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     removal of the support for two outdated crypto cards (PCICC and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, 16 deletions

diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index 246a7eb4b680..501dcd4ca4a0 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -12,8 +12,10 @@
 #include <linux/module.h>
 #include <linux/irqflags.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/vtimer.h>
 #include <asm/div64.h>
+#include <asm/idle.h>
 
 void __delay(unsigned long loops)
 {
@@ -30,26 +32,22 @@ EXPORT_SYMBOL(__delay);
 
 static void __udelay_disabled(unsigned long long usecs)
 {
-	unsigned long cr0, cr6, new;
-	u64 clock_saved, end;
+	unsigned long cr0, cr0_new, psw_mask;
+	struct s390_idle_data idle;
+	u64 end;
 
 	end = get_tod_clock() + (usecs << 12);
-	clock_saved = local_tick_disable();
 	__ctl_store(cr0, 0, 0);
-	__ctl_store(cr6, 6, 6);
-	new = (cr0 &  0xffff00e0) | 0x00000800;
-	__ctl_load(new , 0, 0);
-	new = 0;
-	__ctl_load(new, 6, 6);
-	lockdep_off();
-	do {
-		set_clock_comparator(end);
-		enabled_wait();
-	} while (get_tod_clock_fast() < end);
-	lockdep_on();
+	cr0_new = cr0 & ~CR0_IRQ_SUBCLASS_MASK;
+	cr0_new |= (1UL << (63 - 52)); /* enable clock comparator irq */
+	__ctl_load(cr0_new, 0, 0);
+	psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT;
+	set_clock_comparator(end);
+	set_cpu_flag(CIF_IGNORE_IRQ);
+	psw_idle(&idle, psw_mask);
+	clear_cpu_flag(CIF_IGNORE_IRQ);
+	set_clock_comparator(S390_lowcore.clock_comparator);
 	__ctl_load(cr0, 0, 0);
-	__ctl_load(cr6, 6, 6);
-	local_tick_enable(clock_saved);
 }
 
 static void __udelay_enabled(unsigned long long usecs)