Subject: + mm-extract-code-to-fault-in-a-page-from-__get_user_pages.patch added to -mm tree
To: kirill.shutemov@xxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Fri, 18 Apr 2014 15:16:01 -0700
The patch titled
Subject: mm: extract code to fault in a page from __get_user_pages()
has been added to the -mm tree. Its filename is
mm-extract-code-to-fault-in-a-page-from-__get_user_pages.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-extract-code-to-fault-in-a-page-from-__get_user_pages.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-extract-code-to-fault-in-a-page-from-__get_user_pages.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: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Subject: mm: extract code to fault in a page from __get_user_pages()
Nesting level in __get_user_pages() is just insane. Let's try to fix it
a bit.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/gup.c | 130 ++++++++++++++++++++++++++++-------------------------
1 file changed, 69 insertions(+), 61 deletions(-)
diff -puN mm/gup.c~mm-extract-code-to-fault-in-a-page-from-__get_user_pages mm/gup.c
--- a/mm/gup.c~mm-extract-code-to-fault-in-a-page-from-__get_user_pages
+++ a/mm/gup.c
@@ -261,6 +261,61 @@ out:
return 0;
}
+static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
+ unsigned long address, unsigned int *flags, int *nonblocking)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned int fault_flags = 0;
+ int ret;
+
+ /* For mlock, just skip the stack guard page. */
+ if ((*flags & FOLL_MLOCK) && stack_guard_page(vma, address))
+ return -ENOENT;
+ 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;
+
+ ret = handle_mm_fault(mm, vma, address, fault_flags);
+ if (ret & VM_FAULT_ERROR) {
+ if (ret & VM_FAULT_OOM)
+ return -ENOMEM;
+ if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
+ return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
+ if (ret & VM_FAULT_SIGBUS)
+ return -EFAULT;
+ BUG();
+ }
+
+ if (tsk) {
+ if (ret & VM_FAULT_MAJOR)
+ tsk->maj_flt++;
+ else
+ tsk->min_flt++;
+ }
+
+ if (ret & VM_FAULT_RETRY) {
+ if (nonblocking)
+ *nonblocking = 0;
+ return -EBUSY;
+ }
+
+ /*
+ * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when
+ * necessary, even if maybe_mkwrite decided not to set pte_write. We
+ * can thus safely do subsequent page lookups as if they were reads.
+ * But only do so when looping for pte_write is futile: in some cases
+ * userspace may also be wanting to write to the gotten user page,
+ * which a read fault here might prevent (a readonly page might get
+ * reCOWed by userspace write).
+ */
+ if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
+ *flags &= ~FOLL_WRITE;
+ return 0;
+}
+
/**
* __get_user_pages() - pin user pages in memory
* @tsk: task_struct of target task
@@ -384,69 +439,22 @@ long __get_user_pages(struct task_struct
while (!(page = follow_page_mask(vma, start,
foll_flags, &page_mask))) {
int ret;
- unsigned int fault_flags = 0;
-
- /* For mlock, just skip the stack guard page. */
- if (foll_flags & FOLL_MLOCK) {
- if (stack_guard_page(vma, start))
- goto next_page;
- }
- if (foll_flags & FOLL_WRITE)
- fault_flags |= FAULT_FLAG_WRITE;
- if (nonblocking)
- fault_flags |= FAULT_FLAG_ALLOW_RETRY;
- if (foll_flags & FOLL_NOWAIT)
- fault_flags |= (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT);
-
- ret = handle_mm_fault(mm, vma, start,
- fault_flags);
-
- if (ret & VM_FAULT_ERROR) {
- if (ret & VM_FAULT_OOM)
- return i ? i : -ENOMEM;
- if (ret & (VM_FAULT_HWPOISON |
- VM_FAULT_HWPOISON_LARGE)) {
- if (i)
- return i;
- else if (gup_flags & FOLL_HWPOISON)
- return -EHWPOISON;
- else
- return -EFAULT;
- }
- if (ret & VM_FAULT_SIGBUS)
- return i ? i : -EFAULT;
- BUG();
- }
-
- if (tsk) {
- if (ret & VM_FAULT_MAJOR)
- tsk->maj_flt++;
- else
- tsk->min_flt++;
- }
-
- if (ret & VM_FAULT_RETRY) {
- if (nonblocking)
- *nonblocking = 0;
+ ret = faultin_page(tsk, vma, start, &foll_flags,
+ nonblocking);
+ switch (ret) {
+ case 0:
+ break;
+ case -EFAULT:
+ case -ENOMEM:
+ case -EHWPOISON:
+ return i ? i : ret;
+ case -EBUSY:
return i;
+ case -ENOENT:
+ goto next_page;
+ default:
+ BUILD_BUG();
}
-
- /*
- * The VM_FAULT_WRITE bit tells us that
- * do_wp_page has broken COW when necessary,
- * even if maybe_mkwrite decided not to set
- * pte_write. We can thus safely do subsequent
- * page lookups as if they were reads. But only
- * do so when looping for pte_write is futile:
- * in some cases userspace may also be wanting
- * to write to the gotten user page, which a
- * read fault here might prevent (a readonly
- * page might get reCOWed by userspace write).
- */
- if ((ret & VM_FAULT_WRITE) &&
- !(vma->vm_flags & VM_WRITE))
- foll_flags &= ~FOLL_WRITE;
-
cond_resched();
}
if (IS_ERR(page))
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
thp-close-race-between-split-and-zap-huge-pages.patch
pagewalk-update-page-table-walker-core.patch
pagewalk-add-walk_page_vma.patch
smaps-redefine-callback-functions-for-page-table-walker.patch
clear_refs-redefine-callback-functions-for-page-table-walker.patch
pagemap-redefine-callback-functions-for-page-table-walker.patch
numa_maps-redefine-callback-functions-for-page-table-walker.patch
memcg-redefine-callback-functions-for-page-table-walker.patch
arch-powerpc-mm-subpage-protc-use-walk_page_vma-instead-of-walk_page_range.patch
pagewalk-remove-argument-hmask-from-hugetlb_entry.patch
mempolicy-apply-page-table-walker-on-queue_pages_range.patch
mm-introduce-do_shared_fault-and-drop-do_fault-fix-fix.patch
thp-consolidate-assert-checks-in-__split_huge_page.patch
mm-huge_memoryc-complete-conversion-to-pr_foo.patch
mm-pass-vm_bug_on-reason-to-dump_page.patch
mm-pass-vm_bug_on-reason-to-dump_page-fix.patch
hugetlb-prep_compound_gigantic_page-drop-__init-marker.patch
hugetlb-add-hstate_is_gigantic.patch
hugetlb-update_and_free_page-dont-clear-pg_reserved-bit.patch
hugetlb-move-helpers-up-in-the-file.patch
hugetlb-add-support-for-gigantic-page-allocation-at-runtime.patch
mm-move-get_user_pages-related-code-to-separate-file.patch
mm-extract-in_gate_area-case-from-__get_user_pages.patch
mm-cleanup-follow_page_mask.patch
mm-extract-code-to-fault-in-a-page-from-__get_user_pages.patch
mm-cleanup-__get_user_pages.patch
do_shared_fault-check-that-mmap_sem-is-held.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
