Merge tag 'kvmarm-fixes-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm fixes for 5.3 - A bunch of switch/case fall-through annotation, fixing one actual bug - Fix PMU reset bug - Add missing exception class debug strings
author: Paolo Bonzini <pbonzini@redhat.com> 2019-08-09 16:53:39 +0200
committer: Paolo Bonzini <pbonzini@redhat.com> 2019-08-09 16:53:39 +0200
commit: 0e1c438c44dd9cde56effb44c5f1cfeda72e108d (patch)
tree: fa3492d4d7d8b7444e5d8ebe6c78210826333e4b /arch/x86
parent: c096397c78f766db972f923433031f2dec01cae0 (diff)
parent: cdb2d3ee0436d74fa9092f2df46aaa6f9e03c969 (diff)
68 files changed, 493 insertions, 504 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9df2d1cb7a9e..222855cc0158 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -70,6 +70,7 @@ config X86
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PMEM_API		if X86_64
+	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
@@ -80,7 +81,6 @@ config X86
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_HAS_ZONE_DEVICE		if X86_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
@@ -94,6 +94,7 @@ config X86
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
+	select ARCH_WANT_HUGE_PMD_SHARE
 	select ARCH_WANTS_THP_SWAP		if X86_64
 	select BUILDTIME_EXTABLE_SORT
 	select CLKEVT_I8253
@@ -307,9 +308,6 @@ config ARCH_HIBERNATION_POSSIBLE
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 
-config ARCH_WANT_HUGE_PMD_SHARE
-	def_bool y
-
 config ARCH_WANT_GENERAL_HUGETLB
 	def_bool y
 
@@ -402,7 +400,7 @@ config SMP
 	  Management" code will be disabled if you say Y here.
 
 	  See also <file:Documentation/x86/i386/IO-APIC.rst>,
-	  <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO available at
+	  <file:Documentation/admin-guide/lockup-watchdogs.rst> and the SMP-HOWTO available at
 	  <http://www.tldp.org/docs.html#howto>.
 
 	  If you don't know what to do here, say N.
@@ -1528,6 +1526,7 @@ config AMD_MEM_ENCRYPT
 	depends on X86_64 && CPU_SUP_AMD
 	select DYNAMIC_PHYSICAL_MASK
 	select ARCH_USE_MEMREMAP_PROT
+	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	---help---
 	  Say yes to enable support for the encryption of system memory.
 	  This requires an AMD processor that supports Secure Memory
@@ -1959,7 +1958,7 @@ config EFI_STUB
           This kernel feature allows a bzImage to be loaded directly
 	  by EFI firmware without the use of a bootloader.
 
-	  See Documentation/efi-stub.txt for more information.
+	  See Documentation/admin-guide/efi-stub.rst for more information.
 
 config EFI_MIXED
 	bool "EFI mixed-mode support"
@@ -2057,7 +2056,7 @@ config CRASH_DUMP
 	  to a memory address not used by the main kernel or BIOS using
 	  PHYSICAL_START, or it must be built as a relocatable image
 	  (CONFIG_RELOCATABLE=y).
-	  For more details see Documentation/kdump/kdump.rst
+	  For more details see Documentation/admin-guide/kdump/kdump.rst
 
 config KEXEC_JUMP
 	bool "kexec jump"
@@ -2094,7 +2093,7 @@ config PHYSICAL_START
 	  the reserved region.  In other words, it can be set based on
 	  the "X" value as specified in the "crashkernel=YM@XM"
 	  command line boot parameter passed to the panic-ed
-	  kernel. Please take a look at Documentation/kdump/kdump.rst
+	  kernel. Please take a look at Documentation/admin-guide/kdump/kdump.rst
 	  for more details about crash dumps.
 
 	  Usage of bzImage for capturing the crash dump is recommended as
@@ -2482,7 +2481,7 @@ menuconfig APM
 	  machines with more than one CPU.
 
 	  In order to use APM, you will need supporting software. For location
-	  and more information, read <file:Documentation/power/apm-acpi.txt>
+	  and more information, read <file:Documentation/power/apm-acpi.rst>
 	  and the Battery Powered Linux mini-HOWTO, available from
 	  <http://www.tldp.org/docs.html#howto>.
 
@@ -2733,6 +2732,7 @@ config OLPC
 	select OF
 	select OF_PROMTREE
 	select IRQ_DOMAIN
+	select OLPC_EC
 	---help---
 	  Add support for detecting the unique features of the OLPC
 	  XO hardware.
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 220d1279d0e2..d6662fdef300 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -384,14 +384,11 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	struct apm_bios_info *bi;
 	struct setup_header *hdr;
 	efi_loaded_image_t *image;
-	void *options, *handle;
+	void *handle;
 	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
 	int options_size = 0;
 	efi_status_t status;
 	char *cmdline_ptr;
-	u16 *s2;
-	u8 *s1;
-	int i;
 	unsigned long ramdisk_addr;
 	unsigned long ramdisk_size;
 
@@ -494,8 +491,6 @@ static void add_e820ext(struct boot_params *params,
 			struct setup_data *e820ext, u32 nr_entries)
 {
 	struct setup_data *data;
-	efi_status_t status;
-	unsigned long size;
 
 	e820ext->type = SETUP_E820_EXT;
 	e820ext->len  = nr_entries * sizeof(struct boot_e820_entry);
@@ -677,8 +672,6 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 				   void *priv)
 {
 	const char *signature;
-	__u32 nr_desc;
-	efi_status_t status;
 	struct exit_boot_struct *p = priv;
 
 	signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE
@@ -747,7 +740,6 @@ struct boot_params *
 efi_main(struct efi_config *c, struct boot_params *boot_params)
 {
 	struct desc_ptr *gdt = NULL;
-	efi_loaded_image_t *image;
 	struct setup_header *hdr = &boot_params->hdr;
 	efi_status_t status;
 	struct desc_struct *desc;
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 24e65a0f756d..53ac0cb2396d 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -17,6 +17,7 @@
 #include "pgtable.h"
 #include "../string.h"
 #include "../voffset.h"
+#include <asm/bootparam_utils.h>
 
 /*
  * WARNING!!
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index d2f184165934..c8181392f70d 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -23,7 +23,6 @@
 #include <asm/page.h>
 #include <asm/boot.h>
 #include <asm/bootparam.h>
-#include <asm/bootparam_utils.h>
 
 #define BOOT_CTYPE_H
 #include <linux/acpi.h>
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index f8debf7aeb4c..5f2d03067ae5 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -40,7 +40,6 @@ int cmdline_find_option_bool(const char *option);
 static unsigned long find_trampoline_placement(void)
 {
 	unsigned long bios_start = 0, ebda_start = 0;
-	unsigned long trampoline_start;
 	struct boot_e820_entry *entry;
 	char *signature;
 	int i;
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 9f1f9e3b8230..830bd984182b 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -343,3 +343,9 @@ For 32-bit we have the following conventions - kernel is built with
 .Lafter_call_\@:
 #endif
 .endm
+
+#ifdef CONFIG_PARAVIRT_XXL
+#define GET_CR2_INTO(reg) GET_CR2_INTO_AX ; _ASM_MOV %_ASM_AX, reg
+#else
+#define GET_CR2_INTO(reg) _ASM_MOV %cr2, reg
+#endif
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 90b473297299..2bb986f305ac 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -294,9 +294,11 @@
 .Lfinished_frame_\@:
 .endm
 
-.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0
 	cld
+.if \skip_gs == 0
 	PUSH_GS
+.endif
 	FIXUP_FRAME
 	pushl	%fs
 	pushl	%es
@@ -313,13 +315,13 @@
 	movl	%edx, %es
 	movl	$(__KERNEL_PERCPU), %edx
 	movl	%edx, %fs
+.if \skip_gs == 0
 	SET_KERNEL_GS %edx
-
+.endif
 	/* Switch to kernel stack if necessary */
 .if \switch_stacks > 0
 	SWITCH_TO_KERNEL_STACK
 .endif
-
 .endm
 
 .macro SAVE_ALL_NMI cr3_reg:req
@@ -1441,39 +1443,46 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR,
 
 ENTRY(page_fault)
 	ASM_CLAC
-	pushl	$do_page_fault
-	ALIGN
-	jmp common_exception
+	pushl	$0; /* %gs's slot on the stack */
+
+	SAVE_ALL switch_stacks=1 skip_gs=1
+
+	ENCODE_FRAME_POINTER
+	UNWIND_ESPFIX_STACK
+
+	/* fixup %gs */
+	GS_TO_REG %ecx
+	REG_TO_PTGS %ecx
+	SET_KERNEL_GS %ecx
+
+	GET_CR2_INTO(%ecx)			# might clobber %eax
+
+	/* fixup orig %eax */
+	movl	PT_ORIG_EAX(%esp), %edx		# get the error code
+	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
+
+	TRACE_IRQS_OFF
+	movl	%esp, %eax			# pt_regs pointer
+	call	do_page_fault
+	jmp	ret_from_exception
 END(page_fault)
 
 common_exception:
 	/* the function address is in %gs's slot on the stack */
-	FIXUP_FRAME
-	pushl	%fs
-	pushl	%es
-	pushl	%ds
-	pushl	%eax
-	movl	$(__USER_DS), %eax
-	movl	%eax, %ds
-	movl	%eax, %es
-	movl	$(__KERNEL_PERCPU), %eax
-	movl	%eax, %fs
-	pushl	%ebp
-	pushl	%edi
-	pushl	%esi
-	pushl	%edx
-	pushl	%ecx
-	pushl	%ebx
-	SWITCH_TO_KERNEL_STACK
+	SAVE_ALL switch_stacks=1 skip_gs=1
 	ENCODE_FRAME_POINTER
-	cld
 	UNWIND_ESPFIX_STACK
+
+	/* fixup %gs */
 	GS_TO_REG %ecx
 	movl	PT_GS(%esp), %edi		# get the function address
-	movl	PT_ORIG_EAX(%esp), %edx		# get the error code
-	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
 	REG_TO_PTGS %ecx
 	SET_KERNEL_GS %ecx
+
+	/* fixup orig %eax */
+	movl	PT_ORIG_EAX(%esp), %edx		# get the error code
+	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
+
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
 	CALL_NOSPEC %edi
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 0ea4831a72a4..3f5a978a02a7 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -864,18 +864,84 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  */
 #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + (x) * 8)
 
+.macro idtentry_part do_sym, has_error_code:req, read_cr2:req, paranoid:req, shift_ist=-1, ist_offset=0
+
+	.if \paranoid
+	call	paranoid_entry
+	/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
+	.else
+	call	error_entry
+	.endif
+	UNWIND_HINT_REGS
+
+	.if \read_cr2
+	/*
+	 * Store CR2 early so subsequent faults cannot clobber it. Use R12 as
+	 * intermediate storage as RDX can be clobbered in enter_from_user_mode().
+	 * GET_CR2_INTO can clobber RAX.
+	 */
+	GET_CR2_INTO(%r12);
+	.endif
+
+	.if \shift_ist != -1
+	TRACE_IRQS_OFF_DEBUG			/* reload IDT in case of recursion */
+	.else
+	TRACE_IRQS_OFF
+	.endif
+
+	.if \paranoid == 0
+	testb	$3, CS(%rsp)
+	jz	.Lfrom_kernel_no_context_tracking_\@
+	CALL_enter_from_user_mode
+.Lfrom_kernel_no_context_tracking_\@:
+	.endif
+
+	movq	%rsp, %rdi			/* pt_regs pointer */
+
+	.if \has_error_code
+	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
+	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
+	.else
+	xorl	%esi, %esi			/* no error code */
+	.endif
+
+	.if \shift_ist != -1
+	subq	$\ist_offset, CPU_TSS_IST(\shift_ist)
+	.endif
+
+	.if \read_cr2
+	movq	%r12, %rdx			/* Move CR2 into 3rd argument */
+	.endif
+
+	call	\do_sym
+
+	.if \shift_ist != -1
+	addq	$\ist_offset, CPU_TSS_IST(\shift_ist)
+	.endif
+
+	.if \paranoid
+	/* this procedure expect "no swapgs" flag in ebx */
+	jmp	paranoid_exit
+	.else
+	jmp	error_exit
+	.endif
+
+.endm
+
 /**
  * idtentry - Generate an IDT entry stub
  * @sym:		Name of the generated entry point
- * @do_sym: 		C function to be called
- * @has_error_code: 	True if this IDT vector has an error code on the stack
- * @paranoid: 		non-zero means that this vector may be invoked from
+ * @do_sym:		C function to be called
+ * @has_error_code:	True if this IDT vector has an error code on the stack
+ * @paranoid:		non-zero means that this vector may be invoked from
  *			kernel mode with user GSBASE and/or user CR3.
  *			2 is special -- see below.
  * @shift_ist:		Set to an IST index if entries from kernel mode should
- *             		decrement the IST stack so that nested entries get a
+ *			decrement the IST stack so that nested entries get a
  *			fresh stack.  (This is for #DB, which has a nasty habit
- *             		of recursing.)
+ *			of recursing.)
+ * @create_gap:		create a 6-word stack gap when coming from kernel mode.
+ * @read_cr2:		load CR2 into the 3rd argument; done before calling any C code
  *
  * idtentry generates an IDT stub that sets up a usable kernel context,
  * creates struct pt_regs, and calls @do_sym.  The stub has the following
@@ -900,15 +966,19 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  * @paranoid == 2 is special: the stub will never switch stacks.  This is for
  * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
  */
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 read_cr2=0
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
 	/* Sanity check */
-	.if \shift_ist != -1 && \paranoid == 0
+	.if \shift_ist != -1 && \paranoid != 1
 	.error "using shift_ist requires paranoid=1"
 	.endif
 
+	.if \create_gap && \paranoid
+	.error "using create_gap requires paranoid=0"
+	.endif
+
 	ASM_CLAC
 
 	.if \has_error_code == 0
@@ -934,47 +1004,7 @@ ENTRY(\sym)
 .Lfrom_usermode_no_gap_\@:
 	.endif
 
-	.if \paranoid
-	call	paranoid_entry
-	.else
-	call	error_entry
-	.endif
-	UNWIND_HINT_REGS
-	/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
-
-	.if \paranoid
-	.if \shift_ist != -1
-	TRACE_IRQS_OFF_DEBUG			/* reload IDT in case of recursion */
-	.else
-	TRACE_IRQS_OFF
-	.endif
-	.endif
-
-	movq	%rsp, %rdi			/* pt_regs pointer */
-
-	.if \has_error_code
-	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
-	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
-	.else
-	xorl	%esi, %esi			/* no error code */
-	.endif
-
-	.if \shift_ist != -1
-	subq	$\ist_offset, CPU_TSS_IST(\shift_ist)
-	.endif
-
-	call	\do_sym
-
-	.if \shift_ist != -1
-	addq	$\ist_offset, CPU_TSS_IST(\shift_ist)
-	.endif
-
-	/* these procedures expect "no swapgs" flag in ebx */
-	.if \paranoid
-	jmp	paranoid_exit
-	.else
-	jmp	error_exit
-	.endif
+	idtentry_part \do_sym, \has_error_code, \read_cr2, \paranoid, \shift_ist, \ist_offset
 
 	.if \paranoid == 1
 	/*
@@ -983,21 +1013,9 @@ ENTRY(\sym)
 	 * run in real process context if user_mode(regs).
 	 */
 .Lfrom_usermode_switch_stack_\@:
-	call	error_entry
-
-	movq	%rsp, %rdi			/* pt_regs pointer */
-
-	.if \has_error_code
-	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
-	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
-	.else
-	xorl	%esi, %esi			/* no error code */
+	idtentry_part \do_sym, \has_error_code, \read_cr2, paranoid=0
 	.endif
 
-	call	\do_sym
-
-	jmp	error_exit
-	.endif
 _ASM_NOKPROBE(\sym)
 END(\sym)
 .endm
@@ -1007,7 +1025,7 @@ idtentry overflow			do_overflow			has_error_code=0
 idtentry bounds				do_bounds			has_error_code=0
 idtentry invalid_op			do_invalid_op			has_error_code=0
 idtentry device_not_available		do_device_not_available		has_error_code=0
-idtentry double_fault			do_double_fault			has_error_code=1 paranoid=2
+idtentry double_fault			do_double_fault			has_error_code=1 paranoid=2 read_cr2=1
 idtentry coprocessor_segment_overrun	do_coprocessor_segment_overrun	has_error_code=0
 idtentry invalid_TSS			do_invalid_TSS			has_error_code=1
 idtentry segment_not_present		do_segment_not_present		has_error_code=1
@@ -1176,14 +1194,13 @@ idtentry stack_segment		do_stack_segment	has_error_code=1
 #ifdef CONFIG_XEN_PV
 idtentry xennmi			do_nmi			has_error_code=0
 idtentry xendebug		do_debug		has_error_code=0
-idtentry xenint3		do_int3			has_error_code=0
 #endif
 
 idtentry general_protection	do_general_protection	has_error_code=1
-idtentry page_fault		do_page_fault		has_error_code=1
+idtentry page_fault		do_page_fault		has_error_code=1	read_cr2=1
 
 #ifdef CONFIG_KVM_GUEST
-idtentry async_page_fault	do_async_page_fault	has_error_code=1
+idtentry async_page_fault	do_async_page_fault	has_error_code=1	read_cr2=1
 #endif
 
 #ifdef CONFIG_X86_MCE
@@ -1282,18 +1299,9 @@ ENTRY(error_entry)
 	movq	%rax, %rsp			/* switch stack */
 	ENCODE_FRAME_POINTER
 	pushq	%r12
-
-	/*
-	 * We need to tell lockdep that IRQs are off.  We can't do this until
-	 * we fix gsbase, and we should do it before enter_from_user_mode
-	 * (which can take locks).
-	 */
-	TRACE_IRQS_OFF
-	CALL_enter_from_user_mode
 	ret
 
 .Lerror_entry_done:
-	TRACE_IRQS_OFF
 	ret
 
 	/*
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index cfdca8b42c70..cc20465b2867 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -12,9 +12,7 @@
 
 	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 	.macro THUNK name, func, put_ret_addr_in_rdi=0
-	.globl \name
-	.type \name, @function
-\name:
+	ENTRY(\name)
 	pushq %rbp
 	movq %rsp, %rbp
 
@@ -35,6 +33,7 @@
 
 	call \func
 	jmp  .L_restore
+	ENDPROC(\name)
 	_ASM_NOKPROBE(\name)
 	.endm
 
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 39106111be86..8df549138193 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -56,8 +56,7 @@ VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
 			-z max-page-size=4096
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
-	$(call if_changed,vdso)
-	$(call if_changed,vdso_check)
+	$(call if_changed,vdso_and_check)
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
 hostprogs-y			+= vdso2c
@@ -127,8 +126,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
-	$(call if_changed,vdso)
-	$(call if_changed,vdso_check)
+	$(call if_changed,vdso_and_check)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
 VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
@@ -167,8 +165,7 @@ $(obj)/vdso32.so.dbg: FORCE \
 		      $(obj)/vdso32/note.o \
 		      $(obj)/vdso32/system_call.o \
 		      $(obj)/vdso32/sigreturn.o
-	$(call if_changed,vdso)
-	$(call if_changed,vdso_check)
+	$(call if_changed,vdso_and_check)
 
 #
 # The DSO images are built using a special linker script.
@@ -179,11 +176,13 @@ quiet_cmd_vdso = VDSO    $@
 		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \
-	$(call ld-option, --build-id) $(call ld-option, --eh-frame-hdr) \
-	-Bsymbolic
+VDSO_LDFLAGS = -shared --hash-style=both --build-id \
+	$(call ld-option, --eh-frame-hdr) -Bsymbolic
 GCOV_PROFILE := n
 
+quiet_cmd_vdso_and_check = VDSO    $@
+      cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check)
+
 #
 # Install the unstripped copies of vdso*.so.  If our toolchain supports
 # build-id, install .build-id links as well.
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 42d4c89f990e..240626e7f55a 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -65,9 +65,6 @@ subsys_initcall(sysenter_setup);
 /* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
-static const int zero;
-static const int one = 1;
-
 static struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
@@ -75,8 +72,8 @@ static struct ctl_table abi_table2[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (int *)&zero,
-		.extra2		= (int *)&one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{}
 };
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 85e6984c560b..a6ea07f2aa84 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -202,15 +202,22 @@ static int amd_uncore_event_init(struct perf_event *event)
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
+	if (event->cpu < 0)
+		return -EINVAL;
+
 	/*
 	 * SliceMask and ThreadMask need to be set for certain L3 events in
 	 * Family 17h. For other events, the two fields do not affect the count.
 	 */
-	if (l3_mask)
-		hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+	if (l3_mask && is_llc_event(event)) {
+		int thread = 2 * (cpu_data(event->cpu).cpu_core_id % 4);
 
-	if (event->cpu < 0)
-		return -EINVAL;
+		if (smp_num_siblings > 1)
+			thread += cpu_data(event->cpu).apicid & 1;
+
+		hwc->config |= (1ULL << (AMD64_L3_THREAD_SHIFT + thread) &
+				AMD64_L3_THREAD_MASK) | AMD64_L3_SLICE_MASK;
+	}
 
 	uncore = event_to_amd_uncore(event);
 	if (!uncore)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index bda450ff51ee..9e911a96972b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2161,12 +2161,10 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
 		intel_pmu_disable_fixed(hwc);
-		return;
-	}
-
-	x86_pmu_disable_event(event);
+	else
+		x86_pmu_disable_event(event);
 
 	/*
 	 * Needs to be called after x86_pmu_disable_event,
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 0e033ef11a9f..0d258688c8cf 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -60,8 +60,17 @@ static int hv_cpu_init(unsigned int cpu)
 	if (!hv_vp_assist_page)
 		return 0;
 
-	if (!*hvp)
-		*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+	/*
+	 * The VP ASSIST PAGE is an "overlay" page (see Hyper-V TLFS's Section
+	 * 5.2.1 "GPA Overlay Pages"). Here it must be zeroed out to make sure
+	 * we always write the EOI MSR in hv_apic_eoi_write() *after* the
+	 * EOI optimization is disabled in hv_cpu_die(), otherwise a CPU may
+	 * not be stopped in the case of CPU offlining and the VM will hang.
+	 */
+	if (!*hvp) {
+		*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO,
+				 PAGE_KERNEL);
+	}
 
 	if (*hvp) {
 		u64 val;
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 64a6c952091e..21790307121e 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -239,6 +239,7 @@ COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
 {
 	struct kernel_clone_args args = {
 		.flags		= (clone_flags & ~CSIGNAL),
+		.pidfd		= parent_tidptr,
 		.child_tid	= child_tidptr,
 		.parent_tid	= parent_tidptr,
 		.exit_signal	= (clone_flags & CSIGNAL),
@@ -246,5 +247,8 @@ COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
 		.tls		= tls_val,
 	};
 
+	if (!legacy_clone_args_valid(&args))
+		return -EINVAL;
+
 	return _do_fork(&args);
 }
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 050e5f9ebf81..e647aa095867 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -49,7 +49,7 @@ static inline void generic_apic_probe(void)
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
-extern unsigned int apic_verbosity;
+extern int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 50a30f6c668b..e41cbf2ec41d 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -53,8 +53,20 @@ struct hypervisor_x86 {
 
 	/* runtime callbacks */
 	struct x86_hyper_runtime runtime;
+
+	/* ignore nopv parameter */
+	bool ignore_nopv;
 };
 
+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_kvm;
+extern const struct hypervisor_x86 x86_hyper_jailhouse;
+extern const struct hypervisor_x86 x86_hyper_acrn;
+extern struct hypervisor_x86 x86_hyper_xen_hvm;
+
+extern bool nopv;
 extern enum x86_hypervisor_type x86_hyper_type;
 extern void init_hypervisor_platform(void);
 static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index a06a9f8294ea..6bed97ff6db2 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -165,7 +165,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
 {
 	return (unsigned int)virt_to_phys(address);
 }
-#define isa_page_to_bus(page)	((unsigned int)page_to_phys(page))
 #define isa_bus_to_virt		phys_to_virt
 
 /*
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e92725b2a46f..74e88e5edd9c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1500,25 +1500,29 @@ enum {
 #define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 #define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
 
+asmlinkage void __noreturn kvm_spurious_fault(void);
+
 /*
  * Hardware virtualization extension instructions may fault if a
  * reboot turns off virtualization while processes are running.
- * Trap the fault and ignore the instruction if that happens.
+ * Usually after catching the fault we just panic; during reboot
+ * instead the instruction is ignored.
  */
-asmlinkage void kvm_spurious_fault(void);
-
-#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn)	\
-	"666: " insn "\n\t" \
-	"668: \n\t"                           \
-	".pushsection .fixup, \"ax\" \n" \
-	"667: \n\t" \
-	cleanup_insn "\n\t"		      \
-	"cmpb $0, kvm_rebooting \n\t"	      \
-	"jne 668b \n\t"      		      \
-	__ASM_SIZE(push) " $666b \n\t"	      \
-	"jmp kvm_spurious_fault \n\t"	      \
-	".popsection \n\t" \
-	_ASM_EXTABLE(666b, 667b)
+#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn)		\
+	"666: \n\t"							\
+	insn "\n\t"							\
+	"jmp	668f \n\t"						\
+	"667: \n\t"							\
+	"call	kvm_spurious_fault \n\t"				\
+	"668: \n\t"							\
+	".pushsection .fixup, \"ax\" \n\t"				\
+	"700: \n\t"							\
+	cleanup_insn "\n\t"						\
+	"cmpb	$0, kvm_rebooting\n\t"					\
+	"je	667b \n\t"						\
+	"jmp	668b \n\t"						\
+	".popsection \n\t"						\
+	_ASM_EXTABLE(666b, 700b)
 
 #define __kvm_handle_fault_on_reboot(insn)		\
 	____kvm_handle_fault_on_reboot(insn, "")
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 5ed3cf1c3934..9b4df6eaa11a 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -92,7 +92,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
-void do_async_page_fault(struct pt_regs *regs, unsigned long error_code);
+void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 void __init kvm_spinlock_init(void);
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
index c2bf1de5d901..6fe76282aceb 100644
--- a/arch/x86/include/asm/olpc.h
+++ b/arch/x86/include/asm/olpc.h
@@ -9,12 +9,10 @@
 struct olpc_platform_t {
 	int flags;
 	uint32_t boardrev;
-	int ecver;
 };
 
 #define OLPC_F_PRESENT		0x01
 #define OLPC_F_DCON		0x02
-#define OLPC_F_EC_WIDE_SCI	0x04
 
 #ifdef CONFIG_OLPC
 
@@ -64,13 +62,6 @@ static inline int olpc_board_at_least(uint32_t rev)
 	return olpc_platform_info.boardrev >= rev;
 }
 
-extern void olpc_ec_wakeup_set(u16 value);
-extern void olpc_ec_wakeup_clear(u16 value);
-extern bool olpc_ec_wakeup_available(void);
-
-extern int olpc_ec_mask_write(u16 bits);
-extern int olpc_ec_sci_query(u16 *sci_value);
-
 #else
 
 static inline int machine_is_olpc(void)
@@ -83,14 +74,6 @@ static inline int olpc_has_dcon(void)
 	return 0;
 }
 
-static inline void olpc_ec_wakeup_set(u16 value) { }
-static inline void olpc_ec_wakeup_clear(u16 value) { }
-
-static inline bool olpc_ec_wakeup_available(void)
-{
-	return false;
-}
-
 #endif
 
 #ifdef CONFIG_OLPC_XO1_PM
@@ -101,20 +84,6 @@ extern void olpc_xo1_pm_wakeup_clear(u16 value);
 
 extern int pci_olpc_init(void);
 
-/* SCI source values */
-
-#define EC_SCI_SRC_EMPTY	0x00
-#define EC_SCI_SRC_GAME		0x01
-#define EC_SCI_SRC_BATTERY	0x02
-#define EC_SCI_SRC_BATSOC	0x04
-#define EC_SCI_SRC_BATERR	0x08
-#define EC_SCI_SRC_EBOOK	0x10	/* XO-1 only */
-#define EC_SCI_SRC_WLAN		0x20	/* XO-1 only */
-#define EC_SCI_SRC_ACPWR	0x40
-#define EC_SCI_SRC_BATCRIT	0x80
-#define EC_SCI_SRC_GPWAKE	0x100	/* XO-1.5 only */
-#define EC_SCI_SRC_ALL		0x1FF
-
 /* GPIO assignments */
 
 #define OLPC_GPIO_MIC_AC	1
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index c25c38a05c1c..dce26f1d13e1 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -116,7 +116,7 @@ static inline void write_cr0(unsigned long x)
 
 static inline unsigned long read_cr2(void)
 {
-	return PVOP_CALL0(unsigned long, mmu.read_cr2);
+	return PVOP_CALLEE0(unsigned long, mmu.read_cr2);
 }
 
 static inline void write_cr2(unsigned long x)
@@ -746,6 +746,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	    PV_RESTORE_ALL_CALLER_REGS					\
 	    FRAME_END							\
 	    "ret;"							\
+	    ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";"	\
 	    ".popsection")
 
 /* Get a reference to a callee-save function */
@@ -909,13 +910,7 @@ extern void default_banner(void);
 		  ANNOTATE_RETPOLINE_SAFE;				\
 		  call PARA_INDIRECT(pv_ops+PV_CPU_swapgs);		\
 		 )
-#endif
-
-#define GET_CR2_INTO_RAX				\
-	ANNOTATE_RETPOLINE_SAFE;				\
-	call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2);
 
-#ifdef CONFIG_PARAVIRT_XXL
 #define USERGS_SYSRET64							\
 	PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64),			\
 		  ANNOTATE_RETPOLINE_SAFE;				\
@@ -929,9 +924,19 @@ extern void default_banner(void);
 		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);	    \
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 #endif
-#endif
+#endif /* CONFIG_PARAVIRT_XXL */
+#endif	/* CONFIG_X86_64 */
+
+#ifdef CONFIG_PARAVIRT_XXL
+
+#define GET_CR2_INTO_AX							\
+	PARA_SITE(PARA_PATCH(PV_MMU_read_cr2),				\
+		  ANNOTATE_RETPOLINE_SAFE;				\
+		  call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2);		\
+		 )
+
+#endif /* CONFIG_PARAVIRT_XXL */
 
-#endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */
 #else  /* CONFIG_PARAVIRT */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 946f8f1f1efc..639b2df445ee 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -220,7 +220,7 @@ struct pv_mmu_ops {
 	void (*exit_mmap)(struct mm_struct *mm);
 
 #ifdef CONFIG_PARAVIRT_XXL
-	unsigned long (*read_cr2)(void);
+	struct paravirt_callee_save read_cr2;
 	void (*write_cr2)(unsigned long);
 
 	unsigned long (*read_cr3)(void);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5e0509b41986..0bc530c4eb13 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -271,7 +271,7 @@ static inline int has_transparent_hugepage(void)
 	return boot_cpu_has(X86_FEATURE_PSE);
 }
 
-#ifdef __HAVE_ARCH_PTE_DEVMAP
+#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
 static inline int pmd_devmap(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_DEVMAP);
@@ -732,7 +732,7 @@ static inline int pte_present(pte_t a)
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
-#ifdef __HAVE_ARCH_PTE_DEVMAP
+#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
 static inline int pte_devmap(pte_t a)
 {
 	return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP;
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index d6ff0bbdb394..b5e49e6bac63 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -103,7 +103,6 @@
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #define _PAGE_DEVMAP	(_AT(u64, 1) << _PAGE_BIT_DEVMAP)
-#define __HAVE_ARCH_PTE_DEVMAP
 #else
 #define _PAGE_NX	(_AT(pteval_t, 0))
 #define _PAGE_DEVMAP	(_AT(pteval_t, 0))
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 7d6f3f3fad78..b25e633033c3 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -40,7 +40,7 @@ asmlinkage void simd_coprocessor_error(void);
 asmlinkage void xen_divide_error(void);
 asmlinkage void xen_xennmi(void);
 asmlinkage void xen_xendebug(void);
-asmlinkage void xen_xenint3(void);
+asmlinkage void xen_int3(void);
 asmlinkage void xen_overflow(void);
 asmlinkage void xen_bounds(void);
 asmlinkage void xen_invalid_op(void);
@@ -74,14 +74,14 @@ dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code);
 dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code);
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code);
 #ifdef CONFIG_X86_64
-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 address);
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace
 struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s);
 void __init trap_init(void);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code);
-dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code);
+dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code);
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code);
 dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index c82abd6e4ca3..9c4435307ff8 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -66,7 +66,9 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 })
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-# define WARN_ON_IN_IRQ()	WARN_ON_ONCE(!in_task())
+static inline bool pagefault_disabled(void);
+# define WARN_ON_IN_IRQ()	\
+	WARN_ON_ONCE(!in_task() && !pagefault_disabled())
 #else
 # define WARN_ON_IN_IRQ()
 #endif
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index b85a7c54c6a1..ac0934189017 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -301,6 +301,8 @@ extern struct x86_apic_ops x86_apic_ops;
 extern void x86_early_init_platform_quirks(void);
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
+extern bool bool_x86_init_noop(void);
+extern void x86_op_int_noop(int cpu);
 extern bool x86_pnpbios_disabled(void);
 
 #endif
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 39171b3646bb..42e1245af0d8 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -44,14 +44,14 @@ static inline uint32_t xen_cpuid_base(void)
 }
 
 #ifdef CONFIG_XEN
-extern bool xen_hvm_need_lapic(void);
+extern bool __init xen_hvm_need_lapic(void);
 
-static inline bool xen_x2apic_para_available(void)
+static inline bool __init xen_x2apic_para_available(void)
 {
 	return xen_hvm_need_lapic();
 }
 #else
-static inline bool xen_x2apic_para_available(void)
+static inline bool __init xen_x2apic_para_available(void)
 {
 	return (xen_cpuid_base() != 0);
 }
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/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..a6342c899be5 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
 
@@ -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/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 edd2179ad2da..4ab377c9fffe 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;
 	}
@@ -832,6 +832,7 @@ 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/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
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8e409ad448f9..718f7d9afedc 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -312,29 +312,42 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 
 static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 
-#define FOP_FUNC(name) \
+#define __FOP_FUNC(name) \
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
 	".type " name ", @function \n\t" \
 	name ":\n\t"
 
-#define FOP_RET   "ret \n\t"
+#define FOP_FUNC(name) \
+	__FOP_FUNC(#name)
+
+#define __FOP_RET(name) \
+	"ret \n\t" \
+	".size " name ", .-" name "\n\t"
+
+#define FOP_RET(name) \
+	__FOP_RET(#name)
 
 #define FOP_START(op) \
 	extern void em_##op(struct fastop *fake); \
 	asm(".pushsection .text, \"ax\" \n\t" \
 	    ".global em_" #op " \n\t" \
-	    FOP_FUNC("em_" #op)
+	    ".align " __stringify(FASTOP_SIZE) " \n\t" \
+	    "em_" #op ":\n\t"
 
 #define FOP_END \
 	    ".popsection")
 
+#define __FOPNOP(name) \
+	__FOP_FUNC(name) \
+	__FOP_RET(name)
+
 #define FOPNOP() \
-	FOP_FUNC(__stringify(__UNIQUE_ID(nop))) \
-	FOP_RET
+	__FOPNOP(__stringify(__UNIQUE_ID(nop)))
 
 #define FOP1E(op,  dst) \
-	FOP_FUNC(#op "_" #dst) \
-	"10: " #op " %" #dst " \n\t" FOP_RET
+	__FOP_FUNC(#op "_" #dst) \
+	"10: " #op " %" #dst " \n\t" \
+	__FOP_RET(#op "_" #dst)
 
 #define FOP1EEX(op,  dst) \
 	FOP1E(op, dst) _ASM_EXTABLE(10b, kvm_fastop_exception)
@@ -366,8 +379,9 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	FOP_END
 
 #define FOP2E(op,  dst, src)	   \
-	FOP_FUNC(#op "_" #dst "_" #src) \
-	#op " %" #src ", %" #dst " \n\t" FOP_RET
+	__FOP_FUNC(#op "_" #dst "_" #src) \
+	#op " %" #src ", %" #dst " \n\t" \
+	__FOP_RET(#op "_" #dst "_" #src)
 
 #define FASTOP2(op) \
 	FOP_START(op) \
@@ -405,8 +419,9 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	FOP_END
 
 #define FOP3E(op,  dst, src, src2) \
-	FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \
-	#op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
+	__FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \
+	#op " %" #src2 ", %" #src ", %" #dst " \n\t"\
+	__FOP_RET(#op "_" #dst "_" #src "_" #src2)
 
 /* 3-operand, word-only, src2=cl */
 #define FASTOP3WCL(op) \
@@ -423,7 +438,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	".type " #op ", @function \n\t" \
 	#op ": \n\t" \
 	#op " %al \n\t" \
-	FOP_RET
+	__FOP_RET(#op)
 
 asm(".pushsection .fixup, \"ax\"\n"
     ".global kvm_fastop_exception \n"
@@ -449,7 +464,10 @@ FOP_SETCC(setle)
 FOP_SETCC(setnle)
 FOP_END;
 
-FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET
+FOP_START(salc)
+FOP_FUNC(salc)
+"pushf; sbb %al, %al; popf \n\t"
+FOP_RET(salc)
 FOP_END;
 
 /*
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index d4cb1945b2e3..4010d519eb8c 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -54,9 +54,9 @@ ENTRY(vmx_vmenter)
 	ret
 
 3:	cmpb $0, kvm_rebooting
-	jne 4f
-	call kvm_spurious_fault
-4:	ret
+	je 4f
+	ret
+4:	ud2
 
 	.pushsection .fixup, "ax"
 5:	jmp 3b
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 378a1f70ae7d..4fe1601dbc5d 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -239,7 +239,7 @@ copy_user_handle_tail:
 	ret
 
 	_ASM_EXTABLE_UA(1b, 2b)
-ENDPROC(copy_user_handle_tail)
+END(copy_user_handle_tail)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 74fdff968ea3..304f958c27b2 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -115,29 +115,29 @@ ENDPROC(__get_user_8)
 EXPORT_SYMBOL(__get_user_8)
 
 
+bad_get_user_clac:
+	ASM_CLAC
 bad_get_user:
 	xor %edx,%edx
 	mov $(-EFAULT),%_ASM_AX
-	ASM_CLAC
 	ret
-END(bad_get_user)
 
 #ifdef CONFIG_X86_32
+bad_get_user_8_clac:
+	ASM_CLAC
 bad_get_user_8:
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
-	ASM_CLAC
 	ret
-END(bad_get_user_8)
 #endif
 
-	_ASM_EXTABLE_UA(1b, bad_get_user)
-	_ASM_EXTABLE_UA(2b, bad_get_user)
-	_ASM_EXTABLE_UA(3b, bad_get_user)
+	_ASM_EXTABLE_UA(1b, bad_get_user_clac)
+	_ASM_EXTABLE_UA(2b, bad_get_user_clac)
+	_ASM_EXTABLE_UA(3b, bad_get_user_clac)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE_UA(4b, bad_get_user)
+	_ASM_EXTABLE_UA(4b, bad_get_user_clac)
 #else
-	_ASM_EXTABLE_UA(4b, bad_get_user_8)
-	_ASM_EXTABLE_UA(5b, bad_get_user_8)
+	_ASM_EXTABLE_UA(4b, bad_get_user_8_clac)
+	_ASM_EXTABLE_UA(5b, bad_get_user_8_clac)
 #endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index d2e5c9c39601..14bf78341d3c 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -32,8 +32,6 @@
  */
 
 #define ENTER	mov PER_CPU_VAR(current_task), %_ASM_BX
-#define EXIT	ASM_CLAC ;	\
-		ret
 
 .text
 ENTRY(__put_user_1)
@@ -43,7 +41,8 @@ ENTRY(__put_user_1)
 	ASM_STAC
 1:	movb %al,(%_ASM_CX)
 	xor %eax,%eax
-	EXIT
+	ASM_CLAC
+	ret
 ENDPROC(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
@@ -56,7 +55,8 @@ ENTRY(__put_user_2)
 	ASM_STAC
 2:	movw %ax,(%_ASM_CX)
 	xor %eax,%eax
-	EXIT
+	ASM_CLAC
+	ret
 ENDPROC(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
@@ -69,7 +69,8 @@ ENTRY(__put_user_4)
 	ASM_STAC
 3:	movl %eax,(%_ASM_CX)
 	xor %eax,%eax
-	EXIT
+	ASM_CLAC
+	ret
 ENDPROC(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
@@ -85,19 +86,21 @@ ENTRY(__put_user_8)
 5:	movl %edx,4(%_ASM_CX)
 #endif
 	xor %eax,%eax
-	EXIT
+	ASM_CLAC
+	RET
 ENDPROC(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
+bad_put_user_clac:
+	ASM_CLAC
 bad_put_user:
 	movl $-EFAULT,%eax
-	EXIT
-END(bad_put_user)
+	RET
 
-	_ASM_EXTABLE_UA(1b, bad_put_user)
-	_ASM_EXTABLE_UA(2b, bad_put_user)
-	_ASM_EXTABLE_UA(3b, bad_put_user)
-	_ASM_EXTABLE_UA(4b, bad_put_user)
+	_ASM_EXTABLE_UA(1b, bad_put_user_clac)
+	_ASM_EXTABLE_UA(2b, bad_put_user_clac)
+	_ASM_EXTABLE_UA(3b, bad_put_user_clac)
+	_ASM_EXTABLE_UA(4b, bad_put_user_clac)
 #ifdef CONFIG_X86_32
-	_ASM_EXTABLE_UA(5b, bad_put_user)
+	_ASM_EXTABLE_UA(5b, bad_put_user_clac)
 #endif
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index e0e006f1624e..fff28c6f73a2 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -60,7 +60,7 @@ EXPORT_SYMBOL(clear_user);
  * but reuse __memcpy_mcsafe in case a new read error is encountered.
  * clac() is handled in _copy_to_iter_mcsafe().
  */
-__visible unsigned long
+__visible notrace unsigned long
 mcsafe_handle_tail(char *to, char *from, unsigned len)
 {
 	for (; len; --len, to++, from++) {
diff --git a/arch/x86/math-emu/fpu_emu.h b/arch/x86/math-emu/fpu_emu.h
index a5a41ec58072..0c122226ca56 100644
--- a/arch/x86/math-emu/fpu_emu.h
+++ b/arch/x86/math-emu/fpu_emu.h
@@ -177,7 +177,7 @@ static inline void reg_copy(FPU_REG const *x, FPU_REG *y)
 #define setexponentpos(x,y) { (*(short *)&((x)->exp)) = \
   ((y) + EXTENDED_Ebias) & 0x7fff; }
 #define exponent16(x)         (*(short *)&((x)->exp))
-#define setexponent16(x,y)  { (*(short *)&((x)->exp)) = (y); }
+#define setexponent16(x,y)  { (*(short *)&((x)->exp)) = (u16)(y); }
 #define addexponent(x,y)    { (*(short *)&((x)->exp)) += (y); }
 #define stdexp(x)           { (*(short *)&((x)->exp)) += EXTENDED_Ebias; }
 
diff --git a/arch/x86/math-emu/reg_constant.c b/arch/x86/math-emu/reg_constant.c
index 8dc9095bab22..742619e94bdf 100644
--- a/arch/x86/math-emu/reg_constant.c
+++ b/arch/x86/math-emu/reg_constant.c
@@ -18,7 +18,7 @@
 #include "control_w.h"
 
 #define MAKE_REG(s, e, l, h) { l, h, \
-		((EXTENDED_Ebias+(e)) | ((SIGN_##s != 0)*0x8000)) }
+		(u16)((EXTENDED_Ebias+(e)) | ((SIGN_##s != 0)*0x8000)) }
 
 FPU_REG const CONST_1 = MAKE_REG(POS, 0, 0x00000000, 0x80000000);
 #if 0
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 794f364cb882..6c46095cd0d9 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -46,23 +46,6 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
 	return 0;
 }
 
-static nokprobe_inline int kprobes_fault(struct pt_regs *regs)
-{
-	if (!kprobes_built_in())
-		return 0;
-	if (user_mode(regs))
-		return 0;
-	/*
-	 * To be potentially processing a kprobe fault and to be allowed to call
-	 * kprobe_running(), we have to be non-preemptible.
-	 */
-	if (preemptible())
-		return 0;
-	if (!kprobe_running())
-		return 0;
-	return kprobe_fault_handler(regs, X86_TRAP_PF);
-}
-
 /*
  * Prefetch quirks:
  *
@@ -1282,7 +1265,7 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
 		return;
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (kprobes_fault(regs))
+	if (kprobe_page_fault(regs, X86_TRAP_PF))
 		return;
 
 	/*
@@ -1313,7 +1296,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	mm = tsk->mm;
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (unlikely(kprobes_fault(regs)))
+	if (unlikely(kprobe_page_fault(regs, X86_TRAP_PF)))
 		return;
 
 	/*
@@ -1507,9 +1490,8 @@ good_area:
 NOKPROBE_SYMBOL(do_user_addr_fault);
 
 /*
- * This routine handles page faults.  It determines the address,
- * and the problem, and then passes it off to one of the appropriate
- * routines.
+ * Explicitly marked noinline such that the function tracer sees this as the
+ * page_fault entry point.
  */
 static noinline void
 __do_page_fault(struct pt_regs *regs, unsigned long hw_error_code,
@@ -1528,33 +1510,26 @@ __do_page_fault(struct pt_regs *regs, unsigned long hw_error_code,
 }
 NOKPROBE_SYMBOL(__do_page_fault);
 
-static nokprobe_inline void
-trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
-			 unsigned long error_code)
+static __always_inline void
+trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code,
+			 unsigned long address)
 {
+	if (!trace_pagefault_enabled())
+		return;
+
 	if (user_mode(regs))
 		trace_page_fault_user(address, regs, error_code);
 	else
 		trace_page_fault_kernel(address, regs, error_code);
 }
 
-/*
- * We must have this function blacklisted from kprobes, tagged with notrace
- * and call read_cr2() before calling anything else. To avoid calling any
- * kind of tracing machinery before we've observed the CR2 value.
- *
- * exception_{enter,exit}() contains all sorts of tracepoints.
- */
-dotraplinkage void notrace
-do_page_fault(struct pt_regs *regs, unsigned long error_code)
+dotraplinkage void
+do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 {
-	unsigned long address = read_cr2(); /* Get the faulting address */
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
-	if (trace_pagefault_enabled())
-		trace_page_fault_entries(address, regs, error_code);
-
+	trace_page_fault_entries(regs, error_code, address);
 	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index f265a4316179..4068abb9427f 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -860,7 +860,6 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
@@ -872,7 +871,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 	__remove_pages(zone, start_pfn, nr_pages, altmap);
 }
 #endif
-#endif
 
 int kernel_set_to_readonly __read_mostly;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0f01c7b1d217..a6b5c653727b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1198,7 +1198,6 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
 	remove_pagetable(start, end, false, altmap);
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 static void __meminit
 kernel_physical_mapping_remove(unsigned long start, unsigned long end)
 {
@@ -1213,17 +1212,12 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct page *page = pfn_to_page(start_pfn);
-	struct zone *zone;
+	struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
+	struct zone *zone = page_zone(page);
 
-	/* With altmap the first mapped page is offset from @start */
-	if (altmap)
-		page += vmem_altmap_offset(altmap);
-	zone = page_zone(page);
 	__remove_pages(zone, start_pfn, nr_pages, altmap);
 	kernel_physical_mapping_remove(start, start + size);
 }
-#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_vsyscall;
@@ -1524,7 +1518,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	int err;
 
-	if (boot_cpu_has(X86_FEATURE_PSE))
+	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
+		err = vmemmap_populate_basepages(start, end, node);
+	else if (boot_cpu_has(X86_FEATURE_PSE))
 		err = vmemmap_populate_hugepages(start, end, node, altmap);
 	else if (altmap) {
 		pr_err_once("%s: no cpu support for altmap allocations\n",
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index e500f1df1140..63e99f15d7cf 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -459,6 +459,11 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
+int __init arch_ioremap_p4d_supported(void)
+{
+	return 0;
+}
+
 int __init arch_ioremap_pud_supported(void)
 {
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index e0df96fdfe46..fece30ca8b0c 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -15,6 +15,10 @@
 #include <linux/dma-direct.h>
 #include <linux/swiotlb.h>
 #include <linux/mem_encrypt.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/tlbflush.h>
 #include <asm/fixmap.h>
@@ -41,7 +45,7 @@ EXPORT_SYMBOL_GPL(sev_enable_key);
 bool sev_enabled __section(.data);
 
 /* Buffer used for early in-place encryption by BSP, no locking needed */
-static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE);
+static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);
 
 /*
  * This routine does not change the underlying encryption setting of the
@@ -348,6 +352,32 @@ bool sev_active(void)
 }
 EXPORT_SYMBOL(sev_active);
 
+/* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
+bool force_dma_unencrypted(struct device *dev)
+{
+	/*
+	 * For SEV, all DMA must be to unencrypted addresses.
+	 */
+	if (sev_active())
+		return true;
+
+	/*
+	 * For SME, all DMA must be to unencrypted addresses if the
+	 * device does not support DMA to addresses that include the
+	 * encryption mask.
+	 */
+	if (sme_active()) {
+		u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask));
+		u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask,
+						dev->bus_dma_mask);
+
+		if (dma_dev_mask <= dma_enc_mask)
+			return true;
+	}
+
+	return false;
+}
+
 /* Architecture __weak replacement functions */
 void __init mem_encrypt_free_decrypted_mem(void)
 {
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index c85d485eb4f8..ee2beda590d0 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -26,9 +26,6 @@
 struct olpc_platform_t olpc_platform_info;
 EXPORT_SYMBOL_GPL(olpc_platform_info);
 
-/* EC event mask to be applied during suspend (defining wakeup sources). */
-static u16 ec_wakeup_mask;
-
 /* what the timeout *should* be (in ms) */
 #define EC_BASE_TIMEOUT 20
 
@@ -182,83 +179,6 @@ err:
 	return ret;
 }
 
-void olpc_ec_wakeup_set(u16 value)
-{
-	ec_wakeup_mask |= value;
-}
-EXPORT_SYMBOL_GPL(olpc_ec_wakeup_set);
-
-void olpc_ec_wakeup_clear(u16 value)
-{
-	ec_wakeup_mask &= ~value;
-}
-EXPORT_SYMBOL_GPL(olpc_ec_wakeup_clear);
-
-/*
- * Returns true if the compile and runtime configurations allow for EC events
- * to wake the system.
- */
-bool olpc_ec_wakeup_available(void)
-{
-	if (!machine_is_olpc())
-		return false;
-
-	/*
-	 * XO-1 EC wakeups are available when olpc-xo1-sci driver is
-	 * compiled in
-	 */
-#ifdef CONFIG_OLPC_XO1_SCI
-	if (olpc_platform_info.boardrev < olpc_board_pre(0xd0)) /* XO-1 */
-		return true;
-#endif
-
-	/*
-	 * XO-1.5 EC wakeups are available when olpc-xo15-sci driver is
-	 * compiled in
-	 */
-#ifdef CONFIG_OLPC_XO15_SCI
-	if (olpc_platform_info.boardrev >= olpc_board_pre(0xd0)) /* XO-1.5 */
-		return true;
-#endif
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(olpc_ec_wakeup_available);
-
-int olpc_ec_mask_write(u16 bits)
-{
-	if (olpc_platform_info.flags & OLPC_F_EC_WIDE_SCI) {
-		__be16 ec_word = cpu_to_be16(bits);
-		return olpc_ec_cmd(EC_WRITE_EXT_SCI_MASK, (void *) &ec_word, 2,
-				   NULL, 0);
-	} else {
-		unsigned char ec_byte = bits & 0xff;
-		return olpc_ec_cmd(EC_WRITE_SCI_MASK, &ec_byte, 1, NULL, 0);
-	}
-}
-EXPORT_SYMBOL_GPL(olpc_ec_mask_write);
-
-int olpc_ec_sci_query(u16 *sci_value)
-{
-	int ret;
-
-	if (olpc_platform_info.flags & OLPC_F_EC_WIDE_SCI) {
-		__be16 ec_word;
-		ret = olpc_ec_cmd(EC_EXT_SCI_QUERY,
-			NULL, 0, (void *) &ec_word, 2);
-		if (ret == 0)
-			*sci_value = be16_to_cpu(ec_word);
-	} else {
-		unsigned char ec_byte;
-		ret = olpc_ec_cmd(EC_SCI_QUERY, NULL, 0, &ec_byte, 1);
-		if (ret == 0)
-			*sci_value = ec_byte;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(olpc_ec_sci_query);
-
 static bool __init check_ofw_architecture(struct device_node *root)
 {
 	const char *olpc_arch;
@@ -292,6 +212,10 @@ static bool __init platform_detect(void)
 	if (success) {
 		olpc_platform_info.boardrev = get_board_revision(root);
 		olpc_platform_info.flags |= OLPC_F_PRESENT;
+
+		pr_info("OLPC board revision %s%X\n",
+			((olpc_platform_info.boardrev & 0xf) < 8) ? "pre" : "",
+			olpc_platform_info.boardrev >> 4);
 	}
 
 	of_node_put(root);
@@ -311,27 +235,8 @@ static int __init add_xo1_platform_devices(void)
 	return PTR_ERR_OR_ZERO(pdev);
 }
 
-static int olpc_xo1_ec_probe(struct platform_device *pdev)
-{
-	/* get the EC revision */
-	olpc_ec_cmd(EC_FIRMWARE_REV, NULL, 0,
-			(unsigned char *) &olpc_platform_info.ecver, 1);
-
-	/* EC version 0x5f adds support for wide SCI mask */
-	if (olpc_platform_info.ecver >= 0x5f)
-		olpc_platform_info.flags |= OLPC_F_EC_WIDE_SCI;
-
-	pr_info("OLPC board revision %s%X (EC=%x)\n",
-			((olpc_platform_info.boardrev & 0xf) < 8) ? "pre" : "",
-			olpc_platform_info.boardrev >> 4,
-			olpc_platform_info.ecver);
-
-	return 0;
-}
 static int olpc_xo1_ec_suspend(struct platform_device *pdev)
 {
-	olpc_ec_mask_write(ec_wakeup_mask);
-
 	/*
 	 * Squelch SCIs while suspended.  This is a fix for
 	 * <http://dev.laptop.org/ticket/1835>.
@@ -355,15 +260,27 @@ static int olpc_xo1_ec_resume(struct platform_device *pdev)
 }
 
 static struct olpc_ec_driver ec_xo1_driver = {
-	.probe = olpc_xo1_ec_probe,
 	.suspend = olpc_xo1_ec_suspend,
 	.resume = olpc_xo1_ec_resume,
 	.ec_cmd = olpc_xo1_ec_cmd,
+#ifdef CONFIG_OLPC_XO1_SCI
+	/*
+	 * XO-1 EC wakeups are available when olpc-xo1-sci driver is
+	 * compiled in
+	 */
+	.wakeup_available = true,
+#endif
 };
 
 static struct olpc_ec_driver ec_xo1_5_driver = {
-	.probe = olpc_xo1_ec_probe,
 	.ec_cmd = olpc_xo1_ec_cmd,
+#ifdef CONFIG_OLPC_XO1_5_SCI
+	/*
+	 * XO-1.5 EC wakeups are available when olpc-xo15-sci driver is
+	 * compiled in
+	 */
+	.wakeup_available = true,
+#endif
 };
 
 static int __init olpc_init(void)
diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index c78bfc16a3ca..26d1f6693789 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -216,7 +216,7 @@ static u32 __init olpc_dt_get_board_revision(void)
 	return be32_to_cpu(rev);
 }
 
-int olpc_dt_compatible_match(phandle node, const char *compat)
+static int __init olpc_dt_compatible_match(phandle node, const char *compat)
 {
 	char buf[64], *p;
 	int plen, len;
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 0e75642d42a3..e138f7de52d2 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -210,18 +210,18 @@ static void __init xen_hvm_guest_init(void)
 #endif
 }
 
-static bool xen_nopv;
 static __init int xen_parse_nopv(char *arg)
 {
-       xen_nopv = true;
-       return 0;
+	pr_notice("\"xen_nopv\" is deprecated, please use \"nopv\" instead\n");
+
+	if (xen_cpuid_base())
+		nopv = true;
+	return 0;
 }
 early_param("xen_nopv", xen_parse_nopv);
 
-bool xen_hvm_need_lapic(void)
+bool __init xen_hvm_need_lapic(void)
 {
-	if (xen_nopv)
-		return false;
 	if (xen_pv_domain())
 		return false;
 	if (!xen_hvm_domain())
@@ -230,15 +230,6 @@ bool xen_hvm_need_lapic(void)
 		return false;
 	return true;
 }
-EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
-
-static uint32_t __init xen_platform_hvm(void)
-{
-	if (xen_pv_domain() || xen_nopv)
-		return 0;
-
-	return xen_cpuid_base();
-}
 
 static __init void xen_hvm_guest_late_init(void)
 {
@@ -251,6 +242,9 @@ static __init void xen_hvm_guest_late_init(void)
 	/* PVH detected. */
 	xen_pvh = true;
 
+	if (nopv)
+		panic("\"nopv\" and \"xen_nopv\" parameters are unsupported in PVH guest.");
+
 	/* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */
 	if (!nr_ioapics && acpi_irq_model == ACPI_IRQ_MODEL_PIC)
 		acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM;
@@ -260,7 +254,38 @@ static __init void xen_hvm_guest_late_init(void)
 #endif
 }
 
-const __initconst struct hypervisor_x86 x86_hyper_xen_hvm = {
+static uint32_t __init xen_platform_hvm(void)
+{
+	uint32_t xen_domain = xen_cpuid_base();
+	struct x86_hyper_init *h = &x86_hyper_xen_hvm.init;
+
+	if (xen_pv_domain())
+		return 0;
+
+	if (xen_pvh_domain() && nopv) {
+		/* Guest booting via the Xen-PVH boot entry goes here */
+		pr_info("\"nopv\" parameter is ignored in PVH guest\n");
+		nopv = false;
+	} else if (nopv && xen_domain) {
+		/*
+		 * Guest booting via normal boot entry (like via grub2) goes
+		 * here.
+		 *
+		 * Use interface functions for bare hardware if nopv,
+		 * xen_hvm_guest_late_init is an exception as we need to
+		 * detect PVH and panic there.
+		 */
+		h->init_platform = x86_init_noop;
+		h->x2apic_available = bool_x86_init_noop;
+		h->init_mem_mapping = x86_init_noop;
+		h->init_after_bootmem = x86_init_noop;
+		h->guest_late_init = xen_hvm_guest_late_init;
+		x86_hyper_xen_hvm.runtime.pin_vcpu = x86_op_int_noop;
+	}
+	return xen_domain;
+}
+
+struct hypervisor_x86 x86_hyper_xen_hvm __initdata = {
 	.name                   = "Xen HVM",
 	.detect                 = xen_platform_hvm,
 	.type			= X86_HYPER_XEN_HVM,
@@ -269,4 +294,5 @@ const __initconst struct hypervisor_x86 x86_hyper_xen_hvm = {
 	.init.init_mem_mapping	= xen_hvm_init_mem_mapping,
 	.init.guest_late_init	= xen_hvm_guest_late_init,
 	.runtime.pin_vcpu       = xen_pin_vcpu,
+	.ignore_nopv            = true,
 };
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 4722ba2966ac..7ceb32821093 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -596,12 +596,12 @@ struct trap_array_entry {
 
 static struct trap_array_entry trap_array[] = {
 	{ debug,                       xen_xendebug,                    true },
-	{ int3,                        xen_xenint3,                     true },
 	{ double_fault,                xen_double_fault,                true },
 #ifdef CONFIG_X86_MCE
 	{ machine_check,               xen_machine_check,               true },
 #endif
 	{ nmi,                         xen_xennmi,                      true },
+	{ int3,                        xen_int3,                        false },
 	{ overflow,                    xen_overflow,                    false },
 #ifdef CONFIG_IA32_EMULATION
 	{ entry_INT80_compat,          xen_entry_INT80_compat,          false },
@@ -998,7 +998,8 @@ void __init xen_setup_vcpu_info_placement(void)
 			__PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
 		pv_ops.irq.irq_enable =
 			__PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
-		pv_ops.mmu.read_cr2 = xen_read_cr2_direct;
+		pv_ops.mmu.read_cr2 =
+			__PV_IS_CALLEE_SAVE(xen_read_cr2_direct);
 	}
 }
 
@@ -1463,4 +1464,5 @@ const __initconst struct hypervisor_x86 x86_hyper_xen_pv = {
 	.detect                 = xen_platform_pv,
 	.type			= X86_HYPER_XEN_PV,
 	.runtime.pin_vcpu       = xen_pin_vcpu,
+	.ignore_nopv		= true,
 };
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index f6e5eeecfc69..26e8b326966d 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1307,16 +1307,6 @@ static void xen_write_cr2(unsigned long cr2)
 	this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
 }
 
-static unsigned long xen_read_cr2(void)
-{
-	return this_cpu_read(xen_vcpu)->arch.cr2;
-}
-
-unsigned long xen_read_cr2_direct(void)
-{
-	return this_cpu_read(xen_vcpu_info.arch.cr2);
-}
-
 static noinline void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
@@ -2397,7 +2387,7 @@ static void xen_leave_lazy_mmu(void)
 }
 
 static const struct pv_mmu_ops xen_mmu_ops __initconst = {
-	.read_cr2 = xen_read_cr2,
+	.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2),
 	.write_cr2 = xen_write_cr2,
 
 	.read_cr3 = xen_read_cr3,
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 3776122c87cc..6deb49094c60 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -68,11 +68,8 @@ void xen_init_lock_cpu(int cpu)
 	int irq;
 	char *name;
 
-	if (!xen_pvspin) {
-		if (cpu == 0)
-			static_branch_disable(&virt_spin_lock_key);
+	if (!xen_pvspin)
 		return;
-	}
 
 	WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
 	     cpu, per_cpu(lock_kicker_irq, cpu));
@@ -124,6 +121,7 @@ void __init xen_init_spinlocks(void)
 
 	if (!xen_pvspin) {
 		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
+		static_branch_disable(&virt_spin_lock_key);
 		return;
 	}
 	printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 8019edd0125c..be104eef80be 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -10,6 +10,7 @@
 #include <asm/percpu.h>
 #include <asm/processor-flags.h>
 #include <asm/frame.h>
+#include <asm/asm.h>
 
 #include <linux/linkage.h>
 
@@ -135,3 +136,18 @@ ENTRY(check_events)
 	FRAME_END
 	ret
 ENDPROC(check_events)
+
+ENTRY(xen_read_cr2)
+	FRAME_BEGIN
+	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
+	_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
+	FRAME_END
+	ret
+	ENDPROC(xen_read_cr2);
+
+ENTRY(xen_read_cr2_direct)
+	FRAME_BEGIN
+	_ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX
+	FRAME_END
+	ret
+	ENDPROC(xen_read_cr2_direct);
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 1e9ef0ba30a5..ebf610b49c06 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -32,7 +32,6 @@ xen_pv_trap divide_error
 xen_pv_trap debug
 xen_pv_trap xendebug
 xen_pv_trap int3
-xen_pv_trap xenint3
 xen_pv_trap xennmi
 xen_pv_trap overflow
 xen_pv_trap bounds
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 2f111f47ba98..45a441c33d6d 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -134,6 +134,9 @@ __visible void xen_irq_disable_direct(void);
 __visible unsigned long xen_save_fl_direct(void);
 __visible void xen_restore_fl_direct(unsigned long);
 
+__visible unsigned long xen_read_cr2(void);
+__visible unsigned long xen_read_cr2_direct(void);
+
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
 __visible void xen_sysret32(void);
author	Paolo Bonzini <pbonzini@redhat.com>	2019-08-09 16:53:39 +0200
committer	Paolo Bonzini <pbonzini@redhat.com>	2019-08-09 16:53:39 +0200
commit	0e1c438c44dd9cde56effb44c5f1cfeda72e108d (patch)
tree	fa3492d4d7d8b7444e5d8ebe6c78210826333e4b /arch/x86
parent	c096397c78f766db972f923433031f2dec01cae0 (diff)
parent	cdb2d3ee0436d74fa9092f2df46aaa6f9e03c969 (diff)