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     removal of the support for two outdated crypto cards (PCICC and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, 34 insertions, 21 deletions

diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 9b68e98a724f..8043f10da6b5 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -11,30 +11,25 @@
  * big-endian system because, unlike little endian, the number of each
  * bit depends on the word size.
  *
- * The bitop functions are defined to work on unsigned longs, so for an
- * s390x system the bits end up numbered:
+ * The bitop functions are defined to work on unsigned longs, so the bits
+ * end up numbered:
  *   |63..............0|127............64|191...........128|255...........192|
- * and on s390:
- *   |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
  *
  * There are a few little-endian macros used mostly for filesystem
- * bitmaps, these work on similar bit arrays layouts, but
- * byte-oriented:
+ * bitmaps, these work on similar bit array layouts, but byte-oriented:
  *   |7...0|15...8|23...16|31...24|39...32|47...40|55...48|63...56|
  *
- * The main difference is that bit 3-5 (64b) or 3-4 (32b) in the bit
- * number field needs to be reversed compared to the big-endian bit
- * fields. This can be achieved by XOR with 0x38 (64b) or 0x18 (32b).
+ * The main difference is that bit 3-5 in the bit number field needs to be
+ * reversed compared to the big-endian bit fields. This can be achieved by
+ * XOR with 0x38.
  *
- * We also have special functions which work with an MSB0 encoding:
- * on an s390x system the bits are numbered:
+ * We also have special functions which work with an MSB0 encoding.
+ * The bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
- * and on s390:
- *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  *
- * The main difference is that bit 0-63 (64b) or 0-31 (32b) in the bit
- * number field needs to be reversed compared to the LSB0 encoded bit
- * fields. This can be achieved by XOR with 0x3f (64b) or 0x1f (32b).
+ * The main difference is that bit 0-63 in the bit number field needs to be
+ * reversed compared to the LSB0 encoded bit fields. This can be achieved by
+ * XOR with 0x3f.
  *
  */
 
@@ -64,7 +59,6 @@
 								\
 	typecheck(unsigned long *, (__addr));			\
 	asm volatile(						\
-		__barrier					\
 		__op_string "	%0,%2,%1\n"			\
 		__barrier					\
 		: "=d" (__old),	"+Q" (*(__addr))		\
@@ -276,12 +270,32 @@ static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr)
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static inline int test_and_set_bit_lock(unsigned long nr,
+					volatile unsigned long *ptr)
+{
+	if (test_bit(nr, ptr))
+		return 1;
+	return test_and_set_bit(nr, ptr);
+}
+
+static inline void clear_bit_unlock(unsigned long nr,
+				    volatile unsigned long *ptr)
+{
+	smp_mb__before_atomic();
+	clear_bit(nr, ptr);
+}
+
+static inline void __clear_bit_unlock(unsigned long nr,
+				      volatile unsigned long *ptr)
+{
+	smp_mb();
+	__clear_bit(nr, ptr);
+}
+
 /*
  * Functions which use MSB0 bit numbering.
- * On an s390x system the bits are numbered:
+ * The bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
- * and on s390:
- *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  */
 unsigned long find_first_bit_inv(const unsigned long *addr, unsigned long size);
 unsigned long find_next_bit_inv(const unsigned long *addr, unsigned long size,
@@ -446,7 +460,6 @@ static inline int fls(int word)
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic-setbit.h>