Subject: + mm-cleanup-__get_user_pages.patch added to -mm tree
To: kirill.shutemov@xxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Fri, 02 May 2014 13:47:19 -0700
The patch titled
Subject: mm: cleanup __get_user_pages()
has been added to the -mm tree. Its filename is
mm-cleanup-__get_user_pages.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-cleanup-__get_user_pages.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-cleanup-__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: cleanup __get_user_pages()
Get rid of two nested loops over nr_pages, extract vma flags checking to
separate function and other random cleanups.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/gup.c | 218 ++++++++++++++++++++++++++---------------------------
1 file changed, 107 insertions(+), 111 deletions(-)
diff -puN mm/gup.c~mm-cleanup-__get_user_pages mm/gup.c
--- a/mm/gup.c~mm-cleanup-__get_user_pages
+++ a/mm/gup.c
@@ -315,6 +315,44 @@ static int faultin_page(struct task_stru
return 0;
}
+static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
+{
+ vm_flags_t vm_flags = vma->vm_flags;
+
+ if (vm_flags & (VM_IO | VM_PFNMAP))
+ return -EFAULT;
+
+ if (gup_flags & FOLL_WRITE) {
+ if (!(vm_flags & VM_WRITE)) {
+ if (!(gup_flags & FOLL_FORCE))
+ return -EFAULT;
+ /*
+ * We used to let the write,force case do COW in a
+ * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
+ * set a breakpoint in a read-only mapping of an
+ * executable, without corrupting the file (yet only
+ * when that file had been opened for writing!).
+ * Anon pages in shared mappings are surprising: now
+ * just reject it.
+ */
+ if (!is_cow_mapping(vm_flags)) {
+ WARN_ON_ONCE(vm_flags & VM_MAYWRITE);
+ return -EFAULT;
+ }
+ }
+ } else if (!(vm_flags & VM_READ)) {
+ if (!(gup_flags & FOLL_FORCE))
+ return -EFAULT;
+ /*
+ * Is there actually any vma we can reach here which does not
+ * have VM_MAYREAD set?
+ */
+ if (!(vm_flags & VM_MAYREAD))
+ return -EFAULT;
+ }
+ return 0;
+}
+
/**
* __get_user_pages() - pin user pages in memory
* @tsk: task_struct of target task
@@ -369,9 +407,9 @@ long __get_user_pages(struct task_struct
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *nonblocking)
{
- long i;
- unsigned long vm_flags;
+ long i = 0;
unsigned int page_mask;
+ struct vm_area_struct *vma = NULL;
if (!nr_pages)
return 0;
@@ -386,124 +424,82 @@ long __get_user_pages(struct task_struct
if (!(gup_flags & FOLL_FORCE))
gup_flags |= FOLL_NUMA;
- i = 0;
-
do {
- struct vm_area_struct *vma;
-
- vma = find_extend_vma(mm, start);
- if (!vma && in_gate_area(mm, start)) {
- int ret;
- ret = get_gate_page(mm, start & PAGE_MASK, gup_flags,
- &vma, pages ? &pages[i] : NULL);
- if (ret)
- goto efault;
- page_mask = 0;
- goto next_page;
- }
+ struct page *page;
+ unsigned int foll_flags = gup_flags;
+ unsigned int page_increm;
+
+ /* first iteration or cross vma bound */
+ if (!vma || start >= vma->vm_end) {
+ vma = find_extend_vma(mm, start);
+ if (!vma && in_gate_area(mm, start)) {
+ int ret;
+ ret = get_gate_page(mm, start & PAGE_MASK,
+ gup_flags, &vma,
+ pages ? &pages[i] : NULL);
+ if (ret)
+ return i ? : ret;
+ page_mask = 0;
+ goto next_page;
+ }
- if (!vma)
- goto efault;
- vm_flags = vma->vm_flags;
- if (vm_flags & (VM_IO | VM_PFNMAP))
- goto efault;
-
- if (gup_flags & FOLL_WRITE) {
- if (!(vm_flags & VM_WRITE)) {
- if (!(gup_flags & FOLL_FORCE))
- goto efault;
- /*
- * We used to let the write,force case do COW
- * in a VM_MAYWRITE VM_SHARED !VM_WRITE vma, so
- * ptrace could set a breakpoint in a read-only
- * mapping of an executable, without corrupting
- * the file (yet only when that file had been
- * opened for writing!). Anon pages in shared
- * mappings are surprising: now just reject it.
- */
- if (!is_cow_mapping(vm_flags)) {
- WARN_ON_ONCE(vm_flags & VM_MAYWRITE);
- goto efault;
- }
+ if (!vma || check_vma_flags(vma, gup_flags))
+ return i ? : -EFAULT;
+ if (is_vm_hugetlb_page(vma)) {
+ i = follow_hugetlb_page(mm, vma, pages, vmas,
+ &start, &nr_pages, i,
+ gup_flags);
+ continue;
}
- } else {
- if (!(vm_flags & VM_READ)) {
- if (!(gup_flags & FOLL_FORCE))
- goto efault;
- /*
- * Is there actually any vma we can reach here
- * which does not have VM_MAYREAD set?
- */
- if (!(vm_flags & VM_MAYREAD))
- goto efault;
+ }
+retry:
+ /*
+ * If we have a pending SIGKILL, don't keep faulting pages and
+ * potentially allocating memory.
+ */
+ if (unlikely(fatal_signal_pending(current)))
+ return i ? i : -ERESTARTSYS;
+ cond_resched();
+ page = follow_page_mask(vma, start, foll_flags, &page_mask);
+ if (!page) {
+ int ret;
+ ret = faultin_page(tsk, vma, start, &foll_flags,
+ nonblocking);
+ switch (ret) {
+ case 0:
+ goto retry;
+ case -EFAULT:
+ case -ENOMEM:
+ case -EHWPOISON:
+ return i ? i : ret;
+ case -EBUSY:
+ return i;
+ case -ENOENT:
+ goto next_page;
}
+ BUG();
}
-
- if (is_vm_hugetlb_page(vma)) {
- i = follow_hugetlb_page(mm, vma, pages, vmas,
- &start, &nr_pages, i, gup_flags);
- continue;
+ if (IS_ERR(page))
+ return i ? i : PTR_ERR(page);
+ if (pages) {
+ pages[i] = page;
+ flush_anon_page(vma, page, start);
+ flush_dcache_page(page);
+ page_mask = 0;
}
-
- do {
- struct page *page;
- unsigned int foll_flags = gup_flags;
- unsigned int page_increm;
-
- /*
- * If we have a pending SIGKILL, don't keep faulting
- * pages and potentially allocating memory.
- */
- if (unlikely(fatal_signal_pending(current)))
- return i ? i : -ERESTARTSYS;
-
- cond_resched();
- while (!(page = follow_page_mask(vma, start,
- foll_flags, &page_mask))) {
- int ret;
- 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:
- BUG();
- }
- cond_resched();
- }
- if (IS_ERR(page))
- return i ? i : PTR_ERR(page);
- if (pages) {
- pages[i] = page;
-
- flush_anon_page(vma, page, start);
- flush_dcache_page(page);
- page_mask = 0;
- }
next_page:
- if (vmas) {
- vmas[i] = vma;
- page_mask = 0;
- }
- page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
- if (page_increm > nr_pages)
- page_increm = nr_pages;
- i += page_increm;
- start += page_increm * PAGE_SIZE;
- nr_pages -= page_increm;
- } while (nr_pages && start < vma->vm_end);
+ if (vmas) {
+ vmas[i] = vma;
+ page_mask = 0;
+ }
+ page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+ if (page_increm > nr_pages)
+ page_increm = nr_pages;
+ i += page_increm;
+ start += page_increm * PAGE_SIZE;
+ nr_pages -= page_increm;
} while (nr_pages);
return i;
-efault:
- return i ? : -EFAULT;
}
EXPORT_SYMBOL(__get_user_pages);
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
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-swapc-introduce-put_refcounted_compound_page-helpers-for-spliting-put_compound_page.patch
mm-swapc-split-put_compound_page-function.patch
mm-introdule-compound_head_by_tail.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
