thp: add tlb_remove_pmd_tlb_entry

We have tlb_remove_tlb_entry to indicate a pte tlb flush entry should be
flushed, but not a corresponding API for pmd entry.  This isn't a
problem so far because THP is only for x86 currently and tlb_flush()
under x86 will flush entire TLB.  But this is confusion and could be
missed if thp is ported to other arch.

Also convert tlb->need_flush = 1 to a VM_BUG_ON(!tlb->need_flush) in
__tlb_remove_page() as suggested by Andrea Arcangeli.  The
__tlb_remove_page() function is supposed to be called after
tlb_remove_xxx_tlb_entry() and we can catch any misuse.

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/asm-generic/tlb.h

@@ -139,6 +139,20 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
+/**
+ * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation
+ * This is a nop so far, because only x86 needs it.
+ */
+#ifndef __tlb_remove_pmd_tlb_entry
+#define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0)
+#endif
+
+#define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)		\
+	do {							\
+		tlb->need_flush = 1;				\
+		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);	\
+	} while (0)
+
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
 		tlb->need_flush = 1;				\

include/linux/huge_mm.h

@@ -18,7 +18,7 @@ extern struct page *follow_trans_huge_pmd(struct mm_struct *mm,
 					  unsigned int flags);
 extern int zap_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
-			pmd_t *pmd);
+			pmd_t *pmd, unsigned long addr);
 extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned char *vec);

mm/huge_memory.c

@@ -1026,7 +1026,7 @@ out:
 }
 
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
-		 pmd_t *pmd)
+		 pmd_t *pmd, unsigned long addr)
 {
 	int ret = 0;
 
@@ -1042,6 +1042,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			pgtable = get_pmd_huge_pte(tlb->mm);
 			page = pmd_page(*pmd);
 			pmd_clear(pmd);
+			tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 			page_remove_rmap(page);
 			VM_BUG_ON(page_mapcount(page) < 0);
 			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);

mm/memory.c

@@ -293,7 +293,7 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	struct mmu_gather_batch *batch;
 
-	tlb->need_flush = 1;
+	VM_BUG_ON(!tlb->need_flush);
 
 	if (tlb_fast_mode(tlb)) {
 		free_page_and_swap_cache(page);
@@ -1231,7 +1231,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 			if (next-addr != HPAGE_PMD_SIZE) {
 				VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
 				split_huge_page_pmd(vma->vm_mm, pmd);
-			} else if (zap_huge_pmd(tlb, vma, pmd))
+			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				continue;
 			/* fall through */
 		}