Merging upstream version 4.19.304.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

14 files changed, 358 insertions, 102 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8b1aa1206..2f0fa294d 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -156,6 +156,9 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
 		       madt->address);
 	}
 
+	if (madt->flags & ACPI_MADT_PCAT_COMPAT)
+		legacy_pic_pcat_compat();
+
 	default_acpi_madt_oem_check(madt->header.oem_id,
 				    madt->header.oem_table_id);
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 918a23704..33882d5ab 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -366,6 +366,17 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	u8 insnbuf[MAX_PATCH_LEN];
 
 	DPRINTK("alt table %px, -> %px", start, end);
+
+	/*
+	 * In the case CONFIG_X86_5LEVEL=y, KASAN_SHADOW_START is defined using
+	 * cpu_feature_enabled(X86_FEATURE_LA57) and is therefore patched here.
+	 * During the process, KASAN becomes confused seeing partial LA57
+	 * conversion and triggers a false-positive out-of-bound report.
+	 *
+	 * Disable KASAN until the patching is complete.
+	 */
+	kasan_disable_current();
+
 	/*
 	 * The scan order should be from start to end. A later scanned
 	 * alternative code can overwrite previously scanned alternative code.
@@ -426,6 +437,8 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 
 		text_poke_early(instr, insnbuf, insnbuf_sz);
 	}
+
+	kasan_enable_current();
 }
 
 #ifdef CONFIG_SMP
@@ -677,8 +690,8 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	} else {
 		local_irq_save(flags);
 		memcpy(addr, opcode, len);
-		local_irq_restore(flags);
 		sync_core();
+		local_irq_restore(flags);
 
 		/*
 		 * Could also do a CLFLUSH here to speed up CPU recovery; but
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index f7151cd03..3d7a8049f 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -247,12 +247,6 @@ extern int (*console_blank_hook)(int);
 #endif
 
 /*
- * The apm_bios device is one of the misc char devices.
- * This is its minor number.
- */
-#define	APM_MINOR_DEV	134
-
-/*
  * Various options can be changed at boot time as follows:
  * (We allow underscores for compatibility with the modules code)
  *	apm=on/off			enable/disable APM
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 256f2c612..84667781c 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -69,8 +69,13 @@ static const int amd_erratum_1054[] =
 static const int amd_zenbleed[] =
 	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf),
 			   AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf),
+			   AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf),
 			   AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf));
 
+static const int amd_erratum_1485[] =
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf),
+			   AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf));
+
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
 	int osvw_id = *erratum++;
@@ -1121,6 +1126,10 @@ static void init_amd(struct cpuinfo_x86 *c)
 	check_null_seg_clears_base(c);
 
 	zenbleed_check(c);
+
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
+	     cpu_has_amd_erratum(c, amd_erratum_1485))
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
 }
 
 #ifdef CONFIG_X86_32
@@ -1244,5 +1253,8 @@ static void zenbleed_check_cpu(void *unused)
 
 void amd_check_microcode(void)
 {
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return;
+
 	on_each_cpu(zenbleed_check_cpu, NULL, 1);
 }
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 680fa070e..6e1acbdd2 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -9,7 +9,6 @@
  *	- Andrew D. Balsa (code cleanup).
  */
 #include <linux/init.h>
-#include <linux/utsname.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/nospec.h>
@@ -25,9 +24,7 @@
 #include <asm/msr.h>
 #include <asm/vmx.h>
 #include <asm/paravirt.h>
-#include <asm/alternative.h>
 #include <asm/pgtable.h>
-#include <asm/set_memory.h>
 #include <asm/intel-family.h>
 #include <asm/e820/api.h>
 #include <asm/hypervisor.h>
@@ -47,6 +44,7 @@ static void __init md_clear_select_mitigation(void);
 static void __init taa_select_mitigation(void);
 static void __init mmio_select_mitigation(void);
 static void __init srbds_select_mitigation(void);
+static void __init gds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
@@ -115,21 +113,8 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
 DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear);
 EXPORT_SYMBOL_GPL(mmio_stale_data_clear);
 
-void __init check_bugs(void)
+void __init cpu_select_mitigations(void)
 {
-	identify_boot_cpu();
-
-	/*
-	 * identify_boot_cpu() initialized SMT support information, let the
-	 * core code know.
-	 */
-	cpu_smt_check_topology();
-
-	if (!IS_ENABLED(CONFIG_SMP)) {
-		pr_info("CPU: ");
-		print_cpu_info(&boot_cpu_data);
-	}
-
 	/*
 	 * Read the SPEC_CTRL MSR to account for reserved bits which may
 	 * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
@@ -165,39 +150,7 @@ void __init check_bugs(void)
 	l1tf_select_mitigation();
 	md_clear_select_mitigation();
 	srbds_select_mitigation();
-
-	arch_smt_update();
-
-#ifdef CONFIG_X86_32
-	/*
-	 * Check whether we are able to run this kernel safely on SMP.
-	 *
-	 * - i386 is no longer supported.
-	 * - In order to run on anything without a TSC, we need to be
-	 *   compiled for a i486.
-	 */
-	if (boot_cpu_data.x86 < 4)
-		panic("Kernel requires i486+ for 'invlpg' and other features");
-
-	init_utsname()->machine[1] =
-		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
-	alternative_instructions();
-
-	fpu__init_check_bugs();
-#else /* CONFIG_X86_64 */
-	alternative_instructions();
-
-	/*
-	 * Make sure the first 2MB area is not mapped by huge pages
-	 * There are typically fixed size MTRRs in there and overlapping
-	 * MTRRs into large pages causes slow downs.
-	 *
-	 * Right now we don't do that with gbpages because there seems
-	 * very little benefit for that case.
-	 */
-	if (!direct_gbpages)
-		set_memory_4k((unsigned long)__va(0), 1);
-#endif
+	gds_select_mitigation();
 }
 
 /*
@@ -649,6 +602,149 @@ static int __init srbds_parse_cmdline(char *str)
 early_param("srbds", srbds_parse_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"GDS: " fmt
+
+enum gds_mitigations {
+	GDS_MITIGATION_OFF,
+	GDS_MITIGATION_UCODE_NEEDED,
+	GDS_MITIGATION_FORCE,
+	GDS_MITIGATION_FULL,
+	GDS_MITIGATION_FULL_LOCKED,
+	GDS_MITIGATION_HYPERVISOR,
+};
+
+#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION)
+static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE;
+#else
+static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL;
+#endif
+
+static const char * const gds_strings[] = {
+	[GDS_MITIGATION_OFF]		= "Vulnerable",
+	[GDS_MITIGATION_UCODE_NEEDED]	= "Vulnerable: No microcode",
+	[GDS_MITIGATION_FORCE]		= "Mitigation: AVX disabled, no microcode",
+	[GDS_MITIGATION_FULL]		= "Mitigation: Microcode",
+	[GDS_MITIGATION_FULL_LOCKED]	= "Mitigation: Microcode (locked)",
+	[GDS_MITIGATION_HYPERVISOR]	= "Unknown: Dependent on hypervisor status",
+};
+
+bool gds_ucode_mitigated(void)
+{
+	return (gds_mitigation == GDS_MITIGATION_FULL ||
+		gds_mitigation == GDS_MITIGATION_FULL_LOCKED);
+}
+EXPORT_SYMBOL_GPL(gds_ucode_mitigated);
+
+void update_gds_msr(void)
+{
+	u64 mcu_ctrl_after;
+	u64 mcu_ctrl;
+
+	switch (gds_mitigation) {
+	case GDS_MITIGATION_OFF:
+		rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+		mcu_ctrl |= GDS_MITG_DIS;
+		break;
+	case GDS_MITIGATION_FULL_LOCKED:
+		/*
+		 * The LOCKED state comes from the boot CPU. APs might not have
+		 * the same state. Make sure the mitigation is enabled on all
+		 * CPUs.
+		 */
+	case GDS_MITIGATION_FULL:
+		rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+		mcu_ctrl &= ~GDS_MITG_DIS;
+		break;
+	case GDS_MITIGATION_FORCE:
+	case GDS_MITIGATION_UCODE_NEEDED:
+	case GDS_MITIGATION_HYPERVISOR:
+		return;
+	};
+
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+
+	/*
+	 * Check to make sure that the WRMSR value was not ignored. Writes to
+	 * GDS_MITG_DIS will be ignored if this processor is locked but the boot
+	 * processor was not.
+	 */
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
+	WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after);
+}
+
+static void __init gds_select_mitigation(void)
+{
+	u64 mcu_ctrl;
+
+	if (!boot_cpu_has_bug(X86_BUG_GDS))
+		return;
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		gds_mitigation = GDS_MITIGATION_HYPERVISOR;
+		goto out;
+	}
+
+	if (cpu_mitigations_off())
+		gds_mitigation = GDS_MITIGATION_OFF;
+	/* Will verify below that mitigation _can_ be disabled */
+
+	/* No microcode */
+	if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) {
+		if (gds_mitigation == GDS_MITIGATION_FORCE) {
+			/*
+			 * This only needs to be done on the boot CPU so do it
+			 * here rather than in update_gds_msr()
+			 */
+			setup_clear_cpu_cap(X86_FEATURE_AVX);
+			pr_warn("Microcode update needed! Disabling AVX as mitigation.\n");
+		} else {
+			gds_mitigation = GDS_MITIGATION_UCODE_NEEDED;
+		}
+		goto out;
+	}
+
+	/* Microcode has mitigation, use it */
+	if (gds_mitigation == GDS_MITIGATION_FORCE)
+		gds_mitigation = GDS_MITIGATION_FULL;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	if (mcu_ctrl & GDS_MITG_LOCKED) {
+		if (gds_mitigation == GDS_MITIGATION_OFF)
+			pr_warn("Mitigation locked. Disable failed.\n");
+
+		/*
+		 * The mitigation is selected from the boot CPU. All other CPUs
+		 * _should_ have the same state. If the boot CPU isn't locked
+		 * but others are then update_gds_msr() will WARN() of the state
+		 * mismatch. If the boot CPU is locked update_gds_msr() will
+		 * ensure the other CPUs have the mitigation enabled.
+		 */
+		gds_mitigation = GDS_MITIGATION_FULL_LOCKED;
+	}
+
+	update_gds_msr();
+out:
+	pr_info("%s\n", gds_strings[gds_mitigation]);
+}
+
+static int __init gds_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!boot_cpu_has_bug(X86_BUG_GDS))
+		return 0;
+
+	if (!strcmp(str, "off"))
+		gds_mitigation = GDS_MITIGATION_OFF;
+	else if (!strcmp(str, "force"))
+		gds_mitigation = GDS_MITIGATION_FORCE;
+
+	return 0;
+}
+early_param("gather_data_sampling", gds_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V1 : " fmt
 
 enum spectre_v1_mitigation {
@@ -2196,6 +2292,11 @@ static ssize_t retbleed_show_state(char *buf)
 	return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]);
 }
 
+static ssize_t gds_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -2245,6 +2346,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_RETBLEED:
 		return retbleed_show_state(buf);
 
+	case X86_BUG_GDS:
+		return gds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -2309,4 +2413,9 @@ ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, cha
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED);
 }
+
+ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_GDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ec324be00..d315e928b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -13,14 +13,20 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/task.h>
+#include <linux/sched/smt.h>
 #include <linux/init.h>
 #include <linux/kprobes.h>
 #include <linux/kgdb.h>
+#include <linux/mem_encrypt.h>
 #include <linux/smp.h>
+#include <linux/cpu.h>
 #include <linux/io.h>
 #include <linux/syscore_ops.h>
 
 #include <asm/stackprotector.h>
+#include <linux/utsname.h>
+
+#include <asm/alternative.h>
 #include <asm/perf_event.h>
 #include <asm/mmu_context.h>
 #include <asm/archrandom.h>
@@ -56,6 +62,7 @@
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/uv/uv.h>
 #endif
+#include <asm/set_memory.h>
 
 #include "cpu.h"
 
@@ -1040,6 +1047,12 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define MMIO_SBDS	BIT(2)
 /* CPU is affected by RETbleed, speculating where you would not expect it */
 #define RETBLEED	BIT(3)
+/* CPU is affected by SMT (cross-thread) return predictions */
+#define SMT_RSB		BIT(4)
+/* CPU is affected by SRSO */
+#define SRSO		BIT(5)
+/* CPU is affected by GDS */
+#define GDS		BIT(6)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
@@ -1052,18 +1065,20 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(BROADWELL_X,	X86_STEPPING_ANY,		MMIO),
 	VULNBL_INTEL_STEPPINGS(BROADWELL_CORE,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(SKYLAKE_MOBILE,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	X86_STEPPING_ANY,		MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS),
 	VULNBL_INTEL_STEPPINGS(SKYLAKE_DESKTOP,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE_MOBILE,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE_DESKTOP,X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_MOBILE,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED | GDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_DESKTOP,X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED | GDS),
 	VULNBL_INTEL_STEPPINGS(CANNONLAKE_MOBILE,X86_STEPPING_ANY,		RETBLEED),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_MOBILE,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_XEON_D,	X86_STEPPING_ANY,		MMIO),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPING_ANY,		MMIO),
-	VULNBL_INTEL_STEPPINGS(COMETLAKE,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_MOBILE,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_XEON_D,	X86_STEPPING_ANY,		MMIO | GDS),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPING_ANY,		MMIO | GDS),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
+	VULNBL_INTEL_STEPPINGS(TIGERLAKE_L,	X86_STEPPING_ANY,		GDS),
+	VULNBL_INTEL_STEPPINGS(TIGERLAKE,	X86_STEPPING_ANY,		GDS),
 	VULNBL_INTEL_STEPPINGS(LAKEFIELD,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPING_ANY,		MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS),
 	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
 	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_X,	X86_STEPPING_ANY,		MMIO),
 	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
@@ -1186,6 +1201,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	    !(ia32_cap & ARCH_CAP_PBRSB_NO))
 		setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
 
+	/*
+	 * Check if CPU is vulnerable to GDS. If running in a virtual machine on
+	 * an affected processor, the VMM may have disabled the use of GATHER by
+	 * disabling AVX2. The only way to do this in HW is to clear XCR0[2],
+	 * which means that AVX will be disabled.
+	 */
+	if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) &&
+	    boot_cpu_has(X86_FEATURE_AVX))
+		setup_force_cpu_bug(X86_BUG_GDS);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
@@ -1271,8 +1296,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 	cpu_set_bug_bits(c);
 
-	fpu__init_system(c);
-
 #ifdef CONFIG_X86_32
 	/*
 	 * Regardless of whether PCID is enumerated, the SDM says
@@ -1661,6 +1684,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 	validate_apic_and_package_id(c);
 	x86_spec_ctrl_setup_ap();
 	update_srbds_msr();
+	if (boot_cpu_has_bug(X86_BUG_GDS))
+		update_gds_msr();
 }
 
 static __init int setup_noclflush(char *arg)
@@ -1978,8 +2003,6 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu__init_cpu();
-
 	if (is_uv_system())
 		uv_cpu_init();
 
@@ -2043,8 +2066,6 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu__init_cpu();
-
 	load_fixmap_gdt(cpu);
 }
 #endif
@@ -2097,3 +2118,69 @@ void microcode_check(void)
 	pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
 	pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
 }
+
+void __init arch_cpu_finalize_init(void)
+{
+	identify_boot_cpu();
+
+	/*
+	 * identify_boot_cpu() initialized SMT support information, let the
+	 * core code know.
+	 */
+	cpu_smt_check_topology();
+
+	if (!IS_ENABLED(CONFIG_SMP)) {
+		pr_info("CPU: ");
+		print_cpu_info(&boot_cpu_data);
+	}
+
+	cpu_select_mitigations();
+
+	arch_smt_update();
+
+	if (IS_ENABLED(CONFIG_X86_32)) {
+		/*
+		 * Check whether this is a real i386 which is not longer
+		 * supported and fixup the utsname.
+		 */
+		if (boot_cpu_data.x86 < 4)
+			panic("Kernel requires i486+ for 'invlpg' and other features");
+
+		init_utsname()->machine[1] =
+			'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+	}
+
+	/*
+	 * Must be before alternatives because it might set or clear
+	 * feature bits.
+	 */
+	fpu__init_system();
+	fpu__init_cpu();
+
+	alternative_instructions();
+
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		/*
+		 * Make sure the first 2MB area is not mapped by huge pages
+		 * There are typically fixed size MTRRs in there and overlapping
+		 * MTRRs into large pages causes slow downs.
+		 *
+		 * Right now we don't do that with gbpages because there seems
+		 * very little benefit for that case.
+		 */
+		if (!direct_gbpages)
+			set_memory_4k((unsigned long)__va(0), 1);
+	} else {
+		fpu__init_check_bugs();
+	}
+
+	/*
+	 * This needs to be called before any devices perform DMA
+	 * operations that might use the SWIOTLB bounce buffers. It will
+	 * mark the bounce buffers as decrypted so that their usage will
+	 * not cause "plain-text" data to be decrypted when accessed. It
+	 * must be called after late_time_init() so that Hyper-V x86/x64
+	 * hypercalls work when the SWIOTLB bounce buffers are decrypted.
+	 */
+	mem_encrypt_init();
+}
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 4eb9bf68b..ca1b8bf38 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -79,9 +79,11 @@ extern void detect_ht(struct cpuinfo_x86 *c);
 extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);
+void cpu_select_mitigations(void);
 
 extern void x86_spec_ctrl_setup_ap(void);
 extern void update_srbds_msr(void);
+extern void update_gds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 71ca064e3..31fe56a90 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -44,7 +44,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
 	 * initial apic id, which also represents 32-bit extended x2apic id.
 	 */
 	c->initial_apicid = edx;
-	smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+	smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
 #endif
 	return 0;
 }
@@ -68,7 +68,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	 * Populate HT related information from sub-leaf level 0.
 	 */
 	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
-	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+	core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+	smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
 	sub_index = 1;
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 9692ccc58..644372a10 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -49,7 +49,7 @@ void fpu__init_cpu(void)
 	fpu__init_cpu_xstate();
 }
 
-static bool fpu__probe_without_cpuid(void)
+static bool __init fpu__probe_without_cpuid(void)
 {
 	unsigned long cr0;
 	u16 fsw, fcw;
@@ -67,7 +67,7 @@ static bool fpu__probe_without_cpuid(void)
 	return fsw == 0 && (fcw & 0x103f) == 0x003f;
 }
 
-static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+static void __init fpu__init_system_early_generic(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_CPUID) &&
 	    !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
@@ -297,10 +297,10 @@ static void __init fpu__init_parse_early_param(void)
  * Called on the boot CPU once per system bootup, to set up the initial
  * FPU state that is later cloned into all processes:
  */
-void __init fpu__init_system(struct cpuinfo_x86 *c)
+void __init fpu__init_system(void)
 {
 	fpu__init_parse_early_param();
-	fpu__init_system_early_generic(c);
+	fpu__init_system_early_generic();
 
 	/*
 	 * The FPU has to be operational for some of the
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 7d372db8b..e33b732ad 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -811,6 +811,14 @@ void __init fpu__init_system_xstate(void)
 	fpu__init_prepare_fx_sw_frame();
 	setup_init_fpu_buf();
 	setup_xstate_comp();
+
+	/*
+	 * CPU capabilities initialization runs before FPU init. So
+	 * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely
+	 * functional, set the feature bit so depending code works.
+	 */
+	setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
+
 	print_xstate_offset_size();
 
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 8821d0ab0..82753622f 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -32,6 +32,7 @@
  */
 static void init_8259A(int auto_eoi);
 
+static bool pcat_compat __ro_after_init;
 static int i8259A_auto_eoi;
 DEFINE_RAW_SPINLOCK(i8259A_lock);
 
@@ -301,15 +302,32 @@ static void unmask_8259A(void)
 
 static int probe_8259A(void)
 {
+	unsigned char new_val, probe_val = ~(1 << PIC_CASCADE_IR);
 	unsigned long flags;
-	unsigned char probe_val = ~(1 << PIC_CASCADE_IR);
-	unsigned char new_val;
+
+	/*
+	 * If MADT has the PCAT_COMPAT flag set, then do not bother probing
+	 * for the PIC. Some BIOSes leave the PIC uninitialized and probing
+	 * fails.
+	 *
+	 * Right now this causes problems as quite some code depends on
+	 * nr_legacy_irqs() > 0 or has_legacy_pic() == true. This is silly
+	 * when the system has an IO/APIC because then PIC is not required
+	 * at all, except for really old machines where the timer interrupt
+	 * must be routed through the PIC. So just pretend that the PIC is
+	 * there and let legacy_pic->init() initialize it for nothing.
+	 *
+	 * Alternatively this could just try to initialize the PIC and
+	 * repeat the probe, but for cases where there is no PIC that's
+	 * just pointless.
+	 */
+	if (pcat_compat)
+		return nr_legacy_irqs();
+
 	/*
-	 * Check to see if we have a PIC.
-	 * Mask all except the cascade and read
-	 * back the value we just wrote. If we don't
-	 * have a PIC, we will read 0xff as opposed to the
-	 * value we wrote.
+	 * Check to see if we have a PIC.  Mask all except the cascade and
+	 * read back the value we just wrote. If we don't have a PIC, we
+	 * will read 0xff as opposed to the value we wrote.
 	 */
 	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
@@ -431,5 +449,9 @@ static int __init i8259A_init_ops(void)
 
 	return 0;
 }
-
 device_initcall(i8259A_init_ops);
+
+void __init legacy_pic_pcat_compat(void)
+{
+	pcat_compat = true;
+}
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 736348ead..2ecf1dcc8 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -96,7 +96,7 @@ static void ich_force_hpet_resume(void)
 static void ich_force_enable_hpet(struct pci_dev *dev)
 {
 	u32 val;
-	u32 uninitialized_var(rcba);
+	u32 rcba;
 	int err = 0;
 
 	if (hpet_address || force_hpet_address)
@@ -186,7 +186,7 @@ static void hpet_print_force_info(void)
 static void old_ich_force_hpet_resume(void)
 {
 	u32 val;
-	u32 uninitialized_var(gen_cntl);
+	u32 gen_cntl;
 
 	if (!force_hpet_address || !cached_dev)
 		return;
@@ -208,7 +208,7 @@ static void old_ich_force_hpet_resume(void)
 static void old_ich_force_enable_hpet(struct pci_dev *dev)
 {
 	u32 val;
-	u32 uninitialized_var(gen_cntl);
+	u32 gen_cntl;
 
 	if (hpet_address || force_hpet_address)
 		return;
@@ -299,7 +299,7 @@ static void vt8237_force_hpet_resume(void)
 
 static void vt8237_force_enable_hpet(struct pci_dev *dev)
 {
-	u32 uninitialized_var(val);
+	u32 val;
 
 	if (hpet_address || force_hpet_address)
 		return;
@@ -430,7 +430,7 @@ static void nvidia_force_hpet_resume(void)
 
 static void nvidia_force_enable_hpet(struct pci_dev *dev)
 {
-	u32 uninitialized_var(val);
+	u32 val;
 
 	if (hpet_address || force_hpet_address)
 		return;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8783d065f..2e4f6a1eb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -96,6 +96,17 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
+struct mwait_cpu_dead {
+	unsigned int	control;
+	unsigned int	status;
+};
+
+/*
+ * Cache line aligned data for mwait_play_dead(). Separate on purpose so
+ * that it's unlikely to be touched by other CPUs.
+ */
+static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead);
+
 /* Logical package management. We might want to allocate that dynamically */
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
@@ -231,6 +242,7 @@ static void notrace start_secondary(void *unused)
 #endif
 	load_current_idt();
 	cpu_init();
+	fpu__init_cpu();
 	x86_cpuinit.early_percpu_clock_init();
 	preempt_disable();
 	smp_callin();
@@ -1594,10 +1606,10 @@ static bool wakeup_cpu0(void)
  */
 static inline void mwait_play_dead(void)
 {
+	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
 	unsigned int eax, ebx, ecx, edx;
 	unsigned int highest_cstate = 0;
 	unsigned int highest_subcstate = 0;
-	void *mwait_ptr;
 	int i;
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
@@ -1631,13 +1643,6 @@ static inline void mwait_play_dead(void)
 			(highest_subcstate - 1);
 	}
 
-	/*
-	 * This should be a memory location in a cache line which is
-	 * unlikely to be touched by other processors.  The actual
-	 * content is immaterial as it is not actually modified in any way.
-	 */
-	mwait_ptr = &current_thread_info()->flags;
-
 	wbinvd();
 
 	while (1) {
@@ -1649,9 +1654,9 @@ static inline void mwait_play_dead(void)
 		 * case where we return around the loop.
 		 */
 		mb();
-		clflush(mwait_ptr);
+		clflush(md);
 		mb();
-		__monitor(mwait_ptr, 0, 0);
+		__monitor(md, 0, 0);
 		mb();
 		__mwait(eax, 0);
 		/*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 34c0652ca..20d09355c 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -383,7 +383,7 @@ SECTIONS
 	.brk : AT(ADDR(.brk) - LOAD_OFFSET) {
 		__brk_base = .;
 		. += 64 * 1024;		/* 64k alignment slop space */
-		*(.brk_reservation)	/* areas brk users have reserved */
+		*(.bss..brk)		/* areas brk users have reserved */
 		__brk_limit = .;
 	}