From: Davidlohr Bueso <d...@stgolabs.net>
The i_mmap_rwsem protects shared pages against races
when doing the sharing and unsharing, ultimately
calling huge_pmd_share/unshare() for PMD pages --
it also needs it to avoid races when populating the pud
for pmd allocation when looking for a shareable pmd page
for hugetlb. Ultimately the interval tree remains intact.
Signed-off-by: Davidlohr Bueso <dbu...@suse.de>
---
Resending this patch due to stupid email quota rules, *sigh*
fs/hugetlbfs/inode.c | 4 ++--
mm/hugetlb.c | 12 ++++++------
mm/memory.c | 4 ++--
3 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 5eba47f..0dca54d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -412,10 +412,10 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t
offset)
pgoff = offset >> PAGE_SHIFT;
i_size_write(inode, offset);
- i_mmap_lock_write(mapping);
+ i_mmap_lock_read(mapping);
if (!RB_EMPTY_ROOT(&mapping->i_mmap))
hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_read(mapping);
truncate_hugepages(inode, offset);
return 0;
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7eeab54..f68dd21 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2772,7 +2772,7 @@ static void unmap_ref_private(struct mm_struct *mm,
struct vm_area_struct *vma,
* this mapping should be shared between all the VMAs,
* __unmap_hugepage_range() is called as the lock is already held
*/
- i_mmap_lock_write(mapping);
+ i_mmap_lock_read(mapping);
vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) {
/* Do not unmap the current VMA */
if (iter_vma == vma)
@@ -2789,7 +2789,7 @@ static void unmap_ref_private(struct mm_struct *mm,
struct vm_area_struct *vma,
unmap_hugepage_range(iter_vma, address,
address + huge_page_size(h), page);
}
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_read(mapping);
}
/*
@@ -3346,7 +3346,7 @@ unsigned long hugetlb_change_protection(struct
vm_area_struct *vma,
flush_cache_range(vma, address, end);
mmu_notifier_invalidate_range_start(mm, start, end);
- i_mmap_lock_write(vma->vm_file->f_mapping);
+ i_mmap_lock_read(vma->vm_file->f_mapping);
for (; address < end; address += huge_page_size(h)) {
spinlock_t *ptl;
ptep = huge_pte_offset(mm, address);
@@ -3374,7 +3374,7 @@ unsigned long hugetlb_change_protection(struct
vm_area_struct *vma,
* and that page table be reused and filled with junk.
*/
flush_tlb_range(vma, start, end);
- i_mmap_unlock_write(vma->vm_file->f_mapping);
+ i_mmap_unlock_read(vma->vm_file->f_mapping);
mmu_notifier_invalidate_range_end(mm, start, end);
return pages << h->order;
@@ -3542,7 +3542,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long
addr, pud_t *pud)
if (!vma_shareable(vma, addr))
return (pte_t *)pmd_alloc(mm, pud, addr);
- i_mmap_lock_write(mapping);
+ i_mmap_lock_read(mapping);
vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
if (svma == vma)
continue;
@@ -3570,7 +3570,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long
addr, pud_t *pud)
spin_unlock(ptl);
out:
pte = (pte_t *)pmd_alloc(mm, pud, addr);
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_read(mapping);
return pte;
}
diff --git a/mm/memory.c b/mm/memory.c
index d16c662..b1931c1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1339,9 +1339,9 @@ static void unmap_single_vma(struct mmu_gather *tlb,
* safe to do nothing in this case.
*/
if (vma->vm_file) {
- i_mmap_lock_write(vma->vm_file->f_mapping);
+ i_mmap_lock_read(vma->vm_file->f_mapping);
__unmap_hugepage_range_final(tlb, vma, start,
end, NULL);
- i_mmap_unlock_write(vma->vm_file->f_mapping);
+ i_mmap_unlock_read(vma->vm_file->f_mapping);
}
} else
unmap_page_range(tlb, vma, start, end, details);
--
1.8.4.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
