Merge branch master from git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git

Pick up the spectre documentation so the Grand Schemozzle can be added.

38 files changed, 436 insertions, 189 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 99ef8b6f9a1a..ccd32013c47a 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -625,10 +625,23 @@ extern struct paravirt_patch_site __start_parainstructions[],
  *
  * See entry_{32,64}.S for more details.
  */
-static void __init int3_magic(unsigned int *ptr)
-{
-	*ptr = 1;
-}
+
+/*
+ * We define the int3_magic() function in assembly to control the calling
+ * convention such that we can 'call' it from assembly.
+ */
+
+extern void int3_magic(unsigned int *ptr); /* defined in asm */
+
+asm (
+"	.pushsection	.init.text, \"ax\", @progbits\n"
+"	.type		int3_magic, @function\n"
+"int3_magic:\n"
+"	movl	$1, (%" _ASM_ARG1 ")\n"
+"	ret\n"
+"	.size		int3_magic, .-int3_magic\n"
+"	.popsection\n"
+);
 
 extern __initdata unsigned long int3_selftest_ip; /* defined in asm below */
 
@@ -676,7 +689,9 @@ static void __init int3_selftest(void)
 		      "int3_selftest_ip:\n\t"
 		      __ASM_SEL(.long, .quad) " 1b\n\t"
 		      ".popsection\n\t"
-		      : : __ASM_SEL_RAW(a, D) (&val) : "memory");
+		      : ASM_CALL_CONSTRAINT
+		      : __ASM_SEL_RAW(a, D) (&val)
+		      : "memory");
 
 	BUG_ON(val != 1);
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 1bd91cb7b320..f5291362da1a 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -183,7 +183,7 @@ EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
 /*
  * Debug level, exported for io_apic.c
  */
-unsigned int apic_verbosity;
+int apic_verbosity;
 
 int pic_mode;
 
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index da64452584b0..5c7ee3df4d0b 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -76,6 +76,7 @@ static void __used common(void)
 	BLANK();
 	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
 	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
+	OFFSET(XEN_vcpu_info_arch_cr2, vcpu_info, arch.cr2);
 #endif
 
 	BLANK();
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 6383f0db098c..c6fa3ef10b4e 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1313,7 +1313,7 @@ static ssize_t l1tf_show_state(char *buf)
 
 static ssize_t mds_show_state(char *buf)
 {
-	if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
 		return sprintf(buf, "%s; SMT Host state unknown\n",
 			       mds_strings[mds_mitigation]);
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 300dcf00d287..f125bf7ecb6f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -366,10 +366,62 @@ out:
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
-DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
-EXPORT_SYMBOL(cr_pinning);
-unsigned long cr4_pinned_bits __ro_after_init;
-EXPORT_SYMBOL(cr4_pinned_bits);
+static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
+static unsigned long cr4_pinned_bits __ro_after_init;
+
+void native_write_cr0(unsigned long val)
+{
+	unsigned long bits_missing = 0;
+
+set_register:
+	asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order));
+
+	if (static_branch_likely(&cr_pinning)) {
+		if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) {
+			bits_missing = X86_CR0_WP;
+			val |= bits_missing;
+			goto set_register;
+		}
+		/* Warn after we've set the missing bits. */
+		WARN_ONCE(bits_missing, "CR0 WP bit went missing!?\n");
+	}
+}
+EXPORT_SYMBOL(native_write_cr0);
+
+void native_write_cr4(unsigned long val)
+{
+	unsigned long bits_missing = 0;
+
+set_register:
+	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
+
+	if (static_branch_likely(&cr_pinning)) {
+		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
+			bits_missing = ~val & cr4_pinned_bits;
+			val |= bits_missing;
+			goto set_register;
+		}
+		/* Warn after we've set the missing bits. */
+		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
+			  bits_missing);
+	}
+}
+EXPORT_SYMBOL(native_write_cr4);
+
+void cr4_init(void)
+{
+	unsigned long cr4 = __read_cr4();
+
+	if (boot_cpu_has(X86_FEATURE_PCID))
+		cr4 |= X86_CR4_PCIDE;
+	if (static_branch_likely(&cr_pinning))
+		cr4 |= cr4_pinned_bits;
+
+	__write_cr4(cr4);
+
+	/* Initialize cr4 shadow for this CPU. */
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+}
 
 /*
  * Once CPU feature detection is finished (and boot params have been
@@ -1735,12 +1787,6 @@ void cpu_init(void)
 
 	wait_for_master_cpu(cpu);
 
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
-
 	if (cpu)
 		load_ucode_ap();
 
@@ -1835,12 +1881,6 @@ void cpu_init(void)
 
 	wait_for_master_cpu(cpu);
 
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
-
 	show_ucode_info_early();
 
 	pr_info("Initializing CPU#%d\n", cpu);
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 87e39ad8d873..553bfbfc3a1b 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -26,14 +26,6 @@
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 
-extern const struct hypervisor_x86 x86_hyper_vmware;
-extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
-extern const struct hypervisor_x86 x86_hyper_xen_pv;
-extern const struct hypervisor_x86 x86_hyper_xen_hvm;
-extern const struct hypervisor_x86 x86_hyper_kvm;
-extern const struct hypervisor_x86 x86_hyper_jailhouse;
-extern const struct hypervisor_x86 x86_hyper_acrn;
-
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
 #ifdef CONFIG_XEN_PV
@@ -58,6 +50,14 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] =
 enum x86_hypervisor_type x86_hyper_type;
 EXPORT_SYMBOL(x86_hyper_type);
 
+bool __initdata nopv;
+static __init int parse_nopv(char *arg)
+{
+	nopv = true;
+	return 0;
+}
+early_param("nopv", parse_nopv);
+
 static inline const struct hypervisor_x86 * __init
 detect_hypervisor_vendor(void)
 {
@@ -65,6 +65,9 @@ detect_hypervisor_vendor(void)
 	uint32_t pri, max_pri = 0;
 
 	for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) {
+		if (unlikely(nopv) && !(*p)->ignore_nopv)
+			continue;
+
 		pri = (*p)->detect();
 		if (pri > max_pri) {
 			max_pri = pri;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 066562a1ea20..743370ee4983 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1348,7 +1348,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		local_irq_enable();
 
 		if (kill_it || do_memory_failure(&m))
-			force_sig(SIGBUS, current);
+			force_sig(SIGBUS);
 		local_irq_disable();
 		ist_end_non_atomic();
 	} else {
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 4ddadf672ab5..a0e52bd00ecc 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -59,7 +59,7 @@ static u8 amd_ucode_patch[PATCH_MAX_SIZE];
 
 /*
  * Microcode patch container file is prepended to the initrd in cpio
- * format. See Documentation/x86/microcode.txt
+ * format. See Documentation/x86/microcode.rst
  */
 static const char
 ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index bf3034994754..a46dee8e78db 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2104,8 +2104,7 @@ static int rdt_init_fs_context(struct fs_context *fc)
 	ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
 	fc->fs_private = &ctx->kfc;
 	fc->ops = &rdt_fs_context_ops;
-	if (fc->user_ns)
-		put_user_ns(fc->user_ns);
+	put_user_ns(fc->user_ns);
 	fc->user_ns = get_user_ns(&init_user_ns);
 	fc->global = true;
 	return 0;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a55094b5f452..2bf70a2fed90 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -375,6 +375,12 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 	walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
 			memmap_entry_callback);
 
+	/* Add e820 reserved ranges */
+	cmd.type = E820_TYPE_RESERVED;
+	flags = IORESOURCE_MEM;
+	walk_iomem_res_desc(IORES_DESC_RESERVED, flags, 0, -1, &cmd,
+			   memmap_entry_callback);
+
 	/* Add crashk_low_res region */
 	if (crashk_low_res.end) {
 		ei.addr = crashk_low_res.start;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 8f32e705a980..7da2bcd2b8eb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -86,9 +86,9 @@ static bool _e820__mapped_any(struct e820_table *table,
 			continue;
 		if (entry->addr >= end || entry->addr + entry->size <= start)
 			continue;
-		return 1;
+		return true;
 	}
-	return 0;
+	return false;
 }
 
 bool e820__mapped_raw_any(u64 start, u64 end, enum e820_type type)
@@ -1063,10 +1063,10 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
 	case E820_TYPE_NVS:		return IORES_DESC_ACPI_NV_STORAGE;
 	case E820_TYPE_PMEM:		return IORES_DESC_PERSISTENT_MEMORY;
 	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
+	case E820_TYPE_RESERVED:	return IORES_DESC_RESERVED;
 	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		/* Fall-through: */
 	case E820_TYPE_UNUSABLE:	/* Fall-through: */
-	case E820_TYPE_RESERVED:	/* Fall-through: */
 	default:			return IORES_DESC_NONE;
 	}
 }
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 4b73f5937f41..024c3053dbba 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -373,7 +373,7 @@ static int add_brk_on_nop(struct dyn_ftrace *rec)
 	return add_break(rec->ip, old);
 }
 
-static int add_breakpoints(struct dyn_ftrace *rec, int enable)
+static int add_breakpoints(struct dyn_ftrace *rec, bool enable)
 {
 	unsigned long ftrace_addr;
 	int ret;
@@ -481,7 +481,7 @@ static int add_update_nop(struct dyn_ftrace *rec)
 	return add_update_code(ip, new);
 }
 
-static int add_update(struct dyn_ftrace *rec, int enable)
+static int add_update(struct dyn_ftrace *rec, bool enable)
 {
 	unsigned long ftrace_addr;
 	int ret;
@@ -527,7 +527,7 @@ static int finish_update_nop(struct dyn_ftrace *rec)
 	return ftrace_write(ip, new, 1);
 }
 
-static int finish_update(struct dyn_ftrace *rec, int enable)
+static int finish_update(struct dyn_ftrace *rec, bool enable)
 {
 	unsigned long ftrace_addr;
 	int ret;
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index bcd206c8ac90..f3d3e9646a99 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -29,9 +29,7 @@
 #ifdef CONFIG_PARAVIRT_XXL
 #include <asm/asm-offsets.h>
 #include <asm/paravirt.h>
-#define GET_CR2_INTO(reg) GET_CR2_INTO_RAX ; movq %rax, reg
 #else
-#define GET_CR2_INTO(reg) movq %cr2, reg
 #define INTERRUPT_RETURN iretq
 #endif
 
@@ -195,10 +193,10 @@ ENTRY(secondary_startup_64)
 
 	/* Set up %gs.
 	 *
-	 * The base of %gs always points to the bottom of the irqstack
-	 * union.  If the stack protector canary is enabled, it is
-	 * located at %gs:40.  Note that, on SMP, the boot cpu uses
-	 * init data section till per cpu areas are set up.
+	 * The base of %gs always points to fixed_percpu_data. If the
+	 * stack protector canary is enabled, it is located at %gs:40.
+	 * Note that, on SMP, the boot cpu uses init data section until
+	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
 	movl	initial_gs(%rip),%eax
@@ -253,10 +251,10 @@ END(secondary_startup_64)
  * start_secondary() via .Ljump_to_C_code.
  */
 ENTRY(start_cpu0)
-	movq	initial_stack(%rip), %rsp
 	UNWIND_HINT_EMPTY
+	movq	initial_stack(%rip), %rsp
 	jmp	.Ljump_to_C_code
-ENDPROC(start_cpu0)
+END(start_cpu0)
 #endif
 
 	/* Both SMP bootup and ACPI suspend change these variables */
@@ -323,7 +321,7 @@ early_idt_handler_common:
 
 	cmpq $14,%rsi		/* Page fault? */
 	jnz 10f
-	GET_CR2_INTO(%rdi)	/* Can clobber any volatile register if pv */
+	GET_CR2_INTO(%rdi)	/* can clobber %rax if pv */
 	call early_make_pgtable
 	andl %eax,%eax
 	jz 20f			/* All good */
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index c43e96a938d0..c6f791bc481e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -827,10 +827,6 @@ int __init hpet_enable(void)
 	if (!hpet_cfg_working())
 		goto out_nohpet;
 
-	/* Validate that the counter is counting */
-	if (!hpet_counting())
-		goto out_nohpet;
-
 	/*
 	 * Read the period and check for a sane value:
 	 */
@@ -896,6 +892,14 @@ int __init hpet_enable(void)
 	}
 	hpet_print_config();
 
+	/*
+	 * Validate that the counter is counting. This needs to be done
+	 * after sanitizing the config registers to properly deal with
+	 * force enabled HPETs.
+	 */
+	if (!hpet_counting())
+		goto out_nohpet;
+
 	clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq);
 
 	if (id & HPET_ID_LEGSUP) {
diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c
index 64b973f0e985..4c407833faca 100644
--- a/arch/x86/kernel/ima_arch.c
+++ b/arch/x86/kernel/ima_arch.c
@@ -11,10 +11,11 @@ extern struct boot_params boot_params;
 static enum efi_secureboot_mode get_sb_mode(void)
 {
 	efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
+	efi_char16_t efi_SetupMode_name[] = L"SecureBoot";
 	efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
 	efi_status_t status;
 	unsigned long size;
-	u8 secboot;
+	u8 secboot, setupmode;
 
 	size = sizeof(secboot);
 
@@ -36,7 +37,14 @@ static enum efi_secureboot_mode get_sb_mode(void)
 		return efi_secureboot_mode_unknown;
 	}
 
-	if (secboot == 0) {
+	size = sizeof(setupmode);
+	status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid,
+				  NULL, &size, &setupmode);
+
+	if (status != EFI_SUCCESS)	/* ignore unknown SetupMode */
+		setupmode = 0;
+
+	if (secboot == 0 || setupmode == 1) {
 		pr_info("ima: secureboot mode disabled\n");
 		return efi_secureboot_mode_disabled;
 	}
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index 838cf8a32c49..1cb3ca9bba49 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -65,8 +65,6 @@ static int sched_itmt_update_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-static unsigned int zero;
-static unsigned int one = 1;
 static struct ctl_table itmt_kern_table[] = {
 	{
 		.procname	= "sched_itmt_enabled",
@@ -74,8 +72,8 @@ static struct ctl_table itmt_kern_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= sched_itmt_update_handler,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{}
 };
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 6857b4577f17..3ad34f01de2a 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -217,4 +217,5 @@ const struct hypervisor_x86 x86_hyper_jailhouse __refconst = {
 	.detect			= jailhouse_detect,
 	.init.init_platform	= jailhouse_init_platform,
 	.init.x2apic_available	= jailhouse_x2apic_available,
+	.ignore_nopv		= true,
 };
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 7670ac2bda3a..edaa30b20841 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -67,33 +67,18 @@ static const struct file_operations fops_setup_data = {
 	.llseek		= default_llseek,
 };
 
-static int __init
+static void __init
 create_setup_data_node(struct dentry *parent, int no,
 		       struct setup_data_node *node)
 {
-	struct dentry *d, *type, *data;
+	struct dentry *d;
 	char buf[16];
 
 	sprintf(buf, "%d", no);
 	d = debugfs_create_dir(buf, parent);
-	if (!d)
-		return -ENOMEM;
-
-	type = debugfs_create_x32("type", S_IRUGO, d, &node->type);
-	if (!type)
-		goto err_dir;
-
-	data = debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data);
-	if (!data)
-		goto err_type;
 
-	return 0;
-
-err_type:
-	debugfs_remove(type);
-err_dir:
-	debugfs_remove(d);
-	return -ENOMEM;
+	debugfs_create_x32("type", S_IRUGO, d, &node->type);
+	debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data);
 }
 
 static int __init create_setup_data_nodes(struct dentry *parent)
@@ -106,8 +91,6 @@ static int __init create_setup_data_nodes(struct dentry *parent)
 	int no = 0;
 
 	d = debugfs_create_dir("setup_data", parent);
-	if (!d)
-		return -ENOMEM;
 
 	pa_data = boot_params.hdr.setup_data;
 
@@ -128,19 +111,17 @@ static int __init create_setup_data_nodes(struct dentry *parent)
 		node->paddr = pa_data;
 		node->type = data->type;
 		node->len = data->len;
-		error = create_setup_data_node(d, no, node);
+		create_setup_data_node(d, no, node);
 		pa_data = data->next;
 
 		memunmap(data);
-		if (error)
-			goto err_dir;
 		no++;
 	}
 
 	return 0;
 
 err_dir:
-	debugfs_remove(d);
+	debugfs_remove_recursive(d);
 	return error;
 }
 
@@ -151,35 +132,18 @@ static struct debugfs_blob_wrapper boot_params_blob = {
 
 static int __init boot_params_kdebugfs_init(void)
 {
-	struct dentry *dbp, *version, *data;
-	int error = -ENOMEM;
+	struct dentry *dbp;
+	int error;
 
 	dbp = debugfs_create_dir("boot_params", arch_debugfs_dir);
-	if (!dbp)
-		return -ENOMEM;
-
-	version = debugfs_create_x16("version", S_IRUGO, dbp,
-				     &boot_params.hdr.version);
-	if (!version)
-		goto err_dir;
 
-	data = debugfs_create_blob("data", S_IRUGO, dbp,
-				   &boot_params_blob);
-	if (!data)
-		goto err_version;
+	debugfs_create_x16("version", S_IRUGO, dbp, &boot_params.hdr.version);
+	debugfs_create_blob("data", S_IRUGO, dbp, &boot_params_blob);
 
 	error = create_setup_data_nodes(dbp);
 	if (error)
-		goto err_data;
+		debugfs_remove_recursive(dbp);
 
-	return 0;
-
-err_data:
-	debugfs_remove(data);
-err_version:
-	debugfs_remove(version);
-err_dir:
-	debugfs_remove(dbp);
 	return error;
 }
 #endif /* CONFIG_DEBUG_BOOT_PARAMS */
@@ -189,8 +153,6 @@ static int __init arch_kdebugfs_init(void)
 	int error = 0;
 
 	arch_debugfs_dir = debugfs_create_dir("x86", NULL);
-	if (!arch_debugfs_dir)
-		return -ENOMEM;
 
 #ifdef CONFIG_DEBUG_BOOT_PARAMS
 	error = boot_params_kdebugfs_init();
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index f03237e3f192..5ebcd02cbca7 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -319,6 +319,11 @@ static int bzImage64_probe(const char *buf, unsigned long len)
 		return ret;
 	}
 
+	if (!(header->xloadflags & XLF_5LEVEL) && pgtable_l5_enabled()) {
+		pr_err("bzImage cannot handle 5-level paging mode.\n");
+		return ret;
+	}
+
 	/* I've got a bzImage */
 	pr_debug("It's a relocatable bzImage64\n");
 	ret = 0;
@@ -414,7 +419,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	efi_map_offset = params_cmdline_sz;
 	efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16);
 
-	/* Copy setup header onto bootparams. Documentation/x86/boot.txt */
+	/* Copy setup header onto bootparams. Documentation/x86/boot.rst */
 	setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset;
 
 	/* Is there a limit on setup header size? */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index bd17dbb15d6a..0e0b08008b5a 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -808,7 +808,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 			continue;
 		/*
 		 * Return probes must be pushed on this hash list correct
-		 * order (same as return order) so that it can be poped
+		 * order (same as return order) so that it can be popped
 		 * correctly. However, if we find it is pushed it incorrect
 		 * order, this means we find a function which should not be
 		 * probed, because the wrong order entry is pushed on the
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5169b8cc35bb..b7f34fe2171e 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -242,23 +242,23 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
 NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason);
 
 dotraplinkage void
-do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
+do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 {
 	enum ctx_state prev_state;
 
 	switch (kvm_read_and_reset_pf_reason()) {
 	default:
-		do_page_fault(regs, error_code);
+		do_page_fault(regs, error_code, address);
 		break;
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
 		prev_state = exception_enter();
-		kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs));
+		kvm_async_pf_task_wait((u32)address, !user_mode(regs));
 		exception_exit(prev_state);
 		break;
 	case KVM_PV_REASON_PAGE_READY:
 		rcu_irq_enter();
-		kvm_async_pf_task_wake((u32)read_cr2());
+		kvm_async_pf_task_wake((u32)address);
 		rcu_irq_exit();
 		break;
 	}
@@ -527,6 +527,21 @@ static void kvm_setup_pv_ipi(void)
 	pr_info("KVM setup pv IPIs\n");
 }
 
+static void kvm_smp_send_call_func_ipi(const struct cpumask *mask)
+{
+	int cpu;
+
+	native_send_call_func_ipi(mask);
+
+	/* Make sure other vCPUs get a chance to run if they need to. */
+	for_each_cpu(cpu, mask) {
+		if (vcpu_is_preempted(cpu)) {
+			kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu));
+			break;
+		}
+	}
+}
+
 static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
 {
 	native_smp_prepare_cpus(max_cpus);
@@ -638,6 +653,12 @@ static void __init kvm_guest_init(void)
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+	if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
+	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+		smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
+		pr_info("KVM setup pv sched yield\n");
+	}
 	if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
 				      kvm_cpu_online, kvm_cpu_down_prepare) < 0)
 		pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
@@ -817,6 +838,7 @@ asm(
 "cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
 "setne	%al;"
 "ret;"
+".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
 ".popsection");
 
 #endif
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index d7be2376ac0b..5dcd438ad8f2 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/suspend.h>
 #include <linux/vmalloc.h>
+#include <linux/efi.h>
 
 #include <asm/init.h>
 #include <asm/pgtable.h>
@@ -27,6 +28,55 @@
 #include <asm/setup.h>
 #include <asm/set_memory.h>
 
+#ifdef CONFIG_ACPI
+/*
+ * Used while adding mapping for ACPI tables.
+ * Can be reused when other iomem regions need be mapped
+ */
+struct init_pgtable_data {
+	struct x86_mapping_info *info;
+	pgd_t *level4p;
+};
+
+static int mem_region_callback(struct resource *res, void *arg)
+{
+	struct init_pgtable_data *data = arg;
+	unsigned long mstart, mend;
+
+	mstart = res->start;
+	mend = mstart + resource_size(res) - 1;
+
+	return kernel_ident_mapping_init(data->info, data->level4p, mstart, mend);
+}
+
+static int
+map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p)
+{
+	struct init_pgtable_data data;
+	unsigned long flags;
+	int ret;
+
+	data.info = info;
+	data.level4p = level4p;
+	flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
+	ret = walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1,
+				  &data, mem_region_callback);
+	if (ret && ret != -EINVAL)
+		return ret;
+
+	/* ACPI tables could be located in ACPI Non-volatile Storage region */
+	ret = walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1,
+				  &data, mem_region_callback);
+	if (ret && ret != -EINVAL)
+		return ret;
+
+	return 0;
+}
+#else
+static int map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) { return 0; }
+#endif
+
 #ifdef CONFIG_KEXEC_FILE
 const struct kexec_file_ops * const kexec_file_loaders[] = {
 		&kexec_bzImage64_ops,
@@ -34,6 +84,31 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 };
 #endif
 
+static int
+map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
+{
+#ifdef CONFIG_EFI
+	unsigned long mstart, mend;
+
+	if (!efi_enabled(EFI_BOOT))
+		return 0;
+
+	mstart = (boot_params.efi_info.efi_systab |
+			((u64)boot_params.efi_info.efi_systab_hi<<32));
+
+	if (efi_enabled(EFI_64BIT))
+		mend = mstart + sizeof(efi_system_table_64_t);
+	else
+		mend = mstart + sizeof(efi_system_table_32_t);
+
+	if (!mstart)
+		return 0;
+
+	return kernel_ident_mapping_init(info, level4p, mstart, mend);
+#endif
+	return 0;
+}
+
 static void free_transition_pgtable(struct kimage *image)
 {
 	free_page((unsigned long)image->arch.p4d);
@@ -48,12 +123,13 @@ static void free_transition_pgtable(struct kimage *image)
 
 static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 {
+	pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
+	unsigned long vaddr, paddr;
+	int result = -ENOMEM;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
-	unsigned long vaddr, paddr;
-	int result = -ENOMEM;
 
 	vaddr = (unsigned long)relocate_kernel;
 	paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
@@ -90,7 +166,11 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
 	}
 	pte = pte_offset_kernel(pmd, vaddr);
-	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
+
+	if (sev_active())
+		prot = PAGE_KERNEL_EXEC;
+
+	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
 	return 0;
 err:
 	return result;
@@ -127,6 +207,11 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 	level4p = (pgd_t *)__va(start_pgtable);
 	clear_page(level4p);
 
+	if (sev_active()) {
+		info.page_flag   |= _PAGE_ENC;
+		info.kernpg_flag |= _PAGE_ENC;
+	}
+
 	if (direct_gbpages)
 		info.direct_gbpages = true;
 
@@ -157,6 +242,18 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 			return result;
 	}
 
+	/*
+	 * Prepare EFI systab and ACPI tables for kexec kernel since they are
+	 * not covered by pfn_mapped.
+	 */
+	result = map_efi_systab(&info, level4p);
+	if (result)
+		return result;
+
+	result = map_acpi_tables(&info, level4p);
+	if (result)
+		return result;
+
 	return init_transition_pgtable(image, level4p);
 }
 
@@ -557,8 +654,20 @@ void arch_kexec_unprotect_crashkres(void)
 	kexec_mark_crashkres(false);
 }
 
+/*
+ * During a traditional boot under SME, SME will encrypt the kernel,
+ * so the SME kexec kernel also needs to be un-encrypted in order to
+ * replicate a normal SME boot.
+ *
+ * During a traditional boot under SEV, the kernel has already been
+ * loaded encrypted, so the SEV kexec kernel needs to be encrypted in
+ * order to replicate a normal SEV boot.
+ */
 int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
 {
+	if (sev_active())
+		return 0;
+
 	/*
 	 * If SME is active we need to be sure that kexec pages are
 	 * not encrypted because when we boot to the new kernel the
@@ -569,6 +678,9 @@ int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
 
 void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
 {
+	if (sev_active())
+		return;
+
 	/*
 	 * If SME is active we need to reset the pages back to being
 	 * an encrypted mapping before freeing them.
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 1bfe5c6e6cfe..afac7ccce72f 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -546,17 +546,15 @@ void __init default_get_smp_config(unsigned int early)
 			 * local APIC has default address
 			 */
 			mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-			return;
+			goto out;
 		}
 
 		pr_info("Default MP configuration #%d\n", mpf->feature1);
 		construct_default_ISA_mptable(mpf->feature1);
 
 	} else if (mpf->physptr) {
-		if (check_physptr(mpf, early)) {
-			early_memunmap(mpf, sizeof(*mpf));
-			return;
-		}
+		if (check_physptr(mpf, early))
+			goto out;
 	} else
 		BUG();
 
@@ -565,7 +563,7 @@ void __init default_get_smp_config(unsigned int early)
 	/*
 	 * Only use the first configuration found.
 	 */
-
+out:
 	early_memunmap(mpf, sizeof(*mpf));
 }
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 98039d7fb998..0aa6256eedd8 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -370,7 +370,7 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.exit_mmap		= paravirt_nop,
 
 #ifdef CONFIG_PARAVIRT_XXL
-	.mmu.read_cr2		= native_read_cr2,
+	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(native_read_cr2),
 	.mmu.write_cr2		= native_write_cr2,
 	.mmu.read_cr3		= __native_read_cr3,
 	.mmu.write_cr3		= native_write_cr3,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index dcd272dbd0a9..f62b498b18fb 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -70,7 +70,7 @@ void __init pci_iommu_alloc(void)
 }
 
 /*
- * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
+ * See <Documentation/x86/x86_64/boot-options.rst> for the iommu kernel
  * parameter documentation.
  */
 static __init int iommu_setup(char *p)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 250e4c4ac6d9..af64519b2695 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -143,17 +143,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
 
 void release_thread(struct task_struct *dead_task)
 {
-	if (dead_task->mm) {
-#ifdef CONFIG_MODIFY_LDT_SYSCALL
-		if (dead_task->mm->context.ldt) {
-			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
-				dead_task->comm,
-				dead_task->mm->context.ldt->entries,
-				dead_task->mm->context.ldt->nr_entries);
-			BUG();
-		}
-#endif
-	}
+	WARN_ON(dead_task->mm);
 }
 
 enum which_selector {
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 8eb1e58de043..0fdbe89d0754 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -369,12 +369,22 @@ static int putreg(struct task_struct *child,
 	case offsetof(struct user_regs_struct,fs_base):
 		if (value >= TASK_SIZE_MAX)
 			return -EIO;
-		x86_fsbase_write_task(child, value);
+		/*
+		 * When changing the FS base, use do_arch_prctl_64()
+		 * to set the index to zero and to set the base
+		 * as requested.
+		 */
+		if (child->thread.fsbase != value)
+			return do_arch_prctl_64(child, ARCH_SET_FS, value);
 		return 0;
 	case offsetof(struct user_regs_struct,gs_base):
+		/*
+		 * Exactly the same here as the %fs handling above.
+		 */
 		if (value >= TASK_SIZE_MAX)
 			return -EIO;
-		x86_gsbase_write_task(child, value);
+		if (child->thread.gsbase != value)
+			return do_arch_prctl_64(child, ARCH_SET_GS, value);
 		return 0;
 #endif
 	}
@@ -1321,18 +1331,19 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 #endif
 }
 
-void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
-					 int error_code, int si_code)
+void send_sigtrap(struct pt_regs *regs, int error_code, int si_code)
 {
+	struct task_struct *tsk = current;
+
 	tsk->thread.trap_nr = X86_TRAP_DB;
 	tsk->thread.error_code = error_code;
 
 	/* Send us the fake SIGTRAP */
 	force_sig_fault(SIGTRAP, si_code,
-			user_mode(regs) ? (void __user *)regs->ip : NULL, tsk);
+			user_mode(regs) ? (void __user *)regs->ip : NULL);
 }
 
 void user_single_step_report(struct pt_regs *regs)
 {
-	send_sigtrap(current, regs, 0, TRAP_BRKPT);
+	send_sigtrap(regs, 0, TRAP_BRKPT);
 }
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 08a5f4a131f5..bbe35bf879f5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -453,15 +453,24 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 #define CRASH_ALIGN		SZ_16M
 
 /*
- * Keep the crash kernel below this limit.  On 32 bits earlier kernels
- * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * Keep the crash kernel below this limit.
+ *
+ * On 32 bits earlier kernels would limit the kernel to the low 512 MiB
+ * due to mapping restrictions.
+ *
+ * On 64bit, kdump kernel need be restricted to be under 64TB, which is
+ * the upper limit of system RAM in 4-level paing mode. Since the kdump
+ * jumping could be from 5-level to 4-level, the jumping will fail if
+ * kernel is put above 64TB, and there's no way to detect the paging mode
+ * of the kernel which will be loaded for dumping during the 1st kernel
+ * bootup.
  */
 #ifdef CONFIG_X86_32
 # define CRASH_ADDR_LOW_MAX	SZ_512M
 # define CRASH_ADDR_HIGH_MAX	SZ_512M
 #else
 # define CRASH_ADDR_LOW_MAX	SZ_4G
-# define CRASH_ADDR_HIGH_MAX	MAXMEM
+# define CRASH_ADDR_HIGH_MAX	SZ_64T
 #endif
 
 static int __init reserve_crashkernel_low(void)
@@ -827,8 +836,14 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 
 void __init setup_arch(char **cmdline_p)
 {
+	/*
+	 * Reserve the memory occupied by the kernel between _text and
+	 * __end_of_kernel_reserve symbols. Any kernel sections after the
+	 * __end_of_kernel_reserve symbol must be explicitly reserved with a
+	 * separate memblock_reserve() or they will be discarded.
+	 */
 	memblock_reserve(__pa_symbol(_text),
-			 (unsigned long)__bss_stop - (unsigned long)_text);
+			 (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
 
 	/*
 	 * Make sure page 0 is always reserved because on systems with
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 364813cea647..8eb7193e158d 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -391,7 +391,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		put_user_ex(&frame->uc, &frame->puc);
 
 		/* Create the ucontext.  */
-		if (boot_cpu_has(X86_FEATURE_XSAVE))
+		if (static_cpu_has(X86_FEATURE_XSAVE))
 			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
@@ -857,7 +857,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 		pr_cont("\n");
 	}
 
-	force_sig(SIGSEGV, me);
+	force_sig(SIGSEGV);
 }
 
 #ifdef CONFIG_X86_X32_ABI
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f78801114ee1..fdbd47ceb84d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -210,28 +210,16 @@ static int enable_start_cpu0;
  */
 static void notrace start_secondary(void *unused)
 {
-	unsigned long cr4 = __read_cr4();
-
 	/*
 	 * Don't put *anything* except direct CPU state initialization
 	 * before cpu_init(), SMP booting is too fragile that we want to
 	 * limit the things done here to the most necessary things.
 	 */
-	if (boot_cpu_has(X86_FEATURE_PCID))
-		cr4 |= X86_CR4_PCIDE;
-	if (static_branch_likely(&cr_pinning))
-		cr4 |= cr4_pinned_bits;
-
-	__write_cr4(cr4);
+	cr4_init();
 
 #ifdef CONFIG_X86_32
 	/* switch away from the initial page table */
 	load_cr3(swapper_pg_dir);
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
 	__flush_tlb_all();
 #endif
 	load_current_idt();
@@ -1380,8 +1368,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	pr_info("CPU0: ");
 	print_cpu_info(&cpu_data(0));
 
-	native_pv_lock_init();
-
 	uv_system_init();
 
 	set_mtrr_aps_delayed_init();
@@ -1411,6 +1397,7 @@ void __init native_smp_prepare_boot_cpu(void)
 	/* already set me in cpu_online_mask in boot_cpu_init() */
 	cpumask_set_cpu(me, cpu_callout_mask);
 	cpu_set_state_online(me);
+	native_pv_lock_init();
 }
 
 void __init calculate_max_logical_packages(void)
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 2abf27d7df6b..2d6898c2cb64 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -100,7 +100,7 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
 {
 	int ret;
 
-	if (!access_ok(fp, sizeof(*frame)))
+	if (__range_not_ok(fp, sizeof(*frame), TASK_SIZE))
 		return 0;
 
 	ret = 1;
@@ -129,11 +129,9 @@ void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
 			break;
 		if ((unsigned long)fp < regs->sp)
 			break;
-		if (frame.ret_addr) {
-			if (!consume_entry(cookie, frame.ret_addr, false))
-				return;
-		}
-		if (fp == frame.next_fp)
+		if (!frame.ret_addr)
+			break;
+		if (!consume_entry(cookie, frame.ret_addr, false))
 			break;
 		fp = frame.next_fp;
 	}
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
index 8eb67a670b10..653b7f617b61 100644
--- a/arch/x86/kernel/sysfb_efi.c
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -230,9 +230,55 @@ static const struct dmi_system_id efifb_dmi_system_table[] __initconst = {
 	{},
 };
 
+/*
+ * Some devices have a portrait LCD but advertise a landscape resolution (and
+ * pitch). We simply swap width and height for these devices so that we can
+ * correctly deal with some of them coming with multiple resolutions.
+ */
+static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = {
+	{
+		/*
+		 * Lenovo MIIX310-10ICR, only some batches have the troublesome
+		 * 800x1280 portrait screen. Luckily the portrait version has
+		 * its own BIOS version, so we match on that.
+		 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"),
+			DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"),
+		},
+	},
+	{
+		/* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+					"Lenovo MIIX 320-10ICR"),
+		},
+	},
+	{
+		/* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+					"Lenovo ideapad D330-10IGM"),
+		},
+	},
+	{},
+};
+
 __init void sysfb_apply_efi_quirks(void)
 {
 	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI ||
 	    !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS))
 		dmi_check_system(efifb_dmi_system_table);
+
+	if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI &&
+	    dmi_check_system(efifb_dmi_swap_width_height)) {
+		u16 temp = screen_info.lfb_width;
+
+		screen_info.lfb_width = screen_info.lfb_height;
+		screen_info.lfb_height = temp;
+		screen_info.lfb_linelength = 4 * screen_info.lfb_width;
+	}
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8b6d03e55d2f..4bb0f8447112 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -254,9 +254,9 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 	show_signal(tsk, signr, "trap ", str, regs, error_code);
 
 	if (!sicode)
-		force_sig(signr, tsk);
+		force_sig(signr);
 	else
-		force_sig_fault(signr, sicode, addr, tsk);
+		force_sig_fault(signr, sicode, addr);
 }
 NOKPROBE_SYMBOL(do_trap);
 
@@ -313,13 +313,10 @@ __visible void __noreturn handle_stack_overflow(const char *message,
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
-dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
+dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2)
 {
 	static const char str[] = "double fault";
 	struct task_struct *tsk = current;
-#ifdef CONFIG_VMAP_STACK
-	unsigned long cr2;
-#endif
 
 #ifdef CONFIG_X86_ESPFIX64
 	extern unsigned char native_irq_return_iret[];
@@ -415,7 +412,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 	 * stack even if the actual trigger for the double fault was
 	 * something else.
 	 */
-	cr2 = read_cr2();
 	if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE)
 		handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2);
 #endif
@@ -566,7 +562,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 
 	show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
 
-	force_sig(SIGSEGV, tsk);
+	force_sig(SIGSEGV);
 }
 NOKPROBE_SYMBOL(do_general_protection);
 
@@ -805,7 +801,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	}
 	si_code = get_si_code(tsk->thread.debugreg6);
 	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
-		send_sigtrap(tsk, regs, error_code, si_code);
+		send_sigtrap(regs, error_code, si_code);
 	cond_local_irq_disable(regs);
 	debug_stack_usage_dec();
 
@@ -856,7 +852,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 		return;
 
 	force_sig_fault(SIGFPE, si_code,
-			(void __user *)uprobe_get_trap_addr(regs), task);
+			(void __user *)uprobe_get_trap_addr(regs));
 }
 
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index f8f3cfda01ae..5b345add550f 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -277,7 +277,7 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
 	tsk->thread.error_code	= X86_PF_USER | X86_PF_WRITE;
 	tsk->thread.trap_nr	= X86_TRAP_PF;
 
-	force_sig_fault(SIGSEGV, SEGV_MAPERR, addr, tsk);
+	force_sig_fault(SIGSEGV, SEGV_MAPERR, addr);
 
 	if (!(show_unhandled_signals && unhandled_signal(tsk, SIGSEGV)))
 		return;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 918b5092a85f..d8359ebeea70 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -1074,7 +1074,7 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
 		pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
 		       current->pid, regs->sp, regs->ip);
 
-		force_sig(SIGSEGV, current);
+		force_sig(SIGSEGV);
 	}
 
 	return -1;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 6a38717d179c..a76c12b38e92 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -583,7 +583,7 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno)
 		return 1; /* we let this handle by the calling routine */
 	current->thread.trap_nr = trapno;
 	current->thread.error_code = error_code;
-	force_sig(SIGTRAP, current);
+	force_sig(SIGTRAP);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0850b5149345..e2feacf921a0 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -141,10 +141,10 @@ SECTIONS
 		*(.text.__x86.indirect_thunk)
 		__indirect_thunk_end = .;
 #endif
-	} :text = 0x9090
 
-	/* End of text section */
-	_etext = .;
+		/* End of text section */
+		_etext = .;
+	} :text = 0x9090
 
 	NOTES :text :note
 
@@ -368,6 +368,14 @@ SECTIONS
 		__bss_stop = .;
 	}
 
+	/*
+	 * The memory occupied from _text to here, __end_of_kernel_reserve, is
+	 * automatically reserved in setup_arch(). Anything after here must be
+	 * explicitly reserved using memblock_reserve() or it will be discarded
+	 * and treated as available memory.
+	 */
+	__end_of_kernel_reserve = .;
+
 	. = ALIGN(PAGE_SIZE);
 	.brk : AT(ADDR(.brk) - LOAD_OFFSET) {
 		__brk_base = .;
@@ -379,10 +387,34 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);		/* keep VO_INIT_SIZE page aligned */
 	_end = .;
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	/*
+	 * Early scratch/workarea section: Lives outside of the kernel proper
+	 * (_text - _end).
+	 *
+	 * Resides after _end because even though the .brk section is after
+	 * __end_of_kernel_reserve, the .brk section is later reserved as a
+	 * part of the kernel. Since it is located after __end_of_kernel_reserve
+	 * it will be discarded and become part of the available memory. As
+	 * such, it can only be used by very early boot code and must not be
+	 * needed afterwards.
+	 *
+	 * Currently used by SME for performing in-place encryption of the
+	 * kernel during boot. Resides on a 2MB boundary to simplify the
+	 * pagetable setup used for SME in-place encryption.
+	 */
+	. = ALIGN(HPAGE_SIZE);
+	.init.scratch : AT(ADDR(.init.scratch) - LOAD_OFFSET) {
+		__init_scratch_begin = .;
+		*(.init.scratch)
+		. = ALIGN(HPAGE_SIZE);
+		__init_scratch_end = .;
+	}
+#endif
+
 	STABS_DEBUG
 	DWARF_DEBUG
 
-	/* Sections to be discarded */
 	DISCARDS
 	/DISCARD/ : {
 		*(.eh_frame)
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 50a2b492fdd6..1bef687faf22 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -29,8 +29,8 @@ void x86_init_noop(void) { }
 void __init x86_init_uint_noop(unsigned int unused) { }
 static int __init iommu_init_noop(void) { return 0; }
 static void iommu_shutdown_noop(void) { }
-static bool __init bool_x86_init_noop(void) { return false; }
-static void x86_op_int_noop(int cpu) { }
+bool __init bool_x86_init_noop(void) { return false; }
+void x86_op_int_noop(int cpu) { }
 
 /*
  * The platform setup functions are preset with the default functions