21 files changed, 112 insertions, 68 deletions

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 66ca906aa790..801ecd1c3fd5 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1226,7 +1226,7 @@ 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/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/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/e820.c b/arch/x86/kernel/e820.c
index e69408bf664b..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)
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/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/kvm.c b/arch/x86/kernel/kvm.c
index 82caf01b63dd..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;
 	}
@@ -838,6 +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/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/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 71691a8310e7..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
 	}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 259d1d2be076..fdbd47ceb84d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1368,8 +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();
@@ -1399,6 +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 4f36d3241faf..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;
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 87095a477154..4bb0f8447112 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -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
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