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     removal of the support for two outdated crypto cards (PCICC and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, 16 insertions, 12 deletions

diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index bf05e7fc3e70..40b8102fdadb 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -84,6 +84,7 @@ static struct mask_info *add_cpus_to_mask(struct topology_core *tl_core,
 					  struct mask_info *socket,
 					  int one_socket_per_cpu)
 {
+	struct cpu_topology_s390 *topo;
 	unsigned int core;
 
 	for_each_set_bit(core, &tl_core->mask[0], TOPOLOGY_CORE_BITS) {
@@ -95,15 +96,16 @@ static struct mask_info *add_cpus_to_mask(struct topology_core *tl_core,
 		if (lcpu < 0)
 			continue;
 		for (i = 0; i <= smp_cpu_mtid; i++) {
-			per_cpu(cpu_topology, lcpu + i).book_id = book->id;
-			per_cpu(cpu_topology, lcpu + i).core_id = rcore;
-			per_cpu(cpu_topology, lcpu + i).thread_id = lcpu + i;
+			topo = &per_cpu(cpu_topology, lcpu + i);
+			topo->book_id = book->id;
+			topo->core_id = rcore;
+			topo->thread_id = lcpu + i;
 			cpumask_set_cpu(lcpu + i, &book->mask);
 			cpumask_set_cpu(lcpu + i, &socket->mask);
 			if (one_socket_per_cpu)
-				per_cpu(cpu_topology, lcpu + i).socket_id = rcore;
+				topo->socket_id = rcore;
 			else
-				per_cpu(cpu_topology, lcpu + i).socket_id = socket->id;
+				topo->socket_id = socket->id;
 			smp_cpu_set_polarization(lcpu + i, tl_core->pp);
 		}
 		if (one_socket_per_cpu)
@@ -247,17 +249,19 @@ int topology_set_cpu_management(int fc)
 
 static void update_cpu_masks(void)
 {
+	struct cpu_topology_s390 *topo;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		per_cpu(cpu_topology, cpu).thread_mask = cpu_thread_map(cpu);
-		per_cpu(cpu_topology, cpu).core_mask = cpu_group_map(&socket_info, cpu);
-		per_cpu(cpu_topology, cpu).book_mask = cpu_group_map(&book_info, cpu);
+		topo = &per_cpu(cpu_topology, cpu);
+		topo->thread_mask = cpu_thread_map(cpu);
+		topo->core_mask = cpu_group_map(&socket_info, cpu);
+		topo->book_mask = cpu_group_map(&book_info, cpu);
 		if (!MACHINE_HAS_TOPOLOGY) {
-			per_cpu(cpu_topology, cpu).thread_id = cpu;
-			per_cpu(cpu_topology, cpu).core_id = cpu;
-			per_cpu(cpu_topology, cpu).socket_id = cpu;
-			per_cpu(cpu_topology, cpu).book_id = cpu;
+			topo->thread_id = cpu;
+			topo->core_id = cpu;
+			topo->socket_id = cpu;
+			topo->book_id = cpu;
 		}
 	}
 	numa_update_cpu_topology();