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, 27 insertions, 129 deletions

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index bdb80c4aef6e..310f51d42550 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -201,17 +201,6 @@
 #endif
 #endif
 
-#ifdef CONFIG_STACK_VALIDATION
-#define annotate_unreachable() ({					\
-	asm("%c0:\t\n"							\
-	    ".pushsection .discard.unreachable\t\n"			\
-	    ".long %c0b - .\t\n"					\
-	    ".popsection\t\n" : : "i" (__LINE__));			\
-})
-#else
-#define annotate_unreachable()
-#endif
-
 /*
  * Mark a position in code as unreachable.  This can be used to
  * suppress control flow warnings after asm blocks that transfer
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 043b60de041e..e786337cf5a7 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -185,8 +185,34 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #endif
 
 /* Unreachable code */
+#ifdef CONFIG_STACK_VALIDATION
+#define annotate_reachable() ({						\
+	asm("%c0:\n\t"							\
+	    ".pushsection .discard.reachable\n\t"			\
+	    ".long %c0b - .\n\t"					\
+	    ".popsection\n\t" : : "i" (__LINE__));			\
+})
+#define annotate_unreachable() ({					\
+	asm("%c0:\n\t"							\
+	    ".pushsection .discard.unreachable\n\t"			\
+	    ".long %c0b - .\n\t"					\
+	    ".popsection\n\t" : : "i" (__LINE__));			\
+})
+#define ASM_UNREACHABLE							\
+	"999:\n\t"							\
+	".pushsection .discard.unreachable\n\t"				\
+	".long 999b - .\n\t"						\
+	".popsection\n\t"
+#else
+#define annotate_reachable()
+#define annotate_unreachable()
+#endif
+
+#ifndef ASM_UNREACHABLE
+# define ASM_UNREACHABLE
+#endif
 #ifndef unreachable
-# define unreachable() do { } while (1)
+# define unreachable() do { annotate_reachable(); do { } while (1); } while (0)
 #endif
 
 /*
diff --git a/include/linux/lguest.h b/include/linux/lguest.h
deleted file mode 100644
index 6db19f35f7c5..000000000000
--- a/include/linux/lguest.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * Things the lguest guest needs to know.  Note: like all lguest interfaces,
- * this is subject to wild and random change between versions.
- */
-#ifndef _LINUX_LGUEST_H
-#define _LINUX_LGUEST_H
-
-#ifndef __ASSEMBLY__
-#include <linux/time.h>
-#include <asm/irq.h>
-#include <asm/lguest_hcall.h>
-
-#define LG_CLOCK_MIN_DELTA	100UL
-#define LG_CLOCK_MAX_DELTA	ULONG_MAX
-
-/*G:031
- * The second method of communicating with the Host is to via "struct
- * lguest_data".  Once the Guest's initialization hypercall tells the Host where
- * this is, the Guest and Host both publish information in it.
-:*/
-struct lguest_data {
-	/*
-	 * 512 == enabled (same as eflags in normal hardware).  The Guest
-	 * changes interrupts so often that a hypercall is too slow.
-	 */
-	unsigned int irq_enabled;
-	/* Fine-grained interrupt disabling by the Guest */
-	DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS);
-
-	/*
-	 * The Host writes the virtual address of the last page fault here,
-	 * which saves the Guest a hypercall.  CR2 is the native register where
-	 * this address would normally be found.
-	 */
-	unsigned long cr2;
-
-	/* Wallclock time set by the Host. */
-	struct timespec time;
-
-	/*
-	 * Interrupt pending set by the Host.  The Guest should do a hypercall
-	 * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF).
-	 */
-	int irq_pending;
-
-	/*
-	 * Async hypercall ring.  Instead of directly making hypercalls, we can
-	 * place them in here for processing the next time the Host wants.
-	 * This batching can be quite efficient.
-	 */
-
-	/* 0xFF == done (set by Host), 0 == pending (set by Guest). */
-	u8 hcall_status[LHCALL_RING_SIZE];
-	/* The actual registers for the hypercalls. */
-	struct hcall_args hcalls[LHCALL_RING_SIZE];
-
-/* Fields initialized by the Host at boot: */
-	/* Memory not to try to access */
-	unsigned long reserve_mem;
-	/* KHz for the TSC clock. */
-	u32 tsc_khz;
-
-/* Fields initialized by the Guest at boot: */
-	/* Instruction to suppress interrupts even if enabled */
-	unsigned long noirq_iret;
-	/* Address above which page tables are all identical. */
-	unsigned long kernel_address;
-	/* The vector to try to use for system calls (0x40 or 0x80). */
-	unsigned int syscall_vec;
-};
-extern struct lguest_data lguest_data;
-#endif /* __ASSEMBLY__ */
-#endif	/* _LINUX_LGUEST_H */
diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h
deleted file mode 100644
index acd5b12565cc..000000000000
--- a/include/linux/lguest_launcher.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef _LINUX_LGUEST_LAUNCHER
-#define _LINUX_LGUEST_LAUNCHER
-/* Everything the "lguest" userspace program needs to know. */
-#include <linux/types.h>
-
-/*D:010
- * Drivers
- *
- * The Guest needs devices to do anything useful.  Since we don't let it touch
- * real devices (think of the damage it could do!) we provide virtual devices.
- * We emulate a PCI bus with virtio devices on it; we used to have our own
- * lguest bus which was far simpler, but this tests the virtio 1.0 standard.
- *
- * Virtio devices are also used by kvm, so we can simply reuse their optimized
- * device drivers.  And one day when everyone uses virtio, my plan will be
- * complete.  Bwahahahah!
- */
-
-/* Write command first word is a request. */
-enum lguest_req
-{
-	LHREQ_INITIALIZE, /* + base, pfnlimit, start */
-	LHREQ_GETDMA, /* No longer used */
-	LHREQ_IRQ, /* + irq */
-	LHREQ_BREAK, /* No longer used */
-	LHREQ_EVENTFD, /* No longer used. */
-	LHREQ_GETREG, /* + offset within struct pt_regs (then read value). */
-	LHREQ_SETREG, /* + offset within struct pt_regs, value. */
-	LHREQ_TRAP, /* + trap number to deliver to guest. */
-};
-
-/*
- * This is what read() of the lguest fd populates.  trap ==
- * LGUEST_TRAP_ENTRY for an LHCALL_NOTIFY (addr is the
- * argument), 14 for a page fault in the MMIO region (addr is
- * the trap address, insn is the instruction), or 13 for a GPF
- * (insn is the instruction).
- */
-struct lguest_pending {
-	__u8 trap;
-	__u8 insn[7];
-	__u32 addr;
-};
-#endif /* _LINUX_LGUEST_LAUNCHER */