mm: defer flush of writable TLB entries

If a PTE is unmapped and it's dirty then it was writable recently.  Due to
deferred TLB flushing, it's best to assume a writable TLB cache entry
exists.  With that assumption, the TLB must be flushed before any IO can
start or the page is freed to avoid lost writes or data corruption.  This
patch defers flushing of potentially writable TLBs as long as possible.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/sched.h

@@ -1354,6 +1354,13 @@ struct tlbflush_unmap_batch {
 
 	/* True if any bit in cpumask is set */
 	bool flush_required;
+
+	/*
+	 * If true then the PTE was dirty when unmapped. The entry must be
+	 * flushed before IO is initiated or a stale TLB entry potentially
+	 * allows an update without redirtying the page.
+	 */
+	bool writable;
 };
 
 struct task_struct {

mm/internal.h

@@ -431,10 +431,14 @@ struct tlbflush_unmap_batch;
 
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 void try_to_unmap_flush(void);
+void try_to_unmap_flush_dirty(void);
 #else
 static inline void try_to_unmap_flush(void)
 {
 }
+static inline void try_to_unmap_flush_dirty(void)
+{
+}
 
 #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
 #endif	/* __MM_INTERNAL_H */

mm/rmap.c

@@ -626,16 +626,34 @@ void try_to_unmap_flush(void)
 	}
 	cpumask_clear(&tlb_ubc->cpumask);
 	tlb_ubc->flush_required = false;
+	tlb_ubc->writable = false;
 	put_cpu();
 }
 
+/* Flush iff there are potentially writable TLB entries that can race with IO */
+void try_to_unmap_flush_dirty(void)
+{
+	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+
+	if (tlb_ubc->writable)
+		try_to_unmap_flush();
+}
+
 static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
-		struct page *page)
+		struct page *page, bool writable)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
 
 	cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm));
 	tlb_ubc->flush_required = true;
+
+	/*
+	 * If the PTE was dirty then it's best to assume it's writable. The
+	 * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush()
+	 * before the page is queued for IO.
+	 */
+	if (writable)
+		tlb_ubc->writable = true;
 }
 
 /*
@@ -658,7 +676,7 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
 }
 #else
 static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
-		struct page *page)
+		struct page *page, bool writable)
 {
 }
 
@@ -1315,11 +1333,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		 */
 		pteval = ptep_get_and_clear(mm, address, pte);
 
-		/* Potentially writable TLBs must be flushed before IO */
-		if (pte_dirty(pteval))
-			flush_tlb_page(vma, address);
-		else
-			set_tlb_ubc_flush_pending(mm, page);
+		set_tlb_ubc_flush_pending(mm, page, pte_dirty(pteval));
 	} else {
 		pteval = ptep_clear_flush(vma, address, pte);
 	}

mm/vmscan.c

@@ -1098,7 +1098,12 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			if (!sc->may_writepage)
 				goto keep_locked;
 
-			/* Page is dirty, try to write it out here */
+			/*
+			 * Page is dirty. Flush the TLB if a writable entry
+			 * potentially exists to avoid CPU writes after IO
+			 * starts and then write it out here.
+			 */
+			try_to_unmap_flush_dirty();
 			switch (pageout(page, mapping, sc)) {
 			case PAGE_KEEP:
 				goto keep_locked;