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

Pull x86 fixes from Ingo Molnar:
 "Two families of fixes:

   - Fix an FPU context related boot crash on newer x86 hardware with
     larger context sizes than what most people test.  To fix this
     without ugly kludges or extensive reverts we had to touch core task
     allocator, to allow x86 to determine the task size dynamically, at
     boot time.

     I've tested it on a number of x86 platforms, and I cross-built it
     to a handful of architectures:

                                        (warns)               (warns)
       testing     x86-64:  -git:  pass (    0),  -tip:  pass (    0)
       testing     x86-32:  -git:  pass (    0),  -tip:  pass (    0)
       testing        arm:  -git:  pass ( 1359),  -tip:  pass ( 1359)
       testing       cris:  -git:  pass ( 1031),  -tip:  pass ( 1031)
       testing       m32r:  -git:  pass ( 1135),  -tip:  pass ( 1135)
       testing       m68k:  -git:  pass ( 1471),  -tip:  pass ( 1471)
       testing       mips:  -git:  pass ( 1162),  -tip:  pass ( 1162)
       testing    mn10300:  -git:  pass ( 1058),  -tip:  pass ( 1058)
       testing     parisc:  -git:  pass ( 1846),  -tip:  pass ( 1846)
       testing      sparc:  -git:  pass ( 1185),  -tip:  pass ( 1185)

     ... so I hope the cross-arch impact 'none', as intended.

     (by Dave Hansen)

   - Fix various NMI handling related bugs unearthed by the big asm code
     rewrite and generally make the NMI code more robust and more
     maintainable while at it.  These changes are a bit late in the
     cycle, I hope they are still acceptable.

     (by Andy Lutomirski)"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu, sched: Introduce CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and use it on x86
  x86/fpu, sched: Dynamically allocate 'struct fpu'
  x86/entry/64, x86/nmi/64: Add CONFIG_DEBUG_ENTRY NMI testing code
  x86/nmi/64: Make the "NMI executing" variable more consistent
  x86/nmi/64: Minor asm simplification
  x86/nmi/64: Use DF to avoid userspace RSP confusing nested NMI detection
  x86/nmi/64: Reorder nested NMI checks
  x86/nmi/64: Improve nested NMI comments
  x86/nmi/64: Switch stacks on userspace NMI entry
  x86/nmi/64: Remove asm code that saves CR2
  x86/nmi: Enable nested do_nmi() handling for 64-bit kernels

1 files changed, 40 insertions, 0 deletions

diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 32826791e675..0b39173dd971 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -4,6 +4,8 @@
 #include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 
+#include <linux/sched.h>
+
 /*
  * Initialize the TS bit in CR0 according to the style of context-switches
  * we are using:
@@ -136,6 +138,43 @@ static void __init fpu__init_system_generic(void)
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
 
+/* Enforce that 'MEMBER' is the last field of 'TYPE': */
+#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \
+	BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER))
+
+/*
+ * We append the 'struct fpu' to the task_struct:
+ */
+static void __init fpu__init_task_struct_size(void)
+{
+	int task_size = sizeof(struct task_struct);
+
+	/*
+	 * Subtract off the static size of the register state.
+	 * It potentially has a bunch of padding.
+	 */
+	task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state);
+
+	/*
+	 * Add back the dynamically-calculated register state
+	 * size.
+	 */
+	task_size += xstate_size;
+
+	/*
+	 * We dynamically size 'struct fpu', so we require that
+	 * it be at the end of 'thread_struct' and that
+	 * 'thread_struct' be at the end of 'task_struct'.  If
+	 * you hit a compile error here, check the structure to
+	 * see if something got added to the end.
+	 */
+	CHECK_MEMBER_AT_END_OF(struct fpu, state);
+	CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
+	CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
+
+	arch_task_struct_size = task_size;
+}
+
 /*
  * Set up the xstate_size based on the legacy FPU context size.
  *
@@ -287,6 +326,7 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
 	fpu__init_system_generic();
 	fpu__init_system_xstate_size_legacy();
 	fpu__init_system_xstate();
+	fpu__init_task_struct_size();
 
 	fpu__init_system_ctx_switch();
 }