The patch titled
Subject: mm/hugetlb: page faults check for fallocate hole punch in progress and wait
has been added to the -mm tree. Its filename is
mm-hugetlb-page-faults-check-for-fallocate-hole-punch-in-progress-and-wait.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlb-page-faults-check-for-fallocate-hole-punch-in-progress-and-wait.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlb-page-faults-check-for-fallocate-hole-punch-in-progress-and-wait.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: mm/hugetlb: page faults check for fallocate hole punch in progress and wait
At page fault time, check i_private which indicates a fallocate hole punch
is in progress. If the fault falls within the hole, wait for the hole
punch operation to complete before proceeding with the fault.
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/hugetlb.c | 37 +++++++++++++++++++++++++++++++++++++
1 file changed, 37 insertions(+)
diff -puN mm/hugetlb.c~mm-hugetlb-page-faults-check-for-fallocate-hole-punch-in-progress-and-wait mm/hugetlb.c
--- a/mm/hugetlb.c~mm-hugetlb-page-faults-check-for-fallocate-hole-punch-in-progress-and-wait
+++ a/mm/hugetlb.c
@@ -3583,6 +3583,7 @@ int hugetlb_fault(struct mm_struct *mm,
struct page *pagecache_page = NULL;
struct hstate *h = hstate_vma(vma);
struct address_space *mapping;
+ struct inode *inode = file_inode(vma->vm_file);
int need_wait_lock = 0;
address &= huge_page_mask(h);
@@ -3606,6 +3607,42 @@ int hugetlb_fault(struct mm_struct *mm,
idx = vma_hugecache_offset(h, vma, address);
/*
+ * page faults could race with fallocate hole punch. If a page
+ * is faulted between unmap and deallocation, it will still remain
+ * in the punched hole. During hole punch operations, a hugetlb_falloc
+ * structure will be pointed to by i_private. If this fault is for
+ * a page in a hole being punched, wait for the operation to finish
+ * before proceeding.
+ *
+ * Even with this strategy, it is still possible for a page fault to
+ * race with hole punch. However, the race window is considerably
+ * smaller.
+ */
+ if (unlikely(inode->i_private)) {
+ struct hugetlb_falloc *hugetlb_falloc;
+
+ spin_lock(&inode->i_lock);
+ hugetlb_falloc = inode->i_private;
+ if (hugetlb_falloc && hugetlb_falloc->waitq &&
+ idx >= hugetlb_falloc->start &&
+ idx <= hugetlb_falloc->end) {
+ wait_queue_head_t *hugetlb_falloc_waitq;
+ DEFINE_WAIT(hugetlb_fault_wait);
+
+ hugetlb_falloc_waitq = hugetlb_falloc->waitq;
+ prepare_to_wait(hugetlb_falloc_waitq,
+ &hugetlb_fault_wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock(&inode->i_lock);
+ schedule();
+
+ spin_lock(&inode->i_lock);
+ finish_wait(hugetlb_falloc_waitq, &hugetlb_fault_wait);
+ }
+ spin_unlock(&inode->i_lock);
+ }
+
+ /*
* Serialize hugepage allocation and instantiation, so that we don't
* get spurious allocation failures if two CPUs race to instantiate
* the same page in the page cache.
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
mm-hugetlb-define-hugetlb_falloc-structure-for-hole-punch-race.patch
mm-hugetlb-setup-hugetlb_falloc-during-fallocate-hole-punch.patch
mm-hugetlb-page-faults-check-for-fallocate-hole-punch-in-progress-and-wait.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
