summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-08-15 11:42:25 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-08-16 08:52:46 -0700
commit2b047252d087be7f2ba088b4933cd904f92e6fce (patch)
treeb240af27ca0530f7b26f1314968f01140a72a5f8 /arch
parentf1d6e17f540af37bb1891480143669ba7636c4cf (diff)
downloadop-kernel-dev-2b047252d087be7f2ba088b4933cd904f92e6fce.zip
op-kernel-dev-2b047252d087be7f2ba088b4933cd904f92e6fce.tar.gz
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>
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/tlb.h7
-rw-r--r--arch/arm64/include/asm/tlb.h7
-rw-r--r--arch/ia64/include/asm/tlb.h9
-rw-r--r--arch/s390/include/asm/tlb.h8
-rw-r--r--arch/sh/include/asm/tlb.h6
-rw-r--r--arch/um/include/asm/tlb.h6
6 files changed, 30 insertions, 13 deletions
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 46e7cfb..0baf7f0 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -43,6 +43,7 @@ struct mmu_gather {
struct mm_struct *mm;
unsigned int fullmm;
struct vm_area_struct *vma;
+ unsigned long start, end;
unsigned long range_start;
unsigned long range_end;
unsigned int nr;
@@ -107,10 +108,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->vma = NULL;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 46b3beb..717031a 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -35,6 +35,7 @@ struct mmu_gather {
struct mm_struct *mm;
unsigned int fullmm;
struct vm_area_struct *vma;
+ unsigned long start, end;
unsigned long range_start;
unsigned long range_end;
unsigned int nr;
@@ -97,10 +98,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->vma = NULL;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index ef3a9de..bc5efc7 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -22,7 +22,7 @@
* unmapping a portion of the virtual address space, these hooks are called according to
* the following template:
*
- * tlb <- tlb_gather_mmu(mm, full_mm_flush); // start unmap for address space MM
+ * tlb <- tlb_gather_mmu(mm, start, end); // start unmap for address space MM
* {
* for each vma that needs a shootdown do {
* tlb_start_vma(tlb, vma);
@@ -58,6 +58,7 @@ struct mmu_gather {
unsigned int max;
unsigned char fullmm; /* non-zero means full mm flush */
unsigned char need_flush; /* really unmapped some PTEs? */
+ unsigned long start, end;
unsigned long start_addr;
unsigned long end_addr;
struct page **pages;
@@ -155,13 +156,15 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
tlb->nr = 0;
- tlb->fullmm = full_mm_flush;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->start_addr = ~0UL;
}
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b75d7d6..23a64d2 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -32,6 +32,7 @@ struct mmu_gather {
struct mm_struct *mm;
struct mmu_table_batch *batch;
unsigned int fullmm;
+ unsigned long start, unsigned long end;
};
struct mmu_table_batch {
@@ -48,10 +49,13 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
static inline void tlb_gather_mmu(struct mmu_gather *tlb,
struct mm_struct *mm,
- unsigned int full_mm_flush)
+ unsigned long start,
+ unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
tlb->batch = NULL;
if (tlb->fullmm)
__tlb_flush_mm(mm);
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index e61d43d..362192e 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -36,10 +36,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
init_tlb_gather(tlb);
}
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 4febacd..29b0301 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -45,10 +45,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
init_tlb_gather(tlb);
}
OpenPOWER on IntegriCloud