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
  ...

6 files changed, 48 insertions, 152 deletions

diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 811e4ddb3f37..98491521bb43 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -981,59 +981,6 @@ void __ref xen_setup_vcpu_info_placement(void)
 	}
 }
 
-static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
-			  unsigned long addr, unsigned len)
-{
-	char *start, *end, *reloc;
-	unsigned ret;
-
-	start = end = reloc = NULL;
-
-#define SITE(op, x)							\
-	case PARAVIRT_PATCH(op.x):					\
-	if (xen_have_vcpu_info_placement) {				\
-		start = (char *)xen_##x##_direct;			\
-		end = xen_##x##_direct_end;				\
-		reloc = xen_##x##_direct_reloc;				\
-	}								\
-	goto patch_site
-
-	switch (type) {
-		SITE(pv_irq_ops, irq_enable);
-		SITE(pv_irq_ops, irq_disable);
-		SITE(pv_irq_ops, save_fl);
-		SITE(pv_irq_ops, restore_fl);
-#undef SITE
-
-	patch_site:
-		if (start == NULL || (end-start) > len)
-			goto default_patch;
-
-		ret = paravirt_patch_insns(insnbuf, len, start, end);
-
-		/* Note: because reloc is assigned from something that
-		   appears to be an array, gcc assumes it's non-null,
-		   but doesn't know its relationship with start and
-		   end. */
-		if (reloc > start && reloc < end) {
-			int reloc_off = reloc - start;
-			long *relocp = (long *)(insnbuf + reloc_off);
-			long delta = start - (char *)addr;
-
-			*relocp += delta;
-		}
-		break;
-
-	default_patch:
-	default:
-		ret = paravirt_patch_default(type, clobbers, insnbuf,
-					     addr, len);
-		break;
-	}
-
-	return ret;
-}
-
 static const struct pv_info xen_info __initconst = {
 	.shared_kernel_pmd = 0,
 
@@ -1043,10 +990,6 @@ static const struct pv_info xen_info __initconst = {
 	.name = "Xen",
 };
 
-static const struct pv_init_ops xen_init_ops __initconst = {
-	.patch = xen_patch,
-};
-
 static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.cpuid = xen_cpuid,
 
@@ -1244,7 +1187,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
-	pv_init_ops = xen_init_ops;
+	pv_init_ops.patch = paravirt_patch_default;
 	pv_cpu_ops = xen_cpu_ops;
 
 	x86_platform.get_nmi_reason = xen_get_nmi_reason;
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index eff224df813f..dcd31fa39b5d 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -1,14 +1,8 @@
 /*
- * Asm versions of Xen pv-ops, suitable for either direct use or
- * inlining.  The inline versions are the same as the direct-use
- * versions, with the pre- and post-amble chopped off.
- *
- * This code is encoded for size rather than absolute efficiency, with
- * a view to being able to inline as much as possible.
+ * Asm versions of Xen pv-ops, suitable for direct use.
  *
  * We only bother with direct forms (ie, vcpu in percpu data) of the
- * operations here; the indirect forms are better handled in C, since
- * they're generally too large to inline anyway.
+ * operations here; the indirect forms are better handled in C.
  */
 
 #include <asm/asm-offsets.h>
@@ -16,7 +10,7 @@
 #include <asm/processor-flags.h>
 #include <asm/frame.h>
 
-#include "xen-asm.h"
+#include <linux/linkage.h>
 
 /*
  * Enable events.  This clears the event mask and tests the pending
@@ -38,13 +32,11 @@ ENTRY(xen_irq_enable_direct)
 	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
 	jz 1f
 
-2:	call check_events
+	call check_events
 1:
-ENDPATCH(xen_irq_enable_direct)
 	FRAME_END
 	ret
 	ENDPROC(xen_irq_enable_direct)
-	RELOC(xen_irq_enable_direct, 2b+1)
 
 
 /*
@@ -53,10 +45,8 @@ ENDPATCH(xen_irq_enable_direct)
  */
 ENTRY(xen_irq_disable_direct)
 	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
-ENDPATCH(xen_irq_disable_direct)
 	ret
-	ENDPROC(xen_irq_disable_direct)
-	RELOC(xen_irq_disable_direct, 0)
+ENDPROC(xen_irq_disable_direct)
 
 /*
  * (xen_)save_fl is used to get the current interrupt enable status.
@@ -71,10 +61,8 @@ ENTRY(xen_save_fl_direct)
 	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 	setz %ah
 	addb %ah, %ah
-ENDPATCH(xen_save_fl_direct)
 	ret
 	ENDPROC(xen_save_fl_direct)
-	RELOC(xen_save_fl_direct, 0)
 
 
 /*
@@ -101,13 +89,11 @@ ENTRY(xen_restore_fl_direct)
 	/* check for unmasked and pending */
 	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
 	jnz 1f
-2:	call check_events
+	call check_events
 1:
-ENDPATCH(xen_restore_fl_direct)
 	FRAME_END
 	ret
 	ENDPROC(xen_restore_fl_direct)
-	RELOC(xen_restore_fl_direct, 2b+1)
 
 
 /*
diff --git a/arch/x86/xen/xen-asm.h b/arch/x86/xen/xen-asm.h
deleted file mode 100644
index 465276467a47..000000000000
--- a/arch/x86/xen/xen-asm.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _XEN_XEN_ASM_H
-#define _XEN_XEN_ASM_H
-
-#include <linux/linkage.h>
-
-#define RELOC(x, v)	.globl x##_reloc; x##_reloc=v
-#define ENDPATCH(x)	.globl x##_end; x##_end=.
-
-/* Pseudo-flag used for virtual NMI, which we don't implement yet */
-#define XEN_EFLAGS_NMI	0x80000000
-
-#endif
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index feb6d40a0860..1200e262a116 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -1,14 +1,8 @@
 /*
- * Asm versions of Xen pv-ops, suitable for either direct use or
- * inlining.  The inline versions are the same as the direct-use
- * versions, with the pre- and post-amble chopped off.
- *
- * This code is encoded for size rather than absolute efficiency, with
- * a view to being able to inline as much as possible.
+ * Asm versions of Xen pv-ops, suitable for direct use.
  *
  * We only bother with direct forms (ie, vcpu in pda) of the
- * operations here; the indirect forms are better handled in C, since
- * they're generally too large to inline anyway.
+ * operations here; the indirect forms are better handled in C.
  */
 
 #include <asm/thread_info.h>
@@ -18,21 +12,10 @@
 
 #include <xen/interface/xen.h>
 
-#include "xen-asm.h"
+#include <linux/linkage.h>
 
-/*
- * Force an event check by making a hypercall, but preserve regs
- * before making the call.
- */
-check_events:
-	push %eax
-	push %ecx
-	push %edx
-	call xen_force_evtchn_callback
-	pop %edx
-	pop %ecx
-	pop %eax
-	ret
+/* Pseudo-flag used for virtual NMI, which we don't implement yet */
+#define XEN_EFLAGS_NMI  0x80000000
 
 /*
  * This is run where a normal iret would be run, with the same stack setup:
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index c3df43141e70..3a3b6a211584 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -1,14 +1,8 @@
 /*
- * Asm versions of Xen pv-ops, suitable for either direct use or
- * inlining.  The inline versions are the same as the direct-use
- * versions, with the pre- and post-amble chopped off.
- *
- * This code is encoded for size rather than absolute efficiency, with
- * a view to being able to inline as much as possible.
+ * Asm versions of Xen pv-ops, suitable for direct use.
  *
  * We only bother with direct forms (ie, vcpu in pda) of the
- * operations here; the indirect forms are better handled in C, since
- * they're generally too large to inline anyway.
+ * operations here; the indirect forms are better handled in C.
  */
 
 #include <asm/errno.h>
@@ -20,7 +14,7 @@
 
 #include <xen/interface/xen.h>
 
-#include "xen-asm.h"
+#include <linux/linkage.h>
 
 ENTRY(xen_adjust_exception_frame)
 	mov 8+0(%rsp), %rcx
@@ -46,9 +40,7 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
  */
 ENTRY(xen_iret)
 	pushq $0
-1:	jmp hypercall_iret
-ENDPATCH(xen_iret)
-RELOC(xen_iret, 1b+1)
+	jmp hypercall_iret
 
 ENTRY(xen_sysret64)
 	/*
@@ -65,9 +57,7 @@ ENTRY(xen_sysret64)
 	pushq %rcx
 
 	pushq $VGCF_in_syscall
-1:	jmp hypercall_iret
-ENDPATCH(xen_sysret64)
-RELOC(xen_sysret64, 1b+1)
+	jmp hypercall_iret
 
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
@@ -82,34 +72,47 @@ RELOC(xen_sysret64, 1b+1)
  *	rip
  *	r11
  * rsp->rcx
- *
- * In all the entrypoints, we undo all that to make it look like a
- * CPU-generated syscall/sysenter and jump to the normal entrypoint.
  */
 
-.macro undo_xen_syscall
-	mov 0*8(%rsp), %rcx
-	mov 1*8(%rsp), %r11
-	mov 5*8(%rsp), %rsp
-.endm
-
 /* Normal 64-bit system call target */
 ENTRY(xen_syscall_target)
-	undo_xen_syscall
-	jmp entry_SYSCALL_64_after_swapgs
+	popq %rcx
+	popq %r11
+
+	/*
+	 * Neither Xen nor the kernel really knows what the old SS and
+	 * CS were.  The kernel expects __USER_DS and __USER_CS, so
+	 * report those values even though Xen will guess its own values.
+	 */
+	movq $__USER_DS, 4*8(%rsp)
+	movq $__USER_CS, 1*8(%rsp)
+
+	jmp entry_SYSCALL_64_after_hwframe
 ENDPROC(xen_syscall_target)
 
 #ifdef CONFIG_IA32_EMULATION
 
 /* 32-bit compat syscall target */
 ENTRY(xen_syscall32_target)
-	undo_xen_syscall
-	jmp entry_SYSCALL_compat
+	popq %rcx
+	popq %r11
+
+	/*
+	 * Neither Xen nor the kernel really knows what the old SS and
+	 * CS were.  The kernel expects __USER32_DS and __USER32_CS, so
+	 * report those values even though Xen will guess its own values.
+	 */
+	movq $__USER32_DS, 4*8(%rsp)
+	movq $__USER32_CS, 1*8(%rsp)
+
+	jmp entry_SYSCALL_compat_after_hwframe
 ENDPROC(xen_syscall32_target)
 
 /* 32-bit compat sysenter target */
 ENTRY(xen_sysenter_target)
-	undo_xen_syscall
+	mov 0*8(%rsp), %rcx
+	mov 1*8(%rsp), %r11
+	mov 5*8(%rsp), %rsp
 	jmp entry_SYSENTER_compat
 ENDPROC(xen_sysenter_target)
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 0d5004477db6..70301ac0d414 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -129,17 +129,10 @@ static inline void __init xen_efi_init(void)
 }
 #endif
 
-/* Declare an asm function, along with symbols needed to make it
-   inlineable */
-#define DECL_ASM(ret, name, ...)		\
-	__visible ret name(__VA_ARGS__);	\
-	extern char name##_end[] __visible;	\
-	extern char name##_reloc[] __visible
-
-DECL_ASM(void, xen_irq_enable_direct, void);
-DECL_ASM(void, xen_irq_disable_direct, void);
-DECL_ASM(unsigned long, xen_save_fl_direct, void);
-DECL_ASM(void, xen_restore_fl_direct, unsigned long);
+__visible void xen_irq_enable_direct(void);
+__visible void xen_irq_disable_direct(void);
+__visible unsigned long xen_save_fl_direct(void);
+__visible void xen_restore_fl_direct(unsigned long);
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);