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     removal of the support for two outdated crypto cards (PCICC and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, 19 insertions, 18 deletions

diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index f2dac9f0799d..688a3aad9c79 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -23,6 +23,7 @@
 #include <linux/kprobes.h>
 #include <linux/random.h>
 #include <linux/module.h>
+#include <linux/init_task.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/vtimer.h>
@@ -36,6 +37,9 @@
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
 
+/* FPU save area for the init task */
+__vector128 init_task_fpu_regs[__NUM_VXRS] __init_task_data;
+
 /*
  * Return saved PC of a blocked thread. used in kernel/sched.
  * resume in entry.S does not create a new stack frame, it
@@ -87,31 +91,29 @@ void arch_release_task_struct(struct task_struct *tsk)
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
+	size_t fpu_regs_size;
+
 	*dst = *src;
 
-	/* Set up a new floating-point register save area */
-	dst->thread.fpu.fpc = 0;
-	dst->thread.fpu.flags = 0;	/* Always start with VX disabled */
-	dst->thread.fpu.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
-				       GFP_KERNEL|__GFP_REPEAT);
-	if (!dst->thread.fpu.fprs)
+	/*
+	 * If the vector extension is available, it is enabled for all tasks,
+	 * and, thus, the FPU register save area must be allocated accordingly.
+	 */
+	fpu_regs_size = MACHINE_HAS_VX ? sizeof(__vector128) * __NUM_VXRS
+				       : sizeof(freg_t) * __NUM_FPRS;
+	dst->thread.fpu.regs = kzalloc(fpu_regs_size, GFP_KERNEL|__GFP_REPEAT);
+	if (!dst->thread.fpu.regs)
 		return -ENOMEM;
 
 	/*
 	 * Save the floating-point or vector register state of the current
-	 * task.  The state is not saved for early kernel threads, for example,
-	 * the init_task, which do not have an allocated save area.
-	 * The CIF_FPU flag is set in any case to lazy clear or restore a saved
-	 * state when switching to a different task or returning to user space.
+	 * task and set the CIF_FPU flag to lazy restore the FPU register
+	 * state when returning to user space.
 	 */
 	save_fpu_regs();
 	dst->thread.fpu.fpc = current->thread.fpu.fpc;
-	if (is_vx_task(current))
-		convert_vx_to_fp(dst->thread.fpu.fprs,
-				 current->thread.fpu.vxrs);
-	else
-		memcpy(dst->thread.fpu.fprs, current->thread.fpu.fprs,
-		       sizeof(freg_t) * __NUM_FPRS);
+	memcpy(dst->thread.fpu.regs, current->thread.fpu.regs, fpu_regs_size);
+
 	return 0;
 }
 
@@ -169,7 +171,6 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 
 	/* Don't copy runtime instrumentation info */
 	p->thread.ri_cb = NULL;
-	p->thread.ri_signum = 0;
 	frame->childregs.psw.mask &= ~PSW_MASK_RI;
 
 	/* Set a new TLS ?  */
@@ -199,7 +200,7 @@ int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
 	save_fpu_regs();
 	fpregs->fpc = current->thread.fpu.fpc;
 	fpregs->pad = 0;
-	if (is_vx_task(current))
+	if (MACHINE_HAS_VX)
 		convert_vx_to_fp((freg_t *)&fpregs->fprs,
 				 current->thread.fpu.vxrs);
 	else