s390/fpu: allocate 'struct fpu' with the task_struct

Analog to git commit 0c8c0f03e3a292e031596484275c14cf39c0ab7a
"x86/fpu, sched: Dynamically allocate 'struct fpu'"
move the struct fpu to the end of the struct thread_struct,
set CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and add the
setup_task_size() function to calculate the correct size
fo the task struct.

For the performance_defconfig this increases the size of
struct task_struct from 7424 bytes to 7936 bytes (MACHINE_HAS_VX==1)
or 7552 bytes (MACHINE_HAS_VX==0). The dynamic allocation of the
struct fpu is removed. The slab cache uses an 8KB block for the
task struct in all cases, there is enough room for the struct fpu.
For MACHINE_HAS_VX==1 each task now needs 512 bytes less memory.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

1 files changed, 6 insertions, 3 deletions

diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index d6fd22ea270d..332f4f7dc8d3 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -105,7 +105,6 @@ typedef struct {
  * Thread structure
  */
 struct thread_struct {
-	struct fpu fpu;			/* FP and VX register save area */
 	unsigned int  acrs[NUM_ACRS];
         unsigned long ksp;              /* kernel stack pointer             */
 	mm_segment_t mm_segment;
@@ -120,6 +119,11 @@ struct thread_struct {
 	/* cpu runtime instrumentation */
 	struct runtime_instr_cb *ri_cb;
 	unsigned char trap_tdb[256];	/* Transaction abort diagnose block */
+	/*
+	 * Warning: 'fpu' is dynamically-sized. It *MUST* be at
+	 * the end.
+	 */
+	struct fpu fpu;			/* FP and VX register save area */
 };
 
 /* Flag to disable transactions. */
@@ -155,10 +159,9 @@ struct stack_frame {
 
 #define ARCH_MIN_TASKALIGN	8
 
-extern __vector128 init_task_fpu_regs[__NUM_VXRS];
 #define INIT_THREAD {							\
 	.ksp = sizeof(init_stack) + (unsigned long) &init_stack,	\
-	.fpu.regs = (void *)&init_task_fpu_regs,			\
+	.fpu.regs = (void *) init_task.thread.fpu.fprs,			\
 }
 
 /*