The patch titled
Subject: mm: gup: add mm_lock_present()
has been removed from the -mm tree. Its filename was
mm-gup-add-mm_lock_present.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: Eric B Munson <emunson@xxxxxxxxxx>
Subject: mm: gup: add mm_lock_present()
The upcoming mlock(MLOCK_ONFAULT) implementation will need a way to
request that all present pages in a range are locked without faulting in
pages that are not present. This logic is very close to what the
__mm_populate() call handles without faulting pages so the patch pulls out
the pieces that can be shared and adds mm_lock_present() to gup.c. The
following patch will call it from do_mlock() when MLOCK_ONFAULT is
specified.
Signed-off-by: Eric B Munson <emunson@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/gup.c | 172 ++++++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 157 insertions(+), 15 deletions(-)
diff -puN mm/gup.c~mm-gup-add-mm_lock_present mm/gup.c
--- a/mm/gup.c~mm-gup-add-mm_lock_present
+++ a/mm/gup.c
@@ -818,6 +818,30 @@ long get_user_pages(struct task_struct *
}
EXPORT_SYMBOL(get_user_pages);
+/*
+ * Helper function used by both populate_vma_page_range() and pin_user_pages
+ */
+static int get_gup_flags(vm_flags_t vm_flags)
+{
+ int gup_flags = FOLL_TOUCH | FOLL_POPULATE;
+ /*
+ * We want to touch writable mappings with a write fault in order
+ * to break COW, except for shared mappings because these don't COW
+ * and we would not want to dirty them for nothing.
+ */
+ if ((vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
+ gup_flags |= FOLL_WRITE;
+
+ /*
+ * We want mlock to succeed for regions that have any permissions
+ * other than PROT_NONE.
+ */
+ if (vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
+ gup_flags |= FOLL_FORCE;
+
+ return gup_flags;
+}
+
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
@@ -850,21 +874,7 @@ long populate_vma_page_range(struct vm_a
VM_BUG_ON_VMA(end > vma->vm_end, vma);
VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
- gup_flags = FOLL_TOUCH | FOLL_POPULATE;
- /*
- * We want to touch writable mappings with a write fault in order
- * to break COW, except for shared mappings because these don't COW
- * and we would not want to dirty them for nothing.
- */
- if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
- gup_flags |= FOLL_WRITE;
-
- /*
- * We want mlock to succeed for regions that have any permissions
- * other than PROT_NONE.
- */
- if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
- gup_flags |= FOLL_FORCE;
+ gup_flags = get_gup_flags(vma->vm_flags);
/*
* We made sure addr is within a VMA, so the following will
@@ -874,6 +884,138 @@ long populate_vma_page_range(struct vm_a
NULL, NULL, nonblocking);
}
+static long pin_user_pages(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, int *nonblocking)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long nr_pages = (end - start) / PAGE_SIZE;
+ int gup_flags;
+ long i = 0;
+ unsigned int page_mask;
+
+ VM_BUG_ON(start & ~PAGE_MASK);
+ VM_BUG_ON(end & ~PAGE_MASK);
+ VM_BUG_ON_VMA(start < vma->vm_start, vma);
+ VM_BUG_ON_VMA(end > vma->vm_end, vma);
+ VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
+
+ if (!nr_pages)
+ return 0;
+
+ gup_flags = get_gup_flags(vma->vm_flags);
+
+ /*
+ * If FOLL_FORCE is set then do not force a full fault as the hinting
+ * fault information is unrelated to the reference behaviour of a task
+ * using the address space
+ */
+ if (!(gup_flags & FOLL_FORCE))
+ gup_flags |= FOLL_NUMA;
+
+ vma = NULL;
+
+ do {
+ 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, NULL);
+ if (ret)
+ return i ? : ret;
+ page_mask = 0;
+ goto next_page;
+ }
+
+ if (!vma)
+ return i ? : -EFAULT;
+ if (is_vm_hugetlb_page(vma)) {
+ i = follow_hugetlb_page(mm, vma, NULL, NULL,
+ &start, &nr_pages, i,
+ gup_flags);
+ continue;
+ }
+ }
+
+ /*
+ * If we have a pending SIGKILL, don't keep pinning pages
+ */
+ if (unlikely(fatal_signal_pending(current)))
+ return i ? i : -ERESTARTSYS;
+ cond_resched();
+ page = follow_page_mask(vma, start, foll_flags, &page_mask);
+ if (!page)
+ goto next_page;
+ if (IS_ERR(page))
+ return i ? i : PTR_ERR(page);
+next_page:
+ 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;
+}
+
+/*
+ * mm_lock_present - lock present pages within a range of address space.
+ *
+ * This is used to implement mlock2(MLOCK_LOCKONFAULT). VMAs must be already
+ * marked with the desired vm_flags, and mmap_sem must not be held.
+ */
+int mm_lock_present(unsigned long start, unsigned long len)
+{
+ struct mm_struct *mm = current->mm;
+ unsigned long end, nstart, nend;
+ struct vm_area_struct *vma = NULL;
+ int locked = 0;
+ long ret = 0;
+
+ VM_BUG_ON(start & ~PAGE_MASK);
+ VM_BUG_ON(len != PAGE_ALIGN(len));
+ end = start + len;
+
+ for (nstart = start; nstart < end; nstart = nend) {
+ /*
+ * We want to fault in pages for [nstart; end) address range.
+ * Find first corresponding VMA.
+ */
+ if (!locked) {
+ locked = 1;
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, nstart);
+ } else if (nstart >= vma->vm_end)
+ vma = vma->vm_next;
+ if (!vma || vma->vm_start >= end)
+ break;
+ /*
+ * Set [nstart; nend) to intersection of desired address
+ * range with the first VMA. Also, skip undesirable VMA types.
+ */
+ nend = min(end, vma->vm_end);
+ if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+ continue;
+ if (nstart < vma->vm_start)
+ nstart = vma->vm_start;
+
+ ret = pin_user_pages(vma, nstart, nend, &locked);
+ if (ret < 0)
+ break;
+ nend = nstart + ret * PAGE_SIZE;
+ ret = 0;
+ }
+ if (locked)
+ up_read(&mm->mmap_sem);
+ return ret; /* 0 or negative error code */
+}
+
/*
* __mm_populate - populate and/or mlock pages within a range of address space.
*
_
Patches currently in -mm which might be from emunson@xxxxxxxxxx are
mm-mlock-refactor-mlock-munlock-and-munlockall-code-checkpatch-fixes.patch
mm-mlock-add-new-mlock-munlock-and-munlockall-system-calls-fix.patch
mm-mlock-add-new-mlock-munlock-and-munlockall-system-calls-fix-2.patch
mm-gup-add-mm_lock_present-checkpatch-fixes.patch
mm-mlock-introduce-vm_lockonfault-and-add-mlock-flags-to-enable-it.patch
mm-mlock-introduce-vm_lockonfault-and-add-mlock-flags-to-enable-it-v4.patch
mm-mlock-introduce-vm_lockonfault-and-add-mlock-flags-to-enable-it-v4-checkpatch-fixes.patch
mm-mmap-add-mmap-flag-to-request-vm_lockonfault.patch
mm-mmap-add-mmap-flag-to-request-vm_lockonfault-v4.patch
mm-mmap-add-mmap-flag-to-request-vm_lockonfault-v4-fix.patch
selftests-vm-add-tests-for-lock-on-fault.patch
selftests-vm-add-tests-for-lock-on-fault-v4.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
