Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:
 "The main changes in this development cycle were:

   - a large number of call stack dumping/printing improvements: higher
     robustness, better cross-context dumping, improved output, etc.
     (Josh Poimboeuf)

   - vDSO getcpu() performance improvement for future Intel CPUs with
     the RDPID instruction (Andy Lutomirski)

   - add two new Intel AVX512 features and the CPUID support
     infrastructure for it: AVX512IFMA and AVX512VBMI. (Gayatri Kammela,
     He Chen)

   - more copy-user unification (Borislav Petkov)

   - entry code assembly macro simplifications (Alexander Kuleshov)

   - vDSO C/R support improvements (Dmitry Safonov)

   - misc fixes and cleanups (Borislav Petkov, Paul Bolle)"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  scripts/decode_stacktrace.sh: Fix address line detection on x86
  x86/boot/64: Use defines for page size
  x86/dumpstack: Make stack name tags more comprehensible
  selftests/x86: Add test_vdso to test getcpu()
  x86/vdso: Use RDPID in preference to LSL when available
  x86/dumpstack: Handle NULL stack pointer in show_trace_log_lvl()
  x86/cpufeatures: Enable new AVX512 cpu features
  x86/cpuid: Provide get_scattered_cpuid_leaf()
  x86/cpuid: Cleanup cpuid_regs definitions
  x86/copy_user: Unify the code by removing the 64-bit asm _copy_*_user() variants
  x86/unwind: Ensure stack grows down
  x86/vdso: Set vDSO pointer only after success
  x86/prctl/uapi: Remove #ifdef for CHECKPOINT_RESTORE
  x86/unwind: Detect bad stack return address
  x86/dumpstack: Warn on stack recursion
  x86/unwind: Warn on bad frame pointer
  x86/decoder: Use stderr if insn sanity test fails
  x86/decoder: Use stdout if insn decoder test is successful
  mm/page_alloc: Remove kernel address exposure in free_reserved_area()
  x86/dumpstack: Remove raw stack dump
  ...

32 files changed, 554 insertions, 459 deletions

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 9a9e5884066c..05ed3d393da7 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -90,8 +90,8 @@ For 32-bit we have the following conventions - kernel is built with
 
 #define SIZEOF_PTREGS	21*8
 
-	.macro ALLOC_PT_GPREGS_ON_STACK addskip=0
-	addq	$-(15*8+\addskip), %rsp
+	.macro ALLOC_PT_GPREGS_ON_STACK
+	addq	$-(15*8), %rsp
 	.endm
 
 	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
@@ -147,15 +147,6 @@ For 32-bit we have the following conventions - kernel is built with
 	movq 5*8+\offset(%rsp), %rbx
 	.endm
 
-	.macro ZERO_EXTRA_REGS
-	xorl	%r15d, %r15d
-	xorl	%r14d, %r14d
-	xorl	%r13d, %r13d
-	xorl	%r12d, %r12d
-	xorl	%ebp, %ebp
-	xorl	%ebx, %ebx
-	.endm
-
 	.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
 	.if \rstor_r11
 	movq 6*8(%rsp), %r11
@@ -201,6 +192,26 @@ For 32-bit we have the following conventions - kernel is built with
 	.byte 0xf1
 	.endm
 
+/*
+ * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
+ * frame pointer is replaced with an encoded pointer to pt_regs.  The encoding
+ * is just setting the LSB, which makes it an invalid stack address and is also
+ * a signal to the unwinder that it's a pt_regs pointer in disguise.
+ *
+ * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts
+ * the original rbp.
+ */
+.macro ENCODE_FRAME_POINTER ptregs_offset=0
+#ifdef CONFIG_FRAME_POINTER
+	.if \ptregs_offset
+		leaq \ptregs_offset(%rsp), %rbp
+	.else
+		mov %rsp, %rbp
+	.endif
+	orq	$0x1, %rbp
+#endif
+.endm
+
 #endif /* CONFIG_X86_64 */
 
 /*
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 21b352a11b49..acc0c6f36f3f 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -45,6 +45,7 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/export.h>
+#include <asm/frame.h>
 
 	.section .entry.text, "ax"
 
@@ -175,6 +176,22 @@
 	SET_KERNEL_GS %edx
 .endm
 
+/*
+ * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
+ * frame pointer is replaced with an encoded pointer to pt_regs.  The encoding
+ * is just setting the LSB, which makes it an invalid stack address and is also
+ * a signal to the unwinder that it's a pt_regs pointer in disguise.
+ *
+ * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the
+ * original rbp.
+ */
+.macro ENCODE_FRAME_POINTER
+#ifdef CONFIG_FRAME_POINTER
+	mov %esp, %ebp
+	orl $0x1, %ebp
+#endif
+.endm
+
 .macro RESTORE_INT_REGS
 	popl	%ebx
 	popl	%ecx
@@ -238,6 +255,23 @@ ENTRY(__switch_to_asm)
 END(__switch_to_asm)
 
 /*
+ * The unwinder expects the last frame on the stack to always be at the same
+ * offset from the end of the page, which allows it to validate the stack.
+ * Calling schedule_tail() directly would break that convention because its an
+ * asmlinkage function so its argument has to be pushed on the stack.  This
+ * wrapper creates a proper "end of stack" frame header before the call.
+ */
+ENTRY(schedule_tail_wrapper)
+	FRAME_BEGIN
+
+	pushl	%eax
+	call	schedule_tail
+	popl	%eax
+
+	FRAME_END
+	ret
+ENDPROC(schedule_tail_wrapper)
+/*
  * A newly forked process directly context switches into this address.
  *
  * eax: prev task we switched from
@@ -245,9 +279,7 @@ END(__switch_to_asm)
  * edi: kernel thread arg
  */
 ENTRY(ret_from_fork)
-	pushl	%eax
-	call	schedule_tail
-	popl	%eax
+	call	schedule_tail_wrapper
 
 	testl	%ebx, %ebx
 	jnz	1f		/* kernel threads are uncommon */
@@ -307,13 +339,13 @@ END(ret_from_exception)
 #ifdef CONFIG_PREEMPT
 ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
-need_resched:
+.Lneed_resched:
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	restore_all
 	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
 	jz	restore_all
 	call	preempt_schedule_irq
-	jmp	need_resched
+	jmp	.Lneed_resched
 END(resume_kernel)
 #endif
 
@@ -334,7 +366,7 @@ GLOBAL(__begin_SYSENTER_singlestep_region)
  */
 ENTRY(xen_sysenter_target)
 	addl	$5*4, %esp			/* remove xen-provided frame */
-	jmp	sysenter_past_esp
+	jmp	.Lsysenter_past_esp
 #endif
 
 /*
@@ -371,7 +403,7 @@ ENTRY(xen_sysenter_target)
  */
 ENTRY(entry_SYSENTER_32)
 	movl	TSS_sysenter_sp0(%esp), %esp
-sysenter_past_esp:
+.Lsysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
 	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
 	pushfl				/* pt_regs->flags (except IF = 0) */
@@ -504,9 +536,9 @@ ENTRY(entry_INT80_32)
 
 restore_all:
 	TRACE_IRQS_IRET
-restore_all_notrace:
+.Lrestore_all_notrace:
 #ifdef CONFIG_X86_ESPFIX32
-	ALTERNATIVE	"jmp restore_nocheck", "", X86_BUG_ESPFIX
+	ALTERNATIVE	"jmp .Lrestore_nocheck", "", X86_BUG_ESPFIX
 
 	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
 	/*
@@ -518,22 +550,23 @@ restore_all_notrace:
 	movb	PT_CS(%esp), %al
 	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
 	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
-	je ldt_ss				# returning to user-space with LDT SS
+	je .Lldt_ss				# returning to user-space with LDT SS
 #endif
-restore_nocheck:
+.Lrestore_nocheck:
 	RESTORE_REGS 4				# skip orig_eax/error_code
-irq_return:
+.Lirq_return:
 	INTERRUPT_RETURN
+
 .section .fixup, "ax"
 ENTRY(iret_exc	)
 	pushl	$0				# no error code
 	pushl	$do_iret_error
-	jmp	error_code
+	jmp	common_exception
 .previous
-	_ASM_EXTABLE(irq_return, iret_exc)
+	_ASM_EXTABLE(.Lirq_return, iret_exc)
 
 #ifdef CONFIG_X86_ESPFIX32
-ldt_ss:
+.Lldt_ss:
 /*
  * Setup and switch to ESPFIX stack
  *
@@ -562,7 +595,7 @@ ldt_ss:
 	 */
 	DISABLE_INTERRUPTS(CLBR_EAX)
 	lss	(%esp), %esp			/* switch to espfix segment */
-	jmp	restore_nocheck
+	jmp	.Lrestore_nocheck
 #endif
 ENDPROC(entry_INT80_32)
 
@@ -624,6 +657,7 @@ common_interrupt:
 	ASM_CLAC
 	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
 	SAVE_ALL
+	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 	movl	%esp, %eax
 	call	do_IRQ
@@ -635,6 +669,7 @@ ENTRY(name)				\
 	ASM_CLAC;			\
 	pushl	$~(nr);			\
 	SAVE_ALL;			\
+	ENCODE_FRAME_POINTER;		\
 	TRACE_IRQS_OFF			\
 	movl	%esp, %eax;		\
 	call	fn;			\
@@ -659,7 +694,7 @@ ENTRY(coprocessor_error)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_coprocessor_error
-	jmp	error_code
+	jmp	common_exception
 END(coprocessor_error)
 
 ENTRY(simd_coprocessor_error)
@@ -673,14 +708,14 @@ ENTRY(simd_coprocessor_error)
 #else
 	pushl	$do_simd_coprocessor_error
 #endif
-	jmp	error_code
+	jmp	common_exception
 END(simd_coprocessor_error)
 
 ENTRY(device_not_available)
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
 	pushl	$do_device_not_available
-	jmp	error_code
+	jmp	common_exception
 END(device_not_available)
 
 #ifdef CONFIG_PARAVIRT
@@ -694,59 +729,59 @@ ENTRY(overflow)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_overflow
-	jmp	error_code
+	jmp	common_exception
 END(overflow)
 
 ENTRY(bounds)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_bounds
-	jmp	error_code
+	jmp	common_exception
 END(bounds)
 
 ENTRY(invalid_op)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_invalid_op
-	jmp	error_code
+	jmp	common_exception
 END(invalid_op)
 
 ENTRY(coprocessor_segment_overrun)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_coprocessor_segment_overrun
-	jmp	error_code
+	jmp	common_exception
 END(coprocessor_segment_overrun)
 
 ENTRY(invalid_TSS)
 	ASM_CLAC
 	pushl	$do_invalid_TSS
-	jmp	error_code
+	jmp	common_exception
 END(invalid_TSS)
 
 ENTRY(segment_not_present)
 	ASM_CLAC
 	pushl	$do_segment_not_present
-	jmp	error_code
+	jmp	common_exception
 END(segment_not_present)
 
 ENTRY(stack_segment)
 	ASM_CLAC
 	pushl	$do_stack_segment
-	jmp	error_code
+	jmp	common_exception
 END(stack_segment)
 
 ENTRY(alignment_check)
 	ASM_CLAC
 	pushl	$do_alignment_check
-	jmp	error_code
+	jmp	common_exception
 END(alignment_check)
 
 ENTRY(divide_error)
 	ASM_CLAC
 	pushl	$0				# no error code
 	pushl	$do_divide_error
-	jmp	error_code
+	jmp	common_exception
 END(divide_error)
 
 #ifdef CONFIG_X86_MCE
@@ -754,7 +789,7 @@ ENTRY(machine_check)
 	ASM_CLAC
 	pushl	$0
 	pushl	machine_check_vector
-	jmp	error_code
+	jmp	common_exception
 END(machine_check)
 #endif
 
@@ -762,13 +797,14 @@ ENTRY(spurious_interrupt_bug)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_spurious_interrupt_bug
-	jmp	error_code
+	jmp	common_exception
 END(spurious_interrupt_bug)
 
 #ifdef CONFIG_XEN
 ENTRY(xen_hypervisor_callback)
 	pushl	$-1				/* orig_ax = -1 => not a system call */
 	SAVE_ALL
+	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 
 	/*
@@ -823,6 +859,7 @@ ENTRY(xen_failsafe_callback)
 	jmp	iret_exc
 5:	pushl	$-1				/* orig_ax = -1 => not a system call */
 	SAVE_ALL
+	ENCODE_FRAME_POINTER
 	jmp	ret_from_exception
 
 .section .fixup, "ax"
@@ -882,7 +919,7 @@ ftrace_call:
 	popl	%edx
 	popl	%ecx
 	popl	%eax
-ftrace_ret:
+.Lftrace_ret:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 .globl ftrace_graph_call
 ftrace_graph_call:
@@ -952,7 +989,7 @@ GLOBAL(ftrace_regs_call)
 	popl	%gs
 	addl	$8, %esp			/* Skip orig_ax and ip */
 	popf					/* Pop flags at end (no addl to corrupt flags) */
-	jmp	ftrace_ret
+	jmp	.Lftrace_ret
 
 	popf
 	jmp	ftrace_stub
@@ -963,7 +1000,7 @@ ENTRY(mcount)
 	jb	ftrace_stub			/* Paging not enabled yet? */
 
 	cmpl	$ftrace_stub, ftrace_trace_function
-	jnz	trace
+	jnz	.Ltrace
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	cmpl	$ftrace_stub, ftrace_graph_return
 	jnz	ftrace_graph_caller
@@ -976,7 +1013,7 @@ ftrace_stub:
 	ret
 
 	/* taken from glibc */
-trace:
+.Ltrace:
 	pushl	%eax
 	pushl	%ecx
 	pushl	%edx
@@ -1027,7 +1064,7 @@ return_to_handler:
 ENTRY(trace_page_fault)
 	ASM_CLAC
 	pushl	$trace_do_page_fault
-	jmp	error_code
+	jmp	common_exception
 END(trace_page_fault)
 #endif
 
@@ -1035,7 +1072,10 @@ ENTRY(page_fault)
 	ASM_CLAC
 	pushl	$do_page_fault
 	ALIGN
-error_code:
+	jmp common_exception
+END(page_fault)
+
+common_exception:
 	/* the function address is in %gs's slot on the stack */
 	pushl	%fs
 	pushl	%es
@@ -1047,6 +1087,7 @@ error_code:
 	pushl	%edx
 	pushl	%ecx
 	pushl	%ebx
+	ENCODE_FRAME_POINTER
 	cld
 	movl	$(__KERNEL_PERCPU), %ecx
 	movl	%ecx, %fs
@@ -1064,7 +1105,7 @@ error_code:
 	movl	%esp, %eax			# pt_regs pointer
 	call	*%edi
 	jmp	ret_from_exception
-END(page_fault)
+END(common_exception)
 
 ENTRY(debug)
 	/*
@@ -1079,6 +1120,7 @@ ENTRY(debug)
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
 	SAVE_ALL
+	ENCODE_FRAME_POINTER
 	xorl	%edx, %edx			# error code 0
 	movl	%esp, %eax			# pt_regs pointer
 
@@ -1094,11 +1136,11 @@ ENTRY(debug)
 
 .Ldebug_from_sysenter_stack:
 	/* We're on the SYSENTER stack.  Switch off. */
-	movl	%esp, %ebp
+	movl	%esp, %ebx
 	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
 	TRACE_IRQS_OFF
 	call	do_debug
-	movl	%ebp, %esp
+	movl	%ebx, %esp
 	jmp	ret_from_exception
 END(debug)
 
@@ -1116,11 +1158,12 @@ ENTRY(nmi)
 	movl	%ss, %eax
 	cmpw	$__ESPFIX_SS, %ax
 	popl	%eax
-	je	nmi_espfix_stack
+	je	.Lnmi_espfix_stack
 #endif
 
 	pushl	%eax				# pt_regs->orig_ax
 	SAVE_ALL
+	ENCODE_FRAME_POINTER
 	xorl	%edx, %edx			# zero error code
 	movl	%esp, %eax			# pt_regs pointer
 
@@ -1132,21 +1175,21 @@ ENTRY(nmi)
 
 	/* Not on SYSENTER stack. */
 	call	do_nmi
-	jmp	restore_all_notrace
+	jmp	.Lrestore_all_notrace
 
 .Lnmi_from_sysenter_stack:
 	/*
 	 * We're on the SYSENTER stack.  Switch off.  No one (not even debug)
 	 * is using the thread stack right now, so it's safe for us to use it.
 	 */
-	movl	%esp, %ebp
+	movl	%esp, %ebx
 	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
 	call	do_nmi
-	movl	%ebp, %esp
-	jmp	restore_all_notrace
+	movl	%ebx, %esp
+	jmp	.Lrestore_all_notrace
 
 #ifdef CONFIG_X86_ESPFIX32
-nmi_espfix_stack:
+.Lnmi_espfix_stack:
 	/*
 	 * create the pointer to lss back
 	 */
@@ -1159,12 +1202,13 @@ nmi_espfix_stack:
 	.endr
 	pushl	%eax
 	SAVE_ALL
+	ENCODE_FRAME_POINTER
 	FIXUP_ESPFIX_STACK			# %eax == %esp
 	xorl	%edx, %edx			# zero error code
 	call	do_nmi
 	RESTORE_REGS
 	lss	12+4(%esp), %esp		# back to espfix stack
-	jmp	irq_return
+	jmp	.Lirq_return
 #endif
 END(nmi)
 
@@ -1172,6 +1216,7 @@ ENTRY(int3)
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
 	SAVE_ALL
+	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 	xorl	%edx, %edx			# zero error code
 	movl	%esp, %eax			# pt_regs pointer
@@ -1181,14 +1226,14 @@ END(int3)
 
 ENTRY(general_protection)
 	pushl	$do_general_protection
-	jmp	error_code
+	jmp	common_exception
 END(general_protection)
 
 #ifdef CONFIG_KVM_GUEST
 ENTRY(async_page_fault)
 	ASM_CLAC
 	pushl	$do_async_page_fault
-	jmp	error_code
+	jmp	common_exception
 END(async_page_fault)
 #endif
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index ef766a358b37..5b219707c2f2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -38,12 +38,6 @@
 #include <asm/export.h>
 #include <linux/err.h>
 
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_X86_64			(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_64BIT			0x80000000
-#define __AUDIT_ARCH_LE				0x40000000
-
 .code64
 .section .entry.text, "ax"
 
@@ -469,6 +463,7 @@ END(irq_entries_start)
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
+	ENCODE_FRAME_POINTER
 
 	testb	$3, CS(%rsp)
 	jz	1f
@@ -985,6 +980,7 @@ ENTRY(xen_failsafe_callback)
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
+	ENCODE_FRAME_POINTER
 	jmp	error_exit
 END(xen_failsafe_callback)
 
@@ -1028,6 +1024,7 @@ ENTRY(paranoid_entry)
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
+	ENCODE_FRAME_POINTER 8
 	movl	$1, %ebx
 	movl	$MSR_GS_BASE, %ecx
 	rdmsr
@@ -1075,6 +1072,7 @@ ENTRY(error_entry)
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
+	ENCODE_FRAME_POINTER 8
 	xorl	%ebx, %ebx
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
@@ -1257,6 +1255,7 @@ ENTRY(nmi)
 	pushq	%r13		/* pt_regs->r13 */
 	pushq	%r14		/* pt_regs->r14 */
 	pushq	%r15		/* pt_regs->r15 */
+	ENCODE_FRAME_POINTER
 
 	/*
 	 * At this point we no longer need to worry about stack damage
@@ -1270,11 +1269,10 @@ ENTRY(nmi)
 
 	/*
 	 * Return back to user mode.  We must *not* do the normal exit
-	 * work, because we don't want to enable interrupts.  Fortunately,
-	 * do_nmi doesn't modify pt_regs.
+	 * work, because we don't want to enable interrupts.
 	 */
 	SWAPGS
-	jmp	restore_c_regs_and_iret
+	jmp	restore_regs_and_iret
 
 .Lnmi_from_kernel:
 	/*
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 23c881caabd1..e739002427ed 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -161,8 +161,6 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 	}
 
 	text_start = addr - image->sym_vvar_start;
-	current->mm->context.vdso = (void __user *)text_start;
-	current->mm->context.vdso_image = image;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -189,14 +187,12 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		do_munmap(mm, text_start, image->size);
+	} else {
+		current->mm->context.vdso = (void __user *)text_start;
+		current->mm->context.vdso_image = image;
 	}
 
 up_fail:
-	if (ret) {
-		current->mm->context.vdso = NULL;
-		current->mm->context.vdso_image = NULL;
-	}
-
 	up_write(&mm->mmap_sem);
 	return ret;
 }
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index c5047b8f777b..1c1b9fe705c8 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -36,13 +36,6 @@ static DEFINE_PER_CPU(struct pt, pt_ctx);
 
 static struct pt_pmu pt_pmu;
 
-enum cpuid_regs {
-	CR_EAX = 0,
-	CR_ECX,
-	CR_EDX,
-	CR_EBX
-};
-
 /*
  * Capabilities of Intel PT hardware, such as number of address bits or
  * supported output schemes, are cached and exported to userspace as "caps"
@@ -64,21 +57,21 @@ static struct pt_cap_desc {
 	u8		reg;
 	u32		mask;
 } pt_caps[] = {
-	PT_CAP(max_subleaf,		0, CR_EAX, 0xffffffff),
-	PT_CAP(cr3_filtering,		0, CR_EBX, BIT(0)),
-	PT_CAP(psb_cyc,			0, CR_EBX, BIT(1)),
-	PT_CAP(ip_filtering,		0, CR_EBX, BIT(2)),
-	PT_CAP(mtc,			0, CR_EBX, BIT(3)),
-	PT_CAP(ptwrite,			0, CR_EBX, BIT(4)),
-	PT_CAP(power_event_trace,	0, CR_EBX, BIT(5)),
-	PT_CAP(topa_output,		0, CR_ECX, BIT(0)),
-	PT_CAP(topa_multiple_entries,	0, CR_ECX, BIT(1)),
-	PT_CAP(single_range_output,	0, CR_ECX, BIT(2)),
-	PT_CAP(payloads_lip,		0, CR_ECX, BIT(31)),
-	PT_CAP(num_address_ranges,	1, CR_EAX, 0x3),
-	PT_CAP(mtc_periods,		1, CR_EAX, 0xffff0000),
-	PT_CAP(cycle_thresholds,	1, CR_EBX, 0xffff),
-	PT_CAP(psb_periods,		1, CR_EBX, 0xffff0000),
+	PT_CAP(max_subleaf,		0, CPUID_EAX, 0xffffffff),
+	PT_CAP(cr3_filtering,		0, CPUID_EBX, BIT(0)),
+	PT_CAP(psb_cyc,			0, CPUID_EBX, BIT(1)),
+	PT_CAP(ip_filtering,		0, CPUID_EBX, BIT(2)),
+	PT_CAP(mtc,			0, CPUID_EBX, BIT(3)),
+	PT_CAP(ptwrite,			0, CPUID_EBX, BIT(4)),
+	PT_CAP(power_event_trace,	0, CPUID_EBX, BIT(5)),
+	PT_CAP(topa_output,		0, CPUID_ECX, BIT(0)),
+	PT_CAP(topa_multiple_entries,	0, CPUID_ECX, BIT(1)),
+	PT_CAP(single_range_output,	0, CPUID_ECX, BIT(2)),
+	PT_CAP(payloads_lip,		0, CPUID_ECX, BIT(31)),
+	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x3),
+	PT_CAP(mtc_periods,		1, CPUID_EAX, 0xffff0000),
+	PT_CAP(cycle_thresholds,	1, CPUID_EBX, 0xffff),
+	PT_CAP(psb_periods,		1, CPUID_EBX, 0xffff0000),
 };
 
 static u32 pt_cap_get(enum pt_capabilities cap)
@@ -213,10 +206,10 @@ static int __init pt_pmu_hw_init(void)
 
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
 		cpuid_count(20, i,
-			    &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]);
+			    &pt_pmu.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM]);
 	}
 
 	ret = -ENOMEM;
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index d625b651e526..4dba597c5807 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -227,6 +227,7 @@
 #define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA  ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
 #define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
 #define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
@@ -280,8 +281,10 @@
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_RDPID	(16*32+ 22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index d31881188431..29a594a3b82a 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -21,7 +21,6 @@ enum die_val {
 	DIE_NMIUNKNOWN,
 };
 
-extern void printk_address(unsigned long address);
 extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c84605bb2a15..1f6a92903b09 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -137,6 +137,17 @@ struct cpuinfo_x86 {
 	u32			microcode;
 };
 
+struct cpuid_regs {
+	u32 eax, ebx, ecx, edx;
+};
+
+enum cpuid_regs_idx {
+	CPUID_EAX = 0,
+	CPUID_EBX,
+	CPUID_ECX,
+	CPUID_EDX,
+};
+
 #define X86_VENDOR_INTEL	0
 #define X86_VENDOR_CYRIX	1
 #define X86_VENDOR_AMD		2
@@ -178,6 +189,9 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+				    unsigned int sub_leaf,
+				    enum cpuid_regs_idx reg);
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 37f2e0b377ad..a3269c897ec5 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -30,8 +30,7 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
 int get_stack_info(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info, unsigned long *visit_mask);
 
-void stack_type_str(enum stack_type type, const char **begin,
-		    const char **end);
+const char *stack_type_name(enum stack_type type);
 
 static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
 {
@@ -43,8 +42,6 @@ static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
 		addr + len > begin && addr + len <= end);
 }
 
-extern int kstack_depth_to_print;
-
 #ifdef CONFIG_X86_32
 #define STACKSLOTS_PER_LINE 8
 #else
@@ -86,9 +83,6 @@ get_stack_pointer(struct task_struct *task, struct pt_regs *regs)
 void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, char *log_lvl);
 
-void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-			unsigned long *sp, char *log_lvl);
-
 extern unsigned int code_bytes;
 
 /* The form of the top of the frame on the stack */
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 46de9ac4b990..c5a7f3a930dd 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -13,6 +13,7 @@ struct unwind_state {
 	int graph_idx;
 #ifdef CONFIG_FRAME_POINTER
 	unsigned long *bp;
+	struct pt_regs *regs;
 #else
 	unsigned long *sp;
 #endif
@@ -47,7 +48,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 	if (unwind_done(state))
 		return NULL;
 
-	return state->bp + 1;
+	return state->regs ? &state->regs->ip : state->bp + 1;
+}
+
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return NULL;
+
+	return state->regs;
 }
 
 #else /* !CONFIG_FRAME_POINTER */
@@ -58,6 +67,11 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 	return NULL;
 }
 
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_FRAME_POINTER */
 
 #endif /* _ASM_X86_UNWIND_H */
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index e728699db774..3a01996db58f 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -89,8 +89,13 @@ static inline unsigned int __getcpu(void)
 	 * works on all CPUs.  This is volatile so that it orders
 	 * correctly wrt barrier() and to keep gcc from cleverly
 	 * hoisting it out of the calling function.
+	 *
+	 * If RDPID is available, use it.
 	 */
-	asm volatile ("lsl %1,%0" : "=r" (p) : "r"