![Linus Torvalds](/assets/img/avatar_default.png)
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 commit53a59fc67f
("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 commit597e1c3580
("mm/mmu_gather: enable tlb flush range in generic mmu_gather"), and the range handling was already fixed at least once in commite6c495a96c
("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>
123 lines
3.1 KiB
C
123 lines
3.1 KiB
C
#ifndef __UM_TLB_H
|
|
#define __UM_TLB_H
|
|
|
|
#include <linux/pagemap.h>
|
|
#include <linux/swap.h>
|
|
#include <asm/percpu.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
#define tlb_start_vma(tlb, vma) do { } while (0)
|
|
#define tlb_end_vma(tlb, vma) do { } while (0)
|
|
#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
|
|
|
|
/* struct mmu_gather is an opaque type used by the mm code for passing around
|
|
* any data needed by arch specific code for tlb_remove_page.
|
|
*/
|
|
struct mmu_gather {
|
|
struct mm_struct *mm;
|
|
unsigned int need_flush; /* Really unmapped some ptes? */
|
|
unsigned long start;
|
|
unsigned long end;
|
|
unsigned int fullmm; /* non-zero means full mm flush */
|
|
};
|
|
|
|
static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
|
|
unsigned long address)
|
|
{
|
|
if (tlb->start > address)
|
|
tlb->start = address;
|
|
if (tlb->end < address + PAGE_SIZE)
|
|
tlb->end = address + PAGE_SIZE;
|
|
}
|
|
|
|
static inline void init_tlb_gather(struct mmu_gather *tlb)
|
|
{
|
|
tlb->need_flush = 0;
|
|
|
|
tlb->start = TASK_SIZE;
|
|
tlb->end = 0;
|
|
|
|
if (tlb->fullmm) {
|
|
tlb->start = 0;
|
|
tlb->end = TASK_SIZE;
|
|
}
|
|
}
|
|
|
|
static inline void
|
|
tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
|
|
{
|
|
tlb->mm = mm;
|
|
tlb->start = start;
|
|
tlb->end = end;
|
|
tlb->fullmm = !(start | (end+1));
|
|
|
|
init_tlb_gather(tlb);
|
|
}
|
|
|
|
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
|
|
unsigned long end);
|
|
|
|
static inline void
|
|
tlb_flush_mmu(struct mmu_gather *tlb)
|
|
{
|
|
if (!tlb->need_flush)
|
|
return;
|
|
|
|
flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
|
|
init_tlb_gather(tlb);
|
|
}
|
|
|
|
/* tlb_finish_mmu
|
|
* Called at the end of the shootdown operation to free up any resources
|
|
* that were required.
|
|
*/
|
|
static inline void
|
|
tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
|
|
{
|
|
tlb_flush_mmu(tlb);
|
|
|
|
/* keep the page table cache within bounds */
|
|
check_pgt_cache();
|
|
}
|
|
|
|
/* tlb_remove_page
|
|
* Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)),
|
|
* while handling the additional races in SMP caused by other CPUs
|
|
* caching valid mappings in their TLBs.
|
|
*/
|
|
static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
|
|
{
|
|
tlb->need_flush = 1;
|
|
free_page_and_swap_cache(page);
|
|
return 1; /* avoid calling tlb_flush_mmu */
|
|
}
|
|
|
|
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
|
|
{
|
|
__tlb_remove_page(tlb, page);
|
|
}
|
|
|
|
/**
|
|
* tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
|
|
*
|
|
* Record the fact that pte's were really umapped in ->need_flush, so we can
|
|
* later optimise away the tlb invalidate. This helps when userspace is
|
|
* unmapping already-unmapped pages, which happens quite a lot.
|
|
*/
|
|
#define tlb_remove_tlb_entry(tlb, ptep, address) \
|
|
do { \
|
|
tlb->need_flush = 1; \
|
|
__tlb_remove_tlb_entry(tlb, ptep, address); \
|
|
} while (0)
|
|
|
|
#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
|
|
|
|
#define pud_free_tlb(tlb, pudp, addr) __pud_free_tlb(tlb, pudp, addr)
|
|
|
|
#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
|
|
|
|
#define tlb_migrate_finish(mm) do {} while (0)
|
|
|
|
#endif
|