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
  ...

1 files changed, 26 insertions, 26 deletions

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index b4421cc191b0..a15d381e6020 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -66,13 +66,8 @@ startup_64:
 	 * tables and then reload them.
 	 */
 
-	/*
-	 * Setup stack for verify_cpu(). "-8" because initial_stack is defined
-	 * this way, see below. Our best guess is a NULL ptr for stack
-	 * termination heuristics and we don't want to break anything which
-	 * might depend on it (kgdb, ...).
-	 */
-	leaq	(__end_init_task - 8)(%rip), %rsp
+	/* Set up the stack for verify_cpu(), similar to initial_stack below */
+	leaq	(__end_init_task - SIZEOF_PTREGS)(%rip), %rsp
 
 	/* Sanitize CPU configuration */
 	call verify_cpu
@@ -117,20 +112,20 @@ startup_64:
 	movq	%rdi, %rax
 	shrq	$PGDIR_SHIFT, %rax
 
-	leaq	(4096 + _KERNPG_TABLE)(%rbx), %rdx
+	leaq	(PAGE_SIZE + _KERNPG_TABLE)(%rbx), %rdx
 	movq	%rdx, 0(%rbx,%rax,8)
 	movq	%rdx, 8(%rbx,%rax,8)
 
-	addq	$4096, %rdx
+	addq	$PAGE_SIZE, %rdx
 	movq	%rdi, %rax
 	shrq	$PUD_SHIFT, %rax
 	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, 4096(%rbx,%rax,8)
+	movq	%rdx, PAGE_SIZE(%rbx,%rax,8)
 	incl	%eax
 	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, 4096(%rbx,%rax,8)
+	movq	%rdx, PAGE_SIZE(%rbx,%rax,8)
 
-	addq	$8192, %rbx
+	addq	$PAGE_SIZE * 2, %rbx
 	movq	%rdi, %rax
 	shrq	$PMD_SHIFT, %rdi
 	addq	$(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax
@@ -265,13 +260,17 @@ ENTRY(secondary_startup_64)
 	movl	$MSR_GS_BASE,%ecx
 	movl	initial_gs(%rip),%eax
 	movl	initial_gs+4(%rip),%edx
-	wrmsr	
+	wrmsr
 
 	/* rsi is pointer to real mode structure with interesting info.
 	   pass it to C */
 	movq	%rsi, %rdi
-	
-	/* Finally jump to run C code and to be on real kernel address
+	jmp	start_cpu
+ENDPROC(secondary_startup_64)
+
+ENTRY(start_cpu)
+	/*
+	 * Jump to run C code and to be on a real kernel address.
 	 * Since we are running on identity-mapped space we have to jump
 	 * to the full 64bit address, this is only possible as indirect
 	 * jump.  In addition we need to ensure %cs is set so we make this
@@ -295,12 +294,13 @@ ENTRY(secondary_startup_64)
 	 *	REX.W + FF /5 JMP m16:64 Jump far, absolute indirect,
 	 *		address given in m16:64.
 	 */
-	movq	initial_code(%rip),%rax
-	pushq	$0		# fake return address to stop unwinder
+	call	1f		# put return address on stack for unwinder
+1:	xorq	%rbp, %rbp	# clear frame pointer
+	movq	initial_code(%rip), %rax
 	pushq	$__KERNEL_CS	# set correct cs
 	pushq	%rax		# target address in negative space
 	lretq
-ENDPROC(secondary_startup_64)
+ENDPROC(start_cpu)
 
 #include "verify_cpu.S"
 
@@ -308,15 +308,11 @@ ENDPROC(secondary_startup_64)
 /*
  * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
  * up already except stack. We just set up stack here. Then call
- * start_secondary().
+ * start_secondary() via start_cpu().
  */
 ENTRY(start_cpu0)
-	movq initial_stack(%rip),%rsp
-	movq	initial_code(%rip),%rax
-	pushq	$0		# fake return address to stop unwinder
-	pushq	$__KERNEL_CS	# set correct cs
-	pushq	%rax		# target address in negative space
-	lretq
+	movq	initial_stack(%rip), %rsp
+	jmp	start_cpu
 ENDPROC(start_cpu0)
 #endif
 
@@ -328,7 +324,11 @@ ENDPROC(start_cpu0)
 	GLOBAL(initial_gs)
 	.quad	INIT_PER_CPU_VAR(irq_stack_union)
 	GLOBAL(initial_stack)
-	.quad  init_thread_union+THREAD_SIZE-8
+	/*
+	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
+	 * unwinder reliably detect the end of the stack.
+	 */
+	.quad  init_thread_union + THREAD_SIZE - SIZEOF_PTREGS
 	__FINITDATA
 
 bad_address: