Commit 031e6e6b authored by Steve Capper's avatar Steve Capper Committed by Will Deacon

arm64: hugetlb: Avoid unnecessary clearing in huge_ptep_set_access_flags

For contiguous hugetlb, huge_ptep_set_access_flags performs a
get_clear_flush (which then flushes the TLBs) even when no change of ptes
is necessary.

Unfortunately, this behaviour can lead to back-to-back page faults being
generated when running with multiple threads that access the same
contiguous huge page.

Thread 1                     |  Thread 2
-----------------------------+------------------------------
hugetlb_fault                |
huge_ptep_set_access_flags   |
  -> invalidate pte range    | hugetlb_fault
continue processing          | wait for hugetlb_fault_mutex
release mutex and return     | huge_ptep_set_access_flags
                             |   -> invalidate pte range
hugetlb_fault
...

This patch changes huge_ptep_set_access_flags s.t. we first read the
contiguous range of ptes (whilst preserving dirty information); the pte
range is only then invalidated where necessary and this prevents further
spurious page faults.

Fixes: d8bdcff2 ("arm64: hugetlb: Add break-before-make logic for contiguous entries")
Reported-by: default avatarLei Zhang <zhang.lei@jp.fujitsu.com>
Signed-off-by: default avatarSteve Capper <steve.capper@arm.com>
Signed-off-by: default avatarWill Deacon <will.deacon@arm.com>
parent 469ed9d8
......@@ -323,11 +323,40 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
}
/*
* huge_ptep_set_access_flags will update access flags (dirty, accesssed)
* and write permission.
*
* For a contiguous huge pte range we need to check whether or not write
* permission has to change only on the first pte in the set. Then for
* all the contiguous ptes we need to check whether or not there is a
* discrepancy between dirty or young.
*/
static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
{
int i;
if (pte_write(pte) != pte_write(huge_ptep_get(ptep)))
return 1;
for (i = 0; i < ncontig; i++) {
pte_t orig_pte = huge_ptep_get(ptep + i);
if (pte_dirty(pte) != pte_dirty(orig_pte))
return 1;
if (pte_young(pte) != pte_young(orig_pte))
return 1;
}
return 0;
}
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
int ncontig, i, changed = 0;
int ncontig, i;
size_t pgsize = 0;
unsigned long pfn = pte_pfn(pte), dpfn;
pgprot_t hugeprot;
......@@ -339,9 +368,10 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
dpfn = pgsize >> PAGE_SHIFT;
if (!__cont_access_flags_changed(ptep, pte, ncontig))
return 0;
orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
if (!pte_same(orig_pte, pte))
changed = 1;
/* Make sure we don't lose the dirty or young state */
if (pte_dirty(orig_pte))
......@@ -354,7 +384,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
return changed;
return 1;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment