Fix TLB gather virtual address range invalidation corner cases

Ben Tebulin reported:

 "Since v3.7.2 on two independent machines a very specific Git
  repository fails in 9/10 cases on git-fsck due to an SHA1/memory
  failures.  This only occurs on a very specific repository and can be
  reproduced stably on two independent laptops.  Git mailing list ran
  out of ideas and for me this looks like some very exotic kernel issue"

and bisected the failure to the backport of commit 53a59fc67f97 ("mm:
limit mmu_gather batching to fix soft lockups on !CONFIG_PREEMPT").

That commit itself is not actually buggy, but what it does is to make it
much more likely to hit the partial TLB invalidation case, since it
introduces a new case in tlb_next_batch() that previously only ever
happened when running out of memory.

The real bug is that the TLB gather virtual memory range setup is subtly
buggered.  It was introduced in commit 597e1c3580b7 ("mm/mmu_gather:
enable tlb flush range in generic mmu_gather"), and the range handling
was already fixed at least once in commit e6c495a96ce0 ("mm: fix the TLB
range flushed when __tlb_remove_page() runs out of slots"), but that fix
was not complete.

The problem with the TLB gather virtual address range is that it isn't
set up by the initial tlb_gather_mmu() initialization (which didn't get
the TLB range information), but it is set up ad-hoc later by the
functions that actually flush the TLB.  And so any such case that forgot
to update the TLB range entries would potentially miss TLB invalidates.

Rather than try to figure out exactly which particular ad-hoc range
setup was missing (I personally suspect it's the hugetlb case in
zap_huge_pmd(), which didn't have the same logic as zap_pte_range()
did), this patch just gets rid of the problem at the source: make the
TLB range information available to tlb_gather_mmu(), and initialize it
when initializing all the other tlb gather fields.

This makes the patch larger, but conceptually much simpler.  And the end
result is much more understandable; even if you want to play games with
partial ranges when invalidating the TLB contents in chunks, now the
range information is always there, and anybody who doesn't want to
bother with it won't introduce subtle bugs.

Ben verified that this fixes his problem.

Reported-bisected-and-tested-by: Ben Tebulin <tebulin@googlemail.com>
Build-testing-by: Stephen Rothwell <sfr@canb.auug.org.au>
Build-testing-by: Richard Weinberger <richard.weinberger@gmail.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 24 insertions, 18 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 83aff0a..b60f330 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2490,7 +2490,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 
 	mm = vma->vm_mm;
 
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, start, end);
 	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
 	tlb_finish_mmu(&tlb, start, end);
 }
diff --git a/mm/memory.c b/mm/memory.c
index 4026841..af84bc0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -209,14 +209,15 @@ static int tlb_next_batch(struct mmu_gather *tlb)
  *	tear-down from @mm. The @fullmm argument is used when @mm is without
  *	users and we're going to destroy the full address space (exit/execve).
  */
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 
-	tlb->fullmm     = fullmm;
+	/* Is it from 0 to ~0? */
+	tlb->fullmm     = !(start | (end+1));
 	tlb->need_flush_all = 0;
-	tlb->start	= -1UL;
-	tlb->end	= 0;
+	tlb->start	= start;
+	tlb->end	= end;
 	tlb->need_flush = 0;
 	tlb->local.next = NULL;
 	tlb->local.nr   = 0;
@@ -256,8 +257,6 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
 {
 	struct mmu_gather_batch *batch, *next;
 
-	tlb->start = start;
-	tlb->end   = end;
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
@@ -1099,7 +1098,6 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	spinlock_t *ptl;
 	pte_t *start_pte;
 	pte_t *pte;
-	unsigned long range_start = addr;
 
 again:
 	init_rss_vec(rss);
@@ -1205,17 +1203,25 @@ again:
 	 * and page-free while holding it.
 	 */
 	if (force_flush) {
+		unsigned long old_end;
+
 		force_flush = 0;
 
-#ifdef HAVE_GENERIC_MMU_GATHER
-		tlb->start = range_start;
+		/*
+		 * Flush the TLB just for the previous segment,
+		 * then update the range to be the remaining
+		 * TLB range.
+		 */
+		old_end = tlb->end;
 		tlb->end = addr;
-#endif
+
 		tlb_flush_mmu(tlb);
-		if (addr != end) {
-			range_start = addr;
+
+		tlb->start = addr;
+		tlb->end = old_end;
+
+		if (addr != end)
 			goto again;
-		}
 	}
 
 	return addr;
@@ -1400,7 +1406,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
 	unsigned long end = start + size;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, start, end);
 	update_hiwater_rss(mm);
 	mmu_notifier_invalidate_range_start(mm, start, end);
 	for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
@@ -1426,7 +1432,7 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr
 	unsigned long end = address + size;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, address, end);
 	update_hiwater_rss(mm);
 	mmu_notifier_invalidate_range_start(mm, address, end);
 	unmap_single_vma(&tlb, vma, address, end, details);
diff --git a/mm/mmap.c b/mm/mmap.c
index 1edbaa3..f9c97d1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2336,7 +2336,7 @@ static void unmap_region(struct mm_struct *mm,
 	struct mmu_gather tlb;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, start, end);
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end);
 	free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
@@ -2709,7 +2709,7 @@ void exit_mmap(struct mm_struct *mm)
 
 	lru_add_drain();
 	flush_cache_mm(mm);
-	tlb_gather_mmu(&tlb, mm, 1);
+	tlb_gather_mmu(&tlb, mm, 0, -1);
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);