mm: make __get_user_pages return -EHWPOISON for HWPOISON page optionally

Make __get_user_pages return -EHWPOISON for HWPOISON page only if
FOLL_HWPOISON is specified.  With this patch, the interested callers
can distinguish HWPOISON pages from general FAULT pages, while other
callers will still get -EFAULT for all these pages, so the user space
interface need not to be changed.

This feature is needed by KVM, where UCR MCE should be relayed to
guest for HWPOISON page, while instruction emulation and MMIO will be
tried for general FAULT page.

The idea comes from Andrew Morton.
Signed-off-by: Huang Ying <ying.huang@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/alpha/include/asm/errno.h

@@ -122,4 +122,6 @@
 
 #define	ERFKILL		138	/* Operation not possible due to RF-kill */
 
+#define EHWPOISON	139	/* Memory page has hardware error */
+
 #endif

arch/mips/include/asm/errno.h

@@ -121,6 +121,8 @@
 
 #define	ERFKILL		167	/* Operation not possible due to RF-kill */
 
+#define EHWPOISON	168	/* Memory page has hardware error */
+
 #define EDQUOT		1133	/* Quota exceeded */
 
 #ifdef __KERNEL__

arch/parisc/include/asm/errno.h

@@ -122,4 +122,6 @@
 
 #define	ERFKILL		256	/* Operation not possible due to RF-kill */
 
+#define EHWPOISON	257	/* Memory page has hardware error */
+
 #endif

arch/sparc/include/asm/errno.h

@@ -112,4 +112,6 @@
 
 #define	ERFKILL		134	/* Operation not possible due to RF-kill */
 
+#define EHWPOISON	135	/* Memory page has hardware error */
+
 #endif

include/asm-generic/errno.h

@@ -108,4 +108,6 @@
 
 #define ERFKILL		132	/* Operation not possible due to RF-kill */
 
+#define EHWPOISON	133	/* Memory page has hardware error */
+
 #endif

include/linux/mm.h

@@ -1532,6 +1532,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_FORCE	0x10	/* get_user_pages read/write w/o permission */
 #define FOLL_MLOCK	0x40	/* mark page as mlocked */
 #define FOLL_SPLIT	0x80	/* don't return transhuge pages, split them */
+#define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);

mm/memory.c

@@ -1576,9 +1576,16 @@ 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;
-					if (ret &
-					    (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE|
-					     VM_FAULT_SIGBUS))
+					if (ret & (VM_FAULT_HWPOISON |
+						   VM_FAULT_HWPOISON_LARGE)) {
+						if (i)
+							return i;
+						else if (gup_flags & FOLL_HWPOISON)
+							return -EHWPOISON;
+						else
+							return -EFAULT;
+					}
+					if (ret & VM_FAULT_SIGBUS)
 						return i ? i : -EFAULT;
 					BUG();
 				}