The patch titled
Subject: userfaultfd: hugetlbfs: gup: support VM_FAULT_RETRY
has been added to the -mm tree. Its filename is
userfaultfd-hugetlbfs-gup-support-vm_fault_retry.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/userfaultfd-hugetlbfs-gup-support-vm_fault_retry.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/userfaultfd-hugetlbfs-gup-support-vm_fault_retry.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: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Subject: userfaultfd: hugetlbfs: gup: support VM_FAULT_RETRY
Add support for VM_FAULT_RETRY to follow_hugetlb_page() so that
get_user_pages_unlocked/locked and "nonblocking/FOLL_NOWAIT" features will
work on hugetlbfs. This is required for fully functional userfaultfd
non-present support on hugetlbfs.
Link: http://lkml.kernel.org/r/20161216144821.5183-25-aarcange@xxxxxxxxxx
Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Reviewed-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: "Dr. David Alan Gilbert" <dgilbert@xxxxxxxxxx>
Cc: Hillf Danton <hillf.zj@xxxxxxxxxxxxxxx>
Cc: Michael Rapoport <RAPOPORT@xxxxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 5 ++-
mm/gup.c | 2 -
mm/hugetlb.c | 48 +++++++++++++++++++++++++++++++-------
3 files changed, 44 insertions(+), 11 deletions(-)
diff -puN include/linux/hugetlb.h~userfaultfd-hugetlbfs-gup-support-vm_fault_retry include/linux/hugetlb.h
--- a/include/linux/hugetlb.h~userfaultfd-hugetlbfs-gup-support-vm_fault_retry
+++ a/include/linux/hugetlb.h
@@ -65,7 +65,8 @@ int hugetlb_mempolicy_sysctl_handler(str
int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
struct page **, struct vm_area_struct **,
- unsigned long *, unsigned long *, long, unsigned int);
+ unsigned long *, unsigned long *, long, unsigned int,
+ int *);
void unmap_hugepage_range(struct vm_area_struct *,
unsigned long, unsigned long, struct page *);
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
@@ -136,7 +137,7 @@ static inline unsigned long hugetlb_tota
return 0;
}
-#define follow_hugetlb_page(m,v,p,vs,a,b,i,w) ({ BUG(); 0; })
+#define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; })
#define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL)
#define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; })
static inline void hugetlb_report_meminfo(struct seq_file *m)
diff -puN mm/gup.c~userfaultfd-hugetlbfs-gup-support-vm_fault_retry mm/gup.c
--- a/mm/gup.c~userfaultfd-hugetlbfs-gup-support-vm_fault_retry
+++ a/mm/gup.c
@@ -572,7 +572,7 @@ static long __get_user_pages(struct task
if (is_vm_hugetlb_page(vma)) {
i = follow_hugetlb_page(mm, vma, pages, vmas,
&start, &nr_pages, i,
- gup_flags);
+ gup_flags, nonblocking);
continue;
}
}
diff -puN mm/hugetlb.c~userfaultfd-hugetlbfs-gup-support-vm_fault_retry mm/hugetlb.c
--- a/mm/hugetlb.c~userfaultfd-hugetlbfs-gup-support-vm_fault_retry
+++ a/mm/hugetlb.c
@@ -4046,7 +4046,7 @@ out_release_unlock:
long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
struct page **pages, struct vm_area_struct **vmas,
unsigned long *position, unsigned long *nr_pages,
- long i, unsigned int flags)
+ long i, unsigned int flags, int *nonblocking)
{
unsigned long pfn_offset;
unsigned long vaddr = *position;
@@ -4109,16 +4109,43 @@ long follow_hugetlb_page(struct mm_struc
((flags & FOLL_WRITE) &&
!huge_pte_write(huge_ptep_get(pte)))) {
int ret;
+ unsigned int fault_flags = 0;
if (pte)
spin_unlock(ptl);
- ret = hugetlb_fault(mm, vma, vaddr,
- (flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0);
- if (!(ret & VM_FAULT_ERROR))
- continue;
-
- remainder = 0;
- break;
+ if (flags & FOLL_WRITE)
+ fault_flags |= FAULT_FLAG_WRITE;
+ if (nonblocking)
+ fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+ if (flags & FOLL_NOWAIT)
+ fault_flags |= FAULT_FLAG_ALLOW_RETRY |
+ FAULT_FLAG_RETRY_NOWAIT;
+ if (flags & FOLL_TRIED) {
+ VM_WARN_ON_ONCE(fault_flags &
+ FAULT_FLAG_ALLOW_RETRY);
+ fault_flags |= FAULT_FLAG_TRIED;
+ }
+ ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
+ if (ret & VM_FAULT_ERROR) {
+ remainder = 0;
+ break;
+ }
+ if (ret & VM_FAULT_RETRY) {
+ if (nonblocking)
+ *nonblocking = 0;
+ *nr_pages = 0;
+ /*
+ * VM_FAULT_RETRY must not return an
+ * error, it will return zero
+ * instead.
+ *
+ * No need to update "position" as the
+ * caller will not check it after
+ * *nr_pages is set to 0.
+ */
+ return i;
+ }
+ continue;
}
pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
@@ -4147,6 +4174,11 @@ same_page:
spin_unlock(ptl);
}
*nr_pages = remainder;
+ /*
+ * setting position is actually required only if remainder is
+ * not zero but it's faster not to add a "if (remainder)"
+ * branch.
+ */
*position = vaddr;
return i ? i : -EFAULT;
_
Patches currently in -mm which might be from aarcange@xxxxxxxxxx are
userfaultfd-document-_ior-_iow.patch
userfaultfd-correct-comment-about-uffd_feature_pagefault_flag_wp.patch
userfaultfd-convert-bug-to-warn_on_once.patch
userfaultfd-use-vma_is_anonymous.patch
userfaultfd-non-cooperative-report-all-available-features-to-userland.patch
userfaultfd-non-cooperative-add-fork-event-build-warning-fix.patch
userfaultfd-non-cooperative-optimize-mremap_userfaultfd_complete.patch
userfaultfd-non-cooperative-avoid-madv_dontneed-race-condition.patch
userfaultfd-non-cooperative-wake-userfaults-after-uffdio_unregister.patch
userfaultfd-hugetlbfs-gup-support-vm_fault_retry.patch
userfaultfd-hugetlbfs-uffd_feature_missing_hugetlbfs.patch
userfaultfd-shmem-add-tlbflushh-header-for-microblaze.patch
userfaultfd-shmem-lock-the-page-before-adding-it-to-pagecache.patch
userfaultfd-shmem-avoid-leaking-blocks-and-used-blocks-in-uffdio_copy.patch
userfaultfd-hugetlbfs-uffd_feature_missing_shmem.patch
userfaultfd-selftest-test-uffdio_zeropage-on-all-memory-types.patch
mm-mprotect-use-pmd_trans_unstable-instead-of-taking-the-pmd_lock.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
