Merge branch 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/mce changes from Ingo Molnar:
 "This tree improves the AMD thresholding bank code and includes a
  memory fault signal handling fixlet."

* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Fix siginfo_t->si_addr value for non-recoverable memory faults
  x86, MCE, AMD: Update copyrights and boilerplate
  x86, MCE, AMD: Give proper names to the thresholding banks
  x86, MCE, AMD: Make error_count read only
  x86, MCE, AMD: Cleanup reading of error_count
  x86, MCE, AMD: Print decimal thresholding values
  x86, MCE, AMD: Move shared bank to node descriptor
  x86, MCE, AMD: Remove local_allocate_... wrapper
  x86, MCE, AMD: Remove shared banks sysfs linking
  x86, amd_nb: Export model 0x10 and later PCI id

arch/x86/include/asm/amd_nb.h

@@ -26,10 +26,31 @@ struct amd_l3_cache {
 	u8	 subcaches[4];
 };
 
+struct threshold_block {
+	unsigned int		block;
+	unsigned int		bank;
+	unsigned int		cpu;
+	u32			address;
+	u16			interrupt_enable;
+	bool			interrupt_capable;
+	u16			threshold_limit;
+	struct kobject		kobj;
+	struct list_head	miscj;
+};
+
+struct threshold_bank {
+	struct kobject		*kobj;
+	struct threshold_block	*blocks;
+
+	/* initialized to the number of CPUs on the node sharing this bank */
+	atomic_t		cpus;
+};
+
 struct amd_northbridge {
 	struct pci_dev *misc;
 	struct pci_dev *link;
 	struct amd_l3_cache l3_cache;
+	struct threshold_bank *bank4;
 };
 
 struct amd_northbridge_info {

arch/x86/kernel/amd_nb.c

@@ -19,6 +19,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
 	{}
 };
 EXPORT_SYMBOL(amd_nb_misc_ids);

arch/x86/kernel/cpu/mcheck/mce.c

@@ -1190,6 +1190,7 @@ void mce_notify_process(void)
 {
 	unsigned long pfn;
 	struct mce_info *mi = mce_find_info();
+	int flags = MF_ACTION_REQUIRED;
 
 	if (!mi)
 		mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL);
@@ -1204,8 +1205,9 @@ void mce_notify_process(void)
 	 * doomed. We still need to mark the page as poisoned and alert any
 	 * other users of the page.
 	 */
-	if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
-			   mi->restartable == 0) {
+	if (!mi->restartable)
+		flags |= MF_MUST_KILL;
+	if (memory_failure(pfn, MCE_VECTOR, flags) < 0) {
 		pr_err("Memory error not recovered");
 		force_sig(SIGBUS, current);
 	}

drivers/hwmon/k10temp.c

@@ -33,9 +33,6 @@ static bool force;
 module_param(force, bool, 0444);
 MODULE_PARM_DESC(force, "force loading on processors with erratum 319");
 
-/* PCI-IDs for Northbridge devices not used anywhere else */
-#define PCI_DEVICE_ID_AMD_15H_M10H_NB_F3	0x1403
-
 /* CPUID function 0x80000001, ebx */
 #define CPUID_PKGTYPE_MASK	0xf0000000
 #define CPUID_PKGTYPE_F		0x00000000
@@ -213,7 +210,7 @@ static DEFINE_PCI_DEVICE_TABLE(k10temp_id_table) = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
-	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_NB_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, k10temp_id_table);

include/linux/mm.h

@@ -1591,6 +1591,7 @@ void vmemmap_populate_print_last(void);
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,
 	MF_ACTION_REQUIRED = 1 << 1,
+	MF_MUST_KILL = 1 << 2,
 };
 extern int memory_failure(unsigned long pfn, int trapno, int flags);
 extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);

include/linux/pci_ids.h

@@ -517,6 +517,7 @@
 #define PCI_DEVICE_ID_AMD_11H_NB_DRAM	0x1302
 #define PCI_DEVICE_ID_AMD_11H_NB_MISC	0x1303
 #define PCI_DEVICE_ID_AMD_11H_NB_LINK	0x1304
+#define PCI_DEVICE_ID_AMD_15H_M10H_F3	0x1403
 #define PCI_DEVICE_ID_AMD_15H_NB_F0	0x1600
 #define PCI_DEVICE_ID_AMD_15H_NB_F1	0x1601
 #define PCI_DEVICE_ID_AMD_15H_NB_F2	0x1602

mm/memory-failure.c

@@ -345,14 +345,14 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
  * Also when FAIL is set do a force kill because something went
  * wrong earlier.
  */
-static void kill_procs(struct list_head *to_kill, int doit, int trapno,
+static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 			  int fail, struct page *page, unsigned long pfn,
 			  int flags)
 {
 	struct to_kill *tk, *next;
 
 	list_for_each_entry_safe (tk, next, to_kill, nd) {
-		if (doit) {
+		if (forcekill) {
 			/*
 			 * In case something went wrong with munmapping
 			 * make sure the process doesn't catch the
@@ -858,7 +858,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	int ret;
-	int kill = 1;
+	int kill = 1, forcekill;
 	struct page *hpage = compound_head(p);
 	struct page *ppage;
 
@@ -888,7 +888,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * be called inside page lock (it's recommended but not enforced).
 	 */
 	mapping = page_mapping(hpage);
-	if (!PageDirty(hpage) && mapping &&
+	if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
 	    mapping_cap_writeback_dirty(mapping)) {
 		if (page_mkclean(hpage)) {
 			SetPageDirty(hpage);
@@ -965,12 +965,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * Now that the dirty bit has been propagated to the
 	 * struct page and all unmaps done we can decide if
 	 * killing is needed or not.  Only kill when the page
-	 * was dirty, otherwise the tokill list is merely
+	 * was dirty or the process is not restartable,
+	 * otherwise the tokill list is merely
 	 * freed.  When there was a problem unmapping earlier
 	 * use a more force-full uncatchable kill to prevent
 	 * any accesses to the poisoned memory.
 	 */
-	kill_procs(&tokill, !!PageDirty(ppage), trapno,
+	forcekill = PageDirty(ppage) || (flags & MF_MUST_KILL);
+	kill_procs(&tokill, forcekill, trapno,
 		      ret != SWAP_SUCCESS, p, pfn, flags);
 
 	return ret;