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     removal of the support for two outdated crypto cards (PCICC and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, 14 insertions, 1 deletions

diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 549a73a4b543..3c31609df959 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -17,6 +17,7 @@
 #include <linux/pfn.h>
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
+#include <asm/diag.h>
 #include <asm/ebcdic.h>
 #include <asm/ipl.h>
 #include <asm/lowcore.h>
@@ -286,6 +287,7 @@ static __init void detect_diag9c(void)
 	int rc;
 
 	cpu_address = stap();
+	diag_stat_inc(DIAG_STAT_X09C);
 	asm volatile(
 		"	diag	%2,0,0x9c\n"
 		"0:	la	%0,0\n"
@@ -300,6 +302,7 @@ static __init void detect_diag44(void)
 {
 	int rc;
 
+	diag_stat_inc(DIAG_STAT_X044);
 	asm volatile(
 		"	diag	0,0,0x44\n"
 		"0:	la	%0,0\n"
@@ -326,9 +329,19 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TE;
 	if (test_facility(51))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
-	if (test_facility(129))
+	if (test_facility(129)) {
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
+		__ctl_set_bit(0, 17);
+	}
+}
+
+static int __init disable_vector_extension(char *str)
+{
+	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
+	__ctl_clear_bit(0, 17);
+	return 1;
 }
+early_param("novx", disable_vector_extension);
 
 static int __init cad_setup(char *str)
 {