlb_kernel_range((unsigned long)addr,
+					(unsigned long)addr + size);
+
 	spin_lock(&vb->lock);
 
 	/* Expand dirty range */
@@ -1142,7 +1129,6 @@ void vm_unmap_ram(const void *mem, unsigned int count)
 	BUG_ON(!PAGE_ALIGNED(addr));
 
 	debug_check_no_locks_freed(mem, size);
-	vmap_debug_free_range(addr, addr+size);
 
 	if (likely(count <= VMAP_MAX_ALLOC)) {
 		vb_free(mem, size);
@@ -1499,7 +1485,6 @@ struct vm_struct *remove_vm_area(const void *addr)
 		va->flags |= VM_LAZY_FREE;
 		spin_unlock(&vmap_area_lock);
 
-		vmap_debug_free_range(va->va_start, va->va_end);
 		kasan_free_shadow(vm);
 		free_unmap_vmap_area(va);