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:

 - Introduce the ORC unwinder, which can be enabled via
   CONFIG_ORC_UNWINDER=y.

   The ORC unwinder is a lightweight, Linux kernel specific debuginfo
   implementation, which aims to be DWARF done right for unwinding.
   Objtool is used to generate the ORC unwinder tables during build, so
   the data format is flexible and kernel internal: there's no
   dependency on debuginfo created by an external toolchain.

   The ORC unwinder is almost two orders of magnitude faster than the
   (out of tree) DWARF unwinder - which is important for perf call graph
   profiling. It is also significantly simpler and is coded defensively:
   there has not been a single ORC related kernel crash so far, even
   with early versions. (knock on wood!)

   But the main advantage is that enabling the ORC unwinder allows
   CONFIG_FRAME_POINTERS to be turned off - which speeds up the kernel
   measurably:

   With frame pointers disabled, GCC does not have to add frame pointer
   instrumentation code to every function in the kernel. The kernel's
   .text size decreases by about 3.2%, resulting in better cache
   utilization and fewer instructions executed, resulting in a broad
   kernel-wide speedup. Average speedup of system calls should be
   roughly in the 1-3% range - measurements by Mel Gorman [1] have shown
   a speedup of 5-10% for some function execution intense workloads.

   The main cost of the unwinder is that the unwinder data has to be
   stored in RAM: the memory cost is 2-4MB of RAM, depending on kernel
   config - which is a modest cost on modern x86 systems.

   Given how young the ORC unwinder code is it's not enabled by default
   - but given the performance advantages the plan is to eventually make
   it the default unwinder on x86.

   See Documentation/x86/orc-unwinder.txt for more details.

 - Remove lguest support: its intended role was that of a temporary
   proof of concept for virtualization, plus its removal will enable the
   reduction (removal) of the paravirt API as well, so Rusty agreed to
   its removal. (Juergen Gross)

 - Clean up and fix FSGS related functionality (Andy Lutomirski)

 - Clean up IO access APIs (Andy Shevchenko)

 - Enhance the symbol namespace (Jiri Slaby)

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  objtool: Handle GCC stack pointer adjustment bug
  x86/entry/64: Use ENTRY() instead of ALIGN+GLOBAL for stub32_clone()
  x86/fpu/math-emu: Add ENDPROC to functions
  x86/boot/64: Extract efi_pe_entry() from startup_64()
  x86/boot/32: Extract efi_pe_entry() from startup_32()
  x86/lguest: Remove lguest support
  x86/paravirt/xen: Remove xen_patch()
  objtool: Fix objtool fallthrough detection with function padding
  x86/xen/64: Fix the reported SS and CS in SYSCALL
  objtool: Track DRAP separately from callee-saved registers
  objtool: Fix validate_branch() return codes
  x86: Clarify/fix no-op barriers for text_poke_bp()
  x86/switch_to/64: Rewrite FS/GS switching yet again to fix AMD CPUs
  selftests/x86/fsgsbase: Test selectors 1, 2, and 3
  x86/fsgsbase/64: Report FSBASE and GSBASE correctly in core dumps
  x86/fsgsbase/64: Fully initialize FS and GS state in start_thread_common
  x86/asm: Fix UNWIND_HINT_REGS macro for older binutils
  x86/asm/32: Fix regs_get_register() on segment registers
  x86/xen/64: Rearrange the SYSCALL entries
  x86/asm/32: Remove a bunch of '& 0xffff' from pt_regs segment reads
  ...

4 files changed, 152 insertions, 44 deletions

diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index 9976fcecd17e..af28a8a24366 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -2,7 +2,6 @@
 # Makefile for the x86 low level entry code
 #
 
-OBJECT_FILES_NON_STANDARD_entry_$(BITS).o   := y
 OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
 
 CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 05ed3d393da7..640aafebdc00 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -1,4 +1,5 @@
 #include <linux/jump_label.h>
+#include <asm/unwind_hints.h>
 
 /*
 
@@ -112,6 +113,7 @@ For 32-bit we have the following conventions - kernel is built with
 	movq %rdx, 12*8+\offset(%rsp)
 	movq %rsi, 13*8+\offset(%rsp)
 	movq %rdi, 14*8+\offset(%rsp)
+	UNWIND_HINT_REGS offset=\offset extra=0
 	.endm
 	.macro SAVE_C_REGS offset=0
 	SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
@@ -136,6 +138,7 @@ For 32-bit we have the following conventions - kernel is built with
 	movq %r12, 3*8+\offset(%rsp)
 	movq %rbp, 4*8+\offset(%rsp)
 	movq %rbx, 5*8+\offset(%rsp)
+	UNWIND_HINT_REGS offset=\offset
 	.endm
 
 	.macro RESTORE_EXTRA_REGS offset=0
@@ -145,6 +148,7 @@ For 32-bit we have the following conventions - kernel is built with
 	movq 3*8+\offset(%rsp), %r12
 	movq 4*8+\offset(%rsp), %rbp
 	movq 5*8+\offset(%rsp), %rbx
+	UNWIND_HINT_REGS offset=\offset extra=0
 	.endm
 
 	.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
@@ -167,6 +171,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 	movq 13*8(%rsp), %rsi
 	movq 14*8(%rsp), %rdi
+	UNWIND_HINT_IRET_REGS offset=16*8
 	.endm
 	.macro RESTORE_C_REGS
 	RESTORE_C_REGS_HELPER 1,1,1,1,1
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index ce8dc33dd640..ca0b250eefc4 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -36,6 +36,7 @@
 #include <asm/smap.h>
 #include <asm/pgtable_types.h>
 #include <asm/export.h>
+#include <asm/frame.h>
 #include <linux/err.h>
 
 .code64
@@ -43,9 +44,10 @@
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_usergs_sysret64)
+	UNWIND_HINT_EMPTY
 	swapgs
 	sysretq
-ENDPROC(native_usergs_sysret64)
+END(native_usergs_sysret64)
 #endif /* CONFIG_PARAVIRT */
 
 .macro TRACE_IRQS_IRETQ
@@ -134,19 +136,14 @@ ENDPROC(native_usergs_sysret64)
  */
 
 ENTRY(entry_SYSCALL_64)
+	UNWIND_HINT_EMPTY
 	/*
 	 * Interrupts are off on entry.
 	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
 	 * it is too small to ever cause noticeable irq latency.
 	 */
-	SWAPGS_UNSAFE_STACK
-	/*
-	 * A hypervisor implementation might want to use a label
-	 * after the swapgs, so that it can do the swapgs
-	 * for the guest and jump here on syscall.
-	 */
-GLOBAL(entry_SYSCALL_64_after_swapgs)
 
+	swapgs
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
@@ -158,6 +155,7 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	pushq	%r11				/* pt_regs->flags */
 	pushq	$__USER_CS			/* pt_regs->cs */
 	pushq	%rcx				/* pt_regs->ip */
+GLOBAL(entry_SYSCALL_64_after_hwframe)
 	pushq	%rax				/* pt_regs->orig_ax */
 	pushq	%rdi				/* pt_regs->di */
 	pushq	%rsi				/* pt_regs->si */
@@ -169,6 +167,7 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	pushq	%r10				/* pt_regs->r10 */
 	pushq	%r11				/* pt_regs->r11 */
 	sub	$(6*8), %rsp			/* pt_regs->bp, bx, r12-15 not saved */
+	UNWIND_HINT_REGS extra=0
 
 	/*
 	 * If we need to do entry work or if we guess we'll need to do
@@ -223,6 +222,7 @@ entry_SYSCALL_64_fastpath:
 	movq	EFLAGS(%rsp), %r11
 	RESTORE_C_REGS_EXCEPT_RCX_R11
 	movq	RSP(%rsp), %rsp
+	UNWIND_HINT_EMPTY
 	USERGS_SYSRET64
 
 1:
@@ -316,6 +316,7 @@ syscall_return_via_sysret:
 	/* rcx and r11 are already restored (see code above) */
 	RESTORE_C_REGS_EXCEPT_RCX_R11
 	movq	RSP(%rsp), %rsp
+	UNWIND_HINT_EMPTY
 	USERGS_SYSRET64
 
 opportunistic_sysret_failed:
@@ -343,6 +344,7 @@ ENTRY(stub_ptregs_64)
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	popq	%rax
+	UNWIND_HINT_REGS extra=0
 	jmp	entry_SYSCALL64_slow_path
 
 1:
@@ -351,6 +353,7 @@ END(stub_ptregs_64)
 
 .macro ptregs_stub func
 ENTRY(ptregs_\func)
+	UNWIND_HINT_FUNC
 	leaq	\func(%rip), %rax
 	jmp	stub_ptregs_64
 END(ptregs_\func)
@@ -367,6 +370,7 @@ END(ptregs_\func)
  * %rsi: next task
  */
 ENTRY(__switch_to_asm)
+	UNWIND_HINT_FUNC
 	/*
 	 * Save callee-saved registers
 	 * This must match the order in inactive_task_frame
@@ -406,6 +410,7 @@ END(__switch_to_asm)
  * r12: kernel thread arg
  */
 ENTRY(ret_from_fork)
+	UNWIND_HINT_EMPTY
 	movq	%rax, %rdi
 	call	schedule_tail			/* rdi: 'prev' task parameter */
 
@@ -413,6 +418,7 @@ ENTRY(ret_from_fork)
 	jnz	1f				/* kernel threads are uncommon */
 
 2:
+	UNWIND_HINT_REGS
 	movq	%rsp, %rdi
 	call	syscall_return_slowpath	/* returns with IRQs disabled */
 	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
@@ -440,13 +446,102 @@ END(ret_from_fork)
 ENTRY(irq_entries_start)
     vector=FIRST_EXTERNAL_VECTOR
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+	UNWIND_HINT_IRET_REGS
 	pushq	$(~vector+0x80)			/* Note: always in signed byte range */
-    vector=vector+1
 	jmp	common_interrupt
 	.align	8
+	vector=vector+1
     .endr
 END(irq_entries_start)
 
+.macro DEBUG_ENTRY_ASSERT_IRQS_OFF
+#ifdef CONFIG_DEBUG_ENTRY
+	pushfq
+	testl $X86_EFLAGS_IF, (%rsp)
+	jz .Lokay_\@
+	ud2
+.Lokay_\@:
+	addq $8, %rsp
+#endif
+.endm
+
+/*
+ * Enters the IRQ stack if we're not already using it.  NMI-safe.  Clobbers
+ * flags and puts old RSP into old_rsp, and leaves all other GPRs alone.
+ * Requires kernel GSBASE.
+ *
+ * The invariant is that, if irq_count != -1, then the IRQ stack is in use.
+ */
+.macro ENTER_IRQ_STACK regs=1 old_rsp
+	DEBUG_ENTRY_ASSERT_IRQS_OFF
+	movq	%rsp, \old_rsp
+
+	.if \regs
+	UNWIND_HINT_REGS base=\old_rsp
+	.endif
+
+	incl	PER_CPU_VAR(irq_count)
+	jnz	.Lirq_stack_push_old_rsp_\@
+
+	/*
+	 * Right now, if we just incremented irq_count to zero, we've
+	 * claimed the IRQ stack but we haven't switched to it yet.
+	 *
+	 * If anything is added that can interrupt us here without using IST,
+	 * it must be *extremely* careful to limit its stack usage.  This
+	 * could include kprobes and a hypothetical future IST-less #DB
+	 * handler.
+	 *
+	 * The OOPS unwinder relies on the word at the top of the IRQ
+	 * stack linking back to the previous RSP for the entire time we're
+	 * on the IRQ stack.  For this to work reliably, we need to write
+	 * it before we actually move ourselves to the IRQ stack.
+	 */
+
+	movq	\old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8)
+	movq	PER_CPU_VAR(irq_stack_ptr), %rsp
+
+#ifdef CONFIG_DEBUG_ENTRY
+	/*
+	 * If the first movq above becomes wrong due to IRQ stack layout
+	 * changes, the only way we'll notice is if we try to unwind right
+	 * here.  Assert that we set up the stack right to catch this type
+	 * of bug quickly.
+	 */
+	cmpq	-8(%rsp), \old_rsp
+	je	.Lirq_stack_okay\@
+	ud2
+	.Lirq_stack_okay\@:
+#endif
+
+.Lirq_stack_push_old_rsp_\@:
+	pushq	\old_rsp
+
+	.if \regs
+	UNWIND_HINT_REGS indirect=1
+	.endif
+.endm
+
+/*
+ * Undoes ENTER_IRQ_STACK.
+ */
+.macro LEAVE_IRQ_STACK regs=1
+	DEBUG_ENTRY_ASSERT_IRQS_OFF
+	/* We need to be off the IRQ stack before decrementing irq_count. */
+	popq	%rsp
+
+	.if \regs
+	UNWIND_HINT_REGS
+	.endif
+
+	/*
+	 * As in ENTER_IRQ_STACK, irq_count == 0, we are still claiming
+	 * the irq stack but we're not on it.
+	 */
+
+	decl	PER_CPU_VAR(irq_count)
+.endm
+
 /*
  * Interrupt entry/exit.
  *
@@ -485,17 +580,7 @@ END(irq_entries_start)
 	CALL_enter_from_user_mode
 
 1:
-	/*
-	 * Save previous stack pointer, optionally switch to interrupt stack.
-	 * irq_count is used to check if a CPU is already on an interrupt stack
-	 * or not. While this is essentially redundant with preempt_count it is
-	 * a little cheaper to use a separate counter in the PDA (short of
-	 * moving irq_enter into assembly, which would be too much work)
-	 */
-	movq	%rsp, %rdi
-	incl	PER_CPU_VAR(irq_count)
-	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
-	pushq	%rdi
+	ENTER_IRQ_STACK old_rsp=%rdi
 	/* We entered an interrupt context - irqs are off: */
 	TRACE_IRQS_OFF
 
@@ -515,10 +600,8 @@ common_interrupt:
 ret_from_intr:
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
-	decl	PER_CPU_VAR(irq_count)
 
-	/* Restore saved previous stack */
-	popq	%rsp
+	LEAVE_IRQ_STACK
 
 	testb	$3, CS(%rsp)
 	jz	retint_kernel
@@ -561,6 +644,7 @@ restore_c_regs_and_iret:
 	INTERRUPT_RETURN
 
 ENTRY(native_iret)
+	UNWIND_HINT_IRET_REGS
 	/*
 	 * Are we returning to a stack segment from the LDT?  Note: in
 	 * 64-bit mode SS:RSP on the exception stack is always valid.
@@ -633,6 +717,7 @@ native_irq_return_ldt:
 	orq	PER_CPU_VAR(espfix_stack), %rax
 	SWAPGS
 	movq	%rax, %rsp
+	UNWIND_HINT_IRET_REGS offset=8
 
 	/*
 	 * At this point, we cannot write to the stack any more, but we can
@@ -654,6 +739,7 @@ END(common_interrupt)
  */
 .macro apicinterrupt3 num sym do_sym
 ENTRY(\sym)
+	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
 	pushq	$~(\num)
 .Lcommon_\sym:
@@ -735,6 +821,8 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
+	UNWIND_HINT_IRET_REGS offset=8
+
 	/* Sanity check */
 	.if \shift_ist != -1 && \paranoid == 0
 	.error "using shift_ist requires paranoid=1"
@@ -758,6 +846,7 @@ ENTRY(\sym)
 	.else
 	call	error_entry
 	.endif
+	UNWIND_HINT_REGS
 	/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
 
 	.if \paranoid
@@ -855,6 +944,7 @@ idtentry simd_coprocessor_error		do_simd_coprocessor_error	has_error_code=0
 	 * edi:  new selector
 	 */
 ENTRY(native_load_gs_index)
+	FRAME_BEGIN
 	pushfq
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
 	SWAPGS
@@ -863,8 +953,9 @@ ENTRY(native_load_gs_index)
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
 	SWAPGS
 	popfq
+	FRAME_END
 	ret
-END(native_load_gs_index)
+ENDPROC(native_load_gs_index)
 EXPORT_SYMBOL(native_load_gs_index)
 
 	_ASM_EXTABLE(.Lgs_change, bad_gs)
@@ -887,14 +978,12 @@ bad_gs:
 ENTRY(do_softirq_own_stack)
 	pushq	%rbp
 	mov	%rsp, %rbp
-	incl	PER_CPU_VAR(irq_count)
-	cmove	PER_CPU_VAR(irq_stack_ptr), %rsp
-	push	%rbp				/* frame pointer backlink */
+	ENTER_IRQ_STACK regs=0 old_rsp=%r11
 	call	__do_softirq
+	LEAVE_IRQ_STACK regs=0
 	leaveq
-	decl	PER_CPU_VAR(irq_count)
 	ret
-END(do_softirq_own_stack)
+ENDPROC(do_softirq_own_stack)
 
 #ifdef CONFIG_XEN
 idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
@@ -918,14 +1007,14 @@ ENTRY(xen_do_hypervisor_callback)		/* do_hypervisor_callback(struct *pt_regs) */
  * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
  * see the correct pointer to the pt_regs
  */
+	UNWIND_HINT_FUNC
 	movq	%rdi, %rsp			/* we don't return, adjust the stack frame */
-11:	incl	PER_CPU_VAR(irq_count)
-	movq	%rsp, %rbp
-	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
-	pushq	%rbp				/* frame pointer backlink */
+	UNWIND_HINT_REGS
+
+	ENTER_IRQ_STACK old_rsp=%r10
 	call	xen_evtchn_do_upcall
-	popq	%rsp
-	decl	PER_CPU_VAR(irq_count)
+	LEAVE_IRQ_STACK
+
 #ifndef CONFIG_PREEMPT
 	call	xen_maybe_preempt_hcall
 #endif
@@ -946,6 +1035,7 @@ END(xen_do_hypervisor_callback)
  * with its current contents: any discrepancy means we in category 1.
  */
 ENTRY(xen_failsafe_callback)
+	UNWIND_HINT_EMPTY
 	movl	%ds, %ecx
 	cmpw	%cx, 0x10(%rsp)
 	jne	1f
@@ -965,11 +1055,13 @@ ENTRY(xen_failsafe_callback)
 	pushq	$0				/* RIP */
 	pushq	%r11
 	pushq	%rcx
+	UNWIND_HINT_IRET_REGS offset=8
 	jmp	general_protection
 1:	/* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
 	movq	(%rsp), %rcx
 	movq	8(%rsp), %r11
 	addq	$0x30, %rsp
+	UNWIND_HINT_IRET_REGS
 	pushq	$-1 /* orig_ax = -1 => not a system call */
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
@@ -1015,6 +1107,7 @@ idtentry machine_check					has_error_code=0	paranoid=1 do_sym=*machine_check_vec
  * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
  */
 ENTRY(paranoid_entry)
+	UNWIND_HINT_FUNC
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
@@ -1042,6 +1135,7 @@ END(paranoid_entry)
  * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
  */
 ENTRY(paranoid_exit)
+	UNWIND_HINT_REGS
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF_DEBUG
 	testl	%ebx, %ebx			/* swapgs needed? */
@@ -1063,6 +1157,7 @@ END(paranoid_exit)
  * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
+	UNWIND_HINT_FUNC
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
@@ -1147,6 +1242,7 @@ END(error_entry)
  *   0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
  */
 ENTRY(error_exit)
+	UNWIND_HINT_REGS
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	testl	%ebx, %ebx
@@ -1156,6 +1252,7 @@ END(error_exit)
 
 /* Runs on exception stack */
 ENTRY(nmi)
+	UNWIND_HINT_IRET_REGS
 	/*
 	 * Fix up the exception frame if we're on Xen.
 	 * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most
@@ -1229,11 +1326,13 @@ ENTRY(nmi)
 	cld
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	UNWIND_HINT_IRET_REGS base=%rdx offset=8
 	pushq	5*8(%rdx)	/* pt_regs->ss */
 	pushq	4*8(%rdx)	/* pt_regs->rsp */
 	pushq	3*8(%rdx)	/* pt_regs->flags */
 	pushq	2*8(%rdx)	/* pt_regs->cs */
 	pushq	1*8(%rdx)	/* pt_regs->rip */
+	UNWIND_HINT_IRET_REGS
 	pushq   $-1		/* pt_regs->orig_ax */
 	pushq   %rdi		/* pt_regs->di */
 	pushq   %rsi		/* pt_regs->si */
@@ -1250,6 +1349,7 @@ ENTRY(nmi)
 	pushq	%r13		/* pt_regs->r13 */
 	pushq	%r14		/* pt_regs->r14 */
 	pushq	%r15		/* pt_regs->r15 */
+	UNWIND_HINT_REGS
 	ENCODE_FRAME_POINTER
 
 	/*
@@ -1404,6 +1504,7 @@ first_nmi:
 	.rept 5
 	pushq	11*8(%rsp)
 	.endr
+	UNWIND_HINT_IRET_REGS
 
 	/* Everything up to here is safe from nested NMIs */
 
@@ -1419,6 +1520,7 @@ first_nmi:
 	pushq	$__KERNEL_CS	/* CS */
 	pushq	$1f		/* RIP */
 	INTERRUPT_RETURN	/* continues at repeat_nmi below */
+	UNWIND_HINT_IRET_REGS
 1:
 #endif
 
@@ -1468,6 +1570,7 @@ end_repeat_nmi:
 	 * exceptions might do.
 	 */
 	call	paranoid_entry
+	UNWIND_HINT_REGS
 
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
 	movq	%rsp, %rdi
@@ -1505,17 +1608,19 @@ nmi_restore:
 END(nmi)
 
 ENTRY(ignore_sysret)
+	UNWIND_HINT_EMPTY
 	mov	$-ENOSYS, %eax
 	sysret
 END(ignore_sysret)
 
 ENTRY(rewind_stack_do_exit)
+	UNWIND_HINT_FUNC
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
-	leaq	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%rax), %rsp
+	leaq	-PTREGS_SIZE(%rax), %rsp
+	UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE
 
 	call	do_exit
-1:	jmp 1b
 END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index e1721dafbcb1..4b86d8da3ea3 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -183,21 +183,20 @@ ENDPROC(entry_SYSENTER_compat)
  */
 ENTRY(entry_SYSCALL_compat)
 	/* Interrupts are off on entry. */
-	SWAPGS_UNSAFE_STACK
+	swapgs
 
 	/* Stash user ESP and switch to the kernel stack. */
 	movl	%esp, %r8d
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
-	/* Zero-extending 32-bit regs, do not remove */
-	movl	%eax, %eax
-
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER32_DS		/* pt_regs->ss */
 	pushq	%r8			/* pt_regs->sp */
 	pushq	%r11			/* pt_regs->flags */
 	pushq	$__USER32_CS		/* pt_regs->cs */
 	pushq	%rcx			/* pt_regs->ip */
+GLOBAL(entry_SYSCALL_compat_after_hwframe)
+	movl	%eax, %eax		/* discard orig_ax high bits */
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
@@ -342,8 +341,7 @@ ENTRY(entry_INT80_compat)
 	jmp	restore_regs_and_iret
 END(entry_INT80_compat)
 
-	ALIGN
-GLOBAL(stub32_clone)
+ENTRY(stub32_clone)
 	/*
 	 * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
 	 * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
@@ -353,3 +351,4 @@ GLOBAL(stub32_clone)
 	 */
 	xchg	%r8, %rcx
 	jmp	sys_clone
+ENDPROC(stub32_clone)