mm: factor helpers for memory_failure_dev_pagemap

memory_failure_dev_pagemap code is a bit complex before introduce RMAP
feature for fsdax.  So it is needed to factor some helper functions to
simplify these code.

[akpm@linux-foundation.org: fix CONFIG_HUGETLB_PAGE=n build]
[zhengbin13@huawei.com: fix redefinition of mf_generic_kill_procs]
Link: https://lkml.kernel.org/r/20220628112143.1170473-1-zhengbin13@huawei.com
Link: https://lkml.kernel.org/r/20220603053738.1218681-3-ruansy.fnst@fujitsu.com
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dan Williams <dan.j.wiliams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Ritesh Harjani <riteshh@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b7ca5db..f8a8a5d 100644 (file)
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1499,6 +1499,95 @@ static int try_to_split_thp_page(struct page *page, const char *msg)
        return 0;
 }
 
+static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn,
+               struct address_space *mapping, pgoff_t index, int flags)
+{
+       struct to_kill *tk;
+       unsigned long size = 0;
+
+       list_for_each_entry(tk, to_kill, nd)
+               if (tk->size_shift)
+                       size = max(size, 1UL << tk->size_shift);
+
+       if (size) {
+               /*
+                * Unmap the largest mapping to avoid breaking up device-dax
+                * mappings which are constant size. The actual size of the
+                * mapping being torn down is communicated in siginfo, see
+                * kill_proc()
+                */
+               loff_t start = (index << PAGE_SHIFT) & ~(size - 1);
+
+               unmap_mapping_range(mapping, start, size, 0);
+       }
+
+       kill_procs(to_kill, flags & MF_MUST_KILL, false, pfn, flags);
+}
+
+static int mf_generic_kill_procs(unsigned long long pfn, int flags,
+               struct dev_pagemap *pgmap)
+{
+       struct page *page = pfn_to_page(pfn);
+       LIST_HEAD(to_kill);
+       dax_entry_t cookie;
+       int rc = 0;
+
+       /*
+        * Pages instantiated by device-dax (not filesystem-dax)
+        * may be compound pages.
+        */
+       page = compound_head(page);
+
+       /*
+        * Prevent the inode from being freed while we are interrogating
+        * the address_space, typically this would be handled by
+        * lock_page(), but dax pages do not use the page lock. This
+        * also prevents changes to the mapping of this pfn until
+        * poison signaling is complete.
+        */
+       cookie = dax_lock_page(page);
+       if (!cookie)
+               return -EBUSY;
+
+       if (hwpoison_filter(page)) {
+               rc = -EOPNOTSUPP;
+               goto unlock;
+       }
+
+       switch (pgmap->type) {
+       case MEMORY_DEVICE_PRIVATE:
+       case MEMORY_DEVICE_COHERENT:
+               /*
+                * TODO: Handle device pages which may need coordination
+                * with device-side memory.
+                */
+               rc = -ENXIO;
+               goto unlock;
+       default:
+               break;
+       }
+
+       /*
+        * Use this flag as an indication that the dax page has been
+        * remapped UC to prevent speculative consumption of poison.
+        */
+       SetPageHWPoison(page);
+
+       /*
+        * Unlike System-RAM there is no possibility to swap in a
+        * different physical page at a given virtual address, so all
+        * userspace consumption of ZONE_DEVICE memory necessitates
+        * SIGBUS (i.e. MF_MUST_KILL)
+        */
+       flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
+       collect_procs(page, &to_kill, true);
+
+       unmap_and_kill(&to_kill, pfn, page->mapping, page->index, flags);
+unlock:
+       dax_unlock_page(page, cookie);
+       return rc;
+}
+
 /*
  * Called from hugetlb code with hugetlb_lock held.
  *
@@ -1634,23 +1723,20 @@ out:
        unlock_page(head);
        return res;
 }
+
 #else
 static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb)
 {
        return 0;
 }
-#endif
+
+#endif /* CONFIG_HUGETLB_PAGE */
 
 static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
                struct dev_pagemap *pgmap)
 {
        struct page *page = pfn_to_page(pfn);
-       unsigned long size = 0;
-       struct to_kill *tk;
-       LIST_HEAD(tokill);
-       int rc = -EBUSY;
-       loff_t start;
-       dax_entry_t cookie;
+       int rc = -ENXIO;
 
        if (flags & MF_COUNT_INCREASED)
                /*
@@ -1659,77 +1745,10 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
                put_page(page);
 
        /* device metadata space is not recoverable */
-       if (!pgmap_pfn_valid(pgmap, pfn)) {
-               rc = -ENXIO;
+       if (!pgmap_pfn_valid(pgmap, pfn))
                goto out;
-       }
-
-       /*
-        * Pages instantiated by device-dax (not filesystem-dax)
-        * may be compound pages.
-        */
-       page = compound_head(page);
-
-       /*
-        * Prevent the inode from being freed while we are interrogating
-        * the address_space, typically this would be handled by
-        * lock_page(), but dax pages do not use the page lock. This
-        * also prevents changes to the mapping of this pfn until
-        * poison signaling is complete.
-        */
-       cookie = dax_lock_page(page);
-       if (!cookie)
-               goto out;
-
-       if (hwpoison_filter(page)) {
-               rc = -EOPNOTSUPP;
-               goto unlock;
-       }
-
-       switch (pgmap->type) {
-       case MEMORY_DEVICE_PRIVATE:
-       case MEMORY_DEVICE_COHERENT:
-               /*
-                * TODO: Handle device pages which may need coordination
-                * with device-side memory.
-                */
-               goto unlock;
-       default:
-               break;
-       }
 
-       /*
-        * Use this flag as an indication that the dax page has been
-        * remapped UC to prevent speculative consumption of poison.
-        */
-       SetPageHWPoison(page);
-
-       /*
-        * Unlike System-RAM there is no possibility to swap in a
-        * different physical page at a given virtual address, so all
-        * userspace consumption of ZONE_DEVICE memory necessitates
-        * SIGBUS (i.e. MF_MUST_KILL)
-        */
-       flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
-       collect_procs(page, &tokill, true);
-
-       list_for_each_entry(tk, &tokill, nd)
-               if (tk->size_shift)
-                       size = max(size, 1UL << tk->size_shift);
-       if (size) {
-               /*
-                * Unmap the largest mapping to avoid breaking up
-                * device-dax mappings which are constant size. The
-                * actual size of the mapping being torn down is
-                * communicated in siginfo, see kill_proc()
-                */
-               start = (page->index << PAGE_SHIFT) & ~(size - 1);
-               unmap_mapping_range(page->mapping, start, size, 0);
-       }
-       kill_procs(&tokill, true, false, pfn, flags);
-       rc = 0;
-unlock:
-       dax_unlock_page(page, cookie);
+       rc = mf_generic_kill_procs(pfn, flags, pgmap);
 out:
        /* drop pgmap ref acquired in caller */
        put_dev_pagemap(pgmap);