Merge tag 'efi-urgent' into x86/urgent

 * Avoid WARN_ON() when mapping BGRT on Baytrail (EFI 32-bit).

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 940e50e..0af5250 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -444,6 +444,7 @@
 	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 @@
 	  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"
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index a54ee1d..aaac3b2 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -19,7 +19,7 @@
 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;
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index e6d90ba..04905bf 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,7 +62,7 @@
 
 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_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();
 }
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 59554dc..dec8de4 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -179,7 +179,7 @@
 	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));
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d3153e2..c67ffa6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -767,10 +767,7 @@
 
 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)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3db61c6..5cd9bfa 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -640,21 +640,17 @@
 	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;
 	}
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 8384c0f..617a9e2 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -285,6 +285,15 @@
 
 	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 @@
 
 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 (!container)
+		return -EINVAL;
 
-	if (!uci->cpu_sig.sig)
-		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+#ifdef CONFIG_X86_32
+	get_bsp_sig();
+	cont = (unsigned long)container;
+#else
+	/*
+	 * We need the physical address of the container for both bitness since
+	 * boot_params.hdr.ramdisk_image is a physical address.
+	 */
+	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.
+	 * 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.
 	 */
-	container = (u8 *)(__va((u32)relocated_ramdisk) +
-			   ((u32)container - boot_params.hdr.ramdisk_image));
-#endif
+	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);
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index ce2d0a2..0e25a1b 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,7 +683,7 @@
 	}
 
 	/* 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 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 */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index dbb6087..d99f31d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -266,6 +266,14 @@
 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 @@
 	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);
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 04ee1e2..7c6acd4 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -571,3 +571,40 @@
 			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
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 0342d27..47b6436 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -52,6 +52,8 @@
 			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);
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1a25187..1953e9c 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -42,15 +42,25 @@
 	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 */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ae699b3..dd8dda1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,7 +103,7 @@
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
@@ -131,7 +131,7 @@
 	info.flush_start = start;
 	info.flush_end = end;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -151,44 +151,19 @@
 
 	preempt_disable();
 
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
-/*
- * It can find out the THP large page, or
- * HUGETLB page in tlb_flush when THP disabled
- */
-static inline unsigned long has_large_page(struct mm_struct *mm,
-				 unsigned long start, unsigned long end)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	unsigned long addr = ALIGN(start, HPAGE_SIZE);
-	for (; addr < end; addr += HPAGE_SIZE) {
-		pgd = pgd_offset(mm, addr);
-		if (likely(!pgd_none(*pgd))) {
-			pud = pud_offset(pgd, addr);
-			if (likely(!pud_none(*pud))) {
-				pmd = pmd_offset(pud, addr);
-				if (likely(!pmd_none(*pmd)))
-					if (pmd_large(*pmd))
-						return addr;
-			}
-		}
-	}
-	return 0;
-}
-
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag)
 {
 	unsigned long addr;
 	unsigned act_entries, tlb_entries = 0;
+	unsigned long nr_base_pages;
 
 	preempt_disable();
 	if (current->active_mm != mm)
@@ -210,21 +185,20 @@
 		tlb_entries = tlb_lli_4k[ENTRIES];
 	else
 		tlb_entries = tlb_lld_4k[ENTRIES];
+
 	/* Assume all of TLB entries was occupied by this task */
-	act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
+	act_entries = tlb_entries >> tlb_flushall_shift;
+	act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm;
+	nr_base_pages = (end - start) >> PAGE_SHIFT;
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
-	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
-		count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	if (nr_base_pages > act_entries) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
-		if (has_large_page(mm, start, end)) {
-			local_flush_tlb();
-			goto flush_all;
-		}
 		/* flush range by one by one 'invlpg' */
 		for (addr = start; addr < end;	addr += PAGE_SIZE) {
-			count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 			__flush_tlb_single(addr);
 		}
 
@@ -262,7 +236,7 @@
 
 static void do_flush_tlb_all(void *info)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	__flush_tlb_all();
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(smp_processor_id());
@@ -270,7 +244,7 @@
 
 void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index c557c6d..3a712e2 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -71,12 +71,14 @@
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 		NR_TLB_REMOTE_FLUSH,	/* cpu tried to flush others' tlbs */
 		NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
-#endif
+#endif /* CONFIG_SMP */
 		NR_TLB_LOCAL_FLUSH_ALL,
 		NR_TLB_LOCAL_FLUSH_ONE,
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 		NR_VM_EVENT_ITEMS
 };
 
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index a67b384..67ce70c 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -83,6 +83,14 @@
 #define count_vm_numa_events(x, y) do { (void)(y); } while (0)
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_DEBUG_TLBFLUSH
+#define count_vm_tlb_event(x)	   count_vm_event(x)
+#define count_vm_tlb_events(x, y)  count_vm_events(x, y)
+#else
+#define count_vm_tlb_event(x)     do {} while (0)
+#define count_vm_tlb_events(x, y) do { (void)(y); } while (0)
+#endif
+
 #define __count_zone_vm_events(item, zone, delta) \
 		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
 		zone_idx(zone), delta)
diff --git a/lib/Makefile b/lib/Makefile
index 126b34f..48140e3 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -45,6 +45,7 @@
 obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
 obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
 
+GCOV_PROFILE_hweight.o := n
 CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7249614..def5dd2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -851,12 +851,14 @@
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
-#endif
+#endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };