From: Oscar Salvador <osalvador@xxxxxxx>
Tony reported that the Machine check recovery was broken in v6.9-rc1, as
he was hitting a VM_BUG_ON when injecting uncorrectable memory errors to
DRAM.
After some more digging and debugging on his side, he realized that this
went back to v6.1, with the introduction of 'commit 0d206b5d2e0d
("mm/swap: add swp_offset_pfn() to fetch PFN from swap entry")'. That
commit, among other things, introduced swp_offset_pfn(), replacing
hwpoison_entry_to_pfn() in its favour.
The patch also introduced a VM_BUG_ON() check for is_pfn_swap_entry(), but
is_pfn_swap_entry() never got updated to cover hwpoison entries, which
means that we would hit the VM_BUG_ON whenever we would call
swp_offset_pfn() for such entries on environments with CONFIG_DEBUG_VM
set. Fix this by updating the check to cover hwpoison entries as well,
and update the comment while we are it.
Link: https://lkml.kernel.org/r/20240407130537.16977-1-osalvador@xxxxxxx
Fixes: 0d206b5d2e0d ("mm/swap: add swp_offset_pfn() to fetch PFN from swap entry")
Signed-off-by: Oscar Salvador <osalvador@xxxxxxx>
Reported-by: Tony Luck <tony.luck@xxxxxxxxx>
Closes: https://lore.kernel.org/all/Zg8kLSl2yAlA3o5D@agluck-desk3/
Tested-by: Tony Luck <tony.luck@xxxxxxxxx>
Reviewed-by: Peter Xu <peterx@xxxxxxxxxx>
Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
Acked-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> [6.1.x]
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
(cherry picked from commit 07a57a338adb6ec9e766d6a6790f76527f45ceb5)
Signed-off-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
---
include/linux/swapops.h | 105 ++++++++++++++++++++--------------------
1 file changed, 53 insertions(+), 52 deletions(-)
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index b07b277d6a16..1f59f9edcc24 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -409,6 +409,55 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry)
}
#endif /* CONFIG_MIGRATION */
+#ifdef CONFIG_MEMORY_FAILURE
+
+extern atomic_long_t num_poisoned_pages __read_mostly;
+
+/*
+ * Support for hardware poisoned pages
+ */
+static inline swp_entry_t make_hwpoison_entry(struct page *page)
+{
+ BUG_ON(!PageLocked(page));
+ return swp_entry(SWP_HWPOISON, page_to_pfn(page));
+}
+
+static inline int is_hwpoison_entry(swp_entry_t entry)
+{
+ return swp_type(entry) == SWP_HWPOISON;
+}
+
+static inline void num_poisoned_pages_inc(void)
+{
+ atomic_long_inc(&num_poisoned_pages);
+}
+
+static inline void num_poisoned_pages_sub(long i)
+{
+ atomic_long_sub(i, &num_poisoned_pages);
+}
+
+#else /* CONFIG_MEMORY_FAILURE */
+
+static inline swp_entry_t make_hwpoison_entry(struct page *page)
+{
+ return swp_entry(0, 0);
+}
+
+static inline int is_hwpoison_entry(swp_entry_t swp)
+{
+ return 0;
+}
+
+static inline void num_poisoned_pages_inc(void)
+{
+}
+
+static inline void num_poisoned_pages_sub(long i)
+{
+}
+#endif /* CONFIG_MEMORY_FAILURE */
+
typedef unsigned long pte_marker;
#define PTE_MARKER_UFFD_WP BIT(0)
@@ -503,8 +552,9 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
/*
* A pfn swap entry is a special type of swap entry that always has a pfn stored
- * in the swap offset. They are used to represent unaddressable device memory
- * and to restrict access to a page undergoing migration.
+ * in the swap offset. They can either be used to represent unaddressable device
+ * memory, to restrict access to a page undergoing migration or to represent a
+ * pfn which has been hwpoisoned and unmapped.
*/
static inline bool is_pfn_swap_entry(swp_entry_t entry)
{
@@ -512,7 +562,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry)
BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS);
return is_migration_entry(entry) || is_device_private_entry(entry) ||
- is_device_exclusive_entry(entry);
+ is_device_exclusive_entry(entry) || is_hwpoison_entry(entry);
}
struct page_vma_mapped_walk;
@@ -581,55 +631,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
}
#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
-#ifdef CONFIG_MEMORY_FAILURE
-
-extern atomic_long_t num_poisoned_pages __read_mostly;
-
-/*
- * Support for hardware poisoned pages
- */
-static inline swp_entry_t make_hwpoison_entry(struct page *page)
-{
- BUG_ON(!PageLocked(page));
- return swp_entry(SWP_HWPOISON, page_to_pfn(page));
-}
-
-static inline int is_hwpoison_entry(swp_entry_t entry)
-{
- return swp_type(entry) == SWP_HWPOISON;
-}
-
-static inline void num_poisoned_pages_inc(void)
-{
- atomic_long_inc(&num_poisoned_pages);
-}
-
-static inline void num_poisoned_pages_sub(long i)
-{
- atomic_long_sub(i, &num_poisoned_pages);
-}
-
-#else /* CONFIG_MEMORY_FAILURE */
-
-static inline swp_entry_t make_hwpoison_entry(struct page *page)
-{
- return swp_entry(0, 0);
-}
-
-static inline int is_hwpoison_entry(swp_entry_t swp)
-{
- return 0;
-}
-
-static inline void num_poisoned_pages_inc(void)
-{
-}
-
-static inline void num_poisoned_pages_sub(long i)
-{
-}
-#endif /* CONFIG_MEMORY_FAILURE */
-
static inline int non_swap_entry(swp_entry_t entry)
{
return swp_type(entry) >= MAX_SWAPFILES;
--
2.33.0
