HWPOISON: Add basic support for poisoned pages in fault handler v3

- Add a new VM_FAULT_HWPOISON error code to handle_mm_fault. Right now
architectures have to explicitely enable poison page support, so
this is forward compatible to all architectures. They only need
to add it when they enable poison page support.
- Add poison page handling in swap in fault code

v2: Add missing delayacct_clear_flag (Hidehiro Kawai)
v3: Really use delayacct_clear_flag (Hidehiro Kawai)
Signed-off-by: Andi Kleen <ak@linux.intel.com>

include/linux/mm.h

@@ -685,11 +685,12 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_SIGBUS	0x0002
 #define VM_FAULT_MAJOR	0x0004
 #define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */
+#define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned page */
 
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
 
-#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS)
+#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)
 
 /*
  * Can be called by the pagefault handler when it gets a VM_FAULT_OOM.

mm/memory.c

@@ -1319,7 +1319,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				if (ret & VM_FAULT_ERROR) {
 					if (ret & VM_FAULT_OOM)
 						return i ? i : -ENOMEM;
-					else if (ret & VM_FAULT_SIGBUS)
+					if (ret &
+					    (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
 						return i ? i : -EFAULT;
 					BUG();
 				}
@@ -2511,8 +2512,15 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out;
 
 	entry = pte_to_swp_entry(orig_pte);
+	if (unlikely(non_swap_entry(entry))) {
 		if (is_migration_entry(entry)) {
 			migration_entry_wait(mm, pmd, address);
+		} else if (is_hwpoison_entry(entry)) {
+			ret = VM_FAULT_HWPOISON;
+		} else {
+			print_bad_pte(vma, address, orig_pte, NULL);
+			ret = VM_FAULT_OOM;
+		}
 		goto out;
 	}
 	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
@@ -2536,6 +2544,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* Had to read the page from swap area: Major fault */
 		ret = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
+	} else if (PageHWPoison(page)) {
+		ret = VM_FAULT_HWPOISON;
+		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+		goto out;
 	}
 
 	lock_page(page);