summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorBoaz Harrosh <boaz@plexistor.com>2015-04-15 16:15:11 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-04-15 16:35:20 -0700
commitdd9061846a3ba01b0fa45423aaa087e4a69187fa (patch)
tree799e6c9845a389a95173ca927caa825406175f41 /mm
parent2682582a6ea118d974c33da64923ae8c687fdd0b (diff)
downloadlinux-dd9061846a3ba01b0fa45423aaa087e4a69187fa.tar.bz2
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP
This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memory.c43
1 files changed, 39 insertions, 4 deletions
diff --git a/mm/memory.c b/mm/memory.c
index f9628e568c58..22e037e3364e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2180,6 +2180,42 @@ oom:
return VM_FAULT_OOM;
}
+/*
+ * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED
+ * mapping
+ */
+static int wp_pfn_shared(struct mm_struct *mm,
+ struct vm_area_struct *vma, unsigned long address,
+ pte_t *page_table, spinlock_t *ptl, pte_t orig_pte,
+ pmd_t *pmd)
+{
+ if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) {
+ struct vm_fault vmf = {
+ .page = NULL,
+ .pgoff = linear_page_index(vma, address),
+ .virtual_address = (void __user *)(address & PAGE_MASK),
+ .flags = FAULT_FLAG_WRITE | FAULT_FLAG_MKWRITE,
+ };
+ int ret;
+
+ pte_unmap_unlock(page_table, ptl);
+ ret = vma->vm_ops->pfn_mkwrite(vma, &vmf);
+ if (ret & VM_FAULT_ERROR)
+ return ret;
+ page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+ /*
+ * We might have raced with another page fault while we
+ * released the pte_offset_map_lock.
+ */
+ if (!pte_same(*page_table, orig_pte)) {
+ pte_unmap_unlock(page_table, ptl);
+ return 0;
+ }
+ }
+ return wp_page_reuse(mm, vma, address, page_table, ptl, orig_pte,
+ NULL, 0, 0);
+}
+
static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table,
pmd_t *pmd, spinlock_t *ptl, pte_t orig_pte,
@@ -2258,13 +2294,12 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
* VM_PFNMAP VMA.
*
* We should not cow pages in a shared writeable mapping.
- * Just mark the pages writable as we can't do any dirty
- * accounting on raw pfn maps.
+ * Just mark the pages writable and/or call ops->pfn_mkwrite.
*/
if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
(VM_WRITE|VM_SHARED))
- return wp_page_reuse(mm, vma, address, page_table, ptl,
- orig_pte, old_page, 0, 0);
+ return wp_pfn_shared(mm, vma, address, page_table, ptl,
+ orig_pte, pmd);
pte_unmap_unlock(page_table, ptl);
return wp_page_copy(mm, vma, address, page_table, pmd,