summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorzhenwei pi <pizhenwei@bytedance.com>2022-05-12 20:23:09 -0700
committerAndrew Morton <akpm@linux-foundation.org>2022-05-13 07:20:19 -0700
commit60f272f6b09a8f14156df88cccd21447ab394452 (patch)
tree5a086c2f73a800f9d466985adf407c861a17bddd
parentcd8c1fd8cdd14158f2d8bea2d1bfe8015dccfa3a (diff)
mm/memory-failure.c: move clear_hwpoisoned_pages
Patch series "memory-failure: fix hwpoison_filter", v2. As well known, the memory failure mechanism handles memory corrupted event, and try to send SIGBUS to the user process which uses this corrupted page. For the virtualization case, QEMU catches SIGBUS and tries to inject MCE into the guest, and the guest handles memory failure again. Thus the guest gets the minimal effect from hardware memory corruption. The further step I'm working on: 1, try to modify code to decrease poisoned pages in a single place (mm/memofy-failure.c: simplify num_poisoned_pages_dec in this series). 2, try to use page_handle_poison() to handle SetPageHWPoison() and num_poisoned_pages_inc() together. It would be best to call num_poisoned_pages_inc() in a single place too. 3, introduce memory failure notifier list in memory-failure.c: notify the corrupted PFN to someone who registers this list. If I can complete [1] and [2] part, [3] will be quite easy(just call notifier list after increasing poisoned page). 4, introduce memory recover VQ for memory balloon device, and registers memory failure notifier list. During the guest kernel handles memory failure, balloon device gets notified by memory failure notifier list, and tells the host to recover the corrupted PFN(GPA) by the new VQ. 5, host side remaps the corrupted page(HVA), and tells the guest side to unpoison the PFN(GPA). Then the guest fixes the corrupted page(GPA) dynamically. This patch (of 5): clear_hwpoisoned_pages() clears HWPoison flag and decreases the number of poisoned pages, this actually works as part of memory failure. Move this function from sparse.c to memory-failure.c, finally there is no CONFIG_MEMORY_FAILURE in sparse.c. Link: https://lkml.kernel.org/r/20220509105641.491313-1-pizhenwei@bytedance.com Link: https://lkml.kernel.org/r/20220509105641.491313-2-pizhenwei@bytedance.com Signed-off-by: zhenwei pi <pizhenwei@bytedance.com> Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r--mm/internal.h11
-rw-r--r--mm/memory-failure.c21
-rw-r--r--mm/sparse.c27
3 files changed, 32 insertions, 27 deletions
diff --git a/mm/internal.h b/mm/internal.h
index a770029beb08..6d188161b20e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -711,6 +711,9 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
}
#endif
+/*
+ * mm/memory-failure.c
+ */
extern int hwpoison_filter(struct page *p);
extern u32 hwpoison_filter_dev_major;
@@ -720,6 +723,14 @@ extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
+#ifdef CONFIG_MEMORY_FAILURE
+void clear_hwpoisoned_pages(struct page *memmap, int nr_pages);
+#else
+static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+}
+#endif
+
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 1d117190c350..e7a13e90bd05 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -2392,3 +2392,24 @@ retry:
return ret;
}
+
+void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+ int i;
+
+ /*
+ * A further optimization is to have per section refcounted
+ * num_poisoned_pages. But that would need more space per memmap, so
+ * for now just do a quick global check to speed up this routine in the
+ * absence of bad pages.
+ */
+ if (atomic_long_read(&num_poisoned_pages) == 0)
+ return;
+
+ for (i = 0; i < nr_pages; i++) {
+ if (PageHWPoison(&memmap[i])) {
+ num_poisoned_pages_dec();
+ ClearPageHWPoison(&memmap[i]);
+ }
+ }
+}
diff --git a/mm/sparse.c b/mm/sparse.c
index d2d76d158b39..cb3bfae64036 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -922,33 +922,6 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
return 0;
}
-#ifdef CONFIG_MEMORY_FAILURE
-static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
- int i;
-
- /*
- * A further optimization is to have per section refcounted
- * num_poisoned_pages. But that would need more space per memmap, so
- * for now just do a quick global check to speed up this routine in the
- * absence of bad pages.
- */
- if (atomic_long_read(&num_poisoned_pages) == 0)
- return;
-
- for (i = 0; i < nr_pages; i++) {
- if (PageHWPoison(&memmap[i])) {
- num_poisoned_pages_dec();
- ClearPageHWPoison(&memmap[i]);
- }
- }
-}
-#else
-static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
-}
-#endif
-
void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
unsigned long nr_pages, unsigned long map_offset,
struct vmem_altmap *altmap)