Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Martin Schwidefsky:
 "There is only one new feature in this pull for the 4.4 merge window,
  most of it is small enhancements, cleanup and bug fixes:

   - Add the s390 backend for the software dirty bit tracking.  This
     adds two new pgtable functions pte_clear_soft_dirty and
     pmd_clear_soft_dirty which is why there is a hit to
     arch/x86/include/asm/pgtable.h in this pull request.

   - A series of cleanup patches for the AP bus, this includes the
     removal of the support for two outdated crypto cards (PCICC and
     PCICA).

   - The irq handling / signaling on buffer full in the runtime
     instrumentation code is dropped.

   - Some micro optimizations: remove unnecessary memory barriers for a
     couple of functions: [smb_]rmb, [smb_]wmb, atomics, bitops, and for
     spin_unlock.  Use the builtin bswap if available and make
     test_and_set_bit_lock more cache friendly.

   - Statistics and a tracepoint for the diagnose calls to the
     hypervisor.

   - The CPU measurement facility support to sample KVM guests is
     improved.

   - The vector instructions are now always enabled for user space
     processes if the hardware has the vector facility.  This simplifies
     the FPU handling code.  The fpu-internal.h header is split into fpu
     internals, api and types just like x86.

   - Cleanup and improvements for the common I/O layer.

   - Rework udelay to solve a problem with kprobe.  udelay has busy loop
     semantics but still uses an idle processor state for the wait"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (66 commits)
  s390: remove runtime instrumentation interrupts
  s390/cio: de-duplicate subchannel validation
  s390/css: unneeded initialization in for_each_subchannel
  s390/Kconfig: use builtin bswap
  s390/dasd: fix disconnected device with valid path mask
  s390/dasd: fix invalid PAV assignment after suspend/resume
  s390/dasd: fix double free in dasd_eckd_read_conf
  s390/kernel: fix ptrace peek/poke for floating point registers
  s390/cio: move ccw_device_stlck functions
  s390/cio: move ccw_device_call_handler
  s390/topology: reduce per_cpu() invocations
  s390/nmi: reduce size of percpu variable
  s390/nmi: fix terminology
  s390/nmi: remove casts
  s390/nmi: remove pointless error strings
  s390: don't store registers on disabled wait anymore
  s390: get rid of __set_psw_mask()
  s390/fpu: split fpu-internal.h into fpu internals, api, and type headers
  s390/dasd: fix list_del corruption after lcu changes
  s390/spinlock: remove unneeded serializations at unlock
  ...

1 files changed, 3 insertions, 27 deletions

diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h
index 411464f4c97a..24ea6948e32b 100644
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -32,7 +32,7 @@
 	__old;								\
 })
 
-#define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn)		\
+#define __cmpxchg_double(p1, p2, o1, o2, n1, n2)			\
 ({									\
 	register __typeof__(*(p1)) __old1 asm("2") = (o1);		\
 	register __typeof__(*(p2)) __old2 asm("3") = (o2);		\
@@ -40,7 +40,7 @@
 	register __typeof__(*(p2)) __new2 asm("5") = (n2);		\
 	int cc;								\
 	asm volatile(							\
-			insn   " %[old],%[new],%[ptr]\n"		\
+		"	cdsg	%[old],%[new],%[ptr]\n"			\
 		"	ipm	%[cc]\n"				\
 		"	srl	%[cc],28"				\
 		: [cc] "=d" (cc), [old] "+d" (__old1), "+d" (__old2)	\
@@ -50,30 +50,6 @@
 	!cc;								\
 })
 
-#define __cmpxchg_double_4(p1, p2, o1, o2, n1, n2) \
-	__cmpxchg_double_op(p1, p2, o1, o2, n1, n2, "cds")
-
-#define __cmpxchg_double_8(p1, p2, o1, o2, n1, n2) \
-	__cmpxchg_double_op(p1, p2, o1, o2, n1, n2, "cdsg")
-
-extern void __cmpxchg_double_called_with_bad_pointer(void);
-
-#define __cmpxchg_double(p1, p2, o1, o2, n1, n2)			\
-({									\
-	int __ret;							\
-	switch (sizeof(*(p1))) {					\
-	case 4:								\
-		__ret = __cmpxchg_double_4(p1, p2, o1, o2, n1, n2);	\
-		break;							\
-	case 8:								\
-		__ret = __cmpxchg_double_8(p1, p2, o1, o2, n1, n2);	\
-		break;							\
-	default:							\
-		__cmpxchg_double_called_with_bad_pointer();		\
-	}								\
-	__ret;								\
-})
-
 #define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
 ({									\
 	__typeof__(p1) __p1 = (p1);					\
@@ -81,7 +57,7 @@ extern void __cmpxchg_double_called_with_bad_pointer(void);
 	BUILD_BUG_ON(sizeof(*(p1)) != sizeof(long));			\
 	BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long));			\
 	VM_BUG_ON((unsigned long)((__p1) + 1) != (unsigned long)(__p2));\
-	__cmpxchg_double_8(__p1, __p2, o1, o2, n1, n2);			\
+	__cmpxchg_double(__p1, __p2, o1, o2, n1, n2);			\
 })
 
 #define system_has_cmpxchg_double()	1