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

Pull x86 fixes from Peter Anvin:
 "Quite a varied little collection of fixes.  Most of them are
  relatively small or isolated; the biggest one is Mel Gorman's fixes
  for TLB range flushing.

  A couple of AMD-related fixes (including not crashing when given an
  invalid microcode image) and fix a crash when compiled with gcov"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, microcode, AMD: Unify valid container checks
  x86, hweight: Fix BUG when booting with CONFIG_GCOV_PROFILE_ALL=y
  x86/efi: Allow mapping BGRT on x86-32
  x86: Fix the initialization of physnode_map
  x86, cpu hotplug: Fix stack frame warning in check_irq_vectors_for_cpu_disable()
  x86/intel/mid: Fix X86_INTEL_MID dependencies
  arch/x86/mm/srat: Skip NUMA_NO_NODE while parsing SLIT
  mm, x86: Revisit tlb_flushall_shift tuning for page flushes except on IvyBridge
  x86: mm: change tlb_flushall_shift for IvyBridge
  x86/mm: Eliminate redundant page table walk during TLB range flushing
  x86/mm: Clean up inconsistencies when flushing TLB ranges
  mm, x86: Account for TLB flushes only when debugging
  x86/AMD/NB: Fix amd_set_subcaches() parameter type
  x86/quirks: Add workaround for AMD F16h Erratum792
  x86, doc, kconfig: Fix dud URL for Microcode data

Author: torvalds

arch/x86/Kconfig

@@ -444,6 +444,7 @@ config X86_INTEL_MID
 	bool "Intel MID platform support"
 	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
+	depends on X86_PLATFORM_DEVICES
 	depends on PCI
 	depends on PCI_GOANY
 	depends on X86_IO_APIC
@@ -1051,9 +1052,9 @@ config MICROCODE_INTEL
 	  This options enables microcode patch loading support for Intel
 	  processors.
 
-	  For latest news and information on obtaining all the required
-	  Intel ingredients for this driver, check:
-	  <http://www.urbanmyth.org/microcode/>.
+	  For the current Intel microcode data package go to
+	  <https://downloadcenter.intel.com> and search for
+	  'Linux Processor Microcode Data File'.
 
 config MICROCODE_AMD
 	bool "AMD microcode loading support"

arch/x86/include/asm/amd_nb.h

@@ -19,7 +19,7 @@ extern int amd_cache_northbridges(void);
 extern void amd_flush_garts(void);
 extern int amd_numa_init(void);
 extern int amd_get_subcaches(int);
-extern int amd_set_subcaches(int, int);
+extern int amd_set_subcaches(int, unsigned long);
 
 struct amd_l3_cache {
 	unsigned indices;

arch/x86/include/asm/tlbflush.h

@@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void)
 
 static inline void __flush_tlb_one(unsigned long addr)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
 }
 
@@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr)
  */
 static inline void __flush_tlb_up(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 }
 
 static inline void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb_all();
 }
 

arch/x86/kernel/amd_nb.c

@@ -179,7 +179,7 @@ int amd_get_subcaches(int cpu)
 	return (mask >> (4 * cuid)) & 0xf;
 }
 
-int amd_set_subcaches(int cpu, int mask)
+int amd_set_subcaches(int cpu, unsigned long mask)
 {
 	static unsigned int reset, ban;
 	struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));

arch/x86/kernel/cpu/amd.c

@@ -767,10 +767,7 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 
 static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
 {
-	tlb_flushall_shift = 5;
-
-	if (c->x86 <= 0x11)
-		tlb_flushall_shift = 4;
+	tlb_flushall_shift = 6;
 }
 
 static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)

arch/x86/kernel/cpu/intel.c

@@ -640,21 +640,17 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
 	case 0x61d: /* six-core 45 nm xeon "Dunnington" */
 		tlb_flushall_shift = -1;
 		break;
+	case 0x63a: /* Ivybridge */
+		tlb_flushall_shift = 2;
+		break;
 	case 0x61a: /* 45 nm nehalem, "Bloomfield" */
 	case 0x61e: /* 45 nm nehalem, "Lynnfield" */
 	case 0x625: /* 32 nm nehalem, "Clarkdale" */
 	case 0x62c: /* 32 nm nehalem, "Gulftown" */
 	case 0x62e: /* 45 nm nehalem-ex, "Beckton" */
 	case 0x62f: /* 32 nm Xeon E7 */
-		tlb_flushall_shift = 6;
-		break;
 	case 0x62a: /* SandyBridge */
 	case 0x62d: /* SandyBridge, "Romely-EP" */
-		tlb_flushall_shift = 5;
-		break;
-	case 0x63a: /* Ivybridge */
-		tlb_flushall_shift = 1;
-		break;
 	default:
 		tlb_flushall_shift = 6;
 	}

arch/x86/kernel/cpu/microcode/amd_early.c

@@ -285,6 +285,15 @@ static void __init collect_cpu_sig_on_bsp(void *arg)
 
 	uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
+
+static void __init get_bsp_sig(void)
+{
+	unsigned int bsp = boot_cpu_data.cpu_index;
+	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
+
+	if (!uci->cpu_sig.sig)
+		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+}
 #else
 void load_ucode_amd_ap(void)
 {
@@ -337,31 +346,37 @@ void load_ucode_amd_ap(void)
 
 int __init save_microcode_in_initrd_amd(void)
 {
+	unsigned long cont;
 	enum ucode_state ret;
 	u32 eax;
 
-#ifdef CONFIG_X86_32
-	unsigned int bsp = boot_cpu_data.cpu_index;
-	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
-
-	if (!uci->cpu_sig.sig)
-		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+	if (!container)
+		return -EINVAL;
 
+#ifdef CONFIG_X86_32
+	get_bsp_sig();
+	cont = (unsigned long)container;
+#else
 	/*
-	 * Take into account the fact that the ramdisk might get relocated
-	 * and therefore we need to recompute the container's position in
-	 * virtual memory space.
+	 * We need the physical address of the container for both bitness since
+	 * boot_params.hdr.ramdisk_image is a physical address.
 	 */
-	container = (u8 *)(__va((u32)relocated_ramdisk) +
-			   ((u32)container - boot_params.hdr.ramdisk_image));
+	cont = __pa(container);
 #endif
+
+	/*
+	 * Take into account the fact that the ramdisk might get relocated and
+	 * therefore we need to recompute the container's position in virtual
+	 * memory space.
+	 */
+	if (relocated_ramdisk)
+		container = (u8 *)(__va(relocated_ramdisk) +
+			     (cont - boot_params.hdr.ramdisk_image));
+
 	if (ucode_new_rev)
 		pr_info("microcode: updated early to new patch_level=0x%08x\n",
 			ucode_new_rev);
 
-	if (!container)
-		return -EINVAL;
-
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 

arch/x86/kernel/cpu/mtrr/generic.c

@@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Save MTRR state */
@@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */

arch/x86/kernel/irq.c

@@ -266,6 +266,14 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+/* These two declarations are only used in check_irq_vectors_for_cpu_disable()
+ * below, which is protected by stop_machine().  Putting them on the stack
+ * results in a stack frame overflow.  Dynamically allocating could result in a
+ * failure so declare these two cpumasks as global.
+ */
+static struct cpumask affinity_new, online_new;
+
 /*
  * This cpu is going to be removed and its vectors migrated to the remaining
  * online cpus.  Check to see if there are enough vectors in the remaining cpus.
@@ -277,7 +285,6 @@ int check_irq_vectors_for_cpu_disable(void)
 	unsigned int this_cpu, vector, this_count, count;
 	struct irq_desc *desc;
 	struct irq_data *data;
-	struct cpumask affinity_new, online_new;
 
 	this_cpu = smp_processor_id();
 	cpumask_copy(&online_new, cpu_online_mask);

arch/x86/kernel/quirks.c

@@ -571,3 +571,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5,
 			quirk_amd_nb_node);
 
 #endif
+
+#ifdef CONFIG_PCI
+/*
+ * Processor does not ensure DRAM scrub read/write sequence
+ * is atomic wrt accesses to CC6 save state area. Therefore
+ * if a concurrent scrub read/write access is to same address
+ * the entry may appear as if it is not written. This quirk
+ * applies to Fam16h models 00h-0Fh
+ *
+ * See "Revision Guide" for AMD F16h models 00h-0fh,
+ * document 51810 rev. 3.04, Nov 2013
+ */
+static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
+{
+	u32 val;
+
+	/*
+	 * Suggested workaround:
+	 * set D18F3x58[4:0] = 00h and set D18F3x5C[0] = 0b
+	 */
+	pci_read_config_dword(dev, 0x58, &val);
+	if (val & 0x1F) {
+		val &= ~(0x1F);
+		pci_write_config_dword(dev, 0x58, val);
+	}
+
+	pci_read_config_dword(dev, 0x5C, &val);
+	if (val & BIT(0)) {
+		val &= ~BIT(0);
+		pci_write_config_dword(dev, 0x5c, val);
+	}
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
+			amd_disable_seq_and_redirect_scrub);
+
+#endif

arch/x86/mm/numa_32.c

@@ -52,6 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end)
 			nid, start, end);
 	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
 	printk(KERN_DEBUG "  ");
+	start = round_down(start, PAGES_PER_SECTION);
+	end = round_up(end, PAGES_PER_SECTION);
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
 		physnode_map[pfn / PAGES_PER_SECTION] = nid;
 		printk(KERN_CONT "%lx ", pfn);

arch/x86/mm/srat.c

@@ -42,15 +42,25 @@ static __init inline int srat_disabled(void)
 	return acpi_numa < 0;
 }
 
-/* Callback for SLIT parsing */
+/*
+ * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
+ * I/O localities since SRAT does not list them.  I/O localities are
+ * not supported at this point.
+ */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
 	int i, j;
 
-	for (i = 0; i < slit->locality_count; i++)
-		for (j = 0; j < slit->locality_count; j++)
+	for (i = 0; i < slit->locality_count; i++) {
+		if (pxm_to_node(i) == NUMA_NO_NODE)
+			continue;
+		for (j = 0; j < slit->locality_count; j++) {
+			if (pxm_to_node(j) == NUMA_NO_NODE)
+				continue;
 			numa_set_distance(pxm_to_node(i), pxm_to_node(j),
 				slit->entry[slit->locality_count * i + j]);
+		}
+	}
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */