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

Pull x86 fixes from Thomas Gleixner:
 "A set of small fixes for 4.15:

   - Fix vmapped stack synchronization on systems with 4-level paging
     and a large amount of memory caused by a missing 5-level folding
     which made the pgd synchronization logic to fail and causing double
     faults.

   - Add a missing sanity check in the vmalloc_fault() logic on 5-level
     paging systems.

   - Bring back protection against accessing a freed initrd in the
     microcode loader which was lost by a wrong merge conflict
     resolution.

   - Extend the Broadwell micro code loading sanity check.

   - Add a missing ENDPROC annotation in ftrace assembly code which
     makes ORC unhappy.

   - Prevent loading the AMD power module on !AMD platforms. The load
     itself is uncritical, but an unload attempt results in a kernel
     crash.

   - Update Peter Anvins role in the MAINTAINERS file"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ftrace: Add one more ENDPROC annotation
  x86: Mark hpa as a "Designated Reviewer" for the time being
  x86/mm/64: Tighten up vmalloc_fault() sanity checks on 5-level kernels
  x86/mm/64: Fix vmapped stack syncing on very-large-memory 4-level systems
  x86/microcode: Fix again accessing initrd after having been freed
  x86/microcode/intel: Extend BDW late-loading further with LLC size check
  perf/x86/amd/power: Do not load AMD power module on !AMD platforms

6 files changed, 59 insertions, 23 deletions

diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index a6eee5ac4f58..2aefacf5c5b2 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -277,7 +277,7 @@ static int __init amd_power_pmu_init(void)
 	int ret;
 
 	if (!x86_match_cpu(cpu_match))
-		return 0;
+		return -ENODEV;
 
 	if (!boot_cpu_has(X86_FEATURE_ACC_POWER))
 		return -ENODEV;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index c4fa4a85d4cb..e4fc595cd6ea 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -239,7 +239,7 @@ static int __init save_microcode_in_initrd(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (c->x86 >= 0x10)
-			return save_microcode_in_initrd_amd(cpuid_eax(1));
+			ret = save_microcode_in_initrd_amd(cpuid_eax(1));
 		break;
 	default:
 		break;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index d9e460fc7a3b..f7c55b0e753a 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -45,6 +45,9 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
 /* Current microcode patch used in early patching on the APs. */
 static struct microcode_intel *intel_ucode_patch;
 
+/* last level cache size per core */
+static int llc_size_per_core;
+
 static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
 					unsigned int s2, unsigned int p2)
 {
@@ -912,12 +915,14 @@ static bool is_blacklisted(unsigned int cpu)
 
 	/*
 	 * Late loading on model 79 with microcode revision less than 0x0b000021
-	 * may result in a system hang. This behavior is documented in item
-	 * BDF90, #334165 (Intel Xeon Processor E7-8800/4800 v4 Product Family).
+	 * and LLC size per core bigger than 2.5MB may result in a system hang.
+	 * This behavior is documented in item BDF90, #334165 (Intel Xeon
+	 * Processor E7-8800/4800 v4 Product Family).
 	 */
 	if (c->x86 == 6 &&
 	    c->x86_model == INTEL_FAM6_BROADWELL_X &&
 	    c->x86_mask == 0x01 &&
+	    llc_size_per_core > 2621440 &&
 	    c->microcode < 0x0b000021) {
 		pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode);
 		pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
@@ -975,6 +980,15 @@ static struct microcode_ops microcode_intel_ops = {
 	.apply_microcode                  = apply_microcode_intel,
 };
 
+static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
+{
+	u64 llc_size = c->x86_cache_size * 1024;
+
+	do_div(llc_size, c->x86_max_cores);
+
+	return (int)llc_size;
+}
+
 struct microcode_ops * __init init_intel_microcode(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
@@ -985,5 +999,7 @@ struct microcode_ops * __init init_intel_microcode(void)
 		return NULL;
 	}
 
+	llc_size_per_core = calc_llc_size_per_core(c);
+
 	return &microcode_intel_ops;
 }
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index ef61f540cf0a..91b2cff4b79a 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -295,7 +295,7 @@ trace:
 	restore_mcount_regs
 
 	jmp fgraph_trace
-END(function_hook)
+ENDPROC(function_hook)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b3e40773dce0..800de815519c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -439,18 +439,13 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_ref))
 		return -1;
 
-	if (pgd_none(*pgd)) {
-		set_pgd(pgd, *pgd_ref);
-		arch_flush_lazy_mmu_mode();
-	} else if (CONFIG_PGTABLE_LEVELS > 4) {
-		/*
-		 * With folded p4d, pgd_none() is always false, so the pgd may
-		 * point to an empty page table entry and pgd_page_vaddr()
-		 * will return garbage.
-		 *
-		 * We will do the correct sanity check on the p4d level.
-		 */
-		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+	if (CONFIG_PGTABLE_LEVELS > 4) {
+		if (pgd_none(*pgd)) {
+			set_pgd(pgd, *pgd_ref);
+			arch_flush_lazy_mmu_mode();
+		} else {
+			BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+		}
 	}
 
 	/* With 4-level paging, copying happens on the p4d level. */
@@ -459,7 +454,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (p4d_none(*p4d_ref))
 		return -1;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) {
 		set_p4d(p4d, *p4d_ref);
 		arch_flush_lazy_mmu_mode();
 	} else {
@@ -470,6 +465,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	 * Below here mismatches are bugs because these lower tables
 	 * are shared:
 	 */
+	BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4);
 
 	pud = pud_offset(p4d, address);
 	pud_ref = pud_offset(p4d_ref, address);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a1561957dccb..5bfe61a5e8e3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -151,6 +151,34 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	local_irq_restore(flags);
 }
 
+static void sync_current_stack_to_mm(struct mm_struct *mm)
+{
+	unsigned long sp = current_stack_pointer;
+	pgd_t *pgd = pgd_offset(mm, sp);
+
+	if (CONFIG_PGTABLE_LEVELS > 4) {
+		if (unlikely(pgd_none(*pgd))) {
+			pgd_t *pgd_ref = pgd_offset_k(sp);
+
+			set_pgd(pgd, *pgd_ref);
+		}
+	} else {
+		/*
+		 * "pgd" is faked.  The top level entries are "p4d"s, so sync
+		 * the p4d.  This compiles to approximately the same code as
+		 * the 5-level case.
+		 */
+		p4d_t *p4d = p4d_offset(pgd, sp);
+
+		if (unlikely(p4d_none(*p4d))) {
+			pgd_t *pgd_ref = pgd_offset_k(sp);
+			p4d_t *p4d_ref = p4d_offset(pgd_ref, sp);
+
+			set_p4d(p4d, *p4d_ref);
+		}
+	}
+}
+
 void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			struct task_struct *tsk)
 {
@@ -226,11 +254,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			 * mapped in the new pgd, we'll double-fault.  Forcibly
 			 * map it.
 			 */
-			unsigned int index = pgd_index(current_stack_pointer);
-			pgd_t *pgd = next->pgd + index;
-
-			if (unlikely(pgd_none(*pgd)))
-				set_pgd(pgd, init_mm.pgd[index]);
+			sync_current_stack_to_mm(next);
 		}
 
 		/* Stop remote flushes for the previous mm */