2 files changed, 22 insertions, 6 deletions

diff --git a/include/asm-x86/pgalloc_32.h b/include/asm-x86/pgalloc_32.h
index 0caa37a9a25f..10c2b452e64c 100644
--- a/include/asm-x86/pgalloc_32.h
+++ b/include/asm-x86/pgalloc_32.h
@@ -74,6 +74,13 @@ static inline void pmd_free(pmd_t *pmd)
 
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
+        /* This is called just after the pmd has been detached from
+           the pgd, which requires a full tlb flush to be recognized
+           by the CPU.  Rather than incurring multiple tlb flushes
+           while the address space is being pulled down, make the tlb
+           gathering machinery do a full flush when we're done. */
+        tlb->fullmm = 1;
+
         paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT);
         tlb_remove_page(tlb, virt_to_page(pmd));
 }
diff --git a/include/asm-x86/pgtable-3level.h b/include/asm-x86/pgtable-3level.h
index ed4c6f0e57ec..a195c3e757b9 100644
--- a/include/asm-x86/pgtable-3level.h
+++ b/include/asm-x86/pgtable-3level.h
@@ -96,14 +96,23 @@ static inline void pud_clear(pud_t *pudp)
         set_pud(pudp, __pud(0));
 
         /*
-         * Pentium-II erratum A13: in PAE mode we explicitly have to flush
-         * the TLB via cr3 if the top-level pgd is changed...
+         * In principle we need to do a cr3 reload here to make sure
+         * the processor recognizes the changed pgd.  In practice, all
+         * the places where pud_clear() gets called are followed by
+         * full tlb flushes anyway, so we can defer the cost here.
          *
-         * XXX I don't think we need to worry about this here, since
-         * when clearing the pud, the calling code needs to flush the
-         * tlb anyway.  But do it now for safety's sake. - jsgf
+         * Specifically:
+         *
+         * mm/memory.c:free_pmd_range() - immediately after the
+         * pud_clear() it does a pmd_free_tlb().  We change the
+         * mmu_gather structure to do a full tlb flush (which has the
+         * effect of reloading cr3) when the pagetable free is
+         * complete.
+         *
+         * arch/x86/mm/hugetlbpage.c:huge_pmd_unshare() - the call to
+         * this is followed by a flush_tlb_range, which on x86 does a
+         * full tlb flush.
          */
-        write_cr3(read_cr3());
 }
 
 #define pud_page(pud) \