21 files changed, 263 insertions, 114 deletions

diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
index 4224ede43b4e..26240dde081e 100644
--- a/arch/x86/boot/cpu.c
+++ b/arch/x86/boot/cpu.c
@@ -87,12 +87,6 @@ int validate_cpu(void)
 		return -1;
 	}
 
-	if (CONFIG_X86_MINIMUM_CPU_FAMILY <= 4 && !IS_ENABLED(CONFIG_M486) &&
-	    !has_eflag(X86_EFLAGS_ID)) {
-		printf("This kernel requires a CPU with the CPUID instruction.  Build with CONFIG_M486=y to run on this CPU.\n");
-		return -1;
-	}
-
 	if (err_flags) {
 		puts("This kernel requires the following features "
 		     "not present on the CPU:\n");
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6aa741fbe1df..eaf100508c36 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -602,33 +602,69 @@ static __always_inline void cpu_relax(void)
 	rep_nop();
 }
 
-/* Stop speculative execution and prefetching of modified code. */
+/*
+ * This function forces the icache and prefetched instruction stream to
+ * catch up with reality in two very specific cases:
+ *
+ *  a) Text was modified using one virtual address and is about to be executed
+ *     from the same physical page at a different virtual address.
+ *
+ *  b) Text was modified on a different CPU, may subsequently be
+ *     executed on this CPU, and you want to make sure the new version
+ *     gets executed.  This generally means you're calling this in a IPI.
+ *
+ * If you're calling this for a different reason, you're probably doing
+ * it wrong.
+ */
 static inline void sync_core(void)
 {
-	int tmp;
-
-#ifdef CONFIG_M486
 	/*
-	 * Do a CPUID if available, otherwise do a jump.  The jump
-	 * can conveniently enough be the jump around CPUID.
+	 * There are quite a few ways to do this.  IRET-to-self is nice
+	 * because it works on every CPU, at any CPL (so it's compatible
+	 * with paravirtualization), and it never exits to a hypervisor.
+	 * The only down sides are that it's a bit slow (it seems to be
+	 * a bit more than 2x slower than the fastest options) and that
+	 * it unmasks NMIs.  The "push %cs" is needed because, in
+	 * paravirtual environments, __KERNEL_CS may not be a valid CS
+	 * value when we do IRET directly.
+	 *
+	 * In case NMI unmasking or performance ever becomes a problem,
+	 * the next best option appears to be MOV-to-CR2 and an
+	 * unconditional jump.  That sequence also works on all CPUs,
+	 * but it will fault at CPL3 (i.e. Xen PV and lguest).
+	 *
+	 * CPUID is the conventional way, but it's nasty: it doesn't
+	 * exist on some 486-like CPUs, and it usually exits to a
+	 * hypervisor.
+	 *
+	 * Like all of Linux's memory ordering operations, this is a
+	 * compiler barrier as well.
 	 */
-	asm volatile("cmpl %2,%1\n\t"
-		     "jl 1f\n\t"
-		     "cpuid\n"
-		     "1:"
-		     : "=a" (tmp)
-		     : "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+	register void *__sp asm(_ASM_SP);
+
+#ifdef CONFIG_X86_32
+	asm volatile (
+		"pushfl\n\t"
+		"pushl %%cs\n\t"
+		"pushl $1f\n\t"
+		"iret\n\t"
+		"1:"
+		: "+r" (__sp) : : "memory");
 #else
-	/*
-	 * CPUID is a barrier to speculative execution.
-	 * Prefetched instructions are automatically
-	 * invalidated when modified.
-	 */
-	asm volatile("cpuid"
-		     : "=a" (tmp)
-		     : "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+	unsigned int tmp;
+
+	asm volatile (
+		"mov %%ss, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq %%rsp\n\t"
+		"addq $8, (%%rsp)\n\t"
+		"pushfq\n\t"
+		"mov %%cs, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq $1f\n\t"
+		"iretq\n\t"
+		"1:"
+		: "=&r" (tmp), "+r" (__sp) : : "cc", "memory");
 #endif
 }
 
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index c5a7f3a930dd..6fa75b17aec3 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -12,7 +12,7 @@ struct unwind_state {
 	struct task_struct *task;
 	int graph_idx;
 #ifdef CONFIG_FRAME_POINTER
-	unsigned long *bp;
+	unsigned long *bp, *orig_sp;
 	struct pt_regs *regs;
 #else
 	unsigned long *sp;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 6ba793178441..7ba7e90a9ad6 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -59,7 +59,7 @@ struct x86_init_irqs {
 
 /**
  * struct x86_init_oem - oem platform specific customizing functions
- * @arch_setup:			platform specific architecure setup
+ * @arch_setup:			platform specific architecture setup
  * @banner:			print a platform specific banner
  */
 struct x86_init_oem {
@@ -165,8 +165,25 @@ struct x86_legacy_devices {
 };
 
 /**
+ * enum x86_legacy_i8042_state - i8042 keyboard controller state
+ * @X86_LEGACY_I8042_PLATFORM_ABSENT: the controller is always absent on
+ *	given platform/subarch.
+ * @X86_LEGACY_I8042_FIRMWARE_ABSENT: firmware reports that the controller
+ *	is absent.
+ * @X86_LEGACY_i8042_EXPECTED_PRESENT: the controller is likely to be
+ *	present, the i8042 driver should probe for controller existence.
+ */
+enum x86_legacy_i8042_state {
+	X86_LEGACY_I8042_PLATFORM_ABSENT,
+	X86_LEGACY_I8042_FIRMWARE_ABSENT,
+	X86_LEGACY_I8042_EXPECTED_PRESENT,
+};
+
+/**
  * struct x86_legacy_features - legacy x86 features
  *
+ * @i8042: indicated if we expect the device to have i8042 controller
+ *	present.
  * @rtc: this device has a CMOS real-time clock present
  * @reserve_bios_regions: boot code will search for the EBDA address and the
  * 	start of the 640k - 1M BIOS region.  If false, the platform must
@@ -175,6 +192,7 @@ struct x86_legacy_devices {
  * 	documentation for further details.
  */
 struct x86_legacy_features {
+	enum x86_legacy_i8042_state i8042;
 	int rtc;
 	int reserve_bios_regions;
 	struct x86_legacy_devices devices;
@@ -188,15 +206,14 @@ struct x86_legacy_features {
  * @set_wallclock:		set time back to HW clock
  * @is_untracked_pat_range	exclude from PAT logic
  * @nmi_init			enable NMI on cpus
- * @i8042_detect		pre-detect if i8042 controller exists
  * @save_sched_clock_state:	save state for sched_clock() on suspend
  * @restore_sched_clock_state:	restore state for sched_clock() on resume
- * @apic_post_init:		adjust apic if neeeded
+ * @apic_post_init:		adjust apic if needed
  * @legacy:			legacy features
  * @set_legacy_features:	override legacy features. Use of this callback
  * 				is highly discouraged. You should only need
  * 				this if your hardware platform requires further
- * 				custom fine tuning far beyong what may be
+ * 				custom fine tuning far beyond what may be
  * 				possible in x86_early_init_platform_quirks() by
  * 				only using the current x86_hardware_subarch
  * 				semantics.
@@ -210,7 +227,6 @@ struct x86_platform_ops {
 	bool (*is_untracked_pat_range)(u64 start, u64 end);
 	void (*nmi_init)(void);
 	unsigned char (*get_nmi_reason)(void);
-	int (*i8042_detect)(void);
 	void (*save_sched_clock_state)(void);
 	void (*restore_sched_clock_state)(void);
 	void (*apic_post_init)(void);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 6f65b0eed384..64422f850e95 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -930,6 +930,13 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
 		x86_platform.legacy.devices.pnpbios = 0;
 	}
 
+	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
+	    !(acpi_gbl_FADT.boot_flags & ACPI_FADT_8042) &&
+	    x86_platform.legacy.i8042 != X86_LEGACY_I8042_PLATFORM_ABSENT) {
+		pr_debug("ACPI: i8042 controller is absent\n");
+		x86_platform.legacy.i8042 = X86_LEGACY_I8042_FIRMWARE_ABSENT;
+	}
+
 	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) {
 		pr_debug("ACPI: not registering RTC platform device\n");
 		x86_platform.legacy.rtc = 0;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5cb272a7a5a3..c5b8f760473c 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -337,7 +337,11 @@ done:
 		n_dspl, (unsigned long)orig_insn + n_dspl + repl_len);
 }
 
-static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
+/*
+ * "noinline" to cause control flow change and thus invalidate I$ and
+ * cause refetch after modification.
+ */
+static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
 {
 	unsigned long flags;
 
@@ -346,7 +350,6 @@ static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
 
 	local_irq_save(flags);
 	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
-	sync_core();
 	local_irq_restore(flags);
 
 	DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
@@ -359,9 +362,12 @@ static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
  * This implies that asymmetric systems where APs have less capabilities than
  * the boot processor are not handled. Tough. Make sure you disable such
  * features by hand.
+ *
+ * Marked "noinline" to cause control flow change and thus insn cache
+ * to refetch changed I$ lines.
  */
-void __init_or_module apply_alternatives(struct alt_instr *start,
-					 struct alt_instr *end)
+void __init_or_module noinline apply_alternatives(struct alt_instr *start,
+						  struct alt_instr *end)
 {
 	struct alt_instr *a;
 	u8 *instr, *replacement;
@@ -667,7 +673,6 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	unsigned long flags;
 	local_irq_save(flags);
 	memcpy(addr, opcode, len);
-	sync_core();
 	local_irq_restore(flags);
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1f6b50a449ab..dc1697ca5191 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -667,13 +667,14 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_1_EDX] = edx;
 	}
 
+	/* Thermal and Power Management Leaf: level 0x00000006 (eax) */
+	if (c->cpuid_level >= 0x00000006)
+		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
+
 	/* Additional Intel-defined flags: level 0x00000007 */
 	if (c->cpuid_level >= 0x00000007) {
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
-
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
-
-		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
 		c->x86_capability[CPUID_7_ECX] = ecx;
 	}
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 6f353bdb3a25..6a31e2691f3a 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -116,10 +116,11 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
 
 /*
  * This scans the ucode blob for the proper container as we can have multiple
- * containers glued together.
+ * containers glued together. Returns the equivalence ID from the equivalence
+ * table or 0 if none found.
  */
-static struct container
-find_proper_container(u8 *ucode, size_t size, u16 *ret_id)
+static u16
+find_proper_container(u8 *ucode, size_t size, struct container *ret_cont)
 {
 	struct container ret = { NULL, 0 };
 	u32 eax, ebx, ecx, edx;
@@ -138,7 +139,7 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id)
 	if (header[0] != UCODE_MAGIC ||
 	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
 	    header[2] == 0)                            /* size */
-		return ret;
+		return eq_id;
 
 	eax = 0x00000001;
 	ecx = 0;
@@ -163,8 +164,9 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id)
 			 * ucode update loop below
 			 */
 			left = ret.size - offset;
-			*ret_id = eq_id;
-			return ret;
+
+			*ret_cont = ret;
+			return eq_id;
 		}
 
 		/*
@@ -189,7 +191,7 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id)
 		ucode     = data;
 	}
 
-	return ret;
+	return eq_id;
 }
 
 static int __apply_microcode_amd(struct microcode_amd *mc_amd)
@@ -214,17 +216,18 @@ static int __apply_microcode_amd(struct microcode_amd *mc_amd)
  * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
  * load_microcode_amd() to save equivalent cpu table and microcode patches in
  * kernel heap memory.
+ *
+ * Returns true if container found (sets @ret_cont), false otherwise.
  */
-static struct container
-apply_microcode_early_amd(void *ucode, size_t size, bool save_patch)
+static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch,
+				      struct container *ret_cont)
 {
-	struct container ret = { NULL, 0 };
 	u8 (*patch)[PATCH_MAX_SIZE];
+	u32 rev, *header, *new_rev;
+	struct container ret;
 	int offset, left;
-	u32 rev, *header;
-	u8  *data;
 	u16 eq_id = 0;
-	u32 *new_rev;
+	u8  *data;
 
 #ifdef CONFIG_X86_32
 	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
@@ -235,11 +238,11 @@ apply_microcode_early_amd(void *ucode, size_t size, bool save_patch)
 #endif
 
 	if (check_current_patch_level(&rev, true))
-		return (struct container){ NULL, 0 };
+		return false;
 
-	ret = find_proper_container(ucode, size, &eq_id);
+	eq_id = find_proper_container(ucode, size, &ret);
 	if (!eq_id)
-		return (struct container){ NULL, 0 };
+		return false;
 
 	this_equiv_id = eq_id;
 	header = (u32 *)ret.data;
@@ -273,7 +276,11 @@ apply_microcode_early_amd(void *ucode, size_t size, bool save_patch)
 		data   += offset;
 		left   -= offset;
 	}
-	return ret;
+
+	if (ret_cont)
+		*ret_cont = ret;
+
+	return true;
 }
 
 static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
@@ -294,6 +301,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
 void __init load_ucode_amd_bsp(unsigned int family)
 {
 	struct ucode_cpu_info *uci;
+	u32 eax, ebx, ecx, edx;
 	struct cpio_data cp;
 	const char *path;
 	bool use_pa;
@@ -315,9 +323,12 @@ void __init load_ucode_amd_bsp(unsigned int family)
 		return;
 
 	/* Get BSP's CPUID.EAX(1), needed in load_microcode_amd() */
-	uci->cpu_sig.sig = cpuid_eax(1);
+	eax = 1;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+	uci->cpu_sig.sig = eax;
 
-	apply_microcode_early_amd(cp.data, cp.size, true);
+	apply_microcode_early_amd(cp.data, cp.size, true, NULL);
 }
 
 #ifdef CONFIG_X86_32
@@ -349,7 +360,7 @@ void load_ucode_amd_ap(unsigned int family)
 	 * This would set amd_ucode_patch above so that the following APs can
 	 * use it directly instead of going down this path again.
 	 */
-	apply_microcode_early_amd(cp.data, cp.size, true);
+	apply_microcode_early_amd(cp.data, cp.size, true, NULL);
 }
 #else
 void load_ucode_amd_ap(unsigned int family)
@@ -387,8 +398,7 @@ reget:
 			}
 		}
 
-		cont = apply_microcode_early_amd(cp.data, cp.size, false);
-		if (!(cont.data && cont.size)) {
+		if (!apply_microcode_early_amd(cp.data, cp.size, false, &cont)) {
 			cont.size = -1;
 			return;
 		}
@@ -443,7 +453,7 @@ int __init save_microcode_in_initrd_amd(unsigned int fam)
 				return -EINVAL;
 			}
 
-			cont = find_proper_container(cp.data, cp.size, &eq_id);
+			eq_id = find_proper_container(cp.data, cp.size, &cont);
 			if (!eq_id) {
 				cont.size = -1;
 				return -EINVAL;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 6996413c78c3..2af69d27da62 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -44,7 +44,7 @@
 #define DRIVER_VERSION	"2.2"
 
 static struct microcode_ops	*microcode_ops;
-static bool dis_ucode_ldr;
+static bool dis_ucode_ldr = true;
 
 LIST_HEAD(microcode_cache);
 
@@ -76,6 +76,7 @@ struct cpu_info_ctx {
 static bool __init check_loader_disabled_bsp(void)
 {
 	static const char *__dis_opt_str = "dis_ucode_ldr";
+	u32 a, b, c, d;
 
 #ifdef CONFIG_X86_32
 	const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
@@ -88,8 +89,23 @@ static bool __init check_loader_disabled_bsp(void)
 	bool *res = &dis_ucode_ldr;
 #endif
 
-	if (cmdline_find_option_bool(cmdline, option))
-		*res = true;
+	if (!have_cpuid_p())
+		return *res;
+
+	a = 1;
+	c = 0;
+	native_cpuid(&a, &b, &c, &d);
+
+	/*
+	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
+	 * completely accurate as xen pv guests don't see that CPUID bit set but
+	 * that's good enough as they don't land on the BSP path anyway.
+	 */
+	if (c & BIT(31))
+		return *res;
+
+	if (cmdline_find_option_bool(cmdline, option) <= 0)
+		*res = false;
 
 	return *res;
 }
@@ -121,9 +137,6 @@ void __init load_ucode_bsp(void)
 	if (check_loader_disabled_bsp())
 		return;
 
-	if (!have_cpuid_p())
-		return;
-
 	vendor = x86_cpuid_vendor();
 	family = x86_cpuid_family();
 
@@ -157,9 +170,6 @@ void load_ucode_ap(void)
 	if (check_loader_disabled_ap())
 		return;
 
-	if (!have_cpuid_p())
-		return;
-
 	vendor = x86_cpuid_vendor();
 	family = x86_cpuid_family();
 
@@ -233,14 +243,12 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
 # endif
 
 	/*
-	 * Did we relocate the ramdisk?
-	 *
-	 * So we possibly relocate the ramdisk *after* applying microcode on the
-	 * BSP so we rely on use_pa (use physical addresses) - even if it is not
-	 * absolutely correct - to determine whether we've done the ramdisk
-	 * relocation already.
+	 * Fixup the start address: after reserve_initrd() runs, initrd_start
+	 * has the virtual address of the beginning of the initrd. It also
+	 * possibly relocates the ramdisk. In either case, initrd_start contains
+	 * the updated address so use that instead.
 	 */
-	if (!use_pa && relocated_ramdisk)
+	if (!use_pa && initrd_start)
 		start = initrd_start;
 
 	return find_cpio_data(path, (void *)start, size, NULL);
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 54d50c3694d8..b624b54912e1 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -368,6 +368,26 @@ next:
 	return patch;
 }
 
+static void cpuid_1(void)
+{
+	/*
+	 * According to the Intel SDM, Volume 3, 9.11.7:
+	 *
+	 *   CPUID returns a value in a model specific register in
+	 *   addition to its usual register return values. The
+	 *   semantics of CPUID cause it to deposit an update ID value
+	 *   in the 64-bit model-specific register at address 08BH
+	 *   (IA32_BIOS_SIGN_ID). If no update is present in the
+	 *   processor, the value in the MSR remains unmodified.
+	 *
+	 * Use native_cpuid -- this code runs very early and we don't
+	 * want to mess with paravirt.
+	 */
+	unsigned int eax = 1, ebx, ecx = 0, edx;
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+}
+
 static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 {
 	unsigned int val[2];
@@ -393,7 +413,7 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
+	cpuid_1();
 
 	/* get the current revision from MSR 0x8B */
 	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
@@ -593,7 +613,7 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
+	cpuid_1();
 
 	/* get the current revision from MSR 0x8B */
 	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
@@ -805,7 +825,7 @@ static int apply_microcode_intel(int cpu)
 	wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
+	cpuid_1();
 
 	/* get the current revision from MSR 0x8B */
 	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 6c044543545e..f37e02e41a77 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -30,6 +30,7 @@
 #include <asm/apic.h>
 #include <asm/timer.h>
 #include <asm/reboot.h>
+#include <asm/nmi.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -157,6 +158,26 @@ static unsigned char hv_get_nmi_reason(void)
 	return 0;
 }
 
+#ifdef CONFIG_X86_LOCAL_APIC
+/*
+ * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes
+ * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle
+ * unknown NMI on the first CPU which gets it.
+ */
+static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
+{
+	static atomic_t nmi_cpu = ATOMIC_INIT(-1);
+
+	if (!unknown_nmi_panic)
+		return NMI_DONE;
+
+	if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1)
+		return NMI_HANDLED;
+
+	return NMI_DONE;
+}
+#endif
+
 static void __init ms_hyperv_init_platform(void)
 {
 	/*
@@ -182,6 +203,9 @@ static void __init ms_hyperv_init_platform(void)
 		pr_info("HyperV: LAPIC Timer Frequency: %#x\n",
 			lapic_timer_frequency);
 	}
+
+	register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST,
+			     "hv_nmi_unknown");
 #endif
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index d33ef165b1f8..553acbbb4d32 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -68,7 +68,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 #endif
 
 	default:
-patch_default:
+patch_default: __maybe_unused
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
 
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index f4fcf26c9fce..11aaf1eaa0e4 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -80,7 +80,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 #endif
 
 	default:
-patch_default:
+patch_default: __maybe_unused
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
 
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
index 24a50301f150..91271122f0df 100644
--- a/arch/x86/kernel/platform-quirks.c
+++ b/arch/x86/kernel/platform-quirks.c
@@ -6,6 +6,7 @@
 
 void __init x86_early_init_platform_quirks(void)
 {
+	x86_platform.legacy.i8042 = X86_LEGACY_I8042_EXPECTED_PRESENT;
 	x86_platform.legacy.rtc = 1;
 	x86_platform.legacy.reserve_bios_regions = 0;
 	x86_platform.legacy.devices.pnpbios = 1;
@@ -16,10 +17,14 @@ void __init x86_early_init_platform_quirks(void)
 		break;
 	case X86_SUBARCH_XEN:
 	case X86_SUBARCH_LGUEST:
+		x86_platform.legacy.devices.pnpbios = 0;
+		x86_platform.legacy.rtc = 0;
+		break;
 	case X86_SUBARCH_INTEL_MID:
 	case X86_SUBARCH_CE4100:
 		x86_platform.legacy.devices.pnpbios = 0;
 		x86_platform.legacy.rtc = 0;
+		x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT;
 		break;
 	}
 
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index ea7b7f9a3b9e..4443e499f279 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -6,6 +6,37 @@
 
 #define FRAME_HEADER_SIZE (sizeof(long) * 2)
 
+static void unwind_dump(struct unwind_state *state, unsigned long *sp)
+{
+	static bool dumped_before = false;
+	bool prev_zero, zero = false;
+	unsigned long word;
+
+	if (dumped_before)
+		return;
+
+	dumped_before = true;
+
+	printk_deferred("unwind stack type:%d next_sp:%p mask:%lx graph_idx:%d\n",
+			state->stack_info.type, state->stack_info.next_sp,
+			state->stack_mask, state->graph_idx);
+
+	for (sp = state->orig_sp; sp < state->stack_info.end; sp++) {
+		word = READ_ONCE_NOCHECK(*sp);
+
+		prev_zero = zero;
+		zero = word == 0;
+
+		if (zero) {
+			if (!prev_zero)
+				printk_deferred("%p: %016x ...\n", sp, 0);
+			continue;
+		}
+
+		printk_deferred("%p: %016lx (%pB)\n", sp, word, (void *)word);
+	}
+}
+
 unsigned long unwind_get_return_address(struct unwind_state *state)
 {
 	unsigned long addr;
@@ -20,15 +51,7 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
 	addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
 				     addr_p);
 
-	if (!__kernel_text_address(addr)) {
-		printk_deferred_once(KERN_WARNING
-			"WARNING: unrecognized kernel stack return address %p at %p in %s:%d\n",
-			(void *)addr, addr_p, state->task->comm,
-			state->task->pid);
-		return 0;
-	}
-
-	return addr;
+	return __kernel_text_address(addr) ? addr : 0;
 }
 EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
@@ -46,7 +69,14 @@ static bool is_last_task_frame(struct unwind_state *state)
 	unsigned long bp = (unsigned long)state->bp;
 	unsigned long regs = (unsigned long)task_pt_regs(state->task);
 
-	return bp == regs - FRAME_HEADER_SIZE;
+	/*
+	 * We have to check for the last task frame at two different locations
+	 * because gcc can occasionally decide to realign the stack pointer and
+	 * change the offset of the stack frame by a word in the prologue of a
+	 * function called by head/entry code.
+	 */
+	return bp == regs - FRAME_HEADER_SIZE ||
+	       bp == regs - FRAME_HEADER_SIZE - sizeof(long);
 }
 
 /*
@@ -67,6 +97,7 @@ static bool update_stack_state(struct unwind_state *state, void *addr,
 			       size_t len)
 {
 	struct stack_info *info = &state->stack_info;
+	enum stack_type orig_type = info->type;
 
 	/*
 	 * If addr isn't on the current stack, switch to the next one.
@@ -80,6 +111,9 @@ static bool update_stack_state(struct unwind_state *state, void *addr,
 				   &state->stack_mask))
 			return false;
 
+	if (!state->orig_sp || info->type != orig_type)
+		state->orig_sp = addr;
+
 	return true;
 }
 
@@ -178,11 +212,13 @@ bad_address:
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
 			state->regs, state->task->comm,
 			state->task->pid, next_frame);
+		unwind_dump(state, (unsigned long *)state->regs);
 	} else {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack frame pointer at %p in %s:%d has bad value %p\n",
 			state->bp, state->task->comm,
 			state->task->pid, next_frame);
+		unwind_dump(state, state->bp);
 	}
 the_end:
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 0bd9f1287f39..11a93f005268 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -89,7 +89,6 @@ struct x86_cpuinit_ops x86_cpuinit = {
 };
 
 static void default_nmi_init(void) { };
-static int default_i8042_detect(void) { return 1; };
 
 struct x86_platform_ops x86_platform __ro_after_init = {
 	.calibrate_cpu			= native_calibrate_cpu,
@@ -100,7 +99,6 @@ struct x86_platform_ops x86_platform __ro_after_init = {
 	.is_untracked_pat_range		= is_ISA_range,
 	.nmi_init			= default_nmi_init,
 	.get_nmi_reason			= default_get_nmi_reason,
-	.i8042_detect			= default_i8042_detect,
 	.save_sched_clock_state 	= tsc_save_sched_clock_state,
 	.restore_sched_clock_state 	= tsc_restore_sched_clock_state,
 };
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 821cb41f00e6..ce4b06733c09 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -23,11 +23,6 @@
 #include <asm/io_apic.h>
 #include <asm/emergency-restart.h>
 
-static int ce4100_i8042_detect(void)
-{
-	return 0;
-}
-
 /*
  * The CE4100 platform has an internal 8051 Microcontroller which is
  * responsible for signaling to the external Power Management Unit the
@@ -145,7 +140,6 @@ static void sdv_pci_init(void)
 void __init x86_ce4100_early_setup(void)
 {
 	x86_init.oem.arch_setup = sdv_arch_setup;
-	x86_platform.i8042_detect = ce4100_i8042_detect;
 	x86_init.resources.probe_roms = x86_init_noop;
 	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
 	x86_init.mpparse.find_smp_config = x86_init_noop;
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index dd6cfa4ad3ac..61b5ed2b7d40 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -19,7 +19,7 @@ obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_spidev.o
 # I2C Devices
 obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o
 obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o
-obj-$(subst m,y,$(CONFIG_INPUT_MPU3050)) += platform_mpu3050.o
+obj-$(subst m,y,$(CONFIG_MPU3050_I2C)) += platform_mpu3050.o
 obj-$(subst m,y,$(CONFIG_INPUT_BMA150)) += platform_bma023.o
 obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o
 # I2C GPIO Expanders
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 7850128f0026..12a272582cdc 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -161,12 +161,6 @@ out:
 	regulator_has_full_constraints();
 }
 
-/* MID systems don't have i8042 controller */
-static int intel_mid_i8042_detect(void)
-{
-	return 0;
-}
-
 /*
  * Moorestown does not have external NMI source nor port 0x61 to report
  * NMI status. The possible NMI sources are from pmu as a result of NMI
@@ -197,7 +191,6 @@ void __init x86_intel_mid_early_setup(void)
 	x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
 
 	x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
-	x86_platform.i8042_detect = intel_mid_i8042_detect;
 	x86_init.timers.wallclock_init = intel_mid_rtc_init;
 	x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
 
diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c
index f5bad40936ac..b8f562049cad 100644
--- a/arch/x86/platform/intel-quark/imr_selftest.c
+++ b/arch/x86/platform/intel-quark/imr_selftest.c
@@ -25,7 +25,8 @@
  * @fmt:	format string.
  * ...		variadic argument list.
  */
-static void __init imr_self_test_result(int res, const char *fmt, ...)
+static __printf(2, 3)
+void __init imr_self_test_result(int res, const char *fmt, ...)
 {
 	va_list vlist;
 
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 0c2fae8d929d..73eb7fd4aec4 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -992,11 +992,12 @@ static void emit_relocs(int as_text, int use_real_mode)
 		die("Segment relocations found but --realmode not specified\n");
 
 	/* Order the relocations for more efficient processing */
-	sort_relocs(&relocs16);
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
 	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
+#else
+	sort_relocs(&relocs16);
 #endif
 
 	/* Print the relocations */